Merge tag 'mm-hotfixes-stable-2023-03-14-16-51' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull misc fixes from Andrew Morton:
 "Eleven hotfixes.

  Four of these are cc:stable and the remainder address post-6.2 issues
  or aren't considered suitable for backporting.

  Seven of these fixes are for MM"

* tag 'mm-hotfixes-stable-2023-03-14-16-51' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm:
  mm/damon/paddr: fix folio_nr_pages() after folio_put() in damon_pa_mark_accessed_or_deactivate()
  mm/damon/paddr: fix folio_size() call after folio_put() in damon_pa_young()
  ocfs2: fix data corruption after failed write
  migrate_pages: try migrate in batch asynchronously firstly
  migrate_pages: move split folios processing out of migrate_pages_batch()
  migrate_pages: fix deadlock in batched migration
  .mailmap: add Alexandre Ghiti personal email address
  mailmap: correct Dikshita Agarwal's Qualcomm email address
  mailmap: updates for Jarkko Sakkinen
  mm/userfaultfd: propagate uffd-wp bit when PTE-mapping the huge zeropage
  mm: teach mincore_hugetlb about pte markers

6 files changed, 122 insertions, 99 deletions

diff --git a/.mailmap b/.mailmap
index 424564f40733..86a6307dd824 100644
--- a/.mailmap
+++ b/.mailmap
@@ -28,6 +28,7 @@ Alexander Lobakin <alobakin@pm.me> <bloodyreaper@yandex.ru>
 Alexander Mikhalitsyn <alexander@mihalicyn.com> <alexander.mikhalitsyn@virtuozzo.com>
 Alexander Mikhalitsyn <alexander@mihalicyn.com> <aleksandr.mikhalitsyn@canonical.com>
 Alexandre Belloni <alexandre.belloni@bootlin.com> <alexandre.belloni@free-electrons.com>
+Alexandre Ghiti <alex@ghiti.fr> <alexandre.ghiti@canonical.com>
 Alexei Starovoitov <ast@kernel.org> <alexei.starovoitov@gmail.com>
 Alexei Starovoitov <ast@kernel.org> <ast@fb.com>
 Alexei Starovoitov <ast@kernel.org> <ast@plumgrid.com>
@@ -121,7 +122,7 @@ Dengcheng Zhu <dzhu@wavecomp.com> <dengcheng.zhu@gmail.com>
 Dengcheng Zhu <dzhu@wavecomp.com> <dengcheng.zhu@imgtec.com>
 Dengcheng Zhu <dzhu@wavecomp.com> <dengcheng.zhu@mips.com>
 <dev.kurt@vandijck-laurijssen.be> <kurt.van.dijck@eia.be>
-Dikshita Agarwal <dikshita@qti.qualcomm.com> <dikshita@codeaurora.org>
+Dikshita Agarwal <quic_dikshita@quicinc.com> <dikshita@codeaurora.org>
 Dmitry Baryshkov <dbaryshkov@gmail.com>
 Dmitry Baryshkov <dbaryshkov@gmail.com> <[dbaryshkov@gmail.com]>
 Dmitry Baryshkov <dbaryshkov@gmail.com> <dmitry_baryshkov@mentor.com>
@@ -194,6 +195,7 @@ Jan Glauber <jan.glauber@gmail.com> <jang@linux.vnet.ibm.com>
 Jan Glauber <jan.glauber@gmail.com> <jglauber@cavium.com>
 Jarkko Sakkinen <jarkko@kernel.org> <jarkko.sakkinen@linux.intel.com>
 Jarkko Sakkinen <jarkko@kernel.org> <jarkko@profian.com>
+Jarkko Sakkinen <jarkko@kernel.org> <jarkko.sakkinen@tuni.fi>
 Jason Gunthorpe <jgg@ziepe.ca> <jgg@mellanox.com>
 Jason Gunthorpe <jgg@ziepe.ca> <jgg@nvidia.com>
 Jason Gunthorpe <jgg@ziepe.ca> <jgunthorpe@obsidianresearch.com>
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index 1d65f6ef00ca..0394505fdce3 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -1977,11 +1977,26 @@ int ocfs2_write_end_nolock(struct address_space *mapping,
 	}
 
 	if (unlikely(copied < len) && wc->w_target_page) {
+		loff_t new_isize;
+
 		if (!PageUptodate(wc->w_target_page))
 			copied = 0;
 
