Merge tag 'trace-v7.2-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace

Pull tracing fixes from Steven Rostedt:

 - Fix use-after-free in eventfs_remove_rec()

   The freeing of the eventfs_inode children used list_for_each_entry()
   where the child is freed via srcu, but there's still a chance that it
   gets freed. It should be using list_for_each_entry_safe().

 - Fix eventfs_inode SRCU use of list in freeing

   The iterator uses an SRCU protected list walk on the eventfs inodes.
   The eventfs inode uses its "list" field in a union with the RCU list
   head. When the inode gets added to the SRCU list it immediately
   corrupts the list pointer and can cause an issue with the iterator.
   Move the RCU list head to be shared with the children list head which
   allows the iterator to check the parent inode if is freed before
   referencing the child. Have the iterator check the parent "is_freed"
   field and break out if it is set. Also add memory barriers to make
   sure the ordering is correct.

 - Fix various RCU synchronization issues with direct_functions

   Updates to direct_functions have some missing RCU protection and
   synchronization. Restructure the code a bit to make sure updates to
   the direct_functions are protected.

 - Remove an unneeded comma from a scope_guard()

   There's a spurious comma in a scope_guard(). Remove it.

 - Fix race in per CPU buffer swap in the ring buffer

   When a per CPU buffer swap happens, it must make sure that it doesn't
   occur while a writer is active. Instead it returns an -EBUSY. But
   there's a small race window when a writer moves from one sub-buffer
   to the next that it resets the "committing" counter. If a swap
   happens at that moment, the buffer used for the commit of an event
   will not match the buffer the event is actually on. Instead of using
   the "committing" counter, use the recursive detection counter that
   does not get reset when the writer crosses sub-buffers.

 - Fix off-by-one in ftrace_free_mem()

   The function ftrace_free_mem() gets an "end_ptr" as a parameter that
   is exclusive to the rang to be freed. But its value is used to search
   for the records that expects an inclusive value. Subtract one from
   the parameter to convert it to an inclusive range.

 - Disable resizing of the ring buffer for persistent buffers

   Resizing the persistent buffer has undefined behavior. Prevent it
   from being resized.

 - Disable changing ring buffer subbuf order when resizing is disabled

   The ring buffer subbuffer order can not be changed during resizing.
   Use that instead of just checking if the buffer is mapped as mapped
   buffers also have resizing disabled.

 - Initialize subbuf_order of reader pages when they are created

   In rb_allocate_cpu_buffer() the bpage->order is not updated to the
   current subbuf_order leaving it as zero. This value is used when the
   page is freed.

 - Fix test_ringbuffer() to test for ERR_PTR before calling
   kthread_stop()

   The rb_threads[] array is assigned the output of kthread_run_on_cpu()
   which could return an ERR_PTR. At the end of the test, all threads in
   the array are cleaned up by kthread_stop() passing in the value in
   the array if it isn't zero. But if the array contains an ERR_PTR,
   kthread_stop() will not be able to handle it properly.

* tag 'trace-v7.2-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace:
  ring-buffer: Fix crash passing ERR_PTR to kthread_stop()
  ring-buffer: Initialise reader page order in rb_allocate_cpu_buffer()
  ring-buffer: Prevent subbuf order change when resizing is disabled
  ring-buffer: Prevent resizing of persistent ring buffer
  ftrace: Fix off-by-one fentry site disable in ftrace_free_mem()
  ring-buffer: Use current_context for safe per-CPU buffer swap
  ftrace: Drop extra comma in trace_buffered_event_enable
  ftrace: Protect direct_functions in update_ftrace_direct_mod
  ftrace: Protect direct_functions in update_ftrace_direct_del
  ftrace: Protect direct_functions in ftrace_find_rec_direct
  eventfs: Use children field for rcu head and add memory barriers
  eventfs: Fix use-after-free in eventfs_remove_rec()

