Merge tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf

Daniel Borkmann says:

====================
pull-request: bpf 2023-11-30

We've added 5 non-merge commits during the last 7 day(s) which contain
a total of 10 files changed, 66 insertions(+), 15 deletions(-).

The main changes are:

1) Fix AF_UNIX splat from use after free in BPF sockmap,
   from John Fastabend.

2) Fix a syzkaller splat in netdevsim by properly handling offloaded
   programs (and not device-bound ones), from Stanislav Fomichev.

3) Fix bpf_mem_cache_alloc_flags() to initialize the allocation hint,
   from Hou Tao.

4) Fix netkit by rejecting IFLA_NETKIT_PEER_INFO in changelink,
   from Daniel Borkmann.

* tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf:
  bpf, sockmap: Add af_unix test with both sockets in map
  bpf, sockmap: af_unix stream sockets need to hold ref for pair sock
  netkit: Reject IFLA_NETKIT_PEER_INFO in netkit_change_link
  bpf: Add missed allocation hint for bpf_mem_cache_alloc_flags()
  netdevsim: Don't accept device bound programs
====================

Link: https://lore.kernel.org/r/20231129234916.16128-1-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

10 files changed, 66 insertions, 15 deletions

diff --git a/drivers/net/netdevsim/bpf.c b/drivers/net/netdevsim/bpf.c
index f60eb97e3a627e..608953d4f98da9 100644
--- a/drivers/net/netdevsim/bpf.c
+++ b/drivers/net/netdevsim/bpf.c
@@ -93,7 +93,7 @@ static void nsim_prog_set_loaded(struct bpf_prog *prog, bool loaded)
 {
 	struct nsim_bpf_bound_prog *state;
 
-	if (!prog || !prog->aux->offload)
+	if (!prog || !bpf_prog_is_offloaded(prog->aux))
 		return;
 
 	state = prog->aux->offload->dev_priv;
@@ -311,7 +311,7 @@ nsim_setup_prog_hw_checks(struct netdevsim *ns, struct netdev_bpf *bpf)
 	if (!bpf->prog)
 		return 0;
 
-	if (!bpf->prog->aux->offload) {
+	if (!bpf_prog_is_offloaded(bpf->prog->aux)) {
 		NSIM_EA(bpf->extack, "xdpoffload of non-bound program");
 		return -EINVAL;
 	}
diff --git a/drivers/net/netkit.c b/drivers/net/netkit.c
index 97bd6705c24117..39171380ccf29e 100644
--- a/drivers/net/netkit.c
+++ b/drivers/net/netkit.c
@@ -851,6 +851,12 @@ static int netkit_change_link(struct net_device *dev, struct nlattr *tb[],
 		return -EACCES;
 	}
 
+	if (data[IFLA_NETKIT_PEER_INFO]) {
+		NL_SET_ERR_MSG_ATTR(extack, data[IFLA_NETKIT_PEER_INFO],
+				    "netkit peer info cannot be changed after device creation");
+		return -EINVAL;
+	}
+
 	if (data[IFLA_NETKIT_POLICY]) {
 		attr = data[IFLA_NETKIT_POLICY];
 		policy = nla_get_u32(attr);
diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h
index c1637515a8a416..c953b8c0d2f433 100644
--- a/include/linux/skmsg.h
+++ b/include/linux/skmsg.h
@@ -106,6 +106,7 @@ struct sk_psock {
 	struct mutex			work_mutex;
 	struct sk_psock_work_state	work_state;
 	struct delayed_work		work;
+	struct sock			*sk_pair;
 	struct rcu_work			rwork;
 };
 
diff --git a/include/net/af_unix.h b/include/net/af_unix.h
index 824c258143a3ab..49c4640027d8a6 100644
--- a/include/net/af_unix.h
+++ b/include/net/af_unix.h
@@ -75,6 +75,7 @@ struct unix_sock {
 };
 
 #define unix_sk(ptr) container_of_const(ptr, struct unix_sock, sk)
+#define unix_peer(sk) (unix_sk(sk)->peer)
 
