NFSD: Instantiate a struct file when creating a regular NFSv4 file

There have been reports of races that cause NFSv4 OPEN(CREATE) to
return an error even though the requested file was created. NFSv4
does not provide a status code for this case.

To mitigate some of these problems, reorganize the NFSv4
OPEN(CREATE) logic to allocate resources before the file is actually
created, and open the new file while the parent directory is still
locked.

Two new APIs are added:

+ Add an API that works like nfsd_file_acquire() but does not open
the underlying file. The OPEN(CREATE) path can use this API when it
already has an open file.

+ Add an API that is kin to dentry_open(). NFSD needs to create a
file and grab an open "struct file *" atomically. The
alloc_empty_file() has to be done before the inode create. If it
fails (for example, because the NFS server has exceeded its
max_files limit), we avoid creating the file and can still return
an error to the NFS client.

BugLink: https://bugzilla.linux-nfs.org/show_bug.cgi?id=382
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Tested-by: JianHong Yin <jiyin@redhat.com>

1 files changed, 39 insertions, 4 deletions

diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index 99c0485a29e9..28bae84d7809 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -243,6 +243,37 @@ static inline bool nfsd4_create_is_exclusive(int createmode)
 		createmode == NFS4_CREATE_EXCLUSIVE4_1;
 }
 
+static __be32
+nfsd4_vfs_create(struct svc_fh *fhp, struct dentry *child,
+		 struct nfsd4_open *open)
+{
+	struct file *filp;
+	struct path path;
+	int oflags;
+
+	oflags = O_CREAT | O_LARGEFILE;
+	switch (open->op_share_access & NFS4_SHARE_ACCESS_BOTH) {
+	case NFS4_SHARE_ACCESS_WRITE:
+		oflags |= O_WRONLY;
+		break;
+	case NFS4_SHARE_ACCESS_BOTH:
+		oflags |= O_RDWR;
+		break;
+	default:
+		oflags |= O_RDONLY;
+	}
+
+	path.mnt = fhp->fh_export->ex_path.mnt;
+	path.dentry = child;
+	filp = dentry_create(&path, oflags, open->op_iattr.ia_mode,
+			     current_cred());
+	if (IS_ERR(filp))
+		return nfserrno(PTR_ERR(filp));
+
+	open->op_filp = filp;
+	return nfs_ok;
+}
+
 /*
  * Implement NFSv4's unchecked, guarded, and exclusive create
  * semantics for regular files. Open state for this new file is
@@ -355,11 +386,9 @@ nfsd4_create_file(struct svc_rqst *rqstp, struct svc_fh *fhp,
 	if (!IS_POSIXACL(inode))
 		iap->ia_mode &= ~current_umask();
 
-	host_err = vfs_create(&init_user_ns, inode, child, iap->ia_mode, true);
-	if (host_err < 0) {
-		status = nfserrno(host_err);
+	status = nfsd4_vfs_create(fhp, child, open);
+	if (status != nfs_ok)
 		goto out;
-	}
 	open->op_created = true;
 
 	/* A newly created file already has a file size of zero. */
@@ -517,6 +546,8 @@ nfsd4_open(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 		(int)open->op_fnamelen, open->op_fname,
 		open->op_openowner);
 
+	open->op_filp = NULL;
+
 	/* This check required by spec. */
 	if (open->op_create && open->op_claim_type != NFS4_OPEN_CLAIM_NULL)
 		return nfserr_inval;
@@ -613,6 +644,10 @@ nfsd4_open(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	if (reclaim && !status)
 		nn->somebody_reclaimed = true;
 out:
+	if (open->op_filp) {
+		fput(open->op_filp);
+		open->op_filp = NULL;
+	}
 	if (resfh && resfh != &cstate->current_fh) {
 		fh_dup2(&cstate->current_fh, resfh);
 		fh_put(resfh);