Merge tag 'v4.19.59-rt24' into toradex_4.19.y-rttoradex_4.19.y-rt

Linux 4.19.59-rt24

16 files changed, 104 insertions, 59 deletions

diff --git a/mm/Kconfig b/mm/Kconfig
index 438460486a5b..0dddbb2a3282 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -700,12 +700,12 @@ config DEV_PAGEMAP_OPS
 
 config HMM
 	bool
+	select MMU_NOTIFIER
 	select MIGRATE_VMA_HELPER
 
 config HMM_MIRROR
 	bool "HMM mirror CPU page table into a device page table"
 	depends on ARCH_HAS_HMM
-	select MMU_NOTIFIER
 	select HMM
 	help
 	  Select HMM_MIRROR if you want to mirror range of the CPU page table of a
diff --git a/mm/cma.c b/mm/cma.c
index bfe9f5397165..476dfe13a701 100644
--- a/mm/cma.c
+++ b/mm/cma.c
@@ -106,8 +106,10 @@ static int __init cma_activate_area(struct cma *cma)
 
 	cma->bitmap = kzalloc(bitmap_size, GFP_KERNEL);
 
-	if (!cma->bitmap)
+	if (!cma->bitmap) {
+		cma->count = 0;
 		return -ENOMEM;
+	}
 
 	WARN_ON_ONCE(!pfn_valid(pfn));
 	zone = page_zone(pfn_to_page(pfn));
@@ -369,23 +371,26 @@ err:
 #ifdef CONFIG_CMA_DEBUG
 static void cma_debug_show_areas(struct cma *cma)
 {
-	unsigned long next_zero_bit, next_set_bit;
+	unsigned long next_zero_bit, next_set_bit, nr_zero;
 	unsigned long start = 0;
-	unsigned int nr_zero, nr_total = 0;
+	unsigned long nr_part, nr_total = 0;
+	unsigned long nbits = cma_bitmap_maxno(cma);
 
 	mutex_lock(&cma->lock);
 	pr_info("number of available pages: ");
 	for (;;) {
-		next_zero_bit = find_next_zero_bit(cma->bitmap, cma->count, start);
-		if (next_zero_bit >= cma->count)
+		next_zero_bit = find_next_zero_bit(cma->bitmap, nbits, start);
+		if (next_zero_bit >= nbits)
 			break;
-		next_set_bit = find_next_bit(cma->bitmap, cma->count, next_zero_bit);
+		next_set_bit = find_next_bit(cma->bitmap, nbits, next_zero_bit);
 		nr_zero = next_set_bit - next_zero_bit;
-		pr_cont("%s%u@%lu", nr_total ? "+" : "", nr_zero, next_zero_bit);
-		nr_total += nr_zero;
+		nr_part = nr_zero << cma->order_per_bit;
+		pr_cont("%s%lu@%lu", nr_total ? "+" : "", nr_part,
+			next_zero_bit);
+		nr_total += nr_part;
 		start = next_zero_bit + nr_zero;
 	}
-	pr_cont("=> %u free of %lu total pages\n", nr_total, cma->count);
+	pr_cont("=> %lu free of %lu total pages\n", nr_total, cma->count);
 	mutex_unlock(&cma->lock);
 }
 #else
diff --git a/mm/cma_debug.c b/mm/cma_debug.c
index ad6723e9d110..3e0415076cc9 100644
--- a/mm/cma_debug.c
+++ b/mm/cma_debug.c
@@ -58,7 +58,7 @@ static int cma_maxchunk_get(void *data, u64 *val)
 	mutex_lock(&cma->lock);
 	for (;;) {
 		start = find_next_zero_bit(cma->bitmap, bitmap_maxno, end);
-		if (start >= cma->count)
+		if (start >= bitmap_maxno)
 			break;
 		end = find_next_bit(cma->bitmap, bitmap_maxno, start);
 		maxchunk = max(end - start, maxchunk);
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 0bbb033d7d8c..57053affaad2 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1256,12 +1256,23 @@ void free_huge_page(struct page *page)
 	ClearPagePrivate(page);
 
