tracing: Allow user-space mapping of the ring-buffer

Currently, user-space extracts data from the ring-buffer via splice,
which is handy for storage or network sharing. However, due to splice
limitations, it is imposible to do real-time analysis without a copy.

A solution for that problem is to let the user-space map the ring-buffer
directly.

The mapping is exposed via the per-CPU file trace_pipe_raw. The first
element of the mapping is the meta-page. It is followed by each
subbuffer constituting the ring-buffer, ordered by their unique page ID:

  * Meta-page -- include/uapi/linux/trace_mmap.h for a description
  * Subbuf ID 0
  * Subbuf ID 1
     ...

It is therefore easy to translate a subbuf ID into an offset in the
mapping:

  reader_id = meta->reader->id;
  reader_offset = meta->meta_page_size + reader_id * meta->subbuf_size;

When new data is available, the mapper must call a newly introduced ioctl:
TRACE_MMAP_IOCTL_GET_READER. This will update the Meta-page reader ID to
point to the next reader containing unread data.

Mapping will prevent snapshot and buffer size modifications.

Link: https://lore.kernel.org/linux-trace-kernel/20240510140435.3550353-4-vdonnefort@google.com

CC: <linux-mm@kvack.org>
Signed-off-by: Vincent Donnefort <vdonnefort@google.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>

include/uapi/linux/trace_mmap.h

@@ -43,4 +43,6 @@ struct trace_buffer_meta {
 	__u64	Reserved2;
 };
 
+#define TRACE_MMAP_IOCTL_GET_READER		_IO('T', 0x1)
+
 #endif /* _TRACE_MMAP_H_ */

kernel/trace/trace.c

@@ -1191,6 +1191,12 @@ static void tracing_snapshot_instance_cond(struct trace_array *tr,
 		return;
 	}
 
+	if (tr->mapped) {
+		trace_array_puts(tr, "*** BUFFER MEMORY MAPPED ***\n");
+		trace_array_puts(tr, "*** Can not use snapshot (sorry) ***\n");
+		return;
+	}
+
 	local_irq_save(flags);
 	update_max_tr(tr, current, smp_processor_id(), cond_data);
 	local_irq_restore(flags);
@@ -1323,7 +1329,7 @@ static int tracing_arm_snapshot_locked(struct trace_array *tr)
 	lockdep_assert_held(&trace_types_lock);
 
 	spin_lock(&tr->snapshot_trigger_lock);
-	if (tr->snapshot == UINT_MAX) {
+	if (tr->snapshot == UINT_MAX || tr->mapped) {
 		spin_unlock(&tr->snapshot_trigger_lock);
 		return -EBUSY;
 	}
@@ -8194,15 +8200,32 @@ out:
 	return ret;
 }
 
-/* An ioctl call with cmd 0 to the ring buffer file will wake up all waiters */
 static long tracing_buffers_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 {
 	struct ftrace_buffer_info *info = file->private_data;
 	struct trace_iterator *iter = &info->iter;
+	int err;
 
-	if (cmd)
-		return -ENOIOCTLCMD;
+	if (cmd == TRACE_MMAP_IOCTL_GET_READER) {
+		if (!(file->f_flags & O_NONBLOCK)) {
+			err = ring_buffer_wait(iter->array_buffer->buffer,
+					       iter->cpu_file,
+					       iter->tr->buffer_percent,
+					       NULL, NULL);
+			if (err)
+				return err;
+		}
 
+		return ring_buffer_map_get_reader(iter->array_buffer->buffer,
+						  iter->cpu_file);
+	} else if (cmd) {
+		return -ENOTTY;
+	}
+
+	/*
+	 * An ioctl call with cmd 0 to the ring buffer file will wake up all
+	 * waiters
+	 */
 	mutex_lock(&trace_types_lock);
 
 	/* Make sure the waiters see the new wait_index */
@@ -8214,6 +8237,76 @@ static long tracing_buffers_ioctl(struct file *file, unsigned int cmd, unsigned
 	return 0;
 }
 
+#ifdef CONFIG_TRACER_MAX_TRACE
+static int get_snapshot_map(struct trace_array *tr)
+{
+	int err = 0;
+
+	/*
+	 * Called with mmap_lock held. lockdep would be unhappy if we would now
+	 * take trace_types_lock. Instead use the specific
+	 * snapshot_trigger_lock.
+	 */
+	spin_lock(&tr->snapshot_trigger_lock);
+
+	if (tr->snapshot || tr->mapped == UINT_MAX)
+		err = -EBUSY;
+	else
+		tr->mapped++;
+
+	spin_unlock(&tr->snapshot_trigger_lock);
+
+	/* Wait for update_max_tr() to observe iter->tr->mapped */
+	if (tr->mapped == 1)
+		synchronize_rcu();
+
+	return err;
+
+}
+static void put_snapshot_map(struct trace_array *tr)
+{
+	spin_lock(&tr->snapshot_trigger_lock);
+	if (!WARN_ON(!tr->mapped))
+		tr->mapped--;
+	spin_unlock(&tr->snapshot_trigger_lock);
+}
+#else
+static inline int get_snapshot_map(struct trace_array *tr) { return 0; }
+static inline void put_snapshot_map(struct trace_array *tr) { }
+#endif
+
+static void tracing_buffers_mmap_close(struct vm_area_struct *vma)
+{
+	struct ftrace_buffer_info *info = vma->vm_file->private_data;
+	struct trace_iterator *iter = &info->iter;
+
+	WARN_ON(ring_buffer_unmap(iter->array_buffer->buffer, iter->cpu_file));
+	put_snapshot_map(iter->tr);
+}
+
+static const struct vm_operations_struct tracing_buffers_vmops = {
+	.close		= tracing_buffers_mmap_close,
+};
+
+static int tracing_buffers_mmap(struct file *filp, struct vm_area_struct *vma)
+{
+	struct ftrace_buffer_info *info = filp->private_data;
+	struct trace_iterator *iter = &info->iter;
+	int ret = 0;
+
+	ret = get_snapshot_map(iter->tr);
+	if (ret)
+		return ret;
+
+	ret = ring_buffer_map(iter->array_buffer->buffer, iter->cpu_file, vma);
+	if (ret)
+		put_snapshot_map(iter->tr);
+
+	vma->vm_ops = &tracing_buffers_vmops;
+
+	return ret;
+}
+
 static const struct file_operations tracing_buffers_fops = {
 	.open		= tracing_buffers_open,
 	.read		= tracing_buffers_read,
@@ -8223,6 +8316,7 @@ static const struct file_operations tracing_buffers_fops = {
 	.splice_read	= tracing_buffers_splice_read,
 	.unlocked_ioctl = tracing_buffers_ioctl,
 	.llseek		= no_llseek,
+	.mmap		= tracing_buffers_mmap,
 };
 
 static ssize_t

kernel/trace/trace.h

@@ -336,6 +336,7 @@ struct trace_array {
 	bool			allocated_snapshot;
 	spinlock_t		snapshot_trigger_lock;
 	unsigned int		snapshot;
+	unsigned int		mapped;
 	unsigned long		max_latency;
 #ifdef CONFIG_FSNOTIFY
 	struct dentry		*d_max_latency;