diff options
Diffstat (limited to 'arch/x86/net/bpf_jit_comp.c')
| -rw-r--r-- | arch/x86/net/bpf_jit_comp.c | 684 |
1 files changed, 526 insertions, 158 deletions
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 42b6709e6dc7..79e7a0ec1da5 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -205,6 +205,18 @@ static u8 add_2reg(u8 byte, u32 dst_reg, u32 src_reg) return byte + reg2hex[dst_reg] + (reg2hex[src_reg] << 3); } +/* Some 1-byte opcodes for binary ALU operations */ +static u8 simple_alu_opcodes[] = { + [BPF_ADD] = 0x01, + [BPF_SUB] = 0x29, + [BPF_AND] = 0x21, + [BPF_OR] = 0x09, + [BPF_XOR] = 0x31, + [BPF_LSH] = 0xE0, + [BPF_RSH] = 0xE8, + [BPF_ARSH] = 0xF8, +}; + static void jit_fill_hole(void *area, unsigned int size) { /* Fill whole space with INT3 instructions */ @@ -221,14 +233,48 @@ struct jit_context { /* Number of bytes emit_patch() needs to generate instructions */ #define X86_PATCH_SIZE 5 +/* Number of bytes that will be skipped on tailcall */ +#define X86_TAIL_CALL_OFFSET 11 + +static void push_callee_regs(u8 **pprog, bool *callee_regs_used) +{ + u8 *prog = *pprog; + int cnt = 0; + + if (callee_regs_used[0]) + EMIT1(0x53); /* push rbx */ + if (callee_regs_used[1]) + EMIT2(0x41, 0x55); /* push r13 */ + if (callee_regs_used[2]) + EMIT2(0x41, 0x56); /* push r14 */ + if (callee_regs_used[3]) + EMIT2(0x41, 0x57); /* push r15 */ + *pprog = prog; +} + +static void pop_callee_regs(u8 **pprog, bool *callee_regs_used) +{ + u8 *prog = *pprog; + int cnt = 0; -#define PROLOGUE_SIZE 25 + if (callee_regs_used[3]) + EMIT2(0x41, 0x5F); /* pop r15 */ + if (callee_regs_used[2]) + EMIT2(0x41, 0x5E); /* pop r14 */ + if (callee_regs_used[1]) + EMIT2(0x41, 0x5D); /* pop r13 */ + if (callee_regs_used[0]) + EMIT1(0x5B); /* pop rbx */ + *pprog = prog; +} /* - * Emit x86-64 prologue code for BPF program and check its size. - * bpf_tail_call helper will skip it while jumping into another program + * Emit x86-64 prologue code for BPF program. + * bpf_tail_call helper will skip the first X86_TAIL_CALL_OFFSET bytes + * while jumping to another program */ -static void emit_prologue(u8 **pprog, u32 stack_depth, bool ebpf_from_cbpf) +static void emit_prologue(u8 **pprog, u32 stack_depth, bool ebpf_from_cbpf, + bool tail_call_reachable, bool is_subprog) { u8 *prog = *pprog; int cnt = X86_PATCH_SIZE; @@ -238,19 +284,19 @@ static void emit_prologue(u8 **pprog, u32 stack_depth, bool ebpf_from_cbpf) */ memcpy(prog, ideal_nops[NOP_ATOMIC5], cnt); prog += cnt; + if (!ebpf_from_cbpf) { + if (tail_call_reachable && !is_subprog) + EMIT2(0x31, 0xC0); /* xor eax, eax */ + else + EMIT2(0x66, 0x90); /* nop2 */ + } EMIT1(0x55); /* push rbp */ EMIT3(0x48, 0x89, 0xE5); /* mov rbp, rsp */ /* sub rsp, rounded_stack_depth */ - EMIT3_off32(0x48, 0x81, 0xEC, round_up(stack_depth, 8)); - EMIT1(0x53); /* push rbx */ - EMIT2(0x41, 0x55); /* push r13 */ - EMIT2(0x41, 0x56); /* push r14 */ - EMIT2(0x41, 0x57); /* push r15 */ - if (!ebpf_from_cbpf) { - /* zero init tail_call_cnt */ - EMIT2(0x6a, 0x00); - BUILD_BUG_ON(cnt != PROLOGUE_SIZE); - } + if (stack_depth) + EMIT3_off32(0x48, 0x81, 0xEC, round_up(stack_depth, 8)); + if (tail_call_reachable) + EMIT1(0x50); /* push rax */ *pprog = prog; } @@ -314,13 +360,14 @@ static int __bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t, mutex_lock(&text_mutex); if (memcmp(ip, old_insn, X86_PATCH_SIZE)) goto out; + ret = 1; if (memcmp(ip, new_insn, X86_PATCH_SIZE)) { if (text_live) text_poke_bp(ip, new_insn, X86_PATCH_SIZE, NULL); else