@@ -455,3 +455,4 @@
448 i386 process_mrelease sys_process_mrelease
449 i386 futex_waitv sys_futex_waitv
450 i386 set_mempolicy_home_node sys_set_mempolicy_home_node
+451 i386 map_shadow_stack sys_map_shadow_stack
@@ -372,6 +372,7 @@
448 common process_mrelease sys_process_mrelease
449 common futex_waitv sys_futex_waitv
450 common set_mempolicy_home_node sys_set_mempolicy_home_node
+451 common map_shadow_stack sys_map_shadow_stack
#
# Due to a historical design error, certain syscalls are numbered differently
@@ -26,6 +26,8 @@
((key) & 0x8 ? VM_PKEY_BIT3 : 0))
#endif
+#define SHADOW_STACK_SET_TOKEN 0x1 /* Set up a restore token in the shadow stack */
+
#include <asm-generic/mman.h>
#endif /* _UAPI_ASM_X86_MMAN_H */
@@ -15,6 +15,7 @@
#include <linux/compat.h>
#include <linux/sizes.h>
#include <linux/user.h>
+#include <linux/syscalls.h>
#include <asm/msr.h>
#include <asm/fpu/internal.h>
#include <asm/fpu/xstate.h>
@@ -45,12 +46,14 @@ static int create_rstor_token(bool proc32, unsigned long ssp,
if (write_user_shstk_64((u64 __user *)addr, (u64)ssp))
return -EFAULT;
- *token_addr = addr;
+ if (token_addr)
+ *token_addr = addr;
return 0;
}
-static unsigned long alloc_shstk(unsigned long size)
+static unsigned long alloc_shstk(unsigned long size, unsigned long token_offset,
+ bool set_res_tok)
{
int flags = MAP_ANONYMOUS | MAP_PRIVATE;
struct mm_struct *mm = current->mm;
@@ -61,6 +64,15 @@ static unsigned long alloc_shstk(unsigned long size)
&unused, NULL);
mmap_write_unlock(mm);
+ if (!set_res_tok || IS_ERR_VALUE(addr))
+ goto out;
+
+ if (create_rstor_token(in_ia32_syscall(), addr + token_offset, NULL)) {
+ vm_munmap(addr, size);
+ return -EINVAL;
+ }
+
+out:
return addr;
}
@@ -103,7 +115,7 @@ int shstk_setup(void)
return 1;
size = PAGE_ALIGN(min_t(unsigned long long, rlimit(RLIMIT_STACK), SZ_4G));
- addr = alloc_shstk(size);
+ addr = alloc_shstk(size, size, false);
if (IS_ERR_VALUE(addr))
return 1;
@@ -181,7 +193,7 @@ int shstk_alloc_thread_stack(struct task_struct *tsk, unsigned long clone_flags,
return -EINVAL;
stack_size = PAGE_ALIGN(stack_size);
- addr = alloc_shstk(stack_size);
+ addr = alloc_shstk(stack_size, stack_size, false);
if (IS_ERR_VALUE(addr)) {
shstk->base = 0;
shstk->size = 0;
@@ -380,3 +392,22 @@ int restore_signal_shadow_stack(void)
return err;
}
+
+SYSCALL_DEFINE2(map_shadow_stack, unsigned long, size, unsigned int, flags)
+{
+ unsigned long aligned_size;
+
+ if (!cpu_feature_enabled(X86_FEATURE_SHSTK))
+ return -ENOSYS;
+
+ /*
+ * 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.
+ */
+ aligned_size = PAGE_ALIGN(size);
+ if (aligned_size < size)
+ return -EOVERFLOW;
+
+ return alloc_shstk(aligned_size, size, flags & SHADOW_STACK_SET_TOKEN);
+}
@@ -1060,6 +1060,7 @@ asmlinkage long sys_memfd_secret(unsigned int flags);
asmlinkage long sys_set_mempolicy_home_node(unsigned long start, unsigned long len,
unsigned long home_node,
unsigned long flags);
+asmlinkage long sys_map_shadow_stack(unsigned long size, unsigned int flags);
/*
* Architecture-specific system calls
@@ -887,7 +887,7 @@ __SYSCALL(__NR_futex_waitv, sys_futex_waitv)
__SYSCALL(__NR_set_mempolicy_home_node, sys_set_mempolicy_home_node)
#undef __NR_syscalls
-#define __NR_syscalls 451
+#define __NR_syscalls 452
/*
* 32 bit systems traditionally used different
@@ -380,6 +380,7 @@ COND_SYSCALL(vm86old);
COND_SYSCALL(modify_ldt);
COND_SYSCALL(vm86);
COND_SYSCALL(kexec_file_load);
+COND_SYSCALL(map_shadow_stack);
/* s390 */
COND_SYSCALL(s390_pci_mmio_read);
When operating with shadow stacks enabled, the kernel will automatically allocate shadow stacks for new threads, however in some cases userspace will need additional shadow stacks. The main example of this is the ucontext family of functions, which require userspace allocating and pivoting to userspace managed stacks. Unlike most other user memory permissions, shadow stacks need to be provisioned with special data in order to be useful. They need to be setup with a restore token so that userspace can pivot to them via the RSTORSSP instruction. But, the security design of shadow stack's is that they should not be written to except in limited circumstances. This presents a problem for userspace, as to how userspace can provision this special data, without allowing for the shadow stack to be generally writable. Previously, a new PROT_SHADOW_STACK was attempted, which could be mprotect()ed from RW permissions after the data was provisioned. This was found to not be secure enough, as other thread's could write to the shadow stack during the writable window. The kernel can use a special instruction, WRUSS, to write directly to userspace shadow stacks. So the solution can be that memory can be mapped as shadow stack permissions from the beginning (never generally writable in userspace), and the kernel itself can write the restore token. First, a new madvise() flag was explored, which could operate on the PROT_SHADOW_STACK memory. This had a couple downsides: 1. Extra checks were needed in mprotect() to prevent writable memory from ever becoming PROT_SHADOW_STACK. 2. Extra checks/vma state were needed in the new madvise() to prevent restore tokens being written into the middle of pre-used shadow stacks. It is ideal to prevent restore tokens being added at arbitrary locations, so the check was to make sure the shadow stack had never been written to. 3. It stood out from the rest of the madvise flags, as more of direct action than a hint at future desired behavior. So rather than repurpose two existing syscalls (mmap, madvise) that don't quite fit, just implement a new map_shadow_stack syscall to allow userspace to map and setup new shadow stacks in one step. While ucontext is the primary motivator, userspace may have other unforeseen reasons to setup it's own shadow stacks using the WRSS instruction. Towards this provide a flag so that stacks can be optionally setup securely for the common case of ucontext without enabling WRSS. Or potentially have the kernel set up the shadow stack in some new way. The following example demonstrates how to create a new shadow stack with map_shadow_stack: void *shadow_stack = map_shadow_stack(stack_size, SHADOW_STACK_SET_TOKEN); Signed-off-by: Rick Edgecombe <rick.p.edgecombe@intel.com> --- v1: - New patch (replaces PROT_SHADOW_STACK). arch/x86/entry/syscalls/syscall_32.tbl | 1 + arch/x86/entry/syscalls/syscall_64.tbl | 1 + arch/x86/include/uapi/asm/mman.h | 2 ++ arch/x86/kernel/shstk.c | 39 +++++++++++++++++++++++--- include/linux/syscalls.h | 1 + include/uapi/asm-generic/unistd.h | 2 +- kernel/sys_ni.c | 1 + 7 files changed, 42 insertions(+), 5 deletions(-)