Merge tag 'nfs-rdma-for-4.2' of git://git.linux-nfs.org/projects/anna/nfs-rdma

NFS: NFSoRDMA Client Changes

These patches continue to build up for improving the rsize and wsize that the
NFS client uses when talking over RDMA.  In addition, these patches also add
in scalability enhancements and other bugfixes.

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

* tag 'nfs-rdma-for-4.2' of git://git.linux-nfs.org/projects/anna/nfs-rdma: (142 commits)
  xprtrdma: Reduce per-transport MR allocation
  xprtrdma: Stack relief in fmr_op_map()
  xprtrdma: Split rb_lock
  xprtrdma: Remove rpcrdma_ia::ri_memreg_strategy
  xprtrdma: Remove ->ro_reset
  xprtrdma: Remove unused LOCAL_INV recovery logic
  xprtrdma: Acquire MRs in rpcrdma_register_external()
  xprtrdma: Introduce an FRMR recovery workqueue
  xprtrdma: Acquire FMRs in rpcrdma_fmr_register_external()
  xprtrdma: Introduce helpers for allocating MWs
  xprtrdma: Use ib_device pointer safely
  xprtrdma: Remove rr_func
  xprtrdma: Replace rpcrdma_rep::rr_buffer with rr_rxprt
  xprtrdma: Warn when there are orphaned IB objects
  ...

5 files changed, 22 insertions, 11 deletions

diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
index 421a80b09b62..30b544f025ac 100644
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@ -256,7 +256,8 @@ static int esp_output(struct xfrm_state *x, struct sk_buff *skb)
 	aead_givcrypt_set_crypt(req, sg, sg, clen, iv);
 	aead_givcrypt_set_assoc(req, asg, assoclen);
 	aead_givcrypt_set_giv(req, esph->enc_data,
-			      XFRM_SKB_CB(skb)->seq.output.low);
+			      XFRM_SKB_CB(skb)->seq.output.low +
+			      ((u64)XFRM_SKB_CB(skb)->seq.output.hi << 32));
 
 	ESP_SKB_CB(skb)->tmp = tmp;
 	err = crypto_aead_givencrypt(req);
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index 9f7269f3c54a..0c152087ca15 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -65,7 +65,6 @@ static int vti_input(struct sk_buff *skb, int nexthdr, __be32 spi,
 			goto drop;
 
 		XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = tunnel;
-		skb->mark = be32_to_cpu(tunnel->parms.i_key);
 
 		return xfrm_input(skb, nexthdr, spi, encap_type);
 	}
@@ -91,6 +90,8 @@ static int vti_rcv_cb(struct sk_buff *skb, int err)
 	struct pcpu_sw_netstats *tstats;
 	struct xfrm_state *x;
 	struct ip_tunnel *tunnel = XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4;
+	u32 orig_mark = skb->mark;
+	int ret;
 
 	if (!tunnel)
 		return 1;
@@ -107,7 +108,11 @@ static int vti_rcv_cb(struct sk_buff *skb, int err)
 	x = xfrm_input_state(skb);
 	family = x->inner_mode->afinfo->family;
 
-	if (!xfrm_policy_check(NULL, XFRM_POLICY_IN, skb, family))
+	skb->mark = be32_to_cpu(tunnel->parms.i_key);
+	ret = xfrm_policy_check(NULL, XFRM_POLICY_IN, skb, family);
+	skb->mark = orig_mark;
+
+	if (!ret)
 		return -EPERM;
 
 	skb_scrub_packet(skb, !net_eq(tunnel->net, dev_net(skb->dev)));
@@ -216,8 +221,6 @@ static netdev_tx_t vti_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	memset(&fl, 0, sizeof(fl));
 
-	skb->mark = be32_to_cpu(tunnel->parms.o_key);
-
 	switch (skb->protocol) {
 	case htons(ETH_P_IP):
 		xfrm_decode_session(skb, &fl, AF_INET);
@@ -233,6 +236,9 @@ static netdev_tx_t vti_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
 		return NETDEV_TX_OK;
 	}
 
+	/* override mark with tunnel output key */
+	fl.flowi_mark = be32_to_cpu(tunnel->parms.o_key);
+
 	return vti_xmit(skb, dev, &fl);
 }
 
diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c
index 7a5ae50c80c8..84be008c945c 100644
--- a/net/ipv4/tcp_cong.c
+++ b/net/ipv4/tcp_cong.c
@@ -187,6 +187,7 @@ static void tcp_reinit_congestion_control(struct sock *sk,
 
 	tcp_cleanup_congestion_control(sk);
 	icsk->icsk_ca_ops = ca;
+	icsk->icsk_ca_setsockopt = 1;
 
 	if (sk->sk_state != TCP_CLOSE && icsk->icsk_ca_ops->init)
 		icsk->icsk_ca_ops->init(sk);
@@ -335,8 +336,10 @@ int tcp_set_congestion_control(struct sock *sk, const char *name)
 	rcu_read_lock();
 	ca = __tcp_ca_find_autoload(name);
 	/* No change asking for existing value */
-	if (ca == icsk->icsk_ca_ops)
+	if (ca == icsk->icsk_ca_ops) {
+		icsk->icsk_ca_setsockopt = 1;
 		goto out;
+	}
 	if (!ca)
 		err = -ENOENT;
 	else if (!((ca->flags & TCP_CONG_NON_RESTRICTED) ||
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index b5732a54f2ad..17e7339ee5ca 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -420,7 +420,10 @@ void tcp_ca_openreq_child(struct sock *sk, const struct dst_entry *dst)
 		rcu_read_unlock();
 	}
 
-	if (!ca_got_dst && !try_module_get(icsk->icsk_ca_ops->owner))
+	/* If no valid choice made yet, assign current system default ca. */
+	if (!ca_got_dst &&
+	    (!icsk->icsk_ca_setsockopt ||
+	     !try_module_get(icsk->icsk_ca_ops->owner)))
 		tcp_assign_congestion_control(sk);
 
 	tcp_set_ca_state(sk, TCP_CA_Open);
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index d10b7e0112eb..1c92ea67baef 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1345,10 +1345,8 @@ csum_copy_err:
 	}
 	unlock_sock_fast(sk, slow);
 
-	if (noblock)
-		return -EAGAIN;
-
-	/* starting over for a new packet */
+	/* starting over for a new packet, but check if we need to yield */
+	cond_resched();
 	msg->msg_flags &= ~MSG_TRUNC;
 	goto try_again;
 }