1 files changed, 174 insertions, 87 deletions

diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 2937a8873fe1..ff1b764b0c0e 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -154,7 +154,7 @@ ext4_sb_bread(struct super_block *sb, sector_t block, int op_flags)
 
 	if (bh == NULL)
 		return ERR_PTR(-ENOMEM);
-	if (buffer_uptodate(bh))
+	if (ext4_buffer_uptodate(bh))
 		return bh;
 	ll_rw_block(REQ_OP_READ, REQ_META | op_flags, 1, &bh);
 	wait_on_buffer(bh);
@@ -204,26 +204,6 @@ void ext4_superblock_csum_set(struct super_block *sb)
 	es->s_checksum = ext4_superblock_csum(sb, es);
 }
 
-void *ext4_kvmalloc(size_t size, gfp_t flags)
-{
-	void *ret;
-
-	ret = kmalloc(size, flags | __GFP_NOWARN);
-	if (!ret)
-		ret = __vmalloc(size, flags, PAGE_KERNEL);
-	return ret;
-}
-
-void *ext4_kvzalloc(size_t size, gfp_t flags)
-{
-	void *ret;
-
-	ret = kzalloc(size, flags | __GFP_NOWARN);
-	if (!ret)
-		ret = __vmalloc(size, flags | __GFP_ZERO, PAGE_KERNEL);
-	return ret;
-}
-
 ext4_fsblk_t ext4_block_bitmap(struct super_block *sb,
 			       struct ext4_group_desc *bg)
 {
@@ -367,6 +347,8 @@ static void __save_error_info(struct super_block *sb, const char *func,
 	ext4_update_tstamp(es, s_last_error_time);
 	strncpy(es->s_last_error_func, func, sizeof(es->s_last_error_func));
 	es->s_last_error_line = cpu_to_le32(line);
+	if (es->s_last_error_errcode == 0)
+		es->s_last_error_errcode = EXT4_ERR_EFSCORRUPTED;
 	if (!es->s_first_error_time) {
 		es->s_first_error_time = es->s_last_error_time;
 		es->s_first_error_time_hi = es->s_last_error_time_hi;
@@ -375,6 +357,7 @@ static void __save_error_info(struct super_block *sb, const char *func,
 		es->s_first_error_line = cpu_to_le32(line);
 		es->s_first_error_ino = es->s_last_error_ino;
 		es->s_first_error_block = es->s_last_error_block;
+		es->s_first_error_errcode = es->s_last_error_errcode;
 	}
 	/*
 	 * Start the daily error reporting function if it hasn't been
@@ -631,6 +614,66 @@ const char *ext4_decode_error(struct super_block *sb, int errno,
 	return errstr;
 }
 
+void ext4_set_errno(struct super_block *sb, int err)
+{
+	if (err < 0)
+		err = -err;
+
+	switch (err) {
+	case EIO:
+		err = EXT4_ERR_EIO;
+		break;
+	case ENOMEM:
+		err = EXT4_ERR_ENOMEM;
+		break;
+	case EFSBADCRC:
+		err = EXT4_ERR_EFSBADCRC;
+		break;
+	case EFSCORRUPTED:
+		err = EXT4_ERR_EFSCORRUPTED;
+		break;
+	case ENOSPC:
+		err = EXT4_ERR_ENOSPC;
+		break;
+	case ENOKEY:
+		err = EXT4_ERR_ENOKEY;
+		break;
+	case EROFS:
+		err = EXT4_ERR_EROFS;
+		break;
+	case EFBIG:
+		err = EXT4_ERR_EFBIG;
+		break;
+	case EEXIST:
+		err = EXT4_ERR_EEXIST;
+		break;
+	case ERANGE:
+		err = EXT4_ERR_ERANGE;
+		break;
+	case EOVERFLOW:
+		err = EXT4_ERR_EOVERFLOW;
+		break;
+	case EBUSY:
+		err = EXT4_ERR_EBUSY;
+		break;
+	case ENOTDIR:
+		err = EXT4_ERR_ENOTDIR;
+		break;
+	case ENOTEMPTY:
+		err = EXT4_ERR_ENOTEMPTY;
+		break;
+	case ESHUTDOWN:
+		err = EXT4_ERR_ESHUTDOWN;
+		break;
+	case EFAULT:
+		err = EXT4_ERR_EFAULT;
+		break;
+	default:
+		err = EXT4_ERR_UNKNOWN;
+	}
+	EXT4_SB(sb)->s_es->s_last_error_errcode = err;
+}
+
 /* __ext4_std_error decodes expected errors from journaling functions
  * automatically and invokes the appropriate error response.  */
 
