| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <508b6da5-a32e-465b-b18e-e794bf0f19ab@quicinc.com>
Date: Wed, 24 Apr 2024 11:03:34 -0700
From: "Abhishek Chauhan (ABC)" <quic_abchauha@...cinc.com>
To: Martin KaFai Lau <martin.lau@...ux.dev>,
Willem de Bruijn
<willemdebruijn.kernel@...il.com>
CC: "David S. Miller" <davem@...emloft.net>,
Eric Dumazet
<edumazet@...gle.com>, Jakub Kicinski <kuba@...nel.org>,
Paolo Abeni
<pabeni@...hat.com>, <netdev@...r.kernel.org>,
<linux-kernel@...r.kernel.org>, Andrew Halaney <ahalaney@...hat.com>,
"Martin
KaFai Lau" <martin.lau@...nel.org>,
Daniel Borkmann <daniel@...earbox.net>, bpf <bpf@...r.kernel.org>,
<kernel@...cinc.com>
Subject: Re: [RFC PATCH bpf-next v4 2/2] net: Add additional bit to support
clockid_t timestamp type
On 4/22/2024 11:46 AM, Martin KaFai Lau wrote:
> On 4/19/24 6:13 PM, Abhishek Chauhan (ABC) wrote:
>>
>>
>> On 4/18/2024 5:30 PM, Abhishek Chauhan (ABC) wrote:
>>>
>>>
>>> On 4/18/2024 2:57 PM, Martin KaFai Lau wrote:
>>>> On 4/18/24 1:10 PM, Abhishek Chauhan (ABC) wrote:
>>>>>>> #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?
>>>>
>>>> nit. Shorten it to just SKB_TSTAMP_TYPE_MASK?
>>>>
>>> Okay i will do the same. Noted!
>>>> #ifdef __BIG_ENDIAN_BITFIELD
>>>> #define SKB_TSTAMP_TYPE_MASK (3 << 6)
>>>> #define SKB_TSTAMP_TYPE_RSH (6) /* more on this later */
>>>> #else
>>>> #define SKB_TSTAMP_TYPE_MASK (3)
>>>> #endif
>>>>
>>>>>>
>>>>> I was thinking to keep it as TAI because it will confuse developers. I hope thats okay.
>>>>
>>>> I think it is not very useful to distinguish each bit since it is an enum value now. It becomes more like the "pkt_type:3" and its PKT_TYPE_MAX.
>>>> I see what you are saying.
>>>>>>> +#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?
>>>>>> Actually thinking about it. I feel if its unsupported just fall back to default is the correct thing. I will take care of this.
>>>>>>> }
>>>>>>> }
>>>>>>
>>>>>>> >
>>>>>> @@ -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);
>>>>
>>>> With SKB_TSTAMP_TYPE_MASK defined like above, this could be simplified like this (untested):
>>>>
>>> Let me think this through and raise it as part of the next rfc patch.
>>>> static struct bpf_insn *bpf_convert_tstamp_type_read(const struct bpf_insn *si,
>>>> struct bpf_insn *insn)
>>>> {
>>>> __u8 value_reg = si->dst_reg;
>>>> __u8 skb_reg = si->src_reg;
>>>>
>>>> BUILD_BUG_ON(__SKB_CLOCK_MAX != BPF_SKB_TSTAMP_DELIVERY_TAI);
>>>> *insn++ = BPF_LDX_MEM(BPF_B, value_reg, skb_reg, SKB_BF_MONO_TC_OFFSET);
>>>> *insn++ = BPF_ALU32_IMM(BPF_AND, value_reg, SKB_TSTAMP_TYPE_MASK);
>>>> #ifdef __BIG_ENDIAN_BITFIELD
>>>> *insn++ = BPF_ALU32_IMM(BPF_RSH, value_reg, SKB_TSTAMP_TYPE_RSH);
>>>> #else
>>>> BUILD_BUG_ON(!(SKB_TSTAMP_TYPE_MASK & 0x1));
>>>> #endif
>>>>
>>>> return insn;
>>>> }
>>>>
>>>>>>> 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);
>>>>
>>>> Same as the bpf_convert_tstamp_type_read, this could be simplified with SKB_TSTAMP_TYPE_MASK.
