1 files changed, 109 insertions, 50 deletions

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 6f6dc8712e39..7ddf91c4295f 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -409,8 +409,10 @@ int memcg_expand_shrinker_maps(int new_id)
 		if (mem_cgroup_is_root(memcg))
 			continue;
 		ret = memcg_expand_one_shrinker_map(memcg, size, old_size);
-		if (ret)
+		if (ret) {
+			mem_cgroup_iter_break(NULL, memcg);
 			goto unlock;
+		}
 	}
 unlock:
 	if (!ret)
@@ -775,6 +777,17 @@ void __mod_lruvec_slab_state(void *p, enum node_stat_item idx, int val)
 	rcu_read_unlock();
 }
 
+void mod_memcg_obj_state(void *p, int idx, int val)
+{
+	struct mem_cgroup *memcg;
+
+	rcu_read_lock();
+	memcg = mem_cgroup_from_obj(p);
+	if (memcg)
+		mod_memcg_state(memcg, idx, val);
+	rcu_read_unlock();
+}
+
 /**
  * __count_memcg_events - account VM events in a cgroup
  * @memcg: the memory cgroup
@@ -2295,28 +2308,41 @@ static void high_work_func(struct work_struct *work)
  #define MEMCG_DELAY_SCALING_SHIFT 14
 
 /*
- * Scheduled by try_charge() to be executed from the userland return path
- * and reclaims memory over the high limit.
+ * Get the number of jiffies that we should penalise a mischievous cgroup which
+ * is exceeding its memory.high by checking both it and its ancestors.
  */
-void mem_cgroup_handle_over_high(void)
+static unsigned long calculate_high_delay(struct mem_cgroup *memcg,
+					  unsigned int nr_pages)
 {
-	unsigned long usage, high, clamped_high;
-	unsigned long pflags;
-	unsigned long penalty_jiffies, overage;
-	unsigned int nr_pages = current->memcg_nr_pages_over_high;
-	struct mem_cgroup *memcg;
+	unsigned long penalty_jiffies;
+	u64 max_overage = 0;
 
-	if (likely(!nr_pages))
-		return;
+	do {
+		unsigned long usage, high;
+		u64 overage;
 
-	memcg = get_mem_cgroup_from_mm(current->mm);
-	reclaim_high(memcg, nr_pages, GFP_KERNEL);
-	current->memcg_nr_pages_over_high = 0;
+		usage = page_counter_read(&memcg->memory);
+		high = READ_ONCE(memcg->high);
+
+		/*
+		 * Prevent division by 0 in overage calculation by acting as if
+		 * it was a threshold of 1 page
+		 */
+		high = max(high, 1UL);
+
+		overage = usage - high;
+		overage <<= MEMCG_DELAY_PRECISION_SHIFT;
+		overage = div64_u64(overage, high);
+
+		if (overage > max_overage)
+			max_overage = overage;
+	} while ((memcg = parent_mem_cgroup(memcg)) &&
+		 !mem_cgroup_is_root(memcg));
+
+	if (!max_overage)
+		return 0;
 
 	/*
-	 * memory.high is breached and reclaim is unable to keep up. Throttle
-	 * allocators proactively to slow down excessive growth.
-	 *
 	 * We use overage compared to memory.high to calculate the number of
 	 * jiffies to sleep (penalty_jiffies). Ideally this value should be
 	 * fairly lenient on small overages, and increasingly harsh when the
@@ -2324,24 +2350,9 @@ void mem_cgroup_handle_over_high(void)
 	 * its crazy behaviour, so we exponentially increase the delay based on
 	 * overage amount.
 	 */
-
-	usage = page_counter_read(&memcg->memory);
-	high = READ_ONCE(memcg->high);
-
-	if (usage <= high)
-		goto out;
-
-	/*
-	 * Prevent division by 0 in overage calculation by acting as if it was a
-	 * threshold of 1 page
-	 */
-	clamped_high = max(high, 1UL);
-
-	overage = div_u64((u64)(usage - high) << MEMCG_DELAY_PRECISION_SHIFT,
-			  clamped_high);
-
-	penalty_jiffies = ((u64)overage * overage * HZ)
-		>> (MEMCG_DELAY_PRECISION_SHIFT + MEMCG_DELAY_SCALING_SHIFT);
+	penalty_jiffies = max_overage * max_overage * HZ;
+	penalty_jiffies >>= MEMCG_DELAY_PRECISION_SHIFT;
+	penalty_jiffies >>= MEMCG_DELAY_SCALING_SHIFT;
 
