ext4: Add extsize support

index d8d9aa717a26..090564b6e6d4 100644
@@ -2178,8 +2178,6 @@ static void ext4_mb_use_best_found(struct ext4_allocation_context *ac,
 	 * space in a special descriptor.
 	 */
 	if (ac->ac_o_ex.fe_len < ac->ac_b_ex.fe_len) {
-		/* Aligned allocation doesn't have preallocation support */
-		WARN_ON(ac->ac_flags & EXT4_MB_HINT_ALIGNED);
 		ext4_mb_new_preallocation(ac);
 	}
 

@@ -3024,8 +3022,7 @@ ext4_mb_regular_allocator(struct ext4_allocation_context *ac)
 
 		WARN_ON_ONCE(!is_power_of_2(len));
 		WARN_ON_ONCE(start % len);
-		/* We don't support preallocation yet */
-		WARN_ON_ONCE(ac->ac_b_ex.fe_len != ac->ac_o_ex.fe_len);
+		WARN_ON_ONCE(ac->ac_b_ex.fe_len < ac->ac_o_ex.fe_len);
 	}
 
  exit:

@@ -4474,13 +4471,6 @@ ext4_mb_normalize_request(struct ext4_allocation_context *ac,
 	if (ac->ac_flags & EXT4_MB_HINT_NOPREALLOC)
 		return;
 
-	/*
-	 * caller may have strict alignment requirements. In this case, avoid
-	 * normalization since it is not alignment aware.
-	 */
-	if (ac->ac_flags & EXT4_MB_HINT_ALIGNED)
-		return;
-
 	if (ac->ac_flags & EXT4_MB_HINT_GROUP_ALLOC) {
 		ext4_mb_normalize_group_request(ac);
 		return ;

@@ -4537,6 +4527,21 @@ ext4_mb_normalize_request(struct ext4_allocation_context *ac,
 		size	  = (loff_t) EXT4_C2B(sbi,
 					      ac->ac_o_ex.fe_len) << bsbits;
 	}
+
+	/*
+	 * For aligned allocations, we need to ensure 2 things:
+	 *
+	 * 1. The start should remain same as original start so that finding
+	 * aligned physical blocks for it is straight forward.
+	 *
+	 * 2. The new_size should not be less than the original len. This
+	 * can sometimes happen due to the way we predict size above.
+	 */
+	if (ac->ac_flags & EXT4_MB_HINT_ALIGNED) {
+		start_off = ac->ac_o_ex.fe_logical << bsbits;
+		size = max_t(loff_t, size,
+				 EXT4_C2B(sbi, ac->ac_o_ex.fe_len) << bsbits);
+	}
 	size = size >> bsbits;
 	start = start_off >> bsbits;
 

@@ -4787,32 +4792,46 @@ ext4_mb_check_group_pa(ext4_fsblk_t goal_block,
 }
 
 /*
- * check if found pa meets EXT4_MB_HINT_GOAL_ONLY
+ * check if found pa meets EXT4_MB_HINT_GOAL_ONLY or EXT4_MB_HINT_ALIGNED
  */
 static bool
-ext4_mb_pa_goal_check(struct ext4_allocation_context *ac,
+ext4_mb_pa_check(struct ext4_allocation_context *ac,
 		      struct ext4_prealloc_space *pa)
 {
 	struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb);
 	ext4_fsblk_t start;
 
-	if (likely(!(ac->ac_flags & EXT4_MB_HINT_GOAL_ONLY)))
+	if (likely(!(ac->ac_flags & EXT4_MB_HINT_GOAL_ONLY ||
+		     ac->ac_flags & EXT4_MB_HINT_ALIGNED)))
 		return true;
 
