ext4: fast commit recovery path

This patch adds fast commit recovery path support for Ext4 file
system. We add several helper functions that are similar in spirit to
e2fsprogs journal recovery path handlers. Example of such functions
include - a simple block allocator, idempotent block bitmap update
function etc. Using these routines and the fast commit log in the fast
commit area, the recovery path (ext4_fc_replay()) performs fast commit
log recovery.

Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Harshad Shirwadkar <harshadshirwadkar@gmail.com>
Link: https://lore.kernel.org/r/20201015203802.3597742-8-harshadshirwadkar@gmail.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>

1 files changed, 63 insertions, 26 deletions

diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 7da82b6fdb74..43d6a07262d2 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -101,8 +101,8 @@ static int ext4_inode_csum_verify(struct inode *inode, struct ext4_inode *raw,
 	return provided == calculated;
 }
 
-static void ext4_inode_csum_set(struct inode *inode, struct ext4_inode *raw,
-				struct ext4_inode_info *ei)
+void ext4_inode_csum_set(struct inode *inode, struct ext4_inode *raw,
+			 struct ext4_inode_info *ei)
 {
 	__u32 csum;
 
@@ -514,7 +514,8 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode,
 		return -EFSCORRUPTED;
 
 	/* Lookup extent status tree firstly */
-	if (ext4_es_lookup_extent(inode, map->m_lblk, NULL, &es)) {
+	if (!(EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY) &&
+	    ext4_es_lookup_extent(inode, map->m_lblk, NULL, &es)) {
 		if (ext4_es_is_written(&es) || ext4_es_is_unwritten(&es)) {
 			map->m_pblk = ext4_es_pblock(&es) +
 					map->m_lblk - es.es_lblk;
@@ -827,7 +828,8 @@ struct buffer_head *ext4_getblk(handle_t *handle, struct inode *inode,
 	int create = map_flags & EXT4_GET_BLOCKS_CREATE;
 	int err;
 
-	J_ASSERT(handle != NULL || create == 0);
+	J_ASSERT((EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY)
+		 || handle != NULL || create == 0);
 
 	map.m_lblk = block;
 	map.m_len = 1;
@@ -843,7 +845,8 @@ struct buffer_head *ext4_getblk(handle_t *handle, struct inode *inode,
 		return ERR_PTR(-ENOMEM);
 	if (map.m_flags & EXT4_MAP_NEW) {
 		J_ASSERT(create != 0);
-		J_ASSERT(handle != NULL);
+		J_ASSERT((EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY)
+			 || (handle != NULL));
 
 		/*
 		 * Now that we do not always journal data, we should
@@ -4284,22 +4287,22 @@ out_trace:
  * data in memory that is needed to recreate the on-disk version of this
  * inode.
  */
-static int __ext4_get_inode_loc(struct inode *inode,
-				struct ext4_iloc *iloc, int in_mem)
+static int __ext4_get_inode_loc(struct super_block *sb, unsigned long ino,
+				struct ext4_iloc *iloc, int in_mem,
+				ext4_fsblk_t *ret_block)
 {
 	struct ext4_group_desc	*gdp;
 	struct buffer_head	*bh;
-	struct super_block	*sb = inode->i_sb;
 	ext4_fsblk_t		block;
 	struct blk_plug		plug;
 	int			inodes_per_block, inode_offset;
 
 	iloc->bh = NULL;
-	if (inode->i_ino < EXT4_ROOT_INO ||
-	    inode->i_ino > le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count))
+	if (ino < EXT4_ROOT_INO ||
+	    ino > le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count))
 		return -EFSCORRUPTED;
 
-	iloc->block_group = (inode->i_ino - 1) / EXT4_INODES_PER_GROUP(sb);
+	iloc->block_group = (ino - 1) / EXT4_INODES_PER_GROUP(sb);
 	gdp = ext4_get_group_desc(sb, iloc->block_group, NULL);
 	if (!gdp)
 		return -EIO;
@@ -4308,7 +4311,7 @@ static int __ext4_get_inode_loc(struct inode *inode,
 	 * Figure out the offset within the block group inode table
 	 */
 	inodes_per_block = EXT4_SB(sb)->s_inodes_per_block;
-	inode_offset = ((inode->i_ino - 1) %
+	inode_offset = ((ino - 1) %
 			EXT4_INODES_PER_GROUP(sb));
 	block = ext4_inode_table(sb, gdp) + (inode_offset / inodes_per_block);
 	iloc->offset = (inode_offset % inodes_per_block) * EXT4_INODE_SIZE(sb);
@@ -4400,14 +4403,14 @@ make_io:
 		 * has in-inode xattrs, or we don't have this inode in memory.
 		 * Read the block from disk.
 		 */
-		trace_ext4_load_inode(inode);
+		trace_ext4_load_inode(sb, ino);
 		ext4_read_bh_nowait(bh, REQ_META | REQ_PRIO, NULL);
 		blk_finish_plug(&plug);
 		wait_on_buffer(bh);
 		if (!buffer_uptodate(bh)) {
 		simulate_eio:
-			ext4_error_inode_block(inode, block, EIO,
-					       "unable to read itable block");
+			if (ret_block)
+				*ret_block = block;
 			brelse(bh);
 			return -EIO;
 		}
@@ -4417,11 +4420,43 @@ has_buffer:
 	return 0;
 }
 
