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

Minor conflict, a CHECK was placed into an if() statement
in net-next, whilst a newline was added to that CHECK
call in 'net'.  Thanks to Daniel for the merge resolution.

Signed-off-by: David S. Miller <davem@davemloft.net>

21 files changed, 2602 insertions, 1467 deletions

diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c
index b5030e1a41d8..82689b999257 100644
--- a/arch/arm/net/bpf_jit_32.c
+++ b/arch/arm/net/bpf_jit_32.c
@@ -1452,83 +1452,6 @@ 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/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index a93350451e8e..0b40c8fb0706 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -723,71 +723,6 @@ 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;
diff --git a/arch/mips/net/ebpf_jit.c b/arch/mips/net/ebpf_jit.c
index 3e2798bfea4f..7ba7df9c28fc 100644
--- a/arch/mips/net/ebpf_jit.c
+++ b/arch/mips/net/ebpf_jit.c
@@ -1267,110 +1267,6 @@ 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		|
+ *		[   nv gpr save area	] 6*8		|
  *		[    tail_call_cnt	] 8		|
  *		[    local_tmp_var	] 8		|
  * fp (r31) -->	[   ebpf stack space	] upto 512	|
@@ -28,8 +28,8 @@
  * sp (r1) --->	[    stack pointer	] --------------
  */
 
-/* for gpr non volatile registers BPG_REG_6 to 10, plus skb cache registers */
-#define BPF_PPC_STACK_SAVE	(8*8)
+/* for gpr non volatile registers BPG_REG_6 to 10 */
+#define BPF_PPC_STACK_SAVE	(6*8)
 /* for bpf JIT code internal usage */
 #define BPF_PPC_STACK_LOCALS	16
 /* stack frame excluding BPF stack, ensure this is quadword aligned */
@@ -39,10 +39,8 @@
 #ifndef __ASSEMBLY__
 
 /* BPF register usage */
-#define SKB_HLEN_REG	(MAX_BPF_JIT_REG + 0)
-#define SKB_DATA_REG	(MAX_BPF_JIT_REG + 1)
-#define TMP_REG_1	(MAX_BPF_JIT_REG + 2)
-#define TMP_REG_2	(MAX_BPF_JIT_REG + 3)
+#define TMP_REG_1	(MAX_BPF_JIT_REG + 0)
+#define TMP_REG_2	(MAX_BPF_JIT_REG + 1)
 
 /* BPF to ppc register mappings */
 static const int b2p[] = {
@@ -63,40 +61,23 @@ static const int b2p[] = {
 	[BPF_REG_FP] = 31,
 	/* eBPF jit internal registers */
 	[BPF_REG_AX] = 2,
-	[SKB_HLEN_REG] = 25,
-	[SKB_DATA_REG] = 26,
 	[TMP_REG_1] = 9,
 	[TMP_REG_2] = 10
 };
 
-/* PPC NVR range -- update this if we ever use NVRs below r24 */
-#define BPF_PPC_NVR_MIN		24
-
-/* Assembly helpers */
-#define DECLARE_LOAD_FUNC(func)	u64 func(u64 r3, u64 r4);			\
-				u64 func##_negative_offset(u64 r3, u64 r4);	\
-				u64 func##_positive_offset(u64 r3, u64 r4);
-
-DECLARE_LOAD_FUNC(sk_load_word);
-DECLARE_LOAD_FUNC(sk_load_half);
-DECLARE_LOAD_FUNC(sk_load_byte);
-
-#define CHOOSE_LOAD_FUNC(imm, func)						\
-			(imm < 0 ?						\
-			(imm >= SKF_LL_OFF ? func##_negative_offset : func) :	\
-			func##_positive_offset)
+/* PPC NVR range -- update this if we ever use NVRs below r27 */
+#define BPF_PPC_NVR_MIN		27
 
 #define SEEN_FUNC	0x1000 /* might call external helpers */
 #define SEEN_STACK	0x2000 /* uses BPF stack */
-#define SEEN_SKB	0x4000 /* uses sk_buff */
-#define SEEN_TAILCALL	0x8000 /* uses tail calls */
+#define SEEN_TAILCALL	0x4000 /* uses tail calls */
 
 struct codegen_context {
 	/*
 	 * This is used to track register usage as well
 	 * as calls to external helpers.
 	 * - register usage is tracked with corresponding
-	 *   bits (r3-r10 and r25-r31)
+	 *   bits (r3-r10 and r27-r31)
 	 * - rest of the bits can be used to track other
 	 *   things -- for now, we use bits 16 to 23
 	 *   encoded in SEEN_* macros above
diff --git a/arch/powerpc/net/bpf_jit_asm64.S b/arch/powerpc/net/bpf_jit_asm64.S
deleted file mode 100644
index 7e4c51430b84..000000000000
--- a/arch/powerpc/net/bpf_jit_asm64.S
+++ /dev/null
@@ -1,180 +0,0 @@
-/*
- * bpf_jit_asm64.S: Packet/header access helper functions
- * for PPC64 BPF compiler.
- *
- * Copyright 2016, Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
- * 		   IBM Corporation
- *
- * Based on bpf_jit_asm.S by Matt Evans
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; version 2
- * of the License.
- */
-
-#include <asm/ppc_asm.h>
-#include <asm/ptrace.h>
-#include "bpf_jit64.h"
-
-/*
- * All of these routines are called directly from generated code,
- * with the below register usage:
- * r27		skb pointer (ctx)
- * r25		skb header length
- * r26		skb->data pointer
- * r4		offset
- *
- * Result is passed back in:
- * r8		data read in host endian format (accumulator)
- *
- * r9 is used as a temporary register
- */
-
-#define r_skb	r27
-#define r_hlen	r25
-#define r_data	r26
-#define r_off	r4
-#define r_val	r8
-#define r_tmp	r9
-
-_GLOBAL_TOC(sk_load_word)
-	cmpdi	r_off, 0
-	blt	bpf_slow_path_word_neg
-	b	sk_load_word_positive_offset
-
-_GLOBAL_TOC(sk_load_word_positive_offset)
-	/* Are we accessing past headlen? */
-	subi	r_tmp, r_hlen, 4
-	cmpd	r_tmp, r_off
-	blt	bpf_slow_path_word
-	/* Nope, just hitting the header.  cr0 here is eq or gt! */
-	LWZX_BE	r_val, r_data, r_off
-	blr	/* Return success, cr0 != LT */
-
-_GLOBAL_TOC(sk_load_half)
-	cmpdi	r_off, 0
-	blt	bpf_slow_path_half_neg
-	b	sk_load_half_positive_offset
-
-_GLOBAL_TOC(sk_load_half_positive_offset)
-	subi	r_tmp, r_hlen, 2
-	cmpd	r_tmp, r_off
-	blt	bpf_slow_path_half
-	LHZX_BE	r_val, r_data, r_off
-	blr
-
-_GLOBAL_TOC(sk_load_byte)
-	cmpdi	r_off, 0
-	blt	bpf_slow_path_byte_neg
-	b	sk_load_byte_positive_offset
-
-_GLOBAL_TOC(sk_load_byte_positive_offset)
-	cmpd	r_hlen, r_off
-	ble	bpf_slow_path_byte
-	lbzx	r_val, r_data, r_off
-	blr
-
-/*
- * Call out to skb_copy_bits:
- * Allocate a new stack frame here to remain ABI-compliant in
- * stashing LR.
- */
-#define bpf_slow_path_common(SIZE)					\
-	mflr	r0;							\
-	std	r0, PPC_LR_STKOFF(r1);					\
-	stdu	r1, -(STACK_FRAME_MIN_SIZE + BPF_PPC_STACK_LOCALS)(r1);	\
-	mr	r3, r_skb;						\
-	/* r4 = r_off as passed */					\
-	addi	r5, r1, STACK_FRAME_MIN_SIZE;				\
-	li	r6, SIZE;						\
-	bl	skb_copy_bits;						\
-	nop;								\
-	/* save r5 */							\
-	addi	r5, r1, STACK_FRAME_MIN_SIZE;				\
-	/* r3 = 0 on success */						\
-	addi	r1, r1, STACK_FRAME_MIN_SIZE + BPF_PPC_STACK_LOCALS;	\
-	ld	r0, PPC_LR_STKOFF(r1);					\
-	mtlr	r0;							\
-	cmpdi	r3, 0;							\
-	blt	bpf_error;	/* cr0 = LT */
-
-bpf_slow_path_word:
-	bpf_slow_path_common(4)
-	/* Data value is on stack, and cr0 != LT */
-	LWZX_BE	r_val, 0, r5
-	blr
-
-bpf_slow_path_half:
-	bpf_slow_path_common(2)
-	LHZX_BE	r_val, 0, r5
-	blr
-
-bpf_slow_path_byte:
-	bpf_slow_path_common(1)
-	lbzx	r_val, 0, r5
-	blr
-
-/*
- * Call out to bpf_internal_load_pointer_neg_helper
- */
-#define sk_negative_common(SIZE)				\
-	mflr	r0;						\
-	std	r0, PPC_LR_STKOFF(r1);				\
-	stdu	r1, -STACK_FRAME_MIN_SIZE(r1);			\
-	mr	r3, r_skb;					\
-	/* r4 = r_off, as passed */				\
-	li	r5, SIZE;					\
-	bl	bpf_internal_load_pointer_neg_helper;		\
-	nop;							\
-	addi	r1, r1, STACK_FRAME_MIN_SIZE;			\
-	ld	r0, PPC_LR_STKOFF(r1);				\
-	mtlr	r0;						\
-	/* R3 != 0 on success */				\
-	cmpldi	r3, 0;						\
-	beq	bpf_error_slow;	/* cr0 = EQ */
-
-bpf_slow_path_word_neg:
-	lis     r_tmp, -32	/* SKF_LL_OFF */
-	cmpd	r_off, r_tmp	/* addr < SKF_* */
-	blt	bpf_error	/* cr0 = LT */
-	b	sk_load_word_negative_offset
-
-_GLOBAL_TOC(sk_load_word_negative_offset)
-	sk_negative_common(4)
-	LWZX_BE	r_val, 0, r3
-	blr
-
-bpf_slow_path_half_neg:
-	lis     r_tmp, -32	/* SKF_LL_OFF */
-	cmpd	r_off, r_tmp	/* addr < SKF_* */
-	blt	bpf_error	/* cr0 = LT */
-	b	sk_load_half_negative_offset
-
-_GLOBAL_TOC(sk_load_half_negative_offset)
-	sk_negative_common(2)
-	LHZX_BE	r_val, 0, r3
-	blr
-
-bpf_slow_path_byte_neg:
-	lis     r_tmp, -32	/* SKF_LL_OFF */
-	cmpd	r_off, r_tmp	/* addr < SKF_* */
-	blt	bpf_error	/* cr0 = LT */
-	b	sk_load_byte_negative_offset
-
-_GLOBAL_TOC(sk_load_byte_negative_offset)
-	sk_negative_common(1)
-	lbzx	r_val, 0, r3
-	blr
-
-bpf_error_slow:
-	/* fabricate a cr0 = lt */
-	li	r_tmp, -1
-	cmpdi	r_tmp, 0
-bpf_error:
-	/*
-	 * Entered with cr0 = lt
-	 * Generated code will 'blt epilogue', returning 0.
-	 */
-	li	r_val, 0
-	blr
diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c
index 0ef3d9580e98..1bdb1aff0619 100644
--- a/arch/powerpc/net/bpf_jit_comp64.c
+++ b/arch/powerpc/net/bpf_jit_comp64.c
@@ -59,7 +59,7 @@ static inline bool bpf_has_stack_frame(struct codegen_context *ctx)
  *		[	prev sp		] <-------------
  *		[	  ...       	] 		|
  * sp (r1) --->	[    stack pointer	] --------------
- *		[   nv gpr save area	] 8*8
+ *		[   nv gpr save area	] 6*8
  *		[    tail_call_cnt	] 8
  *		[    local_tmp_var	] 8
  *		[   unused red zone	] 208 bytes protected
@@ -88,21 +88,6 @@ static int bpf_jit_stack_offsetof(struct codegen_context *ctx, int reg)
 	BUG();
 }
 
-static void bpf_jit_emit_skb_loads(u32 *image, struct codegen_context *ctx)
-{
-	/*
-	 * Load skb->len and skb->data_len
-	 * r3 points to skb
-	 */
-	PPC_LWZ(b2p[SKB_HLEN_REG], 3, offsetof(struct sk_buff, len));
-	PPC_LWZ(b2p[TMP_REG_1], 3, offsetof(struct sk_buff, data_len));
-	/* header_len = len - data_len */
-	PPC_SUB(b2p[SKB_HLEN_REG], b2p[SKB_HLEN_REG], b2p[TMP_REG_1]);
-
-	/* skb->data pointer */
-	PPC_BPF_LL(b2p[SKB_DATA_REG], 3, offsetof(struct sk_buff, data));
-}
-
 static void bpf_jit_build_prologue(u32 *image, struct codegen_context *ctx)
 {
 	int i;
@@ -145,18 +130,6 @@ static void bpf_jit_build_prologue(u32 *image, struct codegen_context *ctx)
 		if (bpf_is_seen_register(ctx, i))
 			PPC_BPF_STL(b2p[i], 1, bpf_jit_stack_offsetof(ctx, b2p[i]));
 
-	/*
-	 * Save additional non-volatile regs if we cache skb
-	 * Also, setup skb data
-	 */
-	if (ctx->seen & SEEN_SKB) {
-		PPC_BPF_STL(b2p[SKB_HLEN_REG], 1,
-				bpf_jit_stack_offsetof(ctx, b2p[SKB_HLEN_REG]));
-		PPC_BPF_STL(b2p[SKB_DATA_REG], 1,
-				bpf_jit_stack_offsetof(ctx, b2p[SKB_DATA_REG]));
-		bpf_jit_emit_skb_loads(image, ctx);
-	}
-
 	/* Setup frame pointer to point to the bpf stack area */
 	if (bpf_is_seen_register(ctx, BPF_REG_FP))
 		PPC_ADDI(b2p[BPF_REG_FP], 1,
@@ -172,14 +145,6 @@ static void bpf_jit_emit_common_epilogue(u32 *image, struct codegen_context *ctx
 		if (bpf_is_seen_register(ctx, i))
 			PPC_BPF_LL(b2p[i], 1, bpf_jit_stack_offsetof(ctx, b2p[i]));
 
-	/* Restore non-volatile registers used for skb cache */
-	if (ctx->seen & SEEN_SKB) {
-		PPC_BPF_LL(b2p[SKB_HLEN_REG], 1,
-				bpf_jit_stack_offsetof(ctx, b2p[SKB_HLEN_REG]));
-		PPC_BPF_LL(b2p[SKB_DATA_REG], 1,
-				bpf_jit_stack_offsetof(ctx, b2p[SKB_DATA_REG]));
-	}
-
 	/* Tear down our stack frame */
 	if (bpf_has_stack_frame(ctx)) {
 		PPC_ADDI(1, 1, BPF_PPC_STACKFRAME + ctx->stack_size);
@@ -753,23 +718,10 @@ emit_clear:
 			ctx->seen |= SEEN_FUNC;
 			func = (u8 *) __bpf_call_base + imm;
 
-			/* Save skb pointer if we need to re-cache skb data */
-			if ((ctx->seen & SEEN_SKB) &&
-			    bpf_helper_changes_pkt_data(func))
-				PPC_BPF_STL(3, 1, bpf_jit_stack_local(ctx));
-
 			bpf_jit_emit_func_call(image, ctx, (u64)func);
 
 			/* move return value from r3 to BPF_REG_0 */
 			PPC_MR(b2p[BPF_REG_0], 3);
-
-			/* refresh skb cache */
-			if ((ctx->seen & SEEN_SKB) &&
-			    bpf_helper_changes_pkt_data(func)) {
-				/* reload skb pointer to r3 */
-				PPC_BPF_LL(3, 1, bpf_jit_stack_local(ctx));
-				bpf_jit_emit_skb_loads(image, ctx);
-			}
 			break;
 
 		/*
@@ -887,65 +839,6 @@ cond_branch:
 			break;
 
 		/*
-		 * Loads from packet header/data
-		 * Assume 32-bit input value in imm and X (src_reg)
-		 */
-
-		/* Absolute loads */
-		case BPF_LD | BPF_W | BPF_ABS:
-			func = (u8 *)CHOOSE_LOAD_FUNC(imm, sk_load_word);
-			goto common_load_abs;
-		case BPF_LD | BPF_H | BPF_ABS:
-			func = (u8 *)CHOOSE_LOAD_FUNC(imm, sk_load_half);
-			goto common_load_abs;
-		case BPF_LD | BPF_B | BPF_ABS:
-			func = (u8 *)CHOOSE_LOAD_FUNC(imm, sk_load_byte);
-common_load_abs:
-			/*
-			 * Load from [imm]
-			 * Load into r4, which can just be passed onto
-			 *  skb load helpers as the second parameter
-			 */
-			PPC_LI32(4, imm);
-			goto common_load;
-
-		/* Indirect loads */
-		case BPF_LD | BPF_W | BPF_IND:
-			func = (u8 *)sk_load_word;
-			goto common_load_ind;
-		case BPF_LD | BPF_H | BPF_IND:
-			func = (u8 *)sk_load_half;
-			goto common_load_ind;
-		case BPF_LD | BPF_B | BPF_IND:
-			func = (u8 *)sk_load_byte;
-common_load_ind:
-			/*
-			 * Load from [src_reg + imm]
-			 * Treat src_reg as a 32-bit value
-			 */
-			PPC_EXTSW(4, src_reg);
-			if (imm) {
-				if (imm >= -32768 && imm < 32768)
-					PPC_ADDI(4, 4, IMM_L(imm));
-				else {
-					PPC_LI32(b2p[TMP_REG_1], imm);
-					PPC_ADD(4, 4, b2p[TMP_REG_1]);
-				}
-			}
-
-common_load:
-			ctx->seen |= SEEN_SKB;
-			ctx->seen |= SEEN_FUNC;
-			bpf_jit_emit_func_call(image, ctx, (u64)func);
-
-			/*
-			 * Helper returns 'lt' condition on error, and an
-			 * appropriate return value in BPF_REG_0
-			 */
-			PPC_BCC(COND_LT, exit_addr);
-			break;
-
-		/*
 		 * Tail call
 		 */
 		case BPF_JMP | BPF_TAIL_CALL:
diff --git a/arch/s390/net/Makefile b/arch/s390/net/Makefile
index e0d5f245e42b..d4663b4bf509 100644
--- a/arch/s390/net/Makefile
+++ b/arch/s390/net/Makefile
@@ -2,4 +2,4 @@
 #
 # Arch-specific network modules
 #
-obj-$(CONFIG_BPF_JIT) += bpf_jit.o bpf_jit_comp.o
+obj-$(CONFIG_BPF_JIT) += bpf_jit_comp.o
diff --git a/arch/s390/net/bpf_jit.S b/arch/s390/net/bpf_jit.S
deleted file mode 100644
index 25bb4643c4f4..000000000000
--- a/arch/s390/net/bpf_jit.S
+++ /dev/null
@@ -1,116 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * BPF Jit compiler for s390, help functions.
- *
- * Copyright IBM Corp. 2012,2015
- *
- * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>
- *	      Michael Holzheu <holzheu@linux.vnet.ibm.com>
- */
-
-#include <linux/linkage.h>
-#include "bpf_jit.h"
-
-/*
- * Calling convention:
- * registers %r7-%r10, %r11,%r13, and %r15 are call saved
- *
- * Input (64 bit):
- *   %r3 (%b2) = offset into skb data
- *   %r6 (%b5) = return address
- *   %r7 (%b6) = skb pointer
- *   %r12      = skb data pointer
- *
- * Output:
- *   %r14= %b0 = return value (read skb value)
- *
- * Work registers: %r2,%r4,%r5,%r14
- *
- * skb_copy_bits takes 4 parameters:
- *   %r2 = skb pointer
- *   %r3 = offset into skb data
- *   %r4 = pointer to temp buffer
- *   %r5 = length to copy
- *   Return value in %r2: 0 = ok
- *
- * bpf_internal_load_pointer_neg_helper takes 3 parameters:
- *   %r2 = skb pointer
- *   %r3 = offset into data
- *   %r4 = length to copy
- *   Return value in %r2: Pointer to data
- */
-
-#define SKF_MAX_NEG_OFF	-0x200000	/* SKF_LL_OFF from filter.h */
-
-/*
- * Load SIZE bytes from SKB
- */
-#define sk_load_common(NAME, SIZE, LOAD)				\
-ENTRY(sk_load_##NAME);							\
-	ltgr	%r3,%r3;		/* Is offset negative? */	\
-	jl	sk_load_##NAME##_slow_neg;				\
-ENTRY(sk_load_##NAME##_pos);						\
-	aghi	%r3,SIZE;		/* Offset + SIZE */		\
-	clg	%r3,STK_OFF_HLEN(%r15);	/* Offset + SIZE > hlen? */	\
-	jh	sk_load_##NAME##_slow;					\
-	LOAD	%r14,-SIZE(%r3,%r12);	/* Get data from skb */		\
-	b	OFF_OK(%r6);		/* Return */			\
-									\
-sk_load_##NAME##_slow:;							\
-	lgr	%r2,%r7;		/* Arg1 = skb pointer */	\
-	aghi	%r3,-SIZE;		/* Arg2 = offset */		\
-	la	%r4,STK_OFF_TMP(%r15);	/* Arg3 = temp bufffer */	\
-	lghi	%r5,SIZE;		/* Arg4 = size */		\
-	brasl	%r14,skb_copy_bits;	/* Get data from skb */		\
-	LOAD	%r14,STK_OFF_TMP(%r15);	/* Load from temp bufffer */	\
-	ltgr	%r2,%r2;		/* Set cc to (%r2 != 0) */	\
-	br	%r6;			/* Return */
-
-sk_load_common(word, 4, llgf)	/* r14 = *(u32 *) (skb->data+offset) */
-sk_load_common(half, 2, llgh)	/* r14 = *(u16 *) (skb->data+offset) */
-
-/*
- * Load 1 byte from SKB (optimized version)
- */
-	/* r14 = *(u8 *) (skb->data+offset) */
-ENTRY(sk_load_byte)
-	ltgr	%r3,%r3			# Is offset negative?
-	jl	sk_load_byte_slow_neg
-ENTRY(sk_load_byte_pos)
-	clg	%r3,STK_OFF_HLEN(%r15)	# Offset >= hlen?
-	jnl	sk_load_byte_slow
-	llgc	%r14,0(%r3,%r12)	# Get byte from skb
-	b	OFF_OK(%r6)		# Return OK
-
-sk_load_byte_slow:
-	lgr	%r2,%r7			# Arg1 = skb pointer
-					# Arg2 = offset
-	la	%r4,STK_OFF_TMP(%r15)	# Arg3 = pointer to temp buffer
-	lghi	%r5,1			# Arg4 = size (1 byte)
-	brasl	%r14,skb_copy_bits	# Get data from skb
-	llgc	%r14,STK_OFF_TMP(%r15)	# Load result from temp buffer
-	ltgr	%r2,%r2			# Set cc to (%r2 != 0)
-	br	%r6			# Return cc
-
-#define sk_negative_common(NAME, SIZE, LOAD)				\
-sk_load_##NAME##_slow_neg:;						\
-	cgfi	%r3,SKF_MAX_NEG_OFF;					\
-	jl	bpf_error;						\
-	lgr	%r2,%r7;		/* Arg1 = skb pointer */	\
-					/* Arg2 = offset */		\
-	lghi	%r4,SIZE;		/* Arg3 = size */		\
-	brasl	%r14,bpf_internal_load_pointer_neg_helper;		\
-	ltgr	%r2,%r2;						\
-	jz	bpf_error;						\
-	LOAD	%r14,0(%r2);		/* Get data from pointer */	\
-	xr	%r3,%r3;		/* Set cc to zero */		\
-	br	%r6;			/* Return cc */
-
-sk_negative_common(word, 4, llgf)
-sk_negative_common(half, 2, llgh)
-sk_negative_common(byte, 1, llgc)
-
-bpf_error:
-# force a return 0 from jit handler
-	ltgr	%r15,%r15	# Set condition code
-	br	%r6
diff --git a/arch/s390/net/bpf_jit.h b/arch/s390/net/bpf_jit.h
index 5e1e5133132d..7822ea92e54a 100644
--- a/arch/s390/net/bpf_jit.h
+++ b/arch/s390/net/bpf_jit.h
@@ -16,9 +16,6 @@
 #include <linux/filter.h>
 #include <linux/types.h>
 
