Merge tag 'mlx5-fixes-2017-12-19' of git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux

Saeed Mahameed says:

===================
Mellanox, mlx5 fixes 2017-12-19

The follwoing series includes some fixes for mlx5 core and etherent
driver.

Please pull and let me know if there is any problem.

This series doesn't introduce any conflict with the ongoing mlx5 for-next
submission.

For -stable:

kernels >= v4.7.y
    ("net/mlx5e: Fix possible deadlock of VXLAN lock")
    ("net/mlx5e: Add refcount to VXLAN structure")
    ("net/mlx5e: Prevent possible races in VXLAN control flow")
    ("net/mlx5e: Fix features check of IPv6 traffic")

kernels >= v4.9.y
    ("net/mlx5: Fix error flow in CREATE_QP command")
    ("net/mlx5: Fix rate limit packet pacing naming and struct")

kernels >= v4.13.y
    ("net/mlx5: FPGA, return -EINVAL if size is zero")

kernels >= v4.14.y
    ("Revert "mlx5: move affinity hints assignments to generic code")

All above patches apply and compile with no issues on corresponding -stable.
===================
Signed-off-by: David S. Miller <davem@davemloft.net>

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

@@ -362,7 +362,7 @@ static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op,
 	case MLX5_CMD_OP_QUERY_VPORT_COUNTER:
 	case MLX5_CMD_OP_ALLOC_Q_COUNTER:
 	case MLX5_CMD_OP_QUERY_Q_COUNTER:
-	case MLX5_CMD_OP_SET_RATE_LIMIT:
+	case MLX5_CMD_OP_SET_PP_RATE_LIMIT:
 	case MLX5_CMD_OP_QUERY_RATE_LIMIT:
 	case MLX5_CMD_OP_CREATE_SCHEDULING_ELEMENT:
 	case MLX5_CMD_OP_QUERY_SCHEDULING_ELEMENT:
@@ -505,7 +505,7 @@ const char *mlx5_command_str(int command)
 	MLX5_COMMAND_STR_CASE(ALLOC_Q_COUNTER);
 	MLX5_COMMAND_STR_CASE(DEALLOC_Q_COUNTER);
 	MLX5_COMMAND_STR_CASE(QUERY_Q_COUNTER);
-	MLX5_COMMAND_STR_CASE(SET_RATE_LIMIT);
+	MLX5_COMMAND_STR_CASE(SET_PP_RATE_LIMIT);
 	MLX5_COMMAND_STR_CASE(QUERY_RATE_LIMIT);
 	MLX5_COMMAND_STR_CASE(CREATE_SCHEDULING_ELEMENT);
 	MLX5_COMMAND_STR_CASE(DESTROY_SCHEDULING_ELEMENT);

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

@@ -82,6 +82,9 @@
 	max_t(u32, MLX5_MPWRQ_MIN_LOG_STRIDE_SZ(mdev), req)
 #define MLX5_MPWRQ_DEF_LOG_STRIDE_SZ(mdev)       MLX5_MPWRQ_LOG_STRIDE_SZ(mdev, 6)
 #define MLX5_MPWRQ_CQE_CMPRS_LOG_STRIDE_SZ(mdev) MLX5_MPWRQ_LOG_STRIDE_SZ(mdev, 8)
+#define MLX5E_MPWQE_STRIDE_SZ(mdev, cqe_cmprs) \
+	(cqe_cmprs ? MLX5_MPWRQ_CQE_CMPRS_LOG_STRIDE_SZ(mdev) : \
+	MLX5_MPWRQ_DEF_LOG_STRIDE_SZ(mdev))
 
 #define MLX5_MPWRQ_LOG_WQE_SZ			18
 #define MLX5_MPWRQ_WQE_PAGE_ORDER  (MLX5_MPWRQ_LOG_WQE_SZ - PAGE_SHIFT > 0 ? \
@@ -590,6 +593,7 @@ struct mlx5e_channel {
 	struct mlx5_core_dev      *mdev;
 	struct hwtstamp_config    *tstamp;
 	int                        ix;
+	int                        cpu;
 };
 
 struct mlx5e_channels {
@@ -935,8 +939,9 @@ void mlx5e_set_tx_cq_mode_params(struct mlx5e_params *params,
 				 u8 cq_period_mode);
 void mlx5e_set_rx_cq_mode_params(struct mlx5e_params *params,
 				 u8 cq_period_mode);
-void mlx5e_set_rq_type_params(struct mlx5_core_dev *mdev,
-			      struct mlx5e_params *params, u8 rq_type);
+void mlx5e_init_rq_type_params(struct mlx5_core_dev *mdev,
+			       struct mlx5e_params *params,
+			       u8 rq_type);
 
 static inline bool mlx5e_tunnel_inner_ft_supported(struct mlx5_core_dev *mdev)
 {

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

@@ -274,6 +274,7 @@ int mlx5e_dcbnl_ieee_setets_core(struct mlx5e_priv *priv, struct ieee_ets *ets)
 static int mlx5e_dbcnl_validate_ets(struct net_device *netdev,
 				    struct ieee_ets *ets)
 {
+	bool have_ets_tc = false;
 	int bw_sum = 0;
 	int i;
 
