Merge tag 'f2fs-for-6.5-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs

Pull f2fs updates from Jaegeuk Kim:
 "In this cycle, we've mainly investigated the zoned block device
  support along with patches such as correcting write pointers between
  f2fs and storage, adding asynchronous zone reset flow, and managing
  the number of open zones.

  Other than them, f2fs adds another mount option, "errors=x" to specify
  how to handle when it detects an unexpected behavior at runtime.

  Enhancements:
   - support 'errors=remount-ro|continue|panic' mount option
   - enforce some inode flag policies
   - allow .tmp compression given extensions
   - add some ioctls to manage the f2fs compression
   - improve looped node chain flow
   - avoid issuing small-sized discard commands during checkpoint
   - implement an asynchronous zone reset

  Bug fixes:
   - fix deadlock in xattr and inode page lock
   - fix and add sanity check in some error paths
   - fix to avoid NULL pointer dereference f2fs_write_end_io() along
     with put_super
   - set proper flags to quota files
   - fix potential deadlock due to unpaired node_write lock use
   - fix over-estimating free section during FG GC
   - fix the wrong condition to determine atomic context

  As usual, also there are a number of patches with code refactoring and
  minor clean-ups"

* tag 'f2fs-for-6.5-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs: (46 commits)
  f2fs: fix to do sanity check on direct node in truncate_dnode()
  f2fs: only set release for file that has compressed data
  f2fs: fix compile warning in f2fs_destroy_node_manager()
  f2fs: fix error path handling in truncate_dnode()
  f2fs: fix deadlock in i_xattr_sem and inode page lock
  f2fs: remove unneeded page uptodate check/set
  f2fs: update mtime and ctime in move file range method
  f2fs: compress tmp files given extension
  f2fs: refactor struct f2fs_attr macro
  f2fs: convert to use sbi directly
  f2fs: remove redundant assignment to variable err
  f2fs: do not issue small discard commands during checkpoint
  f2fs: check zone write pointer points to the end of zone
  f2fs: add f2fs_ioc_get_compress_blocks
  f2fs: cleanup MIN_INLINE_XATTR_SIZE
  f2fs: add helper to check compression level
  f2fs: set FMODE_CAN_ODIRECT instead of a dummy direct_IO method
  f2fs: do more sanity check on inode
  f2fs: compress: fix to check validity of i_compress_flag field
  f2fs: add sanity compress level check for compressed file
  ...

1 files changed, 214 insertions, 38 deletions

diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index e34197a70dc1..ca31163da00a 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -164,6 +164,7 @@ enum {
 	Opt_discard_unit,
 	Opt_memory_mode,
 	Opt_age_extent_cache,
+	Opt_errors,
 	Opt_err,
 };
 
@@ -243,6 +244,7 @@ static match_table_t f2fs_tokens = {
 	{Opt_discard_unit, "discard_unit=%s"},
 	{Opt_memory_mode, "memory=%s"},
 	{Opt_age_extent_cache, "age_extent_cache"},
+	{Opt_errors, "errors=%s"},
 	{Opt_err, NULL},
 };
 
@@ -587,14 +589,12 @@ static int f2fs_set_lz4hc_level(struct f2fs_sb_info *sbi, const char *str)
 {
 #ifdef CONFIG_F2FS_FS_LZ4HC
 	unsigned int level;
-#endif
 
 	if (strlen(str) == 3) {
-		F2FS_OPTION(sbi).compress_level = 0;
+		F2FS_OPTION(sbi).compress_level = LZ4HC_DEFAULT_CLEVEL;
 		return 0;
 	}
 
-#ifdef CONFIG_F2FS_FS_LZ4HC
 	str += 3;
 
 	if (str[0] != ':') {
@@ -604,7 +604,7 @@ static int f2fs_set_lz4hc_level(struct f2fs_sb_info *sbi, const char *str)
 	if (kstrtouint(str + 1, 10, &level))
 		return -EINVAL;
 
