x86/entry: Micro-optimize compat fast syscall arg fetch

We're following a 32-bit pointer, and the uaccess code isn't
smart enough to figure out that the access_ok() check isn't
needed.

This saves about three cycles on a cache-hot fast syscall.

Signed-off-by: Andy Lutomirski <luto@kernel.org>
Cc: Andy Lutomirski <luto@amacapital.net>
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: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Link: http://lkml.kernel.org/r/bdff034e2f23c5eb974c760cf494cb5bddce8f29.1444091585.git.luto@kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

arch/x86/entry/common.c

@@ -394,8 +394,20 @@ __visible long do_fast_syscall_32(struct pt_regs *regs)
 	 * WARNING: We are in CONTEXT_USER and RCU isn't paying attention!
 	 */
 	local_irq_enable();
-	if (get_user(*(u32 *)&regs->cx,
-		     (u32 __user __force *)(unsigned long)(u32)regs->sp)) {
+	if (
+#ifdef CONFIG_X86_64
+		/*
+		 * Micro-optimization: the pointer we're following is explicitly
+		 * 32 bits, so it can't be out of range.
+		 */
+		__get_user(*(u32 *)&regs->cx,
+			    (u32 __user __force *)(unsigned long)(u32)regs->sp)
+#else
+		get_user(*(u32 *)&regs->cx,
+			 (u32 __user __force *)(unsigned long)(u32)regs->sp)
+#endif
+		) {
+
 		/* User code screwed up. */
 		local_irq_disable();
 		regs->ax = -EFAULT;