Change on-disk format to support 2^15 uninitialized extents

This change was suggested by Andreas Dilger. 
This patch changes the EXT_MAX_LEN value and extent code which marks/checks
uninitialized extents. With this change it will be possible to have
initialized extents with 2^15 blocks (earlier the max blocks we could have
was 2^15 - 1). This way we can have better extent-to-block alignment.
Now, maximum number of blocks we can have in an initialized extent is 2^15
and in an uninitialized extent is 2^15 - 1.

Signed-off-by: Amit Arora <aarora@in.ibm.com>

2 files changed, 52 insertions, 7 deletions

diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index ded3d469f978..77146b826a13 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -1107,7 +1107,7 @@ static int
 ext4_can_extents_be_merged(struct inode *inode, struct ext4_extent *ex1,
                                 struct ext4_extent *ex2)
 {
-        unsigned short ext1_ee_len, ext2_ee_len;
+        unsigned short ext1_ee_len, ext2_ee_len, max_len;
 
         /*
          * Make sure that either both extents are uninitialized, or
@@ -1116,6 +1116,11 @@ ext4_can_extents_be_merged(struct inode *inode, struct ext4_extent *ex1,
         if (ext4_ext_is_uninitialized(ex1) ^ ext4_ext_is_uninitialized(ex2))
                 return 0;
 
+        if (ext4_ext_is_uninitialized(ex1))
+                max_len = EXT_UNINIT_MAX_LEN;
+        else
+                max_len = EXT_INIT_MAX_LEN;
+
         ext1_ee_len = ext4_ext_get_actual_len(ex1);
         ext2_ee_len = ext4_ext_get_actual_len(ex2);
 
@@ -1128,7 +1133,7 @@ ext4_can_extents_be_merged(struct inode *inode, struct ext4_extent *ex1,
          * as an RO_COMPAT feature, refuse to merge to extents if
          * this can result in the top bit of ee_len being set.
          */
-        if (ext1_ee_len + ext2_ee_len > EXT_MAX_LEN)
+        if (ext1_ee_len + ext2_ee_len > max_len)
                 return 0;
 #ifdef AGGRESSIVE_TEST
         if (le16_to_cpu(ex1->ee_len) >= 4)
@@ -1815,7 +1820,11 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
 
                 ex->ee_block = cpu_to_le32(block);
                 ex->ee_len = cpu_to_le16(num);
-                if (uninitialized)
+                /*
+                 * Do not mark uninitialized if all the blocks in the
+                 * extent have been removed.
+                 */
+                if (uninitialized && num)
                         ext4_ext_mark_uninitialized(ex);
 
                 err = ext4_ext_dirty(handle, inode, path + depth);
@@ -2308,6 +2317,19 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
         /* allocate new block */
         goal = ext4_ext_find_goal(inode, path, iblock);
 
+        /*
+         * See if request is beyond maximum number of blocks we can have in
+         * a single extent. For an initialized extent this limit is
+         * EXT_INIT_MAX_LEN and for an uninitialized extent this limit is
+         * EXT_UNINIT_MAX_LEN.
+         */
+        if (max_blocks > EXT_INIT_MAX_LEN &&
+            create != EXT4_CREATE_UNINITIALIZED_EXT)
+                max_blocks = EXT_INIT_MAX_LEN;
+        else if (max_blocks > EXT_UNINIT_MAX_LEN &&
+                 create == EXT4_CREATE_UNINITIALIZED_EXT)
+                max_blocks = EXT_UNINIT_MAX_LEN;
+
         /* Check if we can really insert (iblock)::(iblock+max_blocks) extent */
         newex.ee_block = cpu_to_le32(iblock);
         newex.ee_len = cpu_to_le16(max_blocks);
diff --git a/include/linux/ext4_fs_extents.h b/include/linux/ext4_fs_extents.h
index edf49ec89eac..81406f3655d4 100644
--- a/include/linux/ext4_fs_extents.h
+++ b/include/linux/ext4_fs_extents.h
@@ -141,7 +141,25 @@ typedef int (*ext_prepare_callback)(struct inode *, struct ext4_ext_path *,
 
 #define EXT_MAX_BLOCK   0xffffffff
 
-#define EXT_MAX_LEN     ((1UL << 15) - 1)
+/*
+ * EXT_INIT_MAX_LEN is the maximum number of blocks we can have in an
+ * initialized extent. This is 2^15 and not (2^16 - 1), since we use the
+ * MSB of ee_len field in the extent datastructure to signify if this
+ * particular extent is an initialized extent or an uninitialized (i.e.
+ * preallocated).
+ * EXT_UNINIT_MAX_LEN is the maximum number of blocks we can have in an
+ * uninitialized extent.
+ * If ee_len is <= 0x8000, it is an initialized extent. Otherwise, it is an
+ * uninitialized one. In other words, if MSB of ee_len is set, it is an
+ * uninitialized extent with only one special scenario when ee_len = 0x8000.
+ * In this case we can not have an uninitialized extent of zero length and
+ * thus we make it as a special case of initialized extent with 0x8000 length.
+ * This way we get better extent-to-group alignment for initialized extents.
+ * Hence, the maximum number of blocks we can have in an *initialized*
+ * extent is 2^15 (32768) and in an *uninitialized* extent is 2^15-1 (32767).
+ */
+#define EXT_INIT_MAX_LEN        (1UL << 15)
+#define EXT_UNINIT_MAX_LEN      (EXT_INIT_MAX_LEN - 1)
 
 
 #define EXT_FIRST_EXTENT(__hdr__) \
@@ -190,17 +208,22 @@ ext4_ext_invalidate_cache(struct inode *inode)
 
 static inline void ext4_ext_mark_uninitialized(struct ext4_extent *ext)
 {
-        ext->ee_len |= cpu_to_le16(0x8000);
+        /* We can not have an uninitialized extent of zero length! */
+        BUG_ON((le16_to_cpu(ext->ee_len) & ~EXT_INIT_MAX_LEN) == 0);
+        ext->ee_len |= cpu_to_le16(EXT_INIT_MAX_LEN);
 }
 
 static inline int ext4_ext_is_uninitialized(struct ext4_extent *ext)
 {
-        return (int)(le16_to_cpu((ext)->ee_len) & 0x8000);
+        /* Extent with ee_len of 0x8000 is treated as an initialized extent */
+        return (le16_to_cpu(ext->ee_len) > EXT_INIT_MAX_LEN);
 }
 
 static inline int ext4_ext_get_actual_len(struct ext4_extent *ext)
 {
-        return (int)(le16_to_cpu((ext)->ee_len) & 0x7FFF);
+        return (le16_to_cpu(ext->ee_len) <= EXT_INIT_MAX_LEN ?
+                le16_to_cpu(ext->ee_len) :
+                (le16_to_cpu(ext->ee_len) - EXT_INIT_MAX_LEN));
 }
 
 extern int ext4_extent_tree_init(handle_t *, struct inode *);