Merge tag 'mm-stable-2022-08-03' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull MM updates from Andrew Morton:
 "Most of the MM queue. A few things are still pending.

  Liam's maple tree rework didn't make it. This has resulted in a few
  other minor patch series being held over for next time.

  Multi-gen LRU still isn't merged as we were waiting for mapletree to
  stabilize. The current plan is to merge MGLRU into -mm soon and to
  later reintroduce mapletree, with a view to hopefully getting both
  into 6.1-rc1.

  Summary:

   - The usual batches of cleanups from Baoquan He, Muchun Song, Miaohe
     Lin, Yang Shi, Anshuman Khandual and Mike Rapoport

   - Some kmemleak fixes from Patrick Wang and Waiman Long

   - DAMON updates from SeongJae Park

   - memcg debug/visibility work from Roman Gushchin

   - vmalloc speedup from Uladzislau Rezki

   - more folio conversion work from Matthew Wilcox

   - enhancements for coherent device memory mapping from Alex Sierra

   - addition of shared pages tracking and CoW support for fsdax, from
     Shiyang Ruan

   - hugetlb optimizations from Mike Kravetz

   - Mel Gorman has contributed some pagealloc changes to improve
     latency and realtime behaviour.

   - mprotect soft-dirty checking has been improved by Peter Xu

   - Many other singleton patches all over the place"

 [ XFS merge from hell as per Darrick Wong in

   https://lore.kernel.org/all/YshKnxb4VwXycPO8@magnolia/ ]

* tag 'mm-stable-2022-08-03' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (282 commits)
  tools/testing/selftests/vm/hmm-tests.c: fix build
  mm: Kconfig: fix typo
  mm: memory-failure: convert to pr_fmt()
  mm: use is_zone_movable_page() helper
  hugetlbfs: fix inaccurate comment in hugetlbfs_statfs()
  hugetlbfs: cleanup some comments in inode.c
  hugetlbfs: remove unneeded header file
  hugetlbfs: remove unneeded hugetlbfs_ops forward declaration
  hugetlbfs: use helper macro SZ_1{K,M}
  mm: cleanup is_highmem()
  mm/hmm: add a test for cross device private faults
  selftests: add soft-dirty into run_vmtests.sh
  selftests: soft-dirty: add test for mprotect
  mm/mprotect: fix soft-dirty check in can_change_pte_writable()
  mm: memcontrol: fix potential oom_lock recursion deadlock
  mm/gup.c: fix formatting in check_and_migrate_movable_page()
  xfs: fail dax mount if reflink is enabled on a partition
  mm/memcontrol.c: remove the redundant updating of stats_flush_threshold
  userfaultfd: don't fail on unrecognized features
  hugetlb_cgroup: fix wrong hugetlb cgroup numa stat
  ...

1 files changed, 79 insertions, 11 deletions

diff --git a/mm/gup.c b/mm/gup.c
index e2a39e30756d..732825157430 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -134,7 +134,7 @@ struct folio *try_grab_folio(struct page *page, int refs, unsigned int flags)
 		 * path.
 		 */
 		if (unlikely((flags & FOLL_LONGTERM) &&
-			     !is_pinnable_page(page)))
+			     !is_longterm_pinnable_page(page)))
 			return NULL;
 
 		/*
@@ -953,6 +953,25 @@ static int faultin_page(struct vm_area_struct *vma,
 	}
 
 	ret = handle_mm_fault(vma, address, fault_flags, NULL);
+
+	if (ret & VM_FAULT_COMPLETED) {
+		/*
+		 * With FAULT_FLAG_RETRY_NOWAIT we'll never release the
+		 * mmap lock in the page fault handler. Sanity check this.
+		 */
+		WARN_ON_ONCE(fault_flags & FAULT_FLAG_RETRY_NOWAIT);
+		if (locked)
+			*locked = 0;
+		/*
+		 * We should do the same as VM_FAULT_RETRY, but let's not
+		 * return -EBUSY since that's not reflecting the reality of
+		 * what has happened - we've just fully completed a page
+		 * fault, with the mmap lock released.  Use -EAGAIN to show
+		 * that we want to take the mmap lock _again_.
+		 */
+		return -EAGAIN;
+	}
+
 	if (ret & VM_FAULT_ERROR) {
 		int err = vm_fault_to_errno(ret, *flags);
 
