bpf.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Kumar Kartikeya Dwivedi <memxor@gmail.com>
To: netdev@vger.kernel.org
Cc: "Kumar Kartikeya Dwivedi" <memxor@gmail.com>,
	"Toke Høiland-Jørgensen" <toke@redhat.com>,
	"Alexei Starovoitov" <ast@kernel.org>,
	"Daniel Borkmann" <daniel@iogearbox.net>,
	"Andrii Nakryiko" <andrii@kernel.org>,
	"Jesper Dangaard Brouer" <brouer@redhat.com>,
	"David S. Miller" <davem@davemloft.net>,
	"Jakub Kicinski" <kuba@kernel.org>,
	"John Fastabend" <john.fastabend@gmail.com>,
	"Martin KaFai Lau" <kafai@fb.com>,
	bpf@vger.kernel.org
Subject: [PATCH net-next v5 1/5] net: core: split out code to run generic XDP prog
Date: Thu,  1 Jul 2021 05:57:55 +0530	[thread overview]
Message-ID: <20210701002759.381983-2-memxor@gmail.com> (raw)
In-Reply-To: <20210701002759.381983-1-memxor@gmail.com>

This helper can later be utilized in code that runs cpumap and devmap
programs in generic redirect mode and adjust skb based on changes made
to xdp_buff.

When returning XDP_REDIRECT/XDP_TX, it invokes __skb_push, so whenever a
generic redirect path invokes devmap/cpumap prog if set, it must
__skb_pull again as we expect mac header to be pulled.

It also drops the skb_reset_mac_len call after do_xdp_generic, as the
mac_header and network_header are advanced by the same offset, so the
difference (mac_len) remains constant.

Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
---
 include/linux/netdevice.h |  2 +
 net/core/dev.c            | 84 ++++++++++++++++++++++++---------------
 2 files changed, 55 insertions(+), 31 deletions(-)

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index be1dcceda5e4..90472ea70db2 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3984,6 +3984,8 @@ static inline void dev_consume_skb_any(struct sk_buff *skb)
 	__dev_kfree_skb_any(skb, SKB_REASON_CONSUMED);
 }
 
+u32 bpf_prog_run_generic_xdp(struct sk_buff *skb, struct xdp_buff *xdp,
+			     struct bpf_prog *xdp_prog);
 void generic_xdp_tx(struct sk_buff *skb, struct bpf_prog *xdp_prog);
 int do_xdp_generic(struct bpf_prog *xdp_prog, struct sk_buff *skb);
 int netif_rx(struct sk_buff *skb);
diff --git a/net/core/dev.c b/net/core/dev.c
index 991d09b67bd9..ad5ab33cbd39 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4740,45 +4740,18 @@ static struct netdev_rx_queue *netif_get_rxqueue(struct sk_buff *skb)
 	return rxqueue;
 }
 
-static u32 netif_receive_generic_xdp(struct sk_buff *skb,
-				     struct xdp_buff *xdp,
-				     struct bpf_prog *xdp_prog)
+u32 bpf_prog_run_generic_xdp(struct sk_buff *skb, struct xdp_buff *xdp,
+			     struct bpf_prog *xdp_prog)
 {
 	void *orig_data, *orig_data_end, *hard_start;
 	struct netdev_rx_queue *rxqueue;
-	u32 metalen, act = XDP_DROP;
 	bool orig_bcast, orig_host;
 	u32 mac_len, frame_sz;
 	__be16 orig_eth_type;
 	struct ethhdr *eth;
+	u32 metalen, act;
 	int off;
 
-	/* Reinjected packets coming from act_mirred or similar should
-	 * not get XDP generic processing.
-	 */
-	if (skb_is_redirected(skb))
-		return XDP_PASS;
-
-	/* XDP packets must be linear and must have sufficient headroom
-	 * of XDP_PACKET_HEADROOM bytes. This is the guarantee that also
-	 * native XDP provides, thus we need to do it here as well.
-	 */
-	if (skb_cloned(skb) || skb_is_nonlinear(skb) ||
-	    skb_headroom(skb) < XDP_PACKET_HEADROOM) {
-		int hroom = XDP_PACKET_HEADROOM - skb_headroom(skb);
-		int troom = skb->tail + skb->data_len - skb->end;
-
-		/* In case we have to go down the path and also linearize,
-		 * then lets do the pskb_expand_head() work just once here.
-		 */
-		if (pskb_expand_head(skb,
-				     hroom > 0 ? ALIGN(hroom, NET_SKB_PAD) : 0,
-				     troom > 0 ? troom + 128 : 0, GFP_ATOMIC))
-			goto do_drop;
-		if (skb_linearize(skb))
-			goto do_drop;
-	}
-
 	/* The XDP program wants to see the packet starting at the MAC
 	 * header.
 	 */
@@ -4833,6 +4806,13 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb,
 		skb->protocol = eth_type_trans(skb, skb->dev);
 	}
 
