[PATCH bpf 0/4] Expose network namespace cookies to user space

[PATCH bpf 0/4] Expose network namespace cookies to user space

[Lorenz Bauer]

We're working on a user space control plane for the BPF sk_lookup
hook [1]. The hook attaches to a network namespace and allows
control over which socket receives a new connection / packet.

Roughly, applications can give a socket to our user space component
to participate in custom bind semantics. This creates an edge case
where  an application can provide us with a socket that lives in
a different network namespace than our BPF sk_lookup program.
We'd like to return an error in this case.

Additionally, we have some user space state that is tied to the
network namespace. We currently use the inode of the nsfs entry
in a directory name, but this is suffers from inode reuse.

I'm proposing to fix both of these issues by adding a new
SO_NETNS_COOKIE socket option as well as a NS_GET_COOKIE ioctl.
Using these we get a stable, unique identifier for a network
namespace and check whether a socket belongs to the "correct"
namespace.

NS_GET_COOKIE could be renamed to NS_GET_NET_COOKIE. I kept the
name generic because it seems like other namespace types could
benefit from a cookie as well.

I'm trying to land this via the bpf tree since this is where the
netns cookie originated, please let me know if this isn't
appropriate.

1: https://www.kernel.org/doc/html/latest/bpf/prog_sk_lookup.html

Cc: bpf@vger.kernel.org
Cc: linux-alpha@vger.kernel.org
Cc: linux-api@vger.kernel.org
Cc: linux-arch@vger.kernel.org
Cc: linux-fsdevel@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Cc: linux-kselftest@vger.kernel.org
Cc: linux-mips@vger.kernel.org
Cc: linux-parisc@vger.kernel.org
Cc: netdev@vger.kernel.org
Cc: sparclinux@vger.kernel.org

Lorenz Bauer (4):
  net: add SO_NETNS_COOKIE socket option
  nsfs: add an ioctl to discover the network namespace cookie
  tools/testing: add test for NS_GET_COOKIE
  tools/testing: add a selftest for SO_NETNS_COOKIE

 arch/alpha/include/uapi/asm/socket.h          |  2 +
 arch/mips/include/uapi/asm/socket.h           |  2 +
 arch/parisc/include/uapi/asm/socket.h         |  2 +
 arch/sparc/include/uapi/asm/socket.h          |  2 +
 fs/nsfs.c                                     |  9 +++
 include/linux/sock_diag.h                     | 20 ++++++
 include/net/net_namespace.h                   | 11 ++++
 include/uapi/asm-generic/socket.h             |  2 +
 include/uapi/linux/nsfs.h                     |  2 +
 net/core/filter.c                             |  9 ++-
 net/core/sock.c                               |  7 +++
 tools/testing/selftests/net/.gitignore        |  1 +
 tools/testing/selftests/net/Makefile          |  2 +-
 tools/testing/selftests/net/so_netns_cookie.c | 61 +++++++++++++++++++
 tools/testing/selftests/nsfs/.gitignore       |  1 +
 tools/testing/selftests/nsfs/Makefile         |  2 +-
 tools/testing/selftests/nsfs/netns.c          | 57 +++++++++++++++++
 17 files changed, 185 insertions(+), 7 deletions(-)
 create mode 100644 tools/testing/selftests/net/so_netns_cookie.c
 create mode 100644 tools/testing/selftests/nsfs/netns.c

-- 
2.27.0

[PATCH bpf 3/4] tools/testing: add test for NS_GET_COOKIE

[Lorenz Bauer]

Check that NS_GET_COOKIE returns a non-zero value, and that distinct
network namespaces have different cookies.

Signed-off-by: Lorenz Bauer <lmb@cloudflare.com>
---
 tools/testing/selftests/nsfs/.gitignore |  1 +
 tools/testing/selftests/nsfs/Makefile   |  2 +-
 tools/testing/selftests/nsfs/netns.c    | 57 +++++++++++++++++++++++++
 3 files changed, 59 insertions(+), 1 deletion(-)
 create mode 100644 tools/testing/selftests/nsfs/netns.c

diff --git a/tools/testing/selftests/nsfs/.gitignore b/tools/testing/selftests/nsfs/.gitignore
index ed79ebdf286e..ca31b216215b 100644
--- a/tools/testing/selftests/nsfs/.gitignore
+++ b/tools/testing/selftests/nsfs/.gitignore
@@ -1,3 +1,4 @@
 # SPDX-License-Identifier: GPL-2.0-only
 owner
 pidns
+netns
diff --git a/tools/testing/selftests/nsfs/Makefile b/tools/testing/selftests/nsfs/Makefile
index dd9bd50b7b93..93793cdb5a7c 100644
--- a/tools/testing/selftests/nsfs/Makefile
+++ b/tools/testing/selftests/nsfs/Makefile
@@ -1,5 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0-only
-TEST_GEN_PROGS := owner pidns
+TEST_GEN_PROGS := owner pidns netns
 