-	if (level < LZ4HC_MIN_CLEVEL || level > LZ4HC_MAX_CLEVEL) {
+	if (!f2fs_is_compress_level_valid(COMPRESS_LZ4, level)) {
 		f2fs_info(sbi, "invalid lz4hc compress level: %d", level);
 		return -EINVAL;
 	}
@@ -612,6 +612,10 @@ static int f2fs_set_lz4hc_level(struct f2fs_sb_info *sbi, const char *str)
 	F2FS_OPTION(sbi).compress_level = level;
 	return 0;
 #else
+	if (strlen(str) == 3) {
+		F2FS_OPTION(sbi).compress_level = 0;
+		return 0;
+	}
 	f2fs_info(sbi, "kernel doesn't support lz4hc compression");
 	return -EINVAL;
 #endif
@@ -625,7 +629,7 @@ static int f2fs_set_zstd_level(struct f2fs_sb_info *sbi, const char *str)
 	int len = 4;
 
 	if (strlen(str) == len) {
-		F2FS_OPTION(sbi).compress_level = 0;
+		F2FS_OPTION(sbi).compress_level = F2FS_ZSTD_DEFAULT_CLEVEL;
 		return 0;
 	}
 
@@ -638,7 +642,7 @@ static int f2fs_set_zstd_level(struct f2fs_sb_info *sbi, const char *str)
 	if (kstrtouint(str + 1, 10, &level))
 		return -EINVAL;
 
-	if (!level || level > zstd_max_clevel()) {
+	if (!f2fs_is_compress_level_valid(COMPRESS_ZSTD, level)) {
 		f2fs_info(sbi, "invalid zstd compress level: %d", level);
 		return -EINVAL;
 	}
@@ -1268,6 +1272,25 @@ static int parse_options(struct super_block *sb, char *options, bool is_remount)
 		case Opt_age_extent_cache:
 			set_opt(sbi, AGE_EXTENT_CACHE);
 			break;
+		case Opt_errors:
+			name = match_strdup(&args[0]);
+			if (!name)
+				return -ENOMEM;
+			if (!strcmp(name, "remount-ro")) {
+				F2FS_OPTION(sbi).errors =
+						MOUNT_ERRORS_READONLY;
+			} else if (!strcmp(name, "continue")) {
+				F2FS_OPTION(sbi).errors =
+						MOUNT_ERRORS_CONTINUE;
+			} else if (!strcmp(name, "panic")) {
+				F2FS_OPTION(sbi).errors =
+						MOUNT_ERRORS_PANIC;
+			} else {
+				kfree(name);
+				return -EINVAL;
+			}
+			kfree(name);
+			break;
 		default:
 			f2fs_err(sbi, "Unrecognized mount option \"%s\" or missing value",
 				 p);
@@ -1340,7 +1363,7 @@ default_check:
 			return -EINVAL;
 		}
 
-		min_size = sizeof(struct f2fs_xattr_header) / sizeof(__le32);
+		min_size = MIN_INLINE_XATTR_SIZE;
 		max_size = MAX_INLINE_XATTR_SIZE;
 
 		if (F2FS_OPTION(sbi).inline_xattr_size < min_size ||
@@ -1550,6 +1573,7 @@ static void f2fs_put_super(struct super_block *sb)
 {
 	struct f2fs_sb_info *sbi = F2FS_SB(sb);
 	int i;
+	int err = 0;
 	bool done;
 
 	/* unregister procfs/sysfs entries in advance to avoid race case */
@@ -1576,7 +1600,7 @@ static void f2fs_put_super(struct super_block *sb)
 		struct cp_control cpc = {
 			.reason = CP_UMOUNT,
 		};
-		f2fs_write_checkpoint(sbi, &cpc);
+		err = f2fs_write_checkpoint(sbi, &cpc);
 	}
 
 	/* be sure to wait for any on-going discard commands */
@@ -1585,7 +1609,7 @@ static void f2fs_put_super(struct super_block *sb)
 		struct cp_control cpc = {
 			.reason = CP_UMOUNT | CP_TRIMMED,
 		};
-		f2fs_write_checkpoint(sbi, &cpc);
+		err = f2fs_write_checkpoint(sbi, &cpc);
 	}
 