>>>>
>> Willem and Martin,
>> When do we clear the tstamp and make it 0 in bpf_convert_tstamp_read? meaning which configuration?
>
> When the bpf prog does not check the skb->tstamp_type. It is
> the "if (!prog->tstamp_type_access)" in bpf_convert_tstamp_read().
>
> If bpf prog does not check the skb->tstamp_type and it is at ingress,
> bpf prog expects recv tstamp (ie. real clock), so it needs to clear
> out the tstamp (i.e read as 0 tstamp).
>
>> I see previously(current upstream code) if mono_delivery is set and tc_ingress_mask is set
>> upstream code used to set the tstamp as 0.
>>
>> Which means with addition of tai mask the new implementation should take care of following cases(correct me if i am wrong)
>> 1. ( tai mask set + ingress mask set ) = Clear tstamp
>> 2. ( mono mask set + ingress mask set ) = Clear tstamp
>> 3. ( mono mask set + tai mask set + ingress mask set ) = Clear tstamp
>> 4. ( No mask set ) = Clear tstamp
>> 5. ( Tai mask set + mono mask set ) = Clear tstamp
>
> No need to check the individual mono and tai bit here. Check the
> tstamp_type as a whole. Like in pseudo C:
>
> if (skb->tc_at_ingress && skb->tstamp_type)
> value_reg = 0;
>
> untested code for tstamp_read() and tstamp_write():
>
> static struct bpf_insn *bpf_convert_tstamp_read(const struct bpf_prog *prog,
> const struct bpf_insn *si,
> struct bpf_insn *insn)
> {
> __u8 value_reg = si->dst_reg;
> __u8 skb_reg = si->src_reg;
>
> #ifdef CONFIG_NET_XGRESS
> /* If the tstamp_type is read,
> * the bpf prog is aware the tstamp could have delivery time.
> * Thus, read skb->tstamp as is if tstamp_type_access is true.
> */
> if (!prog->tstamp_type_access) {
> /* AX is needed because src_reg and dst_reg could be the same */
> __u8 tmp_reg = BPF_REG_AX;
>
> *insn++ = BPF_LDX_MEM(BPF_B, tmp_reg, skb_reg, SKB_BF_MONO_TC_OFFSET);
> *insn++ = BPF_JMP32_IMM(BPF_JSET, tmp_reg, TC_AT_INGRESS_MASK, 1);
> /* goto <read> */
> BPF_JMP_A(4);
> *insn++ = BPF_JMP32_IMM(BPF_JSET, tmp_reg, SKB_TSTAMP_TYPE_MASK, 1);
> /* goto <read> */
> BPF_JMP_A(2);
> /* skb->tc_at_ingress && skb->tstamp_type,
> * read 0 as the (rcv) timestamp.
> */
> *insn++ = BPF_MOV64_IMM(value_reg, 0);
> *insn++ = BPF_JMP_A(1);
> }
> #endif
>
> /* <read>: value_reg = skb->tstamp */
> *insn++ = BPF_LDX_MEM(BPF_DW, value_reg, skb_reg,
> offsetof(struct sk_buff, tstamp));
> return insn;
> }
>
> static struct bpf_insn *bpf_convert_tstamp_write(const struct bpf_prog *prog,
> const struct bpf_insn *si,
> struct bpf_insn *insn)
> {
> __u8 value_reg = si->src_reg;
> __u8 skb_reg = si->dst_reg;
>
> #ifdef CONFIG_NET_XGRESS
> /* If the tstamp_type is read,
> * the bpf prog is aware the tstamp could have delivery time.
> * Thus, write skb->tstamp as is if tstamp_type_access is true.
