Merge tag 'gfs2-v5.15-rc5-mmap-fault' of git://git.kernel.org/pub/scm/linux/kernel/git/gfs2/linux-gfs2

Pull gfs2 mmap + page fault deadlocks fixes from Andreas Gruenbacher:
 "Functions gfs2_file_read_iter and gfs2_file_write_iter are both
  accessing the user buffer to write to or read from while holding the
  inode glock.

  In the most basic deadlock scenario, that buffer will not be resident
  and it will be mapped to the same file. Accessing the buffer will
  trigger a page fault, and gfs2 will deadlock trying to take the same
  inode glock again while trying to handle that fault.

  Fix that and similar, more complex scenarios by disabling page faults
  while accessing user buffers. To make this work, introduce a small
  amount of new infrastructure and fix some bugs that didn't trigger so
  far, with page faults enabled"

* tag 'gfs2-v5.15-rc5-mmap-fault' of git://git.kernel.org/pub/scm/linux/kernel/git/gfs2/linux-gfs2:
  gfs2: Fix mmap + page fault deadlocks for direct I/O
  iov_iter: Introduce nofault flag to disable page faults
  gup: Introduce FOLL_NOFAULT flag to disable page faults
  iomap: Add done_before argument to iomap_dio_rw
  iomap: Support partial direct I/O on user copy failures
  iomap: Fix iomap_dio_rw return value for user copies
  gfs2: Fix mmap + page fault deadlocks for buffered I/O
  gfs2: Eliminate ip->i_gh
  gfs2: Move the inode glock locking to gfs2_file_buffered_write
  gfs2: Introduce flag for glock holder auto-demotion
  gfs2: Clean up function may_grant
  gfs2: Add wrapper for iomap_file_buffered_write
  iov_iter: Introduce fault_in_iov_iter_writeable
  iov_iter: Turn iov_iter_fault_in_readable into fault_in_iov_iter_readable
  gup: Turn fault_in_pages_{readable,writeable} into fault_in_{readable,writeable}
  powerpc/kvm: Fix kvm_use_magic_page
  iov_iter: Fix iov_iter_get_pages{,_alloc} page fault return value

5 files changed, 498 insertions, 168 deletions

diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c
index 5414c2c33580..7235d539e969 100644
--- a/fs/gfs2/bmap.c
+++ b/fs/gfs2/bmap.c
@@ -961,46 +961,6 @@ hole_found:
 	goto out;
 }
 
-static int gfs2_write_lock(struct inode *inode)
-{
-	struct gfs2_inode *ip = GFS2_I(inode);
-	struct gfs2_sbd *sdp = GFS2_SB(inode);
-	int error;
-
-	gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &ip->i_gh);
-	error = gfs2_glock_nq(&ip->i_gh);
-	if (error)
-		goto out_uninit;
-	if (&ip->i_inode == sdp->sd_rindex) {
-		struct gfs2_inode *m_ip = GFS2_I(sdp->sd_statfs_inode);
-
-		error = gfs2_glock_nq_init(m_ip->i_gl, LM_ST_EXCLUSIVE,
-					   GL_NOCACHE, &m_ip->i_gh);
-		if (error)
-			goto out_unlock;
-	}
-	return 0;
-
-out_unlock:
-	gfs2_glock_dq(&ip->i_gh);
-out_uninit:
-	gfs2_holder_uninit(&ip->i_gh);
-	return error;
-}
-
-static void gfs2_write_unlock(struct inode *inode)
-{
-	struct gfs2_inode *ip = GFS2_I(inode);
-	struct gfs2_sbd *sdp = GFS2_SB(inode);
-
-	if (&ip->i_inode == sdp->sd_rindex) {
-		struct gfs2_inode *m_ip = GFS2_I(sdp->sd_statfs_inode);
-
-		gfs2_glock_dq_uninit(&m_ip->i_gh);
-	}
-	gfs2_glock_dq_uninit(&ip->i_gh);
-}
-
 static int gfs2_iomap_page_prepare(struct inode *inode, loff_t pos,
 				   unsigned len)
 {
@@ -1118,11 +1078,6 @@ out_qunlock:
 	return ret;
 }
 
-static inline bool gfs2_iomap_need_write_lock(unsigned flags)
-{
-	return (flags & IOMAP_WRITE) && !(flags & IOMAP_DIRECT);
-}
-
 static int gfs2_iomap_begin(struct inode *inode, loff_t pos, loff_t length,
 			    unsigned flags, struct iomap *iomap,
 			    struct iomap *srcmap)
@@ -1135,12 +1090,6 @@ static int gfs2_iomap_begin(struct inode *inode, loff_t pos, loff_t length,
 		iomap->flags |= IOMAP_F_BUFFER_HEAD;
 
 	trace_gfs2_iomap_start(ip, pos, length, flags);
-	if (gfs2_iomap_need_write_lock(flags)) {
-		ret = gfs2_write_lock(inode);
-		if (ret)
-			goto out;
-	}
-
 	ret = __gfs2_iomap_get(inode, pos, length, flags, iomap, &mp);
 	if (ret)
 		goto out_unlock;
@@ -1168,10 +1117,7 @@ static int gfs2_iomap_begin(struct inode *inode, loff_t pos, loff_t length,
 	ret = gfs2_iomap_begin_write(inode, pos, length, flags, iomap, &mp);
 
