Merge https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Daniel Borkmann says:

====================
bpf-next 2021-08-31

We've added 116 non-merge commits during the last 17 day(s) which contain
a total of 126 files changed, 6813 insertions(+), 4027 deletions(-).

The main changes are:

1) Add opaque bpf_cookie to perf link which the program can read out again,
   to be used in libbpf-based USDT library, from Andrii Nakryiko.

2) Add bpf_task_pt_regs() helper to access userspace pt_regs, from Daniel Xu.

3) Add support for UNIX stream type sockets for BPF sockmap, from Jiang Wang.

4) Allow BPF TCP congestion control progs to call bpf_setsockopt() e.g. to switch
   to another congestion control algorithm during init, from Martin KaFai Lau.

5) Extend BPF iterator support for UNIX domain sockets, from Kuniyuki Iwashima.

6) Allow bpf_{set,get}sockopt() calls from setsockopt progs, from Prankur Gupta.

7) Add bpf_get_netns_cookie() helper for BPF_PROG_TYPE_{SOCK_OPS,CGROUP_SOCKOPT}
   progs, from Xu Liu and Stanislav Fomichev.

8) Support for __weak typed ksyms in libbpf, from Hao Luo.

9) Shrink struct cgroup_bpf by 504 bytes through refactoring, from Dave Marchevsky.

10) Fix a smatch complaint in verifier's narrow load handling, from Andrey Ignatov.

11) Fix BPF interpreter's tail call count limit, from Daniel Borkmann.

12) Big batch of improvements to BPF selftests, from Magnus Karlsson, Li Zhijian,
    Yucong Sun, Yonghong Song, Ilya Leoshkevich, Jussi Maki, Ilya Leoshkevich, others.

13) Another big batch to revamp XDP samples in order to give them consistent look
    and feel, from Kumar Kartikeya Dwivedi.

* https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (116 commits)
  MAINTAINERS: Remove self from powerpc BPF JIT
  selftests/bpf: Fix potential unreleased lock
  samples: bpf: Fix uninitialized variable in xdp_redirect_cpu
  selftests/bpf: Reduce more flakyness in sockmap_listen
  bpf: Fix bpf-next builds without CONFIG_BPF_EVENTS
  bpf: selftests: Add dctcp fallback test
  bpf: selftests: Add connect_to_fd_opts to network_helpers
  bpf: selftests: Add sk_state to bpf_tcp_helpers.h
  bpf: tcp: Allow bpf-tcp-cc to call bpf_(get|set)sockopt
  selftests: xsk: Preface options with opt
  selftests: xsk: Make enums lower case
  selftests: xsk: Generate packets from specification
  selftests: xsk: Generate packet directly in umem
  selftests: xsk: Simplify cleanup of ifobjects
  selftests: xsk: Decrease sending speed
  selftests: xsk: Validate tx stats on tx thread
  selftests: xsk: Simplify packet validation in xsk tests
  selftests: xsk: Rename worker_* functions that are not thread entry points
  selftests: xsk: Disassociate umem size with packets sent
  selftests: xsk: Remove end-of-test packet
  ...
====================

Link: https://lore.kernel.org/r/20210830225618.11634-1-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

14 files changed, 339 insertions, 57 deletions

diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c
index 4b855af267b1..2eb0e55ef54d 100644
--- a/net/bpf/test_run.c
+++ b/net/bpf/test_run.c
@@ -116,7 +116,7 @@ static int bpf_test_run(struct bpf_prog *prog, void *ctx, u32 repeat,
 		if (xdp)
 			*retval = bpf_prog_run_xdp(prog, ctx);
 		else
-			*retval = BPF_PROG_RUN(prog, ctx);
+			*retval = bpf_prog_run(prog, ctx);
 	} while (bpf_test_timer_continue(&t, repeat, &ret, time));
 	bpf_reset_run_ctx(old_ctx);
 	bpf_test_timer_leave(&t);
@@ -327,7 +327,7 @@ __bpf_prog_test_run_raw_tp(void *data)
 	struct bpf_raw_tp_test_run_info *info = data;
 
 	rcu_read_lock();
-	info->retval = BPF_PROG_RUN(info->prog, info->ctx);
+	info->retval = bpf_prog_run(info->prog, info->ctx);
 	rcu_read_unlock();
 }
 
@@ -989,7 +989,7 @@ int bpf_prog_test_run_sk_lookup(struct bpf_prog *prog, const union bpf_attr *kat
 	bpf_test_timer_enter(&t);
 	do {
 		ctx.selected_sk = NULL;
-		retval = BPF_PROG_SK_LOOKUP_RUN_ARRAY(progs, ctx, BPF_PROG_RUN);
+		retval = BPF_PROG_SK_LOOKUP_RUN_ARRAY(progs, ctx, bpf_prog_run);
 	} while (bpf_test_timer_continue(&t, repeat, &ret, &duration));
 	bpf_test_timer_leave(&t);
 
diff --git a/net/core/filter.c b/net/core/filter.c
index 3aca07c44fad..2e32cee2c469 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -114,7 +114,7 @@ EXPORT_SYMBOL_GPL(copy_bpf_fprog_from_user);
  * Run the eBPF program and then cut skb->data to correct size returned by
  * the program. If pkt_len is 0 we toss packet. If skb->len is smaller
  * than pkt_len we keep whole skb->data. This is the socket level
- * wrapper to BPF_PROG_RUN. It returns 0 if the packet should
+ * wrapper to bpf_prog_run. It returns 0 if the packet should
  * be accepted or -EPERM if the packet should be tossed.
  *
  */
@@ -4676,6 +4676,30 @@ static const struct bpf_func_proto bpf_get_netns_cookie_sock_addr_proto = {
 	.arg1_type	= ARG_PTR_TO_CTX_OR_NULL,
 };
 
