Merge branch 'locking/urgent' into locking/core, to pick up fixes

Signed-off-by: Ingo Molnar <mingo@kernel.org>

24 files changed, 684 insertions, 345 deletions

diff --git a/mm/filemap.c b/mm/filemap.c
index 1aaea26556cc..99c49eeae71b 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -988,9 +988,43 @@ void __init pagecache_init(void)
 	page_writeback_init();
 }
 
+/*
+ * The page wait code treats the "wait->flags" somewhat unusually, because
+ * we have multiple different kinds of waits, not just the usual "exclusive"
+ * one.
+ *
+ * We have:
+ *
+ *  (a) no special bits set:
+ *
+ *	We're just waiting for the bit to be released, and when a waker
+ *	calls the wakeup function, we set WQ_FLAG_WOKEN and wake it up,
+ *	and remove it from the wait queue.
+ *
+ *	Simple and straightforward.
+ *
+ *  (b) WQ_FLAG_EXCLUSIVE:
+ *
+ *	The waiter is waiting to get the lock, and only one waiter should
+ *	be woken up to avoid any thundering herd behavior. We'll set the
+ *	WQ_FLAG_WOKEN bit, wake it up, and remove it from the wait queue.
+ *
+ *	This is the traditional exclusive wait.
+ *
+ *  (c) WQ_FLAG_EXCLUSIVE | WQ_FLAG_CUSTOM:
+ *
+ *	The waiter is waiting to get the bit, and additionally wants the
+ *	lock to be transferred to it for fair lock behavior. If the lock
+ *	cannot be taken, we stop walking the wait queue without waking
+ *	the waiter.
+ *
+ *	This is the "fair lock handoff" case, and in addition to setting
+ *	WQ_FLAG_WOKEN, we set WQ_FLAG_DONE to let the waiter easily see
+ *	that it now has the lock.
+ */
 static int wake_page_function(wait_queue_entry_t *wait, unsigned mode, int sync, void *arg)
 {
-	int ret;
+	unsigned int flags;
 	struct wait_page_key *key = arg;
 	struct wait_page_queue *wait_page
 		= container_of(wait, struct wait_page_queue, wait);
@@ -999,35 +1033,44 @@ static int wake_page_function(wait_queue_entry_t *wait, unsigned mode, int sync,
 		return 0;
 
 	/*
-	 * If it's an exclusive wait, we get the bit for it, and
-	 * stop walking if we can't.
-	 *
-	 * If it's a non-exclusive wait, then the fact that this
-	 * wake function was called means that the bit already
-	 * was cleared, and we don't care if somebody then
-	 * re-took it.
+	 * If it's a lock handoff wait, we get the bit for it, and
+	 * stop walking (and do not wake it up) if we can't.
 	 */
-	ret = 0;
-	if (wait->flags & WQ_FLAG_EXCLUSIVE) {
-		if (test_and_set_bit(key->bit_nr, &key->page->flags))
+	flags = wait->flags;
+	if (flags & WQ_FLAG_EXCLUSIVE) {
+		if (test_bit(key->bit_nr, &key->page->flags))
 			return -1;
-		ret = 1;
+		if (flags & WQ_FLAG_CUSTOM) {
+			if (test_and_set_bit(key->bit_nr, &key->page->flags))
+				return -1;
+			flags |= WQ_FLAG_DONE;
+		}
 	}
-	wait->flags |= WQ_FLAG_WOKEN;
 
+	/*
+	 * We are holding the wait-queue lock, but the waiter that
+	 * is waiting for this will be checking the flags without
+	 * any locking.
+	 *
+	 * So update the flags atomically, and wake up the waiter
+	 * afterwards to avoid any races. This store-release pairs
+	 * with the load-acquire in wait_on_page_bit_common().
+	 */
+	smp_store_release(&wait->flags, flags | WQ_FLAG_WOKEN);
 	wake_up_state(wait->private, mode);
 
 	/*
 	 * Ok, we have successfully done what we're waiting for,
 	 * and we can unconditionally remove the wait entry.
 	 *
-	 * Note that this has to be the absolute last thing we do,
-	 * since after list_del_init(&wait->entry) the wait entry
+	 * Note that this pairs with the "finish_wait()" in the
+	 * waiter, and has to be the absolute last thing we do.
+	 * After this list_del_init(&wait->entry) the wait entry
 	 * might be de-allocated and the process might even have
 	 * exited.
 	 */
 	list_del_init_careful(&wait->entry);
-	return ret;
+	return (flags & WQ_FLAG_EXCLUSIVE) != 0;
 }
 
 static void wake_up_page_bit(struct page *page, int bit_nr)
@@ -1107,8 +1150,8 @@ enum behavior {
 };
 
 /*
- * Attempt to check (or get) the page bit, and mark the
- * waiter woken if successful.
+ * Attempt to check (or get) the page bit, and mark us done
+ * if successful.
  */
 static inline bool trylock_page_bit_common(struct page *page, int bit_nr,
 					struct wait_queue_entry *wait)
@@ -1119,13 +1162,17 @@ static inline bool trylock_page_bit_common(struct page *page, int bit_nr,
 	} else if (test_bit(bit_nr, &page->flags))
 		return false;
 
-	wait->flags |= WQ_FLAG_WOKEN;
+	wait->flags |= WQ_FLAG_WOKEN | WQ_FLAG_DONE;
 	return true;
 }
 
+/* How many times do we accept lock stealing from under a waiter? */
+int sysctl_page_lock_unfairness = 5;
+
 static inline int wait_on_page_bit_common(wait_queue_head_t *q,
 	struct page *page, int bit_nr, int state, enum behavior behavior)
 {
+	int unfairness = sysctl_page_lock_unfairness;
 	struct wait_page_queue wait_page;
 	wait_queue_entry_t *wait = &wait_page.wait;
 	bool thrashing = false;
@@ -1143,11 +1190,18 @@ static inline int wait_on_page_bit_common(wait_queue_head_t *q,
 	}
 
 	init_wait(wait);
-	wait->flags = behavior == EXCLUSIVE ? WQ_FLAG_EXCLUSIVE : 0;
 	wait->func = wake_page_function;
 	wait_page.page = page;
 	wait_page.bit_nr = bit_nr;
 
+repeat:
+	wait->flags = 0;
+	if (behavior == EXCLUSIVE) {
+		wait->flags = WQ_FLAG_EXCLUSIVE;
+		if (--unfairness < 0)
+			wait->flags |= WQ_FLAG_CUSTOM;
+	}
+
 	/*
 	 * Do one last check whether we can get the
 	 * page bit synchronously.
@@ -1170,27 +1224,63 @@ static inline int wait_on_page_bit_common(wait_queue_head_t *q,
 
 	/*
 	 * From now on, all the logic will be based on
-	 * the WQ_FLAG_WOKEN flag, and the and the page
-	 * bit testing (and setting) will be - or has
-	 * already been - done by the wake function.
+	 * the WQ_FLAG_WOKEN and WQ_FLAG_DONE flag, to
+	 * see whether the page bit testing has already
+	 * been done by the wake function.
 	 *
 	 * We can drop our reference to the page.
 	 */
 	if (behavior == DROP)
 		put_page(page);
 
+	/*
+	 * Note that until the "finish_wait()", or until
+	 * we see the WQ_FLAG_WOKEN flag, we need to
+	 * be very careful with the 'wait->flags', because
+	 * we may race with a waker that sets them.
+	 */
 	for (;;) {
+		unsigned int flags;
+
 		set_current_state(state);
 
-		if (signal_pending_state(state, current))
+		/* Loop until we've been woken or interrupted */
+		flags = smp_load_acquire(&wait->flags);
+		if (!(flags & WQ_FLAG_WOKEN)) {
+			if (signal_pending_state(state, current))
+				break;
+
+			io_schedule();
+			continue;
+		}
+
+		/* If we were non-exclusive, we're done */
+		if (behavior != EXCLUSIVE)
 			break;
 
-		if (wait->flags & WQ_FLAG_WOKEN)
+		/* If the waker got the lock for us, we're done */
+		if (flags & WQ_FLAG_DONE)
 			break;
 
-		io_schedule();
+		/*
+		 * Otherwise, if we're getting the lock, we need to
+		 * try to get it ourselves.
+		 *
+		 * And if that fails, we'll have to retry this all.
+		 */
+		if (unlikely(test_and_set_bit(bit_nr, &page->flags)))
+			goto repeat;
+
+		wait->flags |= WQ_FLAG_DONE;
+		break;
 	}
 
+	/*
+	 * If a signal happened, this 'finish_wait()' may remove the last
+	 * waiter from the wait-queues, but the PageWaiters bit will remain
+	 * set. That's ok. The next wakeup will take care of it, and trying
+	 * to do it here would be difficult and prone to races.
+	 */
 	finish_wait(q, wait);
 
 	if (thrashing) {
@@ -1200,12 +1290,20 @@ static inline int wait_on_page_bit_common(wait_queue_head_t *q,
 	}
 
 	/*
-	 * A signal could leave PageWaiters set. Clearing it here if
-	 * !waitqueue_active would be possible (by open-coding finish_wait),
-	 * but still fail to catch it in the case of wait hash collision. We
-	 * already can fail to clear wait hash collision cases, so don't
-	 * bother with signals either.
+	 * NOTE! The wait->flags weren't stable until we've done the
+	 * 'finish_wait()', and we could have exited the loop above due
+	 * to a signal, and had a wakeup event happen after the signal
+	 * test but before the 'finish_wait()'.
+	 *
+	 * So only after the finish_wait() can we reliably determine
+	 * if we got woken up or not, so we can now figure out the final
+	 * return value based on that state without races.
+	 *
+	 * Also note that WQ_FLAG_WOKEN is sufficient for a non-exclusive
+	 * waiter, but an exclusive one requires WQ_FLAG_DONE.
 	 */
+	if (behavior == EXCLUSIVE)
+		return wait->flags & WQ_FLAG_DONE ? 0 : -EINTR;
 
 	return wait->flags & WQ_FLAG_WOKEN ? 0 : -EINTR;
 }
@@ -2267,7 +2365,11 @@ readpage:
 		}
 
 		if (!PageUptodate(page)) {
-			error = lock_page_killable(page);
+			if (iocb->ki_flags & IOCB_WAITQ)
+				error = lock_page_async(page, iocb->ki_waitq);
+			else
+				error = lock_page_killable(page);
+
 			if (unlikely(error))
 				goto readpage_error;
 			if (!PageUptodate(page)) {
diff --git a/mm/gup.c b/mm/gup.c
index ae096ea7583f..e869c634cc9a 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -381,22 +381,13 @@ static int follow_pfn_pte(struct vm_area_struct *vma, unsigned long address,
 }
 
