Merge tag 'lsm-pr-20221003' of git://git.kernel.org/pub/scm/linux/kernel/git/pcmoore/lsm

Pull LSM updates from Paul Moore:
"Seven patches for the LSM layer and we've got a mix of trivial and
significant patches. Highlights below, starting with the smaller bits
first so they don't get lost in the discussion of the larger items:

- Remove some redundant NULL pointer checks in the common LSM audit
code.

- Ratelimit the lockdown LSM's access denial messages.

With this change there is a chance that the last visible lockdown
message on the console is outdated/old, but it does help preserve
the initial series of lockdown denials that started the denial
message flood and my gut feeling is that these might be the more
valuable messages.

- Open userfaultfds as readonly instead of read/write.

While this code obviously lives outside the LSM, it does have a
noticeable impact on the LSMs with Ondrej explaining the situation
in the commit description. It is worth noting that this patch
languished on the VFS list for over a year without any comments
(objections or otherwise) so I took the liberty of pulling it into
the LSM tree after giving fair notice. It has been in linux-next
since the end of August without any noticeable problems.

- Add a LSM hook for user namespace creation, with implementations
for both the BPF LSM and SELinux.

Even though the changes are fairly small, this is the bulk of the
diffstat as we are also including BPF LSM selftests for the new
hook.

It's also the most contentious of the changes in this pull request
with Eric Biederman NACK'ing the LSM hook multiple times during its
development and discussion upstream. While I've never taken NACK's
lightly, I'm sending these patches to you because it is my belief
that they are of good quality, satisfy a long-standing need of
users and distros, and are in keeping with the existing nature of
the LSM layer and the Linux Kernel as a whole.

The patches in implement a LSM hook for user namespace creation
that allows for a granular approach, configurable at runtime, which
enables both monitoring and control of user namespaces. The general
consensus has been that this is far preferable to the other
solutions that have been adopted downstream including outright
removal from the kernel, disabling via system wide sysctls, or
various other out-of-tree mechanisms that users have been forced to
adopt since we haven't been able to provide them an upstream
solution for their requests. Eric has been steadfast in his
objections to this LSM hook, explaining that any restrictions on
the user namespace could have significant impact on userspace.
While there is the possibility of impacting userspace, it is
important to note that this solution only impacts userspace when it
is requested based on the runtime configuration supplied by the
distro/admin/user. Frederick (the pathset author), the LSM/security
community, and myself have tried to work with Eric during
development of this patchset to find a mutually acceptable
solution, but Eric's approach and unwillingness to engage in a
meaningful way have made this impossible. I have CC'd Eric directly
on this pull request so he has a chance to provide his side of the
story; there have been no objections outside of Eric's"

* tag 'lsm-pr-20221003' of git://git.kernel.org/pub/scm/linux/kernel/git/pcmoore/lsm:
lockdown: ratelimit denial messages
userfaultfd: open userfaultfds with O_RDONLY
selinux: Implement userns_create hook
selftests/bpf: Add tests verifying bpf lsm userns_create hook
bpf-lsm: Make bpf_lsm_userns_create() sleepable
security, lsm: Introduce security_create_user_ns()
lsm: clean up redundant NULL pointer check

fs/userfaultfd.c

···
 	int fd;
 
 	fd = anon_inode_getfd_secure("[userfaultfd]", &userfaultfd_fops, new,
-			O_RDWR | (new->flags & UFFD_SHARED_FCNTL_FLAGS), inode);
+			O_RDONLY | (new->flags & UFFD_SHARED_FCNTL_FLAGS), inode);
 	if (fd < 0)
 		return fd;
 
···
 	mmgrab(ctx->mm);
 
 	fd = anon_inode_getfd_secure("[userfaultfd]", &userfaultfd_fops, ctx,
-			O_RDWR | (flags & UFFD_SHARED_FCNTL_FLAGS), NULL);
+			O_RDONLY | (flags & UFFD_SHARED_FCNTL_FLAGS), NULL);
 	if (fd < 0) {
 		mmdrop(ctx->mm);
 		kmem_cache_free(userfaultfd_ctx_cachep, ctx);

include/linux/lsm_hook_defs.h

···
 	 unsigned long arg3, unsigned long arg4, unsigned long arg5)
 LSM_HOOK(void, LSM_RET_VOID, task_to_inode, struct task_struct *p,
 	 struct inode *inode)
+LSM_HOOK(int, 0, userns_create, const struct cred *cred)
 LSM_HOOK(int, 0, ipc_permission, struct kern_ipc_perm *ipcp, short flag)
 LSM_HOOK(void, LSM_RET_VOID, ipc_getsecid, struct kern_ipc_perm *ipcp,
 	 u32 *secid)

include/linux/lsm_hooks.h

···
  *	security attributes, e.g. for /proc/pid inodes.
  *	@p contains the task_struct for the task.
  *	@inode contains the inode structure for the inode.
+ * @userns_create:
+ *	Check permission prior to creating a new user namespace.
+ *	@cred points to prepared creds.
+ *	Return 0 if successful, otherwise < 0 error code.
  *
  * Security hooks for Netlink messaging.
  *

