1 files changed, 115 insertions, 72 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index aebcf73f8546..42ec28e29834 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -158,16 +158,6 @@ static void mlx5e_update_carrier_work(struct work_struct *work)
 	mutex_unlock(&priv->state_lock);
 }
 
-void mlx5e_update_ndo_stats(struct mlx5e_priv *priv)
-{
-	int i;
-
-	for (i = mlx5e_nic_stats_grps_num(priv) - 1; i >= 0; i--)
-		if (mlx5e_nic_stats_grps[i]->update_stats_mask &
-		    MLX5E_NDO_UPDATE_STATS)
-			mlx5e_nic_stats_grps[i]->update_stats(priv);
-}
-
 static void mlx5e_update_stats_work(struct work_struct *work)
 {
 	struct mlx5e_priv *priv = container_of(work, struct mlx5e_priv,
@@ -256,12 +246,17 @@ static int mlx5e_rq_alloc_mpwqe_info(struct mlx5e_rq *rq,
 
 static int mlx5e_create_umr_mkey(struct mlx5_core_dev *mdev,
 				 u64 npages, u8 page_shift,
-				 struct mlx5_core_mkey *umr_mkey)
+				 struct mlx5_core_mkey *umr_mkey,
+				 dma_addr_t filler_addr)
 {
-	int inlen = MLX5_ST_SZ_BYTES(create_mkey_in);
+	struct mlx5_mtt *mtt;
+	int inlen;
 	void *mkc;
 	u32 *in;
 	int err;
+	int i;
+
+	inlen = MLX5_ST_SZ_BYTES(create_mkey_in) + sizeof(*mtt) * npages;
 
 	in = kvzalloc(inlen, GFP_KERNEL);
 	if (!in)
@@ -281,6 +276,18 @@ static int mlx5e_create_umr_mkey(struct mlx5_core_dev *mdev,
 	MLX5_SET(mkc, mkc, translations_octword_size,
 		 MLX5_MTT_OCTW(npages));
 	MLX5_SET(mkc, mkc, log_page_size, page_shift);
+	MLX5_SET(create_mkey_in, in, translations_octword_actual_size,
+		 MLX5_MTT_OCTW(npages));
+
+	/* Initialize the mkey with all MTTs pointing to a default
+	 * page (filler_addr). When the channels are activated, UMR
+	 * WQEs will redirect the RX WQEs to the actual memory from
+	 * the RQ's pool, while the gaps (wqe_overflow) remain mapped
+	 * to the default page.
+	 */
+	mtt = MLX5_ADDR_OF(create_mkey_in, in, klm_pas_mtt);
+	for (i = 0 ; i < npages ; i++)
+		mtt[i].ptag = cpu_to_be64(filler_addr);
 
 	err = mlx5_core_create_mkey(mdev, umr_mkey, in, inlen);
 
@@ -292,7 +299,8 @@ static int mlx5e_create_rq_umr_mkey(struct mlx5_core_dev *mdev, struct mlx5e_rq
 {
 	u64 num_mtts = MLX5E_REQUIRED_MTTS(mlx5_wq_ll_get_size(&rq->mpwqe.wq));
 
-	return mlx5e_create_umr_mkey(mdev, num_mtts, PAGE_SHIFT, &rq->umr_mkey);
+	return mlx5e_create_umr_mkey(mdev, num_mtts, PAGE_SHIFT, &rq->umr_mkey,
+				     rq->wqe_overflow.addr);
 }
 
 static inline u64 mlx5e_get_mpwqe_offset(struct mlx5e_rq *rq, u16 wqe_ix)
@@ -360,6 +368,28 @@ static void mlx5e_rq_err_cqe_work(struct work_struct *recover_work)
 	mlx5e_reporter_rq_cqe_err(rq);
 }
 
