diff options
Diffstat (limited to 'drivers/net/ethernet/mellanox/mlx5/core')
11 files changed, 99 insertions, 20 deletions
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c index 79301d116667..eb2e1f2138e4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c @@ -25,18 +25,33 @@ u16 mlx5e_get_linear_rq_headroom(struct mlx5e_params *params, return headroom; } -u32 mlx5e_rx_get_linear_frag_sz(struct mlx5e_params *params, - struct mlx5e_xsk_param *xsk) +u32 mlx5e_rx_get_min_frag_sz(struct mlx5e_params *params, + struct mlx5e_xsk_param *xsk) { u32 hw_mtu = MLX5E_SW2HW_MTU(params, params->sw_mtu); u16 linear_rq_headroom = mlx5e_get_linear_rq_headroom(params, xsk); - u32 frag_sz = linear_rq_headroom + hw_mtu; + + return linear_rq_headroom + hw_mtu; +} + +u32 mlx5e_rx_get_linear_frag_sz(struct mlx5e_params *params, + struct mlx5e_xsk_param *xsk) +{ + u32 frag_sz = mlx5e_rx_get_min_frag_sz(params, xsk); /* AF_XDP doesn't build SKBs in place. */ if (!xsk) frag_sz = MLX5_SKB_FRAG_SZ(frag_sz); - /* XDP in mlx5e doesn't support multiple packets per page. */ + /* XDP in mlx5e doesn't support multiple packets per page. AF_XDP is a + * special case. It can run with frames smaller than a page, as it + * doesn't allocate pages dynamically. However, here we pretend that + * fragments are page-sized: it allows to treat XSK frames like pages + * by redirecting alloc and free operations to XSK rings and by using + * the fact there are no multiple packets per "page" (which is a frame). + * The latter is important, because frames may come in a random order, + * and we will have trouble assemblying a real page of multiple frames. + */ if (mlx5e_rx_is_xdp(params, xsk)) frag_sz = max_t(u32, frag_sz, PAGE_SIZE); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.h b/drivers/net/ethernet/mellanox/mlx5/core/en/params.h index 3a615d663d84..989d8f429438 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/params.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.h @@ -76,6 +76,8 @@ static inline bool mlx5e_qid_validate(const struct mlx5e_profile *profile, u16 mlx5e_get_linear_rq_headroom(struct mlx5e_params *params, struct mlx5e_xsk_param *xsk); +u32 mlx5e_rx_get_min_frag_sz(struct mlx5e_params *params, + struct mlx5e_xsk_param *xsk); u32 mlx5e_rx_get_linear_frag_sz(struct mlx5e_params *params, struct mlx5e_xsk_param *xsk); u8 mlx5e_mpwqe_log_pkts_per_wqe(struct mlx5e_params *params, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c index 1ed5c33e022f..f049e0ac308a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c @@ -122,6 +122,7 @@ bool mlx5e_xdp_handle(struct mlx5e_rq *rq, struct mlx5e_dma_info *di, void *va, u16 *rx_headroom, u32 *len, bool xsk) { struct bpf_prog *prog = READ_ONCE(rq->xdp_prog); + struct xdp_umem *umem = rq->umem; struct xdp_buff xdp; u32 act; int err; @@ -138,8 +139,11 @@ bool mlx5e_xdp_handle(struct mlx5e_rq *rq, struct mlx5e_dma_info *di, xdp.rxq = &rq->xdp_rxq; act = bpf_prog_run_xdp(prog, &xdp); - if (xsk) - xdp.handle += xdp.data - xdp.data_hard_start; + if (xsk) { + u64 off = xdp.data - xdp.data_hard_start; + + xdp.handle = xsk_umem_adjust_offset(umem, xdp.handle, off); + } switch (act) { case XDP_PASS: *rx_headroom = xdp.data - xdp.data_hard_start; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c index 6a55573ec8f2..475b6bd5d29b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c @@ -24,7 +24,8 @@ int mlx5e_xsk_page_alloc_umem(struct mlx5e_rq *rq, if (!xsk_umem_peek_addr_rq(umem, &handle)) return -ENOMEM; - dma_info->xsk.handle = handle + rq->buff.umem_headroom; + dma_info->xsk.handle = xsk_umem_adjust_offset(umem, handle, + rq->buff.umem_headroom); dma_info->xsk.data = xdp_umem_get_data(umem, dma_info->xsk.handle); /* No need to add headroom to the DMA address. In striding RQ case, we @@ -104,7 +105,7 @@ struct sk_buff *mlx5e_xsk_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, /* head_offset is not used in this function, because di->xsk.data and * di->addr point directly to the necessary place. Furthermore, in the - * current implementation, one page = one packet = one frame, so + * current implementation, UMR pages are mapped to XSK frames, so * head_offset should always be 0. */ WARN_ON_ONCE(head_offset); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.h b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.h index 307b923a1361..cab0e93497ae 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.h @@ -5,6 +5,7 @@ #define __MLX5_EN_XSK_RX_H__ #include "en.h" +#include <net/xdp_sock.h> /* RX data path */ @@ -24,4 +25,17 @@ struct sk_buff *mlx5e_xsk_skb_from_cqe_linear(struct mlx5e_rq *rq, struct mlx5e_wqe_frag_info *wi, u32 cqe_bcnt); +static inline bool mlx5e_xsk_update_rx_wakeup(struct mlx5e_rq *rq, bool alloc_err) +{ + if (!xsk_umem_uses_need_wakeup(rq->umem)) + return alloc_err; + + if (unlikely(alloc_err)) + xsk_set_rx_need_wakeup(rq->umem); + else + xsk_clear_rx_need_wakeup(rq->umem); + + return false; +} + #endif /* __MLX5_EN_XSK_RX_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c index d360750b25b7..631af8dee517 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c @@ -4,18 +4,23 @@ #include "setup.h" #include "en/params.h" +/* It matches XDP_UMEM_MIN_CHUNK_SIZE, but as this constant is private and may + * change unexpectedly, and mlx5e has a minimum valid stride size for striding + * RQ, keep this check in the driver. + */ +#define MLX5E_MIN_XSK_CHUNK_SIZE 2048 + bool mlx5e_validate_xsk_param(struct mlx5e_params *params, struct mlx5e_xsk_param *xsk, struct mlx5_core_dev *mdev) { - /* AF_XDP doesn't support frames larger than PAGE_SIZE, and the current - * mlx5e XDP implementation doesn't support multiple packets per page. - */ - if (xsk->chunk_size != PAGE_SIZE) + /* AF_XDP doesn't support frames larger than PAGE_SIZE. */ + if (xsk->chunk_size > PAGE_SIZE || + xsk->chunk_size < MLX5E_MIN_XSK_CHUNK_SIZE) return false; /* Current MTU and XSK headroom don't allow packets to fit the frames. */ - if (mlx5e_rx_get_linear_frag_sz(params, xsk) > xsk->chunk_size) + if (mlx5e_rx_get_min_frag_sz(params, xsk) > xsk->chunk_size) return false; /* frag_sz is different for regular and XSK RQs, so ensure that linear diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c index fd2c75b4b519..87827477d38c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c @@ -7,7 +7,7 @@ #include "en/params.h" #include <net/xdp_sock.h> -int mlx5e_xsk_async_xmit(struct net_device *dev, u32 qid) +int mlx5e_xsk_wakeup(struct net_device *dev, u32 qid, u32 flags) { struct mlx5e_priv *priv = netdev_priv(dev); struct mlx5e_params *params = &priv->channels.params; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.h b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.h index 7add18bf78d8..79b487d89757 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.h @@ -5,11 +5,23 @@ #define __MLX5_EN_XSK_TX_H__ #include "en.h" +#include <net/xdp_sock.h> /* TX