ext4: Mark the unwritten buffer_head as mapped during write_begin

Setting BH_Unwritten buffer_heads as BH_Mapped avoids multiple
(unnecessary) calls to get_block() during the call to the write(2)
system call.  Setting BH_Unwritten buffer heads as BH_Mapped requires
that the writepages() functions can handle BH_Unwritten buffer_heads.

After this commit, things work as follows:

ext4_ext_get_block() returns unmapped, unwritten, buffer head when
called with create = 0 for prealloc space. This makes sure we handle
the read path and non-delayed allocation case correctly.  Even though
the buffer head is marked unmapped we have valid b_blocknr and b_bdev
values in the buffer_head.

ext4_da_get_block_prep() called for block resrevation will now return
mapped, unwritten, new buffer_head for prealloc space. This avoids
multiple calls to get_block() for write to same offset. By making such
buffers as BH_New, we also assure that sub-block zeroing of buffered
writes happens correctly.

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>

2 files changed, 54 insertions, 32 deletions

diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index a953214f2829..ea5c47608cea 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -2872,6 +2872,8 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
                         if (create == EXT4_CREATE_UNINITIALIZED_EXT)
                                 goto out;
                         if (!create) {
+                                if (allocated > max_blocks)
+                                        allocated = max_blocks;
                                 /*
                                  * We have blocks reserved already.  We
                                  * return allocated blocks so that delalloc
@@ -2879,8 +2881,6 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
                                  * the buffer head will be unmapped so that
                                  * a read from the block returns 0s.
                                  */
-                                if (allocated > max_blocks)
-                                        allocated = max_blocks;
                                 set_buffer_unwritten(bh_result);
                                 bh_result->b_bdev = inode->i_sb->s_bdev;
                                 bh_result->b_blocknr = newblock;
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index d7ad0bb73cd5..96f3366f59f6 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -1852,7 +1852,7 @@ static int mpage_da_submit_io(struct mpage_da_data *mpd)
  * @logical - first logical block to start assignment with
  *
  * the function goes through all passed space and put actual disk
- * block numbers into buffer heads, dropping BH_Delay
+ * block numbers into buffer heads, dropping BH_Delay and BH_Unwritten
  */
 static void mpage_put_bnr_to_bhs(struct mpage_da_data *mpd, sector_t logical,
                                  struct buffer_head *exbh)
@@ -1902,16 +1902,24 @@ static void mpage_put_bnr_to_bhs(struct mpage_da_data *mpd, sector_t logical,
                         do {
                                 if (cur_logical >= logical + blocks)
                                         break;
-                                if (buffer_delay(bh)) {
-                                        bh->b_blocknr = pblock;
-                                        clear_buffer_delay(bh);
-                                        bh->b_bdev = inode->i_sb->s_bdev;
-                                } else if (buffer_unwritten(bh)) {
-                                        bh->b_blocknr = pblock;
-                                        clear_buffer_unwritten(bh);
-                                        set_buffer_mapped(bh);
-                                        set_buffer_new(bh);
-                                        bh->b_bdev = inode->i_sb->s_bdev;
+
+                                if (buffer_delay(bh) ||
+                                                buffer_unwritten(bh)) {
+
+                                        BUG_ON(bh->b_bdev != inode->i_sb->s_bdev);
+
+                                        if (buffer_delay(bh)) {
+                                                clear_buffer_delay(bh);
+                                                bh->b_blocknr = pblock;
+                                        } else {
+                                                /*
+                                                 * unwritten already should have
+                                                 * blocknr assigned. Verify that
+                                                 */
+                                                clear_buffer_unwritten(bh);
+                                                BUG_ON(bh->b_blocknr != pblock);
+                                        }
+
                                 } else if (buffer_mapped(bh))
                                         BUG_ON(bh->b_blocknr != pblock);
 
