--- /dev/null
+From ddc8f013eda8d06600cf0d832feac578fd5cffa3 Mon Sep 17 00:00:00 2001
+From: Louis DeLosSantos <louis.delos.devel@gmail.com>
+Date: Wed, 31 May 2023 15:38:48 -0400
+Subject: bpf: Add table ID to bpf_fib_lookup BPF helper
+
+From: Louis DeLosSantos <louis.delos.devel@gmail.com>
+
+commit 8ad77e72caae22a1ddcfd0c03f2884929e93b7a4 upstream.
+
+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@gmail.com>
+Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
+Link: https://lore.kernel.org/bpf/20230505-bpf-add-tbid-fib-lookup-v2-1-0a31c22c748c@gmail.com
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ 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(-)
+
+--- a/include/uapi/linux/bpf.h
++++ b/include/uapi/linux/bpf.h
+@@ -3109,6 +3109,10 @@ 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).
+@@ -6687,6 +6691,7 @@ 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 {
+@@ -6747,9 +6752,19 @@ 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 */
+ };
+--- a/net/core/filter.c
++++ b/net/core/filter.c
+@@ -5752,6 +5752,12 @@ static int bpf_ipv4_fib_lookup(struct ne
+ 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;
+@@ -5885,6 +5891,12 @@ static int bpf_ipv6_fib_lookup(struct ne
+ 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;
+@@ -5957,7 +5969,7 @@ set_fwd_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)
+--- a/tools/include/uapi/linux/bpf.h
++++ b/tools/include/uapi/linux/bpf.h
+@@ -3109,6 +3109,10 @@ 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).
+@@ -6687,6 +6691,7 @@ 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 {
+@@ -6747,9 +6752,19 @@ 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 */
+ };
--- /dev/null
+From db9010b83cc326ed468c56ee3ba23fd97464d4aa Mon Sep 17 00:00:00 2001
+From: Martynas Pumputis <m@lambda.lt>
+Date: Sat, 7 Oct 2023 10:14:14 +0200
+Subject: bpf: Derive source IP addr via bpf_*_fib_lookup()
+
+From: Martynas Pumputis <m@lambda.lt>
+
+commit dab4e1f06cabb6834de14264394ccab197007302 upstream.
+
+Extend the bpf_fib_lookup() helper by making it to return the source
+IPv4/IPv6 address if the BPF_FIB_LOOKUP_SRC flag is set.
+
+For example, the following snippet can be used to derive the desired
+source IP address:
+
+ struct bpf_fib_lookup p = { .ipv4_dst = ip4->daddr };
+
+ ret = bpf_skb_fib_lookup(skb, p, sizeof(p),
+ BPF_FIB_LOOKUP_SRC | BPF_FIB_LOOKUP_SKIP_NEIGH);
+ if (ret != BPF_FIB_LKUP_RET_SUCCESS)
+ return TC_ACT_SHOT;
+
+ /* the p.ipv4_src now contains the source address */
+
+The inability to derive the proper source address may cause malfunctions
+in BPF-based dataplanes for hosts containing netdevs with more than one
+routable IP address or for multi-homed hosts.
+
+For example, Cilium implements packet masquerading in BPF. If an
+egressing netdev to which the Cilium's BPF prog is attached has
+multiple IP addresses, then only one [hardcoded] IP address can be used for
+masquerading. This breaks connectivity if any other IP address should have
+been selected instead, for example, when a public and private addresses
+are attached to the same egress interface.
+
+The change was tested with Cilium [1].
+
+Nikolay Aleksandrov helped to figure out the IPv6 addr selection.
