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

Pull networking updates from David Miller:

 1) Add Maglev hashing scheduler to IPVS, from Inju Song.

 2) Lots of new TC subsystem tests from Roman Mashak.

 3) Add TCP zero copy receive and fix delayed acks and autotuning with
    SO_RCVLOWAT, from Eric Dumazet.

 4) Add XDP_REDIRECT support to mlx5 driver, from Jesper Dangaard
    Brouer.

 5) Add ttl inherit support to vxlan, from Hangbin Liu.

 6) Properly separate ipv6 routes into their logically independant
    components. fib6_info for the routing table, and fib6_nh for sets of
    nexthops, which thus can be shared. From David Ahern.

 7) Add bpf_xdp_adjust_tail helper, which can be used to generate ICMP
    messages from XDP programs. From Nikita V. Shirokov.

 8) Lots of long overdue cleanups to the r8169 driver, from Heiner
    Kallweit.

 9) Add BTF ("BPF Type Format"), from Martin KaFai Lau.

10) Add traffic condition monitoring to iwlwifi, from Luca Coelho.

11) Plumb extack down into fib_rules, from Roopa Prabhu.

12) Add Flower classifier offload support to igb, from Vinicius Costa
    Gomes.

13) Add UDP GSO support, from Willem de Bruijn.

14) Add documentation for eBPF helpers, from Quentin Monnet.

15) Add TLS tx offload to mlx5, from Ilya Lesokhin.

16) Allow applications to be given the number of bytes available to read
    on a socket via a control message returned from recvmsg(), from
    Soheil Hassas Yeganeh.

17) Add x86_32 eBPF JIT compiler, from Wang YanQing.

18) Add AF_XDP sockets, with zerocopy support infrastructure as well.
    From Björn Töpel.

19) Remove indirect load support from all of the BPF JITs and handle
    these operations in the verifier by translating them into native BPF
    instead. From Daniel Borkmann.

20) Add GRO support to ipv6 gre tunnels, from Eran Ben Elisha.

21) Allow XDP programs to do lookups in the main kernel routing tables
    for forwarding. From David Ahern.

22) Allow drivers to store hardware state into an ELF section of kernel
    dump vmcore files, and use it in cxgb4. From Rahul Lakkireddy.

23) Various RACK and loss detection improvements in TCP, from Yuchung
    Cheng.

24) Add TCP SACK compression, from Eric Dumazet.

25) Add User Mode Helper support and basic bpfilter infrastructure, from
    Alexei Starovoitov.

26) Support ports and protocol values in RTM_GETROUTE, from Roopa
    Prabhu.

27) Support bulking in ->ndo_xdp_xmit() API, from Jesper Dangaard
    Brouer.

28) Add lots of forwarding selftests, from Petr Machata.

29) Add generic network device failover driver, from Sridhar Samudrala.

* ra.kernel.org:/pub/scm/linux/kernel/git/davem/net-next: (1959 commits)
  strparser: Add __strp_unpause and use it in ktls.
  rxrpc: Fix terminal retransmission connection ID to include the channel
  net: hns3: Optimize PF CMDQ interrupt switching process
  net: hns3: Fix for VF mailbox receiving unknown message
  net: hns3: Fix for VF mailbox cannot receiving PF response
  bnx2x: use the right constant
  Revert "net: sched: cls: Fix offloading when ingress dev is vxlan"
  net: dsa: b53: Fix for brcm tag issue in Cygnus SoC
  enic: fix UDP rss bits
  netdev-FAQ: clarify DaveM's position for stable backports
  rtnetlink: validate attributes in do_setlink()
  mlxsw: Add extack messages for port_{un, }split failures
  netdevsim: Add extack error message for devlink reload
  devlink: Add extack to reload and port_{un, }split operations
  net: metrics: add proper netlink validation
  ipmr: fix error path when ipmr_new_table fails
  ip6mr: only set ip6mr_table from setsockopt when ip6mr_new_table succeeds
  net: hns3: remove unused hclgevf_cfg_func_mta_filter
  netfilter: provide udp*_lib_lookup for nf_tproxy
  qed*: Utilize FW 8.37.2.0
  ...

25 files changed, 2788 insertions, 1505 deletions

diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c
index b5030e1a41d8..6e8b71613039 100644
--- a/arch/arm/net/bpf_jit_32.c
+++ b/arch/arm/net/bpf_jit_32.c
@@ -84,7 +84,7 @@
  *
  * 1. First argument is passed using the arm 32bit registers and rest of the
  * arguments are passed on stack scratch space.
- * 2. First callee-saved arugument is mapped to arm 32 bit registers and rest
+ * 2. First callee-saved argument is mapped to arm 32 bit registers and rest
  * arguments are mapped to scratch space on stack.
  * 3. We need two 64 bit temp registers to do complex operations on eBPF
  * registers.
@@ -234,18 +234,11 @@ static void jit_fill_hole(void *area, unsigned int size)
 #define SCRATCH_SIZE 80
 