@@ -288,11 +289,14 @@ static int mlx5e_dbcnl_validate_ets(struct net_device *netdev,
 	}
 
 	/* Validate Bandwidth Sum */
-	for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++)
-		if (ets->tc_tsa[i] == IEEE_8021QAZ_TSA_ETS)
+	for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) {
+		if (ets->tc_tsa[i] == IEEE_8021QAZ_TSA_ETS) {
+			have_ets_tc = true;
 			bw_sum += ets->tc_tx_bw[i];
+		}
+	}
 
-	if (bw_sum != 0 && bw_sum != 100) {
+	if (have_ets_tc && bw_sum != 100) {
 		netdev_err(netdev,
 			   "Failed to validate ETS: BW sum is illegal\n");
 		return -EINVAL;

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

@@ -1523,8 +1523,10 @@ int mlx5e_modify_rx_cqe_compression_locked(struct mlx5e_priv *priv, bool new_val
 	new_channels.params = priv->channels.params;
 	MLX5E_SET_PFLAG(&new_channels.params, MLX5E_PFLAG_RX_CQE_COMPRESS, new_val);
 
-	mlx5e_set_rq_type_params(priv->mdev, &new_channels.params,
-				 new_channels.params.rq_wq_type);
+	new_channels.params.mpwqe_log_stride_sz =
+		MLX5E_MPWQE_STRIDE_SZ(priv->mdev, new_val);
+	new_channels.params.mpwqe_log_num_strides =
+		MLX5_MPWRQ_LOG_WQE_SZ - new_channels.params.mpwqe_log_stride_sz;
 
 	if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) {
 		priv->channels.params = new_channels.params;
@@ -1536,6 +1538,10 @@ int mlx5e_modify_rx_cqe_compression_locked(struct mlx5e_priv *priv, bool new_val
 		return err;
 
 	mlx5e_switch_priv_channels(priv, &new_channels, NULL);
+	mlx5e_dbg(DRV, priv, "MLX5E: RxCqeCmprss was turned %s\n",
+		  MLX5E_GET_PFLAG(&priv->channels.params,
+				  MLX5E_PFLAG_RX_CQE_COMPRESS) ? "ON" : "OFF");
+
 	return 0;
 }
 

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

@@ -71,11 +71,6 @@ struct mlx5e_channel_param {
 	struct mlx5e_cq_param      icosq_cq;
 };
 
-static int mlx5e_get_node(struct mlx5e_priv *priv, int ix)
-{
-	return pci_irq_get_node(priv->mdev->pdev, MLX5_EQ_VEC_COMP_BASE + ix);
-}
-
 static bool mlx5e_check_fragmented_striding_rq_cap(struct mlx5_core_dev *mdev)
 {
 	return MLX5_CAP_GEN(mdev, striding_rq) &&
@@ -83,7 +78,7 @@ static bool mlx5e_check_fragmented_striding_rq_cap(struct mlx5_core_dev *mdev)
 		MLX5_CAP_ETH(mdev, reg_umr_sq);
 }
 
-void mlx5e_set_rq_type_params(struct mlx5_core_dev *mdev,
+void mlx5e_init_rq_type_params(struct mlx5_core_dev *mdev,
 			       struct mlx5e_params *params, u8 rq_type)
 {
 	params->rq_wq_type = rq_type;
@@ -93,10 +88,8 @@ void mlx5e_set_rq_type_params(struct mlx5_core_dev *mdev,
 		params->log_rq_size = is_kdump_kernel() ?
 			MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE_MPW :
 			MLX5E_PARAMS_DEFAULT_LOG_RQ_SIZE_MPW;
-		params->mpwqe_log_stride_sz =
-			MLX5E_GET_PFLAG(params, MLX5E_PFLAG_RX_CQE_COMPRESS) ?
-			MLX5_MPWRQ_CQE_CMPRS_LOG_STRIDE_SZ(mdev) :
-			MLX5_MPWRQ_DEF_LOG_STRIDE_SZ(mdev);
+		params->mpwqe_log_stride_sz = MLX5E_MPWQE_STRIDE_SZ(mdev,
+			MLX5E_GET_PFLAG(params, MLX5E_PFLAG_RX_CQE_COMPRESS));
 		params->mpwqe_log_num_strides = MLX5_MPWRQ_LOG_WQE_SZ -
 			params->mpwqe_log_stride_sz;
 		break;
@@ -120,13 +113,14 @@ void mlx5e_set_rq_type_params(struct mlx5_core_dev *mdev,
 		       MLX5E_GET_PFLAG(params, MLX5E_PFLAG_RX_CQE_COMPRESS));
 }
 
