ext4: rework bigalloc reserved cluster accounting

index caff935fbeb8..ad2c215720be 100644
@@ -3142,10 +3142,6 @@ extern struct ext4_ext_path *ext4_find_extent(struct inode *, ext4_lblk_t,
 					      int flags);
 extern void ext4_ext_drop_refs(struct ext4_ext_path *);
 extern int ext4_ext_check_inode(struct inode *inode);
-extern int ext4_find_delalloc_range(struct inode *inode,
-				    ext4_lblk_t lblk_start,
-				    ext4_lblk_t lblk_end);
-extern int ext4_find_delalloc_cluster(struct inode *inode, ext4_lblk_t lblk);
 extern ext4_lblk_t ext4_ext_next_allocated_block(struct ext4_ext_path *path);
 extern int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 			__u64 start, __u64 len);

88 lines not on this page · raw message

189 lines not on this page · raw message

index 8efdeb903d6b..df9628c3ec3b 100644
@@ -90,11 +90,18 @@ extern void ext4_es_cache_extent(struct inode *inode, ext4_lblk_t lblk,
 				 unsigned int status);
 extern int ext4_es_remove_extent(struct inode *inode, ext4_lblk_t lblk,
 				 ext4_lblk_t len);
-extern void ext4_es_find_delayed_extent_range(struct inode *inode,
-					ext4_lblk_t lblk, ext4_lblk_t end,
-					struct extent_status *es);
+extern void ext4_es_find_extent_range(struct inode *inode,
+				      int (*match_fn)(struct extent_status *es),
+				      ext4_lblk_t lblk, ext4_lblk_t end,
+				      struct extent_status *es);
 extern int ext4_es_lookup_extent(struct inode *inode, ext4_lblk_t lblk,
 				 struct extent_status *es);
+extern bool ext4_es_scan_range(struct inode *inode,
+			       int (*matching_fn)(struct extent_status *es),
+			       ext4_lblk_t lblk, ext4_lblk_t end);
+extern bool ext4_es_scan_clu(struct inode *inode,
+			     int (*matching_fn)(struct extent_status *es),
+			     ext4_lblk_t lblk);
 
 static inline unsigned int ext4_es_status(struct extent_status *es)
 {

index d767e993591d..b83bf3308b5e 100644
@@ -577,8 +577,8 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode,
 				EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN;
 		if (!(flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) &&
 		    !(status & EXTENT_STATUS_WRITTEN) &&
-		    ext4_find_delalloc_range(inode, map->m_lblk,
-					     map->m_lblk + map->m_len - 1))
+		    ext4_es_scan_range(inode, &ext4_es_is_delayed, map->m_lblk,
+				       map->m_lblk + map->m_len - 1))
 			status |= EXTENT_STATUS_DELAYED;
 		ret = ext4_es_insert_extent(inode, map->m_lblk,
 					    map->m_len, map->m_pblk, status);

@@ -701,8 +701,8 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode,
 				EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN;
 		if (!(flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) &&
 		    !(status & EXTENT_STATUS_WRITTEN) &&
-		    ext4_find_delalloc_range(inode, map->m_lblk,
-					     map->m_lblk + map->m_len - 1))
+		    ext4_es_scan_range(inode, &ext4_es_is_delayed, map->m_lblk,
+				       map->m_lblk + map->m_len - 1))
 			status |= EXTENT_STATUS_DELAYED;
 		ret = ext4_es_insert_extent(inode, map->m_lblk, map->m_len,
 					    map->m_pblk, status);

@@ -1681,7 +1681,7 @@ static void ext4_da_page_release_reservation(struct page *page,
 		lblk = (page->index << (PAGE_SHIFT - inode->i_blkbits)) +
 			((num_clusters - 1) << sbi->s_cluster_bits);
 		if (sbi->s_cluster_ratio == 1 ||
-		    !ext4_find_delalloc_cluster(inode, lblk))
+		    !ext4_es_scan_clu(inode, &ext4_es_is_delayed, lblk))
 			ext4_da_release_space(inode, 1);
 
 		num_clusters--;

@@ -1859,6 +1859,7 @@ static int ext4_da_map_blocks(struct inode *inode, sector_t iblock,
 add_delayed:
 	if (retval == 0) {
 		int ret;
+
 		/*
 		 * XXX: __block_prepare_write() unmaps passed block,
 		 * is it OK?

