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

Alexei Starovoitov says:

====================
pull-request: bpf-next 2020-06-01

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

We've added 55 non-merge commits during the last 1 day(s) which contain
a total of 91 files changed, 4986 insertions(+), 463 deletions(-).

The main changes are:

1) Add rx_queue_mapping to bpf_sock from Amritha.

2) Add BPF ring buffer, from Andrii.

3) Attach and run programs through devmap, from David.

4) Allow SO_BINDTODEVICE opt in bpf_setsockopt, from Ferenc.

5) link based flow_dissector, from Jakub.

6) Use tracing helpers for lsm programs, from Jiri.

7) Several sk_msg fixes and extensions, from John.
====================

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

5 files changed, 211 insertions, 133 deletions

diff --git a/net/core/dev.c b/net/core/dev.c
index ae37586f6ee8..10684833f864 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -5420,6 +5420,18 @@ 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;
+
+		/* 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]))
+				return -EINVAL;
+		}
+	}
+
 	switch (xdp->command) {
 	case XDP_SETUP_PROG:
 		rcu_assign_pointer(dev->xdp_prog, new);
@@ -8835,6 +8847,12 @@ int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack,
 			return -EINVAL;
 		}
 
+		if (prog->expected_attach_type == BPF_XDP_DEVMAP) {
+			NL_SET_ERR_MSG(extack, "BPF_XDP_DEVMAP programs can not be attached to a device");
+			bpf_prog_put(prog);
+			return -EINVAL;
+		}
+
 		/* prog->aux->id may be 0 for orphaned device-bound progs */
 		if (prog->aux->id && prog->aux->id == prog_id) {
 			bpf_prog_put(prog);
diff --git a/net/core/filter.c b/net/core/filter.c
index bd2853d23b50..ae82bcb03124 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -4248,6 +4248,9 @@ static const struct bpf_func_proto bpf_get_socket_uid_proto = {
 static int _bpf_setsockopt(struct sock *sk, int level, int optname,
 			   char *optval, int optlen, u32 flags)
 {
+	char devname[IFNAMSIZ];
+	struct net *net;
+	int ifindex;
 	int ret = 0;
 	int val;
 
@@ -4257,7 +4260,7 @@ static int _bpf_setsockopt(struct sock *sk, int level, int optname,
 	sock_owned_by_me(sk);
 
 	if (level == SOL_SOCKET) {
-		if (optlen != sizeof(int))
+		if (optlen != sizeof(int) && optname != SO_BINDTODEVICE)
 			return -EINVAL;
 		val = *((int *)optval);
 
