From aa00f67adc2c0d6439f81b5a81ff181377c47a7e Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 22 Oct 2024 13:47:00 -0600 Subject: io_uring: add support for fixed wait regions Generally applications have 1 or a few waits of waiting, yet they pass in a struct io_uring_getevents_arg every time. This needs to get copied and, in turn, the timeout value needs to get copied. Rather than do this for every invocation, allow the application to register a fixed set of wait regions that can simply be indexed when asking the kernel to wait on events. At ring setup time, the application can register a number of these wait regions and initialize region/index 0 upfront: struct io_uring_reg_wait *reg; reg = io_uring_setup_reg_wait(ring, nr_regions, &ret); /* set timeout and mark as set, sigmask/sigmask_sz as needed */ reg->ts.tv_sec = 0; reg->ts.tv_nsec = 100000; reg->flags = IORING_REG_WAIT_TS; where nr_regions >= 1 && nr_regions <= PAGE_SIZE / sizeof(*reg). The above initializes index 0, but 63 other regions can be initialized, if needed. Now, instead of doing: struct __kernel_timespec timeout = { .tv_nsec = 100000, }; io_uring_submit_and_wait_timeout(ring, &cqe, nr, &t, NULL); to wait for events for each submit_and_wait, or just wait, operation, it can just reference the above region at offset 0 and do: io_uring_submit_and_wait_reg(ring, &cqe, nr, 0); to achieve the same goal of waiting 100usec without needing to copy both struct io_uring_getevents_arg (24b) and struct __kernel_timeout (16b) for each invocation. Struct io_uring_reg_wait looks as follows: struct io_uring_reg_wait { struct __kernel_timespec ts; __u32 min_wait_usec; __u32 flags; __u64 sigmask; __u32 sigmask_sz; __u32 pad[3]; __u64 pad2[2]; }; embedding the timeout itself in the region, rather than passing it as a pointer as well. Note that the signal mask is still passed as a pointer, both for compatability reasons, but also because there doesn't seem to be a lot of high frequency waits scenarios that involve setting and resetting the signal mask for each wait. The application is free to modify any region before a wait call, or it can use keep multiple regions with different settings to avoid needing to modify the same one for wait calls. Up to a page size of regions is mapped by default, allowing PAGE_SIZE / 64 available regions for use. The registered region must fit within a page. On a 4kb page size system, that allows for 64 wait regions if a full page is used, as the size of struct io_uring_reg_wait is 64b. The region registered must be aligned to io_uring_reg_wait in size. It's valid to register less than 64 entries. In network performance testing with zero-copy, this reduced the time spent waiting on the TX side from 3.12% to 0.3% and the RX side from 4.4% to 0.3%. Wait regions are fixed for the lifetime of the ring - once registered, they are persistent until the ring is torn down. The regions support minimum wait timeout as well as the regular waits. Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 41 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 41 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 60b9c98595fa..65b7417c1b05 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -518,6 +518,7 @@ struct io_cqring_offsets { #define IORING_ENTER_EXT_ARG (1U << 3) #define IORING_ENTER_REGISTERED_RING (1U << 4) #define IORING_ENTER_ABS_TIMER (1U << 5) +#define IORING_ENTER_EXT_ARG_REG (1U << 6) /* * Passed in for io_uring_setup(2). Copied back with updated info on success @@ -620,6 +621,9 @@ enum io_uring_register_op { /* resize CQ ring */ IORING_REGISTER_RESIZE_RINGS = 33, + /* register fixed io_uring_reg_wait arguments */ + IORING_REGISTER_CQWAIT_REG = 34, + /* this goes last */ IORING_REGISTER_LAST, @@ -803,6 +807,43 @@ enum io_uring_register_restriction_op { IORING_RESTRICTION_LAST }; +enum { + IORING_REG_WAIT_TS = (1U << 0), +}; + +/* + * Argument for IORING_REGISTER_CQWAIT_REG, registering a region of + * struct io_uring_reg_wait that can be indexed when io_uring_enter(2) is + * called rather than pass in a wait argument structure separately. + */ +struct io_uring_cqwait_reg_arg { + __u32 flags; + __u32 struct_size; + __u32 nr_entries; + __u32 pad; + __u64 user_addr; + __u64 pad2[3]; +}; + +/* + * Argument for io_uring_enter(2) with + * IORING_GETEVENTS | IORING_ENTER_EXT_ARG_REG set, where the actual argument + * is an index into a previously registered fixed wait region described by + * the below structure. + */ +struct io_uring_reg_wait { + struct __kernel_timespec ts; + __u32 min_wait_usec; + __u32 flags; + __u64 sigmask; + __u32 sigmask_sz; + __u32 pad[3]; + __u64 pad2[2]; +}; + +/* + * Argument for io_uring_enter(2) with IORING_GETEVENTS | IORING_ENTER_EXT_ARG + */ struct io_uring_getevents_arg { __u64 sigmask; __u32 sigmask_sz; -- cgit v1.2.3