Re: [RFC PATCH bpf-next v4 2/2] net: Add additional bit to support clockid_t timestamp type

[Willem de Bruijn]

Abhishek Chauhan wrote:
> tstamp_type is now set based on actual clockid_t compressed
> into 2 bits.
> 
> To make the design scalable for future needs this commit bring in
> the change to extend the tstamp_type:1 to tstamp_type:2 to support
> other clockid_t timestamp.
> 
> We now support CLOCK_TAI as part of tstamp_type as part of this
> commit with exisiting support CLOCK_MONOTONIC and CLOCK_REALTIME.
> 
> Link: https://lore.kernel.org/netdev/bc037db4-58bb-4861-ac31-a361a93841d3@xxxxxxxxx/
> Signed-off-by: Abhishek Chauhan <quic_abchauha@xxxxxxxxxxx>
>  
>  /**
> - * tstamp_type:1 can take 2 values each
> + * tstamp_type:2 can take 4 values each
>   * represented by time base in skb
>   * 0x0 => real timestamp_type
>   * 0x1 => mono timestamp_type
> + * 0x2 => tai timestamp_type
> + * 0x3 => undefined timestamp_type

Same point as previous patch about comment that repeats name.

> @@ -833,7 +836,8 @@ enum skb_tstamp_type {
>   *	@tstamp_type: When set, skb->tstamp has the
>   *		delivery_time in mono clock base (i.e. EDT).  Otherwise, the
>   *		skb->tstamp has the (rcv) timestamp at ingress and
> - *		delivery_time at egress.
> + *		delivery_time at egress or skb->tstamp defined by skb->sk->sk_clockid
> + *		coming from userspace

I would simplify the comment: clock base of skb->tstamp.
Already in the first patch.

>   *	@napi_id: id of the NAPI struct this skb came from
>   *	@sender_cpu: (aka @napi_id) source CPU in XPS
>   *	@alloc_cpu: CPU which did the skb allocation.
> @@ -961,7 +965,7 @@ struct sk_buff {
>  	/* private: */
>  	__u8			__mono_tc_offset[0];
>  	/* public: */
> -	__u8			tstamp_type:1;	/* See SKB_CLOCK_*_MASK */
> +	__u8			tstamp_type:2;	/* See skb_tstamp_type enum */

Probably good to call out that according to pahole this fills a hole.

>  #ifdef CONFIG_NET_XGRESS
>  	__u8			tc_at_ingress:1;	/* See TC_AT_INGRESS_MASK */
>  	__u8			tc_skip_classify:1;
> @@ -1096,10 +1100,12 @@ struct sk_buff {
>   */
>  #ifdef __BIG_ENDIAN_BITFIELD
>  #define SKB_MONO_DELIVERY_TIME_MASK	(1 << 7)
> -#define TC_AT_INGRESS_MASK		(1 << 6)
> +#define SKB_TAI_DELIVERY_TIME_MASK	(1 << 6)

SKB_TSTAMP_TYPE_BIT2_MASK?

> +#define TC_AT_INGRESS_MASK		(1 << 5)
>  #else
>  #define SKB_MONO_DELIVERY_TIME_MASK	(1 << 0)
> -#define TC_AT_INGRESS_MASK		(1 << 1)
> +#define SKB_TAI_DELIVERY_TIME_MASK	(1 << 1)
> +#define TC_AT_INGRESS_MASK		(1 << 2)
>  #endif
>  #define SKB_BF_MONO_TC_OFFSET		offsetof(struct sk_buff, __mono_tc_offset)
>  
> @@ -4206,6 +4212,11 @@ static inline void skb_set_delivery_time(struct sk_buff *skb, ktime_t kt,
>  	case CLOCK_MONOTONIC:
>  		skb->tstamp_type = SKB_CLOCK_MONO;
>  		break;
> +	case CLOCK_TAI:
> +		skb->tstamp_type = SKB_CLOCK_TAI;
> +		break;
> +	default:
> +		WARN_ONCE(true, "clockid %d not supported", tstamp_type);

and set to 0 and default tstamp_type?

