[PATCH 5/5] trace: Make addition of pages in ring buffer atomic

[Vaibhav Nagarnaik <vnagarnaik@google.com>]

This patch adds the capability to add new pages to a ring buffer
atomically while write operations are going on. This makes it possible
to expand the ring buffer size without reinitializing the ring buffer.

The new pages are attached between the head page and its previous page.

Signed-off-by: Vaibhav Nagarnaik <vnagarnaik@google.com>
---
 kernel/trace/ring_buffer.c |  109 +++++++++++++++++++++++++++++++------------
 1 files changed, 78 insertions(+), 31 deletions(-)

diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 0b43758..aecef65 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -1415,36 +1415,68 @@ out:
 }
 
 static void
-rb_insert_pages(struct ring_buffer_per_cpu *cpu_buffer,
-		struct list_head *pages, unsigned nr_pages)
+rb_insert_pages(struct ring_buffer_per_cpu *cpu_buffer)
 {
-	struct buffer_page *bpage;
-	struct list_head *p;
-	unsigned i;
+	struct list_head *pages = &cpu_buffer->new_pages;
+	int retries, success;
 
-	/* stop the writers while inserting pages */
-	atomic_inc(&cpu_buffer->record_disabled);
+	spin_lock_irq(&cpu_buffer->reader_lock);
+	/*
+	 * We are holding the reader lock, so the reader page won't be swapped
+	 * in the ring buffer. Now we are racing with the writer trying to
+	 * move head page and the tail page.
+	 * We are going to adapt the reader page update process where:
+	 * 1. We first splice the start and end of list of new pages between
+	 *    the head page and its previous page.
+	 * 2. We cmpxchg the prev_page->next to point from head page to the
+	 *    start of new pages list.
+	 * 3. Finally, we update the head->prev to the end of new list.
+	 *
+	 * We will try this process 3 times, to make sure that we don't keep
+	 * spinning.
+	 */
+	retries = 3;
+	success = 0;
+	while (retries--) {
+		struct list_head *last_page, *first_page;
+		struct list_head *head_page, *prev_page, *r;
+		struct list_head *head_page_with_bit;
 
-	/* Make sure all writers are done with this buffer. */
-	synchronize_sched();
+		head_page = &rb_set_head_page(cpu_buffer)->list;
+		prev_page = head_page->prev;
 
-	spin_lock_irq(&cpu_buffer->reader_lock);
-	rb_head_page_deactivate(cpu_buffer);
+		first_page = pages->next;
+		last_page  = pages->prev;
 
-	for (i = 0; i < nr_pages; i++) {
-		if (RB_WARN_ON(cpu_buffer, list_empty(pages)))
-			goto out;
-		p = pages->next;
-		bpage = list_entry(p, struct buffer_page, list);
-		list_del_init(&bpage->list);
-		list_add_tail(&bpage->list, cpu_buffer->pages);
+
+		head_page_with_bit = (struct list_head *)
+				((unsigned long)head_page | RB_PAGE_HEAD);
+
+		last_page->next  = head_page_with_bit;
+		first_page->prev = prev_page;
+
+		r = cmpxchg(&prev_page->next, head_page_with_bit, first_page);
+
+		if (r == head_page_with_bit) {
+			/*
+			 * yay, we replaced the page pointer to our new list,
+			 * now, we just have to update to head page's prev
+			 * pointer to point to end of list
+			 */
+			head_page->prev = last_page;
+			success = 1;
+			break;
+		}
 	}
-	rb_reset_cpu(cpu_buffer);
-	rb_check_pages(cpu_buffer);
 
