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

Pull networking updates from David Miller:

 1) Significantly shrink the core networking routing structures. Result
    of http://vger.kernel.org/~davem/seoul2017_netdev_keynote.pdf

 2) Add netdevsim driver for testing various offloads, from Jakub
    Kicinski.

 3) Support cross-chip FDB operations in DSA, from Vivien Didelot.

 4) Add a 2nd listener hash table for TCP, similar to what was done for
    UDP. From Martin KaFai Lau.

 5) Add eBPF based queue selection to tun, from Jason Wang.

 6) Lockless qdisc support, from John Fastabend.

 7) SCTP stream interleave support, from Xin Long.

 8) Smoother TCP receive autotuning, from Eric Dumazet.

 9) Lots of erspan tunneling enhancements, from William Tu.

10) Add true function call support to BPF, from Alexei Starovoitov.

11) Add explicit support for GRO HW offloading, from Michael Chan.

12) Support extack generation in more netlink subsystems. From Alexander
    Aring, Quentin Monnet, and Jakub Kicinski.

13) Add 1000BaseX, flow control, and EEE support to mvneta driver. From
    Russell King.

14) Add flow table abstraction to netfilter, from Pablo Neira Ayuso.

15) Many improvements and simplifications to the NFP driver bpf JIT,
    from Jakub Kicinski.

16) Support for ipv6 non-equal cost multipath routing, from Ido
    Schimmel.

17) Add resource abstration to devlink, from Arkadi Sharshevsky.

18) Packet scheduler classifier shared filter block support, from Jiri
    Pirko.

19) Avoid locking in act_csum, from Davide Caratti.

20) devinet_ioctl() simplifications from Al viro.

21) More TCP bpf improvements from Lawrence Brakmo.

22) Add support for onlink ipv6 route flag, similar to ipv4, from David
    Ahern.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1925 commits)
  tls: Add support for encryption using async offload accelerator
  ip6mr: fix stale iterator
  net/sched: kconfig: Remove blank help texts
  openvswitch: meter: Use 64-bit arithmetic instead of 32-bit
  tcp_nv: fix potential integer overflow in tcpnv_acked
  r8169: fix RTL8168EP take too long to complete driver initialization.
  qmi_wwan: Add support for Quectel EP06
  rtnetlink: enable IFLA_IF_NETNSID for RTM_NEWLINK
  ipmr: Fix ptrdiff_t print formatting
  ibmvnic: Wait for device response when changing MAC
  qlcnic: fix deadlock bug
  tcp: release sk_frag.page in tcp_disconnect
  ipv4: Get the address of interface correctly.
  net_sched: gen_estimator: fix lockdep splat
  net: macb: Handle HRESP error
  net/mlx5e: IPoIB, Fix copy-paste bug in flow steering refactoring
  ipv6: addrconf: break critical section in addrconf_verify_rtnl()
  ipv6: change route cache aging logic
  i40e/i40evf: Update DESC_NEEDED value to reflect larger value
  bnxt_en: cleanup DIM work on device shutdown
  ...

38 files changed, 608 insertions, 163 deletions

diff --git a/arch/Kconfig b/arch/Kconfig
index 1b560e7f06dc..d007b2a15b22 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -196,6 +196,9 @@ config HAVE_OPTPROBES
 config HAVE_KPROBES_ON_FTRACE
 	bool
 
+config HAVE_FUNCTION_ERROR_INJECTION
+	bool
+
 config HAVE_NMI
 	bool
 
diff --git a/arch/arm/boot/dts/imx25.dtsi b/arch/arm/boot/dts/imx25.dtsi
index 09ce8b81fafa..fcaff1c66bcb 100644
--- a/arch/arm/boot/dts/imx25.dtsi
+++ b/arch/arm/boot/dts/imx25.dtsi
@@ -122,7 +122,7 @@
 			};
 
 			can1: can@43f88000 {
-				compatible = "fsl,imx25-flexcan", "fsl,p1010-flexcan";
+				compatible = "fsl,imx25-flexcan";
 				reg = <0x43f88000 0x4000>;
 				interrupts = <43>;
 				clocks = <&clks 75>, <&clks 75>;
@@ -131,7 +131,7 @@
 			};
 
 			can2: can@43f8c000 {
-				compatible = "fsl,imx25-flexcan", "fsl,p1010-flexcan";
+				compatible = "fsl,imx25-flexcan";
 				reg = <0x43f8c000 0x4000>;
 				interrupts = <44>;
 				clocks = <&clks 76>, <&clks 76>;
diff --git a/arch/arm/boot/dts/imx28.dtsi b/arch/arm/boot/dts/imx28.dtsi
index 2f4ebe0318d3..e52e05c0fe56 100644
--- a/arch/arm/boot/dts/imx28.dtsi
+++ b/arch/arm/boot/dts/imx28.dtsi
@@ -1038,7 +1038,7 @@
 			};
 
 			can0: can@80032000 {
-				compatible = "fsl,imx28-flexcan", "fsl,p1010-flexcan";
+				compatible = "fsl,imx28-flexcan";
 				reg = <0x80032000 0x2000>;
 				interrupts = <8>;
 				clocks = <&clks 58>, <&clks 58>;
@@ -1047,7 +1047,7 @@
 			};
 
 			can1: can@80034000 {
-				compatible = "fsl,imx28-flexcan", "fsl,p1010-flexcan";
+				compatible = "fsl,imx28-flexcan";
 				reg = <0x80034000 0x2000>;
 				interrupts = <9>;
 				clocks = <&clks 59>, <&clks 59>;
diff --git a/arch/arm/boot/dts/imx35.dtsi b/arch/arm/boot/dts/imx35.dtsi
index 6d5e6a60bee7..1f0e2203b576 100644
--- a/arch/arm/boot/dts/imx35.dtsi
+++ b/arch/arm/boot/dts/imx35.dtsi
@@ -303,7 +303,7 @@
 			};
 
 			can1: can@53fe4000 {
-				compatible = "fsl,imx35-flexcan", "fsl,p1010-flexcan";
+				compatible = "fsl,imx35-flexcan";
 				reg = <0x53fe4000 0x1000>;
 				clocks = <&clks 33>, <&clks 33>;
 				clock-names = "ipg", "per";
@@ -312,7 +312,7 @@
 			};
 
 			can2: can@53fe8000 {
-				compatible = "fsl,imx35-flexcan", "fsl,p1010-flexcan";
+				compatible = "fsl,imx35-flexcan";
 				reg = <0x53fe8000 0x1000>;
 				clocks = <&clks 34>, <&clks 34>;
 				clock-names = "ipg", "per";
diff --git a/arch/arm/boot/dts/imx53.dtsi b/arch/arm/boot/dts/imx53.dtsi
index 84f17f7abb71..85071ff8c639 100644
--- a/arch/arm/boot/dts/imx53.dtsi
+++ b/arch/arm/boot/dts/imx53.dtsi
@@ -536,7 +536,7 @@
 			};
 
 			can1: can@53fc8000 {
-				compatible = "fsl,imx53-flexcan", "fsl,p1010-flexcan";
+				compatible = "fsl,imx53-flexcan";
 				reg = <0x53fc8000 0x4000>;
 				interrupts = <82>;
 				clocks = <&clks IMX5_CLK_CAN1_IPG_GATE>,
@@ -546,7 +546,7 @@
 			};
 
