Merge tag 'v4.4.121' into toradex_vf_4.4-nextColibri-VF_LXDE-Image_2.8b2.97-20180331

This is the 4.4.121 stable release

16 files changed, 121 insertions, 68 deletions

diff --git a/mm/cma.c b/mm/cma.c
index bd0e1412475e..43f4a122e969 100644
--- a/mm/cma.c
+++ b/mm/cma.c
@@ -54,7 +54,7 @@ unsigned long cma_get_size(const struct cma *cma)
 }
 
 static unsigned long cma_bitmap_aligned_mask(const struct cma *cma,
-					     int align_order)
+					     unsigned int align_order)
 {
 	if (align_order <= cma->order_per_bit)
 		return 0;
@@ -62,17 +62,14 @@ static unsigned long cma_bitmap_aligned_mask(const struct cma *cma,
 }
 
 /*
- * Find a PFN aligned to the specified order and return an offset represented in
- * order_per_bits.
+ * Find the offset of the base PFN from the specified align_order.
+ * The value returned is represented in order_per_bits.
  */
 static unsigned long cma_bitmap_aligned_offset(const struct cma *cma,
-					       int align_order)
+					       unsigned int align_order)
 {
-	if (align_order <= cma->order_per_bit)
-		return 0;
-
-	return (ALIGN(cma->base_pfn, (1UL << align_order))
-		- cma->base_pfn) >> cma->order_per_bit;
+	return (cma->base_pfn & ((1UL << align_order) - 1))
+		>> cma->order_per_bit;
 }
 
 static unsigned long cma_bitmap_pages_to_bits(const struct cma *cma,
diff --git a/mm/compaction.c b/mm/compaction.c
index dba02dec7195..b6f145ed7ae1 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -200,7 +200,8 @@ static void reset_cached_positions(struct zone *zone)
 {
 	zone->compact_cached_migrate_pfn[0] = zone->zone_start_pfn;
 	zone->compact_cached_migrate_pfn[1] = zone->zone_start_pfn;
-	zone->compact_cached_free_pfn = zone_end_pfn(zone);
+	zone->compact_cached_free_pfn =
+			round_down(zone_end_pfn(zone) - 1, pageblock_nr_pages);
 }
 
 /*
@@ -552,13 +553,17 @@ unsigned long
 isolate_freepages_range(struct compact_control *cc,
 			unsigned long start_pfn, unsigned long end_pfn)
 {
-	unsigned long isolated, pfn, block_end_pfn;
+	unsigned long isolated, pfn, block_start_pfn, block_end_pfn;
 	LIST_HEAD(freelist);
 
 	pfn = start_pfn;
+	block_start_pfn = pfn & ~(pageblock_nr_pages - 1);
+	if (block_start_pfn < cc->zone->zone_start_pfn)
+		block_start_pfn = cc->zone->zone_start_pfn;
 	block_end_pfn = ALIGN(pfn + 1, pageblock_nr_pages);
 
 	for (; pfn < end_pfn; pfn += isolated,
+				block_start_pfn = block_end_pfn,
 				block_end_pfn += pageblock_nr_pages) {
 		/* Protect pfn from changing by isolate_freepages_block */
 		unsigned long isolate_start_pfn = pfn;
@@ -571,11 +576,13 @@ isolate_freepages_range(struct compact_control *cc,
 		 * scanning range to right one.
 		 */
 		if (pfn >= block_end_pfn) {
+			block_start_pfn = pfn & ~(pageblock_nr_pages - 1);
 			block_end_pfn = ALIGN(pfn + 1, pageblock_nr_pages);
 			block_end_pfn = min(block_end_pfn, end_pfn);
 		}
 
-		if (!pageblock_pfn_to_page(pfn, block_end_pfn, cc->zone))
+		if (!pageblock_pfn_to_page(block_start_pfn,
+					block_end_pfn, cc->zone))
 			break;
 
 		isolated = isolate_freepages_block(cc, &isolate_start_pfn,
@@ -861,18 +868,23 @@ unsigned long
 isolate_migratepages_range(struct compact_control *cc, unsigned long start_pfn,
 							unsigned long end_pfn)
 {
-	unsigned long pfn, block_end_pfn;
+	unsigned long pfn, block_start_pfn, block_end_pfn;
 
 	/* Scan block by block. First and last block may be incomplete */
 	pfn = start_pfn;
+	block_start_pfn = pfn & ~(pageblock_nr_pages - 1);
+	if (block_start_pfn < cc->zone->zone_start_pfn)
+		block_start_pfn = cc->zone->zone_start_pfn;
 	block_end_pfn = ALIGN(pfn + 1, pageblock_nr_pages);
 
 	for (; pfn < end_pfn; pfn = block_end_pfn,
+				block_start_pfn = block_end_pfn,
 				block_end_pfn += pageblock_nr_pages) {
 
 		block_end_pfn = min(block_end_pfn, end_pfn);
 
