thp, s390: disable thp for kvm host on s390

This patch is part of the architecture backend for thp on s390.  It
disables thp for kvm hosts, because there is no kvm host hugepage support
so far.  Existing thp mappings are split by follow_page() with FOLL_SPLIT,
and future thp mappings are prevented by setting VM_NOHUGEPAGE in
mm->def_flags.

Signed-off-by: Gerald Schaefer <gerald.schaefer@de.ibm.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Hillf Danton <dhillf@gmail.com>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index 1ca371a..e86a523 100644 (file)
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -787,6 +787,30 @@ void tlb_remove_table(struct mmu_gather *tlb, void *table)
                tlb_table_flush(tlb);
 }
 
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+void thp_split_vma(struct vm_area_struct *vma)
+{
+       unsigned long addr;
+       struct page *page;
+
+       for (addr = vma->vm_start; addr < vma->vm_end; addr += PAGE_SIZE) {
+               page = follow_page(vma, addr, FOLL_SPLIT);
+       }
+}
+
+void thp_split_mm(struct mm_struct *mm)
+{
+       struct vm_area_struct *vma = mm->mmap;
+
+       while (vma != NULL) {
+               thp_split_vma(vma);
+               vma->vm_flags &= ~VM_HUGEPAGE;
+               vma->vm_flags |= VM_NOHUGEPAGE;
+               vma = vma->vm_next;
+       }
+}
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+
 /*
  * switch on pgstes for its userspace process (for kvm)
  */
@@ -824,6 +848,12 @@ int s390_enable_sie(void)
        if (!mm)
                return -ENOMEM;
 
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+       /* split thp mappings and disable thp for future mappings */
+       thp_split_mm(mm);
+       mm->def_flags |= VM_NOHUGEPAGE;
+#endif
+
        /* Now lets check again if something happened */
        task_lock(tsk);
        if (!tsk->mm || atomic_read(&tsk->mm->mm_users) > 1 ||