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

The BTF conflicts were simple overlapping changes.

The virtio_net conflict was an overlap of a fix of statistics counter,
happening alongisde a move over to a bonafide statistics structure
rather than counting value on the stack.

Signed-off-by: David S. Miller <davem@davemloft.net>

kernel/auditsc.c

@@ -1279,8 +1279,12 @@ static void show_special(struct audit_context *context, int *call_panic)
 		break;
 	case AUDIT_KERN_MODULE:
 		audit_log_format(ab, "name=");
-		audit_log_untrustedstring(ab, context->module.name);
-		kfree(context->module.name);
+		if (context->module.name) {
+			audit_log_untrustedstring(ab, context->module.name);
+			kfree(context->module.name);
+		} else
+			audit_log_format(ab, "(null)");
+
 		break;
 	}
 	audit_log_end(ab);
@@ -2411,8 +2415,9 @@ void __audit_log_kern_module(char *name)
 {
 	struct audit_context *context = audit_context();
 
-	context->module.name = kmalloc(strlen(name) + 1, GFP_KERNEL);
-	strcpy(context->module.name, name);
+	context->module.name = kstrdup(name, GFP_KERNEL);
+	if (!context->module.name)
+		audit_log_lost("out of memory in __audit_log_kern_module");
 	context->type = AUDIT_KERN_MODULE;
 }
 

kernel/bpf/arraymap.c

@@ -378,7 +378,7 @@ static int array_map_check_btf(const struct bpf_map *map, const struct btf *btf,
 		return -EINVAL;
 
 	value_type = btf_type_id_size(btf, &btf_value_id, &value_size);
-	if (!value_type || value_size > map->value_size)
+	if (!value_type || value_size != map->value_size)
 		return -EINVAL;
 
 	return 0;

kernel/bpf/btf.c

@@ -1519,9 +1519,9 @@ static s32 btf_struct_check_meta(struct btf_verifier_env *env,
 {
 	bool is_union = BTF_INFO_KIND(t->info) == BTF_KIND_UNION;
 	const struct btf_member *member;
+	u32 meta_needed, last_offset;
 	struct btf *btf = env->btf;
 	u32 struct_size = t->size;
-	u32 meta_needed;
 	u16 i;
 
 	meta_needed = btf_type_vlen(t) * sizeof(*member);
@@ -1534,6 +1534,7 @@ static s32 btf_struct_check_meta(struct btf_verifier_env *env,
 
 	btf_verifier_log_type(env, t, NULL);
 
+	last_offset = 0;
 	for_each_member(i, t, member) {
 		if (!btf_name_offset_valid(btf, member->name_off)) {
 			btf_verifier_log_member(env, t, member,
@@ -1555,6 +1556,16 @@ static s32 btf_struct_check_meta(struct btf_verifier_env *env,
 			return -EINVAL;
 		}
 
+		/*
+		 * ">" instead of ">=" because the last member could be
+		 * "char a[0];"
+		 */
+		if (last_offset > member->offset) {
+			btf_verifier_log_member(env, t, member,
+						"Invalid member bits_offset");
+			return -EINVAL;
+		}
+
 		if (BITS_ROUNDUP_BYTES(member->offset) > struct_size) {
 			btf_verifier_log_member(env, t, member,
 						"Memmber bits_offset exceeds its struct size");
@@ -1562,6 +1573,7 @@ static s32 btf_struct_check_meta(struct btf_verifier_env *env,
 		}
 
 		btf_verifier_log_member(env, t, member, NULL);
+		last_offset = member->offset;
 	}
 
 	return meta_needed;

kernel/events/core.c

@@ -6343,7 +6343,7 @@ static u64 perf_virt_to_phys(u64 virt)
 
 static struct perf_callchain_entry __empty_callchain = { .nr = 0, };
 
-static struct perf_callchain_entry *
+struct perf_callchain_entry *
 perf_callchain(struct perf_event *event, struct pt_regs *regs)
 {
 	bool kernel = !event->attr.exclude_callchain_kernel;
@@ -6382,7 +6382,9 @@ void perf_prepare_sample(struct perf_event_header *header,
 	if (sample_type & PERF_SAMPLE_CALLCHAIN) {
 		int size = 1;
 
