The flow in set_task_ioprio can be simplified by simply open coding
create_task_io_context, which removes a refcount roundtrip on the I/O
context.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jan Kara <jack@suse.cz>
Link: https://lore.kernel.org/r/20211209063131.18537-10-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
struct io_context *ioc;
task_unlock(task);
- ioc = create_task_io_context(task, GFP_ATOMIC, NUMA_NO_NODE);
- if (ioc) {
- ioc->ioprio = ioprio;
- put_io_context(ioc);
+
+ ioc = alloc_io_context(GFP_ATOMIC, NUMA_NO_NODE);
+ if (!ioc)
+ return -ENOMEM;
+
+ task_lock(task);
+ if (task->io_context || (task->flags & PF_EXITING)) {
+ kmem_cache_free(iocontext_cachep, ioc);
+ ioc = task->io_context;
+ } else {
+ task->io_context = ioc;
}
- return 0;
}
task->io_context->ioprio = ioprio;
task_unlock(task);