|
| 1 | +.. SPDX-License-Identifier: GPL-2.0 |
| 2 | +
|
| 3 | +===================== |
| 4 | +io_uring zero copy Rx |
| 5 | +===================== |
| 6 | + |
| 7 | +Introduction |
| 8 | +============ |
| 9 | + |
| 10 | +io_uring zero copy Rx (ZC Rx) is a feature that removes kernel-to-user copy on |
| 11 | +the network receive path, allowing packet data to be received directly into |
| 12 | +userspace memory. This feature is different to TCP_ZEROCOPY_RECEIVE in that |
| 13 | +there are no strict alignment requirements and no need to mmap()/munmap(). |
| 14 | +Compared to kernel bypass solutions such as e.g. DPDK, the packet headers are |
| 15 | +processed by the kernel TCP stack as normal. |
| 16 | + |
| 17 | +NIC HW Requirements |
| 18 | +=================== |
| 19 | + |
| 20 | +Several NIC HW features are required for io_uring ZC Rx to work. For now the |
| 21 | +kernel API does not configure the NIC and it must be done by the user. |
| 22 | + |
| 23 | +Header/data split |
| 24 | +----------------- |
| 25 | + |
| 26 | +Required to split packets at the L4 boundary into a header and a payload. |
| 27 | +Headers are received into kernel memory as normal and processed by the TCP |
| 28 | +stack as normal. Payloads are received into userspace memory directly. |
| 29 | + |
| 30 | +Flow steering |
| 31 | +------------- |
| 32 | + |
| 33 | +Specific HW Rx queues are configured for this feature, but modern NICs |
| 34 | +typically distribute flows across all HW Rx queues. Flow steering is required |
| 35 | +to ensure that only desired flows are directed towards HW queues that are |
| 36 | +configured for io_uring ZC Rx. |
| 37 | + |
| 38 | +RSS |
| 39 | +--- |
| 40 | + |
| 41 | +In addition to flow steering above, RSS is required to steer all other non-zero |
| 42 | +copy flows away from queues that are configured for io_uring ZC Rx. |
| 43 | + |
| 44 | +Usage |
| 45 | +===== |
| 46 | + |
| 47 | +Setup NIC |
| 48 | +--------- |
| 49 | + |
| 50 | +Must be done out of band for now. |
| 51 | + |
| 52 | +Ensure there are at least two queues:: |
| 53 | + |
| 54 | + ethtool -L eth0 combined 2 |
| 55 | + |
| 56 | +Enable header/data split:: |
| 57 | + |
| 58 | + ethtool -G eth0 tcp-data-split on |
| 59 | + |
| 60 | +Carve out half of the HW Rx queues for zero copy using RSS:: |
| 61 | + |
| 62 | + ethtool -X eth0 equal 1 |
| 63 | + |
| 64 | +Set up flow steering, bearing in mind that queues are 0-indexed:: |
| 65 | + |
| 66 | + ethtool -N eth0 flow-type tcp6 ... action 1 |
| 67 | + |
| 68 | +Setup io_uring |
| 69 | +-------------- |
| 70 | + |
| 71 | +This section describes the low level io_uring kernel API. Please refer to |
| 72 | +liburing documentation for how to use the higher level API. |
| 73 | + |
| 74 | +Create an io_uring instance with the following required setup flags:: |
| 75 | + |
| 76 | + IORING_SETUP_SINGLE_ISSUER |
| 77 | + IORING_SETUP_DEFER_TASKRUN |
| 78 | + IORING_SETUP_CQE32 |
| 79 | + |
| 80 | +Create memory area |
| 81 | +------------------ |
| 82 | + |
| 83 | +Allocate userspace memory area for receiving zero copy data:: |
| 84 | + |
| 85 | + void *area_ptr = mmap(NULL, area_size, |
| 86 | + PROT_READ | PROT_WRITE, |
| 87 | + MAP_ANONYMOUS | MAP_PRIVATE, |
| 88 | + 0, 0); |
| 89 | + |
| 90 | +Create refill ring |
| 91 | +------------------ |
| 92 | + |
| 93 | +Allocate memory for a shared ringbuf used for returning consumed buffers:: |
| 94 | + |
| 95 | + void *ring_ptr = mmap(NULL, ring_size, |
| 96 | + PROT_READ | PROT_WRITE, |
| 97 | + MAP_ANONYMOUS | MAP_PRIVATE, |
| 98 | + 0, 0); |
| 99 | + |
| 100 | +This refill ring consists of some space for the header, followed by an array of |
| 101 | +``struct io_uring_zcrx_rqe``:: |
