x86-64: Improve insn scheduling in SAVE_ARGS_IRQ

In one case, use an address register that was computed earlier (and
with a simpler instruction), thus reducing the risk of a stall.

In the second case, eliminate a branch by using a conditional move (as
is already done in call_softirq and xen_do_hypervisor_callback).

Signed-off-by: Jan Beulich <jbeulich@suse.com>
Link: http://lkml.kernel.org/r/4F4788A50200007800074A26@nat28.tlf.novell.com
Reviewed-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index a20e1cb..211b2e1 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -319,7 +319,7 @@
 	movq %rsp, %rsi
 
 	leaq -RBP(%rsp),%rdi	/* arg1 for handler */
-	testl $3, CS(%rdi)
+	testl $3, CS-RBP(%rsi)
 	je 1f
 	SWAPGS
 	/*
@@ -329,11 +329,10 @@
 	 * moving irq_enter into assembly, which would be too much work)
 	 */
 1:	incl PER_CPU_VAR(irq_count)
-	jne 2f
-	mov PER_CPU_VAR(irq_stack_ptr),%rsp
+	cmovzq PER_CPU_VAR(irq_stack_ptr),%rsp
 	CFI_DEF_CFA_REGISTER	rsi
 
-2:	/* Store previous stack value */
+	/* Store previous stack value */
 	pushq %rsi
 	CFI_ESCAPE	0x0f /* DW_CFA_def_cfa_expression */, 6, \
 			0x77 /* DW_OP_breg7 */, 0, \