x86-64: Cleanup some assembly entry points

system_call_after_swapgs doesn't really benefit from forcing
alignment from it - quite the opposite, native code needlessly
so far got a big NOP instruction inserted in front of it. Xen
being the only user of the separate entry point can well live
with the branch going to three bytes into a cache line.

The compatibility mode ptregs entry points for one can make use
of the GLOBAL() macro, and should be suitably aligned. Their
shared continuation point (ia32_ptregs_common) otoh doesn't need
to be global at all, but should continue to be properly aligned.

Signed-off-by: Jan Beulich <jbeulich@suse.com>
Reviewed-by: Andi Kleen <ak@linux.intel.com>
Link: http://lkml.kernel.org/r/4ED4CEEA020000780006407D@nat28.tlf.novell.com
Signed-off-by: Ingo Molnar <mingo@elte.hu>

arch/x86/ia32/ia32entry.S

@@ -453,8 +453,8 @@ quiet_ni_syscall:
 	CFI_ENDPROC
 	
 	.macro PTREGSCALL label, func, arg
-	.globl \label
-\label:
+	ALIGN
+GLOBAL(\label)
 	leaq \func(%rip),%rax
 	leaq -ARGOFFSET+8(%rsp),\arg	/* 8 for return address */
 	jmp  ia32_ptregs_common	
@@ -471,7 +471,8 @@ quiet_ni_syscall:
 	PTREGSCALL stub32_vfork, sys_vfork, %rdi
 	PTREGSCALL stub32_iopl, sys_iopl, %rsi
 
-ENTRY(ia32_ptregs_common)
+	ALIGN
+ia32_ptregs_common:
 	popq %r11
 	CFI_ENDPROC
 	CFI_STARTPROC32	simple

arch/x86/kernel/entry_64.S

@@ -465,7 +465,7 @@ ENTRY(system_call)
 	 * after the swapgs, so that it can do the swapgs
 	 * for the guest and jump here on syscall.
 	 */
-ENTRY(system_call_after_swapgs)
+GLOBAL(system_call_after_swapgs)
 
 	movq	%rsp,PER_CPU_VAR(old_rsp)
 	movq	PER_CPU_VAR(kernel_stack),%rsp