diff mbox series

[bpf,v4,3/4] bpf: fix bpf socket lookup from tc/xdp to respect socket VRF bindings

Message ID 20230428083007.148364-4-gilad9366@gmail.com (mailing list archive)
State New, archived
Delegated to: BPF
Headers show
Series Socket lookup BPF API from tc/xdp ingress does not respect VRF bindings. | expand

Checks

Context Check Description
netdev/series_format success Posting correctly formatted
netdev/tree_selection success Clearly marked for bpf, async
netdev/fixes_present success Fixes tag present in non-next series
netdev/header_inline success No static functions without inline keyword in header files
netdev/build_32bit success Errors and warnings before: 4193 this patch: 4193
netdev/cc_maintainers success CCed 19 of 19 maintainers
netdev/build_clang success Errors and warnings before: 932 this patch: 932
netdev/verify_signedoff success Signed-off-by tag matches author and committer
netdev/deprecated_api success None detected
netdev/check_selftest success No net selftest shell script
netdev/verify_fixes success Fixes tag looks correct
netdev/build_allmodconfig_warn success Errors and warnings before: 4401 this patch: 4401
netdev/checkpatch success total: 0 errors, 0 warnings, 0 checks, 174 lines checked
netdev/kdoc success Errors and warnings before: 0 this patch: 0
netdev/source_inline success Was 0 now: 0
bpf/vmtest-bpf-PR success PR summary
bpf/vmtest-bpf-VM_Test-1 success Logs for ShellCheck
bpf/vmtest-bpf-VM_Test-7 success Logs for set-matrix
bpf/vmtest-bpf-VM_Test-2 success Logs for build for aarch64 with gcc
bpf/vmtest-bpf-VM_Test-3 success Logs for build for aarch64 with llvm-17
bpf/vmtest-bpf-VM_Test-5 success Logs for build for x86_64 with gcc
bpf/vmtest-bpf-VM_Test-6 success Logs for build for x86_64 with llvm-16
bpf/vmtest-bpf-VM_Test-4 success Logs for build for s390x with gcc
bpf/vmtest-bpf-VM_Test-8 success Logs for test_maps on aarch64 with gcc
bpf/vmtest-bpf-VM_Test-9 success Logs for test_maps on aarch64 with llvm-17
bpf/vmtest-bpf-VM_Test-11 success Logs for test_maps on x86_64 with gcc
bpf/vmtest-bpf-VM_Test-12 success Logs for test_maps on x86_64 with llvm-16
bpf/vmtest-bpf-VM_Test-18 fail Logs for test_progs_no_alu32 on aarch64 with gcc
bpf/vmtest-bpf-VM_Test-19 fail Logs for test_progs_no_alu32 on aarch64 with llvm-17
bpf/vmtest-bpf-VM_Test-21 fail Logs for test_progs_no_alu32 on x86_64 with gcc
bpf/vmtest-bpf-VM_Test-22 success Logs for test_progs_no_alu32 on x86_64 with llvm-16
bpf/vmtest-bpf-VM_Test-23 success Logs for test_progs_no_alu32_parallel on aarch64 with gcc
bpf/vmtest-bpf-VM_Test-24 success Logs for test_progs_no_alu32_parallel on aarch64 with llvm-17
bpf/vmtest-bpf-VM_Test-25 success Logs for test_progs_no_alu32_parallel on x86_64 with gcc
bpf/vmtest-bpf-VM_Test-26 success Logs for test_progs_no_alu32_parallel on x86_64 with llvm-16
bpf/vmtest-bpf-VM_Test-27 success Logs for test_progs_parallel on aarch64 with gcc
bpf/vmtest-bpf-VM_Test-28 success Logs for test_progs_parallel on aarch64 with llvm-17
bpf/vmtest-bpf-VM_Test-29 success Logs for test_progs_parallel on x86_64 with gcc
bpf/vmtest-bpf-VM_Test-30 success Logs for test_progs_parallel on x86_64 with llvm-16
bpf/vmtest-bpf-VM_Test-31 success Logs for test_verifier on aarch64 with gcc
bpf/vmtest-bpf-VM_Test-32 success Logs for test_verifier on aarch64 with llvm-17
bpf/vmtest-bpf-VM_Test-34 success Logs for test_verifier on x86_64 with gcc
bpf/vmtest-bpf-VM_Test-35 success Logs for test_verifier on x86_64 with llvm-16
bpf/vmtest-bpf-VM_Test-36 success Logs for veristat
bpf/vmtest-bpf-VM_Test-13 fail Logs for test_progs on aarch64 with gcc
bpf/vmtest-bpf-VM_Test-14 fail Logs for test_progs on aarch64 with llvm-17
bpf/vmtest-bpf-VM_Test-16 success Logs for test_progs on x86_64 with gcc
bpf/vmtest-bpf-VM_Test-17 success Logs for test_progs on x86_64 with llvm-16
bpf/vmtest-bpf-VM_Test-20 success Logs for test_progs_no_alu32 on s390x with gcc
bpf/vmtest-bpf-VM_Test-33 success Logs for test_verifier on s390x with gcc
bpf/vmtest-bpf-VM_Test-15 fail Logs for test_progs on s390x with gcc
bpf/vmtest-bpf-VM_Test-10 success Logs for test_maps on s390x with gcc