include/linux/security.h

···
 int security_task_prctl(int option, unsigned long arg2, unsigned long arg3,
 			unsigned long arg4, unsigned long arg5);
 void security_task_to_inode(struct task_struct *p, struct inode *inode);
+int security_create_user_ns(const struct cred *cred);
 int security_ipc_permission(struct kern_ipc_perm *ipcp, short flag);
 void security_ipc_getsecid(struct kern_ipc_perm *ipcp, u32 *secid);
 int security_msg_msg_alloc(struct msg_msg *msg);
···
 
 static inline void security_task_to_inode(struct task_struct *p, struct inode *inode)
 { }
+
+static inline int security_create_user_ns(const struct cred *cred)
+{
+	return 0;
+}
 
 static inline int security_ipc_permission(struct kern_ipc_perm *ipcp,
 					  short flag)

kernel/bpf/bpf_lsm.c

···
 BTF_ID(func, bpf_lsm_task_prctl)
 BTF_ID(func, bpf_lsm_task_setscheduler)
 BTF_ID(func, bpf_lsm_task_to_inode)
+BTF_ID(func, bpf_lsm_userns_create)
 BTF_SET_END(sleepable_lsm_hooks)
 
 bool bpf_lsm_is_sleepable_hook(u32 btf_id)

kernel/user_namespace.c

···
 #include <linux/highuid.h>
 #include <linux/cred.h>
 #include <linux/securebits.h>
+#include <linux/security.h>
 #include <linux/keyctl.h>
 #include <linux/key-type.h>
 #include <keys/user-type.h>
···
 	ret = -EPERM;
 	if (!kuid_has_mapping(parent_ns, owner) ||
 	    !kgid_has_mapping(parent_ns, group))
+		goto fail_dec;
+
+	ret = security_create_user_ns(new);
+	if (ret < 0)
 		goto fail_dec;
 
 	ret = -ENOMEM;

security/lockdown/lockdown.c

···
 
 	if (kernel_locked_down >= what) {
 		if (lockdown_reasons[what])
-			pr_notice("Lockdown: %s: %s is restricted; see man kernel_lockdown.7\n",
+			pr_notice_ratelimited("Lockdown: %s: %s is restricted; see man kernel_lockdown.7\n",
 				  current->comm, lockdown_reasons[what]);
 		return -EPERM;
 	}

security/lsm_audit.c

···
 	struct iphdr *ih;
 
 	ih = ip_hdr(skb);
-	if (ih == NULL)
-		return -EINVAL;
-
 	ad->u.net->v4info.saddr = ih->saddr;
 	ad->u.net->v4info.daddr = ih->daddr;
 
···
 	switch (ih->protocol) {
 	case IPPROTO_TCP: {
 		struct tcphdr *th = tcp_hdr(skb);
-		if (th == NULL)
-			break;
 
 		ad->u.net->sport = th->source;
 		ad->u.net->dport = th->dest;
···
 	}
 	case IPPROTO_UDP: {
 		struct udphdr *uh = udp_hdr(skb);
-		if (uh == NULL)
-			break;
 
 		ad->u.net->sport = uh->source;
 		ad->u.net->dport = uh->dest;
···
 	}
 	case IPPROTO_DCCP: {
 		struct dccp_hdr *dh = dccp_hdr(skb);
-		if (dh == NULL)
-			break;
 
 		ad->u.net->sport = dh->dccph_sport;
 		ad->u.net->dport = dh->dccph_dport;
···
 	}
 	case IPPROTO_SCTP: {
 		struct sctphdr *sh = sctp_hdr(skb);
-		if (sh == NULL)
-			break;
+
 		ad->u.net->sport = sh->source;
 		ad->u.net->dport = sh->dest;
 		break;
···
 	__be16 frag_off;
 
 	ip6 = ipv6_hdr(skb);
-	if (ip6 == NULL)
-		return -EINVAL;
 	ad->u.net->v6info.saddr = ip6->saddr;
 	ad->u.net->v6info.daddr = ip6->daddr;
 	/* IPv6 can have several extension header before the Transport header

security/security.c

···
 	call_void_hook(task_to_inode, p, inode);
 }
 
+int security_create_user_ns(const struct cred *cred)
+{
+	return call_int_hook(userns_create, 0, cred);
+}
+
 int security_ipc_permission(struct kern_ipc_perm *ipcp, short flag)
 {
 	return call_int_hook(ipc_permission, 0, ipcp, flag);

security/selinux/hooks.c

···
 	spin_unlock(&isec->lock);
 }
 
+static int selinux_userns_create(const struct cred *cred)
+{
+	u32 sid = current_sid();
+
+	return avc_has_perm(&selinux_state, sid, sid, SECCLASS_USER_NAMESPACE,
+						USER_NAMESPACE__CREATE, NULL);
+}
+
 /* Returns error only if unable to parse addresses */
 static int selinux_parse_skb_ipv4(struct sk_buff *skb,
 			struct common_audit_data *ad, u8 *proto)
···
 	LSM_HOOK_INIT(task_movememory, selinux_task_movememory),
 	LSM_HOOK_INIT(task_kill, selinux_task_kill),
 	LSM_HOOK_INIT(task_to_inode, selinux_task_to_inode),
+	LSM_HOOK_INIT(userns_create, selinux_userns_create),
 
