i386: Enable CET support in ucontext functions

1. getcontext and swapcontext are updated to save the caller's shadow
stack pointer and return address.
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 the helper code, L(exitcode).
4. Since we no longer save and restore EAX, ECX and EDX in getcontext,
setcontext and swapcontext, we can use them as scratch register slots
to enable CET in ucontext functions.

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.

Tested on i386 CET/non-CET machines.

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

1 files changed, 123 insertions, 0 deletions

diff --git a/sysdeps/unix/sysv/linux/i386/makecontext.S b/sysdeps/unix/sysv/linux/i386/makecontext.S
index ad9ce5f977..91009675d1 100644
--- a/sysdeps/unix/sysv/linux/i386/makecontext.S
+++ b/sysdeps/unix/sysv/linux/i386/makecontext.S
@@ -18,6 +18,7 @@
    <https://www.gnu.org/licenses/>.  */
 
 #include <sysdep.h>
+#include <asm/prctl.h>
 
 #include "ucontext_i.h"
 
@@ -68,6 +69,127 @@ ENTRY(__makecontext)
 	jnz	1b
 2:
 
+#if SHSTK_ENABLED
+	/* Check if Shadow Stack is enabled.  */
+	testl	$X86_FEATURE_1_SHSTK, %gs:FEATURE_1_OFFSET
+	jz	L(skip_ssp)
+
+	/* Reload the pointer to ucontext.  */
+	movl	4(%esp), %eax
+
+	/* Shadow stack is enabled.  We need to allocate a new shadow
+	   stack.  */
+	subl	oSS_SP(%eax), %edx
+	shrl	$STACK_SIZE_TO_SHADOW_STACK_SIZE_SHIFT, %edx
+
+	/* Align shadow stack size to 8 bytes.  */
+	addl	$7, %edx
+	andl	$-8, %edx
+
+	/* Store shadow stack size in __ssp[2].  */
+	movl	%edx, (oSSP + 8)(%eax)
+
+	/* Save ESI in the second scratch register slot.  */
+	movl	%esi, oSCRATCH2(%eax)
+	/* Save EDI in the third scratch register slot.  */
+	movl	%edi, oSCRATCH3(%eax)
+
+	/* Save the pointer to ucontext.  */
+	movl	%eax, %edi
+
+	/* Get the original shadow stack pointer.  */
+	rdsspd	%esi
+
+	/* Align the saved original shadow stack pointer to the next
+	   8 byte aligned boundary.  */
+	andl	$-8, %esi
+
+	/* Load the top of the new stack into EDX.  */
+	movl	oESP(%eax), %edx
+
+	/* We need to terminate the FDE here because the unwinder looks
+	   at ra-1 for unwind information.  */
+	cfi_endproc
+
+	/* Swap the original stack pointer with the top of the new
+	   stack.  */
+	xchgl	%esp, %edx
+
+	/* Add 4 bytes since CALL will push the 4-byte return address
+	   onto stack.  */
+	addl	$4, %esp
+
+	/* Allocate the new shadow stack.  Save EBX in the first scratch
+	   register slot.  */
+	movl	%ebx, oSCRATCH1(%eax)
+
+	/* CET syscall takes 64-bit sizes.  */
+	subl	$16, %esp
+	movl	(oSSP + 8)(%eax), %ecx
+	movl	%ecx, (%esp)
+	movl	$0, 4(%esp)
+	movl	%ecx, 8(%esp)
+	movl	$0, 12(%esp)
+	movl	%esp, %ecx
+
+	movl	$ARCH_CET_ALLOC_SHSTK, %ebx
+	movl	$__NR_arch_prctl, %eax
+	ENTER_KERNEL
+	testl	%eax, %eax
+	jne	L(hlt)		/* This should never happen.  */
+
+	/* Copy the base address of the new shadow stack to __ssp[1].  */
+	movl	(%esp), %eax
+	movl	%eax, (oSSP + 4)(%edi)
+
+	addl	$16, %esp
+
+	/* Restore EBX from the first scratch register slot.  */
+	movl	oSCRATCH1(%edi), %ebx
+
+	/* Get the size of the new shadow stack.  */
+	movl	(oSSP + 8)(%edi), %ecx
+
+	/* Use the restore stoken to restore the new shadow stack.  */
+	rstorssp -8(%eax, %ecx)
+
+	/* Save the restore token at the next 8 byte aligned boundary
+	   on the original shadow stack.  */
+	saveprevssp
+
+	/* Push the address of "jmp exitcode" onto the new stack as
+	   well as the new shadow stack.  */
+	call	1f
+	jmp	L(exitcode)
+1:
+
+	/* Get the new shadow stack pointer.  */
+	rdsspd	%eax
+
+	/* Use the restore stoken to restore the original shadow stack.  */
+	rstorssp -8(%esi)
+
+	/* Save the restore token on the new shadow stack.  */
+	saveprevssp
+
+	/* Store the new shadow stack pointer in __ssp[0].  */
+	movl	%eax, oSSP(%edi)
+
+	/* Restore the original stack.  */
+	mov	%edx, %esp
+
+	cfi_startproc
+
+	/* Restore ESI from the second scratch register slot.  */
+	movl	oSCRATCH2(%edi), %esi
+	/* Restore EDI from the third scratch register slot.  */
+	movl	oSCRATCH3(%edi), %edi
+
+	ret
+
+L(skip_ssp):
+#endif
+
 	/* If the function we call returns we must continue with the
 	   context which is given in the uc_link element.  To do this
 	   set the return address for the function the user provides
@@ -123,6 +245,7 @@ L(call_exit):
 	call	HIDDEN_JUMPTARGET(exit)
 	/* The 'exit' call should never return.  In case it does cause
 	   the process to terminate.  */
+L(hlt):
 	hlt
 	cfi_startproc
 END(__makecontext)