Merge tag 'v5.5-rc5' into locking/kcsan, to resolve conflict

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

7 files changed, 96 insertions, 26 deletions

diff --git a/mm/gup_benchmark.c b/mm/gup_benchmark.c
index 7dd602d7f8db..ad9d5b1c4473 100644
--- a/mm/gup_benchmark.c
+++ b/mm/gup_benchmark.c
@@ -26,6 +26,7 @@ static int __gup_benchmark_ioctl(unsigned int cmd,
 	unsigned long i, nr_pages, addr, next;
 	int nr;
 	struct page **pages;
+	int ret = 0;
 
 	if (gup->size > ULONG_MAX)
 		return -EINVAL;
@@ -63,7 +64,9 @@ static int __gup_benchmark_ioctl(unsigned int cmd,
 					    NULL);
 			break;
 		default:
-			return -1;
+			kvfree(pages);
+			ret = -EINVAL;
+			goto out;
 		}
 
 		if (nr <= 0)
@@ -85,7 +88,8 @@ static int __gup_benchmark_ioctl(unsigned int cmd,
 	gup->put_delta_usec = ktime_us_delta(end_time, start_time);
 
 	kvfree(pages);
-	return 0;
+out:
+	return ret;
 }
 
 static long gup_benchmark_ioctl(struct file *filep, unsigned int cmd,
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index ac65bb5e38ac..dd8737a94bec 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -27,6 +27,7 @@
 #include <linux/swapops.h>
 #include <linux/jhash.h>
 #include <linux/numa.h>
+#include <linux/llist.h>
 
 #include <asm/page.h>
 #include <asm/pgtable.h>
@@ -1136,7 +1137,7 @@ static inline void ClearPageHugeTemporary(struct page *page)
 	page[2].mapping = NULL;
 }
 
-void free_huge_page(struct page *page)
+static void __free_huge_page(struct page *page)
 {
 	/*
 	 * Can't pass hstate in here because it is called from the
@@ -1199,6 +1200,54 @@ void free_huge_page(struct page *page)
 	spin_unlock(&hugetlb_lock);
 }
 
+/*
+ * As free_huge_page() can be called from a non-task context, we have
+ * to defer the actual freeing in a workqueue to prevent potential
+ * hugetlb_lock deadlock.
+ *
+ * free_hpage_workfn() locklessly retrieves the linked list of pages to
+ * be freed and frees them one-by-one. As the page->mapping pointer is
+ * going to be cleared in __free_huge_page() anyway, it is reused as the
+ * llist_node structure of a lockless linked list of huge pages to be freed.
+ */
+static LLIST_HEAD(hpage_freelist);
+
+static void free_hpage_workfn(struct work_struct *work)
+{
+	struct llist_node *node;
+	struct page *page;
+
+	node = llist_del_all(&hpage_freelist);
+
+	while (node) {
+		page = container_of((struct address_space **)node,
+				     struct page, mapping);
+		node = node->next;
+		__free_huge_page(page);
+	}
+}
+static DECLARE_WORK(free_hpage_work, free_hpage_workfn);
+
+void free_huge_page(struct page *page)
+{
+	/*
+	 * Defer freeing if in non-task context to avoid hugetlb_lock deadlock.
+	 */
+	if (!in_task()) {
+		/*
+		 * Only call schedule_work() if hpage_freelist is previously
+		 * empty. Otherwise, schedule_work() had been called but the
+		 * workfn hasn't retrieved the list yet.
+		 */
+		if (llist_add((struct llist_node *)&page->mapping,
+			      &hpage_freelist))
+			schedule_work(&free_hpage_work);
+		return;
+	}
+
+	__free_huge_page(page);
+}
+
 static void prep_new_huge_page(struct hstate *h, struct page *page, int nid)
 {
 	INIT_LIST_HEAD(&page->lru);
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 55ac23ef11c1..a91a072f2b2c 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -483,8 +483,9 @@ static void update_pgdat_span(struct pglist_data *pgdat)
 	pgdat->node_spanned_pages = node_end_pfn - node_start_pfn;
 }
 