-		ocfs2_zero_new_buffers(wc->w_target_page, start+copied,
-				       start+len);
+		new_isize = max_t(loff_t, i_size_read(inode), pos + copied);
+		if (new_isize > page_offset(wc->w_target_page))
+			ocfs2_zero_new_buffers(wc->w_target_page, start+copied,
+					       start+len);
+		else {
+			/*
+			 * When page is fully beyond new isize (data copy
+			 * failed), do not bother zeroing the page. Invalidate
+			 * it instead so that writeback does not get confused
+			 * put page & buffer dirty bits into inconsistent
+			 * state.
+			 */
+			block_invalidate_folio(page_folio(wc->w_target_page),
+						0, PAGE_SIZE);
+		}
 	}
 	if (wc->w_target_page)
 		flush_dcache_page(wc->w_target_page);
diff --git a/mm/damon/paddr.c b/mm/damon/paddr.c
index 6c655d9b5639..dd9c33fbe805 100644
--- a/mm/damon/paddr.c
+++ b/mm/damon/paddr.c
@@ -130,7 +130,6 @@ static bool damon_pa_young(unsigned long paddr, unsigned long *folio_sz)
 			accessed = false;
 		else
 			accessed = true;
-		folio_put(folio);
 		goto out;
 	}
 
@@ -144,10 +143,10 @@ static bool damon_pa_young(unsigned long paddr, unsigned long *folio_sz)
 
 	if (need_lock)
 		folio_unlock(folio);
-	folio_put(folio);
 
 out:
 	*folio_sz = folio_size(folio);
+	folio_put(folio);
 	return accessed;
 }
 
@@ -281,8 +280,8 @@ static inline unsigned long damon_pa_mark_accessed_or_deactivate(
 			folio_mark_accessed(folio);
 		else
 			folio_deactivate(folio);
-		folio_put(folio);
 		applied += folio_nr_pages(folio);
+		folio_put(folio);
 	}
 	return applied * PAGE_SIZE;
 }
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 4fc43859e59a..032fb0ef9cd1 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -2037,7 +2037,7 @@ static void __split_huge_zero_page_pmd(struct vm_area_struct *vma,
 {
 	struct mm_struct *mm = vma->vm_mm;
 	pgtable_t pgtable;
-	pmd_t _pmd;
+	pmd_t _pmd, old_pmd;
 	int i;
 
 	/*
@@ -2048,7 +2048,7 @@ static void __split_huge_zero_page_pmd(struct vm_area_struct *vma,
 	 *
 	 * See Documentation/mm/mmu_notifier.rst
 	 */
-	pmdp_huge_clear_flush(vma, haddr, pmd);
+	old_pmd = pmdp_huge_clear_flush(vma, haddr, pmd);
 
 	pgtable = pgtable_trans_huge_withdraw(mm, pmd);
 	pmd_populate(mm, &_pmd, pgtable);
@@ -2057,6 +2057,8 @@ static void __split_huge_zero_page_pmd(struct vm_area_struct *vma,
 		pte_t *pte, entry;
 		entry = pfn_pte(my_zero_pfn(haddr), vma->vm_page_prot);
 		entry = pte_mkspecial(entry);
+		if (pmd_uffd_wp(old_pmd))
+			entry = pte_mkuffd_wp(entry);
 		pte = pte_offset_map(&_pmd, haddr);
 		VM_BUG_ON(!pte_none(*pte));
 		set_pte_at(mm, haddr, pte, entry);
diff --git a/mm/migrate.c b/mm/migrate.c
index 98f1c11197a8..db3f154446af 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -1112,9 +1112,8 @@ static void migrate_folio_done(struct folio *src,
 /* Obtain the lock on page, remove all ptes. */
 static int migrate_folio_unmap(new_page_t get_new_page, free_page_t put_new_page,
 			       unsigned long private, struct folio *src,
-			       struct folio **dstp, int force, bool avoid_force_lock,
-			       enum migrate_mode mode, enum migrate_reason reason,
-			       struct list_head *ret)
+			       struct folio **dstp, enum migrate_mode mode,
+			       enum migrate_reason reason, struct list_head *ret)
 {
 	struct folio *dst;
 	int rc = -EAGAIN;
@@ -1144,7 +1143,7 @@ static int migrate_folio_unmap(new_page_t get_new_page, free_page_t put_new_page
 	dst->private = NULL;
 