>  	}
>  }

>  >
 @@ -9372,10 +9378,16 @@ static struct bpf_insn *bpf_convert_tstamp_type_read(const struct bpf_insn *si,
>  	*insn++ = BPF_LDX_MEM(BPF_B, tmp_reg, skb_reg,
>  			      SKB_BF_MONO_TC_OFFSET);
>  	*insn++ = BPF_JMP32_IMM(BPF_JSET, tmp_reg,
> -				SKB_MONO_DELIVERY_TIME_MASK, 2);
> +				SKB_MONO_DELIVERY_TIME_MASK | SKB_TAI_DELIVERY_TIME_MASK, 2);
> +	*insn++ = BPF_JMP32_IMM(BPF_JSET, tmp_reg,
> +				SKB_MONO_DELIVERY_TIME_MASK, 3);
> +	*insn++ = BPF_JMP32_IMM(BPF_JSET, tmp_reg,
> +				SKB_TAI_DELIVERY_TIME_MASK, 4);
>  	*insn++ = BPF_MOV32_IMM(value_reg, BPF_SKB_TSTAMP_UNSPEC);
>  	*insn++ = BPF_JMP_A(1);
>  	*insn++ = BPF_MOV32_IMM(value_reg, BPF_SKB_TSTAMP_DELIVERY_MONO);
> +	*insn++ = BPF_JMP_A(1);
> +	*insn++ = BPF_MOV32_IMM(value_reg, BPF_SKB_TSTAMP_DELIVERY_TAI);
>  
>  	return insn;
>  }
> @@ -9418,10 +9430,26 @@ static struct bpf_insn *bpf_convert_tstamp_read(const struct bpf_prog *prog,
>  		__u8 tmp_reg = BPF_REG_AX;
>  
>  		*insn++ = BPF_LDX_MEM(BPF_B, tmp_reg, skb_reg, SKB_BF_MONO_TC_OFFSET);
> +		/*check if all three bits are set*/
>  		*insn++ = BPF_ALU32_IMM(BPF_AND, tmp_reg,
> -					TC_AT_INGRESS_MASK | SKB_MONO_DELIVERY_TIME_MASK);
> -		*insn++ = BPF_JMP32_IMM(BPF_JNE, tmp_reg,
> -					TC_AT_INGRESS_MASK | SKB_MONO_DELIVERY_TIME_MASK, 2);
> +					TC_AT_INGRESS_MASK | SKB_MONO_DELIVERY_TIME_MASK |
> +					SKB_TAI_DELIVERY_TIME_MASK);
> +		/*if all 3 bits are set jump 3 instructions and clear the register */
> +		*insn++ = BPF_JMP32_IMM(BPF_JEQ, tmp_reg,
> +					TC_AT_INGRESS_MASK | SKB_MONO_DELIVERY_TIME_MASK |
> +					SKB_TAI_DELIVERY_TIME_MASK, 4);
> +		/*Now check Mono is set with ingress mask if so clear */
> +		*insn++ = BPF_JMP32_IMM(BPF_JEQ, tmp_reg,
> +					TC_AT_INGRESS_MASK | SKB_MONO_DELIVERY_TIME_MASK, 3);
> +		/*Now Check tai is set with ingress mask if so clear */
> +		*insn++ = BPF_JMP32_IMM(BPF_JEQ, tmp_reg,
> +					TC_AT_INGRESS_MASK | SKB_TAI_DELIVERY_TIME_MASK, 2);
> +		/*Now Check tai and mono are set if so clear */
> +		*insn++ = BPF_JMP32_IMM(BPF_JEQ, tmp_reg,
> +					SKB_MONO_DELIVERY_TIME_MASK |
> +					SKB_TAI_DELIVERY_TIME_MASK, 1);

This looks as if all JEQ result in "if so clear"?

Is the goal to only do something different for the two bits being 0x1,
can we have a single test with a two-bit mask, rather than four tests?