 /*
- * FOLL_FORCE or a forced COW break can write even to unwritable pte's,
- * but only after we've gone through a COW cycle and they are dirty.
+ * FOLL_FORCE can write to even unwritable pte's, but only
+ * after we've gone through a COW cycle and they are dirty.
  */
 static inline bool can_follow_write_pte(pte_t pte, unsigned int flags)
 {
-	return pte_write(pte) || ((flags & FOLL_COW) && pte_dirty(pte));
-}
-
-/*
- * A (separate) COW fault might break the page the other way and
- * get_user_pages() would return the page from what is now the wrong
- * VM. So we need to force a COW break at GUP time even for reads.
- */
-static inline bool should_force_cow_break(struct vm_area_struct *vma, unsigned int flags)
-{
-	return is_cow_mapping(vma->vm_flags) && (flags & (FOLL_GET | FOLL_PIN));
+	return pte_write(pte) ||
+		((flags & FOLL_FORCE) && (flags & FOLL_COW) && pte_dirty(pte));
 }
 
 static struct page *follow_page_pte(struct vm_area_struct *vma,
@@ -843,7 +834,7 @@ static int get_gate_page(struct mm_struct *mm, unsigned long address,
 			goto unmap;
 		*page = pte_page(*pte);
 	}
-	if (unlikely(!try_get_page(*page))) {
+	if (unlikely(!try_grab_page(*page, gup_flags))) {
 		ret = -ENOMEM;
 		goto unmap;
 	}
@@ -1067,11 +1058,9 @@ static long __get_user_pages(struct mm_struct *mm,
 				goto out;
 			}
 			if (is_vm_hugetlb_page(vma)) {
-				if (should_force_cow_break(vma, foll_flags))
-					foll_flags |= FOLL_WRITE;
 				i = follow_hugetlb_page(mm, vma, pages, vmas,
 						&start, &nr_pages, i,
-						foll_flags, locked);
+						gup_flags, locked);
 				if (locked && *locked == 0) {
 					/*
 					 * We've got a VM_FAULT_RETRY
@@ -1085,10 +1074,6 @@ static long __get_user_pages(struct mm_struct *mm,
 				continue;
 			}
 		}
-
-		if (should_force_cow_break(vma, foll_flags))
-			foll_flags |= FOLL_WRITE;
-
 retry:
 		/*
 		 * If we have a pending SIGKILL, don't keep faulting pages and
@@ -1270,6 +1255,9 @@ static __always_inline long __get_user_pages_locked(struct mm_struct *mm,
 		BUG_ON(*locked != 1);
 	}
 
+	if (flags & FOLL_PIN)
+		atomic_set(&mm->has_pinned, 1);
+
 	/*
 	 * FOLL_PIN and FOLL_GET are mutually exclusive. Traditional behavior
 	 * is to set FOLL_GET if the caller wants pages[] filled in (but has
@@ -2500,13 +2488,13 @@ static int gup_huge_pgd(pgd_t orig, pgd_t *pgdp, unsigned long addr,
 	return 1;
 }
 
-static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end,
+static int gup_pmd_range(pud_t *pudp, pud_t pud, unsigned long addr, unsigned long end,
 		unsigned int flags, struct page **pages, int *nr)
 {
 	unsigned long next;
 	pmd_t *pmdp;
 
-	pmdp = pmd_offset(&pud, addr);
+	pmdp = pmd_offset_lockless(pudp, pud, addr);
 	do {
 		pmd_t pmd = READ_ONCE(*pmdp);
 
@@ -2543,13 +2531,13 @@ static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end,
 	return 1;
 }
 
-static int gup_pud_range(p4d_t p4d, unsigned long addr, unsigned long end,
+static int gup_pud_range(p4d_t *p4dp, p4d_t p4d, unsigned long addr, unsigned long end,
 			 unsigned int flags, struct page **pages, int *nr)
 {
 	unsigned long next;
 	pud_t *pudp;
 
-	pudp = pud_offset(&p4d, addr);
+	pudp = pud_offset_lockless(p4dp, p4d, addr);
 	do {
 		pud_t pud = READ_ONCE(*pudp);
 
@@ -2564,20 +2552,20 @@ static int gup_pud_range(p4d_t p4d, unsigned long addr, unsigned long end,
 			if (!gup_huge_pd(__hugepd(pud_val(pud)), addr,
 					 PUD_SHIFT, next, flags, pages, nr))
 				return 0;
-		} else if (!gup_pmd_range(pud, addr, next, flags, pages, nr))
+		} else if (!gup_pmd_range(pudp, pud, addr, next, flags, pages, nr))
 			return 0;
 	} while (pudp++, addr = next, addr != end);
 
 	return 1;
 }
 
-static int gup_p4d_range(pgd_t pgd, unsigned long addr, unsigned long end,
+static int gup_p4d_range(pgd_t *pgdp, pgd_t pgd, unsigned long addr, unsigned long end,
 			 unsigned int flags, struct page **pages, int *nr)
 {
 	unsigned long next;
 	p4d_t *p4dp;
 
-	p4dp = p4d_offset(&pgd, addr);
+	p4dp = p4d_offset_lockless(pgdp, pgd, addr);
 	do {
 		p4d_t p4d = READ_ONCE(*p4dp);
 
@@ -2589,7 +2577,7 @@ static int gup_p4d_range(pgd_t pgd, unsigned long addr, unsigned long end,
 			if (!gup_huge_pd(__hugepd(p4d_val(p4d)), addr,
 					 P4D_SHIFT, next, flags, pages, nr))
 				return 0;
-		} else if (!gup_pud_range(p4d, addr, next, flags, pages, nr))
+		} else if (!gup_pud_range(p4dp, p4d, addr, next, flags, pages, nr))
 			return 0;
 	} while (p4dp++, addr = next, addr != end);
 
@@ -2617,7 +2605,7 @@ static void gup_pgd_range(unsigned long addr, unsigned long end,
 			if (!gup_huge_pd(__hugepd(pgd_val(pgd)), addr,
 					 PGDIR_SHIFT, next, flags, pages, nr))
 				return;
-		} else if (!gup_p4d_range(pgd, addr, next, flags, pages, nr))
+		} else if (!gup_p4d_range(pgdp, pgd, addr, next, flags, pages, nr))
 			return;
 	} while (pgdp++, addr = next, addr != end);
 }
@@ -2675,6 +2663,9 @@ static int internal_get_user_pages_fast(unsigned long start, int nr_pages,
 				       FOLL_FAST_ONLY)))
 		return -EINVAL;
 
+	if (gup_flags & FOLL_PIN)
+		atomic_set(&current->mm->has_pinned, 1);
+
 	if (!(gup_flags & FOLL_FAST_ONLY))
 		might_lock_read(&current->mm->mmap_lock);
 
@@ -2689,19 +2680,6 @@ static int internal_get_user_pages_fast(unsigned long start, int nr_pages,
 		return -EFAULT;
 
 	/*
-	 * The FAST_GUP case requires FOLL_WRITE even for pure reads,
-	 * because get_user_pages() may need to cause an early COW in
-	 * order to avoid confusing the normal COW routines. So only
-	 * targets that are already writable are safe to do by just
-	 * looking at the page tables.
-	 *
-	 * NOTE! With FOLL_FAST_ONLY we allow read-only gup_fast() here,
-	 * because there is no slow path to fall back on. But you'd
-	 * better be careful about possible COW pages - you'll get _a_
-	 * COW page, but not necessarily the one you intended to get
-	 * depending on what COW event happens after this. COW may break
-	 * the page copy in a random direction.
-	 *
 	 * Disable interrupts. The nested form is used, in order to allow
 	 * full, general purpose use of this routine.
 	 *
@@ -2714,8 +2692,6 @@ static int internal_get_user_pages_fast(unsigned long start, int nr_pages,
 	 */
 	if (IS_ENABLED(CONFIG_HAVE_FAST_GUP) && gup_fast_permitted(start, end)) {
 		unsigned long fast_flags = gup_flags;
-		if (!(gup_flags & FOLL_FAST_ONLY))
-			fast_flags |= FOLL_WRITE;
 
 		local_irq_save(flags);
 		gup_pgd_range(addr, end, fast_flags, pages, &nr_pinned);
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 2ccff8472cd4..da397779a6d4 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1074,6 +1074,24 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 
 	src_page = pmd_page(pmd);
 	VM_BUG_ON_PAGE(!PageHead(src_page), src_page);
+
+	/*
+	 * If this page is a potentially pinned page, split and retry the fault
+	 * with smaller page size.  Normally this should not happen because the
+	 * userspace should use MADV_DONTFORK upon pinned regions.  This is a
+	 * best effort that the pinned pages won't be replaced by another
+	 * random page during the coming copy-on-write.
+	 */
+	if (unlikely(is_cow_mapping(vma->vm_flags) &&
+		     atomic_read(&src_mm->has_pinned) &&
+		     page_maybe_dma_pinned(src_page))) {
+		pte_free(dst_mm, pgtable);
+		spin_unlock(src_ptl);
+		spin_unlock(dst_ptl);
+		__split_huge_pmd(vma, src_pmd, addr, false, NULL);
+		return -EAGAIN;
+	}
+
 	get_page(src_page);
 	page_dup_rmap(src_page, true);
 	add_mm_counter(dst_mm, MM_ANONPAGES, HPAGE_PMD_NR);
@@ -1177,6 +1195,16 @@ int copy_huge_pud(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 		/* No huge zero pud yet */
 	}
 
+	/* Please refer to comments in copy_huge_pmd() */
+	if (unlikely(is_cow_mapping(vma->vm_flags) &&
+		     atomic_read(&src_mm->has_pinned) &&
+		     page_maybe_dma_pinned(pud_page(pud)))) {
+		spin_unlock(src_ptl);
+		spin_unlock(dst_ptl);
+		__split_huge_pud(vma, src_pud, addr);
+		return -EAGAIN;
+	}
+
 	pudp_set_wrprotect(src_mm, addr, src_pud);
 	pud = pud_mkold(pud_wrprotect(pud));
 	set_pud_at(dst_mm, addr, dst_pud, pud);
@@ -1291,12 +1319,13 @@ fallback:
 }
 