 	/*
-	 * A return code of zero implies that the subpool will be under its
-	 * minimum size if the reservation is not restored after page is free.
-	 * Therefore, force restore_reserve operation.
+	 * If PagePrivate() was set on page, page allocation consumed a
+	 * reservation.  If the page was associated with a subpool, there
+	 * would have been a page reserved in the subpool before allocation
+	 * via hugepage_subpool_get_pages().  Since we are 'restoring' the
+	 * reservtion, do not call hugepage_subpool_put_pages() as this will
+	 * remove the reserved page from the subpool.
 	 */
-	if (hugepage_subpool_put_pages(spool, 1) == 0)
-		restore_reserve = true;
+	if (!restore_reserve) {
+		/*
+		 * A return code of zero implies that the subpool will be
+		 * under its minimum size if the reservation is not restored
+		 * after page is free.  Therefore, force restore_reserve
+		 * operation.
+		 */
+		if (hugepage_subpool_put_pages(spool, 1) == 0)
+			restore_reserve = true;
+	}
 
 	spin_lock(&hugetlb_lock);
 	clear_page_huge_active(page);
@@ -1478,16 +1489,29 @@ static int free_pool_huge_page(struct hstate *h, nodemask_t *nodes_allowed,
 
 /*
  * Dissolve a given free hugepage into free buddy pages. This function does
- * nothing for in-use (including surplus) hugepages. Returns -EBUSY if the
- * dissolution fails because a give page is not a free hugepage, or because
- * free hugepages are fully reserved.
+ * nothing for in-use hugepages and non-hugepages.
+ * This function returns values like below:
+ *
+ *  -EBUSY: failed to dissolved free hugepages or the hugepage is in-use
+ *          (allocated or reserved.)
+ *       0: successfully dissolved free hugepages or the page is not a
+ *          hugepage (considered as already dissolved)
  */
 int dissolve_free_huge_page(struct page *page)
 {
 	int rc = -EBUSY;
 
+	/* Not to disrupt normal path by vainly holding hugetlb_lock */
+	if (!PageHuge(page))
+		return 0;
+
 	spin_lock(&hugetlb_lock);
-	if (PageHuge(page) && !page_count(page)) {
+	if (!PageHuge(page)) {
+		rc = 0;
+		goto out;
+	}
+
+	if (!page_count(page)) {
 		struct page *head = compound_head(page);
 		struct hstate *h = page_hstate(head);
 		int nid = page_to_nid(head);
@@ -1532,11 +1556,9 @@ int dissolve_free_huge_pages(unsigned long start_pfn, unsigned long end_pfn)
 
 	for (pfn = start_pfn; pfn < end_pfn; pfn += 1 << minimum_order) {
 		page = pfn_to_page(pfn);
-		if (PageHuge(page) && !page_count(page)) {
-			rc = dissolve_free_huge_page(page);
-			if (rc)
-				break;
-		}
+		rc = dissolve_free_huge_page(page);
+		if (rc)
+			break;
 	}
 
 	return rc;
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index fde5820be24d..ecefdba4b0dd 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -1005,6 +1005,9 @@ static void collapse_huge_page(struct mm_struct *mm,
 	 * handled by the anon_vma lock + PG_lock.
 	 */
 	down_write(&mm->mmap_sem);
+	result = SCAN_ANY_PROCESS;
+	if (!mmget_still_valid(mm))
+		goto out;
 	result = hugepage_vma_revalidate(mm, address, &vma);
 	if (result)
 		goto out;
diff --git a/mm/list_lru.c b/mm/list_lru.c
index f0a15d32b959..758653dd1443 100644
--- a/mm/list_lru.c
+++ b/mm/list_lru.c
@@ -353,7 +353,7 @@ static int __memcg_init_list_lru_node(struct list_lru_memcg *memcg_lrus,
 	}
 	return 0;
 fail:
-	__memcg_destroy_list_lru_node(memcg_lrus, begin, i - 1);
+	__memcg_destroy_list_lru_node(memcg_lrus, begin, i);
 	return -ENOMEM;
 }
 
