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, 198 insertions, 8 deletions

diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 74a48d6ff9cc..85abbfb98cbe 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -1502,14 +1502,16 @@ static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b,
 
 		blocknr = ext4_group_first_block_no(sb, e4b->bd_group);
 		blocknr += EXT4_C2B(sbi, block);
-		ext4_grp_locked_error(sb, e4b->bd_group,
-				      inode ? inode->i_ino : 0,
-				      blocknr,
-				      "freeing already freed block "
-				      "(bit %u); block bitmap corrupt.",
-				      block);
-		ext4_mark_group_bitmap_corrupted(sb, e4b->bd_group,
+		if (!(sbi->s_mount_state & EXT4_FC_REPLAY)) {
+			ext4_grp_locked_error(sb, e4b->bd_group,
+					      inode ? inode->i_ino : 0,
+					      blocknr,
+					      "freeing already freed block (bit %u); block bitmap corrupt.",
+					      block);
+			ext4_mark_group_bitmap_corrupted(
+				sb, e4b->bd_group,
 				EXT4_GROUP_INFO_BBITMAP_CORRUPT);
+		}
 		mb_regenerate_buddy(e4b);
 		goto done;
 	}
@@ -3297,6 +3299,84 @@ out_err:
 }
 
 /*
+ * Idempotent helper for Ext4 fast commit replay path to set the state of
+ * blocks in bitmaps and update counters.
+ */
+void ext4_mb_mark_bb(struct super_block *sb, ext4_fsblk_t block,
+			int len, int state)
+{
+	struct buffer_head *bitmap_bh = NULL;
+	struct ext4_group_desc *gdp;
+	struct buffer_head *gdp_bh;
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	ext4_group_t group;
+	ext4_grpblk_t blkoff;
+	int i, clen, err;
+	int already;
+
+	clen = EXT4_B2C(sbi, len);
+
+	ext4_get_group_no_and_offset(sb, block, &group, &blkoff);
+	bitmap_bh = ext4_read_block_bitmap(sb, group);
+	if (IS_ERR(bitmap_bh)) {
+		err = PTR_ERR(bitmap_bh);
+		bitmap_bh = NULL;
+		goto out_err;
+	}
+
+	err = -EIO;
+	gdp = ext4_get_group_desc(sb, group, &gdp_bh);
+	if (!gdp)
+		goto out_err;
+
+	ext4_lock_group(sb, group);
+	already = 0;
+	for (i = 0; i < clen; i++)
+		if (!mb_test_bit(blkoff + i, bitmap_bh->b_data) == !state)
+			already++;
+
+	if (state)
+		ext4_set_bits(bitmap_bh->b_data, blkoff, clen);
+	else
+		mb_test_and_clear_bits(bitmap_bh->b_data, blkoff, clen);
+	if (ext4_has_group_desc_csum(sb) &&
+	    (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT))) {
+		gdp->bg_flags &= cpu_to_le16(~EXT4_BG_BLOCK_UNINIT);
+		ext4_free_group_clusters_set(sb, gdp,
+					     ext4_free_clusters_after_init(sb,
+						group, gdp));
+	}
+	if (state)
+		clen = ext4_free_group_clusters(sb, gdp) - clen + already;
+	else
+		clen = ext4_free_group_clusters(sb, gdp) + clen - already;
+
+	ext4_free_group_clusters_set(sb, gdp, clen);
+	ext4_block_bitmap_csum_set(sb, group, gdp, bitmap_bh);
+	ext4_group_desc_csum_set(sb, group, gdp);
+
+	ext4_unlock_group(sb, group);
+
+	if (sbi->s_log_groups_per_flex) {
+		ext4_group_t flex_group = ext4_flex_group(sbi, group);
+
+		atomic64_sub(len,
+			     &sbi_array_rcu_deref(sbi, s_flex_groups,
+						  flex_group)->free_clusters);
+	}
+
+	err = ext4_handle_dirty_metadata(NULL, NULL, bitmap_bh);
+	if (err)
+		goto out_err;
+	sync_dirty_buffer(bitmap_bh);
+	err = ext4_handle_dirty_metadata(NULL, NULL, gdp_bh);
+	sync_dirty_buffer(gdp_bh);
+
+out_err:
+	brelse(bitmap_bh);
+}
+
+/*
  * here we normalize request for locality group
  * Group request are normalized to s_mb_group_prealloc, which goes to
  * s_strip if we set the same via mount option.
@@ -4272,6 +4352,9 @@ void ext4_discard_preallocations(struct inode *inode, unsigned int needed)
 		return;
 	}
 
+	if (EXT4_SB(sb)->s_mount_state & EXT4_FC_REPLAY)
+		return;
+
 	mb_debug(sb, "discard preallocation for inode %lu\n",
 		 inode->i_ino);
 	trace_ext4_discard_preallocations(inode,
@@ -4819,6 +4902,9 @@ out_dbg:
 	return ret;
 }
 
+static ext4_fsblk_t ext4_mb_new_blocks_simple(handle_t *handle,
+				struct ext4_allocation_request *ar, int *errp);
+
 /*
  * Main entry point into mballoc to allocate blocks
  * it tries to use preallocation first, then falls back
@@ -4840,6 +4926,8 @@ ext4_fsblk_t ext4_mb_new_blocks(handle_t *handle,
 	sbi = EXT4_SB(sb);
 
 	trace_ext4_request_blocks(ar);
+	if (sbi->s_mount_state & EXT4_FC_REPLAY)
+		return ext4_mb_new_blocks_simple(handle, ar, errp);
 
