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

Pull networking updates from David Miller:
 "Most notable changes in here:

   1) By far the biggest accomplishment, thanks to a large range of
      contributors, is the addition of multi-send for transmit.  This is
      the result of discussions back in Chicago, and the hard work of
      several individuals.

      Now, when the ->ndo_start_xmit() method of a driver sees
      skb->xmit_more as true, it can choose to defer the doorbell
      telling the driver to start processing the new TX queue entires.

      skb->xmit_more means that the generic networking is guaranteed to
      call the driver immediately with another SKB to send.

      There is logic added to the qdisc layer to dequeue multiple
      packets at a time, and the handling mis-predicted offloads in
      software is now done with no locks held.

      Finally, pktgen is extended to have a "burst" parameter that can
      be used to test a multi-send implementation.

      Several drivers have xmit_more support: i40e, igb, ixgbe, mlx4,
      virtio_net

      Adding support is almost trivial, so export more drivers to
      support this optimization soon.

      I want to thank, in no particular or implied order, Jesper
      Dangaard Brouer, Eric Dumazet, Alexander Duyck, Tom Herbert, Jamal
      Hadi Salim, John Fastabend, Florian Westphal, Daniel Borkmann,
      David Tat, Hannes Frederic Sowa, and Rusty Russell.

   2) PTP and timestamping support in bnx2x, from Michal Kalderon.

   3) Allow adjusting the rx_copybreak threshold for a driver via
      ethtool, and add rx_copybreak support to enic driver.  From
      Govindarajulu Varadarajan.

   4) Significant enhancements to the generic PHY layer and the bcm7xxx
      driver in particular (EEE support, auto power down, etc.) from
      Florian Fainelli.

   5) Allow raw buffers to be used for flow dissection, allowing drivers
      to determine the optimal "linear pull" size for devices that DMA
      into pools of pages.  The objective is to get exactly the
      necessary amount of headers into the linear SKB area pre-pulled,
      but no more.  The new interface drivers use is eth_get_headlen().
      From WANG Cong, with driver conversions (several had their own
      by-hand duplicated implementations) by Alexander Duyck and Eric
      Dumazet.

   6) Support checksumming more smoothly and efficiently for
      encapsulations, and add "foo over UDP" facility.  From Tom
      Herbert.

   7) Add Broadcom SF2 switch driver to DSA layer, from Florian
      Fainelli.

   8) eBPF now can load programs via a system call and has an extensive
      testsuite.  Alexei Starovoitov and Daniel Borkmann.

   9) Major overhaul of the packet scheduler to use RCU in several major
      areas such as the classifiers and rate estimators.  From John
      Fastabend.

  10) Add driver for Intel FM10000 Ethernet Switch, from Alexander
      Duyck.

  11) Rearrange TCP_SKB_CB() to reduce cache line misses, from Eric
      Dumazet.

  12) Add Datacenter TCP congestion control algorithm support, From
      Florian Westphal.

  13) Reorganize sk_buff so that __copy_skb_header() is significantly
      faster.  From Eric Dumazet"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1558 commits)
  netlabel: directly return netlbl_unlabel_genl_init()
  net: add netdev_txq_bql_{enqueue, complete}_prefetchw() helpers
  net: description of dma_cookie cause make xmldocs warning
  cxgb4: clean up a type issue
  cxgb4: potential shift wrapping bug
  i40e: skb->xmit_more support
  net: fs_enet: Add NAPI TX
  net: fs_enet: Remove non NAPI RX
  r8169:add support for RTL8168EP
  net_sched: copy exts->type in tcf_exts_change()
  wimax: convert printk to pr_foo()
  af_unix: remove 0 assignment on static
  ipv6: Do not warn for informational ICMP messages, regardless of type.
  Update Intel Ethernet Driver maintainers list
  bridge: Save frag_max_size between PRE_ROUTING and POST_ROUTING
  tipc: fix bug in multicast congestion handling
  net: better IFF_XMIT_DST_RELEASE support
  net/mlx4_en: remove NETDEV_TX_BUSY
  3c59x: fix bad split of cpu_to_le32(pci_map_single())
  net: bcmgenet: fix Tx ring priority programming
  ...