-extern u8 sk_load_word_pos[], sk_load_half_pos[], sk_load_byte_pos[];
-extern u8 sk_load_word[], sk_load_half[], sk_load_byte[];
-
 #endif /* __ASSEMBLY__ */
 
 /*
@@ -36,15 +33,6 @@ extern u8 sk_load_word[], sk_load_half[], sk_load_byte[];
  *	      |		      |     |
  *	      |   BPF stack   |     |
  *	      |		      |     |
- *	      +---------------+     |
- *	      | 8 byte skbp   |     |
- * R15+176 -> +---------------+     |
- *	      | 8 byte hlen   |     |
- * R15+168 -> +---------------+     |
- *	      | 4 byte align  |     |
- *	      +---------------+     |
- *	      | 4 byte temp   |     |
- *	      | for bpf_jit.S |     |
  * R15+160 -> +---------------+     |
  *	      | new backchain |     |
  * R15+152 -> +---------------+     |
@@ -57,17 +45,11 @@ extern u8 sk_load_word[], sk_load_half[], sk_load_byte[];
  * The stack size used by the BPF program ("BPF stack" above) is passed
  * via "aux->stack_depth".
  */
-#define STK_SPACE_ADD (8 + 8 + 4 + 4 + 160)
+#define STK_SPACE_ADD	(160)
 #define STK_160_UNUSED	(160 - 12 * 8)
 #define STK_OFF		(STK_SPACE_ADD - STK_160_UNUSED)
-#define STK_OFF_TMP	160	/* Offset of tmp buffer on stack */
-#define STK_OFF_HLEN	168	/* Offset of SKB header length on stack */
-#define STK_OFF_SKBP	176	/* Offset of SKB pointer on stack */
 
 #define STK_OFF_R6	(160 - 11 * 8)	/* Offset of r6 on stack */
 #define STK_OFF_TCCNT	(160 - 12 * 8)	/* Offset of tail_call_cnt on stack */
 
-/* Offset to skip condition code check */
-#define OFF_OK		4
-
 #endif /* __ARCH_S390_NET_BPF_JIT_H */
diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c
index 78a19c93b380..b020bea040b7 100644
--- a/arch/s390/net/bpf_jit_comp.c
+++ b/arch/s390/net/bpf_jit_comp.c
@@ -47,23 +47,21 @@ struct bpf_jit {
 
 #define BPF_SIZE_MAX	0xffff	/* Max size for program (16 bit branches) */
 
-#define SEEN_SKB	1	/* skb access */
-#define SEEN_MEM	2	/* use mem[] for temporary storage */
-#define SEEN_RET0	4	/* ret0_ip points to a valid return 0 */
-#define SEEN_LITERAL	8	/* code uses literals */
-#define SEEN_FUNC	16	/* calls C functions */
-#define SEEN_TAIL_CALL	32	/* code uses tail calls */
-#define SEEN_REG_AX	64	/* code uses constant blinding */
-#define SEEN_STACK	(SEEN_FUNC | SEEN_MEM | SEEN_SKB)
+#define SEEN_MEM	(1 << 0)	/* use mem[] for temporary storage */
+#define SEEN_RET0	(1 << 1)	/* ret0_ip points to a valid return 0 */
+#define SEEN_LITERAL	(1 << 2)	/* code uses literals */
+#define SEEN_FUNC	(1 << 3)	/* calls C functions */
+#define SEEN_TAIL_CALL	(1 << 4)	/* code uses tail calls */
+#define SEEN_REG_AX	(1 << 5)	/* code uses constant blinding */
+#define SEEN_STACK	(SEEN_FUNC | SEEN_MEM)
 
 /*
  * s390 registers
  */
 #define REG_W0		(MAX_BPF_JIT_REG + 0)	/* Work register 1 (even) */
 #define REG_W1		(MAX_BPF_JIT_REG + 1)	/* Work register 2 (odd) */
-#define REG_SKB_DATA	(MAX_BPF_JIT_REG + 2)	/* SKB data register */
-#define REG_L		(MAX_BPF_JIT_REG + 3)	/* Literal pool register */
-#define REG_15		(MAX_BPF_JIT_REG + 4)	/* Register 15 */
+#define REG_L		(MAX_BPF_JIT_REG + 2)	/* Literal pool register */
+#define REG_15		(MAX_BPF_JIT_REG + 3)	/* Register 15 */
 #define REG_0		REG_W0			/* Register 0 */
 #define REG_1		REG_W1			/* Register 1 */
 #define REG_2		BPF_REG_1		/* Register 2 */
@@ -88,10 +86,8 @@ static const int reg2hex[] = {
 	[BPF_REG_9]	= 10,
 	/* BPF stack pointer */
 	[BPF_REG_FP]	= 13,
-	/* Register for blinding (shared with REG_SKB_DATA) */
+	/* Register for blinding */
 	[BPF_REG_AX]	= 12,
-	/* SKB data pointer */
-	[REG_SKB_DATA]	= 12,
 	/* Work registers for s390x backend */
 	[REG_W0]	= 0,
 	[REG_W1]	= 1,
@@ -385,27 +381,6 @@ static void save_restore_regs(struct bpf_jit *jit, int op, u32 stack_depth)
 }
 
 /*
- * For SKB access %b1 contains the SKB pointer. For "bpf_jit.S"
- * we store the SKB header length on the stack and the SKB data
- * pointer in REG_SKB_DATA if BPF_REG_AX is not used.
- */
-static void emit_load_skb_data_hlen(struct bpf_jit *jit)
-{
-	/* Header length: llgf %w1,<len>(%b1) */
-	EMIT6_DISP_LH(0xe3000000, 0x0016, REG_W1, REG_0, BPF_REG_1,
-		      offsetof(struct sk_buff, len));
-	/* s %w1,<data_len>(%b1) */
-	EMIT4_DISP(0x5b000000, REG_W1, BPF_REG_1,
-		   offsetof(struct sk_buff, data_len));
-	/* stg %w1,ST_OFF_HLEN(%r0,%r15) */
-	EMIT6_DISP_LH(0xe3000000, 0x0024, REG_W1, REG_0, REG_15, STK_OFF_HLEN);
-	if (!(jit->seen & SEEN_REG_AX))
-		/* lg %skb_data,data_off(%b1) */
-		EMIT6_DISP_LH(0xe3000000, 0x0004, REG_SKB_DATA, REG_0,
-			      BPF_REG_1, offsetof(struct sk_buff, data));
-}
-
-/*
  * Emit function prologue
  *
  * Save registers and create stack frame if necessary.
@@ -445,12 +420,6 @@ static void bpf_jit_prologue(struct bpf_jit *jit, u32 stack_depth)
 			EMIT6_DISP_LH(0xe3000000, 0x0024, REG_W1, REG_0,
 				      REG_15, 152);
 	}
-	if (jit->seen & SEEN_SKB) {
-		emit_load_skb_data_hlen(jit);
-		/* stg %b1,ST_OFF_SKBP(%r0,%r15) */
-		EMIT6_DISP_LH(0xe3000000, 0x0024, BPF_REG_1, REG_0, REG_15,
-			      STK_OFF_SKBP);
-	}
 }
 
 /*
@@ -483,12 +452,12 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, int i
 {
 	struct bpf_insn *insn = &fp->insnsi[i];
 	int jmp_off, last, insn_count = 1;
-	unsigned int func_addr, mask;
 	u32 dst_reg = insn->dst_reg;
 	u32 src_reg = insn->src_reg;
 	u32 *addrs = jit->addrs;
 	s32 imm = insn->imm;
 	s16 off = insn->off;
+	unsigned int mask;
 
 	if (dst_reg == BPF_REG_AX || src_reg == BPF_REG_AX)
 		jit->seen |= SEEN_REG_AX;
@@ -970,13 +939,6 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, int i
 		EMIT2(0x0d00, REG_14, REG_W1);
 		/* lgr %b0,%r2: load return value into %b0 */
 		EMIT4(0xb9040000, BPF_REG_0, REG_2);
-		if ((jit->seen & SEEN_SKB) &&
-		    bpf_helper_changes_pkt_data((void *)func)) {
-			/* lg %b1,ST_OFF_SKBP(%r15) */
-			EMIT6_DISP_LH(0xe3000000, 0x0004, BPF_REG_1, REG_0,
-				      REG_15, STK_OFF_SKBP);
-			emit_load_skb_data_hlen(jit);
-		}
 		break;
 	}
 	case BPF_JMP | BPF_TAIL_CALL:
@@ -1176,73 +1138,6 @@ branch_oc:
 		jmp_off = addrs[i + off + 1] - (addrs[i + 1] - 4);
 		EMIT4_PCREL(0xa7040000 | mask << 8, jmp_off);
 		break;
-	/*
-	 * BPF_LD
-	 */
-	case BPF_LD | BPF_ABS | BPF_B: /* b0 = *(u8 *) (skb->data+imm) */
-	case BPF_LD | BPF_IND | BPF_B: /* b0 = *(u8 *) (skb->data+imm+src) */
-		if ((BPF_MODE(insn->code) == BPF_ABS) && (imm >= 0))
-			func_addr = __pa(sk_load_byte_pos);
-		else
-			func_addr = __pa(sk_load_byte);
-		goto call_fn;
-	case BPF_LD | BPF_ABS | BPF_H: /* b0 = *(u16 *) (skb->data+imm) */
-	case BPF_LD | BPF_IND | BPF_H: /* b0 = *(u16 *) (skb->data+imm+src) */
-		if ((BPF_MODE(insn->code) == BPF_ABS) && (imm >= 0))
-			func_addr = __pa(sk_load_half_pos);
-		else
-			func_addr = __pa(sk_load_half);
-		goto call_fn;
-	case BPF_LD | BPF_ABS | BPF_W: /* b0 = *(u32 *) (skb->data+imm) */
-	case BPF_LD | BPF_IND | BPF_W: /* b0 = *(u32 *) (skb->data+imm+src) */
-		if ((BPF_MODE(insn->code) == BPF_ABS) && (imm >= 0))
-			func_addr = __pa(sk_load_word_pos);
-		else
-			func_addr = __pa(sk_load_word);
-		goto call_fn;
-call_fn:
-		jit->seen |= SEEN_SKB | SEEN_RET0 | SEEN_FUNC;
-		REG_SET_SEEN(REG_14); /* Return address of possible func call */
-
-		/*
-		 * Implicit input:
-		 *  BPF_REG_6	 (R7) : skb pointer
-		 *  REG_SKB_DATA (R12): skb data pointer (if no BPF_REG_AX)
-		 *
-		 * Calculated input:
-		 *  BPF_REG_2	 (R3) : offset of byte(s) to fetch in skb
-		 *  BPF_REG_5	 (R6) : return address
-		 *
-		 * Output:
-		 *  BPF_REG_0	 (R14): data read from skb
-		 *
-		 * Scratch registers (BPF_REG_1-5)
-		 */
-
-		/* Call function: llilf %w1,func_addr  */
-		EMIT6_IMM(0xc00f0000, REG_W1, func_addr);
-
-		/* Offset: lgfi %b2,imm */
-		EMIT6_IMM(0xc0010000, BPF_REG_2, imm);
-		if (BPF_MODE(insn->code) == BPF_IND)
-			/* agfr %b2,%src (%src is s32 here) */
-			EMIT4(0xb9180000, BPF_REG_2, src_reg);
-
-		/* Reload REG_SKB_DATA if BPF_REG_AX is used */
-		if (jit->seen & SEEN_REG_AX)
-			/* lg %skb_data,data_off(%b6) */
-			EMIT6_DISP_LH(0xe3000000, 0x0004, REG_SKB_DATA, REG_0,
-				      BPF_REG_6, offsetof(struct sk_buff, data));
-		/* basr %b5,%w1 (%b5 is call saved) */
-		EMIT2(0x0d00, BPF_REG_5, REG_W1);
-
-		/*
-		 * Note: For fast access we jump directly after the
-		 * jnz instruction from bpf_jit.S
-		 */
-		/* jnz <ret0> */
-		EMIT4_PCREL(0xa7740000, jit->ret0_ip - jit->prg);
-		break;
 	default: /* too complex, give up */
 		pr_err("Unknown opcode %02x\n", insn->code);
 		return -1;
diff --git a/arch/sparc/net/Makefile b/arch/sparc/net/Makefile
index 76fa8e95b721..d32aac3a25b8 100644
--- a/arch/sparc/net/Makefile
+++ b/arch/sparc/net/Makefile
@@ -1,4 +1,7 @@
 #
 # Arch-specific network modules
 #
-obj-$(CONFIG_BPF_JIT) += bpf_jit_asm_$(BITS).o bpf_jit_comp_$(BITS).o
+obj-$(CONFIG_BPF_JIT) += bpf_jit_comp_$(BITS).o
+ifeq ($(BITS),32)
+obj-$(CONFIG_BPF_JIT) += bpf_jit_asm_32.o
+endif
diff --git a/arch/sparc/net/bpf_jit_64.h b/arch/sparc/net/bpf_jit_64.h
index 428f7fd19175..fbc836f1c51c 100644
--- a/arch/sparc/net/bpf_jit_64.h
+++ b/arch/sparc/net/bpf_jit_64.h
@@ -33,35 +33,6 @@
 #define I5		0x1d
 #define FP		0x1e
 #define I7		0x1f
-
-#define r_SKB		L0
-#define r_HEADLEN	L4
-#define r_SKB_DATA	L5
-#define r_TMP		G1
-#define r_TMP2		G3
-
-/* assembly code in arch/sparc/net/bpf_jit_asm_64.S */
-extern u32 bpf_jit_load_word[];
-extern u32 bpf_jit_load_half[];
-extern u32 bpf_jit_load_byte[];
-extern u32 bpf_jit_load_byte_msh[];
-extern u32 bpf_jit_load_word_positive_offset[];
-extern u32 bpf_jit_load_half_positive_offset[];
-extern u32 bpf_jit_load_byte_positive_offset[];
-extern u32 bpf_jit_load_byte_msh_positive_offset[];
-extern u32 bpf_jit_load_word_negative_offset[];
-extern u32 bpf_jit_load_half_negative_offset[];
-extern u32 bpf_jit_load_byte_negative_offset[];
-extern u32 bpf_jit_load_byte_msh_negative_offset[];
-
-#else
-#define r_RESULT	%o0
-#define r_SKB		%o0
-#define r_OFF		%o1
-#define r_HEADLEN	%l4
-#define r_SKB_DATA	%l5
-#define r_TMP		%g1
-#define r_TMP2		%g3
 #endif
 
 #endif /* _BPF_JIT_H */
diff --git a/arch/sparc/net/bpf_jit_asm_64.S b/arch/sparc/net/bpf_jit_asm_64.S
deleted file mode 100644
index 7177867052a1..000000000000
--- a/arch/sparc/net/bpf_jit_asm_64.S
+++ /dev/null
@@ -1,162 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#include <asm/ptrace.h>
-
-#include "bpf_jit_64.h"
-
-#define SAVE_SZ		176
-#define SCRATCH_OFF	STACK_BIAS + 128
-#define BE_PTR(label)	be,pn %xcc, label
-#define SIGN_EXTEND(reg)	sra reg, 0, reg
-
-#define SKF_MAX_NEG_OFF	(-0x200000) /* SKF_LL_OFF from filter.h */
-
-	.text
-	.globl	bpf_jit_load_word
-bpf_jit_load_word:
-	cmp	r_OFF, 0
-	bl	bpf_slow_path_word_neg
-	 nop
-	.globl	bpf_jit_load_word_positive_offset
-bpf_jit_load_word_positive_offset:
-	sub	r_HEADLEN, r_OFF, r_TMP
-	cmp	r_TMP, 3
-	ble	bpf_slow_path_word
-	 add	r_SKB_DATA, r_OFF, r_TMP
-	andcc	r_TMP, 3, %g0
-	bne	load_word_unaligned
-	 nop
-	retl
-	 ld	[r_TMP], r_RESULT
-load_word_unaligned:
-	ldub	[r_TMP + 0x0], r_OFF
-	ldub	[r_TMP + 0x1], r_TMP2
-	sll	r_OFF, 8, r_OFF
-	or	r_OFF, r_TMP2, r_OFF
-	ldub	[r_TMP + 0x2], r_TMP2
-	sll	r_OFF, 8, r_OFF
-	or	r_OFF, r_TMP2, r_OFF
-	ldub	[r_TMP + 0x3], r_TMP2
-	sll	r_OFF, 8, r_OFF
-	retl
-	 or	r_OFF, r_TMP2, r_RESULT
-
-	.globl	bpf_jit_load_half
-bpf_jit_load_half:
-	cmp	r_OFF, 0
-	bl	bpf_slow_path_half_neg
-	 nop
-	.globl	bpf_jit_load_half_positive_offset
-bpf_jit_load_half_positive_offset:
-	sub	r_HEADLEN, r_OFF, r_TMP
-	cmp	r_TMP, 1
-	ble	bpf_slow_path_half
-	 add	r_SKB_DATA, r_OFF, r_TMP
-	andcc	r_TMP, 1, %g0
-	bne	load_half_unaligned
-	 nop
-	retl
-	 lduh	[r_TMP], r_RESULT
-load_half_unaligned:
-	ldub	[r_TMP + 0x0], r_OFF
-	ldub	[r_TMP + 0x1], r_TMP2
-	sll	r_OFF, 8, r_OFF
-	retl
-	 or	r_OFF, r_TMP2, r_RESULT
-
-	.globl	bpf_jit_load_byte
-bpf_jit_load_byte:
-	cmp	r_OFF, 0
-	bl	bpf_slow_path_byte_neg
-	 nop
-	.globl	bpf_jit_load_byte_positive_offset
-bpf_jit_load_byte_positive_offset:
-	cmp	r_OFF, r_HEADLEN
-	bge	bpf_slow_path_byte
-	 nop
-	retl
-	 ldub	[r_SKB_DATA + r_OFF], r_RESULT
-
-#define bpf_slow_path_common(LEN)	\
-	save	%sp, -SAVE_SZ, %sp;	\
-	mov	%i0, %o0;		\
-	mov	%i1, %o1;		\
-	add	%fp, SCRATCH_OFF, %o2;	\
-	call	skb_copy_bits;		\
-	 mov	(LEN), %o3;		\
-	cmp	%o0, 0;			\
-	restore;
-
-bpf_slow_path_word:
-	bpf_slow_path_common(4)
-	bl	bpf_error
-	 ld	[%sp + SCRATCH_OFF], r_RESULT
-	retl
-	 nop
-bpf_slow_path_half:
-	bpf_slow_path_common(2)
-	bl	bpf_error
-	 lduh	[%sp + SCRATCH_OFF], r_RESULT
-	retl
-	 nop
-bpf_slow_path_byte:
-	bpf_slow_path_common(1)
-	bl	bpf_error
-	 ldub	[%sp + SCRATCH_OFF], r_RESULT
-	retl
-	 nop
-
-#define bpf_negative_common(LEN)			\
-	save	%sp, -SAVE_SZ, %sp;			\
-	mov	%i0, %o0;				\
-	mov	%i1, %o1;				\
-	SIGN_EXTEND(%o1);				\
-	call	bpf_internal_load_pointer_neg_helper;	\
-	 mov	(LEN), %o2;				\
-	mov	%o0, r_TMP;				\
-	cmp	%o0, 0;					\
-	BE_PTR(bpf_error);				\
-	 restore;
-
-bpf_slow_path_word_neg:
-	sethi	%hi(SKF_MAX_NEG_OFF), r_TMP
-	cmp	r_OFF, r_TMP
-	bl	bpf_error
-	 nop
-	.globl	bpf_jit_load_word_negative_offset
-bpf_jit_load_word_negative_offset:
-	bpf_negative_common(4)
-	andcc	r_TMP, 3, %g0
-	bne	load_word_unaligned
-	 nop
-	retl
-	 ld	[r_TMP], r_RESULT
-
-bpf_slow_path_half_neg:
-	sethi	%hi(SKF_MAX_NEG_OFF), r_TMP
-	cmp	r_OFF, r_TMP
-	bl	bpf_error
-	 nop
-	.globl	bpf_jit_load_half_negative_offset
-bpf_jit_load_half_negative_offset:
-	bpf_negative_common(2)
-	andcc	r_TMP, 1, %g0
-	bne	load_half_unaligned
-	 nop
-	retl
-	 lduh	[r_TMP], r_RESULT
-
-bpf_slow_path_byte_neg:
-	sethi	%hi(SKF_MAX_NEG_OFF), r_TMP
-	cmp	r_OFF, r_TMP
-	bl	bpf_error
-	 nop
-	.globl	bpf_jit_load_byte_negative_offset
-bpf_jit_load_byte_negative_offset:
-	bpf_negative_common(1)
-	retl
-	 ldub	[r_TMP], r_RESULT
-
-bpf_error:
-	/* Make the JIT program itself return zero. */
-	ret
-	restore	%g0, %g0, %o0
diff --git a/arch/sparc/net/bpf_jit_comp_64.c b/arch/sparc/net/bpf_jit_comp_64.c
index 48a25869349b..9f5918e0693a 100644
--- a/arch/sparc/net/bpf_jit_comp_64.c
+++ b/arch/sparc/net/bpf_jit_comp_64.c
@@ -48,10 +48,6 @@ static void bpf_flush_icache(void *start_, void *end_)
 	}
 }
 
-#define SEEN_DATAREF 1 /* might call external helpers */
-#define SEEN_XREG    2 /* ebx is used */
-#define SEEN_MEM     4 /* use mem[] for temporary storage */
-
 #define S13(X)		((X) & 0x1fff)
 #define S5(X)		((X) & 0x1f)
 #define IMMED		0x00002000
@@ -198,7 +194,6 @@ struct jit_ctx {
 	bool 			tmp_1_used;
 	bool 			tmp_2_used;
 	bool 			tmp_3_used;
-	bool			saw_ld_abs_ind;
 	bool			saw_frame_pointer;
 	bool			saw_call;
 	bool			saw_tail_call;
@@ -207,9 +202,7 @@ struct jit_ctx {
 
 #define TMP_REG_1	(MAX_BPF_JIT_REG + 0)
 #define TMP_REG_2	(MAX_BPF_JIT_REG + 1)
-#define SKB_HLEN_REG	(MAX_BPF_JIT_REG + 2)
-#define SKB_DATA_REG	(MAX_BPF_JIT_REG + 3)
-#define TMP_REG_3	(MAX_BPF_JIT_REG + 4)
+#define TMP_REG_3	(MAX_BPF_JIT_REG + 2)
 
 /* Map BPF registers to SPARC registers */
 static const int bpf2sparc[] = {
@@ -238,9 +231,6 @@ static const int bpf2sparc[] = {
 	[TMP_REG_1] = G1,
 	[TMP_REG_2] = G2,
 	[TMP_REG_3] = G3,
-
-	[SKB_HLEN_REG] = L4,
-	[SKB_DATA_REG] = L5,
 };
 
 static void emit(const u32 insn, struct jit_ctx *ctx)
@@ -800,25 +790,6 @@ static int emit_compare_and_branch(const u8 code, const u8 dst, u8 src,
 	return 0;
 }
 
