Merge tag 'seccomp-v5.5-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux

Pull seccomp updates from Kees Cook:
 "Mostly this is implementing the new flag SECCOMP_USER_NOTIF_FLAG_CONTINUE,
  but there are cleanups as well.

   - implement SECCOMP_USER_NOTIF_FLAG_CONTINUE (Christian Brauner)

   - fixes to selftests (Christian Brauner)

   - remove secure_computing() argument (Christian Brauner)"

* tag 'seccomp-v5.5-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux:
  seccomp: rework define for SECCOMP_USER_NOTIF_FLAG_CONTINUE
  seccomp: fix SECCOMP_USER_NOTIF_FLAG_CONTINUE test
  seccomp: simplify secure_computing()
  seccomp: test SECCOMP_USER_NOTIF_FLAG_CONTINUE
  seccomp: add SECCOMP_USER_NOTIF_FLAG_CONTINUE
  seccomp: avoid overflow in implicit constant conversion

11 files changed, 170 insertions, 17 deletions

diff --git a/arch/arm/kernel/ptrace.c b/arch/arm/kernel/ptrace.c
index 324352787aea..b606cded90cd 100644
--- a/arch/arm/kernel/ptrace.c
+++ b/arch/arm/kernel/ptrace.c
@@ -923,7 +923,7 @@ asmlinkage int syscall_trace_enter(struct pt_regs *regs, int scno)
 
 	/* Do seccomp after ptrace; syscall may have changed. */
 #ifdef CONFIG_HAVE_ARCH_SECCOMP_FILTER
-	if (secure_computing(NULL) == -1)
+	if (secure_computing() == -1)
 		return -1;
 #else
 	/* XXX: remove this once OABI gets fixed */
diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index 21176d02e21a..6771c399d40c 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -1816,7 +1816,7 @@ int syscall_trace_enter(struct pt_regs *regs)
 	}
 
 	/* Do the secure computing after ptrace; failures should be fast. */
-	if (secure_computing(NULL) == -1)
+	if (secure_computing() == -1)
 		return -1;
 
 	if (test_thread_flag(TIF_SYSCALL_TRACEPOINT))
diff --git a/arch/parisc/kernel/ptrace.c b/arch/parisc/kernel/ptrace.c
index 9f6ff7bc06f9..f8c07dcbfb49 100644
--- a/arch/parisc/kernel/ptrace.c
+++ b/arch/parisc/kernel/ptrace.c
@@ -342,7 +342,7 @@ long do_syscall_trace_enter(struct pt_regs *regs)
 	}
 
 	/* Do the secure computing check after ptrace. */
-	if (secure_computing(NULL) == -1)
+	if (secure_computing() == -1)
 		return -1;
 
 #ifdef CONFIG_HAVE_SYSCALL_TRACEPOINTS
diff --git a/arch/riscv/kernel/ptrace.c b/arch/riscv/kernel/ptrace.c
index 0f84628b9385..407464201b91 100644
--- a/arch/riscv/kernel/ptrace.c
+++ b/arch/riscv/kernel/ptrace.c
@@ -159,7 +159,7 @@ __visible void do_syscall_trace_enter(struct pt_regs *regs)
 	 * If this fails we might have return value in a0 from seccomp
 	 * (via SECCOMP_RET_ERRNO/TRACE).
 	 */
-	if (secure_computing(NULL) == -1) {
+	if (secure_computing() == -1) {
 		syscall_set_nr(current, regs, -1);
 		return;
 	}
diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c
index ad71132374f0..58faa12542a1 100644
--- a/arch/s390/kernel/ptrace.c
+++ b/arch/s390/kernel/ptrace.c
@@ -856,7 +856,7 @@ asmlinkage long do_syscall_trace_enter(struct pt_regs *regs)
 	}
 
 	/* Do the secure computing check after ptrace. */
-	if (secure_computing(NULL)) {
+	if (secure_computing()) {
 		/* seccomp failures shouldn't expose any additional code. */
 		return -1;
 	}
diff --git a/arch/um/kernel/skas/syscall.c b/arch/um/kernel/skas/syscall.c
index f574b1856bc6..40d90dddf3f1 100644
--- a/arch/um/kernel/skas/syscall.c
+++ b/arch/um/kernel/skas/syscall.c
@@ -35,7 +35,7 @@ void handle_syscall(struct uml_pt_regs *r)
 		goto out;
 