 out_unlock:
-	if (ret && gfs2_iomap_need_write_lock(flags))
-		gfs2_write_unlock(inode);
 	release_metapath(&mp);
-out:
 	trace_gfs2_iomap_end(ip, iomap, ret);
 	return ret;
 }
@@ -1219,15 +1165,11 @@ static int gfs2_iomap_end(struct inode *inode, loff_t pos, loff_t length,
 	}
 
 	if (unlikely(!written))
-		goto out_unlock;
+		return 0;
 
 	if (iomap->flags & IOMAP_F_SIZE_CHANGED)
 		mark_inode_dirty(inode);
 	set_bit(GLF_DIRTY, &ip->i_gl->gl_flags);
-
-out_unlock:
-	if (gfs2_iomap_need_write_lock(flags))
-		gfs2_write_unlock(inode);
 	return 0;
 }
 
diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c
index 5436a688157a..8f4627a19359 100644
--- a/fs/gfs2/file.c
+++ b/fs/gfs2/file.c
@@ -776,27 +776,99 @@ static int gfs2_fsync(struct file *file, loff_t start, loff_t end,
 	return ret ? ret : ret1;
 }
 
+static inline bool should_fault_in_pages(ssize_t ret, struct iov_iter *i,
+					 size_t *prev_count,
+					 size_t *window_size)
+{
+	char __user *p = i->iov[0].iov_base + i->iov_offset;
+	size_t count = iov_iter_count(i);
+	int pages = 1;
+
+	if (likely(!count))
+		return false;
+	if (ret <= 0 && ret != -EFAULT)
+		return false;
+	if (!iter_is_iovec(i))
+		return false;
+
+	if (*prev_count != count || !*window_size) {
+		int pages, nr_dirtied;
+
+		pages = min_t(int, BIO_MAX_VECS,
+			      DIV_ROUND_UP(iov_iter_count(i), PAGE_SIZE));
+		nr_dirtied = max(current->nr_dirtied_pause -
+				 current->nr_dirtied, 1);
+		pages = min(pages, nr_dirtied);
+	}
+
+	*prev_count = count;
+	*window_size = (size_t)PAGE_SIZE * pages - offset_in_page(p);
+	return true;
+}
+
 static ssize_t gfs2_file_direct_read(struct kiocb *iocb, struct iov_iter *to,
 				     struct gfs2_holder *gh)
 {
 	struct file *file = iocb->ki_filp;
 	struct gfs2_inode *ip = GFS2_I(file->f_mapping->host);
-	size_t count = iov_iter_count(to);
+	size_t prev_count = 0, window_size = 0;
+	size_t written = 0;
 	ssize_t ret;
 
-	if (!count)
+	/*
+	 * In this function, we disable page faults when we're holding the
+	 * inode glock while doing I/O.  If a page fault occurs, we indicate
+	 * that the inode glock may be dropped, fault in the pages manually,
+	 * and retry.
+	 *
+	 * Unlike generic_file_read_iter, for reads, iomap_dio_rw can trigger
+	 * physical as well as manual page faults, and we need to disable both
+	 * kinds.
+	 *
+	 * For direct I/O, gfs2 takes the inode glock in deferred mode.  This
+	 * locking mode is compatible with other deferred holders, so multiple
+	 * processes and nodes can do direct I/O to a file at the same time.
+	 * There's no guarantee that reads or writes will be atomic.  Any
+	 * coordination among readers and writers needs to happen externally.
+	 */
+
+	if (!iov_iter_count(to))
 		return 0; /* skip atime */
 
 	gfs2_holder_init(ip->i_gl, LM_ST_DEFERRED, 0, gh);
+retry:
 	ret = gfs2_glock_nq(gh);
 	if (ret)
 		goto out_uninit;
+retry_under_glock:
+	pagefault_disable();
+	to->nofault = true;
+	ret = iomap_dio_rw(iocb, to, &gfs2_iomap_ops, NULL,
+			   IOMAP_DIO_PARTIAL, written);
+	to->nofault = false;
+	pagefault_enable();
+	if (ret > 0)
+		written = ret;
+
+	if (should_fault_in_pages(ret, to, &prev_count, &window_size)) {
+		size_t leftover;
 
-	ret = iomap_dio_rw(iocb, to, &gfs2_iomap_ops, NULL, 0);
-	gfs2_glock_dq(gh);
+		gfs2_holder_allow_demote(gh);
+		leftover = fault_in_iov_iter_writeable(to, window_size);
+		gfs2_holder_disallow_demote(gh);
+		if (leftover != window_size) {
+			if (!gfs2_holder_queued(gh))
+				goto retry;
+			goto retry_under_glock;
+		}
+	}
+	if (gfs2_holder_queued(gh))
+		gfs2_glock_dq(gh);
 out_uninit:
 	gfs2_holder_uninit(gh);
-	return ret;
+	if (ret < 0)
+		return ret;
+	return written;
 }
 
 static ssize_t gfs2_file_direct_write(struct kiocb *iocb, struct iov_iter *from,
@@ -805,11 +877,21 @@ static ssize_t gfs2_file_direct_write(struct kiocb *iocb, struct iov_iter *from,
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file->f_mapping->host;
 	struct gfs2_inode *ip = GFS2_I(inode);
-	size_t len = iov_iter_count(from);
-	loff_t offset = iocb->ki_pos;
+	size_t prev_count = 0, window_size = 0;
+	size_t read = 0;
 	ssize_t ret;
 
