diff options
Diffstat (limited to 'drivers/net/ethernet/mellanox/mlx5')
24 files changed, 1840 insertions, 255 deletions
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile index 5fe2bf916c06..90db891fcc22 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile +++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile @@ -24,7 +24,7 @@ mlx5_core-y := main.o cmd.o debugfs.o fw.o eq.o uar.o pagealloc.o \ mlx5_core-$(CONFIG_MLX5_CORE_EN) += en_main.o en_common.o en_fs.o en_ethtool.o \ en_tx.o en_rx.o en_dim.o en_txrx.o en/xdp.o en_stats.o \ en_selftest.o en/port.o en/monitor_stats.o en/reporter_tx.o \ - en/params.o + en/params.o en/xsk/umem.o en/xsk/setup.o en/xsk/rx.o en/xsk/tx.o # # Netdev extra diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 010140753e73..cb00e622c006 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -137,6 +137,7 @@ struct page_pool; #define MLX5E_MAX_NUM_CHANNELS (MLX5E_INDIR_RQT_SIZE >> 1) #define MLX5E_MAX_NUM_SQS (MLX5E_MAX_NUM_CHANNELS * MLX5E_MAX_NUM_TC) #define MLX5E_TX_CQ_POLL_BUDGET 128 +#define MLX5E_TX_XSK_POLL_BUDGET 64 #define MLX5E_SQ_RECOVER_MIN_INTERVAL 500 /* msecs */ #define MLX5E_UMR_WQE_INLINE_SZ \ @@ -155,6 +156,11 @@ do { \ ##__VA_ARGS__); \ } while (0) +enum mlx5e_rq_group { + MLX5E_RQ_GROUP_REGULAR, + MLX5E_RQ_GROUP_XSK, + MLX5E_NUM_RQ_GROUPS /* Keep last. */ +}; static inline u16 mlx5_min_rx_wqes(int wq_type, u32 wq_size) { @@ -179,7 +185,8 @@ static inline int mlx5e_get_max_num_channels(struct mlx5_core_dev *mdev) /* Use this function to get max num channels after netdev was created */ static inline int mlx5e_get_netdev_max_channels(struct net_device *netdev) { - return min_t(unsigned int, netdev->num_rx_queues, + return min_t(unsigned int, + netdev->num_rx_queues / MLX5E_NUM_RQ_GROUPS, netdev->num_tx_queues); } @@ -250,6 +257,7 @@ struct mlx5e_params { u32 lro_timeout; u32 pflags; struct bpf_prog *xdp_prog; + struct mlx5e_xsk *xsk; unsigned int sw_mtu; int hard_mtu; }; @@ -399,8 +407,14 @@ struct mlx5e_txqsq { } ____cacheline_aligned_in_smp; struct mlx5e_dma_info { - struct page *page; - dma_addr_t addr; + dma_addr_t addr; + union { + struct page *page; + struct { + u64 handle; + void *data; + } xsk; + }; }; /* XDP packets can be transmitted in different ways. On completion, we need to @@ -467,9 +481,11 @@ struct mlx5e_xdp_mpwqe { }; struct mlx5e_xdpsq; +typedef int (*mlx5e_fp_xmit_xdp_frame_check)(struct mlx5e_xdpsq *); typedef bool (*mlx5e_fp_xmit_xdp_frame)(struct mlx5e_xdpsq *, struct mlx5e_xdp_xmit_data *, - struct mlx5e_xdp_info *); + struct mlx5e_xdp_info *, + int); struct mlx5e_xdpsq { /* data path */ @@ -487,8 +503,10 @@ struct mlx5e_xdpsq { struct mlx5e_cq cq; /* read only */ + struct xdp_umem *umem; struct mlx5_wq_cyc wq; struct mlx5e_xdpsq_stats *stats; + mlx5e_fp_xmit_xdp_frame_check xmit_xdp_frame_check; mlx5e_fp_xmit_xdp_frame xmit_xdp_frame; struct { struct mlx5e_xdp_wqe_info *wqe_info; @@ -619,6 +637,7 @@ struct mlx5e_rq { } mpwqe; }; struct { + u16 umem_headroom; u16 headroom; u8 map_dir; /* dma map direction */ } buff; @@ -649,6 +668,10 @@ struct mlx5e_rq { DECLARE_BITMAP(flags, 8); struct page_pool *page_pool; + /* AF_XDP zero-copy */ + struct zero_copy_allocator zca; + struct xdp_umem *umem; + /* control */ struct mlx5_wq_ctrl wq_ctrl; __be32 mkey_be; @@ -661,6 +684,11 @@ struct mlx5e_rq { struct xdp_rxq_info xdp_rxq; } ____cacheline_aligned_in_smp; +enum