Merge branch 'linus' into timers/urgent

Merge in Linus's branch which already has timers/core merged.

Signed-off-by: Ingo Molnar <mingo@kernel.org>

15 files changed, 184 insertions, 116 deletions

diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c
index 5b40073..4ee522b 100644
--- a/fs/cifs/cifssmb.c
+++ b/fs/cifs/cifssmb.c
@@ -86,7 +86,31 @@ static struct {
 #endif /* CONFIG_CIFS_WEAK_PW_HASH */
 #endif /* CIFS_POSIX */
 
-/* Forward declarations */
+#ifdef CONFIG_HIGHMEM
+/*
+ * On arches that have high memory, kmap address space is limited. By
+ * serializing the kmap operations on those arches, we ensure that we don't
+ * end up with a bunch of threads in writeback with partially mapped page
+ * arrays, stuck waiting for kmap to come back. That situation prevents
+ * progress and can deadlock.
+ */
+static DEFINE_MUTEX(cifs_kmap_mutex);
+
+static inline void
+cifs_kmap_lock(void)
+{
+	mutex_lock(&cifs_kmap_mutex);
+}
+
+static inline void
+cifs_kmap_unlock(void)
+{
+	mutex_unlock(&cifs_kmap_mutex);
+}
+#else /* !CONFIG_HIGHMEM */
+#define cifs_kmap_lock() do { ; } while(0)
+#define cifs_kmap_unlock() do { ; } while(0)
+#endif /* CONFIG_HIGHMEM */
 
 /* Mark as invalid, all open files on tree connections since they
    were closed when session to server was lost */
@@ -1503,7 +1527,9 @@ cifs_readv_receive(struct TCP_Server_Info *server, struct mid_q_entry *mid)
 	}
 
 	/* marshal up the page array */
+	cifs_kmap_lock();
 	len = rdata->marshal_iov(rdata, data_len);
+	cifs_kmap_unlock();
 	data_len -= len;
 
 	/* issue the read if we have any iovecs left to fill */
@@ -2069,7 +2095,9 @@ cifs_async_writev(struct cifs_writedata *wdata)
 	 * and set the iov_len properly for each one. It may also set
 	 * wdata->bytes too.
 	 */
+	cifs_kmap_lock();
 	wdata->marshal_iov(iov, wdata);
+	cifs_kmap_unlock();
 
 	cFYI(1, "async write at %llu %u bytes", wdata->offset, wdata->bytes);
 
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index 0ae86dd..94b7788 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -3445,6 +3445,18 @@ void cifs_setup_cifs_sb(struct smb_vol *pvolume_info,
 #define CIFS_DEFAULT_NON_POSIX_RSIZE (60 * 1024)
 #define CIFS_DEFAULT_NON_POSIX_WSIZE (65536)
 
+/*
+ * On hosts with high memory, we can't currently support wsize/rsize that are
+ * larger than we can kmap at once. Cap the rsize/wsize at
+ * LAST_PKMAP * PAGE_SIZE. We'll never be able to fill a read or write request
+ * larger than that anyway.
+ */
+#ifdef CONFIG_HIGHMEM
+#define CIFS_KMAP_SIZE_LIMIT	(LAST_PKMAP * PAGE_CACHE_SIZE)
+#else /* CONFIG_HIGHMEM */
+#define CIFS_KMAP_SIZE_LIMIT	(1<<24)
+#endif /* CONFIG_HIGHMEM */
+
 static unsigned int
 cifs_negotiate_wsize(struct cifs_tcon *tcon, struct smb_vol *pvolume_info)
 {
@@ -3475,6 +3487,9 @@ cifs_negotiate_wsize(struct cifs_tcon *tcon, struct smb_vol *pvolume_info)
 		wsize = min_t(unsigned int, wsize,
 				server->maxBuf - sizeof(WRITE_REQ) + 4);
 