 	/*
@@ -1602,6 +1626,19 @@ static void f2fs_put_super(struct super_block *sb)
 
 	f2fs_wait_on_all_pages(sbi, F2FS_WB_CP_DATA);
 
+	if (err) {
+		truncate_inode_pages_final(NODE_MAPPING(sbi));
+		truncate_inode_pages_final(META_MAPPING(sbi));
+	}
+
+	for (i = 0; i < NR_COUNT_TYPE; i++) {
+		if (!get_pages(sbi, i))
+			continue;
+		f2fs_err(sbi, "detect filesystem reference count leak during "
+			"umount, type: %d, count: %lld", i, get_pages(sbi, i));
+		f2fs_bug_on(sbi, 1);
+	}
+
 	f2fs_bug_on(sbi, sbi->fsync_node_num);
 
 	f2fs_destroy_compress_inode(sbi);
@@ -1622,6 +1659,9 @@ static void f2fs_put_super(struct super_block *sb)
 	f2fs_destroy_node_manager(sbi);
 	f2fs_destroy_segment_manager(sbi);
 
+	/* flush s_error_work before sbi destroy */
+	flush_work(&sbi->s_error_work);
+
 	f2fs_destroy_post_read_wq(sbi);
 
 	kvfree(sbi->ckpt);
@@ -2052,12 +2092,32 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root)
 	else if (F2FS_OPTION(sbi).memory_mode == MEMORY_MODE_LOW)
 		seq_printf(seq, ",memory=%s", "low");
 
+	if (F2FS_OPTION(sbi).errors == MOUNT_ERRORS_READONLY)
+		seq_printf(seq, ",errors=%s", "remount-ro");
+	else if (F2FS_OPTION(sbi).errors == MOUNT_ERRORS_CONTINUE)
+		seq_printf(seq, ",errors=%s", "continue");
+	else if (F2FS_OPTION(sbi).errors == MOUNT_ERRORS_PANIC)
+		seq_printf(seq, ",errors=%s", "panic");
+
 	return 0;
 }
 
-static void default_options(struct f2fs_sb_info *sbi)
+static void default_options(struct f2fs_sb_info *sbi, bool remount)
 {
 	/* init some FS parameters */
+	if (!remount) {
+		set_opt(sbi, READ_EXTENT_CACHE);
+		clear_opt(sbi, DISABLE_CHECKPOINT);
+
+		if (f2fs_hw_support_discard(sbi) || f2fs_hw_should_discard(sbi))
+			set_opt(sbi, DISCARD);
+
+		if (f2fs_sb_has_blkzoned(sbi))
+			F2FS_OPTION(sbi).discard_unit = DISCARD_UNIT_SECTION;
+		else
+			F2FS_OPTION(sbi).discard_unit = DISCARD_UNIT_BLOCK;
+	}
+
 	if (f2fs_sb_has_readonly(sbi))
 		F2FS_OPTION(sbi).active_logs = NR_CURSEG_RO_TYPE;
 	else
@@ -2080,29 +2140,23 @@ static void default_options(struct f2fs_sb_info *sbi)
 	}
 	F2FS_OPTION(sbi).bggc_mode = BGGC_MODE_ON;
 	F2FS_OPTION(sbi).memory_mode = MEMORY_MODE_NORMAL;
+	F2FS_OPTION(sbi).errors = MOUNT_ERRORS_CONTINUE;
 
 	sbi->sb->s_flags &= ~SB_INLINECRYPT;
 
