On 03/19/2018 09:30 AM, Alexei Starovoitov wrote:
> On Sun, Mar 18, 2018 at 12:57:20PM -0700, John Fastabend wrote:
>> In the case where we need a specific number of bytes before a
>> verdict can be assigned, even if the data spans multiple sendmsg
>> or sendfile calls. The BPF program may use msg_cork_bytes().
>>
>> The extreme case is a user can call sendmsg repeatedly with
>> 1-byte msg segments. Obviously, this is bad for performance but
>> is still valid. If the BPF program needs N bytes to validate
>> a header it can use msg_cork_bytes to specify N bytes and the
>> BPF program will not be called again until N bytes have been
>> accumulated. The infrastructure will attempt to coalesce data
>> if possible so in many cases (most my use cases at least) the
>> data will be in a single scatterlist element with data pointers
>> pointing to start/end of the element. However, this is dependent
>> on available memory so is not guaranteed. So BPF programs must
>> validate data pointer ranges, but this is the case anyways to
>> convince the verifier the accesses are valid.
>>
>> Signed-off-by: John Fastabend <john.fastab...@gmail.com>
>> ---
>> include/uapi/linux/bpf.h | 3 ++-
>> net/core/filter.c | 16 ++++++++++++++++
>> 2 files changed, 18 insertions(+), 1 deletion(-)
>>
>> diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
>> index a557a2a..1765cfb 100644
>> --- a/include/uapi/linux/bpf.h
>> +++ b/include/uapi/linux/bpf.h
>> @@ -792,7 +792,8 @@ struct bpf_stack_build_id {
>> FN(override_return), \
>> FN(sock_ops_cb_flags_set), \
>> FN(msg_redirect_map), \
>> - FN(msg_apply_bytes),
>> + FN(msg_apply_bytes), \
>> + FN(msg_cork_bytes),
>>
>> /* integer value in 'imm' field of BPF_CALL instruction selects which helper
>> * function eBPF program intends to call
>> diff --git a/net/core/filter.c b/net/core/filter.c
>> index 17d6775..0c9daf6 100644
>> --- a/net/core/filter.c
>> +++ b/net/core/filter.c
>> @@ -1942,6 +1942,20 @@ struct sock *do_msg_redirect_map(struct sk_msg_buff
>> *msg)
>> .arg2_type = ARG_ANYTHING,
>> };
>>
>> +BPF_CALL_2(bpf_msg_cork_bytes, struct sk_msg_buff *, msg, u32, bytes)
>> +{
>> + msg->cork_bytes = bytes;
>> + return 0;
>> +}
>
> my understanding that setting it here and in the other helper *_bytes to zero
> will be effectively a nop. Right?
>
Correct, setting cork_bytes or apply_bytes to zero is just a nop.
> Acked-by: Alexei Starovoitov <a...@kernel.org>
>