-static void mlx5e_set_rq_params(struct mlx5_core_dev *mdev, struct mlx5e_params *params)
+static void mlx5e_set_rq_params(struct mlx5_core_dev *mdev,
+				struct mlx5e_params *params)
 {
 	u8 rq_type = mlx5e_check_fragmented_striding_rq_cap(mdev) &&
 		    !params->xdp_prog && !MLX5_IPSEC_DEV(mdev) ?
 		    MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ :
 		    MLX5_WQ_TYPE_LINKED_LIST;
-	mlx5e_set_rq_type_params(mdev, params, rq_type);
+	mlx5e_init_rq_type_params(mdev, params, rq_type);
 }
 
 static void mlx5e_update_carrier(struct mlx5e_priv *priv)
@@ -444,17 +438,16 @@ static int mlx5e_rq_alloc_mpwqe_info(struct mlx5e_rq *rq,
 	int wq_sz = mlx5_wq_ll_get_size(&rq->wq);
 	int mtt_sz = mlx5e_get_wqe_mtt_sz();
 	int mtt_alloc = mtt_sz + MLX5_UMR_ALIGN - 1;
-	int node = mlx5e_get_node(c->priv, c->ix);
 	int i;
 
 	rq->mpwqe.info = kzalloc_node(wq_sz * sizeof(*rq->mpwqe.info),
-					GFP_KERNEL, node);
+				      GFP_KERNEL, cpu_to_node(c->cpu));
 	if (!rq->mpwqe.info)
 		goto err_out;
 
 	/* We allocate more than mtt_sz as we will align the pointer */
-	rq->mpwqe.mtt_no_align = kzalloc_node(mtt_alloc * wq_sz,
-					GFP_KERNEL, node);
+	rq->mpwqe.mtt_no_align = kzalloc_node(mtt_alloc * wq_sz, GFP_KERNEL,
+					cpu_to_node(c->cpu));
 	if (unlikely(!rq->mpwqe.mtt_no_align))
 		goto err_free_wqe_info;
 
@@ -562,7 +555,7 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
 	int err;
 	int i;
 
-	rqp->wq.db_numa_node = mlx5e_get_node(c->priv, c->ix);
+	rqp->wq.db_numa_node = cpu_to_node(c->cpu);
 
 	err = mlx5_wq_ll_create(mdev, &rqp->wq, rqc_wq, &rq->wq,
 				&rq->wq_ctrl);
@@ -629,8 +622,7 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
 	default: /* MLX5_WQ_TYPE_LINKED_LIST */
 		rq->wqe.frag_info =
 			kzalloc_node(wq_sz * sizeof(*rq->wqe.frag_info),
-				     GFP_KERNEL,
-				     mlx5e_get_node(c->priv, c->ix));
+				     GFP_KERNEL, cpu_to_node(c->cpu));
 		if (!rq->wqe.frag_info) {
 			err = -ENOMEM;
 			goto err_rq_wq_destroy;
@@ -1000,13 +992,13 @@ static int mlx5e_alloc_xdpsq(struct mlx5e_channel *c,
 	sq->uar_map   = mdev->mlx5e_res.bfreg.map;
 	sq->min_inline_mode = params->tx_min_inline_mode;
 
-	param->wq.db_numa_node = mlx5e_get_node(c->priv, c->ix);
+	param->wq.db_numa_node = cpu_to_node(c->cpu);
 	err = mlx5_wq_cyc_create(mdev, &param->wq, sqc_wq, &sq->wq, &sq->wq_ctrl);
 	if (err)
 		return err;
 	sq->wq.db = &sq->wq.db[MLX5_SND_DBR];
 
-	err = mlx5e_alloc_xdpsq_db(sq, mlx5e_get_node(c->priv, c->ix));
+	err = mlx5e_alloc_xdpsq_db(sq, cpu_to_node(c->cpu));
 	if (err)
 		goto err_sq_wq_destroy;
 
@@ -1053,13 +1045,13 @@ static int mlx5e_alloc_icosq(struct mlx5e_channel *c,
 	sq->channel   = c;
 	sq->uar_map   = mdev->mlx5e_res.bfreg.map;
 
-	param->wq.db_numa_node = mlx5e_get_node(c->priv, c->ix);
+	param->wq.db_numa_node = cpu_to_node(c->cpu);
 	err = mlx5_wq_cyc_create(mdev, &param->wq, sqc_wq, &sq->wq, &sq->wq_ctrl);
 	if (err)
 		return err;
 	sq->wq.db = &sq->wq.db[MLX5_SND_DBR];
 
-	err = mlx5e_alloc_icosq_db(sq, mlx5e_get_node(c->priv, c->ix));
+	err = mlx5e_alloc_icosq_db(sq, cpu_to_node(c->cpu));
 	if (err)
 		goto err_sq_wq_destroy;
 
@@ -1126,13 +1118,13 @@ static int mlx5e_alloc_txqsq(struct mlx5e_channel *c,
 	if (MLX5_IPSEC_DEV(c->priv->mdev))
 		set_bit(MLX5E_SQ_STATE_IPSEC, &sq->state);
 
-	param->wq.db_numa_node = mlx5e_get_node(c->priv, c->ix);
+	param->wq.db_numa_node = cpu_to_node(c->cpu);
 	err = mlx5_wq_cyc_create(mdev, &param->wq, sqc_wq, &sq->wq, &sq->wq_ctrl);
 	if (err)
 		return err;
 	sq->wq.db    = &sq->wq.db[MLX5_SND_DBR];
 
-	err = mlx5e_alloc_txqsq_db(sq, mlx5e_get_node(c->priv, c->ix));
+	err = mlx5e_alloc_txqsq_db(sq, cpu_to_node(c->cpu));
 	if (err)
 		goto err_sq_wq_destroy;
 
@@ -1504,8 +1496,8 @@ static int mlx5e_alloc_cq(struct mlx5e_channel *c,
 	struct mlx5_core_dev *mdev = c->priv->mdev;
 	int err;
 