memcpy(ip, new_insn, X86_PATCH_SIZE); + ret = 0; } - ret = 0; out: mutex_unlock(&text_mutex); return ret; @@ -337,6 +384,22 @@ int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t, return __bpf_arch_text_poke(ip, t, old_addr, new_addr, true); } +static int get_pop_bytes(bool *callee_regs_used) +{ + int bytes = 0; + + if (callee_regs_used[3]) + bytes += 2; + if (callee_regs_used[2]) + bytes += 2; + if (callee_regs_used[1]) + bytes += 2; + if (callee_regs_used[0]) + bytes += 1; + + return bytes; +} + /* * Generate the following code: * @@ -351,12 +414,32 @@ int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t, * goto *(prog->bpf_func + prologue_size); * out: */ -static void emit_bpf_tail_call_indirect(u8 **pprog) +static void emit_bpf_tail_call_indirect(u8 **pprog, bool *callee_regs_used, + u32 stack_depth) { + int tcc_off = -4 - round_up(stack_depth, 8); u8 *prog = *pprog; - int label1, label2, label3; + int pop_bytes = 0; + int off1 = 42; + int off2 = 31; + int off3 = 9; int cnt = 0; + /* count the additional bytes used for popping callee regs from stack + * that need to be taken into account for each of the offsets that + * are used for bailing out of the tail call + */ + pop_bytes = get_pop_bytes(callee_regs_used); + off1 += pop_bytes; + off2 += pop_bytes; + off3 += pop_bytes; + + if (stack_depth) { + off1 += 7; + off2 += 7; + off3 += 7; + } + /* * rdi - pointer to ctx * rsi - pointer to bpf_array @@ -370,72 +453,112 @@ static void emit_bpf_tail_call_indirect(u8 **pprog) 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 (off1 + RETPOLINE_RCX_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; */ - EMIT2_off32(0x8B, 0x85, -36 - MAX_BPF_STACK); /* mov eax, dword ptr [rbp - 548] */ + EMIT2_off32(0x8B, 0x85, tcc_off); /* mov eax, dword ptr [rbp - tcc_off] */ EMIT3(0x83, 0xF8, MAX_TAIL_CALL_CNT); /* cmp eax, MAX_TAIL_CALL_CNT */ -#define OFFSET2 (30 + RETPOLINE_RAX_BPF_JIT_SIZE) +#define OFFSET2 (off2 + RETPOLINE_RCX_BPF_JIT_SIZE) EMIT2(X86_JA, OFFSET2); /* ja out */ - label2 = cnt; EMIT3(0x83, 0xC0, 0x01); /* add eax, 1 */ - EMIT2_off32(0x89, 0x85, -36 - MAX_BPF_STACK); /* mov dword ptr [rbp -548], eax */ + EMIT2_off32(0x89, 0x85, tcc_off); /* mov dword ptr [rbp - tcc_off], eax */ /* prog = array->ptrs[index]; */ - EMIT4_off32(0x48, 0x8B, 0x84, 0xD6, /* mov rax, [rsi + rdx * 8 + offsetof(...)] */ + EMIT4_off32(0x48, 0x8B, 0x8C, 0xD6, /* mov rcx, [rsi + rdx * 8 + offsetof(...)] */ offsetof(struct bpf_array, ptrs)); /* * if (prog == NULL) * goto out; */ - EMIT3(0x48, 0x85, 0xC0); /* test rax,rax */ -#define OFFSET3 (8 + RETPOLINE_RAX_BPF_JIT_SIZE) + EMIT3(0x48, 0x85, 0xC9); /* test rcx,rcx */ +#define OFFSET3 (off3 + RETPOLINE_RCX_BPF_JIT_SIZE) EMIT2(X86_JE, OFFSET3); /* je out */ - label3 = cnt; - /* goto *(prog->bpf_func + prologue_size); */ - EMIT4(0x48, 0x8B, 0x40, /* mov rax, qword ptr [rax + 32] */ - offsetof(struct bpf_prog, bpf_func)); - EMIT4(0x48, 0x83, 0xC0, PROLOGUE_SIZE); /* add rax, prologue_size */ + *pprog = prog; + pop_callee_regs(pprog, callee_regs_used); + prog = *pprog; + EMIT1(0x58); /* pop rax */ + if (stack_depth) + EMIT3_off32(0x48, 0x81, 0xC4, /* add rsp, sd */ + round_up(stack_depth, 8)); + + /* goto *(prog->bpf_func + X86_TAIL_CALL_OFFSET); */ + EMIT4(0x48, 0x8B, 0x49, /* mov rcx, qword ptr [rcx + 32] */ + offsetof(struct bpf_prog, bpf_func)); + EMIT4(0x48, 0x83, 0xC1, /* add rcx, X86_TAIL_CALL_OFFSET */ + X86_TAIL_CALL_OFFSET); /* - * Wow we're ready to jump into next BPF program + * Now