 /* total stack size used in JITed code */
-#define _STACK_SIZE \
-	(ctx->prog->aux->stack_depth + \
-	 + SCRATCH_SIZE + \
-	 + 4 /* extra for skb_copy_bits buffer */)
-
-#define STACK_SIZE ALIGN(_STACK_SIZE, STACK_ALIGNMENT)
+#define _STACK_SIZE	(ctx->prog->aux->stack_depth + SCRATCH_SIZE)
+#define STACK_SIZE	ALIGN(_STACK_SIZE, STACK_ALIGNMENT)
 
 /* Get the offset of eBPF REGISTERs stored on scratch space. */
-#define STACK_VAR(off) (STACK_SIZE-off-4)
-
-/* Offset of skb_copy_bits buffer */
-#define SKB_BUFFER STACK_VAR(SCRATCH_SIZE)
+#define STACK_VAR(off) (STACK_SIZE - off)
 
 #if __LINUX_ARM_ARCH__ < 7
 
@@ -708,7 +701,7 @@ static inline void emit_a32_arsh_r64(const u8 dst[], const u8 src[], bool dstk,
 }
 
 /* dst = dst >> src */
-static inline void emit_a32_lsr_r64(const u8 dst[], const u8 src[], bool dstk,
+static inline void emit_a32_rsh_r64(const u8 dst[], const u8 src[], bool dstk,
 				     bool sstk, struct jit_ctx *ctx) {
 	const u8 *tmp = bpf2a32[TMP_REG_1];
 	const u8 *tmp2 = bpf2a32[TMP_REG_2];
@@ -724,7 +717,7 @@ static inline void emit_a32_lsr_r64(const u8 dst[], const u8 src[], bool dstk,
 		emit(ARM_LDR_I(rm, ARM_SP, STACK_VAR(dst_hi)), ctx);
 	}
 
-	/* Do LSH operation */
+	/* Do RSH operation */
 	emit(ARM_RSB_I(ARM_IP, rt, 32), ctx);
 	emit(ARM_SUBS_I(tmp2[0], rt, 32), ctx);
 	emit(ARM_MOV_SR(ARM_LR, rd, SRTYPE_LSR, rt), ctx);
@@ -774,7 +767,7 @@ static inline void emit_a32_lsh_i64(const u8 dst[], bool dstk,
 }
 
 /* dst = dst >> val */
-static inline void emit_a32_lsr_i64(const u8 dst[], bool dstk,
+static inline void emit_a32_rsh_i64(const u8 dst[], bool dstk,
 				    const u32 val, struct jit_ctx *ctx) {
 	const u8 *tmp = bpf2a32[TMP_REG_1];
 	const u8 *tmp2 = bpf2a32[TMP_REG_2];
@@ -1199,8 +1192,8 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 	s32 jmp_offset;
 