+	/* limit to the amount that we can kmap at once */
+	wsize = min_t(unsigned int, wsize, CIFS_KMAP_SIZE_LIMIT);
+
 	/* hard limit of CIFS_MAX_WSIZE */
 	wsize = min_t(unsigned int, wsize, CIFS_MAX_WSIZE);
 
@@ -3516,6 +3531,9 @@ cifs_negotiate_rsize(struct cifs_tcon *tcon, struct smb_vol *pvolume_info)
 	if (!(server->capabilities & CAP_LARGE_READ_X))
 		rsize = min_t(unsigned int, CIFSMaxBufSize, rsize);
 
+	/* limit to the amount that we can kmap at once */
+	rsize = min_t(unsigned int, rsize, CIFS_KMAP_SIZE_LIMIT);
+
 	/* hard limit of CIFS_MAX_RSIZE */
 	rsize = min_t(unsigned int, rsize, CIFS_MAX_RSIZE);
 
diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c
index 0a8224d..a4217f0 100644
--- a/fs/cifs/readdir.c
+++ b/fs/cifs/readdir.c
@@ -86,9 +86,12 @@ cifs_readdir_lookup(struct dentry *parent, struct qstr *name,
 
 	dentry = d_lookup(parent, name);
 	if (dentry) {
-		/* FIXME: check for inode number changes? */
-		if (dentry->d_inode != NULL)
+		inode = dentry->d_inode;
+		/* update inode in place if i_ino didn't change */
+		if (inode && CIFS_I(inode)->uniqueid == fattr->cf_uniqueid) {
+			cifs_fattr_to_inode(inode, fattr);
 			return dentry;
+		}
 		d_drop(dentry);
 		dput(dentry);
 	}
diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c
index 3097ee5..f25d4ea 100644
--- a/fs/cifs/transport.c
+++ b/fs/cifs/transport.c
@@ -365,16 +365,14 @@ cifs_setup_async_request(struct TCP_Server_Info *server, struct kvec *iov,
 	if (mid == NULL)
 		return -ENOMEM;
 
-	/* put it on the pending_mid_q */
-	spin_lock(&GlobalMid_Lock);
-	list_add_tail(&mid->qhead, &server->pending_mid_q);
-	spin_unlock(&GlobalMid_Lock);
-
 	rc = cifs_sign_smb2(iov, nvec, server, &mid->sequence_number);
-	if (rc)
-		delete_mid(mid);
+	if (rc) {
+		DeleteMidQEntry(mid);
+		return rc;
+	}
+
 	*ret_mid = mid;
-	return rc;
+	return 0;
 }
 
 /*
@@ -407,17 +405,21 @@ cifs_call_async(struct TCP_Server_Info *server, struct kvec *iov,
 	mid->callback_data = cbdata;
 	mid->mid_state = MID_REQUEST_SUBMITTED;
 
+	/* put it on the pending_mid_q */
+	spin_lock(&GlobalMid_Lock);
+	list_add_tail(&mid->qhead, &server->pending_mid_q);
+	spin_unlock(&GlobalMid_Lock);
+
+
 	cifs_in_send_inc(server);
 	rc = smb_sendv(server, iov, nvec);
 	cifs_in_send_dec(server);
 	cifs_save_when_sent(mid);
 	mutex_unlock(&server->srv_mutex);
 
-	if (rc)
-		goto out_err;
+	if (rc == 0)
+		return 0;
 
-	return rc;
-out_err:
 	delete_mid(mid);
 	add_credits(server, 1);
 	wake_up(&server->request_q);
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 74598f6..1c8b556 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -1710,7 +1710,7 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd,
 		goto error_tgt_fput;
 
 	/* Check if EPOLLWAKEUP is allowed */
-	if ((epds.events & EPOLLWAKEUP) && !capable(CAP_EPOLLWAKEUP))
+	if ((epds.events & EPOLLWAKEUP) && !capable(CAP_BLOCK_SUSPEND))
 		epds.events &= ~EPOLLWAKEUP;
 