-	param->wq.buf_numa_node = mlx5e_get_node(c->priv, c->ix);
-	param->wq.db_numa_node  = mlx5e_get_node(c->priv, c->ix);
+	param->wq.buf_numa_node = cpu_to_node(c->cpu);
+	param->wq.db_numa_node  = cpu_to_node(c->cpu);
 	param->eq_ix   = c->ix;
 
 	err = mlx5e_alloc_cq_common(mdev, param, cq);
@@ -1604,6 +1596,11 @@ static void mlx5e_close_cq(struct mlx5e_cq *cq)
 	mlx5e_free_cq(cq);
 }
 
+static int mlx5e_get_cpu(struct mlx5e_priv *priv, int ix)
+{
+	return cpumask_first(priv->mdev->priv.irq_info[ix].mask);
+}
+
 static int mlx5e_open_tx_cqs(struct mlx5e_channel *c,
 			     struct mlx5e_params *params,
 			     struct mlx5e_channel_param *cparam)
@@ -1752,12 +1749,13 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix,
 {
 	struct mlx5e_cq_moder icocq_moder = {0, 0};
 	struct net_device *netdev = priv->netdev;
+	int cpu = mlx5e_get_cpu(priv, ix);
 	struct mlx5e_channel *c;
 	unsigned int irq;
 	int err;
 	int eqn;
 
-	c = kzalloc_node(sizeof(*c), GFP_KERNEL, mlx5e_get_node(priv, ix));
+	c = kzalloc_node(sizeof(*c), GFP_KERNEL, cpu_to_node(cpu));
 	if (!c)
 		return -ENOMEM;
 
@@ -1765,6 +1763,7 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix,
 	c->mdev     = priv->mdev;
 	c->tstamp   = &priv->tstamp;
 	c->ix       = ix;
+	c->cpu      = cpu;
 	c->pdev     = &priv->mdev->pdev->dev;
 	c->netdev   = priv->netdev;
 	c->mkey_be  = cpu_to_be32(priv->mdev->mlx5e_res.mkey.key);
@@ -1853,8 +1852,7 @@ static void mlx5e_activate_channel(struct mlx5e_channel *c)
 	for (tc = 0; tc < c->num_tc; tc++)
 		mlx5e_activate_txqsq(&c->sq[tc]);
 	mlx5e_activate_rq(&c->rq);
-	netif_set_xps_queue(c->netdev,
-		mlx5_get_vector_affinity(c->priv->mdev, c->ix), c->ix);
+	netif_set_xps_queue(c->netdev, get_cpu_mask(c->cpu), c->ix);
 }
 
 static void mlx5e_deactivate_channel(struct mlx5e_channel *c)
@@ -3679,6 +3677,7 @@ static netdev_features_t mlx5e_tunnel_features_check(struct mlx5e_priv *priv,
 						     struct sk_buff *skb,
 						     netdev_features_t features)
 {
+	unsigned int offset = 0;
 	struct udphdr *udph;
 	u8 proto;
 	u16 port;
@@ -3688,7 +3687,7 @@ static netdev_features_t mlx5e_tunnel_features_check(struct mlx5e_priv *priv,
 		proto = ip_hdr(skb)->protocol;
 		break;
 	case htons(ETH_P_IPV6):
-		proto = ipv6_hdr(skb)->nexthdr;
+		proto = ipv6_find_hdr(skb, &offset, -1, NULL, NULL);
 		break;
 	default:
 		goto out;

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

@@ -466,7 +466,7 @@ static irqreturn_t mlx5_eq_int(int irq, void *eq_ptr)
 			break;
 		case MLX5_EVENT_TYPE_CQ_ERROR:
 			cqn = be32_to_cpu(eqe->data.cq_err.cqn) & 0xffffff;
-			mlx5_core_warn(dev, "CQ error on CQN 0x%x, syndrom 0x%x\n",
+			mlx5_core_warn(dev, "CQ error on CQN 0x%x, syndrome 0x%x\n",
 				       cqn, eqe->data.cq_err.syndrome);
 			mlx5_cq_event(dev, cqn, eqe->type);
 			break;
@@ -775,7 +775,7 @@ int mlx5_start_eqs(struct mlx5_core_dev *dev)
 	return err;
 }
 
-int mlx5_stop_eqs(struct mlx5_core_dev *dev)
+void mlx5_stop_eqs(struct mlx5_core_dev *dev)
 {
 	struct mlx5_eq_table *table = &dev->priv.eq_table;
 	int err;
@@ -784,22 +784,26 @@ int mlx5_stop_eqs(struct mlx5_core_dev *dev)
 	if (MLX5_CAP_GEN(dev, pg)) {
 		err = mlx5_destroy_unmap_eq(dev, &table->pfault_eq);
 		if (err)
-			return err;
+			mlx5_core_err(dev, "failed to destroy page fault eq, err(%d)\n",
+				      err);
 	}
 #endif
 
 	err = mlx5_destroy_unmap_eq(dev, &table->pages_eq);
 	if (err)
-		return err;
+		mlx5_core_err(dev, "failed to destroy pages eq, err(%d)\n",
+			      err);
 
