Merge branch 'akpm' (patches from Andrew)

Merge various fixes from Andrew Morton:
 "10 fixes"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>:
  mm, page_alloc: recalculate the preferred zoneref if the context can ignore memory policies
  mm, page_alloc: reset zonelist iterator after resetting fair zone allocation policy
  mm, oom_reaper: do not use siglock in try_oom_reaper()
  mm, page_alloc: prevent infinite loop in buffered_rmqueue()
  checkpatch: reduce git commit description style false positives
  mm/z3fold.c: avoid modifying HEADLESS page and minor cleanup
  memcg: add RCU locking around css_for_each_descendant_pre() in memcg_offline_kmem()
  mm: check the return value of lookup_page_ext for all call sites
  kdump: fix dmesg gdbmacro to work with record based printk
  mm: fix overflow in vm_map_ram()

8 files changed, 86 insertions, 32 deletions

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 925b431..58c69c9 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -2896,6 +2896,7 @@ static void memcg_offline_kmem(struct mem_cgroup *memcg)
 	 * ordering is imposed by list_lru_node->lock taken by
 	 * memcg_drain_all_list_lrus().
 	 */
+	rcu_read_lock(); /* can be called from css_free w/o cgroup_mutex */
 	css_for_each_descendant_pre(css, &memcg->css) {
 		child = mem_cgroup_from_css(css);
 		BUG_ON(child->kmemcg_id != kmemcg_id);
@@ -2903,6 +2904,8 @@ static void memcg_offline_kmem(struct mem_cgroup *memcg)
 		if (!memcg->use_hierarchy)
 			break;
 	}
+	rcu_read_unlock();
+
 	memcg_drain_all_list_lrus(kmemcg_id, parent->kmemcg_id);
 
 	memcg_free_cache_id(kmemcg_id);
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index dfb1ab6..acbc432 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -625,8 +625,6 @@ void try_oom_reaper(struct task_struct *tsk)
 	if (atomic_read(&mm->mm_users) > 1) {
 		rcu_read_lock();
 		for_each_process(p) {
-			bool exiting;
-
 			if (!process_shares_mm(p, mm))
 				continue;
 			if (fatal_signal_pending(p))
@@ -636,10 +634,7 @@ void try_oom_reaper(struct task_struct *tsk)
 			 * If the task is exiting make sure the whole thread group
 			 * is exiting and cannot acces mm anymore.
 			 */
-			spin_lock_irq(&p->sighand->siglock);
-			exiting = signal_group_exit(p->signal);
-			spin_unlock_irq(&p->sighand->siglock);
-			if (exiting)
+			if (signal_group_exit(p->signal))
 				continue;
 
 			/* Give up */
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index f8f3bfc..6903b69 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -656,6 +656,9 @@ static inline void set_page_guard(struct zone *zone, struct page *page,
 		return;
 
 	page_ext = lookup_page_ext(page);
+	if (unlikely(!page_ext))
+		return;
+
 	__set_bit(PAGE_EXT_DEBUG_GUARD, &page_ext->flags);
 
 	INIT_LIST_HEAD(&page->lru);
@@ -673,6 +676,9 @@ static inline void clear_page_guard(struct zone *zone, struct page *page,
 		return;
 
 	page_ext = lookup_page_ext(page);
+	if (unlikely(!page_ext))
+		return;
+
 	__clear_bit(PAGE_EXT_DEBUG_GUARD, &page_ext->flags);
 
 	set_page_private(page, 0);
@@ -2609,11 +2615,12 @@ struct page *buffered_rmqueue(struct zone *preferred_zone,
 				page = list_last_entry(list, struct page, lru);
 			else
 				page = list_first_entry(list, struct page, lru);
-		} while (page && check_new_pcp(page));
 
-		__dec_zone_state(zone, NR_ALLOC_BATCH);
-		list_del(&page->lru);
-		pcp->count--;
+			__dec_zone_state(zone, NR_ALLOC_BATCH);
+			list_del(&page->lru);
+			pcp->count--;
+
+		} while (check_new_pcp(page));
 	} else {
 		/*
 		 * We most definitely don't want callers attempting to
@@ -3023,6 +3030,7 @@ reset_fair:
 		apply_fair = false;
 		fair_skipped = false;
 		reset_alloc_batches(ac->preferred_zoneref->zone);
+		z = ac->preferred_zoneref;
 		goto zonelist_scan;
 	}
 
@@ -3596,6 +3604,17 @@ retry:
 	 */
 	alloc_flags = gfp_to_alloc_flags(gfp_mask);
 
+	/*
+	 * Reset the zonelist iterators if memory policies can be ignored.
+	 * These allocations are high priority and system rather than user
+	 * orientated.
+	 */
+	if ((alloc_flags & ALLOC_NO_WATERMARKS) || !(alloc_flags & ALLOC_CPUSET)) {
+		ac->zonelist = node_zonelist(numa_node_id(), gfp_mask);
+		ac->preferred_zoneref = first_zones_zonelist(ac->zonelist,
+					ac->high_zoneidx, ac->nodemask);
+	}
+
 	/* This is the last chance, in general, before the goto nopage. */
 	page = get_page_from_freelist(gfp_mask, order,
 				alloc_flags & ~ALLOC_NO_WATERMARKS, ac);
@@ -3604,12 +3623,6 @@ retry:
 
