Merge tag 'xfs-fixes-for-4.19-rc6' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux

Dave writes:
  "XFS fixes for 4.19-rc6

   Accumlated regression and bug fixes for 4.19-rc6, including:

   o make iomap correctly mark dirty pages for sub-page block sizes
   o fix regression in handling extent-to-btree format conversion errors
   o fix torn log wrap detection for new logs
   o various corrupt inode detection fixes
   o various delalloc state fixes
   o cleanup all the missed transaction cancel cases missed from changes merged
     in 4.19-rc1
   o fix lockdep false positive on transaction allocation
   o fix locking and reference counting on buffer log items"

* tag 'xfs-fixes-for-4.19-rc6' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux:
  xfs: fix error handling in xfs_bmap_extents_to_btree
  iomap: set page dirty after partial delalloc on mkwrite
  xfs: remove invalid log recovery first/last cycle check
  xfs: validate inode di_forkoff
  xfs: skip delalloc COW blocks in xfs_reflink_end_cow
  xfs: don't treat unknown di_flags2 as corruption in scrub
  xfs: remove duplicated include from alloc.c
  xfs: don't bring in extents in xfs_bmap_punch_delalloc_range
  xfs: fix transaction leak in xfs_reflink_allocate_cow()
  xfs: avoid lockdep false positives in xfs_trans_alloc
  xfs: refactor xfs_buf_log_item reference count handling
  xfs: clean up xfs_trans_brelse()
  xfs: don't unlock invalidated buf on aborted tx commit
  xfs: remove last of unnecessary xfs_defer_cancel() callers
  xfs: don't crash the vfs on a garbage inline symlink

fs/iomap.c

@@ -1051,6 +1051,7 @@ iomap_page_mkwrite_actor(struct inode *inode, loff_t pos, loff_t length,
 	} else {
 		WARN_ON_ONCE(!PageUptodate(page));
 		iomap_page_create(inode, page);
+		set_page_dirty(page);
 	}
 
 	return length;
@@ -1090,7 +1091,6 @@ int iomap_page_mkwrite(struct vm_fault *vmf, const struct iomap_ops *ops)
 		length -= ret;
 	}
 
-	set_page_dirty(page);
 	wait_for_stable_page(page);
 	return VM_FAULT_LOCKED;
 out_unlock:

fs/xfs/libxfs/xfs_attr.c

@@ -587,7 +587,7 @@ xfs_attr_leaf_addname(
 		 */
 		error = xfs_attr3_leaf_to_node(args);
 		if (error)
-			goto out_defer_cancel;
+			return error;
 		error = xfs_defer_finish(&args->trans);
 		if (error)
 			return error;
@@ -675,7 +675,7 @@ xfs_attr_leaf_addname(
 			error = xfs_attr3_leaf_to_shortform(bp, args, forkoff);
 			/* bp is gone due to xfs_da_shrink_inode */
 			if (error)
-				goto out_defer_cancel;
+				return error;
 			error = xfs_defer_finish(&args->trans);
 			if (error)
 				return error;
@@ -693,9 +693,6 @@ xfs_attr_leaf_addname(
 		error = xfs_attr3_leaf_clearflag(args);
 	}
 	return error;
-out_defer_cancel:
-	xfs_defer_cancel(args->trans);
-	return error;
 }
 
 /*
@@ -738,15 +735,12 @@ xfs_attr_leaf_removename(
 		error = xfs_attr3_leaf_to_shortform(bp, args, forkoff);
 		/* bp is gone due to xfs_da_shrink_inode */
 		if (error)
-			goto out_defer_cancel;
+			return error;
 		error = xfs_defer_finish(&args->trans);
 		if (error)
 			return error;
 	}
 	return 0;
-out_defer_cancel:
-	xfs_defer_cancel(args->trans);
-	return error;
 }
 
 /*
@@ -864,7 +858,7 @@ restart:
 			state = NULL;
 			error = xfs_attr3_leaf_to_node(args);
 			if (error)
-				goto out_defer_cancel;
+				goto out;
 			error = xfs_defer_finish(&args->trans);
 			if (error)
 				goto out;
@@ -888,7 +882,7 @@ restart:
 		 */
 		error = xfs_da3_split(state);
 		if (error)
-			goto out_defer_cancel;
+			goto out;
 		error = xfs_defer_finish(&args->trans);
 		if (error)
 			goto out;
@@ -984,7 +978,7 @@ restart:
 		if (retval && (state->path.active > 1)) {
 			error = xfs_da3_join(state);
 			if (error)
-				goto out_defer_cancel;
+				goto out;
 			error = xfs_defer_finish(&args->trans);
 			if (error)
 				goto out;
@@ -1013,9 +1007,6 @@ out:
 	if (error)
 		return error;
 	return retval;
-out_defer_cancel:
-	xfs_defer_cancel(args->trans);
-	goto out;
 }
 
