Merge tag 'nfsd-5.13' of git://git.kernel.org/pub/scm/linux/kernel/git/cel/linux

Pull nfsd updates from Chuck Lever:
 "Highlights:

   - Update NFSv2 and NFSv3 XDR encoding functions

   - Add batch Receive posting to the server's RPC/RDMA transport (take 2)

   - Reduce page allocator traffic in svcrdma"

* tag 'nfsd-5.13' of git://git.kernel.org/pub/scm/linux/kernel/git/cel/linux: (70 commits)
  NFSD: Use DEFINE_SPINLOCK() for spinlock
  sunrpc: Remove unused function ip_map_lookup
  NFSv4.2: fix copy stateid copying for the async copy
  UAPI: nfsfh.h: Replace one-element array with flexible-array member
  svcrdma: Clean up dto_q critical section in svc_rdma_recvfrom()
  svcrdma: Remove svc_rdma_recv_ctxt::rc_pages and ::rc_arg
  svcrdma: Remove sc_read_complete_q
  svcrdma: Single-stage RDMA Read
  SUNRPC: Move svc_xprt_received() call sites
  SUNRPC: Export svc_xprt_received()
  svcrdma: Retain the page backing rq_res.head[0].iov_base
  svcrdma: Remove unused sc_pages field
  svcrdma: Normalize Send page handling
  svcrdma: Add a "deferred close" helper
  svcrdma: Maintain a Receive water mark
  svcrdma: Use svc_rdma_refresh_recvs() in wc_receive
  svcrdma: Add a batch Receive posting mechanism
  svcrdma: Remove stale comment for svc_rdma_wc_receive()
  svcrdma: Provide an explanatory comment in CMA event handler
  svcrdma: RPCDBG_FACILITY is no longer used
  ...

Author: torvalds

fs/nfs_common/nfsacl.c

@@ -136,6 +136,77 @@ int nfsacl_encode(struct xdr_buf *buf, unsigned int base, struct inode *inode,
 }
 EXPORT_SYMBOL_GPL(nfsacl_encode);
 
+/**
+ * nfs_stream_encode_acl - Encode an NFSv3 ACL
+ *
+ * @xdr: an xdr_stream positioned to receive an encoded ACL
+ * @inode: inode of file whose ACL this is
+ * @acl: posix_acl to encode
+ * @encode_entries: whether to encode ACEs as well
+ * @typeflag: ACL type: NFS_ACL_DEFAULT or zero
+ *
+ * Return values:
+ *   %false: The ACL could not be encoded
+ *   %true: @xdr is advanced to the next available position
+ */
+bool nfs_stream_encode_acl(struct xdr_stream *xdr, struct inode *inode,
+			   struct posix_acl *acl, int encode_entries,
+			   int typeflag)
+{
+	const size_t elem_size = XDR_UNIT * 3;
+	u32 entries = (acl && acl->a_count) ? max_t(int, acl->a_count, 4) : 0;
+	struct nfsacl_encode_desc nfsacl_desc = {
+		.desc = {
+			.elem_size = elem_size,
+			.array_len = encode_entries ? entries : 0,
+			.xcode = xdr_nfsace_encode,
+		},
+		.acl = acl,
+		.typeflag = typeflag,
+		.uid = inode->i_uid,
+		.gid = inode->i_gid,
+	};
+	struct nfsacl_simple_acl aclbuf;
+	unsigned int base;
+	int err;
+
+	if (entries > NFS_ACL_MAX_ENTRIES)
+		return false;
+	if (xdr_stream_encode_u32(xdr, entries) < 0)
+		return false;
+
+	if (encode_entries && acl && acl->a_count == 3) {
+		struct posix_acl *acl2 = &aclbuf.acl;
+
+		/* Avoid the use of posix_acl_alloc().  nfsacl_encode() is
+		 * invoked in contexts where a memory allocation failure is
+		 * fatal.  Fortunately this fake ACL is small enough to
+		 * construct on the stack. */
+		posix_acl_init(acl2, 4);
+
+		/* Insert entries in canonical order: other orders seem
+		 to confuse Solaris VxFS. */
+		acl2->a_entries[0] = acl->a_entries[0];  /* ACL_USER_OBJ */
+		acl2->a_entries[1] = acl->a_entries[1];  /* ACL_GROUP_OBJ */
+		acl2->a_entries[2] = acl->a_entries[1];  /* ACL_MASK */
+		acl2->a_entries[2].e_tag = ACL_MASK;
+		acl2->a_entries[3] = acl->a_entries[2];  /* ACL_OTHER */
+		nfsacl_desc.acl = acl2;
+	}
+
+	base = xdr_stream_pos(xdr);
+	if (!xdr_reserve_space(xdr, XDR_UNIT +
+			       elem_size * nfsacl_desc.desc.array_len))
+		return false;
+	err = xdr_encode_array2(xdr->buf, base, &nfsacl_desc.desc);
+	if (err)
+		return false;
+
+	return true;
+}
+EXPORT_SYMBOL_GPL(nfs_stream_encode_acl);
+
+
 struct nfsacl_decode_desc {
 	struct xdr_array2_desc desc;
 	unsigned int count;