@@ -655,6 +698,7 @@ void __ext4_std_error(struct super_block *sb, const char *function,
 		       sb->s_id, function, line, errstr);
 	}
 
+	ext4_set_errno(sb, -errno);
 	save_error_info(sb, function, line);
 	ext4_handle_error(sb);
 }
@@ -970,6 +1014,8 @@ static void ext4_put_super(struct super_block *sb)
 {
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 	struct ext4_super_block *es = sbi->s_es;
+	struct buffer_head **group_desc;
+	struct flex_groups **flex_groups;
 	int aborted = 0;
 	int i, err;
 
@@ -982,8 +1028,10 @@ static void ext4_put_super(struct super_block *sb)
 		aborted = is_journal_aborted(sbi->s_journal);
 		err = jbd2_journal_destroy(sbi->s_journal);
 		sbi->s_journal = NULL;
-		if ((err < 0) && !aborted)
+		if ((err < 0) && !aborted) {
+			ext4_set_errno(sb, -err);
 			ext4_abort(sb, "Couldn't clean up the journal");
+		}
 	}
 
 	ext4_unregister_sysfs(sb);
@@ -1000,15 +1048,23 @@ static void ext4_put_super(struct super_block *sb)
 	if (!sb_rdonly(sb))
 		ext4_commit_super(sb, 1);
 
+	rcu_read_lock();
+	group_desc = rcu_dereference(sbi->s_group_desc);
 	for (i = 0; i < sbi->s_gdb_count; i++)
-		brelse(sbi->s_group_desc[i]);
-	kvfree(sbi->s_group_desc);
-	kvfree(sbi->s_flex_groups);
+		brelse(group_desc[i]);
+	kvfree(group_desc);
+	flex_groups = rcu_dereference(sbi->s_flex_groups);
+	if (flex_groups) {
+		for (i = 0; i < sbi->s_flex_groups_allocated; i++)
+			kvfree(flex_groups[i]);
+		kvfree(flex_groups);
+	}
+	rcu_read_unlock();
 	percpu_counter_destroy(&sbi->s_freeclusters_counter);
 	percpu_counter_destroy(&sbi->s_freeinodes_counter);
 	percpu_counter_destroy(&sbi->s_dirs_counter);
 	percpu_counter_destroy(&sbi->s_dirtyclusters_counter);
-	percpu_free_rwsem(&sbi->s_journal_flag_rwsem);
+	percpu_free_rwsem(&sbi->s_writepages_rwsem);
 #ifdef CONFIG_QUOTA
 	for (i = 0; i < EXT4_MAXQUOTAS; i++)
 		kfree(get_qf_name(sb, sbi, i));
@@ -1085,8 +1141,6 @@ static struct inode *ext4_alloc_inode(struct super_block *sb)
 	ei->i_es_shk_nr = 0;
 	ei->i_es_shrink_lblk = 0;
 	ei->i_reserved_data_blocks = 0;
-	ei->i_da_metadata_calc_len = 0;
-	ei->i_da_metadata_calc_last_lblock = 0;
 	spin_lock_init(&(ei->i_block_reservation_lock));
 	ext4_init_pending_tree(&ei->i_pending_tree);
 #ifdef CONFIG_QUOTA
@@ -1548,6 +1602,7 @@ static const match_table_t tokens = {
 	{Opt_auto_da_alloc, "auto_da_alloc"},
 	{Opt_noauto_da_alloc, "noauto_da_alloc"},
 	{Opt_dioread_nolock, "dioread_nolock"},
+	{Opt_dioread_lock, "nodioread_nolock"},
 	{Opt_dioread_lock, "dioread_lock"},
 	{Opt_discard, "discard"},
 	{Opt_nodiscard, "nodiscard"},
@@ -2335,8 +2390,8 @@ done:
 int ext4_alloc_flex_bg_array(struct super_block *sb, ext4_group_t ngroup)
 {
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
-	struct flex_groups *new_groups;
-	int size;
+	struct flex_groups **old_groups, **new_groups;
+	int size, i;
 
