Merge branch 'lwt_encap_ip'

Peter Oskolkov says:

====================
This patchset implements BPF_LWT_ENCAP_IP mode in bpf_lwt_push_encap
BPF helper. It enables BPF programs (specifically, BPF_PROG_TYPE_LWT_IN
and BPF_PROG_TYPE_LWT_XMIT prog types) to add IP encapsulation headers
to packets (e.g. IP/GRE, GUE, IPIP).

This is useful when thousands of different short-lived flows should be
encapped, each with different and dynamically determined destination.
Although lwtunnels can be used in some of these scenarios, the ability
to dynamically generate encap headers adds more flexibility, e.g.
when routing depends on the state of the host (reflected in global bpf
maps).

V2 changes: added flowi-based route lookup, IPv6 encapping, and
   encapping on ingress.

V3 changes: incorporated David Ahern's suggestions:
   - added l3mdev check/oif (patch 2)
   - sync bpf.h from include/uapi into tools/include/uapi
   - selftest tweaks

V4 changes: moved route lookup/dst change from bpf_push_ip_encap
   to when BPF_LWT_REROUTE is handled, as suggested by David Ahern.

V5 changes: added a check in lwt_xmit that skb->protocol stays the
   same if the skb is to be passed back to the stack (ret == BPF_OK).
   Again, suggested by David Ahern.

V6 changes: abandoned.

V7 changes: added handling of GSO packets (patch 3 in the patchset added),
   as suggested by BPF maintainers.

V8 changes:
   - fixed build errors when LWT or IPV6 are not enabled;
   - whitelisted TCP GSO instead of blacklisting SCTP and UDP GSO, as
     suggested by Willem de Bruijn;
   - added validation that pushed length cover needed headers when GRE/UDP
     encap is detected, as suggested by Willem de Bruijn;
   - a couple of minor/stylistic tweaks/fixed typos.

V9 changes:
   - fixed a kbuild test robot compiler warning;
   - added ipv6_route_input to ipv6_stub (patch 4 in the patchset
     added), and IPv6 routing functions are now invoked via ipv6_stub,
     as suggested by David Ahern.

V10 changes:
   - removed unnecessary IS_ENABLED and pr_warn_once from patch 5.

V11 changes: fixed a potential dst leak in patch 5, as suggested by
    David Ahern.
====================

Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

4 files changed, 309 insertions, 7 deletions

diff --git a/net/core/filter.c b/net/core/filter.c
index 353735575204..a78deb2656e1 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -73,6 +73,7 @@
 #include <linux/seg6_local.h>
 #include <net/seg6.h>
 #include <net/seg6_local.h>
+#include <net/lwtunnel.h>
 
 /**
  *	sk_filter_trim_cap - run a packet through a socket filter
@@ -4815,7 +4816,15 @@ static int bpf_push_seg6_encap(struct sk_buff *skb, u32 type, void *hdr, u32 len
 }
 #endif /* CONFIG_IPV6_SEG6_BPF */
 
-BPF_CALL_4(bpf_lwt_push_encap, struct sk_buff *, skb, u32, type, void *, hdr,
+#if IS_ENABLED(CONFIG_LWTUNNEL_BPF)
+static int bpf_push_ip_encap(struct sk_buff *skb, void *hdr, u32 len,
+			     bool ingress)
+{
+	return bpf_lwt_push_ip_encap(skb, hdr, len, ingress);
+}
+#endif
+
+BPF_CALL_4(bpf_lwt_in_push_encap, struct sk_buff *, skb, u32, type, void *, hdr,
 	   u32, len)
 {
 	switch (type) {
@@ -4824,13 +4833,40 @@ BPF_CALL_4(bpf_lwt_push_encap, struct sk_buff *, skb, u32, type, void *, hdr,
 	case BPF_LWT_ENCAP_SEG6_INLINE:
 		return bpf_push_seg6_encap(skb, type, hdr, len);
 #endif
+#if IS_ENABLED(CONFIG_LWTUNNEL_BPF)
+	case BPF_LWT_ENCAP_IP:
+		return bpf_push_ip_encap(skb, hdr, len, true /* ingress */);
+#endif
+	default:
+		return -EINVAL;
+	}
+}
+
+BPF_CALL_4(bpf_lwt_xmit_push_encap, struct sk_buff *, skb, u32, type,
+	   void *, hdr, u32, len)
+{
+	switch (type) {
+#if IS_ENABLED(CONFIG_LWTUNNEL_BPF)
+	case BPF_LWT_ENCAP_IP:
+		return bpf_push_ip_encap(skb, hdr, len, false /* egress */);
+#endif
 	default:
 		return -EINVAL;
 	}
 }
 