 	/*
diff --git a/fs/exofs/ore.c b/fs/exofs/ore.c
index 49cf230..24a49d4 100644
--- a/fs/exofs/ore.c
+++ b/fs/exofs/ore.c
@@ -735,13 +735,7 @@ static int _prepare_for_striping(struct ore_io_state *ios)
 out:
 	ios->numdevs = devs_in_group;
 	ios->pages_consumed = cur_pg;
-	if (unlikely(ret)) {
-		if (length == ios->length)
-			return ret;
-		else
-			ios->length -= length;
-	}
-	return 0;
+	return ret;
 }
 
 int ore_create(struct ore_io_state *ios)
diff --git a/fs/exofs/ore_raid.c b/fs/exofs/ore_raid.c
index d222c77..5f376d1 100644
--- a/fs/exofs/ore_raid.c
+++ b/fs/exofs/ore_raid.c
@@ -144,26 +144,26 @@ static void _sp2d_reset(struct __stripe_pages_2d *sp2d,
 {
 	unsigned data_devs = sp2d->data_devs;
 	unsigned group_width = data_devs + sp2d->parity;
-	unsigned p;
+	int p, c;
 
 	if (!sp2d->needed)
 		return;
 
-	for (p = 0; p < sp2d->pages_in_unit; p++) {
-		struct __1_page_stripe *_1ps = &sp2d->_1p_stripes[p];
-
-		if (_1ps->write_count < group_width) {
-			unsigned c;
+	for (c = data_devs - 1; c >= 0; --c)
+		for (p = sp2d->pages_in_unit - 1; p >= 0; --p) {
+			struct __1_page_stripe *_1ps = &sp2d->_1p_stripes[p];
 
-			for (c = 0; c < data_devs; c++)
-				if (_1ps->page_is_read[c]) {
-					struct page *page = _1ps->pages[c];
+			if (_1ps->page_is_read[c]) {
+				struct page *page = _1ps->pages[c];
 
-					r4w->put_page(priv, page);
-					_1ps->page_is_read[c] = false;
-				}
+				r4w->put_page(priv, page);
+				_1ps->page_is_read[c] = false;
+			}
 		}
 
+	for (p = 0; p < sp2d->pages_in_unit; p++) {
+		struct __1_page_stripe *_1ps = &sp2d->_1p_stripes[p];
+
 		memset(_1ps->pages, 0, group_width * sizeof(*_1ps->pages));
 		_1ps->write_count = 0;
 		_1ps->tx = NULL;
@@ -461,16 +461,12 @@ static void _mark_read4write_pages_uptodate(struct ore_io_state *ios, int ret)
  * ios->sp2d[p][*], xor is calculated the same way. These pages are
  * allocated/freed and don't go through cache
  */
-static int _read_4_write(struct ore_io_state *ios)
+static int _read_4_write_first_stripe(struct ore_io_state *ios)
 {
-	struct ore_io_state *ios_read;
 	struct ore_striping_info read_si;
 	struct __stripe_pages_2d *sp2d = ios->sp2d;
 	u64 offset = ios->si.first_stripe_start;
-	u64 last_stripe_end;
-	unsigned bytes_in_stripe = ios->si.bytes_in_stripe;
-	unsigned i, c, p, min_p = sp2d->pages_in_unit, max_p = -1;
-	int ret;
+	unsigned c, p, min_p = sp2d->pages_in_unit, max_p = -1;
 
 	if (offset == ios->offset) /* Go to start collect $200 */
 		goto read_last_stripe;
@@ -478,6 +474,9 @@ static int _read_4_write(struct ore_io_state *ios)
 	min_p = _sp2d_min_pg(sp2d);
 	max_p = _sp2d_max_pg(sp2d);
 
