Merge tag 'nfsd-4.21' of git://linux-nfs.org/~bfields/linux

Pull nfsd updates from Bruce Fields:
"Thanks to Vasily Averin for fixing a use-after-free in the
containerized NFSv4.2 client, and cleaning up some convoluted
backchannel server code in the process.

Otherwise, miscellaneous smaller bugfixes and cleanup"

* tag 'nfsd-4.21' of git://linux-nfs.org/~bfields/linux: (25 commits)
nfs: fixed broken compilation in nfs_callback_up_net()
nfs: minor typo in nfs4_callback_up_net()
sunrpc: fix debug message in svc_create_xprt()
sunrpc: make visible processing error in bc_svc_process()
sunrpc: remove unused xpo_prep_reply_hdr callback
sunrpc: remove svc_rdma_bc_class
sunrpc: remove svc_tcp_bc_class
sunrpc: remove unused bc_up operation from rpc_xprt_ops
sunrpc: replace svc_serv->sv_bc_xprt by boolean flag
sunrpc: use-after-free in svc_process_common()
sunrpc: use SVC_NET() in svcauth_gss_* functions
nfsd: drop useless LIST_HEAD
lockd: Show pid of lockd for remote locks
NFSD remove OP_CACHEME from 4.2 op_flags
nfsd: Return EPERM, not EACCES, in some SETATTR cases
sunrpc: fix cache_head leak due to queued request
nfsd: clean up indentation, increase indentation in switch statement
svcrdma: Optimize the logic that selects the R_key to invalidate
nfsd: fix a warning in __cld_pipe_upcall()
nfsd4: fix crash on writing v4_end_grace before nfsd startup
...

fs/lockd/clnt4xdr.c

···
 static int decode_netobj(struct xdr_stream *xdr,
 			 struct xdr_netobj *obj)
 {
-	u32 length;
-	__be32 *p;
+	ssize_t ret;
 
-	p = xdr_inline_decode(xdr, 4);
-	if (unlikely(p == NULL))
-		goto out_overflow;
-	length = be32_to_cpup(p++);
-	if (unlikely(length > XDR_MAX_NETOBJ))
-		goto out_size;
-	obj->len = length;
-	obj->data = (u8 *)p;
+	ret = xdr_stream_decode_opaque_inline(xdr, (void *)&obj->data,
+						XDR_MAX_NETOBJ);
+	if (unlikely(ret < 0))
+		return -EIO;
+	obj->len = ret;
 	return 0;
-out_size:
-	dprintk("NFS: returned netobj was too long: %u\n", length);
-	return -EIO;
-out_overflow:
-	print_overflow_msg(__func__, xdr);
-	return -EIO;
 }
 
 /*

fs/lockd/clntproc.c

···
 			fl->fl_start = req->a_res.lock.fl.fl_start;
 			fl->fl_end = req->a_res.lock.fl.fl_end;
 			fl->fl_type = req->a_res.lock.fl.fl_type;
-			fl->fl_pid = 0;
+			fl->fl_pid = -req->a_res.lock.fl.fl_pid;
 			break;
 		default:
 			status = nlm_stat_to_errno(req->a_res.status);

fs/lockd/clntxdr.c

···
 static int decode_netobj(struct xdr_stream *xdr,
 			 struct xdr_netobj *obj)
 {
-	u32 length;
-	__be32 *p;
+	ssize_t ret;
 
-	p = xdr_inline_decode(xdr, 4);
-	if (unlikely(p == NULL))
-		goto out_overflow;
-	length = be32_to_cpup(p++);
-	if (unlikely(length > XDR_MAX_NETOBJ))
-		goto out_size;
-	obj->len = length;
-	obj->data = (u8 *)p;
+	ret = xdr_stream_decode_opaque_inline(xdr, (void *)&obj->data,
+			XDR_MAX_NETOBJ);
+	if (unlikely(ret < 0))
+		return -EIO;
+	obj->len = ret;
 	return 0;
-out_size:
-	dprintk("NFS: returned netobj was too long: %u\n", length);
-	return -EIO;
-out_overflow:
-	print_overflow_msg(__func__, xdr);
-	return -EIO;
 }
 
 /*

fs/lockd/xdr.c

···
 
 	locks_init_lock(fl);
 	fl->fl_owner = current->files;
-	fl->fl_pid   = (pid_t)lock->svid;
+	fl->fl_pid   = current->tgid;
 	fl->fl_flags = FL_POSIX;
 	fl->fl_type  = F_RDLCK;		/* as good as anything else */
 	start = ntohl(*p++);
···
 	memset(lock, 0, sizeof(*lock));
 	locks_init_lock(&lock->fl);
 	lock->svid = ~(u32) 0;
-	lock->fl.fl_pid = (pid_t)lock->svid;
+	lock->fl.fl_pid = current->tgid;
 
 	if (!(p = nlm_decode_cookie(p, &argp->cookie))
 	 || !(p = xdr_decode_string_inplace(p, &lock->caller,

fs/lockd/xdr4.c

···
 
 	locks_init_lock(fl);
 	fl->fl_owner = current->files;
-	fl->fl_pid   = (pid_t)lock->svid;
+	fl->fl_pid   = current->tgid;
 	fl->fl_flags = FL_POSIX;
 	fl->fl_type  = F_RDLCK;		/* as good as anything else */
 	p = xdr_decode_hyper(p, &start);
···
 	memset(lock, 0, sizeof(*lock));
 	locks_init_lock(&lock->fl);
 	lock->svid = ~(u32) 0;
-	lock->fl.fl_pid = (pid_t)lock->svid;
+	lock->fl.fl_pid = current->tgid;
 
 	if (!(p = nlm4_decode_cookie(p, &argp->cookie))
 	 || !(p = xdr_decode_string_inplace(p, &lock->caller,

fs/nfs/callback.c

···
 				nfs_callback_set_tcpport, SVC_SOCK_ANONYMOUS);
 	if (ret > 0) {
 		nn->nfs_callback_tcpport6 = ret;
-		dprintk("NFS: Callback listener port = %u (af %u, net %x\n",
+		dprintk("NFS: Callback listener port = %u (af %u, net %x)\n",
 			nn->nfs_callback_tcpport6, PF_INET6, net->ns.inum);
 	} else if (ret != -EAFNOSUPPORT)
 		goto out_err;
···
 		goto err_bind;
 	}
 
-	ret = -EPROTONOSUPPORT;
+	ret = 0;
 	if (!IS_ENABLED(CONFIG_NFS_V4_1) || minorversion == 0)
 		ret = nfs4_callback_up_net(serv, net);
-	else if (xprt->ops->bc_up)
-		ret = xprt->ops->bc_up(serv, net);
+	else if (xprt->ops->bc_setup)
+		set_bc_enabled(serv);
+	else
+		ret = -EPROTONOSUPPORT;
 
 	if (ret < 0) {
 		printk(KERN_ERR "NFS: callback service start failed\n");

fs/nfsd/nfs4layouts.c

···
 	struct nfsd_net *nn;
 	ktime_t now, cutoff;
 	const struct nfsd4_layout_ops *ops;
-	LIST_HEAD(reaplist);
 
 
 	switch (task->tk_status) {

fs/nfsd/nfs4proc.c

···
 	struct nfsd4_rename *rename = &u->rename;
 	__be32 status;
 
-	if (opens_in_grace(SVC_NET(rqstp)) &&
-		!(cstate->save_fh.fh_export->ex_flags & NFSEXP_NOSUBTREECHECK))
+	if (opens_in_grace(SVC_NET(rqstp)))
 		return nfserr_grace;
 	status = nfsd_rename(rqstp, &cstate->save_fh, rename->rn_sname,
 			     rename->rn_snamelen, &cstate->current_fh,
···
 
 	nvecs = svc_fill_write_vector(rqstp, write->wr_pagelist,
 				      &write->wr_head, write->wr_buflen);
-	if (!nvecs)
-		return nfserr_io;
 	WARN_ON_ONCE(nvecs > ARRAY_SIZE(rqstp->rq_vec));
 
 	status = nfsd_vfs_write(rqstp, &cstate->current_fh, filp,
···
 nfsd4_fallocate(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 		struct nfsd4_fallocate *fallocate, int flags)
 {
-	__be32 status = nfserr_notsupp;
+	__be32 status;
 	struct file *file;
 
 	status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh,
···
 	/* NFSv4.2 operations */
 	[OP_ALLOCATE] = {
 		.op_func = nfsd4_allocate,
-		.op_flags = OP_MODIFIES_SOMETHING | OP_CACHEME,
+		.op_flags = OP_MODIFIES_SOMETHING,
 		.op_name = "OP_ALLOCATE",
 		.op_rsize_bop = nfsd4_only_status_rsize,
 	},
 	[OP_DEALLOCATE] = {
 		.op_func = nfsd4_deallocate,
-		.op_flags = OP_MODIFIES_SOMETHING | OP_CACHEME,
+		.op_flags = OP_MODIFIES_SOMETHING,
 		.op_name = "OP_DEALLOCATE",
 		.op_rsize_bop = nfsd4_only_status_rsize,
 	},
 	[OP_CLONE] = {
 		.op_func = nfsd4_clone,
-		.op_flags = OP_MODIFIES_SOMETHING | OP_CACHEME,
+		.op_flags = OP_MODIFIES_SOMETHING,
 		.op_name = "OP_CLONE",
 		.op_rsize_bop = nfsd4_only_status_rsize,
 	},
 	[OP_COPY] = {
 		.op_func = nfsd4_copy,
-		.op_flags = OP_MODIFIES_SOMETHING | OP_CACHEME,
+		.op_flags = OP_MODIFIES_SOMETHING,
 		.op_name = "OP_COPY",
 		.op_rsize_bop = nfsd4_copy_rsize,
 	},

fs/nfsd/nfs4recover.c

···
 struct cld_upcall {
 	struct list_head	 cu_list;
 	struct cld_net		*cu_net;
-	struct task_struct	*cu_task;
+	struct completion	 cu_done;
 	struct cld_msg		 cu_msg;
 };
 
···
 {
 	int ret;
 	struct rpc_pipe_msg msg;
+	struct cld_upcall *cup = container_of(cmsg, struct cld_upcall, cu_msg);
 
 	memset(&msg, 0, sizeof(msg));
 	msg.data = cmsg;
 	msg.len = sizeof(*cmsg);
 
-	/*
-	 * Set task state before we queue the upcall. That prevents
-	 * wake_up_process in the downcall from racing with schedule.
-	 */
-	set_current_state(TASK_UNINTERRUPTIBLE);
 	ret = rpc_queue_upcall(pipe, &msg);
 	if (ret < 0) {
-		set_current_state(TASK_RUNNING);
 		goto out;
 	}
 
-	schedule();
+	wait_for_completion(&cup->cu_done);
 
 	if (msg.errno < 0)
 		ret = msg.errno;
···
 	if (copy_from_user(&cup->cu_msg, src, mlen) != 0)
 		return -EFAULT;
 
-	wake_up_process(cup->cu_task);
+	complete(&cup->cu_done);
 	return mlen;
 }
 
···
 	if (msg->errno >= 0)
 		return;
 
-	wake_up_process(cup->cu_task);
+	complete(&cup->cu_done);
 }
 
 static const struct rpc_pipe_ops cld_upcall_ops = {
···
 			goto restart_search;
 		}
 	}
-	new->cu_task = current;
+	init_completion(&new->cu_done);
 	new->cu_msg.cm_vers = CLD_UPCALL_VERSION;
 	put_unaligned(cn->cn_xid++, &new->cu_msg.cm_xid);
 	new->cu_net = cn;

fs/nfsd/nfs4state.c

···
 }
 
 static __be32
-nfs4_check_olstateid(struct svc_fh *fhp, struct nfs4_ol_stateid *ols, int flags)
+nfs4_check_olstateid(struct nfs4_ol_stateid *ols, int flags)
 {
 	__be32 status;
 
···
 		break;
 	case NFS4_OPEN_STID:
 	case NFS4_LOCK_STID:
-		status = nfs4_check_olstateid(fhp, openlockstateid(s), flags);
+		status = nfs4_check_olstateid(openlockstateid(s), flags);
 		break;
 	default:
 		status = nfserr_bad_stateid;
···
 		case NFS4_READ_LT:
 		case NFS4_READW_LT:
 			file_lock->fl_type = F_RDLCK;
-		break;
+			break;
 		case NFS4_WRITE_LT:
 		case NFS4_WRITEW_LT:
 			file_lock->fl_type = F_WRLCK;
-		break;
+			break;
 		default:
 			dprintk("NFSD: nfs4_lockt: bad lock type!\n");
 			status = nfserr_inval;
-		goto out;
+			goto out;
 	}
 
 	lo = find_lockowner_str(cstate->clp, &lockt->lt_owner);

fs/nfsd/nfsctl.c

···
 		case 'Y':
 		case 'y':
 		case '1':
+			if (nn->nfsd_serv)
+				return -EBUSY;
 			nfsd4_end_grace(nn);
 			break;
 		default:

fs/nfsd/vfs.c

···
 	bool		get_write_count;
 	bool		size_change = (iap->ia_valid & ATTR_SIZE);
 
-	if (iap->ia_valid & (ATTR_ATIME | ATTR_MTIME | ATTR_SIZE))
+	if (iap->ia_valid & ATTR_SIZE) {
 		accmode |= NFSD_MAY_WRITE|NFSD_MAY_OWNER_OVERRIDE;
-	if (iap->ia_valid & ATTR_SIZE)
 		ftype = S_IFREG;
+	}
+
+	/*
+	 * If utimes(2) and friends are called with times not NULL, we should
+	 * not set NFSD_MAY_WRITE bit. Otherwise fh_verify->nfsd_permission
+	 * will return EACCESS, when the caller's effective UID does not match
+	 * the owner of the file, and the caller is not privileged. In this
+	 * situation, we should return EPERM(notify_change will return this).
+	 */
+	if (iap->ia_valid & (ATTR_ATIME | ATTR_MTIME)) {
+		accmode |= NFSD_MAY_OWNER_OVERRIDE;
+		if (!(iap->ia_valid & (ATTR_ATIME_SET | ATTR_MTIME_SET)))
+			accmode |= NFSD_MAY_WRITE;
+	}
 
 	/* Callers that do fh_verify should do the fh_want_write: */
 	get_write_count = !fhp->fh_dentry;

include/linux/sunrpc/bc_xprt.h

···
 /*
  * Determine if a shared backchannel is in use
  */
-static inline int svc_is_backchannel(const struct svc_rqst *rqstp)
+static inline bool svc_is_backchannel(const struct svc_rqst *rqstp)
 {
-	if (rqstp->rq_server->sv_bc_xprt)
-		return 1;
-	return 0;
+	return rqstp->rq_server->sv_bc_enabled;
+}
+
+static inline void set_bc_enabled(struct svc_serv *serv)
+{
+	serv->sv_bc_enabled = true;
 }
 #else /* CONFIG_SUNRPC_BACKCHANNEL */
 static inline int xprt_setup_backchannel(struct rpc_xprt *xprt,
···
 	return 0;
 }
 
-static inline int svc_is_backchannel(const struct svc_rqst *rqstp)
+static inline bool svc_is_backchannel(const struct svc_rqst *rqstp)
 {
-	return 0;
+	return false;
+}
+
+static inline void set_bc_enabled(struct svc_serv *serv)
+{
 }
 
 static inline void xprt_free_bc_request(struct rpc_rqst *req)

include/linux/sunrpc/svc.h

···
 	spinlock_t		sv_cb_lock;	/* protects the svc_cb_list */
 	wait_queue_head_t	sv_cb_waitq;	/* sleep here if there are no
 						 * entries in the svc_cb_list */
-	struct svc_xprt		*sv_bc_xprt;	/* callback on fore channel */
+	bool			sv_bc_enabled;	/* service uses backchannel */
 #endif /* CONFIG_SUNRPC_BACKCHANNEL */
 };
 
···
 	struct svc_cacherep *	rq_cacherep;	/* cache info */
 	struct task_struct	*rq_task;	/* service thread */
 	spinlock_t		rq_lock;	/* per-request lock */
+	struct net		*rq_bc_net;	/* pointer to backchannel's
+						 * net namespace
+						 */
 };
 
-#define SVC_NET(svc_rqst)	(svc_rqst->rq_xprt->xpt_net)
+#define SVC_NET(rqst) (rqst->rq_xprt ? rqst->rq_xprt->xpt_net : rqst->rq_bc_net)
 
 /*
  * Rigorous type checking on sockaddr type conversions

include/linux/sunrpc/svc_rdma.h

···
 	u32			rc_byte_len;
 	unsigned int		rc_page_count;
 	unsigned int		rc_hdr_count;
+	u32			rc_inv_rkey;
 	struct page		*rc_pages[RPCSVC_MAXPAGES];
 };
 
···
 extern int svc_rdma_create_listen(struct svc_serv *, int, struct sockaddr *);
 extern void svc_sq_reap(struct svcxprt_rdma *);
 extern void svc_rq_reap(struct svcxprt_rdma *);
-extern void svc_rdma_prep_reply_hdr(struct svc_rqst *);
 
 extern struct svc_xprt_class svc_rdma_class;
 #ifdef CONFIG_SUNRPC_BACKCHANNEL

include/linux/sunrpc/svc_xprt.h

···
 	struct svc_xprt	*(*xpo_accept)(struct svc_xprt *);
 	int		(*xpo_has_wspace)(struct svc_xprt *);
 	int		(*xpo_recvfrom)(struct svc_rqst *);
-	void		(*xpo_prep_reply_hdr)(struct svc_rqst *);
 	int		(*xpo_sendto)(struct svc_rqst *);
 	void		(*xpo_release_rqst)(struct svc_rqst *);
 	void		(*xpo_detach)(struct svc_xprt *);

include/linux/sunrpc/xprt.h

···
 	void		(*inject_disconnect)(struct rpc_xprt *xprt);
 	int		(*bc_setup)(struct rpc_xprt *xprt,
 				    unsigned int min_reqs);
-	int		(*bc_up)(struct svc_serv *serv, struct net *net);
 	size_t		(*bc_maxpayload)(struct rpc_xprt *xprt);
 	void		(*bc_free_rqst)(struct rpc_rqst *rqst);
 	void		(*bc_destroy)(struct rpc_xprt *xprt,

include/trace/events/sunrpc.h

···
 		__field(u32, vers)
 		__field(u32, proc)
 		__string(service, name)
-		__string(addr, rqst->rq_xprt->xpt_remotebuf)
+		__string(addr, rqst->rq_xprt ?
+			 rqst->rq_xprt->xpt_remotebuf : "(null)")
 	),
 
 	TP_fast_assign(
···
 		__entry->vers = rqst->rq_vers;
 		__entry->proc = rqst->rq_proc;
 		__assign_str(service, name);
-		__assign_str(addr, rqst->rq_xprt->xpt_remotebuf);
+		__assign_str(addr, rqst->rq_xprt ?
+			     rqst->rq_xprt->xpt_remotebuf : "(null)");
 	),
 
 	TP_printk("addr=%s xid=0x%08x service=%s vers=%u proc=%u",

net/sunrpc/auth_gss/svcauth_gss.c

···
 	struct kvec *resv = &rqstp->rq_res.head[0];
 	struct rsi *rsip, rsikey;
 	int ret;
-	struct sunrpc_net *sn = net_generic(rqstp->rq_xprt->xpt_net, sunrpc_net_id);
+	struct sunrpc_net *sn = net_generic(SVC_NET(rqstp), sunrpc_net_id);
 
 	memset(&rsikey, 0, sizeof(rsikey));
 	ret = gss_read_verf(gc, argv, authp,
···
 	uint64_t handle;
 	int status;
 	int ret;
-	struct net *net = rqstp->rq_xprt->xpt_net;
+	struct net *net = SVC_NET(rqstp);
 	struct sunrpc_net *sn = net_generic(net, sunrpc_net_id);
 
 	memset(&ud, 0, sizeof(ud));
···
 	__be32		*rpcstart;
 	__be32		*reject_stat = resv->iov_base + resv->iov_len;
 	int		ret;
-	struct sunrpc_net *sn = net_generic(rqstp->rq_xprt->xpt_net, sunrpc_net_id);
+	struct sunrpc_net *sn = net_generic(SVC_NET(rqstp), sunrpc_net_id);
 
 	dprintk("RPC:       svcauth_gss: argv->iov_len = %zd\n",
 			argv->iov_len);
···
 	struct rpc_gss_wire_cred *gc = &gsd->clcred;
 	struct xdr_buf *resbuf = &rqstp->rq_res;
 	int stat = -EINVAL;
-	struct sunrpc_net *sn = net_generic(rqstp->rq_xprt->xpt_net, sunrpc_net_id);
+	struct sunrpc_net *sn = net_generic(SVC_NET(rqstp), sunrpc_net_id);
 
 	if (gc->gc_proc != RPC_GSS_PROC_DATA)
 		goto out;

net/sunrpc/cache.c

···
 	h->last_refresh = now;
 }
 
+static void cache_fresh_locked(struct cache_head *head, time_t expiry,
+				struct cache_detail *detail);
+static void cache_fresh_unlocked(struct cache_head *head,
+				struct cache_detail *detail);
+
 static struct cache_head *sunrpc_cache_find_rcu(struct cache_detail *detail,
 						struct cache_head *key,
 						int hash)
···
 			if (cache_is_expired(detail, tmp)) {
 				hlist_del_init_rcu(&tmp->cache_list);
 				detail->entries --;
+				cache_fresh_locked(tmp, 0, detail);
 				freeme = tmp;
 				break;
 			}
···
 	cache_get(new);
 	spin_unlock(&detail->hash_lock);
 
-	if (freeme)
+	if (freeme) {
+		cache_fresh_unlocked(freeme, detail);
 		cache_put(freeme, detail);
+	}
 	return new;
 }
 

net/sunrpc/svc.c

···
 #endif
 
 /*
+ * Setup response header for TCP, it has a 4B record length field.
+ */
+static void svc_tcp_prep_reply_hdr(struct svc_rqst *rqstp)
+{
+	struct kvec *resv = &rqstp->rq_res.head[0];
+
+	/* tcp needs a space for the record length... */
+	svc_putnl(resv, 0);
+}
+
+/*
  * Common routine for processing the RPC request.
  */
 static int
···
 	clear_bit(RQ_DROPME, &rqstp->rq_flags);
 
 	/* Setup reply header */
-	rqstp->rq_xprt->xpt_ops->xpo_prep_reply_hdr(rqstp);
+	if (rqstp->rq_prot == IPPROTO_TCP)
+		svc_tcp_prep_reply_hdr(rqstp);
 
 	svc_putu32(resv, rqstp->rq_xid);
 
···
 	 * for lower versions. RPC_PROG_MISMATCH seems to be the closest
 	 * fit.
 	 */
-	if (versp->vs_need_cong_ctrl &&
+	if (versp->vs_need_cong_ctrl && rqstp->rq_xprt &&
 	    !test_bit(XPT_CONG_CTRL, &rqstp->rq_xprt->xpt_flags))
 		goto err_bad_vers;
 
···
 	return 0;
 
  close:
-	if (test_bit(XPT_TEMP, &rqstp->rq_xprt->xpt_flags))
+	if (rqstp->rq_xprt && test_bit(XPT_TEMP, &rqstp->rq_xprt->xpt_flags))
 		svc_close_xprt(rqstp->rq_xprt);
 	dprintk("svc: svc_process close\n");
 	return 0;
···
 	dprintk("svc: %s(%p)\n", __func__, req);
 
 	/* Build the svc_rqst used by the common processing routine */
-	rqstp->rq_xprt = serv->sv_bc_xprt;
 	rqstp->rq_xid = req->rq_xid;
 	rqstp->rq_prot = req->rq_xprt->prot;
 	rqstp->rq_server = serv;
+	rqstp->rq_bc_net = req->rq_xprt->xprt_net;
 
 	rqstp->rq_addrlen = sizeof(req->rq_xprt->addr);
 	memcpy(&rqstp->rq_addr, &req->rq_xprt->addr, rqstp->rq_addrlen);
···
 	if (!proc_error) {
 		/* Processing error: drop the request */
 		xprt_free_bc_request(req);
-		return 0;
+		error = -EINVAL;
+		goto out;
 	}
-
 	/* Finally, send the reply synchronously */
 	memcpy(&req->rq_snd_buf, &rqstp->rq_res, sizeof(req->rq_snd_buf));
 	task = rpc_run_bc_task(req);

net/sunrpc/svc_xprt.c

···
 		request_module("svc%s", xprt_name);
 		err = _svc_create_xprt(serv, xprt_name, net, family, port, flags);
 	}
-	if (err)
+	if (err < 0)
 		dprintk("svc: transport %s not found, err %d\n",
-			xprt_name, err);
+			xprt_name, -err);
 	return err;
 }
 EXPORT_SYMBOL_GPL(svc_create_xprt);
···
  */
 void svc_reserve(struct svc_rqst *rqstp, int space)
 {
+	struct svc_xprt *xprt = rqstp->rq_xprt;
+
 	space += rqstp->rq_res.head[0].iov_len;
 
-	if (space < rqstp->rq_reserved) {
-		struct svc_xprt *xprt = rqstp->rq_xprt;
+	if (xprt && space < rqstp->rq_reserved) {
 		atomic_sub((rqstp->rq_reserved - space), &xprt->xpt_reserved);
 		rqstp->rq_reserved = space;
 

net/sunrpc/svcsock.c

···
 static struct svc_xprt *svc_create_socket(struct svc_serv *, int,
 					  struct net *, struct sockaddr *,
 					  int, int);
-#if defined(CONFIG_SUNRPC_BACKCHANNEL)
-static struct svc_xprt *svc_bc_create_socket(struct svc_serv *, int,
-					     struct net *, struct sockaddr *,
-					     int, int);
-static void svc_bc_sock_free(struct svc_xprt *xprt);
-#endif /* CONFIG_SUNRPC_BACKCHANNEL */
-
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 static struct lock_class_key svc_key[2];
 static struct lock_class_key svc_slock_key[2];
···
 	return error;
 }
 
-static void svc_udp_prep_reply_hdr(struct svc_rqst *rqstp)
-{
-}
-
 static int svc_udp_has_wspace(struct svc_xprt *xprt)
 {
 	struct svc_sock *svsk = container_of(xprt, struct svc_sock, sk_xprt);
···
 	.xpo_release_rqst = svc_release_udp_skb,
 	.xpo_detach = svc_sock_detach,
 	.xpo_free = svc_sock_free,
-	.xpo_prep_reply_hdr = svc_udp_prep_reply_hdr,
 	.xpo_has_wspace = svc_udp_has_wspace,
 	.xpo_accept = svc_udp_accept,
 	.xpo_secure_port = svc_sock_secure_port,
···
 	return sent;
 }
 
-/*
- * Setup response header. TCP has a 4B record length field.
- */
-static void svc_tcp_prep_reply_hdr(struct svc_rqst *rqstp)
-{
-	struct kvec *resv = &rqstp->rq_res.head[0];
-
-	/* tcp needs a space for the record length... */
-	svc_putnl(resv, 0);
-}
-
 static struct svc_xprt *svc_tcp_create(struct svc_serv *serv,
 				       struct net *net,
 				       struct sockaddr *sa, int salen,
···
 	return svc_create_socket(serv, IPPROTO_TCP, net, sa, salen, flags);
 }
 
-#if defined(CONFIG_SUNRPC_BACKCHANNEL)
-static struct svc_xprt *svc_bc_create_socket(struct svc_serv *, int,
-					     struct net *, struct sockaddr *,
-					     int, int);
-static void svc_bc_sock_free(struct svc_xprt *xprt);
-
-static struct svc_xprt *svc_bc_tcp_create(struct svc_serv *serv,
-				       struct net *net,
-				       struct sockaddr *sa, int salen,
-				       int flags)
-{
-	return svc_bc_create_socket(serv, IPPROTO_TCP, net, sa, salen, flags);
-}
-
-static void svc_bc_tcp_sock_detach(struct svc_xprt *xprt)
-{
-}
-
-static const struct svc_xprt_ops svc_tcp_bc_ops = {
-	.xpo_create = svc_bc_tcp_create,
-	.xpo_detach = svc_bc_tcp_sock_detach,
-	.xpo_free = svc_bc_sock_free,
-	.xpo_prep_reply_hdr = svc_tcp_prep_reply_hdr,
-	.xpo_secure_port = svc_sock_secure_port,
-};
-
-static struct svc_xprt_class svc_tcp_bc_class = {
-	.xcl_name = "tcp-bc",
-	.xcl_owner = THIS_MODULE,
-	.xcl_ops = &svc_tcp_bc_ops,
-	.xcl_max_payload = RPCSVC_MAXPAYLOAD_TCP,
-};
-
-static void svc_init_bc_xprt_sock(void)
-{
-	svc_reg_xprt_class(&svc_tcp_bc_class);
-}
-
-static void svc_cleanup_bc_xprt_sock(void)
-{
-	svc_unreg_xprt_class(&svc_tcp_bc_class);
-}
-#else /* CONFIG_SUNRPC_BACKCHANNEL */
-static void svc_init_bc_xprt_sock(void)
-{
-}
-
-static void svc_cleanup_bc_xprt_sock(void)
-{
-}
-#endif /* CONFIG_SUNRPC_BACKCHANNEL */
-
 static const struct svc_xprt_ops svc_tcp_ops = {
 	.xpo_create = svc_tcp_create,
 	.xpo_recvfrom = svc_tcp_recvfrom,
···
 	.xpo_release_rqst = svc_release_skb,
 	.xpo_detach = svc_tcp_sock_detach,
 	.xpo_free = svc_sock_free,
-	.xpo_prep_reply_hdr = svc_tcp_prep_reply_hdr,
 	.xpo_has_wspace = svc_tcp_has_wspace,
 	.xpo_accept = svc_tcp_accept,
 	.xpo_secure_port = svc_sock_secure_port,
···
 {
 	svc_reg_xprt_class(&svc_tcp_class);
 	svc_reg_xprt_class(&svc_udp_class);
-	svc_init_bc_xprt_sock();
 }
 
 void svc_cleanup_xprt_sock(void)
 {
 	svc_unreg_xprt_class(&svc_tcp_class);
 	svc_unreg_xprt_class(&svc_udp_class);
-	svc_cleanup_bc_xprt_sock();
 }
 
 static void svc_tcp_init(struct svc_sock *svsk, struct svc_serv *serv)
···
 		sock_release(svsk->sk_sock);
 	kfree(svsk);
 }
-
-#if defined(CONFIG_SUNRPC_BACKCHANNEL)
-/*
- * Create a back channel svc_xprt which shares the fore channel socket.
- */
-static struct svc_xprt *svc_bc_create_socket(struct svc_serv *serv,
-					     int protocol,
-					     struct net *net,
-					     struct sockaddr *sin, int len,
-					     int flags)
-{
-	struct svc_sock *svsk;
-	struct svc_xprt *xprt;
-
-	if (protocol != IPPROTO_TCP) {
-		printk(KERN_WARNING "svc: only TCP sockets"
-			" supported on shared back channel\n");
-		return ERR_PTR(-EINVAL);
-	}
-
-	svsk = kzalloc(sizeof(*svsk), GFP_KERNEL);
-	if (!svsk)
-		return ERR_PTR(-ENOMEM);
-
-	xprt = &svsk->sk_xprt;
-	svc_xprt_init(net, &svc_tcp_bc_class, xprt, serv);
-	set_bit(XPT_CONG_CTRL, &svsk->sk_xprt.xpt_flags);
-
-	serv->sv_bc_xprt = xprt;
-
-	return xprt;
-}
-
-/*
- * Free a back channel svc_sock.
- */
-static void svc_bc_sock_free(struct svc_xprt *xprt)
-{
-	if (xprt)
-		kfree(container_of(xprt, struct svc_sock, sk_xprt));
-}
-#endif /* CONFIG_SUNRPC_BACKCHANNEL */

net/sunrpc/xprtrdma/backchannel.c

···
 }
 
 /**
- * xprt_rdma_bc_up - Create transport endpoint for backchannel service
- * @serv: server endpoint
- * @net: network namespace
- *
- * The "xprt" is an implied argument: it supplies the name of the
- * backchannel transport class.
- *
- * Returns zero on success, negative errno on failure
- */
-int xprt_rdma_bc_up(struct svc_serv *serv, struct net *net)
-{
-	int ret;
-
-	ret = svc_create_xprt(serv, "rdma-bc", net, PF_INET, 0, 0);
-	if (ret < 0)
-		return ret;
-	return 0;
-}
-
-/**
  * xprt_rdma_bc_maxpayload - Return maximum backchannel message size
  * @xprt: transport
  *

net/sunrpc/xprtrdma/svc_rdma.c

···
 		unregister_sysctl_table(svcrdma_table_header);
 		svcrdma_table_header = NULL;
 	}
-#if defined(CONFIG_SUNRPC_BACKCHANNEL)
-	svc_unreg_xprt_class(&svc_rdma_bc_class);
-#endif
 	svc_unreg_xprt_class(&svc_rdma_class);
 }
 
···
 
 	/* Register RDMA with the SVC transport switch */
 	svc_reg_xprt_class(&svc_rdma_class);
-#if defined(CONFIG_SUNRPC_BACKCHANNEL)
-	svc_reg_xprt_class(&svc_rdma_bc_class);
-#endif
 	return 0;
 }

net/sunrpc/xprtrdma/svc_rdma_recvfrom.c

···
 	return p;
 }
 
+/* RPC-over-RDMA Version One private extension: Remote Invalidation.
+ * Responder's choice: requester signals it can handle Send With
+ * Invalidate, and responder chooses one R_key to invalidate.
+ *
+ * If there is exactly one distinct R_key in the received transport
+ * header, set rc_inv_rkey to that R_key. Otherwise, set it to zero.
+ *
+ * Perform this operation while the received transport header is
+ * still in the CPU cache.
+ */
+static void svc_rdma_get_inv_rkey(struct svcxprt_rdma *rdma,
+				  struct svc_rdma_recv_ctxt *ctxt)
+{
+	__be32 inv_rkey, *p;
+	u32 i, segcount;
+
+	ctxt->rc_inv_rkey = 0;
+
+	if (!rdma->sc_snd_w_inv)
+		return;
+
+	inv_rkey = xdr_zero;
+	p = ctxt->rc_recv_buf;
+	p += rpcrdma_fixed_maxsz;
+
+	/* Read list */
+	while (*p++ != xdr_zero) {
+		p++;	/* position */
+		if (inv_rkey == xdr_zero)
+			inv_rkey = *p;
+		else if (inv_rkey != *p)
+			return;
+		p += 4;
+	}
+
+	/* Write list */
+	while (*p++ != xdr_zero) {
+		segcount = be32_to_cpup(p++);
+		for (i = 0; i < segcount; i++) {
+			if (inv_rkey == xdr_zero)
+				inv_rkey = *p;
+			else if (inv_rkey != *p)
+				return;
+			p += 4;
+		}
+	}
+
+	/* Reply chunk */
+	if (*p++ != xdr_zero) {
+		segcount = be32_to_cpup(p++);
+		for (i = 0; i < segcount; i++) {
+			if (inv_rkey == xdr_zero)
+				inv_rkey = *p;
+			else if (inv_rkey != *p)
+				return;
+			p += 4;
+		}
+	}
+
+	ctxt->rc_inv_rkey = be32_to_cpu(inv_rkey);
+}
+
 /* On entry, xdr->head[0].iov_base points to first byte in the
  * RPC-over-RDMA header.
  *
···
 		svc_rdma_recv_ctxt_put(rdma_xprt, ctxt);
 		return ret;
 	}
+	svc_rdma_get_inv_rkey(rdma_xprt, ctxt);
 
 	p += rpcrdma_fixed_maxsz;
 	if (*p != xdr_zero)

net/sunrpc/xprtrdma/svc_rdma_sendto.c

···
 		*reply = NULL;
 }
 
-/* RPC-over-RDMA Version One private extension: Remote Invalidation.
- * Responder's choice: requester signals it can handle Send With
- * Invalidate, and responder chooses one rkey to invalidate.
- *
- * Find a candidate rkey to invalidate when sending a reply.  Picks the
- * first R_key it finds in the chunk lists.
- *
- * Returns zero if RPC's chunk lists are empty.
- */
-static u32 svc_rdma_get_inv_rkey(__be32 *rdma_argp,
-				 __be32 *wr_lst, __be32 *rp_ch)
-{
-	__be32 *p;
-
-	p = rdma_argp + rpcrdma_fixed_maxsz;
-	if (*p != xdr_zero)
-		p += 2;
-	else if (wr_lst && be32_to_cpup(wr_lst + 1))
-		p = wr_lst + 2;
-	else if (rp_ch && be32_to_cpup(rp_ch + 1))
-		p = rp_ch + 2;
-	else
-		return 0;
-	return be32_to_cpup(p);
-}
-
 static int svc_rdma_dma_map_page(struct svcxprt_rdma *rdma,
 				 struct svc_rdma_send_ctxt *ctxt,
 				 struct page *page,
···
  *
  * RDMA Send is the last step of transmitting an RPC reply. Pages
  * involved in the earlier RDMA Writes are here transferred out
- * of the rqstp and into the ctxt's page array. These pages are
+ * of the rqstp and into the sctxt's page array. These pages are
  * DMA unmapped by each Write completion, but the subsequent Send
  * completion finally releases these pages.
  *
···
  * - The Reply's transport header will never be larger than a page.
  */
 static int svc_rdma_send_reply_msg(struct svcxprt_rdma *rdma,
-				   struct svc_rdma_send_ctxt *ctxt,
-				   __be32 *rdma_argp,
+				   struct svc_rdma_send_ctxt *sctxt,
+				   struct svc_rdma_recv_ctxt *rctxt,
 				   struct svc_rqst *rqstp,
 				   __be32 *wr_lst, __be32 *rp_ch)
 {
 	int ret;
 
 	if (!rp_ch) {
-		ret = svc_rdma_map_reply_msg(rdma, ctxt,
+		ret = svc_rdma_map_reply_msg(rdma, sctxt,
 					     &rqstp->rq_res, wr_lst);
 		if (ret < 0)
 			return ret;
 	}
 
-	svc_rdma_save_io_pages(rqstp, ctxt);
+	svc_rdma_save_io_pages(rqstp, sctxt);
 
-	ctxt->sc_send_wr.opcode = IB_WR_SEND;
-	if (rdma->sc_snd_w_inv) {
-		ctxt->sc_send_wr.ex.invalidate_rkey =
-			svc_rdma_get_inv_rkey(rdma_argp, wr_lst, rp_ch);
-		if (ctxt->sc_send_wr.ex.invalidate_rkey)
-			ctxt->sc_send_wr.opcode = IB_WR_SEND_WITH_INV;
+	if (rctxt->rc_inv_rkey) {
+		sctxt->sc_send_wr.opcode = IB_WR_SEND_WITH_INV;
+		sctxt->sc_send_wr.ex.invalidate_rkey = rctxt->rc_inv_rkey;
+	} else {
+		sctxt->sc_send_wr.opcode = IB_WR_SEND;
 	}
 	dprintk("svcrdma: posting Send WR with %u sge(s)\n",
-		ctxt->sc_send_wr.num_sge);
-	return svc_rdma_send(rdma, &ctxt->sc_send_wr);
+		sctxt->sc_send_wr.num_sge);
+	return svc_rdma_send(rdma, &sctxt->sc_send_wr);
 }
 