 	if (!sbi->s_log_groups_per_flex)
 		return 0;
@@ -2345,22 +2400,37 @@ int ext4_alloc_flex_bg_array(struct super_block *sb, ext4_group_t ngroup)
 	if (size <= sbi->s_flex_groups_allocated)
 		return 0;
 
-	size = roundup_pow_of_two(size * sizeof(struct flex_groups));
-	new_groups = kvzalloc(size, GFP_KERNEL);
+	new_groups = kvzalloc(roundup_pow_of_two(size *
+			      sizeof(*sbi->s_flex_groups)), GFP_KERNEL);
 	if (!new_groups) {
-		ext4_msg(sb, KERN_ERR, "not enough memory for %d flex groups",
-			 size / (int) sizeof(struct flex_groups));
+		ext4_msg(sb, KERN_ERR,
+			 "not enough memory for %d flex group pointers", size);
 		return -ENOMEM;
 	}
-
-	if (sbi->s_flex_groups) {
-		memcpy(new_groups, sbi->s_flex_groups,
-		       (sbi->s_flex_groups_allocated *
-			sizeof(struct flex_groups)));
-		kvfree(sbi->s_flex_groups);
+	for (i = sbi->s_flex_groups_allocated; i < size; i++) {
+		new_groups[i] = kvzalloc(roundup_pow_of_two(
+					 sizeof(struct flex_groups)),
+					 GFP_KERNEL);
+		if (!new_groups[i]) {
+			for (i--; i >= sbi->s_flex_groups_allocated; i--)
+				kvfree(new_groups[i]);
+			kvfree(new_groups);
+			ext4_msg(sb, KERN_ERR,
+				 "not enough memory for %d flex groups", size);
+			return -ENOMEM;
+		}
 	}
-	sbi->s_flex_groups = new_groups;
-	sbi->s_flex_groups_allocated = size / sizeof(struct flex_groups);
+	rcu_read_lock();
+	old_groups = rcu_dereference(sbi->s_flex_groups);
+	if (old_groups)
+		memcpy(new_groups, old_groups,
+		       (sbi->s_flex_groups_allocated *
+			sizeof(struct flex_groups *)));
+	rcu_read_unlock();
+	rcu_assign_pointer(sbi->s_flex_groups, new_groups);
+	sbi->s_flex_groups_allocated = size;
+	if (old_groups)
+		ext4_kvfree_array_rcu(old_groups);
 	return 0;
 }
 
@@ -2368,6 +2438,7 @@ static int ext4_fill_flex_info(struct super_block *sb)
 {
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 	struct ext4_group_desc *gdp = NULL;
+	struct flex_groups *fg;
 	ext4_group_t flex_group;
 	int i, err;
 
