Merge tag 'nfsd-5.9' of git://git.linux-nfs.org/projects/cel/cel-2.6

Pull NFS server updates from Chuck Lever:
 "Highlights:
   - Support for user extended attributes on NFS (RFC 8276)
   - Further reduce unnecessary NFSv4 delegation recalls

  Notable fixes:
   - Fix recent krb5p regression
   - Address a few resource leaks and a rare NULL dereference

  Other:
   - De-duplicate RPC/RDMA error handling and other utility functions
   - Replace storage and display of kernel memory addresses by tracepoints"

* tag 'nfsd-5.9' of git://git.linux-nfs.org/projects/cel/cel-2.6: (38 commits)
  svcrdma: CM event handler clean up
  svcrdma: Remove transport reference counting
  svcrdma: Fix another Receive buffer leak
  SUNRPC: Refresh the show_rqstp_flags() macro
  nfsd: netns.h: delete a duplicated word
  SUNRPC: Fix ("SUNRPC: Add "@len" parameter to gss_unwrap()")
  nfsd: avoid a NULL dereference in __cld_pipe_upcall()
  nfsd4: a client's own opens needn't prevent delegations
  nfsd: Use seq_putc() in two functions
  svcrdma: Display chunk completion ID when posting a rw_ctxt
  svcrdma: Record send_ctxt completion ID in trace_svcrdma_post_send()
  svcrdma: Introduce Send completion IDs
  svcrdma: Record Receive completion ID in svc_rdma_decode_rqst
  svcrdma: Introduce Receive completion IDs
  svcrdma: Introduce infrastructure to support completion IDs
  svcrdma: Add common XDR encoders for RDMA and Read segments
  svcrdma: Add common XDR decoders for RDMA and Read segments
  SUNRPC: Add helpers for decoding list discriminators symbolically
  svcrdma: Remove declarations for functions long removed
  svcrdma: Clean up trace_svcrdma_send_failed() tracepoint
  ...

fs/locks.c

@@ -1808,6 +1808,9 @@ check_conflicting_open(struct file *filp, const long arg, int flags)
 
 	if (flags & FL_LAYOUT)
 		return 0;
+	if (flags & FL_DELEG)
+		/* We leave these checks to the caller. */
+		return 0;
 
 	if (arg == F_RDLCK)
 		return inode_is_open_for_write(inode) ? -EAGAIN : 0;

fs/nfsd/netns.h

@@ -171,7 +171,7 @@ struct nfsd_net {
 	unsigned int             longest_chain_cachesize;
 
 	struct shrinker		nfsd_reply_cache_shrinker;
-	/* utsname taken from the the process that starts the server */
+	/* utsname taken from the process that starts the server */
 	char			nfsd_name[UNX_MAXNODENAME+1];
 };
 

fs/nfsd/nfs4idmap.c

@@ -168,7 +168,7 @@ idtoname_show(struct seq_file *m, struct cache_detail *cd, struct cache_head *h)
 			ent->id);
 	if (test_bit(CACHE_VALID, &h->flags))
 		seq_printf(m, " %s", ent->name);
-	seq_printf(m, "\n");
+	seq_putc(m, '\n');
 	return 0;
 }
 
@@ -346,7 +346,7 @@ nametoid_show(struct seq_file *m, struct cache_detail *cd, struct cache_head *h)
 			ent->name);
 	if (test_bit(CACHE_VALID, &h->flags))
 		seq_printf(m, " %u", ent->id);
-	seq_printf(m, "\n");
+	seq_putc(m, '\n');
 	return 0;
 }
 

fs/nfsd/nfs4proc.c

@@ -566,8 +566,14 @@ nfsd4_access(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	     union nfsd4_op_u *u)
 {
 	struct nfsd4_access *access = &u->access;
+	u32 access_full;
 
-	if (access->ac_req_access & ~NFS3_ACCESS_FULL)
+	access_full = NFS3_ACCESS_FULL;
+	if (cstate->minorversion >= 2)
+		access_full |= NFS4_ACCESS_XALIST | NFS4_ACCESS_XAREAD |
+			       NFS4_ACCESS_XAWRITE;
+
+	if (access->ac_req_access & ~access_full)
 		return nfserr_inval;
 
 	access->ac_resp_access = access->ac_req_access;
@@ -2091,6 +2097,68 @@ nfsd4_layoutreturn(struct svc_rqst *rqstp,
 }
 #endif /* CONFIG_NFSD_PNFS */
 