+static int __ext4_get_inode_loc_noinmem(struct inode *inode,
+					struct ext4_iloc *iloc)
+{
+	ext4_fsblk_t err_blk;
+	int ret;
+
+	ret = __ext4_get_inode_loc(inode->i_sb, inode->i_ino, iloc, 0,
+					&err_blk);
+
+	if (ret == -EIO)
+		ext4_error_inode_block(inode, err_blk, EIO,
+					"unable to read itable block");
+
+	return ret;
+}
+
 int ext4_get_inode_loc(struct inode *inode, struct ext4_iloc *iloc)
 {
+	ext4_fsblk_t err_blk;
+	int ret;
+
 	/* We have all inode data except xattrs in memory here. */
-	return __ext4_get_inode_loc(inode, iloc,
-		!ext4_test_inode_state(inode, EXT4_STATE_XATTR));
+	ret = __ext4_get_inode_loc(inode->i_sb, inode->i_ino, iloc,
+		!ext4_test_inode_state(inode, EXT4_STATE_XATTR), &err_blk);
+
+	if (ret == -EIO)
+		ext4_error_inode_block(inode, err_blk, EIO,
+					"unable to read itable block");
+
+	return ret;
+}
+
+
+int ext4_get_fc_inode_loc(struct super_block *sb, unsigned long ino,
+			  struct ext4_iloc *iloc)
+{
+	return __ext4_get_inode_loc(sb, ino, iloc, 0, NULL);
 }
 
 static bool ext4_should_enable_dax(struct inode *inode)
@@ -4587,7 +4622,7 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino,
 	ei = EXT4_I(inode);
 	iloc.bh = NULL;
 
-	ret = __ext4_get_inode_loc(inode, &iloc, 0);
+	ret = __ext4_get_inode_loc_noinmem(inode, &iloc);
 	if (ret < 0)
 		goto bad_inode;
 	raw_inode = ext4_raw_inode(&iloc);
@@ -4633,10 +4668,11 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino,
 					      sizeof(gen));
 	}
 
-	if (!ext4_inode_csum_verify(inode, raw_inode, ei) ||
-	    ext4_simulate_fail(sb, EXT4_SIM_INODE_CRC)) {
-		ext4_error_inode_err(inode, function, line, 0, EFSBADCRC,
-				     "iget: checksum invalid");
+	if ((!ext4_inode_csum_verify(inode, raw_inode, ei) ||
+	    ext4_simulate_fail(sb, EXT4_SIM_INODE_CRC)) &&
+	     (!(EXT4_SB(sb)->s_mount_state & EXT4_FC_REPLAY))) {
+		ext4_error_inode_err(inode, function, line, 0,
+				EFSBADCRC, "iget: checksum invalid");
 		ret = -EFSBADCRC;
 		goto bad_inode;
 	}
@@ -4790,9 +4826,10 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino,
 		goto bad_inode;
 	} else if (!ext4_has_inline_data(inode)) {
 		/* validate the block references in the inode */
-		if (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
-		   (S_ISLNK(inode->i_mode) &&
-		    !ext4_inode_is_fast_symlink(inode))) {
+		if (!(EXT4_SB(sb)->s_mount_state & EXT4_FC_REPLAY) &&
+			(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
+			(S_ISLNK(inode->i_mode) &&
+			!ext4_inode_is_fast_symlink(inode)))) {
 			if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
 				ret = ext4_ext_check_inode(inode);
 			else
@@ -5176,7 +5213,7 @@ int ext4_write_inode(struct inode *inode, struct writeback_control *wbc)
 	} else {
 		struct ext4_iloc iloc;
 
-		err = __ext4_get_inode_loc(inode, &iloc, 0);
+		err = __ext4_get_inode_loc_noinmem(inode, &iloc);
 		if (err)
 			return err;
 		/*