-static const struct bpf_func_proto bpf_lwt_push_encap_proto = {
-	.func		= bpf_lwt_push_encap,
+static const struct bpf_func_proto bpf_lwt_in_push_encap_proto = {
+	.func		= bpf_lwt_in_push_encap,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_ANYTHING,
+	.arg3_type	= ARG_PTR_TO_MEM,
+	.arg4_type	= ARG_CONST_SIZE
+};
+
+static const struct bpf_func_proto bpf_lwt_xmit_push_encap_proto = {
+	.func		= bpf_lwt_xmit_push_encap,
 	.gpl_only	= false,
 	.ret_type	= RET_INTEGER,
 	.arg1_type	= ARG_PTR_TO_CTX,
@@ -5417,7 +5453,8 @@ bool bpf_helper_changes_pkt_data(void *func)
 	    func == bpf_lwt_seg6_adjust_srh ||
 	    func == bpf_lwt_seg6_action ||
 #endif
-	    func == bpf_lwt_push_encap)
+	    func == bpf_lwt_in_push_encap ||
+	    func == bpf_lwt_xmit_push_encap)
 		return true;
 
 	return false;
@@ -5815,7 +5852,7 @@ lwt_in_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 {
 	switch (func_id) {
 	case BPF_FUNC_lwt_push_encap:
-		return &bpf_lwt_push_encap_proto;
+		return &bpf_lwt_in_push_encap_proto;
 	default:
 		return lwt_out_func_proto(func_id, prog);
 	}
@@ -5851,6 +5888,8 @@ lwt_xmit_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_l4_csum_replace_proto;
 	case BPF_FUNC_set_hash_invalid:
 		return &bpf_set_hash_invalid_proto;
+	case BPF_FUNC_lwt_push_encap:
+		return &bpf_lwt_xmit_push_encap_proto;
 	default:
 		return lwt_out_func_proto(func_id, prog);
 	}
diff --git a/net/core/lwt_bpf.c b/net/core/lwt_bpf.c
index a648568c5e8f..32251f3fcda0 100644
--- a/net/core/lwt_bpf.c
+++ b/net/core/lwt_bpf.c
@@ -16,6 +16,8 @@
 #include <linux/types.h>
 #include <linux/bpf.h>
 #include <net/lwtunnel.h>
+#include <net/gre.h>
+#include <net/ip6_route.h>
 
 struct bpf_lwt_prog {
 	struct bpf_prog *prog;
@@ -55,6 +57,7 @@ static int run_lwt_bpf(struct sk_buff *skb, struct bpf_lwt_prog *lwt,
 
 	switch (ret) {
 	case BPF_OK:
+	case BPF_LWT_REROUTE:
 		break;
 
 	case BPF_REDIRECT:
@@ -87,6 +90,30 @@ static int run_lwt_bpf(struct sk_buff *skb, struct bpf_lwt_prog *lwt,
 	return ret;
 }
 
+static int bpf_lwt_input_reroute(struct sk_buff *skb)
+{
+	int err = -EINVAL;
+
+	if (skb->protocol == htons(ETH_P_IP)) {
+		struct iphdr *iph = ip_hdr(skb);
+
+		err = ip_route_input_noref(skb, iph->daddr, iph->saddr,
+					   iph->tos, skb_dst(skb)->dev);
+	} else if (skb->protocol == htons(ETH_P_IPV6)) {
+		err = ipv6_stub->ipv6_route_input(skb);
+	} else {
+		err = -EAFNOSUPPORT;
+	}
+
+	if (err)
+		goto err;
+	return dst_input(skb);
+
+err:
+	kfree_skb(skb);
+	return err;
+}
+
 static int bpf_input(struct sk_buff *skb)
 {
 	struct dst_entry *dst = skb_dst(skb);
@@ -98,11 +125,11 @@ static int bpf_input(struct sk_buff *skb)
 		ret = run_lwt_bpf(skb, &bpf->in, dst, NO_REDIRECT);
 		if (ret < 0)
 			return ret;
+		if (ret == BPF_LWT_REROUTE)
+			return bpf_lwt_input_reroute(skb);
 	}
 