> * Otherwise, writing at ingress will have to clear the
> * mono_delivery_time (skb->tstamp_type:1)bit also.
> */
> if (!prog->tstamp_type_access) {
> __u8 tmp_reg = BPF_REG_AX;
>
> *insn++ = BPF_LDX_MEM(BPF_B, tmp_reg, skb_reg, SKB_BF_MONO_TC_OFFSET);
> /* Writing __sk_buff->tstamp as ingress, goto <clear> */
> *insn++ = BPF_JMP32_IMM(BPF_JSET, tmp_reg, TC_AT_INGRESS_MASK, 1);
> /* goto <store> */
> *insn++ = BPF_JMP_A(2);
> /* <clear>: skb->tstamp_type */
> *insn++ = BPF_ALU32_IMM(BPF_AND, tmp_reg, ~SKB_TSTAMP_TYPE_MASK);
> *insn++ = BPF_STX_MEM(BPF_B, skb_reg, tmp_reg, SKB_BF_MONO_TC_OFFSET);
> }
> #endif
>
> /* <store>: skb->tstamp = tstamp */
> *insn++ = BPF_RAW_INSN(BPF_CLASS(si->code) | BPF_DW | BPF_MEM,
> skb_reg, value_reg, offsetof(struct sk_buff, tstamp), si->imm);
> return insn;
> }
>
Thanks Martin. I will raise the RFC patch v5 today. Also made changes in test_tc_dtime.c which
needs a closer review too.
>>
>> This leaves us with only two values which can be support which is 0x1 and 0x2
>>
>> This means the tstamp_type should be either 0x1(mono) and tstamp_type 0x2 (tai) to set the value_reg with tstamp
>> Is my understanding correct ?
>>
>> Do you think the below simplified version looks okay ?
>>
>> static struct bpf_insn *bpf_convert_tstamp_read(const struct bpf_prog *prog,
>> const struct bpf_insn *si,
>> struct bpf_insn *insn)
>> {
>> __u8 value_reg = si->dst_reg;
>> __u8 skb_reg = si->src_reg;
>>
>> BUILD_BUG_ON(__SKB_CLOCK_MAX != BPF_SKB_TSTAMP_DELIVERY_TAI);
>> #ifdef CONFIG_NET_XGRESS
>> /* If the tstamp_type is read,
>> * the bpf prog is aware the tstamp could have delivery time.
>> * Thus, read skb->tstamp as is if tstamp_type_access is true.
>> */
>> if (!prog->tstamp_type_access) {
>> /* AX is needed because src_reg and dst_reg could be the same */
>> __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_TSTAMP_TYPE_MASK);
>>
>> /* If the value of tmp_reg is 7,6,5,4,3,0 which means invalid
>> * configuration set the tstamp to 0, value 0x1 and 0x2
>> * is correct configuration
>> */
>> #ifdef __BIG_ENDIAN_BITFIELD
>> *insn++ = BPF_JMP32_IMM(BPF_JEQ, tmp_reg, 0x1 << SKB_TSTAMP_TYPE_RSH, 3);
>> *insn++ = BPF_JMP32_IMM(BPF_JEQ, tmp_reg, 0x2 << SKB_TSTAMP_TYPE_RSH, 2);
>> #endif
>> *insn++ = BPF_JMP32_IMM(BPF_JEQ, tmp_reg, 0x1, 3);
>> *insn++ = BPF_JMP32_IMM(BPF_JEQ, tmp_reg, 0x2, 2);
>> #endif
>> /* skb->tc_at_ingress && skb->tstamp_type:2,
>> * read 0 as the (rcv) timestamp.
>> */
>> *insn++ = BPF_MOV64_IMM(value_reg, 0);
>> *insn++ = BPF_JMP_A(1);
>> }
>> #endif
>>
>> *insn++ = BPF_LDX_MEM(BPF_DW, value_reg, skb_reg,
>> offsetof(struct sk_buff, tstamp));
>> return insn;
>> }
>>
>>
>
Powered by blists - more mailing lists