+	ORE_DBGMSG("stripe_start=0x%llx ios->offset=0x%llx min_p=%d max_p=%d\n",
+		   offset, ios->offset, min_p, max_p);
+
 	for (c = 0; ; c++) {
 		ore_calc_stripe_info(ios->layout, offset, 0, &read_si);
 		read_si.obj_offset += min_p * PAGE_SIZE;
@@ -512,6 +511,18 @@ static int _read_4_write(struct ore_io_state *ios)
 	}
 
 read_last_stripe:
+	return 0;
+}
+
+static int _read_4_write_last_stripe(struct ore_io_state *ios)
+{
+	struct ore_striping_info read_si;
+	struct __stripe_pages_2d *sp2d = ios->sp2d;
+	u64 offset;
+	u64 last_stripe_end;
+	unsigned bytes_in_stripe = ios->si.bytes_in_stripe;
+	unsigned c, p, min_p = sp2d->pages_in_unit, max_p = -1;
+
 	offset = ios->offset + ios->length;
 	if (offset % PAGE_SIZE)
 		_add_to_r4w_last_page(ios, &offset);
@@ -527,15 +538,15 @@ read_last_stripe:
 	c = _dev_order(ios->layout->group_width * ios->layout->mirrors_p1,
 		       ios->layout->mirrors_p1, read_si.par_dev, read_si.dev);
 
-	BUG_ON(ios->si.first_stripe_start + bytes_in_stripe != last_stripe_end);
-	/* unaligned IO must be within a single stripe */
-
 	if (min_p == sp2d->pages_in_unit) {
 		/* Didn't do it yet */
 		min_p = _sp2d_min_pg(sp2d);
 		max_p = _sp2d_max_pg(sp2d);
 	}
 
+	ORE_DBGMSG("offset=0x%llx stripe_end=0x%llx min_p=%d max_p=%d\n",
+		   offset, last_stripe_end, min_p, max_p);
+
 	while (offset < last_stripe_end) {
 		struct __1_page_stripe *_1ps = &sp2d->_1p_stripes[p];
 
@@ -568,6 +579,15 @@ read_last_stripe:
 	}
 
 read_it:
+	return 0;
+}
+
+static int _read_4_write_execute(struct ore_io_state *ios)
+{
+	struct ore_io_state *ios_read;
+	unsigned i;
+	int ret;
+
 	ios_read = ios->ios_read_4_write;
 	if (!ios_read)
 		return 0;
@@ -591,6 +611,8 @@ read_it:
 	}
 
 	_mark_read4write_pages_uptodate(ios_read, ret);
+	ore_put_io_state(ios_read);
+	ios->ios_read_4_write = NULL; /* Might need a reuse at last stripe */
 	return 0;
 }
 
@@ -626,8 +648,11 @@ int _ore_add_parity_unit(struct ore_io_state *ios,
 			/* If first stripe, Read in all read4write pages
 			 * (if needed) before we calculate the first parity.
 			 */
-			_read_4_write(ios);
+			_read_4_write_first_stripe(ios);
 		}
+		if (!cur_len) /* If last stripe r4w pages of last stripe */
+			_read_4_write_last_stripe(ios);
+		_read_4_write_execute(ios);
 
 		for (i = 0; i < num_pages; i++) {
 			pages[i] = _raid_page_alloc();
@@ -654,34 +679,14 @@ int _ore_add_parity_unit(struct ore_io_state *ios,
 
 int _ore_post_alloc_raid_stuff(struct ore_io_state *ios)
 {
-	struct ore_layout *layout = ios->layout;
-
 	if (ios->parity_pages) {
+		struct ore_layout *layout = ios->layout;
 		unsigned pages_in_unit = layout->stripe_unit / PAGE_SIZE;
-		unsigned stripe_size = ios->si.bytes_in_stripe;
-		u64 last_stripe, first_stripe;
 