Commit Message

Gilad Sever April 28, 2023, 8:30 a.m. UTC 
When calling bpf_sk_lookup_tcp(), bpf_sk_lookup_udp() or
bpf_skc_lookup_tcp() from tc/xdp ingress, VRF socket bindings aren't
respoected, i.e. unbound sockets are returned, and bound sockets aren't
found.

VRF binding is determined by the sdif argument to sk_lookup(), however
when called from tc the IP SKB control block isn't initialized and thus
inet{,6}_sdif() always returns 0.

Fix by calculating sdif for the tc/xdp flows by observing the device's
l3 enslaved state.

The cg/sk_skb hooking points which are expected to support
inet{,6}_sdif() pass sdif=-1 which makes __bpf_skc_lookup() use the
existing logic.

Fixes: 6acc9b432e67 ("bpf: Add helper to retrieve socket in BPF")
Acked-by: Stanislav Fomichev <sdf@google.com>
Reviewed-by: Shmulik Ladkani <shmulik.ladkani@gmail.com>
Reviewed-by: Eyal Birger <eyal.birger@gmail.com>
Signed-off-by: Gilad Sever <gilad9366@gmail.com>
---
v4: Move dev_sdif() to include/linux/netdevice.h as suggested by Stanislav Fomichev

v3: Rename bpf_l2_sdif() to dev_sdif() as suggested by Stanislav Fomichev
---
 include/linux/netdevice.h |  9 +++++++
 net/core/filter.c         | 54 ++++++++++++++++++++++++---------------
 2 files changed, 42 insertions(+), 21 deletions(-)
diff mbox series

Patch

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 08fbd4622ccf..b40c3825dd3b 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -5090,6 +5090,15 @@  static inline bool netif_is_l3_slave(const struct net_device *dev)
 	return dev->priv_flags & IFF_L3MDEV_SLAVE;
 }
 
+static inline int dev_sdif(const struct net_device *dev)
+{
+#if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV)
+	if (netif_is_l3_slave(dev))
+		return dev->ifindex;
+#endif
+	return 0;
+}
+
 static inline bool netif_is_bridge_master(const struct net_device *dev)
 {
 	return dev->priv_flags & IFF_EBRIDGE;
diff --git a/net/core/filter.c b/net/core/filter.c
index e06547922edc..3249036e8f27 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -6555,12 +6555,11 @@  static struct sock *sk_lookup(struct net *net, struct bpf_sock_tuple *tuple,
 static struct sock *
 __bpf_skc_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len,
 		 struct net *caller_net, u32 ifindex, u8 proto, u64 netns_id,
-		 u64 flags)
+		 u64 flags, int sdif)
 {
 	struct sock *sk = NULL;
 	struct net *net;
 	u8 family;
-	int sdif;
 
 	if (len == sizeof(tuple->ipv4))
 		family = AF_INET;
@@ -6572,10 +6571,12 @@  __bpf_skc_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len,
 	if (unlikely(flags || !((s32)netns_id < 0 || netns_id <= S32_MAX)))
 		goto out;
 
