arm64/mm: Implement map_shadow_stack()

As discussed extensively in the changelog for the addition of this
syscall on x86 ("x86/shstk: Introduce map_shadow_stack syscall") the
existing mmap() and madvise() syscalls do not map entirely well onto the
security requirements for guarded control stacks since they lead to
windows where memory is allocated but not yet protected or stacks which
are not properly and safely initialised. Instead a new syscall
map_shadow_stack() has been defined which allocates and initialises a
shadow stack page.

Implement this for arm64.  Two flags are provided, allowing applications
to request that the stack be initialised with a valid cap token at the
top of the stack and optionally also an end of stack marker above that.
We support requesting an end of stack marker alone but since this is a
NULL pointer it is indistinguishable from not initialising anything by
itself.

Reviewed-by: Thiago Jung Bauermann <thiago.bauermann@linaro.org>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Acked-by: Yury Khrustalev <yury.khrustalev@arm.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
Link: https://lore.kernel.org/r/20241001-arm64-gcs-v13-24-222b78d87eee@kernel.org
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>

1 files changed, 64 insertions, 0 deletions

diff --git a/arch/arm64/mm/gcs.c b/arch/arm64/mm/gcs.c
index 61a80de6baf8..5c46ec527b1c 100644
--- a/arch/arm64/mm/gcs.c
+++ b/arch/arm64/mm/gcs.c
@@ -68,6 +68,70 @@ unsigned long gcs_alloc_thread_stack(struct task_struct *tsk,
 	return addr;
 }
 
+SYSCALL_DEFINE3(map_shadow_stack, unsigned long, addr, unsigned long, size, unsigned int, flags)
+{
+	unsigned long alloc_size;
+	unsigned long __user *cap_ptr;
+	unsigned long cap_val;
+	int ret = 0;
+	int cap_offset;
+
+	if (!system_supports_gcs())
+		return -EOPNOTSUPP;
+
+	if (flags & ~(SHADOW_STACK_SET_TOKEN | SHADOW_STACK_SET_MARKER))
+		return -EINVAL;
+
+	if (!PAGE_ALIGNED(addr))
+		return -EINVAL;
+
+	if (size == 8 || !IS_ALIGNED(size, 8))
+		return -EINVAL;
+
+	/*
+	 * An overflow would result in attempting to write the restore token
+	 * to the wrong location. Not catastrophic, but just return the right
+	 * error code and block it.
+	 */
+	alloc_size = PAGE_ALIGN(size);
+	if (alloc_size < size)
+		return -EOVERFLOW;
+
+	addr = alloc_gcs(addr, alloc_size);
+	if (IS_ERR_VALUE(addr))
+		return addr;
+
+	/*
+	 * Put a cap token at the end of the allocated region so it
+	 * can be switched to.
+	 */
+	if (flags & SHADOW_STACK_SET_TOKEN) {
+		/* Leave an extra empty frame as a top of stack marker? */
+		if (flags & SHADOW_STACK_SET_MARKER)
+			cap_offset = 2;
+		else
+			cap_offset = 1;
+
+		cap_ptr = (unsigned long __user *)(addr + size -
+						   (cap_offset * sizeof(unsigned long)));
+		cap_val = GCS_CAP(cap_ptr);
+
+		put_user_gcs(cap_val, cap_ptr, &ret);
+		if (ret != 0) {
+			vm_munmap(addr, size);
+			return -EFAULT;
+		}
+
+		/*
+		 * Ensure the new cap is ordered before standard
+		 * memory accesses to the same location.
+		 */
+		gcsb_dsync();
+	}
+
+	return addr;
+}
+
 /*
  * Apply the GCS mode configured for the specified task to the
  * hardware.