10 files changed, 134 insertions, 9 deletions

diff --git a/arch/arm/boot/dts/am33xx.dtsi b/arch/arm/boot/dts/am33xx.dtsi
index abe530f70296..831810583823 100644
--- a/arch/arm/boot/dts/am33xx.dtsi
+++ b/arch/arm/boot/dts/am33xx.dtsi
@@ -132,6 +132,11 @@
 			};
 		};
 
+		cm: syscon@44e10000 {
+			compatible = "ti,am33xx-controlmodule", "syscon";
+			reg = <0x44e10000 0x800>;
+		};
+
 		intc: interrupt-controller@48200000 {
 			compatible = "ti,am33xx-intc";
 			interrupt-controller;
@@ -699,6 +704,7 @@
 			 */
 			interrupts = <40 41 42 43>;
 			ranges;
+			syscon = <&cm>;
 			status = "disabled";
 
 			davinci_mdio: mdio@4a101000 {
diff --git a/arch/arm/boot/dts/berlin2q-marvell-dmp.dts b/arch/arm/boot/dts/berlin2q-marvell-dmp.dts
index a357ce02a64e..ea1f99b8eed6 100644
--- a/arch/arm/boot/dts/berlin2q-marvell-dmp.dts
+++ b/arch/arm/boot/dts/berlin2q-marvell-dmp.dts
@@ -45,3 +45,7 @@
 &uart0 {
 	status = "okay";
 };
+
+&eth0 {
+	status = "okay";
+};
diff --git a/arch/arm/boot/dts/berlin2q.dtsi b/arch/arm/boot/dts/berlin2q.dtsi
index 400c40fceccc..891d56b03922 100644
--- a/arch/arm/boot/dts/berlin2q.dtsi
+++ b/arch/arm/boot/dts/berlin2q.dtsi
@@ -114,6 +114,23 @@
 			#interrupt-cells = <3>;
 		};
 
+		eth0: ethernet@b90000 {
+			compatible = "marvell,pxa168-eth";
+			reg = <0xb90000 0x10000>;
+			clocks = <&chip CLKID_GETH0>;
+			interrupts = <GIC_SPI 24 IRQ_TYPE_LEVEL_HIGH>;
+			/* set by bootloader */
+			local-mac-address = [00 00 00 00 00 00];
+			#address-cells = <1>;
+			#size-cells = <0>;
+			phy-handle = <&ethphy0>;
+			status = "disabled";
+
+			ethphy0: ethernet-phy@0 {
+				reg = <0>;
+			};
+		};
+
 		cpu-ctrl@dd0000 {
 			compatible = "marvell,berlin-cpu-ctrl";
 			reg = <0xdd0000 0x10000>;
diff --git a/arch/arm/boot/dts/imx6sx.dtsi b/arch/arm/boot/dts/imx6sx.dtsi
index 888dd767a0b3..f3e88c03b1e4 100644
--- a/arch/arm/boot/dts/imx6sx.dtsi
+++ b/arch/arm/boot/dts/imx6sx.dtsi
@@ -779,6 +779,8 @@
 					 <&clks IMX6SX_CLK_ENET_PTP>;
 				clock-names = "ipg", "ahb", "ptp",
 					      "enet_clk_ref", "enet_out";
+				fsl,num-tx-queues=<3>;
+				fsl,num-rx-queues=<3>;
 				status = "disabled";
                         };
 
diff --git a/arch/arm/boot/dts/rk3188-radxarock.dts b/arch/arm/boot/dts/rk3188-radxarock.dts
index 39f66e349445..15910c9ddbc7 100644
--- a/arch/arm/boot/dts/rk3188-radxarock.dts
+++ b/arch/arm/boot/dts/rk3188-radxarock.dts
@@ -102,6 +102,22 @@
 	};
 };
 
+&emac {
+	status = "okay";
+
+	pinctrl-names = "default";
+	pinctrl-0 = <&emac_xfer>, <&emac_mdio>, <&phy_int>;
+
+	phy = <&phy0>;
+	phy-supply = <&vcc_rmii>;
+
+	phy0: ethernet-phy@0 {
+		reg = <0>;
+		interrupt-parent = <&gpio3>;
+		interrupts = <26 IRQ_TYPE_LEVEL_LOW>;
+	};
+};
+
 &i2c1 {
 	status = "okay";
 	clock-frequency = <400000>;
@@ -240,6 +256,12 @@
 		};
 	};
 
