Set the page pool memory provider for the rx queue configured for zero copy to io_uring. Then the rx queue is reset using netdev_rx_queue_restart() and netdev core + page pool will take care of filling the rx queue from the io_uring zero copy memory provider. For now, there is only one ifq so its destruction happens implicitly during io_uring cleanup. Reviewed-by: Jens Axboe <axboe@xxxxxxxxx> Signed-off-by: David Wei <dw@xxxxxxxxxxx> --- io_uring/zcrx.c | 83 ++++++++++++++++++++++++++++++++++++++++++++----- 1 file changed, 75 insertions(+), 8 deletions(-) diff --git a/io_uring/zcrx.c b/io_uring/zcrx.c index 1122c80502d6..756c78c0920e 100644 --- a/io_uring/zcrx.c +++ b/io_uring/zcrx.c @@ -10,11 +10,12 @@ #include <net/page_pool/helpers.h> #include <net/netlink.h> - -#include <trace/events/page_pool.h> +#include <net/netdev_rx_queue.h> #include <net/tcp.h> #include <net/rps.h> +#include <trace/events/page_pool.h> + #include <uapi/linux/io_uring.h> #include "io_uring.h" @@ -119,6 +120,65 @@ static void io_zcrx_get_niov_uref(struct net_iov *niov) atomic_inc(io_get_user_counter(niov)); } +static int io_open_zc_rxq(struct io_zcrx_ifq *ifq, unsigned ifq_idx) +{ + struct netdev_rx_queue *rxq; + struct net_device *dev = ifq->dev; + int ret; + + ASSERT_RTNL(); + + if (ifq_idx >= dev->num_rx_queues) + return -EINVAL; + ifq_idx = array_index_nospec(ifq_idx, dev->num_rx_queues); + + rxq = __netif_get_rx_queue(ifq->dev, ifq_idx); + if (rxq->mp_params.mp_priv) + return -EEXIST; + + ifq->if_rxq = ifq_idx; + rxq->mp_params.mp_ops = &io_uring_pp_zc_ops; + rxq->mp_params.mp_priv = ifq; + ret = netdev_rx_queue_restart(ifq->dev, ifq->if_rxq); + if (ret) + goto fail; + return 0; +fail: + rxq->mp_params.mp_ops = NULL; + rxq->mp_params.mp_priv = NULL; + ifq->if_rxq = -1; + return ret; +} + +static void io_close_zc_rxq(struct io_zcrx_ifq *ifq) +{ + struct netdev_rx_queue *rxq; + int err; + + if (ifq->if_rxq == -1) + return; + + rtnl_lock(); + if (WARN_ON_ONCE(ifq->if_rxq >= ifq->dev->num_rx_queues)) { + rtnl_unlock(); + return; + } + + rxq = __netif_get_rx_queue(ifq->dev, ifq->if_rxq); + + WARN_ON_ONCE(rxq->mp_params.mp_priv != ifq); + + rxq->mp_params.mp_ops = NULL; + rxq->mp_params.mp_priv = NULL; + + err = netdev_rx_queue_restart(ifq->dev, ifq->if_rxq); + if (err) + pr_devel("io_uring: can't restart a queue on zcrx close\n"); + + rtnl_unlock(); + ifq->if_rxq = -1; +} + static int io_allocate_rbuf_ring(struct io_zcrx_ifq *ifq, struct io_uring_zcrx_ifq_reg *reg, struct io_uring_region_desc *rd) @@ -255,6 +315,8 @@ static struct io_zcrx_ifq *io_zcrx_ifq_alloc(struct io_ring_ctx *ctx) static void io_zcrx_ifq_free(struct io_zcrx_ifq *ifq) { + io_close_zc_rxq(ifq); + if (ifq->area) io_zcrx_free_area(ifq->area); @@ -317,7 +379,6 @@ int io_register_zcrx_ifq(struct io_ring_ctx *ctx, goto err; ifq->rq_entries = reg.rq_entries; - ifq->if_rxq = reg.if_rxq; ret = -ENODEV; ifq->dev = netdev_get_by_index(current->nsproxy->net_ns, reg.if_idx, @@ -329,16 +390,20 @@ int io_register_zcrx_ifq(struct io_ring_ctx *ctx, if (ret) goto err; + rtnl_lock(); + ret = io_open_zc_rxq(ifq, reg.if_rxq); + rtnl_unlock(); + if (ret) + goto err; + reg.offsets.rqes = sizeof(struct io_uring); reg.offsets.head = offsetof(struct io_uring, head); reg.offsets.tail = offsetof(struct io_uring, tail); if (copy_to_user(arg, ®, sizeof(reg)) || - copy_to_user(u64_to_user_ptr(reg.region_ptr), &rd, sizeof(rd))) { - ret = -EFAULT; - goto err; - } - if (copy_to_user(u64_to_user_ptr(reg.area_ptr), &area, sizeof(area))) { + copy_to_user(u64_to_user_ptr(reg.region_ptr), &rd, sizeof(rd)) || + copy_to_user(u64_to_user_ptr(reg.area_ptr), &area, sizeof(area))) { + io_close_zc_rxq(ifq); ret = -EFAULT; goto err; } @@ -415,6 +480,8 @@ void io_shutdown_zcrx_ifqs(struct io_ring_ctx *ctx) if (ctx->ifq) io_zcrx_scrub(ctx->ifq); + + io_close_zc_rxq(ctx->ifq); } static inline u32 io_zcrx_rqring_entries(struct io_zcrx_ifq *ifq) -- 2.43.5