From 6224590d242fc8c6b26941328e02a40b4384949b Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Sat, 2 Oct 2021 19:36:14 +0100 Subject: io_uring: add flag to not fail link after timeout For some reason non-off IORING_OP_TIMEOUT always fails links, it's pretty inconvenient and unnecessary limits chaining after it to hard linking, which is far from ideal, e.g. doesn't pair well with timeout cancellation. Add a flag forcing it to not fail links on -ETIME. Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/17c7ec0fb7a6113cc6be8cdaedcada0ba836ac0e.1633199723.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi/linux/io_uring.h') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index b270a07b285e..c45b5e9a9387 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -158,6 +158,7 @@ enum { #define IORING_TIMEOUT_BOOTTIME (1U << 2) #define IORING_TIMEOUT_REALTIME (1U << 3) #define IORING_LINK_TIMEOUT_UPDATE (1U << 4) +#define IORING_TIMEOUT_ETIME_SUCCESS (1U << 5) #define IORING_TIMEOUT_CLOCK_MASK (IORING_TIMEOUT_BOOTTIME | IORING_TIMEOUT_REALTIME) #define IORING_TIMEOUT_UPDATE_MASK (IORING_TIMEOUT_UPDATE | IORING_LINK_TIMEOUT_UPDATE) /* -- cgit v1.2.3 From 04c76b41ca974b508522831441dd7e5b1b59cbb0 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Wed, 10 Nov 2021 15:49:32 +0000 Subject: io_uring: add option to skip CQE posting Emitting a CQE is expensive from the kernel perspective. Often, it's also not convenient for the userspace, spends some cycles on processing and just complicates the logic. A similar problems goes for linked requests, where we post an CQE for each request in the link. Introduce a new flags, IOSQE_CQE_SKIP_SUCCESS, trying to help with it. When set and a request completed successfully, it won't generate a CQE. When fails, it produces an CQE, but all following linked requests will be CQE-less, regardless whether they have IOSQE_CQE_SKIP_SUCCESS or not. The notion of "fail" is the same as for link failing-cancellation, where it's opcode dependent, and _usually_ result >= 0 is a success, but not always. Linked timeouts are a bit special. When the requests it's linked to was not attempted to be executed, e.g. failing linked requests, it follows the description above. Otherwise, whether a linked timeout will post a completion or not solely depends on IOSQE_CQE_SKIP_SUCCESS of that linked timeout request. Linked timeout never "fail" during execution, so for them it's unconditional. It's expected for users to not really care about the result of it but rely solely on the result of the master request. Another reason for such a treatment is that it's racy, and the timeout callback may be running awhile the master request posts its completion. use case 1: If one doesn't care about results of some requests, e.g. normal timeouts, just set IOSQE_CQE_SKIP_SUCCESS. Error result will still be posted and need to be handled. use case 2: Set IOSQE_CQE_SKIP_SUCCESS for all requests of a link but the last, and it'll post a completion only for the last one if everything goes right, otherwise there will be one only one CQE for the first failed request. Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/0220fbe06f7cf99e6fc71b4297bb1cb6c0e89c2c.1636559119.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/uapi/linux/io_uring.h') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index c45b5e9a9387..787f491f0d2a 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -70,6 +70,7 @@ enum { IOSQE_IO_HARDLINK_BIT, IOSQE_ASYNC_BIT, IOSQE_BUFFER_SELECT_BIT, + IOSQE_CQE_SKIP_SUCCESS_BIT, }; /* @@ -87,6 +88,8 @@ enum { #define IOSQE_ASYNC (1U << IOSQE_ASYNC_BIT) /* select buffer from sqe->buf_group */ #define IOSQE_BUFFER_SELECT (1U << IOSQE_BUFFER_SELECT_BIT) +/* don't post CQE if request succeeded */ +#define IOSQE_CQE_SKIP_SUCCESS (1U << IOSQE_CQE_SKIP_SUCCESS_BIT) /* * io_uring_setup() flags @@ -289,6 +292,7 @@ struct io_uring_params { #define IORING_FEAT_EXT_ARG (1U << 8) #define IORING_FEAT_NATIVE_WORKERS (1U << 9) #define IORING_FEAT_RSRC_TAGS (1U << 10) +#define IORING_FEAT_CQE_SKIP (1U << 11) /* * io_uring_register(2) opcodes and arguments -- cgit v1.2.3