+	/* Redirect/Tx gives L2 packet, code that will reuse skb must __skb_pull
+	 * before calling us again on redirect path. We do not call do_redirect
+	 * as we leave that up to the caller.
+	 *
+	 * Caller is responsible for managing lifetime of skb (i.e. calling
+	 * kfree_skb in response to actions it cannot handle/XDP_DROP).
+	 */
 	switch (act) {
 	case XDP_REDIRECT:
 	case XDP_TX:
@@ -4843,6 +4823,49 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb,
 		if (metalen)
 			skb_metadata_set(skb, metalen);
 		break;
+	}
+
+	return act;
+}
+
+static u32 netif_receive_generic_xdp(struct sk_buff *skb,
+				     struct xdp_buff *xdp,
+				     struct bpf_prog *xdp_prog)
+{
+	u32 act = XDP_DROP;
+
+	/* Reinjected packets coming from act_mirred or similar should
+	 * not get XDP generic processing.
+	 */
+	if (skb_is_redirected(skb))
+		return XDP_PASS;
+
+	/* XDP packets must be linear and must have sufficient headroom
+	 * of XDP_PACKET_HEADROOM bytes. This is the guarantee that also
+	 * native XDP provides, thus we need to do it here as well.
+	 */
+	if (skb_cloned(skb) || skb_is_nonlinear(skb) ||
+	    skb_headroom(skb) < XDP_PACKET_HEADROOM) {
+		int hroom = XDP_PACKET_HEADROOM - skb_headroom(skb);
+		int troom = skb->tail + skb->data_len - skb->end;
+
+		/* In case we have to go down the path and also linearize,
+		 * then lets do the pskb_expand_head() work just once here.
+		 */
+		if (pskb_expand_head(skb,
+				     hroom > 0 ? ALIGN(hroom, NET_SKB_PAD) : 0,
+				     troom > 0 ? troom + 128 : 0, GFP_ATOMIC))
+			goto do_drop;
+		if (skb_linearize(skb))
+			goto do_drop;
+	}
+
+	act = bpf_prog_run_generic_xdp(skb, xdp, xdp_prog);
+	switch (act) {
+	case XDP_REDIRECT:
+	case XDP_TX:
+	case XDP_PASS:
+		break;
 	default:
 		bpf_warn_invalid_xdp_action(act);
 		fallthrough;
@@ -5308,7 +5331,6 @@ static int __netif_receive_skb_core(struct sk_buff **pskb, bool pfmemalloc,
 			ret = NET_RX_DROP;
 			goto out;
 		}
-		skb_reset_mac_len(skb);
 	}
 
 	if (eth_type_vlan(skb->protocol)) {
-- 
2.31.1


  reply	other threads:[~2021-07-01  0:30 UTC|newest]

Thread overview: 8+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-07-01  0:27 [PATCH net-next v5 0/5] Generic XDP improvements Kumar Kartikeya Dwivedi
2021-07-01  0:27 ` Kumar Kartikeya Dwivedi [this message]
2021-07-01  0:27 ` [PATCH net-next v5 2/5] bitops: add non-atomic bitops for pointers Kumar Kartikeya Dwivedi
2021-07-01  0:27 ` [PATCH net-next v5 3/5] bpf: cpumap: implement generic cpumap Kumar Kartikeya Dwivedi
2021-07-01  9:16   ` Jesper Dangaard Brouer
2021-07-02 11:18     ` Kumar Kartikeya Dwivedi
2021-07-01  0:27 ` [PATCH net-next v5 4/5] bpf: devmap: implement devmap prog execution for generic XDP Kumar Kartikeya Dwivedi
2021-07-01  0:27 ` [PATCH net-next v5 5/5] bpf: tidy xdp attach selftests Kumar Kartikeya Dwivedi

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=20210701002759.381983-2-memxor@gmail.com \
    --to=memxor@gmail.com \
    --cc=andrii@kernel.org \
    --cc=ast@kernel.org \
    --cc=bpf@vger.kernel.org \
    --cc=brouer@redhat.com \
    --cc=daniel@iogearbox.net \
    --cc=davem@davemloft.net \
    --cc=john.fastabend@gmail.com \
    --cc=kafai@fb.com \
    --cc=kuba@kernel.org \
    --cc=netdev@vger.kernel.org \
    --cc=toke@redhat.com \
    --subject='Re: [PATCH net-next v5 1/5] net: core: split out code to run generic XDP prog' \
    /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

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).