ext4: call ext4_forget() from ext4_free_blocks()

Add the facility for ext4_forget() to be called from
ext4_free_blocks().  This simplifies the code in a large number of
places, and centralizes most of the work of calling ext4_forget() into
a single place.

Also fix a bug in the extents migration code; it wasn't calling
ext4_forget() when releasing the indirect blocks during the
conversion.  As a result, if the system cashed during or shortly after
the extents migration, and the released indirect blocks get reused as
data blocks, the journal replay would corrupt the data blocks.  With
this new patch, fixing this bug was as simple as adding the
EXT4_FREE_BLOCKS_FORGET flags to the call to ext4_free_blocks().

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

1 files changed, 36 insertions, 13 deletions

diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 0dca90be1afb..78de5d3c5dce 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -4436,8 +4436,8 @@ ext4_mb_free_metadata(handle_t *handle, struct ext4_buddy *e4b,
  * @metadata:           Are these metadata blocks
  */
 void ext4_free_blocks(handle_t *handle, struct inode *inode,
-                      ext4_fsblk_t block, unsigned long count,
-                      int metadata)
+                      struct buffer_head *bh, ext4_fsblk_t block,
+                      unsigned long count, int flags)
 {
         struct buffer_head *bitmap_bh = NULL;
         struct super_block *sb = inode->i_sb;
@@ -4454,15 +4454,12 @@ void ext4_free_blocks(handle_t *handle, struct inode *inode,
         int err = 0;
         int ret;
 
-        /* 
-         * We need to make sure we don't reuse the freed block until
-         * after the transaction is committed, which we can do by
-         * treating the block as metadata, below.  We make an
-         * exception if the inode is to be written in writeback mode
-         * since writeback mode has weak data consistency guarantees.
-         */
-        if (!ext4_should_writeback_data(inode))
-                metadata = 1;
+        if (bh) {
+                if (block)
+                        BUG_ON(block != bh->b_blocknr);
+                else
+                        block = bh->b_blocknr;
+        }
 
         sbi = EXT4_SB(sb);
         es = EXT4_SB(sb)->s_es;
@@ -4476,7 +4473,32 @@ void ext4_free_blocks(handle_t *handle, struct inode *inode,
         }
 
         ext4_debug("freeing block %llu\n", block);
-        trace_ext4_free_blocks(inode, block, count, metadata);
+        trace_ext4_free_blocks(inode, block, count, flags);
+
+        if (flags & EXT4_FREE_BLOCKS_FORGET) {
+                struct buffer_head *tbh = bh;
+                int i;
+
+                BUG_ON(bh && (count > 1));
+
+                for (i = 0; i < count; i++) {
+                        if (!bh)
+                                tbh = sb_find_get_block(inode->i_sb,
+                                                        block + i);
+                        ext4_forget(handle, flags & EXT4_FREE_BLOCKS_METADATA, 
+                                    inode, tbh, block + i);
+                }
+        }
+
+        /* 
+         * We need to make sure we don't reuse the freed block until
+         * after the transaction is committed, which we can do by
+         * treating the block as metadata, below.  We make an
+         * exception if the inode is to be written in writeback mode
+         * since writeback mode has weak data consistency guarantees.
+         */
+        if (!ext4_should_writeback_data(inode))
+                flags |= EXT4_FREE_BLOCKS_METADATA;
 
         ac = kmem_cache_alloc(ext4_ac_cachep, GFP_NOFS);
         if (ac) {
@@ -4552,7 +4574,8 @@ do_more:
         err = ext4_mb_load_buddy(sb, block_group, &e4b);
         if (err)
                 goto error_return;
-        if (metadata && ext4_handle_valid(handle)) {
+
+        if ((flags & EXT4_FREE_BLOCKS_METADATA) && ext4_handle_valid(handle)) {
                 struct ext4_free_data *new_entry;
                 /*
                  * blocks being freed are metadata. these blocks shouldn't