 /*
@@ -1107,7 +1098,7 @@ xfs_attr_node_removename(
 	if (retval && (state->path.active > 1)) {
 		error = xfs_da3_join(state);
 		if (error)
-			goto out_defer_cancel;
+			goto out;
 		error = xfs_defer_finish(&args->trans);
 		if (error)
 			goto out;
@@ -1138,7 +1129,7 @@ xfs_attr_node_removename(
 			error = xfs_attr3_leaf_to_shortform(bp, args, forkoff);
 			/* bp is gone due to xfs_da_shrink_inode */
 			if (error)
-				goto out_defer_cancel;
+				goto out;
 			error = xfs_defer_finish(&args->trans);
 			if (error)
 				goto out;
@@ -1150,9 +1141,6 @@ xfs_attr_node_removename(
 out:
 	xfs_da_state_free(state);
 	return error;
-out_defer_cancel:
-	xfs_defer_cancel(args->trans);
-	goto out;
 }
 
 /*

fs/xfs/libxfs/xfs_attr_remote.c

@@ -485,7 +485,7 @@ xfs_attr_rmtval_set(
 				  blkcnt, XFS_BMAPI_ATTRFORK, args->total, &map,
 				  &nmap);
 		if (error)
-			goto out_defer_cancel;
+			return error;
 		error = xfs_defer_finish(&args->trans);
 		if (error)
 			return error;
@@ -553,9 +553,6 @@ xfs_attr_rmtval_set(
 	}
 	ASSERT(valuelen == 0);
 	return 0;
-out_defer_cancel:
-	xfs_defer_cancel(args->trans);
-	return error;
 }
 
 /*
@@ -625,7 +622,7 @@ xfs_attr_rmtval_remove(
 		error = xfs_bunmapi(args->trans, args->dp, lblkno, blkcnt,
 				    XFS_BMAPI_ATTRFORK, 1, &done);
 		if (error)
-			goto out_defer_cancel;
+			return error;
 		error = xfs_defer_finish(&args->trans);
 		if (error)
 			return error;
@@ -638,7 +635,4 @@ xfs_attr_rmtval_remove(
 			return error;
 	}
 	return 0;
-out_defer_cancel:
-	xfs_defer_cancel(args->trans);
-	return error;
 }

fs/xfs/libxfs/xfs_bmap.c

@@ -673,7 +673,8 @@ xfs_bmap_extents_to_btree(
 	ASSERT(XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_EXTENTS);
 
 	/*
-	 * Make space in the inode incore.
+	 * Make space in the inode incore. This needs to be undone if we fail
+	 * to expand the root.
 	 */
 	xfs_iroot_realloc(ip, 1, whichfork);
 	ifp->if_flags |= XFS_IFBROOT;
@@ -711,16 +712,15 @@ xfs_bmap_extents_to_btree(
 	args.minlen = args.maxlen = args.prod = 1;
 	args.wasdel = wasdel;
 	*logflagsp = 0;
-	if ((error = xfs_alloc_vextent(&args))) {
-		ASSERT(ifp->if_broot == NULL);
-		goto err1;
-	}
+	error = xfs_alloc_vextent(&args);
+	if (error)
+		goto out_root_realloc;
 
 	if (WARN_ON_ONCE(args.fsbno == NULLFSBLOCK)) {
-		ASSERT(ifp->if_broot == NULL);
 		error = -ENOSPC;
-		goto err1;
+		goto out_root_realloc;
 	}
+
 	/*
 	 * Allocation can't fail, the space was reserved.
 	 */
@@ -732,9 +732,10 @@ xfs_bmap_extents_to_btree(
 	xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_BCOUNT, 1L);
 	abp = xfs_btree_get_bufl(mp, tp, args.fsbno, 0);
 	if (!abp) {
-		error = -ENOSPC;
-		goto err2;
+		error = -EFSCORRUPTED;
+		goto out_unreserve_dquot;
 	}
+
 	/*
 	 * Fill in the child block.
 	 */
@@ -775,11 +776,12 @@ xfs_bmap_extents_to_btree(
 	*logflagsp = XFS_ILOG_CORE | xfs_ilog_fbroot(whichfork);
 	return 0;
 
-err2:
+out_unreserve_dquot:
 	xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_BCOUNT, -1L);
-err1:
+out_root_realloc:
 	xfs_iroot_realloc(ip, -1, whichfork);
 	XFS_IFORK_FMT_SET(ip, whichfork, XFS_DINODE_FMT_EXTENTS);
+	ASSERT(ifp->if_broot == NULL);
 	xfs_btree_del_cursor(cur, XFS_BTREE_ERROR);
 
 	return error;

fs/xfs/libxfs/xfs_format.h

@@ -1016,6 +1016,8 @@ static inline void xfs_dinode_put_rdev(struct xfs_dinode *dip, xfs_dev_t rdev)
 #define XFS_DIFLAG_EXTSZINHERIT_BIT 12	/* inherit inode extent size */
 #define XFS_DIFLAG_NODEFRAG_BIT     13	/* do not reorganize/defragment */
 #define XFS_DIFLAG_FILESTREAM_BIT   14  /* use filestream allocator */
+/* Do not use bit 15, di_flags is legacy and unchanging now */
+
 #define XFS_DIFLAG_REALTIME      (1 << XFS_DIFLAG_REALTIME_BIT)
 #define XFS_DIFLAG_PREALLOC      (1 << XFS_DIFLAG_PREALLOC_BIT)
 #define XFS_DIFLAG_NEWRTBM       (1 << XFS_DIFLAG_NEWRTBM_BIT)

