x86/entry/64: Clean up and document espfix64 stack setup

The espfix64 setup code was a bit inscrutible and contained an
unnecessary push of RAX.  Remove that push, update all the stack
offsets to match, and document the whole mess.
Reported-By: Borislav Petkov <bp@alien8.de>
Signed-off-by: Andy Lutomirski <luto@kernel.org>
Reviewed-by: Borislav Petkov <bp@suse.de>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/e5459eb10cf1175c8b36b840bc425f210d045f35.1473717910.git.luto@kernel.orgSigned-off-by: Ingo Molnar <mingo@kernel.org>

arch/x86/entry/entry_64.S

@@ -586,27 +586,69 @@ native_irq_return_iret:
 
 #ifdef CONFIG_X86_ESPFIX64
 native_irq_return_ldt:
-	pushq	%rax
-	pushq	%rdi
+	/*
+	 * We are running with user GSBASE.  All GPRs contain their user
+	 * values.  We have a percpu ESPFIX stack that is eight slots
+	 * long (see ESPFIX_STACK_SIZE).  espfix_waddr points to the bottom
+	 * of the ESPFIX stack.
+	 *
+	 * We clobber RAX and RDI in this code.  We stash RDI on the
+	 * normal stack and RAX on the ESPFIX stack.
+	 *
+	 * The ESPFIX stack layout we set up looks like this:
+	 *
+	 * --- top of ESPFIX stack ---
+	 * SS
+	 * RSP
+	 * RFLAGS
+	 * CS
+	 * RIP  <-- RSP points here when we're done
+	 * RAX  <-- espfix_waddr points here
+	 * --- bottom of ESPFIX stack ---
+	 */
+
+	pushq	%rdi				/* Stash user RDI */
 	SWAPGS
 	movq	PER_CPU_VAR(espfix_waddr), %rdi
-	movq	%rax, (0*8)(%rdi)		/* RAX */
-	movq	(2*8)(%rsp), %rax		/* RIP */
+	movq	%rax, (0*8)(%rdi)		/* user RAX */
+	movq	(1*8)(%rsp), %rax		/* user RIP */
 	movq	%rax, (1*8)(%rdi)
-	movq	(3*8)(%rsp), %rax		/* CS */
+	movq	(2*8)(%rsp), %rax		/* user CS */
 	movq	%rax, (2*8)(%rdi)
-	movq	(4*8)(%rsp), %rax		/* RFLAGS */
+	movq	(3*8)(%rsp), %rax		/* user RFLAGS */
 	movq	%rax, (3*8)(%rdi)
-	movq	(6*8)(%rsp), %rax		/* SS */
+	movq	(5*8)(%rsp), %rax		/* user SS */
 	movq	%rax, (5*8)(%rdi)
-	movq	(5*8)(%rsp), %rax		/* RSP */
+	movq	(4*8)(%rsp), %rax		/* user RSP */
 	movq	%rax, (4*8)(%rdi)
-	andl	$0xffff0000, %eax
-	popq	%rdi
+	/* Now RAX == RSP. */
+
+	andl	$0xffff0000, %eax		/* RAX = (RSP & 0xffff0000) */
+	popq	%rdi				/* Restore user RDI */
+
+	/*
+	 * espfix_stack[31:16] == 0.  The page tables are set up such that
+	 * (espfix_stack | (X & 0xffff0000)) points to a read-only alias of
+	 * espfix_waddr for any X.  That is, there are 65536 RO aliases of
+	 * the same page.  Set up RSP so that RSP[31:16] contains the
+	 * respective 16 bits of the /userspace/ RSP and RSP nonetheless
+	 * still points to an RO alias of the ESPFIX stack.
+	 */
 	orq	PER_CPU_VAR(espfix_stack), %rax
 	SWAPGS
 	movq	%rax, %rsp
-	popq	%rax
+
+	/*
+	 * At this point, we cannot write to the stack any more, but we can
+	 * still read.
+	 */
+	popq	%rax				/* Restore user RAX */
+
+	/*
+	 * RSP now points to an ordinary IRET frame, except that the page
+	 * is read-only and RSP[31:16] are preloaded with the userspace
+	 * values.  We can now IRET back to userspace.
+	 */
 	jmp	native_irq_return_iret
 #endif
 END(common_interrupt)