-static void load_skb_regs(struct jit_ctx *ctx, u8 r_skb)
-{
-	const u8 r_headlen = bpf2sparc[SKB_HLEN_REG];
-	const u8 r_data = bpf2sparc[SKB_DATA_REG];
-	const u8 r_tmp = bpf2sparc[TMP_REG_1];
-	unsigned int off;
-
-	off = offsetof(struct sk_buff, len);
-	emit(LD32I | RS1(r_skb) | S13(off) | RD(r_headlen), ctx);
-
-	off = offsetof(struct sk_buff, data_len);
-	emit(LD32I | RS1(r_skb) | S13(off) | RD(r_tmp), ctx);
-
-	emit(SUB | RS1(r_headlen) | RS2(r_tmp) | RD(r_headlen), ctx);
-
-	off = offsetof(struct sk_buff, data);
-	emit(LDPTRI | RS1(r_skb) | S13(off) | RD(r_data), ctx);
-}
-
 /* Just skip the save instruction and the ctx register move.  */
 #define BPF_TAILCALL_PROLOGUE_SKIP	16
 #define BPF_TAILCALL_CNT_SP_OFF		(STACK_BIAS + 128)
@@ -857,9 +828,6 @@ static void build_prologue(struct jit_ctx *ctx)
 
 	emit_reg_move(I0, O0, ctx);
 	/* If you add anything here, adjust BPF_TAILCALL_PROLOGUE_SKIP above. */
-
-	if (ctx->saw_ld_abs_ind)
-		load_skb_regs(ctx, bpf2sparc[BPF_REG_1]);
 }
 
 static void build_epilogue(struct jit_ctx *ctx)
@@ -1225,16 +1193,11 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 		u8 *func = ((u8 *)__bpf_call_base) + imm;
 
 		ctx->saw_call = true;
-		if (ctx->saw_ld_abs_ind && bpf_helper_changes_pkt_data(func))
-			emit_reg_move(bpf2sparc[BPF_REG_1], L7, ctx);
 
 		emit_call((u32 *)func, ctx);
 		emit_nop(ctx);
 
 		emit_reg_move(O0, bpf2sparc[BPF_REG_0], ctx);
-
-		if (ctx->saw_ld_abs_ind && bpf_helper_changes_pkt_data(func))
-			load_skb_regs(ctx, L7);
 		break;
 	}
 
@@ -1412,43 +1375,6 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 		emit_nop(ctx);
 		break;
 	}
-#define CHOOSE_LOAD_FUNC(K, func) \
-		((int)K < 0 ? ((int)K >= SKF_LL_OFF ? func##_negative_offset : func) : func##_positive_offset)
-
-	/* R0 = ntohx(*(size *)(((struct sk_buff *)R6)->data + imm)) */
-	case BPF_LD | BPF_ABS | BPF_W:
-		func = CHOOSE_LOAD_FUNC(imm, bpf_jit_load_word);
-		goto common_load;
-	case BPF_LD | BPF_ABS | BPF_H:
-		func = CHOOSE_LOAD_FUNC(imm, bpf_jit_load_half);
-		goto common_load;
-	case BPF_LD | BPF_ABS | BPF_B:
-		func = CHOOSE_LOAD_FUNC(imm, bpf_jit_load_byte);
-		goto common_load;
-	/* R0 = ntohx(*(size *)(((struct sk_buff *)R6)->data + src + imm)) */
-	case BPF_LD | BPF_IND | BPF_W:
-		func = bpf_jit_load_word;
-		goto common_load;
-	case BPF_LD | BPF_IND | BPF_H:
-		func = bpf_jit_load_half;
-		goto common_load;
-
-	case BPF_LD | BPF_IND | BPF_B:
-		func = bpf_jit_load_byte;
-	common_load:
-		ctx->saw_ld_abs_ind = true;
-
-		emit_reg_move(bpf2sparc[BPF_REG_6], O0, ctx);
-		emit_loadimm(imm, O1, ctx);
-
-		if (BPF_MODE(code) == BPF_IND)
-			emit_alu(ADD, src, O1, ctx);
-
-		emit_call(func, ctx);
-		emit_alu_K(SRA, O1, 0, ctx);
-
-		emit_reg_move(O0, bpf2sparc[BPF_REG_0], ctx);
-		break;
 
 	default:
 		pr_err_once("unknown opcode %02x\n", code);
@@ -1583,12 +1509,11 @@ skip_init_ctx:
 		build_epilogue(&ctx);
 
 		if (bpf_jit_enable > 1)
-			pr_info("Pass %d: shrink = %d, seen = [%c%c%c%c%c%c%c]\n", pass,
+			pr_info("Pass %d: shrink = %d, seen = [%c%c%c%c%c%c]\n", pass,
 				image_size - (ctx.idx * 4),
 				ctx.tmp_1_used ? '1' : ' ',
 				ctx.tmp_2_used ? '2' : ' ',
 				ctx.tmp_3_used ? '3' : ' ',
-				ctx.saw_ld_abs_ind ? 'L' : ' ',
 				ctx.saw_frame_pointer ? 'F' : ' ',
 				ctx.saw_call ? 'C' : ' ',
 				ctx.saw_tail_call ? 'T' : ' ');
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index c07f492b871a..d51a71dcbac2 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -138,7 +138,7 @@ config X86
 	select HAVE_DMA_CONTIGUOUS
 	select HAVE_DYNAMIC_FTRACE
 	select HAVE_DYNAMIC_FTRACE_WITH_REGS
-	select HAVE_EBPF_JIT			if X86_64
+	select HAVE_EBPF_JIT
 	select HAVE_EFFICIENT_UNALIGNED_ACCESS
 	select HAVE_EXIT_THREAD
 	select HAVE_FENTRY			if X86_64 || DYNAMIC_FTRACE
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index f928ad9b143f..2cd344d1a6e5 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -291,16 +291,20 @@ do {									\
  *    lfence
  *    jmp spec_trap
  *  do_rop:
- *    mov %rax,(%rsp)
+ *    mov %rax,(%rsp) for x86_64
+ *    mov %edx,(%esp) for x86_32
  *    retq
  *
  * Without retpolines configured:
  *
- *    jmp *%rax
+ *    jmp *%rax for x86_64
+ *    jmp *%edx for x86_32
  */
 #ifdef CONFIG_RETPOLINE
+#ifdef CONFIG_X86_64
 # define RETPOLINE_RAX_BPF_JIT_SIZE	17
 # define RETPOLINE_RAX_BPF_JIT()				\
+do {								\
 	EMIT1_off32(0xE8, 7);	 /* callq do_rop */		\
 	/* spec_trap: */					\
 	EMIT2(0xF3, 0x90);       /* pause */			\
@@ -308,11 +312,31 @@ do {									\
 	EMIT2(0xEB, 0xF9);       /* jmp spec_trap */		\
 	/* do_rop: */						\
 	EMIT4(0x48, 0x89, 0x04, 0x24); /* mov %rax,(%rsp) */	\
-	EMIT1(0xC3);             /* retq */
+	EMIT1(0xC3);             /* retq */			\
+} while (0)
 #else
+# define RETPOLINE_EDX_BPF_JIT()				\
+do {								\
+	EMIT1_off32(0xE8, 7);	 /* call do_rop */		\
+	/* spec_trap: */					\
+	EMIT2(0xF3, 0x90);       /* pause */			\
+	EMIT3(0x0F, 0xAE, 0xE8); /* lfence */			\
+	EMIT2(0xEB, 0xF9);       /* jmp spec_trap */		\
+	/* do_rop: */						\
+	EMIT3(0x89, 0x14, 0x24); /* mov %edx,(%esp) */		\
+	EMIT1(0xC3);             /* ret */			\
+} while (0)
+#endif
+#else /* !CONFIG_RETPOLINE */
+
+#ifdef CONFIG_X86_64
 # define RETPOLINE_RAX_BPF_JIT_SIZE	2
 # define RETPOLINE_RAX_BPF_JIT()				\
 	EMIT2(0xFF, 0xE0);	 /* jmp *%rax */
+#else
+# define RETPOLINE_EDX_BPF_JIT()				\
+	EMIT2(0xFF, 0xE2) /* jmp *%edx */
+#endif
 #endif
 
 #endif /* _ASM_X86_NOSPEC_BRANCH_H_ */
diff --git a/arch/x86/net/Makefile b/arch/x86/net/Makefile
index fefb4b619598..59e123da580c 100644
--- a/arch/x86/net/Makefile
+++ b/arch/x86/net/Makefile
@@ -1,6 +1,9 @@
 #
 # Arch-specific network modules
 #
-OBJECT_FILES_NON_STANDARD_bpf_jit.o += y
 
-obj-$(CONFIG_BPF_JIT) += bpf_jit.o bpf_jit_comp.o
+ifeq ($(CONFIG_X86_32),y)
+        obj-$(CONFIG_BPF_JIT) += bpf_jit_comp32.o
+else
+        obj-$(CONFIG_BPF_JIT) += bpf_jit_comp.o
+endif
diff --git a/arch/x86/net/bpf_jit.S b/arch/x86/net/bpf_jit.S
deleted file mode 100644
index b33093f84528..000000000000
--- a/arch/x86/net/bpf_jit.S
+++ /dev/null
@@ -1,154 +0,0 @@
-/* bpf_jit.S : BPF JIT helper functions
- *
- * Copyright (C) 2011 Eric Dumazet (eric.dumazet@gmail.com)
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; version 2
- * of the License.
- */
-#include <linux/linkage.h>
-#include <asm/frame.h>
-
-/*
- * Calling convention :
- * rbx : skb pointer (callee saved)
- * esi : offset of byte(s) to fetch in skb (can be scratched)
- * r10 : copy of skb->data
- * r9d : hlen = skb->len - skb->data_len
- */
-#define SKBDATA	%r10
-#define SKF_MAX_NEG_OFF    $(-0x200000) /* SKF_LL_OFF from filter.h */
-
-#define FUNC(name) \
-	.globl name; \
-	.type name, @function; \
-	name:
-
-FUNC(sk_load_word)
-	test	%esi,%esi
-	js	bpf_slow_path_word_neg
-
-FUNC(sk_load_word_positive_offset)
-	mov	%r9d,%eax		# hlen
-	sub	%esi,%eax		# hlen - offset
-	cmp	$3,%eax
-	jle	bpf_slow_path_word
-	mov     (SKBDATA,%rsi),%eax
-	bswap   %eax  			/* ntohl() */
-	ret
-
-FUNC(sk_load_half)
-	test	%esi,%esi
-	js	bpf_slow_path_half_neg
-
-FUNC(sk_load_half_positive_offset)
-	mov	%r9d,%eax
-	sub	%esi,%eax		#	hlen - offset
-	cmp	$1,%eax
-	jle	bpf_slow_path_half
-	movzwl	(SKBDATA,%rsi),%eax
-	rol	$8,%ax			# ntohs()
-	ret
-
-FUNC(sk_load_byte)
-	test	%esi,%esi
-	js	bpf_slow_path_byte_neg
-
-FUNC(sk_load_byte_positive_offset)
-	cmp	%esi,%r9d   /* if (offset >= hlen) goto bpf_slow_path_byte */
-	jle	bpf_slow_path_byte
-	movzbl	(SKBDATA,%rsi),%eax
-	ret
-
-/* rsi contains offset and can be scratched */
-#define bpf_slow_path_common(LEN)		\
-	lea	32(%rbp), %rdx;\
-	FRAME_BEGIN;				\
-	mov	%rbx, %rdi; /* arg1 == skb */	\
-	push	%r9;				\
-	push	SKBDATA;			\
-/* rsi already has offset */			\
-	mov	$LEN,%ecx;	/* len */	\
-	call	skb_copy_bits;			\
-	test    %eax,%eax;			\
-	pop	SKBDATA;			\
-	pop	%r9;				\
-	FRAME_END
-
-
-bpf_slow_path_word:
-	bpf_slow_path_common(4)
-	js	bpf_error
-	mov	32(%rbp),%eax
-	bswap	%eax
-	ret
-
-bpf_slow_path_half:
-	bpf_slow_path_common(2)
-	js	bpf_error
-	mov	32(%rbp),%ax
-	rol	$8,%ax
-	movzwl	%ax,%eax
-	ret
-
-bpf_slow_path_byte:
-	bpf_slow_path_common(1)
-	js	bpf_error
-	movzbl	32(%rbp),%eax
-	ret
-
-#define sk_negative_common(SIZE)				\
-	FRAME_BEGIN;						\
-	mov	%rbx, %rdi; /* arg1 == skb */			\
-	push	%r9;						\
-	push	SKBDATA;					\
-/* rsi already has offset */					\
-	mov	$SIZE,%edx;	/* size */			\
-	call	bpf_internal_load_pointer_neg_helper;		\
-	test	%rax,%rax;					\
-	pop	SKBDATA;					\
-	pop	%r9;						\
-	FRAME_END;						\
-	jz	bpf_error
-
-bpf_slow_path_word_neg:
-	cmp	SKF_MAX_NEG_OFF, %esi	/* test range */
-	jl	bpf_error	/* offset lower -> error  */
-
-FUNC(sk_load_word_negative_offset)
-	sk_negative_common(4)
-	mov	(%rax), %eax
-	bswap	%eax
-	ret
-
-bpf_slow_path_half_neg:
-	cmp	SKF_MAX_NEG_OFF, %esi
-	jl	bpf_error
-
-FUNC(sk_load_half_negative_offset)
-	sk_negative_common(2)
-	mov	(%rax),%ax
-	rol	$8,%ax
-	movzwl	%ax,%eax
-	ret
-
-bpf_slow_path_byte_neg:
-	cmp	SKF_MAX_NEG_OFF, %esi
-	jl	bpf_error
-
-FUNC(sk_load_byte_negative_offset)
-	sk_negative_common(1)
-	movzbl	(%rax), %eax
-	ret
-
-bpf_error:
-# force a return 0 from jit handler
-	xor	%eax,%eax
-	mov	(%rbp),%rbx
-	mov	8(%rbp),%r13
-	mov	16(%rbp),%r14
-	mov	24(%rbp),%r15
-	add	$40, %rbp
-	leaveq
-	ret
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 263c8453815e..8fca446aaef6 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -1,4 +1,5 @@
-/* bpf_jit_comp.c : BPF JIT compiler
+/*
+ * bpf_jit_comp.c: BPF JIT compiler
  *
  * Copyright (C) 2011-2013 Eric Dumazet (eric.dumazet@gmail.com)
  * Internal BPF Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com
@@ -16,15 +17,6 @@
 #include <asm/set_memory.h>
 #include <asm/nospec-branch.h>
 
-/*
- * assembly code in arch/x86/net/bpf_jit.S
- */
-extern u8 sk_load_word[], sk_load_half[], sk_load_byte[];
-extern u8 sk_load_word_positive_offset[], sk_load_half_positive_offset[];
-extern u8 sk_load_byte_positive_offset[];
-extern u8 sk_load_word_negative_offset[], sk_load_half_negative_offset[];
-extern u8 sk_load_byte_negative_offset[];
-
 static u8 *emit_code(u8 *ptr, u32 bytes, unsigned int len)
 {
 	if (len == 1)
@@ -45,14 +37,15 @@ static u8 *emit_code(u8 *ptr, u32 bytes, unsigned int len)
 #define EMIT2(b1, b2)		EMIT((b1) + ((b2) << 8), 2)
 #define EMIT3(b1, b2, b3)	EMIT((b1) + ((b2) << 8) + ((b3) << 16), 3)
 #define EMIT4(b1, b2, b3, b4)   EMIT((b1) + ((b2) << 8) + ((b3) << 16) + ((b4) << 24), 4)
+
 #define EMIT1_off32(b1, off) \
-	do {EMIT1(b1); EMIT(off, 4); } while (0)
+	do { EMIT1(b1); EMIT(off, 4); } while (0)
 #define EMIT2_off32(b1, b2, off) \
-	do {EMIT2(b1, b2); EMIT(off, 4); } while (0)
+	do { EMIT2(b1, b2); EMIT(off, 4); } while (0)
 #define EMIT3_off32(b1, b2, b3, off) \
-	do {EMIT3(b1, b2, b3); EMIT(off, 4); } while (0)
+	do { EMIT3(b1, b2, b3); EMIT(off, 4); } while (0)
 #define EMIT4_off32(b1, b2, b3, b4, off) \
-	do {EMIT4(b1, b2, b3, b4); EMIT(off, 4); } while (0)
+	do { EMIT4(b1, b2, b3, b4); EMIT(off, 4); } while (0)
 
 static bool is_imm8(int value)
 {
@@ -70,9 +63,10 @@ static bool is_uimm32(u64 value)
 }
 
 /* mov dst, src */
-#define EMIT_mov(DST, SRC) \
-	do {if (DST != SRC) \
-		EMIT3(add_2mod(0x48, DST, SRC), 0x89, add_2reg(0xC0, DST, SRC)); \
+#define EMIT_mov(DST, SRC)								 \
+	do {										 \
+		if (DST != SRC)								 \
+			EMIT3(add_2mod(0x48, DST, SRC), 0x89, add_2reg(0xC0, DST, SRC)); \
 	} while (0)
 
 static int bpf_size_to_x86_bytes(int bpf_size)
@@ -89,7 +83,8 @@ static int bpf_size_to_x86_bytes(int bpf_size)
 		return 0;
 }
 
-/* list of x86 cond jumps opcodes (. + s8)
+/*
+ * List of x86 cond jumps opcodes (. + s8)
  * Add 0x10 (and an extra 0x0f) to generate far jumps (. + s32)
  */
 #define X86_JB  0x72
@@ -103,38 +98,37 @@ static int bpf_size_to_x86_bytes(int bpf_size)
 #define X86_JLE 0x7E
 #define X86_JG  0x7F
 
-#define CHOOSE_LOAD_FUNC(K, func) \
-	((int)K < 0 ? ((int)K >= SKF_LL_OFF ? func##_negative_offset : func) : func##_positive_offset)
-
-/* pick a register outside of BPF range for JIT internal work */
+/* Pick a register outside of BPF range for JIT internal work */
 #define AUX_REG (MAX_BPF_JIT_REG + 1)
 
-/* The following table maps BPF registers to x64 registers.
+/*
+ * The following table maps BPF registers to x86-64 registers.
  *
- * x64 register r12 is unused, since if used as base address
+ * x86-64 register R12 is unused, since if used as base address
  * register in load/store instructions, it always needs an
  * extra byte of encoding and is callee saved.
  *
- *  r9 caches skb->len - skb->data_len
- * r10 caches skb->data, and used for blinding (if enabled)
+ * Also x86-64 register R9 is unused. x86-64 register R10 is
+ * used for blinding (if enabled).
  */
 static const int reg2hex[] = {
-	[BPF_REG_0] = 0,  /* rax */
-	[BPF_REG_1] = 7,  /* rdi */
-	[BPF_REG_2] = 6,  /* rsi */
-	[BPF_REG_3] = 2,  /* rdx */
-	[BPF_REG_4] = 1,  /* rcx */
-	[BPF_REG_5] = 0,  /* r8 */
-	[BPF_REG_6] = 3,  /* rbx callee saved */
-	[BPF_REG_7] = 5,  /* r13 callee saved */
-	[BPF_REG_8] = 6,  /* r14 callee saved */
-	[BPF_REG_9] = 7,  /* r15 callee saved */
-	[BPF_REG_FP] = 5, /* rbp readonly */
-	[BPF_REG_AX] = 2, /* r10 temp register */
-	[AUX_REG] = 3,    /* r11 temp register */
+	[BPF_REG_0] = 0,  /* RAX */
+	[BPF_REG_1] = 7,  /* RDI */
+	[BPF_REG_2] = 6,  /* RSI */
+	[BPF_REG_3] = 2,  /* RDX */
+	[BPF_REG_4] = 1,  /* RCX */
+	[BPF_REG_5] = 0,  /* R8  */
+	[BPF_REG_6] = 3,  /* RBX callee saved */
+	[BPF_REG_7] = 5,  /* R13 callee saved */
+	[BPF_REG_8] = 6,  /* R14 callee saved */
+	[BPF_REG_9] = 7,  /* R15 callee saved */
+	[BPF_REG_FP] = 5, /* RBP readonly */
+	[BPF_REG_AX] = 2, /* R10 temp register */
+	[AUX_REG] = 3,    /* R11 temp register */
 };
 
-/* is_ereg() == true if BPF register 'reg' maps to x64 r8..r15
+/*
+ * is_ereg() == true if BPF register 'reg' maps to x86-64 r8..r15
  * which need extra byte of encoding.
  * rax,rcx,...,rbp have simpler encoding
  */
@@ -153,7 +147,7 @@ static bool is_axreg(u32 reg)
 	return reg == BPF_REG_0;
 }
 
-/* add modifiers if 'reg' maps to x64 registers r8..r15 */
+/* Add modifiers if 'reg' maps to x86-64 registers R8..R15 */
 static u8 add_1mod(u8 byte, u32 reg)
 {
 	if (is_ereg(reg))
@@ -170,13 +164,13 @@ static u8 add_2mod(u8 byte, u32 r1, u32 r2)
 	return byte;
 }
 
-/* encode 'dst_reg' register into x64 opcode 'byte' */
+/* Encode 'dst_reg' register into x86-64 opcode 'byte' */
 static u8 add_1reg(u8 byte, u32 dst_reg)
 {
 	return byte + reg2hex[dst_reg];
 }
 
-/* encode 'dst_reg' and 'src_reg' registers into x64 opcode 'byte' */
+/* Encode 'dst_reg' and 'src_reg' registers into x86-64 opcode 'byte' */
 static u8 add_2reg(u8 byte, u32 dst_reg, u32 src_reg)
 {
 	return byte + reg2hex[dst_reg] + (reg2hex[src_reg] << 3);
@@ -184,27 +178,24 @@ static u8 add_2reg(u8 byte, u32 dst_reg, u32 src_reg)
 
 static void jit_fill_hole(void *area, unsigned int size)
 {
-	/* fill whole space with int3 instructions */
+	/* Fill whole space with INT3 instructions */
 	memset(area, 0xcc, size);
 }
 
 struct jit_context {
-	int cleanup_addr; /* epilogue code offset */
-	bool seen_ld_abs;
-	bool seen_ax_reg;
+	int cleanup_addr; /* Epilogue code offset */
 };
 
-/* maximum number of bytes emitted while JITing one eBPF insn */
+/* Maximum number of bytes emitted while JITing one eBPF insn */
 #define BPF_MAX_INSN_SIZE	128
 #define BPF_INSN_SAFETY		64
 
-#define AUX_STACK_SPACE \
-	(32 /* space for rbx, r13, r14, r15 */ + \
-	 8 /* space for skb_copy_bits() buffer */)
+#define AUX_STACK_SPACE		40 /* Space for RBX, R13, R14, R15, tailcnt */
 
-#define PROLOGUE_SIZE 37
+#define PROLOGUE_SIZE		37
 
-/* emit x64 prologue code for BPF program and check it's size.
+/*
+ * Emit x86-64 prologue code for BPF program and check its size.
  * bpf_tail_call helper will skip it while jumping into another program
  */
 static void emit_prologue(u8 **pprog, u32 stack_depth, bool ebpf_from_cbpf)
@@ -212,8 +203,11 @@ static void emit_prologue(u8 **pprog, u32 stack_depth, bool ebpf_from_cbpf)
 	u8 *prog = *pprog;
 	int cnt = 0;
 
-	EMIT1(0x55); /* push rbp */
-	EMIT3(0x48, 0x89, 0xE5); /* mov rbp,rsp */
+	/* push rbp */
+	EMIT1(0x55);
+
+	/* mov rbp,rsp */
+	EMIT3(0x48, 0x89, 0xE5);
 
 	/* sub rsp, rounded_stack_depth + AUX_STACK_SPACE */
 	EMIT3_off32(0x48, 0x81, 0xEC,
@@ -222,19 +216,8 @@ static void emit_prologue(u8 **pprog, u32 stack_depth, bool ebpf_from_cbpf)
 	/* sub rbp, AUX_STACK_SPACE */
 	EMIT4(0x48, 0x83, 0xED, AUX_STACK_SPACE);
 
-	/* all classic BPF filters use R6(rbx) save it */
-
 	/* mov qword ptr [rbp+0],rbx */
 	EMIT4(0x48, 0x89, 0x5D, 0);
-
-	/* bpf_convert_filter() maps classic BPF register X to R7 and uses R8
-	 * as temporary, so all tcpdump filters need to spill/fill R7(r13) and
-	 * R8(r14). R9(r15) spill could be made conditional, but there is only
-	 * one 'bpf_error' return path out of helper functions inside bpf_jit.S
-	 * The overhead of extra spill is negligible for any filter other
-	 * than synthetic ones. Therefore not worth adding complexity.
-	 */
-
 	/* mov qword ptr [rbp+8],r13 */
 	EMIT4(0x4C, 0x89, 0x6D, 8);
 	/* mov qword ptr [rbp+16],r14 */
@@ -243,9 +226,10 @@ static void emit_prologue(u8 **pprog, u32 stack_depth, bool ebpf_from_cbpf)
 	EMIT4(0x4C, 0x89, 0x7D, 24);
 
 	if (!ebpf_from_cbpf) {
-		/* Clear the tail call counter (tail_call_cnt): for eBPF tail
+		/*
+		 * Clear the tail call counter (tail_call_cnt): for eBPF tail
 		 * calls we need to reset the counter to 0. It's done in two
-		 * instructions, resetting rax register to 0, and moving it
+		 * instructions, resetting RAX register to 0, and moving it
 		 * to the counter location.
 		 */
 
