Merge tag 'xfs-for-linus-3.17-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/dgc/linux-xfs

Pull xfs fixes from Dave Chinner:
 "The fixes all address recently discovered data corruption issues.

  The original Direct IO issue was discovered by Chris Mason @ Facebook
  on a production workload which mixed buffered reads with direct reads
  and writes IO to the same file.  The fix for that exposed other issues
  with page invalidation (exposed by millions of fsx operations) failing
  due to dirty buffers beyond EOF.

  Finally, the collapse_range code could also cause problems due to
  racing writeback changing the extent map while it was being shifted
  around.  The commits for that problem are simple mitigation fixes that
  prevent the problem from occuring.  A more robust fix for 3.18 that
  addresses the underlying problem is currently being worked on by
  Brian.

  Summary of fixes:
   - a direct IO read/buffered read data corruption
   - the associated fallout from the DIO data corruption fix
   - collapse range bugs that are potential data corruption issues"

* tag 'xfs-for-linus-3.17-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/dgc/linux-xfs:
  xfs: trim eofblocks before collapse range
  xfs: xfs_file_collapse_range is delalloc challenged
  xfs: don't log inode unless extent shift makes extent modifications
  xfs: use ranged writeback and invalidation for direct IO
  xfs: don't zero partial page cache pages during O_DIRECT writes
  xfs: don't zero partial page cache pages during O_DIRECT writes
  xfs: don't dirty buffers beyond EOF

4 files changed, 114 insertions, 12 deletions

diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index de2d26d32844..86df952d3e24 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -5424,7 +5424,7 @@ xfs_bmap_shift_extents(
 	struct xfs_bmap_free	*flist,
 	int			num_exts)
 {
-	struct xfs_btree_cur		*cur;
+	struct xfs_btree_cur		*cur = NULL;
 	struct xfs_bmbt_rec_host	*gotp;
 	struct xfs_bmbt_irec            got;
 	struct xfs_bmbt_irec		left;
@@ -5435,7 +5435,7 @@ xfs_bmap_shift_extents(
 	int				error = 0;
 	int				i;
 	int				whichfork = XFS_DATA_FORK;
-	int				logflags;
+	int				logflags = 0;
 	xfs_filblks_t			blockcount = 0;
 	int				total_extents;
 
@@ -5478,16 +5478,11 @@ xfs_bmap_shift_extents(
 		}
 	}
 
-	/* We are going to change core inode */
-	logflags = XFS_ILOG_CORE;
 	if (ifp->if_flags & XFS_IFBROOT) {
 		cur = xfs_bmbt_init_cursor(mp, tp, ip, whichfork);
 		cur->bc_private.b.firstblock = *firstblock;
 		cur->bc_private.b.flist = flist;
 		cur->bc_private.b.flags = 0;
-	} else {
-		cur = NULL;
-		logflags |= XFS_ILOG_DEXT;
 	}
 
 	/*
@@ -5545,11 +5540,14 @@ xfs_bmap_shift_extents(
 			blockcount = left.br_blockcount +
 				got.br_blockcount;
 			xfs_iext_remove(ip, *current_ext, 1, 0);
+			logflags |= XFS_ILOG_CORE;
 			if (cur) {
 				error = xfs_btree_delete(cur, &i);
 				if (error)
 					goto del_cursor;
 				XFS_WANT_CORRUPTED_GOTO(i == 1, del_cursor);
+			} else {
+				logflags |= XFS_ILOG_DEXT;
 			}
 			XFS_IFORK_NEXT_SET(ip, whichfork,
 				XFS_IFORK_NEXTENTS(ip, whichfork) - 1);
@@ -5575,6 +5573,7 @@ xfs_bmap_shift_extents(
 			got.br_startoff = startoff;
 		}
 
+		logflags |= XFS_ILOG_CORE;
 		if (cur) {
 			error = xfs_bmbt_update(cur, got.br_startoff,
 						got.br_startblock,
@@ -5582,6 +5581,8 @@ xfs_bmap_shift_extents(
 						got.br_state);
 			if (error)
 				goto del_cursor;
+		} else {
+			logflags |= XFS_ILOG_DEXT;
 		}
 
 		(*current_ext)++;
@@ -5597,6 +5598,7 @@ del_cursor:
 		xfs_btree_del_cursor(cur,
 			error ? XFS_BTREE_ERROR : XFS_BTREE_NOERROR);
 
-	xfs_trans_log_inode(tp, ip, logflags);
+	if (logflags)
+		xfs_trans_log_inode(tp, ip, logflags);
 	return error;
 }
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 11e9b4caa54f..b984647c24db 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -1753,11 +1753,72 @@ xfs_vm_readpages(
 	return mpage_readpages(mapping, pages, nr_pages, xfs_get_blocks);
 }
 
