Merge tag 'xfs-for-linus-4.8-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/dgc/linux-xfs

Pull xfs updates from Dave Chinner:
 "The major addition is the new iomap based block mapping
  infrastructure.  We've been kicking this about locally for years, but
  there are other filesystems want to use it too (e.g. gfs2).  Now it
  is fully working, reviewed and ready for merge and be used by other
  filesystems.

  There are a lot of other fixes and cleanups in the tree, but those are
  XFS internal things and none are of the scale or visibility of the
  iomap changes.  See below for details.

  I am likely to send another pull request next week - we're just about
  ready to merge some new functionality (on disk block->owner reverse
  mapping infrastructure), but that's a huge chunk of code (74 files
  changed, 7283 insertions(+), 1114 deletions(-)) so I'm keeping that
  separate to all the "normal" pull request changes so they don't get
  lost in the noise.

  Summary of changes in this update:
   - generic iomap based IO path infrastructure
   - generic iomap based fiemap implementation
   - xfs iomap based Io path implementation
   - buffer error handling fixes
   - tracking of in flight buffer IO for unmount serialisation
   - direct IO and DAX io path separation and simplification
   - shortform directory format definition changes for wider platform
     compatibility
   - various buffer cache fixes
   - cleanups in preparation for rmap merge
   - error injection cleanups and fixes
   - log item format buffer memory allocation restructuring to prevent
     rare OOM reclaim deadlocks
   - sparse inode chunks are now fully supported"

* tag 'xfs-for-linus-4.8-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/dgc/linux-xfs: (53 commits)
  xfs: remove EXPERIMENTAL tag from sparse inode feature
  xfs: bufferhead chains are invalid after end_page_writeback
  xfs: allocate log vector buffers outside CIL context lock
  libxfs: directory node splitting does not have an extra block
  xfs: remove dax code from object file when disabled
  xfs: skip dirty pages in ->releasepage()
  xfs: remove __arch_pack
  xfs: kill xfs_dir2_inou_t
  xfs: kill xfs_dir2_sf_off_t
  xfs: split direct I/O and DAX path
  xfs: direct calls in the direct I/O path
  xfs: stop using generic_file_read_iter for direct I/O
  xfs: split xfs_file_read_iter into buffered and direct I/O helpers
  xfs: remove s_maxbytes enforcement in xfs_file_read_iter
  xfs: kill ioflags
  xfs: don't pass ioflags around in the ioctl path
  xfs: track and serialize in-flight async buffers against unmount
  xfs: exclude never-released buffers from buftarg I/O accounting
  xfs: don't reset b_retries to 0 on every failure
  xfs: remove extraneous buffer flag changes
  ...

1 files changed, 48 insertions, 284 deletions

diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 87d2b215cbbd..7575cfc3ad15 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -87,6 +87,12 @@ xfs_find_bdev_for_inode(
  * We're now finished for good with this page.  Update the page state via the
  * associated buffer_heads, paying attention to the start and end offsets that
  * we need to process on the page.
+ *
+ * Landmine Warning: bh->b_end_io() will call end_page_writeback() on the last
+ * buffer in the IO. Once it does this, it is unsafe to access the bufferhead or
+ * the page at all, as we may be racing with memory reclaim and it can free both
+ * the bufferhead chain and the page as it will see the page as clean and
+ * unused.
  */
 static void
 xfs_finish_page_writeback(
@@ -95,8 +101,9 @@ xfs_finish_page_writeback(
 	int			error)
 {
 	unsigned int		end = bvec->bv_offset + bvec->bv_len - 1;
-	struct buffer_head	*head, *bh;
+	struct buffer_head	*head, *bh, *next;
 	unsigned int		off = 0;
+	unsigned int		bsize;
 
