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 V14 2/7] bpf: fix bpf_fib_lookup helper MTU check for SKB ctx
Date: Mon, 01 Feb 2021 11:52:16 +0100 [thread overview]
Message-ID: <161217673648.494501.14458670792610885379.stgit@firesoul> (raw)
In-Reply-To: <161217668357.494501.557971074995969677.stgit@firesoul>
BPF end-user on Cilium slack-channel (Carlo Carraro) wants to use
bpf_fib_lookup for doing MTU-check, but *prior* to extending packet size,
by adjusting fib_params 'tot_len' with the packet length plus the expected
encap size. (Just like the bpf_check_mtu helper supports). He discovered
that for SKB ctx the param->tot_len was not used, instead skb->len was used
(via MTU check in is_skb_forwardable() that checks against netdev MTU).
Fix this by using fib_params 'tot_len' for MTU check. If not provided (e.g.
zero) then keep existing TC behaviour intact. Notice that 'tot_len' for MTU
check is done like XDP code-path, which checks against FIB-dst MTU.
V13:
- Only do ifindex lookup one time, calling dev_get_by_index_rcu().
V10:
- Use same method as XDP for 'tot_len' MTU check
Fixes: 4c79579b44b1 ("bpf: Change bpf_fib_lookup to return lookup status")
Reported-by: Carlo Carraro <colrack@gmail.com>
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Acked-by: John Fastabend <john.fastabend@gmail.com>
---
net/core/filter.c | 50 ++++++++++++++++++++++++++++----------------------
1 file changed, 28 insertions(+), 22 deletions(-)
diff --git a/net/core/filter.c b/net/core/filter.c
index 5beadd659091..252fbb294001 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -5301,22 +5301,18 @@ static int bpf_fib_set_fwd_params(struct bpf_fib_lookup *params,
#endif
#if IS_ENABLED(CONFIG_INET)
-static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
+static int bpf_ipv4_fib_lookup(struct net *net, struct net_device *dev,
+ struct bpf_fib_lookup *params,
u32 flags, bool check_mtu)
{
struct fib_nh_common *nhc;
struct in_device *in_dev;
struct neighbour *neigh;
- struct net_device *dev;
struct fib_result res;
struct flowi4 fl4;
int err;
u32 mtu;
- dev = dev_get_by_index_rcu(net, params->ifindex);
- if (unlikely(!dev))
- return -ENODEV;
-
/* verify forwarding is enabled on this interface */
in_dev = __in_dev_get_rcu(dev);
if (unlikely(!in_dev || !IN_DEV_FORWARD(in_dev)))
@@ -5418,14 +5414,14 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
#endif
#if IS_ENABLED(CONFIG_IPV6)
-static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
+static int bpf_ipv6_fib_lookup(struct net *net, struct net_device *dev,
+ struct bpf_fib_lookup *params,
u32 flags, bool check_mtu)
{
struct in6_addr *src = (struct in6_addr *) params->ipv6_src;
struct in6_addr *dst = (struct in6_addr *) params->ipv6_dst;
struct fib6_result res = {};
struct neighbour *neigh;
- struct net_device *dev;
struct inet6_dev *idev;
struct flowi6 fl6;
int strict = 0;
@@ -5436,10 +5432,6 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
if (rt6_need_strict(dst) || rt6_need_strict(src))
return BPF_FIB_LKUP_RET_NOT_FWDED;
- dev = dev_get_by_index_rcu(net, params->ifindex);
- if (unlikely(!dev))
- return -ENODEV;
-
idev = __in6_dev_get_safely(dev);
if (unlikely(!idev || !idev->cnf.forwarding))
return BPF_FIB_LKUP_RET_FWD_DISABLED;
