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

Alexei Starovoitov says:

====================
pull-request: bpf-next 2021-07-15

The following pull-request contains BPF updates for your *net-next* tree.

We've added 45 non-merge commits during the last 15 day(s) which contain
a total of 52 files changed, 3122 insertions(+), 384 deletions(-).

The main changes are:

1) Introduce bpf timers, from Alexei.

2) Add sockmap support for unix datagram socket, from Cong.

3) Fix potential memleak and UAF in the verifier, from He.

4) Add bpf_get_func_ip helper, from Jiri.

5) Improvements to generic XDP mode, from Kumar.

6) Support for passing xdp_md to XDP programs in bpf_prog_run, from Zvi.
===================

Signed-off-by: David S. Miller <davem@davemloft.net>

9 files changed, 361 insertions, 94 deletions

diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c
index aa47af349ba8..cda8375bbbaf 100644
--- a/net/bpf/test_run.c
+++ b/net/bpf/test_run.c
@@ -15,6 +15,7 @@
 #include <linux/error-injection.h>
 #include <linux/smp.h>
 #include <linux/sock_diag.h>
+#include <net/xdp.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/bpf_test_run.h>
@@ -687,6 +688,64 @@ out:
 	return ret;
 }
 
+static int xdp_convert_md_to_buff(struct xdp_md *xdp_md, struct xdp_buff *xdp)
+{
+	unsigned int ingress_ifindex, rx_queue_index;
+	struct netdev_rx_queue *rxqueue;
+	struct net_device *device;
+
+	if (!xdp_md)
+		return 0;
+
+	if (xdp_md->egress_ifindex != 0)
+		return -EINVAL;
+
+	ingress_ifindex = xdp_md->ingress_ifindex;
+	rx_queue_index = xdp_md->rx_queue_index;
+
+	if (!ingress_ifindex && rx_queue_index)
+		return -EINVAL;
+
+	if (ingress_ifindex) {
+		device = dev_get_by_index(current->nsproxy->net_ns,
+					  ingress_ifindex);
+		if (!device)
+			return -ENODEV;
+
+		if (rx_queue_index >= device->real_num_rx_queues)
+			goto free_dev;
+
+		rxqueue = __netif_get_rx_queue(device, rx_queue_index);
+
+		if (!xdp_rxq_info_is_reg(&rxqueue->xdp_rxq))
+			goto free_dev;
+
+		xdp->rxq = &rxqueue->xdp_rxq;
+		/* The device is now tracked in the xdp->rxq for later
+		 * dev_put()
+		 */
+	}
+
+	xdp->data = xdp->data_meta + xdp_md->data;
+	return 0;
+
+free_dev:
+	dev_put(device);
+	return -EINVAL;
+}
+
+static void xdp_convert_buff_to_md(struct xdp_buff *xdp, struct xdp_md *xdp_md)
+{
+	if (!xdp_md)
+		return;
+
+	xdp_md->data = xdp->data - xdp->data_meta;
+	xdp_md->data_end = xdp->data_end - xdp->data_meta;
+
+	if (xdp_md->ingress_ifindex)
+		dev_put(xdp->rxq->dev);
+}
+
 int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr,
 			  union bpf_attr __user *uattr)
 {
@@ -697,35 +756,69 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr,
 	struct netdev_rx_queue *rxqueue;
 	struct xdp_buff xdp = {};
 	u32 retval, duration;
+	struct xdp_md *ctx;
 	u32 max_data_sz;
 	void *data;
-	int ret;
+	int ret = -EINVAL;
 
-	if (kattr->test.ctx_in || kattr->test.ctx_out)
-		return -EINVAL;
+	ctx = bpf_ctx_init(kattr, sizeof(struct xdp_md));
+	if (IS_ERR(ctx))
+		return PTR_ERR(ctx);
+
+	if (ctx) {
+		/* There can't be user provided data before the meta data */
+		if (ctx->data_meta || ctx->data_end != size ||
+		    ctx->data > ctx->data_end ||
+		    unlikely(xdp_metalen_invalid(ctx->data)))
+			goto free_ctx;
+		/* Meta data is allocated from the headroom */
+		headroom -= ctx->data;
+	}
 
