Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next

Pull networking updates from David Miller:
 "Another merge window, another set of networking changes.  I've heard
  rumblings that the lightweight tunnels infrastructure has been voted
  networking change of the year.  But what do I know?

   1) Add conntrack support to openvswitch, from Joe Stringer.

   2) Initial support for VRF (Virtual Routing and Forwarding), which
      allows the segmentation of routing paths without using multiple
      devices.  There are some semantic kinks to work out still, but
      this is a reasonably strong foundation.  From David Ahern.

   3) Remove spinlock fro act_bpf fast path, from Alexei Starovoitov.

   4) Ignore route nexthops with a link down state in ipv6, just like
      ipv4.  From Andy Gospodarek.

   5) Remove spinlock from fast path of act_gact and act_mirred, from
      Eric Dumazet.

   6) Document the DSA layer, from Florian Fainelli.

   7) Add netconsole support to bcmgenet, systemport, and DSA.  Also
      from Florian Fainelli.

   8) Add Mellanox Switch Driver and core infrastructure, from Jiri
      Pirko.

   9) Add support for "light weight tunnels", which allow for
      encapsulation and decapsulation without bearing the overhead of a
      full blown netdevice.  From Thomas Graf, Jiri Benc, and a cast of
      others.

  10) Add Identifier Locator Addressing support for ipv6, from Tom
      Herbert.

  11) Support fragmented SKBs in iwlwifi, from Johannes Berg.

  12) Allow perf PMUs to be accessed from eBPF programs, from Kaixu Xia.

  13) Add BQL support to 3c59x driver, from Loganaden Velvindron.

  14) Stop using a zero TX queue length to mean that a device shouldn't
      have a qdisc attached, use an explicit flag instead.  From Phil
      Sutter.

  15) Use generic geneve netdevice infrastructure in openvswitch, from
      Pravin B Shelar.

  16) Add infrastructure to avoid re-forwarding a packet in software
      that was already forwarded by a hardware switch.  From Scott
      Feldman.

  17) Allow AF_PACKET fanout function to be implemented in a bpf
      program, from Willem de Bruijn"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1458 commits)
  netfilter: nf_conntrack: make nf_ct_zone_dflt built-in
  netfilter: nf_dup{4, 6}: fix build error when nf_conntrack disabled
  net: fec: clear receive interrupts before processing a packet
  ipv6: fix exthdrs offload registration in out_rt path
  xen-netback: add support for multicast control
  bgmac: Update fixed_phy_register()
  sock, diag: fix panic in sock_diag_put_filterinfo
  flow_dissector: Use 'const' where possible.
  flow_dissector: Fix function argument ordering dependency
  ixgbe: Resolve "initialized field overwritten" warnings
  ixgbe: Remove bimodal SR-IOV disabling
  ixgbe: Add support for reporting 2.5G link speed
  ixgbe: fix bounds checking in ixgbe_setup_tc for 82598
  ixgbe: support for ethtool set_rxfh
  ixgbe: Avoid needless PHY access on copper phys
  ixgbe: cleanup to use cached mask value
  ixgbe: Remove second instance of lan_id variable
  ixgbe: use kzalloc for allocating one thing
  flow: Move __get_hash_from_flowi{4,6} into flow_dissector.c
  ixgbe: Remove unused PCI bus types
  ...

1 files changed, 136 insertions, 36 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 3d23bd6..0983a20 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -42,24 +42,27 @@
 
 #define MLX5E_MAX_NUM_TC	8
 
-#define MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE                0x7
+#define MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE                0x6
 #define MLX5E_PARAMS_DEFAULT_LOG_SQ_SIZE                0xa
 #define MLX5E_PARAMS_MAXIMUM_LOG_SQ_SIZE                0xd
 
-#define MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE                0x7
+#define MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE                0x1
 #define MLX5E_PARAMS_DEFAULT_LOG_RQ_SIZE                0xa
 #define MLX5E_PARAMS_MAXIMUM_LOG_RQ_SIZE                0xd
 
-#define MLX5E_PARAMS_DEFAULT_LRO_WQE_SZ                 (16 * 1024)
+#define MLX5E_PARAMS_DEFAULT_LRO_WQE_SZ                 (64 * 1024)
 #define MLX5E_PARAMS_DEFAULT_RX_CQ_MODERATION_USEC      0x10
 #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_PKTS      0x20
 #define MLX5E_PARAMS_DEFAULT_MIN_RX_WQES                0x80
-#define MLX5E_PARAMS_DEFAULT_RX_HASH_LOG_TBL_SZ         0x7
 
