x86-64/CET: Extend ucontext_t to save shadow stack

This patch adds a field to ucontext_t to save shadow stack:

1. getcontext and swapcontext are updated to save the caller's shadow
stack pointer and return addresses.
2. setcontext and swapcontext are updated to restore shadow stack and
jump to new context directly.
3. makecontext is updated to allocate a new shadow stack and set the
caller's return address to __start_context.

Since makecontext allocates a new shadow stack when making a new
context and kernel allocates a new shadow stack for clone/fork/vfork
syscalls, we track the current shadow stack base.  In setcontext and
swapcontext, if the target shadow stack base is the same as the current
shadow stack base, we unwind the shadow stack.  Otherwise it is a stack
switch and we look for a restore token.

We enable shadow stack at run-time only if program and all used shared
objects, including dlopened ones, are shadow stack enabled, which means
that they must be compiled with GCC 8 or above and glibc 2.28 or above.
We need to save and restore shadow stack only if shadow stack is enabled.
When caller of getcontext, setcontext, swapcontext and makecontext is
compiled with smaller ucontext_t, shadow stack won't be enabled at
run-time.  We check if shadow stack is enabled before accessing the
extended field in ucontext_t.

Reviewed-by: Carlos O'Donell <carlos@redhat.com>

	* sysdeps/unix/sysv/linux/x86/sys/ucontext.h (ucontext_t): Add
	__ssp.
	* sysdeps/unix/sysv/linux/x86_64/__start_context.S: Include
	<asm/prctl.h> and "ucontext_i.h" when shadow stack is enabled.
	(__push___start_context): New.
	* sysdeps/unix/sysv/linux/x86_64/getcontext.S: Include
	<asm/prctl.h>.
	(__getcontext): Record the current shadow stack base.  Save the
	caller's shadow stack pointer and base.
	* sysdeps/unix/sysv/linux/x86_64/makecontext.c: Include
	<pthread.h>, <libc-pointer-arith.h> and <sys/prctl.h>.
	(__push___start_context): New prototype.
	(__makecontext): Call __push___start_context to allocate a new
	shadow stack, push __start_context onto the new stack as well
	as the new shadow stack.
	* sysdeps/unix/sysv/linux/x86_64/setcontext.S: Include
	<asm/prctl.h>.
	(__setcontext): Restore the target shadow stack.
	* sysdeps/unix/sysv/linux/x86_64/swapcontext.S: Include
	<asm/prctl.h>.
	(__swapcontext): Record the current shadow stack base.  Save
	the caller's shadow stack pointer and base.  Restore the target
	shadow stack.
	* sysdeps/unix/sysv/linux/x86_64/sysdep.h
	(STACK_SIZE_TO_SHADOW_STACK_SIZE_SHIFT): New.
	* sysdeps/unix/sysv/linux/x86_64/ucontext_i.sym (oSSP): New.

1 files changed, 129 insertions, 0 deletions

diff --git a/sysdeps/unix/sysv/linux/x86_64/swapcontext.S b/sysdeps/unix/sysv/linux/x86_64/swapcontext.S
index 1110c479fa..92d3371807 100644
--- a/sysdeps/unix/sysv/linux/x86_64/swapcontext.S
+++ b/sysdeps/unix/sysv/linux/x86_64/swapcontext.S
@@ -18,6 +18,7 @@
    <http://www.gnu.org/licenses/>.  */
 
 #include <sysdep.h>
+#include <asm/prctl.h>
 
 #include "ucontext_i.h"
 
@@ -67,6 +68,7 @@ ENTRY(__swapcontext)
 
 	/* The syscall destroys some registers, save them.  */
 	movq	%rsi, %r12
+	movq	%rdi, %r9
 
 	/* Save the current signal mask and install the new one with
 	   rt_sigprocmask (SIG_BLOCK, newset, oldset,_NSIG/8).  */
@@ -99,6 +101,133 @@ ENTRY(__swapcontext)
 	movq	oR14(%rdx), %r14
 	movq	oR15(%rdx), %r15
 