-static void __remove_zone(struct zone *zone, unsigned long start_pfn,
-		unsigned long nr_pages)
+void __ref remove_pfn_range_from_zone(struct zone *zone,
+				      unsigned long start_pfn,
+				      unsigned long nr_pages)
 {
 	struct pglist_data *pgdat = zone->zone_pgdat;
 	unsigned long flags;
@@ -499,28 +500,30 @@ static void __remove_zone(struct zone *zone, unsigned long start_pfn,
 		return;
 #endif
 
+	clear_zone_contiguous(zone);
+
 	pgdat_resize_lock(zone->zone_pgdat, &flags);
 	shrink_zone_span(zone, start_pfn, start_pfn + nr_pages);
 	update_pgdat_span(pgdat);
 	pgdat_resize_unlock(zone->zone_pgdat, &flags);
+
+	set_zone_contiguous(zone);
 }
 
-static void __remove_section(struct zone *zone, unsigned long pfn,
-		unsigned long nr_pages, unsigned long map_offset,
-		struct vmem_altmap *altmap)
+static void __remove_section(unsigned long pfn, unsigned long nr_pages,
+			     unsigned long map_offset,
+			     struct vmem_altmap *altmap)
 {
 	struct mem_section *ms = __nr_to_section(pfn_to_section_nr(pfn));
 
 	if (WARN_ON_ONCE(!valid_section(ms)))
 		return;
 
-	__remove_zone(zone, pfn, nr_pages);
 	sparse_remove_section(ms, pfn, nr_pages, map_offset, altmap);
 }
 
 /**
- * __remove_pages() - remove sections of pages from a zone
- * @zone: zone from which pages need to be removed
+ * __remove_pages() - remove sections of pages
  * @pfn: starting pageframe (must be aligned to start of a section)
  * @nr_pages: number of pages to remove (must be multiple of section size)
  * @altmap: alternative device page map or %NULL if default memmap is used
@@ -530,16 +533,14 @@ static void __remove_section(struct zone *zone, unsigned long pfn,
  * sure that pages are marked reserved and zones are adjust properly by
  * calling offline_pages().
  */
-void __remove_pages(struct zone *zone, unsigned long pfn,
-		    unsigned long nr_pages, struct vmem_altmap *altmap)
+void __remove_pages(unsigned long pfn, unsigned long nr_pages,
+		    struct vmem_altmap *altmap)
 {
 	unsigned long map_offset = 0;
 	unsigned long nr, start_sec, end_sec;
 
 	map_offset = vmem_altmap_offset(altmap);
 
-	clear_zone_contiguous(zone);
-
 	if (check_pfn_span(pfn, nr_pages, "remove"))
 		return;
 
@@ -551,13 +552,11 @@ void __remove_pages(struct zone *zone, unsigned long pfn,
 		cond_resched();
 		pfns = min(nr_pages, PAGES_PER_SECTION
 				- (pfn & ~PAGE_SECTION_MASK));
-		__remove_section(zone, pfn, pfns, map_offset, altmap);
+		__remove_section(pfn, pfns, map_offset, altmap);
 		pfn += pfns;
 		nr_pages -= pfns;
 		map_offset = 0;
 	}
-
-	set_zone_contiguous(zone);
 }
 
 int set_online_page_callback(online_page_callback_t callback)
@@ -869,6 +868,7 @@ failed_addition:
 		 (unsigned long long) pfn << PAGE_SHIFT,
 		 (((unsigned long long) pfn + nr_pages) << PAGE_SHIFT) - 1);
 	memory_notify(MEM_CANCEL_ONLINE, &arg);
+	remove_pfn_range_from_zone(zone, pfn, nr_pages);
 	mem_hotplug_done();
 	return ret;
 }
@@ -1628,6 +1628,7 @@ static int __ref __offline_pages(unsigned long start_pfn,
 	writeback_set_ratelimit();
 
 	memory_notify(MEM_OFFLINE, &arg);
+	remove_pfn_range_from_zone(zone, start_pfn, nr_pages);
 	mem_hotplug_done();
 	return 0;
 
