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 V15 3/7] bpf: bpf_fib_lookup return MTU value as output when looked up
Date: Tue, 02 Feb 2021 17:26:56 +0100	[thread overview]
Message-ID: <161228321684.576669.10873647164254991996.stgit@firesoul> (raw)
In-Reply-To: <161228314075.576669.15427172810948915572.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.

V5:
 - Fixed uninit value spotted by Dan Carpenter.
 - Name struct output member mtu_result

Reported-by: kernel test robot <lkp@intel.com>
Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Acked-by: John Fastabend <john.fastabend@gmail.com>
---
 include/uapi/linux/bpf.h       |   11 +++++++++--
 net/core/filter.c              |   22 +++++++++++++++-------
 tools/include/uapi/linux/bpf.h |   11 +++++++++--
 3 files changed, 33 insertions(+), 11 deletions(-)

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index c001766adcbc..05bfc8c843dc 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -2231,6 +2231,9 @@ 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 output params->mtu_result 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.
@@ -4981,9 +4984,13 @@ 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; /* L3 length from network hdr (iph->tot_len) */
 
+		/* output: MTU value */
+		__u16	mtu_result;
+	};
 	/* 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 252fbb294001..7b1b9baaabd5 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -5289,12 +5289,14 @@ 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;
+	if (mtu)
+		params->mtu_result = mtu; /* union with tot_len */
 
 	return 0;
 }
@@ -5310,8 +5312,8 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct net_device *dev,
 	struct neighbour *neigh;
 	struct fib_result res;
 	struct flowi4 fl4;
+	u32 mtu = 0;
 	int err;
-	u32 mtu;
 
 	/* verify forwarding is enabled on this interface */
 	in_dev = __in_dev_get_rcu(dev);
@@ -5374,8 +5376,10 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct net_device *dev,
 
 	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_result = mtu; /* union with tot_len */
 			return BPF_FIB_LKUP_RET_FRAG_NEEDED;
+		}
 	}
 
 	nhc = res.nhc;
@@ -5409,7 +5413,7 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct net_device *dev,
 	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
 
@@ -5426,7 +5430,7 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct net_device *dev,
 	struct flowi6 fl6;
 	int strict = 0;
 	int oif, err;
-	u32 mtu;
+	u32 mtu = 0;
 
 	/* link local addresses are never forwarded */
 	if (rt6_need_strict(dst) || rt6_need_strict(src))
@@ -5497,8 +5501,10 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct net_device *dev,
 
 	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_result = mtu; /* union with tot_len */
 			return BPF_FIB_LKUP_RET_FRAG_NEEDED;
+		}
 	}
 
 	if (res.nh->fib_nh_lws)
@@ -5518,7 +5524,7 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct net_device *dev,
 	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
 
@@ -5601,6 +5607,8 @@ BPF_CALL_4(bpf_skb_fib_lookup, struct sk_buff *, skb,
 		 */
 		if (!is_skb_forwardable(dev, skb))
 			rc = BPF_FIB_LKUP_RET_FRAG_NEEDED;
+
+		params->mtu_result = 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 c001766adcbc..05bfc8c843dc 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -2231,6 +2231,9 @@ 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 output params->mtu_result 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.
@@ -4981,9 +4984,13 @@ 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; /* L3 length from network hdr (iph->tot_len) */
 
+		/* output: MTU value */
+		__u16	mtu_result;
+	};
 	/* input: L3 device index for lookup
 	 * output: device index from FIB lookup
 	 */



  parent reply	other threads:[~2021-02-02 16:51 UTC|newest]

Thread overview: 14+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-02-02 16:26 [PATCH bpf-next V15 0/7] bpf: New approach for BPF MTU handling Jesper Dangaard Brouer
2021-02-02 16:26 ` [PATCH bpf-next V15 1/7] bpf: Remove MTU check in __bpf_skb_max_len Jesper Dangaard Brouer
2021-02-02 16:26 ` [PATCH bpf-next V15 2/7] bpf: fix bpf_fib_lookup helper MTU check for SKB ctx Jesper Dangaard Brouer
2021-02-05  0:06   ` Daniel Borkmann
2021-02-08 13:57     ` Jesper Dangaard Brouer
2021-02-08 15:20       ` Jesper Dangaard Brouer
2021-02-08 15:41         ` Daniel Borkmann
2021-02-08 16:27           ` Jesper Dangaard Brouer
2021-02-08 16:46             ` Daniel Borkmann
2021-02-02 16:26 ` Jesper Dangaard Brouer [this message]
2021-02-02 16:27 ` [PATCH bpf-next V15 4/7] bpf: add BPF-helper for MTU checking Jesper Dangaard Brouer
2021-02-02 16:27 ` [PATCH bpf-next V15 5/7] bpf: drop MTU check when doing TC-BPF redirect to ingress Jesper Dangaard Brouer
2021-02-02 16:27 ` [PATCH bpf-next V15 6/7] selftests/bpf: use bpf_check_mtu in selftest test_cls_redirect Jesper Dangaard Brouer
2021-02-02 16:27 ` [PATCH bpf-next V15 7/7] selftests/bpf: tests using bpf_check_mtu BPF-helper Jesper Dangaard Brouer

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=161228321684.576669.10873647164254991996.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 \
    /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).