Merge tag 'nfs-for-4.16-4' of git://git.linux-nfs.org/projects/trondmy/linux-nfs

Pull NFS client bugfixes from Trond Myklebust:
 "Hightlights include the following stable fixes:

   - NFS: Fix an incorrect type in struct nfs_direct_req

   - pNFS: Prevent the layout header refcount going to zero in
     pnfs_roc()

   - NFS: Fix unstable write completion"

* tag 'nfs-for-4.16-4' of git://git.linux-nfs.org/projects/trondmy/linux-nfs:
  NFS: Fix unstable write completion
  pNFS: Prevent the layout header refcount going to zero in pnfs_roc()
  NFS: Fix an incorrect type in struct nfs_direct_req

3 files changed, 54 insertions, 44 deletions

diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index 8c10b0562e75..621c517b325c 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -86,10 +86,10 @@ struct nfs_direct_req {
 	struct nfs_direct_mirror mirrors[NFS_PAGEIO_DESCRIPTOR_MIRROR_MAX];
 	int			mirror_count;
 
+	loff_t			io_start;	/* Start offset for I/O */
 	ssize_t			count,		/* bytes actually processed */
 				max_count,	/* max expected count */
 				bytes_left,	/* bytes left to be sent */
-				io_start,	/* start of IO */
 				error;		/* any reported error */
 	struct completion	completion;	/* wait for i/o completion */
 
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index c13e826614b5..ee723aa153a3 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -292,8 +292,11 @@ pnfs_detach_layout_hdr(struct pnfs_layout_hdr *lo)
 void
 pnfs_put_layout_hdr(struct pnfs_layout_hdr *lo)
 {
-	struct inode *inode = lo->plh_inode;
+	struct inode *inode;
 
+	if (!lo)
+		return;
+	inode = lo->plh_inode;
 	pnfs_layoutreturn_before_put_layout_hdr(lo);
 
 	if (refcount_dec_and_lock(&lo->plh_refcount, &inode->i_lock)) {
@@ -1241,10 +1244,12 @@ retry:
 	spin_lock(&ino->i_lock);
 	lo = nfsi->layout;
 	if (!lo || !pnfs_layout_is_valid(lo) ||
-	    test_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags))
+	    test_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags)) {
+		lo = NULL;
 		goto out_noroc;
+	}
+	pnfs_get_layout_hdr(lo);
 	if (test_bit(NFS_LAYOUT_RETURN_LOCK, &lo->plh_flags)) {
-		pnfs_get_layout_hdr(lo);
 		spin_unlock(&ino->i_lock);
 		wait_on_bit(&lo->plh_flags, NFS_LAYOUT_RETURN,
 				TASK_UNINTERRUPTIBLE);
@@ -1312,10 +1317,12 @@ out_noroc:
 		struct pnfs_layoutdriver_type *ld = NFS_SERVER(ino)->pnfs_curr_ld;
 		if (ld->prepare_layoutreturn)
 			ld->prepare_layoutreturn(args);
+		pnfs_put_layout_hdr(lo);
 		return true;
 	}
 	if (layoutreturn)
 		pnfs_send_layoutreturn(lo, &stateid, iomode, true);
+	pnfs_put_layout_hdr(lo);
 	return false;
 }
 
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 7428a669d7a7..e7d8ceae8f26 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -1876,40 +1876,43 @@ int nfs_generic_commit_list(struct inode *inode, struct list_head *head,
 	return status;
 }
 
-int nfs_commit_inode(struct inode *inode, int how)
+static int __nfs_commit_inode(struct inode *inode, int how,
+		struct writeback_control *wbc)
 {
 	LIST_HEAD(head);
 	struct nfs_commit_info cinfo;
 	int may_wait = how & FLUSH_SYNC;
-	int error = 0;
-	int res;
+	int ret, nscan;
 
 	nfs_init_cinfo_from_inode(&cinfo, inode);
 	nfs_commit_begin(cinfo.mds);
-	res = nfs_scan_commit(inode, &head, &cinfo);
-	if (res)
-		error = nfs_generic_commit_list(inode, &head, how, &cinfo);
+	for (;;) {
+		ret = nscan = nfs_scan_commit(inode, &head, &cinfo);
+		if (ret <= 0)
+			break;
+		ret = nfs_generic_commit_list(inode, &head, how, &cinfo);
+		if (ret < 0)
+			break;
+		ret = 0;
+		if (wbc && wbc->sync_mode == WB_SYNC_NONE) {
+			if (nscan < wbc->nr_to_write)
+				wbc->nr_to_write -= nscan;
+			else
+				wbc->nr_to_write = 0;
+		}
+		if (nscan < INT_MAX)
+			break;
+		cond_resched();
+	}
 	nfs_commit_end(cinfo.mds);
-	if (res == 0)
-		return res;
-	if (error < 0)
-		goto out_error;
-	if (!may_wait)
-		goto out_mark_dirty;
-	error = wait_on_commit(cinfo.mds);
-	if (error < 0)
-		return error;
-	return res;
-out_error:
-	res = error;
-	/* Note: If we exit without ensuring that the commit is complete,
-	 * we must mark the inode as dirty. Otherwise, future calls to
-	 * sync_inode() with the WB_SYNC_ALL flag set will fail to ensure
-	 * that the data is on the disk.
-	 */
-out_mark_dirty:
-	__mark_inode_dirty(inode, I_DIRTY_DATASYNC);
-	return res;
+	if (ret || !may_wait)
+		return ret;
+	return wait_on_commit(cinfo.mds);
+}
+
+int nfs_commit_inode(struct inode *inode, int how)
+{
+	return __nfs_commit_inode(inode, how, NULL);
 }
 EXPORT_SYMBOL_GPL(nfs_commit_inode);
 
@@ -1919,11 +1922,11 @@ int nfs_write_inode(struct inode *inode, struct writeback_control *wbc)
 	int flags = FLUSH_SYNC;
 	int ret = 0;
 
-	/* no commits means nothing needs to be done */
-	if (!atomic_long_read(&nfsi->commit_info.ncommit))
-		return ret;
-
 	if (wbc->sync_mode == WB_SYNC_NONE) {
+		/* no commits means nothing needs to be done */
+		if (!atomic_long_read(&nfsi->commit_info.ncommit))
+			goto check_requests_outstanding;
+
 		/* Don't commit yet if this is a non-blocking flush and there
 		 * are a lot of outstanding writes for this mapping.
 		 */
@@ -1934,16 +1937,16 @@ int nfs_write_inode(struct inode *inode, struct writeback_control *wbc)
 		flags = 0;
 	}
 
-	ret = nfs_commit_inode(inode, flags);
-	if (ret >= 0) {
-		if (wbc->sync_mode == WB_SYNC_NONE) {
-			if (ret < wbc->nr_to_write)
-				wbc->nr_to_write -= ret;
-			else
-				wbc->nr_to_write = 0;
-		}
-		return 0;
-	}
+	ret = __nfs_commit_inode(inode, flags, wbc);
+	if (!ret) {
+		if (flags & FLUSH_SYNC)
+			return 0;
+	} else if (atomic_long_read(&nfsi->commit_info.ncommit))
+		goto out_mark_dirty;
+
+check_requests_outstanding:
+	if (!atomic_read(&nfsi->commit_info.rpcs_out))
+		return ret;
 out_mark_dirty:
 	__mark_inode_dirty(inode, I_DIRTY_DATASYNC);
 	return ret;