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, 50 insertions, 0 deletions

diff --git a/sysdeps/unix/sysv/linux/x86_64/getcontext.S b/sysdeps/unix/sysv/linux/x86_64/getcontext.S
index 33347bc02e..84b986ca98 100644
--- a/sysdeps/unix/sysv/linux/x86_64/getcontext.S
+++ b/sysdeps/unix/sysv/linux/x86_64/getcontext.S
@@ -18,6 +18,7 @@
    <http://www.gnu.org/licenses/>.  */
 
 #include <sysdep.h>
+#include <asm/prctl.h>
 
 #include "ucontext_i.h"
 
@@ -53,6 +54,55 @@ ENTRY(__getcontext)
 	leaq	8(%rsp), %rcx		/* Exclude the return address.  */
 	movq	%rcx, oRSP(%rdi)
 
+#if SHSTK_ENABLED
+	/* Check if shadow stack is enabled.  */
+	testl	$X86_FEATURE_1_SHSTK, %fs:FEATURE_1_OFFSET
+	jz	L(no_shstk)
+
+	/* Save RDI in RDX which won't be clobbered by syscall.  */
+	movq	%rdi, %rdx
+
+	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
+
+	/* Restore RDI.  */
+	movq	%rdx, %rdi
+
+L(shadow_stack_bound_recorded):
+	/* Get the current shadow stack pointer.  */
+	rdsspq	%rax
+	/* NB: Save the caller's shadow stack so that we can jump back
+	   to the caller directly.  */
+	addq	$8, %rax
+	movq	%rax, oSSP(%rdx)
+
+	/* Save the current shadow stack base in ucontext.  */
+	movq	%fs:SSP_BASE_OFFSET, %rax
+	movq	%rax, (oSSP + 8)(%rdi)
+
+L(no_shstk):
+#endif
 	/* We have separate floating-point register content memory on the
 	   stack.  We use the __fpregs_mem block in the context.  Set the
 	   links up correctly.  */