Merge tag 'mlx5-updates-2019-08-01' of git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux

Saeed Mahameed says:

====================
mlx5-updates-2019-08-01

Misc updates for mlx5 netdev driver:

1) Ingress rate support for E-Switch vports from Eli.
2) Gavi introduces flow counters bulk allocation and pool,
   To improve the performance of flow counter acquisition.
3) From Tariq, micro improvements for tx path
4) From Shay, small improvement for XDP TX MPWQE inline flow.
5) Aya provides some cleanups for tx devlink health reporters.
6) Saeed, refactor checksum handling into a single function.
7) Tonghao, allows dropping specific tunnel packets.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

Author: davem330

drivers/net/ethernet/mellanox/mlx5/core/en.h

@@ -359,6 +359,7 @@ enum {
 	MLX5E_SQ_STATE_IPSEC,
 	MLX5E_SQ_STATE_AM,
 	MLX5E_SQ_STATE_TLS,
+	MLX5E_SQ_STATE_VLAN_NEED_L2_INLINE,
 };
 
 struct mlx5e_sq_wqe_info {
@@ -483,8 +484,6 @@ struct mlx5e_xdp_mpwqe {
 	struct mlx5e_tx_wqe *wqe;
 	u8                   ds_count;
 	u8                   pkt_count;
-	u8                   max_ds_count;
-	u8                   complete;
 	u8                   inline_on;
 };
 
@@ -1134,7 +1133,6 @@ void mlx5e_build_rq_params(struct mlx5_core_dev *mdev,
 			   struct mlx5e_params *params);
 void mlx5e_build_rss_params(struct mlx5e_rss_params *rss_params,
 			    u16 num_channels);
-u8 mlx5e_params_calculate_tx_min_inline(struct mlx5_core_dev *mdev);
 void mlx5e_rx_dim_work(struct work_struct *work);
 void mlx5e_tx_dim_work(struct work_struct *work);
 

drivers/net/ethernet/mellanox/mlx5/core/en/reporter.h

@@ -4,7 +4,6 @@
 #ifndef __MLX5E_EN_REPORTER_H
 #define __MLX5E_EN_REPORTER_H
 
-#include <linux/mlx5/driver.h>
 #include "en.h"
 
 int mlx5e_tx_reporter_create(struct mlx5e_priv *priv);

drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c

@@ -1,7 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 /* Copyright (c) 2019 Mellanox Technologies. */
 
-#include <net/devlink.h>
 #include "reporter.h"
 #include "lib/eq.h"
 
@@ -117,7 +116,7 @@ static int mlx5_tx_health_report(struct devlink_health_reporter *tx_reporter,
 				 char *err_str,
 				 struct mlx5e_tx_err_ctx *err_ctx)
 {
-	if (IS_ERR_OR_NULL(tx_reporter)) {
+	if (!tx_reporter) {
 		netdev_err(err_ctx->sq->channel->netdev, err_str);
 		return err_ctx->recover(err_ctx->sq);
 	}
@@ -289,23 +288,27 @@ static const struct devlink_health_reporter_ops mlx5_tx_reporter_ops = {
 
 int mlx5e_tx_reporter_create(struct mlx5e_priv *priv)
 {
+	struct devlink_health_reporter *reporter;
 	struct mlx5_core_dev *mdev = priv->mdev;
 	struct devlink *devlink = priv_to_devlink(mdev);
 
-	priv->tx_reporter =
+	reporter =
 		devlink_health_reporter_create(devlink, &mlx5_tx_reporter_ops,
 					       MLX5_REPORTER_TX_GRACEFUL_PERIOD,
 					       true, priv);
-	if (IS_ERR(priv->tx_reporter))
+	if (IS_ERR(reporter)) {
 		netdev_warn(priv->netdev,
 			    "Failed to create tx reporter, err = %ld\n",
-			    PTR_ERR(priv->tx_reporter));
-	return IS_ERR_OR_NULL(priv->tx_reporter);
+			    PTR_ERR(reporter));
+		return PTR_ERR(reporter);
+	}
+	priv->tx_reporter = reporter;
+	return 0;
 }
 
 void mlx5e_tx_reporter_destroy(struct mlx5e_priv *priv)
 {
-	if (IS_ERR_OR_NULL(priv->tx_reporter))
+	if (!priv->tx_reporter)
 		return;
 
 	devlink_health_reporter_destroy(priv->tx_reporter);

drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h

@@ -6,7 +6,7 @@
 
 #include "en.h"
 
