1 files changed, 57 insertions, 192 deletions

diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 2bfbcf28b1bd..b7352bc4c815 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -761,68 +761,26 @@ xfs_inode_inherit_flags2(
 }
 
 /*
- * Allocate an inode on disk and return a copy of its in-core version.
- * The in-core inode is locked exclusively.  Set mode, nlink, and rdev
- * appropriately within the inode.  The uid and gid for the inode are
- * set according to the contents of the given cred structure.
- *
- * Use xfs_dialloc() to allocate the on-disk inode. If xfs_dialloc()
- * has a free inode available, call xfs_iget() to obtain the in-core
- * version of the allocated inode.  Finally, fill in the inode and
- * log its initial contents.  In this case, ialloc_context would be
- * set to NULL.
- *
- * If xfs_dialloc() does not have an available inode, it will replenish
- * its supply by doing an allocation. Since we can only do one
- * allocation within a transaction without deadlocks, we must commit
- * the current transaction before returning the inode itself.
- * In this case, therefore, we will set ialloc_context and return.
- * The caller should then commit the current transaction, start a new
- * transaction, and call xfs_ialloc() again to actually get the inode.
- *
- * To ensure that some other process does not grab the inode that
- * was allocated during the first call to xfs_ialloc(), this routine
- * also returns the [locked] bp pointing to the head of the freelist
- * as ialloc_context.  The caller should hold this buffer across
- * the commit and pass it back into this routine on the second call.
- *
- * If we are allocating quota inodes, we do not have a parent inode
- * to attach to or associate with (i.e. pip == NULL) because they
- * are not linked into the directory structure - they are attached
- * directly to the superblock - and so have no parent.
+ * Initialise a newly allocated inode and return the in-core inode to the
+ * caller locked exclusively.
  */
 static int
-xfs_ialloc(
-	xfs_trans_t	*tp,
-	xfs_inode_t	*pip,
-	umode_t		mode,
-	xfs_nlink_t	nlink,
-	dev_t		rdev,
-	prid_t		prid,
-	xfs_buf_t	**ialloc_context,
-	xfs_inode_t	**ipp)
-{
-	struct xfs_mount *mp = tp->t_mountp;
-	xfs_ino_t	ino;
-	xfs_inode_t	*ip;
-	uint		flags;
-	int		error;
-	struct timespec64 tv;
-	struct inode	*inode;
-
-	/*
-	 * Call the space management code to pick
-	 * the on-disk inode to be allocated.
-	 */
-	error = xfs_dialloc(tp, pip ? pip->i_ino : 0, mode,
-			    ialloc_context, &ino);
-	if (error)
-		return error;
-	if (*ialloc_context || ino == NULLFSINO) {
-		*ipp = NULL;
-		return 0;
-	}
-	ASSERT(*ialloc_context == NULL);
+xfs_init_new_inode(
+	struct xfs_trans	*tp,
+	struct xfs_inode	*pip,
+	xfs_ino_t		ino,
+	umode_t			mode,
+	xfs_nlink_t		nlink,
+	dev_t			rdev,
+	prid_t			prid,
+	struct xfs_inode	**ipp)
+{
+	struct xfs_mount	*mp = tp->t_mountp;
+	struct xfs_inode	*ip;
+	unsigned int		flags;
+	int			error;
+	struct timespec64	tv;
+	struct inode		*inode;
 
 	/*
 	 * Protect against obviously corrupt allocation btree records. Later
@@ -837,14 +795,13 @@ xfs_ialloc(
 	}
 
 	/*
-	 * Get the in-core inode with the lock held exclusively.
-	 * This is because we're setting fields here we need
-	 * to prevent others from looking at until we're done.
+	 * Get the in-core inode with the lock held exclusively to prevent
+	 * others from looking at until we're done.
 	 */
-	error = xfs_iget(mp, tp, ino, XFS_IGET_CREATE,
-			 XFS_ILOCK_EXCL, &ip);
+	error = xfs_iget(mp, tp, ino, XFS_IGET_CREATE, XFS_ILOCK_EXCL, &ip);
 	if (error)
 		return error;
+
 	ASSERT(ip != NULL);
 	inode = VFS_I(ip);
 	inode->i_mode = mode;
@@ -932,143 +889,51 @@ xfs_ialloc(
 }
 
 /*
- * Allocates a new inode from disk and return a pointer to the
- * incore copy. This routine will internally commit the current
- * transaction and allocate a new one if the Space Manager needed
- * to do an allocation to replenish the inode free-list.
- *
- * This routine is designed to be called from xfs_create and
- * xfs_create_dir.
+ * Allocates a new inode from disk and return a pointer to the incore copy. This
+ * routine will internally commit the current transaction and allocate a new one
+ * if we needed to allocate more on-disk free inodes to perform the requested
+ * operation.
  *
+ * If we are allocating quota inodes, we do not have a parent inode to attach to
+ * or associate with (i.e. dp == NULL) because they are not linked into the
+ * directory structure - they are attached directly to the superblock - and so
+ * have no parent.
  */
 int
 xfs_dir_ialloc(
-	xfs_trans_t	**tpp,		/* input: current transaction;
-					   output: may be a new transaction. */
-	xfs_inode_t	*dp,		/* directory within whose allocate
-					   the inode. */
-	umode_t		mode,
-	xfs_nlink_t	nlink,
-	dev_t		rdev,
-	prid_t		prid,		/* project id */
-	xfs_inode_t	**ipp)		/* pointer to inode; it will be
-					   locked. */
-{
-	xfs_trans_t	*tp;
-	xfs_inode_t	*ip;
-	xfs_buf_t	*ialloc_context = NULL;
-	int		code;
-	void		*dqinfo;
-	uint		tflags;
-
-	tp = *tpp;
-	ASSERT(tp->t_flags & XFS_TRANS_PERM_LOG_RES);
+	struct xfs_trans	**tpp,
+	struct xfs_inode	*dp,
+	umode_t			mode,
+	xfs_nlink_t		nlink,
+	dev_t			rdev,
+	prid_t			prid,
+	struct xfs_inode	**ipp)
+{
+	struct xfs_buf		*agibp;
+	xfs_ino_t		parent_ino = dp ? dp->i_ino : 0;
+	xfs_ino_t		ino;
+	int			error;
 