+BPF_CALL_1(bpf_get_netns_cookie_sock_ops, struct bpf_sock_ops_kern *, ctx)
+{
+	return __bpf_get_netns_cookie(ctx ? ctx->sk : NULL);
+}
+
+static const struct bpf_func_proto bpf_get_netns_cookie_sock_ops_proto = {
+	.func		= bpf_get_netns_cookie_sock_ops,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX_OR_NULL,
+};
+
+BPF_CALL_1(bpf_get_netns_cookie_sk_msg, struct sk_msg *, ctx)
+{
+	return __bpf_get_netns_cookie(ctx ? ctx->sk : NULL);
+}
+
+static const struct bpf_func_proto bpf_get_netns_cookie_sk_msg_proto = {
+	.func		= bpf_get_netns_cookie_sk_msg,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX_OR_NULL,
+};
+
 BPF_CALL_1(bpf_get_socket_uid, struct sk_buff *, skb)
 {
 	struct sock *sk = sk_to_full_sk(skb->sk);
@@ -5027,6 +5051,12 @@ err_clear:
 BPF_CALL_5(bpf_sk_setsockopt, struct sock *, sk, int, level,
 	   int, optname, char *, optval, int, optlen)
 {
+	if (level == SOL_TCP && optname == TCP_CONGESTION) {
+		if (optlen >= sizeof("cdg") - 1 &&
+		    !strncmp("cdg", optval, optlen))
+			return -ENOTSUPP;
+	}
+
 	return _bpf_setsockopt(sk, level, optname, optval, optlen);
 }
 
@@ -7491,6 +7521,8 @@ sock_ops_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_sk_storage_get_proto;
 	case BPF_FUNC_sk_storage_delete:
 		return &bpf_sk_storage_delete_proto;
+	case BPF_FUNC_get_netns_cookie:
+		return &bpf_get_netns_cookie_sock_ops_proto;
 #ifdef CONFIG_INET
 	case BPF_FUNC_load_hdr_opt:
 		return &bpf_sock_ops_load_hdr_opt_proto;
@@ -7537,6 +7569,8 @@ sk_msg_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_sk_storage_get_proto;
 	case BPF_FUNC_sk_storage_delete:
 		return &bpf_sk_storage_delete_proto;
+	case BPF_FUNC_get_netns_cookie:
+		return &bpf_get_netns_cookie_sk_msg_proto;
 #ifdef CONFIG_CGROUPS
 	case BPF_FUNC_get_current_cgroup_id:
 		return &bpf_get_current_cgroup_id_proto;
@@ -10115,7 +10149,7 @@ struct sock *bpf_run_sk_reuseport(struct sock_reuseport *reuse, struct sock *sk,
 	enum sk_action action;
 
 	bpf_init_reuseport_kern(&reuse_kern, reuse, sk, skb, migrating_sk, hash);
-	action = BPF_PROG_RUN(prog, &reuse_kern);
+	action = bpf_prog_run(prog, &reuse_kern);
 
 	if (action == SK_PASS)
 		return reuse_kern.selected_sk;
diff --git a/net/core/ptp_classifier.c b/net/core/ptp_classifier.c
index e33fde06d528..dd4cf01d1e0a 100644
--- a/net/core/ptp_classifier.c
+++ b/net/core/ptp_classifier.c
@@ -103,7 +103,7 @@ static struct bpf_prog *ptp_insns __read_mostly;
 
 unsigned int ptp_classify_raw(const struct sk_buff *skb)
 {
-	return BPF_PROG_RUN(ptp_insns, skb);
+	return bpf_prog_run(ptp_insns, skb);
 }
 EXPORT_SYMBOL_GPL(ptp_classify_raw);
 
diff --git a/net/core/sock_map.c b/net/core/sock_map.c
index ae5fa4338d9c..e252b8ec2b85 100644
--- a/net/core/sock_map.c
+++ b/net/core/sock_map.c
@@ -1494,6 +1494,7 @@ void sock_map_unhash(struct sock *sk)
 	rcu_read_unlock();
 	saved_unhash(sk);
 }
+EXPORT_SYMBOL_GPL(sock_map_unhash);
 
 void sock_map_close(struct sock *sk, long timeout)
 {
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 0e4d758c2585..1d816a5fd3eb 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -452,7 +452,7 @@ int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 	 * changes context in a wrong way it will be caught.
 	 */
 	err = BPF_CGROUP_RUN_PROG_INET_BIND_LOCK(sk, uaddr,
-						 BPF_CGROUP_INET4_BIND, &flags);
+						 CGROUP_INET4_BIND, &flags);
 	if (err)
 		return err;
 
