diff options
Diffstat (limited to 'arch/x86/net/bpf_jit_comp32.c')
| -rw-r--r-- | arch/x86/net/bpf_jit_comp32.c | 2553 |
1 files changed, 2553 insertions, 0 deletions
diff --git a/arch/x86/net/bpf_jit_comp32.c b/arch/x86/net/bpf_jit_comp32.c new file mode 100644 index 000000000000..61e61341b777 --- /dev/null +++ b/arch/x86/net/bpf_jit_comp32.c @@ -0,0 +1,2553 @@ +// 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 + \ + + 4 /* Extra space for skb_copy_bits buffer */) + +#define STACK_SIZE ALIGN(_STACK_SIZE, STACK_ALIGNMENT) + +/* Get the offset of eBPF REGISTERs stored on scratch space. */ +#define STACK_VAR(off) (off) + +/* Offset of skb_copy_bits buffer */ +#define SKB_BUFFER STACK_VAR(SCRATCH_SIZE) + +/* 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; +} + < |