#include <linux/rhashtable.h>
#include <net/switchdev.h>
#include <net/xdp.h>
-#include <linux/net_dim.h>
+#include <linux/dim.h>
#include <linux/bits.h>
#include "wq.h"
#include "mlx5_core.h"
#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 \
##__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)
{
/* 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);
}
struct mlx5_wqe_ctrl_seg ctrl;
struct mlx5_wqe_umr_ctrl_seg uctrl;
struct mlx5_mkey_seg mkc;
- struct mlx5_mtt inline_mtts[0];
+ union {
+ struct mlx5_mtt inline_mtts[0];
+ u8 tls_static_params_ctx[0];
+ };
};
extern const char mlx5e_self_tests[][ETH_GSTRING_LEN];
u16 num_channels;
u8 num_tc;
bool rx_cqe_compress_def;
- struct net_dim_cq_moder rx_cq_moderation;
- struct net_dim_cq_moder tx_cq_moderation;
bool tunneled_offload_en;
+ struct dim_cq_moder rx_cq_moderation;
+ struct dim_cq_moder tx_cq_moderation;
bool lro_en;
u8 tx_min_inline_mode;
bool vlan_strip_disable;
u32 lro_timeout;
u32 pflags;
struct bpf_prog *xdp_prog;
+ struct mlx5e_xsk *xsk;
unsigned int sw_mtu;
int hard_mtu;
};
MLX5E_RQ_STATE_ENABLED,
MLX5E_RQ_STATE_AM,
MLX5E_RQ_STATE_NO_CSUM_COMPLETE,
+ MLX5E_RQ_STATE_CSUM_FULL, /* cqe_csum_full hw bit is set */
};
struct mlx5e_cq {
u32 num_bytes;
u8 num_wqebbs;
u8 num_dma;
+#ifdef CONFIG_MLX5_EN_TLS
+ skb_frag_t *resync_dump_frag;
+#endif
};
enum mlx5e_dma_map_type {
struct mlx5e_sq_wqe_info {
u8 opcode;
+
+ /* Auxiliary data for different opcodes. */
+ union {
+ struct {
+ struct mlx5e_rq *rq;
+ } umr;
+ };
};
struct mlx5e_txqsq {
/* dirtied @completion */
u16 cc;
u32 dma_fifo_cc;
- struct net_dim dim; /* Adaptive Moderation */
+ struct dim dim; /* Adaptive Moderation */
/* dirtied @xmit */
u16 pc ____cacheline_aligned_in_smp;
void __iomem *uar_map;
struct netdev_queue *txq;
u32 sqn;
+ u16 stop_room;
u8 min_inline_mode;
struct device *pdev;
__be32 mkey_be;
} ____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
+ * distinguish between them to clean up things in a proper way.
+ */
+enum mlx5e_xdp_xmit_mode {
+ /* An xdp_frame was transmitted due to either XDP_REDIRECT from another
+ * device or XDP_TX from an XSK RQ. The frame has to be unmapped and
+ * returned.
+ */
+ MLX5E_XDP_XMIT_MODE_FRAME,
+
+ /* The xdp_frame was created in place as a result of XDP_TX from a
+ * regular RQ. No DMA remapping happened, and the page belongs to us.
+ */
+ MLX5E_XDP_XMIT_MODE_PAGE,
+
+ /* No xdp_frame was created at all, the transmit happened from a UMEM
+ * page. The UMEM Completion Ring producer pointer has to be increased.
+ */
+ MLX5E_XDP_XMIT_MODE_XSK,
};
struct mlx5e_xdp_info {
- struct xdp_frame *xdpf;
- dma_addr_t dma_addr;
- struct mlx5e_dma_info di;
+ enum mlx5e_xdp_xmit_mode mode;
+ union {
+ struct {
+ struct xdp_frame *xdpf;
+ dma_addr_t dma_addr;
+ } frame;
+ struct {
+ struct mlx5e_rq *rq;
+ struct mlx5e_dma_info di;
+ } page;
+ };
+};
+
+struct mlx5e_xdp_xmit_data {
+ dma_addr_t dma_addr;
+ void *data;
+ u32 len;
};
struct mlx5e_xdp_info_fifo {
};
struct mlx5e_xdpsq;
-typedef bool (*mlx5e_fp_xmit_xdp_frame)(struct mlx5e_xdpsq*,
- struct mlx5e_xdp_info*);
+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 *,
+ int);
+
struct mlx5e_xdpsq {
/* data path */
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;
struct mlx5e_channel *channel;
} ____cacheline_aligned_in_smp;
-static inline bool
-mlx5e_wqc_has_room_for(struct mlx5_wq_cyc *wq, u16 cc, u16 pc, u16 n)
-{
- return (mlx5_wq_cyc_ctr2ix(wq, cc - pc) >= n) || (cc == pc);
-}
-
struct mlx5e_wqe_frag_info {
struct mlx5e_dma_info *di;
u32 offset;
u8 log_stride_sz;
u8 umr_in_progress;
u8 umr_last_bulk;
+ u8 umr_completed;
} mpwqe;
};
struct {
+ u16 umem_headroom;
u16 headroom;
u8 map_dir; /* dma map direction */
} buff;
int ix;
unsigned int hw_mtu;
- struct net_dim dim; /* Dynamic Interrupt Moderation */
+ struct dim dim; /* Dynamic Interrupt Moderation */
/* XDP */
struct bpf_prog *xdp_prog;
- struct mlx5e_xdpsq xdpsq;
+ struct mlx5e_xdpsq *xdpsq;
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;
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;
+ struct mlx5e_xdpsq rq_xdpsq;
struct mlx5e_txqsq sq[MLX5E_MAX_NUM_TC];
struct mlx5e_icosq icosq; /* internal control operations */
bool xdp;
/* 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;
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;
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 {
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];
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];
struct mlx5e_tls *tls;
#endif
struct devlink_health_reporter *tx_reporter;
+ struct mlx5e_xsk xsk;
};
struct mlx5e_profile {
void (*cleanup_tx)(struct mlx5e_priv *priv);
void (*enable)(struct mlx5e_priv *priv);
void (*disable)(struct mlx5e_priv *priv);
+ int (*update_rx)(struct mlx5e_priv *priv);
void (*update_stats)(struct mlx5e_priv *priv);
void (*update_carrier)(struct mlx5e_priv *priv);
struct {
struct mlx5e_tx_wqe *wqe, u16 pi, bool xmit_more);
void mlx5e_trigger_irq(struct mlx5e_icosq *sq);
-void mlx5e_completion_event(struct mlx5_core_cq *mcq);
+void mlx5e_completion_event(struct mlx5_core_cq *mcq, struct mlx5_eqe *eqe);
void mlx5e_cq_error_event(struct mlx5_core_cq *mcq, enum mlx5_event event);
int mlx5e_napi_poll(struct napi_struct *napi, int budget);
bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget);
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);
+void mlx5e_poll_ico_cq(struct mlx5e_cq *cq);
bool mlx5e_post_rx_mpwqes(struct mlx5e_rq *rq);
void mlx5e_dealloc_rx_wqe(struct mlx5e_rq *rq, u16 ix);
void mlx5e_dealloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix);
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 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);
MLX5_CAP_ETH(mdev, swp_csum) && MLX5_CAP_ETH(mdev, swp_lso);
}
-struct mlx5e_swp_spec {
- __be16 l3_proto;
- u8 l4_proto;
- u8 is_tun;
- __be16 tun_l3_proto;
- u8 tun_l4_proto;
-};
-
-static inline void
-mlx5e_set_eseg_swp(struct sk_buff *skb, struct mlx5_wqe_eth_seg *eseg,
- struct mlx5e_swp_spec *swp_spec)
-{
- /* SWP offsets are in 2-bytes words */
- eseg->swp_outer_l3_offset = skb_network_offset(skb) / 2;
- if (swp_spec->l3_proto == htons(ETH_P_IPV6))
- eseg->swp_flags |= MLX5_ETH_WQE_SWP_OUTER_L3_IPV6;
- if (swp_spec->l4_proto) {
- eseg->swp_outer_l4_offset = skb_transport_offset(skb) / 2;
- if (swp_spec->l4_proto == IPPROTO_UDP)
- eseg->swp_flags |= MLX5_ETH_WQE_SWP_OUTER_L4_UDP;
- }
-
- if (swp_spec->is_tun) {
- eseg->swp_inner_l3_offset = skb_inner_network_offset(skb) / 2;
- if (swp_spec->tun_l3_proto == htons(ETH_P_IPV6))
- eseg->swp_flags |= MLX5_ETH_WQE_SWP_INNER_L3_IPV6;
- } else { /* typically for ipsec when xfrm mode != XFRM_MODE_TUNNEL */
- eseg->swp_inner_l3_offset = skb_network_offset(skb) / 2;
- if (swp_spec->l3_proto == htons(ETH_P_IPV6))
- eseg->swp_flags |= MLX5_ETH_WQE_SWP_INNER_L3_IPV6;
- }
- switch (swp_spec->tun_l4_proto) {
- case IPPROTO_UDP:
- eseg->swp_flags |= MLX5_ETH_WQE_SWP_INNER_L4_UDP;
- /* fall through */
- case IPPROTO_TCP:
- eseg->swp_inner_l4_offset = skb_inner_transport_offset(skb) / 2;
- break;
- }
-}
-
-static inline void mlx5e_sq_fetch_wqe(struct mlx5e_txqsq *sq,
- struct mlx5e_tx_wqe **wqe,
- u16 *pi)
-{
- struct mlx5_wq_cyc *wq = &sq->wq;
-
- *pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc);
- *wqe = mlx5_wq_cyc_get_wqe(wq, *pi);
- memset(*wqe, 0, sizeof(**wqe));
-}
-
-static inline
-struct mlx5e_tx_wqe *mlx5e_post_nop(struct mlx5_wq_cyc *wq, u32 sqn, u16 *pc)
-{
- u16 pi = mlx5_wq_cyc_ctr2ix(wq, *pc);
- struct mlx5e_tx_wqe *wqe = mlx5_wq_cyc_get_wqe(wq, pi);
- struct mlx5_wqe_ctrl_seg *cseg = &wqe->ctrl;
-
- memset(cseg, 0, sizeof(*cseg));
-
- cseg->opmod_idx_opcode = cpu_to_be32((*pc << 8) | MLX5_OPCODE_NOP);
- cseg->qpn_ds = cpu_to_be32((sqn << 8) | 0x01);
-
- (*pc)++;
-
- return wqe;
-}
-
-static inline
-void mlx5e_notify_hw(struct mlx5_wq_cyc *wq, u16 pc,
- void __iomem *uar_map,
- struct mlx5_wqe_ctrl_seg *ctrl)
-{
- ctrl->fm_ce_se = MLX5_WQE_CTRL_CQ_UPDATE;
- /* ensure wqe is visible to device before updating doorbell record */
- dma_wmb();
-
- *wq->db = cpu_to_be32(pc);
-
- /* ensure doorbell record is visible to device before ringing the
- * doorbell
- */
- wmb();
-
- mlx5_write64((__be32 *)ctrl, uar_map);
-}
-
-static inline void mlx5e_cq_arm(struct mlx5e_cq *cq)
-{
- struct mlx5_core_cq *mcq;
-
- mcq = &cq->mcq;
- mlx5_cq_arm(mcq, MLX5_CQ_DB_REQ_NOT, mcq->uar->map, cq->wq.cc);
-}
-
extern const struct ethtool_ops mlx5e_ethtool_ops;
#ifdef CONFIG_MLX5_CORE_EN_DCB
extern const struct dcbnl_rtnl_ops mlx5e_dcbnl_ops;
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,
- u32 underlay_qpn, u32 *tisn);
+int mlx5e_create_tis(struct mlx5_core_dev *mdev, void *in, u32 *tisn);
void mlx5e_destroy_tis(struct mlx5_core_dev *mdev, u32 tisn);
int mlx5e_create_tises(struct mlx5e_priv *priv);
+int mlx5e_update_nic_rx(struct mlx5e_priv *priv);
void mlx5e_update_carrier(struct mlx5e_priv *priv);
int mlx5e_close(struct net_device *netdev);
int mlx5e_open(struct net_device *netdev);
u32 mlx5e_ethtool_get_rxfh_indir_size(struct mlx5e_priv *priv);
int mlx5e_ethtool_get_ts_info(struct mlx5e_priv *priv,
struct ethtool_ts_info *info);
-int mlx5e_ethtool_flash_device(struct mlx5e_priv *priv,
- struct ethtool_flash *flash);
void mlx5e_ethtool_get_pauseparam(struct mlx5e_priv *priv,
struct ethtool_pauseparam *pauseparam);
int mlx5e_ethtool_set_pauseparam(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);
#include <linux/bpf.h>
#include <linux/if_bridge.h>
#include <net/page_pool.h>
+#include <net/xdp_sock.h>
#include "eswitch.h"
#include "en.h"
+#include "en/txrx.h"
#include "en_tc.h"
#include "en_rep.h"
#include "en_accel/ipsec.h"
#include "en/monitor_stats.h"
#include "en/reporter.h"
#include "en/params.h"
+#include "en/xsk/umem.h"
+#include "en/xsk/setup.h"
+#include "en/xsk/rx.h"
+#include "en/xsk/tx.h"
-struct mlx5e_rq_param {
- u32 rqc[MLX5_ST_SZ_DW(rqc)];
- struct mlx5_wq_param wq;
- struct mlx5e_rq_frags_info frags_info;
-};
-
-struct mlx5e_sq_param {
- u32 sqc[MLX5_ST_SZ_DW(sqc)];
- struct mlx5_wq_param wq;
- bool is_mpw;
-};
-
-struct mlx5e_cq_param {
- u32 cqc[MLX5_ST_SZ_DW(cqc)];
- struct mlx5_wq_param wq;
- u16 eq_ix;
- u8 cq_period_mode;
-};
-
-struct mlx5e_channel_param {
- struct mlx5e_rq_param rq;
- struct mlx5e_sq_param sq;
- struct mlx5e_sq_param xdp_sq;
- struct mlx5e_sq_param icosq;
- struct mlx5e_cq_param rx_cq;
- struct mlx5e_cq_param tx_cq;
- struct mlx5e_cq_param icosq_cq;
-};
bool mlx5e_check_fragmented_striding_rq_cap(struct mlx5_core_dev *mdev)
{
mlx5_core_info(mdev, "MLX5E: StrdRq(%d) RqSz(%ld) StrdSz(%ld) RxCqeCmprss(%d)\n",
params->rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ,
params->rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ ?
- BIT(mlx5e_mpwqe_get_log_rq_size(params)) :
+ BIT(mlx5e_mpwqe_get_log_rq_size(params, NULL)) :
BIT(params->log_rq_mtu_frames),
- BIT(mlx5e_mpwqe_get_log_stride_size(mdev, params)),
+ BIT(mlx5e_mpwqe_get_log_stride_size(mdev, params, NULL)),
MLX5E_GET_PFLAG(params, MLX5E_PFLAG_RX_CQE_COMPRESS));
}
bool mlx5e_striding_rq_possible(struct mlx5_core_dev *mdev,
struct mlx5e_params *params)
{
- return mlx5e_check_fragmented_striding_rq_cap(mdev) &&
- !MLX5_IPSEC_DEV(mdev) &&
- !(params->xdp_prog && !mlx5e_rx_mpwqe_is_linear_skb(mdev, params));
+ if (!mlx5e_check_fragmented_striding_rq_cap(mdev))
+ return false;
+
+ if (MLX5_IPSEC_DEV(mdev))
+ return false;
+
+ if (params->xdp_prog) {
+ /* XSK params are not considered here. If striding RQ is in use,
+ * and an XSK is being opened, mlx5e_rx_mpwqe_is_linear_skb will
+ * be called with the known XSK params.
+ */
+ if (!mlx5e_rx_mpwqe_is_linear_skb(mdev, params, NULL))
+ return false;
+ }
+
+ return true;
}
void mlx5e_set_rq_type(struct mlx5_core_dev *mdev, struct mlx5e_params *params)
static int mlx5e_alloc_rq(struct mlx5e_channel *c,
struct mlx5e_params *params,
+ struct mlx5e_xsk_param *xsk,
+ struct xdp_umem *umem,
struct mlx5e_rq_param *rqp,
struct mlx5e_rq *rq)
{
struct mlx5_core_dev *mdev = c->mdev;
void *rqc = rqp->rqc;
void *rqc_wq = MLX5_ADDR_OF(rqc, rqc, wq);
+ u32 num_xsk_frames = 0;
+ u32 rq_xdp_ix;
u32 pool_size;
int wq_sz;
int err;
rq->ix = c->ix;
rq->mdev = mdev;
rq->hw_mtu = MLX5E_SW2HW_MTU(params, params->sw_mtu);
- rq->stats = &c->priv->channel_stats[c->ix].rq;
+ rq->xdpsq = &c->rq_xdpsq;
+ rq->umem = umem;
+
+ if (rq->umem)
+ rq->stats = &c->priv->channel_stats[c->ix].xskrq;
+ else
+ rq->stats = &c->priv->channel_stats[c->ix].rq;
rq->xdp_prog = params->xdp_prog ? bpf_prog_inc(params->xdp_prog) : NULL;
if (IS_ERR(rq->xdp_prog)) {
goto err_rq_wq_destroy;
}
- err = xdp_rxq_info_reg(&rq->xdp_rxq, rq->netdev, rq->ix);
+ rq_xdp_ix = rq->ix;
+ if (xsk)
+ rq_xdp_ix += params->num_channels * MLX5E_RQ_GROUP_XSK;
+ err = xdp_rxq_info_reg(&rq->xdp_rxq, rq->netdev, rq_xdp_ix);
if (err < 0)
goto err_rq_wq_destroy;
rq->buff.map_dir = rq->xdp_prog ? DMA_BIDIRECTIONAL : DMA_FROM_DEVICE;
- rq->buff.headroom = mlx5e_get_rq_headroom(mdev, params);
+ rq->buff.headroom = mlx5e_get_rq_headroom(mdev, params, xsk);
+ rq->buff.umem_headroom = xsk ? xsk->headroom : 0;
pool_size = 1 << params->log_rq_mtu_frames;
switch (rq->wq_type) {
wq_sz = mlx5_wq_ll_get_size(&rq->mpwqe.wq);
- pool_size = MLX5_MPWRQ_PAGES_PER_WQE << mlx5e_mpwqe_get_log_rq_size(params);
+ if (xsk)
+ num_xsk_frames = wq_sz <<
+ mlx5e_mpwqe_get_log_num_strides(mdev, params, xsk);
+
+ pool_size = MLX5_MPWRQ_PAGES_PER_WQE <<
+ mlx5e_mpwqe_get_log_rq_size(params, xsk);
rq->post_wqes = mlx5e_post_rx_mpwqes;
rq->dealloc_wqe = mlx5e_dealloc_rx_mpwqe;
goto err_rq_wq_destroy;
}
- rq->mpwqe.skb_from_cqe_mpwrq =
- mlx5e_rx_mpwqe_is_linear_skb(mdev, params) ?
- mlx5e_skb_from_cqe_mpwrq_linear :
- mlx5e_skb_from_cqe_mpwrq_nonlinear;
- rq->mpwqe.log_stride_sz = mlx5e_mpwqe_get_log_stride_size(mdev, params);
- rq->mpwqe.num_strides = BIT(mlx5e_mpwqe_get_log_num_strides(mdev, params));
+ rq->mpwqe.skb_from_cqe_mpwrq = xsk ?
+ mlx5e_xsk_skb_from_cqe_mpwrq_linear :
+ mlx5e_rx_mpwqe_is_linear_skb(mdev, params, NULL) ?
+ mlx5e_skb_from_cqe_mpwrq_linear :
+ mlx5e_skb_from_cqe_mpwrq_nonlinear;
+
+ rq->mpwqe.log_stride_sz = mlx5e_mpwqe_get_log_stride_size(mdev, params, xsk);
+ rq->mpwqe.num_strides =
+ BIT(mlx5e_mpwqe_get_log_num_strides(mdev, params, xsk));
err = mlx5e_create_rq_umr_mkey(mdev, rq);
if (err)
wq_sz = mlx5_wq_cyc_get_size(&rq->wqe.wq);
+ if (xsk)
+ num_xsk_frames = wq_sz << rq->wqe.info.log_num_frags;
+
rq->wqe.info = rqp->frags_info;
rq->wqe.frags =
kvzalloc_node(array_size(sizeof(*rq->wqe.frags),
err = mlx5e_init_di_list(rq, wq_sz, c->cpu);
if (err)
goto err_free;
+
rq->post_wqes = mlx5e_post_rx_wqes;
rq->dealloc_wqe = mlx5e_dealloc_rx_wqe;
goto err_free;
}
- rq->wqe.skb_from_cqe = mlx5e_rx_is_linear_skb(params) ?
- mlx5e_skb_from_cqe_linear :
- mlx5e_skb_from_cqe_nonlinear;
+ rq->wqe.skb_from_cqe = xsk ?
+ mlx5e_xsk_skb_from_cqe_linear :
+ mlx5e_rx_is_linear_skb(params, NULL) ?
+ mlx5e_skb_from_cqe_linear :
+ mlx5e_skb_from_cqe_nonlinear;
rq->mkey_be = c->mkey_be;
}
- /* Create a page_pool and register it with rxq */
- pp_params.order = 0;
- pp_params.flags = 0; /* No-internal DMA mapping in page_pool */
- pp_params.pool_size = pool_size;
- pp_params.nid = cpu_to_node(c->cpu);
- pp_params.dev = c->pdev;
- pp_params.dma_dir = rq->buff.map_dir;
-
- /* page_pool can be used even when there is no rq->xdp_prog,
- * given page_pool does not handle DMA mapping there is no
- * required state to clear. And page_pool gracefully handle
- * elevated refcnt.
- */
- rq->page_pool = page_pool_create(&pp_params);
- if (IS_ERR(rq->page_pool)) {
- err = PTR_ERR(rq->page_pool);
- rq->page_pool = NULL;
- goto err_free;
+ if (xsk) {
+ err = mlx5e_xsk_resize_reuseq(umem, num_xsk_frames);
+ if (unlikely(err)) {
+ mlx5_core_err(mdev, "Unable to allocate the Reuse Ring for %u frames\n",
+ num_xsk_frames);
+ goto err_free;
+ }
+
+ rq->zca.free = mlx5e_xsk_zca_free;
+ err = xdp_rxq_info_reg_mem_model(&rq->xdp_rxq,
+ MEM_TYPE_ZERO_COPY,
+ &rq->zca);
+ } else {
+ /* Create a page_pool and register it with rxq */
+ pp_params.order = 0;
+ pp_params.flags = 0; /* No-internal DMA mapping in page_pool */
+ pp_params.pool_size = pool_size;
+ pp_params.nid = cpu_to_node(c->cpu);
+ pp_params.dev = c->pdev;
+ pp_params.dma_dir = rq->buff.map_dir;
+
+ /* page_pool can be used even when there is no rq->xdp_prog,
+ * given page_pool does not handle DMA mapping there is no
+ * required state to clear. And page_pool gracefully handle
+ * elevated refcnt.