@@ -781,7 +781,7 @@ int inet_getname(struct socket *sock, struct sockaddr *uaddr,
 		sin->sin_port = inet->inet_dport;
 		sin->sin_addr.s_addr = inet->inet_daddr;
 		BPF_CGROUP_RUN_SA_PROG_LOCK(sk, (struct sockaddr *)sin,
-					    BPF_CGROUP_INET4_GETPEERNAME,
+					    CGROUP_INET4_GETPEERNAME,
 					    NULL);
 	} else {
 		__be32 addr = inet->inet_rcv_saddr;
@@ -790,7 +790,7 @@ int inet_getname(struct socket *sock, struct sockaddr *uaddr,
 		sin->sin_port = inet->inet_sport;
 		sin->sin_addr.s_addr = addr;
 		BPF_CGROUP_RUN_SA_PROG_LOCK(sk, (struct sockaddr *)sin,
-					    BPF_CGROUP_INET4_GETSOCKNAME,
+					    CGROUP_INET4_GETSOCKNAME,
 					    NULL);
 	}
 	memset(sin->sin_zero, 0, sizeof(sin->sin_zero));
diff --git a/net/ipv4/bpf_tcp_ca.c b/net/ipv4/bpf_tcp_ca.c
index 9e41eff4a685..0dcee9df1326 100644
--- a/net/ipv4/bpf_tcp_ca.c
+++ b/net/ipv4/bpf_tcp_ca.c
@@ -10,6 +10,9 @@
 #include <net/tcp.h>
 #include <net/bpf_sk_storage.h>
 
+/* "extern" is to avoid sparse warning.  It is only used in bpf_struct_ops.c. */
+extern struct bpf_struct_ops bpf_tcp_congestion_ops;
+
 static u32 optional_ops[] = {
 	offsetof(struct tcp_congestion_ops, init),
 	offsetof(struct tcp_congestion_ops, release),
@@ -163,6 +166,19 @@ static const struct bpf_func_proto bpf_tcp_send_ack_proto = {
 	.arg2_type	= ARG_ANYTHING,
 };
 
+static u32 prog_ops_moff(const struct bpf_prog *prog)
+{
+	const struct btf_member *m;
+	const struct btf_type *t;
+	u32 midx;
+
+	midx = prog->expected_attach_type;
+	t = bpf_tcp_congestion_ops.type;
+	m = &btf_type_member(t)[midx];
+
+	return btf_member_bit_offset(t, m) / 8;
+}
+
 static const struct bpf_func_proto *
 bpf_tcp_ca_get_func_proto(enum bpf_func_id func_id,
 			  const struct bpf_prog *prog)
@@ -174,6 +190,28 @@ bpf_tcp_ca_get_func_proto(enum bpf_func_id func_id,
 		return &bpf_sk_storage_get_proto;
 	case BPF_FUNC_sk_storage_delete:
 		return &bpf_sk_storage_delete_proto;
+	case BPF_FUNC_setsockopt:
+		/* Does not allow release() to call setsockopt.
+		 * release() is called when the current bpf-tcp-cc
+		 * is retiring.  It is not allowed to call
+		 * setsockopt() to make further changes which
+		 * may potentially allocate new resources.
+		 */
+		if (prog_ops_moff(prog) !=
+		    offsetof(struct tcp_congestion_ops, release))
+			return &bpf_sk_setsockopt_proto;
+		return NULL;
+	case BPF_FUNC_getsockopt:
+		/* Since get/setsockopt is usually expected to
+		 * be available together, disable getsockopt for
+		 * release also to avoid usage surprise.
+		 * The bpf-tcp-cc already has a more powerful way
+		 * to read tcp_sock from the PTR_TO_BTF_ID.
+		 */
+		if (prog_ops_moff(prog) !=
+		    offsetof(struct tcp_congestion_ops, release))
+			return &bpf_sk_getsockopt_proto;
+		return NULL;
 	default:
 		return bpf_base_func_proto(func_id);
 	}
@@ -286,9 +324,6 @@ static void bpf_tcp_ca_unreg(void *kdata)
 	tcp_unregister_congestion_control(kdata);
 }
 
-/* Avoid sparse warning.  It is only used in bpf_struct_ops.c. */
-extern struct bpf_struct_ops bpf_tcp_congestion_ops;
-
 struct bpf_struct_ops bpf_tcp_congestion_ops = {
 	.verifier_ops = &bpf_tcp_ca_verifier_ops,
 	.reg = bpf_tcp_ca_reg,
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 1a742b710e54..8851c9463b4b 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1143,7 +1143,7 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 		rcu_read_unlock();
 	}
 