-	/*
-	 * If EXT4_MB_HINT_GOAL_ONLY is set, ac_g_ex will not be adjusted
-	 * in ext4_mb_normalize_request and will keep same with ac_o_ex
-	 * from ext4_mb_initialize_context. Choose ac_g_ex here to keep
-	 * consistent with ext4_mb_find_by_goal.
-	 */
-	start = pa->pa_pstart +
-		(ac->ac_g_ex.fe_logical - pa->pa_lstart);
-	if (ext4_grp_offs_to_block(ac->ac_sb, &ac->ac_g_ex) != start)
-		return false;
+	if (ac->ac_flags & EXT4_MB_HINT_GOAL_ONLY) {
+		/*
+		 * If EXT4_MB_HINT_GOAL_ONLY is set, ac_g_ex will not be adjusted
+		 * in ext4_mb_normalize_request and will keep same with ac_o_ex
+		 * from ext4_mb_initialize_context. Choose ac_g_ex here to keep
+		 * consistent with ext4_mb_find_by_goal.
+		 */
+		start = pa->pa_pstart +
+			(ac->ac_g_ex.fe_logical - pa->pa_lstart);
+		if (ext4_grp_offs_to_block(ac->ac_sb, &ac->ac_g_ex) != start)
+			return false;
 
-	if (ac->ac_g_ex.fe_len > pa->pa_len -
-	    EXT4_B2C(sbi, ac->ac_g_ex.fe_logical - pa->pa_lstart))
-		return false;
+		if (ac->ac_g_ex.fe_len >
+		    pa->pa_len - EXT4_B2C(sbi, ac->ac_g_ex.fe_logical -
+						       pa->pa_lstart))
+			return false;
+	} else if (ac->ac_flags & EXT4_MB_HINT_ALIGNED) {
+		start = pa->pa_pstart +
+			(ac->ac_g_ex.fe_logical - pa->pa_lstart);
+		if (start % EXT4_C2B(sbi, ac->ac_g_ex.fe_len))
+			return false;
+
+		if (EXT4_C2B(sbi, ac->ac_g_ex.fe_len) >
+		    (EXT4_C2B(sbi, pa->pa_len) -
+		     (ac->ac_g_ex.fe_logical - pa->pa_lstart)))
+			return false;
+	}
 
 	return true;
 }

@@ -4835,10 +4854,6 @@ ext4_mb_use_preallocated(struct ext4_allocation_context *ac)
 	if (!(ac->ac_flags & EXT4_MB_HINT_DATA))
 		return false;
 
-	/* using preallocated blocks is not alignment aware. */
-	if (ac->ac_flags & EXT4_MB_HINT_ALIGNED)
-		return false;
-
 	/*
 	 * first, try per-file preallocation by searching the inode pa rbtree.
 	 *

@@ -4944,7 +4959,7 @@ ext4_mb_use_preallocated(struct ext4_allocation_context *ac)
 		goto try_group_pa;
 	}
 
-	if (tmp_pa->pa_free && likely(ext4_mb_pa_goal_check(ac, tmp_pa))) {
+	if (tmp_pa->pa_free && likely(ext4_mb_pa_check(ac, tmp_pa))) {
 		atomic_inc(&tmp_pa->pa_count);
 		ext4_mb_use_inode_pa(ac, tmp_pa);
 		spin_unlock(&tmp_pa->pa_lock);

@@ -4979,6 +4994,19 @@ ext4_mb_use_preallocated(struct ext4_allocation_context *ac)
 		 * pa_free == 0.
 		 */
 		WARN_ON_ONCE(tmp_pa->pa_free == 0);
+
+		/*
+		 * If, for any reason, we reach here then we need to disable PA
+		 * because otherwise ext4_mb_normalize_request() will try to
+		 * allocate a new PA for this logical range where another PA
+		 * already exists. This is not allowed and will trigger BUG_ONs.
+		 * Hence, as a workaround we disable PA.
+		 *
+		 * NOTE: ideally we would want to have some logic to take care
+		 * of the unusable PA. Maybe a more fine grained discard logic
+		 * that could allow us to discard only specific PAs.
+		 */
+		ac->ac_flags |= EXT4_MB_HINT_NOPREALLOC;
 	}
 	spin_unlock(&tmp_pa->pa_lock);
 try_group_pa:

@@ -5785,6 +5813,7 @@ static void ext4_mb_group_or_file(struct ext4_allocation_context *ac)
 	int bsbits = ac->ac_sb->s_blocksize_bits;
 	loff_t size, isize;
 	bool inode_pa_eligible, group_pa_eligible;
+	bool is_aligned = (ac->ac_flags & EXT4_MB_HINT_ALIGNED);
 
 	if (!(ac->ac_flags & EXT4_MB_HINT_DATA))
 		return;

@@ -5792,7 +5821,8 @@ static void ext4_mb_group_or_file(struct ext4_allocation_context *ac)
 	if (unlikely(ac->ac_flags & EXT4_MB_HINT_GOAL_ONLY))
 		return;
 
-	group_pa_eligible = sbi->s_mb_group_prealloc > 0;
+	/* Aligned allocation does not support group pa */
+	group_pa_eligible = (!is_aligned && sbi->s_mb_group_prealloc > 0);
 	inode_pa_eligible = true;
 	size = extent_logical_end(sbi, &ac->ac_o_ex);
 	isize = (i_size_read(ac->ac_inode) + ac->ac_sb->s_blocksize - 1)

index f0f155458697..3233ab89c99e 100644
@@ -3350,7 +3350,8 @@ static struct ext4_ext_path *ext4_split_extent_at(handle_t *handle,
 static struct ext4_ext_path *ext4_split_extent(handle_t *handle,
 					       struct inode *inode,
 					       struct ext4_ext_path *path,
-					       struct ext4_map_blocks *map,
+					       ext4_lblk_t lblk,
+					       unsigned int len,
 					       int split_flag, int flags,
 					       unsigned int *allocated)
 {

@@ -3366,7 +3367,7 @@ static struct ext4_ext_path *ext4_split_extent(handle_t *handle,
 	ee_len = ext4_ext_get_actual_len(ex);
 	unwritten = ext4_ext_is_unwritten(ex);
 
-	if (map->m_lblk + map->m_len < ee_block + ee_len) {
+	if (lblk + len < ee_block + ee_len) {
 		split_flag1 = split_flag & EXT4_EXT_MAY_ZEROOUT;
 		flags1 = flags | EXT4_GET_BLOCKS_PRE_IO;
 		if (unwritten)

@@ -3375,28 +3376,28 @@ static struct ext4_ext_path *ext4_split_extent(handle_t *handle,
 		if (split_flag & EXT4_EXT_DATA_VALID2)
 			split_flag1 |= EXT4_EXT_DATA_VALID1;
 		path = ext4_split_extent_at(handle, inode, path,
-				map->m_lblk + map->m_len, split_flag1, flags1);
+				lblk + len, split_flag1, flags1);
 		if (IS_ERR(path))
 			return path;
 		/*
 		 * Update path is required because previous ext4_split_extent_at
 		 * may result in split of original leaf or extent zeroout.
 		 */
-		path = ext4_find_extent(inode, map->m_lblk, path, flags);
+		path = ext4_find_extent(inode, lblk, path, flags);
 		if (IS_ERR(path))
 			return path;
 		depth = ext_depth(inode);
 		ex = path[depth].p_ext;
 		if (!ex) {
 			EXT4_ERROR_INODE(inode, "unexpected hole at %lu",
-					(unsigned long) map->m_lblk);
+					(unsigned long) lblk);
 			ext4_free_ext_path(path);
 			return ERR_PTR(-EFSCORRUPTED);
 		}
 		unwritten = ext4_ext_is_unwritten(ex);
 	}
 
-	if (map->m_lblk >= ee_block) {
+	if (lblk >= ee_block) {
 		split_flag1 = split_flag & EXT4_EXT_DATA_VALID2;
 		if (unwritten) {
 			split_flag1 |= EXT4_EXT_MARK_UNWRIT1;

