From 03d89a2de25bbc5c77e61a0cf77663978c4b6ea7 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 5 Nov 2021 17:20:54 -0600 Subject: io_uring: support for user allocated memory for rings/sqes Currently io_uring applications must call mmap(2) twice to map the rings themselves, and the sqes array. This works fine, but it does not support using huge pages to back the rings/sqes. Provide a way for the application to pass in pre-allocated memory for the rings/sqes, which can then suitably be allocated from shmfs or via mmap to get huge page support. Particularly for larger rings, this reduces the TLBs needed. If an application wishes to take advantage of that, it must pre-allocate the memory needed for the sq/cq ring, and the sqes. The former must be passed in via the io_uring_params->cq_off.user_data field, while the latter is passed in via the io_uring_params->sq_off.user_data field. Then it must set IORING_SETUP_NO_MMAP in the io_uring_params->flags field, and io_uring will then map the existing memory into the kernel for shared use. The application must not call mmap(2) to map rings as it otherwise would have, that will now fail with -EINVAL if this setup flag was used. The pages used for the rings and sqes must be contigious. The intent here is clearly that huge pages should be used, otherwise the normal setup procedure works fine as-is. The application may use one huge page for both the rings and sqes. Outside of those initialization changes, everything works like it did before. Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 0716cb17e436..2edba9a274de 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -173,6 +173,11 @@ enum { */ #define IORING_SETUP_DEFER_TASKRUN (1U << 13) +/* + * Application provides the memory for the rings + */ +#define IORING_SETUP_NO_MMAP (1U << 14) + enum io_uring_op { IORING_OP_NOP, IORING_OP_READV, @@ -406,7 +411,7 @@ struct io_sqring_offsets { __u32 dropped; __u32 array; __u32 resv1; - __u64 resv2; + __u64 user_addr; }; /* @@ -425,7 +430,7 @@ struct io_cqring_offsets { __u32 cqes; __u32 flags; __u32 resv1; - __u64 resv2; + __u64 user_addr; }; /* -- cgit v1.2.3 From 6e76ac595855db27bbdaef337173294a6fd6eb2c Mon Sep 17 00:00:00 2001 From: Josh Triplett Date: Sat, 29 Apr 2023 01:40:30 +0900 Subject: io_uring: Add io_uring_setup flag to pre-register ring fd and never install it With IORING_REGISTER_USE_REGISTERED_RING, an application can register the ring fd and use it via registered index rather than installed fd. This allows using a registered ring for everything *except* the initial mmap. With IORING_SETUP_NO_MMAP, io_uring_setup uses buffers allocated by the user, rather than requiring a subsequent mmap. The combination of the two allows a user to operate *entirely* via a registered ring fd, making it unnecessary to ever install the fd in the first place. So, add a flag IORING_SETUP_REGISTERED_FD_ONLY to make io_uring_setup register the fd and return a registered index, without installing the fd. This allows an application to avoid touching the fd table at all, and allows a library to never even momentarily install a file descriptor. This splits out an io_ring_add_registered_file helper from io_ring_add_registered_fd, for use by io_uring_setup. Signed-off-by: Josh Triplett Link: https://lore.kernel.org/r/bc8f431bada371c183b95a83399628b605e978a3.1682699803.git.josh@joshtriplett.org Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 2edba9a274de..f222d263bc55 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -178,6 +178,13 @@ enum { */ #define IORING_SETUP_NO_MMAP (1U << 14) +/* + * Register the ring fd in itself for use with + * IORING_REGISTER_USE_REGISTERED_RING; return a registered fd index rather + * than an fd. + */ +#define IORING_SETUP_REGISTERED_FD_ONLY (1U << 15) + enum io_uring_op { IORING_OP_NOP, IORING_OP_READV, -- cgit v1.2.3