 		if (_sp2d_alloc(pages_in_unit, layout->group_width,
 				layout->parity, &ios->sp2d)) {
 			return -ENOMEM;
 		}
-
-		/* Round io down to last full strip */
-		first_stripe = div_u64(ios->offset, stripe_size);
-		last_stripe = div_u64(ios->offset + ios->length, stripe_size);
-
-		/* If an IO spans more then a single stripe it must end at
-		 * a stripe boundary. The reminder at the end is pushed into the
-		 * next IO.
-		 */
-		if (last_stripe != first_stripe) {
-			ios->length = last_stripe * stripe_size - ios->offset;
-
-			BUG_ON(!ios->length);
-			ios->nr_pages = (ios->length + PAGE_SIZE - 1) /
-					PAGE_SIZE;
-			ios->si.length = ios->length; /*make it consistent */
-		}
 	}
 	return 0;
 }
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index e34deac..6ec6f9ee 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -268,7 +268,6 @@ group_extend_out:
 		err = ext4_move_extents(filp, donor_filp, me.orig_start,
 					me.donor_start, me.len, &me.moved_len);
 		mnt_drop_write_file(filp);
-		mnt_drop_write(filp->f_path.mnt);
 
 		if (copy_to_user((struct move_extent __user *)arg,
 				 &me, sizeof(me)))
diff --git a/fs/fifo.c b/fs/fifo.c
index b1a524d..cf6f434 100644
--- a/fs/fifo.c
+++ b/fs/fifo.c
@@ -14,7 +14,7 @@
 #include <linux/sched.h>
 #include <linux/pipe_fs_i.h>
 
-static void wait_for_partner(struct inode* inode, unsigned int *cnt)
+static int wait_for_partner(struct inode* inode, unsigned int *cnt)
 {
 	int cur = *cnt;	
 
@@ -23,6 +23,7 @@ static void wait_for_partner(struct inode* inode, unsigned int *cnt)
 		if (signal_pending(current))
 			break;
 	}
+	return cur == *cnt ? -ERESTARTSYS : 0;
 }
 
 static void wake_up_partner(struct inode* inode)
@@ -67,8 +68,7 @@ static int fifo_open(struct inode *inode, struct file *filp)
 				 * seen a writer */
 				filp->f_version = pipe->w_counter;
 			} else {
-				wait_for_partner(inode, &pipe->w_counter);
-				if(signal_pending(current))
+				if (wait_for_partner(inode, &pipe->w_counter))
 					goto err_rd;
 			}
 		}
@@ -90,8 +90,7 @@ static int fifo_open(struct inode *inode, struct file *filp)
 			wake_up_partner(inode);
 
 		if (!pipe->readers) {
-			wait_for_partner(inode, &pipe->r_counter);
-			if (signal_pending(current))
+			if (wait_for_partner(inode, &pipe->r_counter))
 				goto err_wr;
 		}
 		break;
diff --git a/fs/nfs/objlayout/objio_osd.c b/fs/nfs/objlayout/objio_osd.c
index b47277ba..f50d3e8 100644
--- a/fs/nfs/objlayout/objio_osd.c
+++ b/fs/nfs/objlayout/objio_osd.c
@@ -454,7 +454,10 @@ int objio_read_pagelist(struct nfs_read_data *rdata)
 	objios->ios->done = _read_done;
 	dprintk("%s: offset=0x%llx length=0x%x\n", __func__,
 		rdata->args.offset, rdata->args.count);
-	return ore_read(objios->ios);
+	ret = ore_read(objios->ios);
+	if (unlikely(ret))
+		objio_free_result(&objios->oir);
+	return ret;
 }
 
 /*
@@ -486,8 +489,16 @@ static struct page *__r4w_get_page(void *priv, u64 offset, bool *uptodate)
 	struct nfs_write_data *wdata = objios->oir.rpcdata;
 	struct address_space *mapping = wdata->header->inode->i_mapping;
 	pgoff_t index = offset / PAGE_SIZE;
-	struct page *page = find_get_page(mapping, index);
+	struct page *page;
+	loff_t i_size = i_size_read(wdata->header->inode);
+
+	if (offset >= i_size) {
+		*uptodate = true;
+		dprintk("%s: g_zero_page index=0x%lx\n", __func__, index);
+		return ZERO_PAGE(0);
+	}
 
