/*
* 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)
{
u8 *prog = *pprog;
int cnt = 0;
/* push rbp */
EMIT1(0x55);
/* mov rbp,rsp */
EMIT3(0x48, 0x89, 0xE5);
/* sub rsp, rounded_stack_depth + AUX_STACK_SPACE */
EMIT3_off32(0x48, 0x81, 0xEC,
round_up(stack_depth, 8) + AUX_STACK_SPACE);
/* sub rbp, AUX_STACK_SPACE */
EMIT4(0x48, 0x83, 0xED, AUX_STACK_SPACE);
/* mov qword ptr [rbp+0],rbx */
EMIT4(0x48, 0x89, 0x5D, 0);
/* mov qword ptr [rbp+8],r13 */
EMIT4(0x4C, 0x89, 0x6D, 8);
/* mov qword ptr [rbp+16],r14 */
EMIT4(0x4C, 0x89, 0x75, 16);
/* mov qword ptr [rbp+24],r15 */
EMIT4(0x4C, 0x89, 0x7D, 24);
if (!ebpf_from_cbpf) {
/*
* 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
* to the counter location.
*/
/* xor eax, eax */
EMIT2(0x31, 0xc0);
/* mov qword ptr [rbp+32], rax */
EMIT4(0x48, 0x89, 0x45, 32);
BUILD_BUG_ON(cnt != PROLOGUE_SIZE);
}
*pprog = prog;
}
static void emit_mov_imm32(u8 **pprog, bool sign_propagate,
u32 dst_reg, const u32 imm32)
{
u8 *prog = *pprog;
u8 b1, b2, b3;
int cnt = 0;
/*
* Optimization: if imm32 is positive, use 'mov %eax, imm32'
* (which zero-extends imm32) to save 2 bytes.
*/
if (sign_propagate && (s32)imm32 < 0) {
/* 'mov %rax, imm32' sign extends imm32 */
b1 = add_1mod(0x48, dst_reg);
b2 = 0xC7;
b3 = 0xC0;
EMIT3_off32(b1, b2, add_1reg(b3, dst_reg), imm32);
goto done;
}
/*
* Optimization: if imm32 is zero, use 'xor %eax, %eax'
* to save 3 bytes.
*/
if (imm32 == 0) {
if (is_ereg(dst_reg))
EMIT1(add_2mod(0x40, dst_reg, dst_reg));
b2 = 0x31; /* xor */
b3 = 0xC0;
EMIT2(b2, add_2reg(b3, dst_reg, dst_reg));
goto done;
}
/* mov %eax, imm32 */
if (is_ereg(dst_reg))
EMIT1(add_1mod(0x40, dst_reg));
EMIT1_off32(add_1reg(0xB8, dst_reg), imm32);
done:
*pprog = prog;
}
/* emit x64 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)
{
u8 *prog = *pprog;
int cnt = 0;
EMIT1(0x55); /* push rbp */
EMIT3(0x48, 0x89, 0xE5); /* mov rbp,rsp */
/* sub rsp, STACKSIZE */
EMIT3_off32(0x48, 0x81, 0xEC, STACKSIZE);
/* all classic BPF filters use R6(rbx) save it */
/* mov qword ptr [rbp-X],rbx */
EMIT3_off32(0x48, 0x89, 0x9D, -STACKSIZE);
/* 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-X],r13 */
EMIT3_off32(0x4C, 0x89, 0xAD, -STACKSIZE + 8);
/* mov qword ptr [rbp-X],r14 */
EMIT3_off32(0x4C, 0x89, 0xB5, -STACKSIZE + 16);
/* mov qword ptr [rbp-X],r15 */
EMIT3_off32(0x4C, 0x89, 0xBD, -STACKSIZE + 24);
/* 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 (xor on eax gets 0 extended), and
* moving it to the counter location.
*/
/* xor eax, eax */
EMIT2(0x31, 0xc0);
/* mov qword ptr [rbp-X], rax */
EMIT3_off32(0x48, 0x89, 0x85, -STACKSIZE + 32);
BUILD_BUG_ON(cnt != PROLOGUE_SIZE);
*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_ld_abs = ctx->seen_ld_abs | (oldproglen == 0);
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);
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;
u32 src_reg = insn->src_reg;
u8 b1 = 0, b2 = 0, b3 = 0;
s64 jmp_offset;
u8 jmp_cond;
bool reload_skb_data;
int ilen;
u8 *func;
switch (insn->code) {
/* ALU */
case BPF_ALU | BPF_ADD | BPF_X:
case BPF_ALU | BPF_SUB | BPF_X:
case BPF_ALU | BPF_AND | BPF_X:
case BPF_ALU | BPF_OR | BPF_X:
case BPF_ALU | BPF_XOR | BPF_X:
case BPF_ALU64 | BPF_ADD | BPF_X:
case BPF_ALU64 | BPF_SUB | BPF_X:
case BPF_ALU64 | BPF_AND | BPF_X:
case BPF_ALU64 | BPF_OR | BPF_X:
case BPF_ALU64 | BPF_XOR | BPF_X:
switch (BPF_OP(insn->code)) {
case BPF_ADD: b2 = 0x01; break;
case BPF_SUB: b2 = 0x29; break;
case BPF_AND: b2 = 0x21; break;
case BPF_OR: b2 = 0x09; break;
case BPF_XOR: b2 = 0x31; break;
}
if (BPF_CLASS(insn->code) == BPF_ALU64)
EMIT1(add_2mod(0x48, dst_reg, src_reg));
else if (is_ereg(dst_reg) || is_ereg(src_reg))
EMIT1(add_2mod(0x40, dst_reg, src_reg));
EMIT2(b2, add_2reg(0xC0, dst_reg, src_reg));
break;
/* mov dst, src */
case BPF_ALU64 | BPF_MOV | BPF_X:
EMIT_mov(dst_reg, src_reg);
break;
/* mov32 dst, src */
case BPF_ALU | BPF_MOV | BPF_X:
if (is_ereg(dst_reg) || is_ereg(src_reg))
EMIT1(add_2mod(0x40, dst_reg, src_reg));
EMIT2(0x89, add_2reg(0xC0, dst_reg, src_reg));
break;
/* neg dst */
case BPF_ALU | BPF_NEG:
case BPF_ALU64 | BPF_NEG:
if (BPF_CLASS(insn->code) == BPF_ALU64)
EMIT1(add_1mod(0x48, dst_reg));
else if (is_ereg(dst_reg))
EMIT1(add_1mod(0x40, dst_reg));
EMIT2(0xF7, add_1reg(0xD8, dst_reg));
break;
case BPF_ALU | BPF_ADD | BPF_K:
case BPF_ALU | BPF_SUB | BPF_K:
case BPF_ALU | BPF_AND | BPF_K:
case BPF_ALU | BPF_OR | BPF_K:
case BPF_ALU | BPF_XOR | BPF_K:
case BPF_ALU64 | BPF_ADD | BPF_K:
case BPF_ALU64 | BPF_SUB | BPF_K:
case BPF_ALU64 | BPF_AND | BPF_K:
case BPF_ALU64 | BPF_OR | BPF_K:
case BPF_ALU64 | BPF_XOR | BPF_K:
if (BPF_CLASS(insn->code) == BPF_ALU64)
EMIT1(add_1mod(0x48, dst_reg));
else if (is_ereg(dst_reg))
EMIT1(add_1mod(0x40, dst_reg));
switch (BPF_OP(insn->code)) {
case BPF_ADD: b3 = 0xC0; break;
case BPF_SUB: b3 = 0xE8; break;
case BPF_AND: b3 = 0xE0; break;
case BPF_OR: b3 = 0xC8; break;
case BPF_XOR: b3 = 0xF0; break;
}
if (is_imm8(imm32))
EMIT3(0x83, add_1reg(b3, dst_reg), imm32);
else
EMIT2_off32(0x81, add_1reg(b3, dst_reg), imm32);
break;
case BPF_ALU64 | BPF_MOV | BPF_K:
/* optimization: if imm32 is positive,
* use 'mov eax, imm32' (which zero-extends imm32)
* to save 2 bytes
*/
if (imm32 < 0) {
/* 'mov rax, imm32' sign extends imm32 */
b1 = add_1mod(0x48, dst_reg);
b2 = 0xC7;
b3 = 0xC0;
EMIT3_off32(b1, b2, add_1reg(b3, dst_reg), imm32);
break;
}
case BPF_ALU | BPF_MOV | BPF_K:
/* optimization: if imm32 is zero, use 'xor <dst>,<dst>'
* to save 3 bytes.
