Merge tag 'nfs-rdma-for-4.1-1' of git://git.linux-nfs.org/projects/anna/nfs-rdma

NFS: NFSoRDMA Client Changes

This patch series creates an operation vector for each of the different
memory registration modes.  This should make it easier to one day increase
credit limit, rsize, and wsize.

Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>

12 files changed, 75 insertions, 37 deletions

diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 14d02ea905b6..3e44b9b0b78e 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -268,6 +268,7 @@ static int inet_csk_wait_for_connect(struct sock *sk, long timeo)
 		release_sock(sk);
 		if (reqsk_queue_empty(&icsk->icsk_accept_queue))
 			timeo = schedule_timeout(timeo);
+		sched_annotate_sleep();
 		lock_sock(sk);
 		err = 0;
 		if (!reqsk_queue_empty(&icsk->icsk_accept_queue))
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index 81751f12645f..592aff37366b 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -71,6 +71,20 @@ static inline void inet_diag_unlock_handler(
 	mutex_unlock(&inet_diag_table_mutex);
 }
 
+static size_t inet_sk_attr_size(void)
+{
+	return	  nla_total_size(sizeof(struct tcp_info))
+		+ nla_total_size(1) /* INET_DIAG_SHUTDOWN */
+		+ nla_total_size(1) /* INET_DIAG_TOS */
+		+ nla_total_size(1) /* INET_DIAG_TCLASS */
+		+ nla_total_size(sizeof(struct inet_diag_meminfo))
+		+ nla_total_size(sizeof(struct inet_diag_msg))
+		+ nla_total_size(SK_MEMINFO_VARS * sizeof(u32))
+		+ nla_total_size(TCP_CA_NAME_MAX)
+		+ nla_total_size(sizeof(struct tcpvegas_info))
+		+ 64;
+}
+
 int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk,
 			      struct sk_buff *skb, struct inet_diag_req_v2 *req,
 			      struct user_namespace *user_ns,		      	
@@ -326,9 +340,7 @@ int inet_diag_dump_one_icsk(struct inet_hashinfo *hashinfo, struct sk_buff *in_s
 	if (err)
 		goto out;
 
-	rep = nlmsg_new(sizeof(struct inet_diag_msg) +
-			sizeof(struct inet_diag_meminfo) +
-			sizeof(struct tcp_info) + 64, GFP_KERNEL);
+	rep = nlmsg_new(inet_sk_attr_size(), GFP_KERNEL);
 	if (!rep) {
 		err = -ENOMEM;
 		goto out;
diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c
index 787b3c294ce6..d9bc28ac5d1b 100644
--- a/net/ipv4/ip_forward.c
+++ b/net/ipv4/ip_forward.c
@@ -67,6 +67,7 @@ static int ip_forward_finish(struct sk_buff *skb)
 	if (unlikely(opt->optlen))
 		ip_forward_options(skb);
 
+	skb_sender_cpu_clear(skb);
 	return dst_output(skb);
 }
 
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index 2c8d98e728c0..145a50c4d566 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -659,27 +659,30 @@ EXPORT_SYMBOL(ip_defrag);
 struct sk_buff *ip_check_defrag(struct sk_buff *skb, u32 user)
 {
 	struct iphdr iph;
+	int netoff;
 	u32 len;
 
 	if (skb->protocol != htons(ETH_P_IP))
 		return skb;
 
-	if (skb_copy_bits(skb, 0, &iph, sizeof(iph)) < 0)
+	netoff = skb_network_offset(skb);
+
+	if (skb_copy_bits(skb, netoff, &iph, sizeof(iph)) < 0)
 		return skb;
 
 	if (iph.ihl < 5 || iph.version != 4)
 		return skb;
 
 	len = ntohs(iph.tot_len);
-	if (skb->len < len || len < (iph.ihl * 4))
+	if (skb->len < netoff + len || len < (iph.ihl * 4))
 		return skb;
 
 	if (ip_is_fragment(&iph)) {
 		skb = skb_share_check(skb, GFP_ATOMIC);
 		if (skb) {
-			if (!pskb_may_pull(skb, iph.ihl*4))
+			if (!pskb_may_pull(skb, netoff + iph.ihl * 4))
 				return skb;
-			if (pskb_trim_rcsum(skb, len))
+			if (pskb_trim_rcsum(skb, netoff + len))
 				return skb;
 			memset(IPCB(skb), 0, sizeof(struct inet_skb_parm));
 			if (ip_defrag(skb, user))
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 31d8c71986b4..5cd99271d3a6 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -432,17 +432,32 @@ void ip_local_error(struct sock *sk, int err, __be32 daddr, __be16 port, u32 inf
 		kfree_skb(skb);
 }
 
