seccomp: Add filter flag to opt-out of SSB mitigation

If a seccomp user is not interested in Speculative Store Bypass mitigation
by default, it can set the new SECCOMP_FILTER_FLAG_SPEC_ALLOW flag when
adding filters.
Signed-off-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

include/linux/seccomp.h

@@ -5,7 +5,8 @@
 #include <uapi/linux/seccomp.h>
 
 #define SECCOMP_FILTER_FLAG_MASK	(SECCOMP_FILTER_FLAG_TSYNC	| \
-					 SECCOMP_FILTER_FLAG_LOG)
+					 SECCOMP_FILTER_FLAG_LOG	| \
+					 SECCOMP_FILTER_FLAG_SPEC_ALLOW)
 
 #ifdef CONFIG_SECCOMP
 

include/uapi/linux/seccomp.h

@@ -17,8 +17,9 @@
 #define SECCOMP_GET_ACTION_AVAIL	2
 
 /* Valid flags for SECCOMP_SET_MODE_FILTER */
-#define SECCOMP_FILTER_FLAG_TSYNC	1
-#define SECCOMP_FILTER_FLAG_LOG		2
+#define SECCOMP_FILTER_FLAG_TSYNC	(1UL << 0)
+#define SECCOMP_FILTER_FLAG_LOG		(1UL << 1)
+#define SECCOMP_FILTER_FLAG_SPEC_ALLOW	(1UL << 2)
 
 /*
  * All BPF programs must return a 32-bit value.

kernel/seccomp.c

@@ -243,7 +243,8 @@ static inline void spec_mitigate(struct task_struct *task,
 }
 
 static inline void seccomp_assign_mode(struct task_struct *task,
-				       unsigned long seccomp_mode)
+				       unsigned long seccomp_mode,
+				       unsigned long flags)
 {
 	assert_spin_locked(&task->sighand->siglock);
 
@@ -253,7 +254,8 @@ static inline void seccomp_assign_mode(struct task_struct *task,
 	 * filter) is set.
 	 */
 	smp_mb__before_atomic();
-	/* Assume seccomp processes want speculation flaw mitigation. */
+	/* Assume default seccomp processes want spec flaw mitigation. */
+	if ((flags & SECCOMP_FILTER_FLAG_SPEC_ALLOW) == 0)
 		spec_mitigate(task, PR_SPEC_STORE_BYPASS);
 	set_tsk_thread_flag(task, TIF_SECCOMP);
 }
@@ -322,7 +324,7 @@ static inline pid_t seccomp_can_sync_threads(void)
  * without dropping the locks.
  *
  */
-static inline void seccomp_sync_threads(void)
+static inline void seccomp_sync_threads(unsigned long flags)
 {
 	struct task_struct *thread, *caller;
 
@@ -363,7 +365,8 @@ static inline void seccomp_sync_threads(void)
 		 * allow one thread to transition the other.
 		 */
 		if (thread->seccomp.mode == SECCOMP_MODE_DISABLED)
-			seccomp_assign_mode(thread, SECCOMP_MODE_FILTER);
+			seccomp_assign_mode(thread, SECCOMP_MODE_FILTER,
+					    flags);
 	}
 }
 
@@ -486,7 +489,7 @@ static long seccomp_attach_filter(unsigned int flags,
 
 	/* Now that the new filter is in place, synchronize to all threads. */
 	if (flags & SECCOMP_FILTER_FLAG_TSYNC)
-		seccomp_sync_threads();
+		seccomp_sync_threads(flags);
 
 	return 0;
 }
@@ -835,7 +838,7 @@ static long seccomp_set_mode_strict(void)
 #ifdef TIF_NOTSC
 	disable_TSC();
 #endif
-	seccomp_assign_mode(current, seccomp_mode);
+	seccomp_assign_mode(current, seccomp_mode, 0);
 	ret = 0;
 
 out:
@@ -893,7 +896,7 @@ static long seccomp_set_mode_filter(unsigned int flags,
 	/* Do not free the successfully attached filter. */
 	prepared = NULL;
 
-	seccomp_assign_mode(current, seccomp_mode);
+	seccomp_assign_mode(current, seccomp_mode, flags);
 out:
 	spin_unlock_irq(&current->sighand->siglock);
 	if (flags & SECCOMP_FILTER_FLAG_TSYNC)

tools/testing/selftests/seccomp/seccomp_bpf.c

@@ -134,11 +134,15 @@ struct seccomp_data {
 #endif
 
 #ifndef SECCOMP_FILTER_FLAG_TSYNC
-#define SECCOMP_FILTER_FLAG_TSYNC 1
+#define SECCOMP_FILTER_FLAG_TSYNC (1UL << 0)
 #endif
 
 #ifndef SECCOMP_FILTER_FLAG_LOG
-#define SECCOMP_FILTER_FLAG_LOG 2
+#define SECCOMP_FILTER_FLAG_LOG (1UL << 1)
+#endif
+
+#ifndef SECCOMP_FILTER_FLAG_SPEC_ALLOW
+#define SECCOMP_FILTER_FLAG_SPEC_ALLOW (1UL << 2)
 #endif
 
 #ifndef PTRACE_SECCOMP_GET_METADATA
@@ -2072,14 +2076,26 @@ TEST(seccomp_syscall_mode_lock)
 TEST(detect_seccomp_filter_flags)
 {
 	unsigned int flags[] = { SECCOMP_FILTER_FLAG_TSYNC,
-				 SECCOMP_FILTER_FLAG_LOG };
+				 SECCOMP_FILTER_FLAG_LOG,
+				 SECCOMP_FILTER_FLAG_SPEC_ALLOW };
 	unsigned int flag, all_flags;
 	int i;
 	long ret;
 
 	/* Test detection of known-good filter flags */
 	for (i = 0, all_flags = 0; i < ARRAY_SIZE(flags); i++) {
+		int bits = 0;
+
 		flag = flags[i];
+		/* Make sure the flag is a single bit! */
+		while (flag) {
+			if (flag & 0x1)
+				bits ++;
+			flag >>= 1;
+		}
+		ASSERT_EQ(1, bits);
+		flag = flags[i];
+
 		ret = seccomp(SECCOMP_SET_MODE_FILTER, flag, NULL);
 		ASSERT_NE(ENOSYS, errno) {
 			TH_LOG("Kernel does not support seccomp syscall!");