| 102 | + |
| 103 | + size_t rq_entries = 4096; |
| 104 | + size_t ring_size = rq_entries * sizeof(struct io_uring_zcrx_rqe) + PAGE_SIZE; |
| 105 | + /* align to page size */ |
| 106 | + ring_size = (ring_size + (PAGE_SIZE - 1)) & ~(PAGE_SIZE - 1); |
| 107 | + |
| 108 | +Register ZC Rx |
| 109 | +-------------- |
| 110 | + |
| 111 | +Fill in registration structs:: |
| 112 | + |
| 113 | + struct io_uring_zcrx_area_reg area_reg = { |
| 114 | + .addr = (__u64)(unsigned long)area_ptr, |
| 115 | + .len = area_size, |
| 116 | + .flags = 0, |
| 117 | + }; |
| 118 | + |
| 119 | + struct io_uring_region_desc region_reg = { |
| 120 | + .user_addr = (__u64)(unsigned long)ring_ptr, |
| 121 | + .size = ring_size, |
| 122 | + .flags = IORING_MEM_REGION_TYPE_USER, |
| 123 | + }; |
| 124 | + |
| 125 | + struct io_uring_zcrx_ifq_reg reg = { |
| 126 | + .if_idx = if_nametoindex("eth0"), |
| 127 | + /* this is the HW queue with desired flow steered into it */ |
| 128 | + .if_rxq = 1, |
| 129 | + .rq_entries = rq_entries, |
| 130 | + .area_ptr = (__u64)(unsigned long)&area_reg, |
| 131 | + .region_ptr = (__u64)(unsigned long)®ion_reg, |
| 132 | + }; |
| 133 | + |
| 134 | +Register with kernel:: |
| 135 | + |
| 136 | + io_uring_register_ifq(ring, ®); |
| 137 | + |
| 138 | +Map refill ring |
| 139 | +--------------- |
| 140 | + |
| 141 | +The kernel fills in fields for the refill ring in the registration ``struct |
| 142 | +io_uring_zcrx_ifq_reg``. Map it into userspace:: |
| 143 | + |
| 144 | + struct io_uring_zcrx_rq refill_ring; |
| 145 | + |
| 146 | + refill_ring.khead = (unsigned *)((char *)ring_ptr + reg.offsets.head); |
| 147 | + refill_ring.khead = (unsigned *)((char *)ring_ptr + reg.offsets.tail); |
| 148 | + refill_ring.rqes = |
| 149 | + (struct io_uring_zcrx_rqe *)((char *)ring_ptr + reg.offsets.rqes); |
| 150 | + refill_ring.rq_tail = 0; |
| 151 | + refill_ring.ring_ptr = ring_ptr; |
| 152 | +
|
| 153 | +Receiving data |
| 154 | +-------------- |
| 155 | + |
| 156 | +Prepare a zero copy recv request:: |
| 157 | + |
| 158 | + struct io_uring_sqe *sqe; |
| 159 | + |
| 160 | + sqe = io_uring_get_sqe(ring); |
| 161 | + io_uring_prep_rw(IORING_OP_RECV_ZC, sqe, fd, NULL, 0, 0); |
| 162 | + sqe->ioprio |= IORING_RECV_MULTISHOT; |
| 163 | + |
| 164 | +Now, submit and wait:: |
| 165 | + |
| 166 | + io_uring_submit_and_wait(ring, 1); |
| 167 | + |
| 168 | +Finally, process completions:: |
| 169 | + |
| 170 | + struct io_uring_cqe *cqe; |
| 171 | + unsigned int count = 0; |
| 172 | + unsigned int head; |
| 173 | + |
| 174 | + io_uring_for_each_cqe(ring, head, cqe) { |
| 175 | + struct io_uring_zcrx_cqe *rcqe = (struct io_uring_zcrx_cqe *)(cqe + 1); |
| 176 | + |
| 177 | + unsigned long mask = (1ULL << IORING_ZCRX_AREA_SHIFT) - 1; |
| 178 | + unsigned char *data = area_ptr + (rcqe->off & mask); |
| 179 | + /* do something with the data */ |
| 180 | + |
| 181 | + count++; |
| 182 | + } |
| 183 | + io_uring_cq_advance(ring, count); |
| 184 | + |
| 185 | +Recycling buffers |
| 186 | +----------------- |
| 187 | + |
| 188 | +Return buffers back to the kernel to be used again:: |
| 189 | + |
| 190 | + struct io_uring_zcrx_rqe *rqe; |
| 191 | + unsigned mask = refill_ring.ring_entries - 1; |
| 192 | + rqe = &refill_ring.rqes[refill_ring.rq_tail & mask]; |
| 193 | + |
| 194 | + unsigned long area_offset = rcqe->off & ~IORING_ZCRX_AREA_MASK; |
| 195 | + rqe->off = area_offset | area_reg.rq_area_token; |
| 196 | + rqe->len = cqe->res; |
| 197 | + IO_URING_WRITE_ONCE(*refill_ring.ktail, ++refill_ring.rq_tail); |
| 198 | + |
| 199 | +Testing |
| 200 | +======= |
| 201 | + |
| 202 | +See ``tools/testing/selftests/drivers/net/hw/iou-zcrx.c`` |
0 commit comments