*/
if (imm32 == 0) {
if (is_ereg(dst_reg))
EMIT1(add_2mod(0x40, dst_reg, dst_reg));
b2 = 0x31; /* xor */
b3 = 0xC0;
EMIT2(b2, add_2reg(b3, dst_reg, dst_reg));
break;
}
/* mov %eax, imm32 */
if (is_ereg(dst_reg))
EMIT1(add_1mod(0x40, dst_reg));
EMIT1_off32(add_1reg(0xB8, dst_reg), imm32);
break;
case BPF_LD | BPF_IMM | BPF_DW:
if (insn[1].code != 0 || insn[1].src_reg != 0 ||
insn[1].dst_reg != 0 || insn[1].off != 0) {
/* verifier must catch invalid insns */
pr_err("invalid BPF_LD_IMM64 insn\n");
return -EINVAL;
}
/* optimization: if imm64 is zero, use 'xor <dst>,<dst>'
* to save 7 bytes.
*/
if (insn[0].imm == 0 && insn[1].imm == 0) {
b1 = add_2mod(0x48, dst_reg, dst_reg);
b2 = 0x31; /* xor */
b3 = 0xC0;
EMIT3(b1, b2, add_2reg(b3, dst_reg, dst_reg));
insn++;
i++;
break;
}
/* movabsq %rax, imm64 */
EMIT2(add_1mod(0x48, dst_reg), add_1reg(0xB8, dst_reg));
EMIT(insn[0].imm, 4);
EMIT(insn[1].imm, 4);
insn++;
i++;
break;
/* dst %= src, dst /= src, dst %= imm32, dst /= imm32 */
case BPF_ALU | BPF_MOD | BPF_X:
case BPF_ALU | BPF_DIV | BPF_X:
case BPF_ALU | BPF_MOD | BPF_K:
case BPF_ALU | BPF_DIV | BPF_K:
case BPF_ALU64 | BPF_MOD | BPF_X:
case BPF_ALU64 | BPF_DIV | BPF_X:
case BPF_ALU64 | BPF_MOD | BPF_K:
case BPF_ALU64 | BPF_DIV | BPF_K:
EMIT1(0x50); /* push rax */
EMIT1(0x52); /* push rdx */
if (BPF_SRC(insn->code) == BPF_X)
/* mov r11, src_reg */
EMIT_mov(AUX_REG, src_reg);
else
/* mov r11, imm32 */
EMIT3_off32(0x49, 0xC7, 0xC3, imm32);
/* mov rax, dst_reg */
EMIT_mov(BPF_REG_0, dst_reg);
/* xor edx, edx
* equivalent to 'xor rdx, rdx', but one byte less
*/
EMIT2(0x31, 0xd2);
if (BPF_SRC(insn->code) == BPF_X) {
/* if (src_reg == 0) return 0 */
/* cmp r11, 0 */
EMIT4(0x49, 0x83, 0xFB, 0x00);
/* jne .+9 (skip over pop, pop, xor and jmp) */
EMIT2(X86_JNE, 1 + 1 + 2 + 5);
EMIT1(0x5A); /* pop rdx */
EMIT1(0x58); /* pop rax */
EMIT2(0x31, 0xc0); /* xor eax, eax */
/* jmp cleanup_addr
* addrs[i] - 11, because there are 11 bytes
* after this insn: div, mov, pop, pop, mov
*/
jmp_offset = ctx->cleanup_addr - (addrs[i] - 11);
EMIT1_off32(0xE9, jmp_offset);
}
if (BPF_CLASS(insn->code) == BPF_ALU64)
/* div r11 */
EMIT3(0x49, 0xF7, 0xF3);
else
/* div r11d */
EMIT3(0x41, 0xF7, 0xF3);
if (BPF_OP(insn->code) == BPF_MOD)
/* mov r11, rdx */
EMIT3(0x49, 0x89, 0xD3);
else
/* mov r11, rax */
EMIT3(0x49, 0x89, 0xC3);
EMIT1(0x5A); /* pop rdx */
EMIT1(0x58); /* pop rax */
/* mov dst_reg, r11 */
EMIT_mov(dst_reg, AUX_REG);
break;
case BPF_ALU | BPF_MUL | BPF_K:
case BPF_ALU | BPF_MUL | BPF_X:
case BPF_ALU64 | BPF_MUL | BPF_K:
case BPF_ALU64 | BPF_MUL | BPF_X:
EMIT1(0x50); /* push rax */
EMIT1(0x52); /* push rdx */
/* mov r11, dst_reg */
EMIT_mov(AUX_REG, dst_reg);
if (BPF_SRC(insn->code) == BPF_X)
/* mov rax, src_reg */
EMIT_mov(BPF_REG_0, src_reg);
else
/* mov rax, imm32 */
EMIT3_off32(0x48, 0xC7, 0xC0, imm32);
if (BPF_CLASS(insn->code) == BPF_ALU64)
EMIT1(add_1mod(0x48, AUX_REG));
else if (is_ereg(AUX_REG))
EMIT1(add_1mod(0x40, AUX_REG));
/* mul(q) r11 */
EMIT2(0xF7, add_1reg(0xE0, AUX_REG));
/* mov r11, rax */
EMIT_mov(AUX_REG, BPF_REG_0);
EMIT1(0x5A); /* pop rdx */
EMIT1(0x58); /* pop rax */
/* mov dst_reg, r11 */
EMIT_mov(dst_reg, AUX_REG);
break;
/* shifts */
case BPF_ALU | BPF_LSH | BPF_K:
case BPF_ALU | BPF_RSH | BPF_K:
case BPF_ALU | BPF_ARSH | BPF_K:
case BPF_ALU64 | BPF_LSH | BPF_K:
case BPF_ALU64 | BPF_RSH | BPF_K:
case BPF_ALU64 | BPF_ARSH | BPF_K:
if (BPF_CLASS(insn->code) == BPF_ALU64)
EMIT1(add_1mod(0x48, dst_reg));
else if (is_ereg(dst_reg))
EMIT1(add_1mod(0x40, dst_reg));
switch (BPF_OP(insn->code)) {
case BPF_LSH: b3 = 0xE0; break;
case BPF_RSH: b3 = 0xE8; break;
case BPF_ARSH: b3 = 0xF8; break;
}
EMIT3(0xC1, add_1reg(b3, dst_reg), imm32);
break;
case BPF_ALU | BPF_LSH | BPF_X:
case BPF_ALU | BPF_RSH | BPF_X:
case BPF_ALU | BPF_ARSH | BPF_X:
case BPF_ALU64 | BPF_LSH | BPF_X:
case BPF_ALU64 | BPF_RSH | BPF_X:
case BPF_ALU64 | BPF_ARSH | BPF_X:
/* check for bad case when dst_reg == rcx */
if (dst_reg == BPF_REG_4) {
/* mov r11, dst_reg */
EMIT_mov(AUX_REG, dst_reg);
dst_reg = AUX_REG;
}
if (src_reg != BPF_REG_4) { /* common case */
EMIT1(0x51); /* push rcx */
/* mov rcx, src_reg */
EMIT_mov(BPF_REG_4, src_reg);
}