 	if (unlikely(!dst->lwtstate->orig_input)) {
-		pr_warn_once("orig_input not set on dst for prog %s\n",
-			     bpf->out.name);
 		kfree_skb(skb);
 		return -EINVAL;
 	}
@@ -147,6 +174,91 @@ static int xmit_check_hhlen(struct sk_buff *skb)
 	return 0;
 }
 
+static int bpf_lwt_xmit_reroute(struct sk_buff *skb)
+{
+	struct net_device *l3mdev = l3mdev_master_dev_rcu(skb_dst(skb)->dev);
+	int oif = l3mdev ? l3mdev->ifindex : 0;
+	struct dst_entry *dst = NULL;
+	struct sock *sk;
+	struct net *net;
+	bool ipv4;
+	int err;
+
+	if (skb->protocol == htons(ETH_P_IP))
+		ipv4 = true;
+	else if (skb->protocol == htons(ETH_P_IPV6))
+		ipv4 = false;
+	else
+		return -EAFNOSUPPORT;
+
+	sk = sk_to_full_sk(skb->sk);
+	if (sk) {
+		if (sk->sk_bound_dev_if)
+			oif = sk->sk_bound_dev_if;
+		net = sock_net(sk);
+	} else {
+		net = dev_net(skb_dst(skb)->dev);
+	}
+
+	if (ipv4) {
+		struct iphdr *iph = ip_hdr(skb);
+		struct flowi4 fl4 = {};
+		struct rtable *rt;
+
+		fl4.flowi4_oif = oif;
+		fl4.flowi4_mark = skb->mark;
+		fl4.flowi4_uid = sock_net_uid(net, sk);
+		fl4.flowi4_tos = RT_TOS(iph->tos);
+		fl4.flowi4_flags = FLOWI_FLAG_ANYSRC;
+		fl4.flowi4_proto = iph->protocol;
+		fl4.daddr = iph->daddr;
+		fl4.saddr = iph->saddr;
+
+		rt = ip_route_output_key(net, &fl4);
+		if (IS_ERR(rt))
+			return -EINVAL;
+		dst = &rt->dst;
+	} else {
+		struct ipv6hdr *iph6 = ipv6_hdr(skb);
+		struct flowi6 fl6 = {};
+
+		fl6.flowi6_oif = oif;
+		fl6.flowi6_mark = skb->mark;
+		fl6.flowi6_uid = sock_net_uid(net, sk);
+		fl6.flowlabel = ip6_flowinfo(iph6);
+		fl6.flowi6_proto = iph6->nexthdr;
+		fl6.daddr = iph6->daddr;
+		fl6.saddr = iph6->saddr;
+
+		err = ipv6_stub->ipv6_dst_lookup(net, skb->sk, &dst, &fl6);
+		if (err || IS_ERR(dst))
+			return -EINVAL;
+	}
+	if (unlikely(dst->error)) {
+		dst_release(dst);
+		return -EINVAL;
+	}
+
+	/* Although skb header was reserved in bpf_lwt_push_ip_encap(), it
+	 * was done for the previous dst, so we are doing it here again, in
+	 * case the new dst needs much more space. The call below is a noop
+	 * if there is enough header space in skb.
+	 */
+	err = skb_cow_head(skb, LL_RESERVED_SPACE(dst->dev));
+	if (unlikely(err))
+		return err;
+
+	skb_dst_drop(skb);
+	skb_dst_set(skb, dst);
+
+	err = dst_output(dev_net(skb_dst(skb)->dev), skb->sk, skb);
+	if (unlikely(err))
+		return err;
+
+	/* ip[6]_finish_output2 understand LWTUNNEL_XMIT_DONE */
+	return LWTUNNEL_XMIT_DONE;
+}
+
 static int bpf_xmit(struct sk_buff *skb)
 {
 	struct dst_entry *dst = skb_dst(skb);
@@ -154,11 +266,20 @@ static int bpf_xmit(struct sk_buff *skb)
 
