On 1/28/19 8:02 AM, Christoph Hellwig wrote:
>> struct {
>> spinlock_t completion_lock;
>> + unsigned poll_multi_file;
>
> This seems to be used as a bool.
Fixed
>> -static void __io_cqring_add_event(struct io_ring_ctx *ctx, u64 ki_user_data,
>> - long res, unsigned ev_flags)
>> +static void io_cqring_fill_event(struct io_ring_ctx *ctx, u64 ki_user_data,
>> + long res, unsigned ev_flags)
>> {
>> struct io_uring_cqe *cqe;
>>
>> @@ -206,9 +213,15 @@ static void __io_cqring_add_event(struct io_ring_ctx *ctx, u64 ki_user_data,
>> cqe->user_data = ki_user_data;
>> cqe->res = res;
>> cqe->flags = ev_flags;
>> - io_commit_cqring(ctx);
>> } else
>> ctx->cq_ring->overflow++;
>> +}
>
> Maybe we should have created this low-level helper already in the
> patch introducing the code?
I think that can go both ways. If we create it early, it'll just be a
pointless helper. Don't really care too much about this particular case.
--
Jens Axboe