mlx5e_channel_state { + MLX5E_CHANNEL_STATE_XSK, + MLX5E_CHANNEL_NUM_STATES +}; + struct mlx5e_channel { /* data path */ struct mlx5e_rq rq; @@ -677,6 +705,13 @@ struct mlx5e_channel { /* XDP_REDIRECT */ struct mlx5e_xdpsq xdpsq; + /* AF_XDP zero-copy */ + struct mlx5e_rq xskrq; + struct mlx5e_xdpsq xsksq; + struct mlx5e_icosq xskicosq; + /* xskicosq can be accessed from any CPU - the spinlock protects it. */ + spinlock_t xskicosq_lock; + /* data path - accessed per napi poll */ struct irq_desc *irq_desc; struct mlx5e_ch_stats *stats; @@ -685,6 +720,7 @@ struct mlx5e_channel { struct mlx5e_priv *priv; struct mlx5_core_dev *mdev; struct hwtstamp_config *tstamp; + DECLARE_BITMAP(state, MLX5E_CHANNEL_NUM_STATES); int ix; int cpu; cpumask_var_t xps_cpumask; @@ -700,14 +736,17 @@ struct mlx5e_channel_stats { struct mlx5e_ch_stats ch; struct mlx5e_sq_stats sq[MLX5E_MAX_NUM_TC]; struct mlx5e_rq_stats rq; + struct mlx5e_rq_stats xskrq; struct mlx5e_xdpsq_stats rq_xdpsq; struct mlx5e_xdpsq_stats xdpsq; + struct mlx5e_xdpsq_stats xsksq; } ____cacheline_aligned_in_smp; enum { MLX5E_STATE_OPENED, MLX5E_STATE_DESTROYING, MLX5E_STATE_XDP_TX_ENABLED, + MLX5E_STATE_XDP_OPEN, }; struct mlx5e_rqt { @@ -740,6 +779,17 @@ struct mlx5e_modify_sq_param { int rl_index; }; +struct mlx5e_xsk { + /* UMEMs are stored separately from channels, because we don't want to + * lose them when channels are recreated. The kernel also stores UMEMs, + * but it doesn't distinguish between zero-copy and non-zero-copy UMEMs, + * so rely on our mechanism. + */ + struct xdp_umem **umems; + u16 refcnt; + bool ever_used; +}; + struct mlx5e_priv { /* priv data path fields - start */ struct mlx5e_txqsq *txq2sq[MLX5E_MAX_NUM_CHANNELS * MLX5E_MAX_NUM_TC]; @@ -760,6 +810,7 @@ struct mlx5e_priv { struct mlx5e_tir indir_tir[MLX5E_NUM_INDIR_TIRS]; struct mlx5e_tir inner_indir_tir[MLX5E_NUM_INDIR_TIRS]; struct mlx5e_tir direct_tir[MLX5E_MAX_NUM_CHANNELS]; + struct mlx5e_tir xsk_tir[MLX5E_MAX_NUM_CHANNELS]; struct mlx5e_rss_params rss_params; u32 tx_rates[MLX5E_MAX_NUM_SQS]; @@ -796,6 +847,7 @@ struct mlx5e_priv { struct mlx5e_tls *tls; #endif struct devlink_health_reporter *tx_reporter; + struct mlx5e_xsk xsk; }; struct mlx5e_profile { @@ -839,8 +891,9 @@ bool mlx5e_striding_rq_possible(struct mlx5_core_dev *mdev, struct mlx5e_params *params); void mlx5e_page_dma_unmap(struct mlx5e_rq *rq, struct mlx5e_dma_info *dma_info); -void mlx5e_page_release(struct mlx5e_rq *rq, struct mlx5e_dma_info *dma_info, - bool recycle); +void mlx5e_page_release_dynamic(struct mlx5e_rq *rq, + struct mlx5e_dma_info *dma_info, + bool recycle); void mlx5e_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe); void mlx5e_handle_rx_cqe_mpwrq(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe); bool mlx5e_post_rx_wqes(struct mlx5e_rq *rq); @@ -900,6 +953,30 @@ void mlx5e_build_indir_tir_ctx_hash(struct mlx5e_rss_params *rss_params, void mlx5e_modify_tirs_hash(struct mlx5e_priv *priv, void *in, int inlen); struct mlx5e_tirc_config mlx5e_tirc_get_default_config(enum mlx5e_traffic_types tt); +struct mlx5e_xsk_param; + +struct mlx5e_rq_param; +int mlx5e_open_rq(struct mlx5e_channel *c, struct mlx5e_params *params, + struct mlx5e_rq_param *param, struct mlx5e_xsk_param *xsk, + struct xdp_umem *umem, struct mlx5e_rq *rq); +int mlx5e_wait_for_min_rx_wqes(struct mlx5e_rq *rq, int