netdev.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Daniel Borkmann <daniel@iogearbox.net>
To: David Miller <davem@davemloft.net>, netdev@vger.kernel.org
Cc: xdp-newbies@vger.kernel.org
Subject: Re: [PATCH v3 net-next RFC] Generic XDP
Date: Thu, 13 Apr 2017 17:57:06 +0200	[thread overview]
Message-ID: <58EF9FD2.90807@iogearbox.net> (raw)
In-Reply-To: <20170412.145415.1441440342830198148.davem@davemloft.net>

On 04/12/2017 08:54 PM, David Miller wrote:
[...]
> +static u32 netif_receive_generic_xdp(struct sk_buff *skb,
> +				     struct bpf_prog *xdp_prog)
> +{
> +	struct xdp_buff xdp;
> +	u32 act = XDP_DROP;
> +	void *orig_data;
> +	int hlen, off;
> +
> +	if (skb_linearize(skb))

Btw, given the skb can come from all kind of points in the stack,
it could also be a clone at this point. One example is act_mirred
which in fact does skb_clone() and can push the skb back to
ingress path through netif_receive_skb() and thus could then go
into generic xdp processing, where skb can be mangled.

Instead of skb_linearize() we would therefore need to use something
like skb_ensure_writable(skb, skb->len) as equivalent, which also
makes sure that we unclone whenever needed.

> +		goto do_drop;
> +
> +	/* The XDP program wants to see the packet starting at the MAC
> +	 * header.
> +	 */
> +	hlen = skb_headlen(skb) + skb->mac_len;
> +	xdp.data = skb->data - skb->mac_len;
> +	xdp.data_end = xdp.data + hlen;
> +	xdp.data_hard_start = xdp.data - skb_headroom(skb);
> +	orig_data = xdp.data;
> +
> +	act = bpf_prog_run_xdp(xdp_prog, &xdp);
> +
> +	off = xdp.data - orig_data;
> +	if (off)
> +		__skb_push(skb, off);
> +
> +	switch (act) {
> +	case XDP_TX:
> +		__skb_push(skb, skb->mac_len);
> +		/* fall through */
> +	case XDP_PASS:
> +		break;
> +
> +	default:
> +		bpf_warn_invalid_xdp_action(act);
> +		/* fall through */
> +	case XDP_ABORTED:
> +		trace_xdp_exception(skb->dev, xdp_prog, act);
> +		/* fall through */
> +	case XDP_DROP:
> +	do_drop:
> +		kfree_skb(skb);
> +		break;
> +	}
> +
> +	return act;
> +}
> +
>   static int netif_receive_skb_internal(struct sk_buff *skb)
>   {
>   	int ret;
> @@ -4258,6 +4341,21 @@ static int netif_receive_skb_internal(struct sk_buff *skb)
>
>   	rcu_read_lock();
>
> +	if (static_key_false(&generic_xdp_needed)) {
> +		struct bpf_prog *xdp_prog = rcu_dereference(skb->dev->xdp_prog);
> +
> +		if (xdp_prog) {
> +			u32 act = netif_receive_generic_xdp(skb, xdp_prog);
> +
> +			if (act != XDP_PASS) {
> +				rcu_read_unlock();
> +				if (act == XDP_TX)
> +					dev_queue_xmit(skb);
> +				return NET_RX_DROP;
> +			}
> +		}
> +	}
> +
[...]

  parent reply	other threads:[~2017-04-13 15:57 UTC|newest]

Thread overview: 36+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-04-12 18:54 [PATCH v3 net-next RFC] Generic XDP David Miller
2017-04-12 19:54 ` David Ahern
2017-04-13  2:08   ` David Miller
2017-04-13  2:16     ` David Ahern
2017-04-12 21:30 ` Stephen Hemminger
2017-04-12 21:49   ` Eric Dumazet
2017-04-13  1:55     ` David Miller
2017-04-13  1:54   ` David Miller
2017-04-13  4:20 ` Alexei Starovoitov
2017-04-13  6:10   ` Johannes Berg
2017-04-13 15:38     ` David Miller
2017-04-14 19:41       ` Alexei Starovoitov
2017-04-18  9:47         ` Johannes Berg
2017-04-18 23:09           ` Alexei Starovoitov
2017-04-13 15:37   ` David Miller
2017-04-13 19:22     ` Johannes Berg
2017-04-13 20:01       ` David Miller
2017-04-14  8:07         ` Johannes Berg
2017-04-14 19:09           ` Alexei Starovoitov
2017-04-14  9:05     ` Jesper Dangaard Brouer
2017-04-14 19:28       ` Alexei Starovoitov
2017-04-14 22:18         ` Daniel Borkmann
2017-04-14 22:30         ` Jakub Kicinski
2017-04-15  0:46           ` Alexei Starovoitov
2017-04-15  1:47             ` Jakub Kicinski
2017-04-16 20:26             ` Jesper Dangaard Brouer
2017-04-17 19:49               ` David Miller
2017-04-17 23:04                 ` Alexei Starovoitov
2017-04-17 23:33                   ` Daniel Borkmann
2017-04-18 18:46                   ` David Miller
2017-04-18 23:05                     ` Alexei Starovoitov
2017-04-13  6:48 ` Michael Chan
2017-04-13 15:38   ` David Miller
2017-04-13 15:57 ` Daniel Borkmann [this message]
2017-04-13 16:04   ` David Miller
2017-04-13 17:13 ` aa5c2fd79f: net/core/dev.c:#suspicious_rcu_dereference_check()usage kernel test robot

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=58EF9FD2.90807@iogearbox.net \
    --to=daniel@iogearbox.net \
    --cc=davem@davemloft.net \
    --cc=netdev@vger.kernel.org \
    --cc=xdp-newbies@vger.kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).