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

Pull networking updates from David Miller:
 "Highlights:

   1) Support TX_RING in AF_PACKET TPACKET_V3 mode, from Sowmini
      Varadhan.

   2) Simplify classifier state on sk_buff in order to shrink it a bit.
      From Willem de Bruijn.

   3) Introduce SIPHASH and it's usage for secure sequence numbers and
      syncookies. From Jason A. Donenfeld.

   4) Reduce CPU usage for ICMP replies we are going to limit or
      suppress, from Jesper Dangaard Brouer.

   5) Introduce Shared Memory Communications socket layer, from Ursula
      Braun.

   6) Add RACK loss detection and allow it to actually trigger fast
      recovery instead of just assisting after other algorithms have
      triggered it. From Yuchung Cheng.

   7) Add xmit_more and BQL support to mvneta driver, from Simon Guinot.

   8) skb_cow_data avoidance in esp4 and esp6, from Steffen Klassert.

   9) Export MPLS packet stats via netlink, from Robert Shearman.

  10) Significantly improve inet port bind conflict handling, especially
      when an application is restarted and changes it's setting of
      reuseport. From Josef Bacik.

  11) Implement TX batching in vhost_net, from Jason Wang.

  12) Extend the dummy device so that VF (virtual function) features,
      such as configuration, can be more easily tested. From Phil
      Sutter.

  13) Avoid two atomic ops per page on x86 in bnx2x driver, from Eric
      Dumazet.

  14) Add new bpf MAP, implementing a longest prefix match trie. From
      Daniel Mack.

  15) Packet sample offloading support in mlxsw driver, from Yotam Gigi.

  16) Add new aquantia driver, from David VomLehn.

  17) Add bpf tracepoints, from Daniel Borkmann.

  18) Add support for port mirroring to b53 and bcm_sf2 drivers, from
      Florian Fainelli.

  19) Remove custom busy polling in many drivers, it is done in the core
      networking since 4.5 times. From Eric Dumazet.

  20) Support XDP adjust_head in virtio_net, from John Fastabend.

  21) Fix several major holes in neighbour entry confirmation, from
      Julian Anastasov.

  22) Add XDP support to bnxt_en driver, from Michael Chan.

  23) VXLAN offloads for enic driver, from Govindarajulu Varadarajan.

  24) Add IPVTAP driver (IP-VLAN based tap driver) from Sainath Grandhi.

  25) Support GRO in IPSEC protocols, from Steffen Klassert"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1764 commits)
  Revert "ath10k: Search SMBIOS for OEM board file extension"
  net: socket: fix recvmmsg not returning error from sock_error
  bnxt_en: use eth_hw_addr_random()
  bpf: fix unlocking of jited image when module ronx not set
  arch: add ARCH_HAS_SET_MEMORY config
  net: napi_watchdog() can use napi_schedule_irqoff()
  tcp: Revert "tcp: tcp_probe: use spin_lock_bh()"
  net/hsr: use eth_hw_addr_random()
  net: mvpp2: enable building on 64-bit platforms
  net: mvpp2: switch to build_skb() in the RX path
  net: mvpp2: simplify MVPP2_PRS_RI_* definitions
  net: mvpp2: fix indentation of MVPP2_EXT_GLOBAL_CTRL_DEFAULT
  net: mvpp2: remove unused register definitions
  net: mvpp2: simplify mvpp2_bm_bufs_add()
  net: mvpp2: drop useless fields in mvpp2_bm_pool and related code
  net: mvpp2: remove unused 'tx_skb' field of 'struct mvpp2_tx_queue'
  net: mvpp2: release reference to txq_cpu[] entry after unmapping
  net: mvpp2: handle too large value in mvpp2_rx_time_coal_set()
  net: mvpp2: handle too large value handling in mvpp2_rx_pkts_coal_set()
  net: mvpp2: remove useless arguments in mvpp2_rx_{pkts, time}_coal_set
  ...

