Merge branch 'selftests/bpf: Add sockaddr tests for kernel networking'

Jordan Rife says:

====================
This patch series adds test coverage for BPF sockaddr hooks and their
interactions with kernel socket functions (i.e. kernel_bind(),
kernel_connect(), kernel_sendmsg(), sock_sendmsg(),
kernel_getpeername(), and kernel_getsockname()) while also rounding out
IPv4 and IPv6 sockaddr hook coverage in prog_tests/sock_addr.c.

As with v1 of this patch series, we add regression coverage for the
issues addressed by these patches,

- commit 0bdf399("net: Avoid address overwrite in kernel_connect")
- commit 86a7e0b("net: prevent rewrite of msg_name in sock_sendmsg()")
- commit c889a99("net: prevent address rewrite in kernel_bind()")
- commit 01b2885("net: Save and restore msg_namelen in sock_sendmsg")

but broaden the focus a bit.

In order to extend prog_tests/sock_addr.c to test these kernel
functions, we add a set of new kfuncs that wrap individual socket
operations to bpf_testmod and invoke them through set of corresponding
SYSCALL programs (progs/sock_addr_kern.c). Each test case can be
configured to use a different set of "sock_ops" depending on whether it
is testing kernel calls (kernel_bind(), kernel_connect(), etc.) or
system calls (bind(), connect(), etc.).

=======
Patches
=======
* Patch 1 fixes the sock_addr bind test program to work for big endian
  architectures such as s390x.
* Patch 2 introduces the new kfuncs to bpf_testmod.
* Patch 3 introduces the BPF program which allows us to invoke these
  kfuncs invividually from the test program.
* Patch 4 lays the groundwork for IPv4 and IPv6 sockaddr hook coverage
  by migrating much of the environment setup logic from
  bpf/test_sock_addr.sh into prog_tests/sock_addr.c and moves test cases
  to cover bind4/6, connect4/6, sendmsg4/6 and recvmsg4/6 hooks.
* Patch 5 makes the set of socket operations for each test case
  configurable, laying the groundwork for Patch 6.
* Patch 6 introduces two sets of sock_ops that invoke the kernel
  equivalents of connect(), bind(), etc. and uses these to add coverage
  for the kernel socket functions.

=======
Changes
=======
v2->v3
------
* Renamed bind helpers. Dropped "_ntoh" suffix.
* Added guards to kfuncs to make sure addrlen and msglen do not exceed
  the buffer capacity.
* Added KF_SLEEPABLE flag to kfuncs.
* Added a mutex (sock_lock) to kfuncs to serialize access to sock.
* Added NULL check for sock to each kfunc.
* Use the "sock_addr" networking namespace for all network interface
  setup and testing.
* Use "nodad" when calling "ip -6 addr add" during interface setup to
  avoid delays and remove ping loop.
* Removed test cases from test_sock_addr.c to make it clear what remains
  to be migrated.
* Removed unused parameter (expect_change) from sock_addr_op().

Link: https://lore.kernel.org/bpf/20240412165230.2009746-1-jrife@google.com/T/#u

v1->v2
------
* Dropped test_progs/sock_addr_kern.c and the sock_addr_kern test module
  in favor of simply expanding bpf_testmod and test_progs/sock_addr.c.
* Migrated environment setup logic from bpf/test_sock_addr.sh into
  prog_tests/sock_addr.c rather than invoking the script from the test
  program.
* Added kfuncs to bpf_testmod as well as the sock_addr_kern BPF program
  to enable us to invoke kernel socket functions from
  test_progs/sock_addr.c.
* Added test coverage for kernel socket functions to
  test_progs/sock_addr.c.