+ */
+ rq->page_pool = page_pool_create(&pp_params);
+ if (IS_ERR(rq->page_pool)) {
+ err = PTR_ERR(rq->page_pool);
+ rq->page_pool = NULL;
+ goto err_free;
+ }
+ err = xdp_rxq_info_reg_mem_model(&rq->xdp_rxq,
+ MEM_TYPE_PAGE_POOL, rq->page_pool);
}
- err = xdp_rxq_info_reg_mem_model(&rq->xdp_rxq,
- MEM_TYPE_PAGE_POOL, rq->page_pool);
if (err)
goto err_free;
switch (params->rx_cq_moderation.cq_period_mode) {
case MLX5_CQ_PERIOD_MODE_START_FROM_CQE:
- rq->dim.mode = NET_DIM_CQ_PERIOD_MODE_START_FROM_CQE;
+ rq->dim.mode = DIM_CQ_PERIOD_MODE_START_FROM_CQE;
break;
case MLX5_CQ_PERIOD_MODE_START_FROM_EQE:
default:
- rq->dim.mode = NET_DIM_CQ_PERIOD_MODE_START_FROM_EQE;
+ rq->dim.mode = DIM_CQ_PERIOD_MODE_START_FROM_EQE;
}
rq->page_cache.head = 0;
if (rq->xdp_prog)
bpf_prog_put(rq->xdp_prog);
xdp_rxq_info_unreg(&rq->xdp_rxq);
- if (rq->page_pool)
- page_pool_destroy(rq->page_pool);
+ page_pool_destroy(rq->page_pool);
mlx5_wq_destroy(&rq->wq_ctrl);
return err;
if (rq->xdp_prog)
bpf_prog_put(rq->xdp_prog);
- xdp_rxq_info_unreg(&rq->xdp_rxq);
- if (rq->page_pool)
- page_pool_destroy(rq->page_pool);
-
switch (rq->wq_type) {
case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
kvfree(rq->mpwqe.info);
i = (i + 1) & (MLX5E_CACHE_SIZE - 1)) {
struct mlx5e_dma_info *dma_info = &rq->page_cache.page_cache[i];
- mlx5e_page_release(rq, dma_info, false);
+ /* With AF_XDP, page_cache is not used, so this loop is not
+ * entered, and it's safe to call mlx5e_page_release_dynamic
+ * directly.
+ */
+ mlx5e_page_release_dynamic(rq, dma_info, false);
}
+
+ xdp_rxq_info_unreg(&rq->xdp_rxq);
+ page_pool_destroy(rq->page_pool);
mlx5_wq_destroy(&rq->wq_ctrl);
}
mlx5_core_destroy_rq(rq->mdev, rq->rqn);
}
-static int mlx5e_wait_for_min_rx_wqes(struct mlx5e_rq *rq, int wait_time)
+int mlx5e_wait_for_min_rx_wqes(struct mlx5e_rq *rq, int wait_time)
{
unsigned long exp_time = jiffies + msecs_to_jiffies(wait_time);
struct mlx5e_channel *c = rq->channel;
}
-static int mlx5e_open_rq(struct mlx5e_channel *c,
- struct mlx5e_params *params,
- struct mlx5e_rq_param *param,
- struct mlx5e_rq *rq)
+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 err;
- err = mlx5e_alloc_rq(c, params, param, rq);
+ err = mlx5e_alloc_rq(c, params, xsk, umem, param, rq);
if (err)
return err;
if (err)
goto err_destroy_rq;
+ if (MLX5_CAP_ETH(c->mdev, cqe_checksum_full))
+ __set_bit(MLX5E_RQ_STATE_CSUM_FULL, &c->rq.state);
+
if (params->rx_dim_enabled)
__set_bit(MLX5E_RQ_STATE_AM, &c->rq.state);
mlx5e_trigger_irq(&rq->channel->icosq);
}
-static void mlx5e_deactivate_rq(struct mlx5e_rq *rq)
+void mlx5e_deactivate_rq(struct mlx5e_rq *rq)
{
clear_bit(MLX5E_RQ_STATE_ENABLED, &rq->state);
napi_synchronize(&rq->channel->napi); /* prevent mlx5e_post_rx_wqes */
}
-static void mlx5e_close_rq(struct mlx5e_rq *rq)
+void mlx5e_close_rq(struct mlx5e_rq *rq)
{
cancel_work_sync(&rq->dim.work);
mlx5e_destroy_rq(rq);
static int mlx5e_alloc_xdpsq(struct mlx5e_channel *c,
struct mlx5e_params *params,
+ struct xdp_umem *umem,
struct mlx5e_sq_param *param,
struct mlx5e_xdpsq *sq,
bool is_redirect)
sq->uar_map = mdev->mlx5e_res.bfreg.map;
sq->min_inline_mode = params->tx_min_inline_mode;
sq->hw_mtu = MLX5E_SW2HW_MTU(params, params->sw_mtu);
- sq->stats = is_redirect ?
- &c->priv->channel_stats[c->ix].xdpsq :
- &c->priv->channel_stats[c->ix].rq_xdpsq;
+ sq->umem = umem;
+
+ sq->stats = sq->umem ?
+ &c->priv->channel_stats[c->ix].xsksq :
+ is_redirect ?
+ &c->priv->channel_stats[c->ix].xdpsq :
+ &c->priv->channel_stats[c->ix].rq_xdpsq;
param->wq.db_numa_node = cpu_to_node(c->cpu);
err = mlx5_wq_cyc_create(mdev, ¶m->wq, sqc_wq, wq, &sq->wq_ctrl);
sq->uar_map = mdev->mlx5e_res.bfreg.map;
sq->min_inline_mode = params->tx_min_inline_mode;
sq->stats = &c->priv->channel_stats[c->ix].sq[tc];
+ sq->stop_room = MLX5E_SQ_STOP_ROOM;
INIT_WORK(&sq->recover_work, mlx5e_tx_err_cqe_work);
if (MLX5_IPSEC_DEV(c->priv->mdev))
set_bit(MLX5E_SQ_STATE_IPSEC, &sq->state);
- if (mlx5_accel_is_tls_device(c->priv->mdev))
+ if (mlx5_accel_is_tls_device(c->priv->mdev)) {
set_bit(MLX5E_SQ_STATE_TLS, &sq->state);
+ sq->stop_room += MLX5E_SQ_TLS_ROOM;
+ }
param->wq.db_numa_node = cpu_to_node(c->cpu);
err = mlx5_wq_cyc_create(mdev, ¶m->wq, sqc_wq, wq, &sq->wq_ctrl);
mlx5e_tx_reporter_err_cqe(sq);
}
-static int mlx5e_open_icosq(struct mlx5e_channel *c,
- struct mlx5e_params *params,
- struct mlx5e_sq_param *param,
- struct mlx5e_icosq *sq)
+int mlx5e_open_icosq(struct mlx5e_channel *c, struct mlx5e_params *params,
+ struct mlx5e_sq_param *param, struct mlx5e_icosq *sq)
{
struct mlx5e_create_sq_param csp = {};
int err;
return err;
}
-static void mlx5e_close_icosq(struct mlx5e_icosq *sq)
+void mlx5e_close_icosq(struct mlx5e_icosq *sq)
{
struct mlx5e_channel *c = sq->channel;
mlx5e_free_icosq(sq);
}
-static int mlx5e_open_xdpsq(struct mlx5e_channel *c,
- struct mlx5e_params *params,
- struct mlx5e_sq_param *param,
- struct mlx5e_xdpsq *sq,
- bool is_redirect)
+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)
{
struct mlx5e_create_sq_param csp = {};
int err;
- err = mlx5e_alloc_xdpsq(c, params, param, sq, is_redirect);
+ err = mlx5e_alloc_xdpsq(c, params, umem, param, sq, is_redirect);
if (err)
return err;
return err;
}
-static void mlx5e_close_xdpsq(struct mlx5e_xdpsq *sq, struct mlx5e_rq *rq)
+void mlx5e_close_xdpsq(struct mlx5e_xdpsq *sq)
{
struct mlx5e_channel *c = sq->channel;
napi_synchronize(&c->napi);
mlx5e_destroy_sq(c->mdev, sq->sqn);
- mlx5e_free_xdpsq_descs(sq, rq);
+ mlx5e_free_xdpsq_descs(sq);
mlx5e_free_xdpsq(sq);
}
static int mlx5e_create_cq(struct mlx5e_cq *cq, struct mlx5e_cq_param *param)
{
+ u32 out[MLX5_ST_SZ_DW(create_cq_out)];
struct mlx5_core_dev *mdev = cq->mdev;
struct mlx5_core_cq *mcq = &cq->mcq;
MLX5_ADAPTER_PAGE_SHIFT);
MLX5_SET64(cqc, cqc, dbr_addr, cq->wq_ctrl.db.dma);
- err = mlx5_core_create_cq(mdev, mcq, in, inlen);
+ err = mlx5_core_create_cq(mdev, mcq, in, inlen, out, sizeof(out));
kvfree(in);
mlx5_core_destroy_cq(cq->mdev, &cq->mcq);
}
-static int mlx5e_open_cq(struct mlx5e_channel *c,
- struct net_dim_cq_moder moder,
- struct mlx5e_cq_param *param,
- struct mlx5e_cq *cq)
+int mlx5e_open_cq(struct mlx5e_channel *c, struct dim_cq_moder moder,
+ struct mlx5e_cq_param *param, struct mlx5e_cq *cq)
{
struct mlx5_core_dev *mdev = c->mdev;
int err;
return err;
}
-static void mlx5e_close_cq(struct mlx5e_cq *cq)
+void mlx5e_close_cq(struct mlx5e_cq *cq)
{
mlx5e_destroy_cq(cq);
mlx5e_free_cq(cq);
free_cpumask_var(c->xps_cpumask);
}
-static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix,
- struct mlx5e_params *params,
- struct mlx5e_channel_param *cparam,
- struct mlx5e_channel **cp)
+static int mlx5e_open_queues(struct mlx5e_channel *c,
+ struct mlx5e_params *params,
+ struct mlx5e_channel_param *cparam)
{
- int cpu = cpumask_first(mlx5_comp_irq_get_affinity_mask(priv->mdev, ix));
- struct net_dim_cq_moder icocq_moder = {0, 0};
- struct net_device *netdev = priv->netdev;
- struct mlx5e_channel *c;
- unsigned int irq;
+ struct dim_cq_moder icocq_moder = {0, 0};
int err;
- int eqn;
-
- err = mlx5_vector2eqn(priv->mdev, ix, &eqn, &irq);
- if (err)
- return err;
-
- c = kvzalloc_node(sizeof(*c), GFP_KERNEL, cpu_to_node(cpu));
- if (!c)
- return -ENOMEM;
-
- c->priv = priv;
- c->mdev = priv->mdev;
- c->tstamp = &priv->tstamp;
- c->ix = ix;
- c->cpu = cpu;
- c->pdev = priv->mdev->device;
- c->netdev = priv->netdev;
- c->mkey_be = cpu_to_be32(priv->mdev->mlx5e_res.mkey.key);
- c->num_tc = params->num_tc;
- c->xdp = !!params->xdp_prog;
- c->stats = &priv->channel_stats[ix].ch;
- c->irq_desc = irq_to_desc(irq);
-
- err = mlx5e_alloc_xps_cpumask(c, params);
- if (err)
- goto err_free_channel;
-
- netif_napi_add(netdev, &c->napi, mlx5e_napi_poll, 64);
err = mlx5e_open_cq(c, icocq_moder, &cparam->icosq_cq, &c->icosq.cq);
if (err)
- goto err_napi_del;
+ return err;
err = mlx5e_open_tx_cqs(c, params, cparam);
if (err)
/* XDP SQ CQ params are same as normal TXQ sq CQ params */
err = c->xdp ? mlx5e_open_cq(c, params->tx_cq_moderation,
- &cparam->tx_cq, &c->rq.xdpsq.cq) : 0;
+ &cparam->tx_cq, &c->rq_xdpsq.cq) : 0;
if (err)
goto err_close_rx_cq;
if (err)
goto err_close_icosq;
- err = c->xdp ? mlx5e_open_xdpsq(c, params, &cparam->xdp_sq, &c->rq.xdpsq, false) : 0;
- if (err)
- goto err_close_sqs;
+ if (c->xdp) {
+ err = mlx5e_open_xdpsq(c, params, &cparam->xdp_sq, NULL,
+ &c->rq_xdpsq, false);
+ if (err)
+ goto err_close_sqs;
+ }
- err = mlx5e_open_rq(c, params, &cparam->rq, &c->rq);
+ err = mlx5e_open_rq(c, params, &cparam->rq, NULL, NULL, &c->rq);
if (err)
goto err_close_xdp_sq;
- err = mlx5e_open_xdpsq(c, params, &cparam->xdp_sq, &c->xdpsq, true);
+ err = mlx5e_open_xdpsq(c, params, &cparam->xdp_sq, NULL, &c->xdpsq, true);
if (err)
goto err_close_rq;
- *cp = c;
-
return 0;
err_close_rq:
err_close_xdp_sq:
if (c->xdp)
- mlx5e_close_xdpsq(&c->rq.xdpsq, &c->rq);
+ mlx5e_close_xdpsq(&c->rq_xdpsq);
err_close_sqs:
mlx5e_close_sqs(c);
err_disable_napi:
napi_disable(&c->napi);
+
if (c->xdp)
- mlx5e_close_cq(&c->rq.xdpsq.cq);
+ mlx5e_close_cq(&c->rq_xdpsq.cq);
err_close_rx_cq:
mlx5e_close_cq(&c->rq.cq);
err_close_icosq_cq:
mlx5e_close_cq(&c->icosq.cq);
+ return err;
+}
+
+static void mlx5e_close_queues(struct mlx5e_channel *c)
+{
+ mlx5e_close_xdpsq(&c->xdpsq);
+ mlx5e_close_rq(&c->rq);
+ if (c->xdp)
+ mlx5e_close_xdpsq(&c->rq_xdpsq);
+ mlx5e_close_sqs(c);
+ mlx5e_close_icosq(&c->icosq);
+ napi_disable(&c->napi);
+ if (c->xdp)
+ mlx5e_close_cq(&c->rq_xdpsq.cq);
+ mlx5e_close_cq(&c->rq.cq);
+ mlx5e_close_cq(&c->xdpsq.cq);
+ mlx5e_close_tx_cqs(c);
+ mlx5e_close_cq(&c->icosq.cq);
+}
+
+static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix,
+ struct mlx5e_params *params,
+ struct mlx5e_channel_param *cparam,
+ struct xdp_umem *umem,
+ struct mlx5e_channel **cp)
+{
+ int cpu = cpumask_first(mlx5_comp_irq_get_affinity_mask(priv->mdev, ix));
+ struct net_device *netdev = priv->netdev;
+ struct mlx5e_xsk_param xsk;
+ struct mlx5e_channel *c;
+ unsigned int irq;
+ int err;
+ int eqn;
+
+ err = mlx5_vector2eqn(priv->mdev, ix, &eqn, &irq);
+ if (err)
+ return err;
+
+ c = kvzalloc_node(sizeof(*c), GFP_KERNEL, cpu_to_node(cpu));
+ if (!c)
+ return -ENOMEM;
+
+ c->priv = priv;
+ c->mdev = priv->mdev;
+ c->tstamp = &priv->tstamp;
+ c->ix = ix;
+ c->cpu = cpu;
+ c->pdev = priv->mdev->device;
+ c->netdev = priv->netdev;
+ c->mkey_be = cpu_to_be32(priv->mdev->mlx5e_res.mkey.key);
+ c->num_tc = params->num_tc;
+ c->xdp = !!params->xdp_prog;
+ c->stats = &priv->channel_stats[ix].ch;
+ c->irq_desc = irq_to_desc(irq);
+
+ err = mlx5e_alloc_xps_cpumask(c, params);
+ if (err)
+ goto err_free_channel;
+
+ netif_napi_add(netdev, &c->napi, mlx5e_napi_poll, 64);
+
+ err = mlx5e_open_queues(c, params, cparam);
+ if (unlikely(err))
+ goto err_napi_del;
+
+ if (umem) {
+ mlx5e_build_xsk_param(umem, &xsk);
+ err = mlx5e_open_xsk(priv, params, &xsk, umem, c);
+ if (unlikely(err))
+ goto err_close_queues;
+ }
+
+ *cp = c;
+
+ return 0;
+
+err_close_queues:
+ mlx5e_close_queues(c);
+
err_napi_del:
netif_napi_del(&c->napi);
mlx5e_free_xps_cpumask(c);
mlx5e_activate_txqsq(&c->sq[tc]);
mlx5e_activate_rq(&c->rq);
netif_set_xps_queue(c->netdev, c->xps_cpumask, c->ix);
+
+ if (test_bit(MLX5E_CHANNEL_STATE_XSK, c->state))
+ mlx5e_activate_xsk(c);
}
static void mlx5e_deactivate_channel(struct mlx5e_channel *c)
{
int tc;
+ if (test_bit(MLX5E_CHANNEL_STATE_XSK, c->state))
+ mlx5e_deactivate_xsk(c);
+
mlx5e_deactivate_rq(&c->rq);
for (tc = 0; tc < c->num_tc; tc++)
mlx5e_deactivate_txqsq(&c->sq[tc]);
static void mlx5e_close_channel(struct mlx5e_channel *c)
{
- mlx5e_close_xdpsq(&c->xdpsq, NULL);
- mlx5e_close_rq(&c->rq);
- if (c->xdp)
- mlx5e_close_xdpsq(&c->rq.xdpsq, &c->rq);
- mlx5e_close_sqs(c);
- mlx5e_close_icosq(&c->icosq);
- napi_disable(&c->napi);
- if (c->xdp)
- mlx5e_close_cq(&c->rq.xdpsq.cq);
- mlx5e_close_cq(&c->rq.cq);
- mlx5e_close_cq(&c->xdpsq.cq);
- mlx5e_close_tx_cqs(c);
- mlx5e_close_cq(&c->icosq.cq);
+ if (test_bit(MLX5E_CHANNEL_STATE_XSK, c->state))
+ mlx5e_close_xsk(c);
+ mlx5e_close_queues(c);
netif_napi_del(&c->napi);
mlx5e_free_xps_cpumask(c);
static void mlx5e_build_rq_frags_info(struct mlx5_core_dev *mdev,
struct mlx5e_params *params,
+ struct mlx5e_xsk_param *xsk,
struct mlx5e_rq_frags_info *info)
{
u32 byte_count = MLX5E_SW2HW_MTU(params, params->sw_mtu);
byte_count += MLX5E_METADATA_ETHER_LEN;
#endif
- if (mlx5e_rx_is_linear_skb(params)) {
+ if (mlx5e_rx_is_linear_skb(params, xsk)) {
int frag_stride;
- frag_stride = mlx5e_rx_get_linear_frag_sz(params);
+ frag_stride = mlx5e_rx_get_linear_frag_sz(params, xsk);
frag_stride = roundup_pow_of_two(frag_stride);
info->arr[0].frag_size = byte_count;
return MLX5_GET(wq, wq, log_wq_sz);
}
-static void mlx5e_build_rq_param(struct mlx5e_priv *priv,
- struct mlx5e_params *params,
- struct mlx5e_rq_param *param)
+void mlx5e_build_rq_param(struct mlx5e_priv *priv,
+ struct mlx5e_params *params,
+ struct mlx5e_xsk_param *xsk,
+ struct mlx5e_rq_param *param)
{
struct mlx5_core_dev *mdev = priv->mdev;
void *rqc = param->rqc;
switch (params->rq_wq_type) {
case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
MLX5_SET(wq, wq, log_wqe_num_of_strides,
- mlx5e_mpwqe_get_log_num_strides(mdev, params) -
+ mlx5e_mpwqe_get_log_num_strides(mdev, params, xsk) -
MLX5_MPWQE_LOG_NUM_STRIDES_BASE);
MLX5_SET(wq, wq, log_wqe_stride_size,
- mlx5e_mpwqe_get_log_stride_size(mdev, params) -
+ mlx5e_mpwqe_get_log_stride_size(mdev, params, xsk) -
MLX5_MPWQE_LOG_STRIDE_SZ_BASE);
- MLX5_SET(wq, wq, log_wq_sz, mlx5e_mpwqe_get_log_rq_size(params));
+ MLX5_SET(wq, wq, log_wq_sz, mlx5e_mpwqe_get_log_rq_size(params, xsk));
break;
default: /* MLX5_WQ_TYPE_CYCLIC */
MLX5_SET(wq, wq, log_wq_sz, params->log_rq_mtu_frames);
- mlx5e_build_rq_frags_info(mdev, params, ¶m->frags_info);
+ mlx5e_build_rq_frags_info(mdev, params, xsk, ¶m->frags_info);
ndsegs = param->frags_info.num_frags;
}
param->wq.buf_numa_node = dev_to_node(mdev->device);
}
-static void mlx5e_build_sq_param_common(struct mlx5e_priv *priv,
- struct mlx5e_sq_param *param)
+void mlx5e_build_sq_param_common(struct mlx5e_priv *priv,
+ struct mlx5e_sq_param *param)
{
void *sqc = param->sqc;
void *wq = MLX5_ADDR_OF(sqc, sqc, wq);
MLX5_SET(cqc, cqc, cqe_sz, CQE_STRIDE_128_PAD);
}
-static void mlx5e_build_rx_cq_param(struct mlx5e_priv *priv,
- struct mlx5e_params *params,
- struct mlx5e_cq_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)
{
struct mlx5_core_dev *mdev = priv->mdev;
void *cqc = param->cqc;
switch (params->rq_wq_type) {
case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
- log_cq_size = mlx5e_mpwqe_get_log_rq_size(params) +
- mlx5e_mpwqe_get_log_num_strides(mdev, params);
+ log_cq_size = mlx5e_mpwqe_get_log_rq_size(params, xsk) +
+ mlx5e_mpwqe_get_log_num_strides(mdev, params, xsk);
break;
default: /* MLX5_WQ_TYPE_CYCLIC */
log_cq_size = params->log_rq_mtu_frames;
param->cq_period_mode = params->rx_cq_moderation.cq_period_mode;
}
-static void mlx5e_build_tx_cq_param(struct mlx5e_priv *priv,
- struct mlx5e_params *params,
- 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 *cqc = param->cqc;
param->cq_period_mode = params->tx_cq_moderation.cq_period_mode;
}
-static void mlx5e_build_ico_cq_param(struct mlx5e_priv *priv,
- u8 log_wq_size,
- 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 *cqc = param->cqc;
mlx5e_build_common_cq_param(priv, param);
- param->cq_period_mode = NET_DIM_CQ_PERIOD_MODE_START_FROM_EQE;
+ param->cq_period_mode = DIM_CQ_PERIOD_MODE_START_FROM_EQE;
}
-static void mlx5e_build_icosq_param(struct mlx5e_priv *priv,
- u8 log_wq_size,
- struct mlx5e_sq_param *param)
+void mlx5e_build_icosq_param(struct mlx5e_priv *priv,
+ u8 log_wq_size,
+ struct mlx5e_sq_param *param)
{
void *sqc = param->sqc;
void *wq = MLX5_ADDR_OF(sqc, sqc, wq);
MLX5_SET(sqc, sqc, reg_umr, MLX5_CAP_ETH(priv->mdev, reg_umr_sq));
}
-static void mlx5e_build_xdpsq_param(struct mlx5e_priv *priv,
- struct mlx5e_params *params,
- struct mlx5e_sq_param *param)
+void mlx5e_build_xdpsq_param(struct mlx5e_priv *priv,
+ struct mlx5e_params *params,
+ struct mlx5e_sq_param *param)
{
void *sqc = param->sqc;
void *wq = MLX5_ADDR_OF(sqc, sqc, wq);
{
u8 icosq_log_wq_sz;
- mlx5e_build_rq_param(priv, params, &cparam->rq);
+ mlx5e_build_rq_param(priv, params, NULL, &cparam->rq);
icosq_log_wq_sz = mlx5e_build_icosq_log_wq_sz(params, &cparam->rq);
mlx5e_build_sq_param(priv, params, &cparam->sq);
mlx5e_build_xdpsq_param(priv, params, &cparam->xdp_sq);
mlx5e_build_icosq_param(priv, icosq_log_wq_sz, &cparam->icosq);
- mlx5e_build_rx_cq_param(priv, params, &cparam->rx_cq);
+ mlx5e_build_rx_cq_param(priv, params, NULL, &cparam->rx_cq);
mlx5e_build_tx_cq_param(priv, params, &cparam->tx_cq);
mlx5e_build_ico_cq_param(priv, icosq_log_wq_sz, &cparam->icosq_cq);
}
mlx5e_build_channel_param(priv, &chs->params, cparam);
for (i = 0; i < chs->num; i++) {
- err = mlx5e_open_channel(priv, i, &chs->params, cparam, &chs->c[i]);
+ struct xdp_umem *umem = NULL;
+
+ if (chs->params.xdp_prog)
+ umem = mlx5e_xsk_get_umem(&chs->params, chs->params.xsk, i);
+
+ err = mlx5e_open_channel(priv, i, &chs->params, cparam, umem, &chs->c[i]);
if (err)
goto err_close_channels;
}
int timeout = err ? 0 : MLX5E_RQ_WQES_TIMEOUT;
err |= mlx5e_wait_for_min_rx_wqes(&chs->c[i]->rq, timeout);
+
+ /* Don't wait on the XSK RQ, because the newer xdpsock sample
+ * doesn't provide any Fill Ring entries at the setup stage.