7 files changed, 521 insertions, 154 deletions

diff --git a/include/linux/mlx5/cq.h b/include/linux/mlx5/cq.h
index 7c3c0d3aca37..95898847c7d4 100644
--- a/include/linux/mlx5/cq.h
+++ b/include/linux/mlx5/cq.h
@@ -42,13 +42,13 @@ struct mlx5_core_cq {
 	int			cqe_sz;
 	__be32		       *set_ci_db;
 	__be32		       *arm_db;
+	struct mlx5_uars_page  *uar;
 	atomic_t		refcount;
 	struct completion	free;
 	unsigned		vector;
 	unsigned int		irqn;
 	void (*comp)		(struct mlx5_core_cq *);
 	void (*event)		(struct mlx5_core_cq *, enum mlx5_event);
-	struct mlx5_uar	       *uar;
 	u32			cons_index;
 	unsigned		arm_sn;
 	struct mlx5_rsc_debug	*dbg;
@@ -144,7 +144,6 @@ enum {
 
 static inline void mlx5_cq_arm(struct mlx5_core_cq *cq, u32 cmd,
 			       void __iomem *uar_page,
-			       spinlock_t *doorbell_lock,
 			       u32 cons_index)
 {
 	__be32 doorbell[2];
@@ -164,7 +163,7 @@ static inline void mlx5_cq_arm(struct mlx5_core_cq *cq, u32 cmd,
 	doorbell[0] = cpu_to_be32(sn << 28 | cmd | ci);
 	doorbell[1] = cpu_to_be32(cq->cqn);
 
-	mlx5_write64(doorbell, uar_page + MLX5_CQ_DOORBELL, doorbell_lock);
+	mlx5_write64(doorbell, uar_page + MLX5_CQ_DOORBELL, NULL);
 }
 
 int mlx5_init_cq_table(struct mlx5_core_dev *dev);
diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index 52b437431c6a..dd9a263ed368 100644
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -67,10 +67,11 @@
 
 /* insert a value to a struct */
 #define MLX5_SET(typ, p, fld, v) do { \
+	u32 _v = v; \
 	BUILD_BUG_ON(__mlx5_st_sz_bits(typ) % 32);             \
 	*((__be32 *)(p) + __mlx5_dw_off(typ, fld)) = \
 	cpu_to_be32((be32_to_cpu(*((__be32 *)(p) + __mlx5_dw_off(typ, fld))) & \
-		     (~__mlx5_dw_mask(typ, fld))) | (((v) & __mlx5_mask(typ, fld)) \
+		     (~__mlx5_dw_mask(typ, fld))) | (((_v) & __mlx5_mask(typ, fld)) \
 		     << __mlx5_dw_bit_off(typ, fld))); \
 } while (0)
 
@@ -212,10 +213,20 @@ enum {
 };
 
 enum {
-	MLX5_BF_REGS_PER_PAGE		= 4,
-	MLX5_MAX_UAR_PAGES		= 1 << 8,
-	MLX5_NON_FP_BF_REGS_PER_PAGE	= 2,
-	MLX5_MAX_UUARS	= MLX5_MAX_UAR_PAGES * MLX5_NON_FP_BF_REGS_PER_PAGE,
+	MLX5_ADAPTER_PAGE_SHIFT		= 12,
+	MLX5_ADAPTER_PAGE_SIZE		= 1 << MLX5_ADAPTER_PAGE_SHIFT,
+};
+
+enum {
+	MLX5_BFREGS_PER_UAR		= 4,
+	MLX5_MAX_UARS			= 1 << 8,
+	MLX5_NON_FP_BFREGS_PER_UAR	= 2,
+	MLX5_FP_BFREGS_PER_UAR		= MLX5_BFREGS_PER_UAR -
+					  MLX5_NON_FP_BFREGS_PER_UAR,
+	MLX5_MAX_BFREGS			= MLX5_MAX_UARS *
+					  MLX5_NON_FP_BFREGS_PER_UAR,
+	MLX5_UARS_IN_PAGE		= PAGE_SIZE / MLX5_ADAPTER_PAGE_SIZE,
+	MLX5_NON_FP_BFREGS_IN_PAGE	= MLX5_NON_FP_BFREGS_PER_UAR * MLX5_UARS_IN_PAGE,
 };
 
 enum {
@@ -279,6 +290,7 @@ enum mlx5_event {
 	MLX5_EVENT_TYPE_GPIO_EVENT	   = 0x15,
 	MLX5_EVENT_TYPE_PORT_MODULE_EVENT  = 0x16,
 	MLX5_EVENT_TYPE_REMOTE_CONFIG	   = 0x19,
+	MLX5_EVENT_TYPE_PPS_EVENT          = 0x25,
 
 	MLX5_EVENT_TYPE_DB_BF_CONGESTION   = 0x1a,
 	MLX5_EVENT_TYPE_STALL_EVENT	   = 0x1b,
@@ -389,11 +401,6 @@ enum {
 };
 
 enum {
-	MLX5_ADAPTER_PAGE_SHIFT		= 12,
-	MLX5_ADAPTER_PAGE_SIZE		= 1 << MLX5_ADAPTER_PAGE_SHIFT,
-};
-
-enum {
 	MLX5_CAP_OFF_CMDIF_CSUM		= 46,
 };
 