-#define MLX5E_SQ_NOPS_ROOM  MLX5_SEND_WQE_MAX_WQEBBS
+#define MLX5E_SQ_NOPS_ROOM (MLX5_SEND_WQE_MAX_WQEBBS - 1)
 #define MLX5E_SQ_STOP_ROOM (MLX5_SEND_WQE_MAX_WQEBBS +\
 			    MLX5E_SQ_NOPS_ROOM)
 
@@ -117,9 +117,27 @@ mlx5e_notify_hw(struct mlx5_wq_cyc *wq, u16 pc, void __iomem *uar_map,
 	mlx5_write64((__be32 *)ctrl, uar_map);
 }
 
-static inline bool mlx5e_transport_inline_tx_wqe(struct mlx5e_tx_wqe *wqe)
+static inline bool mlx5e_transport_inline_tx_wqe(struct mlx5_wqe_ctrl_seg *cseg)
 {
-	return !!wqe->ctrl.tisn;
+	return cseg && !!cseg->tisn;
+}
+
+static inline u8
+mlx5e_tx_wqe_inline_mode(struct mlx5e_txqsq *sq, struct mlx5_wqe_ctrl_seg *cseg,
+			 struct sk_buff *skb)
+{
+	u8 mode;
+
+	if (mlx5e_transport_inline_tx_wqe(cseg))
+		return MLX5_INLINE_MODE_TCP_UDP;
+
+	mode = sq->min_inline_mode;
+
+	if (skb_vlan_tag_present(skb) &&
+	    test_bit(MLX5E_SQ_STATE_VLAN_NEED_L2_INLINE, &sq->state))
+		mode = max_t(u8, MLX5_INLINE_MODE_L2, mode);
+
+	return mode;
 }
 
 static inline void mlx5e_cq_arm(struct mlx5e_cq *cq)

drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c

@@ -179,33 +179,19 @@ static void mlx5e_xdp_mpwqe_session_start(struct mlx5e_xdpsq *sq)
 	struct mlx5e_xdp_mpwqe *session = &sq->mpwqe;
 	struct mlx5e_xdpsq_stats *stats = sq->stats;
 	struct mlx5_wq_cyc *wq = &sq->wq;
-	u8  wqebbs;
-	u16 pi;
-
-	mlx5e_xdpsq_fetch_wqe(sq, &session->wqe);
-
-	prefetchw(session->wqe->data);
-	session->ds_count  = MLX5E_XDP_TX_EMPTY_DS_COUNT;
-	session->pkt_count = 0;
-	session->complete  = 0;
+	u16 pi, contig_wqebbs;
 
 	pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc);
+	contig_wqebbs = mlx5_wq_cyc_get_contig_wqebbs(wq, pi);
 
-/* The mult of MLX5_SEND_WQE_MAX_WQEBBS * MLX5_SEND_WQEBB_NUM_DS
- * (16 * 4 == 64) does not fit in the 6-bit DS field of Ctrl Segment.
- * We use a bound lower that MLX5_SEND_WQE_MAX_WQEBBS to let a
- * full-session WQE be cache-aligned.
- */
-#if L1_CACHE_BYTES < 128
-#define MLX5E_XDP_MPW_MAX_WQEBBS (MLX5_SEND_WQE_MAX_WQEBBS - 1)
-#else
-#define MLX5E_XDP_MPW_MAX_WQEBBS (MLX5_SEND_WQE_MAX_WQEBBS - 2)
-#endif
+	if (unlikely(contig_wqebbs < MLX5_SEND_WQE_MAX_WQEBBS))
+		mlx5e_fill_xdpsq_frag_edge(sq, wq, pi, contig_wqebbs);
 