+	lan8720a  {
+		phy_int: phy-int {
+			rockchip,pins = <RK_GPIO3 26 RK_FUNC_GPIO &pcfg_pull_up>;
+		};
+	};
+
 	ir-receiver {
 		ir_recv_pin: ir-recv-pin {
 			rockchip,pins = <RK_GPIO0 10 RK_FUNC_GPIO &pcfg_pull_none>;
diff --git a/arch/arm/boot/dts/rk3188.dtsi b/arch/arm/boot/dts/rk3188.dtsi
index 82732f5249b2..ddaada788b45 100644
--- a/arch/arm/boot/dts/rk3188.dtsi
+++ b/arch/arm/boot/dts/rk3188.dtsi
@@ -168,6 +168,24 @@
 			 */
 		};
 
+		emac {
+			emac_xfer: emac-xfer {
+				rockchip,pins = <RK_GPIO3 16 RK_FUNC_2 &pcfg_pull_none>, /* tx_en */
+						<RK_GPIO3 17 RK_FUNC_2 &pcfg_pull_none>, /* txd1 */
+						<RK_GPIO3 18 RK_FUNC_2 &pcfg_pull_none>, /* txd0 */
+						<RK_GPIO3 19 RK_FUNC_2 &pcfg_pull_none>, /* rxd0 */
+						<RK_GPIO3 20 RK_FUNC_2 &pcfg_pull_none>, /* rxd1 */
+						<RK_GPIO3 21 RK_FUNC_2 &pcfg_pull_none>, /* mac_clk */
+						<RK_GPIO3 22 RK_FUNC_2 &pcfg_pull_none>, /* rx_err */
+						<RK_GPIO3 23 RK_FUNC_2 &pcfg_pull_none>; /* crs_dvalid */
+			};
+
+			emac_mdio: emac-mdio {
+				rockchip,pins = <RK_GPIO3 24 RK_FUNC_2 &pcfg_pull_none>,
+						<RK_GPIO3 25 RK_FUNC_2 &pcfg_pull_none>;
+			};
+		};
+
 		i2c0 {
 			i2c0_xfer: i2c0-xfer {
 				rockchip,pins = <RK_GPIO1 24 RK_FUNC_1 &pcfg_pull_none>,
@@ -380,6 +398,10 @@
 	};
 };
 
+&emac {
+	compatible = "rockchip,rk3188-emac";
+};
+
 &global_timer {
 	interrupts = <GIC_PPI 11 0xf04>;
 };
diff --git a/arch/arm/boot/dts/rk3xxx.dtsi b/arch/arm/boot/dts/rk3xxx.dtsi
index 7332d12eb565..499468d42ada 100644
--- a/arch/arm/boot/dts/rk3xxx.dtsi
+++ b/arch/arm/boot/dts/rk3xxx.dtsi
@@ -152,6 +152,23 @@
 		status = "disabled";
 	};
 
+	emac: ethernet@10204000 {
+		compatible = "snps,arc-emac";
+		reg = <0x10204000 0x3c>;
+		interrupts = <GIC_SPI 19 IRQ_TYPE_LEVEL_HIGH>;
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		rockchip,grf = <&grf>;
+
+		clocks = <&cru HCLK_EMAC>, <&cru SCLK_MAC>;
+		clock-names = "hclk", "macref";
+		max-speed = <100>;
+		phy-mode = "rmii";
+
+		status = "disabled";
+	};
+
 	mmc0: dwmmc@10214000 {
 		compatible = "rockchip,rk2928-dw-mshc";
 		reg = <0x10214000 0x1000>;
diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c
index a37b989a2f91..e1268f905026 100644
--- a/arch/arm/net/bpf_jit_32.c
+++ b/arch/arm/net/bpf_jit_32.c
@@ -12,11 +12,11 @@
 #include <linux/compiler.h>
 #include <linux/errno.h>
 #include <linux/filter.h>
-#include <linux/moduleloader.h>
 #include <linux/netdevice.h>
 #include <linux/string.h>
 #include <linux/slab.h>
 #include <linux/if_vlan.h>
+
 #include <asm/cacheflush.h>
 #include <asm/hwcap.h>
 #include <asm/opcodes.h>
@@ -174,6 +174,14 @@ static inline bool is_load_to_a(u16 inst)
 	}
 }
 
