Merge branch 'master' into for-4.4-fixes

The following commit which went into mainline through networking tree

  3b13758f51 ("cgroups: Allow dynamically changing net_classid")

conflicts in net/core/netclassid_cgroup.c with the following pending
fix in cgroup/for-4.4-fixes.

  1f7dd3e5a6 ("cgroup: fix handling of multi-destination migration from subtree_control enabling")

The former separates out update_classid() from cgrp_attach() and
updates it to walk all fds of all tasks in the target css so that it
can be used from both migration and config change paths.  The latter
drops @css from cgrp_attach().

Resolve the conflict by making cgrp_attach() call update_classid()
with the css from the first task.  We can revive @tset walking in
cgrp_attach() but given that net_cls is v1 only where there always is
only one target css during migration, this is fine.

Signed-off-by: Tejun Heo <tj@kernel.org>
Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Cc: Nina Schiff <ninasc@fb.com>

kernel/bpf/arraymap.c

@@ -28,11 +28,17 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr)
 	    attr->value_size == 0)
 		return ERR_PTR(-EINVAL);
 
+	if (attr->value_size >= 1 << (KMALLOC_SHIFT_MAX - 1))
+		/* if value_size is bigger, the user space won't be able to
+		 * access the elements.
+		 */
+		return ERR_PTR(-E2BIG);
+
 	elem_size = round_up(attr->value_size, 8);
 
 	/* check round_up into zero and u32 overflow */
 	if (elem_size == 0 ||
-	    attr->max_entries > (U32_MAX - sizeof(*array)) / elem_size)
+	    attr->max_entries > (U32_MAX - PAGE_SIZE - sizeof(*array)) / elem_size)
 		return ERR_PTR(-ENOMEM);
 
 	array_size = sizeof(*array) + attr->max_entries * elem_size;
@@ -105,7 +111,7 @@ static int array_map_update_elem(struct bpf_map *map, void *key, void *value,
 		/* all elements already exist */
 		return -EEXIST;
 
-	memcpy(array->value + array->elem_size * index, value, array->elem_size);
+	memcpy(array->value + array->elem_size * index, value, map->value_size);
 	return 0;
 }
 

kernel/bpf/hashtab.c

@@ -64,12 +64,35 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr)
 		 */
 		goto free_htab;
 
-	err = -ENOMEM;
+	if (htab->map.value_size >= (1 << (KMALLOC_SHIFT_MAX - 1)) -
+	    MAX_BPF_STACK - sizeof(struct htab_elem))
+		/* if value_size is bigger, the user space won't be able to
+		 * access the elements via bpf syscall. This check also makes
+		 * sure that the elem_size doesn't overflow and it's
+		 * kmalloc-able later in htab_map_update_elem()
+		 */
+		goto free_htab;
+
+	htab->elem_size = sizeof(struct htab_elem) +
+			  round_up(htab->map.key_size, 8) +
+			  htab->map.value_size;
+
 	/* prevent zero size kmalloc and check for u32 overflow */
 	if (htab->n_buckets == 0 ||
 	    htab->n_buckets > U32_MAX / sizeof(struct hlist_head))
 		goto free_htab;
 
+	if ((u64) htab->n_buckets * sizeof(struct hlist_head) +
+	    (u64) htab->elem_size * htab->map.max_entries >=
+	    U32_MAX - PAGE_SIZE)
+		/* make sure page count doesn't overflow */
+		goto free_htab;
+
+	htab->map.pages = round_up(htab->n_buckets * sizeof(struct hlist_head) +
+				   htab->elem_size * htab->map.max_entries,
+				   PAGE_SIZE) >> PAGE_SHIFT;
+
+	err = -ENOMEM;
 	htab->buckets = kmalloc_array(htab->n_buckets, sizeof(struct hlist_head),
 				      GFP_USER | __GFP_NOWARN);
 
@@ -85,13 +108,6 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr)
 	raw_spin_lock_init(&htab->lock);
 	htab->count = 0;
 
-	htab->elem_size = sizeof(struct htab_elem) +
-			  round_up(htab->map.key_size, 8) +
-			  htab->map.value_size;
-
-	htab->map.pages = round_up(htab->n_buckets * sizeof(struct hlist_head) +
-				   htab->elem_size * htab->map.max_entries,
-				   PAGE_SIZE) >> PAGE_SHIFT;
 	return &htab->map;
 
 free_htab:
@@ -222,7 +238,7 @@ static int htab_map_update_elem(struct bpf_map *map, void *key, void *value,
 	WARN_ON_ONCE(!rcu_read_lock_held());
 