 	if (!folio_trylock(src)) {
-		if (!force || mode == MIGRATE_ASYNC)
+		if (mode == MIGRATE_ASYNC)
 			goto out;
 
 		/*
@@ -1163,17 +1162,6 @@ static int migrate_folio_unmap(new_page_t get_new_page, free_page_t put_new_page
 		if (current->flags & PF_MEMALLOC)
 			goto out;
 
-		/*
-		 * We have locked some folios and are going to wait to lock
-		 * this folio.  To avoid a potential deadlock, let's bail
-		 * out and not do that. The locked folios will be moved and
-		 * unlocked, then we can wait to lock this folio.
-		 */
-		if (avoid_force_lock) {
-			rc = -EDEADLOCK;
-			goto out;
-		}
-
 		folio_lock(src);
 	}
 	locked = true;
@@ -1193,8 +1181,6 @@ static int migrate_folio_unmap(new_page_t get_new_page, free_page_t put_new_page
 			rc = -EBUSY;
 			goto out;
 		}
-		if (!force)
-			goto out;
 		folio_wait_writeback(src);
 	}
 
@@ -1253,7 +1239,7 @@ static int migrate_folio_unmap(new_page_t get_new_page, free_page_t put_new_page
 		/* Establish migration ptes */
 		VM_BUG_ON_FOLIO(folio_test_anon(src) &&
 			       !folio_test_ksm(src) && !anon_vma, src);
-		try_to_migrate(src, TTU_BATCH_FLUSH);
+		try_to_migrate(src, mode == MIGRATE_ASYNC ? TTU_BATCH_FLUSH : 0);
 		page_was_mapped = 1;
 	}
 
@@ -1267,7 +1253,7 @@ out:
 	 * A folio that has not been unmapped will be restored to
 	 * right list unless we want to retry.
 	 */
-	if (rc == -EAGAIN || rc == -EDEADLOCK)
+	if (rc == -EAGAIN)
 		ret = NULL;
 
 	migrate_folio_undo_src(src, page_was_mapped, anon_vma, locked, ret);
@@ -1508,6 +1494,9 @@ static inline int try_split_folio(struct folio *folio, struct list_head *split_f
 #define NR_MAX_BATCHED_MIGRATION	512
 #endif
 #define NR_MAX_MIGRATE_PAGES_RETRY	10
+#define NR_MAX_MIGRATE_ASYNC_RETRY	3
+#define NR_MAX_MIGRATE_SYNC_RETRY					\
+	(NR_MAX_MIGRATE_PAGES_RETRY - NR_MAX_MIGRATE_ASYNC_RETRY)
 
 struct migrate_pages_stats {
 	int nr_succeeded;	/* Normal and large folios migrated successfully, in
@@ -1618,13 +1607,19 @@ static int migrate_hugetlbs(struct list_head *from, new_page_t get_new_page,
 /*
  * migrate_pages_batch() first unmaps folios in the from list as many as
  * possible, then move the unmapped folios.
+ *
+ * We only batch migration if mode == MIGRATE_ASYNC to avoid to wait a
+ * lock or bit when we have locked more than one folio.  Which may cause
+ * deadlock (e.g., for loop device).  So, if mode != MIGRATE_ASYNC, the
+ * length of the from list must be <= 1.
  */
 static int migrate_pages_batch(struct list_head *from, new_page_t get_new_page,
 		free_page_t put_new_page, unsigned long private,
 		enum migrate_mode mode, int reason, struct list_head *ret_folios,
-		struct migrate_pages_stats *stats)
+		struct list_head *split_folios, struct migrate_pages_stats *stats,
+		int nr_pass)
 {
-	int retry;
+	int retry = 1;
 	int large_retry = 1;
 	int thp_retry = 1;
 	int nr_failed = 0;
@@ -1634,21 +1629,15 @@ static int migrate_pages_batch(struct list_head *from, new_page_t get_new_page,
 	bool is_large = false;
 	bool is_thp = false;
 	struct folio *folio, *folio2, *dst = NULL, *dst2;
-	int rc, rc_saved, nr_pages;
-	LIST_HEAD(split_folios);
+	int rc, rc_saved = 0, nr_pages;
 	LIST_HEAD(unmap_folios);
 	LIST_HEAD(dst_folios);
 	bool nosplit = (reason == MR_NUMA_MISPLACED);
-	bool no_split_folio_counting = false;
-	bool avoid_force_lock;
 