fs/tracefs/event_inode.c

@@ -124,7 +124,17 @@ static inline void put_ei(struct eventfs_inode *ei)
 static inline void free_ei(struct eventfs_inode *ei)
 {
 	if (ei) {
+		/* The ei should have no children if it is being freed. */
+		WARN_ON_ONCE(!list_empty(&ei->children));
 		ei->is_freed = 1;
+		/*
+		 * The SRCU iteration has a smp_rmb() to make sure it
+		 * sees a child (that may have already been freed)
+		 * before it reads is_free. If is_free is set, it must
+		 * not use the child it acquired from ei->children, as
+		 * the list may be used for SRCU.
+		 */
+		smp_wmb();
 		put_ei(ei);
 	}
 }
@@ -627,6 +637,20 @@ static int eventfs_iterate(struct file *file, struct dir_context *ctx)
 	list_for_each_entry_srcu(ei_child, &ei->children, list,
 				 srcu_read_lock_held(&eventfs_srcu)) {
 
+		/*
+		 * If the ei is being freed, then the ei->children may be
+		 * being used as the rcu list, which means the next element
+		 * may be garbage. The ei->is_free is set before switching
+		 * the ei->children over to ei->rcu. The read memory barrier
+		 * here makes sure the ei_child is read before is_free is
+		 * updated.
+		 *
+		 * Matches the smp_wmb() in free_ei()
+		 */
+		smp_rmb();
+		if (ei->is_freed)
+			return -EINVAL;
+
 		if (c > 0) {
 			c--;
 			continue;
@@ -822,7 +846,7 @@ struct eventfs_inode *eventfs_create_events_dir(const char *name, struct dentry
  */
 static void eventfs_remove_rec(struct eventfs_inode *ei, int level)
 {
-	struct eventfs_inode *ei_child;
+	struct eventfs_inode *ei_child, *tmp;
 
 	/*
 	 * Check recursion depth. It should never be greater than 3:
@@ -835,7 +859,7 @@ static void eventfs_remove_rec(struct eventfs_inode *ei, int level)
 		return;
 
 	/* search for nested folders or files */
-	list_for_each_entry(ei_child, &ei->children, list)
+	list_for_each_entry_safe(ei_child, tmp, &ei->children, list)
 		eventfs_remove_rec(ei_child, level + 1);
 
 	list_del_rcu(&ei->list);

fs/tracefs/internal.h

@@ -46,11 +46,11 @@ struct eventfs_attr {
  * @ino:	The saved inode number
  */
 struct eventfs_inode {
+	struct list_head	list;
 	union {
-		struct list_head	list;
+		struct list_head	children;
 		struct rcu_head		rcu;
 	};
-	struct list_head		children;
 	const struct eventfs_entry	*entries;
 	const char			*name;
 	struct eventfs_attr		*entry_attrs;

kernel/trace/ftrace.c

@@ -2645,7 +2645,8 @@ unsigned long ftrace_find_rec_direct(unsigned long ip)
 {
 	struct ftrace_func_entry *entry;
 
-	entry = __ftrace_lookup_ip(direct_functions, ip);
+	guard(preempt_notrace)();
+	entry = __ftrace_lookup_ip(rcu_dereference_sched(direct_functions), ip);
 	if (!entry)
 		return 0;
 
@@ -6511,6 +6512,7 @@ int update_ftrace_direct_del(struct ftrace_ops *ops, struct ftrace_hash *hash)
 	struct ftrace_hash *new_direct_functions;
 	struct ftrace_hash *new_filter_hash = NULL;
 	struct ftrace_hash *old_filter_hash;
+	struct ftrace_hash *direct_hash;
 	struct ftrace_func_entry *entry;
 	struct ftrace_func_entry *del;
 	unsigned long size;
@@ -6522,11 +6524,13 @@ int update_ftrace_direct_del(struct ftrace_ops *ops, struct ftrace_hash *hash)
 		return -EINVAL;
 	if (!(ops->flags & FTRACE_OPS_FL_ENABLED))
 		return -EINVAL;
-	if (direct_functions == EMPTY_HASH)
-		return -EINVAL;
 
 	mutex_lock(&direct_mutex);
 