-		if (!pageblock_pfn_to_page(pfn, block_end_pfn, cc->zone))
+		if (!pageblock_pfn_to_page(block_start_pfn,
+					block_end_pfn, cc->zone))
 			continue;
 
 		pfn = isolate_migratepages_block(cc, pfn, block_end_pfn,
@@ -1090,7 +1102,9 @@ int sysctl_compact_unevictable_allowed __read_mostly = 1;
 static isolate_migrate_t isolate_migratepages(struct zone *zone,
 					struct compact_control *cc)
 {
-	unsigned long low_pfn, end_pfn;
+	unsigned long block_start_pfn;
+	unsigned long block_end_pfn;
+	unsigned long low_pfn;
 	unsigned long isolate_start_pfn;
 	struct page *page;
 	const isolate_mode_t isolate_mode =
@@ -1102,16 +1116,21 @@ static isolate_migrate_t isolate_migratepages(struct zone *zone,
 	 * initialized by compact_zone()
 	 */
 	low_pfn = cc->migrate_pfn;
+	block_start_pfn = cc->migrate_pfn & ~(pageblock_nr_pages - 1);
+	if (block_start_pfn < zone->zone_start_pfn)
+		block_start_pfn = zone->zone_start_pfn;
 
 	/* Only scan within a pageblock boundary */
-	end_pfn = ALIGN(low_pfn + 1, pageblock_nr_pages);
+	block_end_pfn = ALIGN(low_pfn + 1, pageblock_nr_pages);
 
 	/*
 	 * Iterate over whole pageblocks until we find the first suitable.
 	 * Do not cross the free scanner.
 	 */
-	for (; end_pfn <= cc->free_pfn;
-			low_pfn = end_pfn, end_pfn += pageblock_nr_pages) {
+	for (; block_end_pfn <= cc->free_pfn;
+			low_pfn = block_end_pfn,
+			block_start_pfn = block_end_pfn,
+			block_end_pfn += pageblock_nr_pages) {
 
 		/*
 		 * This can potentially iterate a massively long zone with
@@ -1122,7 +1141,8 @@ static isolate_migrate_t isolate_migratepages(struct zone *zone,
 						&& compact_should_abort(cc))
 			break;
 
-		page = pageblock_pfn_to_page(low_pfn, end_pfn, zone);
+		page = pageblock_pfn_to_page(block_start_pfn, block_end_pfn,
+									zone);
 		if (!page)
 			continue;
 
@@ -1141,8 +1161,8 @@ static isolate_migrate_t isolate_migratepages(struct zone *zone,
 
 		/* Perform the isolation */
 		isolate_start_pfn = low_pfn;
-		low_pfn = isolate_migratepages_block(cc, low_pfn, end_pfn,
-								isolate_mode);
+		low_pfn = isolate_migratepages_block(cc, low_pfn,
+						block_end_pfn, isolate_mode);
 
 		if (!low_pfn || cc->contended) {
 			acct_isolated(zone, cc);
@@ -1358,11 +1378,11 @@ static int compact_zone(struct zone *zone, struct compact_control *cc)
 	 */
 	cc->migrate_pfn = zone->compact_cached_migrate_pfn[sync];
 	cc->free_pfn = zone->compact_cached_free_pfn;
-	if (cc->free_pfn < start_pfn || cc->free_pfn > end_pfn) {
-		cc->free_pfn = end_pfn & ~(pageblock_nr_pages-1);
+	if (cc->free_pfn < start_pfn || cc->free_pfn >= end_pfn) {
+		cc->free_pfn = round_down(end_pfn - 1, pageblock_nr_pages);
 		zone->compact_cached_free_pfn = cc->free_pfn;
 	}
-	if (cc->migrate_pfn < start_pfn || cc->migrate_pfn > end_pfn) {
+	if (cc->migrate_pfn < start_pfn || cc->migrate_pfn >= end_pfn) {
 		cc->migrate_pfn = start_pfn;
 		zone->compact_cached_migrate_pfn[0] = cc->migrate_pfn;
 		zone->compact_cached_migrate_pfn[1] = cc->migrate_pfn;
diff --git a/mm/early_ioremap.c b/mm/early_ioremap.c
index 6d5717bd7197..57540de2b44c 100644
--- a/mm/early_ioremap.c
+++ b/mm/early_ioremap.c
@@ -103,7 +103,7 @@ __early_ioremap(resource_size_t phys_addr, unsigned long size, pgprot_t prot)
 	enum fixed_addresses idx;
 	int i, slot;
 