we're ready to jump into next BPF program * rdi == ctx (1st arg) - * rax == prog->bpf_func + prologue_size + * rcx == prog->bpf_func + X86_TAIL_CALL_OFFSET */ - RETPOLINE_RAX_BPF_JIT(); + RETPOLINE_RCX_BPF_JIT(); /* out: */ - BUILD_BUG_ON(cnt - label1 != OFFSET1); - BUILD_BUG_ON(cnt - label2 != OFFSET2); - BUILD_BUG_ON(cnt - label3 != OFFSET3); *pprog = prog; } static void emit_bpf_tail_call_direct(struct bpf_jit_poke_descriptor *poke, - u8 **pprog, int addr, u8 *image) + u8 **pprog, int addr, u8 *image, + bool *callee_regs_used, u32 stack_depth) { + int tcc_off = -4 - round_up(stack_depth, 8); u8 *prog = *pprog; + int pop_bytes = 0; + int off1 = 20; + int poke_off; int cnt = 0; + /* count the additional bytes used for popping callee regs to stack + * that need to be taken into account for jump offset that is used for + * bailing out from of the tail call when limit is reached + */ + pop_bytes = get_pop_bytes(callee_regs_used); + off1 += pop_bytes; + + /* + * total bytes for: + * - nop5/ jmpq $off + * - pop callee regs + * - sub rsp, $val if depth > 0 + * - pop rax + */ + poke_off = X86_PATCH_SIZE + pop_bytes + 1; + if (stack_depth) { + poke_off += 7; + off1 += 7; + } + /* * if (tail_call_cnt > MAX_TAIL_CALL_CNT) * goto out; */ - EMIT2_off32(0x8B, 0x85, -36 - MAX_BPF_STACK); /* mov eax, dword ptr [rbp - 548] */ + EMIT2_off32(0x8B, 0x85, tcc_off); /* mov eax, dword ptr [rbp - tcc_off] */ EMIT3(0x83, 0xF8, MAX_TAIL_CALL_CNT); /* cmp eax, MAX_TAIL_CALL_CNT */ - EMIT2(X86_JA, 14); /* ja out */ + EMIT2(X86_JA, off1); /* ja out */ EMIT3(0x83, 0xC0, 0x01); /* add eax, 1 */ - EMIT2_off32(0x89, 0x85, -36 - MAX_BPF_STACK); /* mov dword ptr [rbp -548], eax */ + EMIT2_off32(0x89, 0x85, tcc_off); /* mov dword ptr [rbp - tcc_off], eax */ + + poke->tailcall_bypass = image + (addr - poke_off - X86_PATCH_SIZE); + poke->adj_off = X86_TAIL_CALL_OFFSET; + poke->tailcall_target = image + (addr - X86_PATCH_SIZE); + poke->bypass_addr = (u8 *)poke->tailcall_target + X86_PATCH_SIZE; + + emit_jump(&prog, (u8 *)poke->tailcall_target + X86_PATCH_SIZE, + poke->tailcall_bypass); - poke->ip = image + (addr - X86_PATCH_SIZE); - poke->adj_off = PROLOGUE_SIZE; + *pprog = prog; + pop_callee_regs(pprog, callee_regs_used); + prog = *pprog; + EMIT1(0x58); /* pop rax */ + if (stack_depth) + EMIT3_off32(0x48, 0x81, 0xC4, round_up(stack_depth, 8)); memcpy(prog, ideal_nops[NOP_ATOMIC5], X86_PATCH_SIZE); prog += X86_PATCH_SIZE; @@ -453,7 +576,7 @@ static void bpf_tail_call_direct_fixup(struct bpf_prog *prog) for (i = 0; i < prog->aux->size_poke_tab; i++) { poke = &prog->aux->poke_tab[i]; - WARN_ON_ONCE(READ_ONCE(poke->ip_stable)); + WARN_ON_ONCE(READ_ONCE(poke->tailcall_target_stable)); if (poke->reason != BPF_POKE_REASON_TAIL_CALL) continue; @@ -464,18 +587,25 @@ static void bpf_tail_call_direct_fixup(struct bpf_prog *prog) if (target) { /* Plain memcpy is used when image is not live yet * and still not locked as read-only. Once poke - * location is active (poke->ip_stable), any parallel - * bpf_arch_text_poke() might occur still on the - * read-write image until we finally locked it as - * read-only. Both modifications on the given image - * are under text_mutex to avoid interference. + * location is active (poke->tailcall_target_stable), + * any parallel bpf_arch_text_poke() might occur + * still on the read-write image until we finally + * locked it as read-only. Both modifications on + * the given image are under text_mutex to avoid + * interference. */ - ret = __bpf_arch_text_poke(poke->ip, BPF_MOD_JUMP, NULL, + ret = __bpf_arch_text_poke(poke->tailcall_target, + BPF_MOD_JUMP, NULL, (u8 *)target->bpf_func + poke->adj_off, false); BUG_ON(ret < 0); + ret = __bpf_arch_text_poke(poke->tailcall_bypass, + BPF_MOD_JUMP, + (u8 *)poke->tailcall_target + + X86_PATCH_SIZE, NULL, false); + BUG_ON(ret < 0); } - WRITE_ONCE(poke->ip_stable, true); + WRITE_ONCE(poke->tailcall_target_stable, true); mutex_unlock(&array->aux->poke_mutex); } } @@ -563,6 +693,42 @@ static void emit_mov_reg(u8 **pprog, bool is64, u32 dst_reg, u32 src_reg) *pprog = prog; } +/* Emit the suffix (ModR/M etc) for addressing *(ptr_reg + off) and val_reg */ +static void emit_insn_suffix(u8 **pprog, u32 ptr_reg, u32 val_reg, int off) +{ + u8 *prog = *pprog; + int cnt = 0; + + if (is_imm8(off)) { + /* 1-byte signed displacement. + * + * If off == 0 we could skip this and save one extra byte, but + * special case of x86 R13 which always needs an offset is not + * worth the hassle + */ + EMIT2(add_2reg(0x40, ptr_reg, val_reg), off); + } else { + /* 4-byte signed displacement */ + EMIT1_off32(add_2reg(0x80, ptr_reg, val_reg), off); + } + *pprog = prog; +} + +/* + * Emit a REX byte if it will be necessary to address these registers + */ +static void maybe_emit_mod(u8 **pprog, u32 dst_reg, u32 src_reg, bool is64) +{ + u8 *prog = *pprog; + int cnt = 0; + + if (is64) + 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)); + *pprog = prog; +} + /* LDX: dst_reg = *(u8*)(src_reg + off) */ static void emit_ldx(u8 **pprog, u32 size, u32 dst_reg, u32 src_reg, int off) { @@ -590,15 +756,7 @@ static void emit_ldx(u8 **pprog, u32 size, u32 dst_reg, u32 src_reg, int off) EMIT2(add_2mod(0x48, src_reg, dst_reg), 0x8B); break; } - /* - * 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(off)) - EMIT2(add_2reg(0x40, src_reg, dst_reg), off); - else - EMIT1_off32(add_2reg(0x80, src_reg, dst_reg), off); + emit_insn_suffix(&prog, src_reg, dst_reg, off); *pprog = prog; } @@ -633,13 +791,53 @@ static void emit_stx(u8 **pprog, u32 size, u32 dst_reg, u32 src_reg, int off) EMIT2(add_2mod(0x48, dst_reg, src_reg), 0x89); break; } - if (is_imm8(off)) - EMIT2(add_2reg(0x40, dst_reg, src_reg), off); - else - EMIT1_off32(add_2reg(0x80, dst_reg, src_reg), off); + emit_insn_suffix(&prog, dst_reg, src_reg, off); *pprog = prog; } +static int emit_atomic(u8 **pprog, u8 atomic_op, + u32 dst_reg, u32 src_reg, s16 off, u8 bpf_size) +{ + u8 *prog = *pprog; + int cnt = 0; + + EMIT1(0xF0); /* lock prefix */ + + maybe_emit_mod(&prog, dst_reg, src_reg, bpf_size == BPF_DW); + + /* emit opcode */ + switch (atomic_op) { + case BPF_ADD: + case BPF_SUB: + case BPF_AND: + case BPF_OR: + case BPF_XOR: + /* lock *(u32/u64*)(dst_reg + off) <op>= src_reg */ + EMIT1(simple_alu_opcodes[atomic_op]); + break; + case BPF_ADD | BPF_FETCH: + /* src_reg = atomic_fetch_add(dst_reg + off, src_reg); */ + EMIT2(0x0F, 0xC1); + break; + case BPF_XCHG: + /* src_reg = atomic_xchg(dst_reg + off, src_reg); */ + EMIT1(0x87); + break; + case BPF_CMPXCHG: + /* r0 = atomic_cmpxchg(dst_reg + off, r0, src_reg); */ + EMIT2(0x0F, 0xB1); + break; + default: + pr_err("bpf_jit: unknown atomic opcode %02x\n", atomic_op); + return -EFAULT; + } + + emit_insn_suffix(&prog, dst_reg, src_reg, off); + + *pprog = prog; + return 0; +} + static bool ex_handler_bpf(const struct exception_table_entry *x, struct pt_regs *regs, int trapnr, unsigned long error_code, unsigned long fault_addr) @@ -652,30 +850,91 @@ static bool ex_handler_bpf(const