@@ -3404,16 +3405,16 @@ static struct ext4_ext_path *ext4_split_extent(handle_t *handle,
 						     EXT4_EXT_MARK_UNWRIT2);
 		}
 		path = ext4_split_extent_at(handle, inode, path,
-				map->m_lblk, split_flag1, flags);
+				lblk, split_flag1, flags);
 		if (IS_ERR(path))
 			return path;
 	}
 
 	if (allocated) {
-		if (map->m_lblk + map->m_len > ee_block + ee_len)
-			*allocated = ee_len - (map->m_lblk - ee_block);
+		if (lblk + len > ee_block + ee_len)
+			*allocated = ee_len - (lblk - ee_block);
 		else
-			*allocated = map->m_len;
+			*allocated = len;
 	}
 	ext4_ext_show_leaf(inode, path);
 	return path;

@@ -3661,8 +3662,8 @@ ext4_ext_convert_to_initialized(handle_t *handle, struct inode *inode,
 	}
 
 fallback:
-	path = ext4_split_extent(handle, inode, path, &split_map, split_flag,
-				 flags, NULL);
+	path = ext4_split_extent(handle, inode, path, split_map.m_lblk,
+				 split_map.m_len, split_flag, flags, NULL);
 	if (IS_ERR(path))
 		return path;
 out:

@@ -3702,11 +3703,11 @@ ext4_ext_convert_to_initialized(handle_t *handle, struct inode *inode,
  * allocated pointer. Return an extent path pointer on success, or an error
  * pointer on failure.
  */
-static struct ext4_ext_path *ext4_split_convert_extents(handle_t *handle,
-					struct inode *inode,
-					struct ext4_map_blocks *map,
-					struct ext4_ext_path *path,
-					int flags, unsigned int *allocated)
+static struct ext4_ext_path *
+ext4_split_convert_extents(handle_t *handle, struct inode *inode,
+			   ext4_lblk_t lblk, unsigned int len,
+			   struct ext4_ext_path *path, int flags,
+			   unsigned int *allocated)
 {
 	ext4_lblk_t eof_block;
 	ext4_lblk_t ee_block;

@@ -3715,12 +3716,12 @@ static struct ext4_ext_path *ext4_split_convert_extents(handle_t *handle,
 	int split_flag = 0, depth;
 
 	ext_debug(inode, "logical block %llu, max_blocks %u\n",
-		  (unsigned long long)map->m_lblk, map->m_len);
+		  (unsigned long long)lblk, len);
 
 	eof_block = (EXT4_I(inode)->i_disksize + inode->i_sb->s_blocksize - 1)
 			>> inode->i_sb->s_blocksize_bits;
-	if (eof_block < map->m_lblk + map->m_len)
-		eof_block = map->m_lblk + map->m_len;
+	if (eof_block < lblk + len)
+		eof_block = lblk + len;
 	/*
 	 * It is safe to convert extent to initialized via explicit
 	 * zeroout only if extent is fully inside i_size or new_size.

@@ -3740,8 +3741,8 @@ static struct ext4_ext_path *ext4_split_convert_extents(handle_t *handle,
 		split_flag |= (EXT4_EXT_MARK_UNWRIT2 | EXT4_EXT_DATA_VALID2);
 	}
 	flags |= EXT4_GET_BLOCKS_PRE_IO;
-	return ext4_split_extent(handle, inode, path, map, split_flag, flags,
-				 allocated);
+	return ext4_split_extent(handle, inode, path, lblk, len, split_flag,
+				 flags, allocated);
 }
 
 static struct ext4_ext_path *

@@ -3776,7 +3777,7 @@ ext4_convert_unwritten_extents_endio(handle_t *handle, struct inode *inode,
 			     inode->i_ino, (unsigned long long)ee_block, ee_len,
 			     (unsigned long long)map->m_lblk, map->m_len);
 #endif
-		path = ext4_split_convert_extents(handle, inode, map, path,
+		path = ext4_split_convert_extents(handle, inode, map->m_lblk, map->m_len, path,
 						EXT4_GET_BLOCKS_CONVERT, NULL);
 		if (IS_ERR(path))
 			return path;

