[v5,bpf-next,2/3] netfilter: add bpf_xdp_flow_lookup kfunc

Commit Message

Lorenzo Bianconi June 14, 2024, 3:40 p.m. UTC

Introduce bpf_xdp_flow_lookup kfunc in order to perform the lookup
of a given flowtable entry based on a fib tuple of incoming traffic.
bpf_xdp_flow_lookup can be used as building block to offload in xdp
the processing of sw flowtable when hw flowtable is not available.

Acked-by: Kumar Kartikeya Dwivedi <[e-mail]>
Signed-off-by: Lorenzo Bianconi <[e-mail]>
---
 include/net/netfilter/nf_flow_table.h |  10 +++
 net/netfilter/Makefile                |   5 ++
 net/netfilter/nf_flow_table_bpf.c     | 117 ++++++++++++++++++++++++++
 net/netfilter/nf_flow_table_inet.c    |   2 +-
 4 files changed, 133 insertions(+), 1 deletion(-)
 create mode 100644 net/netfilter/nf_flow_table_bpf.c

Comments

Daniel Borkmann June 28, 2024, 9:21 p.m. UTC | #1

On 6/14/24 5:40 PM, Lorenzo Bianconi wrote:
[...]
> +enum {
> +	NF_BPF_FLOWTABLE_OPTS_SZ = 4,
> +};
> +
> +__diag_push();
> +__diag_ignore_all("-Wmissing-prototypes",
> +		  "Global functions as their definitions will be in nf_flow_table BTF");

nit: __bpf_kfunc_start_defs();

> +static struct flow_offload_tuple_rhash *
> +bpf_xdp_flow_tuple_lookup(struct net_device *dev,
> +			  struct flow_offload_tuple *tuple, __be16 proto)
> +{
> +	struct flow_offload_tuple_rhash *tuplehash;
> +	struct nf_flowtable *nf_flow_table;
> +	struct flow_offload *nf_flow;
> +
> +	nf_flow_table = nf_flowtable_by_dev(dev);
> +	if (!nf_flow_table)
> +		return ERR_PTR(-ENOENT);
> +
> +	tuplehash = flow_offload_lookup(nf_flow_table, tuple);
> +	if (!tuplehash)
> +		return ERR_PTR(-ENOENT);
> +
> +	nf_flow = container_of(tuplehash, struct flow_offload,
> +			       tuplehash[tuplehash->tuple.dir]);
> +	flow_offload_refresh(nf_flow_table, nf_flow, false);
> +
> +	return tuplehash;
> +}
> +
> +__bpf_kfunc struct flow_offload_tuple_rhash *
> +bpf_xdp_flow_lookup(struct xdp_md *ctx, struct bpf_fib_lookup *fib_tuple,
> +		    struct bpf_flowtable_opts *opts, u32 opts_len)
> +{
> +	struct xdp_buff *xdp = (struct xdp_buff *)ctx;
> +	struct flow_offload_tuple tuple = {
> +		.iifidx = fib_tuple->ifindex,
> +		.l3proto = fib_tuple->family,
> +		.l4proto = fib_tuple->l4_protocol,
> +		.src_port = fib_tuple->sport,
> +		.dst_port = fib_tuple->dport,
> +	};
> +	struct flow_offload_tuple_rhash *tuplehash;
> +	__be16 proto;
> +
> +	if (opts_len != NF_BPF_FLOWTABLE_OPTS_SZ) {
> +		opts->error = -EINVAL;
> +		return NULL;
> +	}
> +
> +	switch (fib_tuple->family) {
> +	case AF_INET:
> +		tuple.src_v4.s_addr = fib_tuple->ipv4_src;
> +		tuple.dst_v4.s_addr = fib_tuple->ipv4_dst;
> +		proto = htons(ETH_P_IP);
> +		break;
> +	case AF_INET6:
> +		tuple.src_v6 = *(struct in6_addr *)&fib_tuple->ipv6_src;
> +		tuple.dst_v6 = *(struct in6_addr *)&fib_tuple->ipv6_dst;
> +		proto = htons(ETH_P_IPV6);
> +		break;
> +	default:
> +		opts->error = -EAFNOSUPPORT;
> +		return NULL;
> +	}
> +
> +	tuplehash = bpf_xdp_flow_tuple_lookup(xdp->rxq->dev, &tuple, proto);
> +	if (IS_ERR(tuplehash)) {
> +		opts->error = PTR_ERR(tuplehash);
> +		return NULL;
> +	}
> +
> +	return tuplehash;
> +}
> +
> +__diag_pop()

__bpf_kfunc_end_defs();

Otherwise LGTM!