-	mlx5_destroy_unmap_eq(dev, &table->async_eq);
+	err = mlx5_destroy_unmap_eq(dev, &table->async_eq);
+	if (err)
+		mlx5_core_err(dev, "failed to destroy async eq, err(%d)\n",
+			      err);
 	mlx5_cmd_use_polling(dev);
 
 	err = mlx5_destroy_unmap_eq(dev, &table->cmd_eq);
 	if (err)
-		mlx5_cmd_use_events(dev);
-
-	return err;
+		mlx5_core_err(dev, "failed to destroy command eq, err(%d)\n",
+			      err);
 }
 
 int mlx5_core_eq_query(struct mlx5_core_dev *dev, struct mlx5_eq *eq,

drivers/net/ethernet/mellanox/mlx5/core/fpga/sdk.c

@@ -66,6 +66,9 @@ static int mlx5_fpga_mem_read_i2c(struct mlx5_fpga_device *fdev, size_t size,
 	u8 actual_size;
 	int err;
 
+	if (!size)
+		return -EINVAL;
+
 	if (!fdev->mdev)
 		return -ENOTCONN;
 
@@ -95,6 +98,9 @@ static int mlx5_fpga_mem_write_i2c(struct mlx5_fpga_device *fdev, size_t size,
 	u8 actual_size;
 	int err;
 
+	if (!size)
+		return -EINVAL;
+
 	if (!fdev->mdev)
 		return -ENOTCONN;
 

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

@@ -174,6 +174,8 @@ static void del_hw_fte(struct fs_node *node);
 static void del_sw_flow_table(struct fs_node *node);
 static void del_sw_flow_group(struct fs_node *node);
 static void del_sw_fte(struct fs_node *node);
+static void del_sw_prio(struct fs_node *node);
+static void del_sw_ns(struct fs_node *node);
 /* Delete rule (destination) is special case that 
  * requires to lock the FTE for all the deletion process.
  */
@@ -408,6 +410,16 @@ static inline struct mlx5_core_dev *get_dev(struct fs_node *node)
 	return NULL;
 }
 
+static void del_sw_ns(struct fs_node *node)
+{
+	kfree(node);
+}
+
+static void del_sw_prio(struct fs_node *node)
+{
+	kfree(node);
+}
+
 static void del_hw_flow_table(struct fs_node *node)
 {
 	struct mlx5_flow_table *ft;
@@ -2064,7 +2076,7 @@ static struct fs_prio *fs_create_prio(struct mlx5_flow_namespace *ns,
 		return ERR_PTR(-ENOMEM);
 
 	fs_prio->node.type = FS_TYPE_PRIO;
-	tree_init_node(&fs_prio->node, NULL, NULL);
+	tree_init_node(&fs_prio->node, NULL, del_sw_prio);
 	tree_add_node(&fs_prio->node, &ns->node);
 	fs_prio->num_levels = num_levels;
 	fs_prio->prio = prio;
@@ -2090,7 +2102,7 @@ static struct mlx5_flow_namespace *fs_create_namespace(struct fs_prio *prio)
 		return ERR_PTR(-ENOMEM);
 
 	fs_init_namespace(ns);
-	tree_init_node(&ns->node, NULL, NULL);
+	tree_init_node(&ns->node, NULL, del_sw_ns);
 	tree_add_node(&ns->node, &prio->node);
 	list_add_tail(&ns->node.list, &prio->node.children);
 

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

@@ -241,7 +241,7 @@ static void print_health_info(struct mlx5_core_dev *dev)
 	u32 fw;
 	int i;
 
-	/* If the syndrom is 0, the device is OK and no need to print buffer */
+	/* If the syndrome is 0, the device is OK and no need to print buffer */
 	if (!ioread8(&h->synd))
 		return;
 

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

@@ -57,7 +57,7 @@ static void mlx5i_build_nic_params(struct mlx5_core_dev *mdev,
 				   struct mlx5e_params *params)
 {
 	/* Override RQ params as IPoIB supports only LINKED LIST RQ for now */
-	mlx5e_set_rq_type_params(mdev, params, MLX5_WQ_TYPE_LINKED_LIST);
+	mlx5e_init_rq_type_params(mdev, params, MLX5_WQ_TYPE_LINKED_LIST);
 
 	/* RQ size in ipoib by default is 512 */
 	params->log_rq_size = is_kdump_kernel() ?

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

@@ -317,9 +317,6 @@ static int mlx5_alloc_irq_vectors(struct mlx5_core_dev *dev)
 {
 	struct mlx5_priv *priv = &dev->priv;
 	struct mlx5_eq_table *table = &priv->eq_table;
-	struct irq_affinity irqdesc = {
-		.pre_vectors = MLX5_EQ_VEC_COMP_BASE,
-	};
 	int num_eqs = 1 << MLX5_CAP_GEN(dev, log_max_eq);
 	int nvec;
 
@@ -333,10 +330,9 @@ static int mlx5_alloc_irq_vectors(struct mlx5_core_dev *dev)
 	if (!priv->irq_info)
 		goto err_free_msix;
 