fs/nfsd/Kconfig

@@ -99,7 +99,7 @@ config NFSD_BLOCKLAYOUT
 	help
 	  This option enables support for the exporting pNFS block layouts
 	  in the kernel's NFS server. The pNFS block layout enables NFS
-	  clients to directly perform I/O to block devices accesible to both
+	  clients to directly perform I/O to block devices accessible to both
 	  the server and the clients.  See RFC 5663 for more details.
 
 	  If unsure, say N.
@@ -113,7 +113,7 @@ config NFSD_SCSILAYOUT
 	help
 	  This option enables support for the exporting pNFS SCSI layouts
 	  in the kernel's NFS server. The pNFS SCSI layout enables NFS
-	  clients to directly perform I/O to SCSI devices accesible to both
+	  clients to directly perform I/O to SCSI devices accessible to both
 	  the server and the clients.  See draft-ietf-nfsv4-scsi-layout for
 	  more details.
 
@@ -127,7 +127,7 @@ config NFSD_FLEXFILELAYOUT
 	  This option enables support for the exporting pNFS Flex File
 	  layouts in the kernel's NFS server. The pNFS Flex File  layout
 	  enables NFS clients to directly perform I/O to NFSv3 devices
-	  accesible to both the server and the clients.  See
+	  accessible to both the server and the clients.  See
 	  draft-ietf-nfsv4-flex-files for more details.
 
 	  Warning, this server implements the bare minimum functionality

fs/nfsd/netns.h

@@ -51,9 +51,6 @@ struct nfsd_net {
 	bool grace_ended;
 	time64_t boot_time;
 
-	/* internal mount of the "nfsd" pseudofilesystem: */
-	struct vfsmount *nfsd_mnt;
-
 	struct dentry *nfsd_client_dir;
 
 	/*
@@ -130,6 +127,9 @@ struct nfsd_net {
 	wait_queue_head_t ntf_wq;
 	atomic_t ntf_refcnt;
 
+	/* Allow umount to wait for nfsd state cleanup */
+	struct completion nfsd_shutdown_complete;
+
 	/*
 	 * clientid and stateid data for construction of net unique COPY
 	 * stateids.

fs/nfsd/nfs2acl.c

@@ -242,79 +242,61 @@ static int nfsaclsvc_decode_accessargs(struct svc_rqst *rqstp, __be32 *p)
 /* GETACL */
 static int nfsaclsvc_encode_getaclres(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct xdr_stream *xdr = &rqstp->rq_res_stream;
 	struct nfsd3_getaclres *resp = rqstp->rq_resp;
 	struct dentry *dentry = resp->fh.fh_dentry;
 	struct inode *inode;
-	struct kvec *head = rqstp->rq_res.head;
-	unsigned int base;
-	int n;
 	int w;
 
-	*p++ = resp->status;
-	if (resp->status != nfs_ok)
-		return xdr_ressize_check(rqstp, p);
+	if (!svcxdr_encode_stat(xdr, resp->status))
+		return 0;
 