 #define peer_wait peer_wq.wait
 
diff --git a/kernel/bpf/memalloc.c b/kernel/bpf/memalloc.c
index 63b909d277d479..6a51cfe4c2d63f 100644
--- a/kernel/bpf/memalloc.c
+++ b/kernel/bpf/memalloc.c
@@ -978,6 +978,8 @@ void notrace *bpf_mem_cache_alloc_flags(struct bpf_mem_alloc *ma, gfp_t flags)
 		memcg = get_memcg(c);
 		old_memcg = set_active_memcg(memcg);
 		ret = __alloc(c, NUMA_NO_NODE, GFP_KERNEL | __GFP_NOWARN | __GFP_ACCOUNT);
+		if (ret)
+			*(struct bpf_mem_cache **)ret = c;
 		set_active_memcg(old_memcg);
 		mem_cgroup_put(memcg);
 	}
diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index 6c31eefbd77786..93ecfceac1bc49 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -826,6 +826,8 @@ static void sk_psock_destroy(struct work_struct *work)
 
 	if (psock->sk_redir)
 		sock_put(psock->sk_redir);
+	if (psock->sk_pair)
+		sock_put(psock->sk_pair);
 	sock_put(psock->sk);
 	kfree(psock);
 }
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index a357dc5f24046d..ac1f2bc18fc968 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -213,8 +213,6 @@ static inline bool unix_secdata_eq(struct scm_cookie *scm, struct sk_buff *skb)
 }
 #endif /* CONFIG_SECURITY_NETWORK */
 
-#define unix_peer(sk) (unix_sk(sk)->peer)
-
 static inline int unix_our_peer(struct sock *sk, struct sock *osk)
 {
 	return unix_peer(osk) == sk;
diff --git a/net/unix/unix_bpf.c b/net/unix/unix_bpf.c
index 2f9d8271c6ec7d..7ea7c3a0d0d062 100644
--- a/net/unix/unix_bpf.c
+++ b/net/unix/unix_bpf.c
@@ -159,12 +159,17 @@ int unix_dgram_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool re
 
 int unix_stream_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore)
 {
+	struct sock *sk_pair;
+
 	if (restore) {
 		sk->sk_write_space = psock->saved_write_space;
 		sock_replace_proto(sk, psock->sk_proto);
 		return 0;
 	}
 
+	sk_pair = unix_peer(sk);
+	sock_hold(sk_pair);
+	psock->sk_pair = sk_pair;
 	unix_stream_bpf_check_needs_rebuild(psock->sk_proto);
 	sock_replace_proto(sk, &unix_stream_bpf_prot);
 	return 0;
diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
index a934d430c20c13..a92807bfcd1349 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
@@ -1337,7 +1337,8 @@ static void test_redir(struct test_sockmap_listen *skel, struct bpf_map *map,
 }
 
 static void pairs_redir_to_connected(int cli0, int peer0, int cli1, int peer1,
-				     int sock_mapfd, int verd_mapfd, enum redir_mode mode)
+				     int sock_mapfd, int nop_mapfd,
+				     int verd_mapfd, enum redir_mode mode)
 {
 	const char *log_prefix = redir_mode_str(mode);
 	unsigned int pass;
@@ -1351,6 +1352,12 @@ static void pairs_redir_to_connected(int cli0, int peer0, int cli1, int peer1,
 	if (err)
 		return;
 
+	if (nop_mapfd >= 0) {
+		err = add_to_sockmap(nop_mapfd, cli0, cli1);
+		if (err)
+			return;
+	}
+
 	n = write(cli1, "a", 1);
 	if (n < 0)
 		FAIL_ERRNO("%s: write", log_prefix);
@@ -1387,7 +1394,7 @@ static void unix_redir_to_connected(int sotype, int sock_mapfd,
 		goto close0;
 	c1 = sfd[0], p1 = sfd[1];
 
-	pairs_redir_to_connected(c0, p0, c1, p1, sock_mapfd, verd_mapfd, mode);
+	pairs_redir_to_connected(c0, p0, c1, p1, sock_mapfd, -1, verd_mapfd, mode);
 
 	xclose(c1);
 	xclose(p1);
@@ -1677,7 +1684,7 @@ static void udp_redir_to_connected(int family, int sock_mapfd, int verd_mapfd,
 	if (err)
 		goto close_cli0;
 
-	pairs_redir_to_connected(c0, p0, c1, p1, sock_mapfd, verd_mapfd, mode);
+	pairs_redir_to_connected(c0, p0, c1, p1, sock_mapfd, -1, verd_mapfd, mode);
 
 	xclose(c1);
 	xclose(p1);
@@ -1735,7 +1742,7 @@ static void inet_unix_redir_to_connected(int family, int type, int sock_mapfd,
 	if (err)
 		goto close;
 
