mm/memcontrol: support MEMORY_DEVICE_PRIVATE

HMM pages (private or public device pages) are ZONE_DEVICE page and thus
need special handling when it comes to lru or refcount.  This patch make
sure that memcontrol properly handle those when it face them.  Those pages
are use like regular pages in a process address space either as anonymous
page or as file back page.  So from memcg point of view we want to handle
them like regular page for now at least.

Link: http://lkml.kernel.org/r/20170817000548.32038-11-jglisse@redhat.com
Signed-off-by: Jérôme Glisse <jglisse@redhat.com>
Acked-by: Balbir Singh <bsingharora@gmail.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
Cc: Aneesh Kumar <aneesh.kumar@linux.vnet.ibm.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: David Nellans <dnellans@nvidia.com>
Cc: Evgeny Baskakov <ebaskakov@nvidia.com>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Mark Hairgrove <mhairgrove@nvidia.com>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Ross Zwisler <ross.zwisler@linux.intel.com>
Cc: Sherry Cheung <SCheung@nvidia.com>
Cc: Subhash Gutti <sgutti@nvidia.com>
Cc: Bob Liu <liubo95@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

kernel/memremap.c

@@ -516,6 +516,7 @@ void put_zone_device_private_page(struct page *page)
 		__ClearPageWaiters(page);
 
 		page->mapping = NULL;
+		mem_cgroup_uncharge(page);
 
 		page->pgmap->page_free(page, page->pgmap->data);
 	} else if (!count)

mm/memcontrol.c

@@ -4414,12 +4414,13 @@ enum mc_target_type {
 	MC_TARGET_NONE = 0,
 	MC_TARGET_PAGE,
 	MC_TARGET_SWAP,
+	MC_TARGET_DEVICE,
 };
 
 static struct page *mc_handle_present_pte(struct vm_area_struct *vma,
 						unsigned long addr, pte_t ptent)
 {
-	struct page *page = vm_normal_page(vma, addr, ptent);
+	struct page *page = _vm_normal_page(vma, addr, ptent, true);
 
 	if (!page || !page_mapped(page))
 		return NULL;
@@ -4436,7 +4437,7 @@ static struct page *mc_handle_present_pte(struct vm_area_struct *vma,
 	return page;
 }
 
-#ifdef CONFIG_SWAP
+#if defined(CONFIG_SWAP) || defined(CONFIG_DEVICE_PRIVATE)
 static struct page *mc_handle_swap_pte(struct vm_area_struct *vma,
 			pte_t ptent, swp_entry_t *entry)
 {
@@ -4445,6 +4446,23 @@ static struct page *mc_handle_swap_pte(struct vm_area_struct *vma,
 
 	if (!(mc.flags & MOVE_ANON) || non_swap_entry(ent))
 		return NULL;
+
+	/*
+	 * Handle MEMORY_DEVICE_PRIVATE which are ZONE_DEVICE page belonging to
+	 * a device and because they are not accessible by CPU they are store
+	 * as special swap entry in the CPU page table.
+	 */
+	if (is_device_private_entry(ent)) {
+		page = device_private_entry_to_page(ent);
+		/*
+		 * MEMORY_DEVICE_PRIVATE means ZONE_DEVICE page and which have
+		 * a refcount of 1 when free (unlike normal page)
+		 */
+		if (!page_ref_add_unless(page, 1, 1))
+			return NULL;
+		return page;
+	}
+
 	/*
 	 * Because lookup_swap_cache() updates some statistics counter,
 	 * we call find_get_page() with swapper_space directly.
@@ -4605,6 +4623,12 @@ static int mem_cgroup_move_account(struct page *page,
  *   2(MC_TARGET_SWAP): if the swap entry corresponding to this pte is a
  *     target for charge migration. if @target is not NULL, the entry is stored
  *     in target->ent.
+ *   3(MC_TARGET_DEVICE): like MC_TARGET_PAGE  but page is MEMORY_DEVICE_PRIVATE
+ *     (so ZONE_DEVICE page and thus not on the lru). For now we such page is
+ *     charge like a regular page would be as for all intent and purposes it is
+ *     just special memory taking the place of a regular page.
+ *
+ *     See Documentations/vm/hmm.txt and include/linux/hmm.h
  *
  * Called with pte lock held.
  */
@@ -4633,6 +4657,8 @@ static enum mc_target_type get_mctgt_type(struct vm_area_struct *vma,
 		 */
 		if (page->mem_cgroup == mc.from) {
 			ret = MC_TARGET_PAGE;
+			if (is_device_private_page(page))
+				ret = MC_TARGET_DEVICE;
 			if (target)
 				target->page = page;
 		}
@@ -4700,6 +4726,11 @@ static int mem_cgroup_count_precharge_pte_range(pmd_t *pmd,
 
 	ptl = pmd_trans_huge_lock(pmd, vma);
 	if (ptl) {
+		/*
+		 * Note their can not be MC_TARGET_DEVICE for now as we do not
+		 * support transparent huge page with MEMORY_DEVICE_PUBLIC or
+		 * MEMORY_DEVICE_PRIVATE but this might change.
+		 */
 		if (get_mctgt_type_thp(vma, addr, *pmd, NULL) == MC_TARGET_PAGE)
 			mc.precharge += HPAGE_PMD_NR;
 		spin_unlock(ptl);
@@ -4915,6 +4946,14 @@ static int mem_cgroup_move_charge_pte_range(pmd_t *pmd,
 				putback_lru_page(page);
 			}
 			put_page(page);
+		} else if (target_type == MC_TARGET_DEVICE) {
+			page = target.page;
+			if (!mem_cgroup_move_account(page, true,
+						     mc.from, mc.to)) {
+				mc.precharge -= HPAGE_PMD_NR;
+				mc.moved_charge += HPAGE_PMD_NR;
+			}
+			put_page(page);
 		}
 		spin_unlock(ptl);
 		return 0;
@@ -4926,12 +4965,16 @@ static int mem_cgroup_move_charge_pte_range(pmd_t *pmd,
 	pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
 	for (; addr != end; addr += PAGE_SIZE) {
 		pte_t ptent = *(pte++);
+		bool device = false;
 		swp_entry_t ent;
 
 		if (!mc.precharge)
 			break;
 
 		switch (get_mctgt_type(vma, addr, ptent, &target)) {
+		case MC_TARGET_DEVICE:
+			device = true;
+			/* fall through */
 		case MC_TARGET_PAGE:
 			page = target.page;
 			/*
@@ -4942,7 +4985,7 @@ static int mem_cgroup_move_charge_pte_range(pmd_t *pmd,
 			 */
 			if (PageTransCompound(page))
 				goto put;
-			if (isolate_lru_page(page))
+			if (!device && isolate_lru_page(page))
 				goto put;
 			if (!mem_cgroup_move_account(page, false,
 						mc.from, mc.to)) {
@@ -4950,7 +4993,8 @@ static int mem_cgroup_move_charge_pte_range(pmd_t *pmd,
 				/* we uncharge from mc.from later. */
 				mc.moved_charge++;
 			}
-			putback_lru_page(page);
+			if (!device)
+				putback_lru_page(page);
 put:			/* get_mctgt_type() gets the page */
 			put_page(page);
 			break;