wait_time); +void mlx5e_deactivate_rq(struct mlx5e_rq *rq); +void mlx5e_close_rq(struct mlx5e_rq *rq); + +struct mlx5e_sq_param; +int mlx5e_open_icosq(struct mlx5e_channel *c, struct mlx5e_params *params, + struct mlx5e_sq_param *param, struct mlx5e_icosq *sq); +void mlx5e_close_icosq(struct mlx5e_icosq *sq); +int mlx5e_open_xdpsq(struct mlx5e_channel *c, struct mlx5e_params *params, + struct mlx5e_sq_param *param, struct xdp_umem *umem, + struct mlx5e_xdpsq *sq, bool is_redirect); +void mlx5e_close_xdpsq(struct mlx5e_xdpsq *sq); + +struct mlx5e_cq_param; +int mlx5e_open_cq(struct mlx5e_channel *c, struct net_dim_cq_moder moder, + struct mlx5e_cq_param *param, struct mlx5e_cq *cq); +void mlx5e_close_cq(struct mlx5e_cq *cq); + int mlx5e_open_locked(struct net_device *netdev); int mlx5e_close_locked(struct net_device *netdev); @@ -1070,10 +1147,10 @@ int mlx5e_create_indirect_rqt(struct mlx5e_priv *priv); int mlx5e_create_indirect_tirs(struct mlx5e_priv *priv, bool inner_ttc); void mlx5e_destroy_indirect_tirs(struct mlx5e_priv *priv, bool inner_ttc); -int mlx5e_create_direct_rqts(struct mlx5e_priv *priv); -void mlx5e_destroy_direct_rqts(struct mlx5e_priv *priv); -int mlx5e_create_direct_tirs(struct mlx5e_priv *priv); -void mlx5e_destroy_direct_tirs(struct mlx5e_priv *priv); +int mlx5e_create_direct_rqts(struct mlx5e_priv *priv, struct mlx5e_tir *tirs); +void mlx5e_destroy_direct_rqts(struct mlx5e_priv *priv, struct mlx5e_tir *tirs); +int mlx5e_create_direct_tirs(struct mlx5e_priv *priv, struct mlx5e_tir *tirs); +void mlx5e_destroy_direct_tirs(struct mlx5e_priv *priv, struct mlx5e_tir *tirs); void mlx5e_destroy_rqt(struct mlx5e_priv *priv, struct mlx5e_rqt *rqt); int mlx5e_create_tis(struct mlx5_core_dev *mdev, int tc, @@ -1142,6 +1219,7 @@ void mlx5e_detach_netdev(struct mlx5e_priv *priv); void mlx5e_destroy_netdev(struct mlx5e_priv *priv); void mlx5e_set_netdev_mtu_boundaries(struct mlx5e_priv *priv); void mlx5e_build_nic_params(struct mlx5_core_dev *mdev, + struct mlx5e_xsk *xsk, struct mlx5e_rss_params *rss_params, struct mlx5e_params *params, u16 max_channels, u16 mtu); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c index 0de908b12fcc..79301d116667 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c @@ -49,48 +49,56 @@ u32 mlx5e_rx_get_linear_frag_sz(struct mlx5e_params *params, return frag_sz; } -u8 mlx5e_mpwqe_log_pkts_per_wqe(struct mlx5e_params *params) +u8 mlx5e_mpwqe_log_pkts_per_wqe(struct mlx5e_params *params, + struct mlx5e_xsk_param *xsk) { - u32 linear_frag_sz = mlx5e_rx_get_linear_frag_sz(params, NULL); + u32 linear_frag_sz = mlx5e_rx_get_linear_frag_sz(params, xsk); return MLX5_MPWRQ_LOG_WQE_SZ - order_base_2(linear_frag_sz); } -bool mlx5e_rx_is_linear_skb(struct mlx5e_params *params) +bool mlx5e_rx_is_linear_skb(struct mlx5e_params *params, + struct mlx5e_xsk_param *xsk) { - u32 frag_sz = mlx5e_rx_get_linear_frag_sz(params, NULL); + /* AF_XDP allocates SKBs on XDP_PASS - ensure they don't occupy more + * than one page. For this, check both with and without xsk. + */ + u32 linear_frag_sz = max(mlx5e_rx_get_linear_frag_sz(params, xsk), + mlx5e_rx_get_linear_frag_sz(params, NULL)); - return !params->lro_en && frag_sz <= PAGE_SIZE; + return !params->lro_en && linear_frag_sz <= PAGE_SIZE; } #define MLX5_MAX_MPWQE_LOG_WQE_STRIDE_SZ ((BIT(__mlx5_bit_sz(wq, log_wqe_stride_size)) - 1) + \ MLX5_MPWQE_LOG_STRIDE_SZ_BASE) bool mlx5e_rx_mpwqe_is_linear_skb(struct mlx5_core_dev *mdev, - struct mlx5e_params *params) + struct mlx5e_params *params, + struct mlx5e_xsk_param *xsk) { - u32 frag_sz = mlx5e_rx_get_linear_frag_sz(params, NULL); + u32 linear_frag_sz = mlx5e_rx_get_linear_frag_sz(params, xsk); s8 signed_log_num_strides_param; u8 log_num_strides; - if (!mlx5e_rx_is_linear_skb(params)) + if (!mlx5e_rx_is_linear_skb(params, xsk)) return false; - if (order_base_2(frag_sz) > MLX5_MAX_MPWQE_LOG_WQE_STRIDE_SZ) + if (order_base_2(linear_frag_sz) > MLX5_MAX_MPWQE_LOG_WQE_STRIDE_SZ) return false; if (MLX5_CAP_GEN(mdev, ext_stride_num_range)) return true; - log_num_strides = MLX5_MPWRQ_LOG_WQE_SZ - order_base_2(frag_sz); + log_num_strides = MLX5_MPWRQ_LOG_WQE_SZ - order_base_2(linear_frag_sz); signed_log_num_strides_param = (s8)log_num_strides - MLX5_MPWQE_LOG_NUM_STRIDES_BASE; return signed_log_num_strides_param >= 0; } -u8 mlx5e_mpwqe_get_log_rq_size(struct mlx5e_params *params) +u8 mlx5e_mpwqe_get_log_rq_size(struct mlx5e_params *params, + struct mlx5e_xsk_param *xsk) { - u8 log_pkts_per_wqe = mlx5e_mpwqe_log_pkts_per_wqe(params); + u8 log_pkts_per_wqe = mlx5e_mpwqe_log_pkts_per_wqe(params, xsk); /* Numbers are unsigned, don't subtract to avoid underflow. */ if (params->log_rq_mtu_frames < @@ -101,27 +109,30 @@ u8 mlx5e_mpwqe_get_log_rq_size(struct mlx5e_params *params) } u8 mlx5e_mpwqe_get_log_stride_size(struct mlx5_core_dev *mdev, - struct mlx5e_params *params) + struct mlx5e_params *params, + struct mlx5e_xsk_param *xsk) { - if (mlx5e_rx_mpwqe_is_linear_skb(mdev, params)) - return order_base_2(mlx5e_rx_get_linear_frag_sz(params, NULL)); + if (mlx5e_rx_mpwqe_is_linear_skb(mdev, params, xsk)) + return order_base_2(mlx5e_rx_get_linear_frag_sz(params, xsk)); return MLX5_MPWRQ_DEF_LOG_STRIDE_SZ(mdev); } u8 mlx5e_mpwqe_get_log_num_strides(struct mlx5_core_dev *mdev, - struct mlx5e_params *params) + struct mlx5e_params *params, + struct mlx5e_xsk_param *xsk) { return MLX5_MPWRQ_LOG_WQE_SZ - - mlx5e_mpwqe_get_log_stride_size(mdev, params); + mlx5e_mpwqe_get_log_stride_size(mdev, params, xsk); } u16 mlx5e_get_rq_headroom(struct mlx5_core_dev *mdev, - struct mlx5e_params *params) + struct mlx5e_params *params, + struct mlx5e_xsk_param *xsk) { bool is_linear_skb = (params->rq_wq_type == MLX5_WQ_TYPE_CYCLIC) ? - mlx5e_rx_is_linear_skb(params) : - mlx5e_rx_mpwqe_is_linear_skb(mdev, params); + mlx5e_rx_is_linear_skb(params, xsk) : + mlx5e_rx_mpwqe_is_linear_skb(mdev, params, xsk); - return is_linear_skb ? mlx5e_get_linear_rq_headroom(params, NULL) : 0; + return is_linear_skb ? mlx5e_get_linear_rq_headroom(params, xsk) : 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.h b/drivers/net/ethernet/mellanox/mlx5/core/en/params.h index f83417b822bf..bd882b5ee9a7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/params.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.h @@ -40,22 +40,85 @@ struct mlx5e_channel_param { struct mlx5e_cq_param icosq_cq; }; +static inline bool mlx5e_qid_get_ch_if_in_group(struct mlx5e_params *params, + u16 qid, + enum mlx5e_rq_group group, + u16 *ix) +{ + int nch = params->num_channels; + int ch = qid - nch * group; + + if (ch < 0 || ch >= nch) + return false; + + *ix = ch; + return true; +} + +static inline void mlx5e_qid_get_ch_and_group(struct mlx5e_params *params, + u16 qid, + u16 *ix, + enum mlx5e_rq_group *group) +{ + u16 nch = params->num_channels; + + *ix = qid % nch; + *group = qid / nch; +} + +static inline bool mlx5e_qid_validate(struct mlx5e_params *params, u64 qid) +{ + return qid < params->num_channels * MLX5E_NUM_RQ_GROUPS; +} + /* Parameter calculations */ u16 mlx5e_get_linear_rq_headroom(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); -bool mlx5e_rx_is_linear_skb(struct mlx5e_params *params); +u8 mlx5e_mpwqe_log_pkts_per_wqe(struct mlx5e_params *params, + struct mlx5e_xsk_param *xsk); +bool mlx5e_rx_is_linear_skb(struct mlx5e_params *params, + struct mlx5e_xsk_param *xsk); bool mlx5e_rx_mpwqe_is_linear_skb(struct mlx5_core_dev *mdev, - struct mlx5e_params *params); -u8 mlx5e_mpwqe_get_log_rq_size(struct mlx5e_params *params); + struct mlx5e_params *params, + struct mlx5e_xsk_param *xsk); +u8 mlx5e_mpwqe_get_log_rq_size(struct mlx5e_params *params, + struct mlx5e_xsk_param *xsk); u8 mlx5e_mpwqe_get_log_stride_size(struct mlx5_core_dev *mdev, - struct mlx5e_params *params); + struct mlx5e_params *params, + struct mlx5e_xsk_param *xsk); u8 mlx5e_mpwqe_get_log_num_strides(struct mlx5_core_dev *mdev, - struct mlx5e_params *params); + struct mlx5e_params *params, + struct mlx5e_xsk_param *xsk); u16 mlx5e_get_rq_headroom(struct mlx5_core_dev *mdev, - struct mlx5e_params *params); + struct mlx5e_params *params, + struct mlx5e_xsk_param *xsk); + +/* Build queue parameters */ + +void mlx5e_build_rq_param(struct mlx5e_priv *priv, + struct mlx5e_params *params, + struct mlx5e_xsk_param *xsk, + struct mlx5e_rq_param *param); +void mlx5e_build_sq_param_common(struct mlx5e_priv *priv, + struct mlx5e_sq_param *param); +void mlx5e_build_rx_cq_param(struct mlx5e_priv *priv, + struct mlx5e_params *params, + struct mlx5e_xsk_param *xsk, + struct mlx5e_cq_param *param); +void mlx5e_build_tx_cq_param(struct mlx5e_priv *priv, + struct mlx5e_params *params, + struct mlx5e_cq_param *param); +void mlx5e_build_ico_cq_param(struct mlx5e_priv *priv, + u8 log_wq_size, + struct mlx5e_cq_param *param); +void mlx5e_build_icosq_param(struct mlx5e_priv *priv, + u8 log_wq_size, + struct mlx5e_sq_param *param); +void mlx5e_build_xdpsq_param(struct mlx5e_priv *priv, + struct mlx5e_params *params, + struct mlx5e_sq_param *param); #endif /* __MLX5_EN_PARAMS_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c index ee99efde9143..b0b982cf69bb 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c @@ -31,6 +31,7 @@ */ #include <linux/bpf_trace.h> +#include <net/xdp_sock.h> #include "en/xdp.h" #include "en/params.h" @@ -113,12 +114,12 @@ mlx5e_xmit_xdp_buff(struct mlx5e_xdpsq *sq, struct mlx5e_rq *rq, xdpi.page.di = *di; } - return sq->xmit_xdp_frame(sq, &xdptxd, &xdpi); + return sq->xmit_xdp_frame(sq, &xdptxd, &xdpi, 0); } /* returns true if packet was consumed by xdp */ bool mlx5e_xdp_handle(struct mlx5e_rq *rq, struct mlx5e_dma_info *di, - void *va, u16 *rx_headroom, u32 *len) + void *va, u16 *rx_headroom, u32 *len, bool xsk) { struct bpf_prog *prog = READ_ONCE(rq->xdp_prog); struct xdp_buff xdp; @@ -132,9 +133,13 @@ bool mlx5e_xdp_handle(struct mlx5e_rq *rq, struct mlx5e_dma_info *di, xdp_set_data_meta_invalid(&xdp); xdp.data_end = xdp.data + *len; xdp.data_hard_start = va; + if (xsk) + xdp.handle = di->xsk.handle; xdp.rxq = &rq->xdp_rxq; act = bpf_prog_run_xdp(prog, &xdp); + if (xsk) + xdp.handle += xdp.data - xdp.data_hard_start; switch (act) { case XDP_PASS: *rx_headroom = xdp.data - xdp.data_hard_start; @@ -152,7 +157,8 @@ bool mlx5e_xdp_handle(struct mlx5e_rq *rq, struct mlx5e_dma_info *di, goto xdp_abort; __set_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags); __set_bit(MLX5E_RQ_FLAG_XDP_REDIRECT, rq->flags); - mlx5e_page_dma_unmap(rq, di); + if (!xsk) + mlx5e_page_dma_unmap(rq, di); rq->stats->xdp_redirect++; return true; default: @@ -206,7 +212,7 @@ static void mlx5e_xdp_mpwqe_session_start(struct mlx5e_xdpsq *sq) stats->mpwqe++; } -static void mlx5e_xdp_mpwqe_complete(struct mlx5e_xdpsq *sq) +void mlx5e_xdp_mpwqe_complete(struct mlx5e_xdpsq *sq) { struct mlx5_wq_cyc *wq = &sq->wq; struct mlx5e_xdp_mpwqe *session = &sq->mpwqe; @@ -229,9 +235,32 @@ static void mlx5e_xdp_mpwqe_complete(struct mlx5e_xdpsq *sq) session->wqe = NULL; /* Close session */ } +enum { + MLX5E_XDP_CHECK_OK = 1, + MLX5E_XDP_CHECK_START_MPWQE = 2, +}; + +static int mlx5e_xmit_xdp_frame_check_mpwqe(struct mlx5e_xdpsq *sq) +{ + if (unlikely(!sq->mpwqe.wqe)) { + if (unlikely(!mlx5e_wqc_has_room_for(&sq->wq, sq->cc, sq->pc, + MLX5_SEND_WQE_MAX_WQEBBS))) { + /* SQ is full, ring doorbell */ + mlx5e_xmit_xdp_doorbell(sq); + sq->stats->full++; + return -EBUSY; + } + + return MLX5E_XDP_CHECK_START_MPWQE; + } + + return MLX5E_XDP_CHECK_OK; +} + static bool mlx5e_xmit_xdp_frame_mpwqe(struct mlx5e_xdpsq *sq, struct mlx5e_xdp_xmit_data *xdptxd, - struct mlx5e_xdp_info *xdpi) + struct mlx5e_xdp_info *xdpi, + int check_result) { struct mlx5e_xdp_mpwqe *session = &sq->mpwqe; struct mlx5e_xdpsq_stats *stats = sq->stats; @@ -241,15 +270,16 @@ static bool mlx5e_xmit_xdp_frame_mpwqe(struct mlx5e_xdpsq *sq, return false; } - if (unlikely(!session->wqe)) { - if (unlikely(!mlx5e_wqc_has_room_for(&sq->wq, sq->cc, sq->pc, - MLX5_SEND_WQE_MAX_WQEBBS))) { - /* SQ is full, ring doorbell */ - mlx5e_xmit_xdp_doorbell(sq); - stats->full++; - return false; - } + if (!check_result) + check_result = mlx5e_xmit_xdp_frame_check_mpwqe(sq); + if (unlikely(check_result < 0)) + return false; + if (check_result == MLX5E_XDP_CHECK_START_MPWQE) { + /* Start the session when nothing can fail, so it's guaranteed + * that if there is an active session, it has at least one dseg, + * and it's safe to complete it at any time. + */ mlx5e_xdp_mpwqe_session_start(sq); } @@ -264,9 +294,22 @@ static bool mlx5e_xmit_xdp_frame_mpwqe(struct mlx5e_xdpsq *sq, return true; } +static int mlx5e_xmit_xdp_frame_check(struct mlx5e_xdpsq *sq) +{ + if (unlikely(!mlx5e_wqc_has_room_for(&sq->wq, sq->cc, sq->pc, 1))) { + /* SQ is full, ring doorbell */ + mlx5e_xmit_xdp_doorbell(sq); + sq->stats->full++; + return -EBUSY; + } + + return MLX5E_XDP_CHECK_OK; +} + static bool mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xdp_xmit_data *xdptxd, - struct mlx5e_xdp_info *xdpi) + struct mlx5e_xdp_info *xdpi, + int check_result) { struct mlx5_wq_cyc *wq = &sq->wq; u16 pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc); @@ -288,12 +331,10 @@ static bool mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, return false; } - if (unlikely(!mlx5e_wqc_has_room_for(wq, sq->cc, sq->pc, 1))) { - /* SQ is full, ring doorbell */ - mlx5e_xmit_xdp_doorbell(sq); - stats->full++; + if (!check_result) + check_result = mlx5e_xmit_xdp_frame_check(sq); + if (unlikely(check_result < 0)) return false; - } cseg->fm_ce_se = 0; @@ -323,6 +364,7 @@ static bool mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, static void mlx5e_free_xdpsq_desc(struct mlx5e_xdpsq *sq, struct mlx5e_xdp_wqe_info *wi, + u32 *xsk_frames, bool recycle) { struct mlx5e_xdp_info_fifo *xdpi_fifo = &sq->db.xdpi_fifo; @@ -340,7 +382,11 @@ static void mlx5e_free_xdpsq_desc(struct mlx5e_xdpsq *sq, break; case MLX5E_XDP_XMIT_MODE_PAGE: /* XDP_TX from the regular RQ */ - mlx5e_page_release(xdpi.page.rq, &xdpi.page.di, recycle); + mlx5e_page_release_dynamic(xdpi.page.rq, &xdpi.page.di, recycle); + break; + case MLX5E_XDP_XMIT_MODE_XSK: + /* AF_XDP send */ + (*xsk_frames)++; break; default: WARN_ON_ONCE(true); @@ -352,6 +398,7 @@ bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq) { struct mlx5e_xdpsq *sq; struct mlx5_cqe64 *cqe; + u32 xsk_frames = 0; u16 sqcc; int i; @@ -393,10 +440,13 @@ bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq) sqcc += wi->num_wqebbs; - mlx5e_free_xdpsq_desc(sq, wi, true); + mlx5e_free_xdpsq_desc(sq, wi, &xsk_frames, true); } while (!last_wqe); } while ((++i < MLX5E_TX_CQ_POLL_BUDGET) && (cqe = mlx5_cqwq_get_cqe(&cq->wq))); + if (xsk_frames) + xsk_umem_complete_tx(sq->umem, xsk_frames); + sq->stats->cqes += i; mlx5_cqwq_update_db_record(&cq->wq); @@ -410,6 +460,8 @@ bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq) void mlx5e_free_xdpsq_descs(struct mlx5e_xdpsq *sq) { + u32 xsk_frames = 0; + while (sq->cc != sq->pc) { struct mlx5e_xdp_wqe_info *wi; u16 ci; @@ -419,8 +471,11 @@ void mlx5e_free_xdpsq_descs(struct mlx5e_xdpsq *sq) sq->cc += wi->num_wqebbs; - mlx5e_free_xdpsq_desc(sq, wi, false); + mlx5e_free_xdpsq_desc(sq, wi, &xsk_frames, false); } + + if (xsk_frames) + xsk_umem_complete_tx(sq->umem, xsk_frames); } int mlx5e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames, @@ -466,7 +521,7 @@ int mlx5e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames, xdpi.frame.xdpf = xdpf; xdpi.frame.dma_addr = xdptxd.dma_addr; - if (unlikely(!sq->xmit_xdp_frame(sq, &xdptxd, &xdpi))) { + if (unlikely(!sq->xmit_xdp_frame(sq, &xdptxd, &xdpi, 0))) { dma_unmap_single(sq->pdev, xdptxd.dma_addr, xdptxd.len, DMA_TO_DEVICE); xdp_return_frame_rx_napi(xdpf); @@ -500,6 +555,8 @@ void mlx5e_xdp_rx_poll_complete(struct mlx5e_rq *rq) void mlx5e_set_xmit_fp(struct mlx5e_xdpsq *sq, bool is_mpw) { + sq->xmit_xdp_frame_check = is_mpw ? + mlx5e_xmit_xdp_frame_check_mpwqe : mlx5e_xmit_xdp_frame_check; sq->xmit_xdp_frame = is_mpw ? mlx5e_xmit_xdp_frame_mpwqe : mlx5e_xmit_xdp_frame; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h index 9200cb9f499b..2d934c8d3807 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h @@ -42,7 +42,8 @@ struct mlx5e_xsk_param; int mlx5e_xdp_max_mtu(struct mlx5e_params *params, struct mlx5e_xsk_param *xsk); bool mlx5e_xdp_handle(struct mlx5e_rq *rq, struct mlx5e_dma_info *di, - void *va, u16 *rx_headroom, u32 *len); + void *va, u16 *rx_headroom, u32 *len, bool xsk); +void mlx5e_xdp_mpwqe_complete(struct mlx5e_xdpsq *sq); bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq); void mlx5e_free_xdpsq_descs(struct mlx5e_xdpsq *sq); void mlx5e_set_xmit_fp(struct mlx5e_xdpsq *sq, bool is_mpw); @@ -67,6 +68,21 @@ static inline bool mlx5e_xdp_tx_is_enabled(struct mlx5e_priv *priv) return test_bit(MLX5E_STATE_XDP_TX_ENABLED, &priv->state); } +static inline void mlx5e_xdp_set_open(struct mlx5e_priv *priv) +{ + set_bit(MLX5E_STATE_XDP_OPEN, &priv->state); +} + +static