 	set_opt(sbi, INLINE_XATTR);
 	set_opt(sbi, INLINE_DATA);
 	set_opt(sbi, INLINE_DENTRY);
-	set_opt(sbi, READ_EXTENT_CACHE);
 	set_opt(sbi, NOHEAP);
-	clear_opt(sbi, DISABLE_CHECKPOINT);
 	set_opt(sbi, MERGE_CHECKPOINT);
 	F2FS_OPTION(sbi).unusable_cap = 0;
 	sbi->sb->s_flags |= SB_LAZYTIME;
 	if (!f2fs_is_readonly(sbi))
 		set_opt(sbi, FLUSH_MERGE);
-	if (f2fs_hw_support_discard(sbi) || f2fs_hw_should_discard(sbi))
-		set_opt(sbi, DISCARD);
-	if (f2fs_sb_has_blkzoned(sbi)) {
+	if (f2fs_sb_has_blkzoned(sbi))
 		F2FS_OPTION(sbi).fs_mode = FS_MODE_LFS;
-		F2FS_OPTION(sbi).discard_unit = DISCARD_UNIT_SECTION;
-	} else {
+	else
 		F2FS_OPTION(sbi).fs_mode = FS_MODE_ADAPTIVE;
-		F2FS_OPTION(sbi).discard_unit = DISCARD_UNIT_BLOCK;
-	}
 
 #ifdef CONFIG_F2FS_FS_XATTR
 	set_opt(sbi, XATTR_USER);
@@ -2274,13 +2328,16 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
 			clear_sbi_flag(sbi, SBI_NEED_SB_WRITE);
 	}
 
-	default_options(sbi);
+	default_options(sbi, true);
 
 	/* parse mount options */
 	err = parse_options(sb, data, true);
 	if (err)
 		goto restore_opts;
 
+	/* flush outstanding errors before changing fs state */
+	flush_work(&sbi->s_error_work);
+
 	/*
 	 * Previous and new state of filesystem is RO,
 	 * so skip checking GC and FLUSH_MERGE conditions.
@@ -2713,6 +2770,7 @@ static int f2fs_quota_enable(struct super_block *sb, int type, int format_id,
 {
 	struct inode *qf_inode;
 	unsigned long qf_inum;
+	unsigned long qf_flag = F2FS_QUOTA_DEFAULT_FL;
 	int err;
 
 	BUG_ON(!f2fs_sb_has_quota_ino(F2FS_SB(sb)));
@@ -2728,7 +2786,15 @@ static int f2fs_quota_enable(struct super_block *sb, int type, int format_id,
 	}
 
 	/* Don't account quota for quota files to avoid recursion */
+	inode_lock(qf_inode);
 	qf_inode->i_flags |= S_NOQUOTA;
+
+	if ((F2FS_I(qf_inode)->i_flags & qf_flag) != qf_flag) {
+		F2FS_I(qf_inode)->i_flags |= qf_flag;
+		f2fs_set_inode_flags(qf_inode);
+	}
+	inode_unlock(qf_inode);
+
 	err = dquot_load_quota_inode(qf_inode, type, format_id, flags);
 	iput(qf_inode);
 	return err;
@@ -2859,18 +2925,29 @@ static int f2fs_quota_on(struct super_block *sb, int type, int format_id,
 		return -EBUSY;
 	}
 
+	if (path->dentry->d_sb != sb)
+		return -EXDEV;
+
 	err = f2fs_quota_sync(sb, type);
 	if (err)
 		return err;
 
-	err = dquot_quota_on(sb, type, format_id, path);
+	inode = d_inode(path->dentry);
+
+	err = filemap_fdatawrite(inode->i_mapping);
 	if (err)
 		return err;
 
-	inode = d_inode(path->dentry);
+	err = filemap_fdatawait(inode->i_mapping);
+	if (err)
+		return err;
+
+	err = dquot_quota_on(sb, type, format_id, path);
+	if (err)
+		return err;
 
 	inode_lock(inode);
-	F2FS_I(inode)->i_flags |= F2FS_NOATIME_FL | F2FS_IMMUTABLE_FL;
+	F2FS_I(inode)->i_flags |= F2FS_QUOTA_DEFAULT_FL;
 	f2fs_set_inode_flags(inode);
 	inode_unlock(inode);
 	f2fs_mark_inode_dirty_sync(inode, false);
@@ -2895,7 +2972,7 @@ static int __f2fs_quota_off(struct super_block *sb, int type)
 		goto out_put;
 
 	inode_lock(inode);
-	F2FS_I(inode)->i_flags &= ~(F2FS_NOATIME_FL | F2FS_IMMUTABLE_FL);
+	F2FS_I(inode)->i_flags &= ~F2FS_QUOTA_DEFAULT_FL;
 	f2fs_set_inode_flags(inode);
 	inode_unlock(inode);
 	f2fs_mark_inode_dirty_sync(inode, false);
@@ -3926,55 +4003,73 @@ int f2fs_commit_super(struct f2fs_sb_info *sbi, bool recover)
 	return err;
 }
 