-	/*
-	 * Since this is version 2, the check for nfserr in
-	 * nfsd_dispatch actually ensures the following cannot happen.
-	 * However, it seems fragile to depend on that.
-	 */
 	if (dentry == NULL || d_really_is_negative(dentry))
-		return 0;
+		return 1;
 	inode = d_inode(dentry);
 
-	p = nfs2svc_encode_fattr(rqstp, p, &resp->fh, &resp->stat);
-	*p++ = htonl(resp->mask);
-	if (!xdr_ressize_check(rqstp, p))
+	if (!svcxdr_encode_fattr(rqstp, xdr, &resp->fh, &resp->stat))
+		return 0;
+	if (xdr_stream_encode_u32(xdr, resp->mask) < 0)
 		return 0;
-	base = (char *)p - (char *)head->iov_base;
 
 	rqstp->rq_res.page_len = w = nfsacl_size(
 		(resp->mask & NFS_ACL)   ? resp->acl_access  : NULL,
 		(resp->mask & NFS_DFACL) ? resp->acl_default : NULL);
 	while (w > 0) {
 		if (!*(rqstp->rq_next_page++))
-			return 0;
+			return 1;
 		w -= PAGE_SIZE;
 	}
 
-	n = nfsacl_encode(&rqstp->rq_res, base, inode,
-			  resp->acl_access,
-			  resp->mask & NFS_ACL, 0);
-	if (n > 0)
-		n = nfsacl_encode(&rqstp->rq_res, base + n, inode,
-				  resp->acl_default,
-				  resp->mask & NFS_DFACL,
-				  NFS_ACL_DEFAULT);
-	return (n > 0);
-}
-
-static int nfsaclsvc_encode_attrstatres(struct svc_rqst *rqstp, __be32 *p)
-{
-	struct nfsd_attrstat *resp = rqstp->rq_resp;
-
-	*p++ = resp->status;
-	if (resp->status != nfs_ok)
-		goto out;
+	if (!nfs_stream_encode_acl(xdr, inode, resp->acl_access,
+				   resp->mask & NFS_ACL, 0))
+		return 0;
+	if (!nfs_stream_encode_acl(xdr, inode, resp->acl_default,
+				   resp->mask & NFS_DFACL, NFS_ACL_DEFAULT))
+		return 0;
 
-	p = nfs2svc_encode_fattr(rqstp, p, &resp->fh, &resp->stat);
-out:
-	return xdr_ressize_check(rqstp, p);
+	return 1;
 }
 
 /* ACCESS */
 static int nfsaclsvc_encode_accessres(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct xdr_stream *xdr = &rqstp->rq_res_stream;
 	struct nfsd3_accessres *resp = rqstp->rq_resp;
 
-	*p++ = resp->status;
-	if (resp->status != nfs_ok)
-		goto out;
+	if (!svcxdr_encode_stat(xdr, resp->status))
+		return 0;
+	switch (resp->status) {
+	case nfs_ok:
+		if (!svcxdr_encode_fattr(rqstp, xdr, &resp->fh, &resp->stat))
+			return 0;
+		if (xdr_stream_encode_u32(xdr, resp->access) < 0)
+			return 0;
+		break;
+	}
 
-	p = nfs2svc_encode_fattr(rqstp, p, &resp->fh, &resp->stat);
-	*p++ = htonl(resp->access);
-out:
-	return xdr_ressize_check(rqstp, p);
+	return 1;
 }
 
 /*
@@ -329,13 +311,6 @@ static void nfsaclsvc_release_getacl(struct svc_rqst *rqstp)
 	posix_acl_release(resp->acl_default);
 }
 