 	/*
+	 * In this function, we disable page faults when we're holding the
+	 * inode glock while doing I/O.  If a page fault occurs, we indicate
+	 * that the inode glock may be dropped, fault in the pages manually,
+	 * and retry.
+	 *
+	 * For writes, iomap_dio_rw only triggers manual page faults, so we
+	 * don't need to disable physical ones.
+	 */
+
+	/*
 	 * Deferred lock, even if its a write, since we do no allocation on
 	 * this path. All we need to change is the atime, and this lock mode
 	 * ensures that other nodes have flushed their buffered read caches
@@ -818,31 +900,62 @@ static ssize_t gfs2_file_direct_write(struct kiocb *iocb, struct iov_iter *from,
 	 * VFS does.
 	 */
 	gfs2_holder_init(ip->i_gl, LM_ST_DEFERRED, 0, gh);
+retry:
 	ret = gfs2_glock_nq(gh);
 	if (ret)
 		goto out_uninit;
-
+retry_under_glock:
 	/* Silently fall back to buffered I/O when writing beyond EOF */
-	if (offset + len > i_size_read(&ip->i_inode))
+	if (iocb->ki_pos + iov_iter_count(from) > i_size_read(&ip->i_inode))
 		goto out;
 
-	ret = iomap_dio_rw(iocb, from, &gfs2_iomap_ops, NULL, 0);
+	from->nofault = true;
+	ret = iomap_dio_rw(iocb, from, &gfs2_iomap_ops, NULL,
+			   IOMAP_DIO_PARTIAL, read);
+	from->nofault = false;
+
 	if (ret == -ENOTBLK)
 		ret = 0;
+	if (ret > 0)
+		read = ret;
+
+	if (should_fault_in_pages(ret, from, &prev_count, &window_size)) {
+		size_t leftover;
+
+		gfs2_holder_allow_demote(gh);
+		leftover = fault_in_iov_iter_readable(from, window_size);
+		gfs2_holder_disallow_demote(gh);
+		if (leftover != window_size) {
+			if (!gfs2_holder_queued(gh))
+				goto retry;
+			goto retry_under_glock;
+		}
+	}
 out:
-	gfs2_glock_dq(gh);
+	if (gfs2_holder_queued(gh))
+		gfs2_glock_dq(gh);
 out_uninit:
 	gfs2_holder_uninit(gh);
-	return ret;
+	if (ret < 0)
+		return ret;
+	return read;
 }
 
 static ssize_t gfs2_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
 {
 	struct gfs2_inode *ip;
 	struct gfs2_holder gh;
+	size_t prev_count = 0, window_size = 0;
 	size_t written = 0;
 	ssize_t ret;
 
+	/*
+	 * In this function, we disable page faults when we're holding the
+	 * inode glock while doing I/O.  If a page fault occurs, we indicate
+	 * that the inode glock may be dropped, fault in the pages manually,
+	 * and retry.
+	 */
+
 	if (iocb->ki_flags & IOCB_DIRECT) {
 		ret = gfs2_file_direct_read(iocb, to, &gh);
 		if (likely(ret != -ENOTBLK))
@@ -864,18 +977,118 @@ static ssize_t gfs2_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
 	}
 	ip = GFS2_I(iocb->ki_filp->f_mapping->host);
 	gfs2_holder_init(ip->i_gl, LM_ST_SHARED, 0, &gh);
+retry:
 	ret = gfs2_glock_nq(&gh);
 	if (ret)
 		goto out_uninit;
+retry_under_glock:
+	pagefault_disable();
 	ret = generic_file_read_iter(iocb, to);
+	pagefault_enable();
 	if (ret > 0)
 		written += ret;
-	gfs2_glock_dq(&gh);
+
+	if (should_fault_in_pages(ret, to, &prev_count, &window_size)) {
+		size_t leftover;
+
+		gfs2_holder_allow_demote(&gh);
+		leftover = fault_in_iov_iter_writeable(to, window_size);
+		gfs2_holder_disallow_demote(&gh);
+		if (leftover != window_size) {
+			if (!gfs2_holder_queued(&gh)) {
+				if (written)
+					goto out_uninit;
+				goto retry;
+			}
+			goto retry_under_glock;
+		}
+	}
+	if (gfs2_holder_queued(&gh))
+		gfs2_glock_dq(&gh);
 out_uninit:
 	gfs2_holder_uninit(&gh);
 	return written ? written : ret;
 }
 
