io_uring: io_uring: add support for async work inheriting files

This is in preparation for adding opcodes that need to add new files
in a process file table, system calls like open(2) or accept4(2).

If an opcode needs this, it must set IO_WQ_WORK_NEEDS_FILES in the work
item. If work that needs to get punted to async context have this
set, the async worker will assume the original task file table before
executing the work.

Note that opcodes that need access to the current files of an
application cannot be done through IORING_SETUP_SQPOLL.

Signed-off-by: Jens Axboe <axboe@kernel.dk>

1 files changed, 26 insertions, 4 deletions

diff --git a/fs/io-wq.c b/fs/io-wq.c
index 37863879e987..253c04a40db5 100644
--- a/fs/io-wq.c
+++ b/fs/io-wq.c
@@ -52,6 +52,7 @@ struct io_worker {
 
 	struct rcu_head rcu;
 	struct mm_struct *mm;
+	struct files_struct *restore_files;
 };
 
 struct io_wq_nulls_list {
@@ -126,22 +127,36 @@ static void io_worker_release(struct io_worker *worker)
  */
 static bool __io_worker_unuse(struct io_wqe *wqe, struct io_worker *worker)
 {
+	bool dropped_lock = false;
+
+	if (current->files != worker->restore_files) {
+		__acquire(&wqe->lock);
+		spin_unlock_irq(&wqe->lock);
+		dropped_lock = true;
+
+		task_lock(current);
+		current->files = worker->restore_files;
+		task_unlock(current);
+	}
+
 	/*
 	 * If we have an active mm, we need to drop the wq lock before unusing
 	 * it. If we do, return true and let the caller retry the idle loop.
 	 */
 	if (worker->mm) {
-		__acquire(&wqe->lock);
-		spin_unlock_irq(&wqe->lock);
+		if (!dropped_lock) {
+			__acquire(&wqe->lock);
+			spin_unlock_irq(&wqe->lock);
+			dropped_lock = true;
+		}
 		__set_current_state(TASK_RUNNING);
 		set_fs(KERNEL_DS);
 		unuse_mm(worker->mm);
 		mmput(worker->mm);
 		worker->mm = NULL;
-		return true;
 	}
 
-	return false;
+	return dropped_lock;
 }
 
 static void io_worker_exit(struct io_worker *worker)
@@ -189,6 +204,7 @@ static void io_worker_start(struct io_wqe *wqe, struct io_worker *worker)
 	current->flags |= PF_IO_WORKER;
 
 	worker->flags |= (IO_WORKER_F_UP | IO_WORKER_F_RUNNING);
+	worker->restore_files = current->files;
 	atomic_inc(&wqe->nr_running);
 }
 
@@ -291,6 +307,12 @@ static void io_worker_handle_work(struct io_worker *worker)
 		if (!work)
 			break;
 next:
+		if ((work->flags & IO_WQ_WORK_NEEDS_FILES) &&
+		    current->files != work->files) {
+			task_lock(current);
+			current->files = work->files;
+			task_unlock(current);
+		}
 		if ((work->flags & IO_WQ_WORK_NEEDS_USER) && !worker->mm &&
 		    wq->mm && mmget_not_zero(wq->mm)) {
 			use_mm(wq->mm);