bpf.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Jesper Dangaard Brouer <brouer@redhat.com>
To: bpf@vger.kernel.org
Cc: Jesper Dangaard Brouer <brouer@redhat.com>,
	netdev@vger.kernel.org, Daniel Borkmann <borkmann@iogearbox.net>,
	Alexei Starovoitov <alexei.starovoitov@gmail.com>,
	maze@google.com, lmb@cloudflare.com, shaun@tigera.io,
	Lorenzo Bianconi <lorenzo@kernel.org>,
	marek@cloudflare.com, John Fastabend <john.fastabend@gmail.com>,
	Jakub Kicinski <kuba@kernel.org>,
	eyal.birger@gmail.com, colrack@gmail.com
Subject: [PATCH bpf-next V16 5/7] bpf: drop MTU check when doing TC-BPF redirect to ingress
Date: Tue, 09 Feb 2021 14:38:29 +0100	[thread overview]
Message-ID: <161287790971.790810.11785274340154740591.stgit@firesoul> (raw)
In-Reply-To: <161287779408.790810.15631860742170694244.stgit@firesoul>

The use-case for dropping the MTU check when TC-BPF does redirect to
ingress, is described by Eyal Birger in email[0]. The summary is the
ability to increase packet size (e.g. with IPv6 headers for NAT64) and
ingress redirect packet and let normal netstack fragment packet as needed.

[0] https://lore.kernel.org/netdev/CAHsH6Gug-hsLGHQ6N0wtixdOa85LDZ3HNRHVd0opR=19Qo4W4Q@mail.gmail.com/

V15:
 - missing static for function declaration

V9:
 - Make net_device "up" (IFF_UP) check explicit in skb_do_redirect

V4:
 - Keep net_device "up" (IFF_UP) check.
 - Adjustment to handle bpf_redirect_peer() helper

Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Acked-by: John Fastabend <john.fastabend@gmail.com>
---
 include/linux/netdevice.h |   32 ++++++++++++++++++++++++++++++--
 net/core/dev.c            |   32 ++++++++++++++------------------
 net/core/filter.c         |    6 +++---
 3 files changed, 47 insertions(+), 23 deletions(-)

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index ef517254367d..b9bcbfde7849 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3931,14 +3931,42 @@ int xdp_umem_query(struct net_device *dev, u16 queue_id);
 
 int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb);
 int dev_forward_skb(struct net_device *dev, struct sk_buff *skb);
+int dev_forward_skb_nomtu(struct net_device *dev, struct sk_buff *skb);
 bool is_skb_forwardable(const struct net_device *dev,
 			const struct sk_buff *skb);
 
+static __always_inline bool __is_skb_forwardable(const struct net_device *dev,
+						 const struct sk_buff *skb,
+						 const bool check_mtu)
+{
+	const u32 vlan_hdr_len = 4; /* VLAN_HLEN */
+	unsigned int len;
+
+	if (!(dev->flags & IFF_UP))
+		return false;
+
+	if (!check_mtu)
+		return true;
+
+	len = dev->mtu + dev->hard_header_len + vlan_hdr_len;
+	if (skb->len <= len)
+		return true;
+
+	/* if TSO is enabled, we don't care about the length as the packet
+	 * could be forwarded without being segmented before
+	 */
+	if (skb_is_gso(skb))
+		return true;
+
+	return false;
+}
+
 static __always_inline int ____dev_forward_skb(struct net_device *dev,
-					       struct sk_buff *skb)
+					       struct sk_buff *skb,
+					       const bool check_mtu)
 {
 	if (skb_orphan_frags(skb, GFP_ATOMIC) ||
-	    unlikely(!is_skb_forwardable(dev, skb))) {
+	    unlikely(!__is_skb_forwardable(dev, skb, check_mtu))) {
 		atomic_long_inc(&dev->rx_dropped);
 		kfree_skb(skb);
 		return NET_RX_DROP;
diff --git a/net/core/dev.c b/net/core/dev.c
index 07a0347c33fb..8c820fe0eff3 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2194,28 +2194,14 @@ static inline void net_timestamp_set(struct sk_buff *skb)
 
 bool is_skb_forwardable(const struct net_device *dev, const struct sk_buff *skb)
 {
-	unsigned int len;
-
-	if (!(dev->flags & IFF_UP))
-		return false;
-
-	len = dev->mtu + dev->hard_header_len + VLAN_HLEN;
-	if (skb->len <= len)
-		return true;
-
-	/* if TSO is enabled, we don't care about the length as the packet
-	 * could be forwarded without being segmented before
-	 */
-	if (skb_is_gso(skb))
-		return true;
-
-	return false;
+	return __is_skb_forwardable(dev, skb, true);
 }
 EXPORT_SYMBOL_GPL(is_skb_forwardable);
 