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 6edc6db5ec1b..2994ceb2e7b0 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -1731,6 +1731,8 @@ static int soft_offline_huge_page(struct page *page, int flags)
 		if (!ret) {
 			if (set_hwpoison_free_buddy_page(page))
 				num_poisoned_pages_inc();
+			else
+				ret = -EBUSY;
 		}
 	}
 	return ret;
@@ -1855,11 +1857,8 @@ static int soft_offline_in_use_page(struct page *page, int flags)
 
 static int soft_offline_free_page(struct page *page)
 {
-	int rc = 0;
-	struct page *head = compound_head(page);
+	int rc = dissolve_free_huge_page(page);
 
-	if (PageHuge(head))
-		rc = dissolve_free_huge_page(page);
 	if (!rc) {
 		if (set_hwpoison_free_buddy_page(page))
 			num_poisoned_pages_inc();
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 360b24bc69e5..62f945ea3e36 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -306,7 +306,7 @@ static void mpol_rebind_nodemask(struct mempolicy *pol, const nodemask_t *nodes)
 	else {
 		nodes_remap(tmp, pol->v.nodes,pol->w.cpuset_mems_allowed,
 								*nodes);
-		pol->w.cpuset_mems_allowed = tmp;
+		pol->w.cpuset_mems_allowed = *nodes;
 	}
 
 	if (nodes_empty(tmp))
diff --git a/mm/mlock.c b/mm/mlock.c
index 41cc47e28ad6..0ab8250af1f8 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -636,11 +636,11 @@ static int apply_vma_lock_flags(unsigned long start, size_t len,
  * is also counted.
  * Return value: previously mlocked page counts
  */
-static int count_mm_mlocked_page_nr(struct mm_struct *mm,
+static unsigned long count_mm_mlocked_page_nr(struct mm_struct *mm,
 		unsigned long start, size_t len)
 {
 	struct vm_area_struct *vma;
-	int count = 0;
+	unsigned long count = 0;
 
 	if (mm == NULL)
 		mm = current->mm;
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index a01c15fdb723..1679f5883307 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -6022,13 +6022,15 @@ static unsigned long __meminit zone_spanned_pages_in_node(int nid,
 					unsigned long *zone_end_pfn,
 					unsigned long *ignored)
 {
+	unsigned long zone_low = arch_zone_lowest_possible_pfn[zone_type];
+	unsigned long zone_high = arch_zone_highest_possible_pfn[zone_type];
 	/* When hotadd a new node from cpu_up(), the node should be empty */
 	if (!node_start_pfn && !node_end_pfn)
 		return 0;
 
 	/* Get the start and end of the zone */
-	*zone_start_pfn = arch_zone_lowest_possible_pfn[zone_type];
-	*zone_end_pfn = arch_zone_highest_possible_pfn[zone_type];
+	*zone_start_pfn = clamp(node_start_pfn, zone_low, zone_high);
+	*zone_end_pfn = clamp(node_end_pfn, zone_low, zone_high);
 	adjust_zone_range_for_zone_movable(nid, zone_type,
 				node_start_pfn, node_end_pfn,
 				zone_start_pfn, zone_end_pfn);
diff --git a/mm/page_idle.c b/mm/page_idle.c
index 6302bc62c27d..52ed59bbc275 100644
--- a/mm/page_idle.c
+++ b/mm/page_idle.c
@@ -136,7 +136,7 @@ static ssize_t page_idle_bitmap_read(struct file *file, struct kobject *kobj,
 
 	end_pfn = pfn + count * BITS_PER_BYTE;
 	if (end_pfn > max_pfn)
-		end_pfn = ALIGN(max_pfn, BITMAP_CHUNK_BITS);
+		end_pfn = max_pfn;
 
 	for (; pfn < end_pfn; pfn++) {
 		bit = pfn % BITMAP_CHUNK_BITS;
@@ -181,7 +181,7 @@ static ssize_t page_idle_bitmap_write(struct file *file, struct kobject *kobj,
 
 	end_pfn = pfn + count * BITS_PER_BYTE;
 	if (end_pfn > max_pfn)
-		end_pfn = ALIGN(max_pfn, BITMAP_CHUNK_BITS);
+		end_pfn = max_pfn;
 