 	ASSERT(bvec->bv_offset < PAGE_SIZE);
 	ASSERT((bvec->bv_offset & ((1 << inode->i_blkbits) - 1)) == 0);
@@ -105,15 +112,17 @@ xfs_finish_page_writeback(
 
 	bh = head = page_buffers(bvec->bv_page);
 
+	bsize = bh->b_size;
 	do {
+		next = bh->b_this_page;
 		if (off < bvec->bv_offset)
 			goto next_bh;
 		if (off > end)
 			break;
 		bh->b_end_io(bh, !error);
 next_bh:
-		off += bh->b_size;
-	} while ((bh = bh->b_this_page) != head);
+		off += bsize;
+	} while ((bh = next) != head);
 }
 
 /*
@@ -1041,6 +1050,20 @@ xfs_vm_releasepage(
 
 	trace_xfs_releasepage(page->mapping->host, page, 0, 0);
 
+	/*
+	 * mm accommodates an old ext3 case where clean pages might not have had
+	 * the dirty bit cleared. Thus, it can send actual dirty pages to
+	 * ->releasepage() via shrink_active_list(). Conversely,
+	 * block_invalidatepage() can send pages that are still marked dirty
+	 * but otherwise have invalidated buffers.
+	 *
+	 * We've historically freed buffers on the latter. Instead, quietly
+	 * filter out all dirty pages to avoid spurious buffer state warnings.
+	 * This can likely be removed once shrink_active_list() is fixed.
+	 */
+	if (PageDirty(page))
+		return 0;
+
 	xfs_count_page_state(page, &delalloc, &unwritten);
 
 	if (WARN_ON_ONCE(delalloc))
@@ -1144,6 +1167,8 @@ __xfs_get_blocks(
 	ssize_t			size;
 	int			new = 0;
 
+	BUG_ON(create && !direct);
+
 	if (XFS_FORCED_SHUTDOWN(mp))
 		return -EIO;
 
@@ -1151,22 +1176,14 @@ __xfs_get_blocks(
 	ASSERT(bh_result->b_size >= (1 << inode->i_blkbits));
 	size = bh_result->b_size;
 
-	if (!create && direct && offset >= i_size_read(inode))
+	if (!create && offset >= i_size_read(inode))
 		return 0;
 
 	/*
 	 * Direct I/O is usually done on preallocated files, so try getting
-	 * a block mapping without an exclusive lock first.  For buffered
-	 * writes we already have the exclusive iolock anyway, so avoiding
-	 * a lock roundtrip here by taking the ilock exclusive from the
-	 * beginning is a useful micro optimization.
+	 * a block mapping without an exclusive lock first.
 	 */
-	if (create && !direct) {
-		lockmode = XFS_ILOCK_EXCL;
-		xfs_ilock(ip, lockmode);
-	} else {
-		lockmode = xfs_ilock_data_map_shared(ip);
-	}
+	lockmode = xfs_ilock_data_map_shared(ip);
 
 	ASSERT(offset <= mp->m_super->s_maxbytes);
 	if (offset + size > mp->m_super->s_maxbytes)
@@ -1185,37 +1202,19 @@ __xfs_get_blocks(
 	     (imap.br_startblock == HOLESTARTBLOCK ||
 	      imap.br_startblock == DELAYSTARTBLOCK) ||
 	     (IS_DAX(inode) && ISUNWRITTEN(&imap)))) {
-		if (direct || xfs_get_extsz_hint(ip)) {
-			/*
-			 * xfs_iomap_write_direct() expects the shared lock. It
-			 * is unlocked on return.
-			 */
-			if (lockmode == XFS_ILOCK_EXCL)
-				xfs_ilock_demote(ip, lockmode);
-
-			error = xfs_iomap_write_direct(ip, offset, size,
-						       &imap, nimaps);
-			if (error)
-				return error;
-			new = 1;
+		/*
+		 * xfs_iomap_write_direct() expects the shared lock. It
+		 * is unlocked on return.
+		 */
+		if (lockmode == XFS_ILOCK_EXCL)
+			xfs_ilock_demote(ip, lockmode);
 