 			can2: can@53fcc000 {
-				compatible = "fsl,imx53-flexcan", "fsl,p1010-flexcan";
+				compatible = "fsl,imx53-flexcan";
 				reg = <0x53fcc000 0x4000>;
 				interrupts = <83>;
 				clocks = <&clks IMX5_CLK_CAN2_IPG_GATE>,
diff --git a/arch/arm/boot/dts/imx6q-b450v3.dts b/arch/arm/boot/dts/imx6q-b450v3.dts
index 404a93d9596b..3ec58500e9c2 100644
--- a/arch/arm/boot/dts/imx6q-b450v3.dts
+++ b/arch/arm/boot/dts/imx6q-b450v3.dts
@@ -112,3 +112,55 @@
                 line-name = "PCA9539-P07";
         };
 };
+
+&pci_root {
+	/* Intel Corporation I210 Gigabit Network Connection */
+	switch_nic: ethernet@3,0 {
+		compatible = "pci8086,1533";
+		reg = <0x00010000 0 0 0 0>;
+	};
+};
+
+&switch_ports {
+	port@0 {
+		reg = <0>;
+		label = "enacq";
+		phy-handle = <&switchphy0>;
+	};
+
+	port@1 {
+		reg = <1>;
+		label = "eneport1";
+		phy-handle = <&switchphy1>;
+	};
+
+	port@2 {
+		reg = <2>;
+		label = "enix";
+		phy-handle = <&switchphy2>;
+	};
+
+	port@3 {
+		reg = <3>;
+		label = "enid";
+		phy-handle = <&switchphy3>;
+	};
+
+	port@4 {
+		reg = <4>;
+		label = "cpu";
+		ethernet = <&switch_nic>;
+		phy-handle = <&switchphy4>;
+	};
+
+	port@5 {
+		reg = <5>;
+		label = "enembc";
+
+		/* connected to Ethernet MAC of AT91RM9200 in MII mode */
+		fixed-link {
+			speed = <100>;
+			full-duplex;
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/imx6q-b650v3.dts b/arch/arm/boot/dts/imx6q-b650v3.dts
index 7f9f176901d4..5650a9b11091 100644
--- a/arch/arm/boot/dts/imx6q-b650v3.dts
+++ b/arch/arm/boot/dts/imx6q-b650v3.dts
@@ -111,3 +111,55 @@
 	fsl,tx-cal-45-dp-ohms = <55>;
 	fsl,tx-d-cal = <100>;
 };
+
+&pci_root {
+	/* Intel Corporation I210 Gigabit Network Connection */
+	switch_nic: ethernet@3,0 {
+		compatible = "pci8086,1533";
+		reg = <0x00010000 0 0 0 0>;
+	};
+};
+
+&switch_ports {
+	port@0 {
+		reg = <0>;
+		label = "enacq";
+		phy-handle = <&switchphy0>;
+	};
+
+	port@1 {
+		reg = <1>;
+		label = "eneport1";
+		phy-handle = <&switchphy1>;
+	};
+
+	port@2 {
+		reg = <2>;
+		label = "enix";
+		phy-handle = <&switchphy2>;
+	};
+
+	port@3 {
+		reg = <3>;
+		label = "enid";
+		phy-handle = <&switchphy3>;
+	};
+
+	port@4 {
+		reg = <4>;
+		label = "cpu";
+		ethernet = <&switch_nic>;
+		phy-handle = <&switchphy4>;
+	};
+
+	port@5 {
+		reg = <5>;
+		label = "enembc";
+
+		/* connected to Ethernet MAC of AT91RM9200 in MII mode */
+		fixed-link {
+			speed = <100>;
+			full-duplex;
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/imx6q-b850v3.dts b/arch/arm/boot/dts/imx6q-b850v3.dts
index 46bdc6722715..35edbdc7bcd1 100644
--- a/arch/arm/boot/dts/imx6q-b850v3.dts
+++ b/arch/arm/boot/dts/imx6q-b850v3.dts
@@ -212,3 +212,78 @@
 		};
 	};
 };
+
+&pci_root {
+	/* PLX Technology, Inc. PEX 8605 PCI Express 4-port Gen2 Switch */
+	bridge@1,0 {
+		compatible = "pci10b5,8605";
+		reg = <0x00010000 0 0 0 0>;
+
+		#address-cells = <3>;
+		#size-cells = <2>;
+		#interrupt-cells = <1>;
+
+		bridge@2,1 {
+			compatible = "pci10b5,8605";
+			reg = <0x00020800 0 0 0 0>;
+
+			#address-cells = <3>;
+			#size-cells = <2>;
+			#interrupt-cells = <1>;
+
+			/* Intel Corporation I210 Gigabit Network Connection */
+			ethernet@3,0 {
+				compatible = "pci8086,1533";
+				reg = <0x00030000 0 0 0 0>;
+			};
+		};
+
+		bridge@2,2 {
+			compatible = "pci10b5,8605";
+			reg = <0x00021000 0 0 0 0>;
+
+			#address-cells = <3>;
+			#size-cells = <2>;
+			#interrupt-cells = <1>;
+
+			/* Intel Corporation I210 Gigabit Network Connection */
+			switch_nic: ethernet@4,0 {
+				compatible = "pci8086,1533";
+				reg = <0x00040000 0 0 0 0>;
+			};
+		};
+	};
+};
+
+&switch_ports {
+	port@0 {
+		reg = <0>;
+		label = "eneport1";
+		phy-handle = <&switchphy0>;
+	};
+
+	port@1 {
+		reg = <1>;
+		label = "eneport2";
+		phy-handle = <&switchphy1>;
+	};
+
+	port@2 {
+		reg = <2>;
+		label = "enix";
+		phy-handle = <&switchphy2>;
+	};
+
+	port@3 {
+		reg = <3>;
+		label = "enid";
+		phy-handle = <&switchphy3>;
+	};
+
+	port@4 {
+		reg = <4>;
+		label = "cpu";
+		ethernet = <&switch_nic>;
+		phy-handle = <&switchphy4>;
+	};
+};
diff --git a/arch/arm/boot/dts/imx6q-bx50v3.dtsi b/arch/arm/boot/dts/imx6q-bx50v3.dtsi
index b915837bbb5f..916ea94d75ca 100644
--- a/arch/arm/boot/dts/imx6q-bx50v3.dtsi
+++ b/arch/arm/boot/dts/imx6q-bx50v3.dtsi
@@ -92,6 +92,56 @@
 		mux-int-port = <1>;
 		mux-ext-port = <4>;
 	};
+
+	aliases {
+		mdio-gpio0 = &mdio0;
+	};
+
+	mdio0: mdio-gpio {
+		compatible = "virtual,mdio-gpio";
+		gpios = <&gpio2 5 GPIO_ACTIVE_HIGH>, /* mdc */
+			<&gpio2 7 GPIO_ACTIVE_HIGH>; /* mdio */
+
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		switch@0 {
+			compatible = "marvell,mv88e6085"; /* 88e6240*/
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <0>;
+
+			switch_ports: ports {
+				#address-cells = <1>;
+				#size-cells = <0>;
+			};
+
+			mdio {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				switchphy0: switchphy@0 {
+					reg = <0>;
+				};
+
+				switchphy1: switchphy@1 {
+					reg = <1>;
+				};
+
+				switchphy2: switchphy@2 {
+					reg = <2>;
+				};
+
+				switchphy3: switchphy@3 {
+					reg = <3>;
+				};
+
+				switchphy4: switchphy@4 {
+					reg = <4>;
+				};
+			};
+		};
+	};
 };
 