-		data->callchain = perf_callchain(event, regs);
+		if (!(sample_type & __PERF_SAMPLE_CALLCHAIN_EARLY))
+			data->callchain = perf_callchain(event, regs);
+
 		size += data->callchain->nr;
 
 		header->size += size * sizeof(u64);
@@ -7335,6 +7337,10 @@ static bool perf_addr_filter_match(struct perf_addr_filter *filter,
 				     struct file *file, unsigned long offset,
 				     unsigned long size)
 {
+	/* d_inode(NULL) won't be equal to any mapped user-space file */
+	if (!filter->path.dentry)
+		return false;
+
 	if (d_inode(filter->path.dentry) != file_inode(file))
 		return false;
 

kernel/fork.c

@@ -312,10 +312,8 @@ struct vm_area_struct *vm_area_alloc(struct mm_struct *mm)
 {
 	struct vm_area_struct *vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL);
 
-	if (vma) {
-		vma->vm_mm = mm;
-		INIT_LIST_HEAD(&vma->anon_vma_chain);
-	}
+	if (vma)
+		vma_init(vma, mm);
 	return vma;
 }
 

kernel/kthread.c

@@ -325,8 +325,14 @@ struct task_struct *__kthread_create_on_node(int (*threadfn)(void *data),
 	task = create->result;
 	if (!IS_ERR(task)) {
 		static const struct sched_param param = { .sched_priority = 0 };
+		char name[TASK_COMM_LEN];
 
-		vsnprintf(task->comm, sizeof(task->comm), namefmt, args);
+		/*
+		 * task is already visible to other tasks, so updating
+		 * COMM must be protected.
+		 */
+		vsnprintf(name, sizeof(name), namefmt, args);
+		set_task_comm(task, name);
 		/*
 		 * root may have changed our (kthreadd's) priority or CPU mask.
 		 * The kernel thread should not inherit these properties.

kernel/locking/rtmutex.c

@@ -1465,6 +1465,29 @@ rt_mutex_fastunlock(struct rt_mutex *lock,
 		rt_mutex_postunlock(&wake_q);
 }
 
+static inline void __rt_mutex_lock(struct rt_mutex *lock, unsigned int subclass)
+{
+	might_sleep();
+
+	mutex_acquire(&lock->dep_map, subclass, 0, _RET_IP_);
+	rt_mutex_fastlock(lock, TASK_UNINTERRUPTIBLE, rt_mutex_slowlock);
+}
+
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+/**
+ * rt_mutex_lock_nested - lock a rt_mutex
+ *
+ * @lock: the rt_mutex to be locked
+ * @subclass: the lockdep subclass
+ */
+void __sched rt_mutex_lock_nested(struct rt_mutex *lock, unsigned int subclass)
+{
+	__rt_mutex_lock(lock, subclass);
+}
+EXPORT_SYMBOL_GPL(rt_mutex_lock_nested);
+#endif
+
+#ifndef CONFIG_DEBUG_LOCK_ALLOC
 /**
  * rt_mutex_lock - lock a rt_mutex
  *
@@ -1472,12 +1495,10 @@ rt_mutex_fastunlock(struct rt_mutex *lock,
  */
 void __sched rt_mutex_lock(struct rt_mutex *lock)
 {
-	might_sleep();
-
-	mutex_acquire(&lock->dep_map, 0, 0, _RET_IP_);
-	rt_mutex_fastlock(lock, TASK_UNINTERRUPTIBLE, rt_mutex_slowlock);
+	__rt_mutex_lock(lock, 0);
 }
 EXPORT_SYMBOL_GPL(rt_mutex_lock);
+#endif
 
 /**
  * rt_mutex_lock_interruptible - lock a rt_mutex interruptible

kernel/memremap.c

@@ -176,10 +176,27 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap)
 	unsigned long pfn, pgoff, order;
 	pgprot_t pgprot = PAGE_KERNEL;
 	int error, nid, is_ram;
+	struct dev_pagemap *conflict_pgmap;
 
 	align_start = res->start & ~(SECTION_SIZE - 1);
 	align_size = ALIGN(res->start + resource_size(res), SECTION_SIZE)
 		- align_start;
+	align_end = align_start + align_size - 1;
+
+	conflict_pgmap = get_dev_pagemap(PHYS_PFN(align_start), NULL);
+	if (conflict_pgmap) {
+		dev_WARN(dev, "Conflicting mapping in same section\n");
+		put_dev_pagemap(conflict_pgmap);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	conflict_pgmap = get_dev_pagemap(PHYS_PFN(align_end), NULL);
+	if (conflict_pgmap) {
+		dev_WARN(dev, "Conflicting mapping in same section\n");
+		put_dev_pagemap(conflict_pgmap);
+		return ERR_PTR(-ENOMEM);
+	}
+
 	is_ram = region_intersects(align_start, align_size,
 		IORESOURCE_SYSTEM_RAM, IORES_DESC_NONE);
 
