Unverified Commit 0da3938c authored by openeuler-ci-bot's avatar openeuler-ci-bot Committed by Gitee
Browse files

!8931 v2 ext4: avoid deadlock in fs reclaim with page writeback 

Merge Pull Request from: @ci-robot 
 
PR sync from: Baokun Li <libaokun1@huawei.com>
https://mailweb.openeuler.org/hyperkitty/list/kernel@openeuler.org/message/SDHHNAKPLQEYNYKAJYIKEXC6BM343UC6/ 
 
https://gitee.com/openeuler/kernel/issues/I9SYGK 
 
Link:https://gitee.com/openeuler/kernel/pulls/8931

 

Reviewed-by: default avatarzhangyi (F) <yi.zhang@huawei.com>
Signed-off-by: default avatarZhang Changzhong <zhangchangzhong@huawei.com>
parents f51dbc4f 7b208222

fs/ext4/ext4.h

+25 −0
Original line number Diff line number Diff line
@@ -37,6 +37,7 @@ 
#include <crypto/hash.h>

#include <linux/falloc.h>

#include <linux/percpu-rwsem.h>

#include <linux/sched/mm.h>

#ifdef __KERNEL__

#include <linux/compat.h>

#endif
@@ -1571,6 +1572,30 @@ static inline struct ext4_inode_info *EXT4_I(struct inode *inode) 
	return container_of(inode, struct ext4_inode_info, vfs_inode);

}



static inline int ext4_writepages_down_read(struct super_block *sb)

{

	percpu_down_read(&EXT4_SB(sb)->s_writepages_rwsem);

	return memalloc_nofs_save();

}



static inline void ext4_writepages_up_read(struct super_block *sb, int ctx)

{

	memalloc_nofs_restore(ctx);

	percpu_up_read(&EXT4_SB(sb)->s_writepages_rwsem);

}



static inline int ext4_writepages_down_write(struct super_block *sb)

{

	percpu_down_write(&EXT4_SB(sb)->s_writepages_rwsem);

	return memalloc_nofs_save();

}



static inline void ext4_writepages_up_write(struct super_block *sb, int ctx)

{

	memalloc_nofs_restore(ctx);

	percpu_up_write(&EXT4_SB(sb)->s_writepages_rwsem);

}



static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino)

{

	return ino == EXT4_ROOT_INO ||

fs/ext4/inode.c

+10 −8
Original line number Diff line number Diff line
@@ -2744,13 +2744,14 @@ static int ext4_writepages(struct address_space *mapping, 
	struct blk_plug plug;

	bool give_up_on_write = false;

	unsigned long retry_warn_ddl = 0;

	int alloc_ctx;



#define RETRY_WARN_TIMEOUT (30 * HZ)



	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))

		return -EIO;



	percpu_down_read(&sbi->s_writepages_rwsem);

	alloc_ctx = ext4_writepages_down_read(inode->i_sb);

	trace_ext4_writepages(inode, wbc);



	/*
@@ -2981,7 +2982,7 @@ static int ext4_writepages(struct address_space *mapping, 
out_writepages:

	trace_ext4_writepages_result(inode, wbc, ret,

				     nr_to_write - wbc->nr_to_write);

	percpu_up_read(&sbi->s_writepages_rwsem);

	ext4_writepages_up_read(inode->i_sb, alloc_ctx);

	return ret;

}
@@ -2992,17 +2993,18 @@ static int ext4_dax_writepages(struct address_space *mapping, 
	long nr_to_write = wbc->nr_to_write;

	struct inode *inode = mapping->host;

	struct ext4_sb_info *sbi = EXT4_SB(mapping->host->i_sb);

	int alloc_ctx;



	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))

		return -EIO;



	percpu_down_read(&sbi->s_writepages_rwsem);

	alloc_ctx = ext4_writepages_down_read(inode->i_sb);

	trace_ext4_writepages(inode, wbc);



	ret = dax_writeback_mapping_range(mapping, inode->i_sb->s_bdev, wbc);

	trace_ext4_writepages_result(inode, wbc, ret,

				     nr_to_write - wbc->nr_to_write);

	percpu_up_read(&sbi->s_writepages_rwsem);

	ext4_writepages_up_read(inode->i_sb, alloc_ctx);

	return ret;

}
@@ -6242,7 +6244,7 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val) 
	journal_t *journal;

	handle_t *handle;

	int err;

	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);

	int alloc_ctx;



	/*

	 * We have to be very careful here: changing a data block's
@@ -6282,7 +6284,7 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val) 
		}

	}



	percpu_down_write(&sbi->s_writepages_rwsem);

	alloc_ctx = ext4_writepages_down_write(inode->i_sb);

	jbd2_journal_lock_updates(journal);



	/*
@@ -6299,7 +6301,7 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val) 
		err = jbd2_journal_flush(journal);

		if (err < 0) {

			jbd2_journal_unlock_updates(journal);

			percpu_up_write(&sbi->s_writepages_rwsem);

			ext4_writepages_up_write(inode->i_sb, alloc_ctx);

			ext4_inode_resume_unlocked_dio(inode);

			return err;