-	WARN_ON(system_state != SYSTEM_BOOTING);
+	WARN_ON(system_state >= SYSTEM_RUNNING);
 
 	slot = -1;
 	for (i = 0; i < FIX_BTMAPS_SLOTS; i++) {
diff --git a/mm/kmemleak.c b/mm/kmemleak.c
index 19423a45d7d7..1914ab9009d9 100644
--- a/mm/kmemleak.c
+++ b/mm/kmemleak.c
@@ -1394,6 +1394,8 @@ static void kmemleak_scan(void)
 			if (page_count(page) == 0)
 				continue;
 			scan_block(page, page + 1, NULL);
+			if (!(pfn % (MAX_SCAN_SIZE / sizeof(*page))))
+				cond_resched();
 		}
 	}
 	put_online_mems();
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index e25b93a4267d..55a9facb8e8d 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -5576,7 +5576,7 @@ static void uncharge_list(struct list_head *page_list)
 		next = page->lru.next;
 
 		VM_BUG_ON_PAGE(PageLRU(page), page);
-		VM_BUG_ON_PAGE(page_count(page), page);
+		VM_BUG_ON_PAGE(!PageHWPoison(page) && page_count(page), page);
 
 		if (!page->mem_cgroup)
 			continue;
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 091fe9b06663..92a647957f91 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -539,6 +539,13 @@ static int delete_from_lru_cache(struct page *p)
 		 */
 		ClearPageActive(p);
 		ClearPageUnevictable(p);
+
+		/*
+		 * Poisoned page might never drop its ref count to 0 so we have
+		 * to uncharge it manually from its memcg.
+		 */
+		mem_cgroup_uncharge(p);
+
 		/*
 		 * drop the page count elevated by isolate_lru_page()
 		 */
diff --git a/mm/memory.c b/mm/memory.c
index 9ac55172aa7b..31ca97f7ebbc 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -72,7 +72,7 @@
 
 #include "internal.h"
 
-#ifdef LAST_CPUPID_NOT_IN_PAGE_FLAGS
+#if defined(LAST_CPUPID_NOT_IN_PAGE_FLAGS) && !defined(CONFIG_COMPILE_TEST)
 #warning Unfortunate NUMA and NUMA Balancing config, growing page-frame for last_cpupid.
 #endif
 
diff --git a/mm/mmap.c b/mm/mmap.c
index eaa460ddcaf9..cc84b97ca250 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -2188,7 +2188,8 @@ int expand_upwards(struct vm_area_struct *vma, unsigned long address)
 		gap_addr = TASK_SIZE;
 
 	next = vma->vm_next;
-	if (next && next->vm_start < gap_addr) {
+	if (next && next->vm_start < gap_addr &&
+			(next->vm_flags & (VM_WRITE|VM_READ|VM_EXEC))) {
 		if (!(next->vm_flags & VM_GROWSUP))
 			return -ENOMEM;
 		/* Check that both stack segments have the same anon_vma? */
@@ -2273,7 +2274,8 @@ int expand_downwards(struct vm_area_struct *vma,
 	if (gap_addr > address)
 		return -ENOMEM;
 	prev = vma->vm_prev;
-	if (prev && prev->vm_end > gap_addr) {
+	if (prev && prev->vm_end > gap_addr &&
+			(prev->vm_flags & (VM_WRITE|VM_READ|VM_EXEC))) {
 		if (!(prev->vm_flags & VM_GROWSDOWN))
 			return -ENOMEM;
 		/* Check that both stack segments have the same anon_vma? */
diff --git a/mm/mmu_context.c b/mm/mmu_context.c
index f802c2d216a7..6f4d27c5bb32 100644
--- a/mm/mmu_context.c
+++ b/mm/mmu_context.c
@@ -4,9 +4,9 @@
  */
 
 #include <linux/mm.h>
+#include <linux/sched.h>
 #include <linux/mmu_context.h>
 #include <linux/export.h>
-#include <linux/sched.h>
 
 #include <asm/mmu_context.h>
 
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index fd51ebfc423f..6d0dbde4503b 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -1162,6 +1162,7 @@ static void wb_update_dirty_ratelimit(struct dirty_throttle_control *dtc,
 	unsigned long balanced_dirty_ratelimit;
 	unsigned long step;
 	unsigned long x;
+	unsigned long shift;
 