+ */
}
return err ? -ETIMEDOUT : 0;
return err;
}
-int mlx5e_create_direct_rqts(struct mlx5e_priv *priv)
+int mlx5e_create_direct_rqts(struct mlx5e_priv *priv, struct mlx5e_tir *tirs)
{
- struct mlx5e_rqt *rqt;
+ const int max_nch = mlx5e_get_netdev_max_channels(priv->netdev);
int err;
int ix;
- for (ix = 0; ix < mlx5e_get_netdev_max_channels(priv->netdev); ix++) {
- rqt = &priv->direct_tir[ix].rqt;
- err = mlx5e_create_rqt(priv, 1 /*size */, rqt);
- if (err)
+ for (ix = 0; ix < max_nch; ix++) {
+ err = mlx5e_create_rqt(priv, 1 /*size */, &tirs[ix].rqt);
+ if (unlikely(err))
goto err_destroy_rqts;
}
return 0;
err_destroy_rqts:
- mlx5_core_warn(priv->mdev, "create direct rqts failed, %d\n", err);
+ mlx5_core_warn(priv->mdev, "create rqts failed, %d\n", err);
for (ix--; ix >= 0; ix--)
- mlx5e_destroy_rqt(priv, &priv->direct_tir[ix].rqt);
+ mlx5e_destroy_rqt(priv, &tirs[ix].rqt);
return err;
}
-void mlx5e_destroy_direct_rqts(struct mlx5e_priv *priv)
+void mlx5e_destroy_direct_rqts(struct mlx5e_priv *priv, struct mlx5e_tir *tirs)
{
+ const int max_nch = mlx5e_get_netdev_max_channels(priv->netdev);
int i;
- for (i = 0; i < mlx5e_get_netdev_max_channels(priv->netdev); i++)
- mlx5e_destroy_rqt(priv, &priv->direct_tir[i].rqt);
+ for (i = 0; i < max_nch; i++)
+ mlx5e_destroy_rqt(priv, &tirs[i].rqt);
}
static int mlx5e_rx_hash_fn(int hfunc)
void mlx5e_activate_priv_channels(struct mlx5e_priv *priv)
{
int num_txqs = priv->channels.num * priv->channels.params.num_tc;
+ int num_rxqs = priv->channels.num * MLX5E_NUM_RQ_GROUPS;
struct net_device *netdev = priv->netdev;
mlx5e_netdev_set_tcs(netdev);
netif_set_real_num_tx_queues(netdev, num_txqs);
- netif_set_real_num_rx_queues(netdev, priv->channels.num);
+ netif_set_real_num_rx_queues(netdev, num_rxqs);
mlx5e_build_tx2sq_maps(priv);
mlx5e_activate_channels(&priv->channels);
mlx5e_wait_channels_min_rx_wqes(&priv->channels);
mlx5e_redirect_rqts_to_channels(priv, &priv->channels);
+
+ mlx5e_xsk_redirect_rqts_to_channels(priv, &priv->channels);
}
void mlx5e_deactivate_priv_channels(struct mlx5e_priv *priv)
{
+ mlx5e_xsk_redirect_rqts_to_drop(priv, &priv->channels);
+
mlx5e_redirect_rqts_to_drop(priv);
if (mlx5e_is_vport_rep(priv))
if (hw_modify)
hw_modify(priv);
- mlx5e_refresh_tirs(priv, false);
+ priv->profile->update_rx(priv);
mlx5e_activate_priv_channels(priv);
/* return carrier back if needed */
int mlx5e_open_locked(struct net_device *netdev)
{
struct mlx5e_priv *priv = netdev_priv(netdev);
+ bool is_xdp = priv->channels.params.xdp_prog;
int err;
set_bit(MLX5E_STATE_OPENED, &priv->state);
+ if (is_xdp)
+ mlx5e_xdp_set_open(priv);
err = mlx5e_open_channels(priv, &priv->channels);
if (err)
goto err_clear_state_opened_flag;
- mlx5e_refresh_tirs(priv, false);
+ priv->profile->update_rx(priv);
mlx5e_activate_priv_channels(priv);
if (priv->profile->update_carrier)
priv->profile->update_carrier(priv);
return 0;
err_clear_state_opened_flag:
+ if (is_xdp)
+ mlx5e_xdp_set_closed(priv);
clear_bit(MLX5E_STATE_OPENED, &priv->state);
return err;
}
if (!test_bit(MLX5E_STATE_OPENED, &priv->state))
return 0;
+ if (priv->channels.params.xdp_prog)
+ mlx5e_xdp_set_closed(priv);
clear_bit(MLX5E_STATE_OPENED, &priv->state);
netif_carrier_off(priv->netdev);
mlx5e_free_cq(&drop_rq->cq);
}
-int mlx5e_create_tis(struct mlx5_core_dev *mdev, int tc,
- u32 underlay_qpn, u32 *tisn)
+int mlx5e_create_tis(struct mlx5_core_dev *mdev, void *in, u32 *tisn)
{
- u32 in[MLX5_ST_SZ_DW(create_tis_in)] = {0};
void *tisc = MLX5_ADDR_OF(create_tis_in, in, ctx);
- MLX5_SET(tisc, tisc, prio, tc << 1);
- MLX5_SET(tisc, tisc, underlay_qpn, underlay_qpn);
MLX5_SET(tisc, tisc, transport_domain, mdev->mlx5e_res.td.tdn);
+ if (MLX5_GET(tisc, tisc, tls_en))
+ MLX5_SET(tisc, tisc, pd, mdev->mlx5e_res.pdn);
+
if (mlx5_lag_is_lacp_owner(mdev))
MLX5_SET(tisc, tisc, strict_lag_tx_port_affinity, 1);
- return mlx5_core_create_tis(mdev, in, sizeof(in), tisn);
+ return mlx5_core_create_tis(mdev, in, MLX5_ST_SZ_BYTES(create_tis_in), tisn);
}
void mlx5e_destroy_tis(struct mlx5_core_dev *mdev, u32 tisn)
int tc;
for (tc = 0; tc < priv->profile->max_tc; tc++) {
- err = mlx5e_create_tis(priv->mdev, tc, 0, &priv->tisn[tc]);
+ u32 in[MLX5_ST_SZ_DW(create_tis_in)] = {};
+ void *tisc;
+
+ tisc = MLX5_ADDR_OF(create_tis_in, in, ctx);
+
+ MLX5_SET(tisc, tisc, prio, tc << 1);
+
+ err = mlx5e_create_tis(priv->mdev, in, &priv->tisn[tc]);
if (err)
goto err_close_tises;
}
return err;
}
-int mlx5e_create_direct_tirs(struct mlx5e_priv *priv)
+int mlx5e_create_direct_tirs(struct mlx5e_priv *priv, struct mlx5e_tir *tirs)
{
- int nch = mlx5e_get_netdev_max_channels(priv->netdev);
+ const int max_nch = mlx5e_get_netdev_max_channels(priv->netdev);
struct mlx5e_tir *tir;
void *tirc;
int inlen;
- int err;
+ int err = 0;
u32 *in;
int ix;
if (!in)
return -ENOMEM;
- for (ix = 0; ix < nch; ix++) {
+ for (ix = 0; ix < max_nch; ix++) {
memset(in, 0, inlen);
- tir = &priv->direct_tir[ix];
+ tir = &tirs[ix];
tirc = MLX5_ADDR_OF(create_tir_in, in, ctx);
- mlx5e_build_direct_tir_ctx(priv, priv->direct_tir[ix].rqt.rqtn, tirc);
+ mlx5e_build_direct_tir_ctx(priv, tir->rqt.rqtn, tirc);
err = mlx5e_create_tir(priv->mdev, tir, in, inlen);
- if (err)
+ if (unlikely(err))
goto err_destroy_ch_tirs;
}
- kvfree(in);
-
- return 0;
+ goto out;
err_destroy_ch_tirs:
- mlx5_core_warn(priv->mdev, "create direct tirs failed, %d\n", err);
+ mlx5_core_warn(priv->mdev, "create tirs failed, %d\n", err);
for (ix--; ix >= 0; ix--)
- mlx5e_destroy_tir(priv->mdev, &priv->direct_tir[ix]);
+ mlx5e_destroy_tir(priv->mdev, &tirs[ix]);
+out:
kvfree(in);
return err;
mlx5e_destroy_tir(priv->mdev, &priv->inner_indir_tir[i]);
}
-void mlx5e_destroy_direct_tirs(struct mlx5e_priv *priv)
+void mlx5e_destroy_direct_tirs(struct mlx5e_priv *priv, struct mlx5e_tir *tirs)
{
- int nch = mlx5e_get_netdev_max_channels(priv->netdev);
+ const int max_nch = mlx5e_get_netdev_max_channels(priv->netdev);
int i;
- for (i = 0; i < nch; i++)
- mlx5e_destroy_tir(priv->mdev, &priv->direct_tir[i]);
+ for (i = 0; i < max_nch; i++)
+ mlx5e_destroy_tir(priv->mdev, &tirs[i]);
}
static int mlx5e_modify_channels_scatter_fcs(struct mlx5e_channels *chs, bool enable)
return 0;
}
-static int mlx5e_setup_tc_mqprio(struct net_device *netdev,
+static int mlx5e_setup_tc_mqprio(struct mlx5e_priv *priv,
struct tc_mqprio_qopt *mqprio)
{
- struct mlx5e_priv *priv = netdev_priv(netdev);
struct mlx5e_channels new_channels = {};
u8 tc = mqprio->num_tc;
int err = 0;
#ifdef CONFIG_MLX5_ESWITCH
static int mlx5e_setup_tc_cls_flower(struct mlx5e_priv *priv,
- struct tc_cls_flower_offload *cls_flower,
+ struct flow_cls_offload *cls_flower,
int flags)
{
switch (cls_flower->command) {
- case TC_CLSFLOWER_REPLACE:
+ case FLOW_CLS_REPLACE:
return mlx5e_configure_flower(priv->netdev, priv, cls_flower,
flags);
- case TC_CLSFLOWER_DESTROY:
+ case FLOW_CLS_DESTROY:
return mlx5e_delete_flower(priv->netdev, priv, cls_flower,
flags);
- case TC_CLSFLOWER_STATS:
+ case FLOW_CLS_STATS:
return mlx5e_stats_flower(priv->netdev, priv, cls_flower,
flags);
default:
return -EOPNOTSUPP;
}
}
-
-static int mlx5e_setup_tc_block(struct net_device *dev,
- struct tc_block_offload *f)
-{
- struct mlx5e_priv *priv = netdev_priv(dev);
-
- if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
- return -EOPNOTSUPP;
-
- switch (f->command) {
- case TC_BLOCK_BIND:
- return tcf_block_cb_register(f->block, mlx5e_setup_tc_block_cb,
- priv, priv, f->extack);
- case TC_BLOCK_UNBIND:
- tcf_block_cb_unregister(f->block, mlx5e_setup_tc_block_cb,
- priv);
- return 0;
- default:
- return -EOPNOTSUPP;
- }
-}
#endif
+static LIST_HEAD(mlx5e_block_cb_list);
+
static int mlx5e_setup_tc(struct net_device *dev, enum tc_setup_type type,
void *type_data)
{
+ struct mlx5e_priv *priv = netdev_priv(dev);
+
switch (type) {
#ifdef CONFIG_MLX5_ESWITCH
case TC_SETUP_BLOCK:
- return mlx5e_setup_tc_block(dev, type_data);
+ return flow_block_cb_setup_simple(type_data,
+ &mlx5e_block_cb_list,
+ mlx5e_setup_tc_block_cb,
+ priv, priv, true);
#endif
case TC_SETUP_QDISC_MQPRIO:
- return mlx5e_setup_tc_mqprio(dev, type_data);
+ return mlx5e_setup_tc_mqprio(priv, type_data);
default:
return -EOPNOTSUPP;
}
for (i = 0; i < mlx5e_get_netdev_max_channels(priv->netdev); i++) {
struct mlx5e_channel_stats *channel_stats = &priv->channel_stats[i];
+ struct mlx5e_rq_stats *xskrq_stats = &channel_stats->xskrq;
struct mlx5e_rq_stats *rq_stats = &channel_stats->rq;
int j;
- s->rx_packets += rq_stats->packets;
- s->rx_bytes += rq_stats->bytes;
+ s->rx_packets += rq_stats->packets + xskrq_stats->packets;
+ s->rx_bytes += rq_stats->bytes + xskrq_stats->bytes;
for (j = 0; j < priv->max_opened_tc; j++) {
struct mlx5e_sq_stats *sq_stats = &channel_stats->sq[j];
mutex_lock(&priv->state_lock);
+ if (enable && priv->xsk.refcnt) {
+ netdev_warn(netdev, "LRO is incompatible with AF_XDP (%hu XSKs are active)\n",
+ priv->xsk.refcnt);
+ err = -EINVAL;
+ goto out;
+ }
+
old_params = &priv->channels.params;
if (enable && !MLX5E_GET_PFLAG(old_params, MLX5E_PFLAG_RX_STRIDING_RQ)) {
netdev_warn(netdev, "can't set LRO with legacy RQ\n");
new_channels.params.lro_en = enable;
if (old_params->rq_wq_type != MLX5_WQ_TYPE_CYCLIC) {
- if (mlx5e_rx_mpwqe_is_linear_skb(mdev, old_params) ==
- mlx5e_rx_mpwqe_is_linear_skb(mdev, &new_channels.params))
+ if (mlx5e_rx_mpwqe_is_linear_skb(mdev, old_params, NULL) ==
+ mlx5e_rx_mpwqe_is_linear_skb(mdev, &new_channels.params, NULL))
reset = false;
}
return features;
}
+static bool mlx5e_xsk_validate_mtu(struct net_device *netdev,
+ struct mlx5e_channels *chs,
+ struct mlx5e_params *new_params,
+ struct mlx5_core_dev *mdev)
+{
+ u16 ix;
+
+ for (ix = 0; ix < chs->params.num_channels; ix++) {
+ struct xdp_umem *umem = mlx5e_xsk_get_umem(&chs->params, chs->params.xsk, ix);
+ struct mlx5e_xsk_param xsk;
+
+ if (!umem)
+ continue;
+
+ mlx5e_build_xsk_param(umem, &xsk);
+
+ if (!mlx5e_validate_xsk_param(new_params, &xsk, mdev)) {
+ u32 hr = mlx5e_get_linear_rq_headroom(new_params, &xsk);
+ int max_mtu_frame, max_mtu_page, max_mtu;
+
+ /* Two criteria must be met:
+ * 1. HW MTU + all headrooms <= XSK frame size.
+ * 2. Size of SKBs allocated on XDP_PASS <= PAGE_SIZE.
+ */
+ max_mtu_frame = MLX5E_HW2SW_MTU(new_params, xsk.chunk_size - hr);
+ max_mtu_page = mlx5e_xdp_max_mtu(new_params, &xsk);
+ max_mtu = min(max_mtu_frame, max_mtu_page);
+
+ netdev_err(netdev, "MTU %d is too big for an XSK running on channel %hu. Try MTU <= %d\n",
+ new_params->sw_mtu, ix, max_mtu);
+ return false;
+ }
+ }
+
+ return true;
+}
+
int mlx5e_change_mtu(struct net_device *netdev, int new_mtu,
change_hw_mtu_cb set_mtu_cb)
{
new_channels.params.sw_mtu = new_mtu;
if (params->xdp_prog &&
- !mlx5e_rx_is_linear_skb(&new_channels.params)) {
+ !mlx5e_rx_is_linear_skb(&new_channels.params, NULL)) {
netdev_err(netdev, "MTU(%d) > %d is not allowed while XDP enabled\n",
- new_mtu, mlx5e_xdp_max_mtu(params));
+ new_mtu, mlx5e_xdp_max_mtu(params, NULL));
+ err = -EINVAL;
+ goto out;
+ }
+
+ if (priv->xsk.refcnt &&
+ !mlx5e_xsk_validate_mtu(netdev, &priv->channels,
+ &new_channels.params, priv->mdev)) {
err = -EINVAL;
goto out;
}
if (params->rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ) {
- bool is_linear = mlx5e_rx_mpwqe_is_linear_skb(priv->mdev, &new_channels.params);
- u8 ppw_old = mlx5e_mpwqe_log_pkts_per_wqe(params);
- u8 ppw_new = mlx5e_mpwqe_log_pkts_per_wqe(&new_channels.params);
+ bool is_linear = mlx5e_rx_mpwqe_is_linear_skb(priv->mdev,
+ &new_channels.params,
+ NULL);
+ u8 ppw_old = mlx5e_mpwqe_log_pkts_per_wqe(params, NULL);
+ u8 ppw_new = mlx5e_mpwqe_log_pkts_per_wqe(&new_channels.params, NULL);
+
+ /* If XSK is active, XSK RQs are linear. */
+ is_linear |= priv->xsk.refcnt;
+ /* Always reset in linear mode - hw_mtu is used in data path. */
reset = reset && (is_linear || (ppw_old != ppw_new));
}
new_channels.params = priv->channels.params;
new_channels.params.xdp_prog = prog;
- if (!mlx5e_rx_is_linear_skb(&new_channels.params)) {
+ /* No XSK params: AF_XDP can't be enabled yet at the point of setting
+ * the XDP program.
+ */
+ if (!mlx5e_rx_is_linear_skb(&new_channels.params, NULL)) {
netdev_warn(netdev, "XDP is not allowed with MTU(%d) > %d\n",
new_channels.params.sw_mtu,
- mlx5e_xdp_max_mtu(&new_channels.params));
+ mlx5e_xdp_max_mtu(&new_channels.params, NULL));
return -EINVAL;
}
return 0;
}
+static int mlx5e_xdp_update_state(struct mlx5e_priv *priv)
+{
+ if (priv->channels.params.xdp_prog)
+ mlx5e_xdp_set_open(priv);
+ else
+ mlx5e_xdp_set_closed(priv);
+
+ return 0;
+}
+
static int mlx5e_xdp_set(struct net_device *netdev, struct bpf_prog *prog)
{
struct mlx5e_priv *priv = netdev_priv(netdev);
/* no need for full reset when exchanging programs */
reset = (!priv->channels.params.xdp_prog || !prog);
- if (was_opened && reset)
- mlx5e_close_locked(netdev);
if (was_opened && !reset) {
/* num_channels is invariant here, so we can take the
* batched reference right upfront.
}
}
- /* exchange programs, extra prog reference we got from caller
- * as long as we don't fail from this point onwards.
- */
- old_prog = xchg(&priv->channels.params.xdp_prog, prog);
+ if (was_opened && reset) {
+ struct mlx5e_channels new_channels = {};
+
+ new_channels.params = priv->channels.params;
+ new_channels.params.xdp_prog = prog;
+ mlx5e_set_rq_type(priv->mdev, &new_channels.params);
+ old_prog = priv->channels.params.xdp_prog;
+
+ err = mlx5e_safe_switch_channels(priv, &new_channels, mlx5e_xdp_update_state);
+ if (err)
+ goto unlock;
+ } else {
+ /* exchange programs, extra prog reference we got from caller
+ * as long as we don't fail from this point onwards.
+ */
+ old_prog = xchg(&priv->channels.params.xdp_prog, prog);
+ }
+
if (old_prog)
bpf_prog_put(old_prog);
- if (reset) /* change RQ type according to priv->xdp_prog */
+ if (!was_opened && reset) /* change RQ type according to priv->xdp_prog */
mlx5e_set_rq_type(priv->mdev, &priv->channels.params);
- if (was_opened && reset)
- err = mlx5e_open_locked(netdev);
-
- if (!test_bit(MLX5E_STATE_OPENED, &priv->state) || reset)
+ if (!was_opened || reset)
goto unlock;
/* exchanging programs w/o reset, we update ref counts on behalf
*/
for (i = 0; i < priv->channels.num; i++) {
struct mlx5e_channel *c = priv->channels.c[i];
+ bool xsk_open = test_bit(MLX5E_CHANNEL_STATE_XSK, c->state);
clear_bit(MLX5E_RQ_STATE_ENABLED, &c->rq.state);
+ if (xsk_open)
+ clear_bit(MLX5E_RQ_STATE_ENABLED, &c->xskrq.state);
napi_synchronize(&c->napi);
/* prevent mlx5e_poll_rx_cq from accessing rq->xdp_prog */
old_prog = xchg(&c->rq.xdp_prog, prog);
+ if (old_prog)
+ bpf_prog_put(old_prog);
+
+ if (xsk_open) {
+ old_prog = xchg(&c->xskrq.xdp_prog, prog);
+ if (old_prog)
+ bpf_prog_put(old_prog);
+ }
set_bit(MLX5E_RQ_STATE_ENABLED, &c->rq.state);
+ if (xsk_open)
+ set_bit(MLX5E_RQ_STATE_ENABLED, &c->xskrq.state);
/* napi_schedule in case we have missed anything */
napi_schedule(&c->napi);
-
- if (old_prog)
- bpf_prog_put(old_prog);
}
unlock:
case XDP_QUERY_PROG:
xdp->prog_id = mlx5e_xdp_query(dev);
return 0;
+ case XDP_SETUP_XSK_UMEM:
+ return mlx5e_xsk_setup_umem(dev, xdp->xsk.umem,
+ xdp->xsk.queue_id);
default:
return -EINVAL;
}
.ndo_tx_timeout = mlx5e_tx_timeout,
.ndo_bpf = mlx5e_xdp,
.ndo_xdp_xmit = mlx5e_xdp_xmit,
+ .ndo_xsk_async_xmit = mlx5e_xsk_async_xmit,
#ifdef CONFIG_MLX5_EN_ARFS
.ndo_rx_flow_steer = mlx5e_rx_flow_steer,
#endif
link_speed > MLX5E_SLOW_PCI_RATIO * pci_bw;
}
-static struct net_dim_cq_moder mlx5e_get_def_tx_moderation(u8 cq_period_mode)
+static struct dim_cq_moder mlx5e_get_def_tx_moderation(u8 cq_period_mode)
{
- struct net_dim_cq_moder moder;
+ struct dim_cq_moder moder;
moder.cq_period_mode = cq_period_mode;
moder.pkts = MLX5E_PARAMS_DEFAULT_TX_CQ_MODERATION_PKTS;
return moder;
}
-static struct net_dim_cq_moder mlx5e_get_def_rx_moderation(u8 cq_period_mode)
+static struct dim_cq_moder mlx5e_get_def_rx_moderation(u8 cq_period_mode)
{
- struct net_dim_cq_moder moder;
+ struct dim_cq_moder moder;
moder.cq_period_mode = cq_period_mode;
moder.pkts = MLX5E_PARAMS_DEFAULT_RX_CQ_MODERATION_PKTS;
static u8 mlx5_to_net_dim_cq_period_mode(u8 cq_period_mode)
{
return cq_period_mode == MLX5_CQ_PERIOD_MODE_START_FROM_CQE ?
- NET_DIM_CQ_PERIOD_MODE_START_FROM_CQE :
- NET_DIM_CQ_PERIOD_MODE_START_FROM_EQE;
+ DIM_CQ_PERIOD_MODE_START_FROM_CQE :
+ DIM_CQ_PERIOD_MODE_START_FROM_EQE;
}
void mlx5e_set_tx_cq_mode_params(struct mlx5e_params *params, u8 cq_period_mode)
* - Striding RQ configuration is not possible/supported.
* - Slow PCI heuristic.
* - Legacy RQ would use linear SKB while Striding RQ would use non-linear.
+ *
+ * No XSK params: checking the availability of striding RQ in general.
