Merge tag 'mlx5-updates-2017-11-04' of git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux

Saeed Mahameed says:

====================
mlx5-updates-2017-11-04

This series includes:

From Huy: dscp to priority mapping for Ethernet packet.

===================================================
First six patches enable differentiated services code point (dscp) to
priority mapping for Ethernet packet. Once this feature is
enabled, the packet is routed to the corresponding priority based on its
dscp. User can combine this feature with priority flow control (pfc)
feature to have priority flow control based on the dscp.

Firmware interface:
Mellanox firmware provides two control knobs for this feature:
  QPTS register allow changing the trust state between dscp and
  pcp mode. The default is pcp mode. Once in dscp mode, firmware will
  route the packet based on its dscp value if the dscp field exists.

  QPDPM register allow mapping a specific dscp (0 to 63) to a
  specific priority (0 to 7). By default, all the dscps are mapped to
  priority zero.

Software interface:
This feature is controlled via application priority TLV. IEEE
specification P802.1Qcd/D2.1 defines priority selector id 5 for
application priority TLV. This APP TLV selector defines DSCP to priority
map. This APP TLV can be sent by the switch or can be set locally using
software such as lldptool. In mlx5 drivers, we add the support for net
dcb's getapp and setapp call back. Mlx5 driver only handles the selector
id 5 application entry (dscp application priority application entry).
If user sends multiple dscp to priority APP TLV entries on the same
dscp, the last sent one will take effect. All the previous sent will be
deleted.

The firmware trust state (in QPTS register) is changed based on the
number of dscp to priority application entries. When the first dscp to
priority application entry is added by the user, the trust state is
changed to dscp. When the last dscp to priority application entry is
deleted by the user, the trust state is changed to pcp.

When the port is in DSCP trust state, the transmit queue is selected
based on the dscp of the skb.

When the port is in DSCP trust state and vport inline mode is not NONE,
firmware requires mlx5 driver to copy the IP header to the
wqe ethernet segment inline header if the skb has it.
This is done by changing the transmit queue sq's min inline mode to L3.
Note that the min inline mode of sqs that belong to other features
such as xdpsq, icosq are not modified.
===================================================

Plus to the dscp series, some small misc changes are include as well:

From Inbar, Ethtool msglvl support and some debug prints in DCBNL logic
From Or Gerlitz, Enlarge the NIC TC offload table size
From Rabie, Initialize destination_flow struct to 0
From Feras, Add inner TTC table to IPoIB flow steering
From Tal, Enable CQE based moderation on TX CQ
====================

Signed-off-by: David S. Miller <[email protected]>

Author: davem330

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

@@ -57,6 +57,7 @@
 #define MLX5E_HW2SW_MTU(priv, hwmtu) ((hwmtu) - ((priv)->hard_mtu))
 #define MLX5E_SW2HW_MTU(priv, swmtu) ((swmtu) + ((priv)->hard_mtu))
 
+#define MLX5E_MAX_DSCP          64
 #define MLX5E_MAX_NUM_TC	8
 
 #define MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE                0x6
@@ -105,6 +106,7 @@
 #define MLX5E_PARAMS_DEFAULT_RX_CQ_MODERATION_USEC_FROM_CQE 0x3
 #define MLX5E_PARAMS_DEFAULT_RX_CQ_MODERATION_PKTS      0x20
 #define MLX5E_PARAMS_DEFAULT_TX_CQ_MODERATION_USEC      0x10
+#define MLX5E_PARAMS_DEFAULT_TX_CQ_MODERATION_USEC_FROM_CQE 0x10
 #define MLX5E_PARAMS_DEFAULT_TX_CQ_MODERATION_PKTS      0x20
 #define MLX5E_PARAMS_DEFAULT_MIN_RX_WQES                0x80
 #define MLX5E_PARAMS_DEFAULT_MIN_RX_WQES_MPW            0x2
@@ -126,6 +128,16 @@
 