		}
@@ -6308,7 +6310,7 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val) 
	ext4_set_aops(inode);



	jbd2_journal_unlock_updates(journal);

	percpu_up_write(&sbi->s_writepages_rwsem);

	ext4_writepages_up_write(inode->i_sb, alloc_ctx);



	if (val)

		up_write(&EXT4_I(inode)->i_mmap_sem);

fs/ext4/migrate.c

+6 −5
Original line number Diff line number Diff line
@@ -407,7 +407,6 @@ static int free_ext_block(handle_t *handle, struct inode *inode) 


int ext4_ext_migrate(struct inode *inode)

{

	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);

	handle_t *handle;

	int retval = 0, i;

	__le32 *i_data;
@@ -417,6 +416,7 @@ int ext4_ext_migrate(struct inode *inode) 
	unsigned long max_entries;

	__u32 goal, tmp_csum_seed;

	uid_t owner[2];

	int alloc_ctx;



	/*

	 * If the filesystem does not support extents, or the inode
@@ -432,7 +432,7 @@ int ext4_ext_migrate(struct inode *inode) 
		 */

		return retval;



	percpu_down_write(&sbi->s_writepages_rwsem);

	alloc_ctx = ext4_writepages_down_write(inode->i_sb);



	/*

	 * Worst case we can touch the allocation bitmaps and a block
@@ -584,7 +584,7 @@ int ext4_ext_migrate(struct inode *inode) 
	unlock_new_inode(tmp_inode);

	iput(tmp_inode);

out_unlock:

	percpu_up_write(&sbi->s_writepages_rwsem);

	ext4_writepages_up_write(inode->i_sb, alloc_ctx);

	return retval;

}
@@ -603,6 +603,7 @@ int ext4_ind_migrate(struct inode *inode) 
	ext4_fsblk_t			blk;

	handle_t			*handle;

	int				ret;

	int				alloc_ctx;



	if (!ext4_has_feature_extents(inode->i_sb) ||

	    (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
@@ -619,7 +620,7 @@ int ext4_ind_migrate(struct inode *inode) 
	if (test_opt(inode->i_sb, DELALLOC))

		ext4_alloc_da_blocks(inode);



	percpu_down_write(&sbi->s_writepages_rwsem);

	alloc_ctx = ext4_writepages_down_write(inode->i_sb);



	handle = ext4_journal_start(inode, EXT4_HT_MIGRATE, 1);

	if (IS_ERR(handle)) {
@@ -661,6 +662,6 @@ int ext4_ind_migrate(struct inode *inode) 
	ext4_journal_stop(handle);

	up_write(&EXT4_I(inode)->i_data_sem);

out_unlock:

	percpu_up_write(&sbi->s_writepages_rwsem);

	ext4_writepages_up_write(inode->i_sb, alloc_ctx);

	return ret;

}

fs/ext4/super.c

+6 −5
Original line number Diff line number Diff line
@@ -5559,6 +5559,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) 
	ext4_group_t g;

	unsigned int journal_ioprio = DEFAULT_JOURNAL_IOPRIO;

	int err = 0;

	int alloc_ctx;

#ifdef CONFIG_QUOTA

	int i, j;

	char *to_free[EXT4_MAXQUOTAS];
@@ -5611,13 +5612,13 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) 
	 * s_writepages_rwsem to avoid race between writepages ops and

	 * remount.

	 */

	percpu_down_write(&sbi->s_writepages_rwsem);

	alloc_ctx = ext4_writepages_down_write(sb);

	if (!parse_options(data, sb, NULL, &journal_ioprio, 1)) {

		err = -EINVAL;

		percpu_up_write(&sbi->s_writepages_rwsem);

		ext4_writepages_up_write(sb, alloc_ctx);

		goto restore_opts;

	}

	percpu_up_write(&sbi->s_writepages_rwsem);

	ext4_writepages_up_write(sb, alloc_ctx);



	if ((old_opts.s_mount_opt & EXT4_MOUNT_JOURNAL_CHECKSUM) ^

	    test_opt(sb, JOURNAL_CHECKSUM)) {
@@ -5850,7 +5851,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) 
	    sb_any_quota_suspended(sb))

		dquot_resume(sb, -1);



	percpu_down_write(&sbi->s_writepages_rwsem);

	alloc_ctx = ext4_writepages_down_write(sb);

	sb->s_flags = old_sb_flags;

	sbi->s_mount_opt = old_opts.s_mount_opt;

	sbi->s_mount_opt2 = old_opts.s_mount_opt2;
@@ -5859,7 +5860,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) 
	sbi->s_commit_interval = old_opts.s_commit_interval;

	sbi->s_min_batch_time = old_opts.s_min_batch_time;

	sbi->s_max_batch_time = old_opts.s_max_batch_time;

	percpu_up_write(&sbi->s_writepages_rwsem);

	ext4_writepages_up_write(sb, alloc_ctx);



	if (!test_opt(sb, BLOCK_VALIDITY) && sbi->system_blks)

		ext4_release_system_zone(sb);