 /* Given the client-provided Write and Reply chunks, the server was not
···
 	}
 
 	return 0;
-}
-
-void svc_rdma_prep_reply_hdr(struct svc_rqst *rqstp)
-{
 }
 
 /**
···
 	}
 
 	svc_rdma_sync_reply_hdr(rdma, sctxt, svc_rdma_reply_hdr_len(rdma_resp));
-	ret = svc_rdma_send_reply_msg(rdma, sctxt, rdma_argp, rqstp,
+	ret = svc_rdma_send_reply_msg(rdma, sctxt, rctxt, rqstp,
 				      wr_lst, rp_ch);
 	if (ret < 0)
 		goto err1;

net/sunrpc/xprtrdma/svc_rdma_transport.c

···
 	.xpo_release_rqst = svc_rdma_release_rqst,
 	.xpo_detach = svc_rdma_detach,
 	.xpo_free = svc_rdma_free,
-	.xpo_prep_reply_hdr = svc_rdma_prep_reply_hdr,
 	.xpo_has_wspace = svc_rdma_has_wspace,
 	.xpo_accept = svc_rdma_accept,
 	.xpo_secure_port = svc_rdma_secure_port,
···
 	.xcl_max_payload = RPCSVC_MAXPAYLOAD_RDMA,
 	.xcl_ident = XPRT_TRANSPORT_RDMA,
 };
-
-#if defined(CONFIG_SUNRPC_BACKCHANNEL)
-static struct svc_xprt *svc_rdma_bc_create(struct svc_serv *, struct net *,
-					   struct sockaddr *, int, int);
-static void svc_rdma_bc_detach(struct svc_xprt *);
-static void svc_rdma_bc_free(struct svc_xprt *);
-
-static const struct svc_xprt_ops svc_rdma_bc_ops = {
-	.xpo_create = svc_rdma_bc_create,
-	.xpo_detach = svc_rdma_bc_detach,
-	.xpo_free = svc_rdma_bc_free,
-	.xpo_prep_reply_hdr = svc_rdma_prep_reply_hdr,
-	.xpo_secure_port = svc_rdma_secure_port,
-};
-
-struct svc_xprt_class svc_rdma_bc_class = {
-	.xcl_name = "rdma-bc",
-	.xcl_owner = THIS_MODULE,
-	.xcl_ops = &svc_rdma_bc_ops,
-	.xcl_max_payload = (1024 - RPCRDMA_HDRLEN_MIN)
-};
-
-static struct svc_xprt *svc_rdma_bc_create(struct svc_serv *serv,
-					   struct net *net,
-					   struct sockaddr *sa, int salen,
-					   int flags)
-{
-	struct svcxprt_rdma *cma_xprt;
-	struct svc_xprt *xprt;
-
-	cma_xprt = svc_rdma_create_xprt(serv, net);
-	if (!cma_xprt)
-		return ERR_PTR(-ENOMEM);
-	xprt = &cma_xprt->sc_xprt;
-
-	svc_xprt_init(net, &svc_rdma_bc_class, xprt, serv);
-	set_bit(XPT_CONG_CTRL, &xprt->xpt_flags);
-	serv->sv_bc_xprt = xprt;
-
-	dprintk("svcrdma: %s(%p)\n", __func__, xprt);
-	return xprt;
-}
-
-static void svc_rdma_bc_detach(struct svc_xprt *xprt)
-{
-	dprintk("svcrdma: %s(%p)\n", __func__, xprt);
-}
-
-static void svc_rdma_bc_free(struct svc_xprt *xprt)
-{
-	struct svcxprt_rdma *rdma =
-		container_of(xprt, struct svcxprt_rdma, sc_xprt);
-
-	dprintk("svcrdma: %s(%p)\n", __func__, xprt);
-	if (xprt)
-		kfree(rdma);
-}
-#endif	/* CONFIG_SUNRPC_BACKCHANNEL */
 
 /* QP event handler */
 static void qp_event_handler(struct ib_event *event, void *context)

net/sunrpc/xprtrdma/transport.c

···
 	.inject_disconnect	= xprt_rdma_inject_disconnect,
 #if defined(CONFIG_SUNRPC_BACKCHANNEL)
 	.bc_setup		= xprt_rdma_bc_setup,
-	.bc_up			= xprt_rdma_bc_up,
 	.bc_maxpayload		= xprt_rdma_bc_maxpayload,
 	.bc_free_rqst		= xprt_rdma_bc_free_rqst,
 	.bc_destroy		= xprt_rdma_bc_destroy,

net/sunrpc/xprtrdma/xprt_rdma.h

···
  */
 #if defined(CONFIG_SUNRPC_BACKCHANNEL)
 int xprt_rdma_bc_setup(struct rpc_xprt *, unsigned int);
-int xprt_rdma_bc_up(struct svc_serv *, struct net *);
 size_t xprt_rdma_bc_maxpayload(struct rpc_xprt *);
 int rpcrdma_bc_post_recv(struct rpcrdma_xprt *, unsigned int);
 void rpcrdma_bc_receive_call(struct rpcrdma_xprt *, struct rpcrdma_rep *);

net/sunrpc/xprtsock.c

···
 }
 
 #if defined(CONFIG_SUNRPC_BACKCHANNEL)
-static int xs_tcp_bc_up(struct svc_serv *serv, struct net *net)
-{
-	int ret;
-
-	ret = svc_create_xprt(serv, "tcp-bc", net, PF_INET, 0,
-			      SVC_SOCK_ANONYMOUS);
-	if (ret < 0)
-		return ret;
-	return 0;
-}
-
 static size_t xs_tcp_bc_maxpayload(struct rpc_xprt *xprt)
 {
 	return PAGE_SIZE;
···
 	.inject_disconnect	= xs_inject_disconnect,
 #ifdef CONFIG_SUNRPC_BACKCHANNEL
 	.bc_setup		= xprt_setup_bc,
-	.bc_up			= xs_tcp_bc_up,
 	.bc_maxpayload		= xs_tcp_bc_maxpayload,
 	.bc_free_rqst		= xprt_free_bc_rqst,
 	.bc_destroy		= xprt_destroy_bc,