 /*
- * FOLL_FORCE or a forced COW break can write even to unwritable pmd's,
- * but only after we've gone through a COW cycle and they are dirty.
+ * FOLL_FORCE can write to even unwritable pmd's, but only
+ * after we've gone through a COW cycle and they are dirty.
  */
 static inline bool can_follow_write_pmd(pmd_t pmd, unsigned int flags)
 {
-	return pmd_write(pmd) || ((flags & FOLL_COW) && pmd_dirty(pmd));
+	return pmd_write(pmd) ||
+	       ((flags & FOLL_FORCE) && (flags & FOLL_COW) && pmd_dirty(pmd));
 }
 
 struct page *follow_trans_huge_pmd(struct vm_area_struct *vma,
@@ -2021,7 +2050,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
 		put_page(page);
 		add_mm_counter(mm, mm_counter_file(page), -HPAGE_PMD_NR);
 		return;
-	} else if (is_huge_zero_pmd(*pmd)) {
+	} else if (pmd_trans_huge(*pmd) && is_huge_zero_pmd(*pmd)) {
 		/*
 		 * FIXME: Do we want to invalidate secondary mmu by calling
 		 * mmu_notifier_invalidate_range() see comments below inside
@@ -2115,30 +2144,34 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
 		pte = pte_offset_map(&_pmd, addr);
 		BUG_ON(!pte_none(*pte));
 		set_pte_at(mm, addr, pte, entry);
-		atomic_inc(&page[i]._mapcount);
-		pte_unmap(pte);
-	}
-
-	/*
-	 * Set PG_double_map before dropping compound_mapcount to avoid
-	 * false-negative page_mapped().
-	 */
-	if (compound_mapcount(page) > 1 && !TestSetPageDoubleMap(page)) {
-		for (i = 0; i < HPAGE_PMD_NR; i++)
+		if (!pmd_migration)
 			atomic_inc(&page[i]._mapcount);
+		pte_unmap(pte);
 	}
 
-	lock_page_memcg(page);
-	if (atomic_add_negative(-1, compound_mapcount_ptr(page))) {
-		/* Last compound_mapcount is gone. */
-		__dec_lruvec_page_state(page, NR_ANON_THPS);
-		if (TestClearPageDoubleMap(page)) {
-			/* No need in mapcount reference anymore */
+	if (!pmd_migration) {
+		/*
+		 * Set PG_double_map before dropping compound_mapcount to avoid
+		 * false-negative page_mapped().
+		 */
+		if (compound_mapcount(page) > 1 &&
+		    !TestSetPageDoubleMap(page)) {
 			for (i = 0; i < HPAGE_PMD_NR; i++)
-				atomic_dec(&page[i]._mapcount);
+				atomic_inc(&page[i]._mapcount);
+		}
+
+		lock_page_memcg(page);
+		if (atomic_add_negative(-1, compound_mapcount_ptr(page))) {
+			/* Last compound_mapcount is gone. */
+			__dec_lruvec_page_state(page, NR_ANON_THPS);
+			if (TestClearPageDoubleMap(page)) {
+				/* No need in mapcount reference anymore */
+				for (i = 0; i < HPAGE_PMD_NR; i++)
+					atomic_dec(&page[i]._mapcount);
+			}
 		}
+		unlock_page_memcg(page);
 	}
-	unlock_page_memcg(page);
 
 	smp_wmb(); /* make pte visible before pmd */
 	pmd_populate(mm, pmd, pgtable);
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index a301c2d672bf..67fc6383995b 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1250,21 +1250,32 @@ static struct page *alloc_gigantic_page(struct hstate *h, gfp_t gfp_mask,
 		int nid, nodemask_t *nodemask)
 {
 	unsigned long nr_pages = 1UL << huge_page_order(h);
+	if (nid == NUMA_NO_NODE)
+		nid = numa_mem_id();
 
 #ifdef CONFIG_CMA
 	{
 		struct page *page;
 		int node;
 
-		for_each_node_mask(node, *nodemask) {
-			if (!hugetlb_cma[node])
-				continue;
-
-			page = cma_alloc(hugetlb_cma[node], nr_pages,
-					 huge_page_order(h), true);
+		if (hugetlb_cma[nid]) {
+			page = cma_alloc(hugetlb_cma[nid], nr_pages,
+					huge_page_order(h), true);
 			if (page)
 				return page;
 		}
+
+		if (!(gfp_mask & __GFP_THISNODE)) {
+			for_each_node_mask(node, *nodemask) {
+				if (node == nid || !hugetlb_cma[node])
+					continue;
+
+				page = cma_alloc(hugetlb_cma[node], nr_pages,
+						huge_page_order(h), true);
+				if (page)
+					return page;
+			}
+		}
 	}
 #endif
 
@@ -3454,6 +3465,22 @@ static unsigned int allowed_mems_nr(struct hstate *h)
 }
 
 #ifdef CONFIG_SYSCTL
+static int proc_hugetlb_doulongvec_minmax(struct ctl_table *table, int write,
+					  void *buffer, size_t *length,
+					  loff_t *ppos, unsigned long *out)
+{
+	struct ctl_table dup_table;
+
+	/*
+	 * In order to avoid races with __do_proc_doulongvec_minmax(), we
+	 * can duplicate the @table and alter the duplicate of it.
+	 */
+	dup_table = *table;
+	dup_table.data = out;
+
+	return proc_doulongvec_minmax(&dup_table, write, buffer, length, ppos);
+}
+
 static int hugetlb_sysctl_handler_common(bool obey_mempolicy,
 			 struct ctl_table *table, int write,
 			 void *buffer, size_t *length, loff_t *ppos)
@@ -3465,9 +3492,8 @@ static int hugetlb_sysctl_handler_common(bool obey_mempolicy,
 	if (!hugepages_supported())
 		return -EOPNOTSUPP;
 
-	table->data = &tmp;
-	table->maxlen = sizeof(unsigned long);
-	ret = proc_doulongvec_minmax(table, write, buffer, length, ppos);
+	ret = proc_hugetlb_doulongvec_minmax(table, write, buffer, length, ppos,
+					     &tmp);
 	if (ret)
 		goto out;
 
@@ -3510,9 +3536,8 @@ int hugetlb_overcommit_handler(struct ctl_table *table, int write,
 	if (write && hstate_is_gigantic(h))
 		return -EINVAL;
 
-	table->data = &tmp;
-	table->maxlen = sizeof(unsigned long);
-	ret = proc_doulongvec_minmax(table, write, buffer, length, ppos);
+	ret = proc_hugetlb_doulongvec_minmax(table, write, buffer, length, ppos,
+					     &tmp);
 	if (ret)
 		goto out;
 
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index e749e568e1ea..cfa0dba5fd3b 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -1709,7 +1709,7 @@ static void collapse_file(struct mm_struct *mm,
 				xas_unlock_irq(&xas);
 				page_cache_sync_readahead(mapping, &file->f_ra,
 							  file, index,
-							  PAGE_SIZE);
+							  end - index);
 				/* drain pagevecs to help isolate_lru_page() */
 				lru_add_drain();
 				page = find_lock_page(mapping, index);
diff --git a/mm/ksm.c b/mm/ksm.c
index 0aa2247bddd7..9afccc36dbd2 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -2453,6 +2453,10 @@ int ksm_madvise(struct vm_area_struct *vma, unsigned long start,
 		if (vma_is_dax(vma))
 			return 0;
 
+#ifdef VM_SAO
+		if (*vm_flags & VM_SAO)
+			return 0;
+#endif
 #ifdef VM_SPARC_ADI
 		if (*vm_flags & VM_SPARC_ADI)
 			return 0;
@@ -2582,6 +2586,10 @@ struct page *ksm_might_need_to_copy(struct page *page,
 		return page;		/* let do_swap_page report the error */
 
 	new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, address);
+	if (new_page && mem_cgroup_charge(new_page, vma->vm_mm, GFP_KERNEL)) {
+		put_page(new_page);
+		new_page = NULL;
+	}
 	if (new_page) {
 		copy_user_highpage(new_page, page, address, vma);
 
@@ -2657,31 +2665,6 @@ again:
 		goto again;
 }
 
-bool reuse_ksm_page(struct page *page,
-		    struct vm_area_struct *vma,
-		    unsigned long address)
-{
-#ifdef CONFIG_DEBUG_VM
-	if (WARN_ON(is_zero_pfn(page_to_pfn(page))) ||
-			WARN_ON(!page_mapped(page)) ||
-			WARN_ON(!PageLocked(page))) {
-		dump_page(page, "reuse_ksm_page");
-		return false;
-	}
-#endif
-
-	if (PageSwapCache(page) || !page_stable_node(page))
-		return false;
-	/* Prohibit parallel get_ksm_page() */
-	if (!page_ref_freeze(page, 1))
-		return false;
-
-	page_move_anon_rmap(page, vma);
-	page->index = linear_page_index(vma, address);
-	page_ref_unfreeze(page, 1);
-
-	return true;
-}
 #ifdef CONFIG_MIGRATION
 void ksm_migrate_page(struct page *newpage, struct page *oldpage)
 {
diff --git a/mm/madvise.c b/mm/madvise.c
index dd1d43cf026d..0e0d61003fc6 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -289,9 +289,9 @@ static long madvise_willneed(struct vm_area_struct *vma,
 	 */
 	*prev = NULL;	/* tell sys_madvise we drop mmap_lock */
 	get_file(file);
-	mmap_read_unlock(current->mm);
 	offset = (loff_t)(start - vma->vm_start)
 			+ ((loff_t)vma->vm_pgoff << PAGE_SHIFT);
+	mmap_read_unlock(current->mm);
 	vfs_fadvise(file, offset, end - start, POSIX_FADV_WILLNEED);
 	fput(file);
 	mmap_read_lock(current->mm);
@@ -381,9 +381,9 @@ huge_unlock:
 		return 0;
 	}
 