+static __be32
+nfsd4_getxattr(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
+	       union nfsd4_op_u *u)
+{
+	struct nfsd4_getxattr *getxattr = &u->getxattr;
+
+	return nfsd_getxattr(rqstp, &cstate->current_fh,
+			     getxattr->getxa_name, &getxattr->getxa_buf,
+			     &getxattr->getxa_len);
+}
+
+static __be32
+nfsd4_setxattr(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
+	   union nfsd4_op_u *u)
+{
+	struct nfsd4_setxattr *setxattr = &u->setxattr;
+	__be32 ret;
+
+	if (opens_in_grace(SVC_NET(rqstp)))
+		return nfserr_grace;
+
+	ret = nfsd_setxattr(rqstp, &cstate->current_fh, setxattr->setxa_name,
+			    setxattr->setxa_buf, setxattr->setxa_len,
+			    setxattr->setxa_flags);
+
+	if (!ret)
+		set_change_info(&setxattr->setxa_cinfo, &cstate->current_fh);
+
+	return ret;
+}
+
+static __be32
+nfsd4_listxattrs(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
+	   union nfsd4_op_u *u)
+{
+	/*
+	 * Get the entire list, then copy out only the user attributes
+	 * in the encode function.
+	 */
+	return nfsd_listxattr(rqstp, &cstate->current_fh,
+			     &u->listxattrs.lsxa_buf, &u->listxattrs.lsxa_len);
+}
+
+static __be32
+nfsd4_removexattr(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
+	   union nfsd4_op_u *u)
+{
+	struct nfsd4_removexattr *removexattr = &u->removexattr;
+	__be32 ret;
+
+	if (opens_in_grace(SVC_NET(rqstp)))
+		return nfserr_grace;
+
+	ret = nfsd_removexattr(rqstp, &cstate->current_fh,
+	    removexattr->rmxa_name);
+
+	if (!ret)
+		set_change_info(&removexattr->rmxa_cinfo, &cstate->current_fh);
+
+	return ret;
+}
+
 /*
  * NULL call.
  */
@@ -2700,6 +2768,42 @@ static inline u32 nfsd4_seek_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op)
 	return (op_encode_hdr_size + 3) * sizeof(__be32);
 }
 
+static inline u32 nfsd4_getxattr_rsize(struct svc_rqst *rqstp,
+				       struct nfsd4_op *op)
+{
+	u32 maxcount, rlen;
+
+	maxcount = svc_max_payload(rqstp);
+	rlen = min_t(u32, XATTR_SIZE_MAX, maxcount);
+
+	return (op_encode_hdr_size + 1 + XDR_QUADLEN(rlen)) * sizeof(__be32);
+}
+
+static inline u32 nfsd4_setxattr_rsize(struct svc_rqst *rqstp,
+				       struct nfsd4_op *op)
+{
+	return (op_encode_hdr_size + op_encode_change_info_maxsz)
+		* sizeof(__be32);
+}
+static inline u32 nfsd4_listxattrs_rsize(struct svc_rqst *rqstp,
+					 struct nfsd4_op *op)
+{
+	u32 maxcount, rlen;
+
+	maxcount = svc_max_payload(rqstp);
+	rlen = min(op->u.listxattrs.lsxa_maxcount, maxcount);
+
+	return (op_encode_hdr_size + 4 + XDR_QUADLEN(rlen)) * sizeof(__be32);
+}
+
+static inline u32 nfsd4_removexattr_rsize(struct svc_rqst *rqstp,
+					  struct nfsd4_op *op)
+{
+	return (op_encode_hdr_size + op_encode_change_info_maxsz)
+		* sizeof(__be32);
+}
+
+
 static const struct nfsd4_operation nfsd4_ops[] = {
 	[OP_ACCESS] = {
 		.op_func = nfsd4_access,
@@ -3081,6 +3185,28 @@ static const struct nfsd4_operation nfsd4_ops[] = {
 		.op_name = "OP_COPY_NOTIFY",
 		.op_rsize_bop = nfsd4_copy_notify_rsize,
 	},
+	[OP_GETXATTR] = {
+		.op_func = nfsd4_getxattr,
+		.op_name = "OP_GETXATTR",
+		.op_rsize_bop = nfsd4_getxattr_rsize,
+	},
+	[OP_SETXATTR] = {
+		.op_func = nfsd4_setxattr,
+		.op_flags = OP_MODIFIES_SOMETHING | OP_CACHEME,
+		.op_name = "OP_SETXATTR",
+		.op_rsize_bop = nfsd4_setxattr_rsize,
+	},
+	[OP_LISTXATTRS] = {
+		.op_func = nfsd4_listxattrs,
+		.op_name = "OP_LISTXATTRS",
+		.op_rsize_bop = nfsd4_listxattrs_rsize,
+	},
+	[OP_REMOVEXATTR] = {
+		.op_func = nfsd4_removexattr,
+		.op_flags = OP_MODIFIES_SOMETHING | OP_CACHEME,
+		.op_name = "OP_REMOVEXATTR",
+		.op_rsize_bop = nfsd4_removexattr_rsize,
+	},
 };
 