 	/*
 	 * The dirty rate will match the writeout rate in long term, except
@@ -1286,11 +1287,11 @@ static void wb_update_dirty_ratelimit(struct dirty_throttle_control *dtc,
 	 * rate itself is constantly fluctuating. So decrease the track speed
 	 * when it gets close to the target. Helps eliminate pointless tremors.
 	 */
-	step >>= dirty_ratelimit / (2 * step + 1);
-	/*
-	 * Limit the tracking speed to avoid overshooting.
-	 */
-	step = (step + 7) / 8;
+	shift = dirty_ratelimit / (2 * step + 1);
+	if (shift < BITS_PER_LONG)
+		step = DIV_ROUND_UP(step >> shift, 8);
+	else
+		step = 0;
 
 	if (dirty_ratelimit < balanced_dirty_ratelimit)
 		dirty_ratelimit += step;
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 3c70f03d91ec..a4c9cd80c7b6 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2468,9 +2468,6 @@ static bool __zone_watermark_ok(struct zone *z, unsigned int order,
 		if (!area->nr_free)
 			continue;
 
-		if (alloc_harder)
-			return true;
-
 		for (mt = 0; mt < MIGRATE_PCPTYPES; mt++) {
 			if (!list_empty(&area->free_list[mt]))
 				return true;
@@ -2482,6 +2479,9 @@ static bool __zone_watermark_ok(struct zone *z, unsigned int order,
 			return true;
 		}
 #endif
+		if (alloc_harder &&
+			!list_empty(&area->free_list[MIGRATE_HIGHATOMIC]))
+			return true;
 	}
 	return false;
 }
diff --git a/mm/rmap.c b/mm/rmap.c
index ede183c32f45..1bceb49aa214 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -587,19 +587,6 @@ vma_address(struct page *page, struct vm_area_struct *vma)
 }
 
 #ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH
-static void percpu_flush_tlb_batch_pages(void *data)
-{
-	/*
-	 * All TLB entries are flushed on the assumption that it is
-	 * cheaper to flush all TLBs and let them be refilled than
-	 * flushing individual PFNs. Note that we do not track mm's
-	 * to flush as that might simply be multiple full TLB flushes
-	 * for no gain.
-	 */
-	count_vm_tlb_event(NR_TLB_REMOTE_FLUSH_RECEIVED);
-	flush_tlb_local();
-}
-
 /*
  * Flush TLB entries for recently unmapped pages from remote CPUs. It is
  * important if a PTE was dirty when it was unmapped that it's flushed
@@ -616,15 +603,14 @@ void try_to_unmap_flush(void)
 
 	cpu = get_cpu();
 
-	trace_tlb_flush(TLB_REMOTE_SHOOTDOWN, -1UL);
-
-	if (cpumask_test_cpu(cpu, &tlb_ubc->cpumask))
-		percpu_flush_tlb_batch_pages(&tlb_ubc->cpumask);
-
-	if (cpumask_any_but(&tlb_ubc->cpumask, cpu) < nr_cpu_ids) {
-		smp_call_function_many(&tlb_ubc->cpumask,
-			percpu_flush_tlb_batch_pages, (void *)tlb_ubc, true);
+	if (cpumask_test_cpu(cpu, &tlb_ubc->cpumask)) {
+		count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL);
+		local_flush_tlb();
+		trace_tlb_flush(TLB_LOCAL_SHOOTDOWN, TLB_FLUSH_ALL);
 	}
+
+	if (cpumask_any_but(&tlb_ubc->cpumask, cpu) < nr_cpu_ids)
+		flush_tlb_others(&tlb_ubc->cpumask, NULL, 0, TLB_FLUSH_ALL);
 	cpumask_clear(&tlb_ubc->cpumask);
 	tlb_ubc->flush_required = false;
 	tlb_ubc->writable = false;
diff --git a/mm/util.c b/mm/util.c
index d5259b62f8d7..818bbae84721 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -80,6 +80,8 @@ EXPORT_SYMBOL(kstrdup_const);
  * @s: the string to duplicate
  * @max: read at most @max chars from @s
  * @gfp: the GFP mask used in the kmalloc() call when allocating memory
+ *
+ * Note: Use kmemdup_nul() instead if the size is known exactly.
  */
 char *kstrndup(const char *s, size_t max, gfp_t gfp)
 {
@@ -118,6 +120,28 @@ void *kmemdup(const void *src, size_t len, gfp_t gfp)
 EXPORT_SYMBOL(kmemdup);
 
