[PATCH v2] f2fs: quiesce background threads during system suspend using PM notifier

[Daeho Jeong <daeho43@gmail.com>]

From: Daeho Jeong <daehojeong@google.com>

During system suspend, a race condition can cause f2fs_gc and f2fs_discard
threads to call submit_bio() while the underlying block device (e.g., UFS)
is in Runtime PM suspend. Because Runtime PM worker threads are already
frozen during task freezing, the threads become trapped in
__bio_queue_enter() waiting on mq_freeze_wq, leading to a PM freezer
timeout.

To prevent this deadlock, register a PM notifier to set SBI_IS_SUSPENDING
during PM_SUSPEND_PREPARE. Background GC and discard threads check this
flag and immediately stop issuing new bios, allowing them to enter a
freezable sleep state cleanly before process freezing begins.

In addition, check freezing() as a fast path to stop issuing new I/O
when non-PM freezing (e.g. dm-snapshot or cgroup freezer) is requested.

Signed-off-by: Daeho Jeong <daehojeong@google.com>
---
v2: check freezing() together for non-PM freezing.
---
 fs/f2fs/f2fs.h    |  9 +++++++++
 fs/f2fs/gc.c      | 13 ++++++++-----
 fs/f2fs/segment.c | 12 ++++++++----
 fs/f2fs/super.c   | 25 +++++++++++++++++++++++++
 4 files changed, 50 insertions(+), 9 deletions(-)

diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index f1774d4e18d2..2a7b0fe8419b 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -25,6 +25,7 @@
 #include <linux/quotaops.h>
 #include <linux/part_stat.h>
 #include <linux/rw_hint.h>
+#include <linux/suspend.h>
 
 #include <linux/fscrypt.h>
 #include <linux/fsverity.h>
@@ -1492,6 +1493,7 @@ enum {
 	SBI_IS_FREEZING,			/* freezefs is in process */
 	SBI_IS_WRITABLE,			/* remove ro mountoption transiently */
 	SBI_ENABLE_CHECKPOINT,			/* indicate it's during f2fs_enable_checkpoint() */
+	SBI_IS_SUSPENDING,			/* system suspend is in progress */
 	MAX_SBI_FLAG,
 };
 
@@ -1755,6 +1757,7 @@ struct f2fs_sb_info {
 	struct f2fs_rwsem sb_lock;		/* lock for raw super block */
 	int valid_super_block;			/* valid super block no */
 	unsigned long s_flag;				/* flags for sbi */
+	struct notifier_block pm_nb;		/* for PM notifier */
 	struct mutex writepages;		/* mutex for writepages() */
 
 #ifdef CONFIG_BLK_DEV_ZONED
@@ -2309,6 +2312,12 @@ static inline void clear_sbi_flag(struct f2fs_sb_info *sbi, unsigned int type)
 	clear_bit(type, &sbi->s_flag);
 }
 
+static inline bool f2fs_is_suspending(struct f2fs_sb_info *sbi)
+{
+	return is_sbi_flag_set(sbi, SBI_IS_SUSPENDING) ||
+				unlikely(freezing(current));
+}
+
 static inline unsigned long long cur_cp_version(struct f2fs_checkpoint *cp)
 {
 	return le64_to_cpu(cp->checkpoint_ver);
diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c
index ffaa7ba76a1b..6c7ea38eb70d 100644
--- a/fs/f2fs/gc.c
+++ b/fs/f2fs/gc.c
@@ -71,7 +71,8 @@ static int gc_thread_func(void *data)
 		if (kthread_should_stop())
 			break;
 
-		if (sbi->sb->s_writers.frozen >= SB_FREEZE_WRITE) {
+		if (sbi->sb->s_writers.frozen >= SB_FREEZE_WRITE ||
+			f2fs_is_suspending(sbi)) {
 			increase_sleep_time(gc_th, &wait_ms);
 			stat_other_skip_bggc_count(sbi);
 			continue;
@@ -1064,8 +1065,9 @@ static int gc_node_segment(struct f2fs_sb_info *sbi,
 		struct node_info ni;
 		int err;
 
-		/* stop BG_GC if there is not enough free sections. */
-		if (gc_type == BG_GC && has_not_enough_free_secs(sbi, 0, 0))
+		/* stop BG_GC if there is not enough free sections or suspending/freezing. */
+		if (gc_type == BG_GC && (has_not_enough_free_secs(sbi, 0, 0) ||
+					f2fs_is_suspending(sbi)))
 			return submitted;
 