/* shl %rax, %cl | shr %rax, %cl | sar %rax, %cl */
if (BPF_CLASS(insn->code) == BPF_ALU64)
EMIT1(add_1mod(0x48, dst_reg));
else if (is_ereg(dst_reg))
EMIT1(add_1mod(0x40, dst_reg));
switch (BPF_OP(insn->code)) {
case BPF_LSH: b3 = 0xE0; break;
case BPF_RSH: b3 = 0xE8; break;
case BPF_ARSH: b3 = 0xF8; break;
}
EMIT2(0xD3, add_1reg(b3, dst_reg));
if (src_reg != BPF_REG_4)
EMIT1(0x59); /* pop rcx */
if (insn->dst_reg == BPF_REG_4)
/* mov dst_reg, r11 */
EMIT_mov(insn->dst_reg, AUX_REG);
break;
case BPF_ALU | BPF_END | BPF_FROM_BE:
switch (imm32) {
case 16:
/* 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' */
if (is_ereg(dst_reg))
EMIT3(0x45, 0x0F, 0xB7);
else
EMIT2(0x0F, 0xB7);
EMIT1(add_2reg(0xC0, dst_reg, dst_reg));
break;
case 32:
/* emit 'bswap eax' to swap lower 4 bytes */
if (is_ereg(dst_reg))
EMIT2(0x41, 0x0F);
else
EMIT1(0x0F);
EMIT1(add_1reg(0xC8, dst_reg));
break;
case 64:
/* emit 'bswap rax' to swap 8 bytes */
EMIT3(add_1mod(0x48, dst_reg), 0x0F,
add_1reg(0xC8, dst_reg));
break;
}
break;
case BPF_ALU | BPF_END | BPF_FROM_LE:
switch (imm32) {
case 16:
/* emit 'movzwl eax, ax' to zero extend 16-bit
* into 64 bit
*/
if (is_ereg(dst_reg))
EMIT3(0x45, 0x0F, 0xB7);
else
EMIT2(0x0F, 0xB7);
EMIT1(add_2reg(0xC0, dst_reg, dst_reg));
break;
case 32:
/* 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));
break;
case 64:
/* nop */
break;
}
break;
/* ST: *(u8*)(dst_reg + off) = imm */
case BPF_ST | BPF_MEM | BPF_B:
if (is_ereg(dst_reg))
EMIT2(0x41, 0xC6);
else
EMIT1(0xC6);
goto st;
case BPF_ST | BPF_MEM | BPF_H:
if (is_ereg(dst_reg))
EMIT3(0x66, 0x41, 0xC7);
else
EMIT2(0x66, 0xC7);
goto st;
case BPF_ST | BPF_MEM | BPF_W:
if (is_ereg(dst_reg))
EMIT2(0x41, 0xC7);
else
EMIT1(0xC7);
goto st;
case BPF_ST | BPF_MEM | BPF_DW:
EMIT2(add_1mod(0x48, dst_reg), 0xC7);
st: if (is_imm8(insn->off))
EMIT2(add_1reg(0x40, dst_reg), insn->off);
else
EMIT1_off32(add_1reg(0x80, dst_reg), insn->off);
EMIT(imm32, bpf_size_to_x86_bytes(BPF_SIZE(insn->code)));
break;
/* STX: *(u8*)(dst_reg + off) = src_reg */
case BPF_STX | BPF_MEM | BPF_B:
/* 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 */
src_reg == BPF_REG_1 || src_reg == BPF_REG_2)
EMIT2(add_2mod(0x40, dst_reg, src_reg), 0x88);
else
EMIT1(0x88);
goto stx;
case BPF_STX | BPF_MEM | BPF_H:
if (is_ereg(dst_reg) || is_ereg(src_reg))
EMIT3(0x66, add_2mod(0x40, dst_reg, src_reg), 0x89);
else
EMIT2(0x66, 0x89);
goto stx;
case BPF_STX | BPF_MEM | BPF_W:
if (is_ereg(dst_reg) || is_ereg(src_reg))
EMIT2(add_2mod(0x40, dst_reg, src_reg), 0x89);
else
EMIT1(0x89);
goto stx;
case BPF_STX | BPF_MEM | BPF_DW:
EMIT2(add_2mod(0x48, dst_reg, src_reg), 0x89);
stx: if (is_imm8(insn->off))
EMIT2(add_2reg(0x40, dst_reg, src_reg), insn->off);
else
EMIT1_off32(add_2reg(0x80, dst_reg, src_reg),
insn->off);
break;
/* LDX: dst_reg = *(u8*)(src_reg + off) */
case BPF_LDX | BPF_MEM | BPF_B:
/* 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]' */
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]' */
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]' */
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
* is not worth the hassle
*/
if (is_imm8(insn->off))
EMIT2(add_2reg(0x40, src_reg, dst_reg), insn->off);
else
EMIT1_off32(add_2reg(0x80, src_reg, dst_reg),
insn->off);
break;
/* STX XADD: lock *(u32*)(dst_reg + off) += src_reg */
case BPF_STX | BPF_XADD | BPF_W:
/* 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
EMIT2(0xF0, 0x01);
goto xadd;
case BPF_STX | BPF_XADD | BPF_DW:
EMIT3(0xF0, add_2mod(0x48, dst_reg, src_reg), 0x01);
xadd: if (is_imm8(insn->off))
EMIT2(add_2reg(0x40, dst_reg, src_reg), insn->off);
else
EMIT1_off32(add_2reg(0x80, dst_reg, src_reg),
insn->off);
break;
/* call */
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_skb_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",
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_CALL | BPF_X:
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_JGE | BPF_X:
case BPF_JMP | BPF_JSGT | BPF_X:
case BPF_JMP | BPF_JSGE | BPF_X:
/* cmp dst_reg, src_reg */
EMIT3(add_2mod(0x48, dst_reg, src_reg), 0x39,
add_2reg(0xC0, dst_reg, src_reg));
goto emit_cond_jmp;
case BPF_JMP | BPF_JSET | BPF_X:
/* test dst_reg, src_reg */