@@ -2385,12 +2456,11 @@ static int ext4_fill_flex_info(struct super_block *sb)
 		gdp = ext4_get_group_desc(sb, i, NULL);
 
 		flex_group = ext4_flex_group(sbi, i);
-		atomic_add(ext4_free_inodes_count(sb, gdp),
-			   &sbi->s_flex_groups[flex_group].free_inodes);
+		fg = sbi_array_rcu_deref(sbi, s_flex_groups, flex_group);
+		atomic_add(ext4_free_inodes_count(sb, gdp), &fg->free_inodes);
 		atomic64_add(ext4_free_group_clusters(sb, gdp),
-			     &sbi->s_flex_groups[flex_group].free_clusters);
-		atomic_add(ext4_used_dirs_count(sb, gdp),
-			   &sbi->s_flex_groups[flex_group].used_dirs);
+			     &fg->free_clusters);
+		atomic_add(ext4_used_dirs_count(sb, gdp), &fg->used_dirs);
 	}
 
 	return 1;
@@ -2964,17 +3034,11 @@ static int ext4_feature_set_ok(struct super_block *sb, int readonly)
 		return 0;
 	}
 
-#ifndef CONFIG_QUOTA
-	if (ext4_has_feature_quota(sb) && !readonly) {
+#if !IS_ENABLED(CONFIG_QUOTA) || !IS_ENABLED(CONFIG_QFMT_V2)
+	if (!readonly && (ext4_has_feature_quota(sb) ||
+			  ext4_has_feature_project(sb))) {
 		ext4_msg(sb, KERN_ERR,
-			 "Filesystem with quota feature cannot be mounted RDWR "
-			 "without CONFIG_QUOTA");
-		return 0;
-	}
-	if (ext4_has_feature_project(sb) && !readonly) {
-		ext4_msg(sb, KERN_ERR,
-			 "Filesystem with project quota feature cannot be mounted RDWR "
-			 "without CONFIG_QUOTA");
+			 "The kernel was not built with CONFIG_QUOTA and CONFIG_QFMT_V2");
 		return 0;
 	}
 #endif  /* CONFIG_QUOTA */
@@ -3595,9 +3659,10 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 {
 	struct dax_device *dax_dev = fs_dax_get_by_bdev(sb->s_bdev);
 	char *orig_data = kstrdup(data, GFP_KERNEL);
-	struct buffer_head *bh;
+	struct buffer_head *bh, **group_desc;
 	struct ext4_super_block *es = NULL;
 	struct ext4_sb_info *sbi = kzalloc(sizeof(*sbi), GFP_KERNEL);
+	struct flex_groups **flex_groups;
 	ext4_fsblk_t block;
 	ext4_fsblk_t sb_block = get_sb_block(&data);
 	ext4_fsblk_t logical_sb_block;
@@ -3720,6 +3785,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 		set_opt(sb, NO_UID32);
 	/* xattr user namespace & acls are now defaulted on */
 	set_opt(sb, XATTR_USER);
+	set_opt(sb, DIOREAD_NOLOCK);
 #ifdef CONFIG_EXT4_FS_POSIX_ACL
 	set_opt(sb, POSIX_ACL);
 #endif
@@ -3768,6 +3834,15 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	 */
 	sbi->s_li_wait_mult = EXT4_DEF_LI_WAIT_MULT;
 
+	blocksize = BLOCK_SIZE << le32_to_cpu(es->s_log_block_size);
+	if (blocksize < EXT4_MIN_BLOCK_SIZE ||
+	    blocksize > EXT4_MAX_BLOCK_SIZE) {
+		ext4_msg(sb, KERN_ERR,
+		       "Unsupported filesystem blocksize %d (%d log_block_size)",
+			 blocksize, le32_to_cpu(es->s_log_block_size));
+		goto failed_mount;
+	}
+
 	if (le32_to_cpu(es->s_rev_level) == EXT4_GOOD_OLD_REV) {
 		sbi->s_inode_size = EXT4_GOOD_OLD_INODE_SIZE;
 		sbi->s_first_ino = EXT4_GOOD_OLD_FIRST_INO;
@@ -3785,6 +3860,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 			ext4_msg(sb, KERN_ERR,
 			       "unsupported inode size: %d",
 			       sbi->s_inode_size);
+			ext4_msg(sb, KERN_ERR, "blocksize: %d", blocksize);
 			goto failed_mount;
 		}
 		/*
@@ -3887,9 +3963,8 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 #endif
 
