parisc: Fix alignment of pa_tlb_lock in assembly on 32-bit SMP kernel

Qemu for PARISC reported on a 32bit SMP parisc kernel strange failures
about "Not-handled unaligned insn 0x0e8011d6 and 0x0c2011c9."

Those opcodes evaluate to the ldcw() assembly instruction which requires
(on 32bit) an alignment of 16 bytes to ensure atomicity.

As it turns out, qemu is correct and in our assembly code in entry.S and
pacache.S we don't pay attention to the required alignment.

This patch fixes the problem by aligning the lock offset in assembly
code in the same manner as we do in our C-code.

Signed-off-by: Helge Deller <deller@gmx.de>
Cc: <stable@vger.kernel.org> # v4.0+

arch/parisc/kernel/pacache.S

@@ -36,6 +36,7 @@
 #include <asm/assembly.h>
 #include <asm/pgtable.h>
 #include <asm/cache.h>
+#include <asm/ldcw.h>
 #include <linux/linkage.h>
 
 	.text
@@ -333,8 +334,12 @@ ENDPROC_CFI(flush_data_cache_local)
 
 	.macro	tlb_lock	la,flags,tmp
 #ifdef CONFIG_SMP
-	ldil		L%pa_tlb_lock,%r1
-	ldo		R%pa_tlb_lock(%r1),\la
+#if __PA_LDCW_ALIGNMENT > 4
+	load32		pa_tlb_lock + __PA_LDCW_ALIGNMENT-1, \la
+	depi		0,31,__PA_LDCW_ALIGN_ORDER, \la
+#else
+	load32		pa_tlb_lock, \la
+#endif
 	rsm		PSW_SM_I,\flags
 1:	LDCW		0(\la),\tmp
 	cmpib,<>,n	0,\tmp,3f