Lorenzo Bianconi June 29, 2024, 7:57 p.m. UTC | #2

> On 6/14/24 5:40 PM, Lorenzo Bianconi wrote:
> [...]
> > +enum {
> > +	NF_BPF_FLOWTABLE_OPTS_SZ = 4,
> > +};
> > +
> > +__diag_push();
> > +__diag_ignore_all("-Wmissing-prototypes",
> > +		  "Global functions as their definitions will be in nf_flow_table BTF");
> 
> nit: __bpf_kfunc_start_defs();

ack, I will fix it in v6.

> 
> > +static struct flow_offload_tuple_rhash *
> > +bpf_xdp_flow_tuple_lookup(struct net_device *dev,
> > +			  struct flow_offload_tuple *tuple, __be16 proto)
> > +{
> > +	struct flow_offload_tuple_rhash *tuplehash;
> > +	struct nf_flowtable *nf_flow_table;
> > +	struct flow_offload *nf_flow;
> > +
> > +	nf_flow_table = nf_flowtable_by_dev(dev);
> > +	if (!nf_flow_table)
> > +		return ERR_PTR(-ENOENT);
> > +
> > +	tuplehash = flow_offload_lookup(nf_flow_table, tuple);
> > +	if (!tuplehash)
> > +		return ERR_PTR(-ENOENT);
> > +
> > +	nf_flow = container_of(tuplehash, struct flow_offload,
> > +			       tuplehash[tuplehash->tuple.dir]);
> > +	flow_offload_refresh(nf_flow_table, nf_flow, false);
> > +
> > +	return tuplehash;
> > +}
> > +
> > +__bpf_kfunc struct flow_offload_tuple_rhash *
> > +bpf_xdp_flow_lookup(struct xdp_md *ctx, struct bpf_fib_lookup *fib_tuple,
> > +		    struct bpf_flowtable_opts *opts, u32 opts_len)
> > +{
> > +	struct xdp_buff *xdp = (struct xdp_buff *)ctx;
> > +	struct flow_offload_tuple tuple = {
> > +		.iifidx = fib_tuple->ifindex,
> > +		.l3proto = fib_tuple->family,
> > +		.l4proto = fib_tuple->l4_protocol,
> > +		.src_port = fib_tuple->sport,
> > +		.dst_port = fib_tuple->dport,
> > +	};
> > +	struct flow_offload_tuple_rhash *tuplehash;
> > +	__be16 proto;
> > +
> > +	if (opts_len != NF_BPF_FLOWTABLE_OPTS_SZ) {
> > +		opts->error = -EINVAL;
> > +		return NULL;
> > +	}
> > +
> > +	switch (fib_tuple->family) {
> > +	case AF_INET:
> > +		tuple.src_v4.s_addr = fib_tuple->ipv4_src;
> > +		tuple.dst_v4.s_addr = fib_tuple->ipv4_dst;
> > +		proto = htons(ETH_P_IP);
> > +		break;
> > +	case AF_INET6:
> > +		tuple.src_v6 = *(struct in6_addr *)&fib_tuple->ipv6_src;
> > +		tuple.dst_v6 = *(struct in6_addr *)&fib_tuple->ipv6_dst;
> > +		proto = htons(ETH_P_IPV6);
> > +		break;
> > +	default:
> > +		opts->error = -EAFNOSUPPORT;
> > +		return NULL;
> > +	}
> > +
> > +	tuplehash = bpf_xdp_flow_tuple_lookup(xdp->rxq->dev, &tuple, proto);
> > +	if (IS_ERR(tuplehash)) {
> > +		opts->error = PTR_ERR(tuplehash);
> > +		return NULL;
> > +	}
> > +
> > +	return tuplehash;
> > +}
> > +
> > +__diag_pop()
> 
> __bpf_kfunc_end_defs();

ack, I will fix it in v6.

