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

Pull networking updates from David Miller:
 "Another merge window, another set of networking changes.  I've heard
  rumblings that the lightweight tunnels infrastructure has been voted
  networking change of the year.  But what do I know?

   1) Add conntrack support to openvswitch, from Joe Stringer.

   2) Initial support for VRF (Virtual Routing and Forwarding), which
      allows the segmentation of routing paths without using multiple
      devices.  There are some semantic kinks to work out still, but
      this is a reasonably strong foundation.  From David Ahern.

   3) Remove spinlock fro act_bpf fast path, from Alexei Starovoitov.

   4) Ignore route nexthops with a link down state in ipv6, just like
      ipv4.  From Andy Gospodarek.

   5) Remove spinlock from fast path of act_gact and act_mirred, from
      Eric Dumazet.

   6) Document the DSA layer, from Florian Fainelli.

   7) Add netconsole support to bcmgenet, systemport, and DSA.  Also
      from Florian Fainelli.

   8) Add Mellanox Switch Driver and core infrastructure, from Jiri
      Pirko.

   9) Add support for "light weight tunnels", which allow for
      encapsulation and decapsulation without bearing the overhead of a
      full blown netdevice.  From Thomas Graf, Jiri Benc, and a cast of
      others.

  10) Add Identifier Locator Addressing support for ipv6, from Tom
      Herbert.

  11) Support fragmented SKBs in iwlwifi, from Johannes Berg.

  12) Allow perf PMUs to be accessed from eBPF programs, from Kaixu Xia.

  13) Add BQL support to 3c59x driver, from Loganaden Velvindron.

  14) Stop using a zero TX queue length to mean that a device shouldn't
      have a qdisc attached, use an explicit flag instead.  From Phil
      Sutter.

  15) Use generic geneve netdevice infrastructure in openvswitch, from
      Pravin B Shelar.

  16) Add infrastructure to avoid re-forwarding a packet in software
      that was already forwarded by a hardware switch.  From Scott
      Feldman.

  17) Allow AF_PACKET fanout function to be implemented in a bpf
      program, from Willem de Bruijn"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1458 commits)
  netfilter: nf_conntrack: make nf_ct_zone_dflt built-in
  netfilter: nf_dup{4, 6}: fix build error when nf_conntrack disabled
  net: fec: clear receive interrupts before processing a packet
  ipv6: fix exthdrs offload registration in out_rt path
  xen-netback: add support for multicast control
  bgmac: Update fixed_phy_register()
  sock, diag: fix panic in sock_diag_put_filterinfo
  flow_dissector: Use 'const' where possible.
  flow_dissector: Fix function argument ordering dependency
  ixgbe: Resolve "initialized field overwritten" warnings
  ixgbe: Remove bimodal SR-IOV disabling
  ixgbe: Add support for reporting 2.5G link speed
  ixgbe: fix bounds checking in ixgbe_setup_tc for 82598
  ixgbe: support for ethtool set_rxfh
  ixgbe: Avoid needless PHY access on copper phys
  ixgbe: cleanup to use cached mask value
  ixgbe: Remove second instance of lan_id variable
  ixgbe: use kzalloc for allocating one thing
  flow: Move __get_hash_from_flowi{4,6} into flow_dissector.c
  ixgbe: Remove unused PCI bus types
  ...

4 files changed, 44 insertions, 4 deletions

diff --git a/arch/arm/boot/dts/am33xx.dtsi b/arch/arm/boot/dts/am33xx.dtsi
index 9117c1a1a4e2..d23e2524d694 100644
--- a/arch/arm/boot/dts/am33xx.dtsi
+++ b/arch/arm/boot/dts/am33xx.dtsi
@@ -717,7 +717,7 @@
 		};
 
 		mac: ethernet@4a100000 {
-			compatible = "ti,cpsw";
+			compatible = "ti,am335x-cpsw","ti,cpsw";
 			ti,hwmods = "cpgmac0";
 			clocks = <&cpsw_125mhz_gclk>, <&cpsw_cpts_rft_clk>;
 			clock-names = "fck", "cpts";
diff --git a/arch/arm/boot/dts/dra7.dtsi b/arch/arm/boot/dts/dra7.dtsi
index a0d3d4bfe9cb..5d65db9ebc2b 100644
--- a/arch/arm/boot/dts/dra7.dtsi
+++ b/arch/arm/boot/dts/dra7.dtsi
@@ -1418,7 +1418,7 @@
 		};
 
 		mac: ethernet@4a100000 {
-			compatible = "ti,cpsw";
+			compatible = "ti,dra7-cpsw","ti,cpsw";
 			ti,hwmods = "gmac";
 			clocks = <&dpll_gmac_ck>, <&gmac_gmii_ref_clk_div>;
 			clock-names = "fck", "cpts";
diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c
index c011e2296cb1..876060bcceeb 100644
--- a/arch/arm/net/bpf_jit_32.c
+++ b/arch/arm/net/bpf_jit_32.c
@@ -857,7 +857,9 @@ b_epilogue:
 			emit(ARM_LDR_I(r_A, r_scratch, off), ctx);
 			break;
 		case BPF_ANC | SKF_AD_IFINDEX:
+		case BPF_ANC | SKF_AD_HATYPE:
 			/* A = skb->dev->ifindex */
+			/* A = skb->dev->type */
 			ctx->seen |= SEEN_SKB;
 			off = offsetof(struct sk_buff, dev);
 			emit(ARM_LDR_I(r_scratch, r_skb, off), ctx);
@@ -867,8 +869,24 @@ b_epilogue:
 