 &ecspi5 {
@@ -326,3 +376,15 @@
 		tcxo-clock-frequency = <26000000>;
 	};
 };
+
+&pcie {
+	/* Synopsys, Inc. Device */
+	pci_root: root@0,0 {
+		compatible = "pci16c3,abcd";
+		reg = <0x00000000 0 0 0 0>;
+
+		#address-cells = <3>;
+		#size-cells = <2>;
+		#interrupt-cells = <1>;
+	};
+};
diff --git a/arch/arm/boot/dts/ls1021a-qds.dts b/arch/arm/boot/dts/ls1021a-qds.dts
index 67b4de0e3439..7bb402d3e9d0 100644
--- a/arch/arm/boot/dts/ls1021a-qds.dts
+++ b/arch/arm/boot/dts/ls1021a-qds.dts
@@ -331,3 +331,19 @@
 &uart1 {
 	status = "okay";
 };
+
+&can0 {
+	status = "okay";
+};
+
+&can1 {
+	status = "okay";
+};
+
+&can2 {
+	status = "disabled";
+};
+
+&can3 {
+	status = "disabled";
+};
diff --git a/arch/arm/boot/dts/ls1021a-twr.dts b/arch/arm/boot/dts/ls1021a-twr.dts
index 44715c8ef756..860b898141f0 100644
--- a/arch/arm/boot/dts/ls1021a-twr.dts
+++ b/arch/arm/boot/dts/ls1021a-twr.dts
@@ -243,3 +243,19 @@
 &uart1 {
 	status = "okay";
 };
+
+&can0 {
+	status = "okay";
+};
+
+&can1 {
+	status = "okay";
+};
+
+&can2 {
+	status = "disabled";
+};
+
+&can3 {
+	status = "disabled";
+};
diff --git a/arch/arm/boot/dts/ls1021a.dtsi b/arch/arm/boot/dts/ls1021a.dtsi
index 9319e1f0f1d8..7789031898b0 100644
--- a/arch/arm/boot/dts/ls1021a.dtsi
+++ b/arch/arm/boot/dts/ls1021a.dtsi
@@ -730,5 +730,41 @@
 					<0000 0 0 3 &gic GIC_SPI 191 IRQ_TYPE_LEVEL_HIGH>,
 					<0000 0 0 4 &gic GIC_SPI 193 IRQ_TYPE_LEVEL_HIGH>;
 		};
+
+		can0: can@2a70000 {
+			compatible = "fsl,ls1021ar2-flexcan";
+			reg = <0x0 0x2a70000 0x0 0x1000>;
+			interrupts = <GIC_SPI 126 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&clockgen 4 1>, <&clockgen 4 1>;
+			clock-names = "ipg", "per";
+			big-endian;
+		};
+
+		can1: can@2a80000 {
+			compatible = "fsl,ls1021ar2-flexcan";
+			reg = <0x0 0x2a80000 0x0 0x1000>;
+			interrupts = <GIC_SPI 127 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&clockgen 4 1>, <&clockgen 4 1>;
+			clock-names = "ipg", "per";
+			big-endian;
+		};
+
+		can2: can@2a90000 {
+			compatible = "fsl,ls1021ar2-flexcan";
+			reg = <0x0 0x2a90000 0x0 0x1000>;
+			interrupts = <GIC_SPI 128 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&clockgen 4 1>, <&clockgen 4 1>;
+			clock-names = "ipg", "per";
+			big-endian;
+		};
+
+		can3: can@2aa0000 {
+			compatible = "fsl,ls1021ar2-flexcan";
+			reg = <0x0 0x2aa0000 0x0 0x1000>;
+			interrupts = <GIC_SPI 129 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&clockgen 4 1>, <&clockgen 4 1>;
+			clock-names = "ipg", "per";
+			big-endian;
+		};
 	};
 };
diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c
index 323a4df59a6c..b5030e1a41d8 100644
--- a/arch/arm/net/bpf_jit_32.c
+++ b/arch/arm/net/bpf_jit_32.c
@@ -25,8 +25,6 @@
 
 #include "bpf_jit_32.h"
 
-int bpf_jit_enable __read_mostly;
-
 /*
  * eBPF prog stack layout:
  *
@@ -365,15 +363,7 @@ static inline int epilogue_offset(const struct jit_ctx *ctx)
 static inline void emit_udivmod(u8 rd, u8 rm, u8 rn, struct jit_ctx *ctx, u8 op)
 {
 	const u8 *tmp = bpf2a32[TMP_REG_1];
-	s32 jmp_offset;
 
-	/* checks if divisor is zero or not. If it is, then
-	 * exit directly.
-	 */
-	emit(ARM_CMP_I(rn, 0), ctx);
-	_emit(ARM_COND_EQ, ARM_MOV_I(ARM_R0, 0), ctx);
-	jmp_offset = epilogue_offset(ctx);
-	_emit(ARM_COND_EQ, ARM_B(jmp_offset), ctx);
 #if __LINUX_ARM_ARCH__ == 7
 	if (elf_hwcap & HWCAP_IDIVA) {
 		if (op == BPF_DIV)
@@ -1821,7 +1811,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 	/* If BPF JIT was not enabled then we must fall back to
 	 * the interpreter.
 	 */
-	if (!bpf_jit_enable)
+	if (!prog->jit_requested)
 		return orig_prog;
 
 	/* If constant blinding was enabled and we failed during blinding
diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index bb32f7f6dd0f..1d4f1da7c58f 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -31,8 +31,6 @@
 
 #include "bpf_jit.h"
 
-int bpf_jit_enable __read_mostly;
-
 #define TMP_REG_1 (MAX_BPF_JIT_REG + 0)
 #define TMP_REG_2 (MAX_BPF_JIT_REG + 1)
 #define TCALL_CNT (MAX_BPF_JIT_REG + 2)
@@ -99,6 +97,20 @@ static inline void emit_a64_mov_i64(const int reg, const u64 val,
 	}
 }
 
+static inline void emit_addr_mov_i64(const int reg, const u64 val,
+				     struct jit_ctx *ctx)
+{
+	u64 tmp = val;
+	int shift = 0;
+
+	emit(A64_MOVZ(1, reg, tmp & 0xffff, shift), ctx);
+	for (;shift < 48;) {
+		tmp >>= 16;
+		shift += 16;
+		emit(A64_MOVK(1, reg, tmp & 0xffff, shift), ctx);
+	}
+}
+
 static inline void emit_a64_mov_i(const int is64, const int reg,
 				  const s32 val, struct jit_ctx *ctx)
 {
@@ -378,18 +390,6 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 	case BPF_ALU64 | BPF_DIV | BPF_X:
 	case BPF_ALU | BPF_MOD | BPF_X:
 	case BPF_ALU64 | BPF_MOD | BPF_X:
-	{
-		const u8 r0 = bpf2a64[BPF_REG_0];
-
-		/* if (src == 0) return 0 */
-		jmp_offset = 3; /* skip ahead to else path */
-		check_imm19(jmp_offset);
-		emit(A64_CBNZ(is64, src, jmp_offset), ctx);
-		emit(A64_MOVZ(1, r0, 0, 0), ctx);
-		jmp_offset = epilogue_offset(ctx);
-		check_imm26(jmp_offset);
-		emit(A64_B(jmp_offset), ctx);
-		/* else */
 		switch (BPF_OP(code)) {
 		case BPF_DIV:
 			emit(A64_UDIV(is64, dst, dst, src), ctx);
@@ -401,7 +401,6 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 			break;
 		}
 		break;
-	}
 	case BPF_ALU | BPF_LSH | BPF_X:
 	case BPF_ALU64 | BPF_LSH | BPF_X:
 		emit(A64_LSLV(is64, dst, dst, src), ctx);
@@ -605,7 +604,10 @@ emit_cond_jmp:
 		const u8 r0 = bpf2a64[BPF_REG_0];
 		const u64 func = (u64)__bpf_call_base + imm;
 
-		emit_a64_mov_i64(tmp, func, ctx);
+		if (ctx->prog->is_func)
+			emit_addr_mov_i64(tmp, func, ctx);
+		else
+			emit_a64_mov_i64(tmp, func, ctx);
 		emit(A64_BLR(tmp), ctx);
 		emit(A64_MOV(1, r0, A64_R(0)), ctx);
 		break;
@@ -837,16 +839,24 @@ static inline void bpf_flush_icache(void *start, void *end)
 	flush_icache_range((unsigned long)start, (unsigned long)end);
 }
 