@@ -4298,6 +4301,29 @@ static int _bpf_setsockopt(struct sock *sk, int level, int optname,
 				sk_dst_reset(sk);
 			}
 			break;
+		case SO_BINDTODEVICE:
+			ret = -ENOPROTOOPT;
+#ifdef CONFIG_NETDEVICES
+			optlen = min_t(long, optlen, IFNAMSIZ - 1);
+			strncpy(devname, optval, optlen);
+			devname[optlen] = 0;
+
+			ifindex = 0;
+			if (devname[0] != '\0') {
+				struct net_device *dev;
+
+				ret = -ENODEV;
+
+				net = sock_net(sk);
+				dev = dev_get_by_name(net, devname);
+				if (!dev)
+					break;
+				ifindex = dev->ifindex;
+				dev_put(dev);
+			}
+			ret = sock_bindtoindex(sk, ifindex, false);
+#endif
+			break;
 		default:
 			ret = -EINVAL;
 		}
@@ -6443,6 +6469,26 @@ sk_msg_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_msg_push_data_proto;
 	case BPF_FUNC_msg_pop_data:
 		return &bpf_msg_pop_data_proto;
+	case BPF_FUNC_perf_event_output:
+		return &bpf_event_output_data_proto;
+	case BPF_FUNC_get_current_uid_gid:
+		return &bpf_get_current_uid_gid_proto;
+	case BPF_FUNC_get_current_pid_tgid:
+		return &bpf_get_current_pid_tgid_proto;
+	case BPF_FUNC_sk_storage_get:
+		return &bpf_sk_storage_get_proto;
+	case BPF_FUNC_sk_storage_delete:
+		return &bpf_sk_storage_delete_proto;
+#ifdef CONFIG_CGROUPS
+	case BPF_FUNC_get_current_cgroup_id:
+		return &bpf_get_current_cgroup_id_proto;
+	case BPF_FUNC_get_current_ancestor_cgroup_id:
+		return &bpf_get_current_ancestor_cgroup_id_proto;
+#endif
+#ifdef CONFIG_CGROUP_NET_CLASSID
+	case BPF_FUNC_get_cgroup_classid:
+		return &bpf_get_cgroup_classid_curr_proto;
+#endif
 	default:
 		return bpf_base_func_proto(func_id);
 	}
@@ -6829,6 +6875,7 @@ bool bpf_sock_is_valid_access(int off, int size, enum bpf_access_type type,
 	case offsetof(struct bpf_sock, protocol):
 	case offsetof(struct bpf_sock, dst_port):
 	case offsetof(struct bpf_sock, src_port):
+	case offsetof(struct bpf_sock, rx_queue_mapping):
 	case bpf_ctx_range(struct bpf_sock, src_ip4):
 	case bpf_ctx_range_till(struct bpf_sock, src_ip6[0], src_ip6[3]):
 	case bpf_ctx_range(struct bpf_sock, dst_ip4):
@@ -6994,6 +7041,13 @@ static bool xdp_is_valid_access(int off, int size,
 				const struct bpf_prog *prog,
 				struct bpf_insn_access_aux *info)
 {
+	if (prog->expected_attach_type != BPF_XDP_DEVMAP) {
+		switch (off) {
+		case offsetof(struct xdp_md, egress_ifindex):
+			return false;
+		}
+	}
+
 	if (type == BPF_WRITE) {
 		if (bpf_prog_is_dev_bound(prog->aux)) {
 			switch (off) {
@@ -7257,6 +7311,11 @@ static bool sk_msg_is_valid_access(int off, int size,
 		if (size != sizeof(__u64))
 			return false;
 		break;
+	case offsetof(struct sk_msg_md, sk):
+		if (size != sizeof(__u64))
+			return false;
+		info->reg_type = PTR_TO_SOCKET;
+		break;
 	case bpf_ctx_range(struct sk_msg_md, family):
 	case bpf_ctx_range(struct sk_msg_md, remote_ip4):
 	case bpf_ctx_range(struct sk_msg_md, local_ip4):
@@ -7872,6 +7931,23 @@ u32 bpf_sock_convert_ctx_access(enum bpf_access_type type,
 						    skc_state),
 				       target_size));
 		break;
+	case offsetof(struct bpf_sock, rx_queue_mapping):
+#ifdef CONFIG_XPS
+		*insn++ = BPF_LDX_MEM(
+			BPF_FIELD_SIZEOF(struct sock, sk_rx_queue_mapping),
+			si->dst_reg, si->src_reg,
+			bpf_target_off(struct sock, sk_rx_queue_mapping,
+				       sizeof_field(struct sock,
+						    sk_rx_queue_mapping),
+				       target_size));
+		*insn++ = BPF_JMP_IMM(BPF_JNE, si->dst_reg, NO_QUEUE_MAPPING,
+				      1);
+		*insn++ = BPF_MOV64_IMM(si->dst_reg, -1);
+#else
+		*insn++ = BPF_MOV64_IMM(si->dst_reg, -1);
+		*target_size = 2;
+#endif
+		break;
 	}
 
 	return insn - insn_buf;
@@ -7942,6 +8018,16 @@ static u32 xdp_convert_ctx_access(enum bpf_access_type type,
 				      offsetof(struct xdp_rxq_info,
 					       queue_index));
 		break;
+	case offsetof(struct xdp_md, egress_ifindex):
+		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct xdp_buff, txq),
+				      si->dst_reg, si->src_reg,
+				      offsetof(struct xdp_buff, txq));
+		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct xdp_txq_info, dev),
+				      si->dst_reg, si->dst_reg,
+				      offsetof(struct xdp_txq_info, dev));
+		*insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg,
+				      offsetof(struct net_device, ifindex));
+		break;
 	}
 
 	return insn - insn_buf;
@@ -8593,6 +8679,12 @@ static u32 sk_msg_convert_ctx_access(enum bpf_access_type type,
 				      si->dst_reg, si->src_reg,
 				      offsetof(struct sk_msg_sg, size));
 		break;
+
+	case offsetof(struct sk_msg_md, sk):
+		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_msg, sk),
+				      si->dst_reg, si->src_reg,
+				      offsetof(struct sk_msg, sk));
+		break;
 	}
 