 	/* Do the seccomp check after ptrace; failures should be fast. */
-	if (secure_computing(NULL) == -1)
+	if (secure_computing() == -1)
 		goto out;
 
 	syscall = UPT_SYSCALL_NR(r);
diff --git a/arch/x86/entry/vsyscall/vsyscall_64.c b/arch/x86/entry/vsyscall/vsyscall_64.c
index e7c596dea947..b10cbf71a8cc 100644
--- a/arch/x86/entry/vsyscall/vsyscall_64.c
+++ b/arch/x86/entry/vsyscall/vsyscall_64.c
@@ -222,7 +222,7 @@ bool emulate_vsyscall(unsigned long error_code,
 	 */
 	regs->orig_ax = syscall_nr;
 	regs->ax = -ENOSYS;
-	tmp = secure_computing(NULL);
+	tmp = secure_computing();
 	if ((!tmp && regs->orig_ax != syscall_nr) || regs->ip != address) {
 		warn_bad_vsyscall(KERN_DEBUG, regs,
 				  "seccomp tried to change syscall nr or ip");
diff --git a/include/linux/seccomp.h b/include/linux/seccomp.h
index 84868d37b35d..03583b6d1416 100644
--- a/include/linux/seccomp.h
+++ b/include/linux/seccomp.h
@@ -33,10 +33,10 @@ struct seccomp {
 
 #ifdef CONFIG_HAVE_ARCH_SECCOMP_FILTER
 extern int __secure_computing(const struct seccomp_data *sd);
-static inline int secure_computing(const struct seccomp_data *sd)
+static inline int secure_computing(void)
 {
 	if (unlikely(test_thread_flag(TIF_SECCOMP)))
-		return  __secure_computing(sd);
+		return  __secure_computing(NULL);
 	return 0;
 }
 #else
@@ -59,7 +59,7 @@ struct seccomp { };
 struct seccomp_filter { };
 
 #ifdef CONFIG_HAVE_ARCH_SECCOMP_FILTER
-static inline int secure_computing(struct seccomp_data *sd) { return 0; }
+static inline int secure_computing(void) { return 0; }
 #else
 static inline void secure_computing_strict(int this_syscall) { return; }
 #endif
diff --git a/include/uapi/linux/seccomp.h b/include/uapi/linux/seccomp.h
index 90734aa5aa36..be84d87f1f46 100644
--- a/include/uapi/linux/seccomp.h
+++ b/include/uapi/linux/seccomp.h
@@ -76,6 +76,35 @@ struct seccomp_notif {
 	struct seccomp_data data;
 };
 
+/*
+ * Valid flags for struct seccomp_notif_resp
+ *
+ * Note, the SECCOMP_USER_NOTIF_FLAG_CONTINUE flag must be used with caution!
+ * If set by the process supervising the syscalls of another process the
+ * syscall will continue. This is problematic because of an inherent TOCTOU.
+ * An attacker can exploit the time while the supervised process is waiting on
+ * a response from the supervising process to rewrite syscall arguments which
+ * are passed as pointers of the intercepted syscall.
+ * It should be absolutely clear that this means that the seccomp notifier
+ * _cannot_ be used to implement a security policy! It should only ever be used
+ * in scenarios where a more privileged process supervises the syscalls of a
+ * lesser privileged process to get around kernel-enforced security
+ * restrictions when the privileged process deems this safe. In other words,
+ * in order to continue a syscall the supervising process should be sure that
+ * another security mechanism or the kernel itself will sufficiently block
+ * syscalls if arguments are rewritten to something unsafe.
+ *
+ * Similar precautions should be applied when stacking SECCOMP_RET_USER_NOTIF
+ * or SECCOMP_RET_TRACE. For SECCOMP_RET_USER_NOTIF filters acting on the
+ * same syscall, the most recently added filter takes precedence. This means
+ * that the new SECCOMP_RET_USER_NOTIF filter can override any
+ * SECCOMP_IOCTL_NOTIF_SEND from earlier filters, essentially allowing all
+ * such filtered syscalls to be executed by sending the response
+ * SECCOMP_USER_NOTIF_FLAG_CONTINUE. Note that SECCOMP_RET_TRACE can equally
+ * be overriden by SECCOMP_USER_NOTIF_FLAG_CONTINUE.
+ */
+#define SECCOMP_USER_NOTIF_FLAG_CONTINUE (1UL << 0)
+
 struct seccomp_notif_resp {
 	__u64 id;
 	__s64 val;
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index dba52a7db5e8..12d2227e5786 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -75,6 +75,7 @@ struct seccomp_knotif {
 	/* The return values, only valid when in SECCOMP_NOTIFY_REPLIED */
 	int error;
 	long val;
+	u32 flags;
 