@@ -260,7 +244,9 @@ static void emit_prologue(u8 **pprog, u32 stack_depth, bool ebpf_from_cbpf)
 	*pprog = prog;
 }
 
-/* generate the following code:
+/*
+ * Generate the following code:
+ *
  * ... bpf_tail_call(void *ctx, struct bpf_array *array, u64 index) ...
  *   if (index >= array->map.max_entries)
  *     goto out;
@@ -278,23 +264,26 @@ static void emit_bpf_tail_call(u8 **pprog)
 	int label1, label2, label3;
 	int cnt = 0;
 
-	/* rdi - pointer to ctx
+	/*
+	 * rdi - pointer to ctx
 	 * rsi - pointer to bpf_array
 	 * rdx - index in bpf_array
 	 */
 
-	/* if (index >= array->map.max_entries)
-	 *   goto out;
+	/*
+	 * if (index >= array->map.max_entries)
+	 *	goto out;
 	 */
 	EMIT2(0x89, 0xD2);                        /* mov edx, edx */
 	EMIT3(0x39, 0x56,                         /* cmp dword ptr [rsi + 16], edx */
 	      offsetof(struct bpf_array, map.max_entries));
-#define OFFSET1 (41 + RETPOLINE_RAX_BPF_JIT_SIZE) /* number of bytes to jump */
+#define OFFSET1 (41 + RETPOLINE_RAX_BPF_JIT_SIZE) /* Number of bytes to jump */
 	EMIT2(X86_JBE, OFFSET1);                  /* jbe out */
 	label1 = cnt;
 
-	/* if (tail_call_cnt > MAX_TAIL_CALL_CNT)
-	 *   goto out;
+	/*
+	 * if (tail_call_cnt > MAX_TAIL_CALL_CNT)
+	 *	goto out;
 	 */
 	EMIT2_off32(0x8B, 0x85, 36);              /* mov eax, dword ptr [rbp + 36] */
 	EMIT3(0x83, 0xF8, MAX_TAIL_CALL_CNT);     /* cmp eax, MAX_TAIL_CALL_CNT */
@@ -308,8 +297,9 @@ static void emit_bpf_tail_call(u8 **pprog)
 	EMIT4_off32(0x48, 0x8B, 0x84, 0xD6,       /* mov rax, [rsi + rdx * 8 + offsetof(...)] */
 		    offsetof(struct bpf_array, ptrs));
 
-	/* if (prog == NULL)
-	 *   goto out;
+	/*
+	 * if (prog == NULL)
+	 *	goto out;
 	 */
 	EMIT3(0x48, 0x85, 0xC0);		  /* test rax,rax */
 #define OFFSET3 (8 + RETPOLINE_RAX_BPF_JIT_SIZE)
@@ -321,7 +311,8 @@ static void emit_bpf_tail_call(u8 **pprog)
 	      offsetof(struct bpf_prog, bpf_func));
 	EMIT4(0x48, 0x83, 0xC0, PROLOGUE_SIZE);   /* add rax, prologue_size */
 
-	/* now we're ready to jump into next BPF program
+	/*
+	 * Wow we're ready to jump into next BPF program
 	 * rdi == ctx (1st arg)
 	 * rax == prog->bpf_func + prologue_size
 	 */
@@ -334,26 +325,6 @@ static void emit_bpf_tail_call(u8 **pprog)
 	*pprog = prog;
 }
 
-
-static void emit_load_skb_data_hlen(u8 **pprog)
-{
-	u8 *prog = *pprog;
-	int cnt = 0;
-
-	/* r9d = skb->len - skb->data_len (headlen)
-	 * r10 = skb->data
-	 */
-	/* mov %r9d, off32(%rdi) */
-	EMIT3_off32(0x44, 0x8b, 0x8f, offsetof(struct sk_buff, len));
-
-	/* sub %r9d, off32(%rdi) */
-	EMIT3_off32(0x44, 0x2b, 0x8f, offsetof(struct sk_buff, data_len));
-
-	/* mov %r10, off32(%rdi) */
-	EMIT3_off32(0x4c, 0x8b, 0x97, offsetof(struct sk_buff, data));
-	*pprog = prog;
-}
-
 static void emit_mov_imm32(u8 **pprog, bool sign_propagate,
 			   u32 dst_reg, const u32 imm32)
 {
@@ -361,7 +332,8 @@ static void emit_mov_imm32(u8 **pprog, bool sign_propagate,
 	u8 b1, b2, b3;
 	int cnt = 0;
 
-	/* optimization: if imm32 is positive, use 'mov %eax, imm32'
+	/*
+	 * Optimization: if imm32 is positive, use 'mov %eax, imm32'
 	 * (which zero-extends imm32) to save 2 bytes.
 	 */
 	if (sign_propagate && (s32)imm32 < 0) {
@@ -373,7 +345,8 @@ static void emit_mov_imm32(u8 **pprog, bool sign_propagate,
 		goto done;
 	}
 
-	/* optimization: if imm32 is zero, use 'xor %eax, %eax'
+	/*
+	 * Optimization: if imm32 is zero, use 'xor %eax, %eax'
 	 * to save 3 bytes.
 	 */
 	if (imm32 == 0) {
@@ -400,7 +373,8 @@ static void emit_mov_imm64(u8 **pprog, u32 dst_reg,
 	int cnt = 0;
 
 	if (is_uimm32(((u64)imm32_hi << 32) | (u32)imm32_lo)) {
-		/* For emitting plain u32, where sign bit must not be
+		/*
+		 * For emitting plain u32, where sign bit must not be
 		 * propagated LLVM tends to load imm64 over mov32
 		 * directly, so save couple of bytes by just doing
 		 * 'mov %eax, imm32' instead.
@@ -439,8 +413,6 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 {
 	struct bpf_insn *insn = bpf_prog->insnsi;
 	int insn_cnt = bpf_prog->len;
-	bool seen_ld_abs = ctx->seen_ld_abs | (oldproglen == 0);
-	bool seen_ax_reg = ctx->seen_ax_reg | (oldproglen == 0);
 	bool seen_exit = false;
 	u8 temp[BPF_MAX_INSN_SIZE + BPF_INSN_SAFETY];
 	int i, cnt = 0;
@@ -450,9 +422,6 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 	emit_prologue(&prog, bpf_prog->aux->stack_depth,
 		      bpf_prog_was_classic(bpf_prog));
 
-	if (seen_ld_abs)
-		emit_load_skb_data_hlen(&prog);
-
 	for (i = 0; i < insn_cnt; i++, insn++) {
 		const s32 imm32 = insn->imm;
 		u32 dst_reg = insn->dst_reg;
@@ -460,13 +429,9 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 		u8 b2 = 0, b3 = 0;
 		s64 jmp_offset;
 		u8 jmp_cond;
-		bool reload_skb_data;
 		int ilen;
 		u8 *func;
 
-		if (dst_reg == BPF_REG_AX || src_reg == BPF_REG_AX)
-			ctx->seen_ax_reg = seen_ax_reg = true;
-
 		switch (insn->code) {
 			/* ALU */
 		case BPF_ALU | BPF_ADD | BPF_X:
@@ -525,7 +490,8 @@ 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
+			/*
+			 * b3 holds 'normal' opcode, b2 short form only valid
 			 * in case dst is eax/rax.
 			 */
 			switch (BPF_OP(insn->code)) {
@@ -593,7 +559,8 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 			/* mov rax, dst_reg */
 			EMIT_mov(BPF_REG_0, dst_reg);
 
-			/* xor edx, edx
+			/*
+			 * xor edx, edx
 			 * equivalent to 'xor rdx, rdx', but one byte less
 			 */
 			EMIT2(0x31, 0xd2);
@@ -655,7 +622,7 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 			}
 			break;
 		}
-			/* shifts */
+			/* Shifts */
 		case BPF_ALU | BPF_LSH | BPF_K:
 		case BPF_ALU | BPF_RSH | BPF_K:
 		case BPF_ALU | BPF_ARSH | BPF_K:
@@ -686,7 +653,7 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 		case BPF_ALU64 | BPF_RSH | BPF_X:
 		case BPF_ALU64 | BPF_ARSH | BPF_X:
 
-			/* check for bad case when dst_reg == rcx */
+			/* Check for bad case when dst_reg == rcx */
 			if (dst_reg == BPF_REG_4) {
 				/* mov r11, dst_reg */
 				EMIT_mov(AUX_REG, dst_reg);
@@ -724,13 +691,13 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 		case BPF_ALU | BPF_END | BPF_FROM_BE:
 			switch (imm32) {
 			case 16:
-				/* emit 'ror %ax, 8' to swap lower 2 bytes */
+				/* Emit 'ror %ax, 8' to swap lower 2 bytes */
 				EMIT1(0x66);
 				if (is_ereg(dst_reg))
 					EMIT1(0x41);
 				EMIT3(0xC1, add_1reg(0xC8, dst_reg), 8);
 
-				/* emit 'movzwl eax, ax' */
+				/* Emit 'movzwl eax, ax' */
 				if (is_ereg(dst_reg))
 					EMIT3(0x45, 0x0F, 0xB7);
 				else
@@ -738,7 +705,7 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 				EMIT1(add_2reg(0xC0, dst_reg, dst_reg));
 				break;
 			case 32:
-				/* emit 'bswap eax' to swap lower 4 bytes */
+				/* Emit 'bswap eax' to swap lower 4 bytes */
 				if (is_ereg(dst_reg))
 					EMIT2(0x41, 0x0F);
 				else
@@ -746,7 +713,7 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 				EMIT1(add_1reg(0xC8, dst_reg));
 				break;
 			case 64:
-				/* emit 'bswap rax' to swap 8 bytes */
+				/* Emit 'bswap rax' to swap 8 bytes */
 				EMIT3(add_1mod(0x48, dst_reg), 0x0F,
 				      add_1reg(0xC8, dst_reg));
 				break;
@@ -756,7 +723,8 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 		case BPF_ALU | BPF_END | BPF_FROM_LE:
 			switch (imm32) {
 			case 16:
-				/* emit 'movzwl eax, ax' to zero extend 16-bit
+				/*
+				 * Emit 'movzwl eax, ax' to zero extend 16-bit
 				 * into 64 bit
 				 */
 				if (is_ereg(dst_reg))
@@ -766,7 +734,7 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 				EMIT1(add_2reg(0xC0, dst_reg, dst_reg));
 				break;
 			case 32:
-				/* emit 'mov eax, eax' to clear upper 32-bits */
+				/* Emit 'mov eax, eax' to clear upper 32-bits */
 				if (is_ereg(dst_reg))
 					EMIT1(0x45);
 				EMIT2(0x89, add_2reg(0xC0, dst_reg, dst_reg));
@@ -809,9 +777,9 @@ st:			if (is_imm8(insn->off))
 
 			/* STX: *(u8*)(dst_reg + off) = src_reg */
 		case BPF_STX | BPF_MEM | BPF_B:
-			/* emit 'mov byte ptr [rax + off], al' */
+			/* Emit 'mov byte ptr [rax + off], al' */
 			if (is_ereg(dst_reg) || is_ereg(src_reg) ||
-			    /* have to add extra byte for x86 SIL, DIL regs */
+			    /* We have to add extra byte for x86 SIL, DIL regs */
 			    src_reg == BPF_REG_1 || src_reg == BPF_REG_2)
 				EMIT2(add_2mod(0x40, dst_reg, src_reg), 0x88);
 			else
@@ -840,25 +808,26 @@ stx:			if (is_imm8(insn->off))
 
 			/* LDX: dst_reg = *(u8*)(src_reg + off) */
 		case BPF_LDX | BPF_MEM | BPF_B:
-			/* emit 'movzx rax, byte ptr [rax + off]' */
+			/* Emit 'movzx rax, byte ptr [rax + off]' */
 			EMIT3(add_2mod(0x48, src_reg, dst_reg), 0x0F, 0xB6);
 			goto ldx;
 		case BPF_LDX | BPF_MEM | BPF_H:
-			/* emit 'movzx rax, word ptr [rax + off]' */
+			/* Emit 'movzx rax, word ptr [rax + off]' */
 			EMIT3(add_2mod(0x48, src_reg, dst_reg), 0x0F, 0xB7);
 			goto ldx;
 		case BPF_LDX | BPF_MEM | BPF_W:
-			/* emit 'mov eax, dword ptr [rax+0x14]' */
+			/* Emit 'mov eax, dword ptr [rax+0x14]' */
 			if (is_ereg(dst_reg) || is_ereg(src_reg))
 				EMIT2(add_2mod(0x40, src_reg, dst_reg), 0x8B);
 			else
 				EMIT1(0x8B);
 			goto ldx;
 		case BPF_LDX | BPF_MEM | BPF_DW:
-			/* emit 'mov rax, qword ptr [rax+0x14]' */
+			/* Emit 'mov rax, qword ptr [rax+0x14]' */
 			EMIT2(add_2mod(0x48, src_reg, dst_reg), 0x8B);
-ldx:			/* if insn->off == 0 we can save one extra byte, but
-			 * special case of x86 r13 which always needs an offset
+ldx:			/*
+			 * If insn->off == 0 we can save one extra byte, but
+			 * special case of x86 R13 which always needs an offset
 			 * is not worth the hassle
 			 */
 			if (is_imm8(insn->off))
@@ -870,7 +839,7 @@ ldx:			/* if insn->off == 0 we can save one extra byte, but
 
 			/* STX XADD: lock *(u32*)(dst_reg + off) += src_reg */
 		case BPF_STX | BPF_XADD | BPF_W:
-			/* emit 'lock add dword ptr [rax + off], eax' */
+			/* Emit 'lock add dword ptr [rax + off], eax' */
 			if (is_ereg(dst_reg) || is_ereg(src_reg))
 				EMIT3(0xF0, add_2mod(0x40, dst_reg, src_reg), 0x01);
 			else
@@ -889,35 +858,12 @@ xadd:			if (is_imm8(insn->off))
 		case BPF_JMP | BPF_CALL:
 			func = (u8 *) __bpf_call_base + imm32;
 			jmp_offset = func - (image + addrs[i]);
-			if (seen_ld_abs) {
-				reload_skb_data = bpf_helper_changes_pkt_data(func);
-				if (reload_skb_data) {
-					EMIT1(0x57); /* push %rdi */
-					jmp_offset += 22; /* pop, mov, sub, mov */
-				} else {
-					EMIT2(0x41, 0x52); /* push %r10 */
-					EMIT2(0x41, 0x51); /* push %r9 */
-					/* need to adjust jmp offset, since
-					 * pop %r9, pop %r10 take 4 bytes after call insn
-					 */
-					jmp_offset += 4;
-				}
-			}
 			if (!imm32 || !is_simm32(jmp_offset)) {
-				pr_err("unsupported bpf func %d addr %p image %p\n",
+				pr_err("unsupported BPF func %d addr %p image %p\n",
 				       imm32, func, image);
 				return -EINVAL;
 			}
 			EMIT1_off32(0xE8, jmp_offset);
-			if (seen_ld_abs) {
-				if (reload_skb_data) {
-					EMIT1(0x5F); /* pop %rdi */
-					emit_load_skb_data_hlen(&prog);
-				} else {
-					EMIT2(0x41, 0x59); /* pop %r9 */
-					EMIT2(0x41, 0x5A); /* pop %r10 */
-				}
-			}
 			break;
 
 		case BPF_JMP | BPF_TAIL_CALL:
@@ -970,7 +916,7 @@ xadd:			if (is_imm8(insn->off))
 			else
 				EMIT2_off32(0x81, add_1reg(0xF8, dst_reg), imm32);
 
-emit_cond_jmp:		/* convert BPF opcode to x86 */
+emit_cond_jmp:		/* Convert BPF opcode to x86 */
 			switch (BPF_OP(insn->code)) {
 			case BPF_JEQ:
 				jmp_cond = X86_JE;
@@ -996,22 +942,22 @@ emit_cond_jmp:		/* convert BPF opcode to x86 */
 				jmp_cond = X86_JBE;
 				break;
 			case BPF_JSGT:
-				/* signed '>', GT in x86 */
+				/* Signed '>', GT in x86 */
 				jmp_cond = X86_JG;
 				break;
 			case BPF_JSLT:
-				/* signed '<', LT in x86 */
+				/* Signed '<', LT in x86 */
 				jmp_cond = X86_JL;
 				break;
 			case BPF_JSGE:
-				/* signed '>=', GE in x86 */
+				/* Signed '>=', GE in x86 */
 				jmp_cond = X86_JGE;
 				break;
 			case BPF_JSLE:
-				/* signed '<=', LE in x86 */
+				/* Signed '<=', LE in x86 */
 				jmp_cond = X86_JLE;
 				break;
-			default: /* to silence gcc warning */
+			default: /* to silence GCC warning */
 				return -EFAULT;
 			}
 			jmp_offset = addrs[i + insn->off] - addrs[i];
@@ -1039,7 +985,7 @@ emit_cond_jmp:		/* convert BPF opcode to x86 */
 				jmp_offset = addrs[i + insn->off] - addrs[i];
 
 			if (!jmp_offset)
-				/* optimize out nop jumps */
+				/* Optimize out nop jumps */
 				break;
 emit_jmp:
 			if (is_imm8(jmp_offset)) {
@@ -1052,66 +998,13 @@ emit_jmp:
 			}
 			break;
 
-		case BPF_LD | BPF_IND | BPF_W:
-			func = sk_load_word;
-			goto common_load;
-		case BPF_LD | BPF_ABS | BPF_W:
-			func = CHOOSE_LOAD_FUNC(imm32, sk_load_word);
-common_load:
-			ctx->seen_ld_abs = seen_ld_abs = true;
-			jmp_offset = func - (image + addrs[i]);
-			if (!func || !is_simm32(jmp_offset)) {
-				pr_err("unsupported bpf func %d addr %p image %p\n",
-				       imm32, func, image);
-				return -EINVAL;
-			}
-			if (BPF_MODE(insn->code) == BPF_ABS) {
-				/* mov %esi, imm32 */
-				EMIT1_off32(0xBE, imm32);
-			} else {
-				/* mov %rsi, src_reg */
-				EMIT_mov(BPF_REG_2, src_reg);
-				if (imm32) {
-					if (is_imm8(imm32))
-						/* add %esi, imm8 */
-						EMIT3(0x83, 0xC6, imm32);
-					else
-						/* add %esi, imm32 */
-						EMIT2_off32(0x81, 0xC6, imm32);
-				}
-			}
-			/* skb pointer is in R6 (%rbx), it will be copied into
-			 * %rdi if skb_copy_bits() call is necessary.
-			 * sk_load_* helpers also use %r10 and %r9d.
-			 * See bpf_jit.S
-			 */
-			if (seen_ax_reg)
-				/* r10 = skb->data, mov %r10, off32(%rbx) */
-				EMIT3_off32(0x4c, 0x8b, 0x93,
-					    offsetof(struct sk_buff, data));
-			EMIT1_off32(0xE8, jmp_offset); /* call */
-			break;
-
-		case BPF_LD | BPF_IND | BPF_H:
-			func = sk_load_half;
-			goto common_load;
-		case BPF_LD | BPF_ABS | BPF_H:
-			func = CHOOSE_LOAD_FUNC(imm32, sk_load_half);
-			goto common_load;
-		case BPF_LD | BPF_IND | BPF_B:
-			func = sk_load_byte;
-			goto common_load;
-		case BPF_LD | BPF_ABS | BPF_B:
-			func = CHOOSE_LOAD_FUNC(imm32, sk_load_byte);
-			goto common_load;
-
 		case BPF_JMP | BPF_EXIT:
 			if (seen_exit) {
 				jmp_offset = ctx->cleanup_addr - addrs[i];
 				goto emit_jmp;
 			}
 			seen_exit = true;
-			/* update cleanup_addr */
+			/* Update cleanup_addr */
 			ctx->cleanup_addr = proglen;
 			/* mov rbx, qword ptr [rbp+0] */
 			EMIT4(0x48, 0x8B, 0x5D, 0);
@@ -1129,10 +1022,11 @@ common_load:
 			break;
 
 		default:
-			/* By design x64 JIT should support all BPF instructions
+			/*
+			 * By design x86-64 JIT should support all BPF instructions.
 			 * This error will be seen if new instruction was added
-			 * to interpreter, but not to JIT
-			 * or if there is junk in bpf_prog
+			 * to the interpreter, but not to the JIT, or if there is
+			 * junk in bpf_prog.
 			 */
 			pr_err("bpf_jit: unknown opcode %02x\n", insn->code);
 			return -EINVAL;
@@ -1184,7 +1078,8 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 		return orig_prog;
 
 	tmp = bpf_jit_blind_constants(prog);
-	/* If blinding was requested and we failed during blinding,
+	/*
+	 * If blinding was requested and we failed during blinding,
 	 * we must fall back to the interpreter.
 	 */
 	if (IS_ERR(tmp))
@@ -1218,8 +1113,9 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 		goto out_addrs;
 	}
 