@@ -3840,8 +3841,9 @@ convert_initialized_extent(handle_t *handle, struct inode *inode,
 		  (unsigned long long)ee_block, ee_len);
 
 	if (ee_block != map->m_lblk || ee_len > map->m_len) {
-		path = ext4_split_convert_extents(handle, inode, map, path,
-				EXT4_GET_BLOCKS_CONVERT_UNWRITTEN, NULL);
+		path = ext4_split_convert_extents(
+			handle, inode, map->m_lblk, map->m_len, path,
+			EXT4_GET_BLOCKS_CONVERT_UNWRITTEN, NULL);
 		if (IS_ERR(path))
 			return path;
 

@@ -3912,8 +3914,9 @@ ext4_ext_handle_unwritten_extents(handle_t *handle, struct inode *inode,
 
 	/* get_block() before submitting IO, split the extent */
 	if (flags & EXT4_GET_BLOCKS_PRE_IO) {
-		path = ext4_split_convert_extents(handle, inode, map, path,
-				flags | EXT4_GET_BLOCKS_CONVERT, allocated);
+		path = ext4_split_convert_extents(
+			handle, inode, map->m_lblk, map->m_len, path,
+			flags | EXT4_GET_BLOCKS_CONVERT, allocated);
 		if (IS_ERR(path))
 			return path;
 		/*

index 9ac0a7d4fa0c..7b353d1af580 100644
@@ -222,6 +222,8 @@ enum criteria {
 /* Avg fragment size rb tree lookup succeeded at least once for
  * CR_BEST_AVAIL_LEN */
 #define EXT4_MB_CR_BEST_AVAIL_LEN_OPTIMIZED		0x00020000
+/* mballoc will try to align physical start to length (aka natural alignment) */
+#define EXT4_MB_HINT_ALIGNED		0x40000
 
 struct ext4_allocation_request {
 	/* target inode for block we're allocating */

94 lines not on this page · raw message

index 845451077c41..d5cec574984c 100644
@@ -36,6 +36,7 @@ struct partial_cluster;
 	{ EXT4_MB_STREAM_ALLOC,		"STREAM_ALLOC" },	\
 	{ EXT4_MB_USE_ROOT_BLOCKS,	"USE_ROOT_BLKS" },	\
 	{ EXT4_MB_USE_RESERVED,		"USE_RESV" },		\
+	{ EXT4_MB_HINT_ALIGNED,		"HINT_ALIGNED" }, \
 	{ EXT4_MB_STRICT_CHECK,		"STRICT_CHECK" })
 
 #define show_map_flags(flags) __print_flags(flags, "|",			\

index 7b353d1af580..d00870cb15f2 100644
@@ -1199,6 +1199,8 @@ struct ext4_inode_info {
 	__u32 i_csum_seed;
 
 	kprojid_t i_projid;
+	/* The extentsize hint for the inode in blocks */
+	ext4_grpblk_t i_extsize;
 };
 
 /*

@@ -3081,6 +3083,10 @@ extern void ext4_da_update_reserve_space(struct inode *inode,
 					int used, int quota_claim);
 extern int ext4_issue_zeroout(struct inode *inode, ext4_lblk_t lblk,
 			      ext4_fsblk_t pblk, ext4_lblk_t len);
+int ext4_inode_xattr_get_extsize(struct inode *inode);
+int ext4_inode_xattr_set_extsize(struct inode *inode, ext4_grpblk_t extsize);
+ext4_grpblk_t ext4_inode_get_extsize(struct ext4_inode_info *ei);
+void ext4_inode_set_extsize(struct ext4_inode_info *ei, ext4_grpblk_t extsize);
 
 static inline bool is_special_ino(struct super_block *sb, unsigned long ino)
 {

98 lines not on this page · raw message

146 lines not on this page · raw message

index c7d39da7e733..2237cb2240f8 100644
@@ -1409,6 +1409,7 @@ static struct inode *ext4_alloc_inode(struct super_block *sb)
 	spin_lock_init(&ei->i_completed_io_lock);
 	ei->i_sync_tid = 0;
 	ei->i_datasync_tid = 0;
+	ei->i_extsize = 0;
 	INIT_WORK(&ei->i_rsv_conversion_work, ext4_end_io_rsv_work);
 	ext4_fc_init_inode(&ei->vfs_inode);
 	spin_lock_init(&ei->i_fc_lock);

index 385fbd745e12..1b60e45a593e 100644
@@ -861,7 +861,6 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode,
 		 * ext4_extents.h here?
 		 */
 		int max_unwrit_len = ((1UL << 15) - 1);
-		loff_t end;
 
 		align = orig_map->m_lblk % extsize;
 		len = orig_map->m_len + align;