Link: https://lore.kernel.org/bpf/20240329191907.1808635-1-jrife@google.com/T/#u
====================

Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>

Author: Martin KaFai Lau

tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c

@@ -10,18 +10,30 @@
 #include <linux/percpu-defs.h>
 #include <linux/sysfs.h>
 #include <linux/tracepoint.h>
+#include <linux/net.h>
+#include <linux/socket.h>
+#include <linux/nsproxy.h>
+#include <linux/inet.h>
+#include <linux/in.h>
+#include <linux/in6.h>
+#include <linux/un.h>
+#include <net/sock.h>
 #include "bpf_testmod.h"
 #include "bpf_testmod_kfunc.h"
 
 #define CREATE_TRACE_POINTS
 #include "bpf_testmod-events.h"
 
+#define CONNECT_TIMEOUT_SEC 1
+
 typedef int (*func_proto_typedef)(long);
 typedef int (*func_proto_typedef_nested1)(func_proto_typedef);
 typedef int (*func_proto_typedef_nested2)(func_proto_typedef_nested1);
 
 DEFINE_PER_CPU(int, bpf_testmod_ksym_percpu) = 123;
 long bpf_testmod_test_struct_arg_result;
+static DEFINE_MUTEX(sock_lock);
+static struct socket *sock;
 
 struct bpf_testmod_struct_arg_1 {
 	int a;
@@ -498,6 +510,237 @@ __bpf_kfunc void bpf_kfunc_call_test_sleepable(void)
 {
 }
 
