Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

11 files changed, 112 insertions, 78 deletions

diff --git a/mm/compaction.c b/mm/compaction.c
index e5acb9714436..190ccdaa6c19 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -1342,7 +1342,7 @@ fast_isolate_freepages(struct compact_control *cc)
 {
 	unsigned int limit = min(1U, freelist_scan_limit(cc) >> 1);
 	unsigned int nr_scanned = 0;
-	unsigned long low_pfn, min_pfn, high_pfn = 0, highest = 0;
+	unsigned long low_pfn, min_pfn, highest = 0;
 	unsigned long nr_isolated = 0;
 	unsigned long distance;
 	struct page *page = NULL;
@@ -1387,6 +1387,7 @@ fast_isolate_freepages(struct compact_control *cc)
 		struct page *freepage;
 		unsigned long flags;
 		unsigned int order_scanned = 0;
+		unsigned long high_pfn = 0;
 
 		if (!area->nr_free)
 			continue;
diff --git a/mm/filemap.c b/mm/filemap.c
index 5c9d564317a5..aa0e0fb04670 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -835,6 +835,7 @@ noinline int __add_to_page_cache_locked(struct page *page,
 	XA_STATE(xas, &mapping->i_pages, offset);
 	int huge = PageHuge(page);
 	int error;
+	bool charged = false;
 
 	VM_BUG_ON_PAGE(!PageLocked(page), page);
 	VM_BUG_ON_PAGE(PageSwapBacked(page), page);
@@ -848,6 +849,7 @@ noinline int __add_to_page_cache_locked(struct page *page,
 		error = mem_cgroup_charge(page, current->mm, gfp);
 		if (error)
 			goto error;
+		charged = true;
 	}
 
 	gfp &= GFP_RECLAIM_MASK;
@@ -896,6 +898,8 @@ unlock:
 
 	if (xas_error(&xas)) {
 		error = xas_error(&xas);
+		if (charged)
+			mem_cgroup_uncharge(page);
 		goto error;
 	}
 
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 9237976abe72..91ca9b103ee5 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -2202,7 +2202,7 @@ void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
 {
 	spinlock_t *ptl;
 	struct mmu_notifier_range range;
-	bool was_locked = false;
+	bool do_unlock_page = false;
 	pmd_t _pmd;
 
 	mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, vma->vm_mm,
@@ -2218,7 +2218,6 @@ void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
 	VM_BUG_ON(freeze && !page);
 	if (page) {
 		VM_WARN_ON_ONCE(!PageLocked(page));
-		was_locked = true;
 		if (page != pmd_page(*pmd))
 			goto out;
 	}
@@ -2227,19 +2226,29 @@ repeat:
 	if (pmd_trans_huge(*pmd)) {
 		if (!page) {
 			page = pmd_page(*pmd);
-			if (unlikely(!trylock_page(page))) {
-				get_page(page);
-				_pmd = *pmd;
-				spin_unlock(ptl);
-				lock_page(page);
-				spin_lock(ptl);
-				if (unlikely(!pmd_same(*pmd, _pmd))) {
-					unlock_page(page);
+			/*
+			 * An anonymous page must be locked, to ensure that a
+			 * concurrent reuse_swap_page() sees stable mapcount;
+			 * but reuse_swap_page() is not used on shmem or file,
+			 * and page lock must not be taken when zap_pmd_range()
+			 * calls __split_huge_pmd() while i_mmap_lock is held.
+			 */
+			if (PageAnon(page)) {
+				if (unlikely(!trylock_page(page))) {
+					get_page(page);
+					_pmd = *pmd;
+					spin_unlock(ptl);
+					lock_page(page);
+					spin_lock(ptl);
+					if (unlikely(!pmd_same(*pmd, _pmd))) {
+						unlock_page(page);
+						put_page(page);
+						page = NULL;
+						goto repeat;
+					}
 					put_page(page);
-					page = NULL;
-					goto repeat;
 				}
-				put_page(page);
+				do_unlock_page = true;
 			}
 		}
 		if (PageMlocked(page))
@@ -2249,7 +2258,7 @@ repeat:
 	__split_huge_pmd_locked(vma, pmd, range.start, freeze);
 out:
 	spin_unlock(ptl);
-	if (!was_locked && page)
+	if (do_unlock_page)
 		unlock_page(page);
 	/*
 	 * No need to double call mmu_notifier->invalidate_range() callback.
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 18f6ee317900..4bdb58ab14cb 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -79,6 +79,21 @@ DEFINE_SPINLOCK(hugetlb_lock);
 static int num_fault_mutexes;
 struct mutex *hugetlb_fault_mutex_table ____cacheline_aligned_in_smp;
 
