1 files changed, 92 insertions, 51 deletions

diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c
index 735f0190ec2a..5e0faf4cda79 100644
--- a/fs/ext3/inode.c
+++ b/fs/ext3/inode.c
@@ -190,18 +190,28 @@ static int truncate_restart_transaction(handle_t *handle, struct inode *inode)
 }
 
 /*
- * Called at the last iput() if i_nlink is zero.
+ * Called at inode eviction from icache
  */
-void ext3_delete_inode (struct inode * inode)
+void ext3_evict_inode (struct inode *inode)
 {
+        struct ext3_block_alloc_info *rsv;
         handle_t *handle;
+        int want_delete = 0;
 
-        if (!is_bad_inode(inode))
+        if (!inode->i_nlink && !is_bad_inode(inode)) {
                 dquot_initialize(inode);
+                want_delete = 1;
+        }
 
         truncate_inode_pages(&inode->i_data, 0);
 
-        if (is_bad_inode(inode))
+        ext3_discard_reservation(inode);
+        rsv = EXT3_I(inode)->i_block_alloc_info;
+        EXT3_I(inode)->i_block_alloc_info = NULL;
+        if (unlikely(rsv))
+                kfree(rsv);
+
+        if (!want_delete)
                 goto no_delete;
 
         handle = start_transaction(inode);
@@ -238,15 +248,22 @@ void ext3_delete_inode (struct inode * inode)
          * having errors), but we can't free the inode if the mark_dirty
          * fails.
          */
-        if (ext3_mark_inode_dirty(handle, inode))
-                /* If that failed, just do the required in-core inode clear. */
-                clear_inode(inode);
-        else
+        if (ext3_mark_inode_dirty(handle, inode)) {
+                /* If that failed, just dquot_drop() and be done with that */
+                dquot_drop(inode);
+                end_writeback(inode);
+        } else {
+                ext3_xattr_delete_inode(handle, inode);
+                dquot_free_inode(inode);
+                dquot_drop(inode);
+                end_writeback(inode);
                 ext3_free_inode(handle, inode);
+        }
         ext3_journal_stop(handle);
         return;
 no_delete:
-        clear_inode(inode);     /* We must guarantee clearing of inode... */
+        end_writeback(inode);
+        dquot_drop(inode);
 }
 
 typedef struct {
@@ -1149,9 +1166,25 @@ static int walk_page_buffers(	handle_t *handle,
 static int do_journal_get_write_access(handle_t *handle,
                                         struct buffer_head *bh)
 {
+        int dirty = buffer_dirty(bh);
+        int ret;
+
         if (!buffer_mapped(bh) || buffer_freed(bh))
                 return 0;
-        return ext3_journal_get_write_access(handle, bh);
+        /*
+         * __block_prepare_write() could have dirtied some buffers. Clean
+         * the dirty bit as jbd2_journal_get_write_access() could complain
+         * otherwise about fs integrity issues. Setting of the dirty bit
+         * by __block_prepare_write() isn't a real problem here as we clear
+         * the bit before releasing a page lock and thus writeback cannot
+         * ever write the buffer.
+         */
+        if (dirty)
+                clear_buffer_dirty(bh);
+        ret = ext3_journal_get_write_access(handle, bh);
+        if (!ret && dirty)
+                ret = ext3_journal_dirty_metadata(handle, bh);
+        return ret;
 }
 
 /*
@@ -1196,8 +1229,7 @@ retry:
                 ret = PTR_ERR(handle);
                 goto out;
         }
-        ret = block_write_begin(file, mapping, pos, len, flags, pagep, fsdata,
-                                                        ext3_get_block);
+        ret = __block_write_begin(page, pos, len, ext3_get_block);
         if (ret)
                 goto write_begin_failed;
 
@@ -1625,10 +1657,7 @@ static int ext3_writeback_writepage(struct page *page,
                 goto out_fail;
         }
 
-        if (test_opt(inode->i_sb, NOBH) && ext3_should_writeback_data(inode))
-                ret = nobh_writepage(page, ext3_get_block, wbc);
-        else
-                ret = block_write_full_page(page, ext3_get_block, wbc);
+        ret = block_write_full_page(page, ext3_get_block, wbc);
 
         err = ext3_journal_stop(handle);
         if (!ret)
@@ -1785,6 +1814,17 @@ retry:
         ret = blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev, iov,
                                  offset, nr_segs,
                                  ext3_get_block, NULL);
+        /*
+         * In case of error extending write may have instantiated a few
+         * blocks outside i_size. Trim these off again.
+         */
+        if (unlikely((rw & WRITE) && ret < 0)) {
+                loff_t isize = i_size_read(inode);
+                loff_t end = offset + iov_length(iov, nr_segs);
+
+                if (end > isize)
+                        vmtruncate(inode, isize);
+        }
         if (ret == -ENOSPC && ext3_should_retry_alloc(inode->i_sb, &retries))
                 goto retry;
 
