knfsd: revised patches to fix IPv6/sunrpc link error and other fixes

diff .prev/net/sunrpc/svcsock.c ./net/sunrpc/svcsock.c
@@ -721,45 +721,23 @@ svc_write_space(struct sock *sk)
 	}
 }
 
-static void svc_udp_get_sender_address(struct svc_rqst *rqstp,
-					struct sk_buff *skb)
+static inline void svc_udp_get_dest_address(struct svc_rqst *rqstp,
+					    struct cmsghdr *cmh)
 {
 	switch (rqstp->rq_sock->sk_sk->sk_family) {
 	case AF_INET: {
-		/* this seems to come from net/ipv4/udp.c:udp_recvmsg */
-			struct sockaddr_in *sin = svc_addr_in(rqstp);
-
-			sin->sin_family = AF_INET;
-			sin->sin_port = skb->h.uh->source;
-			sin->sin_addr.s_addr = skb->nh.iph->saddr;
-			rqstp->rq_addrlen = sizeof(struct sockaddr_in);
-			/* Remember which interface received this request */
-			rqstp->rq_daddr.addr.s_addr = skb->nh.iph->daddr;
-		}
+		struct in_pktinfo *pki = CMSG_DATA(cmh);
+		rqstp->rq_daddr.addr.s_addr = pki->ipi_spec_dst.s_addr;
 		break;
+		}
 #if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
 	case AF_INET6: {
-		/* this is derived from net/ipv6/udp.c:udpv6_recvmesg */
-			struct sockaddr_in6 *sin6 = svc_addr_in6(rqstp);
-
-			sin6->sin6_family = AF_INET6;
-			sin6->sin6_port = skb->h.uh->source;
-			sin6->sin6_flowinfo = 0;
-			sin6->sin6_scope_id = 0;
-			if (ipv6_addr_type(&sin6->sin6_addr) &
-							IPV6_ADDR_LINKLOCAL)
-				sin6->sin6_scope_id = IP6CB(skb)->iif;
-			ipv6_addr_copy(&sin6->sin6_addr,
-							&skb->nh.ipv6h->saddr);
-			rqstp->rq_addrlen = sizeof(struct sockaddr_in);
-			/* Remember which interface received this request */
-			ipv6_addr_copy(&rqstp->rq_daddr.addr6,
-							&skb->nh.ipv6h->saddr);
-		}
+		struct in6_pktinfo *pki = CMSG_DATA(cmh);
+		ipv6_addr_copy(&rqstp->rq_daddr.addr6, &pki->ipi6_addr);
 		break;
+		}
 #endif
 	}
-	return;
 }
 
 /*

@@ -771,7 +749,15 @@ svc_udp_recvfrom(struct svc_rqst *rqstp)
 	struct svc_sock	*svsk = rqstp->rq_sock;
 	struct svc_serv	*serv = svsk->sk_server;
 	struct sk_buff	*skb;
+	char		buffer[CMSG_SPACE(sizeof(union svc_pktinfo_u))];
+	struct cmsghdr *cmh = (struct cmsghdr *)buffer;
 	int		err, len;
+	struct msghdr msg = {
+		.msg_name = svc_addr(rqstp),
+		.msg_control = cmh,
+		.msg_controllen = sizeof(buffer),
+		.msg_flags = MSG_DONTWAIT,
+	};
 
 	if (test_and_clear_bit(SK_CHNGBUF, &svsk->sk_flags))
 	    /* udp sockets need large rcvbuf as all pending

@@ -797,7 +783,9 @@ svc_udp_recvfrom(struct svc_rqst *rqstp)
 	}
 
 	clear_bit(SK_DATA, &svsk->sk_flags);
-	while ((skb = skb_recv_datagram(svsk->sk_sk, 0, 1, &err)) == NULL) {
+	while ((err == kernel_recvmsg(svsk->sk_sock, &msg, NULL,
+				      0, 0, MSG_PEEK | MSG_DONTWAIT)) < 0 ||
+	       (skb = skb_recv_datagram(svsk->sk_sk, 0, 1, &err)) == NULL) {
 		if (err == -EAGAIN) {
 			svc_sock_received(svsk);
 			return err;

@@ -805,6 +793,7 @@ svc_udp_recvfrom(struct svc_rqst *rqstp)
 		/* possibly an icmp error */
 		dprintk("svc: recvfrom returned error %d\n", -err);
 	}
+	rqstp->rq_addrlen = sizeof(rqstp->rq_addr);
 	if (skb->tstamp.off_sec == 0) {
 		struct timeval tv;
 