-		} else {
-			/*
-			 * Delalloc reservations do not require a transaction,
-			 * we can go on without dropping the lock here. If we
-			 * are allocating a new delalloc block, make sure that
-			 * we set the new flag so that we mark the buffer new so
-			 * that we know that it is newly allocated if the write
-			 * fails.
-			 */
-			if (nimaps && imap.br_startblock == HOLESTARTBLOCK)
-				new = 1;
-			error = xfs_iomap_write_delay(ip, offset, size, &imap);
-			if (error)
-				goto out_unlock;
+		error = xfs_iomap_write_direct(ip, offset, size,
+					       &imap, nimaps);
+		if (error)
+			return error;
+		new = 1;
 
-			xfs_iunlock(ip, lockmode);
-		}
 		trace_xfs_get_blocks_alloc(ip, offset, size,
 				ISUNWRITTEN(&imap) ? XFS_IO_UNWRITTEN
 						   : XFS_IO_DELALLOC, &imap);
@@ -1236,9 +1235,7 @@ __xfs_get_blocks(
 	}
 
 	/* trim mapping down to size requested */
-	if (direct || size > (1 << inode->i_blkbits))
-		xfs_map_trim_size(inode, iblock, bh_result,
-				  &imap, offset, size);
+	xfs_map_trim_size(inode, iblock, bh_result, &imap, offset, size);
 
 	/*
 	 * For unwritten extents do not report a disk address in the buffered
@@ -1251,7 +1248,7 @@ __xfs_get_blocks(
 		if (ISUNWRITTEN(&imap))
 			set_buffer_unwritten(bh_result);
 		/* direct IO needs special help */
-		if (create && direct) {
+		if (create) {
 			if (dax_fault)
 				ASSERT(!ISUNWRITTEN(&imap));
 			else
@@ -1280,14 +1277,7 @@ __xfs_get_blocks(
 	     (new || ISUNWRITTEN(&imap))))
 		set_buffer_new(bh_result);
 
-	if (imap.br_startblock == DELAYSTARTBLOCK) {
-		BUG_ON(direct);
-		if (create) {
-			set_buffer_uptodate(bh_result);
-			set_buffer_mapped(bh_result);
-			set_buffer_delay(bh_result);
-		}
-	}
+	BUG_ON(direct && imap.br_startblock == DELAYSTARTBLOCK);
 
 	return 0;
 