-	nvec = pci_alloc_irq_vectors_affinity(dev->pdev,
+	nvec = pci_alloc_irq_vectors(dev->pdev,
 			MLX5_EQ_VEC_COMP_BASE + 1, nvec,
-			PCI_IRQ_MSIX | PCI_IRQ_AFFINITY,
-			&irqdesc);
+			PCI_IRQ_MSIX);
 	if (nvec < 0)
 		return nvec;
 
@@ -622,6 +618,63 @@ u64 mlx5_read_internal_timer(struct mlx5_core_dev *dev)
 	return (u64)timer_l | (u64)timer_h1 << 32;
 }
 
+static int mlx5_irq_set_affinity_hint(struct mlx5_core_dev *mdev, int i)
+{
+	struct mlx5_priv *priv  = &mdev->priv;
+	int irq = pci_irq_vector(mdev->pdev, MLX5_EQ_VEC_COMP_BASE + i);
+
+	if (!zalloc_cpumask_var(&priv->irq_info[i].mask, GFP_KERNEL)) {
+		mlx5_core_warn(mdev, "zalloc_cpumask_var failed");
+		return -ENOMEM;
+	}
+
+	cpumask_set_cpu(cpumask_local_spread(i, priv->numa_node),
+			priv->irq_info[i].mask);
+
+	if (IS_ENABLED(CONFIG_SMP) &&
+	    irq_set_affinity_hint(irq, priv->irq_info[i].mask))
+		mlx5_core_warn(mdev, "irq_set_affinity_hint failed, irq 0x%.4x", irq);
+
+	return 0;
+}
+
+static void mlx5_irq_clear_affinity_hint(struct mlx5_core_dev *mdev, int i)
+{
+	struct mlx5_priv *priv  = &mdev->priv;
+	int irq = pci_irq_vector(mdev->pdev, MLX5_EQ_VEC_COMP_BASE + i);
+
+	irq_set_affinity_hint(irq, NULL);
+	free_cpumask_var(priv->irq_info[i].mask);
+}
+
+static int mlx5_irq_set_affinity_hints(struct mlx5_core_dev *mdev)
+{
+	int err;
+	int i;
+
+	for (i = 0; i < mdev->priv.eq_table.num_comp_vectors; i++) {
+		err = mlx5_irq_set_affinity_hint(mdev, i);
+		if (err)
+			goto err_out;
+	}
+
+	return 0;
+
+err_out:
+	for (i--; i >= 0; i--)
+		mlx5_irq_clear_affinity_hint(mdev, i);
+
+	return err;
+}
+
+static void mlx5_irq_clear_affinity_hints(struct mlx5_core_dev *mdev)
+{
+	int i;
+
+	for (i = 0; i < mdev->priv.eq_table.num_comp_vectors; i++)
+		mlx5_irq_clear_affinity_hint(mdev, i);
+}
+
 int mlx5_vector2eqn(struct mlx5_core_dev *dev, int vector, int *eqn,
 		    unsigned int *irqn)
 {
@@ -1097,6 +1150,12 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv,
 		goto err_stop_eqs;
 	}
 
+	err = mlx5_irq_set_affinity_hints(dev);
+	if (err) {
+		dev_err(&pdev->dev, "Failed to alloc affinity hint cpumask\n");
+		goto err_affinity_hints;
+	}
+
 	err = mlx5_init_fs(dev);
 	if (err) {
 		dev_err(&pdev->dev, "Failed to init flow steering\n");
@@ -1154,6 +1213,9 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv,
 	mlx5_cleanup_fs(dev);
 
 err_fs:
+	mlx5_irq_clear_affinity_hints(dev);
+
+err_affinity_hints:
 	free_comp_eqs(dev);
 
 err_stop_eqs:
@@ -1222,6 +1284,7 @@ static int mlx5_unload_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv,
 
 	mlx5_sriov_detach(dev);
 	mlx5_cleanup_fs(dev);
+	mlx5_irq_clear_affinity_hints(dev);
 	free_comp_eqs(dev);
 	mlx5_stop_eqs(dev);
 	mlx5_put_uars_page(dev, priv->uar);

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

@@ -213,8 +213,8 @@ int mlx5_core_create_qp(struct mlx5_core_dev *dev,
 err_cmd:
 	memset(din, 0, sizeof(din));
 	memset(dout, 0, sizeof(dout));
-	MLX5_SET(destroy_qp_in, in, opcode, MLX5_CMD_OP_DESTROY_QP);
-	MLX5_SET(destroy_qp_in, in, qpn, qp->qpn);
+	MLX5_SET(destroy_qp_in, din, opcode, MLX5_CMD_OP_DESTROY_QP);
+	MLX5_SET(destroy_qp_in, din, qpn, qp->qpn);
 	mlx5_cmd_exec(dev, din, sizeof(din), dout, sizeof(dout));
 	return err;
 }

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

@@ -125,16 +125,16 @@ static struct mlx5_rl_entry *find_rl_entry(struct mlx5_rl_table *table,
 	return ret_entry;
 }
 
-static int mlx5_set_rate_limit_cmd(struct mlx5_core_dev *dev,
+static int mlx5_set_pp_rate_limit_cmd(struct mlx5_core_dev *dev,
 				   u32 rate, u16 index)
 {
-	u32 in[MLX5_ST_SZ_DW(set_rate_limit_in)]   = {0};
-	u32 out[MLX5_ST_SZ_DW(set_rate_limit_out)] = {0};
+	u32 in[MLX5_ST_SZ_DW(set_pp_rate_limit_in)]   = {0};
+	u32 out[MLX5_ST_SZ_DW(set_pp_rate_limit_out)] = {0};
 