data path */ -int mlx5e_xsk_async_xmit(struct net_device *dev, u32 qid); +int mlx5e_xsk_wakeup(struct net_device *dev, u32 qid, u32 flags); bool mlx5e_xsk_tx(struct mlx5e_xdpsq *sq, unsigned int budget); +static inline void mlx5e_xsk_update_tx_wakeup(struct mlx5e_xdpsq *sq) +{ + if (!xsk_umem_uses_need_wakeup(sq->umem)) + return; + + if (sq->pc != sq->cc) + xsk_clear_tx_need_wakeup(sq->umem); + else + xsk_set_tx_need_wakeup(sq->umem); +} + #endif /* __MLX5_EN_XSK_TX_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index dadadf221087..1cacda1bc1b4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -4580,7 +4580,7 @@ const struct net_device_ops mlx5e_netdev_ops = { .ndo_tx_timeout = mlx5e_tx_timeout, .ndo_bpf = mlx5e_xdp, .ndo_xdp_xmit = mlx5e_xdp_xmit, - .ndo_xsk_async_xmit = mlx5e_xsk_async_xmit, + .ndo_xsk_wakeup = mlx5e_xsk_wakeup, #ifdef CONFIG_MLX5_EN_ARFS .ndo_rx_flow_steer = mlx5e_rx_flow_steer, #endif diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index 2fd2760d0bb7..d6a547238de0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -695,8 +695,11 @@ bool mlx5e_post_rx_mpwqes(struct mlx5e_rq *rq) rq->mpwqe.umr_in_progress += rq->mpwqe.umr_last_bulk; rq->mpwqe.actual_wq_head = head; - /* If XSK Fill Ring doesn't have enough frames, busy poll by - * rescheduling the NAPI poll. + /* If XSK Fill Ring doesn't have enough frames, report the error, so + * that one of the actions can be performed: + * 1. If need_wakeup is used, signal that the application has to kick + * the driver when it refills the Fill Ring. + * 2. Otherwise, busy poll by rescheduling the NAPI poll. */ if (unlikely(alloc_err == -ENOMEM && rq->umem)) return true; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c index 49b06b256c92..257a7c9f7a14 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c @@ -33,6 +33,7 @@ #include <linux/irq.h> #include "en.h" #include "en/xdp.h" +#include "en/xsk/rx.h" #include "en/xsk/tx.h" static inline bool mlx5e_channel_no_affinity_change(struct mlx5e_channel *c) @@ -81,6 +82,29 @@ void mlx5e_trigger_irq(struct mlx5e_icosq *sq) mlx5e_notify_hw(wq, sq->pc, sq->uar_map, &nopwqe->ctrl); } +static bool mlx5e_napi_xsk_post(struct mlx5e_xdpsq *xsksq, struct mlx5e_rq *xskrq) +{ + bool busy_xsk = false, xsk_rx_alloc_err; + + /* Handle the race between the application querying need_wakeup and the + * driver setting it: + * 1. Update need_wakeup both before and after the TX. If it goes to + * "yes", it can only happen with the first update. + * 2. If the application queried need_wakeup before we set it, the + * packets will be transmitted anyway, even w/o a wakeup. + * 3. Give a chance to clear need_wakeup after new packets were queued + * for TX. + */ + mlx5e_xsk_update_tx_wakeup(xsksq); + busy_xsk |= mlx5e_xsk_tx(xsksq, MLX5E_TX_XSK_POLL_BUDGET); + mlx5e_xsk_update_tx_wakeup(xsksq); + + xsk_rx_alloc_err = xskrq->post_wqes(xskrq); + busy_xsk |= mlx5e_xsk_update_rx_wakeup(xskrq, xsk_rx_alloc_err); + + return busy_xsk; +} + int mlx5e_napi_poll(struct napi_struct *napi, int budget) { struct mlx5e_channel *c = container_of(napi, struct mlx5e_channel, @@ -122,8 +146,7 @@ int mlx5e_napi_poll(struct napi_struct *napi, int budget) if (xsk_open) { mlx5e_poll_ico_cq(&c->xskicosq.cq); busy |= mlx5e_poll_xdpsq_cq(&xsksq->cq); - busy_xsk |= mlx5e_xsk_tx(xsksq, MLX5E_TX_XSK_POLL_BUDGET); - busy_xsk |= xskrq->post_wqes(xskrq); + busy_xsk |= mlx5e_napi_xsk_post(xsksq, xskrq); } busy |= busy_xsk; |