From:   Toke =?utf-8?Q?H=C3=B8iland-J=C3=B8rgensen?= <toke@redhat.com>
To:     Alexander Lobakin <alexandr.lobakin@intel.com>,
        Alexei Starovoitov <ast@kernel.org>,
        Daniel Borkmann <daniel@iogearbox.net>,
        Andrii Nakryiko <andrii@kernel.org>
Cc:     Martin KaFai Lau <martin.lau@linux.dev>,
        Song Liu <song@kernel.org>,
        Jesper Dangaard Brouer <hawk@kernel.org>,
        Jakub Kicinski <kuba@kernel.org>, bpf@vger.kernel.org,
        netdev@vger.kernel.org, linux-kernel@vger.kernel.org
Subject: Re: [PATCH bpf] bpf, test_run: fix &xdp_frame misplacement for
 LIVE_FRAMES
In-Reply-To: <6db57eb4-02c2-9443-b9eb-21c499142c98@intel.com>
References: <20230209172827.874728-1-alexandr.lobakin@intel.com>
 <6db57eb4-02c2-9443-b9eb-21c499142c98@intel.com>
Date:   Thu, 09 Feb 2023 21:58:07 +0100
Message-ID: <87sffe7e00.fsf@toke.dk>
MIME-Version: 1.0
Content-Type: text/plain
Precedence: bulk

Alexander Lobakin <alexandr.lobakin@intel.com> writes:

> From: Alexander Lobakin <alexandr.lobakin@intel.com>
> Date: Thu, 9 Feb 2023 18:28:27 +0100
>
>> &xdp_buff and &xdp_frame are bound in a way that
>> 
>> xdp_buff->data_hard_start == xdp_frame
>
> [...]
>
>> diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c
>> index 2723623429ac..c3cce7a8d47d 100644
>> --- a/net/bpf/test_run.c
>> +++ b/net/bpf/test_run.c
>> @@ -97,8 +97,11 @@ static bool bpf_test_timer_continue(struct bpf_test_timer *t, int iterations,
>>  struct xdp_page_head {
>>  	struct xdp_buff orig_ctx;
>>  	struct xdp_buff ctx;
>> -	struct xdp_frame frm;
>> -	u8 data[];
>> +	union {
>> +		/* ::data_hard_start starts here */
>> +		DECLARE_FLEX_ARRAY(struct xdp_frame, frm);
>> +		DECLARE_FLEX_ARRAY(u8, data);
>> +	};
>
> BTW, xdp_frame here starts at 112 byte offset, i.e. in 16 bytes a
> cacheline boundary is hit, so xdp_frame gets sliced into halves: 16
> bytes in CL1 + 24 bytes in CL2. Maybe we'd better align this union to
> %NET_SKB_PAD / %SMP_CACHE_BYTES / ... to avoid this?

Hmm, IIRC my reasoning was that both those cache lines will be touched
by the code in xdp_test_run_batch(), so it wouldn't matter? But if
there's a performance benefit I don't mind adding an explicit alignment
annotation, certainly!

> (but in bpf-next probably)

Yeah...

-Toke