+regular_page:
 	if (pmd_trans_unstable(pmd))
 		return 0;
-regular_page:
 #endif
 	tlb_change_page_size(tlb, PAGE_SIZE);
 	orig_pte = pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index b807952b4d43..6877c765b8d0 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1538,9 +1538,9 @@ static char *memory_stat_format(struct mem_cgroup *memcg)
 		       memcg_page_state(memcg, WORKINGSET_ACTIVATE_ANON));
 	seq_buf_printf(&s, "workingset_activate_file %lu\n",
 		       memcg_page_state(memcg, WORKINGSET_ACTIVATE_FILE));
-	seq_buf_printf(&s, "workingset_restore %lu\n",
+	seq_buf_printf(&s, "workingset_restore_anon %lu\n",
 		       memcg_page_state(memcg, WORKINGSET_RESTORE_ANON));
-	seq_buf_printf(&s, "workingset_restore %lu\n",
+	seq_buf_printf(&s, "workingset_restore_file %lu\n",
 		       memcg_page_state(memcg, WORKINGSET_RESTORE_FILE));
 	seq_buf_printf(&s, "workingset_nodereclaim %lu\n",
 		       memcg_page_state(memcg, WORKINGSET_NODERECLAIM));
@@ -6774,6 +6774,9 @@ static void uncharge_batch(const struct uncharge_gather *ug)
 	__this_cpu_add(ug->memcg->vmstats_percpu->nr_page_events, ug->nr_pages);
 	memcg_check_events(ug->memcg, ug->dummy_page);
 	local_irq_restore(flags);
+
+	/* drop reference from uncharge_page */
+	css_put(&ug->memcg->css);
 }
 
 static void uncharge_page(struct page *page, struct uncharge_gather *ug)
@@ -6797,6 +6800,9 @@ static void uncharge_page(struct page *page, struct uncharge_gather *ug)
 			uncharge_gather_clear(ug);
 		}
 		ug->memcg = page->mem_cgroup;
+
+		/* pairs with css_put in uncharge_batch */
+		css_get(&ug->memcg->css);
 	}
 
 	nr_pages = compound_nr(page);
diff --git a/mm/memory.c b/mm/memory.c
index 602f4283122f..eeae590e526a 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -73,6 +73,7 @@
 #include <linux/numa.h>
 #include <linux/perf_event.h>
 #include <linux/ptrace.h>
+#include <linux/vmalloc.h>
 
 #include <trace/events/kmem.h>
 
@@ -83,6 +84,7 @@
 #include <asm/tlb.h>
 #include <asm/tlbflush.h>
 
+#include "pgalloc-track.h"
 #include "internal.h"
 
 #if defined(LAST_CPUPID_NOT_IN_PAGE_FLAGS) && !defined(CONFIG_COMPILE_TEST)
@@ -693,84 +695,185 @@ out:
  * covered by this vma.
  */
 
-static inline unsigned long
-copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
+static unsigned long
+copy_nonpresent_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 		pte_t *dst_pte, pte_t *src_pte, struct vm_area_struct *vma,
 		unsigned long addr, int *rss)
 {
 	unsigned long vm_flags = vma->vm_flags;
 	pte_t pte = *src_pte;
 	struct page *page;
+	swp_entry_t entry = pte_to_swp_entry(pte);
+
+	if (likely(!non_swap_entry(entry))) {
+		if (swap_duplicate(entry) < 0)
+			return entry.val;
+
+		/* make sure dst_mm is on swapoff's mmlist. */
+		if (unlikely(list_empty(&dst_mm->mmlist))) {
+			spin_lock(&mmlist_lock);
+			if (list_empty(&dst_mm->mmlist))
+				list_add(&dst_mm->mmlist,
+						&src_mm->mmlist);
+			spin_unlock(&mmlist_lock);
+		}
+		rss[MM_SWAPENTS]++;
+	} else if (is_migration_entry(entry)) {
+		page = migration_entry_to_page(entry);
 
-	/* pte contains position in swap or file, so copy. */
-	if (unlikely(!pte_present(pte))) {
-		swp_entry_t entry = pte_to_swp_entry(pte);
-
-		if (likely(!non_swap_entry(entry))) {
-			if (swap_duplicate(entry) < 0)
-				return entry.val;
-
-			/* make sure dst_mm is on swapoff's mmlist. */
-			if (unlikely(list_empty(&dst_mm->mmlist))) {
-				spin_lock(&mmlist_lock);
-				if (list_empty(&dst_mm->mmlist))
-					list_add(&dst_mm->mmlist,
-							&src_mm->mmlist);
-				spin_unlock(&mmlist_lock);
-			}
-			rss[MM_SWAPENTS]++;
-		} else if (is_migration_entry(entry)) {
-			page = migration_entry_to_page(entry);
-
-			rss[mm_counter(page)]++;
-
-			if (is_write_migration_entry(entry) &&
-					is_cow_mapping(vm_flags)) {
-				/*
-				 * COW mappings require pages in both
-				 * parent and child to be set to read.
-				 */
-				make_migration_entry_read(&entry);
-				pte = swp_entry_to_pte(entry);
-				if (pte_swp_soft_dirty(*src_pte))
-					pte = pte_swp_mksoft_dirty(pte);
-				if (pte_swp_uffd_wp(*src_pte))
-					pte = pte_swp_mkuffd_wp(pte);
-				set_pte_at(src_mm, addr, src_pte, pte);
-			}
-		} else if (is_device_private_entry(entry)) {
-			page = device_private_entry_to_page(entry);
+		rss[mm_counter(page)]++;
 
+		if (is_write_migration_entry(entry) &&
+				is_cow_mapping(vm_flags)) {
 			/*
-			 * Update rss count even for unaddressable pages, as
-			 * they should treated just like normal pages in this
-			 * respect.
-			 *
-			 * We will likely want to have some new rss counters
-			 * for unaddressable pages, at some point. But for now
-			 * keep things as they are.
+			 * COW mappings require pages in both
+			 * parent and child to be set to read.
 			 */
-			get_page(page);
-			rss[mm_counter(page)]++;
-			page_dup_rmap(page, false);
+			make_migration_entry_read(&entry);
+			pte = swp_entry_to_pte(entry);
+			if (pte_swp_soft_dirty(*src_pte))
+				pte = pte_swp_mksoft_dirty(pte);
+			if (pte_swp_uffd_wp(*src_pte))
+				pte = pte_swp_mkuffd_wp(pte);
+			set_pte_at(src_mm, addr, src_pte, pte);
+		}
+	} else if (is_device_private_entry(entry)) {
+		page = device_private_entry_to_page(entry);
 
-			/*
-			 * We do not preserve soft-dirty information, because so
-			 * far, checkpoint/restore is the only feature that
-			 * requires that. And checkpoint/restore does not work
-			 * when a device driver is involved (you cannot easily
-			 * save and restore device driver state).
-			 */
-			if (is_write_device_private_entry(entry) &&
-			    is_cow_mapping(vm_flags)) {
-				make_device_private_entry_read(&entry);
-				pte = swp_entry_to_pte(entry);
-				if (pte_swp_uffd_wp(*src_pte))
-					pte = pte_swp_mkuffd_wp(pte);
-				set_pte_at(src_mm, addr, src_pte, pte);
-			}
+		/*
+		 * Update rss count even for unaddressable pages, as
+		 * they should treated just like normal pages in this
+		 * respect.
+		 *
+		 * We will likely want to have some new rss counters
+		 * for unaddressable pages, at some point. But for now
+		 * keep things as they are.
+		 */
+		get_page(page);
+		rss[mm_counter(page)]++;
+		page_dup_rmap(page, false);
+
+		/*
+		 * We do not preserve soft-dirty information, because so
+		 * far, checkpoint/restore is the only feature that
+		 * requires that. And checkpoint/restore does not work
+		 * when a device driver is involved (you cannot easily
+		 * save and restore device driver state).
+		 */
+		if (is_write_device_private_entry(entry) &&
+		    is_cow_mapping(vm_flags)) {
+			make_device_private_entry_read(&entry);
+			pte = swp_entry_to_pte(entry);
+			if (pte_swp_uffd_wp(*src_pte))
+				pte = pte_swp_mkuffd_wp(pte);
+			set_pte_at(src_mm, addr, src_pte, pte);
 		}
-		goto out_set_pte;
+	}
+	set_pte_at(dst_mm, addr, dst_pte, pte);
+	return 0;
+}
+
+/*
+ * Copy a present and normal page if necessary.
+ *
+ * NOTE! The usual case is that this doesn't need to do
+ * anything, and can just return a positive value. That
+ * will let the caller know that it can just increase
+ * the page refcount and re-use the pte the traditional
+ * way.
+ *
+ * But _if_ we need to copy it because it needs to be
+ * pinned in the parent (and the child should get its own
+ * copy rather than just a reference to the same page),
+ * we'll do that here and return zero to let the caller
+ * know we're done.
+ *
+ * And if we need a pre-allocated page but don't yet have
+ * one, return a negative error to let the preallocation
+ * code know so that it can do so outside the page table
+ * lock.
+ */
+static inline int
+copy_present_page(struct mm_struct *dst_mm, struct mm_struct *src_mm,
+		pte_t *dst_pte, pte_t *src_pte,
+		struct vm_area_struct *vma, struct vm_area_struct *new,
+		unsigned long addr, int *rss, struct page **prealloc,
+		pte_t pte, struct page *page)
+{
+	struct page *new_page;
+
+	if (!is_cow_mapping(vma->vm_flags))
+		return 1;
+
+	/*
+	 * What we want to do is to check whether this page may
+	 * have been pinned by the parent process.  If so,
+	 * instead of wrprotect the pte on both sides, we copy
+	 * the page immediately so that we'll always guarantee
+	 * the pinned page won't be randomly replaced in the
+	 * future.
+	 *
+	 * The page pinning checks are just "has this mm ever
+	 * seen pinning", along with the (inexact) check of
+	 * the page count. That might give false positives for
+	 * for pinning, but it will work correctly.
+	 */
+	if (likely(!atomic_read(&src_mm->has_pinned)))
+		return 1;
+	if (likely(!page_maybe_dma_pinned(page)))
+		return 1;
+
+	new_page = *prealloc;
+	if (!new_page)
+		return -EAGAIN;
+
+	/*
+	 * We have a prealloc page, all good!  Take it
+	 * over and copy the page & arm it.
+	 */
+	*prealloc = NULL;
+	copy_user_highpage(new_page, page, addr, vma);
+	__SetPageUptodate(new_page);
+	page_add_new_anon_rmap(new_page, new, addr, false);
+	lru_cache_add_inactive_or_unevictable(new_page, new);
+	rss[mm_counter(new_page)]++;
+
+	/* All done, just insert the new page copy in the child */
+	pte = mk_pte(new_page, new->vm_page_prot);
+	pte = maybe_mkwrite(pte_mkdirty(pte), new);
+	set_pte_at(dst_mm, addr, dst_pte, pte);
+	return 0;
+}
+
+/*
+ * Copy one pte.  Returns 0 if succeeded, or -EAGAIN if one preallocated page
+ * is required to copy this pte.
+ */
+static inline int
+copy_present_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
+		pte_t *dst_pte, pte_t *src_pte, struct vm_area_struct *vma,
+		struct vm_area_struct *new,
+		unsigned long addr, int *rss, struct page **prealloc)
+{
+	unsigned long vm_flags = vma->vm_flags;
+	pte_t pte = *src_pte;
+	struct page *page;
+
+	page = vm_normal_page(vma, addr, pte);
+	if (page) {
+		int retval;
+
+		retval = copy_present_page(dst_mm, src_mm,
+			dst_pte, src_pte,
+			vma, new,
+			addr, rss, prealloc,
+			pte, page);
+		if (retval <= 0)
+			return retval;
+
+		get_page(page);
+		page_dup_rmap(page, false);
+		rss[mm_counter(page)]++;
 	}
 