+static ssize_t gfs2_file_buffered_write(struct kiocb *iocb,
+					struct iov_iter *from,
+					struct gfs2_holder *gh)
+{
+	struct file *file = iocb->ki_filp;
+	struct inode *inode = file_inode(file);
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct gfs2_sbd *sdp = GFS2_SB(inode);
+	struct gfs2_holder *statfs_gh = NULL;
+	size_t prev_count = 0, window_size = 0;
+	size_t read = 0;
+	ssize_t ret;
+
+	/*
+	 * In this function, we disable page faults when we're holding the
+	 * inode glock while doing I/O.  If a page fault occurs, we indicate
+	 * that the inode glock may be dropped, fault in the pages manually,
+	 * and retry.
+	 */
+
+	if (inode == sdp->sd_rindex) {
+		statfs_gh = kmalloc(sizeof(*statfs_gh), GFP_NOFS);
+		if (!statfs_gh)
+			return -ENOMEM;
+	}
+
+	gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, gh);
+retry:
+	ret = gfs2_glock_nq(gh);
+	if (ret)
+		goto out_uninit;
+retry_under_glock:
+	if (inode == sdp->sd_rindex) {
+		struct gfs2_inode *m_ip = GFS2_I(sdp->sd_statfs_inode);
+
+		ret = gfs2_glock_nq_init(m_ip->i_gl, LM_ST_EXCLUSIVE,
+					 GL_NOCACHE, statfs_gh);
+		if (ret)
+			goto out_unlock;
+	}
+
+	current->backing_dev_info = inode_to_bdi(inode);
+	pagefault_disable();
+	ret = iomap_file_buffered_write(iocb, from, &gfs2_iomap_ops);
+	pagefault_enable();
+	current->backing_dev_info = NULL;
+	if (ret > 0) {
+		iocb->ki_pos += ret;
+		read += ret;
+	}
+
+	if (inode == sdp->sd_rindex)
+		gfs2_glock_dq_uninit(statfs_gh);
+
+	if (should_fault_in_pages(ret, from, &prev_count, &window_size)) {
+		size_t leftover;
+
+		gfs2_holder_allow_demote(gh);
+		leftover = fault_in_iov_iter_readable(from, window_size);
+		gfs2_holder_disallow_demote(gh);
+		if (leftover != window_size) {
+			if (!gfs2_holder_queued(gh)) {
+				if (read)
+					goto out_uninit;
+				goto retry;
+			}
+			goto retry_under_glock;
+		}
+	}
+out_unlock:
+	if (gfs2_holder_queued(gh))
+		gfs2_glock_dq(gh);
+out_uninit:
+	gfs2_holder_uninit(gh);
+	if (statfs_gh)
+		kfree(statfs_gh);
+	return read ? read : ret;
+}
+
 /**
  * gfs2_file_write_iter - Perform a write to a file
  * @iocb: The io context
@@ -927,9 +1140,7 @@ static ssize_t gfs2_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 			goto out_unlock;
 
 		iocb->ki_flags |= IOCB_DSYNC;
-		current->backing_dev_info = inode_to_bdi(inode);
-		buffered = iomap_file_buffered_write(iocb, from, &gfs2_iomap_ops);
-		current->backing_dev_info = NULL;
+		buffered = gfs2_file_buffered_write(iocb, from, &gh);
 		if (unlikely(buffered <= 0)) {
 			if (!ret)
 				ret = buffered;
@@ -943,7 +1154,6 @@ static ssize_t gfs2_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 		 * the direct I/O range as we don't know if the buffered pages
 		 * made it to disk.
 		 */
-		iocb->ki_pos += buffered;
 		ret2 = generic_write_sync(iocb, buffered);
 		invalidate_mapping_pages(mapping,
 				(iocb->ki_pos - buffered) >> PAGE_SHIFT,
@@ -951,13 +1161,9 @@ static ssize_t gfs2_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 		if (!ret || ret2 > 0)
 			ret += ret2;
 	} else {
-		current->backing_dev_info = inode_to_bdi(inode);
-		ret = iomap_file_buffered_write(iocb, from, &gfs2_iomap_ops);
-		current->backing_dev_info = NULL;
-		if (likely(ret > 0)) {
-			iocb->ki_pos += ret;
+		ret = gfs2_file_buffered_write(iocb, from, &gh);
+		if (likely(ret > 0))
 			ret = generic_write_sync(iocb, ret);
-		}
 	}
 
 out_unlock:
diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index e0eaa9cf9fb6..f686083d0250 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -58,6 +58,7 @@ struct gfs2_glock_iter {
 typedef void (*glock_examiner) (struct gfs2_glock * gl);
 
 static void do_xmote(struct gfs2_glock *gl, struct gfs2_holder *gh, unsigned int target);
+static void __gfs2_glock_dq(struct gfs2_holder *gh);
 
 static struct dentry *gfs2_root;
 static struct workqueue_struct *glock_workqueue;
@@ -197,6 +198,12 @@ static int demote_ok(const struct gfs2_glock *gl)
 
 	if (gl->gl_state == LM_ST_UNLOCKED)
 		return 0;
+	/*
+	 * Note that demote_ok is used for the lru process of disposing of
+	 * glocks. For this purpose, we don't care if the glock's holders
+	 * have the HIF_MAY_DEMOTE flag set or not. If someone is using
+	 * them, don't demote.
+	 */
 	if (!list_empty(&gl->gl_holders))
 		return 0;
 	if (glops->go_demote_ok)
@@ -301,46 +308,59 @@ void gfs2_glock_put(struct gfs2_glock *gl)
 }
 
 /**
- * may_grant - check if its ok to grant a new lock
+ * may_grant - check if it's ok to grant a new lock
  * @gl: The glock
+ * @current_gh: One of the current holders of @gl
  * @gh: The lock request which we wish to grant
  *
- * Returns: true if its ok to grant the lock
+ * With our current compatibility rules, if a glock has one or more active
+ * holders (HIF_HOLDER flag set), any of those holders can be passed in as
+ * @current_gh; they are all the same as far as compatibility with the new @gh
+ * goes.
+ *
+ * Returns true if it's ok to grant the lock.
  */
 