 #define check_imm(bits, imm) do {				\
-	if ((((imm) > 0) && ((imm) >> (bits))) ||		\
-	    (((imm) < 0) && (~(imm) >> (bits)))) {		\
+	if ((imm) >= (1 << ((bits) - 1)) ||			\
+	    (imm) < -(1 << ((bits) - 1))) {			\
 		pr_info("[%2d] imm=%d(0x%x) out of range\n",	\
 			i, imm, imm);				\
 		return -EINVAL;					\
@@ -1330,7 +1323,7 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 	case BPF_ALU64 | BPF_RSH | BPF_K:
 		if (unlikely(imm > 63))
 			return -EINVAL;
-		emit_a32_lsr_i64(dst, dstk, imm, ctx);
+		emit_a32_rsh_i64(dst, dstk, imm, ctx);
 		break;
 	/* dst = dst << src */
 	case BPF_ALU64 | BPF_LSH | BPF_X:
@@ -1338,7 +1331,7 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 		break;
 	/* dst = dst >> src */
 	case BPF_ALU64 | BPF_RSH | BPF_X:
-		emit_a32_lsr_r64(dst, src, dstk, sstk, ctx);
+		emit_a32_rsh_r64(dst, src, dstk, sstk, ctx);
 		break;
 	/* dst = dst >> src (signed) */
 	case BPF_ALU64 | BPF_ARSH | BPF_X:
@@ -1452,83 +1445,6 @@ exit:
 			emit(ARM_LDR_I(rn, ARM_SP, STACK_VAR(src_lo)), ctx);
 		emit_ldx_r(dst, rn, dstk, off, ctx, BPF_SIZE(code));
 		break;
-	/* R0 = ntohx(*(size *)(((struct sk_buff *)R6)->data + imm)) */
-	case BPF_LD | BPF_ABS | BPF_W:
-	case BPF_LD | BPF_ABS | BPF_H:
-	case BPF_LD | BPF_ABS | BPF_B:
-	/* R0 = ntohx(*(size *)(((struct sk_buff *)R6)->data + src + imm)) */
-	case BPF_LD | BPF_IND | BPF_W:
-	case BPF_LD | BPF_IND | BPF_H:
-	case BPF_LD | BPF_IND | BPF_B:
-	{
-		const u8 r4 = bpf2a32[BPF_REG_6][1]; /* r4 = ptr to sk_buff */
-		const u8 r0 = bpf2a32[BPF_REG_0][1]; /*r0: struct sk_buff *skb*/
-						     /* rtn value */
-		const u8 r1 = bpf2a32[BPF_REG_0][0]; /* r1: int k */
-		const u8 r2 = bpf2a32[BPF_REG_1][1]; /* r2: unsigned int size */
-		const u8 r3 = bpf2a32[BPF_REG_1][0]; /* r3: void *buffer */
-		const u8 r6 = bpf2a32[TMP_REG_1][1]; /* r6: void *(*func)(..) */
-		int size;
-
-		/* Setting up first argument */
-		emit(ARM_MOV_R(r0, r4), ctx);
-
-		/* Setting up second argument */
-		emit_a32_mov_i(r1, imm, false, ctx);
-		if (BPF_MODE(code) == BPF_IND)
-			emit_a32_alu_r(r1, src_lo, false, sstk, ctx,
-				       false, false, BPF_ADD);
-
-		/* Setting up third argument */
-		switch (BPF_SIZE(code)) {
-		case BPF_W:
-			size = 4;
-			break;
-		case BPF_H:
-			size = 2;
-			break;
-		case BPF_B:
-			size = 1;
-			break;
-		default:
-			return -EINVAL;
-		}
-		emit_a32_mov_i(r2, size, false, ctx);
-
-		/* Setting up fourth argument */
-		emit(ARM_ADD_I(r3, ARM_SP, imm8m(SKB_BUFFER)), ctx);
-
-		/* Setting up function pointer to call */
-		emit_a32_mov_i(r6, (unsigned int)bpf_load_pointer, false, ctx);
-		emit_blx_r(r6, ctx);
-
-		emit(ARM_EOR_R(r1, r1, r1), ctx);
-		/* Check if return address is NULL or not.
-		 * if NULL then jump to epilogue
-		 * else continue to load the value from retn address
-		 */
-		emit(ARM_CMP_I(r0, 0), ctx);
-		jmp_offset = epilogue_offset(ctx);
-		check_imm24(jmp_offset);
-		_emit(ARM_COND_EQ, ARM_B(jmp_offset), ctx);
-
-		/* Load value from the address */
-		switch (BPF_SIZE(code)) {
-		case BPF_W:
-			emit(ARM_LDR_I(r0, r0, 0), ctx);
-			emit_rev32(r0, r0, ctx);
-			break;
-		case BPF_H:
-			emit(ARM_LDRH_I(r0, r0, 0), ctx);
-			emit_rev16(r0, r0, ctx);
-			break;
-		case BPF_B:
-			emit(ARM_LDRB_I(r0, r0, 0), ctx);
-			/* No need to reverse */
-			break;
-		}
-		break;
-	}
 	/* ST: *(size *)(dst + off) = imm */
 	case BPF_ST | BPF_MEM | BPF_W:
 	case BPF_ST | BPF_MEM | BPF_H:
diff --git a/arch/arm64/boot/dts/qcom/apq8096-db820c-pins.dtsi b/arch/arm64/boot/dts/qcom/apq8096-db820c-pins.dtsi
index 24552f19b3fa..6a573875d45a 100644
--- a/arch/arm64/boot/dts/qcom/apq8096-db820c-pins.dtsi
+++ b/arch/arm64/boot/dts/qcom/apq8096-db820c-pins.dtsi
@@ -36,4 +36,30 @@
 			drive-strength = <2>;	/* 2 MA */
 		};
 	};
+
+	blsp1_uart1_default: blsp1_uart1_default {
+		mux {
+			pins = "gpio41", "gpio42", "gpio43", "gpio44";
+			function = "blsp_uart2";
+		};
+
+		config {
+			pins = "gpio41", "gpio42", "gpio43", "gpio44";
+			drive-strength = <16>;
+			bias-disable;
+		};
+	};
+
+	blsp1_uart1_sleep: blsp1_uart1_sleep {
+		mux {
+			pins = "gpio41", "gpio42", "gpio43", "gpio44";
+			function = "gpio";
+		};
+
+		config {
+			pins = "gpio41", "gpio42", "gpio43", "gpio44";
+			drive-strength = <2>;
+			bias-disable;
+		};
+	};
 };
diff --git a/arch/arm64/boot/dts/qcom/apq8096-db820c-pmic-pins.dtsi b/arch/arm64/boot/dts/qcom/apq8096-db820c-pmic-pins.dtsi
index 59b29ddfb6e9..6167af955659 100644
--- a/arch/arm64/boot/dts/qcom/apq8096-db820c-pmic-pins.dtsi
+++ b/arch/arm64/boot/dts/qcom/apq8096-db820c-pmic-pins.dtsi
@@ -14,6 +14,28 @@
 		};
 	};
 
+	bt_en_gpios: bt_en_gpios {
+		pinconf {
+			pins = "gpio19";
+			function = PMIC_GPIO_FUNC_NORMAL;
+			output-low;
+			power-source = <PM8994_GPIO_S4>; // 1.8V
+			qcom,drive-strength = <PMIC_GPIO_STRENGTH_LOW>;
+			bias-pull-down;
+		};
+	};
+
+	wlan_en_gpios: wlan_en_gpios {
+		pinconf {
+			pins = "gpio8";
+			function = PMIC_GPIO_FUNC_NORMAL;
+			output-low;
+			power-source = <PM8994_GPIO_S4>; // 1.8V
+			qcom,drive-strength = <PMIC_GPIO_STRENGTH_LOW>;
+			bias-pull-down;
+		};
+	};
+
 	volume_up_gpio: pm8996_gpio2 {
 		pinconf {
 			pins = "gpio2";
@@ -26,6 +48,16 @@
 		};
 	};
 