+
+[1]: https://github.com/cilium/cilium/pull/28283
+
+Signed-off-by: Martynas Pumputis <m@lambda.lt>
+Link: https://lore.kernel.org/r/20231007081415.33502-2-m@lambda.lt
+Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
+Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ include/net/ipv6_stubs.h | 5 +++++
+ include/uapi/linux/bpf.h | 10 ++++++++++
+ net/core/filter.c | 18 +++++++++++++++++-
+ net/ipv6/af_inet6.c | 1 +
+ tools/include/uapi/linux/bpf.h | 10 ++++++++++
+ 5 files changed, 43 insertions(+), 1 deletion(-)
+
+--- a/include/net/ipv6_stubs.h
++++ b/include/net/ipv6_stubs.h
+@@ -85,6 +85,11 @@ struct ipv6_bpf_stub {
+ sockptr_t optval, unsigned int optlen);
+ int (*ipv6_getsockopt)(struct sock *sk, int level, int optname,
+ sockptr_t optval, sockptr_t optlen);
++ int (*ipv6_dev_get_saddr)(struct net *net,
++ const struct net_device *dst_dev,
++ const struct in6_addr *daddr,
++ unsigned int prefs,
++ struct in6_addr *saddr);
+ };
+ extern const struct ipv6_bpf_stub *ipv6_bpf_stub __read_mostly;
+
+--- a/include/uapi/linux/bpf.h
++++ b/include/uapi/linux/bpf.h
+@@ -3121,6 +3121,11 @@ union bpf_attr {
+ * and *params*->smac will not be set as output. A common
+ * use case is to call **bpf_redirect_neigh**\ () after
+ * doing **bpf_fib_lookup**\ ().
++ * **BPF_FIB_LOOKUP_SRC**
++ * Derive and set source IP addr in *params*->ipv{4,6}_src
++ * for the nexthop. If the src addr cannot be derived,
++ * **BPF_FIB_LKUP_RET_NO_SRC_ADDR** is returned. In this
++ * case, *params*->dmac and *params*->smac are not set either.
+ *
+ * *ctx* is either **struct xdp_md** for XDP programs or
+ * **struct sk_buff** tc cls_act programs.
+@@ -6692,6 +6697,7 @@ enum {
+ BPF_FIB_LOOKUP_OUTPUT = (1U << 1),
+ BPF_FIB_LOOKUP_SKIP_NEIGH = (1U << 2),
+ BPF_FIB_LOOKUP_TBID = (1U << 3),
++ BPF_FIB_LOOKUP_SRC = (1U << 4),
+ };
+
+ enum {
+@@ -6704,6 +6710,7 @@ enum {
+ BPF_FIB_LKUP_RET_UNSUPP_LWT, /* fwd requires encapsulation */
+ BPF_FIB_LKUP_RET_NO_NEIGH, /* no neighbor entry for nh */
+ BPF_FIB_LKUP_RET_FRAG_NEEDED, /* fragmentation required to fwd */
++ BPF_FIB_LKUP_RET_NO_SRC_ADDR, /* failed to derive IP src addr */
+ };
+
+ struct bpf_fib_lookup {
+@@ -6738,6 +6745,9 @@ struct bpf_fib_lookup {
+ __u32 rt_metric;
+ };
+
++ /* input: source address to consider for lookup
++ * output: source address result from lookup
++ */
+ union {
+ __be32 ipv4_src;
+ __u32 ipv6_src[4]; /* in6_addr; network order */
+--- a/net/core/filter.c
++++ b/net/core/filter.c
+@@ -5809,6 +5809,9 @@ static int bpf_ipv4_fib_lookup(struct ne
+ params->rt_metric = res.fi->fib_priority;
+ params->ifindex = dev->ifindex;
+
++ if (flags & BPF_FIB_LOOKUP_SRC)
++ params->ipv4_src = fib_result_prefsrc(net, &res);
++