fs/xfs/libxfs/xfs_inode_buf.c

@@ -415,6 +415,31 @@ xfs_dinode_verify_fork(
 	return NULL;
 }
 
+static xfs_failaddr_t
+xfs_dinode_verify_forkoff(
+	struct xfs_dinode	*dip,
+	struct xfs_mount	*mp)
+{
+	if (!XFS_DFORK_Q(dip))
+		return NULL;
+
+	switch (dip->di_format)  {
+	case XFS_DINODE_FMT_DEV:
+		if (dip->di_forkoff != (roundup(sizeof(xfs_dev_t), 8) >> 3))
+			return __this_address;
+		break;
+	case XFS_DINODE_FMT_LOCAL:	/* fall through ... */
+	case XFS_DINODE_FMT_EXTENTS:    /* fall through ... */
+	case XFS_DINODE_FMT_BTREE:
+		if (dip->di_forkoff >= (XFS_LITINO(mp, dip->di_version) >> 3))
+			return __this_address;
+		break;
+	default:
+		return __this_address;
+	}
+	return NULL;
+}
+
 xfs_failaddr_t
 xfs_dinode_verify(
 	struct xfs_mount	*mp,
@@ -470,6 +495,11 @@ xfs_dinode_verify(
 	if (mode && (flags & XFS_DIFLAG_REALTIME) && !mp->m_rtdev_targp)
 		return __this_address;
 
+	/* check for illegal values of forkoff */
+	fa = xfs_dinode_verify_forkoff(dip, mp);
+	if (fa)
+		return fa;
+
 	/* Do we have appropriate data fork formats for the mode? */
 	switch (mode & S_IFMT) {
 	case S_IFIFO:

fs/xfs/scrub/alloc.c

@@ -17,7 +17,6 @@
 #include "xfs_sb.h"
 #include "xfs_alloc.h"
 #include "xfs_rmap.h"
-#include "xfs_alloc.h"
 #include "scrub/xfs_scrub.h"
 #include "scrub/scrub.h"
 #include "scrub/common.h"

fs/xfs/scrub/inode.c

@@ -126,6 +126,7 @@ xchk_inode_flags(
 {
 	struct xfs_mount	*mp = sc->mp;
 
+	/* di_flags are all taken, last bit cannot be used */
 	if (flags & ~XFS_DIFLAG_ANY)
 		goto bad;
 
@@ -172,8 +173,9 @@ xchk_inode_flags2(
 {
 	struct xfs_mount	*mp = sc->mp;
 
+	/* Unknown di_flags2 could be from a future kernel */
 	if (flags2 & ~XFS_DIFLAG2_ANY)
-		goto bad;
+		xchk_ino_set_warning(sc, ino);
 
 	/* reflink flag requires reflink feature */
 	if ((flags2 & XFS_DIFLAG2_REFLINK) &&

fs/xfs/xfs_bmap_util.c

@@ -702,13 +702,9 @@ xfs_bmap_punch_delalloc_range(
 	struct xfs_iext_cursor	icur;
 	int			error = 0;
 
-	xfs_ilock(ip, XFS_ILOCK_EXCL);
-	if (!(ifp->if_flags & XFS_IFEXTENTS)) {
-		error = xfs_iread_extents(NULL, ip, XFS_DATA_FORK);
-		if (error)
-			goto out_unlock;
-	}
+	ASSERT(ifp->if_flags & XFS_IFEXTENTS);
 
+	xfs_ilock(ip, XFS_ILOCK_EXCL);
 	if (!xfs_iext_lookup_extent_before(ip, ifp, &end_fsb, &icur, &got))
 		goto out_unlock;
 
@@ -1584,7 +1580,7 @@ xfs_swap_extent_rmap(
 					tirec.br_blockcount, &irec,
 					&nimaps, 0);
 			if (error)
-				goto out_defer;
+				goto out;
 			ASSERT(nimaps == 1);
 			ASSERT(tirec.br_startoff == irec.br_startoff);
 			trace_xfs_swap_extent_rmap_remap_piece(ip, &irec);
@@ -1599,22 +1595,22 @@ xfs_swap_extent_rmap(
 			/* Remove the mapping from the donor file. */
 			error = xfs_bmap_unmap_extent(tp, tip, &uirec);
 			if (error)
-				goto out_defer;
+				goto out;
 
 			/* Remove the mapping from the source file. */
 			error = xfs_bmap_unmap_extent(tp, ip, &irec);
 			if (error)
-				goto out_defer;
+				goto out;
 
 			/* Map the donor file's blocks into the source file. */
 			error = xfs_bmap_map_extent(tp, ip, &uirec);
 			if (error)
-				goto out_defer;
+				goto out;
 