+	divclk4_pin_a: divclk4 {
+		pinconf {
+			pins = "gpio18";
+			function = PMIC_GPIO_FUNC_FUNC2;
+
+			bias-disable;
+			power-source = <PM8994_GPIO_S4>;
+		};
+	};
+
 	usb3_vbus_det_gpio: pm8996_gpio22 {
 		pinconf {
 			pins = "gpio22";
diff --git a/arch/arm64/boot/dts/qcom/apq8096-db820c.dtsi b/arch/arm64/boot/dts/qcom/apq8096-db820c.dtsi
index 1c8f1b86472d..4b8bb026346e 100644
--- a/arch/arm64/boot/dts/qcom/apq8096-db820c.dtsi
+++ b/arch/arm64/boot/dts/qcom/apq8096-db820c.dtsi
@@ -23,6 +23,7 @@
 	aliases {
 		serial0 = &blsp2_uart1;
 		serial1 = &blsp2_uart2;
+		serial2 = &blsp1_uart1;
 		i2c0	= &blsp1_i2c2;
 		i2c1	= &blsp2_i2c1;
 		i2c2	= &blsp2_i2c0;
@@ -34,7 +35,36 @@
 		stdout-path = "serial0:115200n8";
 	};
 
+	clocks {
+		divclk4: divclk4 {
+			compatible = "fixed-clock";
+			#clock-cells = <0>;
+			clock-frequency = <32768>;
+			clock-output-names = "divclk4";
+
+			pinctrl-names = "default";
+			pinctrl-0 = <&divclk4_pin_a>;
+		};
+	};
+
 	soc {
+		serial@7570000 {
+			label = "BT-UART";
+			status = "okay";
+			pinctrl-names = "default", "sleep";
+			pinctrl-0 = <&blsp1_uart1_default>;
+			pinctrl-1 = <&blsp1_uart1_sleep>;
+
+			bluetooth {
+				compatible = "qcom,qca6174-bt";
+
+				/* bt_disable_n gpio */
+				enable-gpios = <&pm8994_gpios 19 GPIO_ACTIVE_HIGH>;
+
+				clocks = <&divclk4>;
+			};
+		};
+
 		serial@75b0000 {
 			label = "LS-UART1";
 			status = "okay";
@@ -139,9 +169,40 @@
 			pinctrl-0 = <&usb2_vbus_det_gpio>;
 		};
 
+		bt_en: bt-en-1-8v {
+			pinctrl-names = "default";
+			pinctrl-0 = <&bt_en_gpios>;
+			compatible = "regulator-fixed";
+			regulator-name = "bt-en-regulator";
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <1800000>;
+
+			/* WLAN card specific delay */
+			startup-delay-us = <70000>;
+			enable-active-high;
+		};
+
+		wlan_en: wlan-en-1-8v {
+			pinctrl-names = "default";
+			pinctrl-0 = <&wlan_en_gpios>;
+			compatible = "regulator-fixed";
+			regulator-name = "wlan-en-regulator";
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <1800000>;
+
+			gpio = <&pm8994_gpios 8 0>;
+
+			/* WLAN card specific delay */
+			startup-delay-us = <70000>;
+			enable-active-high;
+		};
+
 		agnoc@0 {
 			qcom,pcie@600000 {
+				status = "okay";
 				perst-gpio = <&msmgpio 35 GPIO_ACTIVE_LOW>;
+				vddpe-supply = <&wlan_en>;
+				vddpe1-supply = <&bt_en>;
 			};
 
 			qcom,pcie@608000 {
diff --git a/arch/arm64/boot/dts/qcom/msm8996.dtsi b/arch/arm64/boot/dts/qcom/msm8996.dtsi
index 410ae787ebb4..f8e49d0b4681 100644
--- a/arch/arm64/boot/dts/qcom/msm8996.dtsi
+++ b/arch/arm64/boot/dts/qcom/msm8996.dtsi
@@ -419,6 +419,16 @@
 			#clock-cells = <1>;
 		};
 
+		blsp1_uart1: serial@7570000 {
+			compatible = "qcom,msm-uartdm-v1.4", "qcom,msm-uartdm";
+			reg = <0x07570000 0x1000>;
+			interrupts = <GIC_SPI 108 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&gcc GCC_BLSP1_UART2_APPS_CLK>,
+				 <&gcc GCC_BLSP1_AHB_CLK>;
+			clock-names = "core", "iface";
+			status = "disabled";
+		};
+
 		blsp1_spi0: spi@7575000 {
 			compatible = "qcom,spi-qup-v2.2.1";
 			reg = <0x07575000 0x600>;
diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index a93350451e8e..a6fdaea07c63 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -21,7 +21,6 @@
 #include <linux/bpf.h>
 #include <linux/filter.h>
 #include <linux/printk.h>
-#include <linux/skbuff.h>
 #include <linux/slab.h>
 
