Merge tag 'for-linus-v3.8-rc6' of git://oss.sgi.com/xfs/xfs

Pull xfs bugfixes from Ben Myers:
 "Here are fixes for returning EFSCORRUPTED on probe of a non-xfs
  filesystem, the stack switch in xfs_bmapi_allocate, a crash in
  _xfs_buf_find, speculative preallocation as the filesystem nears
  ENOSPC, an unmount hang, a race with AIO, and a regression with
  xfs_fsr:

   - fix return value when filesystem probe finds no XFS magic, a
     regression introduced in 9802182.

   - fix stack switch in __xfs_bmapi_allocate by moving the check for
     stack switch up into xfs_bmapi_write.

   - fix oops in _xfs_buf_find by validating that the requested block is
     within the filesystem bounds.

   - limit speculative preallocation near ENOSPC.

   - fix an unmount hang in xfs_wait_buftarg by freeing the
     xfs_buf_log_item in xfs_buf_item_unlock.

   - fix a possible use after free with AIO.

   - fix xfs_swap_extents after removal of xfs_flushinval_pages, a
     regression introduced in commit fb59581."

* tag 'for-linus-v3.8-rc6' of git://oss.sgi.com/xfs/xfs:
  xfs: Fix xfs_swap_extents() after removal of xfs_flushinval_pages()
  xfs: Fix possible use-after-free with AIO
  xfs: fix shutdown hang on invalid inode during create
  xfs: limit speculative prealloc near ENOSPC thresholds
  xfs: fix _xfs_buf_find oops on blocks beyond the filesystem end
  xfs: pull up stack_switch check into xfs_bmapi_write
  xfs: Do not return EFSCORRUPTED when filesystem probe finds no XFS magic

fs/xfs/xfs_aops.c

@@ -86,11 +86,11 @@ xfs_destroy_ioend(
 	}
 
 	if (ioend->io_iocb) {
+		inode_dio_done(ioend->io_inode);
 		if (ioend->io_isasync) {
 			aio_complete(ioend->io_iocb, ioend->io_error ?
 					ioend->io_error : ioend->io_result, 0);
 		}
-		inode_dio_done(ioend->io_inode);
 	}
 
 	mempool_free(ioend, xfs_ioend_pool);

fs/xfs/xfs_bmap.c

@@ -4680,9 +4680,6 @@ __xfs_bmapi_allocate(
 			return error;
 	}
 
-	if (bma->flags & XFS_BMAPI_STACK_SWITCH)
-		bma->stack_switch = 1;
-
 	error = xfs_bmap_alloc(bma);
 	if (error)
 		return error;
@@ -4956,6 +4953,9 @@ xfs_bmapi_write(
 	bma.flist = flist;
 	bma.firstblock = firstblock;
 
+	if (flags & XFS_BMAPI_STACK_SWITCH)
+		bma.stack_switch = 1;
+
 	while (bno < end && n < *nmap) {
 		inhole = eof || bma.got.br_startoff > bno;
 		wasdelay = !inhole && isnullstartblock(bma.got.br_startblock);

fs/xfs/xfs_buf.c

@@ -487,6 +487,7 @@ _xfs_buf_find(
 	struct rb_node		*parent;
 	xfs_buf_t		*bp;
 	xfs_daddr_t		blkno = map[0].bm_bn;
+	xfs_daddr_t		eofs;
 	int			numblks = 0;
 	int			i;
 
@@ -498,6 +499,23 @@ _xfs_buf_find(
 	ASSERT(!(numbytes < (1 << btp->bt_sshift)));
 	ASSERT(!(BBTOB(blkno) & (xfs_off_t)btp->bt_smask));
 