 CFLAGS := -Wall -Werror
 
diff --git a/tools/testing/selftests/nsfs/netns.c b/tools/testing/selftests/nsfs/netns.c
new file mode 100644
index 000000000000..8ab862667b45
--- /dev/null
+++ b/tools/testing/selftests/nsfs/netns.c
@@ -0,0 +1,57 @@
+// SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE
+#include <sched.h>
+#include <unistd.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <stdint.h>
+#include <fcntl.h>
+#include <sys/ioctl.h>
+
+#define NSIO    0xb7
+#define NS_GET_COOKIE   _IO(NSIO, 0x5)
+
+#define pr_err(fmt, ...) \
+		({ \
+			fprintf(stderr, "%s:%d:" fmt ": %m\n", \
+				__func__, __LINE__, ##__VA_ARGS__); \
+			1; \
+		})
+
+int main(int argc, char *argvp[])
+{
+	uint64_t cookie1, cookie2;
+	char path[128];
+	int ns;
+
+	snprintf(path, sizeof(path), "/proc/%d/ns/net", getpid());
+	ns = open(path, O_RDONLY);
+	if (ns < 0)
+		return pr_err("Unable to open %s", path);
+
+	if (ioctl(ns, NS_GET_COOKIE, &cookie1))
+		return pr_err("Unable to get first namespace cookie");
+
+	if (!cookie1)
+		return pr_err("NS_GET_COOKIE returned zero first cookie");
+
+	close(ns);
+	if (unshare(CLONE_NEWNET))
+		return pr_err("unshare");
+
+	ns = open(path, O_RDONLY);
+	if (ns < 0)
+		return pr_err("Unable to open %s", path);
+
+	if (ioctl(ns, NS_GET_COOKIE, &cookie2))
+		return pr_err("Unable to get second namespace cookie");
+
+	if (!cookie2)
+		return pr_err("NS_GET_COOKIE returned zero second cookie");
+
+	if (cookie1 == cookie2)
+		return pr_err("NS_GET_COOKIE returned identical cookies for distinct ns");
+
+	close(ns);
+	return 0;
+}
-- 
2.27.0

[PATCH bpf 4/4] tools/testing: add a selftest for SO_NETNS_COOKIE

[Lorenz Bauer]

Make sure that SO_NETNS_COOKIE returns a non-zero value, and
that sockets from different namespaces have a distinct cookie
value.

Signed-off-by: Lorenz Bauer <lmb@cloudflare.com>
---
 tools/testing/selftests/net/.gitignore        |  1 +
 tools/testing/selftests/net/Makefile          |  2 +-
 tools/testing/selftests/net/so_netns_cookie.c | 61 +++++++++++++++++++
 3 files changed, 63 insertions(+), 1 deletion(-)
 create mode 100644 tools/testing/selftests/net/so_netns_cookie.c

diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore
index 61ae899cfc17..19deb9cdf72f 100644
--- a/tools/testing/selftests/net/.gitignore
+++ b/tools/testing/selftests/net/.gitignore
@@ -30,3 +30,4 @@ hwtstamp_config
 rxtimestamp
 timestamping
 txtimestamp
+so_netns_cookie
diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index fa5fa425d148..a0f45a71a8f1 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -27,7 +27,7 @@ TEST_GEN_FILES =  socket nettest
 TEST_GEN_FILES += psock_fanout psock_tpacket msg_zerocopy reuseport_addr_any
 TEST_GEN_FILES += tcp_mmap tcp_inq psock_snd txring_overwrite
 TEST_GEN_FILES += udpgso udpgso_bench_tx udpgso_bench_rx ip_defrag
-TEST_GEN_FILES += so_txtime ipv6_flowlabel ipv6_flowlabel_mgr
+TEST_GEN_FILES += so_txtime ipv6_flowlabel ipv6_flowlabel_mgr so_netns_cookie
 TEST_GEN_FILES += tcp_fastopen_backup_key
 TEST_GEN_FILES += fin_ack_lat
 TEST_GEN_FILES += reuseaddr_ports_exhausted
diff --git a/tools/testing/selftests/net/so_netns_cookie.c b/tools/testing/selftests/net/so_netns_cookie.c
new file mode 100644
index 000000000000..b39e87e967cd
--- /dev/null
+++ b/tools/testing/selftests/net/so_netns_cookie.c
@@ -0,0 +1,61 @@
+// SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE
+#include <sched.h>
+#include <unistd.h>
+#include <stdio.h>
+#include <errno.h>
+#include <string.h>
+#include <stdlib.h>
+#include <stdint.h>
+#include <sys/types.h>
+#include <sys/socket.h>
+
+#ifndef SO_NETNS_COOKIE
+#define SO_NETNS_COOKIE 71
+#endif
+
+#define pr_err(fmt, ...) \
+	({ \
+		fprintf(stderr, "%s:%d:" fmt ": %m\n", \
+			__func__, __LINE__, ##__VA_ARGS__); \
+		1; \
+	})
+
+int main(int argc, char *argvp[])
+{
+	uint64_t cookie1, cookie2;
+	socklen_t vallen;
+	int sock1, sock2;
+
+	sock1 = socket(AF_INET, SOCK_STREAM, 0);
+	if (sock1 < 0)
+		return pr_err("Unable to create TCP socket");
+
+	vallen = sizeof(cookie1);
+	if (getsockopt(sock1, SOL_SOCKET, SO_NETNS_COOKIE, &cookie1, &vallen) != 0)
+		return pr_err("getsockopt(SOL_SOCKET, SO_NETNS_COOKIE)");
+
+	if (!cookie1)
+		return pr_err("SO_NETNS_COOKIE returned zero cookie");
+
+	if (unshare(CLONE_NEWNET))
+		return pr_err("unshare");
+
+	sock2 = socket(AF_INET, SOCK_STREAM, 0);
+	if (sock2 < 0)
+		return pr_err("Unable to create TCP socket");
+
+	vallen = sizeof(cookie2);
+	if (getsockopt(sock2, SOL_SOCKET, SO_NETNS_COOKIE, &cookie2, &vallen) != 0)
+		return pr_err("getsockopt(SOL_SOCKET, SO_NETNS_COOKIE)");
+
+	if (!cookie2)
+		return pr_err("SO_NETNS_COOKIE returned zero cookie");
+
+	if (cookie1 == cookie2)
+		return pr_err("SO_NETNS_COOKIE returned identical cookies for distinct ns");
+
+	close(sock1);
+	close(sock2);
+	return 0;
+}
-- 
2.27.0