NFSD: Offer write delegation for OPEN with OPEN4_SHARE_ACCESS_WRITE

RFC8881, section 9.1.2 says:

  "In the case of READ, the server may perform the corresponding
   check on the access mode, or it may choose to allow READ for
   OPEN4_SHARE_ACCESS_WRITE, to accommodate clients whose WRITE
   implementation may unavoidably do reads (e.g., due to buffer cache
   constraints)."

and in section 10.4.1:
   "Similarly, when closing a file opened for OPEN4_SHARE_ACCESS_WRITE/
   OPEN4_SHARE_ACCESS_BOTH and if an OPEN_DELEGATE_WRITE delegation
   is in effect"

This patch allows READ using write delegation stateid granted on OPENs
with OPEN4_SHARE_ACCESS_WRITE only, to accommodate clients whose WRITE
implementation may unavoidably do (e.g., due to buffer cache
constraints).

For write delegation granted for OPEN with OPEN4_SHARE_ACCESS_WRITE
a new nfsd_file and a struct file are allocated to use for reads.
The nfsd_file is freed when the file is closed by release_all_access.

Suggested-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Dai Ngo <dai.ngo@oracle.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>

1 files changed, 47 insertions, 28 deletions

diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index d5694987f86f..54fb323598ea 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -633,18 +633,6 @@ find_readable_file(struct nfs4_file *f)
 	return ret;
 }
 
-static struct nfsd_file *
-find_rw_file(struct nfs4_file *f)
-{
-	struct nfsd_file *ret;
-
-	spin_lock(&f->fi_lock);
-	ret = nfsd_file_get(f->fi_fds[O_RDWR]);
-	spin_unlock(&f->fi_lock);
-
-	return ret;
-}
-
 struct nfsd_file *
 find_any_file(struct nfs4_file *f)
 {
@@ -6000,14 +5988,19 @@ nfs4_set_delegation(struct nfsd4_open *open, struct nfs4_ol_stateid *stp,
 	 *  "An OPEN_DELEGATE_WRITE delegation allows the client to handle,
 	 *   on its own, all opens."
 	 *
-	 * Furthermore the client can use a write delegation for most READ
-	 * operations as well, so we require a O_RDWR file here.
+	 * Furthermore, section 9.1.2 says:
+	 *
+	 *  "In the case of READ, the server may perform the corresponding
+	 *  check on the access mode, or it may choose to allow READ for
+	 *  OPEN4_SHARE_ACCESS_WRITE, to accommodate clients whose WRITE
+	 *  implementation may unavoidably do reads (e.g., due to buffer
+	 *  cache constraints)."
 	 *
-	 * Offer a write delegation in the case of a BOTH open, and ensure
-	 * we get the O_RDWR descriptor.
+	 *  We choose to offer a write delegation for OPEN with the
+	 *  OPEN4_SHARE_ACCESS_WRITE access mode to accommodate such clients.
 	 */
-	if ((open->op_share_access & NFS4_SHARE_ACCESS_BOTH) == NFS4_SHARE_ACCESS_BOTH) {
-		nf = find_rw_file(fp);
+	if (open->op_share_access & NFS4_SHARE_ACCESS_WRITE) {
+		nf = find_writeable_file(fp);
 		dl_type = deleg_ts ? OPEN_DELEGATE_WRITE_ATTRS_DELEG : OPEN_DELEGATE_WRITE;
 	}
 
@@ -6138,7 +6131,7 @@ static bool
 nfs4_delegation_stat(struct nfs4_delegation *dp, struct svc_fh *currentfh,
 		     struct kstat *stat)
 {
-	struct nfsd_file *nf = find_rw_file(dp->dl_stid.sc_file);
+	struct nfsd_file *nf = find_writeable_file(dp->dl_stid.sc_file);
 	struct path path;
 	int rc;
 
@@ -6157,6 +6150,33 @@ nfs4_delegation_stat(struct nfs4_delegation *dp, struct svc_fh *currentfh,
 }
 