+	page = find_get_page(mapping, index);
 	if (!page) {
 		page = find_or_create_page(mapping, index, GFP_NOFS);
 		if (unlikely(!page)) {
@@ -507,8 +518,10 @@ static struct page *__r4w_get_page(void *priv, u64 offset, bool *uptodate)
 
 static void __r4w_put_page(void *priv, struct page *page)
 {
-	dprintk("%s: index=0x%lx\n", __func__, page->index);
-	page_cache_release(page);
+	dprintk("%s: index=0x%lx\n", __func__,
+		(page == ZERO_PAGE(0)) ? -1UL : page->index);
+	if (ZERO_PAGE(0) != page)
+		page_cache_release(page);
 	return;
 }
 
@@ -539,8 +552,10 @@ int objio_write_pagelist(struct nfs_write_data *wdata, int how)
 	dprintk("%s: offset=0x%llx length=0x%x\n", __func__,
 		wdata->args.offset, wdata->args.count);
 	ret = ore_write(objios->ios);
-	if (unlikely(ret))
+	if (unlikely(ret)) {
+		objio_free_result(&objios->oir);
 		return ret;
+	}
 
 	if (objios->sync)
 		_write_done(objios->ios, objios);
diff --git a/fs/ubifs/sb.c b/fs/ubifs/sb.c
index ef3d1ba..15e2fc5 100644
--- a/fs/ubifs/sb.c
+++ b/fs/ubifs/sb.c
@@ -718,8 +718,12 @@ static int fixup_free_space(struct ubifs_info *c)
 		lnum = ubifs_next_log_lnum(c, lnum);
 	}
 
-	/* Fixup the current log head */
-	err = fixup_leb(c, c->lhead_lnum, c->lhead_offs);
+	/*
+	 * Fixup the log head which contains the only a CS node at the
+	 * beginning.
+	 */
+	err = fixup_leb(c, c->lhead_lnum,
+			ALIGN(UBIFS_CS_NODE_SZ, c->min_io_size));
 	if (err)
 		goto out;
 
diff --git a/fs/xfs/xfs_alloc.c b/fs/xfs/xfs_alloc.c
index 9d1aeb7..4f33c32 100644
--- a/fs/xfs/xfs_alloc.c
+++ b/fs/xfs/xfs_alloc.c
@@ -1074,13 +1074,13 @@ restart:
 	 * If we couldn't get anything, give up.
 	 */
 	if (bno_cur_lt == NULL && bno_cur_gt == NULL) {
+		xfs_btree_del_cursor(cnt_cur, XFS_BTREE_NOERROR);
+
 		if (!forced++) {
 			trace_xfs_alloc_near_busy(args);
 			xfs_log_force(args->mp, XFS_LOG_SYNC);
 			goto restart;
 		}
-
-		xfs_btree_del_cursor(cnt_cur, XFS_BTREE_NOERROR);
 		trace_xfs_alloc_size_neither(args);
 		args->agbno = NULLAGBLOCK;
 		return 0;
@@ -2434,13 +2434,22 @@ xfs_alloc_vextent_worker(
 	current_restore_flags_nested(&pflags, PF_FSTRANS);
 }
 
-
-int				/* error */
+/*
+ * Data allocation requests often come in with little stack to work on. Push
+ * them off to a worker thread so there is lots of stack to use. Metadata
+ * requests, OTOH, are generally from low stack usage paths, so avoid the
+ * context switch overhead here.
+ */
+int
 xfs_alloc_vextent(
-	xfs_alloc_arg_t	*args)	/* allocation argument structure */
+	struct xfs_alloc_arg	*args)
 {
 	DECLARE_COMPLETION_ONSTACK(done);
 