 /**

fs/nfsd/nfs4recover.c

@@ -747,13 +747,11 @@ struct cld_upcall {
 };
 
 static int
-__cld_pipe_upcall(struct rpc_pipe *pipe, void *cmsg)
+__cld_pipe_upcall(struct rpc_pipe *pipe, void *cmsg, struct nfsd_net *nn)
 {
 	int ret;
 	struct rpc_pipe_msg msg;
 	struct cld_upcall *cup = container_of(cmsg, struct cld_upcall, cu_u);
-	struct nfsd_net *nn = net_generic(pipe->dentry->d_sb->s_fs_info,
-					  nfsd_net_id);
 
 	memset(&msg, 0, sizeof(msg));
 	msg.data = cmsg;
@@ -773,7 +771,7 @@ __cld_pipe_upcall(struct rpc_pipe *pipe, void *cmsg)
 }
 
 static int
-cld_pipe_upcall(struct rpc_pipe *pipe, void *cmsg)
+cld_pipe_upcall(struct rpc_pipe *pipe, void *cmsg, struct nfsd_net *nn)
 {
 	int ret;
 
@@ -782,7 +780,7 @@ cld_pipe_upcall(struct rpc_pipe *pipe, void *cmsg)
 	 *  upcalls queued.
 	 */
 	do {
-		ret = __cld_pipe_upcall(pipe, cmsg);
+		ret = __cld_pipe_upcall(pipe, cmsg, nn);
 	} while (ret == -EAGAIN);
 
 	return ret;
@@ -1115,7 +1113,7 @@ nfsd4_cld_create(struct nfs4_client *clp)
 	memcpy(cup->cu_u.cu_msg.cm_u.cm_name.cn_id, clp->cl_name.data,
 			clp->cl_name.len);
 
-	ret = cld_pipe_upcall(cn->cn_pipe, &cup->cu_u.cu_msg);
+	ret = cld_pipe_upcall(cn->cn_pipe, &cup->cu_u.cu_msg, nn);
 	if (!ret) {
 		ret = cup->cu_u.cu_msg.cm_status;
 		set_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags);
@@ -1180,7 +1178,7 @@ nfsd4_cld_create_v2(struct nfs4_client *clp)
 	} else
 		cmsg->cm_u.cm_clntinfo.cc_princhash.cp_len = 0;
 
-	ret = cld_pipe_upcall(cn->cn_pipe, cmsg);
+	ret = cld_pipe_upcall(cn->cn_pipe, cmsg, nn);
 	if (!ret) {
 		ret = cmsg->cm_status;
 		set_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags);
@@ -1218,7 +1216,7 @@ nfsd4_cld_remove(struct nfs4_client *clp)
 	memcpy(cup->cu_u.cu_msg.cm_u.cm_name.cn_id, clp->cl_name.data,
 			clp->cl_name.len);
 
-	ret = cld_pipe_upcall(cn->cn_pipe, &cup->cu_u.cu_msg);
+	ret = cld_pipe_upcall(cn->cn_pipe, &cup->cu_u.cu_msg, nn);
 	if (!ret) {
 		ret = cup->cu_u.cu_msg.cm_status;
 		clear_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags);
@@ -1261,7 +1259,7 @@ nfsd4_cld_check_v0(struct nfs4_client *clp)
 	memcpy(cup->cu_u.cu_msg.cm_u.cm_name.cn_id, clp->cl_name.data,
 			clp->cl_name.len);
 
-	ret = cld_pipe_upcall(cn->cn_pipe, &cup->cu_u.cu_msg);
+	ret = cld_pipe_upcall(cn->cn_pipe, &cup->cu_u.cu_msg, nn);
 	if (!ret) {
 		ret = cup->cu_u.cu_msg.cm_status;
 		set_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags);
@@ -1404,7 +1402,7 @@ nfsd4_cld_grace_start(struct nfsd_net *nn)
 	}
 
 	cup->cu_u.cu_msg.cm_cmd = Cld_GraceStart;
-	ret = cld_pipe_upcall(cn->cn_pipe, &cup->cu_u.cu_msg);
+	ret = cld_pipe_upcall(cn->cn_pipe, &cup->cu_u.cu_msg, nn);
 	if (!ret)
 		ret = cup->cu_u.cu_msg.cm_status;
 
@@ -1432,7 +1430,7 @@ nfsd4_cld_grace_done_v0(struct nfsd_net *nn)
 
 	cup->cu_u.cu_msg.cm_cmd = Cld_GraceDone;
 	cup->cu_u.cu_msg.cm_u.cm_gracetime = nn->boot_time;
-	ret = cld_pipe_upcall(cn->cn_pipe, &cup->cu_u.cu_msg);
+	ret = cld_pipe_upcall(cn->cn_pipe, &cup->cu_u.cu_msg, nn);
 	if (!ret)
 		ret = cup->cu_u.cu_msg.cm_status;
 
