io_uring: don't fail overflow on in_idle

As CQE overflows are now untied from requests and so don't hold any
ref, we don't need to handle exiting/exec'ing cases there anymore.
Moreover, it's much nicer in regards to userspace to save overflowed
CQEs whenever possible, so remove failing on in_idle.

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/d873b7dab75c7f3039ead9628a745bea01f2cfd2.1618278933.git.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 1627d69..3632b5a 100644 (file)
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -1513,32 +1513,28 @@ static bool io_cqring_event_overflow(struct io_kiocb *req, long res,
                                     unsigned int cflags)
 {
        struct io_ring_ctx *ctx = req->ctx;
+       struct io_overflow_cqe *ocqe;
 
-       if (!atomic_read(&req->task->io_uring->in_idle)) {
-               struct io_overflow_cqe *ocqe;
-
-               ocqe = kmalloc(sizeof(*ocqe), GFP_ATOMIC | __GFP_ACCOUNT);
-               if (!ocqe)
-                       goto overflow;
-               if (list_empty(&ctx->cq_overflow_list)) {
-                       set_bit(0, &ctx->sq_check_overflow);
-                       set_bit(0, &ctx->cq_check_overflow);
-                       ctx->rings->sq_flags |= IORING_SQ_CQ_OVERFLOW;
-               }
-               ocqe->cqe.user_data = req->user_data;
-               ocqe->cqe.res = res;
-               ocqe->cqe.flags = cflags;
-               list_add_tail(&ocqe->list, &ctx->cq_overflow_list);
-               return true;
+       ocqe = kmalloc(sizeof(*ocqe), GFP_ATOMIC | __GFP_ACCOUNT);
+       if (!ocqe) {
+               /*
+                * If we're in ring overflow flush mode, or in task cancel mode,
+                * or cannot allocate an overflow entry, then we need to drop it
+                * on the floor.
+                */
+               WRITE_ONCE(ctx->rings->cq_overflow, ++ctx->cached_cq_overflow);
+               return false;
        }
-overflow:
-       /*
-        * If we're in ring overflow flush mode, or in task cancel mode,
-        * or cannot allocate an overflow entry, then we need to drop it
-        * on the floor.
-        */
-       WRITE_ONCE(ctx->rings->cq_overflow, ++ctx->cached_cq_overflow);
-       return false;
+       if (list_empty(&ctx->cq_overflow_list)) {
+               set_bit(0, &ctx->sq_check_overflow);
+               set_bit(0, &ctx->cq_check_overflow);
+               ctx->rings->sq_flags |= IORING_SQ_CQ_OVERFLOW;
+       }
+       ocqe->cqe.user_data = req->user_data;
+       ocqe->cqe.res = res;
+       ocqe->cqe.flags = cflags;
+       list_add_tail(&ocqe->list, &ctx->cq_overflow_list);
+       return true;
 }
 
 static inline bool __io_cqring_fill_event(struct io_kiocb *req, long res,