-	MLX5_SET(set_rate_limit_in, in, opcode,
-		 MLX5_CMD_OP_SET_RATE_LIMIT);
-	MLX5_SET(set_rate_limit_in, in, rate_limit_index, index);
-	MLX5_SET(set_rate_limit_in, in, rate_limit, rate);
+	MLX5_SET(set_pp_rate_limit_in, in, opcode,
+		 MLX5_CMD_OP_SET_PP_RATE_LIMIT);
+	MLX5_SET(set_pp_rate_limit_in, in, rate_limit_index, index);
+	MLX5_SET(set_pp_rate_limit_in, in, rate_limit, rate);
 	return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
 }
 
@@ -173,7 +173,7 @@ int mlx5_rl_add_rate(struct mlx5_core_dev *dev, u32 rate, u16 *index)
 		entry->refcount++;
 	} else {
 		/* new rate limit */
-		err = mlx5_set_rate_limit_cmd(dev, rate, entry->index);
+		err = mlx5_set_pp_rate_limit_cmd(dev, rate, entry->index);
 		if (err) {
 			mlx5_core_err(dev, "Failed configuring rate: %u (%d)\n",
 				      rate, err);
@@ -209,7 +209,7 @@ void mlx5_rl_remove_rate(struct mlx5_core_dev *dev, u32 rate)
 	entry->refcount--;
 	if (!entry->refcount) {
 		/* need to remove rate */
-		mlx5_set_rate_limit_cmd(dev, 0, entry->index);
+		mlx5_set_pp_rate_limit_cmd(dev, 0, entry->index);
 		entry->rate = 0;
 	}
 
@@ -262,7 +262,7 @@ void mlx5_cleanup_rl_table(struct mlx5_core_dev *dev)
 	/* Clear all configured rates */
 	for (i = 0; i < table->max_size; i++)
 		if (table->rl_entry[i].rate)
-			mlx5_set_rate_limit_cmd(dev, 0,
+			mlx5_set_pp_rate_limit_cmd(dev, 0,
 						   table->rl_entry[i].index);
 
 	kfree(dev->priv.rl_table.rl_entry);

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

@@ -71,9 +71,9 @@ struct mlx5e_vxlan *mlx5e_vxlan_lookup_port(struct mlx5e_priv *priv, u16 port)
 	struct mlx5e_vxlan_db *vxlan_db = &priv->vxlan;
 	struct mlx5e_vxlan *vxlan;
 
-	spin_lock(&vxlan_db->lock);
+	spin_lock_bh(&vxlan_db->lock);
 	vxlan = radix_tree_lookup(&vxlan_db->tree, port);
-	spin_unlock(&vxlan_db->lock);
+	spin_unlock_bh(&vxlan_db->lock);
 
 	return vxlan;
 }
@@ -88,8 +88,12 @@ static void mlx5e_vxlan_add_port(struct work_struct *work)
 	struct mlx5e_vxlan *vxlan;
 	int err;
 
-	if (mlx5e_vxlan_lookup_port(priv, port))
+	mutex_lock(&priv->state_lock);
+	vxlan = mlx5e_vxlan_lookup_port(priv, port);
+	if (vxlan) {
+		atomic_inc(&vxlan->refcount);
 		goto free_work;
+	}
 
 	if (mlx5e_vxlan_core_add_port_cmd(priv->mdev, port))
 		goto free_work;
@@ -99,10 +103,11 @@ static void mlx5e_vxlan_add_port(struct work_struct *work)
 		goto err_delete_port;
 
 	vxlan->udp_port = port;
+	atomic_set(&vxlan->refcount, 1);
 
-	spin_lock_irq(&vxlan_db->lock);
+	spin_lock_bh(&vxlan_db->lock);
 	err = radix_tree_insert(&vxlan_db->tree, vxlan->udp_port, vxlan);
-	spin_unlock_irq(&vxlan_db->lock);
+	spin_unlock_bh(&vxlan_db->lock);
 	if (err)
 		goto err_free;
 
@@ -113,35 +118,39 @@ static void mlx5e_vxlan_add_port(struct work_struct *work)
 err_delete_port:
 	mlx5e_vxlan_core_del_port_cmd(priv->mdev, port);
 free_work:
+	mutex_unlock(&priv->state_lock);
 	kfree(vxlan_work);
 }
 