 			BUILD_BUG_ON(FIELD_SIZEOF(struct net_device,
 						  ifindex) != 4);
-			off = offsetof(struct net_device, ifindex);
-			emit(ARM_LDR_I(r_A, r_scratch, off), ctx);
+			BUILD_BUG_ON(FIELD_SIZEOF(struct net_device,
+						  type) != 2);
+
+			if (code == (BPF_ANC | SKF_AD_IFINDEX)) {
+				off = offsetof(struct net_device, ifindex);
+				emit(ARM_LDR_I(r_A, r_scratch, off), ctx);
+			} else {
+				/*
+				 * offset of field "type" in "struct
+				 * net_device" is above what can be
+				 * used in the ldrh rd, [rn, #imm]
+				 * instruction, so load the offset in
+				 * a register and use ldrh rd, [rn, rm]
+				 */
+				off = offsetof(struct net_device, type);
+				emit_mov_i(ARM_R3, off, ctx);
+				emit(ARM_LDRH_R(r_A, r_scratch, ARM_R3), ctx);
+			}
 			break;
 		case BPF_ANC | SKF_AD_MARK:
 			ctx->seen |= SEEN_SKB;
@@ -895,6 +913,17 @@ b_epilogue:
 				OP_IMM3(ARM_AND, r_A, r_A, 0x1, ctx);
 			}
 			break;
+		case BPF_ANC | SKF_AD_PKTTYPE:
+			ctx->seen |= SEEN_SKB;
+			BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff,
+						  __pkt_type_offset[0]) != 1);
+			off = PKT_TYPE_OFFSET();
+			emit(ARM_LDRB_I(r_A, r_skb, off), ctx);
+			emit(ARM_AND_I(r_A, r_A, PKT_TYPE_MAX), ctx);
+#ifdef __BIG_ENDIAN_BITFIELD
+			emit(ARM_LSR_I(r_A, r_A, 5), ctx);
+#endif
+			break;
 		case BPF_ANC | SKF_AD_QUEUE:
 			ctx->seen |= SEEN_SKB;
 			BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff,
@@ -904,6 +933,14 @@ b_epilogue:
 			off = offsetof(struct sk_buff, queue_mapping);
 			emit(ARM_LDRH_I(r_A, r_skb, off), ctx);
 			break;
+		case BPF_ANC | SKF_AD_PAY_OFFSET:
+			ctx->seen |= SEEN_SKB | SEEN_CALL;
+
+			emit(ARM_MOV_R(ARM_R0, r_skb), ctx);
+			emit_mov_i(ARM_R3, (unsigned int)skb_get_poff, ctx);
+			emit_blx_r(ARM_R3, ctx);
+			emit(ARM_MOV_R(r_A, ARM_R0), ctx);
+			break;
 		case BPF_LDX | BPF_W | BPF_ABS:
 			/*
 			 * load a 32bit word from struct seccomp_data.
diff --git a/arch/arm/net/bpf_jit_32.h b/arch/arm/net/bpf_jit_32.h
index b2d7d92859d3..4b17d5ab652a 100644
--- a/arch/arm/net/bpf_jit_32.h
+++ b/arch/arm/net/bpf_jit_32.h
@@ -74,6 +74,7 @@
 #define ARM_INST_LDRB_I		0x05d00000
 #define ARM_INST_LDRB_R		0x07d00000
 #define ARM_INST_LDRH_I		0x01d000b0
+#define ARM_INST_LDRH_R		0x019000b0
 #define ARM_INST_LDR_I		0x05900000
 
 #define ARM_INST_LDM		0x08900000
@@ -160,6 +161,8 @@
 				 | (rm))
 #define ARM_LDRH_I(rt, rn, off)	(ARM_INST_LDRH_I | (rt) << 12 | (rn) << 16 \
 				 | (((off) & 0xf0) << 4) | ((off) & 0xf))
+#define ARM_LDRH_R(rt, rn, rm)	(ARM_INST_LDRH_R | (rt) << 12 | (rn) << 16 \
+				 | (rm))
 
 #define ARM_LDM(rn, regs)	(ARM_INST_LDM | (rn) << 16 | (regs))