Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

kernel/bpf/arraymap.c

@@ -26,8 +26,10 @@ static void bpf_array_free_percpu(struct bpf_array *array)
 {
 	int i;
 
-	for (i = 0; i < array->map.max_entries; i++)
+	for (i = 0; i < array->map.max_entries; i++) {
 		free_percpu(array->pptrs[i]);
+		cond_resched();
+	}
 }
 
 static int bpf_array_alloc_percpu(struct bpf_array *array)
@@ -43,6 +45,7 @@ static int bpf_array_alloc_percpu(struct bpf_array *array)
 			return -ENOMEM;
 		}
 		array->pptrs[i] = ptr;
+		cond_resched();
 	}
 
 	return 0;
@@ -73,11 +76,11 @@ static int array_map_alloc_check(union bpf_attr *attr)
 static struct bpf_map *array_map_alloc(union bpf_attr *attr)
 {
 	bool percpu = attr->map_type == BPF_MAP_TYPE_PERCPU_ARRAY;
-	int numa_node = bpf_map_attr_numa_node(attr);
+	int ret, numa_node = bpf_map_attr_numa_node(attr);
 	u32 elem_size, index_mask, max_entries;
 	bool unpriv = !capable(CAP_SYS_ADMIN);
+	u64 cost, array_size, mask64;
 	struct bpf_array *array;
-	u64 array_size, mask64;
 
 	elem_size = round_up(attr->value_size, 8);
 
@@ -109,8 +112,19 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr)
 		array_size += (u64) max_entries * elem_size;
 
 	/* make sure there is no u32 overflow later in round_up() */
-	if (array_size >= U32_MAX - PAGE_SIZE)
+	cost = array_size;
+	if (cost >= U32_MAX - PAGE_SIZE)
 		return ERR_PTR(-ENOMEM);
+	if (percpu) {
+		cost += (u64)attr->max_entries * elem_size * num_possible_cpus();
+		if (cost >= U32_MAX - PAGE_SIZE)
+			return ERR_PTR(-ENOMEM);
+	}
+	cost = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT;
+
+	ret = bpf_map_precharge_memlock(cost);
+	if (ret < 0)
+		return ERR_PTR(ret);
 
 	/* allocate all map elements and zero-initialize them */
 	array = bpf_map_area_alloc(array_size, numa_node);
@@ -121,20 +135,13 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr)
 
 	/* copy mandatory map attributes */
 	bpf_map_init_from_attr(&array->map, attr);
+	array->map.pages = cost;
 	array->elem_size = elem_size;
 
-	if (!percpu)
-		goto out;
-
-	array_size += (u64) attr->max_entries * elem_size * num_possible_cpus();
-
-	if (array_size >= U32_MAX - PAGE_SIZE ||
-	    bpf_array_alloc_percpu(array)) {
+	if (percpu && bpf_array_alloc_percpu(array)) {
 		bpf_map_area_free(array);
 		return ERR_PTR(-ENOMEM);
 	}
-out:
-	array->map.pages = round_up(array_size, PAGE_SIZE) >> PAGE_SHIFT;
 
 	return &array->map;
 }

kernel/bpf/core.c

@@ -1590,7 +1590,7 @@ int bpf_prog_array_copy_to_user(struct bpf_prog_array __rcu *progs,
 	 * so always copy 'cnt' prog_ids to the user.
 	 * In a rare race the user will see zero prog_ids
 	 */
-	ids = kcalloc(cnt, sizeof(u32), GFP_USER);
+	ids = kcalloc(cnt, sizeof(u32), GFP_USER | __GFP_NOWARN);
 	if (!ids)
 		return -ENOMEM;
 	rcu_read_lock();

kernel/bpf/cpumap.c

@@ -334,7 +334,7 @@ static int cpu_map_kthread_run(void *data)
 static struct bpf_cpu_map_entry *__cpu_map_entry_alloc(u32 qsize, u32 cpu,
 						       int map_id)
 {
-	gfp_t gfp = GFP_ATOMIC|__GFP_NOWARN;
+	gfp_t gfp = GFP_KERNEL | __GFP_NOWARN;
 	struct bpf_cpu_map_entry *rcpu;
 	int numa, err;
 

kernel/bpf/lpm_trie.c

@@ -555,7 +555,10 @@ static void trie_free(struct bpf_map *map)
 	struct lpm_trie_node __rcu **slot;
 	struct lpm_trie_node *node;
 
-	raw_spin_lock(&trie->lock);
+	/* Wait for outstanding programs to complete
+	 * update/lookup/delete/get_next_key and free the trie.
+	 */
+	synchronize_rcu();
 
 	/* Always start at the root and walk down to a node that has no
 	 * children. Then free that node, nullify its reference in the parent
@@ -566,10 +569,9 @@ static void trie_free(struct bpf_map *map)
 		slot = &trie->root;
 
 		for (;;) {
-			node = rcu_dereference_protected(*slot,
-					lockdep_is_held(&trie->lock));
+			node = rcu_dereference_protected(*slot, 1);
 			if (!node)
-				goto unlock;
+				goto out;
 
 			if (rcu_access_pointer(node->child[0])) {
 				slot = &node->child[0];
@@ -587,8 +589,8 @@ static void trie_free(struct bpf_map *map)
 		}
 	}
 
