| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <20230505-bpf-add-tbid-fib-lookup-v2-1-0a31c22c748c@gmail.com>
Date: Wed, 31 May 2023 15:38:48 -0400
From: Louis DeLosSantos <louis.delos.devel@...il.com>
To: bpf@...r.kernel.org, netdev@...r.kernel.org
Cc: Martin KaFai Lau <martin.lau@...ux.dev>,
Stanislav Fomichev <sdf@...gle.com>, razor@...ckwall.org,
John Fastabend <john.fastabend@...il.com>, Yonghong Song <yhs@...a.com>,
Louis DeLosSantos <louis.delos.devel@...il.com>
Subject: [PATCH v2 1/2] bpf: add table ID to bpf_fib_lookup BPF helper
Add ability to specify routing table ID to the `bpf_fib_lookup` BPF
helper.
A new field `tbid` is added to `struct bpf_fib_lookup` used as
parameters to the `bpf_fib_lookup` BPF helper.
When the helper is called with the `BPF_FIB_LOOKUP_DIRECT` and
`BPF_FIB_LOOKUP_TBID` flags the `tbid` field in `struct bpf_fib_lookup`
will be used as the table ID for the fib lookup.
If the `tbid` does not exist the fib lookup will fail with
`BPF_FIB_LKUP_RET_NOT_FWDED`.
The `tbid` field becomes a union over the vlan related output fields in
`struct bpf_fib_lookup` and will be zeroed immediately after usage.
This functionality is useful in containerized environments.
For instance, if a CNI wants to dictate the next-hop for traffic leaving
a container it can create a container-specific routing table and perform
a fib lookup against this table in a "host-net-namespace-side" TC program.
This functionality also allows `ip rule` like functionality at the TC
layer, allowing an eBPF program to pick a routing table based on some
aspect of the sk_buff.
As a concrete use case, this feature will be used in Cilium's SRv6 L3VPN
datapath.
When egress traffic leaves a Pod an eBPF program attached by Cilium will
determine which VRF the egress traffic should target, and then perform a
FIB lookup in a specific table representing this VRF's FIB.
Signed-off-by: Louis DeLosSantos <louis.delos.devel@...il.com>
---
include/uapi/linux/bpf.h | 21 ++++++++++++++++++---
net/core/filter.c | 14 +++++++++++++-
tools/include/uapi/linux/bpf.h | 21 ++++++++++++++++++---
3 files changed, 49 insertions(+), 7 deletions(-)
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 1bb11a6ee6676..6254eac48b185 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -3167,6 +3167,10 @@ union bpf_attr {
* **BPF_FIB_LOOKUP_DIRECT**
* Do a direct table lookup vs full lookup using FIB
* rules.
+ * **BPF_FIB_LOOKUP_TBID**
+ * Used with BPF_FIB_LOOKUP_DIRECT.
+ * Use the routing table ID present in *params*->tbid
+ * for the fib lookup.
* **BPF_FIB_LOOKUP_OUTPUT**
* Perform lookup from an egress perspective (default is
* ingress).
@@ -6821,6 +6825,7 @@ enum {
BPF_FIB_LOOKUP_DIRECT = (1U << 0),
BPF_FIB_LOOKUP_OUTPUT = (1U << 1),
BPF_FIB_LOOKUP_SKIP_NEIGH = (1U << 2),
+ BPF_FIB_LOOKUP_TBID = (1U << 3),
};
enum {
@@ -6881,9 +6886,19 @@ struct bpf_fib_lookup {
__u32 ipv6_dst[4]; /* in6_addr; network order */
};
- /* output */
- __be16 h_vlan_proto;
- __be16 h_vlan_TCI;
+ union {
+ struct {
+ /* output */
+ __be16 h_vlan_proto;
+ __be16 h_vlan_TCI;
+ };
+ /* input: when accompanied with the
+ * 'BPF_FIB_LOOKUP_DIRECT | BPF_FIB_LOOKUP_TBID` flags, a
+ * specific routing table to use for the fib lookup.
+ */
+ __u32 tbid;
+ };
+
__u8 smac[6]; /* ETH_ALEN */
__u8 dmac[6]; /* ETH_ALEN */
};
diff --git a/net/core/filter.c b/net/core/filter.c
index 451b0ec7f2421..6a97a2aeabc10 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -5803,6 +5803,12 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
u32 tbid = l3mdev_fib_table_rcu(dev) ? : RT_TABLE_MAIN;
struct fib_table *tb;
+ if (flags & BPF_FIB_LOOKUP_TBID) {
+ tbid = params->tbid;
+ /* zero out for vlan output */
+ params->tbid = 0;
+ }
+
tb = fib_get_table(net, tbid);
if (unlikely(!tb))
return BPF_FIB_LKUP_RET_NOT_FWDED;
@@ -5936,6 +5942,12 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
u32 tbid = l3mdev_fib_table_rcu(dev) ? : RT_TABLE_MAIN;
struct fib6_table *tb;
+ if (flags & BPF_FIB_LOOKUP_TBID) {
+ tbid = params->tbid;
+ /* zero out for vlan output */
+ params->tbid = 0;
+ }
+
tb = ipv6_stub->fib6_get_table(net, tbid);
if (unlikely(!tb))
return BPF_FIB_LKUP_RET_NOT_FWDED;
@@ -6008,7 +6020,7 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
#endif
#define BPF_FIB_LOOKUP_MASK (BPF_FIB_LOOKUP_DIRECT | BPF_FIB_LOOKUP_OUTPUT | \
- BPF_FIB_LOOKUP_SKIP_NEIGH)
+ BPF_FIB_LOOKUP_SKIP_NEIGH | BPF_FIB_LOOKUP_TBID)
BPF_CALL_4(bpf_xdp_fib_lookup, struct xdp_buff *, ctx,
struct bpf_fib_lookup *, params, int, plen, u32, flags)
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 1bb11a6ee6676..6254eac48b185 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -3167,6 +3167,10 @@ union bpf_attr {
* **BPF_FIB_LOOKUP_DIRECT**
* Do a direct table lookup vs full lookup using FIB
* rules.
+ * **BPF_FIB_LOOKUP_TBID**
+ * Used with BPF_FIB_LOOKUP_DIRECT.
+ * Use the routing table ID present in *params*->tbid
+ * for the fib lookup.
* **BPF_FIB_LOOKUP_OUTPUT**
* Perform lookup from an egress perspective (default is
* ingress).
@@ -6821,6 +6825,7 @@ enum {
BPF_FIB_LOOKUP_DIRECT = (1U << 0),
BPF_FIB_LOOKUP_OUTPUT = (1U << 1),
BPF_FIB_LOOKUP_SKIP_NEIGH = (1U << 2),
+ BPF_FIB_LOOKUP_TBID = (1U << 3),
};
enum {
@@ -6881,9 +6886,19 @@ struct bpf_fib_lookup {
__u32 ipv6_dst[4]; /* in6_addr; network order */
};
- /* output */
- __be16 h_vlan_proto;
- __be16 h_vlan_TCI;
+ union {
+ struct {
+ /* output */
+ __be16 h_vlan_proto;
+ __be16 h_vlan_TCI;
+ };
+ /* input: when accompanied with the
+ * 'BPF_FIB_LOOKUP_DIRECT | BPF_FIB_LOOKUP_TBID` flags, a
+ * specific routing table to use for the fib lookup.
+ */
+ __u32 tbid;
+ };
+
__u8 smac[6]; /* ETH_ALEN */
__u8 dmac[6]; /* ETH_ALEN */
};
--
2.40.1
Powered by blists - more mailing lists