EMIT3(add_2mod(0x48, dst_reg, src_reg), 0x85,
add_2reg(0xC0, dst_reg, src_reg));
goto emit_cond_jmp;
case BPF_JMP | BPF_JSET | BPF_K:
/* test dst_reg, imm32 */
EMIT1(add_1mod(0x48, dst_reg));
EMIT2_off32(0xF7, add_1reg(0xC0, dst_reg), imm32);
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_JGE | BPF_K:
case BPF_JMP | BPF_JSGT | BPF_K:
case BPF_JMP | BPF_JSGE | BPF_K:
/* cmp dst_reg, imm8/32 */
EMIT1(add_1mod(0x48, dst_reg));
if (is_imm8(imm32))
EMIT3(0x83, add_1reg(0xF8, dst_reg), imm32);
else
EMIT2_off32(0x81, add_1reg(0xF8, dst_reg), imm32);
emit_cond_jmp: /* convert BPF opcode to x86 */
switch (BPF_OP(insn->code)) {
case BPF_JEQ:
jmp_cond = X86_JE;
break;
case BPF_JSET:
case BPF_JNE:
jmp_cond = X86_JNE;
break;
case BPF_JGT:
/* GT is unsigned '>', JA in x86 */
jmp_cond = X86_JA;
break;
case BPF_JGE:
/* GE is unsigned '>=', JAE in x86 */
jmp_cond = X86_JAE;
break;
case BPF_JSGT:
/* signed '>', GT in x86 */
jmp_cond = X86_JG;
break;
case BPF_JSGE:
/* signed '>=', GE in x86 */
jmp_cond = X86_JGE;
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:
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;
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
*/
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 */
ctx->cleanup_addr = proglen;
/* mov rbx, qword ptr [rbp-X] */
EMIT3_off32(0x48, 0x8B, 0x9D, -STACKSIZE);
/* mov r13, qword ptr [rbp-X] */
EMIT3_off32(0x4C, 0x8B, 0xAD, -STACKSIZE + 8);
/* mov r14, qword ptr [rbp-X] */
EMIT3_off32(0x4C, 0x8B, 0xB5, -STACKSIZE + 16);
/* mov r15, qword ptr [rbp-X] */
EMIT3_off32(0x4C, 0x8B, 0xBD, -STACKSIZE + 24);
EMIT1(0xC9); /* leave */
EMIT1(0xC3); /* ret */
break;
default:
/* By design x64 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
*/
pr_err("bpf_jit: unknown opcode %02x\n", insn->code);
return -EINVAL;
}
ilen = prog - temp;
if (ilen > BPF_MAX_INSN_SIZE) {
pr_err("bpf_jit_compile fatal insn size error\n");
return -EFAULT;
}
if (image) {
if (unlikely(proglen + ilen > oldproglen)) {
pr_err("bpf_jit_compile fatal error\n");
return -EFAULT;
}
memcpy(image + proglen, temp, ilen);
}
proglen += ilen;
addrs[i] = proglen;
prog = temp;
}
return proglen;
}
static int do_jit(struct bpf_program *bpf_prog, int *addrs, u8 *image,
int oldproglen)
{
struct bpf_insn *insn = bpf_prog->insns;
int insn_cnt = bpf_prog->insn_cnt;
u8 temp[64];
int i;
int proglen = 0;
u8 *prog = temp;
int stacksize = 512;
EMIT1(0x55); /* push rbp */
EMIT3(0x48, 0x89, 0xE5); /* mov rbp,rsp */
/* sub rsp, stacksize */
EMIT3_off32(0x48, 0x81, 0xEC, stacksize);
/* mov qword ptr [rbp-X],rbx */
EMIT3_off32(0x48, 0x89, 0x9D, -stacksize);
/* mov qword ptr [rbp-X],r13 */
EMIT3_off32(0x4C, 0x89, 0xAD, -stacksize + 8);
/* mov qword ptr [rbp-X],r14 */
EMIT3_off32(0x4C, 0x89, 0xB5, -stacksize + 16);
/* mov qword ptr [rbp-X],r15 */
EMIT3_off32(0x4C, 0x89, 0xBD, -stacksize + 24);
for (i = 0; i < insn_cnt; i++, insn++) {
const __s32 K = insn->imm;
__u32 a_reg = insn->a_reg;
__u32 x_reg = insn->x_reg;
u8 b1 = 0, b2 = 0, b3 = 0;
u8 jmp_cond;
__s64 jmp_offset;
int ilen;
u8 *func;
switch (insn->code) {
/* ALU */
case BPF_ALU | BPF_ADD | BPF_X:
case BPF_ALU | BPF_SUB | BPF_X:
case BPF_ALU | BPF_AND | BPF_X:
case BPF_ALU | BPF_OR | BPF_X:
case BPF_ALU | BPF_XOR | BPF_X:
b1 = 0x48;
b3 = 0xC0;
switch (BPF_OP(insn->code)) {
case BPF_ADD: b2 = 0x01; break;
case BPF_SUB: b2 = 0x29; break;
case BPF_AND: b2 = 0x21; break;
case BPF_OR: b2 = 0x09; break;
case BPF_XOR: b2 = 0x31; break;
}
EMIT3(add_2mod(b1, a_reg, x_reg), b2,
add_2reg(b3, a_reg, x_reg));
break;
/* mov A, X */
case BPF_ALU | BPF_MOV | BPF_X:
EMIT_mov(a_reg, x_reg);
break;
/* neg A */
case BPF_ALU | BPF_NEG | BPF_X:
EMIT3(add_1mod(0x48, a_reg), 0xF7,
add_1reg(0xD8, a_reg));
break;
case BPF_ALU | BPF_ADD | BPF_K:
case BPF_ALU | BPF_SUB | BPF_K:
case BPF_ALU | BPF_AND | BPF_K:
case BPF_ALU | BPF_OR | BPF_K:
b1 = add_1mod(0x48, a_reg);
switch (BPF_OP(insn->code)) {
case BPF_ADD: b3 = 0xC0; break;
case BPF_SUB: b3 = 0xE8; break;
case BPF_AND: b3 = 0xE0; break;
case BPF_OR: b3 = 0xC8; break;
}
if (is_imm8(K))
EMIT4(b1, 0x83, add_1reg(b3, a_reg), K);
else
EMIT3_off32(b1, 0x81, add_1reg(b3, a_reg), K);
break;
case BPF_ALU | BPF_MOV | BPF_K:
/* 'mov rax, imm32' sign extends imm32.