@@ -1869,7 +1870,8 @@ static int ext4_da_map_blocks(struct inode *inode, sector_t iblock,
 		 * to reserve metadata for every block we're going to write.
 		 */
 		if (EXT4_SB(inode->i_sb)->s_cluster_ratio == 1 ||
-		    !ext4_find_delalloc_cluster(inode, map->m_lblk)) {
+		    !ext4_es_scan_clu(inode,
+				      &ext4_es_is_delayed, map->m_lblk)) {
 			ret = ext4_da_reserve_space(inode);
 			if (ret) {
 				/* not enough space to reserve */

@@ -3450,7 +3452,8 @@ static int ext4_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
 			ext4_lblk_t end = map.m_lblk + map.m_len - 1;
 			struct extent_status es;
 
-			ext4_es_find_delayed_extent_range(inode, map.m_lblk, end, &es);
+			ext4_es_find_extent_range(inode, &ext4_es_is_delayed,
+						  map.m_lblk, end, &es);
 
 			if (!es.es_len || es.es_lblk > end) {
 				/* entire range is a hole */

index 0e31eb136c57..7849b7f8fd9d 100644
@@ -2270,7 +2270,7 @@ TRACE_EVENT(ext4_es_remove_extent,
 		  __entry->lblk, __entry->len)
 );
 
-TRACE_EVENT(ext4_es_find_delayed_extent_range_enter,
+TRACE_EVENT(ext4_es_find_extent_range_enter,
 	TP_PROTO(struct inode *inode, ext4_lblk_t lblk),
 
 	TP_ARGS(inode, lblk),

@@ -2292,7 +2292,7 @@ TRACE_EVENT(ext4_es_find_delayed_extent_range_enter,
 		  (unsigned long) __entry->ino, __entry->lblk)
 );
 
-TRACE_EVENT(ext4_es_find_delayed_extent_range_exit,
+TRACE_EVENT(ext4_es_find_extent_range_exit,
 	TP_PROTO(struct inode *inode, struct extent_status *es),
 
 	TP_ARGS(inode, es),

index ad2c215720be..fc0f41dbf90b 100644
@@ -1030,6 +1030,9 @@ struct ext4_inode_info {
 	ext4_lblk_t i_da_metadata_calc_last_lblock;
 	int i_da_metadata_calc_len;
 
+	/* pending cluster reservations for bigalloc file systems */
+	struct ext4_pending_tree i_pending_tree;
+
 	/* on-disk additional length */
 	__u16 i_extra_isize;
 

196 lines not on this page · raw message

61 lines not on this page · raw message

index 1145109968ef..faf293ed8060 100644
@@ -1040,6 +1040,7 @@ static struct inode *ext4_alloc_inode(struct super_block *sb)
 	ei->i_da_metadata_calc_len = 0;
 	ei->i_da_metadata_calc_last_lblock = 0;
 	spin_lock_init(&(ei->i_block_reservation_lock));
+	ext4_init_pending_tree(&ei->i_pending_tree);
 #ifdef CONFIG_QUOTA
 	ei->i_reserved_quota = 0;
 	memset(&ei->i_dquot, 0, sizeof(ei->i_dquot));

@@ -5954,6 +5955,10 @@ static int __init ext4_init_fs(void)
 	if (err)
 		return err;
 
+	err = ext4_init_pending();
+	if (err)
+		goto out6;
+
 	err = ext4_init_pageio();
 	if (err)
 		goto out5;

@@ -5992,6 +5997,8 @@ static int __init ext4_init_fs(void)
 out4:
 	ext4_exit_pageio();
 out5:
+	ext4_exit_pending();
+out6:
 	ext4_exit_es();
 
 	return err;