@@ -870,18 +869,6 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode,
 		extsize_map.m_len =
 			max_t(unsigned int, roundup_pow_of_two(len), extsize);
 
-		/*
-		 * For now allocations beyond EOF don't use extsize hints so
-		 * that we can avoid dealing with extra blocks allocated past
-		 * EOF. We have inode lock since extsize allocations are
-		 * non-delalloc so i_size can be accessed safely
-		 */
-		end = (extsize_map.m_lblk + (loff_t)extsize_map.m_len) << inode->i_blkbits;
-		if (end > inode->i_size) {
-			flags = orig_flags & ~EXT4_GET_BLOCKS_EXTSIZE;
-			goto set_map;
-		}
-
 		/* Fallback to normal allocation if we go beyond max len */
 		if (extsize_map.m_len >= max_unwrit_len) {
 			flags = orig_flags & ~EXT4_GET_BLOCKS_EXTSIZE;

@@ -4011,10 +3998,13 @@ static int ext4_iomap_alloc(struct inode *inode, struct ext4_map_blocks *map,
 	 * i_disksize out to i_size. This could be beyond where direct I/O is
 	 * happening and thus expose allocated blocks to direct I/O reads.
 	 *
-	 * NOTE for extsize hints: We only support it for writes inside
-	 * EOF (for now) to not have to deal with blocks past EOF
+	 * NOTE: For extsize hint based EOF allocations, we still need
+	 * IO_CREATE_EXT flag because we will be allocating more than the write
+	 * hence the extra blocks need to be marked unwritten and split before
+	 * the I/O.
 	 */
-	else if (((loff_t)map->m_lblk << blkbits) >= i_size_read(inode))
+	else if (((loff_t)map->m_lblk << blkbits) >= i_size_read(inode) &&
+		 !ext4_should_use_extsize(inode))
 		m_flags = EXT4_GET_BLOCKS_CREATE;
 	else if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) {
 		m_flags = EXT4_GET_BLOCKS_IO_CREATE_EXT;

index d00870cb15f2..4b69326a0f2f 100644
@@ -746,6 +746,7 @@ enum {
  * Look EXT4_MAP_QUERY_LAST_IN_LEAF.
  */
 #define EXT4_GET_BLOCKS_QUERY_LAST_IN_LEAF	0x1000
+#define EXT4_GET_BLOCKS_EXTSIZE		0x2000
 
 /*
  * The bit position of these flags must not overlap with any of the

@@ -765,7 +766,8 @@ enum {
  */
 #define EXT4_EX_QUERY_FILTER	(EXT4_EX_NOCACHE | EXT4_EX_FORCE_CACHE |\
 				 EXT4_EX_NOFAIL |\
-				 EXT4_GET_BLOCKS_QUERY_LAST_IN_LEAF)
+				 EXT4_GET_BLOCKS_QUERY_LAST_IN_LEAF |\
+				 EXT4_GET_BLOCKS_EXTSIZE)
 
 /*
  * Flags used by ext4_free_blocks

@@ -3755,7 +3757,8 @@ struct ext4_extent;
 extern void ext4_ext_tree_init(handle_t *handle, struct inode *inode);
 extern int ext4_ext_index_trans_blocks(struct inode *inode, int extents);
 extern int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
-			       struct ext4_map_blocks *map, int flags);
+			       struct ext4_map_blocks *orig_map,
+			       struct ext4_map_blocks *extsize_map, int flags);
 extern int ext4_ext_truncate(handle_t *, struct inode *);
 extern int ext4_ext_remove_space(struct inode *inode, ext4_lblk_t start,
 				 ext4_lblk_t end);

index 63d17c5201b5..dbac8d4f7f78 100644
@@ -458,4 +458,19 @@ static inline int ext4_journal_destroy(struct ext4_sb_info *sbi, journal_t *jour
 	return err;
 }
 