-	pairs_redir_to_connected(c0, p0, c1, p1, sock_mapfd, verd_mapfd, mode);
+	pairs_redir_to_connected(c0, p0, c1, p1, sock_mapfd, -1, verd_mapfd, mode);
 
 	xclose(c1);
 	xclose(p1);
@@ -1770,8 +1777,10 @@ static void inet_unix_skb_redir_to_connected(struct test_sockmap_listen *skel,
 	xbpf_prog_detach2(verdict, sock_map, BPF_SK_SKB_VERDICT);
 }
 
-static void unix_inet_redir_to_connected(int family, int type, int sock_mapfd,
-					int verd_mapfd, enum redir_mode mode)
+static void unix_inet_redir_to_connected(int family, int type,
+					int sock_mapfd, int nop_mapfd,
+					int verd_mapfd,
+					enum redir_mode mode)
 {
 	int c0, c1, p0, p1;
 	int sfd[2];
@@ -1785,7 +1794,8 @@ static void unix_inet_redir_to_connected(int family, int type, int sock_mapfd,
 		goto close_cli0;
 	c1 = sfd[0], p1 = sfd[1];
 
-	pairs_redir_to_connected(c0, p0, c1, p1, sock_mapfd, verd_mapfd, mode);
+	pairs_redir_to_connected(c0, p0, c1, p1,
+				 sock_mapfd, nop_mapfd, verd_mapfd, mode);
 
 	xclose(c1);
 	xclose(p1);
@@ -1799,6 +1809,7 @@ static void unix_inet_skb_redir_to_connected(struct test_sockmap_listen *skel,
 					    struct bpf_map *inner_map, int family)
 {
 	int verdict = bpf_program__fd(skel->progs.prog_skb_verdict);
+	int nop_map = bpf_map__fd(skel->maps.nop_map);
 	int verdict_map = bpf_map__fd(skel->maps.verdict_map);
 	int sock_map = bpf_map__fd(inner_map);
 	int err;
@@ -1808,14 +1819,32 @@ static void unix_inet_skb_redir_to_connected(struct test_sockmap_listen *skel,
 		return;
 
 	skel->bss->test_ingress = false;
-	unix_inet_redir_to_connected(family, SOCK_DGRAM, sock_map, verdict_map,
+	unix_inet_redir_to_connected(family, SOCK_DGRAM,
+				     sock_map, -1, verdict_map,
 				     REDIR_EGRESS);
-	unix_inet_redir_to_connected(family, SOCK_STREAM, sock_map, verdict_map,
+	unix_inet_redir_to_connected(family, SOCK_DGRAM,
+				     sock_map, -1, verdict_map,
+				     REDIR_EGRESS);
+
+	unix_inet_redir_to_connected(family, SOCK_DGRAM,
+				     sock_map, nop_map, verdict_map,
+				     REDIR_EGRESS);
+	unix_inet_redir_to_connected(family, SOCK_STREAM,
+				     sock_map, nop_map, verdict_map,
 				     REDIR_EGRESS);
 	skel->bss->test_ingress = true;
-	unix_inet_redir_to_connected(family, SOCK_DGRAM, sock_map, verdict_map,
+	unix_inet_redir_to_connected(family, SOCK_DGRAM,
+				     sock_map, -1, verdict_map,
+				     REDIR_INGRESS);
+	unix_inet_redir_to_connected(family, SOCK_STREAM,
+				     sock_map, -1, verdict_map,
+				     REDIR_INGRESS);
+
+	unix_inet_redir_to_connected(family, SOCK_DGRAM,
+				     sock_map, nop_map, verdict_map,
 				     REDIR_INGRESS);
-	unix_inet_redir_to_connected(family, SOCK_STREAM, sock_map, verdict_map,
+	unix_inet_redir_to_connected(family, SOCK_STREAM,
+				     sock_map, nop_map, verdict_map,
 				     REDIR_INGRESS);
 
 	xbpf_prog_detach2(verdict, sock_map, BPF_SK_SKB_VERDICT);
diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_listen.c b/tools/testing/selftests/bpf/progs/test_sockmap_listen.c
index 464d35bd57c708..b7250eb9c30cca 100644
--- a/tools/testing/selftests/bpf/progs/test_sockmap_listen.c
+++ b/tools/testing/selftests/bpf/progs/test_sockmap_listen.c
@@ -15,6 +15,13 @@ struct {
 } sock_map SEC(".maps");
 
 struct {
+	__uint(type, BPF_MAP_TYPE_SOCKMAP);
+	__uint(max_entries, 2);
+	__type(key, __u32);
+	__type(value, __u64);
+} nop_map SEC(".maps");
+
+struct {
 	__uint(type, BPF_MAP_TYPE_SOCKHASH);
 	__uint(max_entries, 2);
 	__type(key, __u32);