@@ -6009,6 +6016,7 @@ static void __exit ext4_exit_fs(void)
 	ext4_exit_system_zone();
 	ext4_exit_pageio();
 	ext4_exit_es();
+	ext4_exit_pending();
 }
 
 MODULE_AUTHOR("Remy Card, Stephen Tweedie, Andrew Morton, Andreas Dilger, Theodore Ts'o and others");

index fc0f41dbf90b..d85fd5c8a2c4 100644
@@ -3155,6 +3155,7 @@ extern int ext4_swap_extents(handle_t *handle, struct inode *inode1,
 				struct inode *inode2, ext4_lblk_t lblk1,
 			     ext4_lblk_t lblk2,  ext4_lblk_t count,
 			     int mark_unwritten,int *err);
+extern int ext4_clu_mapped(struct inode *inode, ext4_lblk_t lclu);
 
 /* move_extent.c */
 extern void ext4_double_down_write_data_sem(struct inode *first,

82 lines not on this page · raw message

56 lines not on this page · raw message

index 379b7171c67c..9d3c676ec623 100644
@@ -178,6 +178,16 @@ static inline int ext4_es_is_hole(struct extent_status *es)
 	return (ext4_es_type(es) & EXTENT_STATUS_HOLE) != 0;
 }
 
+static inline int ext4_es_is_mapped(struct extent_status *es)
+{
+	return (ext4_es_is_written(es) || ext4_es_is_unwritten(es));
+}
+
+static inline int ext4_es_is_delonly(struct extent_status *es)
+{
+	return (ext4_es_is_delayed(es) && !ext4_es_is_unwritten(es));
+}
+
 static inline void ext4_es_set_referenced(struct extent_status *es)
 {
 	es->es_pblk |= ((ext4_fsblk_t)EXTENT_STATUS_REFERENCED) << ES_SHIFT;

@@ -232,5 +242,7 @@ extern void ext4_exit_pending(void);
 extern void ext4_init_pending_tree(struct ext4_pending_tree *tree);
 extern void ext4_remove_pending(struct inode *inode, ext4_lblk_t lblk);
 extern bool ext4_is_pending(struct inode *inode, ext4_lblk_t lblk);
+extern int ext4_es_insert_delayed_block(struct inode *inode, ext4_lblk_t lblk,
+					bool allocated);
 
 #endif /* _EXT4_EXTENTS_STATUS_H */

92 lines not on this page · raw message

index 7849b7f8fd9d..6d7a943f849c 100644
@@ -2512,6 +2512,41 @@ TRACE_EVENT(ext4_es_shrink,
 		  __entry->scan_time, __entry->nr_skipped, __entry->retried)
 );
 
+TRACE_EVENT(ext4_es_insert_delayed_block,
+	TP_PROTO(struct inode *inode, struct extent_status *es,
+		 bool allocated),
+
+	TP_ARGS(inode, es, allocated),
+
+	TP_STRUCT__entry(
+		__field(	dev_t,		dev		)
+		__field(	ino_t,		ino		)
+		__field(	ext4_lblk_t,	lblk		)
+		__field(	ext4_lblk_t,	len		)
+		__field(	ext4_fsblk_t,	pblk		)
+		__field(	char,		status		)
+		__field(	bool,		allocated	)
+	),
+
+	TP_fast_assign(
+		__entry->dev		= inode->i_sb->s_dev;
+		__entry->ino		= inode->i_ino;
+		__entry->lblk		= es->es_lblk;
+		__entry->len		= es->es_len;
+		__entry->pblk		= ext4_es_pblock(es);
+		__entry->status		= ext4_es_status(es);
+		__entry->allocated	= allocated;
+	),
+
+	TP_printk("dev %d,%d ino %lu es [%u/%u) mapped %llu status %s "
+		  "allocated %d",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  (unsigned long) __entry->ino,
+		  __entry->lblk, __entry->len,
+		  __entry->pblk, show_extent_status(__entry->status),
+		  __entry->allocated)
+);
+
 /* fsmap traces */
 DECLARE_EVENT_CLASS(ext4_fsmap_class,
 	TP_PROTO(struct super_block *sb, u32 keydev, u32 agno, u64 bno, u64 len,

index 26481e543312..b52ac813ca20 100644
@@ -3819,83 +3819,6 @@ static int check_eofblocks_fl(handle_t *handle, struct inode *inode,
 	return ext4_mark_inode_dirty(handle, inode);
 }
 