+struct arm64_jit_data {
+	struct bpf_binary_header *header;
+	u8 *image;
+	struct jit_ctx ctx;
+};
+
 struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 {
 	struct bpf_prog *tmp, *orig_prog = prog;
 	struct bpf_binary_header *header;
+	struct arm64_jit_data *jit_data;
 	bool tmp_blinded = false;
+	bool extra_pass = false;
 	struct jit_ctx ctx;
 	int image_size;
 	u8 *image_ptr;
 
-	if (!bpf_jit_enable)
+	if (!prog->jit_requested)
 		return orig_prog;
 
 	tmp = bpf_jit_blind_constants(prog);
@@ -860,13 +870,30 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 		prog = tmp;
 	}
 
+	jit_data = prog->aux->jit_data;
+	if (!jit_data) {
+		jit_data = kzalloc(sizeof(*jit_data), GFP_KERNEL);
+		if (!jit_data) {
+			prog = orig_prog;
+			goto out;
+		}
+		prog->aux->jit_data = jit_data;
+	}
+	if (jit_data->ctx.offset) {
+		ctx = jit_data->ctx;
+		image_ptr = jit_data->image;
+		header = jit_data->header;
+		extra_pass = true;
+		image_size = sizeof(u32) * ctx.idx;
+		goto skip_init_ctx;
+	}
 	memset(&ctx, 0, sizeof(ctx));
 	ctx.prog = prog;
 
 	ctx.offset = kcalloc(prog->len, sizeof(int), GFP_KERNEL);
 	if (ctx.offset == NULL) {
 		prog = orig_prog;
-		goto out;
+		goto out_off;
 	}
 
 	/* 1. Initial fake pass to compute ctx->idx. */
@@ -897,6 +924,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 	/* 2. Now, the actual pass. */
 
 	ctx.image = (__le32 *)image_ptr;
+skip_init_ctx:
 	ctx.idx = 0;
 
 	build_prologue(&ctx);
@@ -922,13 +950,31 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 
 	bpf_flush_icache(header, ctx.image + ctx.idx);
 
-	bpf_jit_binary_lock_ro(header);
+	if (!prog->is_func || extra_pass) {
+		if (extra_pass && ctx.idx != jit_data->ctx.idx) {
+			pr_err_once("multi-func JIT bug %d != %d\n",
+				    ctx.idx, jit_data->ctx.idx);
+			bpf_jit_binary_free(header);
+			prog->bpf_func = NULL;
+			prog->jited = 0;
+			goto out_off;
+		}
+		bpf_jit_binary_lock_ro(header);
+	} else {
+		jit_data->ctx = ctx;
+		jit_data->image = image_ptr;
+		jit_data->header = header;
+	}
 	prog->bpf_func = (void *)ctx.image;
 	prog->jited = 1;
 	prog->jited_len = image_size;
 
+	if (!prog->is_func || extra_pass) {
 out_off:
-	kfree(ctx.offset);
+		kfree(ctx.offset);
+		kfree(jit_data);
+		prog->aux->jit_data = NULL;
+	}
 out:
 	if (tmp_blinded)
 		bpf_jit_prog_release_other(prog, prog == orig_prog ?
diff --git a/arch/mips/bcm63xx/dev-enet.c b/arch/mips/bcm63xx/dev-enet.c
index e8284771d620..07b4c65a88a4 100644
--- a/arch/mips/bcm63xx/dev-enet.c
+++ b/arch/mips/bcm63xx/dev-enet.c
@@ -265,6 +265,14 @@ int __init bcm63xx_enet_register(int unit,
 		dpd->dma_chan_width = ENETDMA_CHAN_WIDTH;
 	}
 
+	if (unit == 0) {
+		dpd->rx_chan = 0;
+		dpd->tx_chan = 1;
+	} else {
+		dpd->rx_chan = 2;
+		dpd->tx_chan = 3;
+	}
+
 	ret = platform_device_register(pdev);
 	if (ret)
 		return ret;
diff --git a/arch/mips/include/asm/mach-bcm63xx/bcm63xx_dev_enet.h b/arch/mips/include/asm/mach-bcm63xx/bcm63xx_dev_enet.h
index c0bd47444cff..da39e4d326ba 100644
--- a/arch/mips/include/asm/mach-bcm63xx/bcm63xx_dev_enet.h
+++ b/arch/mips/include/asm/mach-bcm63xx/bcm63xx_dev_enet.h
@@ -55,6 +55,10 @@ struct bcm63xx_enet_platform_data {
 
 	/* DMA descriptor shift */
 	unsigned int dma_desc_shift;
+
+	/* dma channel ids */
+	int rx_chan;
+	int tx_chan;
 };
 
 /*
diff --git a/arch/mips/net/bpf_jit.c b/arch/mips/net/bpf_jit.c
index 44b925005dd3..4d8cb9bb8365 100644
--- a/arch/mips/net/bpf_jit.c
+++ b/arch/mips/net/bpf_jit.c
@@ -1207,8 +1207,6 @@ jmp_cmp:
 	return 0;
 }
 
-int bpf_jit_enable __read_mostly;
-
 void bpf_jit_compile(struct bpf_prog *fp)
 {
 	struct jit_ctx ctx;
diff --git a/arch/mips/net/ebpf_jit.c b/arch/mips/net/ebpf_jit.c
index 962b0259b4b6..3e2798bfea4f 100644
--- a/arch/mips/net/ebpf_jit.c
+++ b/arch/mips/net/ebpf_jit.c
@@ -177,8 +177,6 @@ static u32 b_imm(unsigned int tgt, struct jit_ctx *ctx)
 		(ctx->idx * 4) - 4;
 }
 
-int bpf_jit_enable __read_mostly;
-
 enum which_ebpf_reg {
 	src_reg,
 	src_reg_no_fp,
@@ -743,16 +741,11 @@ static int build_one_insn(const struct bpf_insn *insn, struct jit_ctx *ctx,
 		break;
 	case BPF_ALU | BPF_DIV | BPF_K: /* ALU_IMM */
 	case BPF_ALU | BPF_MOD | BPF_K: /* ALU_IMM */
+		if (insn->imm == 0)
+			return -EINVAL;
 		dst = ebpf_to_mips_reg(ctx, insn, dst_reg);
 		if (dst < 0)
 			return dst;
-		if (insn->imm == 0) { /* Div by zero */
-			b_off = b_imm(exit_idx, ctx);
-			if (is_bad_offset(b_off))
-				return -E2BIG;
-			emit_instr(ctx, beq, MIPS_R_ZERO, MIPS_R_ZERO, b_off);
-			emit_instr(ctx, addu, MIPS_R_V0, MIPS_R_ZERO, MIPS_R_ZERO);
-		}
 		td = get_reg_val_type(ctx, this_idx, insn->dst_reg);
 		if (td == REG_64BIT || td == REG_32BIT_ZERO_EX)
 			/* sign extend */
@@ -772,19 +765,13 @@ static int build_one_insn(const struct bpf_insn *insn, struct jit_ctx *ctx,
 		break;
 	case BPF_ALU64 | BPF_DIV | BPF_K: /* ALU_IMM */
 	case BPF_ALU64 | BPF_MOD | BPF_K: /* ALU_IMM */
+		if (insn->imm == 0)
+			return -EINVAL;
 		dst = ebpf_to_mips_reg(ctx, insn, dst_reg);
 		if (dst < 0)
 			return dst;
-		if (insn->imm == 0) { /* Div by zero */
-			b_off = b_imm(exit_idx, ctx);
-			if (is_bad_offset(b_off))
-				return -E2BIG;
-			emit_instr(ctx, beq, MIPS_R_ZERO, MIPS_R_ZERO, b_off);
-			emit_instr(ctx, addu, MIPS_R_V0, MIPS_R_ZERO, MIPS_R_ZERO);
-		}
 		if (get_reg_val_type(ctx, this_idx, insn->dst_reg) == REG_32BIT)
 			emit_instr(ctx, dinsu, dst, MIPS_R_ZERO, 32, 32);
-
 		if (insn->imm == 1) {
 			/* div by 1 is a nop, mod by 1 is zero */
 			if (bpf_op == BPF_MOD)
@@ -862,11 +849,6 @@ static int build_one_insn(const struct bpf_insn *insn, struct jit_ctx *ctx,
 			break;
 		case BPF_DIV:
 		case BPF_MOD:
-			b_off = b_imm(exit_idx, ctx);
-			if (is_bad_offset(b_off))
-				return -E2BIG;
-			emit_instr(ctx, beq, src, MIPS_R_ZERO, b_off);
-			emit_instr(ctx, movz, MIPS_R_V0, MIPS_R_ZERO, src);
 			emit_instr(ctx, ddivu, dst, src);
 			if (bpf_op == BPF_DIV)
 				emit_instr(ctx, mflo, dst);
@@ -945,11 +927,6 @@ static int build_one_insn(const struct bpf_insn *insn, struct jit_ctx *ctx,
 			break;
 		case BPF_DIV:
 		case BPF_MOD:
-			b_off = b_imm(exit_idx, ctx);
-			if (is_bad_offset(b_off))
-				return -E2BIG;
-			emit_instr(ctx, beq, src, MIPS_R_ZERO, b_off);
-			emit_instr(ctx, movz, MIPS_R_V0, MIPS_R_ZERO, src);
 			emit_instr(ctx, divu, dst, src);
 			if (bpf_op == BPF_DIV)
 				emit_instr(ctx, mflo, dst);
@@ -1869,7 +1846,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 	unsigned int image_size;
 	u8 *image_ptr;
 
