diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 958edce1066b..d3850a6d8650 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -1334,6 +1334,111 @@ static void restore_regs(const struct btf_func_model *m, u8 **prog, int nr_args, -(stack_size - i * 8)); } +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; + int cnt = 0; + + if (emit_call(&prog, __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); + + /* arg1: lea rdi, [rbp - stack_size] */ + EMIT4(0x48, 0x8D, 0x7D, -stack_size); + /* arg2: progs[i]->insnsi for interpreter */ + if (!p->jited) + emit_mov_imm64(&prog, BPF_REG_2, + (long) p->insnsi >> 32, + (u32) (long) p->insnsi); + /* call JITed bpf program or interpreter */ + if (emit_call(&prog, p->bpf_func, prog)) + return -EINVAL; + + /* BPF_TRAMP_MODIFY_RETURN trampolines can modify the return + * of the previous call which is then passed on the stack to + * the next BPF program. + */ + if (mod_ret) + emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_0, -8); + + /* arg1: mov rdi, progs[i] */ + 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; + + *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; + + target = PTR_ALIGN(prog, align); + if (target != prog) + emit_nops(&prog, target - prog); + + *pprog = prog; +} + +static int emit_cond_near_jump(u8 **pprog, void *func, void *ip, u8 jmp_cond) +{ + u8 *prog = *pprog; + int cnt = 0; + s64 offset; + + offset = func - (ip + 2 + 4); + if (!is_simm32(offset)) { + pr_err("Target %p is out of range\n", func); + return -EINVAL; + } + EMIT2_off32(0x0F, jmp_cond + 0x10, offset); + *pprog = prog; + return 0; +} + +static int emit_mod_ret_check_imm8(u8 **pprog, int value) +{ + u8 *prog = *pprog; + int cnt = 0; + + if (!is_imm8(value)) + return -EINVAL; + + if (value == 0) + EMIT2(0x85, add_2reg(0xC0, BPF_REG_0, BPF_REG_0)); + else + EMIT3(0x83, add_1reg(0xF8, BPF_REG_0), value); + + *pprog = prog; + return 0; +} + static int invoke_bpf(const struct btf_func_model *m, u8 **pprog, struct bpf_tramp_progs *tp, int stack_size) { @@ -1341,34 +1446,53 @@ static int invoke_bpf(const struct btf_func_model *m, u8 **pprog, int cnt = 0, i; for (i = 0; i < tp->nr_progs; i++) { - if (emit_call(&prog, __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); - - /* arg1: lea rdi, [rbp - stack_size] */ - EMIT4(0x48, 0x8D, 0x7D, -stack_size); - /* arg2: progs[i]->insnsi for interpreter */ - if (!tp->progs[i]->jited) - emit_mov_imm64(&prog, BPF_REG_2, - (long) tp->progs[i]->insnsi >> 32, - (u32) (long) tp->progs[i]->insnsi); - /* call JITed bpf program or interpreter */ - if (emit_call(&prog, tp->progs[i]->bpf_func, prog)) - return -EINVAL; - - /* arg1: mov rdi, progs[i] */ - emit_mov_imm64(&prog, BPF_REG_1, (long) tp->progs[i] >> 32, - (u32) (long) tp->progs[i]); - /* 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)) + if (invoke_bpf_prog(m, &prog, tp->progs[i], stack_size, false)) return -EINVAL; } *pprog = prog; return 0; } +static int invoke_bpf_mod_ret(const struct btf_func_model *m, u8 **pprog, + struct bpf_tramp_progs *tp, int stack_size, + u8 **branches) +{ + u8 *prog = *pprog; + int i; + + /* The first fmod_ret program will receive a garbage return value. + * Set this to 0 to avoid confusing the program. + */ + emit_mov_imm32(&prog, false, BPF_REG_0, 0); + emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_0, -8); + for (i = 0; i < tp->nr_progs; i++) { + if (invoke_bpf_prog(m, &prog, tp->progs[i], stack_size, true)) + return -EINVAL; + + /* Generate a branch: + * + * if (ret != 0) + * goto do_fexit; + * + * If needed this can be extended to any integer value which can + * be passed by user-space when the program is loaded. + */ + if (emit_mod_ret_check_imm8(&prog, 0)) + return -EINVAL; + + /* Save the location of the branch and Generate 6 nops + * (4 bytes for an offset and 2 bytes for the jump) These nops + * are replaced with a conditional jump once do_fexit (i.e. the + * start of the fexit invocation) is finalized. + */ + branches[i] = prog; + emit_nops(&prog, 4 + 2); + } + + *pprog = prog; + return 0; +} + /* Example: * __be16 eth_type_trans(struct sk_buff *skb, struct net_device *dev); * its 'struct btf_func_model' will be nr_args=2 @@ -1434,10 +1558,12 @@ int arch_prepare_bpf_trampoline(void *image, void *image_end, struct bpf_tramp_progs *tprogs, void *orig_call) { - int cnt = 0, nr_args = m->nr_args; + int ret, i, cnt = 0, nr_args = m->nr_args; int stack_size = nr_args * 8; struct bpf_tramp_progs *fentry = &tprogs[BPF_TRAMP_FENTRY]; struct bpf_tramp_progs *fexit = &tprogs[BPF_TRAMP_FEXIT]; + struct bpf_tramp_progs *fmod_ret = &tprogs[BPF_TRAMP_MODIFY_RETURN]; + u8 **branches = NULL; u8 *prog; /* x86-64 supports up to 6 arguments. 7+ can be added in the future */ @@ -1470,24 +1596,60 @@ int arch_prepare_bpf_trampoline(void *image, void *image_end, if (invoke_bpf(m, &prog, fentry, stack_size)) return -EINVAL; + if (fmod_ret->nr_progs) { + branches = kcalloc(fmod_ret->nr_progs, sizeof(u8 *), + GFP_KERNEL); + if (!branches) + return -ENOMEM; + + if (invoke_bpf_mod_ret(m, &prog, fmod_ret, stack_size, + branches)) { + ret = -EINVAL; + goto cleanup; + } + } + if (flags & BPF_TRAMP_F_CALL_ORIG) { - if (fentry->nr_progs) + if (fentry->nr_progs || fmod_ret->nr_progs) restore_regs(m, &prog, nr_args, stack_size); /* call original function */ - if (emit_call(&prog, orig_call, prog)) - return -EINVAL; + if (emit_call(&prog, orig_call, prog)) { + ret = -EINVAL; + goto cleanup; + } /* remember return value in a stack for bpf prog to access */ emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_0, -8); } + if (fmod_ret->nr_progs) { + /* From Intel 64 and IA-32 Architectures Optimization + * Reference Manual, 3.4.1.4 Code Alignment, Assembly/Compiler + * Coding Rule 11: All branch targets should be 16-byte + * aligned. + */ + emit_align(&prog, 16); + /* Update the branches saved in invoke_bpf_mod_ret with the + * aligned address of do_fexit. + */ + for (i = 0; i < fmod_ret->nr_progs; i++) + emit_cond_near_jump(&branches[i], prog, branches[i], + X86_JNE); + } + if (fexit->nr_progs) - if (invoke_bpf(m, &prog, fexit, stack_size)) - return -EINVAL; + if (invoke_bpf(m, &prog, fexit, stack_size)) { + ret = -EINVAL; + goto cleanup; + } if (flags & BPF_TRAMP_F_RESTORE_REGS) restore_regs(m, &prog, nr_args, stack_size); + /* This needs to be done regardless. If there were fmod_ret programs, + * the return value is only updated on the stack and still needs to be + * restored to R0. + */ if (flags & BPF_TRAMP_F_CALL_ORIG) /* restore original return value back into RAX */ emit_ldx(&prog, BPF_DW, BPF_REG_0, BPF_REG_FP, -8); @@ -1499,9 +1661,15 @@ int arch_prepare_bpf_trampoline(void *image, void *image_end, EMIT4(0x48, 0x83, 0xC4, 8); /* add rsp, 8 */ EMIT1(0xC3); /* ret */ /* Make sure the trampoline generation logic doesn't overflow */ - if (WARN_ON_ONCE(prog > (u8 *)image_end - BPF_INSN_SAFETY)) - return -EFAULT; - return prog - (u8 *)image; + if (WARN_ON_ONCE(prog > (u8 *)image_end - BPF_INSN_SAFETY)) { + ret = -EFAULT; + goto cleanup; + } + ret = prog - (u8 *)image; + +cleanup: + kfree(branches); + return ret; } static int emit_cond_near_jump(u8 **pprog, void *func, void *ip, u8 jmp_cond) diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 4309e5b330ee..dc9442777f6f 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -474,6 +474,7 @@ void notrace __bpf_prog_exit(struct bpf_prog *prog, u64 start); enum bpf_tramp_prog_type { BPF_TRAMP_FENTRY, BPF_TRAMP_FEXIT, + BPF_TRAMP_MODIFY_RETURN, BPF_TRAMP_MAX, BPF_TRAMP_REPLACE, /* more than MAX */ }; diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 1d58137caf46..8b655245ca09 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -210,6 +210,7 @@ enum bpf_attach_type { BPF_TRACE_RAW_TP, BPF_TRACE_FENTRY, BPF_TRACE_FEXIT, + BPF_MODIFY_RETURN, __MAX_BPF_ATTACH_TYPE }; diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index b50c21966c5c..df5415f0c6a9 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -3716,7 +3716,8 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type, nr_args--; } - if (prog->expected_attach_type == BPF_TRACE_FEXIT && + if ((prog->expected_attach_type == BPF_TRACE_FEXIT || + prog->expected_attach_type == BPF_MODIFY_RETURN) && arg == nr_args) { if (!t) /* Default prog with 5 args. 6th arg is retval. */ diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 7487f1f27d8c..10b82a99abab 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -2327,6 +2327,7 @@ static int bpf_tracing_prog_attach(struct bpf_prog *prog) if (prog->expected_attach_type != BPF_TRACE_FENTRY && prog->expected_attach_type != BPF_TRACE_FEXIT && + prog->expected_attach_type != BPF_MODIFY_RETURN && prog->type != BPF_PROG_TYPE_EXT) { err = -EINVAL; goto out_put_prog; diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c index 546198f6f307..221a17af1f81 100644 --- a/kernel/bpf/trampoline.c +++ b/kernel/bpf/trampoline.c @@ -232,7 +232,8 @@ static int bpf_trampoline_update(struct bpf_trampoline *tr) goto out; } - if (tprogs[BPF_TRAMP_FEXIT].nr_progs) + if (tprogs[BPF_TRAMP_FEXIT].nr_progs || + tprogs[BPF_TRAMP_MODIFY_RETURN].nr_progs) flags = BPF_TRAMP_F_CALL_ORIG | BPF_TRAMP_F_SKIP_FRAME; /* Though the second half of trampoline page is unused a task could be @@ -269,6 +270,8 @@ static enum bpf_tramp_prog_type bpf_attach_type_to_tramp(enum bpf_attach_type t) switch (t) { case BPF_TRACE_FENTRY: return BPF_TRAMP_FENTRY; + case BPF_MODIFY_RETURN: + return BPF_TRAMP_MODIFY_RETURN; case BPF_TRACE_FEXIT: return BPF_TRAMP_FEXIT; default: diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index ff15efc844df..6980ea555024 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -10218,6 +10218,7 @@ static int check_attach_btf_id(struct bpf_verifier_env *env) if (!prog_extension) return -EINVAL; /* fallthrough */ + case BPF_MODIFY_RETURN: case BPF_TRACE_FENTRY: case BPF_TRACE_FEXIT: if (!btf_type_is_func(t)) { diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index eb21dca33f0f..e1f9b3430980 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -199,6 +199,10 @@ enum bpf_attach_type { BPF_CGROUP_UDP6_RECVMSG, BPF_CGROUP_GETSOCKOPT, BPF_CGROUP_SETSOCKOPT, + BPF_TRACE_RAW_TP, + BPF_TRACE_FENTRY, + BPF_TRACE_FEXIT, + BPF_MODIFY_RETURN, __MAX_BPF_ATTACH_TYPE };