@@ -8,6 +8,8 @@
#include <asm/types.h>
#include <asm/uaccess.h>
+struct kernel_clone_args;
+
static inline void gcsb_dsync(void)
{
asm volatile(".inst 0xd503227f" : : : "memory");
@@ -58,6 +60,8 @@ static inline bool task_gcs_el0_enabled(struct task_struct *task)
void gcs_set_el0_mode(struct task_struct *task);
void gcs_free(struct task_struct *task);
void gcs_preserve_current_state(void);
+unsigned long gcs_alloc_thread_stack(struct task_struct *tsk,
+ const struct kernel_clone_args *args);
#else
@@ -69,6 +73,11 @@ static inline bool task_gcs_el0_enabled(struct task_struct *task)
static inline void gcs_set_el0_mode(struct task_struct *task) { }
static inline void gcs_free(struct task_struct *task) { }
static inline void gcs_preserve_current_state(void) { }
+static inline unsigned long gcs_alloc_thread_stack(struct task_struct *tsk,
+ const struct kernel_clone_args *args)
+{
+ return -ENOTSUPP;
+}
#endif
@@ -285,9 +285,29 @@ static void flush_gcs(void)
write_sysreg_s(0, SYS_GCSPR_EL0);
}
+static int copy_thread_gcs(struct task_struct *p,
+ const struct kernel_clone_args *args)
+{
+ unsigned long gcs;
+
+ gcs = gcs_alloc_thread_stack(p, args);
+ if (IS_ERR_VALUE(gcs))
+ return PTR_ERR((void *)gcs);
+
+ /* Ensure the current state of the GCS is seen by CoW */
+ gcsb_dsync();
+
+ return 0;
+}
+
#else
static void flush_gcs(void) { }
+static int copy_thread_gcs(struct task_struct *p,
+ const struct kernel_clone_args *args)
+{
+ return 0;
+}
#endif
@@ -369,6 +389,7 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
unsigned long stack_start = args->stack;
unsigned long tls = args->tls;
struct pt_regs *childregs = task_pt_regs(p);
+ int ret;
memset(&p->thread.cpu_context, 0, sizeof(struct cpu_context));
@@ -410,6 +431,10 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
p->thread.uw.tp_value = tls;
p->thread.tpidr2_el0 = 0;
}
+
+ ret = copy_thread_gcs(p, args);
+ if (ret != 0)
+ return ret;
} else {
/*
* A kthread has no context to ERET to, so ensure any buggy
@@ -8,6 +8,82 @@
#include <asm/cpufeature.h>
#include <asm/page.h>
+static unsigned long alloc_gcs(unsigned long addr, unsigned long size,
+ unsigned long token_offset, bool set_res_tok)
+{
+ int flags = MAP_ANONYMOUS | MAP_PRIVATE;
+ struct mm_struct *mm = current->mm;
+ unsigned long mapped_addr, unused;
+
+ if (addr)
+ flags |= MAP_FIXED_NOREPLACE;
+
+ mmap_write_lock(mm);
+ mapped_addr = do_mmap(NULL, addr, size, PROT_READ | PROT_WRITE, flags,
+ VM_SHADOW_STACK, 0, &unused, NULL);
+ mmap_write_unlock(mm);
+
+ return mapped_addr;
+}
+
+static unsigned long gcs_size(unsigned long size)
+{
+ if (size)
+ return PAGE_ALIGN(size);
+
+ /* Allocate RLIMIT_STACK/2 with limits of PAGE_SIZE..2G */
+ size = PAGE_ALIGN(min_t(unsigned long long,
+ rlimit(RLIMIT_STACK) / 2, SZ_2G));
+ return max(PAGE_SIZE, size);
+}
+
+unsigned long gcs_alloc_thread_stack(struct task_struct *tsk,
+ const struct kernel_clone_args *args)
+{
+ unsigned long addr, size;
+
+ /* If the user specified a GCS use it. */
+ if (args->shadow_stack_size) {
+ if (!system_supports_gcs())
+ return (unsigned long)ERR_PTR(-EINVAL);
+
+ size = args->shadow_stack_size;
+
+ if (size < 8)
+ return (unsigned long)ERR_PTR(-EINVAL);
+
+ } else {
+ /*
+ * Otherwise fall back to legacy clone() support and
+ * implicitly allocate a GCS if we need a new one.
+ */
+
+ if (!system_supports_gcs())
+ return 0;
+
+ if (!task_gcs_el0_enabled(tsk))
+ return 0;
+
+ if ((args->flags & (CLONE_VFORK | CLONE_VM)) != CLONE_VM) {
+ tsk->thread.gcspr_el0 = read_sysreg_s(SYS_GCSPR_EL0);
+ return 0;
+ }
+
+ size = args->stack_size;
+ }
+
+ size = gcs_size(size);
+ addr = alloc_gcs(0, size, 0, 0);
+ if (IS_ERR_VALUE(addr))
+ return addr;
+
+ tsk->thread.gcs_base = addr;
+ tsk->thread.gcs_size = size;
+ tsk->thread.gcspr_el0 = addr + size - sizeof(u64);
+
+ return addr;
+}
+
/*
* Apply the GCS mode configured for the specified task to the
* hardware.
When a new thread is created by a thread with GCS enabled the GCS needs to be specified along with the regular stack. clone3() has been extended to support this case, allowing userspace to explicitly request the size for the GCS to be created, but plain clone() is not extensible and existing clone3() users will not specify a size. For compatibility with these cases and also x86 (which did not initially implement clone3() support for shadow stacks) if no GCS is specified we will allocate one thread so when a thread is created which has GCS enabled allocate one for it. We follow the extensively discussed x86 implementation and allocate min(RLIMIT_STACK, 4G). Since the GCS only stores the call stack and not any variables this should be more than sufficient for most applications. GCSs allocated via this mechanism then it will be freed when the thread exits. Signed-off-by: Mark Brown <broonie@kernel.org> --- arch/arm64/include/asm/gcs.h | 9 ++++++ arch/arm64/kernel/process.c | 25 +++++++++++++++ arch/arm64/mm/gcs.c | 76 ++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 110 insertions(+)