@@ -199,7 +216,6 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap)
 
 	mutex_lock(&pgmap_lock);
 	error = 0;
-	align_end = align_start + align_size - 1;
 
 	foreach_order_pgoff(res, order, pgoff) {
 		error = __radix_tree_insert(&pgmap_radix,
@@ -305,7 +321,7 @@ EXPORT_SYMBOL_GPL(get_dev_pagemap);
 
 #ifdef CONFIG_DEV_PAGEMAP_OPS
 DEFINE_STATIC_KEY_FALSE(devmap_managed_key);
-EXPORT_SYMBOL_GPL(devmap_managed_key);
+EXPORT_SYMBOL(devmap_managed_key);
 static atomic_t devmap_enable;
 
 /*
@@ -346,5 +362,5 @@ void __put_devmap_managed_page(struct page *page)
 	} else if (!count)
 		__put_page(page);
 }
-EXPORT_SYMBOL_GPL(__put_devmap_managed_page);
+EXPORT_SYMBOL(__put_devmap_managed_page);
 #endif /* CONFIG_DEV_PAGEMAP_OPS */

kernel/sched/deadline.c

@@ -2090,8 +2090,14 @@ retry:
 	sub_rq_bw(&next_task->dl, &rq->dl);
 	set_task_cpu(next_task, later_rq->cpu);
 	add_rq_bw(&next_task->dl, &later_rq->dl);
+
+	/*
+	 * Update the later_rq clock here, because the clock is used
+	 * by the cpufreq_update_util() inside __add_running_bw().
+	 */
+	update_rq_clock(later_rq);
 	add_running_bw(&next_task->dl, &later_rq->dl);
-	activate_task(later_rq, next_task, 0);
+	activate_task(later_rq, next_task, ENQUEUE_NOCLOCK);
 	ret = 1;
 
 	resched_curr(later_rq);

kernel/sched/rt.c

@@ -836,6 +836,8 @@ static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun)
 		 * can be time-consuming. Try to avoid it when possible.
 		 */
 		raw_spin_lock(&rt_rq->rt_runtime_lock);
+		if (!sched_feat(RT_RUNTIME_SHARE) && rt_rq->rt_runtime != RUNTIME_INF)
+			rt_rq->rt_runtime = rt_b->rt_runtime;
 		skip = !rt_rq->rt_time && !rt_rq->rt_nr_running;
 		raw_spin_unlock(&rt_rq->rt_runtime_lock);
 		if (skip)

kernel/sched/topology.c

@@ -47,7 +47,7 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
 	if (!cpumask_test_cpu(cpu, sched_domain_span(sd))) {
 		printk(KERN_ERR "ERROR: domain->span does not contain CPU%d\n", cpu);
 	}
-	if (!cpumask_test_cpu(cpu, sched_group_span(group))) {
+	if (group && !cpumask_test_cpu(cpu, sched_group_span(group))) {
 		printk(KERN_ERR "ERROR: domain->groups does not contain CPU%d\n", cpu);
 	}
 

kernel/stop_machine.c

@@ -260,6 +260,15 @@ retry:
 	err = 0;
 	__cpu_stop_queue_work(stopper1, work1, &wakeq);
 	__cpu_stop_queue_work(stopper2, work2, &wakeq);
+	/*
+	 * The waking up of stopper threads has to happen
+	 * in the same scheduling context as the queueing.
+	 * Otherwise, there is a possibility of one of the
+	 * above stoppers being woken up by another CPU,
+	 * and preempting us. This will cause us to n ot
+	 * wake up the other stopper forever.
+	 */
+	preempt_disable();
 unlock:
 	raw_spin_unlock(&stopper2->lock);
 	raw_spin_unlock_irq(&stopper1->lock);
@@ -271,7 +280,6 @@ unlock:
 	}
 
 	if (!err) {
-		preempt_disable();
 		wake_up_q(&wakeq);
 		preempt_enable();
 	}

kernel/trace/ring_buffer.c

@@ -3226,6 +3226,22 @@ int ring_buffer_record_is_on(struct ring_buffer *buffer)
 	return !atomic_read(&buffer->record_disabled);
 }
 
