Merge branch 'akpm' (patches from Andrew)

Merge various fixes from Andrew Morton:
 "10 fixes"

* emailed patches from Andrew Morton <[email protected]>:
  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()

Author: torvalds

Documentation/kdump/gdbmacros.txt

@@ -170,21 +170,92 @@ document trapinfo
 	address the kernel panicked.
 end
 
+define dump_log_idx
+	set $idx = $arg0
+	if ($argc > 1)
+		set $prev_flags = $arg1
+	else
+		set $prev_flags = 0
+	end
+	set $msg = ((struct printk_log *) (log_buf + $idx))
+	set $prefix = 1
+	set $newline = 1
+	set $log = log_buf + $idx + sizeof(*$msg)
 
-define dmesg
-	set $i = 0
-	set $end_idx = (log_end - 1) & (log_buf_len - 1)
+	# prev & LOG_CONT && !(msg->flags & LOG_PREIX)
+	if (($prev_flags & 8) && !($msg->flags & 4))
+		set $prefix = 0
+	end
+
+	# msg->flags & LOG_CONT
+	if ($msg->flags & 8)
+		# (prev & LOG_CONT && !(prev & LOG_NEWLINE))
+		if (($prev_flags & 8) && !($prev_flags & 2))
+			set $prefix = 0
+		end
+		# (!(msg->flags & LOG_NEWLINE))
+		if (!($msg->flags & 2))
+			set $newline = 0
+		end
+	end
+
+	if ($prefix)
+		printf "[%5lu.%06lu] ", $msg->ts_nsec / 1000000000, $msg->ts_nsec % 1000000000
+	end
+	if ($msg->text_len != 0)
+		eval "printf \"%%%d.%ds\", $log", $msg->text_len, $msg->text_len
+	end
+	if ($newline)
+		printf "\n"
+	end
+	if ($msg->dict_len > 0)
+		set $dict = $log + $msg->text_len
+		set $idx = 0
+		set $line = 1
+		while ($idx < $msg->dict_len)
+			if ($line)
+				printf " "
+				set $line = 0
+			end
+			set $c = $dict[$idx]
+			if ($c == '\0')
+				printf "\n"
+				set $line = 1
+			else
+				if ($c < ' ' || $c >= 127 || $c == '\\')
+					printf "\\x%02x", $c
+				else
+					printf "%c", $c
+				end
+			end
+			set $idx = $idx + 1
+		end
+		printf "\n"
+	end
+end
+document dump_log_idx
+	Dump a single log given its index in the log buffer.  The first
+	parameter is the index into log_buf, the second is optional and
+	specified the previous log buffer's flags, used for properly
+	formatting continued lines.
+end
 
-	while ($i < logged_chars)
-		set $idx = (log_end - 1 - logged_chars + $i) & (log_buf_len - 1)
+define dmesg
+	set $i = log_first_idx
+	set $end_idx = log_first_idx
+	set $prev_flags = 0
 
-		if ($idx + 100 <= $end_idx) || \
-		   ($end_idx <= $idx && $idx + 100 < log_buf_len)
-			printf "%.100s", &log_buf[$idx]
-			set $i = $i + 100
+	while (1)
+		set $msg = ((struct printk_log *) (log_buf + $i))
+		if ($msg->len == 0)
+			set $i = 0
 		else
-			printf "%c", log_buf[$idx]
-			set $i = $i + 1
+			dump_log_idx $i $prev_flags
+			set $i = $i + $msg->len
+			set $prev_flags = $msg->flags
+		end
+		if ($i == $end_idx)
+			loop_break
 		end
 	end
 end

include/linux/page_idle.h

@@ -46,33 +46,62 @@ extern struct page_ext_operations page_idle_ops;
 
 static inline bool page_is_young(struct page *page)
 {
-	return test_bit(PAGE_EXT_YOUNG, &lookup_page_ext(page)->flags);
+	struct page_ext *page_ext = lookup_page_ext(page);
+
+	if (unlikely(!page_ext))
+		return false;
+
+	return test_bit(PAGE_EXT_YOUNG, &page_ext->flags);
 }
 
 static inline void set_page_young(struct page *page)
 {
-	set_bit(PAGE_EXT_YOUNG, &lookup_page_ext(page)->flags);
+	struct page_ext *page_ext = lookup_page_ext(page);
+
+	if (unlikely(!page_ext))
+		return;
+
+	set_bit(PAGE_EXT_YOUNG, &page_ext->flags);
 }
 
 static inline bool test_and_clear_page_young(struct page *page)
 {
-	return test_and_clear_bit(PAGE_EXT_YOUNG,
-				  &lookup_page_ext(page)->flags);
+	struct page_ext *page_ext = lookup_page_ext(page);
+
+	if (unlikely(!page_ext))
+		return false;
+
+	return test_and_clear_bit(PAGE_EXT_YOUNG, &page_ext->flags);
 }
 
 static inline bool page_is_idle(struct page *page)
 {
-	return test_bit(PAGE_EXT_IDLE, &lookup_page_ext(page)->flags);
+	struct page_ext *page_ext = lookup_page_ext(page);
+
+	if (unlikely(!page_ext))
+		return false;
+
+	return test_bit(PAGE_EXT_IDLE, &page_ext->flags);
 }
 
 static inline void set_page_idle(struct page *page)
 {
-	set_bit(PAGE_EXT_IDLE, &lookup_page_ext(page)->flags);
+	struct page_ext *page_ext = lookup_page_ext(page);
+
+	if (unlikely(!page_ext))
+		return;
+
+	set_bit(PAGE_EXT_IDLE, &page_ext->flags);
 }
 
 static inline void clear_page_idle(struct page *page)
 {
-	clear_bit(PAGE_EXT_IDLE, &lookup_page_ext(page)->flags);
+	struct page_ext *page_ext = lookup_page_ext(page);
+
+	if (unlikely(!page_ext))
+		return;
+
+	clear_bit(PAGE_EXT_IDLE, &page_ext->flags);
 }
 #endif /* CONFIG_64BIT */
 

mm/memcontrol.c

@@ -2896,13 +2896,16 @@ 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);
 		child->kmemcg_id = parent->kmemcg_id;
 		if (!memcg->use_hierarchy)
 			break;
 	}
+	rcu_read_unlock();
+
 	memcg_drain_all_list_lrus(kmemcg_id, parent->kmemcg_id);
 
 	memcg_free_cache_id(kmemcg_id);

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 */

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 @@ get_page_from_freelist(gfp_t gfp_mask, unsigned int order, int alloc_flags,
 		apply_fair = false;
 		fair_skipped = false;
 		reset_alloc_batches(ac->preferred_zoneref->zone);
+		z = ac->preferred_zoneref;
 		goto zonelist_scan;
 	}
 
@@ -3596,6 +3604,17 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
 	 */
 	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 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
 
 	/* 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 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order,
 	/* 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) {

mm/page_owner.c

@@ -55,20 +55,26 @@ 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);
 	}
 }
 
 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),
 		.entries = &page_ext->trace_entries[0],
 		.skip = 3,
 	};
 
+	if (unlikely(!page_ext))
+		return;
+
 	save_stack_trace(&trace);
 
 	page_ext->order = order;
@@ -82,13 +88,21 @@ 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;
 }
 
 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))