+static int mlx5e_alloc_mpwqe_rq_drop_page(struct mlx5e_rq *rq)
+{
+	rq->wqe_overflow.page = alloc_page(GFP_KERNEL);
+	if (!rq->wqe_overflow.page)
+		return -ENOMEM;
+
+	rq->wqe_overflow.addr = dma_map_page(rq->pdev, rq->wqe_overflow.page, 0,
+					     PAGE_SIZE, rq->buff.map_dir);
+	if (dma_mapping_error(rq->pdev, rq->wqe_overflow.addr)) {
+		__free_page(rq->wqe_overflow.page);
+		return -ENOMEM;
+	}
+	return 0;
+}
+
+static void mlx5e_free_mpwqe_rq_drop_page(struct mlx5e_rq *rq)
+{
+	 dma_unmap_page(rq->pdev, rq->wqe_overflow.addr, PAGE_SIZE,
+			rq->buff.map_dir);
+	 __free_page(rq->wqe_overflow.page);
+}
+
 static int mlx5e_alloc_rq(struct mlx5e_channel *c,
 			  struct mlx5e_params *params,
 			  struct mlx5e_xsk_param *xsk,
@@ -399,16 +429,16 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
 
 	if (params->xdp_prog)
 		bpf_prog_inc(params->xdp_prog);
-	rq->xdp_prog = params->xdp_prog;
+	RCU_INIT_POINTER(rq->xdp_prog, params->xdp_prog);
 
 	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;
+		goto err_rq_xdp_prog;
 
-	rq->buff.map_dir = rq->xdp_prog ? DMA_BIDIRECTIONAL : DMA_FROM_DEVICE;
+	rq->buff.map_dir = params->xdp_prog ? DMA_BIDIRECTIONAL : DMA_FROM_DEVICE;
 	rq->buff.headroom = mlx5e_get_rq_headroom(mdev, params, xsk);
 	pool_size = 1 << params->log_rq_mtu_frames;
 
@@ -417,6 +447,10 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
 		err = mlx5_wq_ll_create(mdev, &rqp->wq, rqc_wq, &rq->mpwqe.wq,
 					&rq->wq_ctrl);
 		if (err)
+			goto err_rq_xdp;
+
+		err = mlx5e_alloc_mpwqe_rq_drop_page(rq);
+		if (err)
 			goto err_rq_wq_destroy;
 
 		rq->mpwqe.wq.db = &rq->mpwqe.wq.db[MLX5_RCV_DBR];
@@ -434,18 +468,18 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
 
 		err = mlx5e_create_rq_umr_mkey(mdev, rq);
 		if (err)
-			goto err_rq_wq_destroy;
+			goto err_rq_drop_page;
 		rq->mkey_be = cpu_to_be32(rq->umr_mkey.key);
 
 		err = mlx5e_rq_alloc_mpwqe_info(rq, c);
 		if (err)
-			goto err_free;
+			goto err_rq_mkey;
 		break;
 	default: /* MLX5_WQ_TYPE_CYCLIC */
 		err = mlx5_wq_cyc_create(mdev, &rqp->wq, rqc_wq, &rq->wqe.wq,
 					 &rq->wq_ctrl);
 		if (err)
-			goto err_rq_wq_destroy;
+			goto err_rq_xdp;
 
 		rq->wqe.wq.db = &rq->wqe.wq.db[MLX5_RCV_DBR];
 
@@ -460,19 +494,19 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
 				      GFP_KERNEL, cpu_to_node(c->cpu));
 		if (!rq->wqe.frags) {
 			err = -ENOMEM;
-			goto err_free;
+			goto err_rq_wq_destroy;
 		}
 
 		err = mlx5e_init_di_list(rq, wq_sz, c->cpu);
 		if (err)
-			goto err_free;
+			goto err_rq_frags;
 
 		rq->mkey_be = c->mkey_be;
 	}
 
 	err = mlx5e_rq_set_handlers(rq, params, xsk);
 	if (err)
-		goto err_free;
+		goto err_free_by_rq_type;
 
 	if (xsk) {
 		err = xdp_rxq_info_reg_mem_model(&rq->xdp_rxq,
@@ -496,13 +530,13 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
 		if (IS_ERR(rq->page_pool)) {
 			err = PTR_ERR(rq->page_pool);
 			rq->page_pool = NULL;
-			goto err_free;
+			goto err_free_by_rq_type;
 		}
 		err = xdp_rxq_info_reg_mem_model(&rq->xdp_rxq,
 						 MEM_TYPE_PAGE_POOL, rq->page_pool);
 	}
 	if (err)
-		goto err_free;
+		goto err_free_by_rq_type;
 
 	for (i = 0; i < wq_sz; i++) {
 		if (rq->wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ) {
@@ -552,38 +586,49 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
 
 	return 0;
 
