[PATCH 11/19] ext4: teach ext4_ext_truncate() about the bigalloc feature

[Theodore Ts'o <tytso@mit.edu>]

When we are truncating (as opposed unlinking) a file, we need to worry
about partial truncates of a file, especially in the light of sparse
files.  The changes here make sure that arbitrary truncates of sparse
files works correctly.  Yeah, it's messy.

Note that these functions will need to be revisted when the punch
ioctl is integrated --- in fact this commit will probably have merge
conflicts with the punch changes which Allison Henders and the IBM LTC
have been working on.  I will need to fix this up when either patch
hits mainline.

Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
---
 fs/ext4/extents.c |   82 ++++++++++++++++++++++++++++++++++++++++++++++------
 1 files changed, 72 insertions(+), 10 deletions(-)

diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 2730508..a051adf 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -2156,14 +2156,39 @@ int ext4_ext_index_trans_blocks(struct inode *inode, int nrblocks, int chunk)
 }
 
 static int ext4_remove_blocks(handle_t *handle, struct inode *inode,
-				struct ext4_extent *ex,
-				ext4_lblk_t from, ext4_lblk_t to)
+			      struct ext4_extent *ex,
+			      ext4_fsblk_t *partial_cluster,
+			      ext4_lblk_t from, ext4_lblk_t to)
 {
+	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
 	unsigned short ee_len =  ext4_ext_get_actual_len(ex);
+	ext4_fsblk_t pblk;
 	int flags = EXT4_FREE_BLOCKS_FORGET;
 
 	if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode))
 		flags |= EXT4_FREE_BLOCKS_METADATA;
+	/*
+	 * For bigalloc file systems, we never free a partial cluster
+	 * at the beginning of the extent.  Instead, we make a note
+	 * that we tried freeing the cluster, and check to see if we
+	 * need to free it on a subsequent call to ext4_remove_blocks,
+	 * or at the end of the ext4_truncate() operation.
+	 */
+	flags |= EXT4_FREE_BLOCKS_NOFREE_FIRST_CLUSTER;
+
+	/*
+	 * If we have a partial cluster, and it's different from the
+	 * cluster of the last block, we need to explicitly free the
+	 * partial cluster here.
+	 */
+	pblk = ext4_ext_pblock(ex) + ee_len - 1;
+	if (*partial_cluster && (EXT4_B2C(sbi, pblk) != *partial_cluster)) {
+		ext4_free_blocks(handle, inode, NULL,
+				 EXT4_C2B(sbi, *partial_cluster),
+				 sbi->s_cluster_ratio, flags);
+		*partial_cluster = 0;
+	}
+
 #ifdef EXTENTS_STATS
 	{
 		struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
@@ -2183,12 +2208,24 @@ static int ext4_remove_blocks(handle_t *handle, struct inode *inode,
 	    && to == le32_to_cpu(ex->ee_block) + ee_len - 1) {
 		/* tail removal */
 		ext4_lblk_t num;
-		ext4_fsblk_t start;
 
 		num = le32_to_cpu(ex->ee_block) + ee_len - from;
-		start = ext4_ext_pblock(ex) + ee_len - num;
-		ext_debug("free last %u blocks starting %llu\n", num, start);
-		ext4_free_blocks(handle, inode, NULL, start, num, flags);
+		pblk = ext4_ext_pblock(ex) + ee_len - num;
+		ext_debug("free last %u blocks starting %llu\n", num, pblk);
+		ext4_free_blocks(handle, inode, NULL, pblk, num, flags);
+		/*
+		 * If the block range to be freed didn't start at the
+		 * beginning of a cluster, and we removed the entire
+		 * extent, save the partial cluster here, since we
+		 * might need to delete if we determine that the
+		 * truncate operation has removed all of the blocks in
+		 * the cluster.
+		 */
+		if (pblk & (sbi->s_cluster_ratio - 1) &&
+		    (ee_len == num))
+			*partial_cluster = EXT4_B2C(sbi, pblk);
+		else
+			*partial_cluster = 0;
 	} else if (from == le32_to_cpu(ex->ee_block)
 		   && to <= le32_to_cpu(ex->ee_block) + ee_len - 1) {
 		printk(KERN_INFO "strange request: removal %u-%u from %u:%u\n",
@@ -2203,8 +2240,10 @@ static int ext4_remove_blocks(handle_t *handle, struct inode *inode,
 
 static int
 ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
-		struct ext4_ext_path *path, ext4_lblk_t start)
+		 struct ext4_ext_path *path, ext4_fsblk_t *partial_cluster,
+		 ext4_lblk_t start)
 {
+	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
 	int err = 0, correct_index = 0;
 	int depth = ext_depth(inode), credits;
 	struct ext4_extent_header *eh;
@@ -2291,7 +2330,8 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
 		if (err)
 			goto out;
 
-		err = ext4_remove_blocks(handle, inode, ex, a, b);
+		err = ext4_remove_blocks(handle, inode, ex, partial_cluster,
+					 a, b);
 		if (err)
 			goto out;
 
@@ -2299,7 +2339,8 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
 			/* this extent is removed; mark slot entirely unused */
 			ext4_ext_store_pblock(ex, 0);
 			le16_add_cpu(&eh->eh_entries, -1);
-		}
+		} else
+			*partial_cluster = 0;
 
 		ex->ee_block = cpu_to_le32(block);
 		ex->ee_len = cpu_to_le16(num);
@@ -2324,6 +2365,25 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
 	if (correct_index && eh->eh_entries)
 		err = ext4_ext_correct_indexes(handle, inode, path);
 
+	/*
+	 * If there is still a entry in the leaf node, check to see if
+	 * it references the partial cluster.  This is the only place
+	 * where it could; if it doesn't, we can free the cluster.
+	 */
+	if (*partial_cluster && ex >= EXT_FIRST_EXTENT(eh) &&
+	    (EXT4_B2C(sbi, ext4_ext_pblock(ex) + ex_ee_len - 1) !=
+	     *partial_cluster)) {
+		int flags = EXT4_FREE_BLOCKS_FORGET;
+
+		if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode))
+			flags |= EXT4_FREE_BLOCKS_METADATA;
+
+		ext4_free_blocks(handle, inode, NULL,
+				 EXT4_C2B(sbi, *partial_cluster),
+				 sbi->s_cluster_ratio, flags);
+		*partial_cluster = 0;
+	}
+
 	/* if this leaf is free, then we should
 	 * remove it from index block above */
 	if (err == 0 && eh->eh_entries == 0 && path[depth].p_bh != NULL)
@@ -2359,6 +2419,7 @@ static int ext4_ext_remove_space(struct inode *inode, ext4_lblk_t start)
 	struct super_block *sb = inode->i_sb;
 	int depth = ext_depth(inode);
 	struct ext4_ext_path *path;
+	ext4_fsblk_t partial_cluster = 0;
 	handle_t *handle;
 	int i, err;
 
@@ -2393,7 +2454,8 @@ again:
 	while (i >= 0 && err == 0) {
 		if (i == depth) {
 			/* this is leaf block */
-			err = ext4_ext_rm_leaf(handle, inode, path, start);
+			err = ext4_ext_rm_leaf(handle, inode, path,
+					       &partial_cluster, start);
 			/* root level has p_bh == NULL, brelse() eats this */
 			brelse(path[i].p_bh);
 			path[i].p_bh = NULL;
-- 
1.7.3.1