@@ -534,7 +541,9 @@ struct mlx5_eqe_page_fault {
 			__be16  wqe_index;
 			u16	reserved2;
 			__be16  packet_length;
-			u8	reserved3[12];
+			__be32  token;
+			u8	reserved4[8];
+			__be32  pftype_wq;
 		} __packed wqe;
 		struct {
 			__be32  r_key;
@@ -542,9 +551,9 @@ struct mlx5_eqe_page_fault {
 			__be16  packet_length;
 			__be32  rdma_op_len;
 			__be64  rdma_va;
+			__be32  pftype_token;
 		} __packed rdma;
 	} __packed;
-	__be32 flags_qpn;
 } __packed;
 
 struct mlx5_eqe_vport_change {
@@ -562,6 +571,22 @@ struct mlx5_eqe_port_module {
 	u8        error_type;
 } __packed;
 
+struct mlx5_eqe_pps {
+	u8		rsvd0[3];
+	u8		pin;
+	u8		rsvd1[4];
+	union {
+		struct {
+			__be32		time_sec;
+			__be32		time_nsec;
+		};
+		struct {
+			__be64		time_stamp;
+		};
+	};
+	u8		rsvd2[12];
+} __packed;
+
 union ev_data {
 	__be32				raw[7];
 	struct mlx5_eqe_cmd		cmd;
@@ -576,6 +601,7 @@ union ev_data {
 	struct mlx5_eqe_page_fault	page_fault;
 	struct mlx5_eqe_vport_change	vport_change;
 	struct mlx5_eqe_port_module	port_module;
+	struct mlx5_eqe_pps		pps;
 } __packed;
 
 struct mlx5_eqe {
@@ -945,38 +971,54 @@ enum mlx5_cap_type {
 	MLX5_CAP_NUM
 };
 
+enum mlx5_pcam_reg_groups {
+	MLX5_PCAM_REGS_5000_TO_507F                 = 0x0,
+};
+
+enum mlx5_pcam_feature_groups {
+	MLX5_PCAM_FEATURE_ENHANCED_FEATURES         = 0x0,
+};
+
+enum mlx5_mcam_reg_groups {
+	MLX5_MCAM_REGS_FIRST_128                    = 0x0,
+};
+
+enum mlx5_mcam_feature_groups {
+	MLX5_MCAM_FEATURE_ENHANCED_FEATURES         = 0x0,
+};
+
 /* GET Dev Caps macros */
 #define MLX5_CAP_GEN(mdev, cap) \
-	MLX5_GET(cmd_hca_cap, mdev->hca_caps_cur[MLX5_CAP_GENERAL], cap)
+	MLX5_GET(cmd_hca_cap, mdev->caps.hca_cur[MLX5_CAP_GENERAL], cap)
 
 #define MLX5_CAP_GEN_MAX(mdev, cap) \
-	MLX5_GET(cmd_hca_cap, mdev->hca_caps_max[MLX5_CAP_GENERAL], cap)
+	MLX5_GET(cmd_hca_cap, mdev->caps.hca_max[MLX5_CAP_GENERAL], cap)
 
 #define MLX5_CAP_ETH(mdev, cap) \
 	MLX5_GET(per_protocol_networking_offload_caps,\
-		 mdev->hca_caps_cur[MLX5_CAP_ETHERNET_OFFLOADS], cap)
+		 mdev->caps.hca_cur[MLX5_CAP_ETHERNET_OFFLOADS], cap)
 
 #define MLX5_CAP_ETH_MAX(mdev, cap) \
 	MLX5_GET(per_protocol_networking_offload_caps,\
-		 mdev->hca_caps_max[MLX5_CAP_ETHERNET_OFFLOADS], cap)
+		 mdev->caps.hca_max[MLX5_CAP_ETHERNET_OFFLOADS], cap)
 
 #define MLX5_CAP_ROCE(mdev, cap) \
-	MLX5_GET(roce_cap, mdev->hca_caps_cur[MLX5_CAP_ROCE], cap)
+	MLX5_GET(roce_cap, mdev->caps.hca_cur[MLX5_CAP_ROCE], cap)
 
