arm64/gcs: Implement shadow stack prctl() interface

Implement the architecture neutral prctl() interface for setting the
shadow stack status, this supports setting and reading the current GCS
configuration for the current thread.

Userspace can enable basic GCS functionality and additionally also
support for GCS pushes and arbitrary GCS stores.  It is expected that
this prctl() will be called very early in application startup, for
example by the dynamic linker, and not subsequently adjusted during
normal operation.  Users should carefully note that after enabling GCS
for a thread GCS will become active with no call stack so it is not
normally possible to return from the function that invoked the prctl().

State is stored per thread, enabling GCS for a thread causes a GCS to be
allocated for that thread.

Userspace may lock the current GCS configuration by specifying
PR_SHADOW_STACK_ENABLE_LOCK, this prevents any further changes to the
GCS configuration via any means.

If GCS is not being enabled then all flags other than _LOCK are ignored,
it is not possible to enable stores or pops without enabling GCS.

When disabling the GCS we do not free the allocated stack, this allows
for inspection of the GCS after disabling as part of fault reporting.
Since it is not an expected use case and since it presents some
complications in determining what to do with previously initialsed data
on the GCS attempts to reenable GCS after this are rejected.  This can
be revisted if a use case arises.

Reviewed-by: Thiago Jung Bauermann <[email protected]>
Reviewed-by: Catalin Marinas <[email protected]>
Signed-off-by: Mark Brown <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Catalin Marinas <[email protected]>

Author: broonie

arch/arm64/include/asm/gcs.h

@@ -50,6 +50,9 @@ static inline u64 gcsss2(void)
 	return Xt;
 }
 
+#define PR_SHADOW_STACK_SUPPORTED_STATUS_MASK \
+	(PR_SHADOW_STACK_ENABLE | PR_SHADOW_STACK_WRITE | PR_SHADOW_STACK_PUSH)
+
 #ifdef CONFIG_ARM64_GCS
 
 static inline bool task_gcs_el0_enabled(struct task_struct *task)
@@ -63,6 +66,20 @@ void gcs_preserve_current_state(void);
 unsigned long gcs_alloc_thread_stack(struct task_struct *tsk,
 				     const struct kernel_clone_args *args);
 
+static inline int gcs_check_locked(struct task_struct *task,
+				   unsigned long new_val)
+{
+	unsigned long cur_val = task->thread.gcs_el0_mode;
+
+	cur_val &= task->thread.gcs_el0_locked;
+	new_val &= task->thread.gcs_el0_locked;
+
+	if (cur_val != new_val)
+		return -EBUSY;
+
+	return 0;
+}
+
 #else
 
 static inline bool task_gcs_el0_enabled(struct task_struct *task)
@@ -78,6 +95,11 @@ static inline unsigned long gcs_alloc_thread_stack(struct task_struct *tsk,
 {
 	return -ENOTSUPP;
 }
+static inline int gcs_check_locked(struct task_struct *task,
+				   unsigned long new_val)
+{
+	return 0;
+}
 
 #endif
 

arch/arm64/include/asm/processor.h

@@ -187,6 +187,7 @@ struct thread_struct {
 	u64			por_el0;
 #ifdef CONFIG_ARM64_GCS
 	unsigned int		gcs_el0_mode;
+	unsigned int		gcs_el0_locked;
 	u64			gcspr_el0;
 	u64			gcs_base;
 	u64			gcs_size;

arch/arm64/mm/gcs.c

@@ -109,3 +109,82 @@ void gcs_free(struct task_struct *task)
 	task->thread.gcs_base = 0;
 	task->thread.gcs_size = 0;
 }
+
+int arch_set_shadow_stack_status(struct task_struct *task, unsigned long arg)
+{
+	unsigned long gcs, size;
+	int ret;
+
+	if (!system_supports_gcs())
+		return -EINVAL;
+
+	if (is_compat_thread(task_thread_info(task)))
+		return -EINVAL;
+
+	/* Reject unknown flags */
+	if (arg & ~PR_SHADOW_STACK_SUPPORTED_STATUS_MASK)
+		return -EINVAL;
+
+	ret = gcs_check_locked(task, arg);
+	if (ret != 0)
+		return ret;
+
+	/* If we are enabling GCS then make sure we have a stack */
+	if (arg & PR_SHADOW_STACK_ENABLE &&
+	    !task_gcs_el0_enabled(task)) {
+		/* Do not allow GCS to be reenabled */
+		if (task->thread.gcs_base || task->thread.gcspr_el0)
+			return -EINVAL;
+
+		if (task != current)
+			return -EBUSY;
+
+		size = gcs_size(0);
+		gcs = alloc_gcs(0, size);
+		if (!gcs)
+			return -ENOMEM;
+
+		task->thread.gcspr_el0 = gcs + size - sizeof(u64);
+		task->thread.gcs_base = gcs;
+		task->thread.gcs_size = size;
+		if (task == current)
+			write_sysreg_s(task->thread.gcspr_el0,
+				       SYS_GCSPR_EL0);
+	}
+
+	task->thread.gcs_el0_mode = arg;
+	if (task == current)
+		gcs_set_el0_mode(task);
+
+	return 0;
+}
+
+int arch_get_shadow_stack_status(struct task_struct *task,
+				 unsigned long __user *arg)
+{
+	if (!system_supports_gcs())
+		return -EINVAL;
+
+	if (is_compat_thread(task_thread_info(task)))
+		return -EINVAL;
+
+	return put_user(task->thread.gcs_el0_mode, arg);
+}
+
+int arch_lock_shadow_stack_status(struct task_struct *task,
+				  unsigned long arg)
+{
+	if (!system_supports_gcs())
+		return -EINVAL;
+
+	if (is_compat_thread(task_thread_info(task)))
+		return -EINVAL;
+
+	/*
+	 * We support locking unknown bits so applications can prevent
+	 * any changes in a future proof manner.
+	 */
+	task->thread.gcs_el0_locked |= arg;
+
+	return 0;
+}