-int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb)
+static int __dev_forward_skb2(struct net_device *dev, struct sk_buff *skb,
+			      bool check_mtu)
 {
-	int ret = ____dev_forward_skb(dev, skb);
+	int ret = ____dev_forward_skb(dev, skb, check_mtu);
 
 	if (likely(!ret)) {
 		skb->protocol = eth_type_trans(skb, dev);
@@ -2224,6 +2210,11 @@ int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb)
 
 	return ret;
 }
+
+int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb)
+{
+	return __dev_forward_skb2(dev, skb, true);
+}
 EXPORT_SYMBOL_GPL(__dev_forward_skb);
 
 /**
@@ -2250,6 +2241,11 @@ int dev_forward_skb(struct net_device *dev, struct sk_buff *skb)
 }
 EXPORT_SYMBOL_GPL(dev_forward_skb);
 
+int dev_forward_skb_nomtu(struct net_device *dev, struct sk_buff *skb)
+{
+	return __dev_forward_skb2(dev, skb, false) ?: netif_rx_internal(skb);
+}
+
 static inline int deliver_skb(struct sk_buff *skb,
 			      struct packet_type *pt_prev,
 			      struct net_device *orig_dev)
diff --git a/net/core/filter.c b/net/core/filter.c
index 18beaf82b8b8..0c1819b37fdf 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -2083,13 +2083,13 @@ static const struct bpf_func_proto bpf_csum_level_proto = {
 
 static inline int __bpf_rx_skb(struct net_device *dev, struct sk_buff *skb)
 {
-	return dev_forward_skb(dev, skb);
+	return dev_forward_skb_nomtu(dev, skb);
 }
 
 static inline int __bpf_rx_skb_no_mac(struct net_device *dev,
 				      struct sk_buff *skb)
 {
-	int ret = ____dev_forward_skb(dev, skb);
+	int ret = ____dev_forward_skb(dev, skb, false);
 
 	if (likely(!ret)) {
 		skb->dev = dev;
@@ -2480,7 +2480,7 @@ int skb_do_redirect(struct sk_buff *skb)
 			goto out_drop;
 		dev = ops->ndo_get_peer_dev(dev);
 		if (unlikely(!dev ||
-			     !is_skb_forwardable(dev, skb) ||
+			     !(dev->flags & IFF_UP) ||
 			     net_eq(net, dev_net(dev))))
 			goto out_drop;
 		skb->dev = dev;



  parent reply	other threads:[~2021-02-09 13:41 UTC|newest]

Thread overview: 9+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-02-09 13:38 [PATCH bpf-next V16 0/7] bpf: New approach for BPF MTU handling Jesper Dangaard Brouer
2021-02-09 13:38 ` [PATCH bpf-next V16 1/7] bpf: Remove MTU check in __bpf_skb_max_len Jesper Dangaard Brouer
2021-02-09 13:38 ` [PATCH bpf-next V16 2/7] bpf: fix bpf_fib_lookup helper MTU check for SKB ctx Jesper Dangaard Brouer
2021-02-09 13:38 ` [PATCH bpf-next V16 3/7] bpf: bpf_fib_lookup return MTU value as output when looked up Jesper Dangaard Brouer
2021-02-09 13:38 ` [PATCH bpf-next V16 4/7] bpf: add BPF-helper for MTU checking Jesper Dangaard Brouer
2021-02-09 13:38 ` Jesper Dangaard Brouer [this message]
2021-02-09 13:38 ` [PATCH bpf-next V16 6/7] selftests/bpf: use bpf_check_mtu in selftest test_cls_redirect Jesper Dangaard Brouer
2021-02-09 13:38 ` [PATCH bpf-next V16 7/7] selftests/bpf: tests using bpf_check_mtu BPF-helper Jesper Dangaard Brouer
2021-02-13  0:20 ` [PATCH bpf-next V16 0/7] bpf: New approach for BPF MTU handling patchwork-bot+netdevbpf

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=161287790971.790810.11785274340154740591.stgit@firesoul \
    --to=brouer@redhat.com \
    --cc=alexei.starovoitov@gmail.com \
    --cc=borkmann@iogearbox.net \
    --cc=bpf@vger.kernel.org \
    --cc=colrack@gmail.com \
    --cc=eyal.birger@gmail.com \
    --cc=john.fastabend@gmail.com \
    --cc=kuba@kernel.org \
    --cc=lmb@cloudflare.com \
    --cc=lorenzo@kernel.org \
    --cc=marek@cloudflare.com \
    --cc=maze@google.com \
    --cc=netdev@vger.kernel.org \
    --cc=shaun@tigera.io \
    --subject='Re: [PATCH bpf-next V16 5/7] bpf: drop MTU check when doing TC-BPF redirect to ingress' \
    /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).