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, 75 insertions, 0 deletions

diff --git a/sysdeps/unix/sysv/linux/x86_64/__start_context.S b/sysdeps/unix/sysv/linux/x86_64/__start_context.S
index 0bfde5fc31..87de0e5996 100644
--- a/sysdeps/unix/sysv/linux/x86_64/__start_context.S
+++ b/sysdeps/unix/sysv/linux/x86_64/__start_context.S
@@ -18,6 +18,80 @@
 
 #include <sysdep.h>
 
+#if SHSTK_ENABLED
+# include <asm/prctl.h>
+# include "ucontext_i.h"
+
+/* Use CALL to push __start_context onto the new stack as well as the new
+   shadow stack.  RDI points to ucontext:
+   Incoming:
+     __ssp[0]: The original caller's shadow stack pointer.
+     __ssp[1]: The size of the new shadow stack.
+     __ssp[2]: The size of the new shadow stack.
+   Outgoing:
+     __ssp[0]: The new shadow stack pointer.
+     __ssp[1]: The base address of the new shadow stack.
+     __ssp[2]: The size of the new shadow stack.
+ */
+
+ENTRY(__push___start_context)
+	/* Save the pointer to ucontext.  */
+	movq	%rdi, %r9
+	/* Get the original shadow stack pointer.  */
+	rdsspq	%r8
+	/* Save the original stack pointer.  */
+	movq	%rsp, %rdx
+	/* Load the top of the new stack into RSI.  */
+	movq 	oRSP(%rdi), %rsi
+	/* Add 8 bytes to RSI since CALL will push the 8-byte return
+	   address onto stack.  */
+	leaq	8(%rsi), %rsp
+	/* Allocate the new shadow stack.  The size of the new shadow
+	   stack is passed in __ssp[1].  */
+	lea	(oSSP + 8)(%rdi), %RSI_LP
+	movl	$ARCH_CET_ALLOC_SHSTK, %edi
+	movl	$__NR_arch_prctl, %eax
+	/* The new shadow stack base is returned in __ssp[1].  */
+	syscall
+	testq	%rax, %rax
+	jne	L(hlt)		/* This should never happen.  */
+
+	/* Get the size of the new shadow stack.  */
+	movq	8(%rsi), %rdi
+
+	/* Get the base address of the new shadow stack.  */
+	movq	(%rsi), %rsi
+
+	/* Use the restore stoken to restore the new shadow stack.  */
+	rstorssp -8(%rsi, %rdi)
+
+	/* Save the restore token on the original shadow stack.  */
+	saveprevssp
+
+	/* Push the address of "jmp __start_context" onto the new stack
+	   as well as the new shadow stack.  */
+	call	1f
+	jmp	__start_context
+1:
+
+	/* Get the new shadow stack pointer.  */
+	rdsspq	%rdi
+
+	/* Use the restore stoken to restore the original shadow stack.  */
+	rstorssp -8(%r8)
+
+	/* Save the restore token on the new shadow stack.  */
+	saveprevssp
+
+	/* Store the new shadow stack pointer in __ssp[0].  */
+	movq	%rdi, oSSP(%r9)
+
+	/* Restore the original stack.  */
+	mov	%rdx, %rsp
+	ret
+END(__push___start_context)
+#endif
+
 /* This is the helper code which gets called if a function which is
    registered with 'makecontext' returns.  In this case we have to
    install the context listed in the uc_link element of the context
@@ -45,5 +119,6 @@ ENTRY(__start_context)
 	call	HIDDEN_JUMPTARGET(exit)
 	/* The 'exit' call should never return.  In case it does cause
 	   the process to terminate.  */
+L(hlt):
 	hlt
 END(__start_context)