 			/* Map the source file's blocks into the donor file. */
 			error = xfs_bmap_map_extent(tp, tip, &irec);
 			if (error)
-				goto out_defer;
+				goto out;
 
 			error = xfs_defer_finish(tpp);
 			tp = *tpp;
@@ -1636,8 +1632,6 @@ xfs_swap_extent_rmap(
 	tip->i_d.di_flags2 = tip_flags2;
 	return 0;
 
-out_defer:
-	xfs_defer_cancel(tp);
 out:
 	trace_xfs_swap_extent_rmap_error(ip, error, _RET_IP_);
 	tip->i_d.di_flags2 = tip_flags2;

fs/xfs/xfs_buf_item.c

@@ -531,6 +531,49 @@ xfs_buf_item_push(
 	return rval;
 }
 
+/*
+ * Drop the buffer log item refcount and take appropriate action. This helper
+ * determines whether the bli must be freed or not, since a decrement to zero
+ * does not necessarily mean the bli is unused.
+ *
+ * Return true if the bli is freed, false otherwise.
+ */
+bool
+xfs_buf_item_put(
+	struct xfs_buf_log_item	*bip)
+{
+	struct xfs_log_item	*lip = &bip->bli_item;
+	bool			aborted;
+	bool			dirty;
+
+	/* drop the bli ref and return if it wasn't the last one */
+	if (!atomic_dec_and_test(&bip->bli_refcount))
+		return false;
+
+	/*
+	 * We dropped the last ref and must free the item if clean or aborted.
+	 * If the bli is dirty and non-aborted, the buffer was clean in the
+	 * transaction but still awaiting writeback from previous changes. In
+	 * that case, the bli is freed on buffer writeback completion.
+	 */
+	aborted = test_bit(XFS_LI_ABORTED, &lip->li_flags) ||
+		  XFS_FORCED_SHUTDOWN(lip->li_mountp);
+	dirty = bip->bli_flags & XFS_BLI_DIRTY;
+	if (dirty && !aborted)
+		return false;
+
+	/*
+	 * The bli is aborted or clean. An aborted item may be in the AIL
+	 * regardless of dirty state.  For example, consider an aborted
+	 * transaction that invalidated a dirty bli and cleared the dirty
+	 * state.
+	 */
+	if (aborted)
+		xfs_trans_ail_remove(lip, SHUTDOWN_LOG_IO_ERROR);
+	xfs_buf_item_relse(bip->bli_buf);
+	return true;
+}
+
 /*
  * Release the buffer associated with the buf log item.  If there is no dirty
  * logged data associated with the buffer recorded in the buf log item, then
@@ -556,76 +599,42 @@ xfs_buf_item_unlock(
 {
 	struct xfs_buf_log_item	*bip = BUF_ITEM(lip);
 	struct xfs_buf		*bp = bip->bli_buf;
-	bool			aborted;
-	bool			hold = !!(bip->bli_flags & XFS_BLI_HOLD);
-	bool			dirty = !!(bip->bli_flags & XFS_BLI_DIRTY);
+	bool			released;
+	bool			hold = bip->bli_flags & XFS_BLI_HOLD;
+	bool			stale = bip->bli_flags & XFS_BLI_STALE;
 #if defined(DEBUG) || defined(XFS_WARN)
-	bool			ordered = !!(bip->bli_flags & XFS_BLI_ORDERED);
+	bool			ordered = bip->bli_flags & XFS_BLI_ORDERED;
+	bool			dirty = bip->bli_flags & XFS_BLI_DIRTY;
 #endif
 
-	aborted = test_bit(XFS_LI_ABORTED, &lip->li_flags);
-
-	/* Clear the buffer's association with this transaction. */
-	bp->b_transp = NULL;
-
-	/*
-	 * The per-transaction state has been copied above so clear it from the
-	 * bli.
-	 */
-	bip->bli_flags &= ~(XFS_BLI_LOGGED | XFS_BLI_HOLD | XFS_BLI_ORDERED);
-
-	/*
-	 * If the buf item is marked stale, then don't do anything.  We'll
-	 * unlock the buffer and free the buf item when the buffer is unpinned
-	 * for the last time.
-	 */
-	if (bip->bli_flags & XFS_BLI_STALE) {
-		trace_xfs_buf_item_unlock_stale(bip);
-		ASSERT(bip->__bli_format.blf_flags & XFS_BLF_CANCEL);
-		if (!aborted) {
-			atomic_dec(&bip->bli_refcount);
-			return;
-		}
-	}
-
 	trace_xfs_buf_item_unlock(bip);
 
 	/*
-	 * If the buf item isn't tracking any data, free it, otherwise drop the
-	 * reference we hold to it. If we are aborting the transaction, this may
-	 * be the only reference to the buf item, so we free it anyway
-	 * regardless of whether it is dirty or not. A dirty abort implies a
-	 * shutdown, anyway.
-	 *
 	 * The bli dirty state should match whether the blf has logged segments
 	 * except for ordered buffers, where only the bli should be dirty.
 	 */
 	ASSERT((!ordered && dirty == xfs_buf_item_dirty_format(bip)) ||
 	       (ordered && dirty && !xfs_buf_item_dirty_format(bip)));
+	ASSERT(!stale || (bip->__bli_format.blf_flags & XFS_BLF_CANCEL));
 
