Merge branch 'xfs-4.8-misc-fixes-4' into for-next

fs/xfs/libxfs/xfs_da_btree.c

@@ -356,7 +356,6 @@ xfs_da3_split(
 	struct xfs_da_state_blk	*newblk;
 	struct xfs_da_state_blk	*addblk;
 	struct xfs_da_intnode	*node;
-	struct xfs_buf		*bp;
 	int			max;
 	int			action = 0;
 	int			error;
@@ -397,7 +396,9 @@ xfs_da3_split(
 				break;
 			}
 			/*
-			 * Entry wouldn't fit, split the leaf again.
+			 * Entry wouldn't fit, split the leaf again. The new
+			 * extrablk will be consumed by xfs_da3_node_split if
+			 * the node is split.
 			 */
 			state->extravalid = 1;
 			if (state->inleaf) {
@@ -445,6 +446,14 @@ xfs_da3_split(
 	if (!addblk)
 		return 0;
 
+	/*
+	 * xfs_da3_node_split() should have consumed any extra blocks we added
+	 * during a double leaf split in the attr fork. This is guaranteed as
+	 * we can't be here if the attr fork only has a single leaf block.
+	 */
+	ASSERT(state->extravalid == 0 ||
+	       state->path.blk[max].magic == XFS_DIR2_LEAFN_MAGIC);
+
 	/*
 	 * Split the root node.
 	 */
@@ -457,43 +466,33 @@ xfs_da3_split(
 	}
 
 	/*
-	 * Update pointers to the node which used to be block 0 and
-	 * just got bumped because of the addition of a new root node.
-	 * There might be three blocks involved if a double split occurred,
-	 * and the original block 0 could be at any position in the list.
+	 * Update pointers to the node which used to be block 0 and just got
+	 * bumped because of the addition of a new root node.  Note that the
+	 * original block 0 could be at any position in the list of blocks in
+	 * the tree.
 	 *
-	 * Note: the magic numbers and sibling pointers are in the same
-	 * physical place for both v2 and v3 headers (by design). Hence it
-	 * doesn't matter which version of the xfs_da_intnode structure we use
-	 * here as the result will be the same using either structure.
+	 * Note: the magic numbers and sibling pointers are in the same physical
+	 * place for both v2 and v3 headers (by design). Hence it doesn't matter
+	 * which version of the xfs_da_intnode structure we use here as the
+	 * result will be the same using either structure.
 	 */
 	node = oldblk->bp->b_addr;
 	if (node->hdr.info.forw) {
-		if (be32_to_cpu(node->hdr.info.forw) == addblk->blkno) {
-			bp = addblk->bp;
-		} else {
-			ASSERT(state->extravalid);
-			bp = state->extrablk.bp;
-		}
-		node = bp->b_addr;
+		ASSERT(be32_to_cpu(node->hdr.info.forw) == addblk->blkno);
+		node = addblk->bp->b_addr;
 		node->hdr.info.back = cpu_to_be32(oldblk->blkno);
-		xfs_trans_log_buf(state->args->trans, bp,
-		    XFS_DA_LOGRANGE(node, &node->hdr.info,
-		    sizeof(node->hdr.info)));
+		xfs_trans_log_buf(state->args->trans, addblk->bp,
+				  XFS_DA_LOGRANGE(node, &node->hdr.info,
+				  sizeof(node->hdr.info)));
 	}
 	node = oldblk->bp->b_addr;
 	if (node->hdr.info.back) {
-		if (be32_to_cpu(node->hdr.info.back) == addblk->blkno) {
-			bp = addblk->bp;
-		} else {
-			ASSERT(state->extravalid);
-			bp = state->extrablk.bp;
-		}
-		node = bp->b_addr;
+		ASSERT(be32_to_cpu(node->hdr.info.back) == addblk->blkno);
+		node = addblk->bp->b_addr;
 		node->hdr.info.forw = cpu_to_be32(oldblk->blkno);
-		xfs_trans_log_buf(state->args->trans, bp,
-		    XFS_DA_LOGRANGE(node, &node->hdr.info,
-		    sizeof(node->hdr.info)));
+		xfs_trans_log_buf(state->args->trans, addblk->bp,
+				  XFS_DA_LOGRANGE(node, &node->hdr.info,
+				  sizeof(node->hdr.info)));
 	}
 	addblk->bp = NULL;
 	return 0;