 #define MLX5_CAP_ROCE_MAX(mdev, cap) \
-	MLX5_GET(roce_cap, mdev->hca_caps_max[MLX5_CAP_ROCE], cap)
+	MLX5_GET(roce_cap, mdev->caps.hca_max[MLX5_CAP_ROCE], cap)
 
 #define MLX5_CAP_ATOMIC(mdev, cap) \
-	MLX5_GET(atomic_caps, mdev->hca_caps_cur[MLX5_CAP_ATOMIC], cap)
+	MLX5_GET(atomic_caps, mdev->caps.hca_cur[MLX5_CAP_ATOMIC], cap)
 
 #define MLX5_CAP_ATOMIC_MAX(mdev, cap) \
-	MLX5_GET(atomic_caps, mdev->hca_caps_max[MLX5_CAP_ATOMIC], cap)
+	MLX5_GET(atomic_caps, mdev->caps.hca_max[MLX5_CAP_ATOMIC], cap)
 
 #define MLX5_CAP_FLOWTABLE(mdev, cap) \
-	MLX5_GET(flow_table_nic_cap, mdev->hca_caps_cur[MLX5_CAP_FLOW_TABLE], cap)
+	MLX5_GET(flow_table_nic_cap, mdev->caps.hca_cur[MLX5_CAP_FLOW_TABLE], cap)
 
 #define MLX5_CAP_FLOWTABLE_MAX(mdev, cap) \
-	MLX5_GET(flow_table_nic_cap, mdev->hca_caps_max[MLX5_CAP_FLOW_TABLE], cap)
+	MLX5_GET(flow_table_nic_cap, mdev->caps.hca_max[MLX5_CAP_FLOW_TABLE], cap)
 
 #define MLX5_CAP_FLOWTABLE_NIC_RX(mdev, cap) \
 	MLX5_CAP_FLOWTABLE(mdev, flow_table_properties_nic_receive.cap)
@@ -998,11 +1040,11 @@ enum mlx5_cap_type {
 
 #define MLX5_CAP_ESW_FLOWTABLE(mdev, cap) \
 	MLX5_GET(flow_table_eswitch_cap, \
-		 mdev->hca_caps_cur[MLX5_CAP_ESWITCH_FLOW_TABLE], cap)
+		 mdev->caps.hca_cur[MLX5_CAP_ESWITCH_FLOW_TABLE], cap)
 
 #define MLX5_CAP_ESW_FLOWTABLE_MAX(mdev, cap) \
 	MLX5_GET(flow_table_eswitch_cap, \
-		 mdev->hca_caps_max[MLX5_CAP_ESWITCH_FLOW_TABLE], cap)
+		 mdev->caps.hca_max[MLX5_CAP_ESWITCH_FLOW_TABLE], cap)
 
 #define MLX5_CAP_ESW_FLOWTABLE_FDB(mdev, cap) \
 	MLX5_CAP_ESW_FLOWTABLE(mdev, flow_table_properties_nic_esw_fdb.cap)
@@ -1024,21 +1066,27 @@ enum mlx5_cap_type {
 
 #define MLX5_CAP_ESW(mdev, cap) \
 	MLX5_GET(e_switch_cap, \
-		 mdev->hca_caps_cur[MLX5_CAP_ESWITCH], cap)
+		 mdev->caps.hca_cur[MLX5_CAP_ESWITCH], cap)
 
 #define MLX5_CAP_ESW_MAX(mdev, cap) \
 	MLX5_GET(e_switch_cap, \
-		 mdev->hca_caps_max[MLX5_CAP_ESWITCH], cap)
+		 mdev->caps.hca_max[MLX5_CAP_ESWITCH], cap)
 
 #define MLX5_CAP_ODP(mdev, cap)\
-	MLX5_GET(odp_cap, mdev->hca_caps_cur[MLX5_CAP_ODP], cap)
+	MLX5_GET(odp_cap, mdev->caps.hca_cur[MLX5_CAP_ODP], cap)
 
 #define MLX5_CAP_VECTOR_CALC(mdev, cap) \
 	MLX5_GET(vector_calc_cap, \
-		 mdev->hca_caps_cur[MLX5_CAP_VECTOR_CALC], cap)
+		 mdev->caps.hca_cur[MLX5_CAP_VECTOR_CALC], cap)
 
