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

Pull networking updates from David Miller:
 "Here is my initial pull request for the networking subsystem during
  this merge window:

   1) Support for ESN in AH (RFC 4302) from Fan Du.

   2) Add full kernel doc for ethtool command structures, from Ben
      Hutchings.

   3) Add BCM7xxx PHY driver, from Florian Fainelli.

   4) Export computed TCP rate information in netlink socket dumps, from
      Eric Dumazet.

   5) Allow IPSEC SA to be dumped partially using a filter, from Nicolas
      Dichtel.

   6) Convert many drivers to pci_enable_msix_range(), from Alexander
      Gordeev.

   7) Record SKB timestamps more efficiently, from Eric Dumazet.

   8) Switch to microsecond resolution for TCP round trip times, also
      from Eric Dumazet.

   9) Clean up and fix 6lowpan fragmentation handling by making use of
      the existing inet_frag api for it's implementation.

  10) Add TX grant mapping to xen-netback driver, from Zoltan Kiss.

  11) Auto size SKB lengths when composing netlink messages based upon
      past message sizes used, from Eric Dumazet.

  12) qdisc dumps can take a long time, add a cond_resched(), From Eric
      Dumazet.

  13) Sanitize netpoll core and drivers wrt.  SKB handling semantics.
      Get rid of never-used-in-tree netpoll RX handling.  From Eric W
      Biederman.

  14) Support inter-address-family and namespace changing in VTI tunnel
      driver(s).  From Steffen Klassert.

  15) Add Altera TSE driver, from Vince Bridgers.

  16) Optimizing csum_replace2() so that it doesn't adjust the checksum
      by checksumming the entire header, from Eric Dumazet.

  17) Expand BPF internal implementation for faster interpreting, more
      direct translations into JIT'd code, and much cleaner uses of BPF
      filtering in non-socket ocntexts.  From Daniel Borkmann and Alexei
      Starovoitov"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1976 commits)
  netpoll: Use skb_irq_freeable to make zap_completion_queue safe.
  net: Add a test to see if a skb is freeable in irq context
  qlcnic: Fix build failure due to undefined reference to `vxlan_get_rx_port'
  net: ptp: move PTP classifier in its own file
  net: sxgbe: make "core_ops" static
  net: sxgbe: fix logical vs bitwise operation
  net: sxgbe: sxgbe_mdio_register() frees the bus
  Call efx_set_channels() before efx->type->dimension_resources()
  xen-netback: disable rogue vif in kthread context
  net/mlx4: Set proper build dependancy with vxlan
  be2net: fix build dependency on VxLAN
  mac802154: make csma/cca parameters per-wpan
  mac802154: allow only one WPAN to be up at any given time
  net: filter: minor: fix kdoc in __sk_run_filter
  netlink: don't compare the nul-termination in nla_strcmp
  can: c_can: Avoid led toggling for every packet.
  can: c_can: Simplify TX interrupt cleanup
  can: c_can: Store dlc private
  can: c_can: Reduce register access
  can: c_can: Make the code readable
  ...

1 files changed, 76 insertions, 90 deletions

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 90b96a11b974..30c7d35dd862 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -3300,6 +3300,32 @@ __skb_to_sgvec(struct sk_buff *skb, struct scatterlist *sg, int offset, int len)
 	return elt;
 }
 
+/* As compared with skb_to_sgvec, skb_to_sgvec_nomark only map skb to given
+ * sglist without mark the sg which contain last skb data as the end.
+ * So the caller can mannipulate sg list as will when padding new data after
+ * the first call without calling sg_unmark_end to expend sg list.
+ *
+ * Scenario to use skb_to_sgvec_nomark:
+ * 1. sg_init_table
+ * 2. skb_to_sgvec_nomark(payload1)
+ * 3. skb_to_sgvec_nomark(payload2)
+ *
+ * This is equivalent to:
+ * 1. sg_init_table
+ * 2. skb_to_sgvec(payload1)
+ * 3. sg_unmark_end
+ * 4. skb_to_sgvec(payload2)
+ *
+ * When mapping mutilple payload conditionally, skb_to_sgvec_nomark
+ * is more preferable.
+ */
+int skb_to_sgvec_nomark(struct sk_buff *skb, struct scatterlist *sg,
+			int offset, int len)
+{
+	return __skb_to_sgvec(skb, sg, offset, len);
+}
+EXPORT_SYMBOL_GPL(skb_to_sgvec_nomark);
+
 int skb_to_sgvec(struct sk_buff *skb, struct scatterlist *sg, int offset, int len)
 {
 	int nsg = __skb_to_sgvec(skb, sg, offset, len);
@@ -3562,15 +3588,47 @@ static int skb_maybe_pull_tail(struct sk_buff *skb, unsigned int len,
 	return 0;
 }
 
+#define MAX_TCP_HDR_LEN (15 * 4)
+
+static __sum16 *skb_checksum_setup_ip(struct sk_buff *skb,
+				      typeof(IPPROTO_IP) proto,
+				      unsigned int off)
+{
+	switch (proto) {
+		int err;
+
+	case IPPROTO_TCP:
+		err = skb_maybe_pull_tail(skb, off + sizeof(struct tcphdr),
+					  off + MAX_TCP_HDR_LEN);
+		if (!err && !skb_partial_csum_set(skb, off,
+						  offsetof(struct tcphdr,
+							   check)))
+			err = -EPROTO;
+		return err ? ERR_PTR(err) : &tcp_hdr(skb)->check;
+
+	case IPPROTO_UDP:
+		err = skb_maybe_pull_tail(skb, off + sizeof(struct udphdr),
+					  off + sizeof(struct udphdr));
+		if (!err && !skb_partial_csum_set(skb, off,
+						  offsetof(struct udphdr,
+							   check)))
+			err = -EPROTO;
+		return err ? ERR_PTR(err) : &udp_hdr(skb)->check;
+	}
+
+	return ERR_PTR(-EPROTO);
+}
+
 /* This value should be large enough to cover a tagged ethernet header plus
  * maximally sized IP and TCP or UDP headers.
  */
 #define MAX_IP_HDR_LEN 128
 