+	direct_hash = rcu_dereference_protected(direct_functions, lockdep_is_held(&direct_mutex));
+	if (direct_hash == EMPTY_HASH)
+		goto out_unlock;
+
 	old_filter_hash = ops->func_hash ? ops->func_hash->filter_hash : NULL;
 
 	if (!hash_count(old_filter_hash))
@@ -6536,7 +6540,7 @@ int update_ftrace_direct_del(struct ftrace_ops *ops, struct ftrace_hash *hash)
 	size = 1 << hash->size_bits;
 	for (int i = 0; i < size; i++) {
 		hlist_for_each_entry(entry, &hash->buckets[i], hlist) {
-			del = __ftrace_lookup_ip(direct_functions, entry->ip);
+			del = __ftrace_lookup_ip(direct_hash, entry->ip);
 			if (!del || del->direct != entry->direct)
 				goto out_unlock;
 		}
@@ -6547,7 +6551,7 @@ int update_ftrace_direct_del(struct ftrace_ops *ops, struct ftrace_hash *hash)
 	if (!new_filter_hash)
 		goto out_unlock;
 
-	new_direct_functions = hash_sub(direct_functions, hash);
+	new_direct_functions = hash_sub(direct_hash, hash);
 	if (!new_direct_functions)
 		goto out_unlock;
 
@@ -6574,7 +6578,7 @@ int update_ftrace_direct_del(struct ftrace_ops *ops, struct ftrace_hash *hash)
 		/* free the new_direct_functions */
 		old_direct_functions = new_direct_functions;
 	} else {
-		old_direct_functions = direct_functions;
+		old_direct_functions = direct_hash;
 		rcu_assign_pointer(direct_functions, new_direct_functions);
 	}
 
@@ -6613,6 +6617,7 @@ int update_ftrace_direct_mod(struct ftrace_ops *ops, struct ftrace_hash *hash, b
 		.func		= ftrace_stub,
 		.flags		= FTRACE_OPS_FL_STUB,
 	};
+	struct ftrace_hash *direct_hash;
 	struct ftrace_hash *orig_hash;
 	unsigned long size, i;
 	int err = -EINVAL;
@@ -6623,8 +6628,6 @@ int update_ftrace_direct_mod(struct ftrace_ops *ops, struct ftrace_hash *hash, b
 		return -EINVAL;
 	if (!(ops->flags & FTRACE_OPS_FL_ENABLED))
 		return -EINVAL;
-	if (direct_functions == EMPTY_HASH)
-		return -EINVAL;
 
 	/*
 	 * We can be called from within ops_func callback with direct_mutex
@@ -6632,6 +6635,12 @@ int update_ftrace_direct_mod(struct ftrace_ops *ops, struct ftrace_hash *hash, b
 	 */
 	if (do_direct_lock)
 		mutex_lock(&direct_mutex);
+	else
+		lockdep_assert_held_once(&direct_mutex);
+
+	direct_hash = rcu_dereference_protected(direct_functions, lockdep_is_held(&direct_mutex));
+	if (direct_hash == EMPTY_HASH)
+		goto unlock;
 
 	orig_hash = ops->func_hash ? ops->func_hash->filter_hash : NULL;
 	if (!orig_hash)
@@ -6663,7 +6672,7 @@ int update_ftrace_direct_mod(struct ftrace_ops *ops, struct ftrace_hash *hash, b
 	size = 1 << hash->size_bits;
 	for (i = 0; i < size; i++) {
 		hlist_for_each_entry(entry, &hash->buckets[i], hlist) {
-			tmp = __ftrace_lookup_ip(direct_functions, entry->ip);
+			tmp = __ftrace_lookup_ip(direct_hash, entry->ip);
 			if (!tmp)
 				continue;
 			tmp->direct = entry->direct;
@@ -8296,7 +8305,8 @@ static void add_to_clear_hash_list(struct list_head *clear_list,
 void ftrace_free_mem(struct module *mod, void *start_ptr, void *end_ptr)
 {
 	unsigned long start = (unsigned long)(start_ptr);
-	unsigned long end = (unsigned long)(end_ptr);
+	/* end is inclusive and end_ptr is exclusive */
+	unsigned long end = (unsigned long)(end_ptr) - 1;
 	struct ftrace_page **last_pg = &ftrace_pages_start;
 	struct ftrace_page *tmp_page = NULL;
 	struct ftrace_page *pg;
@@ -8306,6 +8316,9 @@ void ftrace_free_mem(struct module *mod, void *start_ptr, void *end_ptr)
 	struct ftrace_init_func *func, *func_next;
 	LIST_HEAD(clear_hash);
 
