s390/mm: simplify the TLB flushing code

ptep_flush_lazy and pmdp_flush_lazy use mm->context.attach_count to
decide between a lazy TLB flush vs an immediate TLB flush. The field
contains two 16-bit counters, the number of CPUs that have the mm
attached and can create TLB entries for it and the number of CPUs in
the middle of a page table update.

The __tlb_flush_asce, ptep_flush_direct and pmdp_flush_direct functions
use the attach counter and a mask check with mm_cpumask(mm) to decide
between a local flush local of the current CPU and a global flush.

For all these functions the decision between lazy vs immediate and
local vs global TLB flush can be based on CPU masks. There are two
masks:  the mm->context.cpu_attach_mask with the CPUs that are actively
using the mm, and the mm_cpumask(mm) with the CPUs that have used the
mm since the last full flush. The decision between lazy vs immediate
flush is based on the mm->context.cpu_attach_mask, to decide between
local vs global flush the mm_cpumask(mm) is used.

With this patch all checks will use the CPU masks, the old counter
mm->context.attach_count with its two 16-bit values is turned into a
single counter mm->context.flush_count that keeps track of the number
of CPUs with incomplete page table updates. The sole user of this
counter is finish_arch_post_lock_switch() which waits for the end of
all page table updates.

Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>

arch/s390/mm/init.c

@@ -118,10 +118,8 @@ void mark_rodata_ro(void)
 
 void __init mem_init(void)
 {
-	if (MACHINE_HAS_TLB_LC)
-		cpumask_set_cpu(0, &init_mm.context.cpu_attach_mask);
+	cpumask_set_cpu(0, &init_mm.context.cpu_attach_mask);
 	cpumask_set_cpu(0, mm_cpumask(&init_mm));
-	atomic_set(&init_mm.context.attach_count, 1);
 
 	set_max_mapnr(max_low_pfn);
         high_memory = (void *) __va(max_low_pfn * PAGE_SIZE);