+ /* xdp and cls_bpf programs are run in RCU-bh so
+ * rcu_read_lock_bh is not needed here
+ */
+@@ -5951,6 +5954,18 @@ static int bpf_ipv6_fib_lookup(struct ne
+ params->rt_metric = res.f6i->fib6_metric;
+ params->ifindex = dev->ifindex;
+
++ if (flags & BPF_FIB_LOOKUP_SRC) {
++ if (res.f6i->fib6_prefsrc.plen) {
++ *src = res.f6i->fib6_prefsrc.addr;
++ } else {
++ err = ipv6_bpf_stub->ipv6_dev_get_saddr(net, dev,
++ &fl6.daddr, 0,
++ src);
++ if (err)
++ return BPF_FIB_LKUP_RET_NO_SRC_ADDR;
++ }
++ }
++
+ if (flags & BPF_FIB_LOOKUP_SKIP_NEIGH)
+ goto set_fwd_params;
+
+@@ -5969,7 +5984,8 @@ set_fwd_params:
+ #endif
+
+ #define BPF_FIB_LOOKUP_MASK (BPF_FIB_LOOKUP_DIRECT | BPF_FIB_LOOKUP_OUTPUT | \
+- BPF_FIB_LOOKUP_SKIP_NEIGH | BPF_FIB_LOOKUP_TBID)
++ BPF_FIB_LOOKUP_SKIP_NEIGH | BPF_FIB_LOOKUP_TBID | \
++ BPF_FIB_LOOKUP_SRC)
+
+ BPF_CALL_4(bpf_xdp_fib_lookup, struct xdp_buff *, ctx,
+ struct bpf_fib_lookup *, params, int, plen, u32, flags)
+--- a/net/ipv6/af_inet6.c
++++ b/net/ipv6/af_inet6.c
+@@ -1077,6 +1077,7 @@ static const struct ipv6_bpf_stub ipv6_b
+ .udp6_lib_lookup = __udp6_lib_lookup,
+ .ipv6_setsockopt = do_ipv6_setsockopt,
+ .ipv6_getsockopt = do_ipv6_getsockopt,
++ .ipv6_dev_get_saddr = ipv6_dev_get_saddr,
+ };
+
+ static int __init inet6_init(void)
+--- a/tools/include/uapi/linux/bpf.h
++++ b/tools/include/uapi/linux/bpf.h
+@@ -3121,6 +3121,11 @@ union bpf_attr {
+ * and *params*->smac will not be set as output. A common
+ * use case is to call **bpf_redirect_neigh**\ () after
+ * doing **bpf_fib_lookup**\ ().
++ * **BPF_FIB_LOOKUP_SRC**
++ * Derive and set source IP addr in *params*->ipv{4,6}_src
++ * for the nexthop. If the src addr cannot be derived,
++ * **BPF_FIB_LKUP_RET_NO_SRC_ADDR** is returned. In this
++ * case, *params*->dmac and *params*->smac are not set either.
+ *
+ * *ctx* is either **struct xdp_md** for XDP programs or
+ * **struct sk_buff** tc cls_act programs.
+@@ -6692,6 +6697,7 @@ enum {
+ BPF_FIB_LOOKUP_OUTPUT = (1U << 1),
+ BPF_FIB_LOOKUP_SKIP_NEIGH = (1U << 2),
+ BPF_FIB_LOOKUP_TBID = (1U << 3),
++ BPF_FIB_LOOKUP_SRC = (1U << 4),
+ };
+
+ enum {
+@@ -6704,6 +6710,7 @@ enum {
+ BPF_FIB_LKUP_RET_UNSUPP_LWT, /* fwd requires encapsulation */
+ BPF_FIB_LKUP_RET_NO_NEIGH, /* no neighbor entry for nh */
+ BPF_FIB_LKUP_RET_FRAG_NEEDED, /* fragmentation required to fwd */
++ BPF_FIB_LKUP_RET_NO_SRC_ADDR, /* failed to derive IP src addr */
+ };
+
+ struct bpf_fib_lookup {
+@@ -6738,6 +6745,9 @@ struct bpf_fib_lookup {
+ __u32 rt_metric;
+ };
+
++ /* input: source address to consider for lookup
++ * output: source address result from lookup
++ */
+ union {
+ __be32 ipv4_src;
+ __u32 ipv6_src[4]; /* in6_addr; network order */
projects / thirdparty / kernel / stable-queue.git / commitdiff