-static inline int may_grant(const struct gfs2_glock *gl, const struct gfs2_holder *gh)
-{
-	const struct gfs2_holder *gh_head = list_first_entry(&gl->gl_holders, const struct gfs2_holder, gh_list);
+static inline bool may_grant(struct gfs2_glock *gl,
+			     struct gfs2_holder *current_gh,
+			     struct gfs2_holder *gh)
+{
+	if (current_gh) {
+		GLOCK_BUG_ON(gl, !test_bit(HIF_HOLDER, &current_gh->gh_iflags));
+
+		switch(current_gh->gh_state) {
+		case LM_ST_EXCLUSIVE:
+			/*
+			 * Here we make a special exception to grant holders
+			 * who agree to share the EX lock with other holders
+			 * who also have the bit set. If the original holder
+			 * has the LM_FLAG_NODE_SCOPE bit set, we grant more
+			 * holders with the bit set.
+			 */
+			return gh->gh_state == LM_ST_EXCLUSIVE &&
+			       (current_gh->gh_flags & LM_FLAG_NODE_SCOPE) &&
+			       (gh->gh_flags & LM_FLAG_NODE_SCOPE);
 
-	if (gh != gh_head) {
-		/**
-		 * Here we make a special exception to grant holders who agree
-		 * to share the EX lock with other holders who also have the
-		 * bit set. If the original holder has the LM_FLAG_NODE_SCOPE bit
-		 * is set, we grant more holders with the bit set.
-		 */
-		if (gh_head->gh_state == LM_ST_EXCLUSIVE &&
-		    (gh_head->gh_flags & LM_FLAG_NODE_SCOPE) &&
-		    gh->gh_state == LM_ST_EXCLUSIVE &&
-		    (gh->gh_flags & LM_FLAG_NODE_SCOPE))
-			return 1;
-		if ((gh->gh_state == LM_ST_EXCLUSIVE ||
-		     gh_head->gh_state == LM_ST_EXCLUSIVE))
-			return 0;
+		case LM_ST_SHARED:
+		case LM_ST_DEFERRED:
+			return gh->gh_state == current_gh->gh_state;
+
+		default:
+			return false;
+		}
 	}
+
 	if (gl->gl_state == gh->gh_state)
-		return 1;
+		return true;
 	if (gh->gh_flags & GL_EXACT)
-		return 0;
+		return false;
 	if (gl->gl_state == LM_ST_EXCLUSIVE) {
-		if (gh->gh_state == LM_ST_SHARED && gh_head->gh_state == LM_ST_SHARED)
-			return 1;
-		if (gh->gh_state == LM_ST_DEFERRED && gh_head->gh_state == LM_ST_DEFERRED)
-			return 1;
+		return gh->gh_state == LM_ST_SHARED ||
+		       gh->gh_state == LM_ST_DEFERRED;
 	}
-	if (gl->gl_state != LM_ST_UNLOCKED && (gh->gh_flags & LM_FLAG_ANY))
-		return 1;
-	return 0;
+	if (gh->gh_flags & LM_FLAG_ANY)
+		return gl->gl_state != LM_ST_UNLOCKED;
+	return false;
 }
 
 static void gfs2_holder_wake(struct gfs2_holder *gh)
@@ -366,7 +386,7 @@ static void do_error(struct gfs2_glock *gl, const int ret)
 	struct gfs2_holder *gh, *tmp;
 
 	list_for_each_entry_safe(gh, tmp, &gl->gl_holders, gh_list) {
-		if (test_bit(HIF_HOLDER, &gh->gh_iflags))
+		if (!test_bit(HIF_WAIT, &gh->gh_iflags))
 			continue;
 		if (ret & LM_OUT_ERROR)
 			gh->gh_error = -EIO;
@@ -381,6 +401,78 @@ static void do_error(struct gfs2_glock *gl, const int ret)
 }
 
 /**
+ * demote_incompat_holders - demote incompatible demoteable holders
+ * @gl: the glock we want to promote
+ * @new_gh: the new holder to be promoted
+ */
+static void demote_incompat_holders(struct gfs2_glock *gl,
+				    struct gfs2_holder *new_gh)
+{
+	struct gfs2_holder *gh;
+
+	/*
+	 * Demote incompatible holders before we make ourselves eligible.
+	 * (This holder may or may not allow auto-demoting, but we don't want
+	 * to demote the new holder before it's even granted.)
+	 */
+	list_for_each_entry(gh, &gl->gl_holders, gh_list) {
+		/*
+		 * Since holders are at the front of the list, we stop when we
+		 * find the first non-holder.
+		 */
+		if (!test_bit(HIF_HOLDER, &gh->gh_iflags))
+			return;
+		if (test_bit(HIF_MAY_DEMOTE, &gh->gh_iflags) &&
+		    !may_grant(gl, new_gh, gh)) {
+			/*
+			 * We should not recurse into do_promote because
+			 * __gfs2_glock_dq only calls handle_callback,
+			 * gfs2_glock_add_to_lru and __gfs2_glock_queue_work.
+			 */
+			__gfs2_glock_dq(gh);
+		}
+	}
+}
+
+/**
+ * find_first_holder - find the first "holder" gh
+ * @gl: the glock
+ */
+
+static inline struct gfs2_holder *find_first_holder(const struct gfs2_glock *gl)
+{
+	struct gfs2_holder *gh;
+
+	if (!list_empty(&gl->gl_holders)) {
+		gh = list_first_entry(&gl->gl_holders, struct gfs2_holder,
+				      gh_list);
+		if (test_bit(HIF_HOLDER, &gh->gh_iflags))
+			return gh;
+	}
+	return NULL;
+}
+
+/**
+ * find_first_strong_holder - find the first non-demoteable holder
+ * @gl: the glock
+ *
+ * Find the first holder that doesn't have the HIF_MAY_DEMOTE flag set.
+ */
+static inline struct gfs2_holder *
+find_first_strong_holder(struct gfs2_glock *gl)
+{
+	struct gfs2_holder *gh;
+
+	list_for_each_entry(gh, &gl->gl_holders, gh_list) {
+		if (!test_bit(HIF_HOLDER, &gh->gh_iflags))
+			return NULL;
+		if (!test_bit(HIF_MAY_DEMOTE, &gh->gh_iflags))
+			return gh;
+	}
+	return NULL;
+}
+
+/**
  * do_promote - promote as many requests as possible on the current queue
  * @gl: The glock
  * 
@@ -393,14 +485,21 @@ __releases(&gl->gl_lockref.lock)
 __acquires(&gl->gl_lockref.lock)
 {
 	const struct gfs2_glock_operations *glops = gl->gl_ops;
-	struct gfs2_holder *gh, *tmp;
+	struct gfs2_holder *gh, *tmp, *first_gh;
+	bool incompat_holders_demoted = false;
 	int ret;
 