+	if (!args->userdata)
+		return __xfs_alloc_vextent(args);
+
+
 	args->done = &done;
 	INIT_WORK_ONSTACK(&args->work, xfs_alloc_vextent_worker);
 	queue_work(xfs_alloc_wq, &args->work);
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index a4beb42..269b35c 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -989,27 +989,6 @@ xfs_buf_ioerror_alert(
 		(__uint64_t)XFS_BUF_ADDR(bp), func, bp->b_error, bp->b_length);
 }
 
-int
-xfs_bwrite(
-	struct xfs_buf		*bp)
-{
-	int			error;
-
-	ASSERT(xfs_buf_islocked(bp));
-
-	bp->b_flags |= XBF_WRITE;
-	bp->b_flags &= ~(XBF_ASYNC | XBF_READ | _XBF_DELWRI_Q);
-
-	xfs_bdstrat_cb(bp);
-
-	error = xfs_buf_iowait(bp);
-	if (error) {
-		xfs_force_shutdown(bp->b_target->bt_mount,
-				   SHUTDOWN_META_IO_ERROR);
-	}
-	return error;
-}
-
 /*
  * Called when we want to stop a buffer from getting written or read.
  * We attach the EIO error, muck with its flags, and call xfs_buf_ioend
@@ -1079,14 +1058,7 @@ xfs_bioerror_relse(
 	return EIO;
 }
 
-
-/*
- * All xfs metadata buffers except log state machine buffers
- * get this attached as their b_bdstrat callback function.
- * This is so that we can catch a buffer
- * after prematurely unpinning it to forcibly shutdown the filesystem.
- */
-int
+STATIC int
 xfs_bdstrat_cb(
 	struct xfs_buf	*bp)
 {
@@ -1107,6 +1079,27 @@ xfs_bdstrat_cb(
 	return 0;
 }
 
+int
+xfs_bwrite(
+	struct xfs_buf		*bp)
+{
+	int			error;
+
+	ASSERT(xfs_buf_islocked(bp));
+
+	bp->b_flags |= XBF_WRITE;
+	bp->b_flags &= ~(XBF_ASYNC | XBF_READ | _XBF_DELWRI_Q);
+
+	xfs_bdstrat_cb(bp);
+
+	error = xfs_buf_iowait(bp);
+	if (error) {
+		xfs_force_shutdown(bp->b_target->bt_mount,
+				   SHUTDOWN_META_IO_ERROR);
+	}
+	return error;
+}
+
 /*
  * Wrapper around bdstrat so that we can stop data from going to disk in case
  * we are shutting down the filesystem.  Typically user data goes thru this
@@ -1243,7 +1236,7 @@ xfs_buf_iorequest(
 	 */
 	atomic_set(&bp->b_io_remaining, 1);
 	_xfs_buf_ioapply(bp);
-	_xfs_buf_ioend(bp, 0);
+	_xfs_buf_ioend(bp, 1);
 
 	xfs_buf_rele(bp);
 }
diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h
index 7f1d139..79344c4 100644
--- a/fs/xfs/xfs_buf.h
+++ b/fs/xfs/xfs_buf.h
@@ -180,7 +180,6 @@ extern void xfs_buf_unlock(xfs_buf_t *);
 extern int xfs_bwrite(struct xfs_buf *bp);
 
 extern void xfsbdstrat(struct xfs_mount *, struct xfs_buf *);
-extern int xfs_bdstrat_cb(struct xfs_buf *);
 
 extern void xfs_buf_ioend(xfs_buf_t *,	int);
 extern void xfs_buf_ioerror(xfs_buf_t *, int);
diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c
index 45df2b8..d9e4511 100644
--- a/fs/xfs/xfs_buf_item.c
+++ b/fs/xfs/xfs_buf_item.c
@@ -954,7 +954,7 @@ xfs_buf_iodone_callbacks(
 
 		if (!XFS_BUF_ISSTALE(bp)) {
 			bp->b_flags |= XBF_WRITE | XBF_ASYNC | XBF_DONE;
-			xfs_bdstrat_cb(bp);
+			xfs_buf_iorequest(bp);
 		} else {
 			xfs_buf_relse(bp);
 		}