-	/* Before first pass, make a rough estimation of addrs[]
-	 * each bpf instruction is translated to less than 64 bytes
+	/*
+	 * Before first pass, make a rough estimation of addrs[]
+	 * each BPF instruction is translated to less than 64 bytes
 	 */
 	for (proglen = 0, i = 0; i < prog->len; i++) {
 		proglen += 64;
@@ -1228,10 +1124,11 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 	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
+	/*
+	 * JITed image shrinks with every pass and the loop iterates
+	 * until the image stops shrinking. Very large BPF programs
 	 * may converge on the last pass. In such case do one more
-	 * pass to emit the final image
+	 * pass to emit the final image.
 	 */
 	for (pass = 0; pass < 20 || image; pass++) {
 		proglen = do_jit(prog, addrs, image, oldproglen, &ctx);
diff --git a/arch/x86/net/bpf_jit_comp32.c b/arch/x86/net/bpf_jit_comp32.c
new file mode 100644
index 000000000000..0cc04e30adc1
--- /dev/null
+++ b/arch/x86/net/bpf_jit_comp32.c
@@ -0,0 +1,2419 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Just-In-Time compiler for eBPF filters on IA32 (32bit x86)
+ *
+ * Author: Wang YanQing (udknight@gmail.com)
+ * The code based on code and ideas from:
+ * Eric Dumazet (eric.dumazet@gmail.com)
+ * and from:
+ * Shubham Bansal <illusionist.neo@gmail.com>
+ */
+
+#include <linux/netdevice.h>
+#include <linux/filter.h>
+#include <linux/if_vlan.h>
+#include <asm/cacheflush.h>
+#include <asm/set_memory.h>
+#include <asm/nospec-branch.h>
+#include <linux/bpf.h>
+
+/*
+ * eBPF prog stack layout:
+ *
+ *                         high
+ * original ESP =>        +-----+
+ *                        |     | callee saved registers
+ *                        +-----+
+ *                        | ... | eBPF JIT scratch space
+ * BPF_FP,IA32_EBP  =>    +-----+
+ *                        | ... | eBPF prog stack
+ *                        +-----+
+ *                        |RSVD | JIT scratchpad
+ * current ESP =>         +-----+
+ *                        |     |
+ *                        | ... | Function call stack
+ *                        |     |
+ *                        +-----+
+ *                          low
+ *
+ * The callee saved registers:
+ *
+ *                                high
+ * original ESP =>        +------------------+ \
+ *                        |        ebp       | |
+ * current EBP =>         +------------------+ } callee saved registers
+ *                        |    ebx,esi,edi   | |
+ *                        +------------------+ /
+ *                                low
+ */
+
+static u8 *emit_code(u8 *ptr, u32 bytes, unsigned int len)
+{
+	if (len == 1)
+		*ptr = bytes;
+	else if (len == 2)
+		*(u16 *)ptr = bytes;
+	else {
+		*(u32 *)ptr = bytes;
+		barrier();
+	}
+	return ptr + len;
+}
+
+#define EMIT(bytes, len) \
+	do { prog = emit_code(prog, bytes, len); cnt += len; } while (0)
+
+#define EMIT1(b1)		EMIT(b1, 1)
+#define EMIT2(b1, b2)		EMIT((b1) + ((b2) << 8), 2)
+#define EMIT3(b1, b2, b3)	EMIT((b1) + ((b2) << 8) + ((b3) << 16), 3)
+#define EMIT4(b1, b2, b3, b4)   \
+	EMIT((b1) + ((b2) << 8) + ((b3) << 16) + ((b4) << 24), 4)
+
+#define EMIT1_off32(b1, off) \
+	do { EMIT1(b1); EMIT(off, 4); } while (0)
+#define EMIT2_off32(b1, b2, off) \
+	do { EMIT2(b1, b2); EMIT(off, 4); } while (0)
+#define EMIT3_off32(b1, b2, b3, off) \
+	do { EMIT3(b1, b2, b3); EMIT(off, 4); } while (0)
+#define EMIT4_off32(b1, b2, b3, b4, off) \
+	do { EMIT4(b1, b2, b3, b4); EMIT(off, 4); } while (0)
+
+#define jmp_label(label, jmp_insn_len) (label - cnt - jmp_insn_len)
+
+static bool is_imm8(int value)
+{
+	return value <= 127 && value >= -128;
+}
+
+static bool is_simm32(s64 value)
+{
+	return value == (s64) (s32) value;
+}
+
+#define STACK_OFFSET(k)	(k)
+#define TCALL_CNT	(MAX_BPF_JIT_REG + 0)	/* Tail Call Count */
+
+#define IA32_EAX	(0x0)
+#define IA32_EBX	(0x3)
+#define IA32_ECX	(0x1)
+#define IA32_EDX	(0x2)
+#define IA32_ESI	(0x6)
+#define IA32_EDI	(0x7)
+#define IA32_EBP	(0x5)
+#define IA32_ESP	(0x4)
+
+/*
+ * List of x86 cond jumps opcodes (. + s8)
+ * Add 0x10 (and an extra 0x0f) to generate far jumps (. + s32)
+ */
+#define IA32_JB  0x72
+#define IA32_JAE 0x73
+#define IA32_JE  0x74
+#define IA32_JNE 0x75
+#define IA32_JBE 0x76
+#define IA32_JA  0x77
+#define IA32_JL  0x7C
+#define IA32_JGE 0x7D
+#define IA32_JLE 0x7E
+#define IA32_JG  0x7F
+
+/*
+ * Map eBPF registers to IA32 32bit registers or stack scratch space.
+ *
+ * 1. All the registers, R0-R10, are mapped to scratch space on stack.
+ * 2. We need two 64 bit temp registers to do complex operations on eBPF
+ *    registers.
+ * 3. For performance reason, the BPF_REG_AX for blinding constant, is
+ *    mapped to real hardware register pair, IA32_ESI and IA32_EDI.
+ *
+ * As the eBPF registers are all 64 bit registers and IA32 has only 32 bit
+ * registers, we have to map each eBPF registers with two IA32 32 bit regs
+ * or scratch memory space and we have to build eBPF 64 bit register from those.
+ *
+ * We use IA32_EAX, IA32_EDX, IA32_ECX, IA32_EBX as temporary registers.
+ */
+static const u8 bpf2ia32[][2] = {
+	/* Return value from in-kernel function, and exit value from eBPF */
+	[BPF_REG_0] = {STACK_OFFSET(0), STACK_OFFSET(4)},
+
+	/* The arguments from eBPF program to in-kernel function */
+	/* Stored on stack scratch space */
+	[BPF_REG_1] = {STACK_OFFSET(8), STACK_OFFSET(12)},
+	[BPF_REG_2] = {STACK_OFFSET(16), STACK_OFFSET(20)},
+	[BPF_REG_3] = {STACK_OFFSET(24), STACK_OFFSET(28)},
+	[BPF_REG_4] = {STACK_OFFSET(32), STACK_OFFSET(36)},
+	[BPF_REG_5] = {STACK_OFFSET(40), STACK_OFFSET(44)},
+
+	/* Callee saved registers that in-kernel function will preserve */
+	/* Stored on stack scratch space */
+	[BPF_REG_6] = {STACK_OFFSET(48), STACK_OFFSET(52)},
+	[BPF_REG_7] = {STACK_OFFSET(56), STACK_OFFSET(60)},
+	[BPF_REG_8] = {STACK_OFFSET(64), STACK_OFFSET(68)},
+	[BPF_REG_9] = {STACK_OFFSET(72), STACK_OFFSET(76)},
+
+	/* Read only Frame Pointer to access Stack */
+	[BPF_REG_FP] = {STACK_OFFSET(80), STACK_OFFSET(84)},
+
+	/* Temporary register for blinding constants. */
+	[BPF_REG_AX] = {IA32_ESI, IA32_EDI},
+
+	/* Tail call count. Stored on stack scratch space. */
+	[TCALL_CNT] = {STACK_OFFSET(88), STACK_OFFSET(92)},
+};
+
+#define dst_lo	dst[0]
+#define dst_hi	dst[1]
+#define src_lo	src[0]
+#define src_hi	src[1]
+
+#define STACK_ALIGNMENT	8
+/*
+ * Stack space for BPF_REG_1, BPF_REG_2, BPF_REG_3, BPF_REG_4,
+ * BPF_REG_5, BPF_REG_6, BPF_REG_7, BPF_REG_8, BPF_REG_9,
+ * BPF_REG_FP, BPF_REG_AX and Tail call counts.
+ */
+#define SCRATCH_SIZE 96
+
+/* Total stack size used in JITed code */
+#define _STACK_SIZE	(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) (off)
+
+/* Encode 'dst_reg' register into IA32 opcode 'byte' */
+static u8 add_1reg(u8 byte, u32 dst_reg)
+{
+	return byte + dst_reg;
+}
+
+/* Encode 'dst_reg' and 'src_reg' registers into IA32 opcode 'byte' */
+static u8 add_2reg(u8 byte, u32 dst_reg, u32 src_reg)
+{
+	return byte + dst_reg + (src_reg << 3);
+}
+
+static void jit_fill_hole(void *area, unsigned int size)
+{
+	/* Fill whole space with int3 instructions */
+	memset(area, 0xcc, size);
+}
+
+static inline void emit_ia32_mov_i(const u8 dst, const u32 val, bool dstk,
+				   u8 **pprog)
+{
+	u8 *prog = *pprog;
+	int cnt = 0;
+
+	if (dstk) {
+		if (val == 0) {
+			/* xor eax,eax */
+			EMIT2(0x33, add_2reg(0xC0, IA32_EAX, IA32_EAX));
+			/* mov dword ptr [ebp+off],eax */
+			EMIT3(0x89, add_2reg(0x40, IA32_EBP, IA32_EAX),
+			      STACK_VAR(dst));
+		} else {
+			EMIT3_off32(0xC7, add_1reg(0x40, IA32_EBP),
+				    STACK_VAR(dst), val);
+		}
+	} else {
+		if (val == 0)
+			EMIT2(0x33, add_2reg(0xC0, dst, dst));
+		else
+			EMIT2_off32(0xC7, add_1reg(0xC0, dst),
+				    val);
+	}
+	*pprog = prog;
+}
+
+/* dst = imm (4 bytes)*/
+static inline void emit_ia32_mov_r(const u8 dst, const u8 src, bool dstk,
+				   bool sstk, u8 **pprog)
+{
+	u8 *prog = *pprog;
+	int cnt = 0;
+	u8 sreg = sstk ? IA32_EAX : src;
+
+	if (sstk)
+		/* mov eax,dword ptr [ebp+off] */
+		EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EAX), STACK_VAR(src));
+	if (dstk)
+		/* mov dword ptr [ebp+off],eax */
+		EMIT3(0x89, add_2reg(0x40, IA32_EBP, sreg), STACK_VAR(dst));
+	else
+		/* mov dst,sreg */
+		EMIT2(0x89, add_2reg(0xC0, dst, sreg));
+
+	*pprog = prog;
+}
+
+/* dst = src */
+static inline void emit_ia32_mov_r64(const bool is64, const u8 dst[],
+				     const u8 src[], bool dstk,
+				     bool sstk, u8 **pprog)
+{
+	emit_ia32_mov_r(dst_lo, src_lo, dstk, sstk, pprog);
+	if (is64)
+		/* complete 8 byte move */
+		emit_ia32_mov_r(dst_hi, src_hi, dstk, sstk, pprog);
+	else
+		/* zero out high 4 bytes */
+		emit_ia32_mov_i(dst_hi, 0, dstk, pprog);
+}
+
+/* Sign extended move */
+static inline void emit_ia32_mov_i64(const bool is64, const u8 dst[],
+				     const u32 val, bool dstk, u8 **pprog)
+{
+	u32 hi = 0;
+
+	if (is64 && (val & (1<<31)))
+		hi = (u32)~0;
+	emit_ia32_mov_i(dst_lo, val, dstk, pprog);
+	emit_ia32_mov_i(dst_hi, hi, dstk, pprog);
+}
+
+/*
+ * ALU operation (32 bit)
+ * dst = dst * src
+ */
+static inline void emit_ia32_mul_r(const u8 dst, const u8 src, bool dstk,
+				   bool sstk, u8 **pprog)
+{
+	u8 *prog = *pprog;
+	int cnt = 0;
+	u8 sreg = sstk ? IA32_ECX : src;
+
+	if (sstk)
+		/* mov ecx,dword ptr [ebp+off] */
+		EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_ECX), STACK_VAR(src));
+
+	if (dstk)
+		/* mov eax,dword ptr [ebp+off] */
+		EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EAX), STACK_VAR(dst));
+	else
+		/* mov eax,dst */
+		EMIT2(0x8B, add_2reg(0xC0, dst, IA32_EAX));
+
+
+	EMIT2(0xF7, add_1reg(0xE0, sreg));
+
+	if (dstk)
+		/* mov dword ptr [ebp+off],eax */
+		EMIT3(0x89, add_2reg(0x40, IA32_EBP, IA32_EAX),
+		      STACK_VAR(dst));
+	else
+		/* mov dst,eax */
+		EMIT2(0x89, add_2reg(0xC0, dst, IA32_EAX));
+
+	*pprog = prog;
+}
+
+static inline void emit_ia32_to_le_r64(const u8 dst[], s32 val,
+					 bool dstk, u8 **pprog)
+{
+	u8 *prog = *pprog;
+	int cnt = 0;
+	u8 dreg_lo = dstk ? IA32_EAX : dst_lo;
+	u8 dreg_hi = dstk ? IA32_EDX : dst_hi;
+
+	if (dstk && val != 64) {
+		EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EAX),
+		      STACK_VAR(dst_lo));
+		EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EDX),
+		      STACK_VAR(dst_hi));
+	}
+	switch (val) {
+	case 16:
+		/*
+		 * Emit 'movzwl eax,ax' to zero extend 16-bit
+		 * into 64 bit
+		 */
+		EMIT2(0x0F, 0xB7);
+		EMIT1(add_2reg(0xC0, dreg_lo, dreg_lo));
+		/* xor dreg_hi,dreg_hi */
+		EMIT2(0x33, add_2reg(0xC0, dreg_hi, dreg_hi));
+		break;
+	case 32:
+		/* xor dreg_hi,dreg_hi */
+		EMIT2(0x33, add_2reg(0xC0, dreg_hi, dreg_hi));
+		break;
+	case 64:
+		/* nop */
+		break;
+	}
+
+	if (dstk && val != 64) {
+		/* mov dword ptr [ebp+off],dreg_lo */
+		EMIT3(0x89, add_2reg(0x40, IA32_EBP, dreg_lo),
+		      STACK_VAR(dst_lo));
+		/* mov dword ptr [ebp+off],dreg_hi */
+		EMIT3(0x89, add_2reg(0x40, IA32_EBP, dreg_hi),
+		      STACK_VAR(dst_hi));
+	}
+	*pprog = prog;
+}
+
+static inline void emit_ia32_to_be_r64(const u8 dst[], s32 val,
+				       bool dstk, u8 **pprog)
+{
+	u8 *prog = *pprog;
+	int cnt = 0;
+	u8 dreg_lo = dstk ? IA32_EAX : dst_lo;
+	u8 dreg_hi = dstk ? IA32_EDX : dst_hi;
+
+	if (dstk) {
+		EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EAX),
+		      STACK_VAR(dst_lo));
+		EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EDX),
+		      STACK_VAR(dst_hi));
+	}
+	switch (val) {
+	case 16:
+		/* Emit 'ror %ax, 8' to swap lower 2 bytes */
+		EMIT1(0x66);
+		EMIT3(0xC1, add_1reg(0xC8, dreg_lo), 8);
+
+		EMIT2(0x0F, 0xB7);
+		EMIT1(add_2reg(0xC0, dreg_lo, dreg_lo));
+
+		/* xor dreg_hi,dreg_hi */
+		EMIT2(0x33, add_2reg(0xC0, dreg_hi, dreg_hi));
+		break;
+	case 32:
+		/* Emit 'bswap eax' to swap lower 4 bytes */
+		EMIT1(0x0F);
+		EMIT1(add_1reg(0xC8, dreg_lo));
+
+		/* xor dreg_hi,dreg_hi */
+		EMIT2(0x33, add_2reg(0xC0, dreg_hi, dreg_hi));
+		break;
+	case 64:
+		/* Emit 'bswap eax' to swap lower 4 bytes */
+		EMIT1(0x0F);
+		EMIT1(add_1reg(0xC8, dreg_lo));
+
+		/* Emit 'bswap edx' to swap lower 4 bytes */
+		EMIT1(0x0F);
+		EMIT1(add_1reg(0xC8, dreg_hi));
+
+		/* mov ecx,dreg_hi */
+		EMIT2(0x89, add_2reg(0xC0, IA32_ECX, dreg_hi));
+		/* mov dreg_hi,dreg_lo */
+		EMIT2(0x89, add_2reg(0xC0, dreg_hi, dreg_lo));
+		/* mov dreg_lo,ecx */
+		EMIT2(0x89, add_2reg(0xC0, dreg_lo, IA32_ECX));
+
+		break;
+	}
+	if (dstk) {
+		/* mov dword ptr [ebp+off],dreg_lo */
+		EMIT3(0x89, add_2reg(0x40, IA32_EBP, dreg_lo),
+		      STACK_VAR(dst_lo));
+		/* mov dword ptr [ebp+off],dreg_hi */
+		EMIT3(0x89, add_2reg(0x40, IA32_EBP, dreg_hi),
+		      STACK_VAR(dst_hi));
+	}
+	*pprog = prog;
+}
+
+/*
+ * ALU operation (32 bit)
+ * dst = dst (div|mod) src
+ */
+static inline void emit_ia32_div_mod_r(const u8 op, const u8 dst, const u8 src,
+				       bool dstk, bool sstk, u8 **pprog)
+{
+	u8 *prog = *pprog;
+	int cnt = 0;
+
+	if (sstk)
+		/* mov ecx,dword ptr [ebp+off] */
+		EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_ECX),
+		      STACK_VAR(src));
+	else if (src != IA32_ECX)
+		/* mov ecx,src */
+		EMIT2(0x8B, add_2reg(0xC0, src, IA32_ECX));
+
+	if (dstk)
+		/* mov eax,dword ptr [ebp+off] */
+		EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EAX),
+		      STACK_VAR(dst));
+	else
+		/* mov eax,dst */
+		EMIT2(0x8B, add_2reg(0xC0, dst, IA32_EAX));
+
+	/* xor edx,edx */
+	EMIT2(0x31, add_2reg(0xC0, IA32_EDX, IA32_EDX));
+	/* div ecx */
+	EMIT2(0xF7, add_1reg(0xF0, IA32_ECX));
+
+	if (op == BPF_MOD) {
+		if (dstk)
+			EMIT3(0x89, add_2reg(0x40, IA32_EBP, IA32_EDX),
+			      STACK_VAR(dst));
+		else
+			EMIT2(0x89, add_2reg(0xC0, dst, IA32_EDX));
+	} else {
+		if (dstk)
+			EMIT3(0x89, add_2reg(0x40, IA32_EBP, IA32_EAX),
+			      STACK_VAR(dst));
+		else
+			EMIT2(0x89, add_2reg(0xC0, dst, IA32_EAX));
+	}
+	*pprog = prog;
+}
+
+/*
+ * ALU operation (32 bit)
+ * dst = dst (shift) src
+ */
+static inline void emit_ia32_shift_r(const u8 op, const u8 dst, const u8 src,
+				     bool dstk, bool sstk, u8 **pprog)
+{
+	u8 *prog = *pprog;
+	int cnt = 0;
+	u8 dreg = dstk ? IA32_EAX : dst;
+	u8 b2;
+
+	if (dstk)
+		/* mov eax,dword ptr [ebp+off] */
+		EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EAX), STACK_VAR(dst));
+
+	if (sstk)
+		/* mov ecx,dword ptr [ebp+off] */
+		EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_ECX), STACK_VAR(src));
+	else if (src != IA32_ECX)
+		/* mov ecx,src */
+		EMIT2(0x8B, add_2reg(0xC0, src, IA32_ECX));
+
+	switch (op) {
+	case BPF_LSH:
+		b2 = 0xE0; break;
+	case BPF_RSH:
+		b2 = 0xE8; break;
+	case BPF_ARSH:
+		b2 = 0xF8; break;
+	default:
+		return;
+	}
+	EMIT2(0xD3, add_1reg(b2, dreg));
+
+	if (dstk)
+		/* mov dword ptr [ebp+off],dreg */
+		EMIT3(0x89, add_2reg(0x40, IA32_EBP, dreg), STACK_VAR(dst));
+	*pprog = prog;
+}
+
+/*
+ * ALU operation (32 bit)
+ * dst = dst (op) src
+ */
+static inline void emit_ia32_alu_r(const bool is64, const bool hi, const u8 op,
+				   const u8 dst, const u8 src, bool dstk,
+				   bool sstk, u8 **pprog)
+{
+	u8 *prog = *pprog;
+	int cnt = 0;
+	u8 sreg = sstk ? IA32_EAX : src;
+	u8 dreg = dstk ? IA32_EDX : dst;
+
+	if (sstk)
+		/* mov eax,dword ptr [ebp+off] */
+		EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EAX), STACK_VAR(src));
+
+	if (dstk)
+		/* mov eax,dword ptr [ebp+off] */
+		EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EDX), STACK_VAR(dst));
+
+	switch (BPF_OP(op)) {
+	/* dst = dst + src */
+	case BPF_ADD:
+		if (hi && is64)
+			EMIT2(0x11, add_2reg(0xC0, dreg, sreg));
+		else
+			EMIT2(0x01, add_2reg(0xC0, dreg, sreg));
+		break;
+	/* dst = dst - src */
+	case BPF_SUB:
+		if (hi && is64)
+			EMIT2(0x19, add_2reg(0xC0, dreg, sreg));
+		else
+			EMIT2(0x29, add_2reg(0xC0, dreg, sreg));
+		break;
+	/* dst = dst | src */
+	case BPF_OR:
+		EMIT2(0x09, add_2reg(0xC0, dreg, sreg));
+		break;
+	/* dst = dst & src */
+	case BPF_AND:
+		EMIT2(0x21, add_2reg(0xC0, dreg, sreg));
+		break;
+	/* dst = dst ^ src */
+	case BPF_XOR:
+		EMIT2(0x31, add_2reg(0xC0, dreg, sreg));
+		break;
+	}
+
+	if (dstk)
+		/* mov dword ptr [ebp+off],dreg */
+		EMIT3(0x89, add_2reg(0x40, IA32_EBP, dreg),
+		      STACK_VAR(dst));
+	*pprog = prog;
+}
+
+/* ALU operation (64 bit) */
+static inline void emit_ia32_alu_r64(const bool is64, const u8 op,
+				     const u8 dst[], const u8 src[],
+				     bool dstk,  bool sstk,
+				     u8 **pprog)
+{
+	u8 *prog = *pprog;
+
+	emit_ia32_alu_r(is64, false, op, dst_lo, src_lo, dstk, sstk, &prog);
+	if (is64)
+		emit_ia32_alu_r(is64, true, op, dst_hi, src_hi, dstk, sstk,
+				&prog);
+	else
+		emit_ia32_mov_i(dst_hi, 0, dstk, &prog);
+	*pprog = prog;
+}
+
+/*
+ * ALU operation (32 bit)
+ * dst = dst (op) val
+ */