 #include <asm/byteorder.h>
@@ -80,23 +79,66 @@ static inline void emit(const u32 insn, struct jit_ctx *ctx)
 	ctx->idx++;
 }
 
+static inline void emit_a64_mov_i(const int is64, const int reg,
+				  const s32 val, struct jit_ctx *ctx)
+{
+	u16 hi = val >> 16;
+	u16 lo = val & 0xffff;
+
+	if (hi & 0x8000) {
+		if (hi == 0xffff) {
+			emit(A64_MOVN(is64, reg, (u16)~lo, 0), ctx);
+		} else {
+			emit(A64_MOVN(is64, reg, (u16)~hi, 16), ctx);
+			if (lo != 0xffff)
+				emit(A64_MOVK(is64, reg, lo, 0), ctx);
+		}
+	} else {
+		emit(A64_MOVZ(is64, reg, lo, 0), ctx);
+		if (hi)
+			emit(A64_MOVK(is64, reg, hi, 16), ctx);
+	}
+}
+
+static int i64_i16_blocks(const u64 val, bool inverse)
+{
+	return (((val >>  0) & 0xffff) != (inverse ? 0xffff : 0x0000)) +
+	       (((val >> 16) & 0xffff) != (inverse ? 0xffff : 0x0000)) +
+	       (((val >> 32) & 0xffff) != (inverse ? 0xffff : 0x0000)) +
+	       (((val >> 48) & 0xffff) != (inverse ? 0xffff : 0x0000));
+}
+
 static inline void emit_a64_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);
-	tmp >>= 16;
-	shift += 16;
-	while (tmp) {
-		if (tmp & 0xffff)
-			emit(A64_MOVK(1, reg, tmp & 0xffff, shift), ctx);
-		tmp >>= 16;
-		shift += 16;
+	u64 nrm_tmp = val, rev_tmp = ~val;
+	bool inverse;
+	int shift;
+
+	if (!(nrm_tmp >> 32))
+		return emit_a64_mov_i(0, reg, (u32)val, ctx);
+
+	inverse = i64_i16_blocks(nrm_tmp, true) < i64_i16_blocks(nrm_tmp, false);
+	shift = max(round_down((inverse ? (fls64(rev_tmp) - 1) :
+					  (fls64(nrm_tmp) - 1)), 16), 0);
+	if (inverse)
+		emit(A64_MOVN(1, reg, (rev_tmp >> shift) & 0xffff, shift), ctx);
+	else
+		emit(A64_MOVZ(1, reg, (nrm_tmp >> shift) & 0xffff, shift), ctx);
+	shift -= 16;
+	while (shift >= 0) {
+		if (((nrm_tmp >> shift) & 0xffff) != (inverse ? 0xffff : 0x0000))
+			emit(A64_MOVK(1, reg, (nrm_tmp >> shift) & 0xffff, shift), ctx);
+		shift -= 16;
 	}
 }
 
+/*
+ * This is an unoptimized 64 immediate emission used for BPF to BPF call
+ * addresses. It will always do a full 64 bit decomposition as otherwise
+ * more complexity in the last extra pass is required since we previously
+ * reserved 4 instructions for the address.
+ */
 static inline void emit_addr_mov_i64(const int reg, const u64 val,
 				     struct jit_ctx *ctx)
 {
@@ -111,26 +153,6 @@ static inline void emit_addr_mov_i64(const int reg, const u64 val,
 	}
 }
 
-static inline void emit_a64_mov_i(const int is64, const int reg,
-				  const s32 val, struct jit_ctx *ctx)
-{
-	u16 hi = val >> 16;
-	u16 lo = val & 0xffff;
-
-	if (hi & 0x8000) {
-		if (hi == 0xffff) {
-			emit(A64_MOVN(is64, reg, (u16)~lo, 0), ctx);
-		} else {
-			emit(A64_MOVN(is64, reg, (u16)~hi, 16), ctx);
-			emit(A64_MOVK(is64, reg, lo, 0), ctx);
-		}
-	} else {
-		emit(A64_MOVZ(is64, reg, lo, 0), ctx);
-		if (hi)
-			emit(A64_MOVK(is64, reg, hi, 16), ctx);
-	}
-}
-
 static inline int bpf2a64_offset(int bpf_to, int bpf_from,
 				 const struct jit_ctx *ctx)
 {
@@ -163,7 +185,7 @@ static inline int epilogue_offset(const struct jit_ctx *ctx)
 /* Tail call offset to jump into */
 #define PROLOGUE_OFFSET 7
 
