nfs: add 'noalignwrite' option for lock-less 'lost writes' prevention

There are some applications that write to predefined non-overlapping
file offsets from multiple clients and therefore don't need to rely on
file locking. However, if these applications want non-aligned offsets
and sizes they need to either use locks or risk data corruption, as the
NFS client defaults to extending writes to whole pages.

This commit adds a new mount option `noalignwrite`, which allows to turn
that off and avoid the need of locking, as long as these applications
don't overlap on offsets.
Signed-off-by: Dan Aloni <dan.aloni@vastdata.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Anna Schumaker <anna.schumaker@oracle.com>

fs/nfs/fs_context.c

@@ -49,6 +49,7 @@ enum nfs_param {
 	Opt_bsize,
 	Opt_clientaddr,
 	Opt_cto,
+	Opt_alignwrite,
 	Opt_fg,
 	Opt_fscache,
 	Opt_fscache_flag,
@@ -149,6 +150,7 @@ static const struct fs_parameter_spec nfs_fs_parameters[] = {
 	fsparam_u32   ("bsize",		Opt_bsize),
 	fsparam_string("clientaddr",	Opt_clientaddr),
 	fsparam_flag_no("cto",		Opt_cto),
+	fsparam_flag_no("alignwrite",	Opt_alignwrite),
 	fsparam_flag  ("fg",		Opt_fg),
 	fsparam_flag_no("fsc",		Opt_fscache_flag),
 	fsparam_string("fsc",		Opt_fscache),
@@ -592,6 +594,12 @@ static int nfs_fs_context_parse_param(struct fs_context *fc,
 		else
 			ctx->flags |= NFS_MOUNT_TRUNK_DISCOVERY;
 		break;
+	case Opt_alignwrite:
+		if (result.negated)
+			ctx->flags |= NFS_MOUNT_NO_ALIGNWRITE;
+		else
+			ctx->flags &= ~NFS_MOUNT_NO_ALIGNWRITE;
+		break;
 	case Opt_ac:
 		if (result.negated)
 			ctx->flags |= NFS_MOUNT_NOAC;

fs/nfs/super.c

@@ -551,6 +551,9 @@ static void nfs_show_mount_options(struct seq_file *m, struct nfs_server *nfss,
 	else
 		seq_puts(m, ",local_lock=posix");
 
+	if (nfss->flags & NFS_MOUNT_NO_ALIGNWRITE)
+		seq_puts(m, ",noalignwrite");
+
 	if (nfss->flags & NFS_MOUNT_WRITE_EAGER) {
 		if (nfss->flags & NFS_MOUNT_WRITE_WAIT)
 			seq_puts(m, ",write=wait");

fs/nfs/write.c

@@ -1295,7 +1295,10 @@ static int nfs_can_extend_write(struct file *file, struct folio *folio,
 	struct file_lock_context *flctx = locks_inode_context(inode);
 	struct file_lock *fl;
 	int ret;
+	unsigned int mntflags = NFS_SERVER(inode)->flags;
 
+	if (mntflags & NFS_MOUNT_NO_ALIGNWRITE)
+		return 0;
 	if (file->f_flags & O_DSYNC)
 		return 0;
 	if (!nfs_folio_write_uptodate(folio, pagelen))

include/linux/nfs_fs_sb.h

@@ -158,6 +158,7 @@ struct nfs_server {
 #define NFS_MOUNT_WRITE_WAIT		0x02000000
 #define NFS_MOUNT_TRUNK_DISCOVERY	0x04000000
 #define NFS_MOUNT_SHUTDOWN			0x08000000
+#define NFS_MOUNT_NO_ALIGNWRITE		0x10000000
 
 	unsigned int		fattr_valid;	/* Valid attributes */
 	unsigned int		caps;		/* server capabilities */