 	if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) {
-		printk_once(KERN_WARNING "EXT4-fs: Warning: mounting "
-			    "with data=journal disables delayed "
-			    "allocation and O_DIRECT support!\n");
+		printk_once(KERN_WARNING "EXT4-fs: Warning: mounting with data=journal disables delayed allocation, dioread_nolock, and O_DIRECT support!\n");
+		clear_opt(sb, DIOREAD_NOLOCK);
 		if (test_opt2(sb, EXPLICIT_DELALLOC)) {
 			ext4_msg(sb, KERN_ERR, "can't mount with "
 				 "both data=journal and delalloc");
@@ -3988,14 +4063,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	if (!ext4_feature_set_ok(sb, (sb_rdonly(sb))))
 		goto failed_mount;
 
-	blocksize = BLOCK_SIZE << le32_to_cpu(es->s_log_block_size);
-	if (blocksize < EXT4_MIN_BLOCK_SIZE ||
-	    blocksize > EXT4_MAX_BLOCK_SIZE) {
-		ext4_msg(sb, KERN_ERR,
-		       "Unsupported filesystem blocksize %d (%d log_block_size)",
-			 blocksize, le32_to_cpu(es->s_log_block_size));
-		goto failed_mount;
-	}
 	if (le32_to_cpu(es->s_log_block_size) >
 	    (EXT4_MAX_BLOCK_LOG_SIZE - EXT4_MIN_BLOCK_LOG_SIZE)) {
 		ext4_msg(sb, KERN_ERR,
@@ -4249,9 +4316,10 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 			goto failed_mount;
 		}
 	}
-	sbi->s_group_desc = kvmalloc_array(db_count,
-					   sizeof(struct buffer_head *),
-					   GFP_KERNEL);
+	rcu_assign_pointer(sbi->s_group_desc,
+			   kvmalloc_array(db_count,
+					  sizeof(struct buffer_head *),
+					  GFP_KERNEL));
 	if (sbi->s_group_desc == NULL) {
 		ext4_msg(sb, KERN_ERR, "not enough memory");
 		ret = -ENOMEM;
@@ -4267,14 +4335,19 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	}
 
 	for (i = 0; i < db_count; i++) {
+		struct buffer_head *bh;
+
 		block = descriptor_loc(sb, logical_sb_block, i);
-		sbi->s_group_desc[i] = sb_bread_unmovable(sb, block);
-		if (!sbi->s_group_desc[i]) {
+		bh = sb_bread_unmovable(sb, block);
+		if (!bh) {
 			ext4_msg(sb, KERN_ERR,
 			       "can't read group descriptor %d", i);
 			db_count = i;
 			goto failed_mount2;
 		}
+		rcu_read_lock();
+		rcu_dereference(sbi->s_group_desc)[i] = bh;
+		rcu_read_unlock();
 	}
 	sbi->s_gdb_count = db_count;
 	if (!ext4_check_descriptors(sb, logical_sb_block, &first_not_zeroed)) {
@@ -4553,7 +4626,7 @@ no_journal:
 		err = percpu_counter_init(&sbi->s_dirtyclusters_counter, 0,
 					  GFP_KERNEL);
 	if (!err)
-		err = percpu_init_rwsem(&sbi->s_journal_flag_rwsem);
+		err = percpu_init_rwsem(&sbi->s_writepages_rwsem);
 