@@ -1337,7 +1327,7 @@ xfs_get_blocks_dax_fault(
  * whereas if we have flags set we will always be called in task context
  * (i.e. from a workqueue).
  */
-STATIC int
+int
 xfs_end_io_direct_write(
 	struct kiocb		*iocb,
 	loff_t			offset,
@@ -1408,234 +1398,10 @@ xfs_vm_direct_IO(
 	struct kiocb		*iocb,
 	struct iov_iter		*iter)
 {
-	struct inode		*inode = iocb->ki_filp->f_mapping->host;
-	dio_iodone_t		*endio = NULL;
-	int			flags = 0;
-	struct block_device	*bdev;
-
-	if (iov_iter_rw(iter) == WRITE) {
-		endio = xfs_end_io_direct_write;
-		flags = DIO_ASYNC_EXTEND;
-	}
-
-	if (IS_DAX(inode)) {
-		return dax_do_io(iocb, inode, iter,
-				 xfs_get_blocks_direct, endio, 0);
-	}
-
-	bdev = xfs_find_bdev_for_inode(inode);
-	return  __blockdev_direct_IO(iocb, inode, bdev, iter,
-			xfs_get_blocks_direct, endio, NULL, flags);
-}
-
-/*
- * Punch out the delalloc blocks we have already allocated.
- *
- * Don't bother with xfs_setattr given that nothing can have made it to disk yet
- * as the page is still locked at this point.
- */
-STATIC void
-xfs_vm_kill_delalloc_range(
-	struct inode		*inode,
-	loff_t			start,
-	loff_t			end)
-{
-	struct xfs_inode	*ip = XFS_I(inode);
-	xfs_fileoff_t		start_fsb;
-	xfs_fileoff_t		end_fsb;
-	int			error;
-
-	start_fsb = XFS_B_TO_FSB(ip->i_mount, start);
-	end_fsb = XFS_B_TO_FSB(ip->i_mount, end);
-	if (end_fsb <= start_fsb)
-		return;
-
-	xfs_ilock(ip, XFS_ILOCK_EXCL);
-	error = xfs_bmap_punch_delalloc_range(ip, start_fsb,
-						end_fsb - start_fsb);
-	if (error) {
-		/* something screwed, just bail */
-		if (!XFS_FORCED_SHUTDOWN(ip->i_mount)) {
-			xfs_alert(ip->i_mount,
-		"xfs_vm_write_failed: unable to clean up ino %lld",
-					ip->i_ino);
-		}
-	}
-	xfs_iunlock(ip, XFS_ILOCK_EXCL);
-}
-
-STATIC void
-xfs_vm_write_failed(
-	struct inode		*inode,
-	struct page		*page,
-	loff_t			pos,
-	unsigned		len)
-{
-	loff_t			block_offset;
-	loff_t			block_start;
-	loff_t			block_end;
-	loff_t			from = pos & (PAGE_SIZE - 1);
-	loff_t			to = from + len;
-	struct buffer_head	*bh, *head;
-	struct xfs_mount	*mp = XFS_I(inode)->i_mount;
-
 	/*
-	 * The request pos offset might be 32 or 64 bit, this is all fine
-	 * on 64-bit platform.  However, for 64-bit pos request on 32-bit
-	 * platform, the high 32-bit will be masked off if we evaluate the
-	 * block_offset via (pos & PAGE_MASK) because the PAGE_MASK is
-	 * 0xfffff000 as an unsigned long, hence the result is incorrect
-	 * which could cause the following ASSERT failed in most cases.
-	 * In order to avoid this, we can evaluate the block_offset of the
-	 * start of the page by using shifts rather than masks the mismatch
-	 * problem.
+	 * We just need the method present so that open/fcntl allow direct I/O.
 	 */
-	block_offset = (pos >> PAGE_SHIFT) << PAGE_SHIFT;
-
-	ASSERT(block_offset + from == pos);
-
-	head = page_buffers(page);
-	block_start = 0;
-	for (bh = head; bh != head || !block_start;
-	     bh = bh->b_this_page, block_start = block_end,
-				   block_offset += bh->b_size) {
-		block_end = block_start + bh->b_size;
-
-		/* skip buffers before the write */
-		if (block_end <= from)
-			continue;
-
-		/* if the buffer is after the write, we're done */
-		if (block_start >= to)
-			break;
-
-		/*
-		 * Process delalloc and unwritten buffers beyond EOF. We can
-		 * encounter unwritten buffers in the event that a file has
-		 * post-EOF unwritten extents and an extending write happens to
-		 * fail (e.g., an unaligned write that also involves a delalloc
-		 * to the same page).
-		 */