 	for (; pfn < end_pfn; pfn++) {
 		bit = pfn % BITMAP_CHUNK_BITS;
diff --git a/mm/percpu.c b/mm/percpu.c
index 41e58f3d8fbf..ff76fa0b7528 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -988,7 +988,8 @@ static int pcpu_alloc_area(struct pcpu_chunk *chunk, int alloc_bits,
 	/*
 	 * Search to find a fit.
 	 */
-	end = start + alloc_bits + PCPU_BITMAP_BLOCK_BITS;
+	end = min_t(int, start + alloc_bits + PCPU_BITMAP_BLOCK_BITS,
+		    pcpu_chunk_map_bits(chunk));
 	bit_off = bitmap_find_next_zero_area(chunk->alloc_map, end, start,
 					     alloc_bits, align_mask);
 	if (bit_off >= end)
@@ -1721,6 +1722,7 @@ void free_percpu(void __percpu *ptr)
 	struct pcpu_chunk *chunk;
 	unsigned long flags;
 	int off;
+	bool need_balance = false;
 
 	if (!ptr)
 		return;
@@ -1742,7 +1744,7 @@ void free_percpu(void __percpu *ptr)
 
 		list_for_each_entry(pos, &pcpu_slot[pcpu_nr_slots - 1], list)
 			if (pos != chunk) {
-				pcpu_schedule_balance_work();
+				need_balance = true;
 				break;
 			}
 	}
@@ -1750,6 +1752,9 @@ void free_percpu(void __percpu *ptr)
 	trace_percpu_free_percpu(chunk->base_addr, off, ptr);
 
 	spin_unlock_irqrestore(&pcpu_lock, flags);
+
+	if (need_balance)
+		pcpu_schedule_balance_work();
 }
 EXPORT_SYMBOL_GPL(free_percpu);
 
diff --git a/mm/rmap.c b/mm/rmap.c
index 85b7f9423352..f048c2651954 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -926,7 +926,7 @@ static bool page_mkclean_one(struct page *page, struct vm_area_struct *vma,
 				continue;
 
 			flush_cache_page(vma, address, page_to_pfn(page));
-			entry = pmdp_huge_clear_flush(vma, address, pmd);
+			entry = pmdp_invalidate(vma, address, pmd);
 			entry = pmd_wrprotect(entry);
 			entry = pmd_mkclean(entry);
 			set_pmd_at(vma->vm_mm, address, pmd, entry);
diff --git a/mm/slab.c b/mm/slab.c
index 8ccc092fcd39..38f6609343b3 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -4326,8 +4326,12 @@ static int leaks_show(struct seq_file *m, void *p)
 	 * whole processing.
 	 */
 	do {
-		set_store_user_clean(cachep);
 		drain_cpu_caches(cachep);
+		/*
+		 * drain_cpu_caches() could make kmemleak_object and
+		 * debug_objects_cache dirty, so reset afterwards.
+		 */
+		set_store_user_clean(cachep);
 
 		x[1] = 0;
 
diff --git a/mm/vmscan.c b/mm/vmscan.c
index ee545d1e9894..e42f44cf7b43 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1510,7 +1510,7 @@ unsigned long reclaim_clean_pages_from_list(struct zone *zone,
 
 	list_for_each_entry_safe(page, next, page_list, lru) {
 		if (page_is_file_cache(page) && !PageDirty(page) &&
-		    !__PageMovable(page)) {
+		    !__PageMovable(page) && !PageUnevictable(page)) {
 			ClearPageActive(page);
 			list_move(&page->lru, &clean_pages);
 		}
@@ -3599,19 +3599,18 @@ out:
 }
 
 /*
- * pgdat->kswapd_classzone_idx is the highest zone index that a recent
- * allocation request woke kswapd for. When kswapd has not woken recently,
- * the value is MAX_NR_ZONES which is not a valid index. This compares a
- * given classzone and returns it or the highest classzone index kswapd
- * was recently woke for.
+ * The pgdat->kswapd_classzone_idx is used to pass the highest zone index to be
+ * reclaimed by kswapd from the waker. If the value is MAX_NR_ZONES which is not
+ * a valid index then either kswapd runs for first time or kswapd couldn't sleep
+ * after previous reclaim attempt (node is still unbalanced). In that case
+ * return the zone index of the previous kswapd reclaim cycle.
  */
 static enum zone_type kswapd_classzone_idx(pg_data_t *pgdat,
-					   enum zone_type classzone_idx)
+					   enum zone_type prev_classzone_idx)
 {
 	if (pgdat->kswapd_classzone_idx == MAX_NR_ZONES)
-		return classzone_idx;
-
-	return max(pgdat->kswapd_classzone_idx, classzone_idx);
+		return prev_classzone_idx;
+	return pgdat->kswapd_classzone_idx;
 }
 
 static void kswapd_try_to_sleep(pg_data_t *pgdat, int alloc_order, int reclaim_order,
@@ -3752,7 +3751,7 @@ kswapd_try_sleep:
 