*/
if (!slow_pci_heuristic(mdev) &&
mlx5e_striding_rq_possible(mdev, params) &&
- (mlx5e_rx_mpwqe_is_linear_skb(mdev, params) ||
- !mlx5e_rx_is_linear_skb(params)))
+ (mlx5e_rx_mpwqe_is_linear_skb(mdev, params, NULL) ||
+ !mlx5e_rx_is_linear_skb(params, NULL)))
MLX5E_SET_PFLAG(params, MLX5E_PFLAG_RX_STRIDING_RQ, true);
mlx5e_set_rq_type(mdev, params);
mlx5e_init_rq_type_params(mdev, params);
}
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)
/* HW LRO */
/* TODO: && MLX5_CAP_ETH(mdev, lro_cap) */
- if (params->rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ)
- if (!mlx5e_rx_mpwqe_is_linear_skb(mdev, params))
+ if (params->rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ) {
+ /* No XSK params: checking the availability of striding RQ in general. */
+ if (!mlx5e_rx_mpwqe_is_linear_skb(mdev, params, NULL))
params->lro_en = !slow_pci_heuristic(mdev);
+ }
params->lro_timeout = mlx5e_choose_lro_timeout(mdev, MLX5E_DEFAULT_LRO_TIMEOUT);
/* CQ moderation params */
mlx5e_build_rss_params(rss_params, params->num_channels);
params->tunneled_offload_en =
mlx5e_tunnel_inner_ft_supported(mdev);
+
+ /* AF_XDP */
+ params->xsk = xsk;
}
static void mlx5e_set_netdev_dev_addr(struct net_device *netdev)
{
struct mlx5e_priv *priv = netdev_priv(netdev);
- mlx5_query_nic_vport_mac_address(priv->mdev, 0, netdev->dev_addr);
+ mlx5_query_mac_address(priv->mdev, netdev->dev_addr);
if (is_zero_ether_addr(netdev->dev_addr) &&
!MLX5_CAP_GEN(priv->mdev, vport_group_manager)) {
eth_hw_addr_random(netdev);
netdev->ethtool_ops = &mlx5e_ethtool_ops;
netdev->vlan_features |= NETIF_F_SG;
- netdev->vlan_features |= NETIF_F_IP_CSUM;
- netdev->vlan_features |= NETIF_F_IPV6_CSUM;
+ netdev->vlan_features |= NETIF_F_HW_CSUM;
netdev->vlan_features |= NETIF_F_GRO;
netdev->vlan_features |= NETIF_F_TSO;
netdev->vlan_features |= NETIF_F_TSO6;
netdev->vlan_features |= NETIF_F_RXCSUM;
netdev->vlan_features |= NETIF_F_RXHASH;
+ netdev->mpls_features |= NETIF_F_SG;
+ netdev->mpls_features |= NETIF_F_HW_CSUM;
+ netdev->mpls_features |= NETIF_F_TSO;
+ netdev->mpls_features |= NETIF_F_TSO6;
+
netdev->hw_enc_features |= NETIF_F_HW_VLAN_CTAG_TX;
netdev->hw_enc_features |= NETIF_F_HW_VLAN_CTAG_RX;
if (mlx5_vxlan_allowed(mdev->vxlan) || mlx5_geneve_tx_allowed(mdev) ||
MLX5_CAP_ETH(mdev, tunnel_stateless_gre)) {
- netdev->hw_enc_features |= NETIF_F_IP_CSUM;
- netdev->hw_enc_features |= NETIF_F_IPV6_CSUM;
+ netdev->hw_enc_features |= NETIF_F_HW_CSUM;
netdev->hw_enc_features |= NETIF_F_TSO;
netdev->hw_enc_features |= NETIF_F_TSO6;
netdev->hw_enc_features |= NETIF_F_GSO_PARTIAL;
if (err)
return err;
- mlx5e_build_nic_params(mdev, rss, &priv->channels.params,
+ mlx5e_build_nic_params(mdev, &priv->xsk, rss, &priv->channels.params,
mlx5e_get_netdev_max_channels(netdev),
netdev->mtu);
if (err)
goto err_close_drop_rq;
- err = mlx5e_create_direct_rqts(priv);
+ err = mlx5e_create_direct_rqts(priv, priv->direct_tir);
if (err)
goto err_destroy_indirect_rqts;
if (err)
goto err_destroy_direct_rqts;
- err = mlx5e_create_direct_tirs(priv);
+ err = mlx5e_create_direct_tirs(priv, priv->direct_tir);
if (err)
goto err_destroy_indirect_tirs;
+ err = mlx5e_create_direct_rqts(priv, priv->xsk_tir);
+ if (unlikely(err))
+ goto err_destroy_direct_tirs;
+
+ err = mlx5e_create_direct_tirs(priv, priv->xsk_tir);
+ if (unlikely(err))
+ goto err_destroy_xsk_rqts;
+
err = mlx5e_create_flow_steering(priv);
if (err) {
mlx5_core_warn(mdev, "create flow steering failed, %d\n", err);
- goto err_destroy_direct_tirs;
+ goto err_destroy_xsk_tirs;
}
err = mlx5e_tc_nic_init(priv);
err_destroy_flow_steering:
mlx5e_destroy_flow_steering(priv);
+err_destroy_xsk_tirs:
+ mlx5e_destroy_direct_tirs(priv, priv->xsk_tir);
+err_destroy_xsk_rqts:
+ mlx5e_destroy_direct_rqts(priv, priv->xsk_tir);
err_destroy_direct_tirs:
- mlx5e_destroy_direct_tirs(priv);
+ mlx5e_destroy_direct_tirs(priv, priv->direct_tir);
err_destroy_indirect_tirs:
mlx5e_destroy_indirect_tirs(priv, true);
err_destroy_direct_rqts:
- mlx5e_destroy_direct_rqts(priv);
+ mlx5e_destroy_direct_rqts(priv, priv->direct_tir);
err_destroy_indirect_rqts:
mlx5e_destroy_rqt(priv, &priv->indir_rqt);
err_close_drop_rq:
{
mlx5e_tc_nic_cleanup(priv);
mlx5e_destroy_flow_steering(priv);
- mlx5e_destroy_direct_tirs(priv);
+ mlx5e_destroy_direct_tirs(priv, priv->xsk_tir);
+ mlx5e_destroy_direct_rqts(priv, priv->xsk_tir);
+ mlx5e_destroy_direct_tirs(priv, priv->direct_tir);
mlx5e_destroy_indirect_tirs(priv, true);
- mlx5e_destroy_direct_rqts(priv);
+ mlx5e_destroy_direct_rqts(priv, priv->direct_tir);
mlx5e_destroy_rqt(priv, &priv->indir_rqt);
mlx5e_close_drop_rq(&priv->drop_rq);
mlx5e_destroy_q_counters(priv);
mlx5_lag_remove(mdev);
}
+int mlx5e_update_nic_rx(struct mlx5e_priv *priv)
+{
+ return mlx5e_refresh_tirs(priv, false);
+}
+
static const struct mlx5e_profile mlx5e_nic_profile = {
.init = mlx5e_nic_init,
.cleanup = mlx5e_nic_cleanup,
.cleanup_tx = mlx5e_cleanup_nic_tx,
.enable = mlx5e_nic_enable,
.disable = mlx5e_nic_disable,
+ .update_rx = mlx5e_update_nic_rx,
.update_stats = mlx5e_update_ndo_stats,
.update_carrier = mlx5e_update_carrier,
.rx_handlers.handle_rx_cqe = mlx5e_handle_rx_cqe,
netdev = alloc_etherdev_mqs(sizeof(struct mlx5e_priv),
nch * profile->max_tc,
- nch);
+ nch * MLX5E_NUM_RQ_GROUPS);
if (!netdev) {
mlx5_core_err(mdev, "alloc_etherdev_mqs() failed\n");
return NULL;
#ifdef CONFIG_MLX5_ESWITCH
if (MLX5_ESWITCH_MANAGER(mdev) &&
- mlx5_eswitch_mode(mdev->priv.eswitch) == SRIOV_OFFLOADS) {
+ mlx5_eswitch_mode(mdev->priv.eswitch) == MLX5_ESWITCH_OFFLOADS) {
mlx5e_rep_register_vport_reps(mdev);
return mdev;
}
#include <linux/ip.h>
#include <linux/ipv6.h>
#include <linux/tcp.h>
+#include <linux/indirect_call_wrapper.h>
#include <net/ip6_checksum.h>
#include <net/page_pool.h>
#include <net/inet_ecn.h>
#include "en_accel/tls_rxtx.h"
#include "lib/clock.h"
#include "en/xdp.h"
+#include "en/xsk/rx.h"
static inline bool mlx5e_rx_hw_stamp(struct hwtstamp_config *config)
{
return true;
}
-static inline int mlx5e_page_alloc_mapped(struct mlx5e_rq *rq,
- struct mlx5e_dma_info *dma_info)
+static inline int mlx5e_page_alloc_pool(struct mlx5e_rq *rq,
+ struct mlx5e_dma_info *dma_info)
{
if (mlx5e_rx_cache_get(rq, dma_info))
return 0;
dma_info->addr = dma_map_page(rq->pdev, dma_info->page, 0,
PAGE_SIZE, rq->buff.map_dir);
if (unlikely(dma_mapping_error(rq->pdev, dma_info->addr))) {
- put_page(dma_info->page);
+ page_pool_recycle_direct(rq->page_pool, dma_info->page);
dma_info->page = NULL;
return -ENOMEM;
}
return 0;
}
+static inline int mlx5e_page_alloc(struct mlx5e_rq *rq,
+ struct mlx5e_dma_info *dma_info)
+{
+ if (rq->umem)
+ return mlx5e_xsk_page_alloc_umem(rq, dma_info);
+ else
+ return mlx5e_page_alloc_pool(rq, dma_info);
+}
+
void mlx5e_page_dma_unmap(struct mlx5e_rq *rq, struct mlx5e_dma_info *dma_info)
{
dma_unmap_page(rq->pdev, dma_info->addr, PAGE_SIZE, rq->buff.map_dir);
}
-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)
{
if (likely(recycle)) {
if (mlx5e_rx_cache_put(rq, dma_info))
page_pool_recycle_direct(rq->page_pool, dma_info->page);
} else {
mlx5e_page_dma_unmap(rq, dma_info);
+ page_pool_release_page(rq->page_pool, dma_info->page);
put_page(dma_info->page);
}
}
+static inline void mlx5e_page_release(struct mlx5e_rq *rq,
+ struct mlx5e_dma_info *dma_info,
+ bool recycle)
+{
+ if (rq->umem)
+ /* The `recycle` parameter is ignored, and the page is always
+ * put into the Reuse Ring, because there is no way to return
+ * the page to the userspace when the interface goes down.
+ */
+ mlx5e_xsk_page_release(rq, dma_info);
+ else
+ mlx5e_page_release_dynamic(rq, dma_info, recycle);
+}
+
static inline int mlx5e_get_rx_frag(struct mlx5e_rq *rq,
struct mlx5e_wqe_frag_info *frag)
{
* offset) should just use the new one without replenishing again
* by themselves.
*/
- err = mlx5e_page_alloc_mapped(rq, frag->di);
+ err = mlx5e_page_alloc(rq, frag->di);
return err;
}
int err;
int i;
+ if (rq->umem) {
+ int pages_desired = wqe_bulk << rq->wqe.info.log_num_frags;
+
+ if (unlikely(!mlx5e_xsk_pages_enough_umem(rq, pages_desired)))
+ return -ENOMEM;
+ }
+
for (i = 0; i < wqe_bulk; i++) {
struct mlx5e_rx_wqe_cyc *wqe = mlx5_wq_cyc_get_wqe(wq, ix + i);
static void
mlx5e_free_rx_mpwqe(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi, bool recycle)
{
- const bool no_xdp_xmit =
- bitmap_empty(wi->xdp_xmit_bitmap, MLX5_MPWRQ_PAGES_PER_WQE);
+ bool no_xdp_xmit;
struct mlx5e_dma_info *dma_info = wi->umr.dma_info;
int i;
+ /* A common case for AF_XDP. */
+ if (bitmap_full(wi->xdp_xmit_bitmap, MLX5_MPWRQ_PAGES_PER_WQE))
+ return;
+
+ no_xdp_xmit = bitmap_empty(wi->xdp_xmit_bitmap,
+ MLX5_MPWRQ_PAGES_PER_WQE);
+
for (i = 0; i < MLX5_MPWRQ_PAGES_PER_WQE; i++)
if (no_xdp_xmit || !test_bit(i, wi->xdp_xmit_bitmap))
mlx5e_page_release(rq, &dma_info[i], recycle);
mlx5_wq_ll_update_db_record(wq);
}
-static inline u16 mlx5e_icosq_wrap_cnt(struct mlx5e_icosq *sq)
-{
- return mlx5_wq_cyc_get_ctr_wrap_cnt(&sq->wq, sq->pc);
-}
-
static inline void mlx5e_fill_icosq_frag_edge(struct mlx5e_icosq *sq,
struct mlx5_wq_cyc *wq,
u16 pi, u16 nnops)
int err;
int i;
+ if (rq->umem &&
+ unlikely(!mlx5e_xsk_pages_enough_umem(rq, MLX5_MPWRQ_PAGES_PER_WQE))) {
+ err = -ENOMEM;
+ goto err;
+ }
+
pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc);
contig_wqebbs_room = mlx5_wq_cyc_get_contig_wqebbs(wq, pi);
if (unlikely(contig_wqebbs_room < MLX5E_UMR_WQEBBS)) {
}
umr_wqe = mlx5_wq_cyc_get_wqe(wq, pi);
- if (unlikely(mlx5e_icosq_wrap_cnt(sq) < 2))
- memcpy(umr_wqe, &rq->mpwqe.umr_wqe,
- offsetof(struct mlx5e_umr_wqe, inline_mtts));
+ memcpy(umr_wqe, &rq->mpwqe.umr_wqe, offsetof(struct mlx5e_umr_wqe, inline_mtts));
for (i = 0; i < MLX5_MPWRQ_PAGES_PER_WQE; i++, dma_info++) {
- err = mlx5e_page_alloc_mapped(rq, dma_info);
+ err = mlx5e_page_alloc(rq, dma_info);
if (unlikely(err))
goto err_unmap;
umr_wqe->inline_mtts[i].ptag = cpu_to_be64(dma_info->addr | MLX5_EN_WR);
umr_wqe->uctrl.xlt_offset = cpu_to_be16(xlt_offset);
sq->db.ico_wqe[pi].opcode = MLX5_OPCODE_UMR;
+ sq->db.ico_wqe[pi].umr.rq = rq;
sq->pc += MLX5E_UMR_WQEBBS;
sq->doorbell_cseg = &umr_wqe->ctrl;
dma_info--;
mlx5e_page_release(rq, dma_info, true);
}
+
+err:
rq->stats->buff_alloc_err++;
return err;
return !!err;
}
-static void mlx5e_poll_ico_cq(struct mlx5e_cq *cq, struct mlx5e_rq *rq)
+void mlx5e_poll_ico_cq(struct mlx5e_cq *cq)
{
struct mlx5e_icosq *sq = container_of(cq, struct mlx5e_icosq, cq);
struct mlx5_cqe64 *cqe;
- u8 completed_umr = 0;
u16 sqcc;
int i;
if (likely(wi->opcode == MLX5_OPCODE_UMR)) {
sqcc += MLX5E_UMR_WQEBBS;
- completed_umr++;
+ wi->umr.rq->mpwqe.umr_completed++;
} else if (likely(wi->opcode == MLX5_OPCODE_NOP)) {
sqcc++;
} else {
sq->cc = sqcc;
mlx5_cqwq_update_db_record(&cq->wq);
-
- if (likely(completed_umr)) {
- mlx5e_post_rx_mpwqe(rq, completed_umr);
- rq->mpwqe.umr_in_progress -= completed_umr;
- }
}
bool mlx5e_post_rx_mpwqes(struct mlx5e_rq *rq)
{
struct mlx5e_icosq *sq = &rq->channel->icosq;
struct mlx5_wq_ll *wq = &rq->mpwqe.wq;
+ u8 umr_completed = rq->mpwqe.umr_completed;
+ int alloc_err = 0;
u8 missing, i;
u16 head;
if (unlikely(!test_bit(MLX5E_RQ_STATE_ENABLED, &rq->state)))
return false;
- mlx5e_poll_ico_cq(&sq->cq, rq);
+ if (umr_completed) {
+ mlx5e_post_rx_mpwqe(rq, umr_completed);
+ rq->mpwqe.umr_in_progress -= umr_completed;
+ rq->mpwqe.umr_completed = 0;
+ }
missing = mlx5_wq_ll_missing(wq) - rq->mpwqe.umr_in_progress;
head = rq->mpwqe.actual_wq_head;
i = missing;
do {
- if (unlikely(mlx5e_alloc_rx_mpwqe(rq, head)))
+ alloc_err = mlx5e_alloc_rx_mpwqe(rq, head);
+
+ if (unlikely(alloc_err))
break;
head = mlx5_wq_ll_get_wqe_next_ix(wq, head);
} while (--i);
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 (unlikely(alloc_err == -ENOMEM && rq->umem))
+ return true;
+
return false;
}
if (unlikely(get_ip_proto(skb, network_depth, proto) == IPPROTO_SCTP))
goto csum_unnecessary;
+ stats->csum_complete++;
skb->ip_summed = CHECKSUM_COMPLETE;
skb->csum = csum_unfold((__force __sum16)cqe->check_sum);
+
+ if (test_bit(MLX5E_RQ_STATE_CSUM_FULL, &rq->state))
+ return; /* CQE csum covers all received bytes */
+
+ /* csum might need some fixups ...*/
if (network_depth > ETH_HLEN)
/* CQE csum is calculated from the IP header and does
* not cover VLAN headers (if present). This will add
skb->csum);
mlx5e_skb_padding_csum(skb, network_depth, proto, stats);
- stats->csum_complete++;
return;
}
}
rcu_read_lock();
- consumed = mlx5e_xdp_handle(rq, di, va, &rx_headroom, &cqe_bcnt);
+ consumed = mlx5e_xdp_handle(rq, di, va, &rx_headroom, &cqe_bcnt, false);
rcu_read_unlock();
if (consumed)
return NULL; /* page/packet was consumed by XDP */
wi = get_frag(rq, ci);
cqe_bcnt = be32_to_cpu(cqe->byte_cnt);
- skb = rq->wqe.skb_from_cqe(rq, cqe, wi, cqe_bcnt);
+ skb = INDIRECT_CALL_2(rq->wqe.skb_from_cqe,
+ mlx5e_skb_from_cqe_linear,
+ mlx5e_skb_from_cqe_nonlinear,
+ rq, cqe, wi, cqe_bcnt);
if (!skb) {
/* probably for XDP */
if (__test_and_clear_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags)) {
prefetch(data);
rcu_read_lock();
- consumed = mlx5e_xdp_handle(rq, di, va, &rx_headroom, &cqe_bcnt32);
+ consumed = mlx5e_xdp_handle(rq, di, va, &rx_headroom, &cqe_bcnt32, false);
rcu_read_unlock();
if (consumed) {
if (__test_and_clear_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags))
cqe_bcnt = mpwrq_get_cqe_byte_cnt(cqe);
- skb = rq->mpwqe.skb_from_cqe_mpwrq(rq, wi, cqe_bcnt, head_offset,
- page_idx);
+ skb = INDIRECT_CALL_2(rq->mpwqe.skb_from_cqe_mpwrq,
+ mlx5e_skb_from_cqe_mpwrq_linear,
+ mlx5e_skb_from_cqe_mpwrq_nonlinear,
+ rq, wi, cqe_bcnt, head_offset, page_idx);
if (!skb)
goto mpwrq_cqe_out;
mlx5_cqwq_pop(cqwq);
- rq->handle_rx_cqe(rq, cqe);
+ INDIRECT_CALL_2(rq->handle_rx_cqe, mlx5e_handle_rx_cqe_mpwrq,
+ mlx5e_handle_rx_cqe, rq, cqe);
} while ((++work_done < budget) && (cqe = mlx5_cqwq_get_cqe(cqwq)));
out:
wi = get_frag(rq, ci);
cqe_bcnt = be32_to_cpu(cqe->byte_cnt);
- skb = rq->wqe.skb_from_cqe(rq, cqe, wi, cqe_bcnt);
+ skb = INDIRECT_CALL_2(rq->wqe.skb_from_cqe,
+ mlx5e_skb_from_cqe_linear,
+ mlx5e_skb_from_cqe_nonlinear,
+ rq, cqe, wi, cqe_bcnt);
if (!skb)
goto wq_free_wqe;
wi = get_frag(rq, ci);
cqe_bcnt = be32_to_cpu(cqe->byte_cnt);
- skb = rq->wqe.skb_from_cqe(rq, cqe, wi, cqe_bcnt);
+ skb = INDIRECT_CALL_2(rq->wqe.skb_from_cqe,
+ mlx5e_skb_from_cqe_linear,
+ mlx5e_skb_from_cqe_nonlinear,
+ rq, cqe, wi, cqe_bcnt);
if (unlikely(!skb)) {
/* a DROP, save the page-reuse checks */
mlx5e_free_rx_wqe(rq, wi, true);
return mlx5_cmd_exec(dev, in, inlen, out, sizeof(out));
}
+int mlx5_eswitch_modify_esw_vport_context(struct mlx5_eswitch *esw, u16 vport,
+ void *in, int inlen)
+{
+ return modify_esw_vport_context_cmd(esw->dev, vport, in, inlen);
+}
+
+static int query_esw_vport_context_cmd(struct mlx5_core_dev *dev, u16 vport,
+ void *out, int outlen)
+{
+ u32 in[MLX5_ST_SZ_DW(query_esw_vport_context_in)] = {};
+
+ MLX5_SET(query_esw_vport_context_in, in, opcode,
+ MLX5_CMD_OP_QUERY_ESW_VPORT_CONTEXT);
+ MLX5_SET(modify_esw_vport_context_in, in, vport_number, vport);
+ MLX5_SET(modify_esw_vport_context_in, in, other_vport, 1);
+ return mlx5_cmd_exec(dev, in, sizeof(in), out, outlen);
+}
+
+int mlx5_eswitch_query_esw_vport_context(struct mlx5_eswitch *esw, u16 vport,
+ void *out, int outlen)
+{
+ return query_esw_vport_context_cmd(esw->dev, vport, out, outlen);
+}
+
static int modify_esw_vport_cvlan(struct mlx5_core_dev *dev, u16 vport,
u16 vlan, u8 qos, u8 set_flags)
{
fdb_add:
/* SRIOV is enabled: Forward UC MAC to vport */
- if (esw->fdb_table.legacy.fdb && esw->mode == SRIOV_LEGACY)
+ if (esw->fdb_table.legacy.fdb && esw->mode == MLX5_ESWITCH_LEGACY)
vaddr->flow_rule = esw_fdb_set_vport_rule(esw, mac, vport);
esw_debug(esw->dev, "\tADDED UC MAC: vport[%d] %pM fr(%p)\n",
struct mlx5_eswitch *esw = dev->priv.eswitch;
u8 mac[ETH_ALEN];
- mlx5_query_nic_vport_mac_address(dev, vport->vport, mac);
+ mlx5_query_nic_vport_mac_address(dev, vport->vport, true, mac);
esw_debug(dev, "vport[%d] Context Changed: perm mac: %pM\n",
vport->vport, mac);
vport->vport, MLX5_CAP_ESW_EGRESS_ACL(dev, log_max_ft_size));
root_ns = mlx5_get_flow_vport_acl_namespace(dev, MLX5_FLOW_NAMESPACE_ESW_EGRESS,
- vport->vport);
+ mlx5_eswitch_vport_num_to_index(esw, vport->vport));
if (!root_ns) {
esw_warn(dev, "Failed to get E-Switch egress flow namespace for vport (%d)\n", vport->vport);
return -EOPNOTSUPP;
vport->vport, MLX5_CAP_ESW_INGRESS_ACL(dev, log_max_ft_size));
root_ns = mlx5_get_flow_vport_acl_namespace(dev, MLX5_FLOW_NAMESPACE_ESW_INGRESS,
- vport->vport);
+ mlx5_eswitch_vport_num_to_index(esw, vport->vport));
if (!root_ns) {
esw_warn(dev, "Failed to get E-Switch ingress flow namespace for vport (%d)\n", vport->vport);
return -EOPNOTSUPP;
vport->ingress.drop_rule = NULL;
vport->ingress.allow_rule = NULL;
+
+ esw_vport_del_ingress_acl_modify_metadata(esw, vport);
}
void esw_vport_disable_ingress_acl(struct mlx5_eswitch *esw,
struct mlx5_vport *vport)
{
u16 vport_num = vport->vport;
+ int flags;
if (esw->manager_vport == vport_num)
return;
vport->info.node_guid);
}
+ flags = (vport->info.vlan || vport->info.qos) ?