-static int build_prologue(struct jit_ctx *ctx)
+static int build_prologue(struct jit_ctx *ctx, bool ebpf_from_cbpf)
 {
 	const struct bpf_prog *prog = ctx->prog;
 	const u8 r6 = bpf2a64[BPF_REG_6];
@@ -188,7 +210,7 @@ static int build_prologue(struct jit_ctx *ctx)
 	 *                        | ... | BPF prog stack
 	 *                        |     |
 	 *                        +-----+ <= (BPF_FP - prog->aux->stack_depth)
-	 *                        |RSVD | JIT scratchpad
+	 *                        |RSVD | padding
 	 * current A64_SP =>      +-----+ <= (BPF_FP - ctx->stack_size)
 	 *                        |     |
 	 *                        | ... | Function call stack
@@ -210,19 +232,19 @@ static int build_prologue(struct jit_ctx *ctx)
 	/* Set up BPF prog stack base register */
 	emit(A64_MOV(1, fp, A64_SP), ctx);
 
-	/* Initialize tail_call_cnt */
-	emit(A64_MOVZ(1, tcc, 0, 0), ctx);
+	if (!ebpf_from_cbpf) {
+		/* Initialize tail_call_cnt */
+		emit(A64_MOVZ(1, tcc, 0, 0), ctx);
 
-	cur_offset = ctx->idx - idx0;
-	if (cur_offset != PROLOGUE_OFFSET) {
-		pr_err_once("PROLOGUE_OFFSET = %d, expected %d!\n",
-			    cur_offset, PROLOGUE_OFFSET);
-		return -1;
+		cur_offset = ctx->idx - idx0;
+		if (cur_offset != PROLOGUE_OFFSET) {
+			pr_err_once("PROLOGUE_OFFSET = %d, expected %d!\n",
+				    cur_offset, PROLOGUE_OFFSET);
+			return -1;
+		}
 	}
 
-	/* 4 byte extra for skb_copy_bits buffer */
-	ctx->stack_size = prog->aux->stack_depth + 4;
-	ctx->stack_size = STACK_ALIGN(ctx->stack_size);
+	ctx->stack_size = STACK_ALIGN(prog->aux->stack_depth);
 
 	/* Set up function call stack */
 	emit(A64_SUB_I(1, A64_SP, A64_SP, ctx->stack_size), ctx);
@@ -723,71 +745,6 @@ emit_cond_jmp:
 		emit(A64_CBNZ(0, tmp3, jmp_offset), ctx);
 		break;
 
-	/* R0 = ntohx(*(size *)(((struct sk_buff *)R6)->data + imm)) */
-	case BPF_LD | BPF_ABS | BPF_W:
-	case BPF_LD | BPF_ABS | BPF_H:
-	case BPF_LD | BPF_ABS | BPF_B:
-	/* R0 = ntohx(*(size *)(((struct sk_buff *)R6)->data + src + imm)) */
-	case BPF_LD | BPF_IND | BPF_W:
-	case BPF_LD | BPF_IND | BPF_H:
-	case BPF_LD | BPF_IND | BPF_B:
-	{
-		const u8 r0 = bpf2a64[BPF_REG_0]; /* r0 = return value */
-		const u8 r6 = bpf2a64[BPF_REG_6]; /* r6 = pointer to sk_buff */
-		const u8 fp = bpf2a64[BPF_REG_FP];
-		const u8 r1 = bpf2a64[BPF_REG_1]; /* r1: struct sk_buff *skb */
-		const u8 r2 = bpf2a64[BPF_REG_2]; /* r2: int k */
-		const u8 r3 = bpf2a64[BPF_REG_3]; /* r3: unsigned int size */
-		const u8 r4 = bpf2a64[BPF_REG_4]; /* r4: void *buffer */
-		const u8 r5 = bpf2a64[BPF_REG_5]; /* r5: void *(*func)(...) */
-		int size;
-
-		emit(A64_MOV(1, r1, r6), ctx);
-		emit_a64_mov_i(0, r2, imm, ctx);
-		if (BPF_MODE(code) == BPF_IND)
-			emit(A64_ADD(0, r2, r2, src), ctx);
-		switch (BPF_SIZE(code)) {
-		case BPF_W:
-			size = 4;
-			break;
-		case BPF_H:
-			size = 2;
-			break;
-		case BPF_B:
-			size = 1;
-			break;
-		default:
-			return -EINVAL;
-		}
-		emit_a64_mov_i64(r3, size, ctx);
-		emit(A64_SUB_I(1, r4, fp, ctx->stack_size), ctx);
-		emit_a64_mov_i64(r5, (unsigned long)bpf_load_pointer, ctx);
-		emit(A64_BLR(r5), ctx);
-		emit(A64_MOV(1, r0, A64_R(0)), ctx);
-
-		jmp_offset = epilogue_offset(ctx);
-		check_imm19(jmp_offset);
-		emit(A64_CBZ(1, r0, jmp_offset), ctx);
-		emit(A64_MOV(1, r5, r0), ctx);
-		switch (BPF_SIZE(code)) {
-		case BPF_W:
-			emit(A64_LDR32(r0, r5, A64_ZR), ctx);
-#ifndef CONFIG_CPU_BIG_ENDIAN
-			emit(A64_REV32(0, r0, r0), ctx);
-#endif
-			break;
-		case BPF_H:
-			emit(A64_LDRH(r0, r5, A64_ZR), ctx);
-#ifndef CONFIG_CPU_BIG_ENDIAN
-			emit(A64_REV16(0, r0, r0), ctx);
-#endif
-			break;
-		case BPF_B:
-			emit(A64_LDRB(r0, r5, A64_ZR), ctx);
-			break;
-		}
-		break;
-	}
 	default:
 		pr_err_once("unknown opcode %02x\n", code);
 		return -EINVAL;
@@ -851,6 +808,7 @@ 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 was_classic = bpf_prog_was_classic(prog);
 	bool tmp_blinded = false;
 	bool extra_pass = false;
 	struct jit_ctx ctx;
@@ -905,7 +863,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 		goto out_off;
 	}
 