 	/* allocate new element outside of lock */
-	l_new = kmalloc(htab->elem_size, GFP_ATOMIC);
+	l_new = kmalloc(htab->elem_size, GFP_ATOMIC | __GFP_NOWARN);
 	if (!l_new)
 		return -ENOMEM;
 

kernel/bpf/inode.c

@@ -34,7 +34,7 @@ static void *bpf_any_get(void *raw, enum bpf_type type)
 		atomic_inc(&((struct bpf_prog *)raw)->aux->refcnt);
 		break;
 	case BPF_TYPE_MAP:
-		atomic_inc(&((struct bpf_map *)raw)->refcnt);
+		bpf_map_inc(raw, true);
 		break;
 	default:
 		WARN_ON_ONCE(1);
@@ -51,7 +51,7 @@ static void bpf_any_put(void *raw, enum bpf_type type)
 		bpf_prog_put(raw);
 		break;
 	case BPF_TYPE_MAP:
-		bpf_map_put(raw);
+		bpf_map_put_with_uref(raw);
 		break;
 	default:
 		WARN_ON_ONCE(1);
@@ -64,7 +64,7 @@ static void *bpf_fd_probe_obj(u32 ufd, enum bpf_type *type)
 	void *raw;
 
 	*type = BPF_TYPE_MAP;
-	raw = bpf_map_get(ufd);
+	raw = bpf_map_get_with_uref(ufd);
 	if (IS_ERR(raw)) {
 		*type = BPF_TYPE_PROG;
 		raw = bpf_prog_get(ufd);

kernel/bpf/syscall.c

@@ -82,6 +82,14 @@ static void bpf_map_free_deferred(struct work_struct *work)
 	map->ops->map_free(map);
 }
 
+static void bpf_map_put_uref(struct bpf_map *map)
+{
+	if (atomic_dec_and_test(&map->usercnt)) {
+		if (map->map_type == BPF_MAP_TYPE_PROG_ARRAY)
+			bpf_fd_array_map_clear(map);
+	}
+}
+
 /* decrement map refcnt and schedule it for freeing via workqueue
  * (unrelying map implementation ops->map_free() might sleep)
  */
@@ -93,17 +101,15 @@ void bpf_map_put(struct bpf_map *map)
 	}
 }
 
+void bpf_map_put_with_uref(struct bpf_map *map)
+{
+	bpf_map_put_uref(map);
+	bpf_map_put(map);
+}
+
 static int bpf_map_release(struct inode *inode, struct file *filp)
 {
-	struct bpf_map *map = filp->private_data;
-
-	if (map->map_type == BPF_MAP_TYPE_PROG_ARRAY)
-		/* prog_array stores refcnt-ed bpf_prog pointers
-		 * release them all when user space closes prog_array_fd
-		 */
-		bpf_fd_array_map_clear(map);
-
-	bpf_map_put(map);
+	bpf_map_put_with_uref(filp->private_data);
 	return 0;
 }
 
@@ -142,6 +148,7 @@ static int map_create(union bpf_attr *attr)
 		return PTR_ERR(map);
 
 	atomic_set(&map->refcnt, 1);
+	atomic_set(&map->usercnt, 1);
 
 	err = bpf_map_charge_memlock(map);
 	if (err)
@@ -174,7 +181,14 @@ struct bpf_map *__bpf_map_get(struct fd f)
 	return f.file->private_data;
 }
 
-struct bpf_map *bpf_map_get(u32 ufd)
+void bpf_map_inc(struct bpf_map *map, bool uref)
+{
+	atomic_inc(&map->refcnt);
+	if (uref)
+		atomic_inc(&map->usercnt);
+}
+
+struct bpf_map *bpf_map_get_with_uref(u32 ufd)
 {
 	struct fd f = fdget(ufd);
 	struct bpf_map *map;
@@ -183,7 +197,7 @@ struct bpf_map *bpf_map_get(u32 ufd)
 	if (IS_ERR(map))
 		return map;
 
-	atomic_inc(&map->refcnt);
+	bpf_map_inc(map, true);
 	fdput(f);
 
 	return map;
@@ -226,7 +240,7 @@ static int map_lookup_elem(union bpf_attr *attr)
 		goto free_key;
 
 	err = -ENOMEM;
-	value = kmalloc(map->value_size, GFP_USER);
+	value = kmalloc(map->value_size, GFP_USER | __GFP_NOWARN);
 	if (!value)
 		goto free_key;
 