struct exception_table_entry *x, return true; } +static void detect_reg_usage(struct bpf_insn *insn, int insn_cnt, + bool *regs_used, bool *tail_call_seen) +{ + int i; + + for (i = 1; i <= insn_cnt; i++, insn++) { + if (insn->code == (BPF_JMP | BPF_TAIL_CALL)) + *tail_call_seen = true; + if (insn->dst_reg == BPF_REG_6 || insn->src_reg == BPF_REG_6) + regs_used[0] = true; + if (insn->dst_reg == BPF_REG_7 || insn->src_reg == BPF_REG_7) + regs_used[1] = true; + if (insn->dst_reg == BPF_REG_8 || insn->src_reg == BPF_REG_8) + regs_used[2] = true; + if (insn->dst_reg == BPF_REG_9 || insn->src_reg == BPF_REG_9) + regs_used[3] = true; + } +} + +static int emit_nops(u8 **pprog, int len) +{ + u8 *prog = *pprog; + int i, noplen, cnt = 0; + + while (len > 0) { + noplen = len; + + if (noplen > ASM_NOP_MAX) + noplen = ASM_NOP_MAX; + + for (i = 0; i < noplen; i++) + EMIT1(ideal_nops[noplen][i]); + len -= noplen; + } + + *pprog = prog; + + return cnt; +} + +#define INSN_SZ_DIFF (((addrs[i] - addrs[i - 1]) - (prog - temp))) + static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, - int oldproglen, struct jit_context *ctx) + int oldproglen, struct jit_context *ctx, bool jmp_padding) { + bool tail_call_reachable = bpf_prog->aux->tail_call_reachable; struct bpf_insn *insn = bpf_prog->insnsi; + bool callee_regs_used[4] = {}; int insn_cnt = bpf_prog->len; + bool tail_call_seen = false; bool seen_exit = false; u8 temp[BPF_MAX_INSN_SIZE + BPF_INSN_SAFETY]; int i, cnt = 0, excnt = 0; - int proglen = 0; + int ilen, proglen = 0; u8 *prog = temp; + int err; + + detect_reg_usage(insn, insn_cnt, callee_regs_used, + &tail_call_seen); + + /* tail call's presence in current prog implies it is reachable */ + tail_call_reachable |= tail_call_seen; emit_prologue(&prog, bpf_prog->aux->stack_depth, - bpf_prog_was_classic(bpf_prog)); - addrs[0] = prog - temp; + bpf_prog_was_classic(bpf_prog), tail_call_reachable, + bpf_prog->aux->func_idx != 0); + push_callee_regs(&prog, callee_regs_used); + + ilen = prog - temp; + if (image) + memcpy(image + proglen, temp, ilen); + proglen += ilen; + addrs[0] = proglen; + prog = temp; for (i = 1; 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; + u8 *start_of_ldx; s64 jmp_offset; u8 jmp_cond; - int ilen; u8 *func; + int nops; switch (insn->code) { /* ALU */ @@ -689,17 +948,9 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, 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)); + maybe_emit_mod(&prog, dst_reg, src_reg, + BPF_CLASS(insn->code) == BPF_ALU64); + b2 = simple_alu_opcodes[BPF_OP(insn->code)]; EMIT2(b2, add_2reg(0xC0, dst_reg, src_reg)); break; @@ -879,12 +1130,7 @@ 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)); - switch (BPF_OP(insn->code)) { - case BPF_LSH: b3 = 0xE0; break; - case BPF_RSH: b3 = 0xE8; break; - case BPF_ARSH: b3 = 0xF8; break; - } - + b3 = simple_alu_opcodes[BPF_OP(insn->code)]; if (imm32 == 1) EMIT2(0xD1, add_1reg(b3, dst_reg)); else @@ -918,11 +1164,7 @@ 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)); - switch (BPF_OP(insn->code)) { - case BPF_LSH: b3 = 0xE0; break; - case BPF_RSH: b3 = 0xE8; break; - case BPF_ARSH: b3 = 0xF8; break; - } + b3 = simple_alu_opcodes[BPF_OP(insn->code)]; EMIT2(0xD3, add_1reg(b3, dst_reg)); if (src_reg != BPF_REG_4) @@ -1037,12 +1279,30 @@ st: if (is_imm8(insn->off)) case BPF_LDX | BPF_PROBE_MEM | BPF_W: case BPF_LDX | BPF_MEM | BPF_DW: case BPF_LDX | BPF_PROBE_MEM | BPF_DW: + if (BPF_MODE(insn->code) == BPF_PROBE_MEM) { + /* test src_reg, src_reg */ + maybe_emit_mod(&prog, src_reg, src_reg, true); /* always 1 byte */ + EMIT2(0x85, add_2reg(0xC0, src_reg, src_reg)); + /* jne start_of_ldx */ + EMIT2(X86_JNE, 0); + /* xor dst_reg, dst_reg */ + emit_mov_imm32(&prog, false, dst_reg, 0); + /* jmp byte_after_ldx */ + EMIT2(0xEB, 0); + + /* populate jmp_offset for JNE above */ + temp[4] = prog - temp - 5 /* sizeof(test + jne) */; + start_of_ldx = prog; + } emit_ldx(&prog, BPF_SIZE(insn->code), dst_reg, src_reg, insn->off); if (BPF_MODE(insn->code) == BPF_PROBE_MEM) { struct exception_table_entry *ex; u8 *_insn = image + proglen; s64 delta; + /* populate jmp_offset for JMP above */ + start_of_ldx[-1] = prog - start_of_ldx; + if (!bpf_prog->aux->extable) break; @@ -1082,36 +1342,82 @@ st: if (is_imm8(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); + case BPF_STX | BPF_ATOMIC | BPF_W: + case BPF_STX | BPF_ATOMIC | BPF_DW: + if (insn->imm == (BPF_AND | BPF_FETCH) || + insn->imm == (BPF_OR | BPF_FETCH) || + insn->imm == (BPF_XOR | BPF_FETCH)) { + u8 *branch_target; + bool is64 = BPF_SIZE(insn->code) == BPF_DW; + + /* + * Can't be implemented with a single x86 insn. + * Need to do a CMPXCHG loop. + */ + + /* Will need RAX as a CMPXCHG operand so save R0 */ + emit_mov_reg(&prog, true, BPF_REG_AX, BPF_REG_0); + branch_target = prog; + /* Load old value */ + emit_ldx(&prog, BPF_SIZE(insn->code), + BPF_REG_0, dst_reg, insn->off); + /* + * Perform the (commutative) operation locally, + * put the result in the AUX_REG. + */ + emit_mov_reg(&prog, is64, AUX_REG, BPF_REG_0); + maybe_emit_mod(&prog, AUX_REG, src_reg, is64); + EMIT2(simple_alu_opcodes[BPF_OP(insn->imm)], + add_2reg(0xC0, AUX_REG, src_reg)); + /* Attempt to swap in new value */ + err = emit_atomic(&prog, BPF_CMPXCHG, + dst_reg, AUX_REG, insn->off, + BPF_SIZE(insn->code)); + if (WARN_ON(err)) + return err; + /* + * ZF tells us whether we won the race. If it's + * cleared we need to try again. + */ + EMIT2(X86_JNE, -(prog - branch_target) - 2); + /* Return the pre-modification value */ + emit_mov_reg(&prog, is64, src_reg, BPF_REG_0); + /* Restore R0 after clobbering RAX */ + emit_mov_reg(&prog, true, BPF_REG_0, BPF_REG_AX); + break; + + } + + err = emit_atomic(&prog, insn->imm, dst_reg, src_reg, + insn->off, BPF_SIZE(insn->code)); + if (err) + return err; break; /* call */ case BPF_JMP | BPF_CALL: func = (u8 *) __bpf_call_base + imm32; - if (!imm32 || emit_call(&prog, func, image + addrs[i - 1])) - return -EINVAL; + if (tail_call_reachable) { + EMIT3_off32(0x48, 0x8B, 0x85, + -(bpf_prog->aux->stack_depth + 8)); + if (!imm32 || emit_call(&prog, func, image + addrs[i - 1] + 7)) + return -EINVAL; + } else { + if (!imm32 || emit_call(&prog, func, image + addrs[i - 1])) + return -EINVAL; + } break; case BPF_JMP | BPF_TAIL_CALL: if (imm32) emit_bpf_tail_call_direct(&bpf_prog->aux->poke_tab[imm32 - 1], - &prog, addrs[i], image); + &prog, addrs[i], image, + callee_regs_used, + bpf_prog->aux->stack_depth); else - emit_bpf_tail_call_indirect(&prog); + emit_bpf_tail_call_indirect(&prog, + callee_regs_used, + bpf_prog->aux->stack_depth); break; /* cond jump */ @@ -1136,20 +1442,16 @@ xadd: if (is_imm8(insn->off)) case BPF_JMP32 | BPF_JSGE | BPF_X: case BPF_JMP32 | BPF_JSLE | BPF_X: /* cmp dst_reg, src_reg */ - if (BPF_CLASS(insn->code) == BPF_JMP) - 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)); + maybe_emit_mod(&prog, dst_reg, src_reg, + BPF_CLASS(insn->code) == BPF_JMP); EMIT2(0x39, add_2reg(0xC0, dst_reg, src_reg)); goto