-out:
+	if (success)
+		INIT_LIST_HEAD(pages);
+	/*
+	 * If we weren't successful in adding in new pages, warn and stop
+	 * tracing
+	 */
+	RB_WARN_ON(cpu_buffer, !success);
 	spin_unlock_irq(&cpu_buffer->reader_lock);
-	atomic_dec(&cpu_buffer->record_disabled);
 }
 
 static void update_pages_handler(struct work_struct *work)
@@ -1453,8 +1485,7 @@ static void update_pages_handler(struct work_struct *work)
 			struct ring_buffer_per_cpu, update_pages_work);
 
 	if (cpu_buffer->nr_pages_to_update > 0)
-		rb_insert_pages(cpu_buffer, &cpu_buffer->new_pages,
-				cpu_buffer->nr_pages_to_update);
+		rb_insert_pages(cpu_buffer);
 	else
 		rb_remove_pages(cpu_buffer, -cpu_buffer->nr_pages_to_update);
 
@@ -1475,7 +1506,7 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size,
 {
 	struct ring_buffer_per_cpu *cpu_buffer;
 	unsigned nr_pages;
-	int cpu;
+	int cpu, err = 0;
 
 	/*
 	 * Always succeed at resizing a non-existent buffer:
@@ -1500,6 +1531,11 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size,
 		for_each_buffer_cpu(buffer, cpu) {
 			cpu_buffer = buffer->buffers[cpu];
 
+			if (atomic_read(&cpu_buffer->record_disabled)) {
+				err = -EBUSY;
+				goto out_err;
+			}
+
 			cpu_buffer->nr_pages_to_update = nr_pages -
 							cpu_buffer->nr_pages;
 
@@ -1515,9 +1551,11 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size,
 			 */
 			INIT_LIST_HEAD(&cpu_buffer->new_pages);
 			if (__rb_allocate_pages(cpu_buffer->nr_pages_to_update,
-						&cpu_buffer->new_pages, cpu))
+						&cpu_buffer->new_pages, cpu)) {
 				/* not enough memory for new pages */
-				goto no_mem;
+				err = -ENOMEM;
+				goto out_err;
+			}
 		}
 
 		/* fire off all the required work handlers */
@@ -1540,6 +1578,12 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size,
 		}
 	} else {
 		cpu_buffer = buffer->buffers[cpu_id];
+
+		if (atomic_read(&cpu_buffer->record_disabled)) {
+			err = -EBUSY;
+			goto out_err;
+		}
+
 		if (nr_pages == cpu_buffer->nr_pages)
 			goto out;
 
@@ -1549,8 +1593,10 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size,
 		INIT_LIST_HEAD(&cpu_buffer->new_pages);
 		if (cpu_buffer->nr_pages_to_update > 0 &&
 			__rb_allocate_pages(cpu_buffer->nr_pages_to_update,
-						&cpu_buffer->new_pages, cpu_id))
-			goto no_mem;
+					&cpu_buffer->new_pages, cpu_id)) {
+			err = -ENOMEM;
+			goto out_err;
+		}
 
 		schedule_work_on(cpu_id, &cpu_buffer->update_pages_work);
 		wait_for_completion(&cpu_buffer->update_completion);
@@ -1564,7 +1610,7 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size,
 	mutex_unlock(&buffer->mutex);
 	return size;
 
- no_mem:
+ out_err:
 	for_each_buffer_cpu(buffer, cpu) {
 		struct buffer_page *bpage, *tmp;
 
@@ -1582,7 +1628,7 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size,
 		}
 	}
 	mutex_unlock(&buffer->mutex);
-	return -ENOMEM;
+	return err;
 }
 EXPORT_SYMBOL_GPL(ring_buffer_resize);
 
@@ -3727,6 +3773,7 @@ rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer)
 	cpu_buffer->commit_page = cpu_buffer->head_page;
 
 	INIT_LIST_HEAD(&cpu_buffer->reader_page->list);
+	INIT_LIST_HEAD(&cpu_buffer->new_pages);
 	local_set(&cpu_buffer->reader_page->write, 0);
 	local_set(&cpu_buffer->reader_page->entries, 0);
 	local_set(&cpu_buffer->reader_page->page->commit, 0);
-- 
1.7.3.1