Regards,
Lorenzo

> 
> Otherwise LGTM!

Patch

diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h
index 688e02b287cc4..cc52234ef71af 100644
--- a/include/net/netfilter/nf_flow_table.h
+++ b/include/net/netfilter/nf_flow_table.h
@@ -318,6 +318,16 @@  unsigned int nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb,
 unsigned int nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb,
 				       const struct nf_hook_state *state);
 
+#if (IS_BUILTIN(CONFIG_NF_FLOW_TABLE) && IS_ENABLED(CONFIG_DEBUG_INFO_BTF)) || \
+    (IS_MODULE(CONFIG_NF_FLOW_TABLE) && IS_ENABLED(CONFIG_DEBUG_INFO_BTF_MODULES))
+extern int nf_flow_register_bpf(void);
+#else
+static inline int nf_flow_register_bpf(void)
+{
+	return 0;
+}
+#endif
+
 #define MODULE_ALIAS_NF_FLOWTABLE(family)	\
 	MODULE_ALIAS("nf-flowtable-" __stringify(family))
 
diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile
index 18046872a38aa..f0aa4d7ef4998 100644
--- a/net/netfilter/Makefile
+++ b/net/netfilter/Makefile
@@ -144,6 +144,11 @@  obj-$(CONFIG_NF_FLOW_TABLE)	+= nf_flow_table.o
 nf_flow_table-objs		:= nf_flow_table_core.o nf_flow_table_ip.o \
 				   nf_flow_table_offload.o nf_flow_table_xdp.o
 nf_flow_table-$(CONFIG_NF_FLOW_TABLE_PROCFS) += nf_flow_table_procfs.o
+ifeq ($(CONFIG_NF_FLOW_TABLE),m)
+nf_flow_table-$(CONFIG_DEBUG_INFO_BTF_MODULES) += nf_flow_table_bpf.o
+else ifeq ($(CONFIG_NF_FLOW_TABLE),y)
+nf_flow_table-$(CONFIG_DEBUG_INFO_BTF) += nf_flow_table_bpf.o
+endif
 
