thp: implement splitting pmd for huge zero page

We can't split huge zero page itself (and it's bug if we try), but we
can split the pmd which points to it.

On splitting the pmd we create a table with all ptes set to normal zero
page.

[akpm@linux-foundation.org: fix build error]
Signed-off-by: NKirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: "H. Peter Anvin" <hpa@linux.intel.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

mm/huge_memory.c

@@ -1616,6 +1616,7 @@ int split_huge_page(struct page *page)
 	struct anon_vma *anon_vma;
 	int ret = 1;
 
+	BUG_ON(is_huge_zero_pfn(page_to_pfn(page)));
 	BUG_ON(!PageAnon(page));
 	anon_vma = page_lock_anon_vma(page);
 	if (!anon_vma)
@@ -2475,24 +2476,64 @@ static int khugepaged(void *none)
 	return 0;
 }
 
+static void __split_huge_zero_page_pmd(struct vm_area_struct *vma,
+		unsigned long haddr, pmd_t *pmd)
+{
+	struct mm_struct *mm = vma->vm_mm;
+	pgtable_t pgtable;
+	pmd_t _pmd;
+	int i;
+
+	pmdp_clear_flush(vma, haddr, pmd);
+	/* leave pmd empty until pte is filled */
+
+	pgtable = pgtable_trans_huge_withdraw(mm);
+	pmd_populate(mm, &_pmd, pgtable);
+
+	for (i = 0; i < HPAGE_PMD_NR; i++, haddr += PAGE_SIZE) {
+		pte_t *pte, entry;
+		entry = pfn_pte(my_zero_pfn(haddr), vma->vm_page_prot);
+		entry = pte_mkspecial(entry);
+		pte = pte_offset_map(&_pmd, haddr);
+		VM_BUG_ON(!pte_none(*pte));
+		set_pte_at(mm, haddr, pte, entry);
+		pte_unmap(pte);
+	}
+	smp_wmb(); /* make pte visible before pmd */
+	pmd_populate(mm, pmd, pgtable);
+}
+
 void __split_huge_page_pmd(struct vm_area_struct *vma, unsigned long address,
 		pmd_t *pmd)
 {
 	struct page *page;
-	unsigned long haddr = address & HPAGE_PMD_MASK;
 	struct mm_struct *mm = vma->vm_mm;
+	unsigned long haddr = address & HPAGE_PMD_MASK;
+	unsigned long mmun_start;	/* For mmu_notifiers */
+	unsigned long mmun_end;		/* For mmu_notifiers */
 
 	BUG_ON(vma->vm_start > haddr || vma->vm_end < haddr + HPAGE_PMD_SIZE);
 
+	mmun_start = haddr;
+	mmun_end   = haddr + HPAGE_PMD_SIZE;
+	mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);
 	spin_lock(&mm->page_table_lock);
 	if (unlikely(!pmd_trans_huge(*pmd))) {
 		spin_unlock(&mm->page_table_lock);
+		mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
+		return;
+	}
+	if (is_huge_zero_pmd(*pmd)) {
+		__split_huge_zero_page_pmd(vma, haddr, pmd);
+		spin_unlock(&mm->page_table_lock);
+		mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
 		return;
 	}
 	page = pmd_page(*pmd);
 	VM_BUG_ON(!page_count(page));
 	get_page(page);
 	spin_unlock(&mm->page_table_lock);
+	mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
 
 	split_huge_page(page);