-	/*
-	 * xfs_ialloc will return a pointer to an incore inode if
-	 * the Space Manager has an available inode on the free
-	 * list. Otherwise, it will do an allocation and replenish
-	 * the freelist.  Since we can only do one allocation per
-	 * transaction without deadlocks, we will need to commit the
-	 * current transaction and start a new one.  We will then
-	 * need to call xfs_ialloc again to get the inode.
-	 *
-	 * If xfs_ialloc did an allocation to replenish the freelist,
-	 * it returns the bp containing the head of the freelist as
-	 * ialloc_context. We will hold a lock on it across the
-	 * transaction commit so that no other process can steal
-	 * the inode(s) that we've just allocated.
-	 */
-	code = xfs_ialloc(tp, dp, mode, nlink, rdev, prid, &ialloc_context,
-			&ip);
+	ASSERT((*tpp)->t_flags & XFS_TRANS_PERM_LOG_RES);
 
 	/*
-	 * Return an error if we were unable to allocate a new inode.
-	 * This should only happen if we run out of space on disk or
-	 * encounter a disk error.
+	 * Call the space management code to pick the on-disk inode to be
+	 * allocated.
 	 */
-	if (code) {
-		*ipp = NULL;
-		return code;
-	}
-	if (!ialloc_context && !ip) {
-		*ipp = NULL;
-		return -ENOSPC;
-	}
-
-	/*
-	 * If the AGI buffer is non-NULL, then we were unable to get an
-	 * inode in one operation.  We need to commit the current
-	 * transaction and call xfs_ialloc() again.  It is guaranteed
-	 * to succeed the second time.
-	 */
-	if (ialloc_context) {
-		/*
-		 * Normally, xfs_trans_commit releases all the locks.
-		 * We call bhold to hang on to the ialloc_context across
-		 * the commit.  Holding this buffer prevents any other
-		 * processes from doing any allocations in this
-		 * allocation group.
-		 */
-		xfs_trans_bhold(tp, ialloc_context);
-
-		/*
-		 * We want the quota changes to be associated with the next
-		 * transaction, NOT this one. So, detach the dqinfo from this
-		 * and attach it to the next transaction.
-		 */
-		dqinfo = NULL;
-		tflags = 0;
-		if (tp->t_dqinfo) {
-			dqinfo = (void *)tp->t_dqinfo;
-			tp->t_dqinfo = NULL;
-			tflags = tp->t_flags & XFS_TRANS_DQ_DIRTY;
-			tp->t_flags &= ~(XFS_TRANS_DQ_DIRTY);
-		}
-
-		code = xfs_trans_roll(&tp);
-
-		/*
-		 * Re-attach the quota info that we detached from prev trx.
-		 */
-		if (dqinfo) {
-			tp->t_dqinfo = dqinfo;
-			tp->t_flags |= tflags;
-		}
-
-		if (code) {
-			xfs_buf_relse(ialloc_context);
-			*tpp = tp;
-			*ipp = NULL;
-			return code;
-		}
-		xfs_trans_bjoin(tp, ialloc_context);
-
-		/*
-		 * Call ialloc again. Since we've locked out all
-		 * other allocations in this allocation group,
-		 * this call should always succeed.
-		 */
-		code = xfs_ialloc(tp, dp, mode, nlink, rdev, prid,
-				  &ialloc_context, &ip);
-
-		/*
-		 * If we get an error at this point, return to the caller
-		 * so that the current transaction can be aborted.
-		 */
-		if (code) {
-			*tpp = tp;
-			*ipp = NULL;
-			return code;
-		}
-		ASSERT(!ialloc_context && ip);
+	error = xfs_dialloc_select_ag(tpp, parent_ino, mode, &agibp);
+	if (error)
+		return error;
 
-	}
+	if (!agibp)
+		return -ENOSPC;
 
-	*ipp = ip;
-	*tpp = tp;
+	/* Allocate an inode from the selected AG */
+	error = xfs_dialloc_ag(*tpp, agibp, parent_ino, &ino);
+	if (error)
+		return error;
+	ASSERT(ino != NULLFSINO);
 
-	return 0;
+	return xfs_init_new_inode(*tpp, dp, ino, mode, nlink, rdev, prid, ipp);
 }
 
 /*
@@ -1521,7 +1386,7 @@ xfs_itruncate_extents_flags(
 	 * the page cache can't scale that far.
 	 */
 	first_unmap_block = XFS_B_TO_FSB(mp, (xfs_ufsize_t)new_size);
-	if (first_unmap_block >= XFS_MAX_FILEOFF) {
+	if (!xfs_verify_fileoff(mp, first_unmap_block)) {
 		WARN_ON_ONCE(first_unmap_block > XFS_MAX_FILEOFF);
 		return 0;
 	}