 obj-$(CONFIG_NF_FLOW_TABLE_INET) += nf_flow_table_inet.o
 
diff --git a/net/netfilter/nf_flow_table_bpf.c b/net/netfilter/nf_flow_table_bpf.c
new file mode 100644
index 0000000000000..b3f8dffe62535
--- /dev/null
+++ b/net/netfilter/nf_flow_table_bpf.c
@@ -0,0 +1,117 @@ 
+// SPDX-License-Identifier: GPL-2.0-only
+/* Unstable Flow Table Helpers for XDP hook
+ *
+ * These are called from the XDP programs.
+ * Note that it is allowed to break compatibility for these functions since
+ * the interface they are exposed through to BPF programs is explicitly
+ * unstable.
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <net/netfilter/nf_flow_table.h>
+#include <linux/bpf.h>
+#include <linux/btf.h>
+#include <net/xdp.h>
+
+/* bpf_flowtable_opts - options for bpf flowtable helpers
+ * @error: out parameter, set for any encountered error
+ */
+struct bpf_flowtable_opts {
+	s32 error;
+};
+
+enum {
+	NF_BPF_FLOWTABLE_OPTS_SZ = 4,
+};
+
+__diag_push();
+__diag_ignore_all("-Wmissing-prototypes",
+		  "Global functions as their definitions will be in nf_flow_table BTF");
+
+static struct flow_offload_tuple_rhash *
+bpf_xdp_flow_tuple_lookup(struct net_device *dev,
+			  struct flow_offload_tuple *tuple, __be16 proto)
+{
+	struct flow_offload_tuple_rhash *tuplehash;
+	struct nf_flowtable *nf_flow_table;
+	struct flow_offload *nf_flow;
+
+	nf_flow_table = nf_flowtable_by_dev(dev);
+	if (!nf_flow_table)
+		return ERR_PTR(-ENOENT);
+
+	tuplehash = flow_offload_lookup(nf_flow_table, tuple);
+	if (!tuplehash)
+		return ERR_PTR(-ENOENT);
+
+	nf_flow = container_of(tuplehash, struct flow_offload,
+			       tuplehash[tuplehash->tuple.dir]);
+	flow_offload_refresh(nf_flow_table, nf_flow, false);
+
+	return tuplehash;
+}
+
+__bpf_kfunc struct flow_offload_tuple_rhash *
+bpf_xdp_flow_lookup(struct xdp_md *ctx, struct bpf_fib_lookup *fib_tuple,
+		    struct bpf_flowtable_opts *opts, u32 opts_len)
+{
+	struct xdp_buff *xdp = (struct xdp_buff *)ctx;
+	struct flow_offload_tuple tuple = {
+		.iifidx = fib_tuple->ifindex,
+		.l3proto = fib_tuple->family,
+		.l4proto = fib_tuple->l4_protocol,
+		.src_port = fib_tuple->sport,
+		.dst_port = fib_tuple->dport,
+	};
+	struct flow_offload_tuple_rhash *tuplehash;
+	__be16 proto;
+
+	if (opts_len != NF_BPF_FLOWTABLE_OPTS_SZ) {
+		opts->error = -EINVAL;
+		return NULL;
+	}
+
+	switch (fib_tuple->family) {
+	case AF_INET:
+		tuple.src_v4.s_addr = fib_tuple->ipv4_src;
+		tuple.dst_v4.s_addr = fib_tuple->ipv4_dst;
+		proto = htons(ETH_P_IP);
+		break;
+	case AF_INET6:
+		tuple.src_v6 = *(struct in6_addr *)&fib_tuple->ipv6_src;
+		tuple.dst_v6 = *(struct in6_addr *)&fib_tuple->ipv6_dst;
+		proto = htons(ETH_P_IPV6);
+		break;
+	default:
+		opts->error = -EAFNOSUPPORT;
+		return NULL;
+	}
+
+	tuplehash = bpf_xdp_flow_tuple_lookup(xdp->rxq->dev, &tuple, proto);
+	if (IS_ERR(tuplehash)) {
+		opts->error = PTR_ERR(tuplehash);
+		return NULL;
+	}
+
+	return tuplehash;
+}
+
+__diag_pop()
+
+BTF_KFUNCS_START(nf_ft_kfunc_set)
+BTF_ID_FLAGS(func, bpf_xdp_flow_lookup, KF_TRUSTED_ARGS | KF_RET_NULL)
+BTF_KFUNCS_END(nf_ft_kfunc_set)
+
+static const struct btf_kfunc_id_set nf_flow_kfunc_set = {
+	.owner = THIS_MODULE,
+	.set   = &nf_ft_kfunc_set,
+};
+
+int nf_flow_register_bpf(void)
+{
+	return register_btf_kfunc_id_set(BPF_PROG_TYPE_XDP,
+					 &nf_flow_kfunc_set);
+}
+EXPORT_SYMBOL_GPL(nf_flow_register_bpf);
diff --git a/net/netfilter/nf_flow_table_inet.c b/net/netfilter/nf_flow_table_inet.c
index 6eef15648b7b0..88787b45e30d6 100644
--- a/net/netfilter/nf_flow_table_inet.c
+++ b/net/netfilter/nf_flow_table_inet.c
@@ -98,7 +98,7 @@  static int __init nf_flow_inet_module_init(void)
 	nft_register_flowtable_type(&flowtable_ipv6);
 	nft_register_flowtable_type(&flowtable_inet);
 
-	return 0;
+	return nf_flow_register_bpf();
 }
 
 static void __exit nf_flow_inet_module_exit(void)