+static void jit_fill_hole(void *area, unsigned int size)
+{
+	u32 *ptr;
+	/* We are guaranteed to have aligned memory. */
+	for (ptr = area; size >= sizeof(u32); size -= sizeof(u32))
+		*ptr++ = __opcode_to_mem_arm(ARM_INST_UDF);
+}
+
 static void build_prologue(struct jit_ctx *ctx)
 {
 	u16 reg_set = saved_regs(ctx);
@@ -859,9 +867,11 @@ b_epilogue:
 
 void bpf_jit_compile(struct bpf_prog *fp)
 {
+	struct bpf_binary_header *header;
 	struct jit_ctx ctx;
 	unsigned tmp_idx;
 	unsigned alloc_size;
+	u8 *target_ptr;
 
 	if (!bpf_jit_enable)
 		return;
@@ -897,13 +907,15 @@ void bpf_jit_compile(struct bpf_prog *fp)
 	/* there's nothing after the epilogue on ARMv7 */
 	build_epilogue(&ctx);
 #endif
-
 	alloc_size = 4 * ctx.idx;
-	ctx.target = module_alloc(alloc_size);
-	if (unlikely(ctx.target == NULL))
+	header = bpf_jit_binary_alloc(alloc_size, &target_ptr,
+				      4, jit_fill_hole);
+	if (header == NULL)
 		goto out;
 
+	ctx.target = (u32 *) target_ptr;
 	ctx.idx = 0;
+
 	build_prologue(&ctx);
 	build_body(&ctx);
 	build_epilogue(&ctx);
@@ -919,8 +931,9 @@ void bpf_jit_compile(struct bpf_prog *fp)
 		/* there are 2 passes here */
 		bpf_jit_dump(fp->len, alloc_size, 2, ctx.target);
 
+	set_memory_ro((unsigned long)header, header->pages);
 	fp->bpf_func = (void *)ctx.target;
-	fp->jited = 1;
+	fp->jited = true;
 out:
 	kfree(ctx.offsets);
 	return;
@@ -928,7 +941,15 @@ out:
 
 void bpf_jit_free(struct bpf_prog *fp)
 {
-	if (fp->jited)
-		module_free(NULL, fp->bpf_func);
-	kfree(fp);
+	unsigned long addr = (unsigned long)fp->bpf_func & PAGE_MASK;
+	struct bpf_binary_header *header = (void *)addr;
+
+	if (!fp->jited)
+		goto free_filter;
+
+	set_memory_rw(addr, header->pages);
+	bpf_jit_binary_free(header);
+
+free_filter:
+	bpf_prog_unlock_free(fp);
 }
diff --git a/arch/arm/net/bpf_jit_32.h b/arch/arm/net/bpf_jit_32.h
index afb84621ff6f..b2d7d92859d3 100644
--- a/arch/arm/net/bpf_jit_32.h
+++ b/arch/arm/net/bpf_jit_32.h
@@ -114,6 +114,20 @@
 
 #define ARM_INST_UMULL		0x00800090
 
+/*
+ * Use a suitable undefined instruction to use for ARM/Thumb2 faulting.
+ * We need to be careful not to conflict with those used by other modules
+ * (BUG, kprobes, etc) and the register_undef_hook() system.
+ *
+ * The ARM architecture reference manual guarantees that the following
+ * instruction space will produce an undefined instruction exception on
+ * all CPUs:
+ *
+ * ARM:   xxxx 0111 1111 xxxx xxxx xxxx 1111 xxxx	ARMv7-AR, section A5.4
+ * Thumb: 1101 1110 xxxx xxxx				ARMv7-M, section A5.2.6
+ */
+#define ARM_INST_UDF		0xe7fddef1
+
 /* register */
 #define _AL3_R(op, rd, rn, rm)	((op ## _R) | (rd) << 12 | (rn) << 16 | (rm))
 /* immediate */
diff --git a/arch/arm/plat-orion/common.c b/arch/arm/plat-orion/common.c
index 3ec6e8e8d368..f5b00f41c4f6 100644
--- a/arch/arm/plat-orion/common.c
+++ b/arch/arm/plat-orion/common.c
@@ -499,7 +499,7 @@ void __init orion_ge00_switch_init(struct dsa_platform_data *d, int irq)
 
 	d->netdev = &orion_ge00.dev;
 	for (i = 0; i < d->nr_chips; i++)
-		d->chip[i].mii_bus = &orion_ge00_shared.dev;
+		d->chip[i].host_dev = &orion_ge00_shared.dev;
 	orion_switch_device.dev.platform_data = d;
 
 	platform_device_register(&orion_switch_device);