 	return insn - insn_buf;
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 0aeb33572feb..d02df0b6d0d9 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -31,8 +31,7 @@
 #include <net/netfilter/nf_conntrack_core.h>
 #include <net/netfilter/nf_conntrack_labels.h>
 #endif
-
-static DEFINE_MUTEX(flow_dissector_mutex);
+#include <linux/bpf-netns.h>
 
 static void dissector_set_key(struct flow_dissector *flow_dissector,
 			      enum flow_dissector_key_id key_id)
@@ -70,54 +69,11 @@ void skb_flow_dissector_init(struct flow_dissector *flow_dissector,
 }
 EXPORT_SYMBOL(skb_flow_dissector_init);
 
-int skb_flow_dissector_prog_query(const union bpf_attr *attr,
-				  union bpf_attr __user *uattr)
-{
-	__u32 __user *prog_ids = u64_to_user_ptr(attr->query.prog_ids);
-	u32 prog_id, prog_cnt = 0, flags = 0;
-	struct bpf_prog *attached;
-	struct net *net;
-
-	if (attr->query.query_flags)
-		return -EINVAL;
-
-	net = get_net_ns_by_fd(attr->query.target_fd);
-	if (IS_ERR(net))
-		return PTR_ERR(net);
-
-	rcu_read_lock();
-	attached = rcu_dereference(net->flow_dissector_prog);
-	if (attached) {
-		prog_cnt = 1;
-		prog_id = attached->aux->id;
-	}
-	rcu_read_unlock();
-
-	put_net(net);
-
-	if (copy_to_user(&uattr->query.attach_flags, &flags, sizeof(flags)))
-		return -EFAULT;
-	if (copy_to_user(&uattr->query.prog_cnt, &prog_cnt, sizeof(prog_cnt)))
-		return -EFAULT;
-
-	if (!attr->query.prog_cnt || !prog_ids || !prog_cnt)
-		return 0;
-
-	if (copy_to_user(prog_ids, &prog_id, sizeof(u32)))
-		return -EFAULT;
-
-	return 0;
-}
-
-int skb_flow_dissector_bpf_prog_attach(const union bpf_attr *attr,
-				       struct bpf_prog *prog)
+#ifdef CONFIG_BPF_SYSCALL
+int flow_dissector_bpf_prog_attach(struct net *net, struct bpf_prog *prog)
 {
+	enum netns_bpf_attach_type type = NETNS_BPF_FLOW_DISSECTOR;
 	struct bpf_prog *attached;
-	struct net *net;
-	int ret = 0;
-
-	net = current->nsproxy->net_ns;
-	mutex_lock(&flow_dissector_mutex);
 
 	if (net == &init_net) {
 		/* BPF flow dissector in the root namespace overrides
@@ -130,70 +86,29 @@ int skb_flow_dissector_bpf_prog_attach(const union bpf_attr *attr,
 		for_each_net(ns) {
 			if (ns == &init_net)
 				continue;
-			if (rcu_access_pointer(ns->flow_dissector_prog)) {
-				ret = -EEXIST;
-				goto out;
-			}
+			if (rcu_access_pointer(ns->bpf.progs[type]))
+				return -EEXIST;
 		}
 	} else {
 		/* Make sure root flow dissector is not attached
 		 * when attaching to the non-root namespace.
 		 */
-		if (rcu_access_pointer(init_net.flow_dissector_prog)) {
-			ret = -EEXIST;
-			goto out;
-		}
+		if (rcu_access_pointer(init_net.bpf.progs[type]))
+			return -EEXIST;
 	}
 