-	if (!bpf_jit_enable || !cpu_has_mips64r2)
+	if (!prog->jit_requested || !cpu_has_mips64r2)
 		return prog;
 
 	tmp = bpf_jit_blind_constants(prog);
diff --git a/arch/powerpc/boot/dts/fsl/p1010si-post.dtsi b/arch/powerpc/boot/dts/fsl/p1010si-post.dtsi
index af12ead88c5f..1b4aafc1f6a2 100644
--- a/arch/powerpc/boot/dts/fsl/p1010si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/p1010si-post.dtsi
@@ -137,12 +137,14 @@
 		compatible = "fsl,p1010-flexcan";
 		reg = <0x1c000 0x1000>;
 		interrupts = <48 0x2 0 0>;
+		big-endian;
 	};
 
 	can1: can@1d000 {
 		compatible = "fsl,p1010-flexcan";
 		reg = <0x1d000 0x1000>;
 		interrupts = <61 0x2 0 0>;
+		big-endian;
 	};
 
 	L2: l2-cache-controller@20000 {
diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c
index f9941b3b5770..872d1f6dd11e 100644
--- a/arch/powerpc/net/bpf_jit_comp.c
+++ b/arch/powerpc/net/bpf_jit_comp.c
@@ -18,8 +18,6 @@
 
 #include "bpf_jit32.h"
 
-int bpf_jit_enable __read_mostly;
-
 static inline void bpf_flush_icache(void *start, void *end)
 {
 	smp_wmb();
diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c
index d183b4801bdb..0a34b0cec7b7 100644
--- a/arch/powerpc/net/bpf_jit_comp64.c
+++ b/arch/powerpc/net/bpf_jit_comp64.c
@@ -21,8 +21,6 @@
 
 #include "bpf_jit64.h"
 
-int bpf_jit_enable __read_mostly;
-
 static void bpf_jit_fill_ill_insns(void *area, unsigned int size)
 {
 	memset32(area, BREAKPOINT_INSTRUCTION, size/4);
@@ -383,10 +381,6 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
 			goto bpf_alu32_trunc;
 		case BPF_ALU | BPF_DIV | BPF_X: /* (u32) dst /= (u32) src */
 		case BPF_ALU | BPF_MOD | BPF_X: /* (u32) dst %= (u32) src */
-			PPC_CMPWI(src_reg, 0);
-			PPC_BCC_SHORT(COND_NE, (ctx->idx * 4) + 12);
-			PPC_LI(b2p[BPF_REG_0], 0);
-			PPC_JMP(exit_addr);
 			if (BPF_OP(code) == BPF_MOD) {
 				PPC_DIVWU(b2p[TMP_REG_1], dst_reg, src_reg);
 				PPC_MULW(b2p[TMP_REG_1], src_reg,
@@ -397,10 +391,6 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
 			goto bpf_alu32_trunc;
 		case BPF_ALU64 | BPF_DIV | BPF_X: /* dst /= src */
 		case BPF_ALU64 | BPF_MOD | BPF_X: /* dst %= src */
-			PPC_CMPDI(src_reg, 0);
-			PPC_BCC_SHORT(COND_NE, (ctx->idx * 4) + 12);
-			PPC_LI(b2p[BPF_REG_0], 0);
-			PPC_JMP(exit_addr);
 			if (BPF_OP(code) == BPF_MOD) {
 				PPC_DIVD(b2p[TMP_REG_1], dst_reg, src_reg);
 				PPC_MULD(b2p[TMP_REG_1], src_reg,
@@ -995,7 +985,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
 	struct bpf_prog *tmp_fp;
 	bool bpf_blinded = false;
 
-	if (!bpf_jit_enable)
+	if (!fp->jit_requested)
 		return org_fp;
 
 	tmp_fp = bpf_jit_blind_constants(org_fp);
diff --git a/arch/s390/include/asm/diag.h b/arch/s390/include/asm/diag.h
index 6db78567294c..cdbaad50c7c7 100644
--- a/arch/s390/include/asm/diag.h
+++ b/arch/s390/include/asm/diag.h
@@ -229,13 +229,55 @@ struct diag204_x_phys_block {
 } __packed;
 
 enum diag26c_sc {
+	DIAG26C_PORT_VNIC    = 0x00000024,
 	DIAG26C_MAC_SERVICES = 0x00000030
 };
 
 enum diag26c_version {
-	DIAG26C_VERSION2 = 0x00000002	/* z/VM 5.4.0 */
+	DIAG26C_VERSION2	 = 0x00000002,	/* z/VM 5.4.0 */
+	DIAG26C_VERSION6_VM65918 = 0x00020006	/* z/VM 6.4.0 + VM65918 */
 };
 
+#define DIAG26C_VNIC_INFO	0x0002
+struct diag26c_vnic_req {
+	u32	resp_buf_len;
+	u32	resp_version;
+	u16	req_format;
+	u16	vlan_id;
+	u64	sys_name;
+	u8	res[2];
+	u16	devno;
+} __packed __aligned(8);
+
+#define VNIC_INFO_PROT_L3	1
+#define VNIC_INFO_PROT_L2	2
+/* Note: this is the bare minimum, use it for uninitialized VNICs only. */
+struct diag26c_vnic_resp {
+	u32	version;
+	u32	entry_cnt;
+	/* VNIC info: */
+	u32	next_entry;
+	u64	owner;
+	u16	devno;
+	u8	status;
+	u8	type;
+	u64	lan_owner;
+	u64	lan_name;
+	u64	port_name;
+	u8	port_type;
+	u8	ext_status:6;
+	u8	protocol:2;
+	u16	base_devno;
+	u32	port_num;
+	u32	ifindex;
+	u32	maxinfo;
+	u32	dev_count;
+	/* 3x device info: */
+	u8	dev_info1[28];
+	u8	dev_info2[28];
+	u8	dev_info3[28];
+} __packed __aligned(8);
+
 #define DIAG26C_GET_MAC	0x0000
 struct diag26c_mac_req {
 	u32	resp_buf_len;
diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c
index 9557d8b516df..78a19c93b380 100644
--- a/arch/s390/net/bpf_jit_comp.c
+++ b/arch/s390/net/bpf_jit_comp.c
@@ -28,8 +28,6 @@
 #include <asm/set_memory.h>
 #include "bpf_jit.h"
 