inline void mlx5e_xdp_set_closed(struct mlx5e_priv *priv) +{ + clear_bit(MLX5E_STATE_XDP_OPEN, &priv->state); +} + +static inline bool mlx5e_xdp_is_open(struct mlx5e_priv *priv) +{ + return test_bit(MLX5E_STATE_XDP_OPEN, &priv->state); +} + static inline void mlx5e_xmit_xdp_doorbell(struct mlx5e_xdpsq *sq) { if (sq->doorbell_cseg) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/Makefile new file mode 100644 index 000000000000..5ee42991900a --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/Makefile @@ -0,0 +1 @@ +subdir-ccflags-y += -I$(src)/../.. diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c new file mode 100644 index 000000000000..6a55573ec8f2 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c @@ -0,0 +1,192 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +/* Copyright (c) 2019 Mellanox Technologies. */ + +#include "rx.h" +#include "en/xdp.h" +#include <net/xdp_sock.h> + +/* RX data path */ + +bool mlx5e_xsk_pages_enough_umem(struct mlx5e_rq *rq, int count) +{ + /* Check in advance that we have enough frames, instead of allocating + * one-by-one, failing and moving frames to the Reuse Ring. + */ + return xsk_umem_has_addrs_rq(rq->umem, count); +} + +int mlx5e_xsk_page_alloc_umem(struct mlx5e_rq *rq, + struct mlx5e_dma_info *dma_info) +{ + struct xdp_umem *umem = rq->umem; + u64 handle; + + if (!xsk_umem_peek_addr_rq(umem, &handle)) + return -ENOMEM; + + dma_info->xsk.handle = 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 + * just provide pages for UMR, and headroom is counted at the setup + * stage when creating a WQE. In non-striding RQ case, headroom is + * accounted in mlx5e_alloc_rx_wqe. + */ + dma_info->addr = xdp_umem_get_dma(umem, handle); + + xsk_umem_discard_addr_rq(umem); + + dma_sync_single_for_device(rq->pdev, dma_info->addr, PAGE_SIZE, + DMA_BIDIRECTIONAL); + + return 0; +} + +static inline void mlx5e_xsk_recycle_frame(struct mlx5e_rq *rq, u64 handle) +{ + xsk_umem_fq_reuse(rq->umem, handle & rq->umem->chunk_mask); +} + +/* XSKRQ uses pages from UMEM, they must not be released. They are returned to + * the userspace if possible, and if not, this function is called to reuse them + * in the driver. + */ +void mlx5e_xsk_page_release(struct mlx5e_rq *rq, + struct mlx5e_dma_info *dma_info) +{ + mlx5e_xsk_recycle_frame(rq, dma_info->xsk.handle); +} + +/* Return a frame back to the hardware to fill in again. It is used by XDP when + * the XDP program returns XDP_TX or XDP_REDIRECT not to an XSKMAP. + */ +void mlx5e_xsk_zca_free(struct zero_copy_allocator *zca, unsigned long handle) +{ + struct mlx5e_rq *rq = container_of(zca, struct mlx5e_rq, zca); + + mlx5e_xsk_recycle_frame(rq, handle); +} + +static struct sk_buff *mlx5e_xsk_construct_skb(struct mlx5e_rq *rq, void *data, + u32 cqe_bcnt) +{ + struct sk_buff *skb; + + skb = napi_alloc_skb(rq->cq.napi, cqe_bcnt); + if (unlikely(!skb)) { + rq->stats->buff_alloc_err++; + return NULL; + } + + skb_put_data(skb, data, cqe_bcnt); + + return skb; +} + +struct sk_buff *mlx5e_xsk_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, + struct mlx5e_mpw_info *wi, + u16 cqe_bcnt, + u32 head_offset, + u32 page_idx) +{ + struct mlx5e_dma_info *di = &wi->umr.dma_info[page_idx]; + u16 rx_headroom = rq->buff.headroom - rq->buff.umem_headroom; + u32 cqe_bcnt32 = cqe_bcnt; + void *va, *data; + u32 frag_size; + bool |