 	/* XDP have extra tailroom as (most) drivers use full page */
 	max_data_sz = 4096 - headroom - tailroom;
 
 	data = bpf_test_init(kattr, max_data_sz, headroom, tailroom);
-	if (IS_ERR(data))
-		return PTR_ERR(data);
+	if (IS_ERR(data)) {
+		ret = PTR_ERR(data);
+		goto free_ctx;
+	}
 
 	rxqueue = __netif_get_rx_queue(current->nsproxy->net_ns->loopback_dev, 0);
 	xdp_init_buff(&xdp, headroom + max_data_sz + tailroom,
 		      &rxqueue->xdp_rxq);
 	xdp_prepare_buff(&xdp, data, headroom, size, true);
 
+	ret = xdp_convert_md_to_buff(ctx, &xdp);
+	if (ret)
+		goto free_data;
+
 	bpf_prog_change_xdp(NULL, prog);
 	ret = bpf_test_run(prog, &xdp, repeat, &retval, &duration, true);
+	/* We convert the xdp_buff back to an xdp_md before checking the return
+	 * code so the reference count of any held netdevice will be decremented
+	 * even if the test run failed.
+	 */
+	xdp_convert_buff_to_md(&xdp, ctx);
 	if (ret)
 		goto out;
-	if (xdp.data != data + headroom || xdp.data_end != xdp.data + size)
-		size = xdp.data_end - xdp.data;
-	ret = bpf_test_finish(kattr, uattr, xdp.data, size, retval, duration);
+
+	if (xdp.data_meta != data + headroom ||
+	    xdp.data_end != xdp.data_meta + size)
+		size = xdp.data_end - xdp.data_meta;
+
+	ret = bpf_test_finish(kattr, uattr, xdp.data_meta, size, retval,
+			      duration);
+	if (!ret)
+		ret = bpf_ctx_finish(kattr, uattr, ctx,
+				     sizeof(struct xdp_md));
+
 out:
 	bpf_prog_change_xdp(prog, NULL);
+free_data:
 	kfree(data);
+free_ctx:
+	kfree(ctx);
 	return ret;
 }
 
diff --git a/net/core/Makefile b/net/core/Makefile
index f7f16650fe9e..35ced6201814 100644
--- a/net/core/Makefile
+++ b/net/core/Makefile
@@ -33,8 +33,6 @@ obj-$(CONFIG_HWBM) += hwbm.o
 obj-$(CONFIG_NET_DEVLINK) += devlink.o
 obj-$(CONFIG_GRO_CELLS) += gro_cells.o
 obj-$(CONFIG_FAILOVER) += failover.o
-ifeq ($(CONFIG_INET),y)
 obj-$(CONFIG_NET_SOCK_MSG) += skmsg.o
 obj-$(CONFIG_BPF_SYSCALL) += sock_map.o
-endif
 obj-$(CONFIG_BPF_SYSCALL) += bpf_sk_storage.o
diff --git a/net/core/dev.c b/net/core/dev.c
index 64b21f0a2048..3ee58876e8f5 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4744,45 +4744,18 @@ static struct netdev_rx_queue *netif_get_rxqueue(struct sk_buff *skb)
 	return rxqueue;
 }
 
-static u32 netif_receive_generic_xdp(struct sk_buff *skb,
-				     struct xdp_buff *xdp,
-				     struct bpf_prog *xdp_prog)
+u32 bpf_prog_run_generic_xdp(struct sk_buff *skb, struct xdp_buff *xdp,
+			     struct bpf_prog *xdp_prog)
 {
 	void *orig_data, *orig_data_end, *hard_start;
 	struct netdev_rx_queue *rxqueue;
-	u32 metalen, act = XDP_DROP;
 	bool orig_bcast, orig_host;
 	u32 mac_len, frame_sz;
 	__be16 orig_eth_type;
 	struct ethhdr *eth;
+	u32 metalen, act;
 	int off;
 
