netdev.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
Subject: [PATCH bpf-next V3 2/6] bpf: bpf_fib_lookup return MTU value as output when looked up
Date: Thu, 08 Oct 2020 16:09:07 +0200	[thread overview]
Message-ID: <160216614748.882446.6805410687451779968.stgit@firesoul> (raw)
In-Reply-To: <160216609656.882446.16642490462568561112.stgit@firesoul>

The BPF-helpers for FIB lookup (bpf_xdp_fib_lookup and bpf_skb_fib_lookup)
can perform MTU check and return BPF_FIB_LKUP_RET_FRAG_NEEDED.  The BPF-prog
don't know the MTU value that caused this rejection.

If the BPF-prog wants to implement PMTU (Path MTU Discovery) (rfc1191) it
need to know this MTU value for the ICMP packet.

Patch change lookup and result struct bpf_fib_lookup, to contain this MTU
value as output via a union with 'tot_len' as this is the value used for
the MTU lookup.

Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
---
 include/uapi/linux/bpf.h       |   11 +++++++++--
 net/core/filter.c              |   17 ++++++++++++-----
 tools/include/uapi/linux/bpf.h |   11 +++++++++--
 3 files changed, 30 insertions(+), 9 deletions(-)

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index d83561e8cd2c..4a46a1de6d16 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -2216,6 +2216,9 @@ union bpf_attr {
  *		* > 0 one of **BPF_FIB_LKUP_RET_** codes explaining why the
  *		  packet is not forwarded or needs assist from full stack
  *
+ *		If lookup fails with BPF_FIB_LKUP_RET_FRAG_NEEDED, then the MTU
+ *		was exceeded and result params->mtu contains the MTU.
+ *
  * long bpf_sock_hash_update(struct bpf_sock_ops *skops, struct bpf_map *map, void *key, u64 flags)
  *	Description
  *		Add an entry to, or update a sockhash *map* referencing sockets.
@@ -4844,9 +4847,13 @@ struct bpf_fib_lookup {
 	__be16	sport;
 	__be16	dport;
 
-	/* total length of packet from network header - used for MTU check */
-	__u16	tot_len;
+	union {	/* used for MTU check */
+		/* input to lookup */
+		__u16	tot_len; /* total length of packet from network hdr */
 
+		/* output: MTU value (if requested check_mtu) */
+		__u16	mtu;
+	};
 	/* input: L3 device index for lookup
 	 * output: device index from FIB lookup
 	 */
diff --git a/net/core/filter.c b/net/core/filter.c
index ddc1f9ba89d1..da74d6ddc4d7 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -5186,13 +5186,14 @@ static const struct bpf_func_proto bpf_skb_get_xfrm_state_proto = {
 #if IS_ENABLED(CONFIG_INET) || IS_ENABLED(CONFIG_IPV6)
 static int bpf_fib_set_fwd_params(struct bpf_fib_lookup *params,
 				  const struct neighbour *neigh,
-				  const struct net_device *dev)
+				  const struct net_device *dev, u32 mtu)
 {
 	memcpy(params->dmac, neigh->ha, ETH_ALEN);
 	memcpy(params->smac, dev->dev_addr, ETH_ALEN);
 	params->h_vlan_TCI = 0;
 	params->h_vlan_proto = 0;
 	params->ifindex = dev->ifindex;
+	params->mtu = mtu;
 
 	return 0;
 }
@@ -5276,8 +5277,10 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
 
 	if (check_mtu) {
 		mtu = ip_mtu_from_fib_result(&res, params->ipv4_dst);
-		if (params->tot_len > mtu)
+		if (params->tot_len > mtu) {
+			params->mtu = mtu; /* union with tot_len */
 			return BPF_FIB_LKUP_RET_FRAG_NEEDED;
+		}
 	}
 
 	nhc = res.nhc;
@@ -5310,7 +5313,7 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
 	if (!neigh)
 		return BPF_FIB_LKUP_RET_NO_NEIGH;
 
-	return bpf_fib_set_fwd_params(params, neigh, dev);
+	return bpf_fib_set_fwd_params(params, neigh, dev, mtu);
 }
 #endif
 
@@ -5402,8 +5405,10 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
 
 	if (check_mtu) {
 		mtu = ipv6_stub->ip6_mtu_from_fib6(&res, dst, src);
-		if (params->tot_len > mtu)
+		if (params->tot_len > mtu) {
+			params->mtu = mtu; /* union with tot_len */
 			return BPF_FIB_LKUP_RET_FRAG_NEEDED;
+		}
 	}
 
 	if (res.nh->fib_nh_lws)
@@ -5422,7 +5427,7 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
 	if (!neigh)
 		return BPF_FIB_LKUP_RET_NO_NEIGH;
 
-	return bpf_fib_set_fwd_params(params, neigh, dev);
+	return bpf_fib_set_fwd_params(params, neigh, dev, mtu);
 }
 #endif
 
