prctl: Add force disable speculation

For certain use cases it is desired to enforce mitigations so they cannot
be undone afterwards. That's important for loader stubs which want to
prevent a child from disabling the mitigation again. Will also be used for
seccomp(). The extra state preserving of the prctl state for SSB is a
preparatory step for EBPF dymanic speculation control.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

Documentation/userspace-api/spec_ctrl.rst

@@ -25,19 +25,21 @@ PR_GET_SPECULATION_CTRL
 -----------------------
 
 PR_GET_SPECULATION_CTRL returns the state of the speculation misfeature
-which is selected with arg2 of prctl(2). The return value uses bits 0-2 with
+which is selected with arg2 of prctl(2). The return value uses bits 0-3 with
 the following meaning:
 
-==== ================ ===================================================
+==== ===================== ===================================================
 Bit  Define                Description
-==== ================ ===================================================
+==== ===================== ===================================================
 0    PR_SPEC_PRCTL         Mitigation can be controlled per task by
                            PR_SET_SPECULATION_CTRL
 1    PR_SPEC_ENABLE        The speculation feature is enabled, mitigation is
                            disabled
 2    PR_SPEC_DISABLE       The speculation feature is disabled, mitigation is
                            enabled
-==== ================ ===================================================
+3    PR_SPEC_FORCE_DISABLE Same as PR_SPEC_DISABLE, but cannot be undone. A
+                           subsequent prctl(..., PR_SPEC_ENABLE) will fail.
+==== ===================== ===================================================
 
 If all bits are 0 the CPU is not affected by the speculation misfeature.
 
@@ -47,9 +49,11 @@ misfeature will fail.
 
 PR_SET_SPECULATION_CTRL
 -----------------------
+
 PR_SET_SPECULATION_CTRL allows to control the speculation misfeature, which
 is selected by arg2 of :manpage:`prctl(2)` per task. arg3 is used to hand
-in the control value, i.e. either PR_SPEC_ENABLE or PR_SPEC_DISABLE.
+in the control value, i.e. either PR_SPEC_ENABLE or PR_SPEC_DISABLE or
+PR_SPEC_FORCE_DISABLE.
 
 Common error codes
 ------------------
@@ -70,10 +74,13 @@ Value   Meaning
 0       Success
 
 ERANGE  arg3 is incorrect, i.e. it's neither PR_SPEC_ENABLE nor
-        PR_SPEC_DISABLE
+        PR_SPEC_DISABLE nor PR_SPEC_FORCE_DISABLE
 
 ENXIO   Control of the selected speculation misfeature is not possible.
         See PR_GET_SPECULATION_CTRL.
+
+EPERM   Speculation was disabled with PR_SPEC_FORCE_DISABLE and caller
+        tried to enable it again.
 ======= =================================================================
 
 Speculation misfeature controls
@@ -84,3 +91,4 @@ Speculation misfeature controls
    * prctl(PR_GET_SPECULATION_CTRL, PR_SPEC_STORE_BYPASS, 0, 0, 0);
    * prctl(PR_SET_SPECULATION_CTRL, PR_SPEC_STORE_BYPASS, PR_SPEC_ENABLE, 0, 0);
    * prctl(PR_SET_SPECULATION_CTRL, PR_SPEC_STORE_BYPASS, PR_SPEC_DISABLE, 0, 0);
+   * prctl(PR_SET_SPECULATION_CTRL, PR_SPEC_STORE_BYPASS, PR_SPEC_FORCE_DISABLE, 0, 0);

arch/x86/kernel/cpu/bugs.c

@@ -533,21 +533,37 @@ static void ssb_select_mitigation()
 
 static int ssb_prctl_set(struct task_struct *task, unsigned long ctrl)
 {
-	bool rds = !!test_tsk_thread_flag(task, TIF_RDS);
+	bool update;
 
 	if (ssb_mode != SPEC_STORE_BYPASS_PRCTL)
 		return -ENXIO;
 
-	if (ctrl == PR_SPEC_ENABLE)
+	switch (ctrl) {
-		clear_tsk_thread_flag(task, TIF_RDS);
+	case PR_SPEC_ENABLE:
-	else
+		/* If speculation is force disabled, enable is not allowed */
-		set_tsk_thread_flag(task, TIF_RDS);
+		if (task_spec_ssb_force_disable(task))
+			return -EPERM;
+		task_clear_spec_ssb_disable(task);
+		update = test_and_clear_tsk_thread_flag(task, TIF_RDS);
+		break;
+	case PR_SPEC_DISABLE:
+		task_set_spec_ssb_disable(task);
+		update = !test_and_set_tsk_thread_flag(task, TIF_RDS);
+		break;
+	case PR_SPEC_FORCE_DISABLE:
+		task_set_spec_ssb_disable(task);
+		task_set_spec_ssb_force_disable(task);
+		update = !test_and_set_tsk_thread_flag(task, TIF_RDS);
+		break;
+	default:
+		return -ERANGE;
+	}
 