 restart:
+	first_gh = find_first_strong_holder(gl);
 	list_for_each_entry_safe(gh, tmp, &gl->gl_holders, gh_list) {
-		if (test_bit(HIF_HOLDER, &gh->gh_iflags))
+		if (!test_bit(HIF_WAIT, &gh->gh_iflags))
 			continue;
-		if (may_grant(gl, gh)) {
+		if (may_grant(gl, first_gh, gh)) {
+			if (!incompat_holders_demoted) {
+				demote_incompat_holders(gl, first_gh);
+				incompat_holders_demoted = true;
+				first_gh = gh;
+			}
 			if (gh->gh_list.prev == &gl->gl_holders &&
 			    glops->go_lock) {
 				spin_unlock(&gl->gl_lockref.lock);
@@ -426,6 +525,11 @@ restart:
 			gfs2_holder_wake(gh);
 			continue;
 		}
+		/*
+		 * If we get here, it means we may not grant this holder for
+		 * some reason. If this holder is the head of the list, it
+		 * means we have a blocked holder at the head, so return 1.
+		 */
 		if (gh->gh_list.prev == &gl->gl_holders)
 			return 1;
 		do_error(gl, 0);
@@ -723,23 +827,6 @@ out:
 }
 
 /**
- * find_first_holder - find the first "holder" gh
- * @gl: the glock
- */
-
-static inline struct gfs2_holder *find_first_holder(const struct gfs2_glock *gl)
-{
-	struct gfs2_holder *gh;
-
-	if (!list_empty(&gl->gl_holders)) {
-		gh = list_first_entry(&gl->gl_holders, struct gfs2_holder, gh_list);
-		if (test_bit(HIF_HOLDER, &gh->gh_iflags))
-			return gh;
-	}
-	return NULL;
-}
-
-/**
  * run_queue - do all outstanding tasks related to a glock
  * @gl: The glock in question
  * @nonblock: True if we must not block in run_queue
@@ -1354,15 +1441,20 @@ __acquires(&gl->gl_lockref.lock)
 		GLOCK_BUG_ON(gl, true);
 
 	if (gh->gh_flags & (LM_FLAG_TRY | LM_FLAG_TRY_1CB)) {
-		if (test_bit(GLF_LOCK, &gl->gl_flags))
-			try_futile = !may_grant(gl, gh);
+		if (test_bit(GLF_LOCK, &gl->gl_flags)) {
+			struct gfs2_holder *first_gh;
+
+			first_gh = find_first_strong_holder(gl);
+			try_futile = !may_grant(gl, first_gh, gh);
+		}
 		if (test_bit(GLF_INVALIDATE_IN_PROGRESS, &gl->gl_flags))
 			goto fail;
 	}
 
 	list_for_each_entry(gh2, &gl->gl_holders, gh_list) {
 		if (unlikely(gh2->gh_owner_pid == gh->gh_owner_pid &&
-		    (gh->gh_gl->gl_ops->go_type != LM_TYPE_FLOCK)))
+		    (gh->gh_gl->gl_ops->go_type != LM_TYPE_FLOCK) &&
+		    !test_bit(HIF_MAY_DEMOTE, &gh2->gh_iflags)))
 			goto trap_recursive;
 		if (try_futile &&
 		    !(gh2->gh_flags & (LM_FLAG_TRY | LM_FLAG_TRY_1CB))) {
@@ -1458,51 +1550,83 @@ int gfs2_glock_poll(struct gfs2_holder *gh)
 	return test_bit(HIF_WAIT, &gh->gh_iflags) ? 0 : 1;
 }
 
-/**
- * gfs2_glock_dq - dequeue a struct gfs2_holder from a glock (release a glock)
- * @gh: the glock holder
- *
- */
+static inline bool needs_demote(struct gfs2_glock *gl)
+{
+	return (test_bit(GLF_DEMOTE, &gl->gl_flags) ||
+		test_bit(GLF_PENDING_DEMOTE, &gl->gl_flags));
+}
 