 	/*
-	 * Clean buffers, by definition, cannot be in the AIL. However, aborted
-	 * buffers may be in the AIL regardless of dirty state. An aborted
-	 * transaction that invalidates a buffer already in the AIL may have
-	 * marked it stale and cleared the dirty state, for example.
-	 *
-	 * Therefore if we are aborting a buffer and we've just taken the last
-	 * reference away, we have to check if it is in the AIL before freeing
-	 * it. We need to free it in this case, because an aborted transaction
-	 * has already shut the filesystem down and this is the last chance we
-	 * will have to do so.
+	 * Clear the buffer's association with this transaction and
+	 * per-transaction state from the bli, which has been copied above.
 	 */
-	if (atomic_dec_and_test(&bip->bli_refcount)) {
-		if (aborted) {
-			ASSERT(XFS_FORCED_SHUTDOWN(lip->li_mountp));
-			xfs_trans_ail_remove(lip, SHUTDOWN_LOG_IO_ERROR);
-			xfs_buf_item_relse(bp);
-		} else if (!dirty)
-			xfs_buf_item_relse(bp);
-	}
+	bp->b_transp = NULL;
+	bip->bli_flags &= ~(XFS_BLI_LOGGED | XFS_BLI_HOLD | XFS_BLI_ORDERED);
 
-	if (!hold)
-		xfs_buf_relse(bp);
+	/*
+	 * Unref the item and unlock the buffer unless held or stale. Stale
+	 * buffers remain locked until final unpin unless the bli is freed by
+	 * the unref call. The latter implies shutdown because buffer
+	 * invalidation dirties the bli and transaction.
+	 */
+	released = xfs_buf_item_put(bip);
+	if (hold || (stale && !released))
+		return;
+	ASSERT(!stale || test_bit(XFS_LI_ABORTED, &lip->li_flags));
+	xfs_buf_relse(bp);
 }
 
 /*

fs/xfs/xfs_buf_item.h

@@ -51,6 +51,7 @@ struct xfs_buf_log_item {
 
 int	xfs_buf_item_init(struct xfs_buf *, struct xfs_mount *);
 void	xfs_buf_item_relse(struct xfs_buf *);
+bool	xfs_buf_item_put(struct xfs_buf_log_item *);
 void	xfs_buf_item_log(struct xfs_buf_log_item *, uint, uint);
 bool	xfs_buf_item_dirty_format(struct xfs_buf_log_item *);
 void	xfs_buf_attach_iodone(struct xfs_buf *,

fs/xfs/xfs_inode.c

@@ -1563,7 +1563,7 @@ xfs_itruncate_extents_flags(
 		error = xfs_bunmapi(tp, ip, first_unmap_block, unmap_len, flags,
 				    XFS_ITRUNC_MAX_EXTENTS, &done);
 		if (error)
-			goto out_bmap_cancel;
+			goto out;
 
 		/*
 		 * Duplicate the transaction that has the permanent
@@ -1599,14 +1599,6 @@ xfs_itruncate_extents_flags(
 out:
 	*tpp = tp;
 	return error;
-out_bmap_cancel:
-	/*
-	 * If the bunmapi call encounters an error, return to the caller where
-	 * the transaction can be properly aborted.  We just need to make sure
-	 * we're not holding any resources that we were not when we came in.
-	 */
-	xfs_defer_cancel(tp);
-	goto out;
 }
 
 int

fs/xfs/xfs_iops.c

@@ -471,8 +471,18 @@ xfs_vn_get_link_inline(
 	struct inode		*inode,
 	struct delayed_call	*done)
 {
+	char			*link;
+
 	ASSERT(XFS_I(inode)->i_df.if_flags & XFS_IFINLINE);
-	return XFS_I(inode)->i_df.if_u1.if_data;
+
+	/*
+	 * The VFS crashes on a NULL pointer, so return -EFSCORRUPTED if
+	 * if_data is junk.
+	 */
+	link = XFS_I(inode)->i_df.if_u1.if_data;
+	if (!link)
+		return ERR_PTR(-EFSCORRUPTED);
+	return link;
 }
 
 STATIC int

fs/xfs/xfs_log_recover.c

@@ -1570,16 +1570,6 @@ xlog_find_zeroed(
 	if (last_cycle != 0) {		/* log completely written to */
 		xlog_put_bp(bp);
 		return 0;
-	} else if (first_cycle != 1) {
-		/*
-		 * If the cycle of the last block is zero, the cycle of
-		 * the first block must be 1. If it's not, maybe we're
-		 * not looking at a log... Bail out.
-		 */
-		xfs_warn(log->l_mp,
-			"Log inconsistent or not a log (last==0, first!=1)");
-		error = -EINVAL;
-		goto bp_err;
 	}
 