+static inline int ext4_should_use_extsize(struct inode *inode)
+{
+	if (!S_ISREG(inode->i_mode))
+		return 0;
+	if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
+		return 0;
+	return (ext4_inode_get_extsize(EXT4_I(inode)) > 0);
+}
+
+static inline int ext4_should_use_unwrit_extents(struct inode *inode)
+{
+	return (ext4_should_dioread_nolock(inode) ||
+		ext4_should_use_extsize(inode));
+}
+
 #endif	/* _EXT4_JBD2_H */

267 lines not on this page · raw message

576 lines not on this page · raw message

index 1b60e45a593e..010ca890b29c 100644
@@ -772,6 +772,41 @@ static inline void ext4_extsize_reset_map(struct ext4_map_blocks *map,
 	map->m_flags = 0;
 }
 
+static int ext4_map_blocks_extsize(handle_t *handle, struct inode *inode,
+		    struct ext4_map_blocks *map, int flags)
+{
+	int orig_mlen = map->m_len;
+	int ret = 0;
+	int tmp_flags;
+
+	WARN_ON(!ext4_inode_get_extsize(EXT4_I(inode)));
+	WARN_ON(!(flags & EXT4_GET_BLOCKS_CREATE_UNWRIT_EXT));
+
+	/*
+	 * First check if there are any existing allocations
+	 */
+	ret = ext4_map_blocks(handle, inode, map, 0);
+	if (ret < 0)
+		return ret;
+
+	/*
+	 * the present mapping fully covers the requested range. In this
+	 * case just go for a non extsize based allocation. Note that we won't
+	 * really be allocating new blocks but the call to ext4_map_blocks is
+	 * important to ensure things like extent splitting and proper map flags
+	 * are taken care of. For all other cases, just let ext4_map_blocks handle
+	 * the allocations
+	 */
+	if (ret > 0 && map->m_len == orig_mlen)
+		tmp_flags = flags & ~EXT4_GET_BLOCKS_EXTSIZE;
+	else
+		tmp_flags = flags;
+
+	ret = ext4_map_blocks(handle, inode, map, tmp_flags);
+
+	return ret;
+}
+
 /*
  * The ext4_map_blocks() function tries to look up the requested blocks,
  * and returns if the blocks are already mapped.

@@ -1153,8 +1188,12 @@ static int _ext4_get_block(struct inode *inode, sector_t iblock,
 	map.m_lblk = iblock;
 	map.m_len = orig_mlen;
 
-	ret = ext4_map_blocks(ext4_journal_current_handle(), inode, &map,
-			      flags);
+	if ((flags & EXT4_GET_BLOCKS_CREATE) && ext4_should_use_extsize(inode))
+		ret = ext4_map_blocks_extsize(ext4_journal_current_handle(), inode,
+				      &map, flags);
+	else
+		ret = ext4_map_blocks(ext4_journal_current_handle(), inode,
+				      &map, flags);
 	if (ret > 0) {
 		map_bh(bh, inode->i_sb, map.m_pblk);
 		ext4_update_bh_state(bh, map.m_flags);

@@ -4016,6 +4055,8 @@ static int ext4_iomap_alloc(struct inode *inode, struct ext4_map_blocks *map,
 	if (flags & IOMAP_ATOMIC)
 		ret = ext4_map_blocks_atomic_write(handle, inode, map, m_flags,
 						   &force_commit);
+	else if (ext4_should_use_extsize(inode))
+		ret = ext4_map_blocks_extsize(handle, inode, map, m_flags);
 	else
 		ret = ext4_map_blocks(handle, inode, map, m_flags);