 	/* Signals when this has entered SECCOMP_NOTIFY_REPLIED */
 	struct completion ready;
@@ -732,11 +733,12 @@ static u64 seccomp_next_notify_id(struct seccomp_filter *filter)
 	return filter->notif->next_id++;
 }
 
-static void seccomp_do_user_notification(int this_syscall,
-					 struct seccomp_filter *match,
-					 const struct seccomp_data *sd)
+static int seccomp_do_user_notification(int this_syscall,
+					struct seccomp_filter *match,
+					const struct seccomp_data *sd)
 {
 	int err;
+	u32 flags = 0;
 	long ret = 0;
 	struct seccomp_knotif n = {};
 
@@ -764,6 +766,7 @@ static void seccomp_do_user_notification(int this_syscall,
 	if (err == 0) {
 		ret = n.val;
 		err = n.error;
+		flags = n.flags;
 	}
 
 	/*
@@ -780,8 +783,14 @@ static void seccomp_do_user_notification(int this_syscall,
 		list_del(&n.list);
 out:
 	mutex_unlock(&match->notify_lock);
+
+	/* Userspace requests to continue the syscall. */
+	if (flags & SECCOMP_USER_NOTIF_FLAG_CONTINUE)
+		return 0;
+
 	syscall_set_return_value(current, task_pt_regs(current),
 				 err, ret);
+	return -1;
 }
 
 static int __seccomp_filter(int this_syscall, const struct seccomp_data *sd,
@@ -867,8 +876,10 @@ static int __seccomp_filter(int this_syscall, const struct seccomp_data *sd,
 		return 0;
 
 	case SECCOMP_RET_USER_NOTIF:
-		seccomp_do_user_notification(this_syscall, match, sd);
-		goto skip;
+		if (seccomp_do_user_notification(this_syscall, match, sd))
+			goto skip;
+
+		return 0;
 
 	case SECCOMP_RET_LOG:
 		seccomp_log(this_syscall, 0, action, true);
@@ -1087,7 +1098,11 @@ static long seccomp_notify_send(struct seccomp_filter *filter,
 	if (copy_from_user(&resp, buf, sizeof(resp)))
 		return -EFAULT;
 
-	if (resp.flags)
+	if (resp.flags & ~SECCOMP_USER_NOTIF_FLAG_CONTINUE)
+		return -EINVAL;
+
+	if ((resp.flags & SECCOMP_USER_NOTIF_FLAG_CONTINUE) &&
+	    (resp.error || resp.val))
 		return -EINVAL;
 
 	ret = mutex_lock_interruptible(&filter->notify_lock);
@@ -1116,6 +1131,7 @@ static long seccomp_notify_send(struct seccomp_filter *filter,
 	knotif->state = SECCOMP_NOTIFY_REPLIED;
 	knotif->error = resp.error;
 	knotif->val = resp.val;
+	knotif->flags = resp.flags;
 	complete(&knotif->ready);
 out:
 	mutex_unlock(&filter->notify_lock);
diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c
index aeb0fc37a654..6944b898bb53 100644
--- a/tools/testing/selftests/seccomp/seccomp_bpf.c
+++ b/tools/testing/selftests/seccomp/seccomp_bpf.c
@@ -35,6 +35,7 @@
 #include <stdbool.h>
 #include <string.h>
 #include <time.h>
+#include <limits.h>
 #include <linux/elf.h>
 #include <sys/uio.h>
 #include <sys/utsname.h>
@@ -43,6 +44,7 @@
 #include <sys/times.h>
 #include <sys/socket.h>
 #include <sys/ioctl.h>
+#include <linux/kcmp.h>
 
 #include <unistd.h>
 #include <sys/syscall.h>
@@ -206,6 +208,10 @@ struct seccomp_notif_sizes {
 #define PTRACE_EVENTMSG_SYSCALL_EXIT	2
 #endif
 