@@ -1179,6 +1198,7 @@ retry:
 			case 0:
 				goto retry;
 			case -EBUSY:
+			case -EAGAIN:
 				ret = 0;
 				fallthrough;
 			case -EFAULT:
@@ -1305,6 +1325,18 @@ retry:
 		return -EINTR;
 
 	ret = handle_mm_fault(vma, address, fault_flags, NULL);
+
+	if (ret & VM_FAULT_COMPLETED) {
+		/*
+		 * NOTE: it's a pity that we need to retake the lock here
+		 * to pair with the unlock() in the callers. Ideally we
+		 * could tell the callers so they do not need to unlock.
+		 */
+		mmap_read_lock(mm);
+		*unlocked = true;
+		return 0;
+	}
+
 	if (ret & VM_FAULT_ERROR) {
 		int err = vm_fault_to_errno(ret, 0);
 
@@ -1370,7 +1402,7 @@ static __always_inline long __get_user_pages_locked(struct mm_struct *mm,
 			/* VM_FAULT_RETRY couldn't trigger, bypass */
 			return ret;
 
-		/* VM_FAULT_RETRY cannot return errors */
+		/* VM_FAULT_RETRY or VM_FAULT_COMPLETED cannot return errors */
 		if (!*locked) {
 			BUG_ON(ret < 0);
 			BUG_ON(ret >= nr_pages);
@@ -1674,7 +1706,7 @@ static long __get_user_pages_locked(struct mm_struct *mm, unsigned long start,
 			goto finish_or_fault;
 
 		if (pages) {
-			pages[i] = virt_to_page(start);
+			pages[i] = virt_to_page((void *)start);
 			if (pages[i])
 				get_page(pages[i]);
 		}
@@ -1883,7 +1915,7 @@ static long check_and_migrate_movable_pages(unsigned long nr_pages,
 	unsigned long isolation_error_count = 0, i;
 	struct folio *prev_folio = NULL;
 	LIST_HEAD(movable_page_list);
-	bool drain_allow = true;
+	bool drain_allow = true, coherent_pages = false;
 	int ret = 0;
 
 	for (i = 0; i < nr_pages; i++) {
@@ -1893,14 +1925,43 @@ static long check_and_migrate_movable_pages(unsigned long nr_pages,
 			continue;
 		prev_folio = folio;
 
-		if (folio_is_pinnable(folio))
+		/*
+		 * Device coherent pages are managed by a driver and should not
+		 * be pinned indefinitely as it prevents the driver moving the
+		 * page. So when trying to pin with FOLL_LONGTERM instead try
+		 * to migrate the page out of device memory.
+		 */
+		if (folio_is_device_coherent(folio)) {
+			/*
+			 * We always want a new GUP lookup with device coherent
+			 * pages.
+			 */
+			pages[i] = 0;
+			coherent_pages = true;
+
+			/*
+			 * Migration will fail if the page is pinned, so convert
+			 * the pin on the source page to a normal reference.
+			 */
+			if (gup_flags & FOLL_PIN) {
+				get_page(&folio->page);
+				unpin_user_page(&folio->page);
+			}
+
+			ret = migrate_device_coherent_page(&folio->page);
+			if (ret)
+				goto unpin_pages;
+
 			continue;
+		}
 
+		if (folio_is_longterm_pinnable(folio))
+			continue;
 		/*
 		 * Try to move out any movable page before pinning the range.
 		 */
 		if (folio_test_hugetlb(folio)) {
-			if (!isolate_huge_page(&folio->page,
+			if (isolate_hugetlb(&folio->page,
 						&movable_page_list))
 				isolation_error_count++;
 			continue;
@@ -1921,7 +1982,8 @@ static long check_and_migrate_movable_pages(unsigned long nr_pages,
 				    folio_nr_pages(folio));
 	}
 
-	if (!list_empty(&movable_page_list) || isolation_error_count)
+	if (!list_empty(&movable_page_list) || isolation_error_count ||
+	    coherent_pages)
 		goto unpin_pages;
 
 	/*
@@ -1931,10 +1993,16 @@ static long check_and_migrate_movable_pages(unsigned long nr_pages,
 	return nr_pages;
 
 unpin_pages:
-	if (gup_flags & FOLL_PIN) {
-		unpin_user_pages(pages, nr_pages);
-	} else {
-		for (i = 0; i < nr_pages; i++)
+	/*
+	 * pages[i] might be NULL if any device coherent pages were found.
+	 */
+	for (i = 0; i < nr_pages; i++) {
+		if (!pages[i])
+			continue;
+
+		if (gup_flags & FOLL_PIN)
+			unpin_user_page(pages[i]);
+		else
 			put_page(pages[i]);
 	}