-/**
- * Determines how many complete clusters (out of those specified by the 'map')
- * are under delalloc and were reserved quota for.
- * This function is called when we are writing out the blocks that were
- * originally written with their allocation delayed, but then the space was
- * allocated using fallocate() before the delayed allocation could be resolved.
- * The cases to look for are:
- * ('=' indicated delayed allocated blocks
- *  '-' indicates non-delayed allocated blocks)
- * (a) partial clusters towards beginning and/or end outside of allocated range
- *     are not delalloc'ed.
- *	Ex:
- *	|----c---=|====c====|====c====|===-c----|
- *	         |++++++ allocated ++++++|
- *	==> 4 complete clusters in above example
- *
- * (b) partial cluster (outside of allocated range) towards either end is
- *     marked for delayed allocation. In this case, we will exclude that
- *     cluster.
- *	Ex:
- *	|----====c========|========c========|
- *	     |++++++ allocated ++++++|
- *	==> 1 complete clusters in above example
- *
- *	Ex:
- *	|================c================|
- *            |++++++ allocated ++++++|
- *	==> 0 complete clusters in above example
- *
- * The ext4_da_update_reserve_space will be called only if we
- * determine here that there were some "entire" clusters that span
- * this 'allocated' range.
- * In the non-bigalloc case, this function will just end up returning num_blks
- * without ever calling ext4_find_delalloc_range.
- */
-static unsigned int
-get_reserved_cluster_alloc(struct inode *inode, ext4_lblk_t lblk_start,
-			   unsigned int num_blks)
-{
-	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
-	ext4_lblk_t alloc_cluster_start, alloc_cluster_end;
-	ext4_lblk_t lblk_from, lblk_to, c_offset;
-	unsigned int allocated_clusters = 0;
-
-	alloc_cluster_start = EXT4_B2C(sbi, lblk_start);
-	alloc_cluster_end = EXT4_B2C(sbi, lblk_start + num_blks - 1);
-
-	/* max possible clusters for this allocation */
-	allocated_clusters = alloc_cluster_end - alloc_cluster_start + 1;
-
-	trace_ext4_get_reserved_cluster_alloc(inode, lblk_start, num_blks);
-
-	/* Check towards left side */
-	c_offset = EXT4_LBLK_COFF(sbi, lblk_start);
-	if (c_offset) {
-		lblk_from = EXT4_LBLK_CMASK(sbi, lblk_start);
-		lblk_to = lblk_from + c_offset - 1;
-
-		if (ext4_es_scan_range(inode, &ext4_es_is_delayed, lblk_from,
-				       lblk_to))
-			allocated_clusters--;
-	}
-
-	/* Now check towards right. */
-	c_offset = EXT4_LBLK_COFF(sbi, lblk_start + num_blks);
-	if (allocated_clusters && c_offset) {
-		lblk_from = lblk_start + num_blks;
-		lblk_to = lblk_from + (sbi->s_cluster_ratio - c_offset) - 1;
-
-		if (ext4_es_scan_range(inode, &ext4_es_is_delayed, lblk_from,
-				       lblk_to))
-			allocated_clusters--;
-	}
-
-	return allocated_clusters;
-}
-
 static int
 convert_initialized_extent(handle_t *handle, struct inode *inode,
 			   struct ext4_map_blocks *map,

@@ -4077,23 +4000,6 @@ ext4_ext_handle_unwritten_extents(handle_t *handle, struct inode *inode,
 	}
 	map->m_len = allocated;
 
