diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl
index 227538b0ce80..38db4b1c291a 100644
--- a/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/arch/x86/entry/syscalls/syscall_64.tbl
@@ -373,6 +373,7 @@
449 common futex_waitv sys_futex_waitv
450 common set_mempolicy_home_node sys_set_mempolicy_home_node
451 common cachestat sys_cachestat
+452 64 map_shadow_stack sys_map_shadow_stack
#
# Due to a historical design error, certain syscalls are numbered differently
diff --git a/arch/x86/include/uapi/asm/mman.h b/arch/x86/include/uapi/asm/mman.h
index 5a0256e73f1e..8148bdddbd2c 100644
--- a/arch/x86/include/uapi/asm/mman.h
+++ b/arch/x86/include/uapi/asm/mman.h
@@ -13,6 +13,9 @@
((key) & 0x8 ? VM_PKEY_BIT3 : 0))
#endif
+/* Flags for map_shadow_stack(2) */
+#define SHADOW_STACK_SET_TOKEN (1ULL << 0) /* Set up a restore token in the shadow stack */
+
#include <asm-generic/mman.h>
#endif /* _ASM_X86_MMAN_H */
diff --git a/arch/x86/kernel/shstk.c b/arch/x86/kernel/shstk.c
index 50733a510446..04c37b33a625 100644
--- a/arch/x86/kernel/shstk.c
+++ b/arch/x86/kernel/shstk.c
@@ -17,6 +17,7 @@
#include <linux/compat.h>
#include <linux/sizes.h>
#include <linux/user.h>
+#include <linux/syscalls.h>
#include <asm/msr.h>
#include <asm/fpu/xstate.h>
#include <asm/fpu/types.h>
@@ -71,19 +72,31 @@ static int create_rstor_token(unsigned long ssp, unsigned long *token_addr)
return 0;
}
-static unsigned long alloc_shstk(unsigned long size)
+static unsigned long alloc_shstk(unsigned long addr, unsigned long size,
+ unsigned long token_offset, bool set_res_tok)
{
int flags = MAP_ANONYMOUS | MAP_PRIVATE | MAP_ABOVE4G;
struct mm_struct *mm = current->mm;
- unsigned long addr, unused;
+ unsigned long mapped_addr, unused;
+
+ if (addr)
+ flags |= MAP_FIXED_NOREPLACE;
mmap_write_lock(mm);
- addr = do_mmap(NULL, 0, size, PROT_READ, flags,
- VM_SHADOW_STACK | VM_WRITE, 0, &unused, NULL);
-
+ mapped_addr = do_mmap(NULL, addr, size, PROT_READ, flags,
+ VM_SHADOW_STACK | VM_WRITE, 0, &unused, NULL);
mmap_write_unlock(mm);
- return addr;
+ if (!set_res_tok || IS_ERR_VALUE(mapped_addr))
+ goto out;
+
+ if (create_rstor_token(mapped_addr + token_offset, NULL)) {
+ vm_munmap(mapped_addr, size);
+ return -EINVAL;
+ }
+
+out:
+ return mapped_addr;
}
static unsigned long adjust_shstk_size(unsigned long size)
@@ -134,7 +147,7 @@ static int shstk_setup(void)
return -EOPNOTSUPP;
size = adjust_shstk_size(0);
- addr = alloc_shstk(size);
+ addr = alloc_shstk(0, size, 0, false);
if (IS_ERR_VALUE(addr))
return PTR_ERR((void *)addr);
@@ -178,7 +191,7 @@ unsigned long shstk_alloc_thread_stack(struct task_struct *tsk, unsigned long cl
return 0;
size = adjust_shstk_size(stack_size);
- addr = alloc_shstk(size);
+ addr = alloc_shstk(0, size, 0, false);
if (IS_ERR_VALUE(addr))
return addr;
@@ -398,6 +411,36 @@ static int shstk_disable(void)
return 0;
}
+SYSCALL_DEFINE3(map_shadow_stack, unsigned long, addr, unsigned long, size, unsigned int, flags)
+{
+ bool set_tok = flags & SHADOW_STACK_SET_TOKEN;
+ unsigned long aligned_size;
+
+ if (!cpu_feature_enabled(X86_FEATURE_USER_SHSTK))
+ return -EOPNOTSUPP;
+
+ if (flags & ~SHADOW_STACK_SET_TOKEN)
+ return -EINVAL;
+
+ /* If there isn't space for a token */
+ if (set_tok && size < 8)
+ return -ENOSPC;
+
+ if (addr && addr < SZ_4G)
+ return -ERANGE;
+
+ /*
+ * 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(addr, aligned_size, size, set_tok);
+}
+
long shstk_prctl(struct task_struct *task, int option, unsigned long features)
{
if (option == ARCH_SHSTK_LOCK) {
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 03e3d0121d5e..7f6dc0988197 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -953,6 +953,7 @@ asmlinkage long sys_set_mempolicy_home_node(unsigned long start, unsigned long l
asmlinkage long sys_cachestat(unsigned int fd,
struct cachestat_range __user *cstat_range,
struct cachestat __user *cstat, unsigned int flags);
+asmlinkage long sys_map_shadow_stack(unsigned long addr, unsigned long size, unsigned int flags);
/*
* Architecture-specific system calls
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index 781de7cc6a4e..e137c1385c56 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -274,6 +274,7 @@ 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);