+ SET_VLAN_STRIP | SET_VLAN_INSERT : 0;
modify_esw_vport_cvlan(esw->dev, vport_num, vport->info.vlan, vport->info.qos,
- (vport->info.vlan || vport->info.qos));
+ flags);
/* Only legacy mode needs ACLs */
- if (esw->mode == SRIOV_LEGACY) {
+ if (esw->mode == MLX5_ESWITCH_LEGACY) {
esw_vport_ingress_config(esw, vport);
esw_vport_egress_config(esw, vport);
}
esw_debug(esw->dev, "Enabling VPORT(%d)\n", vport_num);
/* Create steering drop counters for ingress and egress ACLs */
- if (vport_num && esw->mode == SRIOV_LEGACY)
+ if (vport_num && esw->mode == MLX5_ESWITCH_LEGACY)
esw_vport_create_drop_counters(vport);
/* Restore old vport configuration */
vport->enabled_events = 0;
esw_vport_disable_qos(esw, vport);
if (esw->manager_vport != vport_num &&
- esw->mode == SRIOV_LEGACY) {
+ esw->mode == MLX5_ESWITCH_LEGACY) {
mlx5_modify_vport_admin_state(esw->dev,
MLX5_VPORT_STATE_OP_MOD_ESW_VPORT,
vport_num, 1,
return NOTIFY_OK;
}
+/**
+ * mlx5_esw_query_functions - Returns raw output about functions state
+ * @dev: Pointer to device to query
+ *
+ * mlx5_esw_query_functions() allocates and returns functions changed
+ * raw output memory pointer from device on success. Otherwise returns ERR_PTR.
+ * Caller must free the memory using kvfree() when valid pointer is returned.
+ */
+const u32 *mlx5_esw_query_functions(struct mlx5_core_dev *dev)
+{
+ int outlen = MLX5_ST_SZ_BYTES(query_esw_functions_out);
+ u32 in[MLX5_ST_SZ_DW(query_esw_functions_in)] = {};
+ u32 *out;
+ int err;
+
+ out = kvzalloc(outlen, GFP_KERNEL);
+ if (!out)
+ return ERR_PTR(-ENOMEM);
+
+ MLX5_SET(query_esw_functions_in, in, opcode,
+ MLX5_CMD_OP_QUERY_ESW_FUNCTIONS);
+
+ err = mlx5_cmd_exec(dev, in, sizeof(in), out, outlen);
+ if (!err)
+ return out;
+
+ kvfree(out);
+ return ERR_PTR(err);
+}
+
+static void mlx5_eswitch_event_handlers_register(struct mlx5_eswitch *esw)
+{
+ MLX5_NB_INIT(&esw->nb, eswitch_vport_event, NIC_VPORT_CHANGE);
+ mlx5_eq_notifier_register(esw->dev, &esw->nb);
+
+ if (esw->mode == MLX5_ESWITCH_OFFLOADS && mlx5_eswitch_is_funcs_handler(esw->dev)) {
+ MLX5_NB_INIT(&esw->esw_funcs.nb, mlx5_esw_funcs_changed_handler,
+ ESW_FUNCTIONS_CHANGED);
+ mlx5_eq_notifier_register(esw->dev, &esw->esw_funcs.nb);
+ }
+}
+
+static void mlx5_eswitch_event_handlers_unregister(struct mlx5_eswitch *esw)
+{
+ if (esw->mode == MLX5_ESWITCH_OFFLOADS && mlx5_eswitch_is_funcs_handler(esw->dev))
+ mlx5_eq_notifier_unregister(esw->dev, &esw->esw_funcs.nb);
+
+ mlx5_eq_notifier_unregister(esw->dev, &esw->nb);
+
+ flush_workqueue(esw->work_queue);
+}
+
/* Public E-Switch API */
#define ESW_ALLOWED(esw) ((esw) && MLX5_ESWITCH_MANAGER((esw)->dev))
-int mlx5_eswitch_enable_sriov(struct mlx5_eswitch *esw, int nvfs, int mode)
+int mlx5_eswitch_enable(struct mlx5_eswitch *esw, int mode)
{
- int vf_nvports = 0, total_nvports = 0;
struct mlx5_vport *vport;
int err;
int i, enabled_events;
if (!ESW_ALLOWED(esw) ||
!MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, ft_support)) {
- esw_warn(esw->dev, "E-Switch FDB is not supported, aborting ...\n");
+ esw_warn(esw->dev, "FDB is not supported, aborting ...\n");
return -EOPNOTSUPP;
}
if (!MLX5_CAP_ESW_INGRESS_ACL(esw->dev, ft_support))
- esw_warn(esw->dev, "E-Switch ingress ACL is not supported by FW\n");
+ esw_warn(esw->dev, "ingress ACL is not supported by FW\n");
if (!MLX5_CAP_ESW_EGRESS_ACL(esw->dev, ft_support))
- esw_warn(esw->dev, "E-Switch engress ACL is not supported by FW\n");
-
- esw_info(esw->dev, "E-Switch enable SRIOV: nvfs(%d) mode (%d)\n", nvfs, mode);
-
- if (mode == SRIOV_OFFLOADS) {
- if (mlx5_core_is_ecpf_esw_manager(esw->dev)) {
- err = mlx5_query_host_params_num_vfs(esw->dev, &vf_nvports);
- if (err)
- return err;
- total_nvports = esw->total_vports;
- } else {
- vf_nvports = nvfs;
- total_nvports = nvfs + MLX5_SPECIAL_VPORTS(esw->dev);
- }
- }
+ esw_warn(esw->dev, "engress ACL is not supported by FW\n");
esw->mode = mode;
mlx5_lag_update(esw->dev);
- if (mode == SRIOV_LEGACY) {
+ if (mode == MLX5_ESWITCH_LEGACY) {
err = esw_create_legacy_table(esw);
if (err)
goto abort;
} else {
mlx5_reload_interface(esw->dev, MLX5_INTERFACE_PROTOCOL_ETH);
mlx5_reload_interface(esw->dev, MLX5_INTERFACE_PROTOCOL_IB);
- err = esw_offloads_init(esw, vf_nvports, total_nvports);
+ err = esw_offloads_init(esw);
}
if (err)
if (err)
esw_warn(esw->dev, "Failed to create eswitch TSAR");
- /* Don't enable vport events when in SRIOV_OFFLOADS mode, since:
- * 1. L2 table (MPFS) is programmed by PF/VF representors netdevs set_rx_mode
- * 2. FDB/Eswitch is programmed by user space tools
- */
- enabled_events = (mode == SRIOV_LEGACY) ? SRIOV_VPORT_EVENTS : 0;
+ enabled_events = (mode == MLX5_ESWITCH_LEGACY) ? SRIOV_VPORT_EVENTS :
+ UC_ADDR_CHANGE;
/* Enable PF vport */
vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_PF);
}
/* Enable VF vports */
- mlx5_esw_for_each_vf_vport(esw, i, vport, nvfs)
+ mlx5_esw_for_each_vf_vport(esw, i, vport, esw->esw_funcs.num_vfs)
esw_enable_vport(esw, vport, enabled_events);
- if (mode == SRIOV_LEGACY) {
- MLX5_NB_INIT(&esw->nb, eswitch_vport_event, NIC_VPORT_CHANGE);
- mlx5_eq_notifier_register(esw->dev, &esw->nb);
- }
+ mlx5_eswitch_event_handlers_register(esw);
+
+ esw_info(esw->dev, "Enable: mode(%s), nvfs(%d), active vports(%d)\n",
+ mode == MLX5_ESWITCH_LEGACY ? "LEGACY" : "OFFLOADS",
+ esw->esw_funcs.num_vfs, esw->enabled_vports);
- esw_info(esw->dev, "SRIOV enabled: active vports(%d)\n",
- esw->enabled_vports);
return 0;
abort:
- esw->mode = SRIOV_NONE;
+ esw->mode = MLX5_ESWITCH_NONE;
- if (mode == SRIOV_OFFLOADS) {
+ if (mode == MLX5_ESWITCH_OFFLOADS) {
mlx5_reload_interface(esw->dev, MLX5_INTERFACE_PROTOCOL_IB);
mlx5_reload_interface(esw->dev, MLX5_INTERFACE_PROTOCOL_ETH);
}
return err;
}
-void mlx5_eswitch_disable_sriov(struct mlx5_eswitch *esw)
+void mlx5_eswitch_disable(struct mlx5_eswitch *esw)
{
struct esw_mc_addr *mc_promisc;
struct mlx5_vport *vport;
int old_mode;
int i;
- if (!ESW_ALLOWED(esw) || esw->mode == SRIOV_NONE)
+ if (!ESW_ALLOWED(esw) || esw->mode == MLX5_ESWITCH_NONE)
return;
- esw_info(esw->dev, "disable SRIOV: active vports(%d) mode(%d)\n",
- esw->enabled_vports, esw->mode);
+ esw_info(esw->dev, "Disable: mode(%s), nvfs(%d), active vports(%d)\n",
+ esw->mode == MLX5_ESWITCH_LEGACY ? "LEGACY" : "OFFLOADS",
+ esw->esw_funcs.num_vfs, esw->enabled_vports);
mc_promisc = &esw->mc_promisc;
-
- if (esw->mode == SRIOV_LEGACY)
- mlx5_eq_notifier_unregister(esw->dev, &esw->nb);
+ mlx5_eswitch_event_handlers_unregister(esw);
mlx5_esw_for_all_vports(esw, i, vport)
esw_disable_vport(esw, vport);
esw_destroy_tsar(esw);
- if (esw->mode == SRIOV_LEGACY)
+ if (esw->mode == MLX5_ESWITCH_LEGACY)
esw_destroy_legacy_table(esw);
- else if (esw->mode == SRIOV_OFFLOADS)
+ else if (esw->mode == MLX5_ESWITCH_OFFLOADS)
esw_offloads_cleanup(esw);
old_mode = esw->mode;
- esw->mode = SRIOV_NONE;
+ esw->mode = MLX5_ESWITCH_NONE;
mlx5_lag_update(esw->dev);
- if (old_mode == SRIOV_OFFLOADS) {
+ if (old_mode == MLX5_ESWITCH_OFFLOADS) {
mlx5_reload_interface(esw->dev, MLX5_INTERFACE_PROTOCOL_IB);
mlx5_reload_interface(esw->dev, MLX5_INTERFACE_PROTOCOL_ETH);
}
int mlx5_eswitch_init(struct mlx5_core_dev *dev)
{
- int total_vports = MLX5_TOTAL_VPORTS(dev);
struct mlx5_eswitch *esw;
struct mlx5_vport *vport;
+ int total_vports;
int err, i;
if (!MLX5_VPORT_MANAGER(dev))
return 0;
+ total_vports = mlx5_eswitch_get_total_vports(dev);
+
esw_info(dev,
"Total vports %d, per vport: max uc(%d) max mc(%d)\n",
total_vports,
esw->dev = dev;
esw->manager_vport = mlx5_eswitch_manager_vport(dev);
+ esw->first_host_vport = mlx5_eswitch_first_host_vport_num(dev);
esw->work_queue = create_singlethread_workqueue("mlx5_esw_wq");
if (!esw->work_queue) {
}
esw->enabled_vports = 0;
- esw->mode = SRIOV_NONE;
+ esw->mode = MLX5_ESWITCH_NONE;
esw->offloads.inline_mode = MLX5_INLINE_MODE_NONE;
- if (MLX5_CAP_ESW_FLOWTABLE_FDB(dev, reformat) &&
- MLX5_CAP_ESW_FLOWTABLE_FDB(dev, decap))
- esw->offloads.encap = DEVLINK_ESWITCH_ENCAP_MODE_BASIC;
- else
- esw->offloads.encap = DEVLINK_ESWITCH_ENCAP_MODE_NONE;
dev->priv.eswitch = esw;
return 0;
ether_addr_copy(evport->info.mac, mac);
evport->info.node_guid = node_guid;
- if (evport->enabled && esw->mode == SRIOV_LEGACY)
+ if (evport->enabled && esw->mode == MLX5_ESWITCH_LEGACY)
err = esw_vport_ingress_config(esw, evport);
unlock:
evport->info.vlan = vlan;
evport->info.qos = qos;
- if (evport->enabled && esw->mode == SRIOV_LEGACY) {
+ if (evport->enabled && esw->mode == MLX5_ESWITCH_LEGACY) {
err = esw_vport_ingress_config(esw, evport);
if (err)
goto unlock;
mlx5_core_warn(esw->dev,
"Spoofchk in set while MAC is invalid, vport(%d)\n",
evport->vport);
- if (evport->enabled && esw->mode == SRIOV_LEGACY)
+ if (evport->enabled && esw->mode == MLX5_ESWITCH_LEGACY)
err = esw_vport_ingress_config(esw, evport);
if (err)
evport->info.spoofchk = pschk;
return -EPERM;
mutex_lock(&esw->state_lock);
- if (esw->mode != SRIOV_LEGACY) {
+ if (esw->mode != MLX5_ESWITCH_LEGACY) {
err = -EOPNOTSUPP;
goto out;
}
return -EPERM;
mutex_lock(&esw->state_lock);
- if (esw->mode != SRIOV_LEGACY) {
+ if (esw->mode != MLX5_ESWITCH_LEGACY) {
err = -EOPNOTSUPP;
goto out;
}
u64 bytes = 0;
int err = 0;
- if (!vport->enabled || esw->mode != SRIOV_LEGACY)
+ if (!vport->enabled || esw->mode != MLX5_ESWITCH_LEGACY)
return 0;
if (vport->egress.drop_counter)
u8 mlx5_eswitch_mode(struct mlx5_eswitch *esw)
{
- return ESW_ALLOWED(esw) ? esw->mode : SRIOV_NONE;
+ return ESW_ALLOWED(esw) ? esw->mode : MLX5_ESWITCH_NONE;
}
EXPORT_SYMBOL_GPL(mlx5_eswitch_mode);
+enum devlink_eswitch_encap_mode
+mlx5_eswitch_get_encap_mode(const struct mlx5_core_dev *dev)
+{
+ struct mlx5_eswitch *esw;
+
+ esw = dev->priv.eswitch;
+ return ESW_ALLOWED(esw) ? esw->offloads.encap :
+ DEVLINK_ESWITCH_ENCAP_MODE_NONE;
+}
+EXPORT_SYMBOL(mlx5_eswitch_get_encap_mode);
+
bool mlx5_esw_lag_prereq(struct mlx5_core_dev *dev0, struct mlx5_core_dev *dev1)
{
- if ((dev0->priv.eswitch->mode == SRIOV_NONE &&
- dev1->priv.eswitch->mode == SRIOV_NONE) ||
- (dev0->priv.eswitch->mode == SRIOV_OFFLOADS &&
- dev1->priv.eswitch->mode == SRIOV_OFFLOADS))
+ if ((dev0->priv.eswitch->mode == MLX5_ESWITCH_NONE &&
+ dev1->priv.eswitch->mode == MLX5_ESWITCH_NONE) ||
+ (dev0->priv.eswitch->mode == MLX5_ESWITCH_OFFLOADS &&
+ dev1->priv.eswitch->mode == MLX5_ESWITCH_OFFLOADS))
return true;
return false;
bool mlx5_esw_multipath_prereq(struct mlx5_core_dev *dev0,
struct mlx5_core_dev *dev1)
{
- return (dev0->priv.eswitch->mode == SRIOV_OFFLOADS &&
- dev1->priv.eswitch->mode == SRIOV_OFFLOADS);
+ return (dev0->priv.eswitch->mode == MLX5_ESWITCH_OFFLOADS &&
+ dev1->priv.eswitch->mode == MLX5_ESWITCH_OFFLOADS);
+}
+
+void mlx5_eswitch_update_num_of_vfs(struct mlx5_eswitch *esw, const int num_vfs)
+{
+ const u32 *out;
+
+ WARN_ON_ONCE(esw->mode != MLX5_ESWITCH_NONE);
+
+ if (!mlx5_core_is_ecpf_esw_manager(esw->dev)) {
+ esw->esw_funcs.num_vfs = num_vfs;
+ return;
+ }
+
+ out = mlx5_esw_query_functions(esw->dev);
+ if (IS_ERR(out))
+ return;
+
+ esw->esw_funcs.num_vfs = MLX5_GET(query_esw_functions_out, out,
+ host_params_context.host_num_of_vfs);
+ kvfree(out);
}
#include "en.h"
#include "fs_core.h"
#include "lib/devcom.h"
-#include "ecpf.h"
#include "lib/eq.h"
/* There are two match-all miss flows, one for unicast dst mac and
return 1;
}
+static void
+mlx5_eswitch_set_rule_source_port(struct mlx5_eswitch *esw,
+ struct mlx5_flow_spec *spec,
+ struct mlx5_esw_flow_attr *attr)
+{
+ void *misc2;
+ void *misc;
+
+ /* Use metadata matching because vport is not represented by single
+ * VHCA in dual-port RoCE mode, and matching on source vport may fail.