 	/*
@@ -798,35 +901,51 @@ copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 	if (!(vm_flags & VM_UFFD_WP))
 		pte = pte_clear_uffd_wp(pte);
 
-	page = vm_normal_page(vma, addr, pte);
-	if (page) {
-		get_page(page);
-		page_dup_rmap(page, false);
-		rss[mm_counter(page)]++;
-	}
-
-out_set_pte:
 	set_pte_at(dst_mm, addr, dst_pte, pte);
 	return 0;
 }
 
+static inline struct page *
+page_copy_prealloc(struct mm_struct *src_mm, struct vm_area_struct *vma,
+		   unsigned long addr)
+{
+	struct page *new_page;
+
+	new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, addr);
+	if (!new_page)
+		return NULL;
+
+	if (mem_cgroup_charge(new_page, src_mm, GFP_KERNEL)) {
+		put_page(new_page);
+		return NULL;
+	}
+	cgroup_throttle_swaprate(new_page, GFP_KERNEL);
+
+	return new_page;
+}
+
 static int copy_pte_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 		   pmd_t *dst_pmd, pmd_t *src_pmd, struct vm_area_struct *vma,
+		   struct vm_area_struct *new,
 		   unsigned long addr, unsigned long end)
 {
 	pte_t *orig_src_pte, *orig_dst_pte;
 	pte_t *src_pte, *dst_pte;
 	spinlock_t *src_ptl, *dst_ptl;
-	int progress = 0;
+	int progress, ret = 0;
 	int rss[NR_MM_COUNTERS];
 	swp_entry_t entry = (swp_entry_t){0};
+	struct page *prealloc = NULL;
 
 again:
+	progress = 0;
 	init_rss_vec(rss);
 
 	dst_pte = pte_alloc_map_lock(dst_mm, dst_pmd, addr, &dst_ptl);
-	if (!dst_pte)
-		return -ENOMEM;
+	if (!dst_pte) {
+		ret = -ENOMEM;
+		goto out;
+	}
 	src_pte = pte_offset_map(src_pmd, addr);
 	src_ptl = pte_lockptr(src_mm, src_pmd);
 	spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING);
@@ -849,10 +968,34 @@ again:
 			progress++;
 			continue;
 		}
-		entry.val = copy_one_pte(dst_mm, src_mm, dst_pte, src_pte,
+		if (unlikely(!pte_present(*src_pte))) {
+			entry.val = copy_nonpresent_pte(dst_mm, src_mm,
+							dst_pte, src_pte,
 							vma, addr, rss);
-		if (entry.val)
+			if (entry.val)
+				break;
+			progress += 8;
+			continue;
+		}
+		/* copy_present_pte() will clear `*prealloc' if consumed */
+		ret = copy_present_pte(dst_mm, src_mm, dst_pte, src_pte,
+				       vma, new, addr, rss, &prealloc);
+		/*
+		 * If we need a pre-allocated page for this pte, drop the
+		 * locks, allocate, and try again.
+		 */
+		if (unlikely(ret == -EAGAIN))
 			break;
+		if (unlikely(prealloc)) {
+			/*
+			 * pre-alloc page cannot be reused by next time so as
+			 * to strictly follow mempolicy (e.g., alloc_page_vma()
+			 * will allocate page according to address).  This
+			 * could only happen if one pinned pte changed.
+			 */
+			put_page(prealloc);
+			prealloc = NULL;
+		}
 		progress += 8;
 	} while (dst_pte++, src_pte++, addr += PAGE_SIZE, addr != end);
 
@@ -864,17 +1007,30 @@ again:
 	cond_resched();
 
 	if (entry.val) {
-		if (add_swap_count_continuation(entry, GFP_KERNEL) < 0)
+		if (add_swap_count_continuation(entry, GFP_KERNEL) < 0) {
+			ret = -ENOMEM;
+			goto out;
+		}
+		entry.val = 0;
+	} else if (ret) {
+		WARN_ON_ONCE(ret != -EAGAIN);
+		prealloc = page_copy_prealloc(src_mm, vma, addr);
+		if (!prealloc)
 			return -ENOMEM;
-		progress = 0;
+		/* We've captured and resolved the error. Reset, try again. */
+		ret = 0;
 	}
 	if (addr != end)
 		goto again;
-	return 0;
+out:
+	if (unlikely(prealloc))
+		put_page(prealloc);
+	return ret;
 }
 
 static inline int copy_pmd_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 		pud_t *dst_pud, pud_t *src_pud, struct vm_area_struct *vma,
+		struct vm_area_struct *new,
 		unsigned long addr, unsigned long end)
 {
 	pmd_t *src_pmd, *dst_pmd;
@@ -901,7 +1057,7 @@ static inline int copy_pmd_range(struct mm_struct *dst_mm, struct mm_struct *src
 		if (pmd_none_or_clear_bad(src_pmd))
 			continue;
 		if (copy_pte_range(dst_mm, src_mm, dst_pmd, src_pmd,
-						vma, addr, next))
+				   vma, new, addr, next))
 			return -ENOMEM;
 	} while (dst_pmd++, src_pmd++, addr = next, addr != end);
 	return 0;
@@ -909,6 +1065,7 @@ static inline int copy_pmd_range(struct mm_struct *dst_mm, struct mm_struct *src
 
 static inline int copy_pud_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 		p4d_t *dst_p4d, p4d_t *src_p4d, struct vm_area_struct *vma,
+		struct vm_area_struct *new,
 		unsigned long addr, unsigned long end)
 {
 	pud_t *src_pud, *dst_pud;
@@ -935,7 +1092,7 @@ static inline int copy_pud_range(struct mm_struct *dst_mm, struct mm_struct *src
 		if (pud_none_or_clear_bad(src_pud))
 			continue;
 		if (copy_pmd_range(dst_mm, src_mm, dst_pud, src_pud,
-						vma, addr, next))
+				   vma, new, addr, next))
 			return -ENOMEM;
 	} while (dst_pud++, src_pud++, addr = next, addr != end);
 	return 0;
@@ -943,6 +1100,7 @@ static inline int copy_pud_range(struct mm_struct *dst_mm, struct mm_struct *src
 
 static inline int copy_p4d_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 		pgd_t *dst_pgd, pgd_t *src_pgd, struct vm_area_struct *vma,
+		struct vm_area_struct *new,
 		unsigned long addr, unsigned long end)
 {
 	p4d_t *src_p4d, *dst_p4d;
@@ -957,14 +1115,14 @@ static inline int copy_p4d_range(struct mm_struct *dst_mm, struct mm_struct *src
 		if (p4d_none_or_clear_bad(src_p4d))
 			continue;
 		if (copy_pud_range(dst_mm, src_mm, dst_p4d, src_p4d,
-						vma, addr, next))
+				   vma, new, addr, next))
 			return -ENOMEM;
 	} while (dst_p4d++, src_p4d++, addr = next, addr != end);
 	return 0;
 }
 
 int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
-		struct vm_area_struct *vma)
+		    struct vm_area_struct *vma, struct vm_area_struct *new)
 {
 	pgd_t *src_pgd, *dst_pgd;
 	unsigned long next;
@@ -1019,7 +1177,7 @@ int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 		if (pgd_none_or_clear_bad(src_pgd))
 			continue;
 		if (unlikely(copy_p4d_range(dst_mm, src_mm, dst_pgd, src_pgd,
-					    vma, addr, next))) {
+					    vma, new, addr, next))) {
 			ret = -ENOMEM;
 			break;
 		}
@@ -2206,7 +2364,8 @@ EXPORT_SYMBOL(vm_iomap_memory);
 
 static int apply_to_pte_range(struct mm_struct *mm, pmd_t *pmd,
 				     unsigned long addr, unsigned long end,
-				     pte_fn_t fn, void *data, bool create)
+				     pte_fn_t fn, void *data, bool create,
+				     pgtbl_mod_mask *mask)
 {
 	pte_t *pte;
 	int err = 0;
@@ -2214,7 +2373,7 @@ static int apply_to_pte_range(struct mm_struct *mm, pmd_t *pmd,
 
 	if (create) {
 		pte = (mm == &init_mm) ?
-			pte_alloc_kernel(pmd, addr) :
+			pte_alloc_kernel_track(pmd, addr, mask) :
 			pte_alloc_map_lock(mm, pmd, addr, &ptl);
 		if (!pte)
 			return -ENOMEM;
@@ -2235,6 +2394,7 @@ static int apply_to_pte_range(struct mm_struct *mm, pmd_t *pmd,
 				break;
 		}
 	} while (addr += PAGE_SIZE, addr != end);
+	*mask |= PGTBL_PTE_MODIFIED;
 
 	arch_leave_lazy_mmu_mode();
 