-unlock:
-	raw_spin_unlock(&trie->lock);
+out:
+	kfree(trie);
 }
 
 static int trie_get_next_key(struct bpf_map *map, void *_key, void *_next_key)

kernel/bpf/sockmap.c

@@ -521,8 +521,8 @@ static struct smap_psock *smap_init_psock(struct sock *sock,
 static struct bpf_map *sock_map_alloc(union bpf_attr *attr)
 {
 	struct bpf_stab *stab;
-	int err = -EINVAL;
 	u64 cost;
+	int err;
 
 	if (!capable(CAP_NET_ADMIN))
 		return ERR_PTR(-EPERM);
@@ -547,6 +547,7 @@ static struct bpf_map *sock_map_alloc(union bpf_attr *attr)
 
 	/* make sure page count doesn't overflow */
 	cost = (u64) stab->map.max_entries * sizeof(struct sock *);
+	err = -EINVAL;
 	if (cost >= U32_MAX - PAGE_SIZE)
 		goto free_stab;
 

kernel/fork.c

@@ -592,7 +592,7 @@ static void check_mm(struct mm_struct *mm)
  * is dropped: either by a lazy thread or by
  * mmput. Free the page directory and the mm.
  */
-static void __mmdrop(struct mm_struct *mm)
+void __mmdrop(struct mm_struct *mm)
 {
 	BUG_ON(mm == &init_mm);
 	mm_free_pgd(mm);
@@ -603,18 +603,7 @@ static void __mmdrop(struct mm_struct *mm)
 	put_user_ns(mm->user_ns);
 	free_mm(mm);
 }
-
-void mmdrop(struct mm_struct *mm)
-{
-	/*
-	 * The implicit full barrier implied by atomic_dec_and_test() is
-	 * required by the membarrier system call before returning to
-	 * user-space, after storing to rq->curr.
-	 */
-	if (unlikely(atomic_dec_and_test(&mm->mm_count)))
-		__mmdrop(mm);
-}
-EXPORT_SYMBOL_GPL(mmdrop);
+EXPORT_SYMBOL_GPL(__mmdrop);
 
 static void mmdrop_async_fn(struct work_struct *work)
 {

kernel/relay.c

@@ -163,7 +163,7 @@ static struct rchan_buf *relay_create_buf(struct rchan *chan)
 {
 	struct rchan_buf *buf;
 
-	if (chan->n_subbufs > UINT_MAX / sizeof(size_t *))
+	if (chan->n_subbufs > KMALLOC_MAX_SIZE / sizeof(size_t *))
 		return NULL;
 
 	buf = kzalloc(sizeof(struct rchan_buf), GFP_KERNEL);

kernel/seccomp.c

@@ -1076,14 +1076,16 @@ long seccomp_get_metadata(struct task_struct *task,
 
 	size = min_t(unsigned long, size, sizeof(kmd));
 
-	if (copy_from_user(&kmd, data, size))
+	if (size < sizeof(kmd.filter_off))
+		return -EINVAL;
+
+	if (copy_from_user(&kmd.filter_off, data, sizeof(kmd.filter_off)))
 		return -EFAULT;
 
 	filter = get_nth_filter(task, kmd.filter_off);
 	if (IS_ERR(filter))
 		return PTR_ERR(filter);
 
-	memset(&kmd, 0, sizeof(kmd));
 	if (filter->log)
 		kmd.flags |= SECCOMP_FILTER_FLAG_LOG;
 

kernel/trace/bpf_trace.c

@@ -872,6 +872,8 @@ int perf_event_query_prog_array(struct perf_event *event, void __user *info)
 		return -EINVAL;
 	if (copy_from_user(&query, uquery, sizeof(query)))
 		return -EFAULT;
+	if (query.ids_len > BPF_TRACE_MAX_PROGS)
+		return -E2BIG;
 
 	mutex_lock(&bpf_event_mutex);
 	ret = bpf_prog_array_copy_info(event->tp_event->prog_array,

kernel/user.c

@@ -101,6 +101,7 @@ struct user_struct root_user = {
 	.sigpending	= ATOMIC_INIT(0),
 	.locked_shm     = 0,
 	.uid		= GLOBAL_ROOT_UID,
+	.ratelimit	= RATELIMIT_STATE_INIT(root_user.ratelimit, 0, 0),
 };
 
 /*
@@ -191,6 +192,8 @@ struct user_struct *alloc_uid(kuid_t uid)
 
 		new->uid = uid;
 		atomic_set(&new->__count, 1);
+		ratelimit_state_init(&new->ratelimit, HZ, 100);
+		ratelimit_set_flags(&new->ratelimit, RATELIMIT_MSG_ON_RELEASE);
 
 		/*
 		 * Before adding this, check whether we raced

kernel/workqueue.c

@@ -4179,6 +4179,22 @@ void workqueue_set_max_active(struct workqueue_struct *wq, int max_active)
 }
 EXPORT_SYMBOL_GPL(workqueue_set_max_active);
 
+/**
+ * current_work - retrieve %current task's work struct
+ *
+ * Determine if %current task is a workqueue worker and what it's working on.
+ * Useful to find out the context that the %current task is running in.
+ *
+ * Return: work struct if %current task is a workqueue worker, %NULL otherwise.
+ */
+struct work_struct *current_work(void)
+{
+	struct worker *worker = current_wq_worker();
+
+	return worker ? worker->current_work : NULL;
+}
+EXPORT_SYMBOL(current_work);
+
 /**
  * current_is_workqueue_rescuer - is %current workqueue rescuer?
  *