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>

4 files changed, 2544 insertions, 379 deletions

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;
+}