-int bpf_jit_enable __read_mostly;
-
 struct bpf_jit {
 	u32 seen;		/* Flags to remember seen eBPF instructions */
 	u32 seen_reg[16];	/* Array to remember which registers are used */
@@ -612,11 +610,6 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, int i
 	{
 		int rc_reg = BPF_OP(insn->code) == BPF_DIV ? REG_W1 : REG_W0;
 
-		jit->seen |= SEEN_RET0;
-		/* ltr %src,%src (if src == 0 goto fail) */
-		EMIT2(0x1200, src_reg, src_reg);
-		/* jz <ret0> */
-		EMIT4_PCREL(0xa7840000, jit->ret0_ip - jit->prg);
 		/* lhi %w0,0 */
 		EMIT4_IMM(0xa7080000, REG_W0, 0);
 		/* lr %w1,%dst */
@@ -632,11 +625,6 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, int i
 	{
 		int rc_reg = BPF_OP(insn->code) == BPF_DIV ? REG_W1 : REG_W0;
 
-		jit->seen |= SEEN_RET0;
-		/* ltgr %src,%src (if src == 0 goto fail) */
-		EMIT4(0xb9020000, src_reg, src_reg);
-		/* jz <ret0> */
-		EMIT4_PCREL(0xa7840000, jit->ret0_ip - jit->prg);
 		/* lghi %w0,0 */
 		EMIT4_IMM(0xa7090000, REG_W0, 0);
 		/* lgr %w1,%dst */
@@ -1299,7 +1287,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
 	struct bpf_jit jit;
 	int pass;
 
-	if (!bpf_jit_enable)
+	if (!fp->jit_requested)
 		return orig_fp;
 
 	tmp = bpf_jit_blind_constants(fp);
diff --git a/arch/sh/boards/board-espt.c b/arch/sh/boards/board-espt.c
index 7291e2f11a47..4d6be53058d6 100644
--- a/arch/sh/boards/board-espt.c
+++ b/arch/sh/boards/board-espt.c
@@ -79,7 +79,6 @@ static struct resource sh_eth_resources[] = {
 
 static struct sh_eth_plat_data sh7763_eth_pdata = {
 	.phy = 0,
-	.edmac_endian = EDMAC_LITTLE_ENDIAN,
 	.phy_interface = PHY_INTERFACE_MODE_MII,
 };
 
diff --git a/arch/sh/boards/board-sh7757lcr.c b/arch/sh/boards/board-sh7757lcr.c
index 0104c8199c48..1bde08dc067d 100644
--- a/arch/sh/boards/board-sh7757lcr.c
+++ b/arch/sh/boards/board-sh7757lcr.c
@@ -76,7 +76,6 @@ static struct resource sh_eth0_resources[] = {
 
 static struct sh_eth_plat_data sh7757_eth0_pdata = {
 	.phy = 1,
-	.edmac_endian = EDMAC_LITTLE_ENDIAN,
 	.set_mdio_gate = sh7757_eth_set_mdio_gate,
 };
 
@@ -104,7 +103,6 @@ static struct resource sh_eth1_resources[] = {
 
 static struct sh_eth_plat_data sh7757_eth1_pdata = {
 	.phy = 1,
-	.edmac_endian = EDMAC_LITTLE_ENDIAN,
 	.set_mdio_gate = sh7757_eth_set_mdio_gate,
 };
 
@@ -148,7 +146,6 @@ static struct resource sh_eth_giga0_resources[] = {
 
 static struct sh_eth_plat_data sh7757_eth_giga0_pdata = {
 	.phy = 18,
-	.edmac_endian = EDMAC_LITTLE_ENDIAN,
 	.set_mdio_gate = sh7757_eth_giga_set_mdio_gate,
 	.phy_interface = PHY_INTERFACE_MODE_RGMII_ID,
 };
@@ -182,7 +179,6 @@ static struct resource sh_eth_giga1_resources[] = {
 
 static struct sh_eth_plat_data sh7757_eth_giga1_pdata = {
 	.phy = 19,
-	.edmac_endian = EDMAC_LITTLE_ENDIAN,
 	.set_mdio_gate = sh7757_eth_giga_set_mdio_gate,
 	.phy_interface = PHY_INTERFACE_MODE_RGMII_ID,
 };
diff --git a/arch/sh/boards/mach-ecovec24/setup.c b/arch/sh/boards/mach-ecovec24/setup.c
index 1faf6cb93dcb..6f929abe0b50 100644
--- a/arch/sh/boards/mach-ecovec24/setup.c
+++ b/arch/sh/boards/mach-ecovec24/setup.c
@@ -159,7 +159,6 @@ static struct resource sh_eth_resources[] = {
 
 static struct sh_eth_plat_data sh_eth_plat = {
 	.phy = 0x1f, /* SMSC LAN8700 */
-	.edmac_endian = EDMAC_LITTLE_ENDIAN,
 	.phy_interface = PHY_INTERFACE_MODE_MII,
 	.ether_link_active_low = 1
 };
diff --git a/arch/sh/boards/mach-se/7724/setup.c b/arch/sh/boards/mach-se/7724/setup.c
index f1fecd395679..255952555656 100644
--- a/arch/sh/boards/mach-se/7724/setup.c
+++ b/arch/sh/boards/mach-se/7724/setup.c
@@ -374,7 +374,6 @@ static struct resource sh_eth_resources[] = {
 
 static struct sh_eth_plat_data sh_eth_plat = {
 	.phy = 0x1f, /* SMSC LAN8187 */
-	.edmac_endian = EDMAC_LITTLE_ENDIAN,
 	.phy_interface = PHY_INTERFACE_MODE_MII,
 };
 
diff --git a/arch/sh/boards/mach-sh7763rdp/setup.c b/arch/sh/boards/mach-sh7763rdp/setup.c
index 2c8fb04685d4..6e62686b81b1 100644
--- a/arch/sh/boards/mach-sh7763rdp/setup.c
+++ b/arch/sh/boards/mach-sh7763rdp/setup.c
@@ -87,7 +87,6 @@ static struct resource sh_eth_resources[] = {
 
 static struct sh_eth_plat_data sh7763_eth_pdata = {
 	.phy = 1,
-	.edmac_endian = EDMAC_LITTLE_ENDIAN,
 	.phy_interface = PHY_INTERFACE_MODE_MII,
 };
 
diff --git a/arch/sh/kernel/cpu/sh2/setup-sh7619.c b/arch/sh/kernel/cpu/sh2/setup-sh7619.c
index 95796ad00fbe..d08db08dec38 100644
--- a/arch/sh/kernel/cpu/sh2/setup-sh7619.c
+++ b/arch/sh/kernel/cpu/sh2/setup-sh7619.c
@@ -122,7 +122,6 @@ static struct platform_device scif2_device = {
 
 static struct sh_eth_plat_data eth_platform_data = {
 	.phy		= 1,
-	.edmac_endian	= EDMAC_LITTLE_ENDIAN,
 	.phy_interface	= PHY_INTERFACE_MODE_MII,
 };
 
diff --git a/arch/sparc/net/bpf_jit_comp_32.c b/arch/sparc/net/bpf_jit_comp_32.c
index 09e318eb34ee..3bd8ca95e521 100644
--- a/arch/sparc/net/bpf_jit_comp_32.c
+++ b/arch/sparc/net/bpf_jit_comp_32.c
@@ -11,8 +11,6 @@
 
 #include "bpf_jit_32.h"
 
-int bpf_jit_enable __read_mostly;
-
 static inline bool is_simm13(unsigned int value)
 {
 	return value + 0x1000 < 0x2000;
diff --git a/arch/sparc/net/bpf_jit_comp_64.c b/arch/sparc/net/bpf_jit_comp_64.c
index ff5f9cb3039a..48a25869349b 100644
--- a/arch/sparc/net/bpf_jit_comp_64.c
+++ b/arch/sparc/net/bpf_jit_comp_64.c
@@ -12,8 +12,6 @@
 