-void f2fs_handle_stop(struct f2fs_sb_info *sbi, unsigned char reason)
+static void save_stop_reason(struct f2fs_sb_info *sbi, unsigned char reason)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&sbi->error_lock, flags);
+	if (sbi->stop_reason[reason] < GENMASK(BITS_PER_BYTE - 1, 0))
+		sbi->stop_reason[reason]++;
+	spin_unlock_irqrestore(&sbi->error_lock, flags);
+}
+
+static void f2fs_record_stop_reason(struct f2fs_sb_info *sbi)
 {
 	struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi);
+	unsigned long flags;
 	int err;
 
 	f2fs_down_write(&sbi->sb_lock);
 
-	if (raw_super->s_stop_reason[reason] < GENMASK(BITS_PER_BYTE - 1, 0))
-		raw_super->s_stop_reason[reason]++;
+	spin_lock_irqsave(&sbi->error_lock, flags);
+	if (sbi->error_dirty) {
+		memcpy(F2FS_RAW_SUPER(sbi)->s_errors, sbi->errors,
+							MAX_F2FS_ERRORS);
+		sbi->error_dirty = false;
+	}
+	memcpy(raw_super->s_stop_reason, sbi->stop_reason, MAX_STOP_REASON);
+	spin_unlock_irqrestore(&sbi->error_lock, flags);
 
 	err = f2fs_commit_super(sbi, false);
-	if (err)
-		f2fs_err(sbi, "f2fs_commit_super fails to record reason:%u err:%d",
-								reason, err);
+
 	f2fs_up_write(&sbi->sb_lock);
+	if (err)
+		f2fs_err(sbi, "f2fs_commit_super fails to record err:%d", err);
 }
 
 void f2fs_save_errors(struct f2fs_sb_info *sbi, unsigned char flag)
 {
-	spin_lock(&sbi->error_lock);
+	unsigned long flags;
+
+	spin_lock_irqsave(&sbi->error_lock, flags);
 	if (!test_bit(flag, (unsigned long *)sbi->errors)) {
 		set_bit(flag, (unsigned long *)sbi->errors);
 		sbi->error_dirty = true;
 	}
-	spin_unlock(&sbi->error_lock);
+	spin_unlock_irqrestore(&sbi->error_lock, flags);
 }
 
 static bool f2fs_update_errors(struct f2fs_sb_info *sbi)
 {
+	unsigned long flags;
 	bool need_update = false;
 
-	spin_lock(&sbi->error_lock);
+	spin_lock_irqsave(&sbi->error_lock, flags);
 	if (sbi->error_dirty) {
 		memcpy(F2FS_RAW_SUPER(sbi)->s_errors, sbi->errors,
 							MAX_F2FS_ERRORS);
 		sbi->error_dirty = false;
 		need_update = true;
 	}
-	spin_unlock(&sbi->error_lock);
+	spin_unlock_irqrestore(&sbi->error_lock, flags);
 
 	return need_update;
 }
 
-void f2fs_handle_error(struct f2fs_sb_info *sbi, unsigned char error)
+static void f2fs_record_errors(struct f2fs_sb_info *sbi, unsigned char error)
 {
 	int err;
 
-	f2fs_save_errors(sbi, error);
-
 	f2fs_down_write(&sbi->sb_lock);
 
 	if (!f2fs_update_errors(sbi))
@@ -3988,6 +4083,83 @@ out_unlock:
 	f2fs_up_write(&sbi->sb_lock);
 }
 