 	/* we have a partially zeroed log */

fs/xfs/xfs_reflink.c

@@ -352,6 +352,47 @@ xfs_reflink_convert_cow(
 	return error;
 }
 
+/*
+ * Find the extent that maps the given range in the COW fork. Even if the extent
+ * is not shared we might have a preallocation for it in the COW fork. If so we
+ * use it that rather than trigger a new allocation.
+ */
+static int
+xfs_find_trim_cow_extent(
+	struct xfs_inode	*ip,
+	struct xfs_bmbt_irec	*imap,
+	bool			*shared,
+	bool			*found)
+{
+	xfs_fileoff_t		offset_fsb = imap->br_startoff;
+	xfs_filblks_t		count_fsb = imap->br_blockcount;
+	struct xfs_iext_cursor	icur;
+	struct xfs_bmbt_irec	got;
+	bool			trimmed;
+
+	*found = false;
+
+	/*
+	 * If we don't find an overlapping extent, trim the range we need to
+	 * allocate to fit the hole we found.
+	 */
+	if (!xfs_iext_lookup_extent(ip, ip->i_cowfp, offset_fsb, &icur, &got) ||
+	    got.br_startoff > offset_fsb)
+		return xfs_reflink_trim_around_shared(ip, imap, shared, &trimmed);
+
+	*shared = true;
+	if (isnullstartblock(got.br_startblock)) {
+		xfs_trim_extent(imap, got.br_startoff, got.br_blockcount);
+		return 0;
+	}
+
+	/* real extent found - no need to allocate */
+	xfs_trim_extent(&got, offset_fsb, count_fsb);
+	*imap = got;
+	*found = true;
+	return 0;
+}
+
 /* Allocate all CoW reservations covering a range of blocks in a file. */
 int
 xfs_reflink_allocate_cow(
@@ -363,78 +404,64 @@ xfs_reflink_allocate_cow(
 	struct xfs_mount	*mp = ip->i_mount;
 	xfs_fileoff_t		offset_fsb = imap->br_startoff;
 	xfs_filblks_t		count_fsb = imap->br_blockcount;
-	struct xfs_bmbt_irec	got;
-	struct xfs_trans	*tp = NULL;
+	struct xfs_trans	*tp;
 	int			nimaps, error = 0;
-	bool			trimmed;
+	bool			found;
 	xfs_filblks_t		resaligned;
 	xfs_extlen_t		resblks = 0;
-	struct xfs_iext_cursor	icur;
 
-retry:
-	ASSERT(xfs_is_reflink_inode(ip));
 	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
+	ASSERT(xfs_is_reflink_inode(ip));
 
-	/*
-	 * Even if the extent is not shared we might have a preallocation for
-	 * it in the COW fork.  If so use it.
-	 */
-	if (xfs_iext_lookup_extent(ip, ip->i_cowfp, offset_fsb, &icur, &got) &&
-	    got.br_startoff <= offset_fsb) {
-		*shared = true;
-
-		/* If we have a real allocation in the COW fork we're done. */
-		if (!isnullstartblock(got.br_startblock)) {
-			xfs_trim_extent(&got, offset_fsb, count_fsb);
-			*imap = got;
-			goto convert;
-		}
+	error = xfs_find_trim_cow_extent(ip, imap, shared, &found);
+	if (error || !*shared)
+		return error;
+	if (found)
+		goto convert;
 
-		xfs_trim_extent(imap, got.br_startoff, got.br_blockcount);
-	} else {
-		error = xfs_reflink_trim_around_shared(ip, imap, shared, &trimmed);
-		if (error || !*shared)
-			goto out;
-	}
+	resaligned = xfs_aligned_fsb_count(imap->br_startoff,
+		imap->br_blockcount, xfs_get_cowextsz_hint(ip));
+	resblks = XFS_DIOSTRAT_SPACE_RES(mp, resaligned);
 
-	if (!tp) {
-		resaligned = xfs_aligned_fsb_count(imap->br_startoff,
-			imap->br_blockcount, xfs_get_cowextsz_hint(ip));
-		resblks = XFS_DIOSTRAT_SPACE_RES(mp, resaligned);
+	xfs_iunlock(ip, *lockmode);
+	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, resblks, 0, 0, &tp);
+	*lockmode = XFS_ILOCK_EXCL;
+	xfs_ilock(ip, *lockmode);
 
-		xfs_iunlock(ip, *lockmode);
-		error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, resblks, 0, 0, &tp);
-		*lockmode = XFS_ILOCK_EXCL;
-		xfs_ilock(ip, *lockmode);
+	if (error)
+		return error;
 
-		if (error)
-			return error;
+	error = xfs_qm_dqattach_locked(ip, false);
+	if (error)
+		goto out_trans_cancel;
 
-		error = xfs_qm_dqattach_locked(ip, false);
-		if (error)
-			goto out;
-		goto retry;
+	/*
+	 * Check for an overlapping extent again now that we dropped the ilock.
+	 */
+	error = xfs_find_trim_cow_extent(ip, imap, shared, &found);
+	if (error || !*shared)
+		goto out_trans_cancel;
+	if (found) {
+		xfs_trans_cancel(tp);
+		goto convert;
 	}
 
 	error = xfs_trans_reserve_quota_nblks(tp, ip, resblks, 0,
 			XFS_QMOPT_RES_REGBLKS);
 	if (error)
-		goto out;
+		goto out_trans_cancel;
 
 	xfs_trans_ijoin(tp, ip, 0);
 