emit_cond_jmp; case BPF_JMP | BPF_JSET | BPF_X: case BPF_JMP32 | BPF_JSET | BPF_X: /* test dst_reg, src_reg */ - if (BPF_CLASS(insn->code) == BPF_JMP) - 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)); + maybe_emit_mod(&prog, dst_reg, src_reg, + BPF_CLASS(insn->code) == BPF_JMP); EMIT2(0x85, add_2reg(0xC0, dst_reg, src_reg)); goto emit_cond_jmp; @@ -1185,10 +1487,8 @@ xadd: if (is_imm8(insn->off)) case BPF_JMP32 | BPF_JSLE | BPF_K: /* test dst_reg, dst_reg to save one extra byte */ if (imm32 == 0) { - if (BPF_CLASS(insn->code) == BPF_JMP) - EMIT1(add_2mod(0x48, dst_reg, dst_reg)); - else if (is_ereg(dst_reg)) - EMIT1(add_2mod(0x40, dst_reg, dst_reg)); + maybe_emit_mod(&prog, dst_reg, dst_reg, + BPF_CLASS(insn->code) == BPF_JMP); EMIT2(0x85, add_2reg(0xC0, dst_reg, dst_reg)); goto emit_cond_jmp; } @@ -1250,6 +1550,30 @@ emit_cond_jmp: /* Convert BPF opcode to x86 */ } jmp_offset = addrs[i + insn->off] - addrs[i]; if (is_imm8(jmp_offset)) { + if (jmp_padding) { + /* To keep the jmp_offset valid, the extra bytes are + * padded before the jump insn, so we substract the + * 2 bytes of jmp_cond insn from INSN_SZ_DIFF. + * + * If the previous pass already emits an imm8 + * jmp_cond, then this BPF insn won't shrink, so + * "nops" is 0. + * + * On the other hand, if the previous pass emits an + * imm32 jmp_cond, the extra 4 bytes(*) is padded to + * keep the image from shrinking further. + * + * (*) imm32 jmp_cond is 6 bytes, and imm8 jmp_cond + * is 2 bytes, so the size difference is 4 bytes. + */ + nops = INSN_SZ_DIFF - 2; + if (nops != 0 && nops != 4) { + pr_err("unexpected jmp_cond padding: %d bytes\n", + nops); + return -EFAULT; + } + cnt += emit_nops(&prog, nops); + } EMIT2(jmp_cond, jmp_offset); } else if (is_simm32(jmp_offset)) { EMIT2_off32(0x0F, jmp_cond + 0x10, jmp_offset); @@ -1272,11 +1596,55 @@ emit_cond_jmp: /* Convert BPF opcode to x86 */ else jmp_offset = addrs[i + insn->off] - addrs[i]; - if (!jmp_offset) - /* Optimize out nop jumps */ + if (!jmp_offset) { + /* + * If jmp_padding is enabled, the extra nops will + * be inserted. Otherwise, optimize out nop jumps. + */ + if (jmp_padding) { + /* There are 3 possible conditions. + * (1) This BPF_JA is already optimized out in + * the previous run, so there is no need + * to pad any extra byte (0 byte). + * (2) The previous pass emits an imm8 jmp, + * so we pad 2 bytes to match the previous + * insn size. + * (3) Similarly, the previous pass emits an + * imm32 jmp, and 5 bytes is padded. + */ + nops = INSN_SZ_DIFF; + if (nops != 0 && nops != 2 && nops != 5) { + pr_err("unexpected nop jump padding: %d bytes\n", + nops); + return -EFAULT; + } + cnt += emit_nops(&prog, nops); + } break; + } emit_jmp: if (is_imm8(jmp_offset)) { + if (jmp_padding) { + /* To avoid breaking jmp_offset, the extra bytes + * are padded before the actual jmp insn, so + * 2 bytes is substracted from INSN_SZ_DIFF. + * + * If the previous pass already emits an imm8 + * jmp, there is nothing to pad (0 byte). + * + * If it emits an imm32 jmp (5 bytes) previously + * and now an imm8 jmp (2 bytes), then we pad + * (5 - 2 = 3) bytes to stop the image from + * shrinking further. + */ + nops = INSN_SZ_DIFF - 2; + if (nops != 0 && nops != 3) { + pr_err("unexpected jump padding: %d bytes\n", + nops); + return -EFAULT; + } + cnt += emit_nops(&prog, INSN_SZ_DIFF - 2); + } EMIT2(0xEB, jmp_offset); } else if (is_simm32(jmp_offset)) { EMIT1_off32(0xE9, jmp_offset); @@ -1294,12 +1662,7 @@ emit_jmp: seen_exit = true; /* Update