+__bpf_kfunc int bpf_kfunc_init_sock(struct init_sock_args *args)
+{
+	int proto;
+	int err;
+
+	mutex_lock(&sock_lock);
+
+	if (sock) {
+		pr_err("%s called without releasing old sock", __func__);
+		err = -EPERM;
+		goto out;
+	}
+
+	switch (args->af) {
+	case AF_INET:
+	case AF_INET6:
+		proto = args->type == SOCK_STREAM ? IPPROTO_TCP : IPPROTO_UDP;
+		break;
+	case AF_UNIX:
+		proto = PF_UNIX;
+		break;
+	default:
+		pr_err("invalid address family %d\n", args->af);
+		err = -EINVAL;
+		goto out;
+	}
+
+	err = sock_create_kern(current->nsproxy->net_ns, args->af, args->type,
+			       proto, &sock);
+
+	if (!err)
+		/* Set timeout for call to kernel_connect() to prevent it from hanging,
+		 * and consider the connection attempt failed if it returns
+		 * -EINPROGRESS.
+		 */
+		sock->sk->sk_sndtimeo = CONNECT_TIMEOUT_SEC * HZ;
+out:
+	mutex_unlock(&sock_lock);
+
+	return err;
+}
+
+__bpf_kfunc void bpf_kfunc_close_sock(void)
+{
+	mutex_lock(&sock_lock);
+
+	if (sock) {
+		sock_release(sock);
+		sock = NULL;
+	}
+
+	mutex_unlock(&sock_lock);
+}
+
+__bpf_kfunc int bpf_kfunc_call_kernel_connect(struct addr_args *args)
+{
+	int err;
+
+	if (args->addrlen > sizeof(args->addr))
+		return -EINVAL;
+
+	mutex_lock(&sock_lock);
+
+	if (!sock) {
+		pr_err("%s called without initializing sock", __func__);
+		err = -EPERM;
+		goto out;
+	}
+
+	err = kernel_connect(sock, (struct sockaddr *)&args->addr,
+			     args->addrlen, 0);
+out:
+	mutex_unlock(&sock_lock);
+
+	return err;
+}
+
+__bpf_kfunc int bpf_kfunc_call_kernel_bind(struct addr_args *args)
+{
+	int err;
+
+	if (args->addrlen > sizeof(args->addr))
+		return -EINVAL;
+
+	mutex_lock(&sock_lock);
+
+	if (!sock) {
+		pr_err("%s called without initializing sock", __func__);
+		err = -EPERM;
+		goto out;
+	}
+
+	err = kernel_bind(sock, (struct sockaddr *)&args->addr, args->addrlen);
+out:
+	mutex_unlock(&sock_lock);
+
+	return err;
+}
+
+__bpf_kfunc int bpf_kfunc_call_kernel_listen(void)
+{
+	int err;
+
+	mutex_lock(&sock_lock);
+
+	if (!sock) {
+		pr_err("%s called without initializing sock", __func__);
+		err = -EPERM;
+		goto out;
+	}
+
+	err = kernel_listen(sock, 128);
+out:
+	mutex_unlock(&sock_lock);
+
+	return err;
+}
+
+__bpf_kfunc int bpf_kfunc_call_kernel_sendmsg(struct sendmsg_args *args)
+{
+	struct msghdr msg = {
+		.msg_name	= &args->addr.addr,
+		.msg_namelen	= args->addr.addrlen,
+	};
+	struct kvec iov;
+	int err;
+
+	if (args->addr.addrlen > sizeof(args->addr.addr) ||
+	    args->msglen > sizeof(args->msg))
+		return -EINVAL;
+
+	iov.iov_base = args->msg;
+	iov.iov_len  = args->msglen;
+
+	mutex_lock(&sock_lock);
+
+	if (!sock) {
+		pr_err("%s called without initializing sock", __func__);
+		err = -EPERM;
+		goto out;
+	}
+
+	err = kernel_sendmsg(sock, &msg, &iov, 1, args->msglen);
+	args->addr.addrlen = msg.msg_namelen;
+out:
+	mutex_unlock(&sock_lock);
+
+	return err;
+}
+
+__bpf_kfunc int bpf_kfunc_call_sock_sendmsg(struct sendmsg_args *args)
+{
+	struct msghdr msg = {
+		.msg_name	= &args->addr.addr,
+		.msg_namelen	= args->addr.addrlen,
+	};
+	struct kvec iov;
+	int err;
+
+	if (args->addr.addrlen > sizeof(args->addr.addr) ||
+	    args->msglen > sizeof(args->msg))
+		return -EINVAL;
+
+	iov.iov_base = args->msg;
+	iov.iov_len  = args->msglen;
+
+	iov_iter_kvec(&msg.msg_iter, ITER_SOURCE, &iov, 1, args->msglen);
+	mutex_lock(&sock_lock);
+
+	if (!sock) {
+		pr_err("%s called without initializing sock", __func__);
+		err = -EPERM;
+		goto out;
+	}
+
+	err = sock_sendmsg(sock, &msg);
+	args->addr.addrlen = msg.msg_namelen;
+out:
+	mutex_unlock(&sock_lock);
+
+	return err;
+}
+
+__bpf_kfunc int bpf_kfunc_call_kernel_getsockname(struct addr_args *args)
+{
+	int err;
+
+	mutex_lock(&sock_lock);
+
+	if (!sock) {
+		pr_err("%s called without initializing sock", __func__);
+		err = -EPERM;
+		goto out;
+	}
+
+	err = kernel_getsockname(sock, (struct sockaddr *)&args->addr);
+	if (err < 0)
+		goto out;
+
+	args->addrlen = err;
+	err = 0;
+out:
+	mutex_unlock(&sock_lock);
+
+	return err;
+}
+
+__bpf_kfunc int bpf_kfunc_call_kernel_getpeername(struct addr_args *args)
+{
+	int err;
+
+	mutex_lock(&sock_lock);
+
+	if (!sock) {
+		pr_err("%s called without initializing sock", __func__);
+		err = -EPERM;
+		goto out;
+	}
+
+	err = kernel_getpeername(sock, (struct sockaddr *)&args->addr);
+	if (err < 0)
+		goto out;
+
+	args->addrlen = err;
+	err = 0;
+out:
+	mutex_unlock(&sock_lock);
+
+	return err;
+}
+
 BTF_KFUNCS_START(bpf_testmod_check_kfunc_ids)
 BTF_ID_FLAGS(func, bpf_testmod_test_mod_kfunc)
 BTF_ID_FLAGS(func, bpf_kfunc_call_test1)
@@ -525,6 +768,15 @@ BTF_ID_FLAGS(func, bpf_kfunc_call_test_destructive, KF_DESTRUCTIVE)
 BTF_ID_FLAGS(func, bpf_kfunc_call_test_static_unused_arg)
 BTF_ID_FLAGS(func, bpf_kfunc_call_test_offset)
 BTF_ID_FLAGS(func, bpf_kfunc_call_test_sleepable, KF_SLEEPABLE)
+BTF_ID_FLAGS(func, bpf_kfunc_init_sock, KF_SLEEPABLE)
+BTF_ID_FLAGS(func, bpf_kfunc_close_sock, KF_SLEEPABLE)
+BTF_ID_FLAGS(func, bpf_kfunc_call_kernel_connect, KF_SLEEPABLE)
+BTF_ID_FLAGS(func, bpf_kfunc_call_kernel_bind, KF_SLEEPABLE)
+BTF_ID_FLAGS(func, bpf_kfunc_call_kernel_listen, KF_SLEEPABLE)
+BTF_ID_FLAGS(func, bpf_kfunc_call_kernel_sendmsg, KF_SLEEPABLE)
+BTF_ID_FLAGS(func, bpf_kfunc_call_sock_sendmsg, KF_SLEEPABLE)
+BTF_ID_FLAGS(func, bpf_kfunc_call_kernel_getsockname, KF_SLEEPABLE)
+BTF_ID_FLAGS(func, bpf_kfunc_call_kernel_getpeername, KF_SLEEPABLE)
 BTF_KFUNCS_END(bpf_testmod_check_kfunc_ids)
 