+static inline bool PageHugeFreed(struct page *head)
+{
+	return page_private(head + 4) == -1UL;
+}
+
+static inline void SetPageHugeFreed(struct page *head)
+{
+	set_page_private(head + 4, -1UL);
+}
+
+static inline void ClearPageHugeFreed(struct page *head)
+{
+	set_page_private(head + 4, 0);
+}
+
 /* Forward declaration */
 static int hugetlb_acct_memory(struct hstate *h, long delta);
 
@@ -1028,6 +1043,7 @@ static void enqueue_huge_page(struct hstate *h, struct page *page)
 	list_move(&page->lru, &h->hugepage_freelists[nid]);
 	h->free_huge_pages++;
 	h->free_huge_pages_node[nid]++;
+	SetPageHugeFreed(page);
 }
 
 static struct page *dequeue_huge_page_node_exact(struct hstate *h, int nid)
@@ -1044,6 +1060,7 @@ static struct page *dequeue_huge_page_node_exact(struct hstate *h, int nid)
 
 		list_move(&page->lru, &h->hugepage_activelist);
 		set_page_refcounted(page);
+		ClearPageHugeFreed(page);
 		h->free_huge_pages--;
 		h->free_huge_pages_node[nid]--;
 		return page;
@@ -1344,12 +1361,11 @@ struct hstate *size_to_hstate(unsigned long size)
  */
 bool page_huge_active(struct page *page)
 {
-	VM_BUG_ON_PAGE(!PageHuge(page), page);
-	return PageHead(page) && PagePrivate(&page[1]);
+	return PageHeadHuge(page) && PagePrivate(&page[1]);
 }
 
 /* never called for tail page */
-static void set_page_huge_active(struct page *page)
+void set_page_huge_active(struct page *page)
 {
 	VM_BUG_ON_PAGE(!PageHeadHuge(page), page);
 	SetPagePrivate(&page[1]);
@@ -1505,6 +1521,7 @@ static void prep_new_huge_page(struct hstate *h, struct page *page, int nid)
 	spin_lock(&hugetlb_lock);
 	h->nr_huge_pages++;
 	h->nr_huge_pages_node[nid]++;
+	ClearPageHugeFreed(page);
 	spin_unlock(&hugetlb_lock);
 }
 
@@ -1755,6 +1772,7 @@ int dissolve_free_huge_page(struct page *page)
 {
 	int rc = -EBUSY;
 
+retry:
 	/* Not to disrupt normal path by vainly holding hugetlb_lock */
 	if (!PageHuge(page))
 		return 0;
@@ -1771,6 +1789,26 @@ int dissolve_free_huge_page(struct page *page)
 		int nid = page_to_nid(head);
 		if (h->free_huge_pages - h->resv_huge_pages == 0)
 			goto out;
+
+		/*
+		 * We should make sure that the page is already on the free list
+		 * when it is dissolved.
+		 */
+		if (unlikely(!PageHugeFreed(head))) {
+			spin_unlock(&hugetlb_lock);
+			cond_resched();
+
+			/*
+			 * Theoretically, we should return -EBUSY when we
+			 * encounter this race. In fact, we have a chance
+			 * to successfully dissolve the page if we do a
+			 * retry. Because the race window is quite small.
+			 * If we seize this opportunity, it is an optimization
+			 * for increasing the success rate of dissolving page.
+			 */
+			goto retry;
+		}
+
 		/*
 		 * Move PageHWPoison flag from head page to the raw error page,
 		 * which makes any subpages rather than the error page reusable.
@@ -2009,13 +2047,16 @@ retry:
 
 	/* Free the needed pages to the hugetlb pool */
 	list_for_each_entry_safe(page, tmp, &surplus_list, lru) {
+		int zeroed;
+
 		if ((--needed) < 0)
 			break;
 		/*
 		 * This page is now managed by the hugetlb allocator and has
 		 * no users -- drop the buddy allocator's reference.
 		 */
-		VM_BUG_ON_PAGE(!put_page_testzero(page), page);
+		zeroed = put_page_testzero(page);
+		VM_BUG_ON_PAGE(!zeroed, page);
 		enqueue_huge_page(h, page);
 	}
 free:
@@ -5555,9 +5596,9 @@ bool isolate_huge_page(struct page *page, struct list_head *list)
 {
 	bool ret = true;
 