+ */
+ if (mlx5_eswitch_vport_match_metadata_enabled(esw)) {
+ misc2 = MLX5_ADDR_OF(fte_match_param, spec->match_value, misc_parameters_2);
+ MLX5_SET(fte_match_set_misc2, misc2, metadata_reg_c_0,
+ mlx5_eswitch_get_vport_metadata_for_match(attr->in_mdev->priv.eswitch,
+ attr->in_rep->vport));
+
+ misc2 = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, misc_parameters_2);
+ MLX5_SET_TO_ONES(fte_match_set_misc2, misc2, metadata_reg_c_0);
+
+ spec->match_criteria_enable |= MLX5_MATCH_MISC_PARAMETERS_2;
+ misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, misc_parameters);
+ if (memchr_inv(misc, 0, MLX5_ST_SZ_BYTES(fte_match_set_misc)))
+ spec->match_criteria_enable |= MLX5_MATCH_MISC_PARAMETERS;
+ } else {
+ misc = MLX5_ADDR_OF(fte_match_param, spec->match_value, misc_parameters);
+ MLX5_SET(fte_match_set_misc, misc, source_port, attr->in_rep->vport);
+
+ if (MLX5_CAP_ESW(esw->dev, merged_eswitch))
+ MLX5_SET(fte_match_set_misc, misc,
+ source_eswitch_owner_vhca_id,
+ MLX5_CAP_GEN(attr->in_mdev, vhca_id));
+
+ misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, misc_parameters);
+ MLX5_SET_TO_ONES(fte_match_set_misc, misc, source_port);
+ if (MLX5_CAP_ESW(esw->dev, merged_eswitch))
+ MLX5_SET_TO_ONES(fte_match_set_misc, misc,
+ source_eswitch_owner_vhca_id);
+
+ spec->match_criteria_enable |= MLX5_MATCH_MISC_PARAMETERS;
+ }
+
+ if (MLX5_CAP_ESW_FLOWTABLE(esw->dev, flow_source) &&
+ attr->in_rep->vport == MLX5_VPORT_UPLINK)
+ spec->flow_context.flow_source = MLX5_FLOW_CONTEXT_FLOW_SOURCE_UPLINK;
+}
+
struct mlx5_flow_handle *
mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw,
struct mlx5_flow_spec *spec,
struct mlx5_flow_handle *rule;
struct mlx5_flow_table *fdb;
int j, i = 0;
- void *misc;
- if (esw->mode != SRIOV_OFFLOADS)
+ if (esw->mode != MLX5_ESWITCH_OFFLOADS)
return ERR_PTR(-EOPNOTSUPP);
flow_act.action = attr->action;
i++;
}
- misc = MLX5_ADDR_OF(fte_match_param, spec->match_value, misc_parameters);
- MLX5_SET(fte_match_set_misc, misc, source_port, attr->in_rep->vport);
-
- if (MLX5_CAP_ESW(esw->dev, merged_eswitch))
- MLX5_SET(fte_match_set_misc, misc,
- source_eswitch_owner_vhca_id,
- MLX5_CAP_GEN(attr->in_mdev, vhca_id));
+ mlx5_eswitch_set_rule_source_port(esw, spec, attr);
- misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, misc_parameters);
- MLX5_SET_TO_ONES(fte_match_set_misc, misc, source_port);
- if (MLX5_CAP_ESW(esw->dev, merged_eswitch))
- MLX5_SET_TO_ONES(fte_match_set_misc, misc,
- source_eswitch_owner_vhca_id);
-
- spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS;
if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_DECAP) {
if (attr->tunnel_match_level != MLX5_MATCH_NONE)
spec->match_criteria_enable |= MLX5_MATCH_OUTER_HEADERS;
goto err_esw_get;
}
- rule = mlx5_add_flow_rules(fdb, spec, &flow_act, dest, i);
+ if (mlx5_eswitch_termtbl_required(esw, &flow_act, spec))
+ rule = mlx5_eswitch_add_termtbl_rule(esw, fdb, spec, attr,
+ &flow_act, dest, i);
+ else
+ rule = mlx5_add_flow_rules(fdb, spec, &flow_act, dest, i);
if (IS_ERR(rule))
goto err_add_rule;
else
struct mlx5_flow_table *fast_fdb;
struct mlx5_flow_table *fwd_fdb;
struct mlx5_flow_handle *rule;
- void *misc;
int i;
fast_fdb = esw_get_prio_table(esw, attr->chain, attr->prio, 0);
dest[i].ft = fwd_fdb,
i++;
- misc = MLX5_ADDR_OF(fte_match_param, spec->match_value, misc_parameters);
- MLX5_SET(fte_match_set_misc, misc, source_port, attr->in_rep->vport);
-
- if (MLX5_CAP_ESW(esw->dev, merged_eswitch))
- MLX5_SET(fte_match_set_misc, misc,
- source_eswitch_owner_vhca_id,
- MLX5_CAP_GEN(attr->in_mdev, vhca_id));
+ mlx5_eswitch_set_rule_source_port(esw, spec, attr);
- misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, misc_parameters);
- MLX5_SET_TO_ONES(fte_match_set_misc, misc, source_port);
- if (MLX5_CAP_ESW(esw->dev, merged_eswitch))
- MLX5_SET_TO_ONES(fte_match_set_misc, misc,
- source_eswitch_owner_vhca_id);
-
- if (attr->match_level == MLX5_MATCH_NONE)
- spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS;
- else
- spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS |
- MLX5_MATCH_MISC_PARAMETERS;
+ spec->match_criteria_enable |= MLX5_MATCH_MISC_PARAMETERS;
+ if (attr->match_level != MLX5_MATCH_NONE)
+ spec->match_criteria_enable |= MLX5_MATCH_OUTER_HEADERS;
rule = mlx5_add_flow_rules(fast_fdb, spec, &flow_act, dest, i);
bool fwd_rule)
{
bool split = (attr->split_count > 0);
+ int i;
mlx5_del_flow_rules(rule);
+
+ /* unref the term table */
+ for (i = 0; i < MLX5_MAX_FLOW_FWD_VPORTS; i++) {
+ if (attr->dests[i].termtbl)
+ mlx5_eswitch_termtbl_put(esw, attr->dests[i].termtbl);
+ }
+
esw->offloads.num_flows--;
if (fwd_rule) {
static int esw_set_global_vlan_pop(struct mlx5_eswitch *esw, u8 val)
{
struct mlx5_eswitch_rep *rep;
- int vf_vport, err = 0;
+ int i, err = 0;
esw_debug(esw->dev, "%s applying global %s policy\n", __func__, val ? "pop" : "none");
- for (vf_vport = 1; vf_vport < esw->enabled_vports; vf_vport++) {
- rep = &esw->offloads.vport_reps[vf_vport];
- if (atomic_read(&rep->rep_if[REP_ETH].state) != REP_LOADED)
+ mlx5_esw_for_each_host_func_rep(esw, i, rep, esw->esw_funcs.num_vfs) {
+ if (atomic_read(&rep->rep_data[REP_ETH].state) != REP_LOADED)
continue;
err = __mlx5_eswitch_set_vport_vlan(esw, rep->vport, 0, 0, val);
mlx5_del_flow_rules(rule);
}
-static void peer_miss_rules_setup(struct mlx5_core_dev *peer_dev,
+static int mlx5_eswitch_enable_passing_vport_metadata(struct mlx5_eswitch *esw)
+{
+ u32 out[MLX5_ST_SZ_DW(query_esw_vport_context_out)] = {};
+ u32 in[MLX5_ST_SZ_DW(modify_esw_vport_context_in)] = {};
+ u8 fdb_to_vport_reg_c_id;
+ int err;
+
+ err = mlx5_eswitch_query_esw_vport_context(esw, esw->manager_vport,
+ out, sizeof(out));
+ if (err)
+ return err;
+
+ fdb_to_vport_reg_c_id = MLX5_GET(query_esw_vport_context_out, out,
+ esw_vport_context.fdb_to_vport_reg_c_id);
+
+ fdb_to_vport_reg_c_id |= MLX5_FDB_TO_VPORT_REG_C_0;
+ MLX5_SET(modify_esw_vport_context_in, in,
+ esw_vport_context.fdb_to_vport_reg_c_id, fdb_to_vport_reg_c_id);
+
+ MLX5_SET(modify_esw_vport_context_in, in,
+ field_select.fdb_to_vport_reg_c_id, 1);
+
+ return mlx5_eswitch_modify_esw_vport_context(esw, esw->manager_vport,
+ in, sizeof(in));
+}
+
+static int mlx5_eswitch_disable_passing_vport_metadata(struct mlx5_eswitch *esw)
+{
+ u32 out[MLX5_ST_SZ_DW(query_esw_vport_context_out)] = {};
+ u32 in[MLX5_ST_SZ_DW(modify_esw_vport_context_in)] = {};
+ u8 fdb_to_vport_reg_c_id;
+ int err;
+
+ err = mlx5_eswitch_query_esw_vport_context(esw, esw->manager_vport,
+ out, sizeof(out));
+ if (err)
+ return err;
+
+ fdb_to_vport_reg_c_id = MLX5_GET(query_esw_vport_context_out, out,
+ esw_vport_context.fdb_to_vport_reg_c_id);
+
+ fdb_to_vport_reg_c_id &= ~MLX5_FDB_TO_VPORT_REG_C_0;
+
+ MLX5_SET(modify_esw_vport_context_in, in,
+ esw_vport_context.fdb_to_vport_reg_c_id, fdb_to_vport_reg_c_id);
+
+ MLX5_SET(modify_esw_vport_context_in, in,
+ field_select.fdb_to_vport_reg_c_id, 1);
+
+ return mlx5_eswitch_modify_esw_vport_context(esw, esw->manager_vport,
+ in, sizeof(in));
+}
+
+static void peer_miss_rules_setup(struct mlx5_eswitch *esw,
+ struct mlx5_core_dev *peer_dev,
struct mlx5_flow_spec *spec,
struct mlx5_flow_destination *dest)
{
- void *misc = MLX5_ADDR_OF(fte_match_param, spec->match_value,
- misc_parameters);
+ void *misc;
- MLX5_SET(fte_match_set_misc, misc, source_eswitch_owner_vhca_id,
- MLX5_CAP_GEN(peer_dev, vhca_id));
+ if (mlx5_eswitch_vport_match_metadata_enabled(esw)) {
+ misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
+ misc_parameters_2);
+ MLX5_SET_TO_ONES(fte_match_set_misc2, misc, metadata_reg_c_0);
- spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS;
+ spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS_2;
+ } else {
+ misc = MLX5_ADDR_OF(fte_match_param, spec->match_value,
+ misc_parameters);
- misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
- misc_parameters);
- MLX5_SET_TO_ONES(fte_match_set_misc, misc, source_port);
- MLX5_SET_TO_ONES(fte_match_set_misc, misc,
- source_eswitch_owner_vhca_id);
+ MLX5_SET(fte_match_set_misc, misc, source_eswitch_owner_vhca_id,
+ MLX5_CAP_GEN(peer_dev, vhca_id));
+
+ spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS;
+
+ misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
+ misc_parameters);
+ MLX5_SET_TO_ONES(fte_match_set_misc, misc, source_port);
+ MLX5_SET_TO_ONES(fte_match_set_misc, misc,
+ source_eswitch_owner_vhca_id);
+ }
dest->type = MLX5_FLOW_DESTINATION_TYPE_VPORT;
dest->vport.num = peer_dev->priv.eswitch->manager_vport;
dest->vport.flags |= MLX5_FLOW_DEST_VPORT_VHCA_ID;
}
+static void esw_set_peer_miss_rule_source_port(struct mlx5_eswitch *esw,
+ struct mlx5_eswitch *peer_esw,
+ struct mlx5_flow_spec *spec,
+ u16 vport)
+{
+ void *misc;
+
+ if (mlx5_eswitch_vport_match_metadata_enabled(esw)) {
+ misc = MLX5_ADDR_OF(fte_match_param, spec->match_value,
+ misc_parameters_2);
+ MLX5_SET(fte_match_set_misc2, misc, metadata_reg_c_0,
+ mlx5_eswitch_get_vport_metadata_for_match(peer_esw,
+ vport));
+ } else {
+ misc = MLX5_ADDR_OF(fte_match_param, spec->match_value,
+ misc_parameters);
+ MLX5_SET(fte_match_set_misc, misc, source_port, vport);
+ }
+}
+
static int esw_add_fdb_peer_miss_rules(struct mlx5_eswitch *esw,
struct mlx5_core_dev *peer_dev)
{
if (!spec)
return -ENOMEM;
- peer_miss_rules_setup(peer_dev, spec, &dest);
+ peer_miss_rules_setup(esw, peer_dev, spec, &dest);
flows = kvzalloc(nvports * sizeof(*flows), GFP_KERNEL);
if (!flows) {
misc_parameters);
if (mlx5_core_is_ecpf_esw_manager(esw->dev)) {
- MLX5_SET(fte_match_set_misc, misc, source_port, MLX5_VPORT_PF);
+ esw_set_peer_miss_rule_source_port(esw, peer_dev->priv.eswitch,
+ spec, MLX5_VPORT_PF);
+
flow = mlx5_add_flow_rules(esw->fdb_table.offloads.slow_fdb,
spec, &flow_act, &dest, 1);
if (IS_ERR(flow)) {
}
mlx5_esw_for_each_vf_vport_num(esw, i, mlx5_core_max_vfs(esw->dev)) {
- MLX5_SET(fte_match_set_misc, misc, source_port, i);
+ esw_set_peer_miss_rule_source_port(esw,
+ peer_dev->priv.eswitch,
+ spec, i);
+
flow = mlx5_add_flow_rules(esw->fdb_table.offloads.slow_fdb,
spec, &flow_act, &dest, 1);
if (IS_ERR(flow)) {
#define MAX_PF_SQ 256
#define MAX_SQ_NVPORTS 32
+static void esw_set_flow_group_source_port(struct mlx5_eswitch *esw,
+ u32 *flow_group_in)
+{
+ void *match_criteria = MLX5_ADDR_OF(create_flow_group_in,
+ flow_group_in,
+ match_criteria);
+
+ if (mlx5_eswitch_vport_match_metadata_enabled(esw)) {
+ MLX5_SET(create_flow_group_in, flow_group_in,
+ match_criteria_enable,
+ MLX5_MATCH_MISC_PARAMETERS_2);
+
+ MLX5_SET_TO_ONES(fte_match_param, match_criteria,
+ misc_parameters_2.metadata_reg_c_0);
+ } else {
+ MLX5_SET(create_flow_group_in, flow_group_in,
+ match_criteria_enable,
+ MLX5_MATCH_MISC_PARAMETERS);
+
+ MLX5_SET_TO_ONES(fte_match_param, match_criteria,
+ misc_parameters.source_port);
+ }
+}
+
static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw, int nvports)
{
int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
/* create peer esw miss group */
memset(flow_group_in, 0, inlen);
- MLX5_SET(create_flow_group_in, flow_group_in, match_criteria_enable,
- MLX5_MATCH_MISC_PARAMETERS);
- match_criteria = MLX5_ADDR_OF(create_flow_group_in, flow_group_in,
- match_criteria);
+ esw_set_flow_group_source_port(esw, flow_group_in);
+
+ if (!mlx5_eswitch_vport_match_metadata_enabled(esw)) {
+ match_criteria = MLX5_ADDR_OF(create_flow_group_in,
+ flow_group_in,
+ match_criteria);
- MLX5_SET_TO_ONES(fte_match_param, match_criteria,
- misc_parameters.source_port);
- MLX5_SET_TO_ONES(fte_match_param, match_criteria,
- misc_parameters.source_eswitch_owner_vhca_id);
+ MLX5_SET_TO_ONES(fte_match_param, match_criteria,
+ misc_parameters.source_eswitch_owner_vhca_id);
+
+ MLX5_SET(create_flow_group_in, flow_group_in,
+ source_eswitch_owner_vhca_id_valid, 1);
+ }
- MLX5_SET(create_flow_group_in, flow_group_in,
- source_eswitch_owner_vhca_id_valid, 1);
MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, ix);
MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index,
ix + esw->total_vports - 1);
int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
struct mlx5_flow_group *g;
u32 *flow_group_in;
- void *match_criteria, *misc;
int err = 0;
nvports = nvports + MLX5_ESW_MISS_FLOWS;
/* create vport rx group */
memset(flow_group_in, 0, inlen);
- MLX5_SET(create_flow_group_in, flow_group_in, match_criteria_enable,
- MLX5_MATCH_MISC_PARAMETERS);
- match_criteria = MLX5_ADDR_OF(create_flow_group_in, flow_group_in, match_criteria);
- misc = MLX5_ADDR_OF(fte_match_param, match_criteria, misc_parameters);
- MLX5_SET_TO_ONES(fte_match_set_misc, misc, source_port);
+ esw_set_flow_group_source_port(esw, flow_group_in);
MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, 0);
MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, nvports - 1);
goto out;
}
- misc = MLX5_ADDR_OF(fte_match_param, spec->match_value, misc_parameters);
- MLX5_SET(fte_match_set_misc, misc, source_port, vport);
+ if (mlx5_eswitch_vport_match_metadata_enabled(esw)) {
+ misc = MLX5_ADDR_OF(fte_match_param, spec->match_value, misc_parameters_2);
+ MLX5_SET(fte_match_set_misc2, misc, metadata_reg_c_0,
+ mlx5_eswitch_get_vport_metadata_for_match(esw, vport));
- misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, misc_parameters);
- MLX5_SET_TO_ONES(fte_match_set_misc, misc, source_port);
+ misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, misc_parameters_2);
+ MLX5_SET_TO_ONES(fte_match_set_misc2, misc, metadata_reg_c_0);
- spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS;
+ spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS_2;
+ } else {
+ misc = MLX5_ADDR_OF(fte_match_param, spec->match_value, misc_parameters);
+ MLX5_SET(fte_match_set_misc, misc, source_port, vport);
+
+ misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, misc_parameters);
+ MLX5_SET_TO_ONES(fte_match_set_misc, misc, source_port);
+
+ spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS;
+ }
flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
flow_rule = mlx5_add_flow_rules(esw->offloads.ft_offloads, spec,
static int esw_offloads_start(struct mlx5_eswitch *esw,
struct netlink_ext_ack *extack)
{
- int err, err1, num_vfs = esw->dev->priv.sriov.num_vfs;
+ int err, err1;
- if (esw->mode != SRIOV_LEGACY &&
+ if (esw->mode != MLX5_ESWITCH_LEGACY &&
!mlx5_core_is_ecpf_esw_manager(esw->dev)) {
NL_SET_ERR_MSG_MOD(extack,
"Can't set offloads mode, SRIOV legacy not enabled");
return -EINVAL;
}
- mlx5_eswitch_disable_sriov(esw);
- err = mlx5_eswitch_enable_sriov(esw, num_vfs, SRIOV_OFFLOADS);
+ mlx5_eswitch_disable(esw);
+ mlx5_eswitch_update_num_of_vfs(esw, esw->dev->priv.sriov.num_vfs);
+ err = mlx5_eswitch_enable(esw, MLX5_ESWITCH_OFFLOADS);
if (err) {
NL_SET_ERR_MSG_MOD(extack,
"Failed setting eswitch to offloads");
- err1 = mlx5_eswitch_enable_sriov(esw, num_vfs, SRIOV_LEGACY);
+ err1 = mlx5_eswitch_enable(esw, MLX5_ESWITCH_LEGACY);
if (err1) {
NL_SET_ERR_MSG_MOD(extack,
"Failed setting eswitch back to legacy");
}
if (esw->offloads.inline_mode == MLX5_INLINE_MODE_NONE) {
if (mlx5_eswitch_inline_mode_get(esw,
- num_vfs,
&esw->offloads.inline_mode)) {
esw->offloads.inline_mode = MLX5_INLINE_MODE_L2;
NL_SET_ERR_MSG_MOD(extack,
int esw_offloads_init_reps(struct mlx5_eswitch *esw)
{
- int total_vports = MLX5_TOTAL_VPORTS(esw->dev);
+ int total_vports = esw->total_vports;
struct mlx5_core_dev *dev = esw->dev;
struct mlx5_eswitch_rep *rep;
u8 hw_id[ETH_ALEN], rep_type;
- int vport;
+ int vport_index;
esw->offloads.vport_reps = kcalloc(total_vports,
sizeof(struct mlx5_eswitch_rep),
if (!esw->offloads.vport_reps)
return -ENOMEM;
- mlx5_query_nic_vport_mac_address(dev, 0, hw_id);
+ mlx5_query_mac_address(dev, hw_id);
- mlx5_esw_for_all_reps(esw, vport, rep) {
- rep->vport = mlx5_eswitch_index_to_vport_num(esw, vport);
+ mlx5_esw_for_all_reps(esw, vport_index, rep) {
+ rep->vport = mlx5_eswitch_index_to_vport_num(esw, vport_index);
+ rep->vport_index = vport_index;
ether_addr_copy(rep->hw_id, hw_id);
for (rep_type = 0; rep_type < NUM_REP_TYPES; rep_type++)
- atomic_set(&rep->rep_if[rep_type].state,
+ atomic_set(&rep->rep_data[rep_type].state,
REP_UNREGISTERED);
}
static void __esw_offloads_unload_rep(struct mlx5_eswitch *esw,
struct mlx5_eswitch_rep *rep, u8 rep_type)
{
- if (atomic_cmpxchg(&rep->rep_if[rep_type].state,
+ if (atomic_cmpxchg(&rep->rep_data[rep_type].state,
REP_LOADED, REP_REGISTERED) == REP_LOADED)
- rep->rep_if[rep_type].unload(rep);
+ esw->offloads.rep_ops[rep_type]->unload(rep);
}
static void __unload_reps_special_vport(struct mlx5_eswitch *esw, u8 rep_type)
__unload_reps_vf_vport(esw, nvports, rep_type);
}
-static void __unload_reps_all_vport(struct mlx5_eswitch *esw, int nvports,
- u8 rep_type)
+static void __unload_reps_all_vport(struct mlx5_eswitch *esw, u8 rep_type)
{
- __unload_reps_vf_vport(esw, nvports, rep_type);
+ __unload_reps_vf_vport(esw, esw->esw_funcs.num_vfs, rep_type);
/* Special vports must be the last to unload. */
__unload_reps_special_vport(esw, rep_type);
}
-static void esw_offloads_unload_all_reps(struct mlx5_eswitch *esw, int nvports)
+static void esw_offloads_unload_all_reps(struct mlx5_eswitch *esw)
{
u8 rep_type = NUM_REP_TYPES;
while (rep_type-- > 0)
- __unload_reps_all_vport(esw, nvports, rep_type);
+ __unload_reps_all_vport(esw, rep_type);
}
static int __esw_offloads_load_rep(struct mlx5_eswitch *esw,
{
int err = 0;
- if (atomic_cmpxchg(&rep->rep_if[rep_type].state,
+ if (atomic_cmpxchg(&rep->rep_data[rep_type].state,
REP_REGISTERED, REP_LOADED) == REP_REGISTERED) {
- err = rep->rep_if[rep_type].load(esw->dev, rep);
+ err = esw->offloads.rep_ops[rep_type]->load(esw->dev, rep);
if (err)
- atomic_set(&rep->rep_if[rep_type].state,
+ atomic_set(&rep->rep_data[rep_type].state,
REP_REGISTERED);
}
return err;
}
+static int __load_reps_all_vport(struct mlx5_eswitch *esw, u8 rep_type)
+{
+ int err;
+
+ /* Special vports must be loaded first, uplink rep creates mdev resource. */
+ err = __load_reps_special_vport(esw, rep_type);
+ if (err)
+ return err;
+
+ err = __load_reps_vf_vport(esw, esw->esw_funcs.num_vfs, rep_type);
+ if (err)
+ goto err_vfs;
+
+ return 0;
+
+err_vfs:
+ __unload_reps_special_vport(esw, rep_type);
+ return err;
+}
+
static int esw_offloads_load_vf_reps(struct mlx5_eswitch *esw, int nvports)
{