-static void nfsaclsvc_release_attrstat(struct svc_rqst *rqstp)
-{
-	struct nfsd_attrstat *resp = rqstp->rq_resp;
-
-	fh_put(&resp->fh);
-}
-
 static void nfsaclsvc_release_access(struct svc_rqst *rqstp)
 {
 	struct nfsd3_accessres *resp = rqstp->rq_resp;
@@ -375,8 +350,8 @@ static const struct svc_procedure nfsd_acl_procedures2[5] = {
 	[ACLPROC2_SETACL] = {
 		.pc_func = nfsacld_proc_setacl,
 		.pc_decode = nfsaclsvc_decode_setaclargs,
-		.pc_encode = nfsaclsvc_encode_attrstatres,
-		.pc_release = nfsaclsvc_release_attrstat,
+		.pc_encode = nfssvc_encode_attrstatres,
+		.pc_release = nfssvc_release_attrstat,
 		.pc_argsize = sizeof(struct nfsd3_setaclargs),
 		.pc_ressize = sizeof(struct nfsd_attrstat),
 		.pc_cachetype = RC_NOCACHE,
@@ -386,8 +361,8 @@ static const struct svc_procedure nfsd_acl_procedures2[5] = {
 	[ACLPROC2_GETATTR] = {
 		.pc_func = nfsacld_proc_getattr,
 		.pc_decode = nfssvc_decode_fhandleargs,
-		.pc_encode = nfsaclsvc_encode_attrstatres,
-		.pc_release = nfsaclsvc_release_attrstat,
+		.pc_encode = nfssvc_encode_attrstatres,
+		.pc_release = nfssvc_release_attrstat,
 		.pc_argsize = sizeof(struct nfsd_fhandle),
 		.pc_ressize = sizeof(struct nfsd_attrstat),
 		.pc_cachetype = RC_NOCACHE,

fs/nfsd/nfs3acl.c

@@ -168,22 +168,25 @@ static int nfs3svc_decode_setaclargs(struct svc_rqst *rqstp, __be32 *p)
 /* GETACL */
 static int nfs3svc_encode_getaclres(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct xdr_stream *xdr = &rqstp->rq_res_stream;
 	struct nfsd3_getaclres *resp = rqstp->rq_resp;
 	struct dentry *dentry = resp->fh.fh_dentry;
+	struct kvec *head = rqstp->rq_res.head;
+	struct inode *inode = d_inode(dentry);
+	unsigned int base;
+	int n;
+	int w;
 
-	*p++ = resp->status;
-	p = nfs3svc_encode_post_op_attr(rqstp, p, &resp->fh);
-	if (resp->status == 0 && dentry && d_really_is_positive(dentry)) {
-		struct inode *inode = d_inode(dentry);
-		struct kvec *head = rqstp->rq_res.head;
-		unsigned int base;
-		int n;
-		int w;
-
-		*p++ = htonl(resp->mask);
-		if (!xdr_ressize_check(rqstp, p))
+	if (!svcxdr_encode_nfsstat3(xdr, resp->status))
+		return 0;
+	switch (resp->status) {
+	case nfs_ok:
+		if (!svcxdr_encode_post_op_attr(rqstp, xdr, &resp->fh))
+			return 0;
+		if (xdr_stream_encode_u32(xdr, resp->mask) < 0)
 			return 0;
-		base = (char *)p - (char *)head->iov_base;
+
+		base = (char *)xdr->p - (char *)head->iov_base;
 
 		rqstp->rq_res.page_len = w = nfsacl_size(
 			(resp->mask & NFS_ACL)   ? resp->acl_access  : NULL,
@@ -204,21 +207,23 @@ static int nfs3svc_encode_getaclres(struct svc_rqst *rqstp, __be32 *p)
 					  NFS_ACL_DEFAULT);
 		if (n <= 0)
 			return 0;
-	} else
-		if (!xdr_ressize_check(rqstp, p))
+		break;
+	default:
+		if (!svcxdr_encode_post_op_attr(rqstp, xdr, &resp->fh))
 			return 0;
+	}
 
 	return 1;
 }
 
 /* SETACL */
 static int nfs3svc_encode_setaclres(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct xdr_stream *xdr = &rqstp->rq_res_stream;
 	struct nfsd3_attrstat *resp = rqstp->rq_resp;
 
-	*p++ = resp->status;
-	p = nfs3svc_encode_post_op_attr(rqstp, p, &resp->fh);
-	return xdr_ressize_check(rqstp, p);
+	return svcxdr_encode_nfsstat3(xdr, resp->status) &&
+		svcxdr_encode_post_op_attr(rqstp, xdr, &resp->fh);
 }
 
 /*