x86-64: Reduce amount of redundant code generated for invalidate_interruptNN

Previously these up to 32 entry points, consisting of all the
same code except for their very first instruction, consumed 0x70
bytes per instance. Just like for device interrupt entry points,
fold them together so that they all use a single instance of the
code after having pushed their vector indicator (resulting in
0x10 bytes per instance, to retain 16-byte alignment of the
individual entry points).

Signed-off-by: Jan Beulich <jbeulich@suse.com>
Reviewed-by: Andi Kleen <ak@linux.intel.com>
Link: http://lkml.kernel.org/r/4ED4CA230200007800064065@nat28.tlf.novell.com
Signed-off-by: Ingo Molnar <mingo@elte.hu>

arch/x86/kernel/entry_64.S

@@ -951,6 +951,7 @@ END(common_interrupt)
 ENTRY(\sym)
 	INTR_FRAME
 	pushq_cfi $~(\num)
+.Lcommon_\sym:
 	interrupt \do_sym
 	jmp ret_from_intr
 	CFI_ENDPROC
@@ -974,13 +975,21 @@ apicinterrupt X86_PLATFORM_IPI_VECTOR \
 	x86_platform_ipi smp_x86_platform_ipi
 
 #ifdef CONFIG_SMP
-.irp idx,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15, \
+	ALIGN
+	INTR_FRAME
+.irp idx,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15, \
 	16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31
 .if NUM_INVALIDATE_TLB_VECTORS > \idx
-apicinterrupt (INVALIDATE_TLB_VECTOR_START)+\idx \
-	invalidate_interrupt\idx smp_invalidate_interrupt
+ENTRY(invalidate_interrupt\idx)
+	pushq_cfi $~(INVALIDATE_TLB_VECTOR_START+\idx)
+	jmp .Lcommon_invalidate_interrupt0
+	CFI_ADJUST_CFA_OFFSET -8
+END(invalidate_interrupt\idx)
 .endif
 .endr
+	CFI_ENDPROC
+apicinterrupt INVALIDATE_TLB_VECTOR_START, \
+	invalidate_interrupt0, smp_invalidate_interrupt
 #endif
 
 apicinterrupt THRESHOLD_APIC_VECTOR \