-	if (cgroup_bpf_enabled(BPF_CGROUP_UDP4_SENDMSG) && !connected) {
+	if (cgroup_bpf_enabled(CGROUP_UDP4_SENDMSG) && !connected) {
 		err = BPF_CGROUP_RUN_PROG_UDP4_SENDMSG_LOCK(sk,
 					    (struct sockaddr *)usin, &ipc.addr);
 		if (err)
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index d92c90d97763..b5878bb8e419 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -455,7 +455,7 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 	 * changes context in a wrong way it will be caught.
 	 */
 	err = BPF_CGROUP_RUN_PROG_INET_BIND_LOCK(sk, uaddr,
-						 BPF_CGROUP_INET6_BIND, &flags);
+						 CGROUP_INET6_BIND, &flags);
 	if (err)
 		return err;
 
@@ -532,7 +532,7 @@ int inet6_getname(struct socket *sock, struct sockaddr *uaddr,
 		if (np->sndflow)
 			sin->sin6_flowinfo = np->flow_label;
 		BPF_CGROUP_RUN_SA_PROG_LOCK(sk, (struct sockaddr *)sin,
-					    BPF_CGROUP_INET6_GETPEERNAME,
+					    CGROUP_INET6_GETPEERNAME,
 					    NULL);
 	} else {
 		if (ipv6_addr_any(&sk->sk_v6_rcv_saddr))
@@ -541,7 +541,7 @@ int inet6_getname(struct socket *sock, struct sockaddr *uaddr,
 			sin->sin6_addr = sk->sk_v6_rcv_saddr;
 		sin->sin6_port = inet->inet_sport;
 		BPF_CGROUP_RUN_SA_PROG_LOCK(sk, (struct sockaddr *)sin,
-					    BPF_CGROUP_INET6_GETSOCKNAME,
+					    CGROUP_INET6_GETSOCKNAME,
 					    NULL);
 	}
 	sin->sin6_scope_id = ipv6_iface_scope_id(&sin->sin6_addr,
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index c5e15e94bb00..ea53847b5b7e 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -1475,7 +1475,7 @@ do_udp_sendmsg:
 		fl6.saddr = np->saddr;
 	fl6.fl6_sport = inet->inet_sport;
 
-	if (cgroup_bpf_enabled(BPF_CGROUP_UDP6_SENDMSG) && !connected) {
+	if (cgroup_bpf_enabled(CGROUP_UDP6_SENDMSG) && !connected) {
 		err = BPF_CGROUP_RUN_PROG_UDP6_SENDMSG_LOCK(sk,
 					   (struct sockaddr *)sin6, &fl6.saddr);
 		if (err)
diff --git a/net/netfilter/xt_bpf.c b/net/netfilter/xt_bpf.c
index 13cf3f9b5938..849ac552a154 100644
--- a/net/netfilter/xt_bpf.c
+++ b/net/netfilter/xt_bpf.c
@@ -90,7 +90,7 @@ static bool bpf_mt(const struct sk_buff *skb, struct xt_action_param *par)
 {
 	const struct xt_bpf_info *info = par->matchinfo;
 
-	return BPF_PROG_RUN(info->filter, skb);
+	return bpf_prog_run(info->filter, skb);
 }
 
 static bool bpf_mt_v1(const struct sk_buff *skb, struct xt_action_param *par)
diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c
index 040807aa15b9..5c36013339e1 100644
--- a/net/sched/act_bpf.c
+++ b/net/sched/act_bpf.c
@@ -47,11 +47,11 @@ static int tcf_bpf_act(struct sk_buff *skb, const struct tc_action *act,
 	if (at_ingress) {
 		__skb_push(skb, skb->mac_len);
 		bpf_compute_data_pointers(skb);
-		filter_res = BPF_PROG_RUN(filter, skb);
+		filter_res = bpf_prog_run(filter, skb);
 		__skb_pull(skb, skb->mac_len);
 	} else {
 		bpf_compute_data_pointers(skb);
-		filter_res = BPF_PROG_RUN(filter, skb);
+		filter_res = bpf_prog_run(filter, skb);
 	}
 	if (skb_sk_is_prefetched(skb) && filter_res != TC_ACT_OK)
 		skb_orphan(skb);
diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c
index 3b472bafdc9d..df19a847829e 100644
--- a/net/sched/cls_bpf.c
+++ b/net/sched/cls_bpf.c
@@ -96,11 +96,11 @@ static int cls_bpf_classify(struct sk_buff *skb, const struct tcf_proto *tp,
 			/* It is safe to push/pull even if skb_shared() */
 			__skb_push(skb, skb->mac_len);
 			bpf_compute_data_pointers(skb);
-			filter_res = BPF_PROG_RUN(prog->filter, skb);
+			filter_res = bpf_prog_run(prog->filter, skb);
 			__skb_pull(skb, skb->mac_len);
 		} else {
 			bpf_compute_data_pointers(skb);
-			filter_res = BPF_PROG_RUN(prog->filter, skb);
+			filter_res = bpf_prog_run(prog->filter, skb);
 		}
 
 		if (prog->exts_integrated) {
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 4cf0b1c47f0f..7cad52ba9cde 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -113,6 +113,7 @@
 #include <linux/security.h>
 #include <linux/freezer.h>
 #include <linux/file.h>
+#include <linux/btf_ids.h>
 