-	attached = rcu_dereference_protected(net->flow_dissector_prog,
-					     lockdep_is_held(&flow_dissector_mutex));
-	if (attached == prog) {
+	attached = rcu_dereference_protected(net->bpf.progs[type],
+					     lockdep_is_held(&netns_bpf_mutex));
+	if (attached == prog)
 		/* The same program cannot be attached twice */
-		ret = -EINVAL;
-		goto out;
-	}
-	rcu_assign_pointer(net->flow_dissector_prog, prog);
+		return -EINVAL;
+
+	rcu_assign_pointer(net->bpf.progs[type], prog);
 	if (attached)
 		bpf_prog_put(attached);
-out:
-	mutex_unlock(&flow_dissector_mutex);
-	return ret;
-}
-
-static int flow_dissector_bpf_prog_detach(struct net *net)
-{
-	struct bpf_prog *attached;
-
-	mutex_lock(&flow_dissector_mutex);
-	attached = rcu_dereference_protected(net->flow_dissector_prog,
-					     lockdep_is_held(&flow_dissector_mutex));
-	if (!attached) {
-		mutex_unlock(&flow_dissector_mutex);
-		return -ENOENT;
-	}
-	RCU_INIT_POINTER(net->flow_dissector_prog, NULL);
-	bpf_prog_put(attached);
-	mutex_unlock(&flow_dissector_mutex);
 	return 0;
 }
-
-int skb_flow_dissector_bpf_prog_detach(const union bpf_attr *attr)
-{
-	return flow_dissector_bpf_prog_detach(current->nsproxy->net_ns);
-}
-
-static void __net_exit flow_dissector_pernet_pre_exit(struct net *net)
-{
-	/* We're not racing with attach/detach because there are no
-	 * references to netns left when pre_exit gets called.
-	 */
-	if (rcu_access_pointer(net->flow_dissector_prog))
-		flow_dissector_bpf_prog_detach(net);
-}
-
-static struct pernet_operations flow_dissector_pernet_ops __net_initdata = {
-	.pre_exit = flow_dissector_pernet_pre_exit,
-};
+#endif /* CONFIG_BPF_SYSCALL */
 
 /**
  * __skb_flow_get_ports - extract the upper layer ports and return them
@@ -1044,11 +959,13 @@ bool __skb_flow_dissect(const struct net *net,
 
 	WARN_ON_ONCE(!net);
 	if (net) {
+		enum netns_bpf_attach_type type = NETNS_BPF_FLOW_DISSECTOR;
+
 		rcu_read_lock();
-		attached = rcu_dereference(init_net.flow_dissector_prog);
+		attached = rcu_dereference(init_net.bpf.progs[type]);
 
 		if (!attached)
-			attached = rcu_dereference(net->flow_dissector_prog);
+			attached = rcu_dereference(net->bpf.progs[type]);
 
 		if (attached) {
 			struct bpf_flow_keys flow_keys;
@@ -1869,7 +1786,6 @@ static int __init init_default_flow_dissectors(void)
 	skb_flow_dissector_init(&flow_keys_basic_dissector,
 				flow_keys_basic_dissector_keys,
 				ARRAY_SIZE(flow_keys_basic_dissector_keys));
-
-	return register_pernet_subsys(&flow_dissector_pernet_ops);
+	return 0;
 }
 core_initcall(init_default_flow_dissectors);
diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index c479372f2cd2..351afbf6bfba 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -7,6 +7,7 @@
 
 #include <net/sock.h>
 #include <net/tcp.h>
+#include <net/tls.h>
 
 static bool sk_msg_try_coalesce_ok(struct sk_msg *msg, int elem_first_coalesce)
 {
@@ -682,13 +683,75 @@ static struct sk_psock *sk_psock_from_strp(struct strparser *strp)
 	return container_of(parser, struct sk_psock, parser);
 }
 
-static void sk_psock_verdict_apply(struct sk_psock *psock,
-				   struct sk_buff *skb, int verdict)
+static void sk_psock_skb_redirect(struct sk_psock *psock, struct sk_buff *skb)
 {
 	struct sk_psock *psock_other;
 	struct sock *sk_other;
 	bool ingress;
 