-	nimaps = 1;
-
 	/* Allocate the entire reservation as unwritten blocks. */
+	nimaps = 1;
 	error = xfs_bmapi_write(tp, ip, imap->br_startoff, imap->br_blockcount,
 			XFS_BMAPI_COWFORK | XFS_BMAPI_PREALLOC,
 			resblks, imap, &nimaps);
 	if (error)
-		goto out_trans_cancel;
+		goto out_unreserve;
 
 	xfs_inode_set_cowblocks_tag(ip);
-
-	/* Finish up. */
 	error = xfs_trans_commit(tp);
 	if (error)
 		return error;
@@ -447,12 +474,12 @@ retry:
 		return -ENOSPC;
 convert:
 	return xfs_reflink_convert_cow_extent(ip, imap, offset_fsb, count_fsb);
-out_trans_cancel:
+
+out_unreserve:
 	xfs_trans_unreserve_quota_nblks(tp, ip, (long)resblks, 0,
 			XFS_QMOPT_RES_REGBLKS);
-out:
-	if (tp)
-		xfs_trans_cancel(tp);
+out_trans_cancel:
+	xfs_trans_cancel(tp);
 	return error;
 }
 
@@ -666,14 +693,12 @@ xfs_reflink_end_cow(
 		if (!del.br_blockcount)
 			goto prev_extent;
 
-		ASSERT(!isnullstartblock(got.br_startblock));
-
 		/*
-		 * Don't remap unwritten extents; these are
-		 * speculatively preallocated CoW extents that have been
-		 * allocated but have not yet been involved in a write.
+		 * Only remap real extent that contain data.  With AIO
+		 * speculatively preallocations can leak into the range we
+		 * are called upon, and we need to skip them.
 		 */
-		if (got.br_state == XFS_EXT_UNWRITTEN)
+		if (!xfs_bmap_is_real_extent(&got))
 			goto prev_extent;
 
 		/* Unmap the old blocks in the data fork. */

fs/xfs/xfs_trace.h

@@ -473,7 +473,6 @@ DEFINE_BUF_ITEM_EVENT(xfs_buf_item_pin);
 DEFINE_BUF_ITEM_EVENT(xfs_buf_item_unpin);
 DEFINE_BUF_ITEM_EVENT(xfs_buf_item_unpin_stale);
 DEFINE_BUF_ITEM_EVENT(xfs_buf_item_unlock);
-DEFINE_BUF_ITEM_EVENT(xfs_buf_item_unlock_stale);
 DEFINE_BUF_ITEM_EVENT(xfs_buf_item_committed);
 DEFINE_BUF_ITEM_EVENT(xfs_buf_item_push);
 DEFINE_BUF_ITEM_EVENT(xfs_trans_get_buf);

fs/xfs/xfs_trans.c

@@ -259,6 +259,14 @@ xfs_trans_alloc(
 	struct xfs_trans	*tp;
 	int			error;
 
+	/*
+	 * Allocate the handle before we do our freeze accounting and setting up
+	 * GFP_NOFS allocation context so that we avoid lockdep false positives
+	 * by doing GFP_KERNEL allocations inside sb_start_intwrite().
+	 */
+	tp = kmem_zone_zalloc(xfs_trans_zone,
+		(flags & XFS_TRANS_NOFS) ? KM_NOFS : KM_SLEEP);
+
 	if (!(flags & XFS_TRANS_NO_WRITECOUNT))
 		sb_start_intwrite(mp->m_super);
 
@@ -270,8 +278,6 @@ xfs_trans_alloc(
 		mp->m_super->s_writers.frozen == SB_FREEZE_COMPLETE);
 	atomic_inc(&mp->m_active_trans);
 
-	tp = kmem_zone_zalloc(xfs_trans_zone,
-		(flags & XFS_TRANS_NOFS) ? KM_NOFS : KM_SLEEP);
 	tp->t_magic = XFS_TRANS_HEADER_MAGIC;
 	tp->t_flags = flags;
 	tp->t_mountp = mp;

