trace ring-buffer updates for v6.13

- Limit time interrupts are disabled in rb_check_pages()
 
   The rb_check_pages() is called after the ring buffer size is updated to
   make sure that the ring buffer has not been corrupted. Commit
   c2274b908d ("ring-buffer: Fix a race between readers and resize
   checks") fixed a race with the check pages and simultaneous resizes to the
   ring buffer by adding a raw_spin_lock_irqsave() around the check
   operation. Although this was a simple fix, it would hold interrupts
   disabled for non determinative amount of time. This could harm PREEMPT_RT
   operations.
 
   Instead, modify the logic by adding a counter when the buffer is modified
   and to release the raw_spin_lock() at each iteration. It checks the
   counter under the lock to see if a modification happened during the loop,
   and if it did, it would restart the loop up to 3 times. After 3 times, it
   will simply exit the check, as it is unlikely that would ever happen as
   buffer resizes are rare occurrences.
 
 - Replace some open coded str_low_high() with the helper
 
 - Fix some documentation/comments
 -----BEGIN PGP SIGNATURE-----
 
 iIoEABYIADIWIQRRSw7ePDh/lE+zeZMp5XQQmuv6qgUCZz5KNxQccm9zdGVkdEBn
 b29kbWlzLm9yZwAKCRAp5XQQmuv6qiANAP4/6cSGOhQgIkaN8UsKmWTfBqU89JK2
 a4tqAZWKsQormgEAkDLPD0Lda0drmu/Dwnr/klS21yyLcQBzyX1CYw9G4gY=
 =jkLz
 -----END PGP SIGNATURE-----

Merge tag 'trace-ring-buffer-v6.13' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace

Pull trace ring-buffer updates from Steven Rostedt:

 - Limit time interrupts are disabled in rb_check_pages()

   rb_check_pages() is called after the ring buffer size is updated to
   make sure that the ring buffer has not been corrupted. Commit
   c2274b908d ("ring-buffer: Fix a race between readers and resize
   checks") fixed a race with the check pages and simultaneous resizes
   to the ring buffer by adding a raw_spin_lock_irqsave() around the
   check operation. Although this was a simple fix, it would hold
   interrupts disabled for non determinative amount of time. This could
   harm PREEMPT_RT operations.

   Instead, modify the logic by adding a counter when the buffer is
   modified and to release the raw_spin_lock() at each iteration. It
   checks the counter under the lock to see if a modification happened
   during the loop, and if it did, it would restart the loop up to 3
   times. After 3 times, it will simply exit the check, as it is
   unlikely that would ever happen as buffer resizes are rare
   occurrences.

 - Replace some open coded str_low_high() with the helper

 - Fix some documentation/comments

* tag 'trace-ring-buffer-v6.13' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace:
  ring-buffer: Correct a grammatical error in a comment
  ring-buffer: Use str_low_high() helper in ring_buffer_producer()
  ring-buffer: Reorganize kerneldoc parameter names
  ring-buffer: Limit time with disabled interrupts in rb_check_pages()

kernel/trace/ring_buffer.c

@@ -482,6 +482,8 @@ struct ring_buffer_per_cpu {
 	unsigned long			nr_pages;
 	unsigned int			current_context;
 	struct list_head		*pages;
+	/* pages generation counter, incremented when the list changes */
+	unsigned long			cnt;
 	struct buffer_page		*head_page;	/* read from head */
 	struct buffer_page		*tail_page;	/* write to tail */
 	struct buffer_page		*commit_page;	/* committed pages */
@@ -1475,40 +1477,87 @@ static void rb_check_bpage(struct ring_buffer_per_cpu *cpu_buffer,
 	RB_WARN_ON(cpu_buffer, val & RB_FLAG_MASK);
 }
 
+static bool rb_check_links(struct ring_buffer_per_cpu *cpu_buffer,
+			   struct list_head *list)
+{
+	if (RB_WARN_ON(cpu_buffer,
+		       rb_list_head(rb_list_head(list->next)->prev) != list))
+		return false;
+
+	if (RB_WARN_ON(cpu_buffer,
+		       rb_list_head(rb_list_head(list->prev)->next) != list))
+		return false;
+
+	return true;
+}
+
 /**
  * rb_check_pages - integrity check of buffer pages
  * @cpu_buffer: CPU buffer with pages to test
  *
  * As a safety measure we check to make sure the data pages have not
  * been corrupted.
- *
- * Callers of this function need to guarantee that the list of pages doesn't get
- * modified during the check. In particular, if it's possible that the function
- * is invoked with concurrent readers which can swap in a new reader page then
- * the caller should take cpu_buffer->reader_lock.
  */
 static void rb_check_pages(struct ring_buffer_per_cpu *cpu_buffer)
 {
-	struct list_head *head = rb_list_head(cpu_buffer->pages);
+	struct list_head *head, *tmp;
-	struct list_head *tmp;
+	unsigned long buffer_cnt;
+	unsigned long flags;
+	int nr_loops = 0;
 
-	if (RB_WARN_ON(cpu_buffer,
+	/*
-			rb_list_head(rb_list_head(head->next)->prev) != head))
+	 * Walk the linked list underpinning the ring buffer and validate all
+	 * its next and prev links.
+	 *
+	 * The check acquires the reader_lock to avoid concurrent processing
+	 * with code that could be modifying the list. However, the lock cannot
+	 * be held for the entire duration of the walk, as this would make the
+	 * time when interrupts are disabled non-deterministic, dependent on the
+	 * ring buffer size. Therefore, the code releases and re-acquires the
+	 * lock after checking each page. The ring_buffer_per_cpu.cnt variable
+	 * is then used to detect if the list was modified while the lock was
+	 * not held, in which case the check needs to be restarted.
+	 *
+	 * The code attempts to perform the check at most three times before
+	 * giving up. This is acceptable because this is only a self-validation
+	 * to detect problems early on. In practice, the list modification
+	 * operations are fairly spaced, and so this check typically succeeds at
+	 * most on the second try.
+	 */
+again:
+	if (++nr_loops > 3)
 		return;
 