 	/*
 	 * If being set on non-current task, delay setting the CPU
 	 * mitigation until it is next scheduled.
 	 */
-	if (task == current && rds != !!test_tsk_thread_flag(task, TIF_RDS))
+	if (task == current && update)
 		speculative_store_bypass_update();
 
 	return 0;
@@ -559,7 +575,9 @@ static int ssb_prctl_get(struct task_struct *task)
 	case SPEC_STORE_BYPASS_DISABLE:
 		return PR_SPEC_DISABLE;
 	case SPEC_STORE_BYPASS_PRCTL:
-		if (test_tsk_thread_flag(task, TIF_RDS))
+		if (task_spec_ssb_force_disable(task))
+			return PR_SPEC_PRCTL | PR_SPEC_FORCE_DISABLE;
+		if (task_spec_ssb_disable(task))
 			return PR_SPEC_PRCTL | PR_SPEC_DISABLE;
 		return PR_SPEC_PRCTL | PR_SPEC_ENABLE;
 	default:
@@ -572,9 +590,6 @@ static int ssb_prctl_get(struct task_struct *task)
 int arch_prctl_spec_ctrl_set(struct task_struct *task, unsigned long which,
 			     unsigned long ctrl)
 {
-	if (ctrl != PR_SPEC_ENABLE && ctrl != PR_SPEC_DISABLE)
-		return -ERANGE;
-
 	switch (which) {
 	case PR_SPEC_STORE_BYPASS:
 		return ssb_prctl_set(task, ctrl);

fs/proc/array.c

@@ -344,6 +344,9 @@ static inline void task_seccomp(struct seq_file *m, struct task_struct *p)
 	case PR_SPEC_NOT_AFFECTED:
 		seq_printf(m, "not vulnerable");
 		break;
+	case PR_SPEC_PRCTL | PR_SPEC_FORCE_DISABLE:
+		seq_printf(m, "thread force mitigated");
+		break;
 	case PR_SPEC_PRCTL | PR_SPEC_DISABLE:
 		seq_printf(m, "thread mitigated");
 		break;

include/linux/sched.h

@@ -1393,7 +1393,8 @@ static inline bool is_percpu_thread(void)
 #define PFA_NO_NEW_PRIVS		0	/* May not gain new privileges. */
 #define PFA_SPREAD_PAGE			1	/* Spread page cache over cpuset */
 #define PFA_SPREAD_SLAB			2	/* Spread some slab caches over cpuset */
-
+#define PFA_SPEC_SSB_DISABLE		3	/* Speculative Store Bypass disabled */
+#define PFA_SPEC_SSB_FORCE_DISABLE	4	/* Speculative Store Bypass force disabled*/
 
 #define TASK_PFA_TEST(name, func)					\
 	static inline bool task_##func(struct task_struct *p)		\
@@ -1418,6 +1419,13 @@ TASK_PFA_TEST(SPREAD_SLAB, spread_slab)
 TASK_PFA_SET(SPREAD_SLAB, spread_slab)
 TASK_PFA_CLEAR(SPREAD_SLAB, spread_slab)
 
+TASK_PFA_TEST(SPEC_SSB_DISABLE, spec_ssb_disable)
+TASK_PFA_SET(SPEC_SSB_DISABLE, spec_ssb_disable)
+TASK_PFA_CLEAR(SPEC_SSB_DISABLE, spec_ssb_disable)
+
+TASK_PFA_TEST(SPEC_SSB_FORCE_DISABLE, spec_ssb_force_disable)
+TASK_PFA_SET(SPEC_SSB_FORCE_DISABLE, spec_ssb_force_disable)
+
 static inline void
 current_restore_flags(unsigned long orig_flags, unsigned long flags)
 {

include/uapi/linux/prctl.h

@@ -217,5 +217,6 @@ struct prctl_mm_map {
 # define PR_SPEC_PRCTL			(1UL << 0)
 # define PR_SPEC_ENABLE			(1UL << 1)
 # define PR_SPEC_DISABLE		(1UL << 2)
+# define PR_SPEC_FORCE_DISABLE		(1UL << 3)
 
 #endif /* _LINUX_PRCTL_H */