 /*
+ * Add NFS4_SHARE_ACCESS_READ to the write delegation granted on OPEN
+ * with NFS4_SHARE_ACCESS_WRITE by allocating separate nfsd_file and
+ * struct file to be used for read with delegation stateid.
+ *
+ */
+static bool
+nfsd4_add_rdaccess_to_wrdeleg(struct svc_rqst *rqstp, struct nfsd4_open *open,
+			      struct svc_fh *fh, struct nfs4_ol_stateid *stp)
+{
+	struct nfs4_file *fp;
+	struct nfsd_file *nf = NULL;
+
+	if ((open->op_share_access & NFS4_SHARE_ACCESS_BOTH) ==
+			NFS4_SHARE_ACCESS_WRITE) {
+		if (nfsd_file_acquire_opened(rqstp, fh, NFSD_MAY_READ, NULL, &nf))
+			return (false);
+		fp = stp->st_stid.sc_file;
+		spin_lock(&fp->fi_lock);
+		__nfs4_file_get_access(fp, NFS4_SHARE_ACCESS_READ);
+		fp = stp->st_stid.sc_file;
+		fp->fi_fds[O_RDONLY] = nf;
+		spin_unlock(&fp->fi_lock);
+	}
+	return true;
+}
+
+/*
  * The Linux NFS server does not offer write delegations to NFSv4.0
  * clients in order to avoid conflicts between write delegations and
  * GETATTRs requesting CHANGE or SIZE attributes.
@@ -6181,8 +6201,9 @@ nfs4_delegation_stat(struct nfs4_delegation *dp, struct svc_fh *currentfh,
  * open or lock state.
  */
 static void
-nfs4_open_delegation(struct nfsd4_open *open, struct nfs4_ol_stateid *stp,
-		     struct svc_fh *currentfh)
+nfs4_open_delegation(struct svc_rqst *rqstp, struct nfsd4_open *open,
+		     struct nfs4_ol_stateid *stp, struct svc_fh *currentfh,
+		     struct svc_fh *fh)
 {
 	struct nfs4_openowner *oo = openowner(stp->st_stateowner);
 	bool deleg_ts = nfsd4_want_deleg_timestamps(open);
@@ -6227,7 +6248,8 @@ nfs4_open_delegation(struct nfsd4_open *open, struct nfs4_ol_stateid *stp,
 	memcpy(&open->op_delegate_stateid, &dp->dl_stid.sc_stateid, sizeof(dp->dl_stid.sc_stateid));
 
 	if (open->op_share_access & NFS4_SHARE_ACCESS_WRITE) {
-		if (!nfs4_delegation_stat(dp, currentfh, &stat)) {
+		if (!nfsd4_add_rdaccess_to_wrdeleg(rqstp, open, fh, stp) ||
+				!nfs4_delegation_stat(dp, currentfh, &stat)) {
 			nfs4_put_stid(&dp->dl_stid);
 			destroy_delegation(dp);
 			goto out_no_deleg;
@@ -6383,7 +6405,8 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf
 	* Attempt to hand out a delegation. No error return, because the
 	* OPEN succeeds even if we fail.
 	*/
-	nfs4_open_delegation(open, stp, &resp->cstate.current_fh);
+	nfs4_open_delegation(rqstp, open, stp,
+		&resp->cstate.current_fh, current_fh);
 
 	/*
 	 * If there is an existing open stateid, it must be updated and
@@ -7076,7 +7099,7 @@ nfsd4_lookup_stateid(struct nfsd4_compound_state *cstate,
 		return_revoked = true;
 	if (typemask & SC_TYPE_DELEG)
 		/* Always allow REVOKED for DELEG so we can
-		 * retturn the appropriate error.
+		 * return the appropriate error.
 		 */
 		statusmask |= SC_STATUS_REVOKED;
 
@@ -7119,10 +7142,6 @@ nfs4_find_file(struct nfs4_stid *s, int flags)
 
 	switch (s->sc_type) {
 	case SC_TYPE_DELEG:
-		spin_lock(&s->sc_file->fi_lock);
-		ret = nfsd_file_get(s->sc_file->fi_deleg_file);
-		spin_unlock(&s->sc_file->fi_lock);
-		break;
 	case SC_TYPE_OPEN:
 	case SC_TYPE_LOCK:
 		if (flags & RD_STATE)