-	if (RB_WARN_ON(cpu_buffer,
+	raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
-			rb_list_head(rb_list_head(head->prev)->next) != head))
+	head = rb_list_head(cpu_buffer->pages);
-		return;
+	if (!rb_check_links(cpu_buffer, head))
+		goto out_locked;
+	buffer_cnt = cpu_buffer->cnt;
+	tmp = head;
+	raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
 
-	for (tmp = rb_list_head(head->next); tmp != head; tmp = rb_list_head(tmp->next)) {
+	while (true) {
-		if (RB_WARN_ON(cpu_buffer,
+		raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
-				rb_list_head(rb_list_head(tmp->next)->prev) != tmp))
-			return;
 
-		if (RB_WARN_ON(cpu_buffer,
+		if (buffer_cnt != cpu_buffer->cnt) {
-				rb_list_head(rb_list_head(tmp->prev)->next) != tmp))
+			/* The list was updated, try again. */
-			return;
+			raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
+			goto again;
+		}
+
+		tmp = rb_list_head(tmp->next);
+		if (tmp == head)
+			/* The iteration circled back, all is done. */
+			goto out_locked;
+
+		if (!rb_check_links(cpu_buffer, tmp))
+			goto out_locked;
+
+		raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
 	}
+
+out_locked:
+	raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
 }
 
 /*
@@ -2384,9 +2433,9 @@ EXPORT_SYMBOL_GPL(__ring_buffer_alloc);
  * __ring_buffer_alloc_range - allocate a new ring_buffer from existing memory
  * @size: the size in bytes per cpu that is needed.
  * @flags: attributes to set for the ring buffer.
+ * @order: sub-buffer order
  * @start: start of allocated range
  * @range_size: size of allocated range
- * @order: sub-buffer order
  * @key: ring buffer reader_lock_key.
  *
  * Currently the only flag that is available is the RB_FL_OVERWRITE
@@ -2532,6 +2581,7 @@ rb_remove_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned long nr_pages)
 
 	/* make sure pages points to a valid page in the ring buffer */
 	cpu_buffer->pages = next_page;
+	cpu_buffer->cnt++;
 
 	/* update head page */
 	if (head_bit)
@@ -2638,6 +2688,7 @@ rb_insert_pages(struct ring_buffer_per_cpu *cpu_buffer)
 			 * pointer to point to end of list
 			 */
 			head_page->prev = last_page;
+			cpu_buffer->cnt++;
 			success = true;
 			break;
 		}
@@ -2873,12 +2924,8 @@ int ring_buffer_resize(struct trace_buffer *buffer, unsigned long size,
 		 */
 		synchronize_rcu();
 		for_each_buffer_cpu(buffer, cpu) {
-			unsigned long flags;
-
 			cpu_buffer = buffer->buffers[cpu];
-			raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
 			rb_check_pages(cpu_buffer);
-			raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
 		}
 		atomic_dec(&buffer->record_disabled);
 	}
@@ -4010,7 +4057,7 @@ static const char *show_irq_str(int bits)
 	return type[bits];
 }
 
-/* Assume this is an trace event */
+/* Assume this is a trace event */
 static const char *show_flags(struct ring_buffer_event *event)
 {
 	struct trace_entry *entry;
@@ -5296,6 +5343,7 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
 	rb_list_head(reader->list.next)->prev = &cpu_buffer->reader_page->list;
 	rb_inc_page(&cpu_buffer->head_page);
 
+	cpu_buffer->cnt++;
 	local_inc(&cpu_buffer->pages_read);
 
 	/* Finally update the reader page to the new head */
@@ -5835,12 +5883,9 @@ void
 ring_buffer_read_finish(struct ring_buffer_iter *iter)
 {
 	struct ring_buffer_per_cpu *cpu_buffer = iter->cpu_buffer;
-	unsigned long flags;
 
 	/* Use this opportunity to check the integrity of the ring buffer. */
-	raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
 	rb_check_pages(cpu_buffer);
-	raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
 
 	atomic_dec(&cpu_buffer->resize_disabled);
 	kfree(iter->event);
@@ -6757,6 +6802,7 @@ int ring_buffer_subbuf_order_set(struct trace_buffer *buffer, int order)
 		/* Install the new pages, remove the head from the list */
 		cpu_buffer->pages = cpu_buffer->new_pages.next;
 		list_del_init(&cpu_buffer->new_pages);
+		cpu_buffer->cnt++;
 
 		cpu_buffer->head_page
 			= list_entry(cpu_buffer->pages, struct buffer_page, list);

kernel/trace/ring_buffer_benchmark.c

@@ -307,14 +307,14 @@ static void ring_buffer_producer(void)
 	if (!disable_reader) {
 		if (consumer_fifo)
 			trace_printk("Running Consumer at SCHED_FIFO %s\n",
-				     consumer_fifo == 1 ? "low" : "high");
+				     str_low_high(consumer_fifo == 1));
 		else
 			trace_printk("Running Consumer at nice: %d\n",
 				     consumer_nice);
 	}
 	if (producer_fifo)
 		trace_printk("Running Producer at SCHED_FIFO %s\n",
-			     producer_fifo == 1 ? "low" : "high");
+			     str_low_high(producer_fifo == 1));
 	else
 		trace_printk("Running Producer at nice: %d\n",
 			     producer_nice);