* possible optimization: if imm32 is positive,
* use 'mov eax, imm32' (which zero-extends imm32)
* to save 2 bytes */
b1 = add_1mod(0x48, a_reg);
b2 = 0xC7;
b3 = 0xC0;
EMIT3_off32(b1, b2, add_1reg(b3, a_reg), K);
break;
/* A %= X
* A /= X */
case BPF_ALU | BPF_MOD | BPF_X:
case BPF_ALU | BPF_DIV | BPF_X:
EMIT1(0x50); /* push rax */
EMIT1(0x52); /* push rdx */
/* mov r9, X */
EMIT_mov(AUX_REG, x_reg);
/* mov rax, A */
EMIT_mov(R0, a_reg);
/* xor rdx, rdx */
EMIT3(0x48, 0x31, 0xd2);
/* if X==0, skip divide, make A=0 */
/* cmp r9, 0 */
EMIT4(0x49, 0x83, 0xF9, 0x00);
/* je .+3 */
EMIT2(X86_JE, 3);
/* div r9 */
EMIT3(0x49, 0xF7, 0xF1);
if (BPF_OP(insn->code) == BPF_MOD) {
/* mov r9, rdx */
EMIT3(0x49, 0x89, 0xD1);
} else {
/* mov r9, rax */
EMIT3(0x49, 0x89, 0xC1);
}
EMIT1(0x5A); /* pop rdx */
EMIT1(0x58); /* pop rax */
/* mov A, r9 */
EMIT_mov(a_reg, AUX_REG);
break;
/* shifts */
case BPF_ALU | BPF_LSH | BPF_K:
case BPF_ALU | BPF_RSH | BPF_K:
case BPF_ALU | BPF_ARSH | BPF_K:
b1 = add_1mod(0x48, a_reg);
switch (BPF_OP(insn->code)) {
case BPF_LSH: b3 = 0xE0; break;
case BPF_RSH: b3 = 0xE8; break;
case BPF_ARSH: b3 = 0xF8; break;
}
EMIT4(b1, 0xC1, add_1reg(b3, a_reg), K);
break;
case BPF_ALU | BPF_BSWAP32 | BPF_X:
/* emit 'bswap eax' to swap lower 4-bytes */
if (is_ereg(a_reg))
EMIT2(0x41, 0x0F);
else
EMIT1(0x0F);
EMIT1(add_1reg(0xC8, a_reg));
break;
case BPF_ALU | BPF_BSWAP64 | BPF_X:
/* emit 'bswap rax' to swap 8-bytes */
EMIT3(add_1mod(0x48, a_reg), 0x0F,
add_1reg(0xC8, a_reg));
break;
/* ST: *(u8*)(a_reg + off) = imm */
case BPF_ST | BPF_REL | BPF_B:
if (is_ereg(a_reg))
EMIT2(0x41, 0xC6);
else
EMIT1(0xC6);
goto st;
case BPF_ST | BPF_REL | BPF_H:
if (is_ereg(a_reg))
EMIT3(0x66, 0x41, 0xC7);
else
EMIT2(0x66, 0xC7);
goto st;
case BPF_ST | BPF_REL | BPF_W:
if (is_ereg(a_reg))
EMIT2(0x41, 0xC7);
else
EMIT1(0xC7);
goto st;
case BPF_ST | BPF_REL | BPF_DW:
EMIT2(add_1mod(0x48, a_reg), 0xC7);
st: if (is_imm8(insn->off))
EMIT2(add_1reg(0x40, a_reg), insn->off);
else
EMIT1_off32(add_1reg(0x80, a_reg), insn->off);
EMIT(K, bpf_size_to_x86_bytes(BPF_SIZE(insn->code)));
break;
/* STX: *(u8*)(a_reg + off) = x_reg */
case BPF_STX | BPF_REL | BPF_B:
/* emit 'mov byte ptr [rax + off], al' */
if (is_ereg(a_reg) || is_ereg(x_reg) ||
/* have to add extra byte for x86 SIL, DIL regs */
x_reg == R1 || x_reg == R2)
EMIT2(add_2mod(0x40, a_reg, x_reg), 0x88);
else
EMIT1(0x88);
goto stx;
case BPF_STX | BPF_REL | BPF_H:
if (is_ereg(a_reg) || is_ereg(x_reg))
EMIT3(0x66, add_2mod(0x40, a_reg, x_reg), 0x89);
else
EMIT2(0x66, 0x89);
goto stx;
case BPF_STX | BPF_REL | BPF_W:
if (is_ereg(a_reg) || is_ereg(x_reg))
EMIT2(add_2mod(0x40, a_reg, x_reg), 0x89);
else
EMIT1(0x89);
goto stx;
case BPF_STX | BPF_REL | BPF_DW:
EMIT2(add_2mod(0x48, a_reg, x_reg), 0x89);
stx: if (is_imm8(insn->off))
EMIT2(add_2reg(0x40, a_reg, x_reg), insn->off);
else
EMIT1_off32(add_2reg(0x80, a_reg, x_reg),
insn->off);
break;
/* LDX: a_reg = *(u8*)(x_reg + off) */
case BPF_LDX | BPF_REL | BPF_B:
/* emit 'movzx rax, byte ptr [rax + off]' */
EMIT3(add_2mod(0x48, x_reg, a_reg), 0x0F, 0xB6);
goto ldx;
case BPF_LDX | BPF_REL | BPF_H:
/* emit 'movzx rax, word ptr [rax + off]' */
EMIT3(add_2mod(0x48, x_reg, a_reg), 0x0F, 0xB7);
goto ldx;
case BPF_LDX | BPF_REL | BPF_W:
/* emit 'mov eax, dword ptr [rax+0x14]' */
if (is_ereg(a_reg) || is_ereg(x_reg))
EMIT2(add_2mod(0x40, x_reg, a_reg), 0x8B);
else
EMIT1(0x8B);
goto ldx;
case BPF_LDX | BPF_REL | BPF_DW:
/* emit 'mov rax, qword ptr [rax+0x14]' */
EMIT2(add_2mod(0x48, x_reg, a_reg), 0x8B);
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 pain */
if (is_imm8(insn->off))
EMIT2(add_2reg(0x40, x_reg, a_reg), insn->off);
else
EMIT1_off32(add_2reg(0x80, x_reg, a_reg),
insn->off);
break;
/* STX XADD: lock *(u8*)(a_reg + off) += x_reg */
case BPF_STX | BPF_XADD | BPF_B:
/* emit 'lock add byte ptr [rax + off], al' */
if (is_ereg(a_reg) || is_ereg(x_reg) ||
/* have to add extra byte for x86 SIL, DIL regs */
x_reg == R1 || x_reg == R2)
EMIT3(0xF0, add_2mod(0x40, a_reg, x_reg), 0x00);
else
EMIT2(0xF0, 0x00);
goto xadd;
case BPF_STX | BPF_XADD | BPF_H:
if (is_ereg(a_reg) || is_ereg(x_reg))
EMIT4(0x66, 0xF0, add_2mod(0x40, a_reg, x_reg),
0x01);
else
EMIT3(0x66, 0xF0, 0x01);
goto xadd;
case BPF_STX | BPF_XADD | BPF_W:
if (is_ereg(a_reg) || is_ereg(x_reg))
EMIT3(0xF0, add_2mod(0x40, a_reg, x_reg), 0x01);
else
EMIT2(0xF0, 0x01);