@@ -285,7 +299,7 @@ static int map_update_elem(union bpf_attr *attr)
 		goto free_key;
 
 	err = -ENOMEM;
-	value = kmalloc(map->value_size, GFP_USER);
+	value = kmalloc(map->value_size, GFP_USER | __GFP_NOWARN);
 	if (!value)
 		goto free_key;
 

kernel/bpf/verifier.c

@@ -2021,8 +2021,7 @@ static int replace_map_fd_with_map_ptr(struct verifier_env *env)
 			 * will be used by the valid program until it's unloaded
 			 * and all maps are released in free_bpf_prog_info()
 			 */
-			atomic_inc(&map->refcnt);
-
+			bpf_map_inc(map, false);
 			fdput(f);
 next_insn:
 			insn++;

kernel/livepatch/core.c

@@ -294,6 +294,12 @@ static int klp_write_object_relocations(struct module *pmod,
 
 	for (reloc = obj->relocs; reloc->name; reloc++) {
 		if (!klp_is_module(obj)) {
+
+#if defined(CONFIG_RANDOMIZE_BASE)
+			/* If KASLR has been enabled, adjust old value accordingly */
+			if (kaslr_enabled())
+				reloc->val += kaslr_offset();
+#endif
 			ret = klp_verify_vmlinux_symbol(reloc->name,
 							reloc->val);
 			if (ret)

kernel/panic.c

@@ -152,8 +152,11 @@ void panic(const char *fmt, ...)
 	 * We may have ended up stopping the CPU holding the lock (in
 	 * smp_send_stop()) while still having some valuable data in the console
 	 * buffer.  Try to acquire the lock then release it regardless of the
-	 * result.  The release will also print the buffers out.
+	 * result.  The release will also print the buffers out.  Locks debug
+	 * should be disabled to avoid reporting bad unlock balance when
+	 * panic() is not being callled from OOPS.
 	 */
+	debug_locks_off();
 	console_trylock();
 	console_unlock();
 

kernel/pid.c

@@ -467,7 +467,7 @@ struct pid *get_task_pid(struct task_struct *task, enum pid_type type)
 	rcu_read_lock();
 	if (type != PIDTYPE_PID)
 		task = task->group_leader;
-	pid = get_pid(task->pids[type].pid);
+	pid = get_pid(rcu_dereference(task->pids[type].pid));
 	rcu_read_unlock();
 	return pid;
 }
@@ -528,7 +528,7 @@ pid_t __task_pid_nr_ns(struct task_struct *task, enum pid_type type,
 	if (likely(pid_alive(task))) {
 		if (type != PIDTYPE_PID)
 			task = task->group_leader;
-		nr = pid_nr_ns(task->pids[type].pid, ns);
+		nr = pid_nr_ns(rcu_dereference(task->pids[type].pid), ns);
 	}
 	rcu_read_unlock();
 

kernel/sched/core.c

@@ -1946,6 +1946,25 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 		goto stat;
 
 #ifdef CONFIG_SMP
+	/*
+	 * Ensure we load p->on_cpu _after_ p->on_rq, otherwise it would be
+	 * possible to, falsely, observe p->on_cpu == 0.
+	 *
+	 * One must be running (->on_cpu == 1) in order to remove oneself
+	 * from the runqueue.
+	 *
+	 *  [S] ->on_cpu = 1;	[L] ->on_rq
+	 *      UNLOCK rq->lock
+	 *			RMB
+	 *      LOCK   rq->lock
+	 *  [S] ->on_rq = 0;    [L] ->on_cpu
+	 *
+	 * Pairs with the full barrier implied in the UNLOCK+LOCK on rq->lock
+	 * from the consecutive calls to schedule(); the first switching to our
+	 * task, the second putting it to sleep.
+	 */
+	smp_rmb();
+
 	/*
 	 * If the owning (remote) cpu is still in the middle of schedule() with
 	 * this task as prev, wait until its done referencing the task.
@@ -1953,7 +1972,13 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 	while (p->on_cpu)
 		cpu_relax();
 	/*
-	 * Pairs with the smp_wmb() in finish_lock_switch().
+	 * Combined with the control dependency above, we have an effective
+	 * smp_load_acquire() without the need for full barriers.
+	 *
+	 * Pairs with the smp_store_release() in finish_lock_switch().
+	 *
+	 * This ensures that tasks getting woken will be fully ordered against
+	 * their previous state and preserve Program Order.
 	 */
 	smp_rmb();
 