 #define MLX5_CAP_QOS(mdev, cap)\
-	MLX5_GET(qos_cap, mdev->hca_caps_cur[MLX5_CAP_QOS], cap)
+	MLX5_GET(qos_cap, mdev->caps.hca_cur[MLX5_CAP_QOS], cap)
+
+#define MLX5_CAP_PCAM_FEATURE(mdev, fld) \
+	MLX5_GET(pcam_reg, (mdev)->caps.pcam, feature_cap_mask.enhanced_features.fld)
+
+#define MLX5_CAP_MCAM_FEATURE(mdev, fld) \
+	MLX5_GET(mcam_reg, (mdev)->caps.mcam, mng_feature_cap_mask.enhanced_features.fld)
 
 enum {
 	MLX5_CMD_STAT_OK			= 0x0,
@@ -1068,9 +1116,14 @@ enum {
 	MLX5_PER_PRIORITY_COUNTERS_GROUP      = 0x10,
 	MLX5_PER_TRAFFIC_CLASS_COUNTERS_GROUP = 0x11,
 	MLX5_PHYSICAL_LAYER_COUNTERS_GROUP    = 0x12,
+	MLX5_PHYSICAL_LAYER_STATISTICAL_GROUP = 0x16,
 	MLX5_INFINIBAND_PORT_COUNTERS_GROUP   = 0x20,
 };
 
+enum {
+	MLX5_PCIE_PERFORMANCE_COUNTERS_GROUP       = 0x0,
+};
+
 static inline u16 mlx5_to_sw_pkey_sz(int pkey_sz)
 {
 	if (pkey_sz > MLX5_MAX_LOG_PKEY_TABLE)
diff --git a/include/linux/mlx5/doorbell.h b/include/linux/mlx5/doorbell.h
index afc78a3f4462..0787de28f2fc 100644
--- a/include/linux/mlx5/doorbell.h
+++ b/include/linux/mlx5/doorbell.h
@@ -68,10 +68,12 @@ static inline void mlx5_write64(__be32 val[2], void __iomem *dest,
 {
 	unsigned long flags;
 
-	spin_lock_irqsave(doorbell_lock, flags);
+	if (doorbell_lock)
+		spin_lock_irqsave(doorbell_lock, flags);
 	__raw_writel((__force u32) val[0], dest);
 	__raw_writel((__force u32) val[1], dest + 4);
-	spin_unlock_irqrestore(doorbell_lock, flags);
+	if (doorbell_lock)
+		spin_unlock_irqrestore(doorbell_lock, flags);
 }
 
 #endif
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 735b36335f29..1bc4641734da 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -42,6 +42,7 @@
 #include <linux/vmalloc.h>
 #include <linux/radix-tree.h>
 #include <linux/workqueue.h>
+#include <linux/mempool.h>
 #include <linux/interrupt.h>
 
 #include <linux/mlx5/device.h>
@@ -83,6 +84,7 @@ enum {
 	MLX5_EQ_VEC_PAGES	 = 0,
 	MLX5_EQ_VEC_CMD		 = 1,
 	MLX5_EQ_VEC_ASYNC	 = 2,
+	MLX5_EQ_VEC_PFAULT	 = 3,
 	MLX5_EQ_VEC_COMP_BASE,
 };
 
@@ -119,10 +121,15 @@ enum {
 	MLX5_REG_PVLC		 = 0x500f,
 	MLX5_REG_PCMR		 = 0x5041,
 	MLX5_REG_PMLP		 = 0x5002,
+	MLX5_REG_PCAM		 = 0x507f,
 	MLX5_REG_NODE_DESC	 = 0x6001,
 	MLX5_REG_HOST_ENDIANNESS = 0x7004,
 	MLX5_REG_MCIA		 = 0x9014,
 	MLX5_REG_MLCR		 = 0x902b,
+	MLX5_REG_MPCNT		 = 0x9051,
+	MLX5_REG_MTPPS		 = 0x9053,
+	MLX5_REG_MTPPSE		 = 0x9054,
+	MLX5_REG_MCAM		 = 0x907f,
 };
 
 enum mlx5_dcbx_oper_mode {
@@ -170,6 +177,7 @@ enum mlx5_dev_event {
 	MLX5_DEV_EVENT_PKEY_CHANGE,
 	MLX5_DEV_EVENT_GUID_CHANGE,
 	MLX5_DEV_EVENT_CLIENT_REREG,
+	MLX5_DEV_EVENT_PPS,
 };
 
 enum mlx5_port_status {
@@ -177,36 +185,26 @@ enum mlx5_port_status {
 	MLX5_PORT_DOWN      = 2,
 };
 
