From 6f377873cb23905009759b7366b9fe85c2a6ff37 Mon Sep 17 00:00:00 2001 From: David Wei Date: Fri, 14 Feb 2025 16:09:36 -0800 Subject: io_uring/zcrx: add interface queue and refill queue Add a new object called an interface queue (ifq) that represents a net rx queue that has been configured for zero copy. Each ifq is registered using a new registration opcode IORING_REGISTER_ZCRX_IFQ. The refill queue is allocated by the kernel and mapped by userspace using a new offset IORING_OFF_RQ_RING, in a similar fashion to the main SQ/CQ. It is used by userspace to return buffers that it is done with, which will then be re-used by the netdev again. The main CQ ring is used to notify userspace of received data by using the upper 16 bytes of a big CQE as a new struct io_uring_zcrx_cqe. Each entry contains the offset + len to the data. For now, each io_uring instance only has a single ifq. Reviewed-by: Jens Axboe Signed-off-by: David Wei Acked-by: Jakub Kicinski Link: https://lore.kernel.org/r/20250215000947.789731-2-dw@davidwei.uk Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 43 ++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 42 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index e11c82638527..6a1632d0fba1 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -639,7 +639,8 @@ enum io_uring_register_op { /* send MSG_RING without having a ring */ IORING_REGISTER_SEND_MSG_RING = 31, - /* 32 reserved for zc rx */ + /* register a netdev hw rx queue for zerocopy */ + IORING_REGISTER_ZCRX_IFQ = 32, /* resize CQ ring */ IORING_REGISTER_RESIZE_RINGS = 33, @@ -956,6 +957,46 @@ enum io_uring_socket_op { SOCKET_URING_OP_SETSOCKOPT, }; +/* Zero copy receive refill queue entry */ +struct io_uring_zcrx_rqe { + __u64 off; + __u32 len; + __u32 __pad; +}; + +struct io_uring_zcrx_cqe { + __u64 off; + __u64 __pad; +}; + +/* The bit from which area id is encoded into offsets */ +#define IORING_ZCRX_AREA_SHIFT 48 +#define IORING_ZCRX_AREA_MASK (~(((__u64)1 << IORING_ZCRX_AREA_SHIFT) - 1)) + +struct io_uring_zcrx_offsets { + __u32 head; + __u32 tail; + __u32 rqes; + __u32 __resv2; + __u64 __resv[2]; +}; + +/* + * Argument for IORING_REGISTER_ZCRX_IFQ + */ +struct io_uring_zcrx_ifq_reg { + __u32 if_idx; + __u32 if_rxq; + __u32 rq_entries; + __u32 flags; + + __u64 area_ptr; /* pointer to struct io_uring_zcrx_area_reg */ + __u64 region_ptr; /* struct io_uring_region_desc * */ + + struct io_uring_zcrx_offsets offsets; + __u64 __resv[4]; +}; + #ifdef __cplusplus } #endif -- cgit v1.2.3 From cf96310c5f9a0d542db99c887742811425ba2ec0 Mon Sep 17 00:00:00 2001 From: David Wei Date: Fri, 14 Feb 2025 16:09:37 -0800 Subject: io_uring/zcrx: add io_zcrx_area Add io_zcrx_area that represents a region of userspace memory that is used for zero copy. During ifq registration, userspace passes in the uaddr and len of userspace memory, which is then pinned by the kernel. Each net_iov is mapped to one of these pages. The freelist is a spinlock protected list that keeps track of all the net_iovs/pages that aren't used. For now, there is only one area per ifq and area registration happens implicitly as part of ifq registration. There is no API for adding/removing areas yet. The struct for area registration is there for future extensibility once we support multiple areas and TCP devmem. Reviewed-by: Jens Axboe Signed-off-by: Pavel Begunkov Signed-off-by: David Wei Acked-by: Jakub Kicinski Link: https://lore.kernel.org/r/20250215000947.789731-3-dw@davidwei.uk Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 6a1632d0fba1..44844707d327 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -981,6 +981,15 @@ struct io_uring_zcrx_offsets { __u64 __resv[2]; }; +struct io_uring_zcrx_area_reg { + __u64 addr; + __u64 len; + __u64 rq_area_token; + __u32 flags; + __u32 __resv1; + __u64 __resv2[2]; +}; + /* * Argument for IORING_REGISTER_ZCRX_IFQ */ -- cgit v1.2.3 From 11ed914bbf948c4a37248f2876973ac18014056d Mon Sep 17 00:00:00 2001 From: David Wei Date: Fri, 14 Feb 2025 16:09:41 -0800 Subject: io_uring/zcrx: add io_recvzc request Add io_uring opcode OP_RECV_ZC for doing zero copy reads out of a socket. Only the connection should be land on the specific rx queue set up for zero copy, and the socket must be handled by the io_uring instance that the rx queue was registered for zero copy with. That's because neither net_iovs / buffers from our queue can be read by outside applications, nor zero copy is possible if traffic for the zero copy connection goes to another queue. This coordination is outside of the scope of this patch series. Also, any traffic directed to the zero copy enabled queue is immediately visible to the application, which is why CAP_NET_ADMIN is required at the registration step. Of course, no data is actually read out of the socket, it has already been copied by the netdev into userspace memory via DMA. OP_RECV_ZC reads skbs out of the socket and checks that its frags are indeed net_iovs that belong to io_uring. A cqe is queued for each one of these frags. Recall that each cqe is a big cqe, with the top half being an io_uring_zcrx_cqe. The cqe res field contains the len or error. The lower IORING_ZCRX_AREA_SHIFT bits of the struct io_uring_zcrx_cqe::off field contain the offset relative to the start of the zero copy area. The upper part of the off field is trivially zero, and will be used to carry the area id. For now, there is no limit as to how much work each OP_RECV_ZC request does. It will attempt to drain a socket of all available data. This request always operates in multishot mode. Reviewed-by: Jens Axboe Signed-off-by: David Wei Acked-by: Jakub Kicinski Link: https://lore.kernel.org/r/20250215000947.789731-7-dw@davidwei.uk Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 44844707d327..05d6255b0f6a 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -87,6 +87,7 @@ struct io_uring_sqe { union { __s32 splice_fd_in; __u32 file_index; + __u32 zcrx_ifq_idx; __u32 optlen; struct { __u16 addr_len; @@ -278,6 +279,7 @@ enum io_uring_op { IORING_OP_FTRUNCATE, IORING_OP_BIND, IORING_OP_LISTEN, + IORING_OP_RECV_ZC, /* this goes last, obviously */ IORING_OP_LAST, -- cgit v1.2.3