+static inline void emit_ia32_alu_i(const bool is64, const bool hi, const u8 op,
+				   const u8 dst, const s32 val, bool dstk,
+				   u8 **pprog)
+{
+	u8 *prog = *pprog;
+	int cnt = 0;
+	u8 dreg = dstk ? IA32_EAX : dst;
+	u8 sreg = IA32_EDX;
+
+	if (dstk)
+		/* mov eax,dword ptr [ebp+off] */
+		EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EAX), STACK_VAR(dst));
+
+	if (!is_imm8(val))
+		/* mov edx,imm32*/
+		EMIT2_off32(0xC7, add_1reg(0xC0, IA32_EDX), val);
+
+	switch (op) {
+	/* dst = dst + val */
+	case BPF_ADD:
+		if (hi && is64) {
+			if (is_imm8(val))
+				EMIT3(0x83, add_1reg(0xD0, dreg), val);
+			else
+				EMIT2(0x11, add_2reg(0xC0, dreg, sreg));
+		} else {
+			if (is_imm8(val))
+				EMIT3(0x83, add_1reg(0xC0, dreg), val);
+			else
+				EMIT2(0x01, add_2reg(0xC0, dreg, sreg));
+		}
+		break;
+	/* dst = dst - val */
+	case BPF_SUB:
+		if (hi && is64) {
+			if (is_imm8(val))
+				EMIT3(0x83, add_1reg(0xD8, dreg), val);
+			else
+				EMIT2(0x19, add_2reg(0xC0, dreg, sreg));
+		} else {
+			if (is_imm8(val))
+				EMIT3(0x83, add_1reg(0xE8, dreg), val);
+			else
+				EMIT2(0x29, add_2reg(0xC0, dreg, sreg));
+		}
+		break;
+	/* dst = dst | val */
+	case BPF_OR:
+		if (is_imm8(val))
+			EMIT3(0x83, add_1reg(0xC8, dreg), val);
+		else
+			EMIT2(0x09, add_2reg(0xC0, dreg, sreg));
+		break;
+	/* dst = dst & val */
+	case BPF_AND:
+		if (is_imm8(val))
+			EMIT3(0x83, add_1reg(0xE0, dreg), val);
+		else
+			EMIT2(0x21, add_2reg(0xC0, dreg, sreg));
+		break;
+	/* dst = dst ^ val */
+	case BPF_XOR:
+		if (is_imm8(val))
+			EMIT3(0x83, add_1reg(0xF0, dreg), val);
+		else
+			EMIT2(0x31, add_2reg(0xC0, dreg, sreg));
+		break;
+	case BPF_NEG:
+		EMIT2(0xF7, add_1reg(0xD8, dreg));
+		break;
+	}
+
+	if (dstk)
+		/* mov dword ptr [ebp+off],dreg */
+		EMIT3(0x89, add_2reg(0x40, IA32_EBP, dreg),
+		      STACK_VAR(dst));
+	*pprog = prog;
+}
+
+/* ALU operation (64 bit) */
+static inline void emit_ia32_alu_i64(const bool is64, const u8 op,
+				     const u8 dst[], const u32 val,
+				     bool dstk, u8 **pprog)
+{
+	u8 *prog = *pprog;
+	u32 hi = 0;
+
+	if (is64 && (val & (1<<31)))
+		hi = (u32)~0;
+
+	emit_ia32_alu_i(is64, false, op, dst_lo, val, dstk, &prog);
+	if (is64)
+		emit_ia32_alu_i(is64, true, op, dst_hi, hi, dstk, &prog);
+	else
+		emit_ia32_mov_i(dst_hi, 0, dstk, &prog);
+
+	*pprog = prog;
+}
+
+/* dst = ~dst (64 bit) */
+static inline void emit_ia32_neg64(const u8 dst[], bool dstk, u8 **pprog)
+{
+	u8 *prog = *pprog;
+	int cnt = 0;
+	u8 dreg_lo = dstk ? IA32_EAX : dst_lo;
+	u8 dreg_hi = dstk ? IA32_EDX : dst_hi;
+
+	if (dstk) {
+		EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EAX),
+		      STACK_VAR(dst_lo));
+		EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EDX),
+		      STACK_VAR(dst_hi));
+	}
+
+	/* xor ecx,ecx */
+	EMIT2(0x31, add_2reg(0xC0, IA32_ECX, IA32_ECX));
+	/* sub dreg_lo,ecx */
+	EMIT2(0x2B, add_2reg(0xC0, dreg_lo, IA32_ECX));
+	/* mov dreg_lo,ecx */
+	EMIT2(0x89, add_2reg(0xC0, dreg_lo, IA32_ECX));
+
+	/* xor ecx,ecx */
+	EMIT2(0x31, add_2reg(0xC0, IA32_ECX, IA32_ECX));
+	/* sbb dreg_hi,ecx */
+	EMIT2(0x19, add_2reg(0xC0, dreg_hi, IA32_ECX));
+	/* mov dreg_hi,ecx */
+	EMIT2(0x89, add_2reg(0xC0, dreg_hi, IA32_ECX));
+
+	if (dstk) {
+		/* mov dword ptr [ebp+off],dreg_lo */
+		EMIT3(0x89, add_2reg(0x40, IA32_EBP, dreg_lo),
+		      STACK_VAR(dst_lo));
+		/* mov dword ptr [ebp+off],dreg_hi */
+		EMIT3(0x89, add_2reg(0x40, IA32_EBP, dreg_hi),
+		      STACK_VAR(dst_hi));
+	}
+	*pprog = prog;
+}
+
+/* dst = dst << src */
+static inline void emit_ia32_lsh_r64(const u8 dst[], const u8 src[],
+				     bool dstk, bool sstk, u8 **pprog)
+{
+	u8 *prog = *pprog;
+	int cnt = 0;
+	static int jmp_label1 = -1;
+	static int jmp_label2 = -1;
+	static int jmp_label3 = -1;
+	u8 dreg_lo = dstk ? IA32_EAX : dst_lo;
+	u8 dreg_hi = dstk ? IA32_EDX : dst_hi;
+
+	if (dstk) {
+		EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EAX),
+		      STACK_VAR(dst_lo));
+		EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EDX),
+		      STACK_VAR(dst_hi));
+	}
+
+	if (sstk)
+		/* mov ecx,dword ptr [ebp+off] */
+		EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_ECX),
+		      STACK_VAR(src_lo));
+	else
+		/* mov ecx,src_lo */
+		EMIT2(0x8B, add_2reg(0xC0, src_lo, IA32_ECX));
+
+	/* cmp ecx,32 */
+	EMIT3(0x83, add_1reg(0xF8, IA32_ECX), 32);
+	/* Jumps when >= 32 */
+	if (is_imm8(jmp_label(jmp_label1, 2)))
+		EMIT2(IA32_JAE, jmp_label(jmp_label1, 2));
+	else
+		EMIT2_off32(0x0F, IA32_JAE + 0x10, jmp_label(jmp_label1, 6));
+
+	/* < 32 */
+	/* shl dreg_hi,cl */
+	EMIT2(0xD3, add_1reg(0xE0, dreg_hi));
+	/* mov ebx,dreg_lo */
+	EMIT2(0x8B, add_2reg(0xC0, dreg_lo, IA32_EBX));
+	/* shl dreg_lo,cl */
+	EMIT2(0xD3, add_1reg(0xE0, dreg_lo));
+
+	/* IA32_ECX = -IA32_ECX + 32 */
+	/* neg ecx */
+	EMIT2(0xF7, add_1reg(0xD8, IA32_ECX));
+	/* add ecx,32 */
+	EMIT3(0x83, add_1reg(0xC0, IA32_ECX), 32);
+
+	/* shr ebx,cl */
+	EMIT2(0xD3, add_1reg(0xE8, IA32_EBX));
+	/* or dreg_hi,ebx */
+	EMIT2(0x09, add_2reg(0xC0, dreg_hi, IA32_EBX));
+
+	/* goto out; */
+	if (is_imm8(jmp_label(jmp_label3, 2)))
+		EMIT2(0xEB, jmp_label(jmp_label3, 2));
+	else
+		EMIT1_off32(0xE9, jmp_label(jmp_label3, 5));
+
+	/* >= 32 */
+	if (jmp_label1 == -1)
+		jmp_label1 = cnt;
+
+	/* cmp ecx,64 */
+	EMIT3(0x83, add_1reg(0xF8, IA32_ECX), 64);
+	/* Jumps when >= 64 */
+	if (is_imm8(jmp_label(jmp_label2, 2)))
+		EMIT2(IA32_JAE, jmp_label(jmp_label2, 2));
+	else
+		EMIT2_off32(0x0F, IA32_JAE + 0x10, jmp_label(jmp_label2, 6));
+
+	/* >= 32 && < 64 */
+	/* sub ecx,32 */
+	EMIT3(0x83, add_1reg(0xE8, IA32_ECX), 32);
+	/* shl dreg_lo,cl */
+	EMIT2(0xD3, add_1reg(0xE0, dreg_lo));
+	/* mov dreg_hi,dreg_lo */
+	EMIT2(0x89, add_2reg(0xC0, dreg_hi, dreg_lo));
+
+	/* xor dreg_lo,dreg_lo */
+	EMIT2(0x33, add_2reg(0xC0, dreg_lo, dreg_lo));
+
+	/* goto out; */
+	if (is_imm8(jmp_label(jmp_label3, 2)))
+		EMIT2(0xEB, jmp_label(jmp_label3, 2));
+	else
+		EMIT1_off32(0xE9, jmp_label(jmp_label3, 5));
+
+	/* >= 64 */
+	if (jmp_label2 == -1)
+		jmp_label2 = cnt;
+	/* xor dreg_lo,dreg_lo */
+	EMIT2(0x33, add_2reg(0xC0, dreg_lo, dreg_lo));
+	/* xor dreg_hi,dreg_hi */
+	EMIT2(0x33, add_2reg(0xC0, dreg_hi, dreg_hi));
+
+	if (jmp_label3 == -1)
+		jmp_label3 = cnt;
+
+	if (dstk) {
+		/* mov dword ptr [ebp+off],dreg_lo */
+		EMIT3(0x89, add_2reg(0x40, IA32_EBP, dreg_lo),
+		      STACK_VAR(dst_lo));
+		/* mov dword ptr [ebp+off],dreg_hi */
+		EMIT3(0x89, add_2reg(0x40, IA32_EBP, dreg_hi),
+		      STACK_VAR(dst_hi));
+	}
+	/* out: */
+	*pprog = prog;
+}
+
+/* dst = dst >> src (signed)*/
+static inline void emit_ia32_arsh_r64(const u8 dst[], const u8 src[],
+				      bool dstk, bool sstk, u8 **pprog)
+{
+	u8 *prog = *pprog;
+	int cnt = 0;
+	static int jmp_label1 = -1;
+	static int jmp_label2 = -1;
+	static int jmp_label3 = -1;
+	u8 dreg_lo = dstk ? IA32_EAX : dst_lo;
+	u8 dreg_hi = dstk ? IA32_EDX : dst_hi;
+
+	if (dstk) {
+		EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EAX),
+		      STACK_VAR(dst_lo));
+		EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EDX),
+		      STACK_VAR(dst_hi));
+	}
+
+	if (sstk)
+		/* mov ecx,dword ptr [ebp+off] */
+		EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_ECX),
+		      STACK_VAR(src_lo));
+	else
+		/* mov ecx,src_lo */
+		EMIT2(0x8B, add_2reg(0xC0, src_lo, IA32_ECX));
+
+	/* cmp ecx,32 */
+	EMIT3(0x83, add_1reg(0xF8, IA32_ECX), 32);
+	/* Jumps when >= 32 */
+	if (is_imm8(jmp_label(jmp_label1, 2)))
+		EMIT2(IA32_JAE, jmp_label(jmp_label1, 2));
+	else
+		EMIT2_off32(0x0F, IA32_JAE + 0x10, jmp_label(jmp_label1, 6));
+
+	/* < 32 */
+	/* lshr dreg_lo,cl */
+	EMIT2(0xD3, add_1reg(0xE8, dreg_lo));
+	/* mov ebx,dreg_hi */
+	EMIT2(0x8B, add_2reg(0xC0, dreg_hi, IA32_EBX));
+	/* ashr dreg_hi,cl */
+	EMIT2(0xD3, add_1reg(0xF8, dreg_hi));
+
+	/* IA32_ECX = -IA32_ECX + 32 */
+	/* neg ecx */
+	EMIT2(0xF7, add_1reg(0xD8, IA32_ECX));
+	/* add ecx,32 */
+	EMIT3(0x83, add_1reg(0xC0, IA32_ECX), 32);
+
+	/* shl ebx,cl */
+	EMIT2(0xD3, add_1reg(0xE0, IA32_EBX));
+	/* or dreg_lo,ebx */
+	EMIT2(0x09, add_2reg(0xC0, dreg_lo, IA32_EBX));
+
+	/* goto out; */
+	if (is_imm8(jmp_label(jmp_label3, 2)))
+		EMIT2(0xEB, jmp_label(jmp_label3, 2));
+	else
+		EMIT1_off32(0xE9, jmp_label(jmp_label3, 5));
+
+	/* >= 32 */
+	if (jmp_label1 == -1)
+		jmp_label1 = cnt;
+
+	/* cmp ecx,64 */
+	EMIT3(0x83, add_1reg(0xF8, IA32_ECX), 64);
+	/* Jumps when >= 64 */
+	if (is_imm8(jmp_label(jmp_label2, 2)))
+		EMIT2(IA32_JAE, jmp_label(jmp_label2, 2));
+	else
+		EMIT2_off32(0x0F, IA32_JAE + 0x10, jmp_label(jmp_label2, 6));
+
+	/* >= 32 && < 64 */
+	/* sub ecx,32 */
+	EMIT3(0x83, add_1reg(0xE8, IA32_ECX), 32);
+	/* ashr dreg_hi,cl */
+	EMIT2(0xD3, add_1reg(0xF8, dreg_hi));
+	/* mov dreg_lo,dreg_hi */
+	EMIT2(0x89, add_2reg(0xC0, dreg_lo, dreg_hi));
+
+	/* ashr dreg_hi,imm8 */
+	EMIT3(0xC1, add_1reg(0xF8, dreg_hi), 31);
+
+	/* goto out; */
+	if (is_imm8(jmp_label(jmp_label3, 2)))
+		EMIT2(0xEB, jmp_label(jmp_label3, 2));
+	else
+		EMIT1_off32(0xE9, jmp_label(jmp_label3, 5));
+
+	/* >= 64 */
+	if (jmp_label2 == -1)
+		jmp_label2 = cnt;
+	/* ashr dreg_hi,imm8 */
+	EMIT3(0xC1, add_1reg(0xF8, dreg_hi), 31);
+	/* mov dreg_lo,dreg_hi */
+	EMIT2(0x89, add_2reg(0xC0, dreg_lo, dreg_hi));
+
+	if (jmp_label3 == -1)
+		jmp_label3 = cnt;
+
+	if (dstk) {
+		/* mov dword ptr [ebp+off],dreg_lo */
+		EMIT3(0x89, add_2reg(0x40, IA32_EBP, dreg_lo),
+		      STACK_VAR(dst_lo));
+		/* mov dword ptr [ebp+off],dreg_hi */
+		EMIT3(0x89, add_2reg(0x40, IA32_EBP, dreg_hi),
+		      STACK_VAR(dst_hi));
+	}
+	/* out: */
+	*pprog = prog;
+}
+
+/* dst = dst >> src */
+static inline void emit_ia32_rsh_r64(const u8 dst[], const u8 src[], bool dstk,
+				     bool sstk, u8 **pprog)
+{
+	u8 *prog = *pprog;
+	int cnt = 0;
+	static int jmp_label1 = -1;
+	static int jmp_label2 = -1;
+	static int jmp_label3 = -1;
+	u8 dreg_lo = dstk ? IA32_EAX : dst_lo;
+	u8 dreg_hi = dstk ? IA32_EDX : dst_hi;
+
+	if (dstk) {
+		EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EAX),
+		      STACK_VAR(dst_lo));
+		EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EDX),
+		      STACK_VAR(dst_hi));
+	}
+
+	if (sstk)
+		/* mov ecx,dword ptr [ebp+off] */
+		EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_ECX),
+		      STACK_VAR(src_lo));
+	else
+		/* mov ecx,src_lo */
+		EMIT2(0x8B, add_2reg(0xC0, src_lo, IA32_ECX));
+
+	/* cmp ecx,32 */
+	EMIT3(0x83, add_1reg(0xF8, IA32_ECX), 32);
+	/* Jumps when >= 32 */
+	if (is_imm8(jmp_label(jmp_label1, 2)))
+		EMIT2(IA32_JAE, jmp_label(jmp_label1, 2));
+	else
+		EMIT2_off32(0x0F, IA32_JAE + 0x10, jmp_label(jmp_label1, 6));
+
+	/* < 32 */
+	/* lshr dreg_lo,cl */
+	EMIT2(0xD3, add_1reg(0xE8, dreg_lo));
+	/* mov ebx,dreg_hi */
+	EMIT2(0x8B, add_2reg(0xC0, dreg_hi, IA32_EBX));
+	/* shr dreg_hi,cl */
+	EMIT2(0xD3, add_1reg(0xE8, dreg_hi));
+
+	/* IA32_ECX = -IA32_ECX + 32 */
+	/* neg ecx */
+	EMIT2(0xF7, add_1reg(0xD8, IA32_ECX));
+	/* add ecx,32 */
+	EMIT3(0x83, add_1reg(0xC0, IA32_ECX), 32);
+
+	/* shl ebx,cl */
+	EMIT2(0xD3, add_1reg(0xE0, IA32_EBX));
+	/* or dreg_lo,ebx */
+	EMIT2(0x09, add_2reg(0xC0, dreg_lo, IA32_EBX));
+
+	/* goto out; */
+	if (is_imm8(jmp_label(jmp_label3, 2)))
+		EMIT2(0xEB, jmp_label(jmp_label3, 2));
+	else
+		EMIT1_off32(0xE9, jmp_label(jmp_label3, 5));
+
+	/* >= 32 */
+	if (jmp_label1 == -1)
+		jmp_label1 = cnt;
+	/* cmp ecx,64 */
+	EMIT3(0x83, add_1reg(0xF8, IA32_ECX), 64);
+	/* Jumps when >= 64 */
+	if (is_imm8(jmp_label(jmp_label2, 2)))
+		EMIT2(IA32_JAE, jmp_label(jmp_label2, 2));
+	else
+		EMIT2_off32(0x0F, IA32_JAE + 0x10, jmp_label(jmp_label2, 6));
+
+	/* >= 32 && < 64 */
+	/* sub ecx,32 */
+	EMIT3(0x83, add_1reg(0xE8, IA32_ECX), 32);
+	/* shr dreg_hi,cl */
+	EMIT2(0xD3, add_1reg(0xE8, dreg_hi));
+	/* mov dreg_lo,dreg_hi */
+	EMIT2(0x89, add_2reg(0xC0, dreg_lo, dreg_hi));
+	/* xor dreg_hi,dreg_hi */
+	EMIT2(0x33, add_2reg(0xC0, dreg_hi, dreg_hi));
+
+	/* goto out; */
+	if (is_imm8(jmp_label(jmp_label3, 2)))
+		EMIT2(0xEB, jmp_label(jmp_label3, 2));
+	else
+		EMIT1_off32(0xE9, jmp_label(jmp_label3, 5));
+
+	/* >= 64 */
+	if (jmp_label2 == -1)
+		jmp_label2 = cnt;
+	/* xor dreg_lo,dreg_lo */
+	EMIT2(0x33, add_2reg(0xC0, dreg_lo, dreg_lo));
+	/* xor dreg_hi,dreg_hi */
+	EMIT2(0x33, add_2reg(0xC0, dreg_hi, dreg_hi));
+
+	if (jmp_label3 == -1)
+		jmp_label3 = cnt;
+
+	if (dstk) {
+		/* mov dword ptr [ebp+off],dreg_lo */
+		EMIT3(0x89, add_2reg(0x40, IA32_EBP, dreg_lo),
+		      STACK_VAR(dst_lo));
+		/* mov dword ptr [ebp+off],dreg_hi */
+		EMIT3(0x89, add_2reg(0x40, IA32_EBP, dreg_hi),
+		      STACK_VAR(dst_hi));
+	}
+	/* out: */
+	*pprog = prog;
+}
+
+/* dst = dst << val */
+static inline void emit_ia32_lsh_i64(const u8 dst[], const u32 val,
+				     bool dstk, u8 **pprog)
+{
+	u8 *prog = *pprog;
+	int cnt = 0;
+	u8 dreg_lo = dstk ? IA32_EAX : dst_lo;
+	u8 dreg_hi = dstk ? IA32_EDX : dst_hi;
+
+	if (dstk) {
+		EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EAX),
+		      STACK_VAR(dst_lo));
+		EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EDX),
+		      STACK_VAR(dst_hi));
+	}
+	/* Do LSH operation */
+	if (val < 32) {
+		/* shl dreg_hi,imm8 */
+		EMIT3(0xC1, add_1reg(0xE0, dreg_hi), val);
+		/* mov ebx,dreg_lo */
+		EMIT2(0x8B, add_2reg(0xC0, dreg_lo, IA32_EBX));
+		/* shl dreg_lo,imm8 */
+		EMIT3(0xC1, add_1reg(0xE0, dreg_lo), val);
+
+		/* IA32_ECX = 32 - val */
+		/* mov ecx,val */
+		EMIT2(0xB1, val);
+		/* movzx ecx,ecx */
+		EMIT3(0x0F, 0xB6, add_2reg(0xC0, IA32_ECX, IA32_ECX));
+		/* neg ecx */
+		EMIT2(0xF7, add_1reg(0xD8, IA32_ECX));
+		/* add ecx,32 */
+		EMIT3(0x83, add_1reg(0xC0, IA32_ECX), 32);
+
+		/* shr ebx,cl */
+		EMIT2(0xD3, add_1reg(0xE8, IA32_EBX));
+		/* or dreg_hi,ebx */
+		EMIT2(0x09, add_2reg(0xC0, dreg_hi, IA32_EBX));
+	} else if (val >= 32 && val < 64) {
+		u32 value = val - 32;
+
+		/* shl dreg_lo,imm8 */
+		EMIT3(0xC1, add_1reg(0xE0, dreg_lo), value);
+		/* mov dreg_hi,dreg_lo */
+		EMIT2(0x89, add_2reg(0xC0, dreg_hi, dreg_lo));
+		/* xor dreg_lo,dreg_lo */
+		EMIT2(0x33, add_2reg(0xC0, dreg_lo, dreg_lo));
+	} else {
+		/* xor dreg_lo,dreg_lo */
+		EMIT2(0x33, add_2reg(0xC0, dreg_lo, dreg_lo));
+		/* xor dreg_hi,dreg_hi */
+		EMIT2(0x33, add_2reg(0xC0, dreg_hi, dreg_hi));
+	}
+
+	if (dstk) {
+		/* mov dword ptr [ebp+off],dreg_lo */
+		EMIT3(0x89, add_2reg(0x40, IA32_EBP, dreg_lo),
+		      STACK_VAR(dst_lo));
+		/* mov dword ptr [ebp+off],dreg_hi */
+		EMIT3(0x89, add_2reg(0x40, IA32_EBP, dreg_hi),
+		      STACK_VAR(dst_hi));
+	}
+	*pprog = prog;
+}
+
+/* dst = dst >> val */
+static inline void emit_ia32_rsh_i64(const u8 dst[], const u32 val,
+				     bool dstk, u8 **pprog)
+{
+	u8 *prog = *pprog;
+	int cnt = 0;
+	u8 dreg_lo = dstk ? IA32_EAX : dst_lo;
+	u8 dreg_hi = dstk ? IA32_EDX : dst_hi;
+
+	if (dstk) {
+		EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EAX),
+		      STACK_VAR(dst_lo));
+		EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EDX),
+		      STACK_VAR(dst_hi));
+	}
+
+	/* Do RSH operation */
+	if (val < 32) {
+		/* shr dreg_lo,imm8 */
+		EMIT3(0xC1, add_1reg(0xE8, dreg_lo), val);
+		/* mov ebx,dreg_hi */
+		EMIT2(0x8B, add_2reg(0xC0, dreg_hi, IA32_EBX));
+		/* shr dreg_hi,imm8 */
+		EMIT3(0xC1, add_1reg(0xE8, dreg_hi), val);
+
+		/* IA32_ECX = 32 - val */
+		/* mov ecx,val */
+		EMIT2(0xB1, val);
+		/* movzx ecx,ecx */
+		EMIT3(0x0F, 0xB6, add_2reg(0xC0, IA32_ECX, IA32_ECX));
+		/* neg ecx */
+		EMIT2(0xF7, add_1reg(0xD8, IA32_ECX));
+		/* add ecx,32 */
+		EMIT3(0x83, add_1reg(0xC0, IA32_ECX), 32);
+
+		/* shl ebx,cl */
+		EMIT2(0xD3, add_1reg(0xE0, IA32_EBX));
+		/* or dreg_lo,ebx */
+		EMIT2(0x09, add_2reg(0xC0, dreg_lo, IA32_EBX));
+	} else if (val >= 32 && val < 64) {
+		u32 value = val - 32;
+
+		/* shr dreg_hi,imm8 */
+		EMIT3(0xC1, add_1reg(0xE8, dreg_hi), value);
+		/* mov dreg_lo,dreg_hi */
+		EMIT2(0x89, add_2reg(0xC0, dreg_lo, dreg_hi));
+		/* xor dreg_hi,dreg_hi */
+		EMIT2(0x33, add_2reg(0xC0, dreg_hi, dreg_hi));
+	} else {
+		/* xor dreg_lo,dreg_lo */
+		EMIT2(0x33, add_2reg(0xC0, dreg_lo, dreg_lo));
+		/* xor dreg_hi,dreg_hi */
+		EMIT2(0x33, add_2reg(0xC0, dreg_hi, dreg_hi));
+	}
+
+	if (dstk) {
+		/* mov dword ptr [ebp+off],dreg_lo */
+		EMIT3(0x89, add_2reg(0x40, IA32_EBP, dreg_lo),
+		      STACK_VAR(dst_lo));
+		/* mov dword ptr [ebp+off],dreg_hi */
+		EMIT3(0x89, add_2reg(0x40, IA32_EBP, dreg_hi),
+		      STACK_VAR(dst_hi));
+	}
+	*pprog = prog;
+}
+
+/* dst = dst >> val (signed) */
+static inline void emit_ia32_arsh_i64(const u8 dst[], const u32 val,
+				      bool dstk, u8 **pprog)
+{
+	u8 *prog = *pprog;
+	int cnt = 0;
+	u8 dreg_lo = dstk ? IA32_EAX : dst_lo;
+	u8 dreg_hi = dstk ? IA32_EDX : dst_hi;
+
+	if (dstk) {
+		EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EAX),
+		      STACK_VAR(dst_lo));
+		EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EDX),
