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>
diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index 67111cc..74f8f2a 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -27,40 +27,37 @@
 static inline pte_t ptep_flush_direct(struct mm_struct *mm,
 				      unsigned long addr, pte_t *ptep)
 {
-	int active, count;
 	pte_t old;
 
 	old = *ptep;
 	if (unlikely(pte_val(old) & _PAGE_INVALID))
 		return old;
-	active = (mm == current->active_mm) ? 1 : 0;
-	count = atomic_add_return(0x10000, &mm->context.attach_count);
-	if (MACHINE_HAS_TLB_LC && (count & 0xffff) <= active &&
+	atomic_inc(&mm->context.flush_count);
+	if (MACHINE_HAS_TLB_LC &&
 	    cpumask_equal(mm_cpumask(mm), cpumask_of(smp_processor_id())))
 		__ptep_ipte_local(addr, ptep);
 	else
 		__ptep_ipte(addr, ptep);
-	atomic_sub(0x10000, &mm->context.attach_count);
+	atomic_dec(&mm->context.flush_count);
 	return old;
 }
 
 static inline pte_t ptep_flush_lazy(struct mm_struct *mm,
 				    unsigned long addr, pte_t *ptep)
 {
-	int active, count;
 	pte_t old;
 
 	old = *ptep;
 	if (unlikely(pte_val(old) & _PAGE_INVALID))
 		return old;
-	active = (mm == current->active_mm) ? 1 : 0;
-	count = atomic_add_return(0x10000, &mm->context.attach_count);
-	if ((count & 0xffff) <= active) {
+	atomic_inc(&mm->context.flush_count);
+	if (cpumask_equal(&mm->context.cpu_attach_mask,
+			  cpumask_of(smp_processor_id()))) {
 		pte_val(*ptep) |= _PAGE_INVALID;
 		mm->context.flush_mm = 1;
 	} else
 		__ptep_ipte(addr, ptep);
-	atomic_sub(0x10000, &mm->context.attach_count);
+	atomic_dec(&mm->context.flush_count);
 	return old;
 }
 
@@ -289,7 +286,6 @@
 static inline pmd_t pmdp_flush_direct(struct mm_struct *mm,
 				      unsigned long addr, pmd_t *pmdp)
 {
-	int active, count;
 	pmd_t old;
 
 	old = *pmdp;
@@ -299,36 +295,34 @@
 		__pmdp_csp(pmdp);
 		return old;
 	}
-	active = (mm == current->active_mm) ? 1 : 0;
-	count = atomic_add_return(0x10000, &mm->context.attach_count);
-	if (MACHINE_HAS_TLB_LC && (count & 0xffff) <= active &&
+	atomic_inc(&mm->context.flush_count);
+	if (MACHINE_HAS_TLB_LC &&
 	    cpumask_equal(mm_cpumask(mm), cpumask_of(smp_processor_id())))
 		__pmdp_idte_local(addr, pmdp);
 	else
 		__pmdp_idte(addr, pmdp);
-	atomic_sub(0x10000, &mm->context.attach_count);
+	atomic_dec(&mm->context.flush_count);
 	return old;
 }
 
 static inline pmd_t pmdp_flush_lazy(struct mm_struct *mm,
 				    unsigned long addr, pmd_t *pmdp)
 {
-	int active, count;
 	pmd_t old;
 
 	old = *pmdp;
 	if (pmd_val(old) & _SEGMENT_ENTRY_INVALID)
 		return old;
-	active = (mm == current->active_mm) ? 1 : 0;
-	count = atomic_add_return(0x10000, &mm->context.attach_count);
-	if ((count & 0xffff) <= active) {
+	atomic_inc(&mm->context.flush_count);
+	if (cpumask_equal(&mm->context.cpu_attach_mask,
+			  cpumask_of(smp_processor_id()))) {
 		pmd_val(*pmdp) |= _SEGMENT_ENTRY_INVALID;
 		mm->context.flush_mm = 1;
 	} else if (MACHINE_HAS_IDTE)
 		__pmdp_idte(addr, pmdp);
 	else
 		__pmdp_csp(pmdp);
-	atomic_sub(0x10000, &mm->context.attach_count);
+	atomic_dec(&mm->context.flush_count);
 	return old;
 }