-	/* Reinjected packets coming from act_mirred or similar should
-	 * not get XDP generic processing.
-	 */
-	if (skb_is_redirected(skb))
-		return XDP_PASS;
-
-	/* XDP packets must be linear and must have sufficient headroom
-	 * of XDP_PACKET_HEADROOM bytes. This is the guarantee that also
-	 * native XDP provides, thus we need to do it here as well.
-	 */
-	if (skb_cloned(skb) || skb_is_nonlinear(skb) ||
-	    skb_headroom(skb) < XDP_PACKET_HEADROOM) {
-		int hroom = XDP_PACKET_HEADROOM - skb_headroom(skb);
-		int troom = skb->tail + skb->data_len - skb->end;
-
-		/* In case we have to go down the path and also linearize,
-		 * then lets do the pskb_expand_head() work just once here.
-		 */
-		if (pskb_expand_head(skb,
-				     hroom > 0 ? ALIGN(hroom, NET_SKB_PAD) : 0,
-				     troom > 0 ? troom + 128 : 0, GFP_ATOMIC))
-			goto do_drop;
-		if (skb_linearize(skb))
-			goto do_drop;
-	}
-
 	/* The XDP program wants to see the packet starting at the MAC
 	 * header.
 	 */
@@ -4837,6 +4810,13 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb,
 		skb->protocol = eth_type_trans(skb, skb->dev);
 	}
 
+	/* Redirect/Tx gives L2 packet, code that will reuse skb must __skb_pull
+	 * before calling us again on redirect path. We do not call do_redirect
+	 * as we leave that up to the caller.
+	 *
+	 * Caller is responsible for managing lifetime of skb (i.e. calling
+	 * kfree_skb in response to actions it cannot handle/XDP_DROP).
+	 */
 	switch (act) {
 	case XDP_REDIRECT:
 	case XDP_TX:
@@ -4847,6 +4827,49 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb,
 		if (metalen)
 			skb_metadata_set(skb, metalen);
 		break;
+	}
+
+	return act;
+}
+
+static u32 netif_receive_generic_xdp(struct sk_buff *skb,
+				     struct xdp_buff *xdp,
+				     struct bpf_prog *xdp_prog)
+{
+	u32 act = XDP_DROP;
+
+	/* Reinjected packets coming from act_mirred or similar should
+	 * not get XDP generic processing.
+	 */
+	if (skb_is_redirected(skb))
+		return XDP_PASS;
+
+	/* XDP packets must be linear and must have sufficient headroom
+	 * of XDP_PACKET_HEADROOM bytes. This is the guarantee that also
+	 * native XDP provides, thus we need to do it here as well.
+	 */
+	if (skb_cloned(skb) || skb_is_nonlinear(skb) ||
+	    skb_headroom(skb) < XDP_PACKET_HEADROOM) {
+		int hroom = XDP_PACKET_HEADROOM - skb_headroom(skb);
+		int troom = skb->tail + skb->data_len - skb->end;
+
+		/* In case we have to go down the path and also linearize,
+		 * then lets do the pskb_expand_head() work just once here.
+		 */
+		if (pskb_expand_head(skb,
+				     hroom > 0 ? ALIGN(hroom, NET_SKB_PAD) : 0,
+				     troom > 0 ? troom + 128 : 0, GFP_ATOMIC))
+			goto do_drop;
+		if (skb_linearize(skb))
+			goto do_drop;
+	}
+
+	act = bpf_prog_run_generic_xdp(skb, xdp, xdp_prog);
+	switch (act) {
+	case XDP_REDIRECT:
+	case XDP_TX:
+	case XDP_PASS:
+		break;
 	default:
 		bpf_warn_invalid_xdp_action(act);
 		fallthrough;
@@ -5312,7 +5335,6 @@ another_round:
 			ret = NET_RX_DROP;
 			goto out;
 		}
-		skb_reset_mac_len(skb);
 	}
 
 	if (eth_type_vlan(skb->protocol)) {
@@ -5638,25 +5660,6 @@ static int generic_xdp_install(struct net_device *dev, struct netdev_bpf *xdp)
 	struct bpf_prog *new = xdp->prog;
 	int ret = 0;
 
