ring-buffer: Return reader page back into existing ring buffer

When reading the ring buffer for consuming, it is optimized for splice,
where a page is taken out of the ring buffer (zero copy) and sent to the
reading consumer. When the read is finished with the page, it calls
ring_buffer_free_read_page(), which simply frees the page. The next time the
reader needs to get a page from the ring buffer, it must call
ring_buffer_alloc_read_page() which allocates and initializes a reader page
for the ring buffer to be swapped into the ring buffer for a new filled page
for the reader.

The problem is that there's no reason to actually free the page when it is
passed back to the ring buffer. It can hold it off and reuse it for the next
iteration. This completely removes the interaction with the page_alloc
mechanism.

Using the trace-cmd utility to record all events (causing trace-cmd to
require reading lots of pages from the ring buffer, and calling
ring_buffer_alloc/free_read_page() several times), and also assigning a
stack trace trigger to the mm_page_alloc event, we can see how many times
the ring_buffer_alloc_read_page() needed to allocate a page for the ring
buffer.

Before this change:

  # trace-cmd record -e all -e mem_page_alloc -R stacktrace sleep 1
  # trace-cmd report |grep ring_buffer_alloc_read_page | wc -l
  9968

After this change:

  # trace-cmd record -e all -e mem_page_alloc -R stacktrace sleep 1
  # trace-cmd report |grep ring_buffer_alloc_read_page | wc -l
  4

Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>

1 files changed, 12 insertions, 5 deletions

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 60c904fa5480..5b645b0fbbb8 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -6054,6 +6054,7 @@ static int tracing_clock_open(struct inode *inode, struct file *file)
 struct ftrace_buffer_info {
 	struct trace_iterator	iter;
 	void			*spare;
+	unsigned int		spare_cpu;
 	unsigned int		read;
 };
 
@@ -6383,9 +6384,11 @@ tracing_buffers_read(struct file *filp, char __user *ubuf,
 		return -EBUSY;
 #endif
 
-	if (!info->spare)
+	if (!info->spare) {
 		info->spare = ring_buffer_alloc_read_page(iter->trace_buffer->buffer,
 							  iter->cpu_file);
+		info->spare_cpu = iter->cpu_file;
+	}
 	if (!info->spare)
 		return -ENOMEM;
 
@@ -6445,7 +6448,8 @@ static int tracing_buffers_release(struct inode *inode, struct file *file)
 	__trace_array_put(iter->tr);
 
 	if (info->spare)
-		ring_buffer_free_read_page(iter->trace_buffer->buffer, info->spare);
+		ring_buffer_free_read_page(iter->trace_buffer->buffer,
+					   info->spare_cpu, info->spare);
 	kfree(info);
 
 	mutex_unlock(&trace_types_lock);
@@ -6456,6 +6460,7 @@ static int tracing_buffers_release(struct inode *inode, struct file *file)
 struct buffer_ref {
 	struct ring_buffer	*buffer;
 	void			*page;
+	int			cpu;
 	int			ref;
 };
 
@@ -6467,7 +6472,7 @@ static void buffer_pipe_buf_release(struct pipe_inode_info *pipe,
 	if (--ref->ref)
 		return;
 
-	ring_buffer_free_read_page(ref->buffer, ref->page);
+	ring_buffer_free_read_page(ref->buffer, ref->cpu, ref->page);
 	kfree(ref);
 	buf->private = 0;
 }
@@ -6501,7 +6506,7 @@ static void buffer_spd_release(struct splice_pipe_desc *spd, unsigned int i)
 	if (--ref->ref)
 		return;
 
-	ring_buffer_free_read_page(ref->buffer, ref->page);
+	ring_buffer_free_read_page(ref->buffer, ref->cpu, ref->page);
 	kfree(ref);
 	spd->partial[i].private = 0;
 }
@@ -6566,11 +6571,13 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
 			kfree(ref);
 			break;
 		}
+		ref->cpu = iter->cpu_file;
 
 		r = ring_buffer_read_page(ref->buffer, &ref->page,
 					  len, iter->cpu_file, 1);
 		if (r < 0) {
-			ring_buffer_free_read_page(ref->buffer, ref->page);
+			ring_buffer_free_read_page(ref->buffer, ref->cpu,
+						   ref->page);
 			kfree(ref);
 			break;
 		}