io_uring: lazy get task

There will be multiple places where req->task is used, so refcount-pin
it lazily with introduced *io_{get,put}_req_task(). We need to always
have valid ->task for cancellation reasons, but don't care about pinning
it in some cases. That's why it sets req->task in io_req_init() and
implements get/put laziness with a flag.

This also removes using @current from polling io_arm_poll_handler(),
etc., but doesn't change observable behaviour.

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

diff --git a/fs/io_uring.c b/fs/io_uring.c
index b6bcd5a..5f946eb 100644 (file)
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -541,6 +541,7 @@ enum {
        REQ_F_NO_FILE_TABLE_BIT,
        REQ_F_QUEUE_TIMEOUT_BIT,
        REQ_F_WORK_INITIALIZED_BIT,
+       REQ_F_TASK_PINNED_BIT,
 
        /* not a real bit, just to check we're not overflowing the space */
        __REQ_F_LAST_BIT,
@@ -598,6 +599,8 @@ enum {
        REQ_F_QUEUE_TIMEOUT     = BIT(REQ_F_QUEUE_TIMEOUT_BIT),
        /* io_wq_work is initialized */
        REQ_F_WORK_INITIALIZED  = BIT(REQ_F_WORK_INITIALIZED_BIT),
+       /* req->task is refcounted */
+       REQ_F_TASK_PINNED       = BIT(REQ_F_TASK_PINNED_BIT),
 };
 
 struct async_poll {
@@ -910,6 +913,21 @@ struct sock *io_uring_get_socket(struct file *file)
 }
 EXPORT_SYMBOL(io_uring_get_socket);
 
+static void io_get_req_task(struct io_kiocb *req)
+{
+       if (req->flags & REQ_F_TASK_PINNED)
+               return;
+       get_task_struct(req->task);
+       req->flags |= REQ_F_TASK_PINNED;
+}
+
+/* not idempotent -- it doesn't clear REQ_F_TASK_PINNED */
+static void __io_put_req_task(struct io_kiocb *req)
+{
+       if (req->flags & REQ_F_TASK_PINNED)
+               put_task_struct(req->task);
+}
+
 static void io_file_put_work(struct work_struct *work);
 
 /*
@@ -1399,9 +1417,7 @@ static void __io_req_aux_free(struct io_kiocb *req)
        kfree(req->io);
        if (req->file)
                io_put_file(req, req->file, (req->flags & REQ_F_FIXED_FILE));
-       if (req->task)
-               put_task_struct(req->task);
-
+       __io_put_req_task(req);
        io_req_work_drop_env(req);
 }
 
@@ -4367,8 +4383,7 @@ static bool io_arm_poll_handler(struct io_kiocb *req)
                memcpy(&apoll->work, &req->work, sizeof(req->work));
        had_io = req->io != NULL;
 
-       get_task_struct(current);
-       req->task = current;
+       io_get_req_task(req);
        req->apoll = apoll;
        INIT_HLIST_NODE(&req->hash_node);
 
@@ -4556,8 +4571,7 @@ static int io_poll_add_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe
        events = READ_ONCE(sqe->poll_events);
        poll->events = demangle_poll(events) | EPOLLERR | EPOLLHUP;
 
-       get_task_struct(current);
-       req->task = current;
+       io_get_req_task(req);
        return 0;
 }
 
@@ -5818,7 +5832,7 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req,
        req->flags = 0;
        /* one is dropped after submission, the other at completion */
        refcount_set(&req->refs, 2);
-       req->task = NULL;
+       req->task = current;
        req->result = 0;
 
        if (unlikely(req->opcode >= IORING_OP_LAST))