Re: [PATCH v2 bpf-next 07/13] bpf: Add BPF_FETCH field / create atomic_fetch_add instruction

[Yonghong Song]

On 11/27/20 9:57 AM, Brendan Jackman wrote:
> This value can be set in bpf_insn.imm, for BPF_ATOMIC instructions,
> in order to have the previous value of the atomically-modified memory
> location loaded into the src register after an atomic op is carried
> out.
>
> Suggested-by: Yonghong Song <yhs@xxxxxx>
> Signed-off-by: Brendan Jackman <jackmanb@xxxxxxxxxx>
> ---
>   arch/x86/net/bpf_jit_comp.c    |  4 ++++
>   include/linux/filter.h         |  9 +++++++++
>   include/uapi/linux/bpf.h       |  3 +++
>   kernel/bpf/core.c              | 13 +++++++++++++
>   kernel/bpf/disasm.c            |  7 +++++++
>   kernel/bpf/verifier.c          | 35 ++++++++++++++++++++++++----------
>   tools/include/linux/filter.h   | 10 ++++++++++
>   tools/include/uapi/linux/bpf.h |  3 +++
>   8 files changed, 74 insertions(+), 10 deletions(-)
>
> diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
> index 7c47ad70ddb4..d3cd45bcd0c1 100644
> --- a/arch/x86/net/bpf_jit_comp.c
> +++ b/arch/x86/net/bpf_jit_comp.c
> @@ -827,6 +827,10 @@ static int emit_atomic(u8 **pprog, u8 atomic_op,
>   		/* 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;
>   	default:
>   		pr_err("bpf_jit: unknown atomic opcode %02x\n", atomic_op);
>   		return -EFAULT;
> diff --git a/include/linux/filter.h b/include/linux/filter.h
> index ce19988fb312..4e04d0fc454f 100644
> --- a/include/linux/filter.h
> +++ b/include/linux/filter.h
> @@ -270,6 +270,15 @@ static inline bool insn_is_zext(const struct bpf_insn *insn)
>   		.imm   = BPF_ADD })
>   #define BPF_STX_XADD BPF_ATOMIC_ADD /* alias */
>   
> +/* Atomic memory add with fetch, src_reg = atomic_fetch_add(*(dst_reg + off), src_reg); */
> +
> +#define BPF_ATOMIC_FETCH_ADD(SIZE, DST, SRC, OFF)		\
> +	((struct bpf_insn) {					\
> +		.code  = BPF_STX | BPF_SIZE(SIZE) | BPF_ATOMIC,	\
> +		.dst_reg = DST,					\
> +		.src_reg = SRC,					\
> +		.off   = OFF,					\
> +		.imm   = BPF_ADD | BPF_FETCH })
>   
>   /* Memory store, *(uint *) (dst_reg + off16) = imm32 */
>   
> diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
> index d0adc48db43c..025e377e7229 100644
> --- a/include/uapi/linux/bpf.h
> +++ b/include/uapi/linux/bpf.h
> @@ -44,6 +44,9 @@
>   #define BPF_CALL	0x80	/* function call */
>   #define BPF_EXIT	0x90	/* function return */
>   
> +/* atomic op type fields (stored in immediate) */
> +#define BPF_FETCH	0x01	/* fetch previous value into src reg */
> +
>   /* Register numbers */
>   enum {
>   	BPF_REG_0 = 0,
[...]
> diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
> index e8b41ccdfb90..cd4c03b25573 100644
> --- a/kernel/bpf/verifier.c
> +++ b/kernel/bpf/verifier.c
> @@ -3602,7 +3602,11 @@ static int check_atomic(struct bpf_verifier_env *env, int insn_idx, struct bpf_i
>   {
>   	int err;
>   
> -	if (insn->imm != BPF_ADD) {
> +	switch (insn->imm) {
> +	case BPF_ADD:
> +	case BPF_ADD | BPF_FETCH:
> +		break;
> +	default:
>   		verbose(env, "BPF_ATOMIC uses invalid atomic opcode %02x\n", insn->imm);
>   		return -EINVAL;
>   	}
> @@ -3631,7 +3635,7 @@ static int check_atomic(struct bpf_verifier_env *env, int insn_idx, struct bpf_i
>   	    is_pkt_reg(env, insn->dst_reg) ||
>   	    is_flow_key_reg(env, insn->dst_reg) ||
>   	    is_sk_reg(env, insn->dst_reg)) {
> -		verbose(env, "atomic stores into R%d %s is not allowed\n",
> +		verbose(env, "BPF_ATOMIC stores into R%d %s is not allowed\n",
>   			insn->dst_reg,
>   			reg_type_str[reg_state(env, insn->dst_reg)->type]);
>   		return -EACCES;
> @@ -3644,8 +3648,20 @@ static int check_atomic(struct bpf_verifier_env *env, int insn_idx, struct bpf_i
>   		return err;
>   
>   	/* check whether we can write into the same memory */
> -	return check_mem_access(env, insn_idx, insn->dst_reg, insn->off,
> -				BPF_SIZE(insn->code), BPF_WRITE, -1, true);
> +	err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off,
> +			       BPF_SIZE(insn->code), BPF_WRITE, -1, true);
> +	if (err)
> +		return err;
> +
> +	if (!(insn->imm & BPF_FETCH))
> +		return 0;
> +
> +	/* check and record load of old value into src reg  */
> +	err = check_reg_arg(env, insn->src_reg, DST_OP);
> +	if (err)
> +		return err;
> +
> +	return 0;
>   }
>   
>   static int __check_stack_boundary(struct bpf_verifier_env *env, u32 regno,
> @@ -9501,12 +9517,6 @@ static int do_check(struct bpf_verifier_env *env)
>   		} else if (class == BPF_STX) {
>   			enum bpf_reg_type *prev_dst_type, dst_reg_type;
>   
> -			if (((BPF_MODE(insn->code) != BPF_MEM &&
> -			      BPF_MODE(insn->code) != BPF_ATOMIC) || insn->imm != 0)) {
> -				verbose(env, "BPF_STX uses reserved fields\n");
> -				return -EINVAL;
> -			}
> -
>   			if (BPF_MODE(insn->code) == BPF_ATOMIC) {
>   				err = check_atomic(env, env->insn_idx, insn);
>   				if (err)
> @@ -9515,6 +9525,11 @@ static int do_check(struct bpf_verifier_env *env)
>   				continue;
>   			}
>   
> +			if (BPF_MODE(insn->code) != BPF_MEM && insn->imm != 0) {

"||" here instead of "&&"?

> +				verbose(env, "BPF_STX uses reserved fields\n");
> +				return -EINVAL;
> +			}
> +
>   			/* check src1 operand */
>   			err = check_reg_arg(env, insn->src_reg, SRC_OP);
>   			if (err)
> diff --git a/tools/include/linux/filter.h b/tools/include/linux/filter.h
[...]