-	if (new) {
-		u32 i;
-
-		mutex_lock(&new->aux->used_maps_mutex);
-
-		/* generic XDP does not work with DEVMAPs that can
-		 * have a bpf_prog installed on an entry
-		 */
-		for (i = 0; i < new->aux->used_map_cnt; i++) {
-			if (dev_map_can_have_prog(new->aux->used_maps[i]) ||
-			    cpu_map_prog_allowed(new->aux->used_maps[i])) {
-				mutex_unlock(&new->aux->used_maps_mutex);
-				return -EINVAL;
-			}
-		}
-
-		mutex_unlock(&new->aux->used_maps_mutex);
-	}
-
 	switch (xdp->command) {
 	case XDP_SETUP_PROG:
 		rcu_assign_pointer(dev->xdp_prog, new);
diff --git a/net/core/filter.c b/net/core/filter.c
index d70187ce851b..3b4986e96e9c 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -77,6 +77,7 @@
 #include <net/transp_v6.h>
 #include <linux/btf_ids.h>
 #include <net/tls.h>
+#include <net/xdp.h>
 
 static const struct bpf_func_proto *
 bpf_sk_base_func_proto(enum bpf_func_id func_id);
@@ -3880,8 +3881,7 @@ BPF_CALL_2(bpf_xdp_adjust_meta, struct xdp_buff *, xdp, int, offset)
 	if (unlikely(meta < xdp_frame_end ||
 		     meta > xdp->data))
 		return -EINVAL;
-	if (unlikely((metalen & (sizeof(__u32) - 1)) ||
-		     (metalen > 32)))
+	if (unlikely(xdp_metalen_invalid(metalen)))
 		return -EACCES;
 
 	xdp->data_meta = meta;
@@ -4040,8 +4040,12 @@ static int xdp_do_generic_redirect_map(struct net_device *dev,
 			goto err;
 		consume_skb(skb);
 		break;
+	case BPF_MAP_TYPE_CPUMAP:
+		err = cpu_map_generic_redirect(fwd, skb);
+		if (unlikely(err))
+			goto err;
+		break;
 	default:
-		/* TODO: Handle BPF_MAP_TYPE_CPUMAP */
 		err = -EBADRQC;
 		goto err;
 	}
diff --git a/net/core/sock_map.c b/net/core/sock_map.c
index 60decd6420ca..ae5fa4338d9c 100644
--- a/net/core/sock_map.c
+++ b/net/core/sock_map.c
@@ -211,8 +211,6 @@ out:
 	return psock;
 }
 
-static bool sock_map_redirect_allowed(const struct sock *sk);
-
 static int sock_map_link(struct bpf_map *map, struct sock *sk)
 {
 	struct sk_psock_progs *progs = sock_map_progs(map);
@@ -223,13 +221,6 @@ static int sock_map_link(struct bpf_map *map, struct sock *sk)
 	struct sk_psock *psock;
 	int ret;
 
-	/* Only sockets we can redirect into/from in BPF need to hold
-	 * refs to parser/verdict progs and have their sk_data_ready
-	 * and sk_write_space callbacks overridden.
-	 */
-	if (!sock_map_redirect_allowed(sk))
-		goto no_progs;
-
 	stream_verdict = READ_ONCE(progs->stream_verdict);
 	if (stream_verdict) {
 		stream_verdict = bpf_prog_inc_not_zero(stream_verdict);
@@ -264,7 +255,6 @@ static int sock_map_link(struct bpf_map *map, struct sock *sk)
 		}
 	}
 