-	/*
-	 * If we have done fallocate with the offset that is already
-	 * delayed allocated, we would have block reservation
-	 * and quota reservation done in the delayed write path.
-	 * But fallocate would have already updated quota and block
-	 * count for this offset. So cancel these reservation
-	 */
-	if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) {
-		unsigned int reserved_clusters;
-		reserved_clusters = get_reserved_cluster_alloc(inode,
-				map->m_lblk, map->m_len);
-		if (reserved_clusters)
-			ext4_da_update_reserve_space(inode,
-						     reserved_clusters,
-						     0);
-	}
-
 map_out:
 	map->m_flags |= EXT4_MAP_MAPPED;
 	if ((flags & EXT4_GET_BLOCKS_KEEP_SIZE) == 0) {

@@ -4482,77 +4388,39 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
 	map->m_flags |= EXT4_MAP_NEW;
 
 	/*
-	 * Update reserved blocks/metadata blocks after successful
-	 * block allocation which had been deferred till now.
+	 * Reduce the reserved cluster count to reflect successful deferred
+	 * allocation of delayed allocated clusters or direct allocation of
+	 * clusters discovered to be delayed allocated.  Once allocated, a
+	 * cluster is not included in the reserved count.
 	 */
-	if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) {
-		unsigned int reserved_clusters;
-		/*
-		 * Check how many clusters we had reserved this allocated range
-		 */
-		reserved_clusters = get_reserved_cluster_alloc(inode,
-						map->m_lblk, allocated);
-		if (!map_from_cluster) {
-			BUG_ON(allocated_clusters < reserved_clusters);
-			if (reserved_clusters < allocated_clusters) {
-				struct ext4_inode_info *ei = EXT4_I(inode);
-				int reservation = allocated_clusters -
-						  reserved_clusters;
-				/*
-				 * It seems we claimed few clusters outside of
-				 * the range of this allocation. We should give
-				 * it back to the reservation pool. This can
-				 * happen in the following case:
-				 *
-				 * * Suppose s_cluster_ratio is 4 (i.e., each
-				 *   cluster has 4 blocks. Thus, the clusters
-				 *   are [0-3],[4-7],[8-11]...
-				 * * First comes delayed allocation write for
-				 *   logical blocks 10 & 11. Since there were no
-				 *   previous delayed allocated blocks in the
-				 *   range [8-11], we would reserve 1 cluster
-				 *   for this write.
-				 * * Next comes write for logical blocks 3 to 8.
-				 *   In this case, we will reserve 2 clusters
-				 *   (for [0-3] and [4-7]; and not for [8-11] as
-				 *   that range has a delayed allocated blocks.
-				 *   Thus total reserved clusters now becomes 3.
-				 * * Now, during the delayed allocation writeout
-				 *   time, we will first write blocks [3-8] and
-				 *   allocate 3 clusters for writing these
-				 *   blocks. Also, we would claim all these
-				 *   three clusters above.
-				 * * Now when we come here to writeout the
-				 *   blocks [10-11], we would expect to claim
-				 *   the reservation of 1 cluster we had made
-				 *   (and we would claim it since there are no
-				 *   more delayed allocated blocks in the range
-				 *   [8-11]. But our reserved cluster count had
-				 *   already gone to 0.
-				 *
-				 *   Thus, at the step 4 above when we determine
-				 *   that there are still some unwritten delayed
-				 *   allocated blocks outside of our current
-				 *   block range, we should increment the
-				 *   reserved clusters count so that when the
-				 *   remaining blocks finally gets written, we
-				 *   could claim them.
-				 */
-				dquot_reserve_block(inode,
-						EXT4_C2B(sbi, reservation));
-				spin_lock(&ei->i_block_reservation_lock);
-				ei->i_reserved_data_blocks += reservation;
-				spin_unlock(&ei->i_block_reservation_lock);
-			}
+	if (test_opt(inode->i_sb, DELALLOC) && !map_from_cluster) {
+		if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) {
 			/*
-			 * We will claim quota for all newly allocated blocks.
-			 * We're updating the reserved space *after* the
-			 * correction above so we do not accidentally free
-			 * all the metadata reservation because we might
-			 * actually need it later on.
+			 * When allocating delayed allocated clusters, simply
+			 * reduce the reserved cluster count and claim quota
 			 */
 			ext4_da_update_reserve_space(inode, allocated_clusters,
 							1);
+		} else {
+			ext4_lblk_t lblk, len;
+			unsigned int n;
+
+			/*
+			 * When allocating non-delayed allocated clusters
+			 * (from fallocate, filemap, DIO, or clusters
+			 * allocated when delalloc has been disabled by
+			 * ext4_nonda_switch), reduce the reserved cluster
+			 * count by the number of allocated clusters that
+			 * have previously been delayed allocated.  Quota
+			 * has been claimed by ext4_mb_new_blocks() above,
+			 * so release the quota reservations made for any
+			 * previously delayed allocated clusters.
+			 */
+			lblk = EXT4_LBLK_CMASK(sbi, map->m_lblk);
+			len = allocated_clusters << sbi->s_cluster_bits;
+			n = ext4_es_delayed_clu(inode, lblk, len);
+			if (n > 0)
+				ext4_da_update_reserve_space(inode, (int) n, 0);
 		}
 	}
 