+#ifndef SECCOMP_USER_NOTIF_FLAG_CONTINUE
+#define SECCOMP_USER_NOTIF_FLAG_CONTINUE 0x00000001
+#endif
+
 #ifndef seccomp
 int seccomp(unsigned int op, unsigned int flags, void *args)
 {
@@ -3083,7 +3089,7 @@ static int user_trap_syscall(int nr, unsigned int flags)
 	return seccomp(SECCOMP_SET_MODE_FILTER, flags, &prog);
 }
 
-#define USER_NOTIF_MAGIC 116983961184613L
+#define USER_NOTIF_MAGIC INT_MAX
 TEST(user_notification_basic)
 {
 	pid_t pid;
@@ -3491,6 +3497,108 @@ TEST(seccomp_get_notif_sizes)
 	EXPECT_EQ(sizes.seccomp_notif_resp, sizeof(struct seccomp_notif_resp));
 }
 
+static int filecmp(pid_t pid1, pid_t pid2, int fd1, int fd2)
+{
+#ifdef __NR_kcmp
+	return syscall(__NR_kcmp, pid1, pid2, KCMP_FILE, fd1, fd2);
+#else
+	errno = ENOSYS;
+	return -1;
+#endif
+}
+
+TEST(user_notification_continue)
+{
+	pid_t pid;
+	long ret;
+	int status, listener;
+	struct seccomp_notif req = {};
+	struct seccomp_notif_resp resp = {};
+	struct pollfd pollfd;
+
+	ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
+	ASSERT_EQ(0, ret) {
+		TH_LOG("Kernel does not support PR_SET_NO_NEW_PRIVS!");
+	}
+
+	listener = user_trap_syscall(__NR_dup, SECCOMP_FILTER_FLAG_NEW_LISTENER);
+	ASSERT_GE(listener, 0);
+
+	pid = fork();
+	ASSERT_GE(pid, 0);
+
+	if (pid == 0) {
+		int dup_fd, pipe_fds[2];
+		pid_t self;
+
+		ret = pipe(pipe_fds);
+		if (ret < 0)
+			exit(1);
+
+		dup_fd = dup(pipe_fds[0]);
+		if (dup_fd < 0)
+			exit(1);
+
+		self = getpid();
+
+		ret = filecmp(self, self, pipe_fds[0], dup_fd);
+		if (ret)
+			exit(2);
+
+		exit(0);
+	}
+
+	pollfd.fd = listener;
+	pollfd.events = POLLIN | POLLOUT;
+
+	EXPECT_GT(poll(&pollfd, 1, -1), 0);
+	EXPECT_EQ(pollfd.revents, POLLIN);
+
+	EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_RECV, &req), 0);
+
+	pollfd.fd = listener;
+	pollfd.events = POLLIN | POLLOUT;
+
+	EXPECT_GT(poll(&pollfd, 1, -1), 0);
+	EXPECT_EQ(pollfd.revents, POLLOUT);
+
+	EXPECT_EQ(req.data.nr, __NR_dup);
+
+	resp.id = req.id;
+	resp.flags = SECCOMP_USER_NOTIF_FLAG_CONTINUE;
+
+	/*
+	 * Verify that setting SECCOMP_USER_NOTIF_FLAG_CONTINUE enforces other
+	 * args be set to 0.
+	 */
+	resp.error = 0;
+	resp.val = USER_NOTIF_MAGIC;
+	EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_SEND, &resp), -1);
+	EXPECT_EQ(errno, EINVAL);
+
+	resp.error = USER_NOTIF_MAGIC;
+	resp.val = 0;
+	EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_SEND, &resp), -1);
+	EXPECT_EQ(errno, EINVAL);
+
+	resp.error = 0;
+	resp.val = 0;
+	EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_SEND, &resp), 0) {
+		if (errno == EINVAL)
+			XFAIL(goto skip, "Kernel does not support SECCOMP_USER_NOTIF_FLAG_CONTINUE");
+	}
+
+skip:
+	EXPECT_EQ(waitpid(pid, &status, 0), pid);
+	EXPECT_EQ(true, WIFEXITED(status));
+	EXPECT_EQ(0, WEXITSTATUS(status)) {
+		if (WEXITSTATUS(status) == 2) {
+			XFAIL(return, "Kernel does not support kcmp() syscall");
+			return;
+		}
+	}
+}
+
 /*
  * TODO:
  * - add microbenchmarks