-static bool ipv4_pktinfo_prepare_errqueue(const struct sock *sk,
-					  const struct sk_buff *skb,
-					  int ee_origin)
+/* IPv4 supports cmsg on all imcp errors and some timestamps
+ *
+ * Timestamp code paths do not initialize the fields expected by cmsg:
+ * the PKTINFO fields in skb->cb[]. Fill those in here.
+ */
+static bool ipv4_datagram_support_cmsg(const struct sock *sk,
+				       struct sk_buff *skb,
+				       int ee_origin)
 {
-	struct in_pktinfo *info = PKTINFO_SKB_CB(skb);
+	struct in_pktinfo *info;
+
+	if (ee_origin == SO_EE_ORIGIN_ICMP)
+		return true;
 
-	if ((ee_origin != SO_EE_ORIGIN_TIMESTAMPING) ||
-	    (!(sk->sk_tsflags & SOF_TIMESTAMPING_OPT_CMSG)) ||
+	if (ee_origin == SO_EE_ORIGIN_LOCAL)
+		return false;
+
+	/* Support IP_PKTINFO on tstamp packets if requested, to correlate
+	 * timestamp with egress dev. Not possible for packets without dev
+	 * or without payload (SOF_TIMESTAMPING_OPT_TSONLY).
+	 */
+	if ((!(sk->sk_tsflags & SOF_TIMESTAMPING_OPT_CMSG)) ||
 	    (!skb->dev))
 		return false;
 
+	info = PKTINFO_SKB_CB(skb);
 	info->ipi_spec_dst.s_addr = ip_hdr(skb)->saddr;
 	info->ipi_ifindex = skb->dev->ifindex;
 	return true;
@@ -483,7 +498,7 @@ int ip_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len)
 
 	serr = SKB_EXT_ERR(skb);
 
-	if (sin && skb->len) {
+	if (sin && serr->port) {
 		sin->sin_family = AF_INET;
 		sin->sin_addr.s_addr = *(__be32 *)(skb_network_header(skb) +
 						   serr->addr_offset);
@@ -496,9 +511,7 @@ int ip_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len)
 	sin = &errhdr.offender;
 	memset(sin, 0, sizeof(*sin));
 
-	if (skb->len &&
-	    (serr->ee.ee_origin == SO_EE_ORIGIN_ICMP ||
-	     ipv4_pktinfo_prepare_errqueue(sk, skb, serr->ee.ee_origin))) {
+	if (ipv4_datagram_support_cmsg(sk, skb, serr->ee.ee_origin)) {
 		sin->sin_family = AF_INET;
 		sin->sin_addr.s_addr = ip_hdr(skb)->saddr;
 		if (inet_sk(sk)->cmsg_flags)
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index 99e810f84671..cf5e82f39d3b 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -272,9 +272,9 @@ static void trace_packet(const struct sk_buff *skb,
 		    &chainname, &comment, &rulenum) != 0)
 			break;
 
-	nf_log_packet(net, AF_INET, hook, skb, in, out, &trace_loginfo,
-		      "TRACE: %s:%s:%s:%u ",
-		      tablename, chainname, comment, rulenum);
+	nf_log_trace(net, AF_INET, hook, skb, in, out, &trace_loginfo,
+		     "TRACE: %s:%s:%s:%u ",
+		     tablename, chainname, comment, rulenum);
 }
 #endif
 
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index e9f66e1cda50..208d5439e59b 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -259,6 +259,9 @@ int ping_init_sock(struct sock *sk)
 	kgid_t low, high;
 	int ret = 0;
 
+	if (sk->sk_family == AF_INET6)
+		sk->sk_ipv6only = 1;
+
 	inet_get_ping_group_range_net(net, &low, &high);
 	if (gid_lte(low, group) && gid_lte(group, high))
 		return 0;
@@ -305,6 +308,11 @@ static int ping_check_bind_addr(struct sock *sk, struct inet_sock *isk,
 		if (addr_len < sizeof(*addr))
 			return -EINVAL;
 
+		if (addr->sin_family != AF_INET &&
+		    !(addr->sin_family == AF_UNSPEC &&
+		      addr->sin_addr.s_addr == htonl(INADDR_ANY)))
+			return -EAFNOSUPPORT;
+
 		pr_debug("ping_check_bind_addr(sk=%p,addr=%pI4,port=%d)\n",
 			 sk, &addr->sin_addr.s_addr, ntohs(addr->sin_port));
 