 	bpf = bpf_lwt_lwtunnel(dst->lwtstate);
 	if (bpf->xmit.prog) {
+		__be16 proto = skb->protocol;
 		int ret;
 
 		ret = run_lwt_bpf(skb, &bpf->xmit, dst, CAN_REDIRECT);
 		switch (ret) {
 		case BPF_OK:
+			/* If the header changed, e.g. via bpf_lwt_push_encap,
+			 * BPF_LWT_REROUTE below should have been used if the
+			 * protocol was also changed.
+			 */
+			if (skb->protocol != proto) {
+				kfree_skb(skb);
+				return -EINVAL;
+			}
 			/* If the header was expanded, headroom might be too
 			 * small for L2 header to come, expand as needed.
 			 */
@@ -169,6 +290,8 @@ static int bpf_xmit(struct sk_buff *skb)
 			return LWTUNNEL_XMIT_CONTINUE;
 		case BPF_REDIRECT:
 			return LWTUNNEL_XMIT_DONE;
+		case BPF_LWT_REROUTE:
+			return bpf_lwt_xmit_reroute(skb);
 		default:
 			return ret;
 		}
@@ -390,6 +513,133 @@ static const struct lwtunnel_encap_ops bpf_encap_ops = {
 	.owner		= THIS_MODULE,
 };
 
+static int handle_gso_type(struct sk_buff *skb, unsigned int gso_type,
+			   int encap_len)
+{
+	struct skb_shared_info *shinfo = skb_shinfo(skb);
+
+	gso_type |= SKB_GSO_DODGY;
+	shinfo->gso_type |= gso_type;
+	skb_decrease_gso_size(shinfo, encap_len);
+	shinfo->gso_segs = 0;
+	return 0;
+}
+
+static int handle_gso_encap(struct sk_buff *skb, bool ipv4, int encap_len)
+{
+	int next_hdr_offset;
+	void *next_hdr;
+	__u8 protocol;
+
+	/* SCTP and UDP_L4 gso need more nuanced handling than what
+	 * handle_gso_type() does above: skb_decrease_gso_size() is not enough.
+	 * So at the moment only TCP GSO packets are let through.
+	 */
+	if (!(skb_shinfo(skb)->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6)))
+		return -ENOTSUPP;
+
+	if (ipv4) {
+		protocol = ip_hdr(skb)->protocol;
+		next_hdr_offset = sizeof(struct iphdr);
+		next_hdr = skb_network_header(skb) + next_hdr_offset;
+	} else {
+		protocol = ipv6_hdr(skb)->nexthdr;
+		next_hdr_offset = sizeof(struct ipv6hdr);
+		next_hdr = skb_network_header(skb) + next_hdr_offset;
+	}
+
+	switch (protocol) {
+	case IPPROTO_GRE:
+		next_hdr_offset += sizeof(struct gre_base_hdr);
+		if (next_hdr_offset > encap_len)
+			return -EINVAL;
+
+		if (((struct gre_base_hdr *)next_hdr)->flags & GRE_CSUM)
+			return handle_gso_type(skb, SKB_GSO_GRE_CSUM,
+					       encap_len);
+		return handle_gso_type(skb, SKB_GSO_GRE, encap_len);
+
+	case IPPROTO_UDP:
+		next_hdr_offset += sizeof(struct udphdr);
+		if (next_hdr_offset > encap_len)
+			return -EINVAL;
+
+		if (((struct udphdr *)next_hdr)->check)
+			return handle_gso_type(skb, SKB_GSO_UDP_TUNNEL_CSUM,
+					       encap_len);
+		return handle_gso_type(skb, SKB_GSO_UDP_TUNNEL, encap_len);
+
+	case IPPROTO_IP:
+	case IPPROTO_IPV6:
+		if (ipv4)
+			return handle_gso_type(skb, SKB_GSO_IPXIP4, encap_len);
+		else
+			return handle_gso_type(skb, SKB_GSO_IPXIP6, encap_len);
+
+	default:
+		return -EPROTONOSUPPORT;
+	}
+}
+
+int bpf_lwt_push_ip_encap(struct sk_buff *skb, void *hdr, u32 len, bool ingress)
+{
+	struct iphdr *iph;
+	bool ipv4;
+	int err;
+
+	if (unlikely(len < sizeof(struct iphdr) || len > LWT_BPF_MAX_HEADROOM))
+		return -EINVAL;
+
+	/* validate protocol and length */
+	iph = (struct iphdr *)hdr;
+	if (iph->version == 4) {
+		ipv4 = true;
+		if (unlikely(len < iph->ihl * 4))
+			return -EINVAL;
+	} else if (iph->version == 6) {
+		ipv4 = false;
+		if (unlikely(len < sizeof(struct ipv6hdr)))
+			return -EINVAL;
+	} else {
+		return -EINVAL;
+	}
+
+	if (ingress)
+		err = skb_cow_head(skb, len + skb->mac_len);
+	else
+		err = skb_cow_head(skb,
+				   len + LL_RESERVED_SPACE(skb_dst(skb)->dev));
+	if (unlikely(err))
+		return err;
+
+	/* push the encap headers and fix pointers */
+	skb_reset_inner_headers(skb);
+	skb->encapsulation = 1;
+	skb_push(skb, len);
+	if (ingress)
+		skb_postpush_rcsum(skb, iph, len);
+	skb_reset_network_header(skb);
+	memcpy(skb_network_header(skb), hdr, len);
+	bpf_compute_data_pointers(skb);
+	skb_clear_hash(skb);
+
+	if (ipv4) {
+		skb->protocol = htons(ETH_P_IP);
+		iph = ip_hdr(skb);
+
+		if (!iph->check)
+			iph->check = ip_fast_csum((unsigned char *)iph,
+						  iph->ihl);
+	} else {
+		skb->protocol = htons(ETH_P_IPV6);
+	}
+
+	if (skb_is_gso(skb))
+		return handle_gso_encap(skb, ipv4, len);
+
+	return 0;
+}
+
 static int __init bpf_lwt_init(void)
 {
 	return lwtunnel_encap_add_ops(&bpf_encap_ops, LWTUNNEL_ENCAP_BPF);
diff --git a/net/ipv6/addrconf_core.c b/net/ipv6/addrconf_core.c
index 5cd0029d930e..6c79af056d9b 100644
--- a/net/ipv6/addrconf_core.c
+++ b/net/ipv6/addrconf_core.c
@@ -134,6 +134,11 @@ static int eafnosupport_ipv6_dst_lookup(struct net *net, struct sock *u1,
 	return -EAFNOSUPPORT;
 }
 