diff --git a/mm/memremap.c b/mm/memremap.c
index 03ccbdfeb697..c51c6bd2fe34 100644
--- a/mm/memremap.c
+++ b/mm/memremap.c
@@ -120,7 +120,7 @@ void memunmap_pages(struct dev_pagemap *pgmap)
 
 	mem_hotplug_begin();
 	if (pgmap->type == MEMORY_DEVICE_PRIVATE) {
-		__remove_pages(page_zone(first_page), PHYS_PFN(res->start),
+		__remove_pages(PHYS_PFN(res->start),
 			       PHYS_PFN(resource_size(res)), NULL);
 	} else {
 		arch_remove_memory(nid, res->start, resource_size(res),
diff --git a/mm/migrate.c b/mm/migrate.c
index eae1565285e3..86873b6f38a7 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -1512,9 +1512,11 @@ static int do_move_pages_to_node(struct mm_struct *mm,
 /*
  * Resolves the given address to a struct page, isolates it from the LRU and
  * puts it to the given pagelist.
- * Returns -errno if the page cannot be found/isolated or 0 when it has been
- * queued or the page doesn't need to be migrated because it is already on
- * the target node
+ * Returns:
+ *     errno - if the page cannot be found/isolated
+ *     0 - when it doesn't have to be migrated because it is already on the
+ *         target node
+ *     1 - when it has been queued
  */
 static int add_page_for_migration(struct mm_struct *mm, unsigned long addr,
 		int node, struct list_head *pagelist, bool migrate_all)
@@ -1553,7 +1555,7 @@ static int add_page_for_migration(struct mm_struct *mm, unsigned long addr,
 	if (PageHuge(page)) {
 		if (PageHead(page)) {
 			isolate_huge_page(page, pagelist);
-			err = 0;
+			err = 1;
 		}
 	} else {
 		struct page *head;
@@ -1563,7 +1565,7 @@ static int add_page_for_migration(struct mm_struct *mm, unsigned long addr,
 		if (err)
 			goto out_putpage;
 
-		err = 0;
+		err = 1;
 		list_add_tail(&head->lru, pagelist);
 		mod_node_page_state(page_pgdat(head),
 			NR_ISOLATED_ANON + page_is_file_cache(head),
@@ -1640,8 +1642,17 @@ static int do_pages_move(struct mm_struct *mm, nodemask_t task_nodes,
 		 */
 		err = add_page_for_migration(mm, addr, current_node,
 				&pagelist, flags & MPOL_MF_MOVE_ALL);
-		if (!err)
+
+		if (!err) {
+			/* The page is already on the target node */
+			err = store_status(status, i, current_node, 1);
+			if (err)
+				goto out_flush;
 			continue;
+		} else if (err > 0) {
+			/* The page is successfully queued for migration */
+			continue;
+		}
 
 		err = store_status(status, i, err, 1);
 		if (err)
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 71e3acea7817..d58c481b3df8 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -890,7 +890,7 @@ static void __oom_kill_process(struct task_struct *victim, const char *message)
 		K(get_mm_counter(mm, MM_FILEPAGES)),
 		K(get_mm_counter(mm, MM_SHMEMPAGES)),
 		from_kuid(&init_user_ns, task_uid(victim)),
-		mm_pgtables_bytes(mm), victim->signal->oom_score_adj);
+		mm_pgtables_bytes(mm) >> 10, victim->signal->oom_score_adj);
 	task_unlock(victim);
 
 	/*
diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c
index 2b2b9aae8a3c..22d17ecfe7df 100644
--- a/mm/zsmalloc.c
+++ b/mm/zsmalloc.c
@@ -2069,6 +2069,11 @@ static int zs_page_migrate(struct address_space *mapping, struct page *newpage,
 		zs_pool_dec_isolated(pool);
 	}
 
+	if (page_zone(newpage) != page_zone(page)) {
+		dec_zone_page_state(page, NR_ZSPAGES);
+		inc_zone_page_state(newpage, NR_ZSPAGES);
+	}
+
 	reset_page(page);
 	put_page(page);
 	page = newpage;