+void f2fs_handle_error(struct f2fs_sb_info *sbi, unsigned char error)
+{
+	f2fs_save_errors(sbi, error);
+	f2fs_record_errors(sbi, error);
+}
+
+void f2fs_handle_error_async(struct f2fs_sb_info *sbi, unsigned char error)
+{
+	f2fs_save_errors(sbi, error);
+
+	if (!sbi->error_dirty)
+		return;
+	if (!test_bit(error, (unsigned long *)sbi->errors))
+		return;
+	schedule_work(&sbi->s_error_work);
+}
+
+static bool system_going_down(void)
+{
+	return system_state == SYSTEM_HALT || system_state == SYSTEM_POWER_OFF
+		|| system_state == SYSTEM_RESTART;
+}
+
+void f2fs_handle_critical_error(struct f2fs_sb_info *sbi, unsigned char reason,
+							bool irq_context)
+{
+	struct super_block *sb = sbi->sb;
+	bool shutdown = reason == STOP_CP_REASON_SHUTDOWN;
+	bool continue_fs = !shutdown &&
+			F2FS_OPTION(sbi).errors == MOUNT_ERRORS_CONTINUE;
+
+	set_ckpt_flags(sbi, CP_ERROR_FLAG);
+
+	if (!f2fs_hw_is_readonly(sbi)) {
+		save_stop_reason(sbi, reason);
+
+		if (irq_context && !shutdown)
+			schedule_work(&sbi->s_error_work);
+		else
+			f2fs_record_stop_reason(sbi);
+	}
+
+	/*
+	 * We force ERRORS_RO behavior when system is rebooting. Otherwise we
+	 * could panic during 'reboot -f' as the underlying device got already
+	 * disabled.
+	 */
+	if (F2FS_OPTION(sbi).errors == MOUNT_ERRORS_PANIC &&
+				!shutdown && !system_going_down() &&
+				!is_sbi_flag_set(sbi, SBI_IS_SHUTDOWN))
+		panic("F2FS-fs (device %s): panic forced after error\n",
+							sb->s_id);
+
+	if (shutdown)
+		set_sbi_flag(sbi, SBI_IS_SHUTDOWN);
+
+	/* continue filesystem operators if errors=continue */
+	if (continue_fs || f2fs_readonly(sb))
+		return;
+
+	f2fs_warn(sbi, "Remounting filesystem read-only");
+	/*
+	 * Make sure updated value of ->s_mount_flags will be visible before
+	 * ->s_flags update
+	 */
+	smp_wmb();
+	sb->s_flags |= SB_RDONLY;
+}
+
+static void f2fs_record_error_work(struct work_struct *work)
+{
+	struct f2fs_sb_info *sbi = container_of(work,
+					struct f2fs_sb_info, s_error_work);
+
+	f2fs_record_stop_reason(sbi);
+}
+
 static int f2fs_scan_devices(struct f2fs_sb_info *sbi)
 {
 	struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi);
@@ -4220,14 +4392,16 @@ try_onemore:
 	sb->s_fs_info = sbi;
 	sbi->raw_super = raw_super;
 
+	INIT_WORK(&sbi->s_error_work, f2fs_record_error_work);
 	memcpy(sbi->errors, raw_super->s_errors, MAX_F2FS_ERRORS);
+	memcpy(sbi->stop_reason, raw_super->s_stop_reason, MAX_STOP_REASON);
 
 	/* precompute checksum seed for metadata */
 	if (f2fs_sb_has_inode_chksum(sbi))
 		sbi->s_chksum_seed = f2fs_chksum(sbi, ~0, raw_super->uuid,
 						sizeof(raw_super->uuid));
 
-	default_options(sbi);
+	default_options(sbi, false);
 	/* parse mount options */
 	options = kstrdup((const char *)data, GFP_KERNEL);
 	if (data && !options) {
@@ -4617,6 +4791,8 @@ free_sm:
 	f2fs_destroy_segment_manager(sbi);
 stop_ckpt_thread:
 	f2fs_stop_ckpt_thread(sbi);
+	/* flush s_error_work before sbi destroy */
+	flush_work(&sbi->s_error_work);
 	f2fs_destroy_post_read_wq(sbi);
 free_devices:
 	destroy_device_list(sbi);