goto xadd;
case BPF_STX | BPF_XADD | BPF_DW:
EMIT3(0xF0, add_2mod(0x48, a_reg, x_reg), 0x01);
xadd: if (is_imm8(insn->off))
EMIT2(add_2reg(0x40, a_reg, x_reg), insn->off);
else
EMIT1_off32(add_2reg(0x80, a_reg, x_reg),
insn->off);
break;
/* call */
case BPF_JMP | BPF_CALL:
func = select_bpf_func(bpf_prog, K);
jmp_offset = func - (image + addrs[i]);
if (!func || !is_simm32(jmp_offset)) {
pr_err("unsupported bpf func %d addr %p image %p\n",
K, func, image);
return -EINVAL;
}
EMIT1_off32(0xE8, jmp_offset);
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_JGE | BPF_X:
case BPF_JMP | BPF_JSGT | BPF_X:
case BPF_JMP | BPF_JSGE | BPF_X:
/* emit 'cmp a_reg, x_reg' insn */
b1 = 0x48;
b2 = 0x39;
b3 = 0xC0;
EMIT3(add_2mod(b1, a_reg, x_reg), b2,
add_2reg(b3, a_reg, x_reg));
goto emit_jump;
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_JGE | BPF_K:
case BPF_JMP | BPF_JSGT | BPF_K:
case BPF_JMP | BPF_JSGE | BPF_K:
/* emit 'cmp a_reg, imm8/32' */
EMIT1(add_1mod(0x48, a_reg));
if (is_imm8(K))
EMIT3(0x83, add_1reg(0xF8, a_reg), K);
else
EMIT2_off32(0x81, add_1reg(0xF8, a_reg), K);
emit_jump: /* convert BPF opcode to x86 */
switch (BPF_OP(insn->code)) {
case BPF_JEQ:
jmp_cond = X86_JE;
break;
case BPF_JNE:
jmp_cond = X86_JNE;
break;
case BPF_JGT:
/* GT is unsigned '>', JA in x86 */
jmp_cond = X86_JA;
break;
case BPF_JGE:
/* GE is unsigned '>=', JAE in x86 */
jmp_cond = X86_JAE;
break;
case BPF_JSGT:
/* signed '>', GT in x86 */
jmp_cond = X86_JG;
break;
case BPF_JSGE:
/* signed '>=', GE in x86 */
jmp_cond = X86_JGE;
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 | BPF_X:
jmp_offset = addrs[i + insn->off] - addrs[i];
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;
case BPF_RET | BPF_K:
/* mov rbx, qword ptr [rbp-X] */
EMIT3_off32(0x48, 0x8B, 0x9D, -stacksize);
/* mov r13, qword ptr [rbp-X] */
EMIT3_off32(0x4C, 0x8B, 0xAD, -stacksize + 8);
/* mov r14, qword ptr [rbp-X] */
EMIT3_off32(0x4C, 0x8B, 0xB5, -stacksize + 16);
/* mov r15, qword ptr [rbp-X] */
EMIT3_off32(0x4C, 0x8B, 0xBD, -stacksize + 24);
EMIT1(0xC9); /* leave */
EMIT1(0xC3); /* ret */
break;
default:
/*pr_debug_bpf_insn(insn, NULL);*/
pr_err("bpf_jit: unknown opcode %02x\n", insn->code);
return -EINVAL;
}
ilen = prog - temp;
if (image) {
if (proglen + ilen > oldproglen)
return -2;
memcpy(image + proglen, temp, ilen);
}
proglen += ilen;
addrs[i] = proglen;
prog = temp;
}
return proglen;
}
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,
bpf_prog_was_classic(bpf_prog));
for (i = 0; i < insn_cnt; i++, insn++) {
const s32 imm32 = insn->imm;
u32 dst_reg = insn->dst_reg;
u32 src_reg = insn->src_reg;
u8 b2 = 0, b3 = 0;
s64 jmp_offset;
u8 jmp_cond;
int ilen;
u8 *func;
switch (insn->code) {
/* ALU */
case BPF_ALU | BPF_ADD | BPF_X:
case BPF_ALU | BPF_SUB | BPF_X:
case BPF_ALU | BPF_AND | BPF_X:
case BPF_ALU | BPF_OR | BPF_X:
case BPF_ALU | BPF_XOR | BPF_X:
case BPF_ALU64 | BPF_ADD | BPF_X:
case BPF_ALU64 | BPF_SUB | BPF_X:
case BPF_ALU64 | BPF_AND | BPF_X:
case BPF_ALU64 | BPF_OR | BPF_X:
case BPF_ALU64 | BPF_XOR | BPF_X:
switch (BPF_OP(insn->code)) {
case BPF_ADD: b2 = 0x01; break;
case BPF_SUB: b2 = 0x29; break;
case BPF_AND: b2 = 0x21; break;
case BPF_OR: b2 = 0x09; break;
case BPF_XOR: b2 = 0x31; break;
}
if (BPF_CLASS(insn->code) == BPF_ALU64)
EMIT1(add_2mod(0x48, dst_reg, src_reg));
else if (is_ereg(dst_reg) || is_ereg(src_reg))
EMIT1(add_2mod(0x40, dst_reg, src_reg));
EMIT2(b2, add_2reg(0xC0, dst_reg, src_reg));
break;
case BPF_ALU64 | BPF_MOV | BPF_X:
case BPF_ALU | BPF_MOV | BPF_X:
emit_mov_reg(&prog,
BPF_CLASS(insn->code) == BPF_ALU64,
dst_reg, src_reg);
break;
/* neg dst */
case BPF_ALU | BPF_NEG:
case BPF_ALU64 | BPF_NEG:
if (BPF_CLASS(insn->code) == BPF_ALU64)
EMIT1(add_1mod(0x48, dst_reg));
else if (is_ereg(dst_reg))
EMIT1(add_1mod(0x40, dst_reg));
EMIT2(0xF7, add_1reg(0xD8, dst_reg));
break;
case BPF_ALU | BPF_ADD | BPF_K:
case BPF_ALU | BPF_SUB | BPF_K:
case BPF_ALU | BPF_AND | BPF_K:
case BPF_ALU | BPF_OR | BPF_K:
case BPF_ALU | BPF_XOR | BPF_K:
case BPF_ALU64 | BPF_ADD | BPF_K:
case BPF_ALU64 | BPF_SUB | BPF_K:
case BPF_ALU64 | BPF_AND | BPF_K:
case BPF_ALU64 | BPF_OR | BPF_K:
case BPF_ALU64 | BPF_XOR | BPF_K:
if (BPF_CLASS(insn->code) == BPF_ALU64)
EMIT1(add_1mod(0x48, dst_reg));
else if (is_ereg(dst_reg))
EMIT1(add_1mod(0x40, dst_reg));
/*
* b3 holds 'normal' opcode, b2 short form only valid
* in case dst is eax/rax.