196 lines not on this page · raw message

index 9d3c676ec623..131a8b7df265 100644
@@ -244,5 +244,9 @@ extern void ext4_remove_pending(struct inode *inode, ext4_lblk_t lblk);
 extern bool ext4_is_pending(struct inode *inode, ext4_lblk_t lblk);
 extern int ext4_es_insert_delayed_block(struct inode *inode, ext4_lblk_t lblk,
 					bool allocated);
+extern unsigned int ext4_es_delayed_clu(struct inode *inode, ext4_lblk_t lblk,
+					ext4_lblk_t len);
+extern void ext4_es_remove_blks(struct inode *inode, ext4_lblk_t lblk,
+				ext4_lblk_t len);
 
 #endif /* _EXT4_EXTENTS_STATUS_H */

index d85fd5c8a2c4..0bdbbd151d2c 100644
@@ -628,6 +628,7 @@ enum {
 #define EXT4_FREE_BLOCKS_NO_QUOT_UPDATE		0x0008
 #define EXT4_FREE_BLOCKS_NOFREE_FIRST_CLUSTER	0x0010
 #define EXT4_FREE_BLOCKS_NOFREE_LAST_CLUSTER	0x0020
+#define EXT4_FREE_BLOCKS_RERESERVE_CLUSTER      0x0040
 
 /*
  * ioctl commands

index adf6668b596f..98bd0e9ee7df 100644
@@ -120,6 +120,19 @@ struct ext4_ext_path {
 };
 
 /*
+ * Used to record a portion of a cluster found at the beginning or end
+ * of an extent while traversing the extent tree during space removal.
+ * A partial cluster may be removed if it does not contain blocks shared
+ * with extents that aren't being deleted (tofree state).  Otherwise,
+ * it cannot be removed (nofree state).
+ */
+struct partial_cluster {
+	ext4_fsblk_t pclu;  /* physical cluster number */
+	ext4_lblk_t lblk;   /* logical block number within logical cluster */
+	enum {initial, tofree, nofree} state;
+};
+
+/*
  * structure for external API
  */
 

383 lines not on this page · raw message

index e29fce2fbf25..e2248083cdca 100644
@@ -4915,9 +4915,17 @@ void ext4_free_blocks(handle_t *handle, struct inode *inode,
 			     &sbi->s_flex_groups[flex_group].free_clusters);
 	}
 