 	LSM_HOOK_INIT(ipc_permission, selinux_ipc_permission),
 	LSM_HOOK_INIT(ipc_getsecid, selinux_ipc_getsecid),

security/selinux/include/classmap.h

···
 	  { COMMON_FILE_PERMS, NULL } },
 	{ "io_uring",
 	  { "override_creds", "sqpoll", "cmd", NULL } },
+	{ "user_namespace",
+	  { "create", NULL } },
 	{ NULL }
   };
 

tools/testing/selftests/bpf/prog_tests/deny_namespace.c

···
+// SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE
+#include <test_progs.h>
+#include "test_deny_namespace.skel.h"
+#include <sched.h>
+#include "cap_helpers.h"
+#include <stdio.h>
+
+static int wait_for_pid(pid_t pid)
+{
+	int status, ret;
+
+again:
+	ret = waitpid(pid, &status, 0);
+	if (ret == -1) {
+		if (errno == EINTR)
+			goto again;
+
+		return -1;
+	}
+
+	if (!WIFEXITED(status))
+		return -1;
+
+	return WEXITSTATUS(status);
+}
+
+/* negative return value -> some internal error
+ * positive return value -> userns creation failed
+ * 0                     -> userns creation succeeded
+ */
+static int create_user_ns(void)
+{
+	pid_t pid;
+
+	pid = fork();
+	if (pid < 0)
+		return -1;
+
+	if (pid == 0) {
+		if (unshare(CLONE_NEWUSER))
+			_exit(EXIT_FAILURE);
+		_exit(EXIT_SUCCESS);
+	}
+
+	return wait_for_pid(pid);
+}
+
+static void test_userns_create_bpf(void)
+{
+	__u32 cap_mask = 1ULL << CAP_SYS_ADMIN;
+	__u64 old_caps = 0;
+
+	cap_enable_effective(cap_mask, &old_caps);
+
+	ASSERT_OK(create_user_ns(), "priv new user ns");
+
+	cap_disable_effective(cap_mask, &old_caps);
+
+	ASSERT_EQ(create_user_ns(), EPERM, "unpriv new user ns");
+
+	if (cap_mask & old_caps)
+		cap_enable_effective(cap_mask, NULL);
+}
+
+static void test_unpriv_userns_create_no_bpf(void)
+{
+	__u32 cap_mask = 1ULL << CAP_SYS_ADMIN;
+	__u64 old_caps = 0;
+
+	cap_disable_effective(cap_mask, &old_caps);
+
+	ASSERT_OK(create_user_ns(), "no-bpf unpriv new user ns");
+
+	if (cap_mask & old_caps)
+		cap_enable_effective(cap_mask, NULL);
+}
+
+void test_deny_namespace(void)
+{
+	struct test_deny_namespace *skel = NULL;
+	int err;
+
+	if (test__start_subtest("unpriv_userns_create_no_bpf"))
+		test_unpriv_userns_create_no_bpf();
+
+	skel = test_deny_namespace__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel load"))
+		goto close_prog;
+
+	err = test_deny_namespace__attach(skel);
+	if (!ASSERT_OK(err, "attach"))
+		goto close_prog;
+
+	if (test__start_subtest("userns_create_bpf"))
+		test_userns_create_bpf();
+
+	test_deny_namespace__detach(skel);
+
+close_prog:
+	test_deny_namespace__destroy(skel);
+}

tools/testing/selftests/bpf/progs/test_deny_namespace.c

···
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include <errno.h>
+#include <linux/capability.h>
+
+struct kernel_cap_struct {
+	__u32 cap[_LINUX_CAPABILITY_U32S_3];
+} __attribute__((preserve_access_index));
+
+struct cred {
+	struct kernel_cap_struct cap_effective;
+} __attribute__((preserve_access_index));
+
+char _license[] SEC("license") = "GPL";
+
+SEC("lsm.s/userns_create")
+int BPF_PROG(test_userns_create, const struct cred *cred, int ret)
+{
+	struct kernel_cap_struct caps = cred->cap_effective;
+	int cap_index = CAP_TO_INDEX(CAP_SYS_ADMIN);
+	__u32 cap_mask = CAP_TO_MASK(CAP_SYS_ADMIN);
+
+	if (ret)
+		return 0;
+
+	ret = -EPERM;
+	if (caps.cap[cap_index] & cap_mask)
+		return 0;
+
+	return -EPERM;
+}