fs/xfs/xfs_trans_buf.c

@@ -322,49 +322,38 @@ xfs_trans_read_buf_map(
 }
 
 /*
- * Release the buffer bp which was previously acquired with one of the
- * xfs_trans_... buffer allocation routines if the buffer has not
- * been modified within this transaction.  If the buffer is modified
- * within this transaction, do decrement the recursion count but do
- * not release the buffer even if the count goes to 0.  If the buffer is not
- * modified within the transaction, decrement the recursion count and
- * release the buffer if the recursion count goes to 0.
+ * Release a buffer previously joined to the transaction. If the buffer is
+ * modified within this transaction, decrement the recursion count but do not
+ * release the buffer even if the count goes to 0. If the buffer is not modified
+ * within the transaction, decrement the recursion count and release the buffer
+ * if the recursion count goes to 0.
  *
- * If the buffer is to be released and it was not modified before
- * this transaction began, then free the buf_log_item associated with it.
+ * If the buffer is to be released and it was not already dirty before this
+ * transaction began, then also free the buf_log_item associated with it.
  *
- * If the transaction pointer is NULL, make this just a normal
- * brelse() call.
+ * If the transaction pointer is NULL, this is a normal xfs_buf_relse() call.
  */
 void
 xfs_trans_brelse(
-	xfs_trans_t		*tp,
-	xfs_buf_t		*bp)
+	struct xfs_trans	*tp,
+	struct xfs_buf		*bp)
 {
-	struct xfs_buf_log_item	*bip;
-	int			freed;
+	struct xfs_buf_log_item	*bip = bp->b_log_item;
 
-	/*
-	 * Default to a normal brelse() call if the tp is NULL.
-	 */
-	if (tp == NULL) {
-		ASSERT(bp->b_transp == NULL);
+	ASSERT(bp->b_transp == tp);
+
+	if (!tp) {
 		xfs_buf_relse(bp);
 		return;
 	}
 
-	ASSERT(bp->b_transp == tp);
-	bip = bp->b_log_item;
+	trace_xfs_trans_brelse(bip);
 	ASSERT(bip->bli_item.li_type == XFS_LI_BUF);
-	ASSERT(!(bip->bli_flags & XFS_BLI_STALE));
-	ASSERT(!(bip->__bli_format.blf_flags & XFS_BLF_CANCEL));
 	ASSERT(atomic_read(&bip->bli_refcount) > 0);
 
-	trace_xfs_trans_brelse(bip);
-
 	/*
-	 * If the release is just for a recursive lock,
-	 * then decrement the count and return.
+	 * If the release is for a recursive lookup, then decrement the count
+	 * and return.
 	 */
 	if (bip->bli_recur > 0) {
 		bip->bli_recur--;
@@ -372,64 +361,24 @@ xfs_trans_brelse(
 	}
 
 	/*
-	 * If the buffer is dirty within this transaction, we can't
+	 * If the buffer is invalidated or dirty in this transaction, we can't
 	 * release it until we commit.
 	 */
 	if (test_bit(XFS_LI_DIRTY, &bip->bli_item.li_flags))
 		return;
-
-	/*
-	 * If the buffer has been invalidated, then we can't release
-	 * it until the transaction commits to disk unless it is re-dirtied
-	 * as part of this transaction.  This prevents us from pulling
-	 * the item from the AIL before we should.
-	 */
 	if (bip->bli_flags & XFS_BLI_STALE)
 		return;
 
-	ASSERT(!(bip->bli_flags & XFS_BLI_LOGGED));
-
 	/*
-	 * Free up the log item descriptor tracking the released item.
+	 * Unlink the log item from the transaction and clear the hold flag, if
+	 * set. We wouldn't want the next user of the buffer to get confused.
 	 */
+	ASSERT(!(bip->bli_flags & XFS_BLI_LOGGED));
 	xfs_trans_del_item(&bip->bli_item);
+	bip->bli_flags &= ~XFS_BLI_HOLD;
 
-	/*
-	 * Clear the hold flag in the buf log item if it is set.
-	 * We wouldn't want the next user of the buffer to
-	 * get confused.
-	 */
-	if (bip->bli_flags & XFS_BLI_HOLD) {
-		bip->bli_flags &= ~XFS_BLI_HOLD;
-	}
-
-	/*
-	 * Drop our reference to the buf log item.
-	 */
-	freed = atomic_dec_and_test(&bip->bli_refcount);
-
-	/*
-	 * If the buf item is not tracking data in the log, then we must free it
-	 * before releasing the buffer back to the free pool.
-	 *
-	 * If the fs has shutdown and we dropped the last reference, it may fall
-	 * on us to release a (possibly dirty) bli if it never made it to the
-	 * AIL (e.g., the aborted unpin already happened and didn't release it
-	 * due to our reference). Since we're already shutdown and need
-	 * ail_lock, just force remove from the AIL and release the bli here.
-	 */
-	if (XFS_FORCED_SHUTDOWN(tp->t_mountp) && freed) {
-		xfs_trans_ail_remove(&bip->bli_item, SHUTDOWN_LOG_IO_ERROR);
-		xfs_buf_item_relse(bp);
-	} else if (!(bip->bli_flags & XFS_BLI_DIRTY)) {
-/***
-		ASSERT(bp->b_pincount == 0);
-***/
-		ASSERT(atomic_read(&bip->bli_refcount) == 0);
-		ASSERT(!test_bit(XFS_LI_IN_AIL, &bip->bli_item.li_flags));
-		ASSERT(!(bip->bli_flags & XFS_BLI_INODE_ALLOC_BUF));
-		xfs_buf_item_relse(bp);
-	}
+	/* drop the reference to the bli */
+	xfs_buf_item_put(bip);
 
 	bp->b_transp = NULL;
 	xfs_buf_relse(bp);