+		      STACK_VAR(dst_hi));
+	}
+	/* Do RSH operation */
+	if (val < 32) {
+		/* shr dreg_lo,imm8 */
+		EMIT3(0xC1, add_1reg(0xE8, dreg_lo), val);
+		/* mov ebx,dreg_hi */
+		EMIT2(0x8B, add_2reg(0xC0, dreg_hi, IA32_EBX));
+		/* ashr dreg_hi,imm8 */
+		EMIT3(0xC1, add_1reg(0xF8, dreg_hi), val);
+
+		/* IA32_ECX = 32 - val */
+		/* mov ecx,val */
+		EMIT2(0xB1, val);
+		/* movzx ecx,ecx */
+		EMIT3(0x0F, 0xB6, add_2reg(0xC0, IA32_ECX, IA32_ECX));
+		/* neg ecx */
+		EMIT2(0xF7, add_1reg(0xD8, IA32_ECX));
+		/* add ecx,32 */
+		EMIT3(0x83, add_1reg(0xC0, IA32_ECX), 32);
+
+		/* shl ebx,cl */
+		EMIT2(0xD3, add_1reg(0xE0, IA32_EBX));
+		/* or dreg_lo,ebx */
+		EMIT2(0x09, add_2reg(0xC0, dreg_lo, IA32_EBX));
+	} else if (val >= 32 && val < 64) {
+		u32 value = val - 32;
+
+		/* ashr dreg_hi,imm8 */
+		EMIT3(0xC1, add_1reg(0xF8, dreg_hi), value);
+		/* mov dreg_lo,dreg_hi */
+		EMIT2(0x89, add_2reg(0xC0, dreg_lo, dreg_hi));
+
+		/* ashr dreg_hi,imm8 */
+		EMIT3(0xC1, add_1reg(0xF8, dreg_hi), 31);
+	} else {
+		/* ashr dreg_hi,imm8 */
+		EMIT3(0xC1, add_1reg(0xF8, dreg_hi), 31);
+		/* mov dreg_lo,dreg_hi */
+		EMIT2(0x89, add_2reg(0xC0, dreg_lo, dreg_hi));
+	}
+
+	if (dstk) {
+		/* mov dword ptr [ebp+off],dreg_lo */
+		EMIT3(0x89, add_2reg(0x40, IA32_EBP, dreg_lo),
+		      STACK_VAR(dst_lo));
+		/* mov dword ptr [ebp+off],dreg_hi */
+		EMIT3(0x89, add_2reg(0x40, IA32_EBP, dreg_hi),
+		      STACK_VAR(dst_hi));
+	}
+	*pprog = prog;
+}
+
+static inline void emit_ia32_mul_r64(const u8 dst[], const u8 src[], bool dstk,
+				     bool sstk, u8 **pprog)
+{
+	u8 *prog = *pprog;
+	int cnt = 0;
+
+	if (dstk)
+		/* mov eax,dword ptr [ebp+off] */
+		EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EAX),
+		      STACK_VAR(dst_hi));
+	else
+		/* mov eax,dst_hi */
+		EMIT2(0x8B, add_2reg(0xC0, dst_hi, IA32_EAX));
+
+	if (sstk)
+		/* mul dword ptr [ebp+off] */
+		EMIT3(0xF7, add_1reg(0x60, IA32_EBP), STACK_VAR(src_lo));
+	else
+		/* mul src_lo */
+		EMIT2(0xF7, add_1reg(0xE0, src_lo));
+
+	/* mov ecx,eax */
+	EMIT2(0x89, add_2reg(0xC0, IA32_ECX, IA32_EAX));
+
+	if (dstk)
+		/* mov eax,dword ptr [ebp+off] */
+		EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EAX),
+		      STACK_VAR(dst_lo));
+	else
+		/* mov eax,dst_lo */
+		EMIT2(0x8B, add_2reg(0xC0, dst_lo, IA32_EAX));
+
+	if (sstk)
+		/* mul dword ptr [ebp+off] */
+		EMIT3(0xF7, add_1reg(0x60, IA32_EBP), STACK_VAR(src_hi));
+	else
+		/* mul src_hi */
+		EMIT2(0xF7, add_1reg(0xE0, src_hi));
+
+	/* add eax,eax */
+	EMIT2(0x01, add_2reg(0xC0, IA32_ECX, IA32_EAX));
+
+	if (dstk)
+		/* mov eax,dword ptr [ebp+off] */
+		EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EAX),
+		      STACK_VAR(dst_lo));
+	else
+		/* mov eax,dst_lo */
+		EMIT2(0x8B, add_2reg(0xC0, dst_lo, IA32_EAX));
+
+	if (sstk)
+		/* mul dword ptr [ebp+off] */
+		EMIT3(0xF7, add_1reg(0x60, IA32_EBP), STACK_VAR(src_lo));
+	else
+		/* mul src_lo */
+		EMIT2(0xF7, add_1reg(0xE0, src_lo));
+
+	/* add ecx,edx */
+	EMIT2(0x01, add_2reg(0xC0, IA32_ECX, IA32_EDX));
+
+	if (dstk) {
+		/* mov dword ptr [ebp+off],eax */
+		EMIT3(0x89, add_2reg(0x40, IA32_EBP, IA32_EAX),
+		      STACK_VAR(dst_lo));
+		/* mov dword ptr [ebp+off],ecx */
+		EMIT3(0x89, add_2reg(0x40, IA32_EBP, IA32_ECX),
+		      STACK_VAR(dst_hi));
+	} else {
+		/* mov dst_lo,eax */
+		EMIT2(0x89, add_2reg(0xC0, dst_lo, IA32_EAX));
+		/* mov dst_hi,ecx */
+		EMIT2(0x89, add_2reg(0xC0, dst_hi, IA32_ECX));
+	}
+
+	*pprog = prog;
+}
+
+static inline void emit_ia32_mul_i64(const u8 dst[], const u32 val,
+				     bool dstk, u8 **pprog)
+{
+	u8 *prog = *pprog;
+	int cnt = 0;
+	u32 hi;
+
+	hi = val & (1<<31) ? (u32)~0 : 0;
+	/* movl eax,imm32 */
+	EMIT2_off32(0xC7, add_1reg(0xC0, IA32_EAX), val);
+	if (dstk)
+		/* mul dword ptr [ebp+off] */
+		EMIT3(0xF7, add_1reg(0x60, IA32_EBP), STACK_VAR(dst_hi));
+	else
+		/* mul dst_hi */
+		EMIT2(0xF7, add_1reg(0xE0, dst_hi));
+
+	/* mov ecx,eax */
+	EMIT2(0x89, add_2reg(0xC0, IA32_ECX, IA32_EAX));
+
+	/* movl eax,imm32 */
+	EMIT2_off32(0xC7, add_1reg(0xC0, IA32_EAX), hi);
+	if (dstk)
+		/* mul dword ptr [ebp+off] */
+		EMIT3(0xF7, add_1reg(0x60, IA32_EBP), STACK_VAR(dst_lo));
+	else
+		/* mul dst_lo */
+		EMIT2(0xF7, add_1reg(0xE0, dst_lo));
+	/* add ecx,eax */
+	EMIT2(0x01, add_2reg(0xC0, IA32_ECX, IA32_EAX));
+
+	/* movl eax,imm32 */
+	EMIT2_off32(0xC7, add_1reg(0xC0, IA32_EAX), val);
+	if (dstk)
+		/* mul dword ptr [ebp+off] */
+		EMIT3(0xF7, add_1reg(0x60, IA32_EBP), STACK_VAR(dst_lo));
+	else
+		/* mul dst_lo */
+		EMIT2(0xF7, add_1reg(0xE0, dst_lo));
+
+	/* add ecx,edx */
+	EMIT2(0x01, add_2reg(0xC0, IA32_ECX, IA32_EDX));
+
+	if (dstk) {
+		/* mov dword ptr [ebp+off],eax */
+		EMIT3(0x89, add_2reg(0x40, IA32_EBP, IA32_EAX),
+		      STACK_VAR(dst_lo));
+		/* mov dword ptr [ebp+off],ecx */
+		EMIT3(0x89, add_2reg(0x40, IA32_EBP, IA32_ECX),
+		      STACK_VAR(dst_hi));
+	} else {
+		/* mov dword ptr [ebp+off],eax */
+		EMIT2(0x89, add_2reg(0xC0, dst_lo, IA32_EAX));
+		/* mov dword ptr [ebp+off],ecx */
+		EMIT2(0x89, add_2reg(0xC0, dst_hi, IA32_ECX));
+	}
+
+	*pprog = prog;
+}
+
+static int bpf_size_to_x86_bytes(int bpf_size)
+{
+	if (bpf_size == BPF_W)
+		return 4;
+	else if (bpf_size == BPF_H)
+		return 2;
+	else if (bpf_size == BPF_B)
+		return 1;
+	else if (bpf_size == BPF_DW)
+		return 4; /* imm32 */
+	else
+		return 0;
+}
+
+struct jit_context {
+	int cleanup_addr; /* Epilogue code offset */
+};
+
+/* Maximum number of bytes emitted while JITing one eBPF insn */
+#define BPF_MAX_INSN_SIZE	128
+#define BPF_INSN_SAFETY		64
+
+#define PROLOGUE_SIZE 35
+
+/*
+ * Emit prologue code for BPF program and check it's size.
+ * bpf_tail_call helper will skip it while jumping into another program.
+ */
+static void emit_prologue(u8 **pprog, u32 stack_depth)
+{
+	u8 *prog = *pprog;
+	int cnt = 0;
+	const u8 *r1 = bpf2ia32[BPF_REG_1];
+	const u8 fplo = bpf2ia32[BPF_REG_FP][0];
+	const u8 fphi = bpf2ia32[BPF_REG_FP][1];
+	const u8 *tcc = bpf2ia32[TCALL_CNT];
+
+	/* push ebp */
+	EMIT1(0x55);
+	/* mov ebp,esp */
+	EMIT2(0x89, 0xE5);
+	/* push edi */
+	EMIT1(0x57);
+	/* push esi */
+	EMIT1(0x56);
+	/* push ebx */
+	EMIT1(0x53);
+
+	/* sub esp,STACK_SIZE */
+	EMIT2_off32(0x81, 0xEC, STACK_SIZE);
+	/* sub ebp,SCRATCH_SIZE+4+12*/
+	EMIT3(0x83, add_1reg(0xE8, IA32_EBP), SCRATCH_SIZE + 16);
+	/* xor ebx,ebx */
+	EMIT2(0x31, add_2reg(0xC0, IA32_EBX, IA32_EBX));
+
+	/* Set up BPF prog stack base register */
+	EMIT3(0x89, add_2reg(0x40, IA32_EBP, IA32_EBP), STACK_VAR(fplo));
+	EMIT3(0x89, add_2reg(0x40, IA32_EBP, IA32_EBX), STACK_VAR(fphi));
+
+	/* Move BPF_CTX (EAX) to BPF_REG_R1 */
+	/* mov dword ptr [ebp+off],eax */
+	EMIT3(0x89, add_2reg(0x40, IA32_EBP, IA32_EAX), STACK_VAR(r1[0]));
+	EMIT3(0x89, add_2reg(0x40, IA32_EBP, IA32_EBX), STACK_VAR(r1[1]));
+
+	/* Initialize Tail Count */
+	EMIT3(0x89, add_2reg(0x40, IA32_EBP, IA32_EBX), STACK_VAR(tcc[0]));
+	EMIT3(0x89, add_2reg(0x40, IA32_EBP, IA32_EBX), STACK_VAR(tcc[1]));
+
+	BUILD_BUG_ON(cnt != PROLOGUE_SIZE);
+	*pprog = prog;
+}
+
+/* Emit epilogue code for BPF program */
+static void emit_epilogue(u8 **pprog, u32 stack_depth)
+{
+	u8 *prog = *pprog;
+	const u8 *r0 = bpf2ia32[BPF_REG_0];
+	int cnt = 0;
+
+	/* mov eax,dword ptr [ebp+off]*/
+	EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EAX), STACK_VAR(r0[0]));
+	/* mov edx,dword ptr [ebp+off]*/
+	EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EDX), STACK_VAR(r0[1]));
+
+	/* add ebp,SCRATCH_SIZE+4+12*/
+	EMIT3(0x83, add_1reg(0xC0, IA32_EBP), SCRATCH_SIZE + 16);
+
+	/* mov ebx,dword ptr [ebp-12]*/
+	EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EBX), -12);
+	/* mov esi,dword ptr [ebp-8]*/
+	EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_ESI), -8);
+	/* mov edi,dword ptr [ebp-4]*/
+	EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EDI), -4);
+
+	EMIT1(0xC9); /* leave */
+	EMIT1(0xC3); /* ret */
+	*pprog = prog;
+}
+
+/*
+ * Generate the following code:
+ * ... bpf_tail_call(void *ctx, struct bpf_array *array, u64 index) ...
+ *   if (index >= array->map.max_entries)
+ *     goto out;
+ *   if (++tail_call_cnt > MAX_TAIL_CALL_CNT)
+ *     goto out;
+ *   prog = array->ptrs[index];
+ *   if (prog == NULL)
+ *     goto out;
+ *   goto *(prog->bpf_func + prologue_size);
+ * out:
+ */
+static void emit_bpf_tail_call(u8 **pprog)
+{
+	u8 *prog = *pprog;
+	int cnt = 0;
+	const u8 *r1 = bpf2ia32[BPF_REG_1];
+	const u8 *r2 = bpf2ia32[BPF_REG_2];
+	const u8 *r3 = bpf2ia32[BPF_REG_3];
+	const u8 *tcc = bpf2ia32[TCALL_CNT];
+	u32 lo, hi;
+	static int jmp_label1 = -1;
+
+	/*
+	 * if (index >= array->map.max_entries)
+	 *     goto out;
+	 */
+	/* mov eax,dword ptr [ebp+off] */
+	EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EAX), STACK_VAR(r2[0]));
+	/* mov edx,dword ptr [ebp+off] */
+	EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EDX), STACK_VAR(r3[0]));
+
+	/* cmp dword ptr [eax+off],edx */
+	EMIT3(0x39, add_2reg(0x40, IA32_EAX, IA32_EDX),
+	      offsetof(struct bpf_array, map.max_entries));
+	/* jbe out */
+	EMIT2(IA32_JBE, jmp_label(jmp_label1, 2));
+
+	/*
+	 * if (tail_call_cnt > MAX_TAIL_CALL_CNT)
+	 *     goto out;
+	 */
+	lo = (u32)MAX_TAIL_CALL_CNT;
+	hi = (u32)((u64)MAX_TAIL_CALL_CNT >> 32);
+	EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_ECX), STACK_VAR(tcc[0]));
+	EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EBX), STACK_VAR(tcc[1]));
+
+	/* cmp edx,hi */
+	EMIT3(0x83, add_1reg(0xF8, IA32_EBX), hi);
+	EMIT2(IA32_JNE, 3);
+	/* cmp ecx,lo */
+	EMIT3(0x83, add_1reg(0xF8, IA32_ECX), lo);
+
+	/* ja out */
+	EMIT2(IA32_JAE, jmp_label(jmp_label1, 2));
+
+	/* add eax,0x1 */
+	EMIT3(0x83, add_1reg(0xC0, IA32_ECX), 0x01);
+	/* adc ebx,0x0 */
+	EMIT3(0x83, add_1reg(0xD0, IA32_EBX), 0x00);
+
+	/* mov dword ptr [ebp+off],eax */
+	EMIT3(0x89, add_2reg(0x40, IA32_EBP, IA32_ECX), STACK_VAR(tcc[0]));
+	/* mov dword ptr [ebp+off],edx */
+	EMIT3(0x89, add_2reg(0x40, IA32_EBP, IA32_EBX), STACK_VAR(tcc[1]));
+
+	/* prog = array->ptrs[index]; */
+	/* mov edx, [eax + edx * 4 + offsetof(...)] */
+	EMIT3_off32(0x8B, 0x94, 0x90, offsetof(struct bpf_array, ptrs));
+
+	/*
+	 * if (prog == NULL)
+	 *     goto out;
+	 */
+	/* test edx,edx */
+	EMIT2(0x85, add_2reg(0xC0, IA32_EDX, IA32_EDX));
+	/* je out */
+	EMIT2(IA32_JE, jmp_label(jmp_label1, 2));
+
+	/* goto *(prog->bpf_func + prologue_size); */
+	/* mov edx, dword ptr [edx + 32] */
+	EMIT3(0x8B, add_2reg(0x40, IA32_EDX, IA32_EDX),
+	      offsetof(struct bpf_prog, bpf_func));
+	/* add edx,prologue_size */
+	EMIT3(0x83, add_1reg(0xC0, IA32_EDX), PROLOGUE_SIZE);
+
+	/* mov eax,dword ptr [ebp+off] */
+	EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EAX), STACK_VAR(r1[0]));
+
+	/*
+	 * Now we're ready to jump into next BPF program:
+	 * eax == ctx (1st arg)
+	 * edx == prog->bpf_func + prologue_size
+	 */
+	RETPOLINE_EDX_BPF_JIT();
+
+	if (jmp_label1 == -1)
+		jmp_label1 = cnt;
+
+	/* out: */
+	*pprog = prog;
+}
+
+/* Push the scratch stack register on top of the stack. */
+static inline void emit_push_r64(const u8 src[], u8 **pprog)
+{
+	u8 *prog = *pprog;
+	int cnt = 0;
+
+	/* mov ecx,dword ptr [ebp+off] */
+	EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_ECX), STACK_VAR(src_hi));
+	/* push ecx */
+	EMIT1(0x51);
+
+	/* mov ecx,dword ptr [ebp+off] */
+	EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_ECX), STACK_VAR(src_lo));
+	/* push ecx */
+	EMIT1(0x51);
+
+	*pprog = prog;
+}
+
+static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
+		  int oldproglen, struct jit_context *ctx)
+{
+	struct bpf_insn *insn = bpf_prog->insnsi;
+	int insn_cnt = bpf_prog->len;
+	bool seen_exit = false;
+	u8 temp[BPF_MAX_INSN_SIZE + BPF_INSN_SAFETY];
+	int i, cnt = 0;
+	int proglen = 0;
+	u8 *prog = temp;
+
+	emit_prologue(&prog, bpf_prog->aux->stack_depth);
+
+	for (i = 0; i < insn_cnt; i++, insn++) {
+		const s32 imm32 = insn->imm;
+		const bool is64 = BPF_CLASS(insn->code) == BPF_ALU64;
+		const bool dstk = insn->dst_reg == BPF_REG_AX ? false : true;
+		const bool sstk = insn->src_reg == BPF_REG_AX ? false : true;
+		const u8 code = insn->code;
+		const u8 *dst = bpf2ia32[insn->dst_reg];
+		const u8 *src = bpf2ia32[insn->src_reg];
+		const u8 *r0 = bpf2ia32[BPF_REG_0];
+		s64 jmp_offset;
+		u8 jmp_cond;
+		int ilen;
+		u8 *func;
+
+		switch (code) {
+		/* ALU operations */
+		/* dst = src */
+		case BPF_ALU | BPF_MOV | BPF_K:
+		case BPF_ALU | BPF_MOV | BPF_X:
+		case BPF_ALU64 | BPF_MOV | BPF_K:
+		case BPF_ALU64 | BPF_MOV | BPF_X:
+			switch (BPF_SRC(code)) {
+			case BPF_X:
+				emit_ia32_mov_r64(is64, dst, src, dstk,
+						  sstk, &prog);
+				break;
+			case BPF_K:
+				/* Sign-extend immediate value to dst reg */
+				emit_ia32_mov_i64(is64, dst, imm32,
+						  dstk, &prog);
+				break;
+			}
+			break;
+		/* dst = dst + src/imm */
+		/* dst = dst - src/imm */
+		/* dst = dst | src/imm */
+		/* dst = dst & src/imm */
+		/* dst = dst ^ src/imm */
+		/* dst = dst * src/imm */
+		/* dst = dst << src */
+		/* dst = dst >> src */
+		case BPF_ALU | BPF_ADD | BPF_K:
+		case BPF_ALU | BPF_ADD | BPF_X:
+		case BPF_ALU | BPF_SUB | BPF_K:
+		case BPF_ALU | BPF_SUB | BPF_X:
+		case BPF_ALU | BPF_OR | BPF_K:
+		case BPF_ALU | BPF_OR | BPF_X:
+		case BPF_ALU | BPF_AND | BPF_K:
+		case BPF_ALU | BPF_AND | BPF_X:
+		case BPF_ALU | BPF_XOR | BPF_K:
+		case BPF_ALU | BPF_XOR | BPF_X:
+		case BPF_ALU64 | BPF_ADD | BPF_K:
+		case BPF_ALU64 | BPF_ADD | BPF_X:
+		case BPF_ALU64 | BPF_SUB | BPF_K:
+		case BPF_ALU64 | BPF_SUB | BPF_X:
+		case BPF_ALU64 | BPF_OR | BPF_K:
+		case BPF_ALU64 | BPF_OR | BPF_X:
+		case BPF_ALU64 | BPF_AND | BPF_K:
+		case BPF_ALU64 | BPF_AND | BPF_X:
+		case BPF_ALU64 | BPF_XOR | BPF_K:
+		case BPF_ALU64 | BPF_XOR | BPF_X:
+			switch (BPF_SRC(code)) {
+			case BPF_X:
+				emit_ia32_alu_r64(is64, BPF_OP(code), dst,
+						  src, dstk, sstk, &prog);
+				break;
+			case BPF_K:
+				emit_ia32_alu_i64(is64, BPF_OP(code), dst,
+						  imm32, dstk, &prog);
+				break;
+			}
+			break;
+		case BPF_ALU | BPF_MUL | BPF_K:
+		case BPF_ALU | BPF_MUL | BPF_X:
+			switch (BPF_SRC(code)) {
+			case BPF_X:
+				emit_ia32_mul_r(dst_lo, src_lo, dstk,
+						sstk, &prog);
+				break;
+			case BPF_K:
+				/* mov ecx,imm32*/
+				EMIT2_off32(0xC7, add_1reg(0xC0, IA32_ECX),
+					    imm32);
+				emit_ia32_mul_r(dst_lo, IA32_ECX, dstk,
+						false, &prog);
+				break;
+			}
+			emit_ia32_mov_i(dst_hi, 0, dstk, &prog);
+			break;
+		case BPF_ALU | BPF_LSH | BPF_X:
+		case BPF_ALU | BPF_RSH | BPF_X:
+		case BPF_ALU | BPF_ARSH | BPF_K:
+		case BPF_ALU | BPF_ARSH | BPF_X:
+			switch (BPF_SRC(code)) {
+			case BPF_X:
+				emit_ia32_shift_r(BPF_OP(code), dst_lo, src_lo,
+						  dstk, sstk, &prog);
+				break;
+			case BPF_K:
+				/* mov ecx,imm32*/
+				EMIT2_off32(0xC7, add_1reg(0xC0, IA32_ECX),
+					    imm32);
+				emit_ia32_shift_r(BPF_OP(code), dst_lo,
+						  IA32_ECX, dstk, false,
+						  &prog);
+				break;
+			}
+			emit_ia32_mov_i(dst_hi, 0, dstk, &prog);
+			break;
+		/* dst = dst / src(imm) */
+		/* dst = dst % src(imm) */
+		case BPF_ALU | BPF_DIV | BPF_K:
+		case BPF_ALU | BPF_DIV | BPF_X:
+		case BPF_ALU | BPF_MOD | BPF_K:
+		case BPF_ALU | BPF_MOD | BPF_X:
+			switch (BPF_SRC(code)) {
+			case BPF_X:
+				emit_ia32_div_mod_r(BPF_OP(code), dst_lo,
+						    src_lo, dstk, sstk, &prog);
+				break;
+			case BPF_K:
+				/* mov ecx,imm32*/
+				EMIT2_off32(0xC7, add_1reg(0xC0, IA32_ECX),
+					    imm32);
+				emit_ia32_div_mod_r(BPF_OP(code), dst_lo,
+						    IA32_ECX, dstk, false,
+						    &prog);
+				break;
+			}
+			emit_ia32_mov_i(dst_hi, 0, dstk, &prog);
+			break;
+		case BPF_ALU64 | BPF_DIV | BPF_K:
+		case BPF_ALU64 | BPF_DIV | BPF_X:
+		case BPF_ALU64 | BPF_MOD | BPF_K:
+		case BPF_ALU64 | BPF_MOD | BPF_X:
+			goto notyet;
+		/* dst = dst >> imm */
+		/* dst = dst << imm */
+		case BPF_ALU | BPF_RSH | BPF_K:
+		case BPF_ALU | BPF_LSH | BPF_K:
+			if (unlikely(imm32 > 31))
+				return -EINVAL;
+			/* mov ecx,imm32*/
+			EMIT2_off32(0xC7, add_1reg(0xC0, IA32_ECX), imm32);
+			emit_ia32_shift_r(BPF_OP(code), dst_lo, IA32_ECX, dstk,
+					  false, &prog);
+			emit_ia32_mov_i(dst_hi, 0, dstk, &prog);
+			break;
+		/* dst = dst << imm */
+		case BPF_ALU64 | BPF_LSH | BPF_K:
+			if (unlikely(imm32 > 63))
+				return -EINVAL;
+			emit_ia32_lsh_i64(dst, imm32, dstk, &prog);
+			break;
+		/* dst = dst >> imm */
+		case BPF_ALU64 | BPF_RSH | BPF_K:
+			if (unlikely(imm32 > 63))
+				return -EINVAL;
+			emit_ia32_rsh_i64(dst, imm32, dstk, &prog);
+			break;
+		/* dst = dst << src */
+		case BPF_ALU64 | BPF_LSH | BPF_X:
+			emit_ia32_lsh_r64(dst, src, dstk, sstk, &prog);
+			break;
+		/* dst = dst >> src */
+		case BPF_ALU64 | BPF_RSH | BPF_X:
+			emit_ia32_rsh_r64(dst, src, dstk, sstk, &prog);