+/**
+ * ring_buffer_record_is_set_on - return true if the ring buffer is set writable
+ * @buffer: The ring buffer to see if write is set enabled
+ *
+ * Returns true if the ring buffer is set writable by ring_buffer_record_on().
+ * Note that this does NOT mean it is in a writable state.
+ *
+ * It may return true when the ring buffer has been disabled by
+ * ring_buffer_record_disable(), as that is a temporary disabling of
+ * the ring buffer.
+ */
+int ring_buffer_record_is_set_on(struct ring_buffer *buffer)
+{
+	return !(atomic_read(&buffer->record_disabled) & RB_BUFFER_OFF);
+}
+
 /**
  * ring_buffer_record_disable_cpu - stop all writes into the cpu_buffer
  * @buffer: The ring buffer to stop writes to.

kernel/trace/trace.c

@@ -1373,6 +1373,12 @@ update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
 
 	arch_spin_lock(&tr->max_lock);
 
+	/* Inherit the recordable setting from trace_buffer */
+	if (ring_buffer_record_is_set_on(tr->trace_buffer.buffer))
+		ring_buffer_record_on(tr->max_buffer.buffer);
+	else
+		ring_buffer_record_off(tr->max_buffer.buffer);
+
 	swap(tr->trace_buffer.buffer, tr->max_buffer.buffer);
 
 	__update_max_tr(tr, tsk, cpu);

kernel/trace/trace_events_trigger.c

@@ -679,6 +679,8 @@ event_trigger_callback(struct event_command *cmd_ops,
 		goto out_free;
 
  out_reg:
+	/* Up the trigger_data count to make sure reg doesn't free it on failure */
+	event_trigger_init(trigger_ops, trigger_data);
 	ret = cmd_ops->reg(glob, trigger_ops, trigger_data, file);
 	/*
 	 * The above returns on success the # of functions enabled,
@@ -686,11 +688,13 @@ event_trigger_callback(struct event_command *cmd_ops,
 	 * Consider no functions a failure too.
 	 */
 	if (!ret) {
+		cmd_ops->unreg(glob, trigger_ops, trigger_data, file);
 		ret = -ENOENT;
-		goto out_free;
-	} else if (ret < 0)
-		goto out_free;
-	ret = 0;
+	} else if (ret > 0)
+		ret = 0;
+
+	/* Down the counter of trigger_data or free it if not used anymore */
+	event_trigger_free(trigger_ops, trigger_data);
  out:
 	return ret;
 
@@ -1416,6 +1420,9 @@ int event_enable_trigger_func(struct event_command *cmd_ops,
 		goto out;
 	}
 
+	/* Up the trigger_data count to make sure nothing frees it on failure */
+	event_trigger_init(trigger_ops, trigger_data);
+
 	if (trigger) {
 		number = strsep(&trigger, ":");
 
@@ -1466,6 +1473,7 @@ int event_enable_trigger_func(struct event_command *cmd_ops,
 		goto out_disable;
 	/* Just return zero, not the number of enabled functions */
 	ret = 0;
+	event_trigger_free(trigger_ops, trigger_data);
  out:
 	return ret;
 
@@ -1476,7 +1484,7 @@ int event_enable_trigger_func(struct event_command *cmd_ops,
  out_free:
 	if (cmd_ops->set_filter)
 		cmd_ops->set_filter(NULL, trigger_data, NULL);
-	kfree(trigger_data);
+	event_trigger_free(trigger_ops, trigger_data);
 	kfree(enable_data);
 	goto out;
 }

kernel/trace/trace_kprobe.c

@@ -400,11 +400,10 @@ static struct trace_kprobe *find_trace_kprobe(const char *event,
 static int
 enable_trace_kprobe(struct trace_kprobe *tk, struct trace_event_file *file)
 {
+	struct event_file_link *link = NULL;
 	int ret = 0;
 
 	if (file) {
-		struct event_file_link *link;
-
 		link = kmalloc(sizeof(*link), GFP_KERNEL);
 		if (!link) {
 			ret = -ENOMEM;
@@ -424,6 +423,18 @@ enable_trace_kprobe(struct trace_kprobe *tk, struct trace_event_file *file)
 		else
 			ret = enable_kprobe(&tk->rp.kp);
 	}
+
+	if (ret) {
+		if (file) {
+			/* Notice the if is true on not WARN() */
+			if (!WARN_ON_ONCE(!link))
+				list_del_rcu(&link->list);
+			kfree(link);
+			tk->tp.flags &= ~TP_FLAG_TRACE;
+		} else {
+			tk->tp.flags &= ~TP_FLAG_PROFILE;
+		}
+	}
  out:
 	return ret;
 }