-	wqebbs = min_t(u16, mlx5_wq_cyc_get_contig_wqebbs(wq, pi),
-		       MLX5E_XDP_MPW_MAX_WQEBBS);
+	session->wqe = mlx5e_xdpsq_fetch_wqe(sq, &pi);
 
-	session->max_ds_count = MLX5_SEND_WQEBB_NUM_DS * wqebbs;
+	prefetchw(session->wqe->data);
+	session->ds_count  = MLX5E_XDP_TX_EMPTY_DS_COUNT;
+	session->pkt_count = 0;
 
 	mlx5e_xdp_update_inline_state(sq);
 
@@ -244,7 +230,7 @@ static int mlx5e_xmit_xdp_frame_check_mpwqe(struct mlx5e_xdpsq *sq)
 {
 	if (unlikely(!sq->mpwqe.wqe)) {
 		if (unlikely(!mlx5e_wqc_has_room_for(&sq->wq, sq->cc, sq->pc,
-						     MLX5_SEND_WQE_MAX_WQEBBS))) {
+						     MLX5E_XDPSQ_STOP_ROOM))) {
 			/* SQ is full, ring doorbell */
 			mlx5e_xmit_xdp_doorbell(sq);
 			sq->stats->full++;
@@ -285,8 +271,8 @@ static bool mlx5e_xmit_xdp_frame_mpwqe(struct mlx5e_xdpsq *sq,
 
 	mlx5e_xdp_mpwqe_add_dseg(sq, xdptxd, stats);
 
-	if (unlikely(session->complete ||
-		     session->ds_count == session->max_ds_count))
+	if (unlikely(mlx5e_xdp_no_room_for_inline_pkt(session) ||
+		     session->ds_count == MLX5E_XDP_MPW_MAX_NUM_DS))
 		mlx5e_xdp_mpwqe_complete(sq);
 
 	mlx5e_xdpi_fifo_push(&sq->db.xdpi_fifo, xdpi);

drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h

@@ -40,6 +40,26 @@
 	(sizeof(struct mlx5e_tx_wqe) / MLX5_SEND_WQE_DS)
 #define MLX5E_XDP_TX_DS_COUNT (MLX5E_XDP_TX_EMPTY_DS_COUNT + 1 /* SG DS */)
 
+#define MLX5E_XDPSQ_STOP_ROOM (MLX5E_SQ_STOP_ROOM)
+
+#define MLX5E_XDP_INLINE_WQE_SZ_THRSD (256 - sizeof(struct mlx5_wqe_inline_seg))
+#define MLX5E_XDP_INLINE_WQE_MAX_DS_CNT \
+	DIV_ROUND_UP(MLX5E_XDP_INLINE_WQE_SZ_THRSD, MLX5_SEND_WQE_DS)
+
+/* The mult of MLX5_SEND_WQE_MAX_WQEBBS * MLX5_SEND_WQEBB_NUM_DS
+ * (16 * 4 == 64) does not fit in the 6-bit DS field of Ctrl Segment.
+ * We use a bound lower that MLX5_SEND_WQE_MAX_WQEBBS to let a
+ * full-session WQE be cache-aligned.
+ */
+#if L1_CACHE_BYTES < 128
+#define MLX5E_XDP_MPW_MAX_WQEBBS (MLX5_SEND_WQE_MAX_WQEBBS - 1)
+#else
+#define MLX5E_XDP_MPW_MAX_WQEBBS (MLX5_SEND_WQE_MAX_WQEBBS - 2)
+#endif
+
+#define MLX5E_XDP_MPW_MAX_NUM_DS \
+	(MLX5E_XDP_MPW_MAX_WQEBBS * MLX5_SEND_WQEBB_NUM_DS)
+
 struct mlx5e_xsk_param;
 int mlx5e_xdp_max_mtu(struct mlx5e_params *params, struct mlx5e_xsk_param *xsk);
 bool mlx5e_xdp_handle(struct mlx5e_rq *rq, struct mlx5e_dma_info *di,
@@ -114,6 +134,30 @@ static inline void mlx5e_xdp_update_inline_state(struct mlx5e_xdpsq *sq)
 		session->inline_on = 1;
 }
 