-	if (family == AF_INET)
-		sdif = inet_sdif(skb);
-	else
-		sdif = inet6_sdif(skb);
+	if (sdif < 0) {
+		if (family == AF_INET)
+			sdif = inet_sdif(skb);
+		else
+			sdif = inet6_sdif(skb);
+	}
 
 	if ((s32)netns_id < 0) {
 		net = caller_net;
@@ -6595,10 +6596,11 @@  __bpf_skc_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len,
 static struct sock *
 __bpf_sk_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len,
 		struct net *caller_net, u32 ifindex, u8 proto, u64 netns_id,
-		u64 flags)
+		u64 flags, int sdif)
 {
 	struct sock *sk = __bpf_skc_lookup(skb, tuple, len, caller_net,
-					   ifindex, proto, netns_id, flags);
+					   ifindex, proto, netns_id, flags,
+					   sdif);
 
 	if (sk) {
 		struct sock *sk2 = sk_to_full_sk(sk);
@@ -6638,7 +6640,7 @@  bpf_skc_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len,
 	}
 
 	return __bpf_skc_lookup(skb, tuple, len, caller_net, ifindex, proto,
-				netns_id, flags);
+				netns_id, flags, -1);
 }
 
 static struct sock *
@@ -6731,11 +6733,12 @@  BPF_CALL_5(bpf_tc_skc_lookup_tcp, struct sk_buff *, skb,
 	   struct bpf_sock_tuple *, tuple, u32, len, u64, netns_id, u64, flags)
 {
 	struct net *caller_net = dev_net(skb->dev);
+	int sdif = dev_sdif(skb->dev);
 	int ifindex = skb->dev->ifindex;
 
 	return (unsigned long)__bpf_skc_lookup(skb, tuple, len, caller_net,
 					       ifindex, IPPROTO_TCP, netns_id,
-					       flags);
+					       flags, sdif);
 }
 
 static const struct bpf_func_proto bpf_tc_skc_lookup_tcp_proto = {
@@ -6754,11 +6757,12 @@  BPF_CALL_5(bpf_tc_sk_lookup_tcp, struct sk_buff *, skb,
 	   struct bpf_sock_tuple *, tuple, u32, len, u64, netns_id, u64, flags)
 {
 	struct net *caller_net = dev_net(skb->dev);
+	int sdif = dev_sdif(skb->dev);
 	int ifindex = skb->dev->ifindex;
 
 	return (unsigned long)__bpf_sk_lookup(skb, tuple, len, caller_net,
 					      ifindex, IPPROTO_TCP, netns_id,
-					      flags);
+					      flags, sdif);
 }
 
 static const struct bpf_func_proto bpf_tc_sk_lookup_tcp_proto = {
@@ -6777,11 +6781,12 @@  BPF_CALL_5(bpf_tc_sk_lookup_udp, struct sk_buff *, skb,
 	   struct bpf_sock_tuple *, tuple, u32, len, u64, netns_id, u64, flags)
 {
 	struct net *caller_net = dev_net(skb->dev);
+	int sdif = dev_sdif(skb->dev);
 	int ifindex = skb->dev->ifindex;
 
 	return (unsigned long)__bpf_sk_lookup(skb, tuple, len, caller_net,
 					      ifindex, IPPROTO_UDP, netns_id,
-					      flags);
+					      flags, sdif);
 }
 
