Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

Pull networking fixes from David Miller:

 1) Fix BPF filter validation of netlink attribute accesses, from
    Mathias Kruase.

 2) Netfilter conntrack generation seqcount not initialized properly,
    from Andrey Vagin.

 3) Fix comparison mask computation on big-endian in nft_cmp_fast(),
    from Patrick McHardy.

 4) Properly limit MTU over ipv6, from Eric Dumazet.

 5) Fix seccomp system call argument population on 32-bit, from Daniel
    Borkmann.

 6) skb_network_protocol() should not use hard-coded ETH_HLEN, instead
    skb->mac_len needs to be used.  From Vlad Yasevich.

 7) We have several cases of using socket based communications to
    implement a tunnel.  For example, some tunnels are encapsulations
    over UDP so we use an internal kernel UDP socket to do the
    transmits.

    These tunnels should behave just like other software devices and
    pass the packets on down to the next layer.

    Most importantly we want the top-level socket (eg TCP) that created
    the traffic to be charged for the SKB memory.

    However, once you get into the IP output path, we have code that
    assumed that whatever was attached to skb->sk is an IP socket.

    To keep the top-level socket being charged for the SKB memory,
    whilst satisfying the needs of the IP output path, we now pass in an
    explicit 'sk' argument.

    From Eric Dumazet.

 8) ping_init_sock() leaks group info, from Xiaoming Wang.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (33 commits)
  cxgb4: use the correct max size for firmware flash
  qlcnic: Fix MSI-X initialization code
  ip6_gre: don't allow to remove the fb_tunnel_dev
  ipv4: add a sock pointer to dst->output() path.
  ipv4: add a sock pointer to ip_queue_xmit()
  driver/net: cosa driver uses udelay incorrectly
  at86rf230: fix __at86rf230_read_subreg function
  at86rf230: remove check if AVDD settled
  net: cadence: Add architecture dependencies
  net: Start with correct mac_len in skb_network_protocol
  Revert "net: sctp: Fix a_rwnd/rwnd management to reflect real state of the receiver's buffer"
  cxgb4: Save the correct mac addr for hw-loopback connections in the L2T
  net: filter: seccomp: fix wrong decoding of BPF_S_ANC_SECCOMP_LD_W
  seccomp: fix populating a0-a5 syscall args in 32-bit x86 BPF
  qlcnic: Do not disable SR-IOV when VFs are assigned to VMs
  qlcnic: Fix QLogic application/driver interface for virtual NIC configuration
  qlcnic: Fix PVID configuration on eSwitch port.
  qlcnic: Fix max ring count calculation
  qlcnic: Fix to send INIT_NIC_FUNC as first mailbox.
  qlcnic: Fix panic due to uninitialzed delayed_work struct in use.
  ...

1 files changed, 65 insertions, 17 deletions

diff --git a/net/sctp/associola.c b/net/sctp/associola.c
index 4f6d6f9d127..39579c3e0d1 100644
--- a/net/sctp/associola.c
+++ b/net/sctp/associola.c
@@ -1395,35 +1395,44 @@ static inline bool sctp_peer_needs_update(struct sctp_association *asoc)
 	return false;
 }
 
-/* Update asoc's rwnd for the approximated state in the buffer,
- * and check whether SACK needs to be sent.
- */
-void sctp_assoc_rwnd_update(struct sctp_association *asoc, bool update_peer)
+/* Increase asoc's rwnd by len and send any window update SACK if needed. */
+void sctp_assoc_rwnd_increase(struct sctp_association *asoc, unsigned int len)
 {
-	int rx_count;
 	struct sctp_chunk *sack;
 	struct timer_list *timer;
 