 	/*
 	 * Factor in the task's own contribution to the overage, such that four
@@ -2358,7 +2369,32 @@ void mem_cgroup_handle_over_high(void)
 	 * application moving forwards and also permit diagnostics, albeit
 	 * extremely slowly.
 	 */
-	penalty_jiffies = min(penalty_jiffies, MEMCG_MAX_HIGH_DELAY_JIFFIES);
+	return min(penalty_jiffies, MEMCG_MAX_HIGH_DELAY_JIFFIES);
+}
+
+/*
+ * Scheduled by try_charge() to be executed from the userland return path
+ * and reclaims memory over the high limit.
+ */
+void mem_cgroup_handle_over_high(void)
+{
+	unsigned long penalty_jiffies;
+	unsigned long pflags;
+	unsigned int nr_pages = current->memcg_nr_pages_over_high;
+	struct mem_cgroup *memcg;
+
+	if (likely(!nr_pages))
+		return;
+
+	memcg = get_mem_cgroup_from_mm(current->mm);
+	reclaim_high(memcg, nr_pages, GFP_KERNEL);
+	current->memcg_nr_pages_over_high = 0;
+
+	/*
+	 * memory.high is breached and reclaim is unable to keep up. Throttle
+	 * allocators proactively to slow down excessive growth.
+	 */
+	penalty_jiffies = calculate_high_delay(memcg, nr_pages);
 
 	/*
 	 * Don't sleep if the amount of jiffies this memcg owes us is so low
@@ -2636,6 +2672,33 @@ static void commit_charge(struct page *page, struct mem_cgroup *memcg,
 }
 
 #ifdef CONFIG_MEMCG_KMEM
+/*
+ * Returns a pointer to the memory cgroup to which the kernel object is charged.
+ *
+ * The caller must ensure the memcg lifetime, e.g. by taking rcu_read_lock(),
+ * cgroup_mutex, etc.
+ */
+struct mem_cgroup *mem_cgroup_from_obj(void *p)
+{
+	struct page *page;
+
+	if (mem_cgroup_disabled())
+		return NULL;
+
+	page = virt_to_head_page(p);
+
+	/*
+	 * Slab pages don't have page->mem_cgroup set because corresponding
+	 * kmem caches can be reparented during the lifetime. That's why
+	 * memcg_from_slab_page() should be used instead.
+	 */
+	if (PageSlab(page))
+		return memcg_from_slab_page(page);
+
+	/* All other pages use page->mem_cgroup */
+	return page->mem_cgroup;
+}
+
 static int memcg_alloc_cache_id(void)
 {
 	int id, size;
@@ -4025,7 +4088,7 @@ static void __mem_cgroup_usage_unregister_event(struct mem_cgroup *memcg,
 	struct mem_cgroup_thresholds *thresholds;
 	struct mem_cgroup_threshold_ary *new;
 	unsigned long usage;
-	int i, j, size;
+	int i, j, size, entries;
 
 	mutex_lock(&memcg->thresholds_lock);
 
@@ -4045,14 +4108,20 @@ static void __mem_cgroup_usage_unregister_event(struct mem_cgroup *memcg,
 	__mem_cgroup_threshold(memcg, type == _MEMSWAP);
 
 	/* Calculate new number of threshold */
-	size = 0;
+	size = entries = 0;
 	for (i = 0; i < thresholds->primary->size; i++) {
 		if (thresholds->primary->entries[i].eventfd != eventfd)
 			size++;
+		else
+			entries++;
 	}
 
 	new = thresholds->spare;
 
+	/* If no items related to eventfd have been cleared, nothing to do */
+	if (!entries)
+		goto unlock;
+
 	/* Set thresholds array to NULL if we don't have thresholds */
 	if (!size) {
 		kfree(new);
@@ -6680,19 +6749,9 @@ void mem_cgroup_sk_alloc(struct sock *sk)
 	if (!mem_cgroup_sockets_enabled)
 		return;
 
-	/*
-	 * Socket cloning can throw us here with sk_memcg already
-	 * filled. It won't however, necessarily happen from
-	 * process context. So the test for root memcg given
-	 * the current task's memcg won't help us in this case.
-	 *
-	 * Respecting the original socket's memcg is a better
-	 * decision in this case.
-	 */
-	if (sk->sk_memcg) {
-		css_get(&sk->sk_memcg->css);
+	/* Do not associate the sock with unrelated interrupted task's memcg. */
+	if (in_interrupt())
 		return;
-	}
 
 	rcu_read_lock();
 	memcg = mem_cgroup_from_task(current);