@@ -330,7 +338,7 @@ static int ping_check_bind_addr(struct sock *sk, struct inet_sock *isk,
 			return -EINVAL;
 
 		if (addr->sin6_family != AF_INET6)
-			return -EINVAL;
+			return -EAFNOSUPPORT;
 
 		pr_debug("ping_check_bind_addr(sk=%p,addr=%pI6c,port=%d)\n",
 			 sk, addr->sin6_addr.s6_addr, ntohs(addr->sin6_port));
@@ -716,7 +724,7 @@ static int ping_v4_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *m
 		if (msg->msg_namelen < sizeof(*usin))
 			return -EINVAL;
 		if (usin->sin_family != AF_INET)
-			return -EINVAL;
+			return -EAFNOSUPPORT;
 		daddr = usin->sin_addr.s_addr;
 		/* no remote port */
 	} else {
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 9d72a0fcd928..995a2259bcfc 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -835,17 +835,13 @@ static unsigned int tcp_xmit_size_goal(struct sock *sk, u32 mss_now,
 				       int large_allowed)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
-	u32 new_size_goal, size_goal, hlen;
+	u32 new_size_goal, size_goal;
 
 	if (!large_allowed || !sk_can_gso(sk))
 		return mss_now;
 
-	/* Maybe we should/could use sk->sk_prot->max_header here ? */
-	hlen = inet_csk(sk)->icsk_af_ops->net_header_len +
-	       inet_csk(sk)->icsk_ext_hdr_len +
-	       tp->tcp_header_len;
-
-	new_size_goal = sk->sk_gso_max_size - 1 - hlen;
+	/* Note : tcp_tso_autosize() will eventually split this later */
+	new_size_goal = sk->sk_gso_max_size - 1 - MAX_TCP_HEADER;
 	new_size_goal = tcp_bound_to_half_wnd(tp, new_size_goal);
 
 	/* We try hard to avoid divides here */
diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c
index d694088214cd..62856e185a93 100644
--- a/net/ipv4/tcp_cong.c
+++ b/net/ipv4/tcp_cong.c
@@ -378,6 +378,12 @@ EXPORT_SYMBOL_GPL(tcp_slow_start);
  */
 void tcp_cong_avoid_ai(struct tcp_sock *tp, u32 w, u32 acked)
 {
+	/* If credits accumulated at a higher w, apply them gently now. */
+	if (tp->snd_cwnd_cnt >= w) {
+		tp->snd_cwnd_cnt = 0;
+		tp->snd_cwnd++;
+	}
+
 	tp->snd_cwnd_cnt += acked;
 	if (tp->snd_cwnd_cnt >= w) {
 		u32 delta = tp->snd_cwnd_cnt / w;
diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c
index 4b276d1ed980..06d3d665a9fd 100644
--- a/net/ipv4/tcp_cubic.c
+++ b/net/ipv4/tcp_cubic.c
@@ -306,8 +306,10 @@ tcp_friendliness:
 		}
 	}
 
-	if (ca->cnt == 0)			/* cannot be zero */
-		ca->cnt = 1;
+	/* The maximum rate of cwnd increase CUBIC allows is 1 packet per
+	 * 2 packets ACKed, meaning cwnd grows at 1.5x per RTT.
+	 */
+	ca->cnt = max(ca->cnt, 2U);
 }
 
 static void bictcp_cong_avoid(struct sock *sk, u32 ack, u32 acked)
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index a2a796c5536b..1db253e36045 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2773,15 +2773,11 @@ void tcp_send_fin(struct sock *sk)
 	} else {
 		/* Socket is locked, keep trying until memory is available. */
 		for (;;) {
-			skb = alloc_skb_fclone(MAX_TCP_HEADER,
-					       sk->sk_allocation);
+			skb = sk_stream_alloc_skb(sk, 0, sk->sk_allocation);
 			if (skb)
 				break;
 			yield();
 		}
-
-		/* Reserve space for headers and prepare control bits. */
-		skb_reserve(skb, MAX_TCP_HEADER);
 		/* FIN eats a sequence byte, write_seq advanced by tcp_queue_skb(). */
 		tcp_init_nondata_skb(skb, tp->write_seq,
 				     TCPHDR_ACK | TCPHDR_FIN);
diff --git a/net/ipv4/xfrm4_output.c b/net/ipv4/xfrm4_output.c
index d5f6bd9a210a..dab73813cb92 100644
--- a/net/ipv4/xfrm4_output.c
+++ b/net/ipv4/xfrm4_output.c
@@ -63,6 +63,7 @@ int xfrm4_prepare_output(struct xfrm_state *x, struct sk_buff *skb)
 		return err;
 
 	IPCB(skb)->flags |= IPSKB_XFRM_TUNNEL_SIZE;
+	skb->protocol = htons(ETH_P_IP);
 
 	return x->outer_mode->output2(x, skb);
 }
@@ -71,7 +72,6 @@ EXPORT_SYMBOL(xfrm4_prepare_output);
 int xfrm4_output_finish(struct sk_buff *skb)
 {
 	memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
-	skb->protocol = htons(ETH_P_IP);
 
 #ifdef CONFIG_NETFILTER
 	IPCB(skb)->flags |= IPSKB_XFRM_TRANSFORMED;