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);
 }
 
 /*
@@ -1040,6 +1049,20 @@ 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))

fs/xfs/xfs_buf_item.c

@@ -957,6 +957,7 @@ xfs_buf_item_free(
 	xfs_buf_log_item_t	*bip)
 {
 	xfs_buf_item_free_format(bip);
+	kmem_free(bip->bli_item.li_lv_shadow);
 	kmem_zone_free(xfs_buf_item_zone, bip);
 }
 

fs/xfs/xfs_dquot.c

@@ -74,6 +74,7 @@ xfs_qm_dqdestroy(
 {
 	ASSERT(list_empty(&dqp->q_lru));
 
+	kmem_free(dqp->q_logitem.qli_item.li_lv_shadow);
 	mutex_destroy(&dqp->q_qlock);
 
 	XFS_STATS_DEC(dqp->q_mount, xs_qm_dquot);

fs/xfs/xfs_dquot_item.c

@@ -370,6 +370,8 @@ xfs_qm_qoffend_logitem_committed(
 	spin_lock(&ailp->xa_lock);
 	xfs_trans_ail_delete(ailp, &qfs->qql_item, SHUTDOWN_LOG_IO_ERROR);
 
+	kmem_free(qfs->qql_item.li_lv_shadow);
+	kmem_free(lip->li_lv_shadow);
 	kmem_free(qfs);
 	kmem_free(qfe);
 	return (xfs_lsn_t)-1;

fs/xfs/xfs_extfree_item.c

@@ -40,6 +40,7 @@ void
 xfs_efi_item_free(
 	struct xfs_efi_log_item	*efip)
 {
+	kmem_free(efip->efi_item.li_lv_shadow);
 	if (efip->efi_format.efi_nextents > XFS_EFI_MAX_FAST_EXTENTS)
 		kmem_free(efip);
 	else
@@ -300,6 +301,7 @@ static inline struct xfs_efd_log_item *EFD_ITEM(struct xfs_log_item *lip)
 STATIC void
 xfs_efd_item_free(struct xfs_efd_log_item *efdp)
 {
+	kmem_free(efdp->efd_item.li_lv_shadow);
 	if (efdp->efd_format.efd_nextents > XFS_EFD_MAX_FAST_EXTENTS)
 		kmem_free(efdp);
 	else

fs/xfs/xfs_file.c

@@ -327,7 +327,7 @@ xfs_file_dio_aio_read(
 	return ret;
 }
 
-STATIC ssize_t
+static noinline ssize_t
 xfs_file_dax_read(
 	struct kiocb		*iocb,
 	struct iov_iter		*to)
@@ -706,7 +706,7 @@ xfs_file_dio_aio_write(
 	return ret;
 }
 
-STATIC ssize_t
+static noinline ssize_t
 xfs_file_dax_write(
 	struct kiocb		*iocb,
 	struct iov_iter		*from)

fs/xfs/xfs_inode_item.c

@@ -651,6 +651,7 @@ void
 xfs_inode_item_destroy(
 	xfs_inode_t	*ip)
 {
+	kmem_free(ip->i_itemp->ili_item.li_lv_shadow);
 	kmem_zone_free(xfs_ili_zone, ip->i_itemp);
 }
 

fs/xfs/xfs_super.c

@@ -1573,10 +1573,6 @@ xfs_fs_fill_super(
 		}
 	}
 
-	if (xfs_sb_version_hassparseinodes(&mp->m_sb))
-		xfs_alert(mp,
-	"EXPERIMENTAL sparse inode feature enabled. Use at your own risk!");
-
 	error = xfs_mountfs(mp);
 	if (error)
 		goto out_filestream_unmount;

fs/xfs/xfs_trans.h

@@ -52,6 +52,7 @@ typedef struct xfs_log_item {
 	/* delayed logging */
 	struct list_head		li_cil;		/* CIL pointers */
 	struct xfs_log_vec		*li_lv;		/* active log vector */
+	struct xfs_log_vec		*li_lv_shadow;	/* standby vector */
 	xfs_lsn_t			li_seq;		/* CIL commit seq */
 } xfs_log_item_t;