+#define MLX5E_LOG_INDIR_RQT_SIZE       0x7
+#define MLX5E_INDIR_RQT_SIZE           BIT(MLX5E_LOG_INDIR_RQT_SIZE)
+#define MLX5E_MAX_NUM_CHANNELS         (MLX5E_INDIR_RQT_SIZE >> 1)
 #define MLX5E_TX_CQ_POLL_BUDGET        128
 #define MLX5E_UPDATE_STATS_INTERVAL    200 /* msecs */
+#define MLX5E_SQ_BF_BUDGET             16
 
 static const char vport_strings[][ETH_GSTRING_LEN] = {
 	/* vport statistics */
@@ -91,6 +94,7 @@ static const char vport_strings[][ETH_GSTRING_LEN] = {
 	"lro_bytes",
 	"rx_csum_good",
 	"rx_csum_none",
+	"rx_csum_sw",
 	"tx_csum_offload",
 	"tx_queue_stopped",
 	"tx_queue_wake",
@@ -128,18 +132,94 @@ struct mlx5e_vport_stats {
 	u64 lro_bytes;
 	u64 rx_csum_good;
 	u64 rx_csum_none;
+	u64 rx_csum_sw;
 	u64 tx_csum_offload;
 	u64 tx_queue_stopped;
 	u64 tx_queue_wake;
 	u64 tx_queue_dropped;
 	u64 rx_wqe_err;
 
-#define NUM_VPORT_COUNTERS     31
+#define NUM_VPORT_COUNTERS     32
+};
+
+static const char pport_strings[][ETH_GSTRING_LEN] = {
+	/* IEEE802.3 counters */
+	"frames_tx",
+	"frames_rx",
+	"check_seq_err",
+	"alignment_err",
+	"octets_tx",
+	"octets_received",
+	"multicast_xmitted",
+	"broadcast_xmitted",
+	"multicast_rx",
+	"broadcast_rx",
+	"in_range_len_errors",
+	"out_of_range_len",
+	"too_long_errors",
+	"symbol_err",
+	"mac_control_tx",
+	"mac_control_rx",
+	"unsupported_op_rx",
+	"pause_ctrl_rx",
+	"pause_ctrl_tx",
+
+	/* RFC2863 counters */
+	"in_octets",
+	"in_ucast_pkts",
+	"in_discards",
+	"in_errors",
+	"in_unknown_protos",
+	"out_octets",
+	"out_ucast_pkts",
+	"out_discards",
+	"out_errors",
+	"in_multicast_pkts",
+	"in_broadcast_pkts",
+	"out_multicast_pkts",
+	"out_broadcast_pkts",
+
+	/* RFC2819 counters */
+	"drop_events",
+	"octets",
+	"pkts",
+	"broadcast_pkts",
+	"multicast_pkts",
+	"crc_align_errors",
+	"undersize_pkts",
+	"oversize_pkts",
+	"fragments",
+	"jabbers",
+	"collisions",
+	"p64octets",
+	"p65to127octets",
+	"p128to255octets",
+	"p256to511octets",
+	"p512to1023octets",
+	"p1024to1518octets",
+	"p1519to2047octets",
+	"p2048to4095octets",
+	"p4096to8191octets",
+	"p8192to10239octets",
+};
+
+#define NUM_IEEE_802_3_COUNTERS		19
+#define NUM_RFC_2863_COUNTERS		13
+#define NUM_RFC_2819_COUNTERS		21
+#define NUM_PPORT_COUNTERS		(NUM_IEEE_802_3_COUNTERS + \
+					 NUM_RFC_2863_COUNTERS + \
+					 NUM_RFC_2819_COUNTERS)
+
+struct mlx5e_pport_stats {
+	__be64 IEEE_802_3_counters[NUM_IEEE_802_3_COUNTERS];
+	__be64 RFC_2863_counters[NUM_RFC_2863_COUNTERS];
+	__be64 RFC_2819_counters[NUM_RFC_2819_COUNTERS];
 };
 
 static const char rq_stats_strings[][ETH_GSTRING_LEN] = {
 	"packets",
 	"csum_none",
+	"csum_sw",
 	"lro_packets",
 	"lro_bytes",
 	"wqe_err"
@@ -148,10 +228,11 @@ static const char rq_stats_strings[][ETH_GSTRING_LEN] = {
 struct mlx5e_rq_stats {
 	u64 packets;
 	u64 csum_none;
+	u64 csum_sw;
 	u64 lro_packets;
 	u64 lro_bytes;
 	u64 wqe_err;
-#define NUM_RQ_STATS 5
+#define NUM_RQ_STATS 6
 };
 