u8 rep_type = 0;
return err;
}
-static int __load_reps_all_vport(struct mlx5_eswitch *esw, int nvports,
- u8 rep_type)
-{
- int err;
-
- /* Special vports must be loaded first. */
- err = __load_reps_special_vport(esw, rep_type);
- if (err)
- return err;
-
- err = __load_reps_vf_vport(esw, nvports, rep_type);
- if (err)
- goto err_vfs;
-
- return 0;
-
-err_vfs:
- __unload_reps_special_vport(esw, rep_type);
- return err;
-}
-
-static int esw_offloads_load_all_reps(struct mlx5_eswitch *esw, int nvports)
+static int esw_offloads_load_all_reps(struct mlx5_eswitch *esw)
{
u8 rep_type = 0;
int err;
for (rep_type = 0; rep_type < NUM_REP_TYPES; rep_type++) {
- err = __load_reps_all_vport(esw, nvports, rep_type);
+ err = __load_reps_all_vport(esw, rep_type);
if (err)
goto err_reps;
}
err_reps:
while (rep_type-- > 0)
- __unload_reps_all_vport(esw, nvports, rep_type);
+ __unload_reps_all_vport(esw, rep_type);
return err;
}
switch (event) {
case ESW_OFFLOADS_DEVCOM_PAIR:
+ if (mlx5_eswitch_vport_match_metadata_enabled(esw) !=
+ mlx5_eswitch_vport_match_metadata_enabled(peer_esw))
+ break;
+
err = mlx5_esw_offloads_pair(esw, peer_esw);
if (err)
goto err_out;
static int esw_vport_ingress_prio_tag_config(struct mlx5_eswitch *esw,
struct mlx5_vport *vport)
{
- struct mlx5_core_dev *dev = esw->dev;
struct mlx5_flow_act flow_act = {0};
struct mlx5_flow_spec *spec;
int err = 0;
/* For prio tag mode, there is only 1 FTEs:
- * 1) Untagged packets - push prio tag VLAN, allow
+ * 1) Untagged packets - push prio tag VLAN and modify metadata if
+ * required, allow
* Unmatched traffic is allowed by default
*/
- if (!MLX5_CAP_ESW_INGRESS_ACL(dev, ft_support))
- return -EOPNOTSUPP;
-
- esw_vport_cleanup_ingress_rules(esw, vport);
-
- err = esw_vport_enable_ingress_acl(esw, vport);
- if (err) {
- mlx5_core_warn(esw->dev,
- "failed to enable prio tag ingress acl (%d) on vport[%d]\n",
- err, vport->vport);
- return err;
- }
-
- esw_debug(esw->dev,
- "vport[%d] configure ingress rules\n", vport->vport);
-
spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
if (!spec) {
err = -ENOMEM;
flow_act.vlan[0].ethtype = ETH_P_8021Q;
flow_act.vlan[0].vid = 0;
flow_act.vlan[0].prio = 0;
+
+ if (vport->ingress.modify_metadata_rule) {
+ flow_act.action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR;
+ flow_act.modify_id = vport->ingress.modify_metadata_id;
+ }
+
vport->ingress.allow_rule =
mlx5_add_flow_rules(vport->ingress.acl, spec,
&flow_act, NULL, 0);
return err;
}
+static int esw_vport_add_ingress_acl_modify_metadata(struct mlx5_eswitch *esw,
+ struct mlx5_vport *vport)
+{
+ u8 action[MLX5_UN_SZ_BYTES(set_action_in_add_action_in_auto)] = {};
+ static const struct mlx5_flow_spec spec = {};
+ struct mlx5_flow_act flow_act = {};
+ int err = 0;
+
+ MLX5_SET(set_action_in, action, action_type, MLX5_ACTION_TYPE_SET);
+ MLX5_SET(set_action_in, action, field, MLX5_ACTION_IN_FIELD_METADATA_REG_C_0);
+ MLX5_SET(set_action_in, action, data,
+ mlx5_eswitch_get_vport_metadata_for_match(esw, vport->vport));
+
+ err = mlx5_modify_header_alloc(esw->dev, MLX5_FLOW_NAMESPACE_ESW_INGRESS,
+ 1, action, &vport->ingress.modify_metadata_id);
+ if (err) {
+ esw_warn(esw->dev,
+ "failed to alloc modify header for vport %d ingress acl (%d)\n",
+ vport->vport, err);
+ return err;
+ }
+
+ flow_act.action = MLX5_FLOW_CONTEXT_ACTION_MOD_HDR | MLX5_FLOW_CONTEXT_ACTION_ALLOW;
+ flow_act.modify_id = vport->ingress.modify_metadata_id;
+ vport->ingress.modify_metadata_rule = mlx5_add_flow_rules(vport->ingress.acl,
+ &spec, &flow_act, NULL, 0);
+ if (IS_ERR(vport->ingress.modify_metadata_rule)) {
+ err = PTR_ERR(vport->ingress.modify_metadata_rule);
+ esw_warn(esw->dev,
+ "failed to add setting metadata rule for vport %d ingress acl, err(%d)\n",
+ vport->vport, err);
+ vport->ingress.modify_metadata_rule = NULL;
+ goto out;
+ }
+
+out:
+ if (err)
+ mlx5_modify_header_dealloc(esw->dev, vport->ingress.modify_metadata_id);
+ return err;
+}
+
+void esw_vport_del_ingress_acl_modify_metadata(struct mlx5_eswitch *esw,
+ struct mlx5_vport *vport)
+{
+ if (vport->ingress.modify_metadata_rule) {
+ mlx5_del_flow_rules(vport->ingress.modify_metadata_rule);
+ mlx5_modify_header_dealloc(esw->dev, vport->ingress.modify_metadata_id);
+
+ vport->ingress.modify_metadata_rule = NULL;
+ }
+}
+
static int esw_vport_egress_prio_tag_config(struct mlx5_eswitch *esw,
struct mlx5_vport *vport)
{
struct mlx5_flow_spec *spec;
int err = 0;
+ if (!MLX5_CAP_GEN(esw->dev, prio_tag_required))
+ return 0;
+
/* For prio tag mode, there is only 1 FTEs:
* 1) prio tag packets - pop the prio tag VLAN, allow
* Unmatched traffic is allowed by default
return err;
}
-static int esw_prio_tag_acls_config(struct mlx5_eswitch *esw, int nvports)
+static int esw_vport_ingress_common_config(struct mlx5_eswitch *esw,
+ struct mlx5_vport *vport)
{
- struct mlx5_vport *vport = NULL;
- int i, j;
int err;
- mlx5_esw_for_each_vf_vport(esw, i, vport, nvports) {
+ if (!mlx5_eswitch_vport_match_metadata_enabled(esw) &&
+ !MLX5_CAP_GEN(esw->dev, prio_tag_required))
+ return 0;
+
+ esw_vport_cleanup_ingress_rules(esw, vport);
+
+ err = esw_vport_enable_ingress_acl(esw, vport);
+ if (err) {
+ esw_warn(esw->dev,
+ "failed to enable ingress acl (%d) on vport[%d]\n",
+ err, vport->vport);
+ return err;
+ }
+
+ esw_debug(esw->dev,
+ "vport[%d] configure ingress rules\n", vport->vport);
+
+ if (mlx5_eswitch_vport_match_metadata_enabled(esw)) {
+ err = esw_vport_add_ingress_acl_modify_metadata(esw, vport);
+ if (err)
+ goto out;
+ }
+
+ if (MLX5_CAP_GEN(esw->dev, prio_tag_required) &&
+ mlx5_eswitch_is_vf_vport(esw, vport->vport)) {
err = esw_vport_ingress_prio_tag_config(esw, vport);
if (err)
- goto err_ingress;
- err = esw_vport_egress_prio_tag_config(esw, vport);
+ goto out;
+ }
+
+out:
+ if (err)
+ esw_vport_disable_ingress_acl(esw, vport);
+ return err;
+}
+
+static bool
+esw_check_vport_match_metadata_supported(const struct mlx5_eswitch *esw)
+{
+ if (!MLX5_CAP_ESW(esw->dev, esw_uplink_ingress_acl))
+ return false;
+
+ if (!(MLX5_CAP_ESW_FLOWTABLE(esw->dev, fdb_to_vport_reg_c_id) &
+ MLX5_FDB_TO_VPORT_REG_C_0))
+ return false;
+
+ if (!MLX5_CAP_ESW_FLOWTABLE(esw->dev, flow_source))
+ return false;
+
+ if (mlx5_core_is_ecpf_esw_manager(esw->dev) ||
+ mlx5_ecpf_vport_exists(esw->dev))
+ return false;
+
+ return true;
+}
+
+static int esw_create_offloads_acl_tables(struct mlx5_eswitch *esw)
+{
+ struct mlx5_vport *vport;
+ int i, j;
+ int err;
+
+ if (esw_check_vport_match_metadata_supported(esw))
+ esw->flags |= MLX5_ESWITCH_VPORT_MATCH_METADATA;
+
+ mlx5_esw_for_all_vports(esw, i, vport) {
+ err = esw_vport_ingress_common_config(esw, vport);
if (err)
- goto err_egress;
+ goto err_ingress;
+
+ if (mlx5_eswitch_is_vf_vport(esw, vport->vport)) {
+ err = esw_vport_egress_prio_tag_config(esw, vport);
+ if (err)
+ goto err_egress;
+ }
}
+ if (mlx5_eswitch_vport_match_metadata_enabled(esw))
+ esw_info(esw->dev, "Use metadata reg_c as source vport to match\n");
+
return 0;
err_egress:
esw_vport_disable_ingress_acl(esw, vport);
err_ingress:
- mlx5_esw_for_each_vf_vport_reverse(esw, j, vport, i - 1) {
+ for (j = MLX5_VPORT_PF; j < i; j++) {
+ vport = &esw->vports[j];
esw_vport_disable_egress_acl(esw, vport);
esw_vport_disable_ingress_acl(esw, vport);
}
return err;
}
-static void esw_prio_tag_acls_cleanup(struct mlx5_eswitch *esw)
+static void esw_destroy_offloads_acl_tables(struct mlx5_eswitch *esw)
{
struct mlx5_vport *vport;
int i;
- mlx5_esw_for_each_vf_vport(esw, i, vport, esw->dev->priv.sriov.num_vfs) {
+ mlx5_esw_for_all_vports(esw, i, vport) {
esw_vport_disable_egress_acl(esw, vport);
esw_vport_disable_ingress_acl(esw, vport);
}
+
+ esw->flags &= ~MLX5_ESWITCH_VPORT_MATCH_METADATA;
}
-static int esw_offloads_steering_init(struct mlx5_eswitch *esw, int vf_nvports,
- int nvports)
+static int esw_offloads_steering_init(struct mlx5_eswitch *esw)
{
+ int num_vfs = esw->esw_funcs.num_vfs;
+ int total_vports;
int err;
+ if (mlx5_core_is_ecpf_esw_manager(esw->dev))
+ total_vports = esw->total_vports;
+ else
+ total_vports = num_vfs + MLX5_SPECIAL_VPORTS(esw->dev);
+
memset(&esw->fdb_table.offloads, 0, sizeof(struct offloads_fdb));
mutex_init(&esw->fdb_table.offloads.fdb_prio_lock);
- if (MLX5_CAP_GEN(esw->dev, prio_tag_required)) {
- err = esw_prio_tag_acls_config(esw, vf_nvports);
- if (err)
- return err;
- }
-
- err = esw_create_offloads_fdb_tables(esw, nvports);
+ err = esw_create_offloads_acl_tables(esw);
if (err)
return err;
- err = esw_create_offloads_table(esw, nvports);
+ err = esw_create_offloads_fdb_tables(esw, total_vports);
+ if (err)
+ goto create_fdb_err;
+
+ err = esw_create_offloads_table(esw, total_vports);
if (err)
goto create_ft_err;
- err = esw_create_vport_rx_group(esw, nvports);
+ err = esw_create_vport_rx_group(esw, total_vports);
if (err)
goto create_fg_err;
create_ft_err:
esw_destroy_offloads_fdb_tables(esw);
+create_fdb_err:
+ esw_destroy_offloads_acl_tables(esw);
+
return err;
}
esw_destroy_vport_rx_group(esw);
esw_destroy_offloads_table(esw);
esw_destroy_offloads_fdb_tables(esw);
- if (MLX5_CAP_GEN(esw->dev, prio_tag_required))
- esw_prio_tag_acls_cleanup(esw);
+ esw_destroy_offloads_acl_tables(esw);
}
-static void esw_host_params_event_handler(struct work_struct *work)
+static void
+esw_vfs_changed_event_handler(struct mlx5_eswitch *esw, const u32 *out)
{
- struct mlx5_host_work *host_work;
- struct mlx5_eswitch *esw;
- int err, num_vf = 0;
+ bool host_pf_disabled;
+ u16 new_num_vfs;
- host_work = container_of(work, struct mlx5_host_work, work);
- esw = host_work->esw;
+ new_num_vfs = MLX5_GET(query_esw_functions_out, out,
+ host_params_context.host_num_of_vfs);
+ host_pf_disabled = MLX5_GET(query_esw_functions_out, out,
+ host_params_context.host_pf_disabled);
- err = mlx5_query_host_params_num_vfs(esw->dev, &num_vf);
- if (err || num_vf == esw->host_info.num_vfs)
- goto out;
+ if (new_num_vfs == esw->esw_funcs.num_vfs || host_pf_disabled)
+ return;
/* Number of VFs can only change from "0 to x" or "x to 0". */
- if (esw->host_info.num_vfs > 0) {
- esw_offloads_unload_vf_reps(esw, esw->host_info.num_vfs);
+ if (esw->esw_funcs.num_vfs > 0) {
+ esw_offloads_unload_vf_reps(esw, esw->esw_funcs.num_vfs);
} else {
- err = esw_offloads_load_vf_reps(esw, num_vf);
+ int err;
+ err = esw_offloads_load_vf_reps(esw, new_num_vfs);
if (err)
- goto out;
+ return;
}
+ esw->esw_funcs.num_vfs = new_num_vfs;
+}
+
+static void esw_functions_changed_event_handler(struct work_struct *work)
+{
+ struct mlx5_host_work *host_work;
+ struct mlx5_eswitch *esw;
+ const u32 *out;
- esw->host_info.num_vfs = num_vf;
+ host_work = container_of(work, struct mlx5_host_work, work);
+ esw = host_work->esw;
+ out = mlx5_esw_query_functions(esw->dev);
+ if (IS_ERR(out))
+ goto out;
+
+ esw_vfs_changed_event_handler(esw, out);
+ kvfree(out);
out:
kfree(host_work);
}
-static int esw_host_params_event(struct notifier_block *nb,
- unsigned long type, void *data)
+int mlx5_esw_funcs_changed_handler(struct notifier_block *nb, unsigned long type, void *data)
{
+ struct mlx5_esw_functions *esw_funcs;
struct mlx5_host_work *host_work;
- struct mlx5_host_info *host_info;
struct mlx5_eswitch *esw;
host_work = kzalloc(sizeof(*host_work), GFP_ATOMIC);
if (!host_work)
return NOTIFY_DONE;
- host_info = mlx5_nb_cof(nb, struct mlx5_host_info, nb);
- esw = container_of(host_info, struct mlx5_eswitch, host_info);
+ esw_funcs = mlx5_nb_cof(nb, struct mlx5_esw_functions, nb);
+ esw = container_of(esw_funcs, struct mlx5_eswitch, esw_funcs);
host_work->esw = esw;
- INIT_WORK(&host_work->work, esw_host_params_event_handler);
+ INIT_WORK(&host_work->work, esw_functions_changed_event_handler);
queue_work(esw->work_queue, &host_work->work);
return NOTIFY_OK;
}
-int esw_offloads_init(struct mlx5_eswitch *esw, int vf_nvports,
- int total_nvports)
+int esw_offloads_init(struct mlx5_eswitch *esw)
{
int err;
- err = esw_offloads_steering_init(esw, vf_nvports, total_nvports);
+ if (MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, reformat) &&
+ MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, decap))
+ esw->offloads.encap = DEVLINK_ESWITCH_ENCAP_MODE_BASIC;
+ else
+ esw->offloads.encap = DEVLINK_ESWITCH_ENCAP_MODE_NONE;
+
+ err = esw_offloads_steering_init(esw);
if (err)
return err;
- err = esw_offloads_load_all_reps(esw, vf_nvports);
+ if (mlx5_eswitch_vport_match_metadata_enabled(esw)) {
+ err = mlx5_eswitch_enable_passing_vport_metadata(esw);
+ if (err)
+ goto err_vport_metadata;
+ }
+
+ err = esw_offloads_load_all_reps(esw);
if (err)
goto err_reps;
esw_offloads_devcom_init(esw);
-
- if (mlx5_core_is_ecpf_esw_manager(esw->dev)) {
- MLX5_NB_INIT(&esw->host_info.nb, esw_host_params_event,
- HOST_PARAMS_CHANGE);
- mlx5_eq_notifier_register(esw->dev, &esw->host_info.nb);
- esw->host_info.num_vfs = vf_nvports;
- }
+ mutex_init(&esw->offloads.termtbl_mutex);
mlx5_rdma_enable_roce(esw->dev);
return 0;
err_reps:
+ if (mlx5_eswitch_vport_match_metadata_enabled(esw))
+ mlx5_eswitch_disable_passing_vport_metadata(esw);
+err_vport_metadata:
esw_offloads_steering_cleanup(esw);
return err;
}
static int esw_offloads_stop(struct mlx5_eswitch *esw,
struct netlink_ext_ack *extack)
{
- int err, err1, num_vfs = esw->dev->priv.sriov.num_vfs;
+ int err, err1;
- mlx5_eswitch_disable_sriov(esw);
- err = mlx5_eswitch_enable_sriov(esw, num_vfs, SRIOV_LEGACY);
+ mlx5_eswitch_disable(esw);
+ err = mlx5_eswitch_enable(esw, MLX5_ESWITCH_LEGACY);
if (err) {
NL_SET_ERR_MSG_MOD(extack, "Failed setting eswitch to legacy");
- err1 = mlx5_eswitch_enable_sriov(esw, num_vfs, SRIOV_OFFLOADS);
+ err1 = mlx5_eswitch_enable(esw, MLX5_ESWITCH_OFFLOADS);
if (err1) {
NL_SET_ERR_MSG_MOD(extack,
"Failed setting eswitch back to offloads");
void esw_offloads_cleanup(struct mlx5_eswitch *esw)
{
- u16 num_vfs;
-
- if (mlx5_core_is_ecpf_esw_manager(esw->dev)) {
- mlx5_eq_notifier_unregister(esw->dev, &esw->host_info.nb);
- flush_workqueue(esw->work_queue);
- num_vfs = esw->host_info.num_vfs;
- } else {
- num_vfs = esw->dev->priv.sriov.num_vfs;
- }
-
mlx5_rdma_disable_roce(esw->dev);
esw_offloads_devcom_cleanup(esw);
- esw_offloads_unload_all_reps(esw, num_vfs);
+ esw_offloads_unload_all_reps(esw);
+ if (mlx5_eswitch_vport_match_metadata_enabled(esw))
+ mlx5_eswitch_disable_passing_vport_metadata(esw);
esw_offloads_steering_cleanup(esw);
+ esw->offloads.encap = DEVLINK_ESWITCH_ENCAP_MODE_NONE;
}
static int esw_mode_from_devlink(u16 mode, u16 *mlx5_mode)
{
switch (mode) {
case DEVLINK_ESWITCH_MODE_LEGACY:
- *mlx5_mode = SRIOV_LEGACY;
+ *mlx5_mode = MLX5_ESWITCH_LEGACY;
break;
case DEVLINK_ESWITCH_MODE_SWITCHDEV:
- *mlx5_mode = SRIOV_OFFLOADS;
+ *mlx5_mode = MLX5_ESWITCH_OFFLOADS;
break;
default:
return -EINVAL;
static int esw_mode_to_devlink(u16 mlx5_mode, u16 *mode)
{
switch (mlx5_mode) {
- case SRIOV_LEGACY:
+ case MLX5_ESWITCH_LEGACY:
*mode = DEVLINK_ESWITCH_MODE_LEGACY;
break;
- case SRIOV_OFFLOADS:
+ case MLX5_ESWITCH_OFFLOADS:
*mode = DEVLINK_ESWITCH_MODE_SWITCHDEV;
break;
default:
if(!MLX5_ESWITCH_MANAGER(dev))
return -EPERM;
- if (dev->priv.eswitch->mode == SRIOV_NONE &&
+ if (dev->priv.eswitch->mode == MLX5_ESWITCH_NONE &&
!mlx5_core_is_ecpf_esw_manager(dev))
return -EOPNOTSUPP;
{
struct mlx5_core_dev *dev = devlink_priv(devlink);
struct mlx5_eswitch *esw = dev->priv.eswitch;
- int err, vport;
+ int err, vport, num_vport;
u8 mlx5_mode;
err = mlx5_devlink_eswitch_check(devlink);
if (err)
goto out;
- for (vport = 1; vport < esw->enabled_vports; vport++) {
+ mlx5_esw_for_each_host_func_vport(esw, vport, esw->esw_funcs.num_vfs) {
err = mlx5_modify_nic_vport_min_inline(dev, vport, mlx5_mode);
if (err) {
NL_SET_ERR_MSG_MOD(extack,
return 0;
revert_inline_mode:
- while (--vport > 0)
+ num_vport = --vport;
+ mlx5_esw_for_each_host_func_vport_reverse(esw, vport, num_vport)
mlx5_modify_nic_vport_min_inline(dev,
vport,
esw->offloads.inline_mode);
return esw_inline_mode_to_devlink(esw->offloads.inline_mode, mode);
}
-int mlx5_eswitch_inline_mode_get(struct mlx5_eswitch *esw, int nvfs, u8 *mode)
+int mlx5_eswitch_inline_mode_get(struct mlx5_eswitch *esw, u8 *mode)
{
u8 prev_mlx5_mode, mlx5_mode = MLX5_INLINE_MODE_L2;
struct mlx5_core_dev *dev = esw->dev;
if (!MLX5_CAP_GEN(dev, vport_group_manager))
return -EOPNOTSUPP;
- if (esw->mode == SRIOV_NONE)
+ if (esw->mode == MLX5_ESWITCH_NONE)
return -EOPNOTSUPP;
switch (MLX5_CAP_ETH(dev, wqe_inline_mode)) {
}
query_vports:
- for (vport = 1; vport <= nvfs; vport++) {
+ mlx5_query_nic_vport_min_inline(dev, esw->first_host_vport, &prev_mlx5_mode);
+ mlx5_esw_for_each_host_func_vport(esw, vport, esw->esw_funcs.num_vfs) {
mlx5_query_nic_vport_min_inline(dev, vport, &mlx5_mode);
- if (vport > 1 && prev_mlx5_mode != mlx5_mode)
+ if (prev_mlx5_mode != mlx5_mode)
return -EINVAL;
prev_mlx5_mode = mlx5_mode;
}
return 0;
}
-int mlx5_devlink_eswitch_encap_mode_set(struct devlink *devlink, u8 encap,
+int mlx5_devlink_eswitch_encap_mode_set(struct devlink *devlink,
+ enum devlink_eswitch_encap_mode encap,
struct netlink_ext_ack *extack)
{
struct mlx5_core_dev *dev = devlink_priv(devlink);
if (encap && encap != DEVLINK_ESWITCH_ENCAP_MODE_BASIC)
return -EOPNOTSUPP;
- if (esw->mode == SRIOV_LEGACY) {
+ if (esw->mode == MLX5_ESWITCH_LEGACY) {
esw->offloads.encap = encap;
return 0;
}
return err;
}
-int mlx5_devlink_eswitch_encap_mode_get(struct devlink *devlink, u8 *encap)
+int mlx5_devlink_eswitch_encap_mode_get(struct devlink *devlink,
+ enum devlink_eswitch_encap_mode *encap)
{
struct mlx5_core_dev *dev = devlink_priv(devlink);
struct mlx5_eswitch *esw = dev->priv.eswitch;
}
void mlx5_eswitch_register_vport_reps(struct mlx5_eswitch *esw,
- struct mlx5_eswitch_rep_if *__rep_if,
+ const struct mlx5_eswitch_rep_ops *ops,
u8 rep_type)
{
- struct mlx5_eswitch_rep_if *rep_if;
+ struct mlx5_eswitch_rep_data *rep_data;
struct mlx5_eswitch_rep *rep;
int i;
+ esw->offloads.rep_ops[rep_type] = ops;
mlx5_esw_for_all_reps(esw, i, rep) {
- rep_if = &rep->rep_if[rep_type];
- rep_if->load = __rep_if->load;
- rep_if->unload = __rep_if->unload;
- rep_if->get_proto_dev = __rep_if->get_proto_dev;
- rep_if->priv = __rep_if->priv;
-
- atomic_set(&rep_if->state, REP_REGISTERED);
+ rep_data = &rep->rep_data[rep_type];
+ atomic_set(&rep_data->state, REP_REGISTERED);
}
}
EXPORT_SYMBOL(mlx5_eswitch_register_vport_reps);