-void gfs2_glock_dq(struct gfs2_holder *gh)
+static void __gfs2_glock_dq(struct gfs2_holder *gh)
 {
 	struct gfs2_glock *gl = gh->gh_gl;
 	struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
 	unsigned delay = 0;
 	int fast_path = 0;
 
-	spin_lock(&gl->gl_lockref.lock);
 	/*
-	 * If we're in the process of file system withdraw, we cannot just
-	 * dequeue any glocks until our journal is recovered, lest we
-	 * introduce file system corruption. We need two exceptions to this
-	 * rule: We need to allow unlocking of nondisk glocks and the glock
-	 * for our own journal that needs recovery.
+	 * This while loop is similar to function demote_incompat_holders:
+	 * If the glock is due to be demoted (which may be from another node
+	 * or even if this holder is GL_NOCACHE), the weak holders are
+	 * demoted as well, allowing the glock to be demoted.
 	 */
-	if (test_bit(SDF_WITHDRAW_RECOVERY, &sdp->sd_flags) &&
-	    glock_blocked_by_withdraw(gl) &&
-	    gh->gh_gl != sdp->sd_jinode_gl) {
-		sdp->sd_glock_dqs_held++;
-		spin_unlock(&gl->gl_lockref.lock);
-		might_sleep();
-		wait_on_bit(&sdp->sd_flags, SDF_WITHDRAW_RECOVERY,
-			    TASK_UNINTERRUPTIBLE);
-		spin_lock(&gl->gl_lockref.lock);
-	}
-	if (gh->gh_flags & GL_NOCACHE)
-		handle_callback(gl, LM_ST_UNLOCKED, 0, false);
+	while (gh) {
+		/*
+		 * If we're in the process of file system withdraw, we cannot
+		 * just dequeue any glocks until our journal is recovered, lest
+		 * we introduce file system corruption. We need two exceptions
+		 * to this rule: We need to allow unlocking of nondisk glocks
+		 * and the glock for our own journal that needs recovery.
+		 */
+		if (test_bit(SDF_WITHDRAW_RECOVERY, &sdp->sd_flags) &&
+		    glock_blocked_by_withdraw(gl) &&
+		    gh->gh_gl != sdp->sd_jinode_gl) {
+			sdp->sd_glock_dqs_held++;
+			spin_unlock(&gl->gl_lockref.lock);
+			might_sleep();
+			wait_on_bit(&sdp->sd_flags, SDF_WITHDRAW_RECOVERY,
+				    TASK_UNINTERRUPTIBLE);
+			spin_lock(&gl->gl_lockref.lock);
+		}
 
-	list_del_init(&gh->gh_list);
-	clear_bit(HIF_HOLDER, &gh->gh_iflags);
-	if (list_empty(&gl->gl_holders) &&
-	    !test_bit(GLF_PENDING_DEMOTE, &gl->gl_flags) &&
-	    !test_bit(GLF_DEMOTE, &gl->gl_flags))
-		fast_path = 1;
+		/*
+		 * This holder should not be cached, so mark it for demote.
+		 * Note: this should be done before the check for needs_demote
+		 * below.
+		 */
+		if (gh->gh_flags & GL_NOCACHE)
+			handle_callback(gl, LM_ST_UNLOCKED, 0, false);
+
+		list_del_init(&gh->gh_list);
+		clear_bit(HIF_HOLDER, &gh->gh_iflags);
+		trace_gfs2_glock_queue(gh, 0);
+
+		/*
+		 * If there hasn't been a demote request we are done.
+		 * (Let the remaining holders, if any, keep holding it.)
+		 */
+		if (!needs_demote(gl)) {
+			if (list_empty(&gl->gl_holders))
+				fast_path = 1;
+			break;
+		}
+		/*
+		 * If we have another strong holder (we cannot auto-demote)
+		 * we are done. It keeps holding it until it is done.
+		 */
+		if (find_first_strong_holder(gl))
+			break;
+
+		/*
+		 * If we have a weak holder at the head of the list, it
+		 * (and all others like it) must be auto-demoted. If there
+		 * are no more weak holders, we exit the while loop.
+		 */
+		gh = find_first_holder(gl);
+	}
 
 	if (!test_bit(GLF_LFLUSH, &gl->gl_flags) && demote_ok(gl))
 		gfs2_glock_add_to_lru(gl);
 
-	trace_gfs2_glock_queue(gh, 0);
 	if (unlikely(!fast_path)) {
 		gl->gl_lockref.count++;
 		if (test_bit(GLF_PENDING_DEMOTE, &gl->gl_flags) &&
@@ -1511,6 +1635,19 @@ void gfs2_glock_dq(struct gfs2_holder *gh)
 			delay = gl->gl_hold_time;
 		__gfs2_glock_queue_work(gl, delay);
 	}
+}
+
+/**
+ * gfs2_glock_dq - dequeue a struct gfs2_holder from a glock (release a glock)
+ * @gh: the glock holder
+ *
+ */
+void gfs2_glock_dq(struct gfs2_holder *gh)
+{
+	struct gfs2_glock *gl = gh->gh_gl;
+
+	spin_lock(&gl->gl_lockref.lock);
+	__gfs2_glock_dq(gh);
 	spin_unlock(&gl->gl_lockref.lock);
 }
 
