[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <c11b7ee7-23e2-65be-6983-2d260aeb90df@intel.com>
Date: Fri, 8 May 2020 14:32:16 +0200
From: Björn Töpel <bjorn.topel@...el.com>
To: Maxim Mikityanskiy <maximmi@...lanox.com>,
Björn Töpel <bjorn.topel@...il.com>
Cc: ast@...nel.org, daniel@...earbox.net, davem@...emloft.net,
kuba@...nel.org, hawk@...nel.org, john.fastabend@...il.com,
netdev@...r.kernel.org, bpf@...r.kernel.org,
magnus.karlsson@...el.com, jonathan.lemon@...il.com,
jeffrey.t.kirsher@...el.com, maciej.fijalkowski@...el.com
Subject: Re: [PATCH bpf-next 04/14] xsk: introduce AF_XDP buffer allocation
API
On 2020-05-08 13:55, Maxim Mikityanskiy wrote:
> On 2020-05-07 13:42, Björn Töpel wrote:
>> From: Björn Töpel <bjorn.topel@...el.com>
>>
>> In order to simplify AF_XDP zero-copy enablement for NIC driver
>> developers, a new AF_XDP buffer allocation API is added. The
>> implementation is based on a single core (single producer/consumer)
>> buffer pool for the AF_XDP UMEM.
>>
>> A buffer is allocated using the xsk_buff_alloc() function, and
>> returned using xsk_buff_free(). If a buffer is disassociated with the
>> pool, e.g. when a buffer is passed to an AF_XDP socket, a buffer is
>> said to be released. Currently, the release function is only used by
>> the AF_XDP internals and not visible to the driver.
>>
>> Drivers using this API should register the XDP memory model with the
>> new MEM_TYPE_XSK_BUFF_POOL type.
>>
>> The API is defined in net/xdp_sock_drv.h.
>>
>> The buffer type is struct xdp_buff, and follows the lifetime of
>> regular xdp_buffs, i.e. the lifetime of an xdp_buff is restricted to
>> a NAPI context. In other words, the API is not replacing xdp_frames.
>>
>> In addition to introducing the API and implementations, the AF_XDP
>> core is migrated to use the new APIs.
>>
>> rfc->v1: Fixed build errors/warnings for m68k and riscv. (kbuild test
>> robot)
>> Added headroom/chunk size getter. (Maxim/Björn)
>>
>> Signed-off-by: Maxim Mikityanskiy <maximmi@...lanox.com>
>> Signed-off-by: Björn Töpel <bjorn.topel@...el.com>
>
> Björn's signoff should go first (as the original author).
>
Oh, I didn't know that. I'll fix in the next revision!
Powered by blists - more mailing lists