-no_progs:
 	psock = sock_map_psock_get_checked(sk);
 	if (IS_ERR(psock)) {
 		ret = PTR_ERR(psock);
@@ -527,12 +517,6 @@ static bool sk_is_tcp(const struct sock *sk)
 	       sk->sk_protocol == IPPROTO_TCP;
 }
 
-static bool sk_is_udp(const struct sock *sk)
-{
-	return sk->sk_type == SOCK_DGRAM &&
-	       sk->sk_protocol == IPPROTO_UDP;
-}
-
 static bool sock_map_redirect_allowed(const struct sock *sk)
 {
 	if (sk_is_tcp(sk))
@@ -550,10 +534,7 @@ static bool sock_map_sk_state_allowed(const struct sock *sk)
 {
 	if (sk_is_tcp(sk))
 		return (1 << sk->sk_state) & (TCPF_ESTABLISHED | TCPF_LISTEN);
-	else if (sk_is_udp(sk))
-		return sk_hashed(sk);
-
-	return false;
+	return true;
 }
 
 static int sock_hash_update_common(struct bpf_map *map, void *key,
@@ -1536,6 +1517,7 @@ void sock_map_close(struct sock *sk, long timeout)
 	release_sock(sk);
 	saved_close(sk, timeout);
 }
+EXPORT_SYMBOL_GPL(sock_map_close);
 
 static int sock_map_iter_attach_target(struct bpf_prog *prog,
 				       union bpf_iter_link_info *linfo,
diff --git a/net/ipv4/udp_bpf.c b/net/ipv4/udp_bpf.c
index 45b8782aec0c..cb1d113ce6fd 100644
--- a/net/ipv4/udp_bpf.c
+++ b/net/ipv4/udp_bpf.c
@@ -112,7 +112,6 @@ static struct proto udp_bpf_prots[UDP_BPF_NUM_PROTS];
 static void udp_bpf_rebuild_protos(struct proto *prot, const struct proto *base)
 {
 	*prot        = *base;
-	prot->unhash = sock_map_unhash;
 	prot->close  = sock_map_close;
 	prot->recvmsg = udp_bpf_recvmsg;
 }
diff --git a/net/unix/Makefile b/net/unix/Makefile
index 54e58cc4f945..20491825b4d0 100644
--- a/net/unix/Makefile
+++ b/net/unix/Makefile
@@ -7,6 +7,7 @@ obj-$(CONFIG_UNIX)	+= unix.o
 
 unix-y			:= af_unix.o garbage.o
 unix-$(CONFIG_SYSCTL)	+= sysctl_net_unix.o
+unix-$(CONFIG_BPF_SYSCALL) += unix_bpf.o
 
 obj-$(CONFIG_UNIX_DIAG)	+= unix_diag.o
 unix_diag-y		:= diag.o
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 23c92ad15c61..89927678c0dc 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -494,6 +494,7 @@ static void unix_dgram_disconnected(struct sock *sk, struct sock *other)
 			sk_error_report(other);
 		}
 	}
+	sk->sk_state = other->sk_state = TCP_CLOSE;
 }
 
 static void unix_sock_destructor(struct sock *sk)
@@ -669,6 +670,8 @@ static ssize_t unix_stream_splice_read(struct socket *,  loff_t *ppos,
 				       unsigned int flags);
 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_dgram_connect(struct socket *, struct sockaddr *,
 			      int, int);
 static int unix_seqpacket_sendmsg(struct socket *, struct msghdr *, size_t);
@@ -746,6 +749,7 @@ static const struct proto_ops unix_dgram_ops = {
 	.listen =	sock_no_listen,
 	.shutdown =	unix_shutdown,
 	.sendmsg =	unix_dgram_sendmsg,
+	.read_sock =	unix_read_sock,
 	.recvmsg =	unix_dgram_recvmsg,
 	.mmap =		sock_no_mmap,
 	.sendpage =	sock_no_sendpage,
@@ -777,10 +781,21 @@ static const struct proto_ops unix_seqpacket_ops = {
 	.show_fdinfo =	unix_show_fdinfo,
 };
 