-	VM_BUG_ON_PAGE(!PageHead(page), page);
 	spin_lock(&hugetlb_lock);
-	if (!page_huge_active(page) || !get_page_unless_zero(page)) {
+	if (!PageHeadHuge(page) || !page_huge_active(page) ||
+	    !get_page_unless_zero(page)) {
 		ret = false;
 		goto unlock;
 	}
diff --git a/mm/kasan/hw_tags.c b/mm/kasan/hw_tags.c
index e529428e7a11..d558799b25b3 100644
--- a/mm/kasan/hw_tags.c
+++ b/mm/kasan/hw_tags.c
@@ -134,12 +134,8 @@ void __init kasan_init_hw_tags(void)
 
 	switch (kasan_arg_stacktrace) {
 	case KASAN_ARG_STACKTRACE_DEFAULT:
-		/*
-		 * Default to enabling stack trace collection for
-		 * debug kernels.
-		 */
-		if (IS_ENABLED(CONFIG_DEBUG_KERNEL))
-			static_branch_enable(&kasan_flag_stacktrace);
+		/* Default to enabling stack trace collection. */
+		static_branch_enable(&kasan_flag_stacktrace);
 		break;
 	case KASAN_ARG_STACKTRACE_OFF:
 		/* Do nothing, kasan_flag_stacktrace keeps its default value. */
diff --git a/mm/kasan/kasan.h b/mm/kasan/kasan.h
index cc4d9e1d49b1..8c706e7652f2 100644
--- a/mm/kasan/kasan.h
+++ b/mm/kasan/kasan.h
@@ -209,7 +209,7 @@ bool check_memory_region(unsigned long addr, size_t size, bool write,
 
 static inline bool addr_has_metadata(const void *addr)
 {
-	return true;
+	return (is_vmalloc_addr(addr) || virt_addr_valid(addr));
 }
 
 #endif /* CONFIG_KASAN_GENERIC || CONFIG_KASAN_SW_TAGS */
diff --git a/mm/memblock.c b/mm/memblock.c
index 1eaaec1e7687..8d9b5f1e7040 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -275,14 +275,6 @@ __memblock_find_range_top_down(phys_addr_t start, phys_addr_t end,
  *
  * Find @size free area aligned to @align in the specified range and node.
  *
- * When allocation direction is bottom-up, the @start should be greater
- * than the end of the kernel image. Otherwise, it will be trimmed. The
- * reason is that we want the bottom-up allocation just near the kernel
- * image so it is highly likely that the allocated memory and the kernel
- * will reside in the same node.
- *
- * If bottom-up allocation failed, will try to allocate memory top-down.
- *
  * Return:
  * Found address on success, 0 on failure.
  */
@@ -291,8 +283,6 @@ static phys_addr_t __init_memblock memblock_find_in_range_node(phys_addr_t size,
 					phys_addr_t end, int nid,
 					enum memblock_flags flags)
 {
-	phys_addr_t kernel_end, ret;
-
 	/* pump up @end */
 	if (end == MEMBLOCK_ALLOC_ACCESSIBLE ||
 	    end == MEMBLOCK_ALLOC_KASAN)
@@ -301,40 +291,13 @@ static phys_addr_t __init_memblock memblock_find_in_range_node(phys_addr_t size,
 	/* avoid allocating the first page */
 	start = max_t(phys_addr_t, start, PAGE_SIZE);
 	end = max(start, end);
-	kernel_end = __pa_symbol(_end);
-
-	/*
-	 * try bottom-up allocation only when bottom-up mode
-	 * is set and @end is above the kernel image.
-	 */
-	if (memblock_bottom_up() && end > kernel_end) {
-		phys_addr_t bottom_up_start;
-
-		/* make sure we will allocate above the kernel */
-		bottom_up_start = max(start, kernel_end);
 
