io_uring: don't check overflow flush failures

The only way to fail overflowed CQEs flush is for CQ to be fully packed.
There is one place checking for flush failures, i.e. io_cqring_wait(),
but we limit the number to be waited for by the CQ size, so getting a
failure automatically means that we're done with waiting.

Don't check for failures, rarely but they might spuriously fail CQ
waiting with -EBUSY.

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/6b720a45c03345655517f8202cbd0bece2848fb2.1670384893.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>

diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index ecd78898dbd3c62a29f65770a9a3fcb122e2f7a5..ba5ef1e675c1c186ad8aa37ea35b92eb4a462a39 100644 (file)
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -618,13 +618,12 @@ static void io_cqring_overflow_kill(struct io_ring_ctx *ctx)
 }
 
 /* Returns true if there are no backlogged entries after the flush */
-static bool __io_cqring_overflow_flush(struct io_ring_ctx *ctx)
+static void __io_cqring_overflow_flush(struct io_ring_ctx *ctx)
 {
-       bool all_flushed;
        size_t cqe_size = sizeof(struct io_uring_cqe);
 
        if (__io_cqring_events(ctx) == ctx->cq_entries)
-               return false;
+               return;
 
        if (ctx->flags & IORING_SETUP_CQE32)
                cqe_size <<= 1;
@@ -643,30 +642,23 @@ static bool __io_cqring_overflow_flush(struct io_ring_ctx *ctx)
                kfree(ocqe);
        }
 
-       all_flushed = list_empty(&ctx->cq_overflow_list);
-       if (all_flushed) {
+       if (list_empty(&ctx->cq_overflow_list)) {
                clear_bit(IO_CHECK_CQ_OVERFLOW_BIT, &ctx->check_cq);
                atomic_andnot(IORING_SQ_CQ_OVERFLOW, &ctx->rings->sq_flags);
        }
-
        io_cq_unlock_post(ctx);
-       return all_flushed;
 }
 
-static bool io_cqring_overflow_flush(struct io_ring_ctx *ctx)
+static void io_cqring_overflow_flush(struct io_ring_ctx *ctx)
 {
-       bool ret = true;
-
        if (test_bit(IO_CHECK_CQ_OVERFLOW_BIT, &ctx->check_cq)) {
                /* iopoll syncs against uring_lock, not completion_lock */
                if (ctx->flags & IORING_SETUP_IOPOLL)
                        mutex_lock(&ctx->uring_lock);
-               ret = __io_cqring_overflow_flush(ctx);
+               __io_cqring_overflow_flush(ctx);
                if (ctx->flags & IORING_SETUP_IOPOLL)
                        mutex_unlock(&ctx->uring_lock);
        }
-
-       return ret;
 }
 
 void __io_put_task(struct task_struct *task, int nr)
@@ -2494,11 +2486,7 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events,
 
        trace_io_uring_cqring_wait(ctx, min_events);
        do {
-               /* if we can't even flush overflow, don't wait for more */
-               if (!io_cqring_overflow_flush(ctx)) {
-                       ret = -EBUSY;
-                       break;
-               }
+               io_cqring_overflow_flush(ctx);
                prepare_to_wait_exclusive(&ctx->cq_wait, &iowq.wq,
                                                TASK_INTERRUPTIBLE);
                ret = io_cqring_wait_schedule(ctx, &iowq, timeout);