-static void __mlx5e_vxlan_core_del_port(struct mlx5e_priv *priv, u16 port)
-{
-	struct mlx5e_vxlan_db *vxlan_db = &priv->vxlan;
-	struct mlx5e_vxlan *vxlan;
-
-	spin_lock_irq(&vxlan_db->lock);
-	vxlan = radix_tree_delete(&vxlan_db->tree, port);
-	spin_unlock_irq(&vxlan_db->lock);
-
-	if (!vxlan)
-		return;
-
-	mlx5e_vxlan_core_del_port_cmd(priv->mdev, vxlan->udp_port);
-
-	kfree(vxlan);
-}
-
 static void mlx5e_vxlan_del_port(struct work_struct *work)
 {
 	struct mlx5e_vxlan_work *vxlan_work =
 		container_of(work, struct mlx5e_vxlan_work, work);
 	struct mlx5e_priv *priv         = vxlan_work->priv;
+	struct mlx5e_vxlan_db *vxlan_db = &priv->vxlan;
 	u16 port = vxlan_work->port;
+	struct mlx5e_vxlan *vxlan;
+	bool remove = false;
+
+	mutex_lock(&priv->state_lock);
+	spin_lock_bh(&vxlan_db->lock);
+	vxlan = radix_tree_lookup(&vxlan_db->tree, port);
+	if (!vxlan)
+		goto out_unlock;
+
+	if (atomic_dec_and_test(&vxlan->refcount)) {
+		radix_tree_delete(&vxlan_db->tree, port);
+		remove = true;
+	}
 
-	__mlx5e_vxlan_core_del_port(priv, port);
+out_unlock:
+	spin_unlock_bh(&vxlan_db->lock);
 
+	if (remove) {
+		mlx5e_vxlan_core_del_port_cmd(priv->mdev, port);
+		kfree(vxlan);
+	}
+	mutex_unlock(&priv->state_lock);
 	kfree(vxlan_work);
 }
 
@@ -171,12 +180,11 @@ void mlx5e_vxlan_cleanup(struct mlx5e_priv *priv)
 	struct mlx5e_vxlan *vxlan;
 	unsigned int port = 0;
 
-	spin_lock_irq(&vxlan_db->lock);
+	/* Lockless since we are the only radix-tree consumers, wq is disabled */
 	while (radix_tree_gang_lookup(&vxlan_db->tree, (void **)&vxlan, port, 1)) {
 		port = vxlan->udp_port;
-		spin_unlock_irq(&vxlan_db->lock);
-		__mlx5e_vxlan_core_del_port(priv, (u16)port);
-		spin_lock_irq(&vxlan_db->lock);
+		radix_tree_delete(&vxlan_db->tree, port);
+		mlx5e_vxlan_core_del_port_cmd(priv->mdev, port);
+		kfree(vxlan);
 	}
-	spin_unlock_irq(&vxlan_db->lock);
 }

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

@@ -36,6 +36,7 @@
 #include "en.h"
 
 struct mlx5e_vxlan {
+	atomic_t refcount;
 	u16 udp_port;
 };
 

include/linux/mlx5/driver.h

@@ -556,6 +556,7 @@ struct mlx5_core_sriov {
 };
 
 struct mlx5_irq_info {
+	cpumask_var_t mask;
 	char name[MLX5_MAX_IRQ_NAME];
 };
 
@@ -1048,7 +1049,7 @@ int mlx5_create_map_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq, u8 vecidx,
 		       enum mlx5_eq_type type);
 int mlx5_destroy_unmap_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq);
 int mlx5_start_eqs(struct mlx5_core_dev *dev);
-int mlx5_stop_eqs(struct mlx5_core_dev *dev);
+void mlx5_stop_eqs(struct mlx5_core_dev *dev);
 int mlx5_vector2eqn(struct mlx5_core_dev *dev, int vector, int *eqn,
 		    unsigned int *irqn);
 int mlx5_core_attach_mcg(struct mlx5_core_dev *dev, union ib_gid *mgid, u32 qpn);

include/linux/mlx5/mlx5_ifc.h

@@ -147,7 +147,7 @@ enum {
 	MLX5_CMD_OP_ALLOC_Q_COUNTER               = 0x771,
 	MLX5_CMD_OP_DEALLOC_Q_COUNTER             = 0x772,
 	MLX5_CMD_OP_QUERY_Q_COUNTER               = 0x773,
-	MLX5_CMD_OP_SET_RATE_LIMIT                = 0x780,
+	MLX5_CMD_OP_SET_PP_RATE_LIMIT             = 0x780,
 	MLX5_CMD_OP_QUERY_RATE_LIMIT              = 0x781,
 	MLX5_CMD_OP_CREATE_SCHEDULING_ELEMENT      = 0x782,
 	MLX5_CMD_OP_DESTROY_SCHEDULING_ELEMENT     = 0x783,
@@ -7239,7 +7239,7 @@ struct mlx5_ifc_add_vxlan_udp_dport_in_bits {
 	u8         vxlan_udp_port[0x10];
 };
 
-struct mlx5_ifc_set_rate_limit_out_bits {
+struct mlx5_ifc_set_pp_rate_limit_out_bits {
 	u8         status[0x8];
 	u8         reserved_at_8[0x18];
 
@@ -7248,7 +7248,7 @@ struct mlx5_ifc_set_rate_limit_out_bits {
 	u8         reserved_at_40[0x40];
 };
 
-struct mlx5_ifc_set_rate_limit_in_bits {
+struct mlx5_ifc_set_pp_rate_limit_in_bits {
 	u8         opcode[0x10];
 	u8         reserved_at_10[0x10];
 
@@ -7261,6 +7261,8 @@ struct mlx5_ifc_set_rate_limit_in_bits {
 	u8         reserved_at_60[0x20];
 
 	u8         rate_limit[0x20];
+
+	u8         reserved_at_a0[0x160];
 };
 
 struct mlx5_ifc_access_register_out_bits {