void mlx5_eswitch_unregister_vport_reps(struct mlx5_eswitch *esw, u8 rep_type)
{
- u16 max_vf = mlx5_core_max_vfs(esw->dev);
struct mlx5_eswitch_rep *rep;
int i;
- if (esw->mode == SRIOV_OFFLOADS)
- __unload_reps_all_vport(esw, max_vf, rep_type);
+ if (esw->mode == MLX5_ESWITCH_OFFLOADS)
+ __unload_reps_all_vport(esw, rep_type);
mlx5_esw_for_all_reps(esw, i, rep)
- atomic_set(&rep->rep_if[rep_type].state, REP_UNREGISTERED);
+ atomic_set(&rep->rep_data[rep_type].state, REP_UNREGISTERED);
}
EXPORT_SYMBOL(mlx5_eswitch_unregister_vport_reps);
struct mlx5_eswitch_rep *rep;
rep = mlx5_eswitch_get_rep(esw, MLX5_VPORT_UPLINK);
- return rep->rep_if[rep_type].priv;
+ return rep->rep_data[rep_type].priv;
}
void *mlx5_eswitch_get_proto_dev(struct mlx5_eswitch *esw,
rep = mlx5_eswitch_get_rep(esw, vport);
- if (atomic_read(&rep->rep_if[rep_type].state) == REP_LOADED &&
- rep->rep_if[rep_type].get_proto_dev)
- return rep->rep_if[rep_type].get_proto_dev(rep);
+ if (atomic_read(&rep->rep_data[rep_type].state) == REP_LOADED &&
+ esw->offloads.rep_ops[rep_type]->get_proto_dev)
+ return esw->offloads.rep_ops[rep_type]->get_proto_dev(rep);
return NULL;
}
EXPORT_SYMBOL(mlx5_eswitch_get_proto_dev);
return mlx5_eswitch_get_rep(esw, vport);
}
EXPORT_SYMBOL(mlx5_eswitch_vport_rep);
+
+bool mlx5_eswitch_is_vf_vport(const struct mlx5_eswitch *esw, u16 vport_num)
+{
+ return vport_num >= MLX5_VPORT_FIRST_VF &&
+ vport_num <= esw->dev->priv.sriov.max_vfs;
+}
+
+bool mlx5_eswitch_vport_match_metadata_enabled(const struct mlx5_eswitch *esw)
+{
+ return !!(esw->flags & MLX5_ESWITCH_VPORT_MATCH_METADATA);
+}
+EXPORT_SYMBOL(mlx5_eswitch_vport_match_metadata_enabled);
+
+u32 mlx5_eswitch_get_vport_metadata_for_match(const struct mlx5_eswitch *esw,
+ u16 vport_num)
+{
+ return ((MLX5_CAP_GEN(esw->dev, vhca_id) & 0xffff) << 16) | vport_num;
+}
+EXPORT_SYMBOL(mlx5_eswitch_get_vport_metadata_for_match);
mlx5e_set_netdev_mtu_boundaries(priv);
netdev->mtu = netdev->max_mtu;
- mlx5e_build_nic_params(mdev, &priv->rss_params, &priv->channels.params,
+ mlx5e_build_nic_params(mdev, NULL, &priv->rss_params, &priv->channels.params,
mlx5e_get_netdev_max_channels(netdev),
netdev->mtu);
mlx5i_build_nic_params(mdev, &priv->channels.params);
mlx5_core_destroy_qp(mdev, qp);
}
+int mlx5i_create_tis(struct mlx5_core_dev *mdev, u32 underlay_qpn, u32 *tisn)
+{
+ u32 in[MLX5_ST_SZ_DW(create_tis_in)] = {};
+ void *tisc;
+
+ tisc = MLX5_ADDR_OF(create_tis_in, in, ctx);
+
+ MLX5_SET(tisc, tisc, underlay_qpn, underlay_qpn);
+
+ return mlx5e_create_tis(mdev, in, tisn);
+}
+
static int mlx5i_init_tx(struct mlx5e_priv *priv)
{
struct mlx5i_priv *ipriv = priv->ppriv;
return err;
}
- err = mlx5e_create_tis(priv->mdev, 0 /* tc */, ipriv->qp.qpn, &priv->tisn[0]);
+ err = mlx5i_create_tis(priv->mdev, ipriv->qp.qpn, &priv->tisn[0]);
if (err) {
mlx5_core_warn(priv->mdev, "create tis failed, %d\n", err);
goto err_destroy_underlay_qp;
if (err)
goto err_close_drop_rq;
- err = mlx5e_create_direct_rqts(priv);
+ err = mlx5e_create_direct_rqts(priv, priv->direct_tir);
if (err)
goto err_destroy_indirect_rqts;
if (err)
goto err_destroy_direct_rqts;
- err = mlx5e_create_direct_tirs(priv);
+ err = mlx5e_create_direct_tirs(priv, priv->direct_tir);
if (err)
goto err_destroy_indirect_tirs;
return 0;
err_destroy_direct_tirs:
- mlx5e_destroy_direct_tirs(priv);
+ mlx5e_destroy_direct_tirs(priv, priv->direct_tir);
err_destroy_indirect_tirs:
mlx5e_destroy_indirect_tirs(priv, true);
err_destroy_direct_rqts:
- mlx5e_destroy_direct_rqts(priv);
+ mlx5e_destroy_direct_rqts(priv, priv->direct_tir);
err_destroy_indirect_rqts:
mlx5e_destroy_rqt(priv, &priv->indir_rqt);
err_close_drop_rq:
static void mlx5i_cleanup_rx(struct mlx5e_priv *priv)
{
mlx5i_destroy_flow_steering(priv);
- mlx5e_destroy_direct_tirs(priv);
+ mlx5e_destroy_direct_tirs(priv, priv->direct_tir);
mlx5e_destroy_indirect_tirs(priv, true);
- mlx5e_destroy_direct_rqts(priv);
+ mlx5e_destroy_direct_rqts(priv, priv->direct_tir);
mlx5e_destroy_rqt(priv, &priv->indir_rqt);
mlx5e_close_drop_rq(&priv->drop_rq);
mlx5e_destroy_q_counters(priv);
.cleanup_rx = mlx5i_cleanup_rx,
.enable = NULL, /* mlx5i_enable */
.disable = NULL, /* mlx5i_disable */
+ .update_rx = mlx5e_update_nic_rx,
.update_stats = NULL, /* mlx5i_update_stats */
.update_carrier = NULL, /* no HW update in IB link */
.rx_handlers.handle_rx_cqe = mlx5i_handle_rx_cqe,
if (err)
goto err_remove_fs_underlay_qp;
- mlx5e_refresh_tirs(epriv, false);
+ epriv->profile->update_rx(epriv);
mlx5e_activate_priv_channels(epriv);
mutex_unlock(&epriv->state_lock);
prof->init(mdev, netdev, prof, ipriv);
- mlx5e_attach_netdev(epriv);
+ err = mlx5e_attach_netdev(epriv);
+ if (err)
+ goto detach;
netif_carrier_off(netdev);
/* set rdma_netdev func pointers */
return 0;
+ detach:
+ prof->cleanup(epriv);
+ if (ipriv->sub_interface)
+ return err;
+ mlx5e_destroy_mdev_resources(mdev);
destroy_ht:
mlx5i_pkey_qpn_ht_cleanup(netdev);
return err;
enum {
MLX5_OBJ_TYPE_GENEVE_TLV_OPT = 0x000b,
+ MLX5_OBJ_TYPE_MKEY = 0xff01,
+ MLX5_OBJ_TYPE_QP = 0xff02,
+ MLX5_OBJ_TYPE_PSV = 0xff03,
+ MLX5_OBJ_TYPE_RMP = 0xff04,
+ MLX5_OBJ_TYPE_XRC_SRQ = 0xff05,
+ MLX5_OBJ_TYPE_RQ = 0xff06,
+ MLX5_OBJ_TYPE_SQ = 0xff07,
+ MLX5_OBJ_TYPE_TIR = 0xff08,
+ MLX5_OBJ_TYPE_TIS = 0xff09,
+ MLX5_OBJ_TYPE_DCT = 0xff0a,
+ MLX5_OBJ_TYPE_XRQ = 0xff0b,
+ MLX5_OBJ_TYPE_RQT = 0xff0e,
+ MLX5_OBJ_TYPE_FLOW_COUNTER = 0xff0f,
+ MLX5_OBJ_TYPE_CQ = 0xff10,
};
enum {
MLX5_CMD_OP_QUERY_ISSI = 0x10a,
MLX5_CMD_OP_SET_ISSI = 0x10b,
MLX5_CMD_OP_SET_DRIVER_VERSION = 0x10d,
+ MLX5_CMD_OP_QUERY_SF_PARTITION = 0x111,
+ MLX5_CMD_OP_ALLOC_SF = 0x113,
+ MLX5_CMD_OP_DEALLOC_SF = 0x114,
MLX5_CMD_OP_CREATE_MKEY = 0x200,
MLX5_CMD_OP_QUERY_MKEY = 0x201,
MLX5_CMD_OP_DESTROY_MKEY = 0x202,
MLX5_CMD_OP_QUERY_XRQ_DC_PARAMS_ENTRY = 0x725,
MLX5_CMD_OP_SET_XRQ_DC_PARAMS_ENTRY = 0x726,
MLX5_CMD_OP_QUERY_XRQ_ERROR_PARAMS = 0x727,
- MLX5_CMD_OP_QUERY_HOST_PARAMS = 0x740,
+ MLX5_CMD_OP_QUERY_ESW_FUNCTIONS = 0x740,
MLX5_CMD_OP_QUERY_VPORT_STATE = 0x750,
MLX5_CMD_OP_MODIFY_VPORT_STATE = 0x751,
MLX5_CMD_OP_QUERY_ESW_VPORT_CONTEXT = 0x752,
u8 reformat_and_modify_action[0x1];
u8 reserved_at_15[0x2];
u8 table_miss_action_domain[0x1];
- u8 reserved_at_18[0x8];
+ u8 termination_table[0x1];
+ u8 reserved_at_19[0x7];
u8 reserved_at_20[0x2];
u8 log_max_ft_size[0x6];
u8 log_max_modify_header_context[0x8];
struct mlx5_ifc_fte_match_mpls_bits outer_first_mpls_over_udp;
- u8 reserved_at_80[0x100];
+ u8 metadata_reg_c_7[0x20];
+
+ u8 metadata_reg_c_6[0x20];
+
+ u8 metadata_reg_c_5[0x20];
+
+ u8 metadata_reg_c_4[0x20];
+
+ u8 metadata_reg_c_3[0x20];
+
+ u8 metadata_reg_c_2[0x20];
+
+ u8 metadata_reg_c_1[0x20];
+
+ u8 metadata_reg_c_0[0x20];
u8 metadata_reg_a[0x20];
u8 reserved_at_e00[0x7200];
};
+enum {
+ MLX5_FDB_TO_VPORT_REG_C_0 = 0x01,
+ MLX5_FDB_TO_VPORT_REG_C_1 = 0x02,
+ MLX5_FDB_TO_VPORT_REG_C_2 = 0x04,
+ MLX5_FDB_TO_VPORT_REG_C_3 = 0x08,
+ MLX5_FDB_TO_VPORT_REG_C_4 = 0x10,
+ MLX5_FDB_TO_VPORT_REG_C_5 = 0x20,
+ MLX5_FDB_TO_VPORT_REG_C_6 = 0x40,
+ MLX5_FDB_TO_VPORT_REG_C_7 = 0x80,
+};
+
struct mlx5_ifc_flow_table_eswitch_cap_bits {
- u8 reserved_at_0[0x1a];
+ u8 fdb_to_vport_reg_c_id[0x8];
+ u8 reserved_at_8[0xf];
+ u8 flow_source[0x1];
+ u8 reserved_at_18[0x2];
u8 multi_fdb_encap[0x1];
u8 reserved_at_1b[0x1];
u8 fdb_multi_path_to_table[0x1];
u8 vport_svlan_insert[0x1];
u8 vport_cvlan_insert_if_not_exist[0x1];
u8 vport_cvlan_insert_overwrite[0x1];
- u8 reserved_at_5[0x16];
+ u8 reserved_at_5[0x3];
+ u8 esw_uplink_ingress_acl[0x1];
+ u8 reserved_at_9[0x10];
+ u8 esw_functions_changed[0x1];
+ u8 reserved_at_1a[0x1];
u8 ecpf_vport_exists[0x1];
u8 counter_eswitch_affinity[0x1];
u8 merged_eswitch[0x1];
u8 reserved_2b[0x6];
u8 max_encap_header_size[0xa];
- u8 reserved_40[0x7c0];
+ u8 reserved_at_40[0xb];
+ u8 log_max_esw_sf[0x5];
+ u8 esw_sf_base_id[0x10];
+
+ u8 reserved_at_60[0x7a0];
};
};
struct mlx5_ifc_debug_cap_bits {
- u8 reserved_at_0[0x20];
+ u8 core_dump_general[0x1];
+ u8 core_dump_qp[0x1];
+ u8 reserved_at_2[0x1e];
u8 reserved_at_20[0x2];
u8 stall_detect[0x1];
u8 swp[0x1];
u8 swp_csum[0x1];
u8 swp_lso[0x1];
- u8 reserved_at_23[0xd];
+ u8 cqe_checksum_full[0x1];
+ u8 reserved_at_24[0xc];
u8 max_vxlan_udp_ports[0x8];
u8 reserved_at_38[0x6];
u8 max_geneve_opt_len[0x1];
u8 reserved_at_180[0x680];
};
+struct mlx5_ifc_device_event_cap_bits {
+ u8 user_affiliated_events[4][0x40];
+
+ u8 user_unaffiliated_events[4][0x40];
+};
+
enum {
MLX5_ATOMIC_CAPS_ATOMIC_SIZE_QP_1_BYTE = 0x0,
MLX5_ATOMIC_CAPS_ATOMIC_SIZE_QP_2_BYTES = 0x2,
u8 reserved_at_c0[0x720];
};
+struct mlx5_ifc_tls_cap_bits {
+ u8 tls_1_2_aes_gcm_128[0x1];
+ u8 tls_1_3_aes_gcm_128[0x1];
+ u8 tls_1_2_aes_gcm_256[0x1];
+ u8 tls_1_3_aes_gcm_256[0x1];
+ u8 reserved_at_4[0x1c];
+
+ u8 reserved_at_20[0x7e0];
+};
+
enum {
MLX5_WQ_TYPE_LINKED_LIST = 0x0,
MLX5_WQ_TYPE_CYCLIC = 0x1,
u8 log_max_srq_sz[0x8];
u8 log_max_qp_sz[0x8];
- u8 reserved_at_90[0x8];
+ u8 event_cap[0x1];
+ u8 reserved_at_91[0x7];
u8 prio_tag_required[0x1];
u8 reserved_at_99[0x2];
u8 log_max_qp[0x5];
u8 cc_modify_allowed[0x1];
u8 start_pad[0x1];
u8 cache_line_128byte[0x1];
- u8 reserved_at_165[0xa];
+ u8 reserved_at_165[0x4];
+ u8 rts2rts_qp_counters_set_id[0x1];
+ u8 reserved_at_16a[0x5];
u8 qcam_reg[0x1];
u8 gid_table_size[0x10];
u8 reserved_at_440[0x20];
- u8 reserved_at_460[0x3];
+ u8 tls[0x1];
+ u8 reserved_at_461[0x2];
u8 log_max_uctx[0x5];
u8 reserved_at_468[0x3];
u8 log_max_umem[0x5];
u8 max_geneve_tlv_option_data_len[0x5];
u8 reserved_at_570[0x10];
- u8 reserved_at_580[0x3c];
+ u8 reserved_at_580[0x33];
+ u8 log_max_dek[0x5];
+ u8 reserved_at_5b8[0x4];
u8 mini_cqe_resp_stride_index[0x1];
u8 cqe_128_always[0x1];
u8 cqe_compression_128[0x1];
u8 reserved_at_640[0x10];
u8 num_q_monitor_counters[0x10];
- u8 reserved_at_660[0x40];
+ u8 reserved_at_660[0x20];
+
+ u8 sf[0x1];
+ u8 sf_set_partition[0x1];
+ u8 reserved_at_682[0x1];
+ u8 log_max_sf[0x5];
+ u8 reserved_at_688[0x8];
+ u8 log_min_sf_size[0x8];
+ u8 max_num_sf_partitions[0x8];
u8 uctx_cap[0x20];
u8 reserved_at_6c0[0x4];
u8 flex_parser_id_geneve_tlv_option_0[0x4];
- u8 reserved_at_6c8[0x138];
+ u8 reserved_at_6c8[0x28];
+ u8 sf_base_id[0x10];
+
+ u8 reserved_at_700[0x100];
};
enum mlx5_flow_destination_type {
struct mlx5_ifc_e_switch_cap_bits e_switch_cap;
struct mlx5_ifc_vector_calc_cap_bits vector_calc_cap;
struct mlx5_ifc_qos_cap_bits qos_cap;
+ struct mlx5_ifc_debug_cap_bits debug_cap;
struct mlx5_ifc_fpga_cap_bits fpga_cap;
+ struct mlx5_ifc_tls_cap_bits tls_cap;
u8 reserved_at_0[0x8000];
};
MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH_2 = 0x800,
};
+enum {
+ MLX5_FLOW_CONTEXT_FLOW_SOURCE_ANY_VPORT = 0x0,
+ MLX5_FLOW_CONTEXT_FLOW_SOURCE_UPLINK = 0x1,
+ MLX5_FLOW_CONTEXT_FLOW_SOURCE_LOCAL_VPORT = 0x2,
+};
+
struct mlx5_ifc_vlan_bits {
u8 ethtype[0x10];
u8 prio[0x3];
u8 action[0x10];
u8 extended_destination[0x1];
- u8 reserved_at_80[0x7];
+ u8 reserved_at_81[0x1];
+ u8 flow_source[0x2];
+ u8 reserved_at_84[0x4];
u8 destination_list_size[0x18];
u8 reserved_at_a0[0x8];
struct mlx5_ifc_tisc_bits {
u8 strict_lag_tx_port_affinity[0x1];
- u8 reserved_at_1[0x3];
+ u8 tls_en[0x1];
+ u8 reserved_at_1[0x2];
u8 lag_tx_port_affinity[0x04];
u8 reserved_at_8[0x4];
u8 reserved_at_140[0x8];
u8 underlay_qpn[0x18];
- u8 reserved_at_160[0x3a0];
+
+ u8 reserved_at_160[0x8];
+ u8 pd[0x18];
+
+ u8 reserved_at_180[0x380];
};
enum {
};
struct mlx5_ifc_esw_vport_context_bits {
- u8 reserved_at_0[0x3];
+ u8 fdb_to_vport_reg_c[0x1];
+ u8 reserved_at_1[0x2];
u8 vport_svlan_strip[0x1];
u8 vport_cvlan_strip[0x1];
u8 vport_svlan_insert[0x1];
u8 vport_cvlan_insert[0x2];
- u8 reserved_at_8[0x18];
+ u8 fdb_to_vport_reg_c_id[0x8];
+ u8 reserved_at_10[0x10];
u8 reserved_at_20[0x20];
};
struct mlx5_ifc_esw_vport_context_fields_select_bits {
- u8 reserved_at_0[0x1c];
+ u8 reserved_at_0[0x1b];
+ u8 fdb_to_vport_reg_c_id[0x1];
u8 vport_cvlan_insert[0x1];
u8 vport_svlan_insert[0x1];
u8 vport_cvlan_strip[0x1];
MLX5_ACTION_IN_FIELD_OUT_DIPV4 = 0x16,
MLX5_ACTION_IN_FIELD_OUT_FIRST_VID = 0x17,
MLX5_ACTION_IN_FIELD_OUT_IPV6_HOPLIMIT = 0x47,
+ MLX5_ACTION_IN_FIELD_METADATA_REG_C_0 = 0x51,
};
struct mlx5_ifc_alloc_modify_header_context_out_bits {
struct mlx5_ifc_flow_table_context_bits {
u8 reformat_en[0x1];
u8 decap_en[0x1];
- u8 reserved_at_2[0x2];
+ u8 reserved_at_2[0x1];
+ u8 termination_table[0x1];
u8 table_miss_action[0x4];
u8 level[0x8];
u8 reserved_at_10[0x8];
u8 reserved_at_280[0x40];
- u8 event_bitmask[0x40];
+ u8 event_bitmask[4][0x40];
- u8 reserved_at_300[0x580];
+ u8 reserved_at_3c0[0x4c0];
u8 pas[0][0x40];
};
u8 mcda[0x1];
u8 mcc[0x1];
u8 mcqi[0x1];
- u8 reserved_at_1f[0x1];
+ u8 mcqs[0x1];
u8 regs_95_to_87[0x9];
u8 mpegc[0x1];
u8 reserved_at_1c0[0x80];
};
+struct mlx5_ifc_core_dump_reg_bits {
+ u8 reserved_at_0[0x18];
+ u8 core_dump_type[0x8];
+
+ u8 reserved_at_20[0x30];
+ u8 vhca_id[0x10];
+
+ u8 reserved_at_60[0x8];
+ u8 qpn[0x18];
+ u8 reserved_at_80[0x180];
+};
+
struct mlx5_ifc_pcap_reg_bits {
u8 reserved_at_0[0x8];
u8 local_port[0x8];
u8 reserved_at_40[0x40];
};
+struct mlx5_ifc_mcqs_reg_bits {
+ u8 last_index_flag[0x1];
+ u8 reserved_at_1[0x7];
+ u8 fw_device[0x8];
+ u8 component_index[0x10];
+
+ u8 reserved_at_20[0x10];
+ u8 identifier[0x10];
+
+ u8 reserved_at_40[0x17];
+ u8 component_status[0x5];
+ u8 component_update_state[0x4];
+
+ u8 last_update_state_changer_type[0x4];
+ u8 last_update_state_changer_host_id[0x4];
+ u8 reserved_at_68[0x18];
+};
+
struct mlx5_ifc_mcqi_cap_bits {
u8 supported_info_bitmask[0x20];
u8 reserved_at_86[0x1a];
};
+struct mlx5_ifc_mcqi_version_bits {
+ u8 reserved_at_0[0x2];
+ u8 build_time_valid[0x1];
+ u8 user_defined_time_valid[0x1];
+ u8 reserved_at_4[0x14];
+ u8 version_string_length[0x8];
+
+ u8 version[0x20];
+
+ u8 build_time[0x40];
+
+ u8 user_defined_time[0x40];
+
+ u8 build_tool_version[0x20];
+
+ u8 reserved_at_e0[0x20];
+
+ u8 version_string[92][0x8];
+};
+
+struct mlx5_ifc_mcqi_activation_method_bits {
+ u8 pending_server_ac_power_cycle[0x1];
+ u8 pending_server_dc_power_cycle[0x1];
+ u8 pending_server_reboot[0x1];
+ u8 pending_fw_reset[0x1];
+ u8 auto_activate[0x1];
+ u8 all_hosts_sync[0x1];
+ u8 device_hw_reset[0x1];
+ u8 reserved_at_7[0x19];
+};
+
+union mlx5_ifc_mcqi_reg_data_bits {
+ struct mlx5_ifc_mcqi_cap_bits mcqi_caps;
+ struct mlx5_ifc_mcqi_version_bits mcqi_version;
+ struct mlx5_ifc_mcqi_activation_method_bits mcqi_activation_mathod;
+};
+
struct mlx5_ifc_mcqi_reg_bits {
u8 read_pending_component[0x1];
u8 reserved_at_1[0xf];
u8 reserved_at_a0[0x10];
u8 data_size[0x10];
- u8 data[0][0x20];
+ union mlx5_ifc_mcqi_reg_data_bits data[0];
};
struct mlx5_ifc_mcc_reg_bits {
struct mlx5_ifc_host_params_context_bits {
u8 host_number[0x8];
- u8 reserved_at_8[0x8];
+ u8 reserved_at_8[0x7];
+ u8 host_pf_disabled[0x1];
u8 host_num_of_vfs[0x10];
- u8 reserved_at_20[0x10];
+ u8 host_total_vfs[0x10];
u8 host_pci_bus[0x10];
u8 reserved_at_40[0x10];
u8 reserved_at_80[0x180];
};
-struct mlx5_ifc_query_host_params_in_bits {
+struct mlx5_ifc_query_esw_functions_in_bits {
u8 opcode[0x10];
u8 reserved_at_10[0x10];
u8 reserved_at_40[0x40];
};
-struct mlx5_ifc_query_host_params_out_bits {
+struct mlx5_ifc_query_esw_functions_out_bits {
u8 status[0x8];
u8 reserved_at_8[0x18];
struct mlx5_ifc_host_params_context_bits host_params_context;
u8 reserved_at_280[0x180];
+ u8 host_sf_enable[0][0x40];
+};
+
+struct mlx5_ifc_sf_partition_bits {
+ u8 reserved_at_0[0x10];
+ u8 log_num_sf[0x8];
+ u8 log_sf_bar_size[0x8];
+};
+
+struct mlx5_ifc_query_sf_partitions_out_bits {
+ u8 status[0x8];
+ u8 reserved_at_8[0x18];
+
+ u8 syndrome[0x20];
+
+ u8 reserved_at_40[0x18];
+ u8 num_sf_partitions[0x8];
+
+ u8 reserved_at_60[0x20];
+
+ struct mlx5_ifc_sf_partition_bits sf_partition[0];
+};
+
+struct mlx5_ifc_query_sf_partitions_in_bits {
+ u8 opcode[0x10];
+ u8 reserved_at_10[0x10];
+
+ u8 reserved_at_20[0x10];
+ u8 op_mod[0x10];
+
+ u8 reserved_at_40[0x40];
+};
+
+struct mlx5_ifc_dealloc_sf_out_bits {
+ u8 status[0x8];
+ u8 reserved_at_8[0x18];
+
+ u8 syndrome[0x20];
+
+ u8 reserved_at_40[0x40];
+};
+
+struct mlx5_ifc_dealloc_sf_in_bits {
+ u8 opcode[0x10];
+ u8 reserved_at_10[0x10];
+
+ u8 reserved_at_20[0x10];
+ u8 op_mod[0x10];
+
+ u8 reserved_at_40[0x10];
+ u8 function_id[0x10];
+
+ u8 reserved_at_60[0x20];
+};
+
+struct mlx5_ifc_alloc_sf_out_bits {
+ u8 status[0x8];
+ u8 reserved_at_8[0x18];
+
+ u8 syndrome[0x20];
+
+ u8 reserved_at_40[0x40];
+};
+
+struct mlx5_ifc_alloc_sf_in_bits {
+ u8 opcode[0x10];
+ u8 reserved_at_10[0x10];
+
+ u8 reserved_at_20[0x10];
+ u8 op_mod[0x10];
+
+ u8 reserved_at_40[0x10];
+ u8 function_id[0x10];
+
+ u8 reserved_at_60[0x20];
+};
+
+struct mlx5_ifc_affiliated_event_header_bits {
+ u8 reserved_at_0[0x10];
+ u8 obj_type[0x10];
+
+ u8 obj_id[0x20];
+};
+
+enum {
+ MLX5_HCA_CAP_GENERAL_OBJECT_TYPES_ENCRYPTION_KEY = BIT(0xc),
+};
+
+enum {
+ MLX5_GENERAL_OBJECT_TYPES_ENCRYPTION_KEY = 0xc,
+};
+
+struct mlx5_ifc_encryption_key_obj_bits {
+ u8 modify_field_select[0x40];
+
+ u8 reserved_at_40[0x14];
+ u8 key_size[0x4];
+ u8 reserved_at_58[0x4];
+ u8 key_type[0x4];
+
+ u8 reserved_at_60[0x8];
+ u8 pd[0x18];
+
+ u8 reserved_at_80[0x180];
+ u8 key[8][0x20];
+
+ u8 reserved_at_300[0x500];
+};
+
+struct mlx5_ifc_create_encryption_key_in_bits {
+ struct mlx5_ifc_general_obj_in_cmd_hdr_bits general_obj_in_cmd_hdr;
+ struct mlx5_ifc_encryption_key_obj_bits encryption_key_object;
+};
+
+enum {
+ MLX5_GENERAL_OBJECT_TYPE_ENCRYPTION_KEY_KEY_SIZE_128 = 0x0,
+ MLX5_GENERAL_OBJECT_TYPE_ENCRYPTION_KEY_KEY_SIZE_256 = 0x1,
+};
+
+enum {
+ MLX5_GENERAL_OBJECT_TYPE_ENCRYPTION_KEY_TYPE_DEK = 0x1,
+};
+
+struct mlx5_ifc_tls_static_params_bits {
+ u8 const_2[0x2];
+ u8 tls_version[0x4];
+ u8 const_1[0x2];
+ u8 reserved_at_8[0x14];
+ u8 encryption_standard[0x4];
+
+ u8 reserved_at_20[0x20];
+
+ u8 initial_record_number[0x40];
+
+ u8 resync_tcp_sn[0x20];
+
+ u8 gcm_iv[0x20];
+
+ u8 implicit_iv[0x40];
+
+ u8 reserved_at_100[0x8];
+ u8 dek_index[0x18];
+
+ u8 reserved_at_120[0xe0];
+};
+
+struct mlx5_ifc_tls_progress_params_bits {
+ u8 valid[0x1];
+ u8 reserved_at_1[0x7];
+ u8 pd[0x18];
+
+ u8 next_record_tcp_sn[0x20];
+
+ u8 hw_resync_tcp_sn[0x20];
+
+ u8 record_tracker_state[0x2];
+ u8 auth_state[0x2];
+ u8 reserved_at_64[0x4];
+ u8 hw_offset_record_number[0x18];
};
#endif /* MLX5_IFC_H */