tracing: Fix WARN_ON in tracing_buffers_mmap_close

When a process forks, the child process copies the parent's VMAs but the
user_mapped reference count is not incremented. As a result, when both the
parent and child processes exit, tracing_buffers_mmap_close() is called
twice. On the second call, user_mapped is already 0, causing the function to
return -ENODEV and triggering a WARN_ON.

Normally, this isn't an issue as the memory is mapped with VM_DONTCOPY set.
But this is only a hint, and the application can call
madvise(MADVISE_DOFORK) which resets the VM_DONTCOPY flag. When the
application does that, it can trigger this issue on fork.

Fix it by incrementing the user_mapped reference count without re-mapping
the pages in the VMA's open callback.

Cc: [email protected]
Cc: Masami Hiramatsu <[email protected]>
Cc: Mathieu Desnoyers <[email protected]>
Cc: Vincent Donnefort <[email protected]>
Cc: Lorenzo Stoakes <[email protected]>
Link: https://patch.msgid.link/[email protected]
Fixes: cf9f0f7c4c ("tracing: Allow user-space mapping of the ring-buffer")
Reported-by: [email protected]
Closes: https://syzkaller.appspot.com/bug?extid=3b5dd2030fe08afdf65d
Tested-by: [email protected]
Signed-off-by: Qing Wang <[email protected]>
Signed-off-by: Steven Rostedt (Google) <[email protected]>

include/linux/ring_buffer.h

@@ -248,6 +248,7 @@ int trace_rb_cpu_prepare(unsigned int cpu, struct hlist_node *node);
 
 int ring_buffer_map(struct trace_buffer *buffer, int cpu,
 		    struct vm_area_struct *vma);
+void ring_buffer_map_dup(struct trace_buffer *buffer, int cpu);
 int ring_buffer_unmap(struct trace_buffer *buffer, int cpu);
 int ring_buffer_map_get_reader(struct trace_buffer *buffer, int cpu);
 #endif /* _LINUX_RING_BUFFER_H */

kernel/trace/ring_buffer.c

@@ -7310,6 +7310,27 @@ int ring_buffer_map(struct trace_buffer *buffer, int cpu,
 	return err;
 }
 
+/*
+ * This is called when a VMA is duplicated (e.g., on fork()) to increment
+ * the user_mapped counter without remapping pages.
+ */
+void ring_buffer_map_dup(struct trace_buffer *buffer, int cpu)
+{
+	struct ring_buffer_per_cpu *cpu_buffer;
+
+	if (WARN_ON(!cpumask_test_cpu(cpu, buffer->cpumask)))
+		return;
+
+	cpu_buffer = buffer->buffers[cpu];
+
+	guard(mutex)(&cpu_buffer->mapping_lock);
+
+	if (cpu_buffer->user_mapped)
+		__rb_inc_dec_mapped(cpu_buffer, true);
+	else
+		WARN(1, "Unexpected buffer stat, it should be mapped");
+}
+
 int ring_buffer_unmap(struct trace_buffer *buffer, int cpu)
 {
 	struct ring_buffer_per_cpu *cpu_buffer;

kernel/trace/trace.c

@@ -8213,6 +8213,18 @@ static inline int get_snapshot_map(struct trace_array *tr) { return 0; }
 static inline void put_snapshot_map(struct trace_array *tr) { }
 #endif
 
+/*
+ * This is called when a VMA is duplicated (e.g., on fork()) to increment
+ * the user_mapped counter without remapping pages.
+ */
+static void tracing_buffers_mmap_open(struct vm_area_struct *vma)
+{
+	struct ftrace_buffer_info *info = vma->vm_file->private_data;
+	struct trace_iterator *iter = &info->iter;
+
+	ring_buffer_map_dup(iter->array_buffer->buffer, iter->cpu_file);
+}
+
 static void tracing_buffers_mmap_close(struct vm_area_struct *vma)
 {
 	struct ftrace_buffer_info *info = vma->vm_file->private_data;
@@ -8232,6 +8244,7 @@ static int tracing_buffers_may_split(struct vm_area_struct *vma, unsigned long a
 }
 
 static const struct vm_operations_struct tracing_buffers_vmops = {
+	.open		= tracing_buffers_mmap_open,
 	.close		= tracing_buffers_mmap_close,
 	.may_split      = tracing_buffers_may_split,
 };