+/*
+ * This is basically a copy of __set_page_dirty_buffers() with one
+ * small tweak: buffers beyond EOF do not get marked dirty. If we mark them
+ * dirty, we'll never be able to clean them because we don't write buffers
+ * beyond EOF, and that means we can't invalidate pages that span EOF
+ * that have been marked dirty. Further, the dirty state can leak into
+ * the file interior if the file is extended, resulting in all sorts of
+ * bad things happening as the state does not match the underlying data.
+ *
+ * XXX: this really indicates that bufferheads in XFS need to die. Warts like
+ * this only exist because of bufferheads and how the generic code manages them.
+ */
+STATIC int
+xfs_vm_set_page_dirty(
+	struct page		*page)
+{
+	struct address_space	*mapping = page->mapping;
+	struct inode		*inode = mapping->host;
+	loff_t			end_offset;
+	loff_t			offset;
+	int			newly_dirty;
+
+	if (unlikely(!mapping))
+		return !TestSetPageDirty(page);
+
+	end_offset = i_size_read(inode);
+	offset = page_offset(page);
+
+	spin_lock(&mapping->private_lock);
+	if (page_has_buffers(page)) {
+		struct buffer_head *head = page_buffers(page);
+		struct buffer_head *bh = head;
+
+		do {
+			if (offset < end_offset)
+				set_buffer_dirty(bh);
+			bh = bh->b_this_page;
+			offset += 1 << inode->i_blkbits;
+		} while (bh != head);
+	}
+	newly_dirty = !TestSetPageDirty(page);
+	spin_unlock(&mapping->private_lock);
+
+	if (newly_dirty) {
+		/* sigh - __set_page_dirty() is static, so copy it here, too */
+		unsigned long flags;
+
+		spin_lock_irqsave(&mapping->tree_lock, flags);
+		if (page->mapping) {	/* Race with truncate? */
+			WARN_ON_ONCE(!PageUptodate(page));
+			account_page_dirtied(page, mapping);
+			radix_tree_tag_set(&mapping->page_tree,
+					page_index(page), PAGECACHE_TAG_DIRTY);
+		}
+		spin_unlock_irqrestore(&mapping->tree_lock, flags);
+		__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
+	}
+	return newly_dirty;
+}
+
 const struct address_space_operations xfs_address_space_operations = {
 	.readpage		= xfs_vm_readpage,
 	.readpages		= xfs_vm_readpages,
 	.writepage		= xfs_vm_writepage,
 	.writepages		= xfs_vm_writepages,
+	.set_page_dirty		= xfs_vm_set_page_dirty,
 	.releasepage		= xfs_vm_releasepage,
 	.invalidatepage		= xfs_vm_invalidatepage,
 	.write_begin		= xfs_vm_write_begin,
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index 2f1e30d39a35..1707980f9a4b 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -1470,6 +1470,26 @@ xfs_collapse_file_space(
 	start_fsb = XFS_B_TO_FSB(mp, offset + len);
 	shift_fsb = XFS_B_TO_FSB(mp, len);
 
+	/*
+	 * Writeback the entire file and force remove any post-eof blocks. The
+	 * writeback prevents changes to the extent list via concurrent
+	 * writeback and the eofblocks trim prevents the extent shift algorithm
+	 * from running into a post-eof delalloc extent.
+	 *
+	 * XXX: This is a temporary fix until the extent shift loop below is
+	 * converted to use offsets and lookups within the ILOCK rather than
+	 * carrying around the index into the extent list for the next
+	 * iteration.
+	 */
+	error = filemap_write_and_wait(VFS_I(ip)->i_mapping);
+	if (error)
+		return error;
+	if (xfs_can_free_eofblocks(ip, true)) {
+		error = xfs_free_eofblocks(mp, ip, false);
+		if (error)
+			return error;
+	}
+
 	error = xfs_free_file_space(ip, offset, len);
 	if (error)
 		return error;
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 076b1708d134..de5368c803f9 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -291,12 +291,22 @@ xfs_file_read_iter(
 		if (inode->i_mapping->nrpages) {
 			ret = filemap_write_and_wait_range(
 							VFS_I(ip)->i_mapping,
-							pos, -1);
+							pos, pos + size - 1);
 			if (ret) {
 				xfs_rw_iunlock(ip, XFS_IOLOCK_EXCL);
 				return ret;
 			}
-			truncate_pagecache_range(VFS_I(ip), pos, -1);
+
+			/*
+			 * Invalidate whole pages. This can return an error if
+			 * we fail to invalidate a page, but this should never
+			 * happen on XFS. Warn if it does fail.
+			 */
+			ret = invalidate_inode_pages2_range(VFS_I(ip)->i_mapping,
+					pos >> PAGE_CACHE_SHIFT,
+					(pos + size - 1) >> PAGE_CACHE_SHIFT);
+			WARN_ON_ONCE(ret);
+			ret = 0;
 		}
 		xfs_rw_ilock_demote(ip, XFS_IOLOCK_EXCL);
 	}
@@ -632,10 +642,19 @@ xfs_file_dio_aio_write(
 
 	if (mapping->nrpages) {
 		ret = filemap_write_and_wait_range(VFS_I(ip)->i_mapping,
-						    pos, -1);
+						    pos, pos + count - 1);
 		if (ret)
 			goto out;
-		truncate_pagecache_range(VFS_I(ip), pos, -1);
+		/*
+		 * Invalidate whole pages. This can return an error if
+		 * we fail to invalidate a page, but this should never
+		 * happen on XFS. Warn if it does fail.
+		 */
+		ret = invalidate_inode_pages2_range(VFS_I(ip)->i_mapping,
+					pos >> PAGE_CACHE_SHIFT,
+					(pos + count - 1) >> PAGE_CACHE_SHIFT);
+		WARN_ON_ONCE(ret);
+		ret = 0;
 	}
 
 	/*