[for-linus][PATCH 1/3] tracing: Fix buffer_ref pipe ops

[Steven Rostedt]

From: Jann Horn <jannh@xxxxxxxxxx>

This fixes multiple issues in buffer_pipe_buf_ops:

 - The ->steal() handler must not return zero unless the pipe buffer has
   the only reference to the page. But generic_pipe_buf_steal() assumes
   that every reference to the pipe is tracked by the page's refcount,
   which isn't true for these buffers - buffer_pipe_buf_get(), which
   duplicates a buffer, doesn't touch the page's refcount.
   Fix it by using generic_pipe_buf_nosteal(), which refuses every
   attempted theft. It should be easy to actually support ->steal, but the
   only current users of pipe_buf_steal() are the virtio console and FUSE,
   and they also only use it as an optimization. So it's probably not worth
   the effort.
 - The ->get() and ->release() handlers can be invoked concurrently on pipe
   buffers backed by the same struct buffer_ref. Make them safe against
   concurrency by using refcount_t.
 - The pointers stored in ->private were only zeroed out when the last
   reference to the buffer_ref was dropped. As far as I know, this
   shouldn't be necessary anyway, but if we do it, let's always do it.

Link: http://lkml.kernel.org/r/20190404215925.253531-1-jannh@xxxxxxxxxx

Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: Masami Hiramatsu <mhiramat@xxxxxxxxxx>
Cc: Al Viro <viro@xxxxxxxxxxxxxxxxxx>
Cc: stable@xxxxxxxxxxxxxxx
Fixes: 73a757e63114d ("ring-buffer: Return reader page back into existing ring buffer")
Signed-off-by: Jann Horn <jannh@xxxxxxxxxx>
Signed-off-by: Steven Rostedt (VMware) <rostedt@xxxxxxxxxxx>
---
 fs/splice.c               |  4 ++--
 include/linux/pipe_fs_i.h |  1 +
 kernel/trace/trace.c      | 28 ++++++++++++++--------------
 3 files changed, 17 insertions(+), 16 deletions(-)

diff --git a/fs/splice.c b/fs/splice.c
index 3ee7e82df48f..e75807380caa 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -330,8 +330,8 @@ const struct pipe_buf_operations default_pipe_buf_ops = {
 	.get = generic_pipe_buf_get,
 };
 
-static int generic_pipe_buf_nosteal(struct pipe_inode_info *pipe,
-				    struct pipe_buffer *buf)
+int generic_pipe_buf_nosteal(struct pipe_inode_info *pipe,
+			     struct pipe_buffer *buf)
 {
 	return 1;
 }
diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h
index 787d224ff43e..a830e9a00eb9 100644
--- a/include/linux/pipe_fs_i.h
+++ b/include/linux/pipe_fs_i.h
@@ -174,6 +174,7 @@ void free_pipe_info(struct pipe_inode_info *);
 void generic_pipe_buf_get(struct pipe_inode_info *, struct pipe_buffer *);
 int generic_pipe_buf_confirm(struct pipe_inode_info *, struct pipe_buffer *);
 int generic_pipe_buf_steal(struct pipe_inode_info *, struct pipe_buffer *);
+int generic_pipe_buf_nosteal(struct pipe_inode_info *, struct pipe_buffer *);
 void generic_pipe_buf_release(struct pipe_inode_info *, struct pipe_buffer *);
 void pipe_buf_mark_unmergeable(struct pipe_buffer *buf);
 
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 21153e64bf1c..0cfa13a60086 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -7025,19 +7025,23 @@ struct buffer_ref {
 	struct ring_buffer	*buffer;
 	void			*page;
 	int			cpu;
-	int			ref;
+	refcount_t		refcount;
 };
 
+static void buffer_ref_release(struct buffer_ref *ref)
+{
+	if (!refcount_dec_and_test(&ref->refcount))
+		return;
+	ring_buffer_free_read_page(ref->buffer, ref->cpu, ref->page);
+	kfree(ref);
+}
+
 static void buffer_pipe_buf_release(struct pipe_inode_info *pipe,
 				    struct pipe_buffer *buf)
 {
 	struct buffer_ref *ref = (struct buffer_ref *)buf->private;
 
-	if (--ref->ref)
-		return;
-
-	ring_buffer_free_read_page(ref->buffer, ref->cpu, ref->page);
-	kfree(ref);
+	buffer_ref_release(ref);
 	buf->private = 0;
 }
 
@@ -7046,14 +7050,14 @@ static void buffer_pipe_buf_get(struct pipe_inode_info *pipe,
 {
 	struct buffer_ref *ref = (struct buffer_ref *)buf->private;
 
-	ref->ref++;
+	refcount_inc(&ref->refcount);
 }
 
 /* Pipe buffer operations for a buffer. */
 static const struct pipe_buf_operations buffer_pipe_buf_ops = {
 	.confirm		= generic_pipe_buf_confirm,
 	.release		= buffer_pipe_buf_release,
-	.steal			= generic_pipe_buf_steal,
+	.steal			= generic_pipe_buf_nosteal,
 	.get			= buffer_pipe_buf_get,
 };
 
@@ -7066,11 +7070,7 @@ static void buffer_spd_release(struct splice_pipe_desc *spd, unsigned int i)
 	struct buffer_ref *ref =
 		(struct buffer_ref *)spd->partial[i].private;
 
-	if (--ref->ref)
-		return;
-
-	ring_buffer_free_read_page(ref->buffer, ref->cpu, ref->page);
-	kfree(ref);
+	buffer_ref_release(ref);
 	spd->partial[i].private = 0;
 }
 
@@ -7125,7 +7125,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
 			break;
 		}
 
-		ref->ref = 1;
+		refcount_set(&ref->refcount, 1);
 		ref->buffer = iter->trace_buffer->buffer;
 		ref->page = ring_buffer_alloc_read_page(ref->buffer, iter->cpu_file);
 		if (IS_ERR(ref->page)) {
-- 
2.20.1