 /**
+ * kmemdup_nul - Create a NUL-terminated string from unterminated data
+ * @s: The data to stringify
+ * @len: The size of the data
+ * @gfp: the GFP mask used in the kmalloc() call when allocating memory
+ */
+char *kmemdup_nul(const char *s, size_t len, gfp_t gfp)
+{
+	char *buf;
+
+	if (!s)
+		return NULL;
+
+	buf = kmalloc_track_caller(len + 1, gfp);
+	if (buf) {
+		memcpy(buf, s, len);
+		buf[len] = '\0';
+	}
+	return buf;
+}
+EXPORT_SYMBOL(kmemdup_nul);
+
+/**
  * memdup_user - duplicate memory region from user space
  *
  * @src: source address in user space
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 440c2df9be82..930f7c67a9c1 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -254,10 +254,13 @@ EXPORT_SYMBOL(register_shrinker);
  */
 void unregister_shrinker(struct shrinker *shrinker)
 {
+	if (!shrinker->nr_deferred)
+		return;
 	down_write(&shrinker_rwsem);
 	list_del(&shrinker->list);
 	up_write(&shrinker_rwsem);
 	kfree(shrinker->nr_deferred);
+	shrinker->nr_deferred = NULL;
 }
 EXPORT_SYMBOL(unregister_shrinker);
 
diff --git a/mm/vmstat.c b/mm/vmstat.c
index c344e3609c53..5712cdaae964 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -736,6 +736,7 @@ const char * const vmstat_text[] = {
 	"nr_slab_unreclaimable",
 	"nr_page_table_pages",
 	"nr_kernel_stack",
+	"nr_overhead",
 	"nr_unstable",
 	"nr_bounce",
 	"nr_vmscan_write",
@@ -1350,7 +1351,9 @@ static int vmstat_show(struct seq_file *m, void *arg)
 	unsigned long *l = arg;
 	unsigned long off = l - (unsigned long *)m->private;
 
-	seq_printf(m, "%s %lu\n", vmstat_text[off], *l);
+	seq_puts(m, vmstat_text[off]);
+	seq_put_decimal_ull(m, ' ', *l);
+	seq_putc(m, '\n');
 	return 0;
 }
 
diff --git a/mm/zswap.c b/mm/zswap.c
index 45476f429789..568015e2fe7a 100644
--- a/mm/zswap.c
+++ b/mm/zswap.c
@@ -123,7 +123,7 @@ struct zswap_pool {
 	struct crypto_comp * __percpu *tfm;
 	struct kref kref;
 	struct list_head list;
-	struct rcu_head rcu_head;
+	struct work_struct work;
 	struct notifier_block notifier;
 	char tfm_name[CRYPTO_MAX_ALG_NAME];
 };
@@ -667,9 +667,11 @@ static int __must_check zswap_pool_get(struct zswap_pool *pool)
 	return kref_get_unless_zero(&pool->kref);
 }
 
-static void __zswap_pool_release(struct rcu_head *head)
+static void __zswap_pool_release(struct work_struct *work)
 {
-	struct zswap_pool *pool = container_of(head, typeof(*pool), rcu_head);
+	struct zswap_pool *pool = container_of(work, typeof(*pool), work);
+
+	synchronize_rcu();
 
 	/* nobody should have been able to get a kref... */
 	WARN_ON(kref_get_unless_zero(&pool->kref));
@@ -689,7 +691,9 @@ static void __zswap_pool_empty(struct kref *kref)
 	WARN_ON(pool == zswap_pool_current());
 
 	list_del_rcu(&pool->list);
-	call_rcu(&pool->rcu_head, __zswap_pool_release);
+
+	INIT_WORK(&pool->work, __zswap_pool_release);
+	schedule_work(&pool->work);
 
 	spin_unlock(&zswap_pools_lock);
 }
@@ -748,18 +752,22 @@ static int __zswap_param_set(const char *val, const struct kernel_param *kp,
 	pool = zswap_pool_find_get(type, compressor);
 	if (pool) {
 		zswap_pool_debug("using existing", pool);
+		WARN_ON(pool == zswap_pool_current());
 		list_del_rcu(&pool->list);
-	} else {
-		spin_unlock(&zswap_pools_lock);
-		pool = zswap_pool_create(type, compressor);
-		spin_lock(&zswap_pools_lock);
 	}
 
+	spin_unlock(&zswap_pools_lock);
+
+	if (!pool)
+		pool = zswap_pool_create(type, compressor);
+
 	if (pool)
 		ret = param_set_charp(s, kp);
 	else
 		ret = -EINVAL;
 
+	spin_lock(&zswap_pools_lock);
+
 	if (!ret) {
 		put_pool = zswap_pool_current();
 		list_add_rcu(&pool->list, &zswap_pools);