+static inline bool
+mlx5e_xdp_no_room_for_inline_pkt(struct mlx5e_xdp_mpwqe *session)
+{
+	return session->inline_on &&
+	       session->ds_count + MLX5E_XDP_INLINE_WQE_MAX_DS_CNT > MLX5E_XDP_MPW_MAX_NUM_DS;
+}
+
+static inline void
+mlx5e_fill_xdpsq_frag_edge(struct mlx5e_xdpsq *sq, struct mlx5_wq_cyc *wq,
+			   u16 pi, u16 nnops)
+{
+	struct mlx5e_xdp_wqe_info *edge_wi, *wi = &sq->db.wqe_info[pi];
+
+	edge_wi = wi + nnops;
+	/* fill sq frag edge with nops to avoid wqe wrapping two pages */
+	for (; wi < edge_wi; wi++) {
+		wi->num_wqebbs = 1;
+		wi->num_pkts   = 0;
+		mlx5e_post_nop(wq, sq->sqn, &sq->pc);
+	}
+
+	sq->stats->nops += nnops;
+}
+
 static inline void
 mlx5e_xdp_mpwqe_add_dseg(struct mlx5e_xdpsq *sq,
 			 struct mlx5e_xdp_xmit_data *xdptxd,
@@ -126,20 +170,12 @@ mlx5e_xdp_mpwqe_add_dseg(struct mlx5e_xdpsq *sq,
 
 	session->pkt_count++;
 
-#define MLX5E_XDP_INLINE_WQE_SZ_THRSD (256 - sizeof(struct mlx5_wqe_inline_seg))
-
 	if (session->inline_on && dma_len <= MLX5E_XDP_INLINE_WQE_SZ_THRSD) {
 		struct mlx5_wqe_inline_seg *inline_dseg =
 			(struct mlx5_wqe_inline_seg *)dseg;
 		u16 ds_len = sizeof(*inline_dseg) + dma_len;
 		u16 ds_cnt = DIV_ROUND_UP(ds_len, MLX5_SEND_WQE_DS);
 
-		if (unlikely(session->ds_count + ds_cnt > session->max_ds_count)) {
-			/* Not enough space for inline wqe, send with memory pointer */
-			session->complete = true;
-			goto no_inline;
-		}
-
 		inline_dseg->byte_count = cpu_to_be32(dma_len | MLX5_INLINE_SEG);
 		memcpy(inline_dseg->data, xdptxd->data, dma_len);
 
@@ -148,21 +184,23 @@ mlx5e_xdp_mpwqe_add_dseg(struct mlx5e_xdpsq *sq,
 		return;
 	}
 
-no_inline:
 	dseg->addr       = cpu_to_be64(xdptxd->dma_addr);
 	dseg->byte_count = cpu_to_be32(dma_len);
 	dseg->lkey       = sq->mkey_be;
 	session->ds_count++;
 }
 
-static inline void mlx5e_xdpsq_fetch_wqe(struct mlx5e_xdpsq *sq,
-					 struct mlx5e_tx_wqe **wqe)
+static inline struct mlx5e_tx_wqe *
+mlx5e_xdpsq_fetch_wqe(struct mlx5e_xdpsq *sq, u16 *pi)
 {
 	struct mlx5_wq_cyc *wq = &sq->wq;
-	u16 pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc);
+	struct mlx5e_tx_wqe *wqe;
+
+	*pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc);
+	wqe = mlx5_wq_cyc_get_wqe(wq, *pi);
+	memset(wqe, 0, sizeof(*wqe));
 
-	*wqe = mlx5_wq_cyc_get_wqe(wq, pi);
-	memset(*wqe, 0, sizeof(**wqe));
+	return wqe;
 }
 
 static inline void

drivers/net/ethernet/mellanox/mlx5/core/en_common.c

@@ -180,15 +180,3 @@ int mlx5e_refresh_tirs(struct mlx5e_priv *priv, bool enable_uc_lb)
 