-retry:
-	rc_saved = 0;
-	avoid_force_lock = false;
-	retry = 1;
-	for (pass = 0;
-	     pass < NR_MAX_MIGRATE_PAGES_RETRY && (retry || large_retry);
-	     pass++) {
+	VM_WARN_ON_ONCE(mode != MIGRATE_ASYNC &&
+			!list_empty(from) && !list_is_singular(from));
+
+	for (pass = 0; pass < nr_pass && (retry || large_retry); pass++) {
 		retry = 0;
 		large_retry = 0;
 		thp_retry = 0;
@@ -1679,7 +1668,7 @@ retry:
 			if (!thp_migration_supported() && is_thp) {
 				nr_large_failed++;
 				stats->nr_thp_failed++;
-				if (!try_split_folio(folio, &split_folios)) {
+				if (!try_split_folio(folio, split_folios)) {
 					stats->nr_thp_split++;
 					continue;
 				}
@@ -1689,15 +1678,13 @@ retry:
 			}
 
 			rc = migrate_folio_unmap(get_new_page, put_new_page, private,
-						 folio, &dst, pass > 2, avoid_force_lock,
-						 mode, reason, ret_folios);
+						 folio, &dst, mode, reason, ret_folios);
 			/*
 			 * The rules are:
 			 *	Success: folio will be freed
 			 *	Unmap: folio will be put on unmap_folios list,
 			 *	       dst folio put on dst_folios list
 			 *	-EAGAIN: stay on the from list
-			 *	-EDEADLOCK: stay on the from list
 			 *	-ENOMEM: stay on the from list
 			 *	Other errno: put on ret_folios list
 			 */
@@ -1712,7 +1699,7 @@ retry:
 					stats->nr_thp_failed += is_thp;
 					/* Large folio NUMA faulting doesn't split to retry. */
 					if (!nosplit) {
-						int ret = try_split_folio(folio, &split_folios);
+						int ret = try_split_folio(folio, split_folios);
 
 						if (!ret) {
 							stats->nr_thp_split += is_thp;
@@ -1729,18 +1716,11 @@ retry:
 							break;
 						}
 					}
-				} else if (!no_split_folio_counting) {
+				} else {
 					nr_failed++;
 				}
 
 				stats->nr_failed_pages += nr_pages + nr_retry_pages;
-				/*
-				 * There might be some split folios of fail-to-migrate large
-				 * folios left in split_folios list. Move them to ret_folios
-				 * list so that they could be put back to the right list by
-				 * the caller otherwise the folio refcnt will be leaked.
-				 */
-				list_splice_init(&split_folios, ret_folios);
 				/* nr_failed isn't updated for not used */
 				nr_large_failed += large_retry;
 				stats->nr_thp_failed += thp_retry;
@@ -1749,19 +1729,11 @@ retry:
 					goto out;
 				else
 					goto move;
-			case -EDEADLOCK:
-				/*
-				 * The folio cannot be locked for potential deadlock.
-				 * Go move (and unlock) all locked folios.  Then we can
-				 * try again.
-				 */
-				rc_saved = rc;
-				goto move;
 			case -EAGAIN:
 				if (is_large) {
 					large_retry++;
 					thp_retry += is_thp;
-				} else if (!no_split_folio_counting) {
+				} else {
 					retry++;
 				}
 				nr_retry_pages += nr_pages;
@@ -1771,11 +1743,6 @@ retry:
 				stats->nr_thp_succeeded += is_thp;
 				break;
 			case MIGRATEPAGE_UNMAP:
-				/*
-				 * We have locked some folios, don't force lock
-				 * to avoid deadlock.
-				 */
-				avoid_force_lock = true;
 				list_move_tail(&folio->lru, &unmap_folios);
 				list_add_tail(&dst->lru, &dst_folios);
 				break;
@@ -1789,7 +1756,7 @@ retry:
 				if (is_large) {
 					nr_large_failed++;
 					stats->nr_thp_failed += is_thp;
-				} else if (!no_split_folio_counting) {
+				} else {
 					nr_failed++;
 				}
 