+static int eafnosupport_ipv6_route_input(struct sk_buff *skb)
+{
+	return -EAFNOSUPPORT;
+}
+
 static struct fib6_table *eafnosupport_fib6_get_table(struct net *net, u32 id)
 {
 	return NULL;
@@ -170,6 +175,7 @@ eafnosupport_ip6_mtu_from_fib6(struct fib6_info *f6i, struct in6_addr *daddr,
 
 const struct ipv6_stub *ipv6_stub __read_mostly = &(struct ipv6_stub) {
 	.ipv6_dst_lookup   = eafnosupport_ipv6_dst_lookup,
+	.ipv6_route_input  = eafnosupport_ipv6_route_input,
 	.fib6_get_table    = eafnosupport_fib6_get_table,
 	.fib6_table_lookup = eafnosupport_fib6_table_lookup,
 	.fib6_lookup       = eafnosupport_fib6_lookup,
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index d99753b5e39b..2f45d2a3e3a3 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -900,10 +900,17 @@ static struct pernet_operations inet6_net_ops = {
 	.exit = inet6_net_exit,
 };
 
+static int ipv6_route_input(struct sk_buff *skb)
+{
+	ip6_route_input(skb);
+	return skb_dst(skb)->error;
+}
+
 static const struct ipv6_stub ipv6_stub_impl = {
 	.ipv6_sock_mc_join = ipv6_sock_mc_join,
 	.ipv6_sock_mc_drop = ipv6_sock_mc_drop,
 	.ipv6_dst_lookup   = ip6_dst_lookup,
+	.ipv6_route_input  = ipv6_route_input,
 	.fib6_get_table	   = fib6_get_table,
 	.fib6_table_lookup = fib6_table_lookup,
 	.fib6_lookup       = fib6_lookup,