 	/* Allocate without watermarks if the context allows */
 	if (alloc_flags & ALLOC_NO_WATERMARKS) {
-		/*
-		 * Ignore mempolicies if ALLOC_NO_WATERMARKS on the grounds
-		 * the allocation is high priority and these type of
-		 * allocations are system rather than user orientated
-		 */
-		ac->zonelist = node_zonelist(numa_node_id(), gfp_mask);
 		page = get_page_from_freelist(gfp_mask, order,
 						ALLOC_NO_WATERMARKS, ac);
 		if (page)
@@ -3808,7 +3821,11 @@ retry_cpuset:
 	/* Dirty zone balancing only done in the fast path */
 	ac.spread_dirty_pages = (gfp_mask & __GFP_WRITE);
 
-	/* The preferred zone is used for statistics later */
+	/*
+	 * The preferred zone is used for statistics but crucially it is
+	 * also used as the starting point for the zonelist iterator. It
+	 * may get reset for allocations that ignore memory policies.
+	 */
 	ac.preferred_zoneref = first_zones_zonelist(ac.zonelist,
 					ac.high_zoneidx, ac.nodemask);
 	if (!ac.preferred_zoneref) {
diff --git a/mm/page_owner.c b/mm/page_owner.c
index 792b56d..c6cda3e 100644
--- a/mm/page_owner.c
+++ b/mm/page_owner.c
@@ -55,6 +55,8 @@ void __reset_page_owner(struct page *page, unsigned int order)
 
 	for (i = 0; i < (1 << order); i++) {
 		page_ext = lookup_page_ext(page + i);
+		if (unlikely(!page_ext))
+			continue;
 		__clear_bit(PAGE_EXT_OWNER, &page_ext->flags);
 	}
 }
@@ -62,6 +64,7 @@ void __reset_page_owner(struct page *page, unsigned int order)
 void __set_page_owner(struct page *page, unsigned int order, gfp_t gfp_mask)
 {
 	struct page_ext *page_ext = lookup_page_ext(page);
+
 	struct stack_trace trace = {
 		.nr_entries = 0,
 		.max_entries = ARRAY_SIZE(page_ext->trace_entries),
@@ -69,6 +72,9 @@ void __set_page_owner(struct page *page, unsigned int order, gfp_t gfp_mask)
 		.skip = 3,
 	};
 
+	if (unlikely(!page_ext))
+		return;
+
 	save_stack_trace(&trace);
 
 	page_ext->order = order;
@@ -82,6 +88,8 @@ void __set_page_owner(struct page *page, unsigned int order, gfp_t gfp_mask)
 void __set_page_owner_migrate_reason(struct page *page, int reason)
 {
 	struct page_ext *page_ext = lookup_page_ext(page);
+	if (unlikely(!page_ext))
+		return;
 
 	page_ext->last_migrate_reason = reason;
 }
@@ -89,6 +97,12 @@ void __set_page_owner_migrate_reason(struct page *page, int reason)
 gfp_t __get_page_owner_gfp(struct page *page)
 {
 	struct page_ext *page_ext = lookup_page_ext(page);
+	if (unlikely(!page_ext))
+		/*
+		 * The caller just returns 0 if no valid gfp
+		 * So return 0 here too.
+		 */
+		return 0;
 
 	return page_ext->gfp_mask;
 }
@@ -99,6 +113,9 @@ void __copy_page_owner(struct page *oldpage, struct page *newpage)
 	struct page_ext *new_ext = lookup_page_ext(newpage);
 	int i;
 
+	if (unlikely(!old_ext || !new_ext))
+		return;
+
 	new_ext->order = old_ext->order;
 	new_ext->gfp_mask = old_ext->gfp_mask;
 	new_ext->nr_entries = old_ext->nr_entries;
@@ -193,6 +210,11 @@ void __dump_page_owner(struct page *page)
 	gfp_t gfp_mask = page_ext->gfp_mask;
 	int mt = gfpflags_to_migratetype(gfp_mask);
 
+	if (unlikely(!page_ext)) {
+		pr_alert("There is not page extension available.\n");
+		return;
+	}
+
 	if (!test_bit(PAGE_EXT_OWNER, &page_ext->flags)) {
 		pr_alert("page_owner info is not active (free page?)\n");
 		return;
@@ -251,6 +273,8 @@ read_page_owner(struct file *file, char __user *buf, size_t count, loff_t *ppos)
 		}
 
 		page_ext = lookup_page_ext(page);
+		if (unlikely(!page_ext))
+			continue;
 
 		/*
 		 * Some pages could be missed by concurrent allocation or free,
@@ -317,6 +341,8 @@ static void init_pages_in_zone(pg_data_t *pgdat, struct zone *zone)
 				continue;
 
 			page_ext = lookup_page_ext(page);
+			if (unlikely(!page_ext))
+				continue;
 