-	if (build_prologue(&ctx)) {
+	if (build_prologue(&ctx, was_classic)) {
 		prog = orig_prog;
 		goto out_off;
 	}
@@ -928,7 +886,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 skip_init_ctx:
 	ctx.idx = 0;
 
-	build_prologue(&ctx);
+	build_prologue(&ctx, was_classic);
 
 	if (build_body(&ctx)) {
 		bpf_jit_binary_free(header);
diff --git a/arch/mips/net/ebpf_jit.c b/arch/mips/net/ebpf_jit.c
index 3e2798bfea4f..aeb7b1b0f202 100644
--- a/arch/mips/net/ebpf_jit.c
+++ b/arch/mips/net/ebpf_jit.c
@@ -95,7 +95,6 @@ enum reg_val_type {
  * struct jit_ctx - JIT context
  * @skf:		The sk_filter
  * @stack_size:		eBPF stack size
- * @tmp_offset:		eBPF $sp offset to 8-byte temporary memory
  * @idx:		Instruction index
  * @flags:		JIT flags
  * @offsets:		Instruction offsets
@@ -105,7 +104,6 @@ enum reg_val_type {
 struct jit_ctx {
 	const struct bpf_prog *skf;
 	int stack_size;
-	int tmp_offset;
 	u32 idx;
 	u32 flags;
 	u32 *offsets;
@@ -293,7 +291,6 @@ static int gen_int_prologue(struct jit_ctx *ctx)
 	locals_size = (ctx->flags & EBPF_SEEN_FP) ? MAX_BPF_STACK : 0;
 
 	stack_adjust += locals_size;
-	ctx->tmp_offset = locals_size;
 
 	ctx->stack_size = stack_adjust;
 
@@ -399,7 +396,6 @@ static void gen_imm_to_reg(const struct bpf_insn *insn, int reg,
 		emit_instr(ctx, lui, reg, upper >> 16);
 		emit_instr(ctx, addiu, reg, reg, lower);
 	}
-
 }
 
 static int gen_imm_insn(const struct bpf_insn *insn, struct jit_ctx *ctx,
@@ -547,28 +543,6 @@ static int gen_imm_insn(const struct bpf_insn *insn, struct jit_ctx *ctx,
 	return 0;
 }
 
-static void * __must_check
-ool_skb_header_pointer(const struct sk_buff *skb, int offset,
-		       int len, void *buffer)
-{
-	return skb_header_pointer(skb, offset, len, buffer);
-}
-
-static int size_to_len(const struct bpf_insn *insn)
-{
-	switch (BPF_SIZE(insn->code)) {
-	case BPF_B:
-		return 1;
-	case BPF_H:
-		return 2;
-	case BPF_W:
-		return 4;
-	case BPF_DW:
-		return 8;
-	}
-	return 0;
-}
-
 static void emit_const_to_reg(struct jit_ctx *ctx, int dst, u64 value)
 {
 	if (value >= 0xffffffffffff8000ull || value < 0x8000ull) {
@@ -1267,110 +1241,6 @@ jeq_common:
 			return -EINVAL;
 		break;
 
