x86/entry/64: Return to userspace from the trampoline stack

By itself, this is useless.  It gives us the ability to run some final code
before exit that cannnot run on the kernel stack.  This could include a CR3
switch a la PAGE_TABLE_ISOLATION or some kernel stack erasing, for
example.  (Or even weird things like *changing* which kernel stack gets
used as an ASLR-strengthening mechanism.)

The SYSRET32 path is not covered yet.  It could be in the future or
we could just ignore it and force the slow path if needed.

Signed-off-by: Andy Lutomirski <[email protected]>
Signed-off-by: Thomas Gleixner <[email protected]>
Reviewed-by: Thomas Gleixner <[email protected]>
Reviewed-by: Borislav Petkov <[email protected]>
Cc: Boris Ostrovsky <[email protected]>
Cc: Borislav Petkov <[email protected]>
Cc: Borislav Petkov <[email protected]>
Cc: Brian Gerst <[email protected]>
Cc: Dave Hansen <[email protected]>
Cc: Dave Hansen <[email protected]>
Cc: David Laight <[email protected]>
Cc: Denys Vlasenko <[email protected]>
Cc: Eduardo Valentin <[email protected]>
Cc: Greg KH <[email protected]>
Cc: H. Peter Anvin <[email protected]>
Cc: Josh Poimboeuf <[email protected]>
Cc: Juergen Gross <[email protected]>
Cc: Linus Torvalds <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Rik van Riel <[email protected]>
Cc: Will Deacon <[email protected]>
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Link: https://lkml.kernel.org/r/[email protected]
Signed-off-by: Ingo Molnar <[email protected]>

Author: amluto

arch/x86/entry/entry_64.S

@@ -326,8 +326,24 @@ syscall_return_via_sysret:
 	popq	%rsi	/* skip rcx */
 	popq	%rdx
 	popq	%rsi
+
+	/*
+	 * Now all regs are restored except RSP and RDI.
+	 * Save old stack pointer and switch to trampoline stack.
+	 */
+	movq	%rsp, %rdi
+	movq	PER_CPU_VAR(cpu_tss + TSS_sp0), %rsp
+
+	pushq	RSP-RDI(%rdi)	/* RSP */
+	pushq	(%rdi)		/* RDI */
+
+	/*
+	 * We are on the trampoline stack.  All regs except RDI are live.
+	 * We can do future final exit work right here.
+	 */
+
 	popq	%rdi
-	movq	RSP-ORIG_RAX(%rsp), %rsp
+	popq	%rsp
 	USERGS_SYSRET64
 END(entry_SYSCALL_64)
 
@@ -630,10 +646,41 @@ GLOBAL(swapgs_restore_regs_and_return_to_usermode)
 	ud2
 1:
 #endif
-	SWAPGS
 	POP_EXTRA_REGS
-	POP_C_REGS
-	addq	$8, %rsp	/* skip regs->orig_ax */
+	popq	%r11
+	popq	%r10
+	popq	%r9
+	popq	%r8
+	popq	%rax
+	popq	%rcx
+	popq	%rdx
+	popq	%rsi
+
+	/*
+	 * The stack is now user RDI, orig_ax, RIP, CS, EFLAGS, RSP, SS.
+	 * Save old stack pointer and switch to trampoline stack.
+	 */
+	movq	%rsp, %rdi
+	movq	PER_CPU_VAR(cpu_tss + TSS_sp0), %rsp
+
+	/* Copy the IRET frame to the trampoline stack. */
+	pushq	6*8(%rdi)	/* SS */
+	pushq	5*8(%rdi)	/* RSP */
+	pushq	4*8(%rdi)	/* EFLAGS */
+	pushq	3*8(%rdi)	/* CS */
+	pushq	2*8(%rdi)	/* RIP */
+
+	/* Push user RDI on the trampoline stack. */
+	pushq	(%rdi)
+
+	/*
+	 * We are on the trampoline stack.  All regs except RDI are live.
+	 * We can do future final exit work right here.
+	 */
+
+	/* Restore RDI. */
+	popq	%rdi
+	SWAPGS
 	INTERRUPT_RETURN