 	/* Allow to use superuser reservation for quota file */
 	if (ext4_is_quota_file(ar->inode))
@@ -5067,6 +5155,102 @@ ext4_mb_free_metadata(handle_t *handle, struct ext4_buddy *e4b,
 	return 0;
 }
 
+/*
+ * Simple allocator for Ext4 fast commit replay path. It searches for blocks
+ * linearly starting at the goal block and also excludes the blocks which
+ * are going to be in use after fast commit replay.
+ */
+static ext4_fsblk_t ext4_mb_new_blocks_simple(handle_t *handle,
+				struct ext4_allocation_request *ar, int *errp)
+{
+	struct buffer_head *bitmap_bh;
+	struct super_block *sb = ar->inode->i_sb;
+	ext4_group_t group;
+	ext4_grpblk_t blkoff;
+	int  i;
+	ext4_fsblk_t goal, block;
+	struct ext4_super_block *es = EXT4_SB(sb)->s_es;
+
+	goal = ar->goal;
+	if (goal < le32_to_cpu(es->s_first_data_block) ||
+			goal >= ext4_blocks_count(es))
+		goal = le32_to_cpu(es->s_first_data_block);
+
+	ar->len = 0;
+	ext4_get_group_no_and_offset(sb, goal, &group, &blkoff);
+	for (; group < ext4_get_groups_count(sb); group++) {
+		bitmap_bh = ext4_read_block_bitmap(sb, group);
+		if (IS_ERR(bitmap_bh)) {
+			*errp = PTR_ERR(bitmap_bh);
+			pr_warn("Failed to read block bitmap\n");
+			return 0;
+		}
+
+		ext4_get_group_no_and_offset(sb,
+			max(ext4_group_first_block_no(sb, group), goal),
+			NULL, &blkoff);
+		i = mb_find_next_zero_bit(bitmap_bh->b_data, sb->s_blocksize,
+						blkoff);
+		brelse(bitmap_bh);
+		if (i >= sb->s_blocksize)
+			continue;
+		if (ext4_fc_replay_check_excluded(sb,
+			ext4_group_first_block_no(sb, group) + i))
+			continue;
+		break;
+	}
+
+	if (group >= ext4_get_groups_count(sb) && i >= sb->s_blocksize)
+		return 0;
+
+	block = ext4_group_first_block_no(sb, group) + i;
+	ext4_mb_mark_bb(sb, block, 1, 1);
+	ar->len = 1;
+
+	return block;
+}
+
+static void ext4_free_blocks_simple(struct inode *inode, ext4_fsblk_t block,
+					unsigned long count)
+{
+	struct buffer_head *bitmap_bh;
+	struct super_block *sb = inode->i_sb;
+	struct ext4_group_desc *gdp;
+	struct buffer_head *gdp_bh;
+	ext4_group_t group;
+	ext4_grpblk_t blkoff;
+	int already_freed = 0, err, i;
+
+	ext4_get_group_no_and_offset(sb, block, &group, &blkoff);
+	bitmap_bh = ext4_read_block_bitmap(sb, group);
+	if (IS_ERR(bitmap_bh)) {
+		err = PTR_ERR(bitmap_bh);
+		pr_warn("Failed to read block bitmap\n");
+		return;
+	}
+	gdp = ext4_get_group_desc(sb, group, &gdp_bh);
+	if (!gdp)
+		return;
+
+	for (i = 0; i < count; i++) {
+		if (!mb_test_bit(blkoff + i, bitmap_bh->b_data))
+			already_freed++;
+	}
+	mb_clear_bits(bitmap_bh->b_data, blkoff, count);
+	err = ext4_handle_dirty_metadata(NULL, NULL, bitmap_bh);
+	if (err)
+		return;
+	ext4_free_group_clusters_set(
+		sb, gdp, ext4_free_group_clusters(sb, gdp) +
+		count - already_freed);
+	ext4_block_bitmap_csum_set(sb, group, gdp, bitmap_bh);
+	ext4_group_desc_csum_set(sb, group, gdp);
+	ext4_handle_dirty_metadata(NULL, NULL, gdp_bh);
+	sync_dirty_buffer(bitmap_bh);
+	sync_dirty_buffer(gdp_bh);
+	brelse(bitmap_bh);
+}
+
 /**
  * ext4_free_blocks() -- Free given blocks and update quota
  * @handle:		handle for this transaction
@@ -5093,6 +5277,13 @@ void ext4_free_blocks(handle_t *handle, struct inode *inode,
 	int err = 0;
 	int ret;
 
+	sbi = EXT4_SB(sb);
+
+	if (sbi->s_mount_state & EXT4_FC_REPLAY) {
+		ext4_free_blocks_simple(inode, block, count);
+		return;
+	}
+
 	might_sleep();
 	if (bh) {
 		if (block)
@@ -5101,7 +5292,6 @@ void ext4_free_blocks(handle_t *handle, struct inode *inode,
 			block = bh->b_blocknr;
 	}
 
-	sbi = EXT4_SB(sb);
 	if (!(flags & EXT4_FREE_BLOCKS_VALIDATED) &&
 	    !ext4_inode_block_valid(inode, block, count)) {
 		ext4_error(sb, "Freeing blocks not in datazone - "