 static const char sq_stats_strings[][ETH_GSTRING_LEN] = {
@@ -179,6 +260,7 @@ struct mlx5e_sq_stats {
 
 struct mlx5e_stats {
 	struct mlx5e_vport_stats   vport;
+	struct mlx5e_pport_stats   pport;
 };
 
 struct mlx5e_params {
@@ -192,9 +274,12 @@ struct mlx5e_params {
 	u16 tx_cq_moderation_usec;
 	u16 tx_cq_moderation_pkts;
 	u16 min_rx_wqes;
-	u16 rx_hash_log_tbl_sz;
 	bool lro_en;
 	u32 lro_wqe_sz;
+	u16 tx_max_inline;
+	u8  rss_hfunc;
+	u8  toeplitz_hash_key[40];
+	u32 indirection_rqt[MLX5E_INDIR_RQT_SIZE];
 };
 
 enum {
@@ -214,6 +299,7 @@ struct mlx5e_cq {
 	struct napi_struct        *napi;
 	struct mlx5_core_cq        mcq;
 	struct mlx5e_channel      *channel;
+	struct mlx5e_priv         *priv;
 
 	/* control */
 	struct mlx5_wq_ctrl        wq_ctrl;
@@ -237,6 +323,7 @@ struct mlx5e_rq {
 	struct mlx5_wq_ctrl    wq_ctrl;
 	u32                    rqn;
 	struct mlx5e_channel  *channel;
+	struct mlx5e_priv     *priv;
 } ____cacheline_aligned_in_smp;
 
 struct mlx5e_tx_skb_cb {
@@ -266,7 +353,9 @@ struct mlx5e_sq {
 	/* dirtied @xmit */
 	u16                        pc ____cacheline_aligned_in_smp;
 	u32                        dma_fifo_pc;
-	u32                        bf_offset;
+	u16                        bf_offset;
+	u16                        prev_cc;
+	u8                         bf_budget;
 	struct mlx5e_sq_stats      stats;
 
 	struct mlx5e_cq            cq;
@@ -279,9 +368,10 @@ struct mlx5e_sq {
 	struct mlx5_wq_cyc         wq;
 	u32                        dma_fifo_mask;
 	void __iomem              *uar_map;
+	void __iomem              *uar_bf_map;
 	struct netdev_queue       *txq;
 	u32                        sqn;
-	u32                        bf_buf_size;
+	u16                        bf_buf_size;
 	u16                        max_inline;
 	u16                        edge;
 	struct device             *pdev;
@@ -315,7 +405,6 @@ struct mlx5e_channel {
 	__be32                     mkey_be;
 	u8                         num_tc;
 	unsigned long              flags;
-	int                        tc_to_txq_map[MLX5E_MAX_NUM_TC];
 
 	/* control */
 	struct mlx5e_priv         *priv;
@@ -324,20 +413,24 @@ struct mlx5e_channel {
 };
 
 enum mlx5e_traffic_types {
-	MLX5E_TT_IPV4_TCP = 0,
-	MLX5E_TT_IPV6_TCP = 1,
-	MLX5E_TT_IPV4_UDP = 2,
-	MLX5E_TT_IPV6_UDP = 3,
-	MLX5E_TT_IPV4     = 4,
-	MLX5E_TT_IPV6     = 5,
-	MLX5E_TT_ANY      = 6,
-	MLX5E_NUM_TT      = 7,
+	MLX5E_TT_IPV4_TCP,
+	MLX5E_TT_IPV6_TCP,
+	MLX5E_TT_IPV4_UDP,
+	MLX5E_TT_IPV6_UDP,
+	MLX5E_TT_IPV4_IPSEC_AH,
+	MLX5E_TT_IPV6_IPSEC_AH,
+	MLX5E_TT_IPV4_IPSEC_ESP,
+	MLX5E_TT_IPV6_IPSEC_ESP,
+	MLX5E_TT_IPV4,
+	MLX5E_TT_IPV6,
+	MLX5E_TT_ANY,
+	MLX5E_NUM_TT,
 };
 