@@ -5533,22 +5525,27 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
BPF_CALL_4(bpf_xdp_fib_lookup, struct xdp_buff *, ctx,
struct bpf_fib_lookup *, params, int, plen, u32, flags)
{
+ struct net *net = dev_net(ctx->rxq->dev);
+ struct net_device *dev;
+
if (plen < sizeof(*params))
return -EINVAL;
if (flags & ~(BPF_FIB_LOOKUP_DIRECT | BPF_FIB_LOOKUP_OUTPUT))
return -EINVAL;
+ dev = dev_get_by_index_rcu(net, params->ifindex);
+ if (unlikely(!dev))
+ return -ENODEV;
+
switch (params->family) {
#if IS_ENABLED(CONFIG_INET)
case AF_INET:
- return bpf_ipv4_fib_lookup(dev_net(ctx->rxq->dev), params,
- flags, true);
+ return bpf_ipv4_fib_lookup(net, dev, params, flags, true);
#endif
#if IS_ENABLED(CONFIG_IPV6)
case AF_INET6:
- return bpf_ipv6_fib_lookup(dev_net(ctx->rxq->dev), params,
- flags, true);
+ return bpf_ipv6_fib_lookup(net, dev, params, flags, true);
#endif
}
return -EAFNOSUPPORT;
@@ -5568,7 +5565,9 @@ BPF_CALL_4(bpf_skb_fib_lookup, struct sk_buff *, skb,
struct bpf_fib_lookup *, params, int, plen, u32, flags)
{
struct net *net = dev_net(skb->dev);
+ struct net_device *dev;
int rc = -EAFNOSUPPORT;
+ bool check_mtu = false;
if (plen < sizeof(*params))
return -EINVAL;
@@ -5576,23 +5575,30 @@ BPF_CALL_4(bpf_skb_fib_lookup, struct sk_buff *, skb,
if (flags & ~(BPF_FIB_LOOKUP_DIRECT | BPF_FIB_LOOKUP_OUTPUT))
return -EINVAL;
+ dev = dev_get_by_index_rcu(net, params->ifindex);
+ if (unlikely(!dev))
+ return -ENODEV;
+
+ if (params->tot_len)
+ check_mtu = true;
+
switch (params->family) {
#if IS_ENABLED(CONFIG_INET)
case AF_INET:
- rc = bpf_ipv4_fib_lookup(net, params, flags, false);
+ rc = bpf_ipv4_fib_lookup(net, dev, params, flags, check_mtu);
break;
#endif
#if IS_ENABLED(CONFIG_IPV6)
case AF_INET6:
- rc = bpf_ipv6_fib_lookup(net, params, flags, false);
+ rc = bpf_ipv6_fib_lookup(net, dev, params, flags, check_mtu);
break;
#endif
}
- if (!rc) {
- struct net_device *dev;
-
- dev = dev_get_by_index_rcu(net, params->ifindex);
+ if (rc == BPF_FIB_LKUP_RET_SUCCESS && !check_mtu) {
+ /* When tot_len isn't provided by user,
+ * check skb against net_device MTU
+ */
if (!is_skb_forwardable(dev, skb))
rc = BPF_FIB_LKUP_RET_FRAG_NEEDED;
}
next prev parent reply other threads:[~2021-02-01 10:56 UTC|newest]
Thread overview: 9+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-02-01 10:52 [PATCH bpf-next V14 0/7] bpf: New approach for BPF MTU handling Jesper Dangaard Brouer
2021-02-01 10:52 ` [PATCH bpf-next V14 1/7] bpf: Remove MTU check in __bpf_skb_max_len Jesper Dangaard Brouer
2021-02-01 10:52 ` Jesper Dangaard Brouer [this message]
2021-02-01 10:52 ` [PATCH bpf-next V14 3/7] bpf: bpf_fib_lookup return MTU value as output when looked up Jesper Dangaard Brouer
2021-02-01 10:52 ` [PATCH bpf-next V14 4/7] bpf: add BPF-helper for MTU checking Jesper Dangaard Brouer
2021-02-01 10:52 ` [PATCH bpf-next V14 5/7] bpf: drop MTU check when doing TC-BPF redirect to ingress Jesper Dangaard Brouer
2021-02-01 19:58 ` kernel test robot
2021-02-01 10:52 ` [PATCH bpf-next V14 6/7] selftests/bpf: use bpf_check_mtu in selftest test_cls_redirect Jesper Dangaard Brouer
2021-02-01 10:52 ` [PATCH bpf-next V14 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=161217673648.494501.14458670792610885379.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).