+			break;
+		/* dst = dst >> src (signed) */
+		case BPF_ALU64 | BPF_ARSH | BPF_X:
+			emit_ia32_arsh_r64(dst, src, dstk, sstk, &prog);
+			break;
+		/* dst = dst >> imm (signed) */
+		case BPF_ALU64 | BPF_ARSH | BPF_K:
+			if (unlikely(imm32 > 63))
+				return -EINVAL;
+			emit_ia32_arsh_i64(dst, imm32, dstk, &prog);
+			break;
+		/* dst = ~dst */
+		case BPF_ALU | BPF_NEG:
+			emit_ia32_alu_i(is64, false, BPF_OP(code),
+					dst_lo, 0, dstk, &prog);
+			emit_ia32_mov_i(dst_hi, 0, dstk, &prog);
+			break;
+		/* dst = ~dst (64 bit) */
+		case BPF_ALU64 | BPF_NEG:
+			emit_ia32_neg64(dst, dstk, &prog);
+			break;
+		/* dst = dst * src/imm */
+		case BPF_ALU64 | BPF_MUL | BPF_X:
+		case BPF_ALU64 | BPF_MUL | BPF_K:
+			switch (BPF_SRC(code)) {
+			case BPF_X:
+				emit_ia32_mul_r64(dst, src, dstk, sstk, &prog);
+				break;
+			case BPF_K:
+				emit_ia32_mul_i64(dst, imm32, dstk, &prog);
+				break;
+			}
+			break;
+		/* dst = htole(dst) */
+		case BPF_ALU | BPF_END | BPF_FROM_LE:
+			emit_ia32_to_le_r64(dst, imm32, dstk, &prog);
+			break;
+		/* dst = htobe(dst) */
+		case BPF_ALU | BPF_END | BPF_FROM_BE:
+			emit_ia32_to_be_r64(dst, imm32, dstk, &prog);
+			break;
+		/* dst = imm64 */
+		case BPF_LD | BPF_IMM | BPF_DW: {
+			s32 hi, lo = imm32;
+
+			hi = insn[1].imm;
+			emit_ia32_mov_i(dst_lo, lo, dstk, &prog);
+			emit_ia32_mov_i(dst_hi, hi, dstk, &prog);
+			insn++;
+			i++;
+			break;
+		}
+		/* ST: *(u8*)(dst_reg + off) = imm */
+		case BPF_ST | BPF_MEM | BPF_H:
+		case BPF_ST | BPF_MEM | BPF_B:
+		case BPF_ST | BPF_MEM | BPF_W:
+		case BPF_ST | BPF_MEM | BPF_DW:
+			if (dstk)
+				/* mov eax,dword ptr [ebp+off] */
+				EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EAX),
+				      STACK_VAR(dst_lo));
+			else
+				/* mov eax,dst_lo */
+				EMIT2(0x8B, add_2reg(0xC0, dst_lo, IA32_EAX));
+
+			switch (BPF_SIZE(code)) {
+			case BPF_B:
+				EMIT(0xC6, 1); break;
+			case BPF_H:
+				EMIT2(0x66, 0xC7); break;
+			case BPF_W:
+			case BPF_DW:
+				EMIT(0xC7, 1); break;
+			}
+
+			if (is_imm8(insn->off))
+				EMIT2(add_1reg(0x40, IA32_EAX), insn->off);
+			else
+				EMIT1_off32(add_1reg(0x80, IA32_EAX),
+					    insn->off);
+			EMIT(imm32, bpf_size_to_x86_bytes(BPF_SIZE(code)));
+
+			if (BPF_SIZE(code) == BPF_DW) {
+				u32 hi;
+
+				hi = imm32 & (1<<31) ? (u32)~0 : 0;
+				EMIT2_off32(0xC7, add_1reg(0x80, IA32_EAX),
+					    insn->off + 4);
+				EMIT(hi, 4);
+			}
+			break;
+
+		/* STX: *(u8*)(dst_reg + off) = src_reg */
+		case BPF_STX | BPF_MEM | BPF_B:
+		case BPF_STX | BPF_MEM | BPF_H:
+		case BPF_STX | BPF_MEM | BPF_W:
+		case BPF_STX | BPF_MEM | BPF_DW:
+			if (dstk)
+				/* mov eax,dword ptr [ebp+off] */
+				EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EAX),
+				      STACK_VAR(dst_lo));
+			else
+				/* mov eax,dst_lo */
+				EMIT2(0x8B, add_2reg(0xC0, dst_lo, IA32_EAX));
+
+			if (sstk)
+				/* mov edx,dword ptr [ebp+off] */
+				EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EDX),
+				      STACK_VAR(src_lo));
+			else
+				/* mov edx,src_lo */
+				EMIT2(0x8B, add_2reg(0xC0, src_lo, IA32_EDX));
+
+			switch (BPF_SIZE(code)) {
+			case BPF_B:
+				EMIT(0x88, 1); break;
+			case BPF_H:
+				EMIT2(0x66, 0x89); break;
+			case BPF_W:
+			case BPF_DW:
+				EMIT(0x89, 1); break;
+			}
+
+			if (is_imm8(insn->off))
+				EMIT2(add_2reg(0x40, IA32_EAX, IA32_EDX),
+				      insn->off);
+			else
+				EMIT1_off32(add_2reg(0x80, IA32_EAX, IA32_EDX),
+					    insn->off);
+
+			if (BPF_SIZE(code) == BPF_DW) {
+				if (sstk)
+					/* mov edi,dword ptr [ebp+off] */
+					EMIT3(0x8B, add_2reg(0x40, IA32_EBP,
+							     IA32_EDX),
+					      STACK_VAR(src_hi));
+				else
+					/* mov edi,src_hi */
+					EMIT2(0x8B, add_2reg(0xC0, src_hi,
+							     IA32_EDX));
+				EMIT1(0x89);
+				if (is_imm8(insn->off + 4)) {
+					EMIT2(add_2reg(0x40, IA32_EAX,
+						       IA32_EDX),
+					      insn->off + 4);
+				} else {
+					EMIT1(add_2reg(0x80, IA32_EAX,
+						       IA32_EDX));
+					EMIT(insn->off + 4, 4);
+				}
+			}
+			break;
+
+		/* LDX: dst_reg = *(u8*)(src_reg + off) */
+		case BPF_LDX | BPF_MEM | BPF_B:
+		case BPF_LDX | BPF_MEM | BPF_H:
+		case BPF_LDX | BPF_MEM | BPF_W:
+		case BPF_LDX | BPF_MEM | BPF_DW:
+			if (sstk)
+				/* mov eax,dword ptr [ebp+off] */
+				EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EAX),
+				      STACK_VAR(src_lo));
+			else
+				/* mov eax,dword ptr [ebp+off] */
+				EMIT2(0x8B, add_2reg(0xC0, src_lo, IA32_EAX));
+
+			switch (BPF_SIZE(code)) {
+			case BPF_B:
+				EMIT2(0x0F, 0xB6); break;
+			case BPF_H:
+				EMIT2(0x0F, 0xB7); break;
+			case BPF_W:
+			case BPF_DW:
+				EMIT(0x8B, 1); break;
+			}
+
+			if (is_imm8(insn->off))
+				EMIT2(add_2reg(0x40, IA32_EAX, IA32_EDX),
+				      insn->off);
+			else
+				EMIT1_off32(add_2reg(0x80, IA32_EAX, IA32_EDX),
+					    insn->off);
+
+			if (dstk)
+				/* mov dword ptr [ebp+off],edx */
+				EMIT3(0x89, add_2reg(0x40, IA32_EBP, IA32_EDX),
+				      STACK_VAR(dst_lo));
+			else
+				/* mov dst_lo,edx */
+				EMIT2(0x89, add_2reg(0xC0, dst_lo, IA32_EDX));
+			switch (BPF_SIZE(code)) {
+			case BPF_B:
+			case BPF_H:
+			case BPF_W:
+				if (dstk) {
+					EMIT3(0xC7, add_1reg(0x40, IA32_EBP),
+					      STACK_VAR(dst_hi));
+					EMIT(0x0, 4);
+				} else {
+					EMIT3(0xC7, add_1reg(0xC0, dst_hi), 0);
+				}
+				break;
+			case BPF_DW:
+				EMIT2_off32(0x8B,
+					    add_2reg(0x80, IA32_EAX, IA32_EDX),
+					    insn->off + 4);
+				if (dstk)
+					EMIT3(0x89,
+					      add_2reg(0x40, IA32_EBP,
+						       IA32_EDX),
+					      STACK_VAR(dst_hi));
+				else
+					EMIT2(0x89,
+					      add_2reg(0xC0, dst_hi, IA32_EDX));
+				break;
+			default:
+				break;
+			}
+			break;
+		/* call */
+		case BPF_JMP | BPF_CALL:
+		{
+			const u8 *r1 = bpf2ia32[BPF_REG_1];
+			const u8 *r2 = bpf2ia32[BPF_REG_2];
+			const u8 *r3 = bpf2ia32[BPF_REG_3];
+			const u8 *r4 = bpf2ia32[BPF_REG_4];
+			const u8 *r5 = bpf2ia32[BPF_REG_5];
+
+			if (insn->src_reg == BPF_PSEUDO_CALL)
+				goto notyet;
+
+			func = (u8 *) __bpf_call_base + imm32;
+			jmp_offset = func - (image + addrs[i]);
+
+			if (!imm32 || !is_simm32(jmp_offset)) {
+				pr_err("unsupported BPF func %d addr %p image %p\n",
+				       imm32, func, image);
+				return -EINVAL;
+			}
+
+			/* mov eax,dword ptr [ebp+off] */
+			EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EAX),
+			      STACK_VAR(r1[0]));
+			/* mov edx,dword ptr [ebp+off] */
+			EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EDX),
+			      STACK_VAR(r1[1]));
+
+			emit_push_r64(r5, &prog);
+			emit_push_r64(r4, &prog);
+			emit_push_r64(r3, &prog);
+			emit_push_r64(r2, &prog);
+
+			EMIT1_off32(0xE8, jmp_offset + 9);
+
+			/* mov dword ptr [ebp+off],eax */
+			EMIT3(0x89, add_2reg(0x40, IA32_EBP, IA32_EAX),
+			      STACK_VAR(r0[0]));
+			/* mov dword ptr [ebp+off],edx */
+			EMIT3(0x89, add_2reg(0x40, IA32_EBP, IA32_EDX),
+			      STACK_VAR(r0[1]));
+
+			/* add esp,32 */
+			EMIT3(0x83, add_1reg(0xC0, IA32_ESP), 32);
+			break;
+		}
+		case BPF_JMP | BPF_TAIL_CALL:
+			emit_bpf_tail_call(&prog);
+			break;
+
+		/* cond jump */
+		case BPF_JMP | BPF_JEQ | BPF_X:
+		case BPF_JMP | BPF_JNE | BPF_X:
+		case BPF_JMP | BPF_JGT | BPF_X:
+		case BPF_JMP | BPF_JLT | BPF_X:
+		case BPF_JMP | BPF_JGE | BPF_X:
+		case BPF_JMP | BPF_JLE | BPF_X:
+		case BPF_JMP | BPF_JSGT | BPF_X:
+		case BPF_JMP | BPF_JSLE | BPF_X:
+		case BPF_JMP | BPF_JSLT | BPF_X:
+		case BPF_JMP | BPF_JSGE | BPF_X: {
+			u8 dreg_lo = dstk ? IA32_EAX : dst_lo;
+			u8 dreg_hi = dstk ? IA32_EDX : dst_hi;
+			u8 sreg_lo = sstk ? IA32_ECX : src_lo;
+			u8 sreg_hi = sstk ? IA32_EBX : src_hi;
+
+			if (dstk) {
+				EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EAX),
+				      STACK_VAR(dst_lo));
+				EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EDX),
+				      STACK_VAR(dst_hi));
+			}
+
+			if (sstk) {
+				EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_ECX),
+				      STACK_VAR(src_lo));
+				EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EBX),
+				      STACK_VAR(src_hi));
+			}
+
+			/* cmp dreg_hi,sreg_hi */
+			EMIT2(0x39, add_2reg(0xC0, dreg_hi, sreg_hi));
+			EMIT2(IA32_JNE, 2);
+			/* cmp dreg_lo,sreg_lo */
+			EMIT2(0x39, add_2reg(0xC0, dreg_lo, sreg_lo));
+			goto emit_cond_jmp;
+		}
+		case BPF_JMP | BPF_JSET | BPF_X: {
+			u8 dreg_lo = dstk ? IA32_EAX : dst_lo;
+			u8 dreg_hi = dstk ? IA32_EDX : dst_hi;
+			u8 sreg_lo = sstk ? IA32_ECX : src_lo;
+			u8 sreg_hi = sstk ? IA32_EBX : src_hi;
+
+			if (dstk) {
+				EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EAX),
+				      STACK_VAR(dst_lo));
+				EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EDX),
+				      STACK_VAR(dst_hi));
+			}
+
+			if (sstk) {
+				EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_ECX),
+				      STACK_VAR(src_lo));
+				EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EBX),
+				      STACK_VAR(src_hi));
+			}
+			/* and dreg_lo,sreg_lo */
+			EMIT2(0x23, add_2reg(0xC0, sreg_lo, dreg_lo));
+			/* and dreg_hi,sreg_hi */
+			EMIT2(0x23, add_2reg(0xC0, sreg_hi, dreg_hi));
+			/* or dreg_lo,dreg_hi */
+			EMIT2(0x09, add_2reg(0xC0, dreg_lo, dreg_hi));
+			goto emit_cond_jmp;
+		}
+		case BPF_JMP | BPF_JSET | BPF_K: {
+			u32 hi;
+			u8 dreg_lo = dstk ? IA32_EAX : dst_lo;
+			u8 dreg_hi = dstk ? IA32_EDX : dst_hi;
+			u8 sreg_lo = IA32_ECX;
+			u8 sreg_hi = IA32_EBX;
+
+			if (dstk) {
+				EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EAX),
+				      STACK_VAR(dst_lo));
+				EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EDX),
+				      STACK_VAR(dst_hi));
+			}
+			hi = imm32 & (1<<31) ? (u32)~0 : 0;
+
+			/* mov ecx,imm32 */
+			EMIT2_off32(0xC7, add_1reg(0xC0, IA32_ECX), imm32);
+			/* mov ebx,imm32 */
+			EMIT2_off32(0xC7, add_1reg(0xC0, IA32_EBX), hi);
+
+			/* and dreg_lo,sreg_lo */
+			EMIT2(0x23, add_2reg(0xC0, sreg_lo, dreg_lo));
+			/* and dreg_hi,sreg_hi */
+			EMIT2(0x23, add_2reg(0xC0, sreg_hi, dreg_hi));
+			/* or dreg_lo,dreg_hi */
+			EMIT2(0x09, add_2reg(0xC0, dreg_lo, dreg_hi));
+			goto emit_cond_jmp;
+		}
+		case BPF_JMP | BPF_JEQ | BPF_K:
+		case BPF_JMP | BPF_JNE | BPF_K:
+		case BPF_JMP | BPF_JGT | BPF_K:
+		case BPF_JMP | BPF_JLT | BPF_K:
+		case BPF_JMP | BPF_JGE | BPF_K:
+		case BPF_JMP | BPF_JLE | BPF_K:
+		case BPF_JMP | BPF_JSGT | BPF_K:
+		case BPF_JMP | BPF_JSLE | BPF_K:
+		case BPF_JMP | BPF_JSLT | BPF_K:
+		case BPF_JMP | BPF_JSGE | BPF_K: {
+			u32 hi;
+			u8 dreg_lo = dstk ? IA32_EAX : dst_lo;
+			u8 dreg_hi = dstk ? IA32_EDX : dst_hi;
+			u8 sreg_lo = IA32_ECX;
+			u8 sreg_hi = IA32_EBX;
+
+			if (dstk) {
+				EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EAX),
+				      STACK_VAR(dst_lo));
+				EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EDX),
+				      STACK_VAR(dst_hi));
+			}
+
+			hi = imm32 & (1<<31) ? (u32)~0 : 0;
+			/* mov ecx,imm32 */
+			EMIT2_off32(0xC7, add_1reg(0xC0, IA32_ECX), imm32);
+			/* mov ebx,imm32 */
+			EMIT2_off32(0xC7, add_1reg(0xC0, IA32_EBX), hi);
+
+			/* cmp dreg_hi,sreg_hi */
+			EMIT2(0x39, add_2reg(0xC0, dreg_hi, sreg_hi));
+			EMIT2(IA32_JNE, 2);
+			/* cmp dreg_lo,sreg_lo */
+			EMIT2(0x39, add_2reg(0xC0, dreg_lo, sreg_lo));
+
+emit_cond_jmp:		/* Convert BPF opcode to x86 */
+			switch (BPF_OP(code)) {
+			case BPF_JEQ:
+				jmp_cond = IA32_JE;
+				break;
+			case BPF_JSET:
+			case BPF_JNE:
+				jmp_cond = IA32_JNE;
+				break;
+			case BPF_JGT:
+				/* GT is unsigned '>', JA in x86 */
+				jmp_cond = IA32_JA;
+				break;
+			case BPF_JLT:
+				/* LT is unsigned '<', JB in x86 */
+				jmp_cond = IA32_JB;
+				break;
+			case BPF_JGE:
+				/* GE is unsigned '>=', JAE in x86 */
+				jmp_cond = IA32_JAE;
+				break;
+			case BPF_JLE:
+				/* LE is unsigned '<=', JBE in x86 */
+				jmp_cond = IA32_JBE;
+				break;
+			case BPF_JSGT:
+				/* Signed '>', GT in x86 */
+				jmp_cond = IA32_JG;
+				break;
+			case BPF_JSLT:
+				/* Signed '<', LT in x86 */
+				jmp_cond = IA32_JL;
+				break;
+			case BPF_JSGE:
+				/* Signed '>=', GE in x86 */
+				jmp_cond = IA32_JGE;
+				break;
+			case BPF_JSLE:
+				/* Signed '<=', LE in x86 */
+				jmp_cond = IA32_JLE;
+				break;
+			default: /* to silence GCC warning */
+				return -EFAULT;
+			}
+			jmp_offset = addrs[i + insn->off] - addrs[i];
+			if (is_imm8(jmp_offset)) {
+				EMIT2(jmp_cond, jmp_offset);
+			} else if (is_simm32(jmp_offset)) {
+				EMIT2_off32(0x0F, jmp_cond + 0x10, jmp_offset);
+			} else {
+				pr_err("cond_jmp gen bug %llx\n", jmp_offset);
+				return -EFAULT;
+			}
+
+			break;
+		}
+		case BPF_JMP | BPF_JA:
+			if (insn->off == -1)
+				/* -1 jmp instructions will always jump
+				 * backwards two bytes. Explicitly handling
+				 * this case avoids wasting too many passes
+				 * when there are long sequences of replaced
+				 * dead code.
+				 */
+				jmp_offset = -2;
+			else
+				jmp_offset = addrs[i + insn->off] - addrs[i];
+
+			if (!jmp_offset)
+				/* Optimize out nop jumps */
+				break;
+emit_jmp:
+			if (is_imm8(jmp_offset)) {
+				EMIT2(0xEB, jmp_offset);
+			} else if (is_simm32(jmp_offset)) {
+				EMIT1_off32(0xE9, jmp_offset);
+			} else {
+				pr_err("jmp gen bug %llx\n", jmp_offset);
+				return -EFAULT;
+			}
+			break;
+		/* STX XADD: lock *(u32 *)(dst + off) += src */
+		case BPF_STX | BPF_XADD | BPF_W:
+		/* STX XADD: lock *(u64 *)(dst + off) += src */
+		case BPF_STX | BPF_XADD | BPF_DW:
+			goto notyet;
+		case BPF_JMP | BPF_EXIT:
+			if (seen_exit) {
+				jmp_offset = ctx->cleanup_addr - addrs[i];
+				goto emit_jmp;
+			}
+			seen_exit = true;
+			/* Update cleanup_addr */
+			ctx->cleanup_addr = proglen;
+			emit_epilogue(&prog, bpf_prog->aux->stack_depth);
+			break;
+notyet:
+			pr_info_once("*** NOT YET: opcode %02x ***\n", code);
+			return -EFAULT;
+		default:
+			/*
+			 * This error will be seen if new instruction was added
+			 * to interpreter, but not to JIT or if there is junk in
+			 * bpf_prog
+			 */
+			pr_err("bpf_jit: unknown opcode %02x\n", code);
+			return -EINVAL;
+		}
+
+		ilen = prog - temp;
+		if (ilen > BPF_MAX_INSN_SIZE) {
+			pr_err("bpf_jit: fatal insn size error\n");
+			return -EFAULT;
+		}
+
+		if (image) {
+			if (unlikely(proglen + ilen > oldproglen)) {
+				pr_err("bpf_jit: fatal error\n");
+				return -EFAULT;
+			}
+			memcpy(image + proglen, temp, ilen);
+		}
+		proglen += ilen;
+		addrs[i] = proglen;
+		prog = temp;
+	}
+	return proglen;
+}
+
+struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
+{
+	struct bpf_binary_header *header = NULL;
+	struct bpf_prog *tmp, *orig_prog = prog;
+	int proglen, oldproglen = 0;
+	struct jit_context ctx = {};
+	bool tmp_blinded = false;
+	u8 *image = NULL;
+	int *addrs;
+	int pass;
+	int i;
+
+	if (!prog->jit_requested)
+		return orig_prog;
+
+	tmp = bpf_jit_blind_constants(prog);
+	/*
+	 * If blinding was requested and we failed during blinding,
+	 * we must fall back to the interpreter.
+	 */
+	if (IS_ERR(tmp))
+		return orig_prog;
+	if (tmp != prog) {
+		tmp_blinded = true;
+		prog = tmp;
+	}
+
+	addrs = kmalloc(prog->len * sizeof(*addrs), GFP_KERNEL);
+	if (!addrs) {
+		prog = orig_prog;
+		goto out;
+	}
+
+	/*
+	 * Before first pass, make a rough estimation of addrs[]
+	 * each BPF instruction is translated to less than 64 bytes
+	 */
+	for (proglen = 0, i = 0; i < prog->len; i++) {
+		proglen += 64;
+		addrs[i] = proglen;
+	}
+	ctx.cleanup_addr = proglen;
+
+	/*
+	 * JITed image shrinks with every pass and the loop iterates
+	 * until the image stops shrinking. Very large BPF programs
+	 * may converge on the last pass. In such case do one more
+	 * pass to emit the final image.
+	 */
+	for (pass = 0; pass < 20 || image; pass++) {
+		proglen = do_jit(prog, addrs, image, oldproglen, &ctx);
+		if (proglen <= 0) {
+out_image:
+			image = NULL;
+			if (header)
+				bpf_jit_binary_free(header);
+			prog = orig_prog;
+			goto out_addrs;
+		}
+		if (image) {
+			if (proglen != oldproglen) {
+				pr_err("bpf_jit: proglen=%d != oldproglen=%d\n",
+				       proglen, oldproglen);
+				goto out_image;
+			}
+			break;
+		}
+		if (proglen == oldproglen) {
+			header = bpf_jit_binary_alloc(proglen, &image,
+						      1, jit_fill_hole);
+			if (!header) {
+				prog = orig_prog;
+				goto out_addrs;
+			}
+		}
+		oldproglen = proglen;
+		cond_resched();
+	}
+
+	if (bpf_jit_enable > 1)
+		bpf_jit_dump(prog->len, proglen, pass + 1, image);
+
+	if (image) {
+		bpf_jit_binary_lock_ro(header);
+		prog->bpf_func = (void *)image;
+		prog->jited = 1;
+		prog->jited_len = proglen;
+	} else {
+		prog = orig_prog;
+	}
+
+out_addrs:
+	kfree(addrs);
+out:
+	if (tmp_blinded)
+		bpf_jit_prog_release_other(prog, prog == orig_prog ?
+					   tmp : orig_prog);
+	return prog;
+}