@@ -2039,7 +2064,6 @@ out:
  */
 int wake_up_process(struct task_struct *p)
 {
-	WARN_ON(task_is_stopped_or_traced(p));
 	return try_to_wake_up(p, TASK_NORMAL, 0);
 }
 EXPORT_SYMBOL(wake_up_process);
@@ -5847,13 +5871,13 @@ static int init_rootdomain(struct root_domain *rd)
 {
 	memset(rd, 0, sizeof(*rd));
 
-	if (!alloc_cpumask_var(&rd->span, GFP_KERNEL))
+	if (!zalloc_cpumask_var(&rd->span, GFP_KERNEL))
 		goto out;
-	if (!alloc_cpumask_var(&rd->online, GFP_KERNEL))
+	if (!zalloc_cpumask_var(&rd->online, GFP_KERNEL))
 		goto free_span;
-	if (!alloc_cpumask_var(&rd->dlo_mask, GFP_KERNEL))
+	if (!zalloc_cpumask_var(&rd->dlo_mask, GFP_KERNEL))
 		goto free_online;
-	if (!alloc_cpumask_var(&rd->rto_mask, GFP_KERNEL))
+	if (!zalloc_cpumask_var(&rd->rto_mask, GFP_KERNEL))
 		goto free_dlo_mask;
 
 	init_dl_bw(&rd->dl_bw);

kernel/sched/cputime.c

@@ -788,6 +788,9 @@ cputime_t task_gtime(struct task_struct *t)
 	unsigned int seq;
 	cputime_t gtime;
 
+	if (!context_tracking_is_enabled())
+		return t->gtime;
+
 	do {
 		seq = read_seqbegin(&t->vtime_seqlock);
 

kernel/sched/rt.c

@@ -64,7 +64,7 @@ static void start_rt_bandwidth(struct rt_bandwidth *rt_b)
 	raw_spin_unlock(&rt_b->rt_runtime_lock);
 }
 
-#ifdef CONFIG_SMP
+#if defined(CONFIG_SMP) && defined(HAVE_RT_PUSH_IPI)
 static void push_irq_work_func(struct irq_work *work);
 #endif
 

kernel/sched/sched.h

@@ -1073,6 +1073,9 @@ static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev)
 	 * We must ensure this doesn't happen until the switch is completely
 	 * finished.
 	 *
+	 * In particular, the load of prev->state in finish_task_switch() must
+	 * happen before this.
+	 *
 	 * Pairs with the control dependency and rmb in try_to_wake_up().
 	 */
 	smp_store_release(&prev->on_cpu, 0);

kernel/sched/wait.c

@@ -583,18 +583,18 @@ EXPORT_SYMBOL(wake_up_atomic_t);
 
 __sched int bit_wait(struct wait_bit_key *word)
 {
-	if (signal_pending_state(current->state, current))
-		return 1;
 	schedule();
+	if (signal_pending(current))
+		return -EINTR;
 	return 0;
 }
 EXPORT_SYMBOL(bit_wait);
 
 __sched int bit_wait_io(struct wait_bit_key *word)
 {
-	if (signal_pending_state(current->state, current))
-		return 1;
 	io_schedule();
+	if (signal_pending(current))
+		return -EINTR;
 	return 0;
 }
 EXPORT_SYMBOL(bit_wait_io);
@@ -602,11 +602,11 @@ EXPORT_SYMBOL(bit_wait_io);
 __sched int bit_wait_timeout(struct wait_bit_key *word)
 {
 	unsigned long now = READ_ONCE(jiffies);
-	if (signal_pending_state(current->state, current))
-		return 1;
 	if (time_after_eq(now, word->timeout))
 		return -EAGAIN;
 	schedule_timeout(word->timeout - now);
+	if (signal_pending(current))
+		return -EINTR;
 	return 0;
 }
 EXPORT_SYMBOL_GPL(bit_wait_timeout);
@@ -614,11 +614,11 @@ EXPORT_SYMBOL_GPL(bit_wait_timeout);
 __sched int bit_wait_io_timeout(struct wait_bit_key *word)
 {
 	unsigned long now = READ_ONCE(jiffies);
-	if (signal_pending_state(current->state, current))
-		return 1;
 	if (time_after_eq(now, word->timeout))
 		return -EAGAIN;
 	io_schedule_timeout(word->timeout - now);
+	if (signal_pending(current))
+		return -EINTR;
 	return 0;
 }
 EXPORT_SYMBOL_GPL(bit_wait_io_timeout);

kernel/signal.c

@@ -3503,7 +3503,7 @@ SYSCALL_DEFINE0(pause)
 