+#if SHSTK_ENABLED
+	/* Check if shadow stack is enabled.  */
+	testl	$X86_FEATURE_1_SHSTK, %fs:FEATURE_1_OFFSET
+	jz	L(no_shstk)
+
+	xorl	%eax, %eax
+	cmpq	%fs:SSP_BASE_OFFSET, %rax
+	jnz	L(shadow_stack_bound_recorded)
+
+	/* Get the base address and size of the default shadow stack
+	   which must be the current shadow stack since nothing has
+	   been recorded yet.  */
+	sub	$24, %RSP_LP
+	mov	%RSP_LP, %RSI_LP
+	movl	$ARCH_CET_STATUS, %edi
+	movl	$__NR_arch_prctl, %eax
+	syscall
+	testq	%rax, %rax
+	jz	L(continue_no_err)
+
+	/* This should never happen.  */
+	hlt
+
+L(continue_no_err):
+	/* Record the base of the current shadow stack.  */
+	movq	8(%rsp), %rax
+	movq	%rax, %fs:SSP_BASE_OFFSET
+	add	$24, %RSP_LP
+
+L(shadow_stack_bound_recorded):
+        /* If we unwind the stack, we can't undo stack unwinding.  Just
+	   save the target shadow stack pointer as the current shadow
+	   stack pointer.   */
+	movq	oSSP(%rdx), %rcx
+	movq	%rcx, oSSP(%r9)
+
+	/* Save the base of the current shadow stack.  */
+	movq	%fs:SSP_BASE_OFFSET, %rax
+	movq	%rax, (oSSP + 8)(%r9)
+
+	/* If the base of the target shadow stack is the same as the
+	   base of the current shadow stack, we unwind the shadow
+	   stack.  Otherwise it is a stack switch and we look for a
+	   restore token.  */
+	movq	oSSP(%rdx), %rsi
+	movq	%rsi, %rdi
+
+	/* Get the base of the target shadow stack.  */
+	movq	(oSSP + 8)(%rdx), %rcx
+	cmpq	%fs:SSP_BASE_OFFSET, %rcx
+	je	L(unwind_shadow_stack)
+
+L(find_restore_token_loop):
+	/* Look for a restore token.  */
+	movq	-8(%rsi), %rax
+	andq	$-8, %rax
+	cmpq	%rsi, %rax
+	je	L(restore_shadow_stack)
+
+	/* Try the next slot.  */
+	subq	$8, %rsi
+	jmp	L(find_restore_token_loop)
+
+L(restore_shadow_stack):
+        /* The target shadow stack will be restored.  Save the current
+	   shadow stack pointer.  */
+	rdsspq	%rcx
+	movq	%rcx, oSSP(%r9)
+
+	/* Restore the target shadow stack.  */
+	rstorssp -8(%rsi)
+
+	/* Save the restore token on the old shadow stack.  NB: This
+	   restore token may be checked by setcontext or swapcontext
+	   later.  */
+	saveprevssp
+
+	/* Record the new shadow stack base that was switched to.   */
+	movq	(oSSP + 8)(%rdx), %rax
+	movq	%rax, %fs:SSP_BASE_OFFSET
+
+L(unwind_shadow_stack):
+	rdsspq	%rcx
+	subq	%rdi, %rcx
+	je	L(skip_unwind_shadow_stack)
+	negq	%rcx
+	shrq	$3, %rcx
+	movl	$255, %esi
+L(loop):
+	cmpq	%rsi, %rcx
+	cmovb	%rcx, %rsi
+	incsspq	%rsi
+	subq	%rsi, %rcx
+	ja	L(loop)
+
+L(skip_unwind_shadow_stack):
+	/* Setup registers used for passing args.  */
+	movq	oRDI(%rdx), %rdi
+	movq	oRSI(%rdx), %rsi
+	movq	oRCX(%rdx), %rcx
+	movq	oR8(%rdx), %r8
+	movq	oR9(%rdx), %r9
+
+	/* Get the return address set with getcontext.  */
+	movq	oRIP(%rdx), %r10
+
+	/* Setup finally %rdx.  */
+	movq	oRDX(%rdx), %rdx
+
+	/* Check if return address is valid for the case when setcontext
+	   is invoked from __start_context with linked context.  */
+	rdsspq	%rax
+	cmpq	(%rax), %r10
+	/* Clear rax to indicate success.  NB: Don't use xorl to keep
+	   EFLAGS for jne.  */
+	movl	$0, %eax
+	jne	L(jmp)
+	/* Return to the new context if return address valid.  */
+	pushq	%r10
+	ret
+
+L(jmp):
+	/* Jump to the new context directly.  */
+	jmp	*%r10
+
+L(no_shstk):
+#endif
 	/* The following ret should return to the address set with
 	getcontext.  Therefore push the address on the stack.  */
 	movq	oRIP(%rdx), %rcx