-static struct proto unix_proto = {
+static void unix_close(struct sock *sk, long timeout)
+{
+	/* Nothing to do here, unix socket does not need a ->close().
+	 * This is merely for sockmap.
+	 */
+}
+
+struct proto unix_proto = {
 	.name			= "UNIX",
 	.owner			= THIS_MODULE,
 	.obj_size		= sizeof(struct unix_sock),
+	.close			= unix_close,
+#ifdef CONFIG_BPF_SYSCALL
+	.psock_update_sk_prot	= unix_bpf_update_proto,
+#endif
 };
 
 static struct sock *unix_create1(struct net *net, struct socket *sock, int kern)
@@ -864,6 +879,7 @@ static int unix_release(struct socket *sock)
 	if (!sk)
 		return 0;
 
+	sk->sk_prot->close(sk, 0);
 	unix_release_sock(sk, 0);
 	sock->sk = NULL;
 
@@ -1199,6 +1215,9 @@ restart:
 		unix_peer(sk) = other;
 		unix_state_double_unlock(sk, other);
 	}
+
+	if (unix_peer(sk))
+		sk->sk_state = other->sk_state = TCP_ESTABLISHED;
 	return 0;
 
 out_unlock:
@@ -1431,12 +1450,10 @@ static int unix_socketpair(struct socket *socka, struct socket *sockb)
 	init_peercred(ska);
 	init_peercred(skb);
 
-	if (ska->sk_type != SOCK_DGRAM) {
-		ska->sk_state = TCP_ESTABLISHED;
-		skb->sk_state = TCP_ESTABLISHED;
-		socka->state  = SS_CONNECTED;
-		sockb->state  = SS_CONNECTED;
-	}
+	ska->sk_state = TCP_ESTABLISHED;
+	skb->sk_state = TCP_ESTABLISHED;
+	socka->state  = SS_CONNECTED;
+	sockb->state  = SS_CONNECTED;
 	return 0;
 }
 
@@ -2081,11 +2098,11 @@ static void unix_copy_addr(struct msghdr *msg, struct sock *sk)
 	}
 }
 
-static int unix_dgram_recvmsg(struct socket *sock, struct msghdr *msg,
-			      size_t size, int flags)
+int __unix_dgram_recvmsg(struct sock *sk, struct msghdr *msg, size_t size,
+			 int flags)
 {
 	struct scm_cookie scm;
-	struct sock *sk = sock->sk;
+	struct socket *sock = sk->sk_socket;
 	struct unix_sock *u = unix_sk(sk);
 	struct sk_buff *skb, *last;
 	long timeo;
@@ -2188,6 +2205,53 @@ out:
 	return err;
 }
 
+static int unix_dgram_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
+			      int flags)
+{
+	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,
+					    flags & ~MSG_DONTWAIT, NULL);
+#endif
+	return __unix_dgram_recvmsg(sk, msg, size, flags);
+}
+
+static int unix_read_sock(struct sock *sk, read_descriptor_t *desc,
+			  sk_read_actor_t recv_actor)
+{
+	int copied = 0;
+
+	while (1) {
+		struct unix_sock *u = unix_sk(sk);
+		struct sk_buff *skb;
+		int used, err;
+
+		mutex_lock(&u->iolock);
+		skb = skb_recv_datagram(sk, 0, 1, &err);
+		mutex_unlock(&u->iolock);
+		if (!skb)
+			return err;
+
+		used = recv_actor(desc, skb, 0, skb->len);
+		if (used <= 0) {
+			if (!copied)
+				copied = used;
+			kfree_skb(skb);
+			break;
+		} else if (used <= skb->len) {
+			copied += used;
+		}
+
+		kfree_skb(skb);
+		if (!desc->count)
+			break;
+	}
+
+	return copied;
+}
+
 /*
  *	Sleep until more data has arrived. But check for races..
  */
@@ -2925,6 +2989,7 @@ static int __init af_unix_init(void)
 