@@ -2245,7 +2405,8 @@ static int apply_to_pte_range(struct mm_struct *mm, pmd_t *pmd,
 
 static int apply_to_pmd_range(struct mm_struct *mm, pud_t *pud,
 				     unsigned long addr, unsigned long end,
-				     pte_fn_t fn, void *data, bool create)
+				     pte_fn_t fn, void *data, bool create,
+				     pgtbl_mod_mask *mask)
 {
 	pmd_t *pmd;
 	unsigned long next;
@@ -2254,7 +2415,7 @@ static int apply_to_pmd_range(struct mm_struct *mm, pud_t *pud,
 	BUG_ON(pud_huge(*pud));
 
 	if (create) {
-		pmd = pmd_alloc(mm, pud, addr);
+		pmd = pmd_alloc_track(mm, pud, addr, mask);
 		if (!pmd)
 			return -ENOMEM;
 	} else {
@@ -2264,7 +2425,7 @@ static int apply_to_pmd_range(struct mm_struct *mm, pud_t *pud,
 		next = pmd_addr_end(addr, end);
 		if (create || !pmd_none_or_clear_bad(pmd)) {
 			err = apply_to_pte_range(mm, pmd, addr, next, fn, data,
-						 create);
+						 create, mask);
 			if (err)
 				break;
 		}
@@ -2274,14 +2435,15 @@ static int apply_to_pmd_range(struct mm_struct *mm, pud_t *pud,
 
 static int apply_to_pud_range(struct mm_struct *mm, p4d_t *p4d,
 				     unsigned long addr, unsigned long end,
-				     pte_fn_t fn, void *data, bool create)
+				     pte_fn_t fn, void *data, bool create,
+				     pgtbl_mod_mask *mask)
 {
 	pud_t *pud;
 	unsigned long next;
 	int err = 0;
 
 	if (create) {
-		pud = pud_alloc(mm, p4d, addr);
+		pud = pud_alloc_track(mm, p4d, addr, mask);
 		if (!pud)
 			return -ENOMEM;
 	} else {
@@ -2291,7 +2453,7 @@ static int apply_to_pud_range(struct mm_struct *mm, p4d_t *p4d,
 		next = pud_addr_end(addr, end);
 		if (create || !pud_none_or_clear_bad(pud)) {
 			err = apply_to_pmd_range(mm, pud, addr, next, fn, data,
-						 create);
+						 create, mask);
 			if (err)
 				break;
 		}
@@ -2301,14 +2463,15 @@ static int apply_to_pud_range(struct mm_struct *mm, p4d_t *p4d,
 
 static int apply_to_p4d_range(struct mm_struct *mm, pgd_t *pgd,
 				     unsigned long addr, unsigned long end,
-				     pte_fn_t fn, void *data, bool create)
+				     pte_fn_t fn, void *data, bool create,
+				     pgtbl_mod_mask *mask)
 {
 	p4d_t *p4d;
 	unsigned long next;
 	int err = 0;
 
 	if (create) {
-		p4d = p4d_alloc(mm, pgd, addr);
+		p4d = p4d_alloc_track(mm, pgd, addr, mask);
 		if (!p4d)
 			return -ENOMEM;
 	} else {
@@ -2318,7 +2481,7 @@ static int apply_to_p4d_range(struct mm_struct *mm, pgd_t *pgd,
 		next = p4d_addr_end(addr, end);
 		if (create || !p4d_none_or_clear_bad(p4d)) {
 			err = apply_to_pud_range(mm, p4d, addr, next, fn, data,
-						 create);
+						 create, mask);
 			if (err)
 				break;
 		}
@@ -2331,8 +2494,9 @@ static int __apply_to_page_range(struct mm_struct *mm, unsigned long addr,
 				 void *data, bool create)
 {
 	pgd_t *pgd;
-	unsigned long next;
+	unsigned long start = addr, next;
 	unsigned long end = addr + size;
+	pgtbl_mod_mask mask = 0;
 	int err = 0;
 
 	if (WARN_ON(addr >= end))
@@ -2343,11 +2507,14 @@ static int __apply_to_page_range(struct mm_struct *mm, unsigned long addr,
 		next = pgd_addr_end(addr, end);
 		if (!create && pgd_none_or_clear_bad(pgd))
 			continue;
-		err = apply_to_p4d_range(mm, pgd, addr, next, fn, data, create);
+		err = apply_to_p4d_range(mm, pgd, addr, next, fn, data, create, &mask);
 		if (err)
 			break;
 	} while (pgd++, addr = next, addr != end);
 
+	if (mask & ARCH_PAGE_TABLE_SYNC_MASK)
+		arch_sync_kernel_mappings(start, start + size);
+
 	return err;
 }
 
@@ -2622,6 +2789,7 @@ static inline void wp_page_reuse(struct vm_fault *vmf)
 	if (ptep_set_access_flags(vma, vmf->address, vmf->pte, entry, 1))
 		update_mmu_cache(vma, vmf->address, vmf->pte);
 	pte_unmap_unlock(vmf->pte, vmf->ptl);
+	count_vm_event(PGREUSE);
 }
 
 /*
@@ -2927,50 +3095,25 @@ static vm_fault_t do_wp_page(struct vm_fault *vmf)
 	 * not dirty accountable.
 	 */
 	if (PageAnon(vmf->page)) {
-		int total_map_swapcount;
-		if (PageKsm(vmf->page) && (PageSwapCache(vmf->page) ||
-					   page_count(vmf->page) != 1))
+		struct page *page = vmf->page;
+
+		/* PageKsm() doesn't necessarily raise the page refcount */
+		if (PageKsm(page) || page_count(page) != 1)
+			goto copy;
+		if (!trylock_page(page))
+			goto copy;
+		if (PageKsm(page) || page_mapcount(page) != 1 || page_count(page) != 1) {
+			unlock_page(page);
 			goto copy;
-		if (!trylock_page(vmf->page)) {
-			get_page(vmf->page);
-			pte_unmap_unlock(vmf->pte, vmf->ptl);
-			lock_page(vmf->page);
-			vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd,
-					vmf->address, &vmf->ptl);
-			if (!pte_same(*vmf->pte, vmf->orig_pte)) {
-				update_mmu_tlb(vma, vmf->address, vmf->pte);
-				unlock_page(vmf->page);
-				pte_unmap_unlock(vmf->pte, vmf->ptl);
-				put_page(vmf->page);
-				return 0;
-			}
-			put_page(vmf->page);
-		}
-		if (PageKsm(vmf->page)) {
-			bool reused = reuse_ksm_page(vmf->page, vmf->vma,
-						     vmf->address);
-			unlock_page(vmf->page);
-			if (!reused)
-				goto copy;
-			wp_page_reuse(vmf);
-			return VM_FAULT_WRITE;
-		}
-		if (reuse_swap_page(vmf->page, &total_map_swapcount)) {
-			if (total_map_swapcount == 1) {
-				/*
-				 * The page is all ours. Move it to
-				 * our anon_vma so the rmap code will
-				 * not search our parent or siblings.
-				 * Protected against the rmap code by
-				 * the page lock.
-				 */
-				page_move_anon_rmap(vmf->page, vma);
-			}
-			unlock_page(vmf->page);
-			wp_page_reuse(vmf);
-			return VM_FAULT_WRITE;
 		}
-		unlock_page(vmf->page);
+		/*
+		 * Ok, we've got the only map reference, and the only
+		 * page count reference, and the page is locked,
+		 * it's dark out, and we're wearing sunglasses. Hit it.
+		 */
+		unlock_page(page);
+		wp_page_reuse(vmf);
+		return VM_FAULT_WRITE;
 	} else if (unlikely((vma->vm_flags & (VM_WRITE|VM_SHARED)) ==
 					(VM_WRITE|VM_SHARED))) {
 		return wp_page_shared(vmf);
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index e9d5ab5d3ca0..ce3e73e3a5c1 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -729,7 +729,7 @@ void __ref move_pfn_range_to_zone(struct zone *zone, unsigned long start_pfn,
 	 * are reserved so nobody should be touching them so we should be safe
 	 */
 	memmap_init_zone(nr_pages, nid, zone_idx(zone), start_pfn,
-			MEMMAP_HOTPLUG, altmap);
+			 MEMINIT_HOTPLUG, altmap);
 
 	set_zone_contiguous(zone);
 }
@@ -1080,7 +1080,8 @@ int __ref add_memory_resource(int nid, struct resource *res)
 	}
 
 	/* link memory sections under this node.*/
-	ret = link_mem_sections(nid, PFN_DOWN(start), PFN_UP(start + size - 1));
+	ret = link_mem_sections(nid, PFN_DOWN(start), PFN_UP(start + size - 1),
+				MEMINIT_HOTPLUG);
 	BUG_ON(ret);
 
 	/* create new memmap entry */
@@ -1575,6 +1576,20 @@ static int __ref __offline_pages(unsigned long start_pfn,
 		/* check again */
 		ret = walk_system_ram_range(start_pfn, end_pfn - start_pfn,
 					    NULL, check_pages_isolated_cb);
+		/*
+		 * per-cpu pages are drained in start_isolate_page_range, but if
+		 * there are still pages that are not free, make sure that we
+		 * drain again, because when we isolated range we might
+		 * have raced with another thread that was adding pages to pcp
+		 * list.
+		 *
+		 * Forward progress should be still guaranteed because
+		 * pages on the pcp list can only belong to MOVABLE_ZONE
+		 * because has_unmovable_pages explicitly checks for
+		 * PageBuddy on freed pages on other zones.
+		 */
+		if (ret)
+			drain_all_pages(zone);
 	} while (ret);
 
 	/* Ok, all of our target is isolated.
diff --git a/mm/memremap.c b/mm/memremap.c
index 03e38b7a38f1..006dace60b1a 100644
--- a/mm/memremap.c
+++ b/mm/memremap.c
@@ -216,7 +216,7 @@ void *memremap_pages(struct dev_pagemap *pgmap, int nid)
 			return ERR_PTR(-EINVAL);
 		}
 		break;
-	case MEMORY_DEVICE_DEVDAX:
+	case MEMORY_DEVICE_GENERIC:
 		need_devmap_managed = false;
 		break;
 	case MEMORY_DEVICE_PCI_P2PDMA:
diff --git a/mm/migrate.c b/mm/migrate.c
index 34a842a8eb6a..04a98bb2f568 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -246,13 +246,13 @@ static bool remove_migration_pte(struct page *page, struct vm_area_struct *vma,
 		else if (pte_swp_uffd_wp(*pvmw.pte))
 			pte = pte_mkuffd_wp(pte);
 