 static int bpf_testmod_ops_init(struct btf *btf)
@@ -655,6 +907,8 @@ static int bpf_testmod_init(void)
 		return ret;
 	if (bpf_fentry_test1(0) < 0)
 		return -EINVAL;
+	sock = NULL;
+	mutex_init(&sock_lock);
 	return sysfs_create_bin_file(kernel_kobj, &bin_attr_bpf_testmod_file);
 }
 
@@ -668,6 +922,7 @@ static void bpf_testmod_exit(void)
 	while (refcount_read(&prog_test_struct.cnt) > 1)
 		msleep(20);
 
+	bpf_kfunc_close_sock();
 	sysfs_remove_bin_file(kernel_kobj, &bin_attr_bpf_testmod_file);
 }
 

tools/testing/selftests/bpf/bpf_testmod/bpf_testmod_kfunc.h

@@ -64,6 +64,22 @@ struct prog_test_fail3 {
 	char arr2[];
 };
 
+struct init_sock_args {
+	int af;
+	int type;
+};
+
+struct addr_args {
+	char addr[sizeof(struct __kernel_sockaddr_storage)];
+	int addrlen;
+};
+
+struct sendmsg_args {
+	struct addr_args addr;
+	char msg[10];
+	int msglen;
+};
+
 struct prog_test_ref_kfunc *
 bpf_kfunc_call_test_acquire(unsigned long *scalar_ptr) __ksym;
 void bpf_kfunc_call_test_release(struct prog_test_ref_kfunc *p) __ksym;
@@ -107,4 +123,15 @@ void bpf_kfunc_call_test_fail3(struct prog_test_fail3 *p);
 void bpf_kfunc_call_test_mem_len_fail1(void *mem, int len);
 
 void bpf_kfunc_common_test(void) __ksym;
+
+int bpf_kfunc_init_sock(struct init_sock_args *args) __ksym;
+void bpf_kfunc_close_sock(void) __ksym;
+int bpf_kfunc_call_kernel_connect(struct addr_args *args) __ksym;
+int bpf_kfunc_call_kernel_bind(struct addr_args *args) __ksym;
+int bpf_kfunc_call_kernel_listen(void) __ksym;
+int bpf_kfunc_call_kernel_sendmsg(struct sendmsg_args *args) __ksym;
+int bpf_kfunc_call_sock_sendmsg(struct sendmsg_args *args) __ksym;
+int bpf_kfunc_call_kernel_getsockname(struct addr_args *args) __ksym;
+int bpf_kfunc_call_kernel_getpeername(struct addr_args *args) __ksym;
+
 #endif /* _BPF_TESTMOD_KFUNC_H */