@@ -827,7 +816,16 @@ svc_udp_recvfrom(struct svc_rqst *rqstp)
 
 	rqstp->rq_prot = IPPROTO_UDP;
 
-	svc_udp_get_sender_address(rqstp, skb);
+	if (cmh->cmsg_level != IPPROTO_IP ||
+	    cmh->cmsg_type != IP_PKTINFO) {
+		if (net_ratelimit())
+			printk("rpcsvc: received unknown control message:"
+			       "%d/%d\n",
+			       cmh->cmsg_level, cmh->cmsg_type);
+		skb_free_datagram(svsk->sk_sk, skb);
+		return 0;
+	}
+	svc_udp_get_dest_address(rqstp, cmh);
 
 	if (skb_is_nonlinear(skb)) {
 		/* we have to copy */

@@ -884,6 +882,9 @@ svc_udp_sendto(struct svc_rqst *rqstp)
 static void
 svc_udp_init(struct svc_sock *svsk)
 {
+	int one = 1;
+	mm_segment_t oldfs;
+
 	svsk->sk_sk->sk_data_ready = svc_udp_data_ready;
 	svsk->sk_sk->sk_write_space = svc_write_space;
 	svsk->sk_recvfrom = svc_udp_recvfrom;

@@ -899,6 +900,13 @@ svc_udp_init(struct svc_sock *svsk)
 
 	set_bit(SK_DATA, &svsk->sk_flags); /* might have come in before data_ready set up */
 	set_bit(SK_CHNGBUF, &svsk->sk_flags);
+
+	oldfs = get_fs();
+	set_fs(KERNEL_DS);
+	/* make sure we get destination address info */
+	svsk->sk_sock->ops->setsockopt(svsk->sk_sock, IPPROTO_IP, IP_PKTINFO,
+				       (char __user *)&one, sizeof(one));
+	set_fs(oldfs);
 }
 
 /*

diff .prev/include/linux/sunrpc/svc.h ./include/linux/sunrpc/svc.h
@@ -194,9 +194,7 @@ static inline void svc_putu32(struct kve
 
 union svc_addr_u {
     struct in_addr	addr;
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
     struct in6_addr	addr6;
-#endif
 };
 
 /*

diff .prev/net/sunrpc/svcsock.c ./net/sunrpc/svcsock.c
@@ -131,13 +131,13 @@ static char *__svc_print_addr(struct soc
 			NIPQUAD(((struct sockaddr_in *) addr)->sin_addr),
 			htons(((struct sockaddr_in *) addr)->sin_port));
 		break;
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+
 	case AF_INET6:
 		snprintf(buf, len, "%x:%x:%x:%x:%x:%x:%x:%x, port=%u",
 			NIP6(((struct sockaddr_in6 *) addr)->sin6_addr),
 			htons(((struct sockaddr_in6 *) addr)->sin6_port));
 		break;
-#endif
+
 	default:
 		snprintf(buf, len, "unknown address type: %d", addr->sa_family);
 		break;

@@ -449,9 +449,7 @@ svc_wake_up(struct svc_serv *serv)
 
 union svc_pktinfo_u {
 	struct in_pktinfo pkti;
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
 	struct in6_pktinfo pkti6;
-#endif
 };
 
 static void svc_set_cmsg_data(struct svc_rqst *rqstp, struct cmsghdr *cmh)

@@ -467,7 +465,7 @@ static void svc_set_cmsg_data(struct svc
 			cmh->cmsg_len = CMSG_LEN(sizeof(*pki));
 		}
 		break;
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+
 	case AF_INET6: {
 			struct in6_pktinfo *pki = CMSG_DATA(cmh);
 

@@ -479,7 +477,6 @@ static void svc_set_cmsg_data(struct svc
 			cmh->cmsg_len = CMSG_LEN(sizeof(*pki));
 		}
 		break;
-#endif
 	}
 	return;
 }

@@ -730,13 +727,11 @@ static inline void svc_udp_get_dest_addr
 		rqstp->rq_daddr.addr.s_addr = pki->ipi_spec_dst.s_addr;
 		break;
 		}
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
 	case AF_INET6: {
 		struct in6_pktinfo *pki = CMSG_DATA(cmh);
 		ipv6_addr_copy(&rqstp->rq_daddr.addr6, &pki->ipi6_addr);
 		break;
 		}
-#endif
 	}
 }
 