@@ -1807,9 +1774,7 @@ move:
 	try_to_unmap_flush();
 
 	retry = 1;
-	for (pass = 0;
-	     pass < NR_MAX_MIGRATE_PAGES_RETRY && (retry || large_retry);
-	     pass++) {
+	for (pass = 0; pass < nr_pass && (retry || large_retry); pass++) {
 		retry = 0;
 		large_retry = 0;
 		thp_retry = 0;
@@ -1838,7 +1803,7 @@ move:
 				if (is_large) {
 					large_retry++;
 					thp_retry += is_thp;
-				} else if (!no_split_folio_counting) {
+				} else {
 					retry++;
 				}
 				nr_retry_pages += nr_pages;
@@ -1851,7 +1816,7 @@ move:
 				if (is_large) {
 					nr_large_failed++;
 					stats->nr_thp_failed += is_thp;
-				} else if (!no_split_folio_counting) {
+				} else {
 					nr_failed++;
 				}
 
@@ -1888,30 +1853,52 @@ out:
 		dst2 = list_next_entry(dst, lru);
 	}
 
-	/*
-	 * Try to migrate split folios of fail-to-migrate large folios, no
-	 * nr_failed counting in this round, since all split folios of a
-	 * large folio is counted as 1 failure in the first round.
-	 */
-	if (rc >= 0 && !list_empty(&split_folios)) {
-		/*
-		 * Move non-migrated folios (after NR_MAX_MIGRATE_PAGES_RETRY
-		 * retries) to ret_folios to avoid migrating them again.
-		 */
-		list_splice_init(from, ret_folios);
-		list_splice_init(&split_folios, from);
-		no_split_folio_counting = true;
-		goto retry;
-	}
+	return rc;
+}
 
+static int migrate_pages_sync(struct list_head *from, new_page_t get_new_page,
+		free_page_t put_new_page, unsigned long private,
+		enum migrate_mode mode, int reason, struct list_head *ret_folios,
+		struct list_head *split_folios, struct migrate_pages_stats *stats)
+{
+	int rc, nr_failed = 0;
+	LIST_HEAD(folios);
+	struct migrate_pages_stats astats;
+
+	memset(&astats, 0, sizeof(astats));
+	/* Try to migrate in batch with MIGRATE_ASYNC mode firstly */
+	rc = migrate_pages_batch(from, get_new_page, put_new_page, private, MIGRATE_ASYNC,
+				 reason, &folios, split_folios, &astats,
+				 NR_MAX_MIGRATE_ASYNC_RETRY);
+	stats->nr_succeeded += astats.nr_succeeded;
+	stats->nr_thp_succeeded += astats.nr_thp_succeeded;
+	stats->nr_thp_split += astats.nr_thp_split;
+	if (rc < 0) {
+		stats->nr_failed_pages += astats.nr_failed_pages;
+		stats->nr_thp_failed += astats.nr_thp_failed;
+		list_splice_tail(&folios, ret_folios);
+		return rc;
+	}
+	stats->nr_thp_failed += astats.nr_thp_split;
+	nr_failed += astats.nr_thp_split;
 	/*
-	 * We have unlocked all locked folios, so we can force lock now, let's
-	 * try again.
+	 * Fall back to migrate all failed folios one by one synchronously. All
+	 * failed folios except split THPs will be retried, so their failure
+	 * isn't counted
 	 */
-	if (rc == -EDEADLOCK)
-		goto retry;
+	list_splice_tail_init(&folios, from);
+	while (!list_empty(from)) {
+		list_move(from->next, &folios);
+		rc = migrate_pages_batch(&folios, get_new_page, put_new_page,
+					 private, mode, reason, ret_folios,
+					 split_folios, stats, NR_MAX_MIGRATE_SYNC_RETRY);
+		list_splice_tail_init(&folios, ret_folios);
+		if (rc < 0)
+			return rc;
+		nr_failed += rc;
+	}
 