-		if (unlikely(is_zone_device_page(new))) {
-			if (is_device_private_page(new)) {
-				entry = make_device_private_entry(new, pte_write(pte));
-				pte = swp_entry_to_pte(entry);
-				if (pte_swp_uffd_wp(*pvmw.pte))
-					pte = pte_mkuffd_wp(pte);
-			}
+		if (unlikely(is_device_private_page(new))) {
+			entry = make_device_private_entry(new, pte_write(pte));
+			pte = swp_entry_to_pte(entry);
+			if (pte_swp_soft_dirty(*pvmw.pte))
+				pte = pte_swp_mksoft_dirty(pte);
+			if (pte_swp_uffd_wp(*pvmw.pte))
+				pte = pte_swp_mkuffd_wp(pte);
 		}
 
 #ifdef CONFIG_HUGETLB_PAGE
@@ -668,7 +668,8 @@ void migrate_page_states(struct page *newpage, struct page *page)
 
 	copy_page_owner(page, newpage);
 
-	mem_cgroup_migrate(page, newpage);
+	if (!PageHuge(page))
+		mem_cgroup_migrate(page, newpage);
 }
 EXPORT_SYMBOL(migrate_page_states);
 
@@ -1445,7 +1446,7 @@ retry:
 			 * Capture required information that might get lost
 			 * during migration.
 			 */
-			is_thp = PageTransHuge(page);
+			is_thp = PageTransHuge(page) && !PageHuge(page);
 			nr_subpages = thp_nr_pages(page);
 			cond_resched();
 
@@ -1471,7 +1472,7 @@ retry:
 				 * we encounter them after the rest of the list
 				 * is processed.
 				 */
-				if (PageTransHuge(page) && !PageHuge(page)) {
+				if (is_thp) {
 					lock_page(page);
 					rc = split_huge_page_to_list(page, from);
 					unlock_page(page);
@@ -1480,8 +1481,7 @@ retry:
 						nr_thp_split++;
 						goto retry;
 					}
-				}
-				if (is_thp) {
+
 					nr_thp_failed++;
 					nr_failed += nr_subpages;
 					goto out;
@@ -2427,10 +2427,17 @@ again:
 			entry = make_migration_entry(page, mpfn &
 						     MIGRATE_PFN_WRITE);
 			swp_pte = swp_entry_to_pte(entry);
-			if (pte_soft_dirty(pte))
-				swp_pte = pte_swp_mksoft_dirty(swp_pte);
-			if (pte_uffd_wp(pte))
-				swp_pte = pte_swp_mkuffd_wp(swp_pte);
+			if (pte_present(pte)) {
+				if (pte_soft_dirty(pte))
+					swp_pte = pte_swp_mksoft_dirty(swp_pte);
+				if (pte_uffd_wp(pte))
+					swp_pte = pte_swp_mkuffd_wp(swp_pte);
+			} else {
+				if (pte_swp_soft_dirty(pte))
+					swp_pte = pte_swp_mksoft_dirty(swp_pte);
+				if (pte_swp_uffd_wp(pte))
+					swp_pte = pte_swp_mkuffd_wp(swp_pte);
+			}
 			set_pte_at(mm, addr, ptep, swp_pte);
 
 			/*
diff --git a/mm/mlock.c b/mm/mlock.c
index 93ca2bf30b4f..884b1216da6a 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -58,11 +58,14 @@ EXPORT_SYMBOL(can_do_mlock);
  */
 void clear_page_mlock(struct page *page)
 {
+	int nr_pages;
+
 	if (!TestClearPageMlocked(page))
 		return;
 
-	mod_zone_page_state(page_zone(page), NR_MLOCK, -thp_nr_pages(page));
-	count_vm_event(UNEVICTABLE_PGCLEARED);
+	nr_pages = thp_nr_pages(page);
+	mod_zone_page_state(page_zone(page), NR_MLOCK, -nr_pages);
+	count_vm_events(UNEVICTABLE_PGCLEARED, nr_pages);
 	/*
 	 * The previous TestClearPageMlocked() corresponds to the smp_mb()
 	 * in __pagevec_lru_add_fn().
@@ -76,7 +79,7 @@ void clear_page_mlock(struct page *page)
 		 * We lost the race. the page already moved to evictable list.
 		 */
 		if (PageUnevictable(page))
-			count_vm_event(UNEVICTABLE_PGSTRANDED);
+			count_vm_events(UNEVICTABLE_PGSTRANDED, nr_pages);
 	}
 }
 
@@ -93,9 +96,10 @@ void mlock_vma_page(struct page *page)
 	VM_BUG_ON_PAGE(PageCompound(page) && PageDoubleMap(page), page);
 
 	if (!TestSetPageMlocked(page)) {
-		mod_zone_page_state(page_zone(page), NR_MLOCK,
-				    thp_nr_pages(page));
-		count_vm_event(UNEVICTABLE_PGMLOCKED);
+		int nr_pages = thp_nr_pages(page);
+
+		mod_zone_page_state(page_zone(page), NR_MLOCK, nr_pages);
+		count_vm_events(UNEVICTABLE_PGMLOCKED, nr_pages);
 		if (!isolate_lru_page(page))
 			putback_lru_page(page);
 	}
@@ -138,7 +142,7 @@ static void __munlock_isolated_page(struct page *page)
 
 	/* Did try_to_unlock() succeed or punt? */
 	if (!PageMlocked(page))
-		count_vm_event(UNEVICTABLE_PGMUNLOCKED);
+		count_vm_events(UNEVICTABLE_PGMUNLOCKED, thp_nr_pages(page));
 
 	putback_lru_page(page);
 }
@@ -154,10 +158,12 @@ static void __munlock_isolated_page(struct page *page)
  */
 static void __munlock_isolation_failed(struct page *page)
 {
+	int nr_pages = thp_nr_pages(page);
+
 	if (PageUnevictable(page))
-		__count_vm_event(UNEVICTABLE_PGSTRANDED);
+		__count_vm_events(UNEVICTABLE_PGSTRANDED, nr_pages);
 	else
-		__count_vm_event(UNEVICTABLE_PGMUNLOCKED);
+		__count_vm_events(UNEVICTABLE_PGMUNLOCKED, nr_pages);
 }
 
 /**
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index fab5e97dc9ca..6866533de8e6 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -3367,9 +3367,16 @@ struct page *rmqueue(struct zone *preferred_zone,
 	struct page *page;
 
 	if (likely(order == 0)) {
-		page = rmqueue_pcplist(preferred_zone, zone, gfp_flags,
+		/*
+		 * MIGRATE_MOVABLE pcplist could have the pages on CMA area and
+		 * we need to skip it when CMA area isn't allowed.
+		 */
+		if (!IS_ENABLED(CONFIG_CMA) || alloc_flags & ALLOC_CMA ||
+				migratetype != MIGRATE_MOVABLE) {
+			page = rmqueue_pcplist(preferred_zone, zone, gfp_flags,
 					migratetype, alloc_flags);
-		goto out;
+			goto out;
+		}
 	}
 
 	/*
@@ -3381,7 +3388,13 @@ struct page *rmqueue(struct zone *preferred_zone,
 
 	do {
 		page = NULL;
-		if (alloc_flags & ALLOC_HARDER) {
+		/*
+		 * order-0 request can reach here when the pcplist is skipped
+		 * due to non-CMA allocation context. HIGHATOMIC area is
+		 * reserved for high-order atomic allocation, so order-0
+		 * request should skip it.
+		 */
+		if (order > 0 && alloc_flags & ALLOC_HARDER) {
 			page = __rmqueue_smallest(zone, order, MIGRATE_HIGHATOMIC);
 			if (page)
 				trace_mm_page_alloc_zone_locked(page, order, migratetype);
@@ -5975,7 +5988,7 @@ overlap_memmap_init(unsigned long zone, unsigned long *pfn)
  * done. Non-atomic initialization, single-pass.
  */
 void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone,
-		unsigned long start_pfn, enum memmap_context context,
+		unsigned long start_pfn, enum meminit_context context,
 		struct vmem_altmap *altmap)
 {
 	unsigned long pfn, end_pfn = start_pfn + size;
@@ -6007,7 +6020,7 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone,
 		 * There can be holes in boot-time mem_map[]s handed to this
 		 * function.  They do not exist on hotplugged memory.
 		 */
-		if (context == MEMMAP_EARLY) {
+		if (context == MEMINIT_EARLY) {
 			if (overlap_memmap_init(zone, &pfn))
 				continue;
 			if (defer_init(nid, pfn, end_pfn))
@@ -6016,7 +6029,7 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone,
 
 		page = pfn_to_page(pfn);
 		__init_single_page(page, pfn, zone, nid);
-		if (context == MEMMAP_HOTPLUG)
+		if (context == MEMINIT_HOTPLUG)
 			__SetPageReserved(page);
 
 		/*
@@ -6099,7 +6112,7 @@ void __ref memmap_init_zone_device(struct zone *zone,
 		 * check here not to call set_pageblock_migratetype() against
 		 * pfn out of zone.
 		 *
-		 * Please note that MEMMAP_HOTPLUG path doesn't clear memmap
+		 * Please note that MEMINIT_HOTPLUG path doesn't clear memmap
 		 * because this is done early in section_activate()
 		 */
 		if (!(pfn & (pageblock_nr_pages - 1))) {
@@ -6137,7 +6150,7 @@ void __meminit __weak memmap_init(unsigned long size, int nid,
 		if (end_pfn > start_pfn) {
 			size = end_pfn - start_pfn;
 			memmap_init_zone(size, nid, zone, start_pfn,
-					 MEMMAP_EARLY, NULL);
+					 MEMINIT_EARLY, NULL);
 		}
 	}
 }
diff --git a/mm/page_isolation.c b/mm/page_isolation.c
index 242c03121d73..63a3db10a8c0 100644
--- a/mm/page_isolation.c
+++ b/mm/page_isolation.c
@@ -170,6 +170,14 @@ __first_valid_page(unsigned long pfn, unsigned long nr_pages)
  * pageblocks we may have modified and return -EBUSY to caller. This
  * prevents two threads from simultaneously working on overlapping ranges.
  *
+ * Please note that there is no strong synchronization with the page allocator
+ * either. Pages might be freed while their page blocks are marked ISOLATED.
+ * In some cases pages might still end up on pcp lists and that would allow
+ * for their allocation even when they are in fact isolated already. Depending
+ * on how strong of a guarantee the caller needs drain_all_pages might be needed
+ * (e.g. __offline_pages will need to call it after check for isolated range for
+ * a next retry).
+ *
  * Return: the number of isolated pageblocks on success and -EBUSY if any part
  * of range cannot be isolated.
  */
diff --git a/mm/percpu.c b/mm/percpu.c
index f4709629e6de..1ed1a349eab8 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -1316,7 +1316,7 @@ static struct pcpu_chunk * __init pcpu_alloc_first_chunk(unsigned long tmp_addr,
 