 	if (err) {
 		ext4_msg(sb, KERN_ERR, "insufficient memory");
@@ -4641,13 +4714,19 @@ failed_mount7:
 	ext4_unregister_li_request(sb);
 failed_mount6:
 	ext4_mb_release(sb);
-	if (sbi->s_flex_groups)
-		kvfree(sbi->s_flex_groups);
+	rcu_read_lock();
+	flex_groups = rcu_dereference(sbi->s_flex_groups);
+	if (flex_groups) {
+		for (i = 0; i < sbi->s_flex_groups_allocated; i++)
+			kvfree(flex_groups[i]);
+		kvfree(flex_groups);
+	}
+	rcu_read_unlock();
 	percpu_counter_destroy(&sbi->s_freeclusters_counter);
 	percpu_counter_destroy(&sbi->s_freeinodes_counter);
 	percpu_counter_destroy(&sbi->s_dirs_counter);
 	percpu_counter_destroy(&sbi->s_dirtyclusters_counter);
-	percpu_free_rwsem(&sbi->s_journal_flag_rwsem);
+	percpu_free_rwsem(&sbi->s_writepages_rwsem);
 failed_mount5:
 	ext4_ext_release(sb);
 	ext4_release_system_zone(sb);
@@ -4676,9 +4755,12 @@ failed_mount3:
 	if (sbi->s_mmp_tsk)
 		kthread_stop(sbi->s_mmp_tsk);
 failed_mount2:
+	rcu_read_lock();
+	group_desc = rcu_dereference(sbi->s_group_desc);
 	for (i = 0; i < db_count; i++)
-		brelse(sbi->s_group_desc[i]);
-	kvfree(sbi->s_group_desc);
+		brelse(group_desc[i]);
+	kvfree(group_desc);
+	rcu_read_unlock();
 failed_mount:
 	if (sbi->s_chksum_driver)
 		crypto_free_shash(sbi->s_chksum_driver);
@@ -5540,9 +5622,12 @@ static int ext4_statfs_project(struct super_block *sb,
 		return PTR_ERR(dquot);
 	spin_lock(&dquot->dq_dqb_lock);
 
-	limit = (dquot->dq_dqb.dqb_bsoftlimit ?
-		 dquot->dq_dqb.dqb_bsoftlimit :
-		 dquot->dq_dqb.dqb_bhardlimit) >> sb->s_blocksize_bits;
+	limit = dquot->dq_dqb.dqb_bsoftlimit;
+	if (dquot->dq_dqb.dqb_bhardlimit &&
+	    (!limit || dquot->dq_dqb.dqb_bhardlimit < limit))
+		limit = dquot->dq_dqb.dqb_bhardlimit;
+	limit >>= sb->s_blocksize_bits;
+
 	if (limit && buf->f_blocks > limit) {
 		curblock = (dquot->dq_dqb.dqb_curspace +
 			    dquot->dq_dqb.dqb_rsvspace) >> sb->s_blocksize_bits;
@@ -5552,9 +5637,11 @@ static int ext4_statfs_project(struct super_block *sb,
 			 (buf->f_blocks - curblock) : 0;
 	}
 
-	limit = dquot->dq_dqb.dqb_isoftlimit ?
-		dquot->dq_dqb.dqb_isoftlimit :
-		dquot->dq_dqb.dqb_ihardlimit;
+	limit = dquot->dq_dqb.dqb_isoftlimit;
+	if (dquot->dq_dqb.dqb_ihardlimit &&
+	    (!limit || dquot->dq_dqb.dqb_ihardlimit < limit))
+		limit = dquot->dq_dqb.dqb_ihardlimit;
+
 	if (limit && buf->f_files > limit) {
 		buf->f_files = limit;
 		buf->f_ffree =
@@ -5987,7 +6074,7 @@ static ssize_t ext4_quota_write(struct super_block *sb, int type,
 		bh = ext4_bread(handle, inode, blk,
 				EXT4_GET_BLOCKS_CREATE |
 				EXT4_GET_BLOCKS_METADATA_NOFAIL);
-	} while (IS_ERR(bh) && (PTR_ERR(bh) == -ENOSPC) &&
+	} while (PTR_ERR(bh) == -ENOSPC &&
 		 ext4_should_retry_alloc(inode->i_sb, &retries));
 	if (IS_ERR(bh))
 		return PTR_ERR(bh);