-static int skb_checksum_setup_ip(struct sk_buff *skb, bool recalculate)
+static int skb_checksum_setup_ipv4(struct sk_buff *skb, bool recalculate)
 {
 	unsigned int off;
 	bool fragment;
+	__sum16 *csum;
 	int err;
 
 	fragment = false;
@@ -3591,51 +3649,15 @@ static int skb_checksum_setup_ip(struct sk_buff *skb, bool recalculate)
 	if (fragment)
 		goto out;
 
-	switch (ip_hdr(skb)->protocol) {
-	case IPPROTO_TCP:
-		err = skb_maybe_pull_tail(skb,
-					  off + sizeof(struct tcphdr),
-					  MAX_IP_HDR_LEN);
-		if (err < 0)
-			goto out;
-
-		if (!skb_partial_csum_set(skb, off,
-					  offsetof(struct tcphdr, check))) {
-			err = -EPROTO;
-			goto out;
-		}
-
-		if (recalculate)
-			tcp_hdr(skb)->check =
-				~csum_tcpudp_magic(ip_hdr(skb)->saddr,
-						   ip_hdr(skb)->daddr,
-						   skb->len - off,
-						   IPPROTO_TCP, 0);
-		break;
-	case IPPROTO_UDP:
-		err = skb_maybe_pull_tail(skb,
-					  off + sizeof(struct udphdr),
-					  MAX_IP_HDR_LEN);
-		if (err < 0)
-			goto out;
-
-		if (!skb_partial_csum_set(skb, off,
-					  offsetof(struct udphdr, check))) {
-			err = -EPROTO;
-			goto out;
-		}
-
-		if (recalculate)
-			udp_hdr(skb)->check =
-				~csum_tcpudp_magic(ip_hdr(skb)->saddr,
-						   ip_hdr(skb)->daddr,
-						   skb->len - off,
-						   IPPROTO_UDP, 0);
-		break;
-	default:
-		goto out;
-	}
+	csum = skb_checksum_setup_ip(skb, ip_hdr(skb)->protocol, off);
+	if (IS_ERR(csum))
+		return PTR_ERR(csum);
 
+	if (recalculate)
+		*csum = ~csum_tcpudp_magic(ip_hdr(skb)->saddr,
+					   ip_hdr(skb)->daddr,
+					   skb->len - off,
+					   ip_hdr(skb)->protocol, 0);
 	err = 0;
 
 out:
@@ -3658,6 +3680,7 @@ static int skb_checksum_setup_ipv6(struct sk_buff *skb, bool recalculate)
 	unsigned int len;
 	bool fragment;
 	bool done;
+	__sum16 *csum;
 
 	fragment = false;
 	done = false;
@@ -3735,51 +3758,14 @@ static int skb_checksum_setup_ipv6(struct sk_buff *skb, bool recalculate)
 	if (!done || fragment)
 		goto out;
 
-	switch (nexthdr) {
-	case IPPROTO_TCP:
-		err = skb_maybe_pull_tail(skb,
-					  off + sizeof(struct tcphdr),
-					  MAX_IPV6_HDR_LEN);
-		if (err < 0)
-			goto out;
-
-		if (!skb_partial_csum_set(skb, off,
-					  offsetof(struct tcphdr, check))) {
-			err = -EPROTO;
-			goto out;
-		}
-
-		if (recalculate)
-			tcp_hdr(skb)->check =
-				~csum_ipv6_magic(&ipv6_hdr(skb)->saddr,
-						 &ipv6_hdr(skb)->daddr,
-						 skb->len - off,
-						 IPPROTO_TCP, 0);
-		break;
-	case IPPROTO_UDP:
-		err = skb_maybe_pull_tail(skb,
-					  off + sizeof(struct udphdr),
-					  MAX_IPV6_HDR_LEN);
-		if (err < 0)
-			goto out;
-
-		if (!skb_partial_csum_set(skb, off,
-					  offsetof(struct udphdr, check))) {
-			err = -EPROTO;
-			goto out;
-		}
-
-		if (recalculate)
-			udp_hdr(skb)->check =
-				~csum_ipv6_magic(&ipv6_hdr(skb)->saddr,
-						 &ipv6_hdr(skb)->daddr,
-						 skb->len - off,
-						 IPPROTO_UDP, 0);
-		break;
-	default:
-		goto out;
-	}
+	csum = skb_checksum_setup_ip(skb, nexthdr, off);
+	if (IS_ERR(csum))
+		return PTR_ERR(csum);
 
+	if (recalculate)
+		*csum = ~csum_ipv6_magic(&ipv6_hdr(skb)->saddr,
+					 &ipv6_hdr(skb)->daddr,
+					 skb->len - off, nexthdr, 0);
 	err = 0;
 
 out:
@@ -3797,7 +3783,7 @@ int skb_checksum_setup(struct sk_buff *skb, bool recalculate)
 
 	switch (skb->protocol) {
 	case htons(ETH_P_IP):
-		err = skb_checksum_setup_ip(skb, recalculate);
+		err = skb_checksum_setup_ipv4(skb, recalculate);
 		break;
 
 	case htons(ETH_P_IPV6):