From e7a6c00dc77aedf27a601738ea509f1caea6d673 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 4 Mar 2022 08:22:22 -0700 Subject: io_uring: add support for registering ring file descriptors Lots of workloads use multiple threads, in which case the file table is shared between them. This makes getting and putting the ring file descriptor for each io_uring_enter(2) system call more expensive, as it involves an atomic get and put for each call. Similarly to how we allow registering normal file descriptors to avoid this overhead, add support for an io_uring_register(2) API that allows to register the ring fds themselves: 1) IORING_REGISTER_RING_FDS - takes an array of io_uring_rsrc_update structs, and registers them with the task. 2) IORING_UNREGISTER_RING_FDS - takes an array of io_uring_src_update structs, and unregisters them. When a ring fd is registered, it is internally represented by an offset. This offset is returned to the application, and the application then uses this offset and sets IORING_ENTER_REGISTERED_RING for the io_uring_enter(2) system call. This works just like using a registered file descriptor, rather than a real one, in an SQE, where IOSQE_FIXED_FILE gets set to tell io_uring that we're using an internal offset/descriptor rather than a real file descriptor. In initial testing, this provides a nice bump in performance for threaded applications in real world cases where the batch count (eg number of requests submitted per io_uring_enter(2) invocation) is low. In a microbenchmark, submitting NOP requests, we see the following increases in performance: Requests per syscall Baseline Registered Increase ---------------------------------------------------------------- 1 ~7030K ~8080K +15% 2 ~13120K ~14800K +13% 4 ~22740K ~25300K +11% Co-developed-by: Xiaoguang Wang Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 787f491f0d2a..42b2fe84dbcd 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -257,10 +257,11 @@ struct io_cqring_offsets { /* * io_uring_enter(2) flags */ -#define IORING_ENTER_GETEVENTS (1U << 0) -#define IORING_ENTER_SQ_WAKEUP (1U << 1) -#define IORING_ENTER_SQ_WAIT (1U << 2) -#define IORING_ENTER_EXT_ARG (1U << 3) +#define IORING_ENTER_GETEVENTS (1U << 0) +#define IORING_ENTER_SQ_WAKEUP (1U << 1) +#define IORING_ENTER_SQ_WAIT (1U << 2) +#define IORING_ENTER_EXT_ARG (1U << 3) +#define IORING_ENTER_REGISTERED_RING (1U << 4) /* * Passed in for io_uring_setup(2). Copied back with updated info on success @@ -325,6 +326,10 @@ enum { /* set/get max number of io-wq workers */ IORING_REGISTER_IOWQ_MAX_WORKERS = 19, + /* register/unregister io_uring fd with the ring */ + IORING_REGISTER_RING_FDS = 20, + IORING_UNREGISTER_RING_FDS = 21, + /* this goes last */ IORING_REGISTER_LAST }; -- cgit v1.2.3 From 4f57f06ce2186c31c3da52386125dc57b1cd6f96 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 10 Mar 2022 06:27:26 -0700 Subject: io_uring: add support for IORING_OP_MSG_RING command This adds support for IORING_OP_MSG_RING, which allows an SQE to signal another ring. That allows either waking up someone waiting on the ring, or even passing a 64-bit value via the user_data field in the CQE. sqe->fd must contain the fd of a ring that should receive the CQE. sqe->off will be propagated to the cqe->user_data on the target ring, and sqe->len will be propagated to cqe->res. The results CQE will have IORING_CQE_F_MSG set in its flags, to indicate that this CQE was generated from a messaging request rather than a SQE issued locally on that ring. This effectively allows passing a 64-bit and a 32-bit quantify between the two rings. This request type has the following request specific error cases: - -EBADFD. Set if the sqe->fd doesn't point to a file descriptor that is of the io_uring type. - -EOVERFLOW. Set if we were not able to deliver a request to the target ring. Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 42b2fe84dbcd..8bd4bfdd9a89 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -143,6 +143,7 @@ enum { IORING_OP_MKDIRAT, IORING_OP_SYMLINKAT, IORING_OP_LINKAT, + IORING_OP_MSG_RING, /* this goes last, obviously */ IORING_OP_LAST, @@ -199,9 +200,11 @@ struct io_uring_cqe { * * IORING_CQE_F_BUFFER If set, the upper 16 bits are the buffer ID * IORING_CQE_F_MORE If set, parent SQE will generate more CQE entries + * IORING_CQE_F_MSG If set, CQE was generated with IORING_OP_MSG_RING */ #define IORING_CQE_F_BUFFER (1U << 0) #define IORING_CQE_F_MORE (1U << 1) +#define IORING_CQE_F_MSG (1U << 2) enum { IORING_CQE_BUFFER_SHIFT = 16, -- cgit v1.2.3 From bcbb7bf6ccde7cb969a5642879832bc84ebf06a3 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 10 Mar 2022 12:59:35 -0700 Subject: io_uring: allow submissions to continue on error By default, io_uring will stop submitting a batch of requests if we run into an error submitting a request. This isn't strictly necessary, as the error result is passed out-of-band via a CQE anyway. And it can be a bit confusing for some applications. Provide a way to setup a ring that will continue submitting on error, when the error CQE has been posted. There's still one case that will break out of submission. If we fail allocating a request, then we'll still return -ENOMEM. We could in theory post a CQE for that condition too even if we never got a request. Leave that for a potential followup. Reported-by: Dylan Yudaken Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 8bd4bfdd9a89..d2be4eb22008 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -101,6 +101,7 @@ enum { #define IORING_SETUP_CLAMP (1U << 4) /* clamp SQ/CQ ring sizes */ #define IORING_SETUP_ATTACH_WQ (1U << 5) /* attach to existing wq */ #define IORING_SETUP_R_DISABLED (1U << 6) /* start with ring disabled */ +#define IORING_SETUP_SUBMIT_ALL (1U << 7) /* continue submit on error */ enum { IORING_OP_NOP, -- cgit v1.2.3