1 files changed, 87 insertions, 55 deletions

diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index d767e993591d..c3d9a42c561e 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -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 @@ found:
 				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);
@@ -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_find_delalloc_cluster(inode, lblk))
-			ext4_da_release_space(inode, 1);
-
-		num_clusters--;
-	}
 }
 
 /*
@@ -1781,6 +1766,65 @@ static int ext4_bh_delay_or_unwritten(handle_t *handle, struct buffer_head *bh)
 }
 
 /*
+ * ext4_insert_delayed_block - adds a delayed block to the extents status
+ *                             tree, incrementing the reserved cluster/block
+ *                             count or making a pending reservation
+ *                             where needed
+ *
+ * @inode - file containing the newly added block
+ * @lblk - logical block to be added
+ *
+ * Returns 0 on success, negative error code on failure.
+ */
+static int ext4_insert_delayed_block(struct inode *inode, ext4_lblk_t lblk)
+{
+	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
+	int ret;
+	bool allocated = false;
+
+	/*
+	 * If the cluster containing lblk is shared with a delayed,
+	 * written, or unwritten extent in a bigalloc file system, it's
+	 * already been accounted for and does not need to be reserved.
+	 * A pending reservation must be made for the cluster if it's
+	 * shared with a written or unwritten extent and doesn't already
+	 * have one.  Written and unwritten extents can be purged from the
+	 * extents status tree if the system is under memory pressure, so
+	 * it's necessary to examine the extent tree if a search of the
+	 * extents status tree doesn't get a match.
+	 */
+	if (sbi->s_cluster_ratio == 1) {
+		ret = ext4_da_reserve_space(inode);
+		if (ret != 0)   /* ENOSPC */
+			goto errout;
+	} else {   /* bigalloc */
+		if (!ext4_es_scan_clu(inode, &ext4_es_is_delonly, lblk)) {
+			if (!ext4_es_scan_clu(inode,
+					      &ext4_es_is_mapped, lblk)) {
+				ret = ext4_clu_mapped(inode,
+						      EXT4_B2C(sbi, lblk));
+				if (ret < 0)
+					goto errout;
+				if (ret == 0) {
+					ret = ext4_da_reserve_space(inode);
+					if (ret != 0)   /* ENOSPC */
+						goto errout;
+				} else {
+					allocated = true;
+				}
+			} else {
+				allocated = true;
+			}
+		}
+	}
+
+	ret = ext4_es_insert_delayed_block(inode, lblk, allocated);
+
+errout:
+	return ret;
+}
+
+/*
  * This function is grabs code from the very beginning of
  * ext4_map_blocks, but assumes that the caller is from delayed write
  * time. This function looks up the requested blocks and sets the
@@ -1859,28 +1903,14 @@ 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?
 		 */
-		/*
-		 * If the block was allocated from previously allocated cluster,
-		 * then we don't need to reserve it again. However we still need
-		 * 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)) {
-			ret = ext4_da_reserve_space(inode);
-			if (ret) {
-				/* not enough space to reserve */
-				retval = ret;
-				goto out_unlock;
-			}
-		}
 
-		ret = ext4_es_insert_extent(inode, map->m_lblk, map->m_len,
-					    ~0, EXTENT_STATUS_DELAYED);
-		if (ret) {
+		ret = ext4_insert_delayed_block(inode, map->m_lblk);
+		if (ret != 0) {
 			retval = ret;
 			goto out_unlock;
 		}
@@ -3450,7 +3480,8 @@ 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 */
@@ -6153,13 +6184,14 @@ static int ext4_bh_unmapped(handle_t *handle, struct buffer_head *bh)
 	return !buffer_mapped(bh);
 }
 
-int ext4_page_mkwrite(struct vm_fault *vmf)
+vm_fault_t ext4_page_mkwrite(struct vm_fault *vmf)
 {
 	struct vm_area_struct *vma = vmf->vma;
 	struct page *page = vmf->page;
 	loff_t size;
 	unsigned long len;
-	int ret;
+	int err;
+	vm_fault_t ret;
 	struct file *file = vma->vm_file;
 	struct inode *inode = file_inode(file);
 	struct address_space *mapping = inode->i_mapping;
@@ -6172,8 +6204,8 @@ int ext4_page_mkwrite(struct vm_fault *vmf)
 
 	down_read(&EXT4_I(inode)->i_mmap_sem);
 
-	ret = ext4_convert_inline_data(inode);
-	if (ret)
+	err = ext4_convert_inline_data(inode);
+	if (err)
 		goto out_ret;
 
 	/* Delalloc case is easy... */
@@ -6181,9 +6213,9 @@ int ext4_page_mkwrite(struct vm_fault *vmf)
 	    !ext4_should_journal_data(inode) &&
 	    !ext4_nonda_switch(inode->i_sb)) {
 		do {
-			ret = block_page_mkwrite(vma, vmf,
+			err = block_page_mkwrite(vma, vmf,
 						   ext4_da_get_block_prep);
-		} while (ret == -ENOSPC &&
+		} while (err == -ENOSPC &&
 		       ext4_should_retry_alloc(inode->i_sb, &retries));
 		goto out_ret;
 	}
@@ -6228,8 +6260,8 @@ retry_alloc:
 		ret = VM_FAULT_SIGBUS;
 		goto out;
 	}
-	ret = block_page_mkwrite(vma, vmf, get_block);
-	if (!ret && ext4_should_journal_data(inode)) {
+	err = block_page_mkwrite(vma, vmf, get_block);
+	if (!err && ext4_should_journal_data(inode)) {
 		if (ext4_walk_page_buffers(handle, page_buffers(page), 0,
 			  PAGE_SIZE, NULL, do_journal_get_write_access)) {
 			unlock_page(page);
@@ -6240,24 +6272,24 @@ retry_alloc:
 		ext4_set_inode_state(inode, EXT4_STATE_JDATA);
 	}
 	ext4_journal_stop(handle);
-	if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
+	if (err == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
 		goto retry_alloc;
 out_ret:
-	ret = block_page_mkwrite_return(ret);
+	ret = block_page_mkwrite_return(err);
 out:
 	up_read(&EXT4_I(inode)->i_mmap_sem);
 	sb_end_pagefault(inode->i_sb);
 	return ret;
 }
 
-int ext4_filemap_fault(struct vm_fault *vmf)
+vm_fault_t ext4_filemap_fault(struct vm_fault *vmf)
 {
 	struct inode *inode = file_inode(vmf->vma->vm_file);
-	int err;
+	vm_fault_t ret;
 
 	down_read(&EXT4_I(inode)->i_mmap_sem);
-	err = filemap_fault(vmf);
+	ret = filemap_fault(vmf);
 	up_read(&EXT4_I(inode)->i_mmap_sem);
 
-	return err;
+	return ret;
 }