 #include "scm.h"
 
@@ -678,6 +679,8 @@ static int unix_dgram_sendmsg(struct socket *, struct msghdr *, size_t);
 static int unix_dgram_recvmsg(struct socket *, struct msghdr *, size_t, int);
 static int unix_read_sock(struct sock *sk, read_descriptor_t *desc,
 			  sk_read_actor_t recv_actor);
+static int unix_stream_read_sock(struct sock *sk, read_descriptor_t *desc,
+				 sk_read_actor_t recv_actor);
 static int unix_dgram_connect(struct socket *, struct sockaddr *,
 			      int, int);
 static int unix_seqpacket_sendmsg(struct socket *, struct msghdr *, size_t);
@@ -731,6 +734,7 @@ static const struct proto_ops unix_stream_ops = {
 	.shutdown =	unix_shutdown,
 	.sendmsg =	unix_stream_sendmsg,
 	.recvmsg =	unix_stream_recvmsg,
+	.read_sock =	unix_stream_read_sock,
 	.mmap =		sock_no_mmap,
 	.sendpage =	unix_stream_sendpage,
 	.splice_read =	unix_stream_splice_read,
@@ -794,17 +798,35 @@ static void unix_close(struct sock *sk, long timeout)
 	 */
 }
 
-struct proto unix_proto = {
-	.name			= "UNIX",
+static void unix_unhash(struct sock *sk)
+{
+	/* Nothing to do here, unix socket does not need a ->unhash().
+	 * This is merely for sockmap.
+	 */
+}
+
+struct proto unix_dgram_proto = {
+	.name			= "UNIX-DGRAM",
 	.owner			= THIS_MODULE,
 	.obj_size		= sizeof(struct unix_sock),
 	.close			= unix_close,
 #ifdef CONFIG_BPF_SYSCALL
-	.psock_update_sk_prot	= unix_bpf_update_proto,
+	.psock_update_sk_prot	= unix_dgram_bpf_update_proto,
 #endif
 };
 
-static struct sock *unix_create1(struct net *net, struct socket *sock, int kern)
+struct proto unix_stream_proto = {
+	.name			= "UNIX-STREAM",
+	.owner			= THIS_MODULE,
+	.obj_size		= sizeof(struct unix_sock),
+	.close			= unix_close,
+	.unhash			= unix_unhash,
+#ifdef CONFIG_BPF_SYSCALL
+	.psock_update_sk_prot	= unix_stream_bpf_update_proto,
+#endif
+};
+
+static struct sock *unix_create1(struct net *net, struct socket *sock, int kern, int type)
 {
 	struct sock *sk = NULL;
 	struct unix_sock *u;
@@ -813,7 +835,11 @@ static struct sock *unix_create1(struct net *net, struct socket *sock, int kern)
 	if (atomic_long_read(&unix_nr_socks) > 2 * get_max_files())
 		goto out;
 
-	sk = sk_alloc(net, PF_UNIX, GFP_KERNEL, &unix_proto, kern);
+	if (type == SOCK_STREAM)
+		sk = sk_alloc(net, PF_UNIX, GFP_KERNEL, &unix_stream_proto, kern);
+	else /*dgram and  seqpacket */
+		sk = sk_alloc(net, PF_UNIX, GFP_KERNEL, &unix_dgram_proto, kern);
+
 	if (!sk)
 		goto out;
 
@@ -875,7 +901,7 @@ static int unix_create(struct net *net, struct socket *sock, int protocol,
 		return -ESOCKTNOSUPPORT;
 	}
 
-	return unix_create1(net, sock, kern) ? 0 : -ENOMEM;
+	return unix_create1(net, sock, kern, sock->type) ? 0 : -ENOMEM;
 }
 
 static int unix_release(struct socket *sock)
@@ -1289,7 +1315,7 @@ static int unix_stream_connect(struct socket *sock, struct sockaddr *uaddr,
 	err = -ENOMEM;
 
 	/* create new sock for complete connection */
-	newsk = unix_create1(sock_net(sk), NULL, 0);
+	newsk = unix_create1(sock_net(sk), NULL, 0, sock->type);
 	if (newsk == NULL)
 		goto out;
 
@@ -2326,8 +2352,10 @@ static int unix_dgram_recvmsg(struct socket *sock, struct msghdr *msg, size_t si
 	struct sock *sk = sock->sk;
 
 #ifdef CONFIG_BPF_SYSCALL
-	if (sk->sk_prot != &unix_proto)
-		return sk->sk_prot->recvmsg(sk, msg, size, flags & MSG_DONTWAIT,
+	const struct proto *prot = READ_ONCE(sk->sk_prot);
+
+	if (prot != &unix_dgram_proto)
+		return prot->recvmsg(sk, msg, size, flags & MSG_DONTWAIT,
 					    flags & ~MSG_DONTWAIT, NULL);
 #endif
 	return __unix_dgram_recvmsg(sk, msg, size, flags);
@@ -2497,6 +2525,15 @@ static struct sk_buff *manage_oob(struct sk_buff *skb, struct sock *sk,
 }
 #endif
 