+	if (start_ptr >= end_ptr)
+		return;
+
 	key.ip = start;
 	key.flags = end;	/* overload flags, as it is unsigned long */
 

kernel/trace/ring_buffer.c

@@ -2510,6 +2510,7 @@ rb_allocate_cpu_buffer(struct trace_buffer *buffer, long nr_pages, int cpu)
 	bpage = alloc_cpu_page(cpu);
 	if (!bpage)
 		return NULL;
+	bpage->order = cpu_buffer->buffer->subbuf_order;
 
 	rb_check_bpage(cpu_buffer, bpage);
 
@@ -2528,6 +2529,8 @@ rb_allocate_cpu_buffer(struct trace_buffer *buffer, long nr_pages, int cpu)
 		if (cpu_buffer->ring_meta->head_buffer)
 			rb_meta_buffer_update(cpu_buffer, bpage);
 		bpage->range = 1;
+
+		atomic_inc(&cpu_buffer->resize_disabled);
 	} else if (buffer->remote) {
 		struct ring_buffer_desc *desc = ring_buffer_desc(buffer->remote->desc, cpu);
 
@@ -6852,7 +6855,7 @@ int ring_buffer_swap_cpu(struct trace_buffer *buffer_a,
 {
 	struct ring_buffer_per_cpu *cpu_buffer_a;
 	struct ring_buffer_per_cpu *cpu_buffer_b;
-	int ret = -EINVAL;
+	int ret = -EBUSY;
 
 	if (!cpumask_test_cpu(cpu, buffer_a->cpumask) ||
 	    !cpumask_test_cpu(cpu, buffer_b->cpumask))
@@ -6893,10 +6896,10 @@ int ring_buffer_swap_cpu(struct trace_buffer *buffer_a,
 	atomic_inc(&cpu_buffer_a->record_disabled);
 	atomic_inc(&cpu_buffer_b->record_disabled);
 
-	ret = -EBUSY;
-	if (local_read(&cpu_buffer_a->committing))
+	/* Do not swap if either buffer is in the process of writing */
+	if (cpu_buffer_a->current_context)
 		goto out_dec;
-	if (local_read(&cpu_buffer_b->committing))
+	if (cpu_buffer_b->current_context)
 		goto out_dec;
 
 	/*
@@ -7358,7 +7361,7 @@ int ring_buffer_subbuf_order_set(struct trace_buffer *buffer, int order)
 
 		cpu_buffer = buffer->buffers[cpu];
 
-		if (cpu_buffer->mapped) {
+		if (atomic_read(&cpu_buffer->resize_disabled)) {
 			err = -EBUSY;
 			goto error;
 		}
@@ -8214,7 +8217,7 @@ static __init int test_ringbuffer(void)
 
  out_free:
 	for_each_online_cpu(cpu) {
-		if (!rb_threads[cpu])
+		if (IS_ERR_OR_NULL(rb_threads[cpu]))
 			break;
 		kthread_stop(rb_threads[cpu]);
 	}

kernel/trace/trace.c

@@ -1788,7 +1788,7 @@ void trace_buffered_event_enable(void)
 
 		per_cpu(trace_buffered_event, cpu) = event;
 
-		scoped_guard(preempt,) {
+		scoped_guard(preempt) {
 			if (cpu == smp_processor_id() &&
 			    __this_cpu_read(trace_buffered_event) !=
 			    per_cpu(trace_buffered_event, cpu))