@@ -5491,6 +5496,8 @@ BPF_CALL_4(bpf_skb_fib_lookup, struct sk_buff *, skb,
 		dev = dev_get_by_index_rcu(net, params->ifindex);
 		if (!is_skb_forwardable(dev, skb))
 			rc = BPF_FIB_LKUP_RET_FRAG_NEEDED;
+
+		params->mtu = dev->mtu; /* union with tot_len */
 	}
 
 	return rc;
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index d83561e8cd2c..4a46a1de6d16 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -2216,6 +2216,9 @@ union bpf_attr {
  *		* > 0 one of **BPF_FIB_LKUP_RET_** codes explaining why the
  *		  packet is not forwarded or needs assist from full stack
  *
+ *		If lookup fails with BPF_FIB_LKUP_RET_FRAG_NEEDED, then the MTU
+ *		was exceeded and result params->mtu contains the MTU.
+ *
  * long bpf_sock_hash_update(struct bpf_sock_ops *skops, struct bpf_map *map, void *key, u64 flags)
  *	Description
  *		Add an entry to, or update a sockhash *map* referencing sockets.
@@ -4844,9 +4847,13 @@ struct bpf_fib_lookup {
 	__be16	sport;
 	__be16	dport;
 
-	/* total length of packet from network header - used for MTU check */
-	__u16	tot_len;
+	union {	/* used for MTU check */
+		/* input to lookup */
+		__u16	tot_len; /* total length of packet from network hdr */
 
+		/* output: MTU value (if requested check_mtu) */
+		__u16	mtu;
+	};
 	/* input: L3 device index for lookup
 	 * output: device index from FIB lookup
 	 */



  parent reply	other threads:[~2020-10-08 14:09 UTC|newest]

Thread overview: 32+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-10-08 14:08 [PATCH bpf-next V3 0/6] bpf: New approach for BPF MTU handling Jesper Dangaard Brouer
2020-10-08 14:09 ` [PATCH bpf-next V3 1/6] bpf: Remove MTU check in __bpf_skb_max_len Jesper Dangaard Brouer
2020-10-09 16:12   ` Daniel Borkmann
2020-10-09 18:26     ` Maciej Żenczykowski
2020-10-10 10:25     ` Jesper Dangaard Brouer
2020-10-08 14:09 ` Jesper Dangaard Brouer [this message]
2020-10-09  4:05   ` [PATCH bpf-next V3 2/6] bpf: bpf_fib_lookup return MTU value as output when looked up David Ahern
2020-10-08 14:09 ` [PATCH bpf-next V3 3/6] bpf: add BPF-helper for MTU checking Jesper Dangaard Brouer
2020-10-09 23:29   ` Maciej Żenczykowski
2020-10-21 11:32     ` Jesper Dangaard Brouer
2020-10-12 15:54   ` Lorenz Bauer
2020-10-08 14:09 ` [PATCH bpf-next V3 4/6] bpf: make it possible to identify BPF redirected SKBs Jesper Dangaard Brouer
2020-10-09 16:47   ` Daniel Borkmann
2020-10-09 18:33     ` Maciej Żenczykowski
2020-10-10 11:09       ` Jesper Dangaard Brouer
2020-10-12 21:04         ` Maciej Żenczykowski
2020-10-08 14:09 ` [PATCH bpf-next V3 5/6] bpf: drop MTU check when doing TC-BPF redirect to ingress Jesper Dangaard Brouer
2020-10-09 23:17   ` Maciej Żenczykowski
2020-10-08 14:09 ` [PATCH bpf-next V3 6/6] net: inline and splitup is_skb_forwardable Jesper Dangaard Brouer
2020-10-09 16:33 ` [PATCH bpf-next V3 0/6] bpf: New approach for BPF MTU handling Jakub Kicinski
2020-10-09 20:49   ` John Fastabend
2020-10-09 21:07     ` Alexei Starovoitov
2020-10-09 21:57       ` Maciej Żenczykowski
2020-10-09 23:00     ` Jakub Kicinski
2020-10-10 10:44       ` Jesper Dangaard Brouer
2020-10-10 16:32         ` Jakub Kicinski
2020-10-10 23:52           ` John Fastabend
2020-10-11 23:30             ` Jakub Kicinski
2020-10-13 20:40           ` Jesper Dangaard Brouer
2020-10-13 23:07             ` Jakub Kicinski
2020-10-13 23:37               ` Alexei Starovoitov
2020-10-13 23:54                 ` Maciej Żenczykowski

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=160216614748.882446.6805410687451779968.stgit@firesoul \
    --to=brouer@redhat.com \
    --cc=alexei.starovoitov@gmail.com \
    --cc=borkmann@iogearbox.net \
    --cc=bpf@vger.kernel.org \
    --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 \
    /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).