+static int unix_stream_read_sock(struct sock *sk, read_descriptor_t *desc,
+				 sk_read_actor_t recv_actor)
+{
+	if (unlikely(sk->sk_state != TCP_ESTABLISHED))
+		return -ENOTCONN;
+
+	return unix_read_sock(sk, desc, recv_actor);
+}
+
 static int unix_stream_read_generic(struct unix_stream_read_state *state,
 				    bool freezable)
 {
@@ -2722,6 +2759,20 @@ static int unix_stream_read_actor(struct sk_buff *skb,
 	return ret ?: chunk;
 }
 
+int __unix_stream_recvmsg(struct sock *sk, struct msghdr *msg,
+			  size_t size, int flags)
+{
+	struct unix_stream_read_state state = {
+		.recv_actor = unix_stream_read_actor,
+		.socket = sk->sk_socket,
+		.msg = msg,
+		.size = size,
+		.flags = flags
+	};
+
+	return unix_stream_read_generic(&state, true);
+}
+
 static int unix_stream_recvmsg(struct socket *sock, struct msghdr *msg,
 			       size_t size, int flags)
 {
@@ -2733,6 +2784,14 @@ static int unix_stream_recvmsg(struct socket *sock, struct msghdr *msg,
 		.flags = flags
 	};
 
+#ifdef CONFIG_BPF_SYSCALL
+	struct sock *sk = sock->sk;
+	const struct proto *prot = READ_ONCE(sk->sk_prot);
+
+	if (prot != &unix_stream_proto)
+		return prot->recvmsg(sk, msg, size, flags & MSG_DONTWAIT,
+					    flags & ~MSG_DONTWAIT, NULL);
+#endif
 	return unix_stream_read_generic(&state, true);
 }
 
@@ -2793,7 +2852,10 @@ static int unix_shutdown(struct socket *sock, int mode)
 		(sk->sk_type == SOCK_STREAM || sk->sk_type == SOCK_SEQPACKET)) {
 
 		int peer_mode = 0;
+		const struct proto *prot = READ_ONCE(other->sk_prot);
 
+		if (prot->unhash)
+			prot->unhash(other);
 		if (mode&RCV_SHUTDOWN)
 			peer_mode |= SEND_SHUTDOWN;
 		if (mode&SEND_SHUTDOWN)
@@ -2802,10 +2864,12 @@ static int unix_shutdown(struct socket *sock, int mode)
 		other->sk_shutdown |= peer_mode;
 		unix_state_unlock(other);
 		other->sk_state_change(other);
-		if (peer_mode == SHUTDOWN_MASK)
+		if (peer_mode == SHUTDOWN_MASK) {
 			sk_wake_async(other, SOCK_WAKE_WAITD, POLL_HUP);
-		else if (peer_mode & RCV_SHUTDOWN)
+			other->sk_state = TCP_CLOSE;
+		} else if (peer_mode & RCV_SHUTDOWN) {
 			sk_wake_async(other, SOCK_WAKE_WAITD, POLL_IN);
+		}
 	}
 	if (other)
 		sock_put(other);
@@ -3150,6 +3214,64 @@ static const struct seq_operations unix_seq_ops = {
 	.stop   = unix_seq_stop,
 	.show   = unix_seq_show,
 };
+
+#if IS_BUILTIN(CONFIG_UNIX) && defined(CONFIG_BPF_SYSCALL)
+struct bpf_iter__unix {
+	__bpf_md_ptr(struct bpf_iter_meta *, meta);
+	__bpf_md_ptr(struct unix_sock *, unix_sk);
+	uid_t uid __aligned(8);
+};
+
+static int unix_prog_seq_show(struct bpf_prog *prog, struct bpf_iter_meta *meta,
+			      struct unix_sock *unix_sk, uid_t uid)
+{
+	struct bpf_iter__unix ctx;
+
+	meta->seq_num--;  /* skip SEQ_START_TOKEN */
+	ctx.meta = meta;
+	ctx.unix_sk = unix_sk;
+	ctx.uid = uid;
+	return bpf_iter_run_prog(prog, &ctx);
+}
+
+static int bpf_iter_unix_seq_show(struct seq_file *seq, void *v)
+{
+	struct bpf_iter_meta meta;
+	struct bpf_prog *prog;
+	struct sock *sk = v;
+	uid_t uid;
+
+	if (v == SEQ_START_TOKEN)
+		return 0;
+
+	uid = from_kuid_munged(seq_user_ns(seq), sock_i_uid(sk));
+	meta.seq = seq;
+	prog = bpf_iter_get_info(&meta, false);
+	return unix_prog_seq_show(prog, &meta, v, uid);
+}
+
+static void bpf_iter_unix_seq_stop(struct seq_file *seq, void *v)
+{
+	struct bpf_iter_meta meta;
+	struct bpf_prog *prog;
+
+	if (!v) {
+		meta.seq = seq;
+		prog = bpf_iter_get_info(&meta, true);
+		if (prog)
+			(void)unix_prog_seq_show(prog, &meta, v, 0);
+	}
+
+	unix_seq_stop(seq, v);
+}
+
+static const struct seq_operations bpf_iter_unix_seq_ops = {
+	.start	= unix_seq_start,
+	.next	= unix_seq_next,
+	.stop	= bpf_iter_unix_seq_stop,
+	.show	= bpf_iter_unix_seq_show,
+};
+#endif
 #endif
 
 static const struct net_proto_family unix_family_ops = {
@@ -3190,13 +3312,48 @@ static struct pernet_operations unix_net_ops = {
 	.exit = unix_net_exit,
 };
 
