ARM: entry: efficiency cleanups

Make the "fast" syscall return path fast again.  The addition of IRQ
tracing and context tracking has made this path grossly inefficient.
We can do much better if these options are enabled if we save the
syscall return code on the stack - we then don't need to save a bunch
of registers around every single callout to C code.

Acked-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>

arch/arm/include/asm/assembler.h

@@ -108,29 +108,37 @@
 	.endm
 #endif
 
-	.macro asm_trace_hardirqs_off
+	.macro asm_trace_hardirqs_off, save=1
 #if defined(CONFIG_TRACE_IRQFLAGS)
+	.if \save
 	stmdb   sp!, {r0-r3, ip, lr}
+	.endif
 	bl	trace_hardirqs_off
+	.if \save
 	ldmia	sp!, {r0-r3, ip, lr}
+	.endif
 #endif
 	.endm
 
-	.macro asm_trace_hardirqs_on, cond=al
+	.macro asm_trace_hardirqs_on, cond=al, save=1
 #if defined(CONFIG_TRACE_IRQFLAGS)
 	/*
 	 * actually the registers should be pushed and pop'd conditionally, but
 	 * after bl the flags are certainly clobbered
 	 */
+	.if \save
 	stmdb   sp!, {r0-r3, ip, lr}
+	.endif
 	bl\cond	trace_hardirqs_on
+	.if \save
 	ldmia	sp!, {r0-r3, ip, lr}
+	.endif
 #endif
 	.endm
 
-	.macro disable_irq
+	.macro disable_irq, save=1
 	disable_irq_notrace
-	asm_trace_hardirqs_off
+	asm_trace_hardirqs_off \save
 	.endm
 
 	.macro enable_irq