linux-kernel - Re: [PATCH v5 net-next 6/6] net: ethernet: ti: cpsw: add XDP support

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

Hash Suite for Android: free password hash cracker in your pocket

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <20190703092603.66f36914@carbon>
Date:   Wed, 3 Jul 2019 09:26:03 +0200
From:   Jesper Dangaard Brouer <brouer@...hat.com>
To:     Ivan Khoronzhuk <ivan.khoronzhuk@...aro.org>
Cc:     grygorii.strashko@...com, hawk@...nel.org, davem@...emloft.net,
        ast@...nel.org, linux-kernel@...r.kernel.org,
        linux-omap@...r.kernel.org, xdp-newbies@...r.kernel.org,
        ilias.apalodimas@...aro.org, netdev@...r.kernel.org,
        daniel@...earbox.net, jakub.kicinski@...ronome.com,
        john.fastabend@...il.com, brouer@...hat.com
Subject: Re: [PATCH v5 net-next 6/6] net: ethernet: ti: cpsw: add XDP
 support


On Sun, 30 Jun 2019 20:23:48 +0300 Ivan Khoronzhuk <ivan.khoronzhuk@...aro.org> wrote:

> Add XDP support based on rx page_pool allocator, one frame per page.
> Page pool allocator is used with assumption that only one rx_handler
> is running simultaneously. DMA map/unmap is reused from page pool
> despite there is no need to map whole page.
> 
> Due to specific of cpsw, the same TX/RX handler can be used by 2
> network devices, so special fields in buffer are added to identify
> an interface the frame is destined to. Thus XDP works for both
> interfaces, that allows to test xdp redirect between two interfaces
> easily. Aslo, each rx queue have own page pools, but common for both
> netdevs.

Looking at the details what happen when a single RX-queue can receive
into multiple net_device'es.  I realize that this driver will
violate/kill some of the "hidden"/implicit RX-bulking that the
XDP_REDIRECT code depend on for performance.

Specifically, it violate this assumption:
 https://github.com/torvalds/linux/blob/v5.2-rc7/kernel/bpf/devmap.c#L324-L329

	/* Ingress dev_rx will be the same for all xdp_frame's in
	 * bulk_queue, because bq stored per-CPU and must be flushed
	 * from net_device drivers NAPI func end.
	 */
	if (!bq->dev_rx)
		bq->dev_rx = dev_rx;

This drivers "NAPI func end", can have received into multiple
net_devices, before it's NAPI cycle ends.  Thus, violating this code
assumption.

Knowing all xdp_frame's in the bulk queue is from the same net_device,
can be used to further optimize XDP.  E.g. the dev->netdev_ops->ndo_xdp_xmit()
call don't take fully advantage of this, yet.  If we merge this driver,
it will block optimizations in this area.

NACK

-- 
Best regards,
  Jesper Dangaard Brouer
  MSc.CS, Principal Kernel Engineer at Red Hat
  LinkedIn: http://www.linkedin.com/in/brouer