@@ -985,11 +980,9 @@ static inline int svc_port_is_privileged
 	case AF_INET:
 		return ntohs(((struct sockaddr_in *)sin)->sin_port)
 			< PROT_SOCK;
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
 	case AF_INET6:
 		return ntohs(((struct sockaddr_in6 *)sin)->sin6_port)
 			< PROT_SOCK;
-#endif
 	default:
 		return 0;
 	}

diff .prev/include/linux/sunrpc/svcsock.h ./include/linux/sunrpc/svcsock.h
@@ -66,7 +66,7 @@ struct svc_sock {
  * Function prototypes.
  */
 int		svc_makesock(struct svc_serv *, int, unsigned short, int flags);
-void		svc_close_socket(struct svc_sock *);
+void		svc_force_close_socket(struct svc_sock *);
 int		svc_recv(struct svc_rqst *, long);
 int		svc_send(struct svc_rqst *);
 void		svc_drop(struct svc_rqst *);

diff .prev/net/sunrpc/svc.c ./net/sunrpc/svc.c
@@ -367,6 +367,7 @@ void
 svc_destroy(struct svc_serv *serv)
 {
 	struct svc_sock	*svsk;
+	struct svc_sock *tmp;
 
 	dprintk("svc: svc_destroy(%s, %d)\n",
 				serv->sv_program->pg_name,

@@ -382,21 +383,17 @@ svc_destroy(struct svc_serv *serv)
 
 	del_timer_sync(&serv->sv_temptimer);
 
-	while (!list_empty(&serv->sv_tempsocks)) {
-		svsk = list_entry(serv->sv_tempsocks.next,
-				  struct svc_sock,
-				  sk_list);
-		svc_close_socket(svsk);
-	}
+	list_for_each_entry_safe(svsk, tmp, &serv->sv_tempsocks, sk_list)
+		svc_force_close_socket(svsk);
+
 	if (serv->sv_shutdown)
 		serv->sv_shutdown(serv);
 
-	while (!list_empty(&serv->sv_permsocks)) {
-		svsk = list_entry(serv->sv_permsocks.next,
-				  struct svc_sock,
-				  sk_list);
-		svc_close_socket(svsk);
-	}
+	list_for_each_entry_safe(svsk, tmp, &serv->sv_permsocks, sk_list)
+		svc_force_close_socket(svsk);
+
+	BUG_ON(!list_empty(&serv->sv_permsocks));
+	BUG_ON(!list_empty(&serv->sv_tempsocks));
 
 	cache_clean_deferred(serv);
 

diff .prev/net/sunrpc/svcsock.c ./net/sunrpc/svcsock.c
@@ -82,6 +82,7 @@ static void		svc_delete_socket(struct sv
 static void		svc_udp_data_ready(struct sock *, int);
 static int		svc_udp_recvfrom(struct svc_rqst *);
 static int		svc_udp_sendto(struct svc_rqst *);
+static void		svc_close_socket(struct svc_sock *svsk);
 
 static struct svc_deferred_req *svc_deferred_dequeue(struct svc_sock *svsk);
 static int svc_deferred_recv(struct svc_rqst *rqstp);

@@ -1787,7 +1788,7 @@ svc_delete_socket(struct svc_sock *svsk)
 	spin_unlock_bh(&serv->sv_lock);
 }
 
-void svc_close_socket(struct svc_sock *svsk)
+static void svc_close_socket(struct svc_sock *svsk)
 {
 	set_bit(SK_CLOSE, &svsk->sk_flags);
 	if (test_and_set_bit(SK_BUSY, &svsk->sk_flags))

@@ -1800,6 +1801,19 @@ void svc_close_socket(struct svc_sock *s
 	svc_sock_put(svsk);
 }
 
+void svc_force_close_socket(struct svc_sock *svsk)
+{
+	set_bit(SK_CLOSE, &svsk->sk_flags);
+	if (test_bit(SK_BUSY, &svsk->sk_flags)) {
+		/* Waiting to be processed, but no threads left,
+		 * So just remove it from the waiting list
+		 */
+		list_del_init(&svsk->sk_ready);
+		clear_bit(SK_BUSY, &svsk->sk_flags);
+	}
+	svc_close_socket(svsk);
+}
+
 /**
  * svc_makesock - Make a socket for nfsd and lockd
  * @serv: RPC server structure

213 lines not on this page · raw message

diff .prev/net/sunrpc/svc.c ./net/sunrpc/svc.c
@@ -79,7 +79,11 @@ svc_pool_map_choose_mode(void)
 		 * x86_64 kernel on Xeons.  In this case we
 		 * want to divide the pools on cpu boundaries.
 		 */
-		return SVC_POOL_PERCPU;
+		/* actually, unless your IRQs round-robin nicely,
+		 * this turns out to be really bad, so just
+		 * go GLOBAL for now until a better fix can be developped
+		 */
+		return SVC_POOL_GLOBAL;
 	}
 
 	/* default: one global pool */