+	/*
+	 * Corrupted block numbers can get through to here, unfortunately, so we
+	 * have to check that the buffer falls within the filesystem bounds.
+	 */
+	eofs = XFS_FSB_TO_BB(btp->bt_mount, btp->bt_mount->m_sb.sb_dblocks);
+	if (blkno >= eofs) {
+		/*
+		 * XXX (dgc): we should really be returning EFSCORRUPTED here,
+		 * but none of the higher level infrastructure supports
+		 * returning a specific error on buffer lookup failures.
+		 */
+		xfs_alert(btp->bt_mount,
+			  "%s: Block out of range: block 0x%llx, EOFS 0x%llx ",
+			  __func__, blkno, eofs);
+		return NULL;
+	}
+
 	/* get tree root */
 	pag = xfs_perag_get(btp->bt_mount,
 				xfs_daddr_to_agno(btp->bt_mount, blkno));
@@ -1487,6 +1505,8 @@ xfs_wait_buftarg(
 	while (!list_empty(&btp->bt_lru)) {
 		bp = list_first_entry(&btp->bt_lru, struct xfs_buf, b_lru);
 		if (atomic_read(&bp->b_hold) > 1) {
+			trace_xfs_buf_wait_buftarg(bp, _RET_IP_);
+			list_move_tail(&bp->b_lru, &btp->bt_lru);
 			spin_unlock(&btp->bt_lru_lock);
 			delay(100);
 			goto restart;

fs/xfs/xfs_buf_item.c

@@ -652,7 +652,10 @@ xfs_buf_item_unlock(
 
 	/*
 	 * If the buf item isn't tracking any data, free it, otherwise drop the
-	 * reference we hold to it.
+	 * 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.
 	 */
 	clean = 1;
 	for (i = 0; i < bip->bli_format_count; i++) {
@@ -664,7 +667,12 @@ xfs_buf_item_unlock(
 	}
 	if (clean)
 		xfs_buf_item_relse(bp);
-	else
+	else if (aborted) {
+		if (atomic_dec_and_test(&bip->bli_refcount)) {
+			ASSERT(XFS_FORCED_SHUTDOWN(lip->li_mountp));
+			xfs_buf_item_relse(bp);
+		}
+	} else
 		atomic_dec(&bip->bli_refcount);
 
 	if (!hold)

fs/xfs/xfs_dfrag.c

@@ -246,10 +246,10 @@ xfs_swap_extents(
 		goto out_unlock;
 	}
 
-	error = -filemap_write_and_wait(VFS_I(ip)->i_mapping);
+	error = -filemap_write_and_wait(VFS_I(tip)->i_mapping);
 	if (error)
 		goto out_unlock;
-	truncate_pagecache_range(VFS_I(ip), 0, -1);
+	truncate_pagecache_range(VFS_I(tip), 0, -1);
 
 	/* Verify O_DIRECT for ftmp */
 	if (VN_CACHED(VFS_I(tip)) != 0) {

fs/xfs/xfs_iomap.c

@@ -351,6 +351,15 @@ xfs_iomap_prealloc_size(
 		}
 		if (shift)
 			alloc_blocks >>= shift;
+
+		/*
+		 * If we are still trying to allocate more space than is
+		 * available, squash the prealloc hard. This can happen if we
+		 * have a large file on a small filesystem and the above
+		 * lowspace thresholds are smaller than MAXEXTLEN.
+		 */
+		while (alloc_blocks >= freesp)
+			alloc_blocks >>= 4;
 	}
 
 	if (alloc_blocks < mp->m_writeio_blocks)

fs/xfs/xfs_mount.c

@@ -658,7 +658,7 @@ xfs_sb_quiet_read_verify(
 		return;
 	}
 	/* quietly fail */
-	xfs_buf_ioerror(bp, EFSCORRUPTED);
+	xfs_buf_ioerror(bp, EWRONGFS);
 }
 
 static void

fs/xfs/xfs_trace.h

@@ -341,6 +341,7 @@ DEFINE_BUF_EVENT(xfs_buf_item_relse);
 DEFINE_BUF_EVENT(xfs_buf_item_iodone);
 DEFINE_BUF_EVENT(xfs_buf_item_iodone_async);
 DEFINE_BUF_EVENT(xfs_buf_error_relse);
+DEFINE_BUF_EVENT(xfs_buf_wait_buftarg);
 DEFINE_BUF_EVENT(xfs_trans_read_buf_io);
 DEFINE_BUF_EVENT(xfs_trans_read_buf_shut);