 #include "bpf_jit_64.h"
 
-int bpf_jit_enable __read_mostly;
-
 static inline bool is_simm13(unsigned int value)
 {
 	return value + 0x1000 < 0x2000;
@@ -969,31 +967,17 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 		emit_alu(MULX, src, dst, ctx);
 		break;
 	case BPF_ALU | BPF_DIV | BPF_X:
-		emit_cmp(src, G0, ctx);
-		emit_branch(BE|ANNUL, ctx->idx, ctx->epilogue_offset, ctx);
-		emit_loadimm(0, bpf2sparc[BPF_REG_0], ctx);
-
 		emit_write_y(G0, ctx);
 		emit_alu(DIV, src, dst, ctx);
 		break;
-
 	case BPF_ALU64 | BPF_DIV | BPF_X:
-		emit_cmp(src, G0, ctx);
-		emit_branch(BE|ANNUL, ctx->idx, ctx->epilogue_offset, ctx);
-		emit_loadimm(0, bpf2sparc[BPF_REG_0], ctx);
-
 		emit_alu(UDIVX, src, dst, ctx);
 		break;
-
 	case BPF_ALU | BPF_MOD | BPF_X: {
 		const u8 tmp = bpf2sparc[TMP_REG_1];
 
 		ctx->tmp_1_used = true;
 
-		emit_cmp(src, G0, ctx);
-		emit_branch(BE|ANNUL, ctx->idx, ctx->epilogue_offset, ctx);
-		emit_loadimm(0, bpf2sparc[BPF_REG_0], ctx);
-
 		emit_write_y(G0, ctx);
 		emit_alu3(DIV, dst, src, tmp, ctx);
 		emit_alu3(MULX, tmp, src, tmp, ctx);
@@ -1005,10 +989,6 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 
 		ctx->tmp_1_used = true;
 
-		emit_cmp(src, G0, ctx);
-		emit_branch(BE|ANNUL, ctx->idx, ctx->epilogue_offset, ctx);
-		emit_loadimm(0, bpf2sparc[BPF_REG_0], ctx);
-
 		emit_alu3(UDIVX, dst, src, tmp, ctx);
 		emit_alu3(MULX, tmp, src, tmp, ctx);
 		emit_alu3(SUB, dst, tmp, dst, ctx);
@@ -1509,17 +1489,25 @@ static void jit_fill_hole(void *area, unsigned int size)
 		*ptr++ = 0x91d02005; /* ta 5 */
 }
 
+struct sparc64_jit_data {
+	struct bpf_binary_header *header;
+	u8 *image;
+	struct jit_ctx ctx;
+};
+
 struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 {
 	struct bpf_prog *tmp, *orig_prog = prog;
+	struct sparc64_jit_data *jit_data;
 	struct bpf_binary_header *header;
 	bool tmp_blinded = false;
+	bool extra_pass = false;
 	struct jit_ctx ctx;
 	u32 image_size;
 	u8 *image_ptr;
 	int pass;
 
-	if (!bpf_jit_enable)
+	if (!prog->jit_requested)
 		return orig_prog;
 
 	tmp = bpf_jit_blind_constants(prog);
@@ -1533,13 +1521,31 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 		prog = tmp;
 	}
 
+	jit_data = prog->aux->jit_data;
+	if (!jit_data) {
+		jit_data = kzalloc(sizeof(*jit_data), GFP_KERNEL);
+		if (!jit_data) {
+			prog = orig_prog;
+			goto out;
+		}
+		prog->aux->jit_data = jit_data;
+	}
+	if (jit_data->ctx.offset) {
+		ctx = jit_data->ctx;
+		image_ptr = jit_data->image;
+		header = jit_data->header;
+		extra_pass = true;
+		image_size = sizeof(u32) * ctx.idx;
+		goto skip_init_ctx;
+	}
+
 	memset(&ctx, 0, sizeof(ctx));
 	ctx.prog = prog;
 
 	ctx.offset = kcalloc(prog->len, sizeof(unsigned int), GFP_KERNEL);
 	if (ctx.offset == NULL) {
 		prog = orig_prog;
-		goto out;
+		goto out_off;
 	}
 
 	/* Fake pass to detect features used, and get an accurate assessment
@@ -1562,7 +1568,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 	}
 
 	ctx.image = (u32 *)image_ptr;
-
+skip_init_ctx:
 	for (pass = 1; pass < 3; pass++) {
 		ctx.idx = 0;
 
@@ -1593,14 +1599,24 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 
 	bpf_flush_icache(header, (u8 *)header + (header->pages * PAGE_SIZE));
 
-	bpf_jit_binary_lock_ro(header);
+	if (!prog->is_func || extra_pass) {
+		bpf_jit_binary_lock_ro(header);
+	} else {
+		jit_data->ctx = ctx;
+		jit_data->image = image_ptr;
+		jit_data->header = header;
+	}
 
 	prog->bpf_func = (void *)ctx.image;
 	prog->jited = 1;
 	prog->jited_len = image_size;
 
+	if (!prog->is_func || extra_pass) {
 out_off:
-	kfree(ctx.offset);
+		kfree(ctx.offset);
+		kfree(jit_data);
+		prog->aux->jit_data = NULL;
+	}
 out:
 	if (tmp_blinded)
 		bpf_jit_prog_release_other(prog, prog == orig_prog ?
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index dbe5542a6666..fcd3b4d24eea 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -155,6 +155,7 @@ config X86
 	select HAVE_KERNEL_XZ
 	select HAVE_KPROBES
 	select HAVE_KPROBES_ON_FTRACE
+	select HAVE_FUNCTION_ERROR_INJECTION
 	select HAVE_KRETPROBES
 	select HAVE_KVM
 	select HAVE_LIVEPATCH			if X86_64
diff --git a/arch/x86/include/asm/error-injection.h b/arch/x86/include/asm/error-injection.h
new file mode 100644
index 000000000000..47b7a1296245
--- /dev/null
+++ b/arch/x86/include/asm/error-injection.h
@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_ERROR_INJECTION_H
+#define _ASM_ERROR_INJECTION_H
+
+#include <linux/compiler.h>
+#include <linux/linkage.h>
+#include <asm/ptrace.h>
+#include <asm-generic/error-injection.h>
+
+asmlinkage void just_return_func(void);
+void override_function_with_return(struct pt_regs *regs);
+
+#endif /* _ASM_ERROR_INJECTION_H */
diff --git a/arch/x86/include/asm/kprobes.h b/arch/x86/include/asm/kprobes.h
index 9f2e3102e0bb..367d99cff426 100644
--- a/arch/x86/include/asm/kprobes.h
+++ b/arch/x86/include/asm/kprobes.h
@@ -67,6 +67,8 @@ extern const int kretprobe_blacklist_size;
 void arch_remove_kprobe(struct kprobe *p);
 asmlinkage void kretprobe_trampoline(void);
 
+extern void arch_kprobe_override_function(struct pt_regs *regs);
+
 /* Architecture specific copy of original instruction*/
 struct arch_specific_insn {
 	/* copy of the original instruction */
diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h
index 14131dd06b29..6de1fd3d0097 100644
--- a/arch/x86/include/asm/ptrace.h
+++ b/arch/x86/include/asm/ptrace.h
@@ -109,6 +109,11 @@ static inline unsigned long regs_return_value(struct pt_regs *regs)
 	return regs->ax;
 }
 