 static const struct bpf_func_proto bpf_tc_sk_lookup_udp_proto = {
@@ -6814,11 +6819,13 @@  BPF_CALL_5(bpf_xdp_sk_lookup_udp, struct xdp_buff *, ctx,
 	   struct bpf_sock_tuple *, tuple, u32, len, u32, netns_id, u64, flags)
 {
 	struct net *caller_net = dev_net(ctx->rxq->dev);
-	int ifindex = ctx->rxq->dev->ifindex;
+	struct net_device *dev = ctx->rxq->dev;
+	int sdif = dev_sdif(dev);
+	int ifindex = dev->ifindex;
 
 	return (unsigned long)__bpf_sk_lookup(NULL, tuple, len, caller_net,
 					      ifindex, IPPROTO_UDP, netns_id,
-					      flags);
+					      flags, sdif);
 }
 
 static const struct bpf_func_proto bpf_xdp_sk_lookup_udp_proto = {
@@ -6837,11 +6844,13 @@  BPF_CALL_5(bpf_xdp_skc_lookup_tcp, struct xdp_buff *, ctx,
 	   struct bpf_sock_tuple *, tuple, u32, len, u32, netns_id, u64, flags)
 {
 	struct net *caller_net = dev_net(ctx->rxq->dev);
-	int ifindex = ctx->rxq->dev->ifindex;
+	struct net_device *dev = ctx->rxq->dev;
+	int sdif = dev_sdif(dev);
+	int ifindex = dev->ifindex;
 
 	return (unsigned long)__bpf_skc_lookup(NULL, tuple, len, caller_net,
 					       ifindex, IPPROTO_TCP, netns_id,
-					       flags);
+					       flags, sdif);
 }
 
 static const struct bpf_func_proto bpf_xdp_skc_lookup_tcp_proto = {
@@ -6860,11 +6869,13 @@  BPF_CALL_5(bpf_xdp_sk_lookup_tcp, struct xdp_buff *, ctx,
 	   struct bpf_sock_tuple *, tuple, u32, len, u32, netns_id, u64, flags)
 {
 	struct net *caller_net = dev_net(ctx->rxq->dev);
-	int ifindex = ctx->rxq->dev->ifindex;
+	struct net_device *dev = ctx->rxq->dev;
+	int sdif = dev_sdif(dev);
+	int ifindex = dev->ifindex;
 
 	return (unsigned long)__bpf_sk_lookup(NULL, tuple, len, caller_net,
 					      ifindex, IPPROTO_TCP, netns_id,
-					      flags);
+					      flags, sdif);
 }
 
 static const struct bpf_func_proto bpf_xdp_sk_lookup_tcp_proto = {
@@ -6884,7 +6895,8 @@  BPF_CALL_5(bpf_sock_addr_skc_lookup_tcp, struct bpf_sock_addr_kern *, ctx,
 {
 	return (unsigned long)__bpf_skc_lookup(NULL, tuple, len,
 					       sock_net(ctx->sk), 0,
-					       IPPROTO_TCP, netns_id, flags);
+					       IPPROTO_TCP, netns_id, flags,
+					       -1);
 }
 
 static const struct bpf_func_proto bpf_sock_addr_skc_lookup_tcp_proto = {
@@ -6903,7 +6915,7 @@  BPF_CALL_5(bpf_sock_addr_sk_lookup_tcp, struct bpf_sock_addr_kern *, ctx,
 {
 	return (unsigned long)__bpf_sk_lookup(NULL, tuple, len,
 					      sock_net(ctx->sk), 0, IPPROTO_TCP,
-					      netns_id, flags);
+					      netns_id, flags, -1);
 }
 
 static const struct bpf_func_proto bpf_sock_addr_sk_lookup_tcp_proto = {
@@ -6922,7 +6934,7 @@  BPF_CALL_5(bpf_sock_addr_sk_lookup_udp, struct bpf_sock_addr_kern *, ctx,
 {
 	return (unsigned long)__bpf_sk_lookup(NULL, tuple, len,
 					      sock_net(ctx->sk), 0, IPPROTO_UDP,
-					      netns_id, flags);
+					      netns_id, flags, -1);
 }
 
 static const struct bpf_func_proto bpf_sock_addr_sk_lookup_udp_proto = {