@@ -1460,7 +1458,7 @@ nfsd4_cld_grace_done(struct nfsd_net *nn)
 	}
 
 	cup->cu_u.cu_msg.cm_cmd = Cld_GraceDone;
-	ret = cld_pipe_upcall(cn->cn_pipe, &cup->cu_u.cu_msg);
+	ret = cld_pipe_upcall(cn->cn_pipe, &cup->cu_u.cu_msg, nn);
 	if (!ret)
 		ret = cup->cu_u.cu_msg.cm_status;
 
@@ -1524,7 +1522,7 @@ nfsd4_cld_get_version(struct nfsd_net *nn)
 		goto out_err;
 	}
 	cup->cu_u.cu_msg.cm_cmd = Cld_GetVersion;
-	ret = cld_pipe_upcall(cn->cn_pipe, &cup->cu_u.cu_msg);
+	ret = cld_pipe_upcall(cn->cn_pipe, &cup->cu_u.cu_msg, nn);
 	if (!ret) {
 		ret = cup->cu_u.cu_msg.cm_status;
 		if (ret)

fs/nfsd/nfs4state.c

@@ -4940,6 +4940,32 @@ static struct file_lock *nfs4_alloc_init_lease(struct nfs4_delegation *dp,
 	return fl;
 }
 
+static int nfsd4_check_conflicting_opens(struct nfs4_client *clp,
+						struct nfs4_file *fp)
+{
+	struct nfs4_clnt_odstate *co;
+	struct file *f = fp->fi_deleg_file->nf_file;
+	struct inode *ino = locks_inode(f);
+	int writes = atomic_read(&ino->i_writecount);
+
+	if (fp->fi_fds[O_WRONLY])
+		writes--;
+	if (fp->fi_fds[O_RDWR])
+		writes--;
+	WARN_ON_ONCE(writes < 0);
+	if (writes > 0)
+		return -EAGAIN;
+	spin_lock(&fp->fi_lock);
+	list_for_each_entry(co, &fp->fi_clnt_odstate, co_perfile) {
+		if (co->co_client != clp) {
+			spin_unlock(&fp->fi_lock);
+			return -EAGAIN;
+		}
+	}
+	spin_unlock(&fp->fi_lock);
+	return 0;
+}
+
 static struct nfs4_delegation *
 nfs4_set_delegation(struct nfs4_client *clp, struct svc_fh *fh,
 		    struct nfs4_file *fp, struct nfs4_clnt_odstate *odstate)
@@ -4959,9 +4985,12 @@ nfs4_set_delegation(struct nfs4_client *clp, struct svc_fh *fh,
 
 	nf = find_readable_file(fp);
 	if (!nf) {
-		/* We should always have a readable file here */
-		WARN_ON_ONCE(1);
-		return ERR_PTR(-EBADF);
+		/*
+		 * We probably could attempt another open and get a read
+		 * delegation, but for now, don't bother until the
+		 * client actually sends us one.
+		 */
+		return ERR_PTR(-EAGAIN);
 	}
 	spin_lock(&state_lock);
 	spin_lock(&fp->fi_lock);
@@ -4991,11 +5020,19 @@ nfs4_set_delegation(struct nfs4_client *clp, struct svc_fh *fh,
 	if (!fl)
 		goto out_clnt_odstate;
 
+	status = nfsd4_check_conflicting_opens(clp, fp);
+	if (status) {
+		locks_free_lock(fl);
+		goto out_clnt_odstate;
+	}
 	status = vfs_setlease(fp->fi_deleg_file->nf_file, fl->fl_type, &fl, NULL);
 	if (fl)
 		locks_free_lock(fl);
 	if (status)
 		goto out_clnt_odstate;
+	status = nfsd4_check_conflicting_opens(clp, fp);
+	if (status)
+		goto out_clnt_odstate;
 
 	spin_lock(&state_lock);
 	spin_lock(&fp->fi_lock);
@@ -5077,17 +5114,6 @@ nfs4_open_delegation(struct svc_fh *fh, struct nfsd4_open *open,
 				goto out_no_deleg;
 			if (!cb_up || !(oo->oo_flags & NFS4_OO_CONFIRMED))
 				goto out_no_deleg;
-			/*
-			 * Also, if the file was opened for write or
-			 * create, there's a good chance the client's
-			 * about to write to it, resulting in an
-			 * immediate recall (since we don't support
-			 * write delegations):
-			 */
-			if (open->op_share_access & NFS4_SHARE_ACCESS_WRITE)
-				goto out_no_deleg;
-			if (open->op_create == NFS4_OPEN_CREATE)
-				goto out_no_deleg;
 			break;
 		default:
 			goto out_no_deleg;