 #endif
 
-int sigsuspend(sigset_t *set)
+static int sigsuspend(sigset_t *set)
 {
 	current->saved_sigmask = current->blocked;
 	set_current_blocked(set);

kernel/trace/ring_buffer.c

@@ -1887,12 +1887,6 @@ rb_event_index(struct ring_buffer_event *event)
 	return (addr & ~PAGE_MASK) - BUF_PAGE_HDR_SIZE;
 }
 
-static void rb_reset_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
-{
-	cpu_buffer->read_stamp = cpu_buffer->reader_page->page->time_stamp;
-	cpu_buffer->reader_page->read = 0;
-}
-
 static void rb_inc_iter(struct ring_buffer_iter *iter)
 {
 	struct ring_buffer_per_cpu *cpu_buffer = iter->cpu_buffer;
@@ -2803,8 +2797,11 @@ rb_reserve_next_event(struct ring_buffer *buffer,
 
 	event = __rb_reserve_next(cpu_buffer, &info);
 
-	if (unlikely(PTR_ERR(event) == -EAGAIN))
+	if (unlikely(PTR_ERR(event) == -EAGAIN)) {
+		if (info.add_timestamp)
+			info.length -= RB_LEN_TIME_EXTEND;
 		goto again;
+	}
 
 	if (!event)
 		goto out_fail;
@@ -3626,7 +3623,7 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
 
 	/* Finally update the reader page to the new head */
 	cpu_buffer->reader_page = reader;
-	rb_reset_reader_page(cpu_buffer);
+	cpu_buffer->reader_page->read = 0;
 
 	if (overwrite != cpu_buffer->last_overrun) {
 		cpu_buffer->lost_events = overwrite - cpu_buffer->last_overrun;
@@ -3636,6 +3633,10 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
 	goto again;
 
  out:
+	/* Update the read_stamp on the first event */
+	if (reader && reader->read == 0)
+		cpu_buffer->read_stamp = reader->page->time_stamp;
+
 	arch_spin_unlock(&cpu_buffer->lock);
 	local_irq_restore(flags);
 

kernel/trace/trace_events.c

@@ -582,6 +582,12 @@ static void __ftrace_clear_event_pids(struct trace_array *tr)
 	unregister_trace_sched_wakeup(event_filter_pid_sched_wakeup_probe_pre, tr);
 	unregister_trace_sched_wakeup(event_filter_pid_sched_wakeup_probe_post, tr);
 
+	unregister_trace_sched_wakeup_new(event_filter_pid_sched_wakeup_probe_pre, tr);
+	unregister_trace_sched_wakeup_new(event_filter_pid_sched_wakeup_probe_post, tr);
+
+	unregister_trace_sched_waking(event_filter_pid_sched_wakeup_probe_pre, tr);
+	unregister_trace_sched_waking(event_filter_pid_sched_wakeup_probe_post, tr);
+
 	list_for_each_entry(file, &tr->events, list) {
 		clear_bit(EVENT_FILE_FL_PID_FILTER_BIT, &file->flags);
 	}
@@ -1729,6 +1735,16 @@ ftrace_event_pid_write(struct file *filp, const char __user *ubuf,
 						 tr, INT_MAX);
 		register_trace_prio_sched_wakeup(event_filter_pid_sched_wakeup_probe_post,
 						 tr, 0);
+
+		register_trace_prio_sched_wakeup_new(event_filter_pid_sched_wakeup_probe_pre,
+						     tr, INT_MAX);
+		register_trace_prio_sched_wakeup_new(event_filter_pid_sched_wakeup_probe_post,
+						     tr, 0);
+
+		register_trace_prio_sched_waking(event_filter_pid_sched_wakeup_probe_pre,
+						 tr, INT_MAX);
+		register_trace_prio_sched_waking(event_filter_pid_sched_wakeup_probe_post,
+						 tr, 0);
 	}
 
 	/*