 #define MLX5E_NUM_MAIN_GROUPS 9
 
+#define MLX5E_MSG_LEVEL			NETIF_MSG_LINK
+
+#define mlx5e_dbg(mlevel, priv, format, ...)                    \
+do {                                                            \
+	if (NETIF_MSG_##mlevel & (priv)->msglevel)              \
+		netdev_warn(priv->netdev, format,               \
+			    ##__VA_ARGS__);                     \
+} while (0)
+
+
 static inline u16 mlx5_min_rx_wqes(int wq_type, u32 wq_size)
 {
 	switch (wq_type) {
@@ -187,12 +199,14 @@ extern const char mlx5e_self_tests[][ETH_GSTRING_LEN];
 
 static const char mlx5e_priv_flags[][ETH_GSTRING_LEN] = {
 	"rx_cqe_moder",
+	"tx_cqe_moder",
 	"rx_cqe_compress",
 };
 
 enum mlx5e_priv_flag {
 	MLX5E_PFLAG_RX_CQE_BASED_MODER = (1 << 0),
-	MLX5E_PFLAG_RX_CQE_COMPRESS = (1 << 1),
+	MLX5E_PFLAG_TX_CQE_BASED_MODER = (1 << 1),
+	MLX5E_PFLAG_RX_CQE_COMPRESS = (1 << 2),
 };
 
 #define MLX5E_SET_PFLAG(params, pflag, enable)			\
@@ -212,6 +226,7 @@ enum mlx5e_priv_flag {
 struct mlx5e_cq_moder {
 	u16 usec;
 	u16 pkts;
+	u8 cq_period_mode;
 };
 
 struct mlx5e_params {
@@ -223,7 +238,6 @@ struct mlx5e_params {
 	u8  log_rq_size;
 	u16 num_channels;
 	u8  num_tc;
-	u8  rx_cq_period_mode;
 	bool rx_cqe_compress_def;
 	struct mlx5e_cq_moder rx_cq_moderation;
 	struct mlx5e_cq_moder tx_cq_moderation;
@@ -260,11 +274,17 @@ enum {
 struct mlx5e_dcbx {
 	enum mlx5_dcbx_oper_mode   mode;
 	struct mlx5e_cee_config    cee_cfg; /* pending configuration */
+	u8                         dscp_app_cnt;
 
 	/* The only setting that cannot be read from FW */
 	u8                         tc_tsa[IEEE_8021QAZ_MAX_TCS];
 	u8                         cap;
 };
+
+struct mlx5e_dcbx_dp {
+	u8                         dscp2prio[MLX5E_MAX_DSCP];
+	u8                         trust_state;
+};
 #endif
 
 enum {
@@ -742,8 +762,12 @@ struct mlx5e_priv {
 	/* priv data path fields - start */
 	struct mlx5e_txqsq *txq2sq[MLX5E_MAX_NUM_CHANNELS * MLX5E_MAX_NUM_TC];
 	int channel_tc2txq[MLX5E_MAX_NUM_CHANNELS][MLX5E_MAX_NUM_TC];
+#ifdef CONFIG_MLX5_CORE_EN_DCB
+	struct mlx5e_dcbx_dp       dcbx_dp;
+#endif
 	/* priv data path fields - end */
 
+	u32                        msglevel;
 	unsigned long              state;
 	struct mutex               state_lock; /* Protects Interface state */
 	struct mlx5e_rq            drop_rq;
@@ -800,6 +824,8 @@ struct mlx5e_profile {
 		mlx5e_fp_handle_rx_cqe handle_rx_cqe;
 		mlx5e_fp_handle_rx_cqe handle_rx_cqe_mpwqe;
 	} rx_handlers;
+	void	(*netdev_registered_init)(struct mlx5e_priv *priv);
+	void    (*netdev_registered_remove)(struct mlx5e_priv *priv);
 	int	max_tc;
 };
 
@@ -903,6 +929,8 @@ void mlx5e_build_default_indir_rqt(u32 *indirection_rqt, int len,
 				   int num_channels);
 int mlx5e_get_max_linkspeed(struct mlx5_core_dev *mdev, u32 *speed);
 