-		/* ok, try bottom-up allocation first */
-		ret = __memblock_find_range_bottom_up(bottom_up_start, end,
-						      size, align, nid, flags);
-		if (ret)
-			return ret;
-
-		/*
-		 * we always limit bottom-up allocation above the kernel,
-		 * but top-down allocation doesn't have the limit, so
-		 * retrying top-down allocation may succeed when bottom-up
-		 * allocation failed.
-		 *
-		 * bottom-up allocation is expected to be fail very rarely,
-		 * so we use WARN_ONCE() here to see the stack trace if
-		 * fail happens.
-		 */
-		WARN_ONCE(IS_ENABLED(CONFIG_MEMORY_HOTREMOVE),
-			  "memblock: bottom-up allocation failed, memory hotremove may be affected\n");
-	}
-
-	return __memblock_find_range_top_down(start, end, size, align, nid,
-					      flags);
+	if (memblock_bottom_up())
+		return __memblock_find_range_bottom_up(start, end, size, align,
+						       nid, flags);
+	else
+		return __memblock_find_range_top_down(start, end, size, align,
+						      nid, flags);
 }
 
 /**
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index e2de77b5bcc2..913c2b9e5c72 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -6271,6 +6271,8 @@ static ssize_t memory_high_write(struct kernfs_open_file *of,
 	if (err)
 		return err;
 
+	page_counter_set_high(&memcg->memory, high);
+
 	for (;;) {
 		unsigned long nr_pages = page_counter_read(&memcg->memory);
 		unsigned long reclaimed;
@@ -6294,10 +6296,7 @@ static ssize_t memory_high_write(struct kernfs_open_file *of,
 			break;
 	}
 
-	page_counter_set_high(&memcg->memory, high);
-
 	memcg_wb_domain_size_changed(memcg);
-
 	return nbytes;
 }
 
diff --git a/mm/migrate.c b/mm/migrate.c
index c0efe921bca5..20ca887ea769 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -1280,6 +1280,12 @@ static int unmap_and_move_huge_page(new_page_t get_new_page,
 		return -ENOSYS;
 	}
 
+	if (page_count(hpage) == 1) {
+		/* page was freed from under us. So we are done. */
+		putback_active_hugepage(hpage);
+		return MIGRATEPAGE_SUCCESS;
+	}
+
 	new_hpage = get_new_page(hpage, private);
 	if (!new_hpage)
 		return -ENOMEM;
diff --git a/mm/mremap.c b/mm/mremap.c
index f554320281cc..aa63bfd3cad2 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -336,8 +336,9 @@ enum pgt_entry {
  * valid. Else returns a smaller extent bounded by the end of the source and
  * destination pgt_entry.
  */
-static unsigned long get_extent(enum pgt_entry entry, unsigned long old_addr,
-			unsigned long old_end, unsigned long new_addr)
+static __always_inline unsigned long get_extent(enum pgt_entry entry,
+			unsigned long old_addr, unsigned long old_end,
+			unsigned long new_addr)
 {
 	unsigned long next, extent, mask, size;
 
diff --git a/mm/slub.c b/mm/slub.c
index 7ecbbbe5bc0c..b22a4b101c84 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -3423,6 +3423,7 @@ static inline int calculate_order(unsigned int size)
 	unsigned int order;
 	unsigned int min_objects;
 	unsigned int max_objects;
+	unsigned int nr_cpus;
 
 	/*
 	 * Attempt to find best configuration for a slab. This
@@ -3433,8 +3434,21 @@ static inline int calculate_order(unsigned int size)
 	 * we reduce the minimum objects required in a slab.
 	 */
 	min_objects = slub_min_objects;
-	if (!min_objects)
-		min_objects = 4 * (fls(num_online_cpus()) + 1);
+	if (!min_objects) {
+		/*
+		 * Some architectures will only update present cpus when
+		 * onlining them, so don't trust the number if it's just 1. But
+		 * we also don't want to use nr_cpu_ids always, as on some other
+		 * architectures, there can be many possible cpus, but never
+		 * onlined. Here we compromise between trying to avoid too high
+		 * order on systems that appear larger than they are, and too
+		 * low order on systems that appear smaller than they are.
+		 */
+		nr_cpus = num_present_cpus();
+		if (nr_cpus <= 1)
+			nr_cpus = nr_cpu_ids;
+		min_objects = 4 * (fls(nr_cpus) + 1);
+	}
 	max_objects = order_objects(slub_max_order, size);
 	min_objects = min(min_objects, max_objects);