bpf: Add link-based BPF program attachment to network namespace

Extend bpf() syscall subcommands that operate on bpf_link, that is
LINK_CREATE, LINK_UPDATE, OBJ_GET_INFO, to accept attach types tied to
network namespaces (only flow dissector at the moment).

Link-based and prog-based attachment can be used interchangeably, but only
one can exist at a time. Attempts to attach a link when a prog is already
attached directly, and the other way around, will be met with -EEXIST.
Attempts to detach a program when link exists result in -EINVAL.

Attachment of multiple links of same attach type to one netns is not
supported with the intention to lift the restriction when a use-case
presents itself. Because of that link create returns -E2BIG when trying to
create another netns link, when one already exists.

Link-based attachments to netns don't keep a netns alive by holding a ref
to it. Instead links get auto-detached from netns when the latter is being
destroyed, using a pernet pre_exit callback.

When auto-detached, link lives in defunct state as long there are open FDs
for it. -ENOLINK is returned if a user tries to update a defunct link.

Because bpf_link to netns doesn't hold a ref to struct net, special care is
taken when releasing, updating, or filling link info. The netns might be
getting torn down when any of these link operations are in progress. That
is why auto-detach and update/release/fill_info are synchronized by the
same mutex. Also, link ops have to always check if auto-detach has not
happened yet and if netns is still alive (refcnt > 0).

Signed-off-by: Jakub Sitnicki <jakub@cloudflare.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20200531082846.2117903-5-jakub@cloudflare.com

4 files changed, 17 insertions, 0 deletions

diff --git a/include/linux/bpf-netns.h b/include/linux/bpf-netns.h
index f3aec3d79824..4052d649f36d 100644
--- a/include/linux/bpf-netns.h
+++ b/include/linux/bpf-netns.h
@@ -34,6 +34,8 @@ int netns_bpf_prog_query(const union bpf_attr *attr,
 int netns_bpf_prog_attach(const union bpf_attr *attr,
 			  struct bpf_prog *prog);
 int netns_bpf_prog_detach(const union bpf_attr *attr);
+int netns_bpf_link_create(const union bpf_attr *attr,
+			  struct bpf_prog *prog);
 #else
 static inline int netns_bpf_prog_query(const union bpf_attr *attr,
 				       union bpf_attr __user *uattr)
@@ -51,6 +53,12 @@ static inline int netns_bpf_prog_detach(const union bpf_attr *attr)
 {
 	return -EOPNOTSUPP;
 }
+
+static inline int netns_bpf_link_create(const union bpf_attr *attr,
+					struct bpf_prog *prog)
+{
+	return -EOPNOTSUPP;
+}
 #endif
 
 #endif /* _BPF_NETNS_H */
diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h
index fa8e1b552acd..a18ae82a298a 100644
--- a/include/linux/bpf_types.h
+++ b/include/linux/bpf_types.h
@@ -126,3 +126,6 @@ BPF_LINK_TYPE(BPF_LINK_TYPE_TRACING, tracing)
 BPF_LINK_TYPE(BPF_LINK_TYPE_CGROUP, cgroup)
 #endif
 BPF_LINK_TYPE(BPF_LINK_TYPE_ITER, iter)
+#ifdef CONFIG_NET
+BPF_LINK_TYPE(BPF_LINK_TYPE_NETNS, netns)
+#endif
diff --git a/include/net/netns/bpf.h b/include/net/netns/bpf.h
index a858d1c5b166..a8dce2a380c8 100644
--- a/include/net/netns/bpf.h
+++ b/include/net/netns/bpf.h
@@ -12,6 +12,7 @@ struct bpf_prog;
 
 struct netns_bpf {
 	struct bpf_prog __rcu *progs[MAX_NETNS_BPF_ATTACH_TYPE];
+	struct bpf_link *links[MAX_NETNS_BPF_ATTACH_TYPE];
 };
 
 #endif /* __NETNS_BPF_H__ */
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index f862a58fb567..b9ed9f14f2a2 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -237,6 +237,7 @@ enum bpf_link_type {
 	BPF_LINK_TYPE_TRACING = 2,
 	BPF_LINK_TYPE_CGROUP = 3,
 	BPF_LINK_TYPE_ITER = 4,
+	BPF_LINK_TYPE_NETNS = 5,
 
 	MAX_BPF_LINK_TYPE,
 };
@@ -3839,6 +3840,10 @@ struct bpf_link_info {
 			__u64 cgroup_id;
 			__u32 attach_type;
 		} cgroup;
+		struct  {
+			__u32 netns_ino;
+			__u32 attach_type;
+		} netns;
 	};
 } __attribute__((aligned(8)));