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>

1 files changed, 2 insertions, 6 deletions

diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index 7b89a7572100..830537432493 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -242,10 +242,8 @@ static void pcpu_prepare_secondary(struct pcpu *pcpu, int cpu)
 {
 	struct lowcore *lc = pcpu->lowcore;
 
-	if (MACHINE_HAS_TLB_LC)
-		cpumask_set_cpu(cpu, &init_mm.context.cpu_attach_mask);
+	cpumask_set_cpu(cpu, &init_mm.context.cpu_attach_mask);
 	cpumask_set_cpu(cpu, mm_cpumask(&init_mm));
-	atomic_inc(&init_mm.context.attach_count);
 	lc->cpu_nr = cpu;
 	lc->spinlock_lockval = arch_spin_lockval(cpu);
 	lc->percpu_offset = __per_cpu_offset[cpu];
@@ -876,10 +874,8 @@ void __cpu_die(unsigned int cpu)
 	while (!pcpu_stopped(pcpu))
 		cpu_relax();
 	pcpu_free_lowcore(pcpu);
-	atomic_dec(&init_mm.context.attach_count);
 	cpumask_clear_cpu(cpu, mm_cpumask(&init_mm));
-	if (MACHINE_HAS_TLB_LC)
-		cpumask_clear_cpu(cpu, &init_mm.context.cpu_attach_mask);
+	cpumask_clear_cpu(cpu, &init_mm.context.cpu_attach_mask);
 }
 
 void __noreturn cpu_die(void)