cleanup_addr */ ctx->cleanup_addr = proglen; - if (!bpf_prog_was_classic(bpf_prog)) - EMIT1(0x5B); /* get rid of tail_call_cnt */ - EMIT2(0x41, 0x5F); /* pop r15 */ - EMIT2(0x41, 0x5E); /* pop r14 */ - EMIT2(0x41, 0x5D); /* pop r13 */ - EMIT1(0x5B); /* pop rbx */ + pop_callee_regs(&prog, callee_regs_used); EMIT1(0xC9); /* leave */ EMIT1(0xC3); /* ret */ break; @@ -1377,13 +1740,26 @@ static int invoke_bpf_prog(const struct btf_func_model *m, u8 **pprog, struct bpf_prog *p, int stack_size, bool mod_ret) { u8 *prog = *pprog; + u8 *jmp_insn; int cnt = 0; - if (emit_call(&prog, __bpf_prog_enter, prog)) - return -EINVAL; + /* arg1: mov rdi, progs[i] */ + emit_mov_imm64(&prog, BPF_REG_1, (long) p >> 32, (u32) (long) p); + if (emit_call(&prog, + p->aux->sleepable ? __bpf_prog_enter_sleepable : + __bpf_prog_enter, prog)) + return -EINVAL; /* remember prog start time returned by __bpf_prog_enter */ emit_mov_reg(&prog, true, BPF_REG_6, BPF_REG_0); + /* if (__bpf_prog_enter*(prog) == 0) + * goto skip_exec_of_prog; + */ + EMIT3(0x48, 0x85, 0xC0); /* test rax,rax */ + /* emit 2 nops that will be replaced with JE insn */ + jmp_insn = prog; + emit_nops(&prog, 2); + /* arg1: lea rdi, [rbp - stack_size] */ EMIT4(0x48, 0x8D, 0x7D, -stack_size); /* arg2: progs[i]->insnsi for interpreter */ @@ -1402,38 +1778,23 @@ static int invoke_bpf_prog(const struct btf_func_model *m, u8 **pprog, if (mod_ret) emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_0, -8); + /* replace 2 nops with JE insn, since jmp target is known */ + jmp_insn[0] = X86_JE; + jmp_insn[1] = prog - jmp_insn - 2; + /* arg1: mov rdi, progs[i] */ - emit_mov_imm64(&prog, BPF_REG_1, (long) p >> 32, - (u32) (long) p); + emit_mov_imm64(&prog, BPF_REG_1, (long) p >> 32, (u32) (long) p); /* arg2: mov rsi, rbx <- start time in nsec */ emit_mov_reg(&prog, true, BPF_REG_2, BPF_REG_6); - if (emit_call(&prog, __bpf_prog_exit, prog)) - return -EINVAL; + if (emit_call(&prog, + p->aux->sleepable ? __bpf_prog_exit_sleepable : + __bpf_prog_exit, prog)) + return -EINVAL; *pprog = prog; return 0; } -static void emit_nops(u8 **pprog, unsigned int len) -{ - unsigned int i, noplen; - u8 *prog = *pprog; - int cnt = 0; - - while (len > 0) { - noplen = len; - - if (noplen > ASM_NOP_MAX) - noplen = ASM_NOP_MAX; - - for (i = 0; i < noplen; i++) - EMIT1(ideal_nops[noplen][i]); - len -= noplen; - } - - *pprog = prog; -} - static void emit_align(u8 **pprog, u32 align) { u8 *target, *prog = *pprog; @@ -1808,6 +2169,9 @@ struct x64_jit_data { struct jit_context ctx; }; +#define MAX_PASSES 20 +#define PADDING_PASSES (MAX_PASSES - 5) + struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) { struct bpf_binary_header *header = NULL; @@ -1817,6 +2181,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) struct jit_context ctx = {}; bool tmp_blinded = false; bool extra_pass = false; + bool padding = false; u8 *image = NULL; int *addrs; int pass; @@ -1853,6 +2218,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) image = jit_data->image; header = jit_data->header; extra_pass = true; + padding = true; goto skip_init_addrs; } addrs = kmalloc_array(prog->len + 1, sizeof(*addrs), GFP_KERNEL); @@ -1878,8 +2244,10 @@ skip_init_addrs: * 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); + for (pass = 0; pass < MAX_PASSES || image; pass++) { + if (!padding && pass >= PADDING_PASSES) + padding = true; + proglen = do_jit(prog, addrs, image, oldproglen, &ctx, padding); if (proglen <= 0) { out_image: image = NULL; |