@@ -2053,7 +2061,8 @@ static int mpage_da_map_blocks(struct mpage_da_data *mpd)
          * We consider only non-mapped and non-allocated blocks
          */
         if ((mpd->b_state  & (1 << BH_Mapped)) &&
-            !(mpd->b_state & (1 << BH_Delay)))
+                !(mpd->b_state & (1 << BH_Delay)) &&
+                !(mpd->b_state & (1 << BH_Unwritten)))
                 return 0;
         /*
          * We need to make sure the BH_Delay flag is passed down to
@@ -2205,6 +2214,17 @@ flush_it:
         return;
 }
 
+static int ext4_bh_unmapped_or_delay(handle_t *handle, struct buffer_head *bh)
+{
+        /*
+         * unmapped buffer is possible for holes.
+         * delay buffer is possible with delayed allocation.
+         * We also need to consider unwritten buffer as unmapped.
+         */
+        return (!buffer_mapped(bh) || buffer_delay(bh) ||
+                                buffer_unwritten(bh)) && buffer_dirty(bh);
+}
+
 /*
  * __mpage_da_writepage - finds extent of pages and blocks
  *
@@ -2289,8 +2309,7 @@ static int __mpage_da_writepage(struct page *page,
                          * Otherwise we won't make progress
                          * with the page in ext4_da_writepage
                          */
-                        if (buffer_dirty(bh) &&
-                            (!buffer_mapped(bh) || buffer_delay(bh))) {
+                        if (ext4_bh_unmapped_or_delay(NULL, bh)) {
                                 mpage_add_bh_to_extent(mpd, logical,
                                                        bh->b_size,
                                                        bh->b_state);
@@ -2318,6 +2337,14 @@ static int __mpage_da_writepage(struct page *page,
 /*
  * this is a special callback for ->write_begin() only
  * it's intention is to return mapped block or reserve space
+ *
+ * For delayed buffer_head we have BH_Mapped, BH_New, BH_Delay set.
+ * We also have b_blocknr = -1 and b_bdev initialized properly
+ *
+ * For unwritten buffer_head we have BH_Mapped, BH_New, BH_Unwritten set.
+ * We also have b_blocknr = physicalblock mapping unwritten extent and b_bdev
+ * initialized properly.
+ *
  */
 static int ext4_da_get_block_prep(struct inode *inode, sector_t iblock,
                                   struct buffer_head *bh_result, int create)
@@ -2353,28 +2380,23 @@ static int ext4_da_get_block_prep(struct inode *inode, sector_t iblock,
                 set_buffer_delay(bh_result);
         } else if (ret > 0) {
                 bh_result->b_size = (ret << inode->i_blkbits);
-                /*
-                 * With sub-block writes into unwritten extents
-                 * we also need to mark the buffer as new so that
-                 * the unwritten parts of the buffer gets correctly zeroed.
-                 */
-                if (buffer_unwritten(bh_result))
+                if (buffer_unwritten(bh_result)) {
+                        /* A delayed write to unwritten bh should
+                         * be marked new and mapped.  Mapped ensures
+                         * that we don't do get_block multiple times
+                         * when we write to the same offset and new
+                         * ensures that we do proper zero out for
+                         * partial write.
+                         */
                         set_buffer_new(bh_result);
+                        set_buffer_mapped(bh_result);
+                }
                 ret = 0;
         }
 
         return ret;
 }
 
-static int ext4_bh_unmapped_or_delay(handle_t *handle, struct buffer_head *bh)
-{
-        /*
-         * unmapped buffer is possible for holes.
-         * delay buffer is possible with delayed allocation
-         */
-        return ((!buffer_mapped(bh) || buffer_delay(bh)) && buffer_dirty(bh));
-}
-
 static int ext4_normal_get_block_write(struct inode *inode, sector_t iblock,
                                    struct buffer_head *bh_result, int create)
 {
@@ -2828,7 +2850,7 @@ static int ext4_da_should_update_i_disksize(struct page *page,
         for (i = 0; i < idx; i++)
                 bh = bh->b_this_page;
 
-        if (!buffer_mapped(bh) || (buffer_delay(bh)))
+        if (!buffer_mapped(bh) || (buffer_delay(bh)) || buffer_unwritten(bh))
                 return 0;
         return 1;
 }