kernel/linux.git - Linux kernel stable tree (mirror)

Age	Commit message (Collapse)	Author	Files	Lines
2022-07-25	io_uring: move io_uring_task (tctx) helpers into its own file	Jens Axboe	1	-0/+4
	Signed-off-by: Jens Axboe <axboe@kernel.dk>
2022-07-25	io_uring: move SQPOLL related handling into its own file	Jens Axboe	1	-0/+34
	Signed-off-by: Jens Axboe <axboe@kernel.dk>
2022-07-25	io_uring: move timeout opcodes and handling into its own file	Jens Axboe	1	-1/+12
	Signed-off-by: Jens Axboe <axboe@kernel.dk>
2022-07-25	io_uring: split network related opcodes into its own file	Jens Axboe	1	-0/+22
	While at it, convert the handlers to just use io_eopnotsupp_prep() if CONFIG_NET isn't set. Signed-off-by: Jens Axboe <axboe@kernel.dk>
2022-07-25	io_uring: move uring_cmd handling to its own file	Jens Axboe	1	-0/+9
	Signed-off-by: Jens Axboe <axboe@kernel.dk>
2022-07-25	io_uring: split out open/close operations	Jens Axboe	1	-0/+32
	Signed-off-by: Jens Axboe <axboe@kernel.dk>
2022-07-25	io_uring: split out splice related operations	Jens Axboe	1	-0/+19
	This splits out splice and tee support. Signed-off-by: Jens Axboe <axboe@kernel.dk>
2022-07-25	io_uring: handle completions in the core	Jens Axboe	1	-0/+5
	Normally request handlers complete requests themselves, if they don't return an error. For the latter case, the core will complete it for them. This is unhandy for pushing opcode handlers further out, as we don't want a bunch of inline completion code and we don't want to make the completion path slower than it is now. Let the core handle any completion, unless the handler explicitly asks us not to. Signed-off-by: Jens Axboe <axboe@kernel.dk>
2022-07-25	io_uring: set completion results upfront	Jens Axboe	1	-0/+13
	Signed-off-by: Jens Axboe <axboe@kernel.dk>