+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,
@@ -968,6 +996,8 @@ extern const struct ethtool_ops mlx5e_ethtool_ops;
 extern const struct dcbnl_rtnl_ops mlx5e_dcbnl_ops;
 int mlx5e_dcbnl_ieee_setets_core(struct mlx5e_priv *priv, struct ieee_ets *ets);
 void mlx5e_dcbnl_initialize(struct mlx5e_priv *priv);
+void mlx5e_dcbnl_init_app(struct mlx5e_priv *priv);
+void mlx5e_dcbnl_delete_app(struct mlx5e_priv *priv);
 #endif
 
 #ifndef CONFIG_RFS_ACCEL
@@ -1020,6 +1050,9 @@ void mlx5e_destroy_rqt(struct mlx5e_priv *priv, struct mlx5e_rqt *rqt);
 int mlx5e_create_ttc_table(struct mlx5e_priv *priv);
 void mlx5e_destroy_ttc_table(struct mlx5e_priv *priv);
 
+int mlx5e_create_inner_ttc_table(struct mlx5e_priv *priv);
+void mlx5e_destroy_inner_ttc_table(struct mlx5e_priv *priv);
+
 int mlx5e_create_tis(struct mlx5_core_dev *mdev, int tc,
 		     u32 underlay_qpn, u32 *tisn);
 void mlx5e_destroy_tis(struct mlx5_core_dev *mdev, u32 tisn);
@@ -1069,5 +1102,5 @@ void mlx5e_destroy_netdev(struct mlx5e_priv *priv);
 void mlx5e_build_nic_params(struct mlx5_core_dev *mdev,
 			    struct mlx5e_params *params,
 			    u16 max_channels);
-
+u8 mlx5e_params_calculate_tx_min_inline(struct mlx5_core_dev *mdev);
 #endif /* __MLX5_EN_H__ */

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

@@ -92,7 +92,7 @@ static enum mlx5e_traffic_types arfs_get_tt(enum arfs_type type)
 
 static int arfs_disable(struct mlx5e_priv *priv)
 {
-	struct mlx5_flow_destination dest;
+	struct mlx5_flow_destination dest = {};
 	struct mlx5e_tir *tir = priv->indir_tir;
 	int err = 0;
 	int tt;
@@ -126,7 +126,7 @@ int mlx5e_arfs_disable(struct mlx5e_priv *priv)
 
 int mlx5e_arfs_enable(struct mlx5e_priv *priv)
 {
-	struct mlx5_flow_destination dest;
+	struct mlx5_flow_destination dest = {};
 	int err = 0;
 	int tt;
 	int i;
@@ -175,7 +175,7 @@ static int arfs_add_default_rule(struct mlx5e_priv *priv,
 {
 	struct arfs_table *arfs_t = &priv->fs.arfs.arfs_tables[type];
 	struct mlx5e_tir *tir = priv->indir_tir;
-	struct mlx5_flow_destination dest;
+	struct mlx5_flow_destination dest = {};
 	MLX5_DECLARE_FLOW_ACT(flow_act);
 	struct mlx5_flow_spec *spec;
 	enum mlx5e_traffic_types tt;
@@ -466,7 +466,7 @@ static struct mlx5_flow_handle *arfs_add_rule(struct mlx5e_priv *priv,
 	struct mlx5e_arfs_tables *arfs = &priv->fs.arfs;
 	struct arfs_tuple *tuple = &arfs_rule->tuple;
 	struct mlx5_flow_handle *rule = NULL;
-	struct mlx5_flow_destination dest;
+	struct mlx5_flow_destination dest = {};
 	MLX5_DECLARE_FLOW_ACT(flow_act);
 	struct arfs_table *arfs_table;
 	struct mlx5_flow_spec *spec;
@@ -557,7 +557,7 @@ static struct mlx5_flow_handle *arfs_add_rule(struct mlx5e_priv *priv,
 static void arfs_modify_rule_rq(struct mlx5e_priv *priv,
 				struct mlx5_flow_handle *rule, u16 rxq)
 {
-	struct mlx5_flow_destination dst;
+	struct mlx5_flow_destination dst = {};
 	int err = 0;
 
 	dst.type = MLX5_FLOW_DESTINATION_TYPE_TIR;

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

@@ -171,3 +171,15 @@ 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;
+}