-	if (asoc->ep->rcvbuf_policy)
-		rx_count = atomic_read(&asoc->rmem_alloc);
-	else
-		rx_count = atomic_read(&asoc->base.sk->sk_rmem_alloc);
+	if (asoc->rwnd_over) {
+		if (asoc->rwnd_over >= len) {
+			asoc->rwnd_over -= len;
+		} else {
+			asoc->rwnd += (len - asoc->rwnd_over);
+			asoc->rwnd_over = 0;
+		}
+	} else {
+		asoc->rwnd += len;
+	}
 
-	if ((asoc->base.sk->sk_rcvbuf - rx_count) > 0)
-		asoc->rwnd = (asoc->base.sk->sk_rcvbuf - rx_count) >> 1;
-	else
-		asoc->rwnd = 0;
+	/* If we had window pressure, start recovering it
+	 * once our rwnd had reached the accumulated pressure
+	 * threshold.  The idea is to recover slowly, but up
+	 * to the initial advertised window.
+	 */
+	if (asoc->rwnd_press && asoc->rwnd >= asoc->rwnd_press) {
+		int change = min(asoc->pathmtu, asoc->rwnd_press);
+		asoc->rwnd += change;
+		asoc->rwnd_press -= change;
+	}
 
-	pr_debug("%s: asoc:%p rwnd=%u, rx_count=%d, sk_rcvbuf=%d\n",
-		 __func__, asoc, asoc->rwnd, rx_count,
-		 asoc->base.sk->sk_rcvbuf);
+	pr_debug("%s: asoc:%p rwnd increased by %d to (%u, %u) - %u\n",
+		 __func__, asoc, len, asoc->rwnd, asoc->rwnd_over,
+		 asoc->a_rwnd);
 
 	/* Send a window update SACK if the rwnd has increased by at least the
 	 * minimum of the association's PMTU and half of the receive buffer.
 	 * The algorithm used is similar to the one described in
 	 * Section 4.2.3.3 of RFC 1122.
 	 */
-	if (update_peer && sctp_peer_needs_update(asoc)) {
+	if (sctp_peer_needs_update(asoc)) {
 		asoc->a_rwnd = asoc->rwnd;
 
 		pr_debug("%s: sending window update SACK- asoc:%p rwnd:%u "
@@ -1445,6 +1454,45 @@ void sctp_assoc_rwnd_update(struct sctp_association *asoc, bool update_peer)
 	}
 }
 
+/* Decrease asoc's rwnd by len. */
+void sctp_assoc_rwnd_decrease(struct sctp_association *asoc, unsigned int len)
+{
+	int rx_count;
+	int over = 0;
+
+	if (unlikely(!asoc->rwnd || asoc->rwnd_over))
+		pr_debug("%s: association:%p has asoc->rwnd:%u, "
+			 "asoc->rwnd_over:%u!\n", __func__, asoc,
+			 asoc->rwnd, asoc->rwnd_over);
+
+	if (asoc->ep->rcvbuf_policy)
+		rx_count = atomic_read(&asoc->rmem_alloc);
+	else
+		rx_count = atomic_read(&asoc->base.sk->sk_rmem_alloc);
+
+	/* If we've reached or overflowed our receive buffer, announce
+	 * a 0 rwnd if rwnd would still be positive.  Store the
+	 * the potential pressure overflow so that the window can be restored
+	 * back to original value.
+	 */
+	if (rx_count >= asoc->base.sk->sk_rcvbuf)
+		over = 1;
+
+	if (asoc->rwnd >= len) {
+		asoc->rwnd -= len;
+		if (over) {
+			asoc->rwnd_press += asoc->rwnd;
+			asoc->rwnd = 0;
+		}
+	} else {
+		asoc->rwnd_over = len - asoc->rwnd;
+		asoc->rwnd = 0;
+	}
+
+	pr_debug("%s: asoc:%p rwnd decreased by %d to (%u, %u, %u)\n",
+		 __func__, asoc, len, asoc->rwnd, asoc->rwnd_over,
+		 asoc->rwnd_press);
+}
 
 /* Build the bind address list for the association based on info from the
  * local endpoint and the remote peer.