-err_free:
+err_free_by_rq_type:
 	switch (rq->wq_type) {
 	case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
 		kvfree(rq->mpwqe.info);
+err_rq_mkey:
 		mlx5_core_destroy_mkey(mdev, &rq->umr_mkey);
+err_rq_drop_page:
+		mlx5e_free_mpwqe_rq_drop_page(rq);
 		break;
 	default: /* MLX5_WQ_TYPE_CYCLIC */
-		kvfree(rq->wqe.frags);
 		mlx5e_free_di_list(rq);
+err_rq_frags:
+		kvfree(rq->wqe.frags);
 	}
-
 err_rq_wq_destroy:
-	if (rq->xdp_prog)
-		bpf_prog_put(rq->xdp_prog);
-	xdp_rxq_info_unreg(&rq->xdp_rxq);
-	page_pool_destroy(rq->page_pool);
 	mlx5_wq_destroy(&rq->wq_ctrl);
+err_rq_xdp:
+	xdp_rxq_info_unreg(&rq->xdp_rxq);
+err_rq_xdp_prog:
+	if (params->xdp_prog)
+		bpf_prog_put(params->xdp_prog);
 
 	return err;
 }
 
 static void mlx5e_free_rq(struct mlx5e_rq *rq)
 {
+	struct mlx5e_channel *c = rq->channel;
+	struct bpf_prog *old_prog = NULL;
 	int i;
 
-	if (rq->xdp_prog)
-		bpf_prog_put(rq->xdp_prog);
+	/* drop_rq has neither channel nor xdp_prog. */
+	if (c)
+		old_prog = rcu_dereference_protected(rq->xdp_prog,
+						     lockdep_is_held(&c->priv->state_lock));
+	if (old_prog)
+		bpf_prog_put(old_prog);
 
 	switch (rq->wq_type) {
 	case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
 		kvfree(rq->mpwqe.info);
 		mlx5_core_destroy_mkey(rq->mdev, &rq->umr_mkey);
+		mlx5e_free_mpwqe_rq_drop_page(rq);
 		break;
 	default: /* MLX5_WQ_TYPE_CYCLIC */
 		kvfree(rq->wqe.frags);
@@ -867,7 +912,7 @@ void mlx5e_activate_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 */
+	synchronize_rcu(); /* Sync with NAPI to prevent mlx5e_post_rx_wqes. */
 }
 
 void mlx5e_close_rq(struct mlx5e_rq *rq)
@@ -1312,12 +1357,10 @@ void mlx5e_tx_disable_queue(struct netdev_queue *txq)
 
 static void mlx5e_deactivate_txqsq(struct mlx5e_txqsq *sq)
 {
-	struct mlx5e_channel *c = sq->channel;
 	struct mlx5_wq_cyc *wq = &sq->wq;
 
 	clear_bit(MLX5E_SQ_STATE_ENABLED, &sq->state);
-	/* prevent netif_tx_wake_queue */
-	napi_synchronize(&c->napi);
+	synchronize_rcu(); /* Sync with NAPI to prevent netif_tx_wake_queue. */
 
 	mlx5e_tx_disable_queue(sq->txq);
 
@@ -1392,10 +1435,8 @@ void mlx5e_activate_icosq(struct mlx5e_icosq *icosq)
 
 void mlx5e_deactivate_icosq(struct mlx5e_icosq *icosq)
 {
-	struct mlx5e_channel *c = icosq->channel;
-
 	clear_bit(MLX5E_SQ_STATE_ENABLED, &icosq->state);
-	napi_synchronize(&c->napi);
+	synchronize_rcu(); /* Sync with NAPI. */
 }
 
 void mlx5e_close_icosq(struct mlx5e_icosq *sq)
@@ -1474,7 +1515,7 @@ void mlx5e_close_xdpsq(struct mlx5e_xdpsq *sq)
 	struct mlx5e_channel *c = sq->channel;
 
 	clear_bit(MLX5E_SQ_STATE_ENABLED, &sq->state);
-	napi_synchronize(&c->napi);
+	synchronize_rcu(); /* Sync with NAPI. */
 
 	mlx5e_destroy_sq(c->mdev, sq->sqn);
 	mlx5e_free_xdpsq_descs(sq);
@@ -3567,6 +3608,7 @@ void mlx5e_fold_sw_stats64(struct mlx5e_priv *priv, struct rtnl_link_stats64 *s)
 
 		s->rx_packets   += rq_stats->packets + xskrq_stats->packets;
 		s->rx_bytes     += rq_stats->bytes + xskrq_stats->bytes;
+		s->multicast    += rq_stats->mcast_packets + xskrq_stats->mcast_packets;
 
 		for (j = 0; j < priv->max_opened_tc; j++) {
 			struct mlx5e_sq_stats *sq_stats = &channel_stats->sq[j];
@@ -3582,7 +3624,6 @@ void
 mlx5e_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats)
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
-	struct mlx5e_vport_stats *vstats = &priv->stats.vport;
 	struct mlx5e_pport_stats *pstats = &priv->stats.pport;
 