@@ -1922,17 +1962,6 @@ static int ext3_block_truncate_page(handle_t *handle, struct page *page,
         length = blocksize - (offset & (blocksize - 1));
         iblock = index << (PAGE_CACHE_SHIFT - inode->i_sb->s_blocksize_bits);
 
-        /*
-         * For "nobh" option,  we can only work if we don't need to
-         * read-in the page - otherwise we create buffers to do the IO.
-         */
-        if (!page_has_buffers(page) && test_opt(inode->i_sb, NOBH) &&
-             ext3_should_writeback_data(inode) && PageUptodate(page)) {
-                zero_user(page, offset, length);
-                set_page_dirty(page);
-                goto unlock;
-        }
-
         if (!page_has_buffers(page))
                 create_empty_buffers(page, blocksize, 0);
 
@@ -2284,27 +2313,6 @@ static void ext3_free_branches(handle_t *handle, struct inode *inode,
                                            depth);
 
                         /*
-                         * We've probably journalled the indirect block several
-                         * times during the truncate.  But it's no longer
-                         * needed and we now drop it from the transaction via
-                         * journal_revoke().
-                         *
-                         * That's easy if it's exclusively part of this
-                         * transaction.  But if it's part of the committing
-                         * transaction then journal_forget() will simply
-                         * brelse() it.  That means that if the underlying
-                         * block is reallocated in ext3_get_block(),
-                         * unmap_underlying_metadata() will find this block
-                         * and will try to get rid of it.  damn, damn.
-                         *
-                         * If this block has already been committed to the
-                         * journal, a revoke record will be written.  And
-                         * revoke records must be emitted *before* clearing
-                         * this block's bit in the bitmaps.
-                         */
-                        ext3_forget(handle, 1, inode, bh, bh->b_blocknr);
-
-                        /*
                          * Everything below this this pointer has been
                          * released.  Now let this top-of-subtree go.
                          *
@@ -2327,6 +2335,31 @@ static void ext3_free_branches(handle_t *handle, struct inode *inode,
                                 truncate_restart_transaction(handle, inode);
                         }
 
+                        /*
+                         * We've probably journalled the indirect block several
+                         * times during the truncate.  But it's no longer
+                         * needed and we now drop it from the transaction via
+                         * journal_revoke().
+                         *
+                         * That's easy if it's exclusively part of this
+                         * transaction.  But if it's part of the committing
+                         * transaction then journal_forget() will simply
+                         * brelse() it.  That means that if the underlying
+                         * block is reallocated in ext3_get_block(),
+                         * unmap_underlying_metadata() will find this block
+                         * and will try to get rid of it.  damn, damn. Thus
+                         * we don't allow a block to be reallocated until
+                         * a transaction freeing it has fully committed.
+                         *
+                         * We also have to make sure journal replay after a
+                         * crash does not overwrite non-journaled data blocks
+                         * with old metadata when the block got reallocated for
+                         * data.  Thus we have to store a revoke record for a
+                         * block in the same transaction in which we free the
+                         * block.
+                         */
+                        ext3_forget(handle, 1, inode, bh, bh->b_blocknr);
+
                         ext3_free_blocks(handle, inode, nr, 1);
 
                         if (parent_bh) {
@@ -2554,7 +2587,7 @@ out_stop:
          * If this was a simple ftruncate(), and the file will remain alive
          * then we need to clear up the orphan record which we created above.
          * However, if this was a real unlink then we were called by
-         * ext3_delete_inode(), and we allow that function to clean up the
+         * ext3_evict_inode(), and we allow that function to clean up the
          * orphan info for us.
          */
         if (inode->i_nlink)
@@ -3198,9 +3231,17 @@ int ext3_setattr(struct dentry *dentry, struct iattr *attr)
                 ext3_journal_stop(handle);
         }
 
-        rc = inode_setattr(inode, attr);
+        if ((attr->ia_valid & ATTR_SIZE) &&
+            attr->ia_size != i_size_read(inode)) {
+                rc = vmtruncate(inode, attr->ia_size);
+                if (rc)
+                        goto err_out;
+        }
+
+        setattr_copy(inode, attr);
+        mark_inode_dirty(inode);
 
-        if (!rc && (ia_valid & ATTR_MODE))
+        if (ia_valid & ATTR_MODE)
                 rc = ext3_acl_chmod(inode);
 
 err_out: