From: Andy Lutomirski <luto@kernel.org>

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 KERNEL_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 <luto@kernel.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Borislav Petkov <bp@suse.de>
Cc: Rik van Riel <riel@redhat.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lkml.kernel.org/r/d350017000eed20922c3b2711a2d9229dc809256.1511497875.git.luto@kernel.org

---
 arch/x86/entry/entry_64.S |   55 ++++++++++++++++++++++++++++++++++++++++++----
 1 file changed, 51 insertions(+), 4 deletions(-)

--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -330,8 +330,24 @@ GLOBAL(entry_SYSCALL_64_after_hwframe)
 	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)
 
@@ -634,10 +650,41 @@ GLOBAL(swapgs_restore_regs_and_return_to
 	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