 			/* Maybe overraping zone */
 			if (test_bit(PAGE_EXT_OWNER, &page_ext->flags))
diff --git a/mm/page_poison.c b/mm/page_poison.c
index 1eae5fa..2e647c6 100644
--- a/mm/page_poison.c
+++ b/mm/page_poison.c
@@ -54,6 +54,9 @@ static inline void set_page_poison(struct page *page)
 	struct page_ext *page_ext;
 
 	page_ext = lookup_page_ext(page);
+	if (unlikely(!page_ext))
+		return;
+
 	__set_bit(PAGE_EXT_DEBUG_POISON, &page_ext->flags);
 }
 
@@ -62,6 +65,9 @@ static inline void clear_page_poison(struct page *page)
 	struct page_ext *page_ext;
 
 	page_ext = lookup_page_ext(page);
+	if (unlikely(!page_ext))
+		return;
+
 	__clear_bit(PAGE_EXT_DEBUG_POISON, &page_ext->flags);
 }
 
@@ -70,7 +76,7 @@ bool page_is_poisoned(struct page *page)
 	struct page_ext *page_ext;
 
 	page_ext = lookup_page_ext(page);
-	if (!page_ext)
+	if (unlikely(!page_ext))
 		return false;
 
 	return test_bit(PAGE_EXT_DEBUG_POISON, &page_ext->flags);
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index cf7ad1a..e11475c 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -1105,7 +1105,7 @@ EXPORT_SYMBOL_GPL(vm_unmap_aliases);
  */
 void vm_unmap_ram(const void *mem, unsigned int count)
 {
-	unsigned long size = count << PAGE_SHIFT;
+	unsigned long size = (unsigned long)count << PAGE_SHIFT;
 	unsigned long addr = (unsigned long)mem;
 
 	BUG_ON(!addr);
@@ -1140,7 +1140,7 @@ EXPORT_SYMBOL(vm_unmap_ram);
  */
 void *vm_map_ram(struct page **pages, unsigned int count, int node, pgprot_t prot)
 {
-	unsigned long size = count << PAGE_SHIFT;
+	unsigned long size = (unsigned long)count << PAGE_SHIFT;
 	unsigned long addr;
 	void *mem;
 
@@ -1574,14 +1574,15 @@ void *vmap(struct page **pages, unsigned int count,
 		unsigned long flags, pgprot_t prot)
 {
 	struct vm_struct *area;
+	unsigned long size;		/* In bytes */
 
 	might_sleep();
 
 	if (count > totalram_pages)
 		return NULL;
 
-	area = get_vm_area_caller((count << PAGE_SHIFT), flags,
-					__builtin_return_address(0));
+	size = (unsigned long)count << PAGE_SHIFT;
+	area = get_vm_area_caller(size, flags, __builtin_return_address(0));
 	if (!area)
 		return NULL;
 
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 77e42ef..cb2a67b 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1061,6 +1061,8 @@ static void pagetypeinfo_showmixedcount_print(struct seq_file *m,
 				continue;
 
 			page_ext = lookup_page_ext(page);
+			if (unlikely(!page_ext))
+				continue;
 
 			if (!test_bit(PAGE_EXT_OWNER, &page_ext->flags))
 				continue;
diff --git a/mm/z3fold.c b/mm/z3fold.c
index 34917d5..8f9e89c 100644
--- a/mm/z3fold.c
+++ b/mm/z3fold.c
@@ -412,7 +412,7 @@ static void z3fold_free(struct z3fold_pool *pool, unsigned long handle)
 		/* HEADLESS page stored */
 		bud = HEADLESS;
 	} else {
-		bud = (handle - zhdr->first_num) & BUDDY_MASK;
+		bud = handle_to_buddy(handle);
 
 		switch (bud) {
 		case FIRST:
@@ -572,15 +572,19 @@ next:
 			pool->pages_nr--;
 			spin_unlock(&pool->lock);
 			return 0;
-		} else if (zhdr->first_chunks != 0 &&
-			   zhdr->last_chunks != 0 && zhdr->middle_chunks != 0) {
-			/* Full, add to buddied list */
-			list_add(&zhdr->buddy, &pool->buddied);
-		} else if (!test_bit(PAGE_HEADLESS, &page->private)) {
-			z3fold_compact_page(zhdr);
-			/* add to unbuddied list */
-			freechunks = num_free_chunks(zhdr);
-			list_add(&zhdr->buddy, &pool->unbuddied[freechunks]);
+		}  else if (!test_bit(PAGE_HEADLESS, &page->private)) {
+			if (zhdr->first_chunks != 0 &&
+			    zhdr->last_chunks != 0 &&
+			    zhdr->middle_chunks != 0) {
+				/* Full, add to buddied list */
+				list_add(&zhdr->buddy, &pool->buddied);
+			} else {
+				z3fold_compact_page(zhdr);
+				/* add to unbuddied list */
+				freechunks = num_free_chunks(zhdr);
+				list_add(&zhdr->buddy,
+					 &pool->unbuddied[freechunks]);
+			}
 		}
 
 		/* add to beginning of LRU */