-enum {
-	MLX5E_RQT_SPREADING  = 0,
-	MLX5E_RQT_DEFAULT_RQ = 1,
-	MLX5E_NUM_RQT        = 2,
+enum mlx5e_rqt_ix {
+	MLX5E_INDIRECTION_RQT,
+	MLX5E_SINGLE_RQ_RQT,
+	MLX5E_NUM_RQT,
 };
 
 struct mlx5e_eth_addr_info {
@@ -362,10 +455,10 @@ struct mlx5e_eth_addr_db {
 enum {
 	MLX5E_STATE_ASYNC_EVENTS_ENABLE,
 	MLX5E_STATE_OPENED,
+	MLX5E_STATE_DESTROYING,
 };
 
 struct mlx5e_vlan_db {
-	unsigned long active_vlans[BITS_TO_LONGS(VLAN_N_VID)];
 	u32           active_vlans_ft_ix[VLAN_N_VID];
 	u32           untagged_rule_ft_ix;
 	u32           any_vlan_rule_ft_ix;
@@ -379,9 +472,9 @@ struct mlx5e_flow_table {
 
 struct mlx5e_priv {
 	/* priv data path fields - start */
-	int                        num_tc;
 	int                        default_vlan_prio;
 	struct mlx5e_sq            **txq_to_sq_map;
+	int channeltc_to_txq_map[MLX5E_MAX_NUM_CHANNELS][MLX5E_MAX_NUM_TC];
 	/* priv data path fields - end */
 
 	unsigned long              state;
@@ -390,10 +483,11 @@ struct mlx5e_priv {
 	u32                        pdn;
 	u32                        tdn;
 	struct mlx5_core_mr        mr;
+	struct mlx5e_rq            drop_rq;
 
 	struct mlx5e_channel     **channel;
 	u32                        tisn[MLX5E_MAX_NUM_TC];
-	u32                        rqtn;
+	u32                        rqtn[MLX5E_NUM_RQT];
 	u32                        tirn[MLX5E_NUM_TT];
 
 	struct mlx5e_flow_table    ft;
@@ -470,10 +564,9 @@ struct mlx5_cqe64 *mlx5e_get_cqe(struct mlx5e_cq *cq);
 
 void mlx5e_update_stats(struct mlx5e_priv *priv);
 
-int mlx5e_open_flow_table(struct mlx5e_priv *priv);
-void mlx5e_close_flow_table(struct mlx5e_priv *priv);
+int mlx5e_create_flow_tables(struct mlx5e_priv *priv);
+void mlx5e_destroy_flow_tables(struct mlx5e_priv *priv);
 void mlx5e_init_eth_addr(struct mlx5e_priv *priv);
-void mlx5e_set_rx_mode_core(struct mlx5e_priv *priv);
 void mlx5e_set_rx_mode_work(struct work_struct *work);
 
 int mlx5e_vlan_rx_add_vid(struct net_device *dev, __always_unused __be16 proto,
@@ -482,17 +575,17 @@ int mlx5e_vlan_rx_kill_vid(struct net_device *dev, __always_unused __be16 proto,
 			   u16 vid);
 void mlx5e_enable_vlan_filter(struct mlx5e_priv *priv);
 void mlx5e_disable_vlan_filter(struct mlx5e_priv *priv);
-int mlx5e_add_all_vlan_rules(struct mlx5e_priv *priv);
-void mlx5e_del_all_vlan_rules(struct mlx5e_priv *priv);
+
+int mlx5e_redirect_rqt(struct mlx5e_priv *priv, enum mlx5e_rqt_ix rqt_ix);
 
 int mlx5e_open_locked(struct net_device *netdev);
 int mlx5e_close_locked(struct net_device *netdev);
-int mlx5e_update_priv_params(struct mlx5e_priv *priv,
-			     struct mlx5e_params *new_params);
 
 static inline void mlx5e_tx_notify_hw(struct mlx5e_sq *sq,
-				      struct mlx5e_tx_wqe *wqe)
+				      struct mlx5e_tx_wqe *wqe, int bf_sz)
 {
+	u16 ofst = MLX5_BF_OFFSET + sq->bf_offset;
+
 	/* ensure wqe is visible to device before updating doorbell record */
 	dma_wmb();
 
@@ -503,9 +596,15 @@ static inline void mlx5e_tx_notify_hw(struct mlx5e_sq *sq,
 	 */
 	wmb();
 
-	mlx5_write64((__be32 *)&wqe->ctrl,
-		     sq->uar_map + MLX5_BF_OFFSET + sq->bf_offset,
-		     NULL);
+	if (bf_sz) {
+		__iowrite64_copy(sq->uar_bf_map + ofst, &wqe->ctrl, bf_sz);
+
+		/* flush the write-combining mapped buffer */
+		wmb();
+
+	} else {
+		mlx5_write64((__be32 *)&wqe->ctrl, sq->uar_map + ofst, NULL);
+	}
 
 	sq->bf_offset ^= sq->bf_buf_size;
 }
@@ -519,3 +618,4 @@ static inline void mlx5e_cq_arm(struct mlx5e_cq *cq)
 }
 
 extern const struct ethtool_ops mlx5e_ethtool_ops;
+u16 mlx5e_get_max_inline_cap(struct mlx5_core_dev *mdev);