+#if IS_BUILTIN(CONFIG_UNIX) && defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_PROC_FS)
+DEFINE_BPF_ITER_FUNC(unix, struct bpf_iter_meta *meta,
+		     struct unix_sock *unix_sk, uid_t uid)
+
+static const struct bpf_iter_seq_info unix_seq_info = {
+	.seq_ops		= &bpf_iter_unix_seq_ops,
+	.init_seq_private	= bpf_iter_init_seq_net,
+	.fini_seq_private	= bpf_iter_fini_seq_net,
+	.seq_priv_size		= sizeof(struct seq_net_private),
+};
+
+static struct bpf_iter_reg unix_reg_info = {
+	.target			= "unix",
+	.ctx_arg_info_size	= 1,
+	.ctx_arg_info		= {
+		{ offsetof(struct bpf_iter__unix, unix_sk),
+		  PTR_TO_BTF_ID_OR_NULL },
+	},
+	.seq_info		= &unix_seq_info,
+};
+
+static void __init bpf_iter_register(void)
+{
+	unix_reg_info.ctx_arg_info[0].btf_id = btf_sock_ids[BTF_SOCK_TYPE_UNIX];
+	if (bpf_iter_reg_target(&unix_reg_info))
+		pr_warn("Warning: could not register bpf iterator unix\n");
+}
+#endif
+
 static int __init af_unix_init(void)
 {
 	int rc = -1;
 
 	BUILD_BUG_ON(sizeof(struct unix_skb_parms) > sizeof_field(struct sk_buff, cb));
 
-	rc = proto_register(&unix_proto, 1);
+	rc = proto_register(&unix_dgram_proto, 1);
+	if (rc != 0) {
+		pr_crit("%s: Cannot create unix_sock SLAB cache!\n", __func__);
+		goto out;
+	}
+
+	rc = proto_register(&unix_stream_proto, 1);
 	if (rc != 0) {
 		pr_crit("%s: Cannot create unix_sock SLAB cache!\n", __func__);
 		goto out;
@@ -3205,6 +3362,11 @@ static int __init af_unix_init(void)
 	sock_register(&unix_family_ops);
 	register_pernet_subsys(&unix_net_ops);
 	unix_bpf_build_proto();
+
+#if IS_BUILTIN(CONFIG_UNIX) && defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_PROC_FS)
+	bpf_iter_register();
+#endif
+
 out:
 	return rc;
 }
@@ -3212,7 +3374,8 @@ out:
 static void __exit af_unix_exit(void)
 {
 	sock_unregister(PF_UNIX);
-	proto_unregister(&unix_proto);
+	proto_unregister(&unix_dgram_proto);
+	proto_unregister(&unix_stream_proto);
 	unregister_pernet_subsys(&unix_net_ops);
 }
 
diff --git a/net/unix/unix_bpf.c b/net/unix/unix_bpf.c
index 20f53575b5c9..b927e2baae50 100644
--- a/net/unix/unix_bpf.c
+++ b/net/unix/unix_bpf.c
@@ -38,9 +38,18 @@ static int unix_msg_wait_data(struct sock *sk, struct sk_psock *psock,
 	return ret;
 }
 
-static int unix_dgram_bpf_recvmsg(struct sock *sk, struct msghdr *msg,
-				  size_t len, int nonblock, int flags,
-				  int *addr_len)
+static int __unix_recvmsg(struct sock *sk, struct msghdr *msg,
+			  size_t len, int flags)
+{
+	if (sk->sk_type == SOCK_DGRAM)
+		return __unix_dgram_recvmsg(sk, msg, len, flags);
+	else
+		return __unix_stream_recvmsg(sk, msg, len, flags);
+}
+
+static int unix_bpf_recvmsg(struct sock *sk, struct msghdr *msg,
+			    size_t len, int nonblock, int flags,
+			    int *addr_len)
 {
 	struct unix_sock *u = unix_sk(sk);
 	struct sk_psock *psock;
@@ -48,14 +57,14 @@ static int unix_dgram_bpf_recvmsg(struct sock *sk, struct msghdr *msg,
 
 	psock = sk_psock_get(sk);
 	if (unlikely(!psock))
-		return __unix_dgram_recvmsg(sk, msg, len, flags);
+		return __unix_recvmsg(sk, msg, len, flags);
 
 	mutex_lock(&u->iolock);
 	if (!skb_queue_empty(&sk->sk_receive_queue) &&
 	    sk_psock_queue_empty(psock)) {
 		mutex_unlock(&u->iolock);
 		sk_psock_put(sk, psock);
-		return __unix_dgram_recvmsg(sk, msg, len, flags);
+		return __unix_recvmsg(sk, msg, len, flags);
 	}
 
 msg_bytes_ready:
@@ -71,7 +80,7 @@ msg_bytes_ready:
 				goto msg_bytes_ready;
 			mutex_unlock(&u->iolock);
 			sk_psock_put(sk, psock);
-			return __unix_dgram_recvmsg(sk, msg, len, flags);
+			return __unix_recvmsg(sk, msg, len, flags);
 		}
 		copied = -EAGAIN;
 	}
@@ -80,30 +89,55 @@ msg_bytes_ready:
 	return copied;
 }
 