-	if (!(flags & EXT4_FREE_BLOCKS_NO_QUOT_UPDATE))
-		dquot_free_block(inode, EXT4_C2B(sbi, count_clusters));
-	percpu_counter_add(&sbi->s_freeclusters_counter, count_clusters);
+	/*
+	 * on a bigalloc file system, defer the s_freeclusters_counter
+	 * update to the caller (ext4_remove_space and friends) so they
+	 * can determine if a cluster freed here should be rereserved
+	 */
+	if (!(flags & EXT4_FREE_BLOCKS_RERESERVE_CLUSTER)) {
+		if (!(flags & EXT4_FREE_BLOCKS_NO_QUOT_UPDATE))
+			dquot_free_block(inode, EXT4_C2B(sbi, count_clusters));
+		percpu_counter_add(&sbi->s_freeclusters_counter,
+				   count_clusters);
+	}
 
 	ext4_mb_unload_buddy(&e4b);
 

160 lines not on this page · raw message

index 0bdbbd151d2c..57cbc98d730f 100644
@@ -2491,6 +2491,7 @@ extern int ext4_page_mkwrite(struct vm_fault *vmf);
 extern int ext4_filemap_fault(struct vm_fault *vmf);
 extern qsize_t *ext4_get_reserved_space(struct inode *inode);
 extern int ext4_get_projid(struct inode *inode, kprojid_t *projid);
+extern void ext4_da_release_space(struct inode *inode, int to_free);
 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,

93 lines not on this page · raw message

index 57c6dd38f071..9b69f88bdacc 100644
@@ -1595,7 +1595,7 @@ static int ext4_da_reserve_space(struct inode *inode)
 	return 0;       /* success */
 }
 
-static void ext4_da_release_space(struct inode *inode, int to_free)
+void ext4_da_release_space(struct inode *inode, int to_free)
 {
 	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
 	struct ext4_inode_info *ei = EXT4_I(inode);

@@ -1634,13 +1634,11 @@ static void ext4_da_page_release_reservation(struct page *page,
 					     unsigned int offset,
 					     unsigned int length)
 {
-	int to_release = 0, contiguous_blks = 0;
+	int contiguous_blks = 0;
 	struct buffer_head *head, *bh;
 	unsigned int curr_off = 0;
 	struct inode *inode = page->mapping->host;
-	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
 	unsigned int stop = offset + length;
-	int num_clusters;
 	ext4_fsblk_t lblk;
 
 	BUG_ON(stop > PAGE_SIZE || stop < length);

@@ -1654,7 +1652,6 @@ static void ext4_da_page_release_reservation(struct page *page,
 			break;
 
 		if ((offset <= curr_off) && (buffer_delay(bh))) {
-			to_release++;
 			contiguous_blks++;
 			clear_buffer_delay(bh);
 		} else if (contiguous_blks) {

@@ -1662,7 +1659,7 @@ static void ext4_da_page_release_reservation(struct page *page,
 			       (PAGE_SHIFT - inode->i_blkbits);
 			lblk += (curr_off >> inode->i_blkbits) -
 				contiguous_blks;
-			ext4_es_remove_extent(inode, lblk, contiguous_blks);
+			ext4_es_remove_blks(inode, lblk, contiguous_blks);
 			contiguous_blks = 0;
 		}
 		curr_off = next_off;

@@ -1671,21 +1668,9 @@ static void ext4_da_page_release_reservation(struct page *page,
 	if (contiguous_blks) {
 		lblk = page->index << (PAGE_SHIFT - inode->i_blkbits);
 		lblk += (curr_off >> inode->i_blkbits) - contiguous_blks;
-		ext4_es_remove_extent(inode, lblk, contiguous_blks);
+		ext4_es_remove_blks(inode, lblk, contiguous_blks);
 	}
 
-	/* If we have released all the blocks belonging to a cluster, then we
-	 * need to release the reserved space for that cluster. */
-	num_clusters = EXT4_NUM_B2C(sbi, to_release);
-	while (num_clusters > 0) {
-		lblk = (page->index << (PAGE_SHIFT - inode->i_blkbits)) +
-			((num_clusters - 1) << sbi->s_cluster_bits);
-		if (sbi->s_cluster_ratio == 1 ||
-		    !ext4_es_scan_clu(inode, &ext4_es_is_delayed, lblk))
-			ext4_da_release_space(inode, 1);
-
-		num_clusters--;
-	}
 }
 
 /*