 	/* In switchdev mode, monitor counters doesn't monitor
@@ -3617,12 +3658,6 @@ mlx5e_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats)
 	stats->rx_errors = stats->rx_length_errors + stats->rx_crc_errors +
 			   stats->rx_frame_errors;
 	stats->tx_errors = stats->tx_aborted_errors + stats->tx_carrier_errors;
-
-	/* vport multicast also counts packets that are dropped due to steering
-	 * or rx out of buffer
-	 */
-	stats->multicast =
-		VPORT_COUNTER_GET(vstats, received_eth_multicast.packets);
 }
 
 static void mlx5e_set_rx_mode(struct net_device *dev)
@@ -4191,6 +4226,21 @@ int mlx5e_get_vf_stats(struct net_device *dev,
 }
 #endif
 
+static bool mlx5e_gre_tunnel_inner_proto_offload_supported(struct mlx5_core_dev *mdev,
+							   struct sk_buff *skb)
+{
+	switch (skb->inner_protocol) {
+	case htons(ETH_P_IP):
+	case htons(ETH_P_IPV6):
+	case htons(ETH_P_TEB):
+		return true;
+	case htons(ETH_P_MPLS_UC):
+	case htons(ETH_P_MPLS_MC):
+		return MLX5_CAP_ETH(mdev, tunnel_stateless_mpls_over_gre);
+	}
+	return false;
+}
+
 static netdev_features_t mlx5e_tunnel_features_check(struct mlx5e_priv *priv,
 						     struct sk_buff *skb,
 						     netdev_features_t features)
@@ -4213,7 +4263,9 @@ static netdev_features_t mlx5e_tunnel_features_check(struct mlx5e_priv *priv,
 
 	switch (proto) {
 	case IPPROTO_GRE:
-		return features;
+		if (mlx5e_gre_tunnel_inner_proto_offload_supported(priv->mdev, skb))
+			return features;
+		break;
 	case IPPROTO_IPIP:
 	case IPPROTO_IPV6:
 		if (mlx5e_tunnel_proto_supported(priv->mdev, IPPROTO_IPIP))
@@ -4330,6 +4382,16 @@ static int mlx5e_xdp_allowed(struct mlx5e_priv *priv, struct bpf_prog *prog)
 	return 0;
 }
 
+static void mlx5e_rq_replace_xdp_prog(struct mlx5e_rq *rq, struct bpf_prog *prog)
+{
+	struct bpf_prog *old_prog;
+
+	old_prog = rcu_replace_pointer(rq->xdp_prog, prog,
+				       lockdep_is_held(&rq->channel->priv->state_lock));
+	if (old_prog)
+		bpf_prog_put(old_prog);
+}
+
 static int mlx5e_xdp_set(struct net_device *netdev, struct bpf_prog *prog)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
@@ -4388,29 +4450,10 @@ static int mlx5e_xdp_set(struct net_device *netdev, struct bpf_prog *prog)
 	 */
 	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);
+		mlx5e_rq_replace_xdp_prog(&c->rq, prog);
+		if (test_bit(MLX5E_CHANNEL_STATE_XSK, c->state))
+			mlx5e_rq_replace_xdp_prog(&c->xskrq, prog);
 	}
 
 unlock:
@@ -5200,7 +5243,7 @@ static const struct mlx5e_profile mlx5e_nic_profile = {
 	.enable		   = mlx5e_nic_enable,
 	.disable	   = mlx5e_nic_disable,
 	.update_rx	   = mlx5e_update_nic_rx,
-	.update_stats	   = mlx5e_update_ndo_stats,
+	.update_stats	   = mlx5e_stats_update_ndo_stats,
 	.update_carrier	   = mlx5e_update_carrier,
 	.rx_handlers       = &mlx5e_rx_handlers_nic,
 	.max_tc		   = MLX5E_MAX_NUM_TC,