-static struct proto *unix_prot_saved __read_mostly;
-static DEFINE_SPINLOCK(unix_prot_lock);
-static struct proto unix_bpf_prot;
+static struct proto *unix_dgram_prot_saved __read_mostly;
+static DEFINE_SPINLOCK(unix_dgram_prot_lock);
+static struct proto unix_dgram_bpf_prot;
+
+static struct proto *unix_stream_prot_saved __read_mostly;
+static DEFINE_SPINLOCK(unix_stream_prot_lock);
+static struct proto unix_stream_bpf_prot;
 
-static void unix_bpf_rebuild_protos(struct proto *prot, const struct proto *base)
+static void unix_dgram_bpf_rebuild_protos(struct proto *prot, const struct proto *base)
 {
 	*prot        = *base;
 	prot->close  = sock_map_close;
-	prot->recvmsg = unix_dgram_bpf_recvmsg;
+	prot->recvmsg = unix_bpf_recvmsg;
+}
+
+static void unix_stream_bpf_rebuild_protos(struct proto *prot,
+					   const struct proto *base)
+{
+	*prot        = *base;
+	prot->close  = sock_map_close;
+	prot->recvmsg = unix_bpf_recvmsg;
+	prot->unhash  = sock_map_unhash;
+}
+
+static void unix_dgram_bpf_check_needs_rebuild(struct proto *ops)
+{
+	if (unlikely(ops != smp_load_acquire(&unix_dgram_prot_saved))) {
+		spin_lock_bh(&unix_dgram_prot_lock);
+		if (likely(ops != unix_dgram_prot_saved)) {
+			unix_dgram_bpf_rebuild_protos(&unix_dgram_bpf_prot, ops);
+			smp_store_release(&unix_dgram_prot_saved, ops);
+		}
+		spin_unlock_bh(&unix_dgram_prot_lock);
+	}
 }
 
-static void unix_bpf_check_needs_rebuild(struct proto *ops)
+static void unix_stream_bpf_check_needs_rebuild(struct proto *ops)
 {
-	if (unlikely(ops != smp_load_acquire(&unix_prot_saved))) {
-		spin_lock_bh(&unix_prot_lock);
-		if (likely(ops != unix_prot_saved)) {
-			unix_bpf_rebuild_protos(&unix_bpf_prot, ops);
-			smp_store_release(&unix_prot_saved, ops);
+	if (unlikely(ops != smp_load_acquire(&unix_stream_prot_saved))) {
+		spin_lock_bh(&unix_stream_prot_lock);
+		if (likely(ops != unix_stream_prot_saved)) {
+			unix_stream_bpf_rebuild_protos(&unix_stream_bpf_prot, ops);
+			smp_store_release(&unix_stream_prot_saved, ops);
 		}
-		spin_unlock_bh(&unix_prot_lock);
+		spin_unlock_bh(&unix_stream_prot_lock);
 	}
 }
 
-int unix_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore)
+int unix_dgram_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore)
 {
 	if (sk->sk_type != SOCK_DGRAM)
 		return -EOPNOTSUPP;
@@ -114,12 +148,27 @@ int unix_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore)
 		return 0;
 	}
 
-	unix_bpf_check_needs_rebuild(psock->sk_proto);
-	WRITE_ONCE(sk->sk_prot, &unix_bpf_prot);
+	unix_dgram_bpf_check_needs_rebuild(psock->sk_proto);
+	WRITE_ONCE(sk->sk_prot, &unix_dgram_bpf_prot);
+	return 0;
+}
+
+int unix_stream_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore)
+{
+	if (restore) {
+		sk->sk_write_space = psock->saved_write_space;
+		WRITE_ONCE(sk->sk_prot, psock->sk_proto);
+		return 0;
+	}
+
+	unix_stream_bpf_check_needs_rebuild(psock->sk_proto);
+	WRITE_ONCE(sk->sk_prot, &unix_stream_bpf_prot);
 	return 0;
 }
 
 void __init unix_bpf_build_proto(void)
 {
-	unix_bpf_rebuild_protos(&unix_bpf_prot, &unix_proto);
+	unix_dgram_bpf_rebuild_protos(&unix_dgram_bpf_prot, &unix_dgram_proto);
+	unix_stream_bpf_rebuild_protos(&unix_stream_bpf_prot, &unix_stream_proto);
+
 }