-	case BPF_LD | BPF_B | BPF_ABS:
-	case BPF_LD | BPF_H | BPF_ABS:
-	case BPF_LD | BPF_W | BPF_ABS:
-	case BPF_LD | BPF_DW | BPF_ABS:
-		ctx->flags |= EBPF_SAVE_RA;
-
-		gen_imm_to_reg(insn, MIPS_R_A1, ctx);
-		emit_instr(ctx, addiu, MIPS_R_A2, MIPS_R_ZERO, size_to_len(insn));
-
-		if (insn->imm < 0) {
-			emit_const_to_reg(ctx, MIPS_R_T9, (u64)bpf_internal_load_pointer_neg_helper);
-		} else {
-			emit_const_to_reg(ctx, MIPS_R_T9, (u64)ool_skb_header_pointer);
-			emit_instr(ctx, daddiu, MIPS_R_A3, MIPS_R_SP, ctx->tmp_offset);
-		}
-		goto ld_skb_common;
-
-	case BPF_LD | BPF_B | BPF_IND:
-	case BPF_LD | BPF_H | BPF_IND:
-	case BPF_LD | BPF_W | BPF_IND:
-	case BPF_LD | BPF_DW | BPF_IND:
-		ctx->flags |= EBPF_SAVE_RA;
-		src = ebpf_to_mips_reg(ctx, insn, src_reg_no_fp);
-		if (src < 0)
-			return src;
-		ts = get_reg_val_type(ctx, this_idx, insn->src_reg);
-		if (ts == REG_32BIT_ZERO_EX) {
-			/* sign extend */
-			emit_instr(ctx, sll, MIPS_R_A1, src, 0);
-			src = MIPS_R_A1;
-		}
-		if (insn->imm >= S16_MIN && insn->imm <= S16_MAX) {
-			emit_instr(ctx, daddiu, MIPS_R_A1, src, insn->imm);
-		} else {
-			gen_imm_to_reg(insn, MIPS_R_AT, ctx);
-			emit_instr(ctx, daddu, MIPS_R_A1, MIPS_R_AT, src);
-		}
-		/* truncate to 32-bit int */
-		emit_instr(ctx, sll, MIPS_R_A1, MIPS_R_A1, 0);
-		emit_instr(ctx, daddiu, MIPS_R_A3, MIPS_R_SP, ctx->tmp_offset);
-		emit_instr(ctx, slt, MIPS_R_AT, MIPS_R_A1, MIPS_R_ZERO);
-
-		emit_const_to_reg(ctx, MIPS_R_T8, (u64)bpf_internal_load_pointer_neg_helper);
-		emit_const_to_reg(ctx, MIPS_R_T9, (u64)ool_skb_header_pointer);
-		emit_instr(ctx, addiu, MIPS_R_A2, MIPS_R_ZERO, size_to_len(insn));
-		emit_instr(ctx, movn, MIPS_R_T9, MIPS_R_T8, MIPS_R_AT);
-
-ld_skb_common:
-		emit_instr(ctx, jalr, MIPS_R_RA, MIPS_R_T9);
-		/* delay slot move */
-		emit_instr(ctx, daddu, MIPS_R_A0, MIPS_R_S0, MIPS_R_ZERO);
-
-		/* Check the error value */
-		b_off = b_imm(exit_idx, ctx);
-		if (is_bad_offset(b_off)) {
-			target = j_target(ctx, exit_idx);
-			if (target == (unsigned int)-1)
-				return -E2BIG;
-
-			if (!(ctx->offsets[this_idx] & OFFSETS_B_CONV)) {
-				ctx->offsets[this_idx] |= OFFSETS_B_CONV;
-				ctx->long_b_conversion = 1;
-			}
-			emit_instr(ctx, bne, MIPS_R_V0, MIPS_R_ZERO, 4 * 3);
-			emit_instr(ctx, nop);
-			emit_instr(ctx, j, target);
-			emit_instr(ctx, nop);
-		} else {
-			emit_instr(ctx, beq, MIPS_R_V0, MIPS_R_ZERO, b_off);
-			emit_instr(ctx, nop);
-		}
-
-#ifdef __BIG_ENDIAN
-		need_swap = false;
-#else
-		need_swap = true;
-#endif
-		dst = MIPS_R_V0;
-		switch (BPF_SIZE(insn->code)) {
-		case BPF_B:
-			emit_instr(ctx, lbu, dst, 0, MIPS_R_V0);
-			break;
-		case BPF_H:
-			emit_instr(ctx, lhu, dst, 0, MIPS_R_V0);
-			if (need_swap)
-				emit_instr(ctx, wsbh, dst, dst);
-			break;
-		case BPF_W:
-			emit_instr(ctx, lw, dst, 0, MIPS_R_V0);
-			if (need_swap) {
-				emit_instr(ctx, wsbh, dst, dst);
-				emit_instr(ctx, rotr, dst, dst, 16);
-			}
-			break;
-		case BPF_DW:
-			emit_instr(ctx, ld, dst, 0, MIPS_R_V0);
-			if (need_swap) {
-				emit_instr(ctx, dsbh, dst, dst);
-				emit_instr(ctx, dshd, dst, dst);
-			}
-			break;
-		}
-
-		break;
 	case BPF_ALU | BPF_END | BPF_FROM_BE:
 	case BPF_ALU | BPF_END | BPF_FROM_LE:
 		dst = ebpf_to_mips_reg(ctx, insn, dst_reg);
diff --git a/arch/powerpc/net/Makefile b/arch/powerpc/net/Makefile
index 02d369ca6a53..809f019d3cba 100644
--- a/arch/powerpc/net/Makefile
+++ b/arch/powerpc/net/Makefile
@@ -3,7 +3,7 @@
 # Arch-specific network modules
 #
 ifeq ($(CONFIG_PPC64),y)
-obj-$(CONFIG_BPF_JIT) += bpf_jit_asm64.o bpf_jit_comp64.o
+obj-$(CONFIG_BPF_JIT) += bpf_jit_comp64.o
 else
 obj-$(CONFIG_BPF_JIT) += bpf_jit_asm.o bpf_jit_comp.o
 endif
diff --git a/arch/powerpc/net/bpf_jit64.h b/arch/powerpc/net/bpf_jit64.h
index 8bdef7ed28a8..3609be4692b3 100644
--- a/arch/powerpc/net/bpf_jit64.h
+++ b/arch/powerpc/net/bpf_jit64.h
@@ -20,7 +20,7 @@
  * with our redzone usage.
  *
  *		[	prev sp		] <-------------
- *		[   nv gpr save area	] 8*8		|