-	return rc;
+	return nr_failed;
 }
 
 /*
@@ -1949,6 +1936,7 @@ int migrate_pages(struct list_head *from, new_page_t get_new_page,
 	struct folio *folio, *folio2;
 	LIST_HEAD(folios);
 	LIST_HEAD(ret_folios);
+	LIST_HEAD(split_folios);
 	struct migrate_pages_stats stats;
 
 	trace_mm_migrate_pages_start(mode, reason);
@@ -1959,6 +1947,7 @@ int migrate_pages(struct list_head *from, new_page_t get_new_page,
 				     mode, reason, &stats, &ret_folios);
 	if (rc_gather < 0)
 		goto out;
+
 again:
 	nr_pages = 0;
 	list_for_each_entry_safe(folio, folio2, from, lru) {
@@ -1969,20 +1958,36 @@ again:
 		}
 
 		nr_pages += folio_nr_pages(folio);
-		if (nr_pages > NR_MAX_BATCHED_MIGRATION)
+		if (nr_pages >= NR_MAX_BATCHED_MIGRATION)
 			break;
 	}
-	if (nr_pages > NR_MAX_BATCHED_MIGRATION)
-		list_cut_before(&folios, from, &folio->lru);
+	if (nr_pages >= NR_MAX_BATCHED_MIGRATION)
+		list_cut_before(&folios, from, &folio2->lru);
 	else
 		list_splice_init(from, &folios);
-	rc = migrate_pages_batch(&folios, get_new_page, put_new_page, private,
-				 mode, reason, &ret_folios, &stats);
+	if (mode == MIGRATE_ASYNC)
+		rc = migrate_pages_batch(&folios, get_new_page, put_new_page, private,
+					 mode, reason, &ret_folios, &split_folios, &stats,
+					 NR_MAX_MIGRATE_PAGES_RETRY);
+	else
+		rc = migrate_pages_sync(&folios, get_new_page, put_new_page, private,
+					mode, reason, &ret_folios, &split_folios, &stats);
 	list_splice_tail_init(&folios, &ret_folios);
 	if (rc < 0) {
 		rc_gather = rc;
+		list_splice_tail(&split_folios, &ret_folios);
 		goto out;
 	}
+	if (!list_empty(&split_folios)) {
+		/*
+		 * Failure isn't counted since all split folios of a large folio
+		 * is counted as 1 failure already.  And, we only try to migrate
+		 * with minimal effort, force MIGRATE_ASYNC mode and retry once.
+		 */
+		migrate_pages_batch(&split_folios, get_new_page, put_new_page, private,
+				    MIGRATE_ASYNC, reason, &ret_folios, NULL, &stats, 1);
+		list_splice_tail_init(&split_folios, &ret_folios);
+	}
 	rc_gather += rc;
 	if (!list_empty(from))
 		goto again;
diff --git a/mm/mincore.c b/mm/mincore.c
index cd69b9db0081..d359650b0f75 100644
--- a/mm/mincore.c
+++ b/mm/mincore.c
@@ -33,7 +33,7 @@ static int mincore_hugetlb(pte_t *pte, unsigned long hmask, unsigned long addr,
 	 * Hugepages under user process are always in RAM and never
 	 * swapped out, but theoretically it needs to be checked.
 	 */
-	present = pte && !huge_pte_none(huge_ptep_get(pte));
+	present = pte && !huge_pte_none_mostly(huge_ptep_get(pte));
 	for (; addr != end; vec++, addr += PAGE_SIZE)
 		*vec = present;
 	walk->private = vec;