+static inline void regs_set_return_value(struct pt_regs *regs, unsigned long rc)
+{
+	regs->ax = rc;
+}
+
 /*
  * user_mode(regs) determines whether a register set came from user
  * mode.  On x86_32, this is true if V8086 mode was enabled OR if the
diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile
index 69a473919260..91e9700cc6dc 100644
--- a/arch/x86/lib/Makefile
+++ b/arch/x86/lib/Makefile
@@ -26,6 +26,7 @@ lib-y += memcpy_$(BITS).o
 lib-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem.o
 lib-$(CONFIG_INSTRUCTION_DECODER) += insn.o inat.o insn-eval.o
 lib-$(CONFIG_RANDOMIZE_BASE) += kaslr.o
+lib-$(CONFIG_FUNCTION_ERROR_INJECTION)	+= error-inject.o
 lib-$(CONFIG_RETPOLINE) += retpoline.o
 OBJECT_FILES_NON_STANDARD_retpoline.o :=y
 
diff --git a/arch/x86/lib/error-inject.c b/arch/x86/lib/error-inject.c
new file mode 100644
index 000000000000..7b881d03d0dd
--- /dev/null
+++ b/arch/x86/lib/error-inject.c
@@ -0,0 +1,19 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/error-injection.h>
+#include <linux/kprobes.h>
+
+asmlinkage void just_return_func(void);
+
+asm(
+	".type just_return_func, @function\n"
+	"just_return_func:\n"
+	"	ret\n"
+	".size just_return_func, .-just_return_func\n"
+);
+
+void override_function_with_return(struct pt_regs *regs)
+{
+	regs->ip = (unsigned long)&just_return_func;
+}
+NOKPROBE_SYMBOL(override_function_with_return);
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 0554e8aef4d5..4923d92f918d 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -15,8 +15,6 @@
 #include <asm/set_memory.h>
 #include <linux/bpf.h>
 
-int bpf_jit_enable __read_mostly;
-
 /*
  * assembly code in arch/x86/net/bpf_jit.S
  */
@@ -154,6 +152,11 @@ static bool is_ereg(u32 reg)
 			     BIT(BPF_REG_AX));
 }
 
+static bool is_axreg(u32 reg)
+{
+	return reg == BPF_REG_0;
+}
+
 /* add modifiers if 'reg' maps to x64 registers r8..r15 */
 static u8 add_1mod(u8 byte, u32 reg)
 {
@@ -447,16 +450,36 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 			else if (is_ereg(dst_reg))
 				EMIT1(add_1mod(0x40, dst_reg));
 
+			/* b3 holds 'normal' opcode, b2 short form only valid
+			 * in case dst is eax/rax.
+			 */
 			switch (BPF_OP(insn->code)) {
-			case BPF_ADD: b3 = 0xC0; break;
-			case BPF_SUB: b3 = 0xE8; break;
-			case BPF_AND: b3 = 0xE0; break;
-			case BPF_OR: b3 = 0xC8; break;
-			case BPF_XOR: b3 = 0xF0; break;
+			case BPF_ADD:
+				b3 = 0xC0;
+				b2 = 0x05;
+				break;
+			case BPF_SUB:
+				b3 = 0xE8;
+				b2 = 0x2D;
+				break;
+			case BPF_AND:
+				b3 = 0xE0;
+				b2 = 0x25;
+				break;
+			case BPF_OR:
+				b3 = 0xC8;
+				b2 = 0x0D;
+				break;
+			case BPF_XOR:
+				b3 = 0xF0;
+				b2 = 0x35;
+				break;
 			}
 
 			if (is_imm8(imm32))
 				EMIT3(0x83, add_1reg(b3, dst_reg), imm32);
+			else if (is_axreg(dst_reg))
+				EMIT1_off32(b2, imm32);
 			else
 				EMIT2_off32(0x81, add_1reg(b3, dst_reg), imm32);
 			break;
@@ -545,26 +568,6 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 			 */
 			EMIT2(0x31, 0xd2);
 
-			if (BPF_SRC(insn->code) == BPF_X) {
-				/* if (src_reg == 0) return 0 */
-
-				/* cmp r11, 0 */
-				EMIT4(0x49, 0x83, 0xFB, 0x00);
-
-				/* jne .+9 (skip over pop, pop, xor and jmp) */
-				EMIT2(X86_JNE, 1 + 1 + 2 + 5);
-				EMIT1(0x5A); /* pop rdx */
-				EMIT1(0x58); /* pop rax */
-				EMIT2(0x31, 0xc0); /* xor eax, eax */
-
-				/* jmp cleanup_addr
-				 * addrs[i] - 11, because there are 11 bytes
-				 * after this insn: div, mov, pop, pop, mov
-				 */
-				jmp_offset = ctx->cleanup_addr - (addrs[i] - 11);
-				EMIT1_off32(0xE9, jmp_offset);
-			}
-
 			if (BPF_CLASS(insn->code) == BPF_ALU64)
 				/* div r11 */
 				EMIT3(0x49, 0xF7, 0xF3);
@@ -1109,19 +1112,29 @@ common_load:
 	return proglen;
 }
 
+struct x64_jit_data {
+	struct bpf_binary_header *header;
+	int *addrs;
+	u8 *image;
+	int proglen;
+	struct jit_context ctx;
+};
+
 struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 {
 	struct bpf_binary_header *header = NULL;
 	struct bpf_prog *tmp, *orig_prog = prog;
+	struct x64_jit_data *jit_data;
 	int proglen, oldproglen = 0;
 	struct jit_context ctx = {};
 	bool tmp_blinded = false;
+	bool extra_pass = false;
 	u8 *image = NULL;
 	int *addrs;
 	int pass;
 	int i;
 
-	if (!bpf_jit_enable)
+	if (!prog->jit_requested)
 		return orig_prog;
 
 	tmp = bpf_jit_blind_constants(prog);
@@ -1135,10 +1148,28 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 		prog = tmp;
 	}
 
+	jit_data = prog->aux->jit_data;
+	if (!jit_data) {
+		jit_data = kzalloc(sizeof(*jit_data), GFP_KERNEL);
+		if (!jit_data) {
+			prog = orig_prog;
+			goto out;
+		}
+		prog->aux->jit_data = jit_data;
+	}
+	addrs = jit_data->addrs;
+	if (addrs) {
+		ctx = jit_data->ctx;
+		oldproglen = jit_data->proglen;
+		image = jit_data->image;
+		header = jit_data->header;
+		extra_pass = true;
+		goto skip_init_addrs;
+	}
 	addrs = kmalloc(prog->len * sizeof(*addrs), GFP_KERNEL);
 	if (!addrs) {
 		prog = orig_prog;
-		goto out;
+		goto out_addrs;
 	}
 
 	/* Before first pass, make a rough estimation of addrs[]
@@ -1149,6 +1180,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 		addrs[i] = proglen;
 	}
 	ctx.cleanup_addr = proglen;
+skip_init_addrs:
 
 	/* JITed image shrinks with every pass and the loop iterates
 	 * until the image stops shrinking. Very large bpf programs
@@ -1189,7 +1221,15 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 
 	if (image) {
 		bpf_flush_icache(header, image + proglen);
-		bpf_jit_binary_lock_ro(header);
+		if (!prog->is_func || extra_pass) {
+			bpf_jit_binary_lock_ro(header);
+		} else {
+			jit_data->addrs = addrs;
+			jit_data->ctx = ctx;
+			jit_data->proglen = proglen;
+			jit_data->image = image;
+			jit_data->header = header;
+		}
 		prog->bpf_func = (void *)image;
 		prog->jited = 1;
 		prog->jited_len = proglen;
@@ -1197,8 +1237,12 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 		prog = orig_prog;
 	}
 
+	if (!prog->is_func || extra_pass) {
 out_addrs:
-	kfree(addrs);
+		kfree(addrs);
+		kfree(jit_data);
+		prog->aux->jit_data = NULL;
+	}
 out:
 	if (tmp_blinded)
 		bpf_jit_prog_release_other(prog, prog == orig_prog ?