 	sock_register(&unix_family_ops);
 	register_pernet_subsys(&unix_net_ops);
+	unix_bpf_build_proto();
 out:
 	return rc;
 }
diff --git a/net/unix/unix_bpf.c b/net/unix/unix_bpf.c
new file mode 100644
index 000000000000..db0cda29fb2f
--- /dev/null
+++ b/net/unix/unix_bpf.c
@@ -0,0 +1,122 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Cong Wang <cong.wang@bytedance.com> */
+
+#include <linux/skmsg.h>
+#include <linux/bpf.h>
+#include <net/sock.h>
+#include <net/af_unix.h>
+
+#define unix_sk_has_data(__sk, __psock)					\
+		({	!skb_queue_empty(&__sk->sk_receive_queue) ||	\
+			!skb_queue_empty(&__psock->ingress_skb) ||	\
+			!list_empty(&__psock->ingress_msg);		\
+		})
+
+static int unix_msg_wait_data(struct sock *sk, struct sk_psock *psock,
+			      long timeo)
+{
+	DEFINE_WAIT_FUNC(wait, woken_wake_function);
+	struct unix_sock *u = unix_sk(sk);
+	int ret = 0;
+
+	if (sk->sk_shutdown & RCV_SHUTDOWN)
+		return 1;
+
+	if (!timeo)
+		return ret;
+
+	add_wait_queue(sk_sleep(sk), &wait);
+	sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk);
+	if (!unix_sk_has_data(sk, psock)) {
+		mutex_unlock(&u->iolock);
+		wait_woken(&wait, TASK_INTERRUPTIBLE, timeo);
+		mutex_lock(&u->iolock);
+		ret = unix_sk_has_data(sk, psock);
+	}
+	sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk);
+	remove_wait_queue(sk_sleep(sk), &wait);
+	return ret;
+}
+
+static int unix_dgram_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;
+	int copied, ret;
+
+	psock = sk_psock_get(sk);
+	if (unlikely(!psock))
+		return __unix_dgram_recvmsg(sk, msg, len, flags);
+
+	mutex_lock(&u->iolock);
+	if (!skb_queue_empty(&sk->sk_receive_queue) &&
+	    sk_psock_queue_empty(psock)) {
+		ret = __unix_dgram_recvmsg(sk, msg, len, flags);
+		goto out;
+	}
+
+msg_bytes_ready:
+	copied = sk_msg_recvmsg(sk, psock, msg, len, flags);
+	if (!copied) {
+		long timeo;
+		int data;
+
+		timeo = sock_rcvtimeo(sk, nonblock);
+		data = unix_msg_wait_data(sk, psock, timeo);
+		if (data) {
+			if (!sk_psock_queue_empty(psock))
+				goto msg_bytes_ready;
+			ret = __unix_dgram_recvmsg(sk, msg, len, flags);
+			goto out;
+		}
+		copied = -EAGAIN;
+	}
+	ret = copied;
+out:
+	mutex_unlock(&u->iolock);
+	sk_psock_put(sk, psock);
+	return ret;
+}
+
+static struct proto *unix_prot_saved __read_mostly;
+static DEFINE_SPINLOCK(unix_prot_lock);
+static struct proto unix_bpf_prot;
+
+static void unix_bpf_rebuild_protos(struct proto *prot, const struct proto *base)
+{
+	*prot        = *base;
+	prot->close  = sock_map_close;
+	prot->recvmsg = unix_dgram_bpf_recvmsg;
+}
+
+static void unix_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);
+		}
+		spin_unlock_bh(&unix_prot_lock);
+	}
+}
+
+int unix_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_bpf_check_needs_rebuild(psock->sk_proto);
+	WRITE_ONCE(sk->sk_prot, &unix_bpf_prot);
+	return 0;
+}
+
+void __init unix_bpf_build_proto(void)
+{
+	unix_bpf_rebuild_protos(&unix_bpf_prot, &unix_proto);
+}