 	return err;
 }
-
-u8 mlx5e_params_calculate_tx_min_inline(struct mlx5_core_dev *mdev)
-{
-	u8 min_inline_mode;
-
-	mlx5_query_min_inline(mdev, &min_inline_mode);
-	if (min_inline_mode == MLX5_INLINE_MODE_NONE &&
-	    !MLX5_CAP_ETH(mdev, wqe_vlan_insert))
-		min_inline_mode = MLX5_INLINE_MODE_L2;
-
-	return min_inline_mode;
-}

drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c

@@ -1101,7 +1101,7 @@ void mlx5e_dcbnl_delete_app(struct mlx5e_priv *priv)
 static void mlx5e_trust_update_tx_min_inline_mode(struct mlx5e_priv *priv,
 						  struct mlx5e_params *params)
 {
-	params->tx_min_inline_mode = mlx5e_params_calculate_tx_min_inline(priv->mdev);
+	mlx5_query_min_inline(priv->mdev, &params->tx_min_inline_mode);
 	if (priv->dcbx_dp.trust_state == MLX5_QPTS_TRUST_DSCP &&
 	    params->tx_min_inline_mode == MLX5_INLINE_MODE_L2)
 		params->tx_min_inline_mode = MLX5_INLINE_MODE_IP;

drivers/net/ethernet/mellanox/mlx5/core/en_main.c

@@ -1131,6 +1131,8 @@ static int mlx5e_alloc_txqsq(struct mlx5e_channel *c,
 	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_CAP_ETH(mdev, wqe_vlan_insert))
+		set_bit(MLX5E_SQ_STATE_VLAN_NEED_L2_INLINE, &sq->state);
 	if (MLX5_IPSEC_DEV(c->priv->mdev))
 		set_bit(MLX5E_SQ_STATE_IPSEC, &sq->state);
 	if (mlx5_accel_is_tls_device(c->priv->mdev)) {
@@ -2323,7 +2325,7 @@ int mlx5e_open_channels(struct mlx5e_priv *priv,
 			goto err_close_channels;
 	}
 
-	if (!IS_ERR_OR_NULL(priv->tx_reporter))
+	if (priv->tx_reporter)
 		devlink_health_reporter_state_update(priv->tx_reporter,
 						     DEVLINK_HEALTH_REPORTER_STATE_HEALTHY);
 
@@ -4777,7 +4779,7 @@ void mlx5e_build_nic_params(struct mlx5_core_dev *mdev,
 	mlx5e_set_tx_cq_mode_params(params, MLX5_CQ_PERIOD_MODE_START_FROM_EQE);
 
 	/* TX inline */
-	params->tx_min_inline_mode = mlx5e_params_calculate_tx_min_inline(mdev);
+	mlx5_query_min_inline(mdev, &params->tx_min_inline_mode);
 
 	/* RSS */
 	mlx5e_build_rss_params(rss_params, params->num_channels);

drivers/net/ethernet/mellanox/mlx5/core/en_rep.c

@@ -1156,6 +1156,23 @@ mlx5e_rep_setup_tc_cls_flower(struct mlx5e_priv *priv,
 	}
 }
 
+static
+int mlx5e_rep_setup_tc_cls_matchall(struct mlx5e_priv *priv,
+				    struct tc_cls_matchall_offload *ma)
+{
+	switch (ma->command) {
+	case TC_CLSMATCHALL_REPLACE:
+		return mlx5e_tc_configure_matchall(priv, ma);
+	case TC_CLSMATCHALL_DESTROY:
+		return mlx5e_tc_delete_matchall(priv, ma);
+	case TC_CLSMATCHALL_STATS:
+		mlx5e_tc_stats_matchall(priv, ma);
+		return 0;
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
 static int mlx5e_rep_setup_tc_cb(enum tc_setup_type type, void *type_data,
 				 void *cb_priv)
 {
@@ -1165,6 +1182,8 @@ static int mlx5e_rep_setup_tc_cb(enum tc_setup_type type, void *type_data,
 	switch (type) {
 	case TC_SETUP_CLSFLOWER:
 		return mlx5e_rep_setup_tc_cls_flower(priv, type_data, flags);
+	case TC_SETUP_CLSMATCHALL:
+		return mlx5e_rep_setup_tc_cls_matchall(priv, type_data);
 	default:
 		return -EOPNOTSUPP;
 	}