*/
switch (BPF_OP(insn->code)) {
case BPF_ADD:
b3 = 0xC0;
b2 = 0x05;
break;
case BPF_SUB:
b3 = 0xE8;
b2 = 0x2D;
break;
case BPF_AND:
b3 = 0xE0;
b2 = 0x25;
break;
case BPF_OR:
b3 = 0xC8;
b2 = 0x0D;
break;
case BPF_XOR:
b3 = 0xF0;
b2 = 0x35;
break;
}
if (is_imm8(imm32))
EMIT3(0x83, add_1reg(b3, dst_reg), imm32);
else if (is_axreg(dst_reg))
EMIT1_off32(b2, imm32);
else
EMIT2_off32(0x81, add_1reg(b3, dst_reg), imm32);
break;
case BPF_ALU64 | BPF_MOV | BPF_K:
case BPF_ALU | BPF_MOV | BPF_K:
emit_mov_imm32(&prog, BPF_CLASS(insn->code) == BPF_ALU64,
dst_reg, imm32);
break;
case BPF_LD | BPF_IMM | BPF_DW:
emit_mov_imm64(&prog, dst_reg, insn[1].imm, insn[0].imm);
insn++;
i++;
break;
/* dst %= src, dst /= src, dst %= imm32, dst /= imm32 */
case BPF_ALU | BPF_MOD | BPF_X:
case BPF_ALU | BPF_DIV | BPF_X:
case BPF_ALU | BPF_MOD | BPF_K:
case BPF_ALU | BPF_DIV | BPF_K:
case BPF_ALU64 | BPF_MOD | BPF_X:
case BPF_ALU64 | BPF_DIV | BPF_X:
case BPF_ALU64 | BPF_MOD | BPF_K:
case BPF_ALU64 | BPF_DIV | BPF_K:
EMIT1(0x50); /* push rax */
EMIT1(0x52); /* push rdx */
if (BPF_SRC(insn->code) == BPF_X)
/* mov r11, src_reg */
EMIT_mov(AUX_REG, src_reg);
else
/* mov r11, imm32 */
EMIT3_off32(0x49, 0xC7, 0xC3, imm32);
/* mov rax, dst_reg */
EMIT_mov(BPF_REG_0, dst_reg);
/*
* xor edx, edx
* equivalent to 'xor rdx, rdx', but one byte less
*/
EMIT2(0x31, 0xd2);
if (BPF_CLASS(insn->code) == BPF_ALU64)
/* div r11 */
EMIT3(0x49, 0xF7, 0xF3);
else
/* div r11d */
EMIT3(0x41, 0xF7, 0xF3);
if (BPF_OP(insn->code) == BPF_MOD)
/* mov r11, rdx */
EMIT3(0x49, 0x89, 0xD3);
else
/* mov r11, rax */
EMIT3(0x49, 0x89, 0xC3);
EMIT1(0x5A); /* pop rdx */
EMIT1(0x58); /* pop rax */
/* mov dst_reg, r11 */
EMIT_mov(dst_reg, AUX_REG);
break;
case BPF_ALU | BPF_MUL | BPF_K:
case BPF_ALU | BPF_MUL | BPF_X:
case BPF_ALU64 | BPF_MUL | BPF_K:
case BPF_ALU64 | BPF_MUL | BPF_X:
{
bool is64 = BPF_CLASS(insn->code) == BPF_ALU64;
if (dst_reg != BPF_REG_0)
EMIT1(0x50); /* push rax */
if (dst_reg != BPF_REG_3)
EMIT1(0x52); /* push rdx */
/* mov r11, dst_reg */
EMIT_mov(AUX_REG, dst_reg);
if (BPF_SRC(insn->code) == BPF_X)
emit_mov_reg(&prog, is64, BPF_REG_0, src_reg);
else
emit_mov_imm32(&prog, is64, BPF_REG_0, imm32);
if (is64)
EMIT1(add_1mod(0x48, AUX_REG));
else if (is_ereg(AUX_REG))
EMIT1(add_1mod(0x40, AUX_REG));
/* mul(q) r11 */
EMIT2(0xF7, add_1reg(0xE0, AUX_REG));
if (dst_reg != BPF_REG_3)
EMIT1(0x5A); /* pop rdx */
if (dst_reg != BPF_REG_0) {
/* mov dst_reg, rax */
EMIT_mov(dst_reg, BPF_REG_0);
EMIT1(0x58); /* pop rax */
}
break;
}
/* Shifts */
case BPF_ALU | BPF_LSH | BPF_K:
case BPF_ALU | BPF_RSH | BPF_K:
case BPF_ALU | BPF_ARSH | BPF_K:
case BPF_ALU64 | BPF_LSH | BPF_K:
case BPF_ALU64 | BPF_RSH | BPF_K:
case BPF_ALU64 | BPF_ARSH | BPF_K:
if (BPF_CLASS(insn->code) == BPF_ALU64)
EMIT1(add_1mod(0x48, dst_reg));
else if (is_ereg(dst_reg))
EMIT1(add_1mod(0x40, dst_reg));
switch (BPF_OP(insn->code)) {
case BPF_LSH: b3 = 0xE0; break;
case BPF_RSH: b3 = 0xE8; break;
case BPF_ARSH: b3 = 0xF8; break;
}
if (imm32 == 1)
EMIT2(0xD1, add_1reg(b3, dst_reg));
else
EMIT3(0xC1, add_1reg(b3, dst_reg), imm32);
break;
case BPF_ALU | BPF_LSH | BPF_X:
case BPF_ALU | BPF_RSH | BPF_X:
case BPF_ALU | BPF_ARSH | BPF_X:
case BPF_ALU64 | BPF_LSH | BPF_X:
case BPF_ALU64 | BPF_RSH | BPF_X:
case BPF_ALU64 | BPF_ARSH | BPF_X:
/* Check for bad case when dst_reg == rcx */
if (dst_reg == BPF_REG_4) {
/* mov r11, dst_reg */
EMIT_mov(AUX_REG, dst_reg);
dst_reg = AUX_REG;
}
if (src_reg != BPF_REG_4) { /* common case */
EMIT1(0x51); /* push rcx */
/* mov rcx, src_reg */
EMIT_mov(BPF_REG_4, src_reg);
}
/* shl %rax, %cl | shr %rax, %cl | sar %rax, %cl */
if (BPF_CLASS(insn->code) == BPF_ALU64)
EMIT1(add_1mod(0x48, dst_reg));
else if (is_ereg(dst_reg))
EMIT1(add_1mod(0x40, dst_reg));
switch (BPF_OP(insn->code)) {
case BPF_LSH: b3 = 0xE0; break;
case BPF_RSH: b3 = 0xE8; break;
case BPF_ARSH: b3 = 0xF8; break;
}
EMIT2(0xD3, add_1reg(b3, dst_reg));
if (src_reg != BPF_REG_4)
EMIT1(0x59); /* pop rcx */
if (insn->dst_reg == BPF_REG_4)
/* mov dst_reg, r11 */
EMIT_mov(insn->dst_reg, AUX_REG);
break;
case BPF_ALU | BPF_END | BPF_FROM_BE:
switch (imm32) {
case 16:
/* 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' */
if (is_ereg(dst_reg))
EMIT3(0x45, 0x0F, 0xB7);
else
EMIT2(0x0F, 0xB7);
EMIT1(add_2reg(0xC0, dst_reg, dst_reg));
break;
case 32:
/* Emit 'bswap eax' to swap lower 4 bytes */
if (is_ereg(dst_reg))
EMIT2(0x41, 0x0F);
else
EMIT1(0x0F);
EMIT1(add_1reg(0xC8, dst_reg));
break;
case 64:
/* Emit 'bswap rax' to swap 8 bytes */
EMIT3(add_1mod(0x48, dst_reg), 0x0F,
add_1reg(0xC8, dst_reg));
break;
}
break;
case BPF_ALU | BPF_END | BPF_FROM_LE:
switch (imm32) {
case 16:
/*
* Emit 'movzwl eax, ax' to zero extend 16-bit
* into 64 bit
*/
if (is_ereg(dst_reg))
EMIT3(0x45, 0x0F, 0xB7);
else
EMIT2(0x0F, 0xB7);
EMIT1(add_2reg(0xC0, dst_reg, dst_reg));
break;
case 32:
/* 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));
break;
case 64:
/* nop */
break;
}
break;
/* ST: *(u8*)(dst_reg + off) = imm */
case BPF_ST | BPF_MEM | BPF_B:
if (is_ereg(dst_reg))
EMIT2(0x41, 0xC6);
else
EMIT1(0xC6);
goto st;
case BPF_ST | BPF_MEM | BPF_H:
if (is_ereg(dst_reg))
EMIT3(0x66, 0x41, 0xC7);
else
EMIT2(0x66, 0xC7);
goto st;
case BPF_ST | BPF_MEM | BPF_W:
if (is_ereg(dst_reg))
EMIT2(0x41, 0xC7);
else
EMIT1(0xC7);
goto st;
case BPF_ST | BPF_MEM | BPF_DW:
EMIT2(add_1mod(0x48, dst_reg), 0xC7);
st: if (is_imm8(insn->off))
EMIT2(add_1reg(0x40, dst_reg), insn->off);
else
EMIT1_off32(add_1reg(0x80, dst_reg), insn->off);
EMIT(imm32, bpf_size_to_x86_bytes(BPF_SIZE(insn->code)));
break;
/* STX: *(u8*)(dst_reg + off) = src_reg */
case BPF_STX | BPF_MEM | BPF_B:
/* Emit 'mov byte ptr [rax + off], al' */
if (is_ereg(dst_reg) || is_ereg(src_reg) ||
/* 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
EMIT1(0x88);
goto stx;
case BPF_STX | BPF_MEM | BPF_H:
if (is_ereg(dst_reg) || is_ereg(src_reg))
EMIT3(0x66, add_2mod(0x40, dst_reg, src_reg), 0x89);
else
EMIT2(0x66, 0x89);
goto stx;
case BPF_STX | BPF_MEM | BPF_W:
if (is_ereg(dst_reg) || is_ereg(src_reg))
EMIT2(add_2mod(0x40, dst_reg, src_reg), 0x89);
else
EMIT1(0x89);
goto stx;
case BPF_STX | BPF_MEM | BPF_DW:
EMIT2(add_2mod(0x48, dst_reg, src_reg), 0x89);
stx: if (is_imm8(insn->off))
EMIT2(add_2reg(0x40, dst_reg, src_reg), insn->off);
else
EMIT1_off32(add_2reg(0x80, dst_reg, src_reg),
insn->off);
break;
/* LDX: dst_reg = *(u8*)(src_reg + off) */
case BPF_LDX | BPF_MEM | BPF_B:
/* 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]' */
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]' */
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]' */
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
* is not worth the hassle
*/
if (is_imm8(insn->off))
EMIT2(add_2reg(0x40, src_reg, dst_reg), insn->off);
else
EMIT1_off32(add_2reg(0x80, src_reg, dst_reg),
insn->off);
break;
/* STX XADD: lock *(u32*)(dst_reg + off) += src_reg */
case BPF_STX | BPF_XADD | BPF_W:
/* 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
EMIT2(0xF0, 0x01);
goto xadd;
case BPF_STX | BPF_XADD | BPF_DW:
EMIT3(0xF0, add_2mod(0x48, dst_reg, src_reg), 0x01);
xadd: if (is_imm8(insn->off))
EMIT2(add_2reg(0x40, dst_reg, src_reg), insn->off);
else
EMIT1_off32(add_2reg(0x80, dst_reg, src_reg),
insn->off);
break;
/* call */
case BPF_JMP | BPF_CALL:
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;
}
EMIT1_off32(0xE8, jmp_offset);
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_JSLT | BPF_X:
case BPF_JMP | BPF_JSGE | BPF_X:
case BPF_JMP | BPF_JSLE | BPF_X:
/* cmp dst_reg, src_reg */
EMIT3(add_2mod(0x48, dst_reg, src_reg), 0x39,
add_2reg(0xC0, dst_reg, src_reg));
goto emit_cond_jmp;
case BPF_JMP | BPF_JSET | BPF_X:
/* test dst_reg, src_reg */
EMIT3(add_2mod(0x48, dst_reg, src_reg), 0x85,
add_2reg(0xC0, dst_reg, src_reg));
goto emit_cond_jmp;
case BPF_JMP | BPF_JSET | BPF_K:
/* test dst_reg, imm32 */
EMIT1(add_1mod(0x48, dst_reg));
EMIT2_off32(0xF7, add_1reg(0xC0, dst_reg), imm32);
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_JSLT | BPF_K:
case BPF_JMP | BPF_JSGE | BPF_K:
case BPF_JMP | BPF_JSLE | BPF_K:
/* cmp dst_reg, imm8/32 */
EMIT1(add_1mod(0x48, dst_reg));
if (is_imm8(imm32))
EMIT3(0x83, add_1reg(0xF8, dst_reg), imm32);
else
EMIT2_off32(0x81, add_1reg(0xF8, dst_reg), imm32);
emit_cond_jmp: /* Convert BPF opcode to x86 */
switch (BPF_OP(insn->code)) {
case BPF_JEQ:
jmp_cond = X86_JE;
break;
case BPF_JSET:
case BPF_JNE:
jmp_cond = X86_JNE;
break;
case BPF_JGT:
/* GT is unsigned '>', JA in x86 */
jmp_cond = X86_JA;
break;
case BPF_JLT:
/* LT is unsigned '<', JB in x86 */
jmp_cond = X86_JB;
break;
case BPF_JGE:
/* GE is unsigned '>=', JAE in x86 */
jmp_cond = X86_JAE;
break;
case BPF_JLE:
/* LE is unsigned '<=', JBE in x86 */
jmp_cond = X86_JBE;
break;
case BPF_JSGT:
/* Signed '>', GT in x86 */
jmp_cond = X86_JG;
break;
case BPF_JSLT:
/* Signed '<', LT in x86 */
jmp_cond = X86_JL;
break;
case BPF_JSGE:
/* Signed '>=', GE in x86 */
jmp_cond = X86_JGE;
break;
case BPF_JSLE:
/* Signed '<=', LE in x86 */
jmp_cond = X86_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;
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;
/* mov rbx, qword ptr [rbp+0] */
EMIT4(0x48, 0x8B, 0x5D, 0);
/* mov r13, qword ptr [rbp+8] */
EMIT4(0x4C, 0x8B, 0x6D, 8);
/* mov r14, qword ptr [rbp+16] */
EMIT4(0x4C, 0x8B, 0x75, 16);
/* mov r15, qword ptr [rbp+24] */
EMIT4(0x4C, 0x8B, 0x7D, 24);
/* add rbp, AUX_STACK_SPACE */
EMIT4(0x48, 0x83, 0xC5, AUX_STACK_SPACE);
EMIT1(0xC9); /* leave */
EMIT1(0xC3); /* ret */
break;
default:
/*
* By design x86-64 JIT should support all BPF instructions.
* This error will be seen if new instruction was added
* 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;
}
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;
}