@@ -1673,6 +1810,7 @@ void gfs2_glock_dq_m(unsigned int num_gh, struct gfs2_holder *ghs)
 
 void gfs2_glock_cb(struct gfs2_glock *gl, unsigned int state)
 {
+	struct gfs2_holder mock_gh = { .gh_gl = gl, .gh_state = state, };
 	unsigned long delay = 0;
 	unsigned long holdtime;
 	unsigned long now = jiffies;
@@ -1687,6 +1825,28 @@ void gfs2_glock_cb(struct gfs2_glock *gl, unsigned int state)
 		if (test_bit(GLF_REPLY_PENDING, &gl->gl_flags))
 			delay = gl->gl_hold_time;
 	}
+	/*
+	 * Note 1: We cannot call demote_incompat_holders from handle_callback
+	 * or gfs2_set_demote due to recursion problems like: gfs2_glock_dq ->
+	 * handle_callback -> demote_incompat_holders -> gfs2_glock_dq
+	 * Plus, we only want to demote the holders if the request comes from
+	 * a remote cluster node because local holder conflicts are resolved
+	 * elsewhere.
+	 *
+	 * Note 2: if a remote node wants this glock in EX mode, lock_dlm will
+	 * request that we set our state to UNLOCKED. Here we mock up a holder
+	 * to make it look like someone wants the lock EX locally. Any SH
+	 * and DF requests should be able to share the lock without demoting.
+	 *
+	 * Note 3: We only want to demote the demoteable holders when there
+	 * are no more strong holders. The demoteable holders might as well
+	 * keep the glock until the last strong holder is done with it.
+	 */
+	if (!find_first_strong_holder(gl)) {
+		if (state == LM_ST_UNLOCKED)
+			mock_gh.gh_state = LM_ST_EXCLUSIVE;
+		demote_incompat_holders(gl, &mock_gh);
+	}
 	handle_callback(gl, state, delay, true);
 	__gfs2_glock_queue_work(gl, delay);
 	spin_unlock(&gl->gl_lockref.lock);
@@ -2076,6 +2236,8 @@ static const char *hflags2str(char *buf, u16 flags, unsigned long iflags)
 		*p++ = 'H';
 	if (test_bit(HIF_WAIT, &iflags))
 		*p++ = 'W';
+	if (test_bit(HIF_MAY_DEMOTE, &iflags))
+		*p++ = 'D';
 	*p = 0;
 	return buf;
 }
diff --git a/fs/gfs2/glock.h b/fs/gfs2/glock.h
index 31a8f2f649b5..9012487da4c6 100644
--- a/fs/gfs2/glock.h
+++ b/fs/gfs2/glock.h
@@ -150,6 +150,8 @@ static inline struct gfs2_holder *gfs2_glock_is_locked_by_me(struct gfs2_glock *
 	list_for_each_entry(gh, &gl->gl_holders, gh_list) {
 		if (!test_bit(HIF_HOLDER, &gh->gh_iflags))
 			break;
+		if (test_bit(HIF_MAY_DEMOTE, &gh->gh_iflags))
+			continue;
 		if (gh->gh_owner_pid == pid)
 			goto out;
 	}
@@ -325,6 +327,24 @@ static inline void glock_clear_object(struct gfs2_glock *gl, void *object)
 	spin_unlock(&gl->gl_lockref.lock);
 }
 
+static inline void gfs2_holder_allow_demote(struct gfs2_holder *gh)
+{
+	struct gfs2_glock *gl = gh->gh_gl;
+
+	spin_lock(&gl->gl_lockref.lock);
+	set_bit(HIF_MAY_DEMOTE, &gh->gh_iflags);
+	spin_unlock(&gl->gl_lockref.lock);
+}
+
+static inline void gfs2_holder_disallow_demote(struct gfs2_holder *gh)
+{
+	struct gfs2_glock *gl = gh->gh_gl;
+
+	spin_lock(&gl->gl_lockref.lock);
+	clear_bit(HIF_MAY_DEMOTE, &gh->gh_iflags);
+	spin_unlock(&gl->gl_lockref.lock);
+}
+
 extern void gfs2_inode_remember_delete(struct gfs2_glock *gl, u64 generation);
 extern bool gfs2_inode_already_deleted(struct gfs2_glock *gl, u64 generation);
 
diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h
index 0fe49770166e..ca42d310fd4d 100644
--- a/fs/gfs2/incore.h
+++ b/fs/gfs2/incore.h
@@ -252,6 +252,7 @@ struct gfs2_lkstats {
 
 enum {
 	/* States */
+	HIF_MAY_DEMOTE		= 1,
 	HIF_HOLDER		= 6,  /* Set for gh that "holds" the glock */
 	HIF_WAIT		= 10,
 };
@@ -386,9 +387,8 @@ struct gfs2_inode {
 	u64 i_generation;
 	u64 i_eattr;
 	unsigned long i_flags;		/* GIF_... */
-	struct gfs2_glock *i_gl; /* Move into i_gh? */
+	struct gfs2_glock *i_gl;
 	struct gfs2_holder i_iopen_gh;
-	struct gfs2_holder i_gh; /* for prepare/commit_write only */
 	struct gfs2_qadata *i_qadata; /* quota allocation data */
 	struct gfs2_holder i_rgd_gh;
 	struct gfs2_blkreserv i_res; /* rgrp multi-block reservation */