 		if (check_valid_map(sbi, segno, off) == 0)
@@ -1611,7 +1613,8 @@ static int gc_data_segment(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
 		 * Or, stop GC if the segment becomes fully valid caused by
 		 * race condition along with SSR block allocation.
 		 */
-		if ((gc_type == BG_GC && has_not_enough_free_secs(sbi, 0, 0)) ||
+		if ((gc_type == BG_GC && (has_not_enough_free_secs(sbi, 0, 0) ||
+					f2fs_is_suspending(sbi))) ||
 			(!force_migrate && get_valid_blocks(sbi, segno, true) ==
 							CAP_BLKS_PER_SEC(sbi)))
 			return submitted;
@@ -2015,7 +2018,7 @@ int f2fs_gc(struct f2fs_sb_info *sbi, struct f2fs_gc_control *gc_control)
 		goto stop;
 	}
 retry:
-	if (unlikely(freezing(current))) {
+	if (f2fs_is_suspending(sbi)) {
 		ret = 0;
 		goto stop;
 	}
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index d71ddb3ee918..7b03b3d06161 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -1300,7 +1300,7 @@ static int __submit_discard_cmd(struct f2fs_sb_info *sbi,
 	if (dc->state != D_PREP)
 		return 0;
 
-	if (is_sbi_flag_set(sbi, SBI_NEED_FSCK))
+	if (is_sbi_flag_set(sbi, SBI_NEED_FSCK) || f2fs_is_suspending(sbi))
 		return 0;
 
 #ifdef CONFIG_BLK_DEV_ZONED
@@ -1341,6 +1341,9 @@ static int __submit_discard_cmd(struct f2fs_sb_info *sbi,
 		unsigned long flags;
 		bool last = true;
 
+		if (f2fs_is_suspending(sbi))
+			break;
+
 		if (len > max_discard_blocks) {
 			len = max_discard_blocks;
 			last = false;
@@ -1615,7 +1618,7 @@ static void __issue_discard_cmd_orderly(struct f2fs_sb_info *sbi,
 		if (dc->state != D_PREP)
 			goto next;
 
-		if (*issued > 0 && unlikely(freezing(current)))
+		if (f2fs_is_suspending(sbi))
 			break;
 
 		if (dpolicy->io_aware && !is_idle(sbi, DISCARD_TIME)) {
@@ -1688,7 +1691,7 @@ static int __issue_discard_cmd(struct f2fs_sb_info *sbi,
 		list_for_each_entry_safe(dc, tmp, pend_list, list) {
 			f2fs_bug_on(sbi, dc->state != D_PREP);
 
-			if (issued > 0 && unlikely(freezing(current))) {
+			if (f2fs_is_suspending(sbi)) {
 				suspended = true;
 				break;
 			}
@@ -1955,7 +1958,8 @@ static int issue_discard_thread(void *data)
 			continue;
 		if (kthread_should_stop())
 			return 0;
-		if (is_sbi_flag_set(sbi, SBI_NEED_FSCK) ||
+		if (f2fs_is_suspending(sbi) ||
+			is_sbi_flag_set(sbi, SBI_NEED_FSCK) ||
 			!atomic_read(&dcc->discard_cmd_cnt)) {
 			wait_ms = dpolicy.max_interval;
 			continue;
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index c448d992ff2a..8c97b5d1ee68 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -1979,6 +1979,26 @@ static void destroy_device_list(struct f2fs_sb_info *sbi)
 	kvfree(sbi->devs);
 }
 
+static int f2fs_pm_notifier(struct notifier_block *nb,
+			    unsigned long action, void *ptr)
+{
+	struct f2fs_sb_info *sbi = container_of(nb, struct f2fs_sb_info, pm_nb);
+
+	switch (action) {
+	case PM_HIBERNATION_PREPARE:
+	case PM_SUSPEND_PREPARE:
+	case PM_RESTORE_PREPARE:
+		set_sbi_flag(sbi, SBI_IS_SUSPENDING);
+		break;
+	case PM_POST_SUSPEND:
+	case PM_POST_HIBERNATION:
+	case PM_POST_RESTORE:
+		clear_sbi_flag(sbi, SBI_IS_SUSPENDING);
+		break;
+	}
+	return NOTIFY_OK;
+}
+
 static void f2fs_put_super(struct super_block *sb)
 {
 	struct f2fs_sb_info *sbi = F2FS_SB(sb);
@@ -1986,6 +2006,8 @@ static void f2fs_put_super(struct super_block *sb)
 	int err = 0;
 	bool done;
 
+	unregister_pm_notifier(&sbi->pm_nb);
+
 	/* unregister procfs/sysfs entries in advance to avoid race case */
 	f2fs_unregister_sysfs(sbi);
 
@@ -5436,6 +5458,9 @@ static int f2fs_fill_super(struct super_block *sb, struct fs_context *fc)
 	f2fs_update_time(sbi, REQ_TIME);
 	clear_sbi_flag(sbi, SBI_CP_DISABLED_QUICK);
 
+	sbi->pm_nb.notifier_call = f2fs_pm_notifier;
+	register_pm_notifier(&sbi->pm_nb);
+
 	sbi->umount_lock_holder = NULL;
 	return 0;
 
-- 
2.55.0.654.g21b8a5bc05-goog