Merge branch 'bpf-support-for-sockets'

David Ahern says:

====================
net: Add bpf support for sockets

The recently added VRF support in Linux leverages the bind-to-device
API for programs to specify an L3 domain for a socket. While
SO_BINDTODEVICE has been around for ages, not every ipv4/ipv6 capable
program has support for it. Even for those programs that do support it,
the API requires processes to be started as root (CAP_NET_RAW) which
is not desirable from a general security perspective.

This patch set leverages Daniel Mack's work to attach bpf programs to
a cgroup to provide a capability to set sk_bound_dev_if for all
AF_INET{6} sockets opened by a process in a cgroup when the sockets
are allocated.

For example:
 1. configure vrf (e.g., using ifupdown2)
        auto eth0
        iface eth0 inet dhcp
            vrf mgmt

        auto mgmt
        iface mgmt
            vrf-table auto

 2. configure cgroup
        mount -t cgroup2 none /tmp/cgroupv2
        mkdir /tmp/cgroupv2/mgmt
        test_cgrp2_sock /tmp/cgroupv2/mgmt 15

 3. set shell into cgroup (e.g., can be done at login using pam)
        echo $$ >> /tmp/cgroupv2/mgmt/cgroup.procs

At this point all commands run in the shell (e.g, apt) have sockets
automatically bound to the VRF (see output of ss -ap 'dev == <vrf>'),
including processes not running as root.

This capability enables running any program in a VRF context and is key
to deploying Management VRF, a fundamental configuration for networking
gear, with any Linux OS installation.

This patchset also exports the socket family, type and protocol as
read-only allowing bpf filters to deny a process in a cgroup the ability
to open specific types of AF_INET or AF_INET6 sockets.

v7
- comments from Alexei

v6
- add export of socket family, type and protocol
====================

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

2 files changed, 57 insertions, 19 deletions

diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index 8c784f8c67cd..a515f7b007c6 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -118,7 +118,7 @@ void __cgroup_bpf_update(struct cgroup *cgrp,
 }
 
 /**
- * __cgroup_bpf_run_filter() - Run a program for packet filtering
+ * __cgroup_bpf_run_filter_skb() - Run a program for packet filtering
  * @sk: The socken sending or receiving traffic
  * @skb: The skb that is being sent or received
  * @type: The type of program to be exectuted
@@ -132,9 +132,9 @@ void __cgroup_bpf_update(struct cgroup *cgrp,
  * This function will return %-EPERM if any if an attached program was found
  * and if it returned != 1 during execution. In all other cases, 0 is returned.
  */
-int __cgroup_bpf_run_filter(struct sock *sk,
-			    struct sk_buff *skb,
-			    enum bpf_attach_type type)
+int __cgroup_bpf_run_filter_skb(struct sock *sk,
+				struct sk_buff *skb,
+				enum bpf_attach_type type)
 {
 	struct bpf_prog *prog;
 	struct cgroup *cgrp;
@@ -164,4 +164,37 @@ int __cgroup_bpf_run_filter(struct sock *sk,
 
 	return ret;
 }
-EXPORT_SYMBOL(__cgroup_bpf_run_filter);
+EXPORT_SYMBOL(__cgroup_bpf_run_filter_skb);
+
+/**
+ * __cgroup_bpf_run_filter_sk() - Run a program on a sock
+ * @sk: sock structure to manipulate
+ * @type: The type of program to be exectuted
+ *
+ * socket is passed is expected to be of type INET or INET6.
+ *
+ * The program type passed in via @type must be suitable for sock
+ * filtering. No further check is performed to assert that.
+ *
+ * This function will return %-EPERM if any if an attached program was found
+ * and if it returned != 1 during execution. In all other cases, 0 is returned.
+ */
+int __cgroup_bpf_run_filter_sk(struct sock *sk,
+			       enum bpf_attach_type type)
+{
+	struct cgroup *cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data);
+	struct bpf_prog *prog;
+	int ret = 0;
+
+
+	rcu_read_lock();
+
+	prog = rcu_dereference(cgrp->bpf.effective[type]);
+	if (prog)
+		ret = BPF_PROG_RUN(prog, sk) == 1 ? 0 : -EPERM;
+
+	rcu_read_unlock();
+
+	return ret;
+}
+EXPORT_SYMBOL(__cgroup_bpf_run_filter_sk);
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 4caa18e6860a..85af86c496cd 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -856,6 +856,7 @@ static int bpf_prog_attach(const union bpf_attr *attr)
 {
 	struct bpf_prog *prog;
 	struct cgroup *cgrp;
+	enum bpf_prog_type ptype;
 
 	if (!capable(CAP_NET_ADMIN))
 		return -EPERM;
@@ -866,25 +867,28 @@ static int bpf_prog_attach(const union bpf_attr *attr)
 	switch (attr->attach_type) {
 	case BPF_CGROUP_INET_INGRESS:
 	case BPF_CGROUP_INET_EGRESS:
-		prog = bpf_prog_get_type(attr->attach_bpf_fd,
-					 BPF_PROG_TYPE_CGROUP_SKB);
-		if (IS_ERR(prog))
-			return PTR_ERR(prog);
-
-		cgrp = cgroup_get_from_fd(attr->target_fd);
-		if (IS_ERR(cgrp)) {
-			bpf_prog_put(prog);
-			return PTR_ERR(cgrp);
-		}
-
-		cgroup_bpf_update(cgrp, prog, attr->attach_type);
-		cgroup_put(cgrp);
+		ptype = BPF_PROG_TYPE_CGROUP_SKB;
+		break;
+	case BPF_CGROUP_INET_SOCK_CREATE:
+		ptype = BPF_PROG_TYPE_CGROUP_SOCK;
 		break;
-
 	default:
 		return -EINVAL;
 	}
 
+	prog = bpf_prog_get_type(attr->attach_bpf_fd, ptype);
+	if (IS_ERR(prog))
+		return PTR_ERR(prog);
+
+	cgrp = cgroup_get_from_fd(attr->target_fd);
+	if (IS_ERR(cgrp)) {
+		bpf_prog_put(prog);
+		return PTR_ERR(cgrp);
+	}
+
+	cgroup_bpf_update(cgrp, prog, attr->attach_type);
+	cgroup_put(cgrp);
+
 	return 0;
 }
 
@@ -903,6 +907,7 @@ static int bpf_prog_detach(const union bpf_attr *attr)
 	switch (attr->attach_type) {
 	case BPF_CGROUP_INET_INGRESS:
 	case BPF_CGROUP_INET_EGRESS:
+	case BPF_CGROUP_INET_SOCK_CREATE:
 		cgrp = cgroup_get_from_fd(attr->target_fd);
 		if (IS_ERR(cgrp))
 			return PTR_ERR(cgrp);