[PATCH V2 4/9] fork: add option to not clone or dup files

[Mike Christie]

Each vhost device gets a thread that is used to perform IO and management
operations. Instead of a thread that is accessing a device, the thread is
part of the device, so when it calls the kernel_worker() function added in
the next patch we can't dup or clone the parent's files/FDS because it would
do an extra increment on ourself.

Later, when we do:

Qemu process exits:
        do_exit -> exit_files -> put_files_struct -> close_files

we would leak the device's resources because of that extra refcount
on the fd or file_struct.

This patch adds a no_files option so these worker threads can prevent
taking an extra refcount on themselves.

Signed-off-by: Mike Christie <michael.christie@xxxxxxxxxx>
---
 include/linux/sched/task.h |  1 +
 kernel/fork.c              | 11 +++++++++--
 2 files changed, 10 insertions(+), 2 deletions(-)

diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h
index cf7c9fffc839..e165cc67fd3c 100644
--- a/include/linux/sched/task.h
+++ b/include/linux/sched/task.h
@@ -20,6 +20,7 @@ struct css_set;
 
 #define KERN_WORKER_IO		BIT(0)
 #define KERN_WORKER_USER	BIT(1)
+#define KERN_WORKER_NO_FILES	BIT(2)
 
 struct kernel_clone_args {
 	u64 flags;
diff --git a/kernel/fork.c b/kernel/fork.c
index 4b0e8257993b..98264cf1d6a6 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1532,7 +1532,8 @@ static int copy_fs(unsigned long clone_flags, struct task_struct *tsk)
 	return 0;
 }
 
-static int copy_files(unsigned long clone_flags, struct task_struct *tsk)
+static int copy_files(unsigned long clone_flags, struct task_struct *tsk,
+		      int no_files)
 {
 	struct files_struct *oldf, *newf;
 	int error = 0;
@@ -1544,6 +1545,11 @@ static int copy_files(unsigned long clone_flags, struct task_struct *tsk)
 	if (!oldf)
 		goto out;
 
+	if (no_files) {
+		tsk->files = NULL;
+		goto out;
+	}
+
 	if (clone_flags & CLONE_FILES) {
 		atomic_inc(&oldf->count);
 		goto out;
@@ -2179,7 +2185,8 @@ static __latent_entropy struct task_struct *copy_process(
 	retval = copy_semundo(clone_flags, p);
 	if (retval)
 		goto bad_fork_cleanup_security;
-	retval = copy_files(clone_flags, p);
+	retval = copy_files(clone_flags, p,
+			    args->worker_flags & KERN_WORKER_NO_FILES);
 	if (retval)
 		goto bad_fork_cleanup_semundo;
 	retval = copy_fs(clone_flags, p);
-- 
2.25.1