-		if (!buffer_delay(bh) && !buffer_unwritten(bh))
-			continue;
-
-		if (!xfs_mp_fail_writes(mp) && !buffer_new(bh) &&
-		    block_offset < i_size_read(inode))
-			continue;
-
-		if (buffer_delay(bh))
-			xfs_vm_kill_delalloc_range(inode, block_offset,
-						   block_offset + bh->b_size);
-
-		/*
-		 * This buffer does not contain data anymore. make sure anyone
-		 * who finds it knows that for certain.
-		 */
-		clear_buffer_delay(bh);
-		clear_buffer_uptodate(bh);
-		clear_buffer_mapped(bh);
-		clear_buffer_new(bh);
-		clear_buffer_dirty(bh);
-		clear_buffer_unwritten(bh);
-	}
-
-}
-
-/*
- * This used to call block_write_begin(), but it unlocks and releases the page
- * on error, and we need that page to be able to punch stale delalloc blocks out
- * on failure. hence we copy-n-waste it here and call xfs_vm_write_failed() at
- * the appropriate point.
- */
-STATIC int
-xfs_vm_write_begin(
-	struct file		*file,
-	struct address_space	*mapping,
-	loff_t			pos,
-	unsigned		len,
-	unsigned		flags,
-	struct page		**pagep,
-	void			**fsdata)
-{
-	pgoff_t			index = pos >> PAGE_SHIFT;
-	struct page		*page;
-	int			status;
-	struct xfs_mount	*mp = XFS_I(mapping->host)->i_mount;
-
-	ASSERT(len <= PAGE_SIZE);
-
-	page = grab_cache_page_write_begin(mapping, index, flags);
-	if (!page)
-		return -ENOMEM;
-
-	status = __block_write_begin(page, pos, len, xfs_get_blocks);
-	if (xfs_mp_fail_writes(mp))
-		status = -EIO;
-	if (unlikely(status)) {
-		struct inode	*inode = mapping->host;
-		size_t		isize = i_size_read(inode);
-
-		xfs_vm_write_failed(inode, page, pos, len);
-		unlock_page(page);
-
-		/*
-		 * If the write is beyond EOF, we only want to kill blocks
-		 * allocated in this write, not blocks that were previously
-		 * written successfully.
-		 */
-		if (xfs_mp_fail_writes(mp))
-			isize = 0;
-		if (pos + len > isize) {
-			ssize_t start = max_t(ssize_t, pos, isize);
-
-			truncate_pagecache_range(inode, start, pos + len);
-		}
-
-		put_page(page);
-		page = NULL;
-	}
-
-	*pagep = page;
-	return status;
-}
-
-/*
- * On failure, we only need to kill delalloc blocks beyond EOF in the range of
- * this specific write because they will never be written. Previous writes
- * beyond EOF where block allocation succeeded do not need to be trashed, so
- * only new blocks from this write should be trashed. For blocks within
- * EOF, generic_write_end() zeros them so they are safe to leave alone and be
- * written with all the other valid data.
- */
-STATIC int
-xfs_vm_write_end(
-	struct file		*file,
-	struct address_space	*mapping,
-	loff_t			pos,
-	unsigned		len,
-	unsigned		copied,
-	struct page		*page,
-	void			*fsdata)
-{
-	int			ret;
-
-	ASSERT(len <= PAGE_SIZE);
-
-	ret = generic_write_end(file, mapping, pos, len, copied, page, fsdata);
-	if (unlikely(ret < len)) {
-		struct inode	*inode = mapping->host;
-		size_t		isize = i_size_read(inode);
-		loff_t		to = pos + len;
-
-		if (to > isize) {
-			/* only kill blocks in this write beyond EOF */
-			if (pos > isize)
-				isize = pos;
-			xfs_vm_kill_delalloc_range(inode, isize, to);
-			truncate_pagecache_range(inode, isize, to);
-		}
-	}
-	return ret;
+	return -EINVAL;
 }
 
 STATIC sector_t
@@ -1748,8 +1514,6 @@ const struct address_space_operations xfs_address_space_operations = {
 	.set_page_dirty		= xfs_vm_set_page_dirty,
 	.releasepage		= xfs_vm_releasepage,
 	.invalidatepage		= xfs_vm_invalidatepage,
-	.write_begin		= xfs_vm_write_begin,
-	.write_end		= xfs_vm_write_end,
 	.bmap			= xfs_vm_bmap,
 	.direct_IO		= xfs_vm_direct_IO,
 	.migratepage		= buffer_migrate_page,