 	/* allocate chunk */
 	alloc_size = sizeof(struct pcpu_chunk) +
-		BITS_TO_LONGS(region_size >> PAGE_SHIFT);
+		BITS_TO_LONGS(region_size >> PAGE_SHIFT) * sizeof(unsigned long);
 	chunk = memblock_alloc(alloc_size, SMP_CACHE_BYTES);
 	if (!chunk)
 		panic("%s: Failed to allocate %zu bytes\n", __func__,
diff --git a/mm/rmap.c b/mm/rmap.c
index 83cc459edc40..9425260774a1 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1511,9 +1511,14 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
 			 */
 			entry = make_migration_entry(page, 0);
 			swp_pte = swp_entry_to_pte(entry);
-			if (pte_soft_dirty(pteval))
+
+			/*
+			 * pteval maps a zone device page and is therefore
+			 * a swap pte.
+			 */
+			if (pte_swp_soft_dirty(pteval))
 				swp_pte = pte_swp_mksoft_dirty(swp_pte);
-			if (pte_uffd_wp(pteval))
+			if (pte_swp_uffd_wp(pteval))
 				swp_pte = pte_swp_mkuffd_wp(swp_pte);
 			set_pte_at(mm, pvmw.address, pvmw.pte, swp_pte);
 			/*
diff --git a/mm/shmem.c b/mm/shmem.c
index 271548ca20f3..8e2b35ba93ad 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -279,11 +279,13 @@ static int shmem_reserve_inode(struct super_block *sb, ino_t *inop)
 
 	if (!(sb->s_flags & SB_KERNMOUNT)) {
 		spin_lock(&sbinfo->stat_lock);
-		if (!sbinfo->free_inodes) {
-			spin_unlock(&sbinfo->stat_lock);
-			return -ENOSPC;
+		if (sbinfo->max_inodes) {
+			if (!sbinfo->free_inodes) {
+				spin_unlock(&sbinfo->stat_lock);
+				return -ENOSPC;
+			}
+			sbinfo->free_inodes--;
 		}
-		sbinfo->free_inodes--;
 		if (inop) {
 			ino = sbinfo->next_ino++;
 			if (unlikely(is_zero_ino(ino)))
diff --git a/mm/slab.c b/mm/slab.c
index 3160dff6fd76..f658e86ec8ce 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -1632,6 +1632,10 @@ static void slab_destroy(struct kmem_cache *cachep, struct page *page)
 		kmem_cache_free(cachep->freelist_cache, freelist);
 }
 
+/*
+ * Update the size of the caches before calling slabs_destroy as it may
+ * recursively call kfree.
+ */
 static void slabs_destroy(struct kmem_cache *cachep, struct list_head *list)
 {
 	struct page *page, *n;
@@ -2153,8 +2157,8 @@ static void do_drain(void *arg)
 	spin_lock(&n->list_lock);
 	free_block(cachep, ac->entry, ac->avail, node, &list);
 	spin_unlock(&n->list_lock);
-	slabs_destroy(cachep, &list);
 	ac->avail = 0;
+	slabs_destroy(cachep, &list);
 }
 
 static void drain_cpu_caches(struct kmem_cache *cachep)
@@ -3402,9 +3406,9 @@ free_done:
 	}
 #endif
 	spin_unlock(&n->list_lock);
-	slabs_destroy(cachep, &list);
 	ac->avail -= batchcount;
 	memmove(ac->entry, &(ac->entry[batchcount]), sizeof(void *)*ac->avail);
+	slabs_destroy(cachep, &list);
 }
 
 /*
diff --git a/mm/slub.c b/mm/slub.c
index 68c02b2eecd9..6d3574013b2f 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -672,12 +672,12 @@ static void slab_fix(struct kmem_cache *s, char *fmt, ...)
 }
 
 static bool freelist_corrupted(struct kmem_cache *s, struct page *page,
-			       void *freelist, void *nextfree)
+			       void **freelist, void *nextfree)
 {
 	if ((s->flags & SLAB_CONSISTENCY_CHECKS) &&
-	    !check_valid_pointer(s, page, nextfree)) {
-		object_err(s, page, freelist, "Freechain corrupt");
-		freelist = NULL;
+	    !check_valid_pointer(s, page, nextfree) && freelist) {
+		object_err(s, page, *freelist, "Freechain corrupt");
+		*freelist = NULL;
 		slab_fix(s, "Isolate corrupted freechain");
 		return true;
 	}
@@ -1413,10 +1413,6 @@ slab_flags_t kmem_cache_flags(unsigned int object_size,
 	char *next_block;
 	slab_flags_t block_flags;
 
-	/* If slub_debug = 0, it folds into the if conditional. */
-	if (!slub_debug_string)
-		return flags | slub_debug;
-
 	len = strlen(name);
 	next_block = slub_debug_string;
 	/* Go through all blocks of debug options, see if any matches our slab's name */
@@ -1450,7 +1446,7 @@ slab_flags_t kmem_cache_flags(unsigned int object_size,
 		}
 	}
 
-	return slub_debug;
+	return flags | slub_debug;
 }
 #else /* !CONFIG_SLUB_DEBUG */
 static inline void setup_object_debug(struct kmem_cache *s,
@@ -1494,7 +1490,7 @@ static inline void dec_slabs_node(struct kmem_cache *s, int node,
 							int objects) {}
 
 static bool freelist_corrupted(struct kmem_cache *s, struct page *page,
-			       void *freelist, void *nextfree)
+			       void **freelist, void *nextfree)
 {
 	return false;
 }
@@ -2184,7 +2180,7 @@ static void deactivate_slab(struct kmem_cache *s, struct page *page,
 		 * 'freelist' is already corrupted.  So isolate all objects
 		 * starting at 'freelist'.
 		 */
-		if (freelist_corrupted(s, page, freelist, nextfree))
+		if (freelist_corrupted(s, page, &freelist, nextfree))
 			break;
 
 		do {
diff --git a/mm/swap.c b/mm/swap.c
index a1ec807e325d..65ef7e3525bf 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -494,14 +494,14 @@ void lru_cache_add_inactive_or_unevictable(struct page *page,
 
 	unevictable = (vma->vm_flags & (VM_LOCKED | VM_SPECIAL)) == VM_LOCKED;
 	if (unlikely(unevictable) && !TestSetPageMlocked(page)) {
+		int nr_pages = thp_nr_pages(page);
 		/*
 		 * We use the irq-unsafe __mod_zone_page_stat because this
 		 * counter is not modified from interrupt context, and the pte
 		 * lock is held(spinlock), which implies preemption disabled.
 		 */
-		__mod_zone_page_state(page_zone(page), NR_MLOCK,
-				    thp_nr_pages(page));
-		count_vm_event(UNEVICTABLE_PGMLOCKED);
+		__mod_zone_page_state(page_zone(page), NR_MLOCK, nr_pages);
+		count_vm_events(UNEVICTABLE_PGMLOCKED, nr_pages);
 	}
 	lru_cache_add(page);
 }
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 12f59e641b5e..debc94155f74 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -1078,7 +1078,7 @@ start_over:
 			goto nextsi;
 		}
 		if (size == SWAPFILE_CLUSTER) {
-			if (!(si->flags & SWP_FS))
+			if (si->flags & SWP_BLKDEV)
 				n_ret = swap_alloc_cluster(si, swp_entries);
 		} else
 			n_ret = scan_swap_map_slots(si, SWAP_HAS_CACHE,
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 99e1796eb833..466fc3144fff 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2615,6 +2615,14 @@ static void shrink_node_memcgs(pg_data_t *pgdat, struct scan_control *sc)
 		unsigned long reclaimed;
 		unsigned long scanned;
 
+		/*
+		 * This loop can become CPU-bound when target memcgs
+		 * aren't eligible for reclaim - either because they
+		 * don't have any reclaimable pages, or because their
+		 * memory is explicitly protected. Avoid soft lockups.
+		 */
+		cond_resched();
+
 		mem_cgroup_calculate_protection(target_memcg, memcg);
 
 		if (mem_cgroup_below_min(memcg)) {
@@ -4260,8 +4268,14 @@ void check_move_unevictable_pages(struct pagevec *pvec)
 	for (i = 0; i < pvec->nr; i++) {
 		struct page *page = pvec->pages[i];
 		struct pglist_data *pagepgdat = page_pgdat(page);
+		int nr_pages;
+
+		if (PageTransTail(page))
+			continue;
+
+		nr_pages = thp_nr_pages(page);
+		pgscanned += nr_pages;
 
-		pgscanned++;
 		if (pagepgdat != pgdat) {
 			if (pgdat)
 				spin_unlock_irq(&pgdat->lru_lock);
@@ -4280,7 +4294,7 @@ void check_move_unevictable_pages(struct pagevec *pvec)
 			ClearPageUnevictable(page);
 			del_page_from_lru_list(page, lruvec, LRU_UNEVICTABLE);
 			add_page_to_lru_list(page, lruvec, lru);
-			pgrescued++;
+			pgrescued += nr_pages;
 		}
 	}
 
diff --git a/mm/vmstat.c b/mm/vmstat.c
index e670f910cd2f..4f7b4ee6aa12 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1241,6 +1241,7 @@ const char * const vmstat_text[] = {
 	"pglazyfreed",
 
 	"pgrefill",
+	"pgreuse",
 	"pgsteal_kswapd",
 	"pgsteal_direct",
 	"pgscan_kswapd",