1 files changed, 43 insertions, 19 deletions

diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index 87e1a7ca3846..e32389a97030 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -875,13 +875,13 @@ static bool __collapse_huge_page_swapin(struct mm_struct *mm,
 					unsigned long address, pmd_t *pmd,
 					int referenced)
 {
-	pte_t pteval;
 	int swapped_in = 0, ret = 0;
-	struct fault_env fe = {
+	struct vm_fault vmf = {
 		.vma = vma,
 		.address = address,
 		.flags = FAULT_FLAG_ALLOW_RETRY,
 		.pmd = pmd,
+		.pgoff = linear_page_index(vma, address),
 	};
 
 	/* we only decide to swapin, if there is enough young ptes */
@@ -889,19 +889,19 @@ static bool __collapse_huge_page_swapin(struct mm_struct *mm,
 		trace_mm_collapse_huge_page_swapin(mm, swapped_in, referenced, 0);
 		return false;
 	}
-	fe.pte = pte_offset_map(pmd, address);
-	for (; fe.address < address + HPAGE_PMD_NR*PAGE_SIZE;
-			fe.pte++, fe.address += PAGE_SIZE) {
-		pteval = *fe.pte;
-		if (!is_swap_pte(pteval))
+	vmf.pte = pte_offset_map(pmd, address);
+	for (; vmf.address < address + HPAGE_PMD_NR*PAGE_SIZE;
+			vmf.pte++, vmf.address += PAGE_SIZE) {
+		vmf.orig_pte = *vmf.pte;
+		if (!is_swap_pte(vmf.orig_pte))
 			continue;
 		swapped_in++;
-		ret = do_swap_page(&fe, pteval);
+		ret = do_swap_page(&vmf);
 
 		/* do_swap_page returns VM_FAULT_RETRY with released mmap_sem */
 		if (ret & VM_FAULT_RETRY) {
 			down_read(&mm->mmap_sem);
-			if (hugepage_vma_revalidate(mm, address, &fe.vma)) {
+			if (hugepage_vma_revalidate(mm, address, &vmf.vma)) {
 				/* vma is no longer available, don't continue to swapin */
 				trace_mm_collapse_huge_page_swapin(mm, swapped_in, referenced, 0);
 				return false;
@@ -915,10 +915,10 @@ static bool __collapse_huge_page_swapin(struct mm_struct *mm,
 			return false;
 		}
 		/* pte is unmapped now, we need to map it */
-		fe.pte = pte_offset_map(pmd, fe.address);
+		vmf.pte = pte_offset_map(pmd, vmf.address);
 	}
-	fe.pte--;
-	pte_unmap(fe.pte);
+	vmf.pte--;
+	pte_unmap(vmf.pte);
 	trace_mm_collapse_huge_page_swapin(mm, swapped_in, referenced, 1);
 	return true;
 }
@@ -1242,6 +1242,7 @@ static void retract_page_tables(struct address_space *mapping, pgoff_t pgoff)
 	struct vm_area_struct *vma;
 	unsigned long addr;
 	pmd_t *pmd, _pmd;
+	bool deposited = false;
 
 	i_mmap_lock_write(mapping);
 	vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff, pgoff) {
@@ -1266,10 +1267,26 @@ static void retract_page_tables(struct address_space *mapping, pgoff_t pgoff)
 			spinlock_t *ptl = pmd_lock(vma->vm_mm, pmd);
 			/* assume page table is clear */
 			_pmd = pmdp_collapse_flush(vma, addr, pmd);
+			/*
+			 * now deposit the pgtable for arch that need it
+			 * otherwise free it.
+			 */
+			if (arch_needs_pgtable_deposit()) {
+				/*
+				 * The deposit should be visibile only after
+				 * collapse is seen by others.
+				 */
+				smp_wmb();
+				pgtable_trans_huge_deposit(vma->vm_mm, pmd,
+							   pmd_pgtable(_pmd));
+				deposited = true;
+			}
 			spin_unlock(ptl);
 			up_write(&vma->vm_mm->mmap_sem);
-			atomic_long_dec(&vma->vm_mm->nr_ptes);
-			pte_free(vma->vm_mm, pmd_pgtable(_pmd));
+			if (!deposited) {
+				atomic_long_dec(&vma->vm_mm->nr_ptes);
+				pte_free(vma->vm_mm, pmd_pgtable(_pmd));
+			}
 		}
 	}
 	i_mmap_unlock_write(mapping);
@@ -1403,6 +1420,9 @@ static void collapse_shmem(struct mm_struct *mm,
 
 		spin_lock_irq(&mapping->tree_lock);
 
+		slot = radix_tree_lookup_slot(&mapping->page_tree, index);
+		VM_BUG_ON_PAGE(page != radix_tree_deref_slot_protected(slot,
+					&mapping->tree_lock), page);
 		VM_BUG_ON_PAGE(page_mapped(page), page);
 
 		/*
@@ -1423,9 +1443,10 @@ static void collapse_shmem(struct mm_struct *mm,
 		list_add_tail(&page->lru, &pagelist);
 
 		/* Finally, replace with the new page. */
-		radix_tree_replace_slot(slot,
+		radix_tree_replace_slot(&mapping->page_tree, slot,
 				new_page + (index % HPAGE_PMD_NR));
 
+		slot = radix_tree_iter_resume(slot, &iter);
 		index++;
 		continue;
 out_lru:
@@ -1521,9 +1542,10 @@ tree_unlocked:
 			if (!page || iter.index < page->index) {
 				if (!nr_none)
 					break;
-				/* Put holes back where they were */
-				radix_tree_replace_slot(slot, NULL);
 				nr_none--;
+				/* Put holes back where they were */
+				radix_tree_delete(&mapping->page_tree,
+						  iter.index);
 				continue;
 			}
 
@@ -1532,7 +1554,9 @@ tree_unlocked:
 			/* Unfreeze the page. */
 			list_del(&page->lru);
 			page_ref_unfreeze(page, 2);
-			radix_tree_replace_slot(slot, page);
+			radix_tree_replace_slot(&mapping->page_tree,
+						slot, page);
+			slot = radix_tree_iter_resume(slot, &iter);
 			spin_unlock_irq(&mapping->tree_lock);
 			putback_lru_page(page);
 			unlock_page(page);
@@ -1616,8 +1640,8 @@ static void khugepaged_scan_shmem(struct mm_struct *mm,
 		present++;
 
 		if (need_resched()) {
+			slot = radix_tree_iter_resume(slot, &iter);
 			cond_resched_rcu();
-			slot = radix_tree_iter_next(&iter);
 		}
 	}
 	rcu_read_unlock();