+	sk_other = tcp_skb_bpf_redirect_fetch(skb);
+	if (unlikely(!sk_other)) {
+		kfree_skb(skb);
+		return;
+	}
+	psock_other = sk_psock(sk_other);
+	if (!psock_other || sock_flag(sk_other, SOCK_DEAD) ||
+	    !sk_psock_test_state(psock_other, SK_PSOCK_TX_ENABLED)) {
+		kfree_skb(skb);
+		return;
+	}
+
+	ingress = tcp_skb_bpf_ingress(skb);
+	if ((!ingress && sock_writeable(sk_other)) ||
+	    (ingress &&
+	     atomic_read(&sk_other->sk_rmem_alloc) <=
+	     sk_other->sk_rcvbuf)) {
+		if (!ingress)
+			skb_set_owner_w(skb, sk_other);
+		skb_queue_tail(&psock_other->ingress_skb, skb);
+		schedule_work(&psock_other->work);
+	} else {
+		kfree_skb(skb);
+	}
+}
+
+static void sk_psock_tls_verdict_apply(struct sk_psock *psock,
+				       struct sk_buff *skb, int verdict)
+{
+	switch (verdict) {
+	case __SK_REDIRECT:
+		sk_psock_skb_redirect(psock, skb);
+		break;
+	case __SK_PASS:
+	case __SK_DROP:
+	default:
+		break;
+	}
+}
+
+int sk_psock_tls_strp_read(struct sk_psock *psock, struct sk_buff *skb)
+{
+	struct bpf_prog *prog;
+	int ret = __SK_PASS;
+
+	rcu_read_lock();
+	prog = READ_ONCE(psock->progs.skb_verdict);
+	if (likely(prog)) {
+		tcp_skb_bpf_redirect_clear(skb);
+		ret = sk_psock_bpf_run(psock, prog, skb);
+		ret = sk_psock_map_verd(ret, tcp_skb_bpf_redirect_fetch(skb));
+	}
+	rcu_read_unlock();
+	sk_psock_tls_verdict_apply(psock, skb, ret);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(sk_psock_tls_strp_read);
+
+static void sk_psock_verdict_apply(struct sk_psock *psock,
+				   struct sk_buff *skb, int verdict)
+{
+	struct sock *sk_other;
+
 	switch (verdict) {
 	case __SK_PASS:
 		sk_other = psock->sk;
@@ -707,25 +770,8 @@ static void sk_psock_verdict_apply(struct sk_psock *psock,
 		}
 		goto out_free;
 	case __SK_REDIRECT:
-		sk_other = tcp_skb_bpf_redirect_fetch(skb);
-		if (unlikely(!sk_other))
-			goto out_free;
-		psock_other = sk_psock(sk_other);
-		if (!psock_other || sock_flag(sk_other, SOCK_DEAD) ||
-		    !sk_psock_test_state(psock_other, SK_PSOCK_TX_ENABLED))
-			goto out_free;
-		ingress = tcp_skb_bpf_ingress(skb);
-		if ((!ingress && sock_writeable(sk_other)) ||
-		    (ingress &&
-		     atomic_read(&sk_other->sk_rmem_alloc) <=
-		     sk_other->sk_rcvbuf)) {
-			if (!ingress)
-				skb_set_owner_w(skb, sk_other);
-			skb_queue_tail(&psock_other->ingress_skb, skb);
-			schedule_work(&psock_other->work);
-			break;
-		}
-		/* fall-through */
+		sk_psock_skb_redirect(psock, skb);
+		break;
 	case __SK_DROP:
 		/* fall-through */
 	default:
@@ -779,9 +825,13 @@ static void sk_psock_strp_data_ready(struct sock *sk)
 	rcu_read_lock();
 	psock = sk_psock(sk);
 	if (likely(psock)) {
-		write_lock_bh(&sk->sk_callback_lock);
-		strp_data_ready(&psock->parser.strp);
-		write_unlock_bh(&sk->sk_callback_lock);
+		if (tls_sw_has_ctx_rx(sk)) {
+			psock->parser.saved_data_ready(sk);
+		} else {
+			write_lock_bh(&sk->sk_callback_lock);
+			strp_data_ready(&psock->parser.strp);
+			write_unlock_bh(&sk->sk_callback_lock);
+		}
 	}
 	rcu_read_unlock();
 }
diff --git a/net/core/sock.c b/net/core/sock.c
index 61ec573221a6..6c4acf1f0220 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -594,13 +594,15 @@ out:
 	return ret;
 }
 
-int sock_bindtoindex(struct sock *sk, int ifindex)
+int sock_bindtoindex(struct sock *sk, int ifindex, bool lock_sk)
 {
 	int ret;
 
-	lock_sock(sk);
+	if (lock_sk)
+		lock_sock(sk);
 	ret = sock_bindtoindex_locked(sk, ifindex);
-	release_sock(sk);
+	if (lock_sk)
+		release_sock(sk);
 
 	return ret;
 }
@@ -646,7 +648,7 @@ static int sock_setbindtodevice(struct sock *sk, char __user *optval,
 			goto out;
 	}
 
-	return sock_bindtoindex(sk, index);
+	return sock_bindtoindex(sk, index, true);
 out:
 #endif