io_uring: optimise SQPOLL mm/files grabbing

There are two reasons for this. First is to optimise
io_sq_thread_acquire_mm_files() for non-SQPOLL case, which currently do
too many checks and function calls in the hot path, e.g. in
io_init_req().

The second is to not grab mm/files when there are not needed. As
__io_queue_sqe() issues only one request now, we can reuse
io_sq_thread_acquire_mm_files() instead of unconditional acquire
mm/files.

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

Author: isilence

fs/io_uring.c

@@ -1145,9 +1145,6 @@ static void io_sq_thread_drop_mm_files(void)
 
 static int __io_sq_thread_acquire_files(struct io_ring_ctx *ctx)
 {
-	if (current->flags & PF_EXITING)
-		return -EFAULT;
-
 	if (!current->files) {
 		struct files_struct *files;
 		struct nsproxy *nsproxy;
@@ -1175,15 +1172,9 @@ static int __io_sq_thread_acquire_mm(struct io_ring_ctx *ctx)
 {
 	struct mm_struct *mm;
 
-	if (current->flags & PF_EXITING)
-		return -EFAULT;
 	if (current->mm)
 		return 0;
 
-	/* Should never happen */
-	if (unlikely(!(ctx->flags & IORING_SETUP_SQPOLL)))
-		return -EFAULT;
-
 	task_lock(ctx->sqo_task);
 	mm = ctx->sqo_task->mm;
 	if (unlikely(!mm || !mmget_not_zero(mm)))
@@ -1198,8 +1189,8 @@ static int __io_sq_thread_acquire_mm(struct io_ring_ctx *ctx)
 	return -EFAULT;
 }
 
-static int io_sq_thread_acquire_mm_files(struct io_ring_ctx *ctx,
-					 struct io_kiocb *req)
+static int __io_sq_thread_acquire_mm_files(struct io_ring_ctx *ctx,
+					   struct io_kiocb *req)
 {
 	const struct io_op_def *def = &io_op_defs[req->opcode];
 	int ret;
@@ -1219,6 +1210,16 @@ static int io_sq_thread_acquire_mm_files(struct io_ring_ctx *ctx,
 	return 0;
 }
 
+static inline int io_sq_thread_acquire_mm_files(struct io_ring_ctx *ctx,
+						struct io_kiocb *req)
+{
+	if (unlikely(current->flags & PF_EXITING))
+		return -EFAULT;
+	if (!(ctx->flags & IORING_SETUP_SQPOLL))
+		return 0;
+	return __io_sq_thread_acquire_mm_files(ctx, req);
+}
+
 static void io_sq_thread_associate_blkcg(struct io_ring_ctx *ctx,
 					 struct cgroup_subsys_state **cur_css)
 
@@ -2336,9 +2337,7 @@ static void __io_req_task_submit(struct io_kiocb *req)
 	struct io_ring_ctx *ctx = req->ctx;
 
 	mutex_lock(&ctx->uring_lock);
-	if (!ctx->sqo_dead &&
-	    !__io_sq_thread_acquire_mm(ctx) &&
-	    !__io_sq_thread_acquire_files(ctx))
+	if (!ctx->sqo_dead && !io_sq_thread_acquire_mm_files(ctx, req))
 		__io_queue_sqe(req);
 	else
 		__io_req_task_cancel(req, -EFAULT);