 		/* Read the new order and classzone_idx */
 		alloc_order = reclaim_order = pgdat->kswapd_order;
-		classzone_idx = kswapd_classzone_idx(pgdat, 0);
+		classzone_idx = kswapd_classzone_idx(pgdat, classzone_idx);
 		pgdat->kswapd_order = 0;
 		pgdat->kswapd_classzone_idx = MAX_NR_ZONES;
 
@@ -3806,8 +3805,12 @@ void wakeup_kswapd(struct zone *zone, gfp_t gfp_flags, int order,
 	if (!cpuset_zone_allowed(zone, gfp_flags))
 		return;
 	pgdat = zone->zone_pgdat;
-	pgdat->kswapd_classzone_idx = kswapd_classzone_idx(pgdat,
-							   classzone_idx);
+
+	if (pgdat->kswapd_classzone_idx == MAX_NR_ZONES)
+		pgdat->kswapd_classzone_idx = classzone_idx;
+	else
+		pgdat->kswapd_classzone_idx = max(pgdat->kswapd_classzone_idx,
+						  classzone_idx);
 	pgdat->kswapd_order = max(pgdat->kswapd_order, order);
 	if (!waitqueue_active(&pgdat->kswapd_wait))
 		return;
diff --git a/mm/zswap.c b/mm/zswap.c
index cd91fd9d96b8..420225d3ff0b 100644
--- a/mm/zswap.c
+++ b/mm/zswap.c
@@ -27,6 +27,7 @@
 #include <linux/highmem.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
+#include <linux/locallock.h>
 #include <linux/types.h>
 #include <linux/atomic.h>
 #include <linux/frontswap.h>
@@ -990,6 +991,8 @@ static void zswap_fill_page(void *ptr, unsigned long value)
 	memset_l(page, value, PAGE_SIZE / sizeof(unsigned long));
 }
 
+/* protect zswap_dstmem from concurrency */
+static DEFINE_LOCAL_IRQ_LOCK(zswap_dstmem_lock);
 /*********************************
 * frontswap hooks
 **********************************/
@@ -1066,12 +1069,11 @@ static int zswap_frontswap_store(unsigned type, pgoff_t offset,
 	}
 
 	/* compress */
-	dst = get_cpu_var(zswap_dstmem);
-	tfm = *get_cpu_ptr(entry->pool->tfm);
+	dst = get_locked_var(zswap_dstmem_lock, zswap_dstmem);
+	tfm = *this_cpu_ptr(entry->pool->tfm);
 	src = kmap_atomic(page);
 	ret = crypto_comp_compress(tfm, src, PAGE_SIZE, dst, &dlen);
 	kunmap_atomic(src);
-	put_cpu_ptr(entry->pool->tfm);
 	if (ret) {
 		ret = -EINVAL;
 		goto put_dstmem;
@@ -1094,7 +1096,7 @@ static int zswap_frontswap_store(unsigned type, pgoff_t offset,
 	memcpy(buf, &zhdr, hlen);
 	memcpy(buf + hlen, dst, dlen);
 	zpool_unmap_handle(entry->pool->zpool, handle);
-	put_cpu_var(zswap_dstmem);
+	put_locked_var(zswap_dstmem_lock, zswap_dstmem);
 
 	/* populate entry */
 	entry->offset = offset;
@@ -1122,7 +1124,7 @@ insert_entry:
 	return 0;
 
 put_dstmem:
-	put_cpu_var(zswap_dstmem);
+	put_locked_var(zswap_dstmem_lock, zswap_dstmem);
 	zswap_pool_put(entry->pool);
 freepage:
 	zswap_entry_cache_free(entry);