-struct mlx5_uuar_info {
-	struct mlx5_uar	       *uars;
-	int			num_uars;
-	int			num_low_latency_uuars;
-	unsigned long	       *bitmap;
+enum mlx5_eq_type {
+	MLX5_EQ_TYPE_COMP,
+	MLX5_EQ_TYPE_ASYNC,
+#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
+	MLX5_EQ_TYPE_PF,
+#endif
+};
+
+struct mlx5_bfreg_info {
+	u32		       *sys_pages;
+	int			num_low_latency_bfregs;
 	unsigned int	       *count;
-	struct mlx5_bf	       *bfs;
 
 	/*
-	 * protect uuar allocation data structs
+	 * protect bfreg allocation data structs
 	 */
 	struct mutex		lock;
 	u32			ver;
-};
-
-struct mlx5_bf {
-	void __iomem	       *reg;
-	void __iomem	       *regreg;
-	int			buf_size;
-	struct mlx5_uar	       *uar;
-	unsigned long		offset;
-	int			need_lock;
-	/* protect blue flame buffer selection when needed
-	 */
-	spinlock_t		lock;
-
-	/* serialize 64 bit writes when done as two 32 bit accesses
-	 */
-	spinlock_t		lock32;
-	int			uuarn;
+	bool			lib_uar_4k;
+	u32			num_sys_pages;
 };
 
 struct mlx5_cmd_first {
@@ -332,6 +330,14 @@ struct mlx5_eq_tasklet {
 	spinlock_t lock;
 };
 
+struct mlx5_eq_pagefault {
+	struct work_struct       work;
+	/* Pagefaults lock */
+	spinlock_t		 lock;
+	struct workqueue_struct *wq;
+	mempool_t		*pool;
+};
+
 struct mlx5_eq {
 	struct mlx5_core_dev   *dev;
 	__be32 __iomem	       *doorbell;
@@ -345,7 +351,13 @@ struct mlx5_eq {
 	struct list_head	list;
 	int			index;
 	struct mlx5_rsc_debug	*dbg;
-	struct mlx5_eq_tasklet	tasklet_ctx;
+	enum mlx5_eq_type	type;
+	union {
+		struct mlx5_eq_tasklet   tasklet_ctx;
+#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
+		struct mlx5_eq_pagefault pf_ctx;
+#endif
+	};
 };
 
 struct mlx5_core_psv {
@@ -369,13 +381,21 @@ struct mlx5_core_sig_ctx {
 	u32			sigerr_count;
 };
 
+enum {
+	MLX5_MKEY_MR = 1,
+	MLX5_MKEY_MW,
+};
+
 struct mlx5_core_mkey {
 	u64			iova;
 	u64			size;
 	u32			key;
 	u32			pd;
+	u32			type;
 };
 
+#define MLX5_24BIT_MASK		((1 << 24) - 1)
+
 enum mlx5_res_type {
 	MLX5_RES_QP	= MLX5_EVENT_QUEUE_TYPE_QP,
 	MLX5_RES_RQ	= MLX5_EVENT_QUEUE_TYPE_RQ,
@@ -410,20 +430,47 @@ struct mlx5_eq_table {
 	struct mlx5_eq		pages_eq;
 	struct mlx5_eq		async_eq;
 	struct mlx5_eq		cmd_eq;
+#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
+	struct mlx5_eq		pfault_eq;
+#endif
 	int			num_comp_vectors;
 	/* protect EQs list
 	 */
 	spinlock_t		lock;
 };
 
-struct mlx5_uar {
-	u32			index;
-	struct list_head	bf_list;
-	unsigned		free_bf_bmap;
-	void __iomem	       *bf_map;
+struct mlx5_uars_page {
 	void __iomem	       *map;
+	bool			wc;
+	u32			index;
+	struct list_head	list;
+	unsigned int		bfregs;
+	unsigned long	       *reg_bitmap; /* for non fast path bf regs */
+	unsigned long	       *fp_bitmap;
+	unsigned int		reg_avail;
+	unsigned int		fp_avail;
+	struct kref		ref_count;
+	struct mlx5_core_dev   *mdev;
+};
+
+struct mlx5_bfreg_head {
+	/* protect blue flame registers allocations */
+	struct mutex		lock;
+	struct list_head	list;
+};
+
+struct mlx5_bfreg_data {
+	struct mlx5_bfreg_head	reg_head;
+	struct mlx5_bfreg_head	wc_head;
 };
 
+struct mlx5_sq_bfreg {
+	void __iomem	       *map;
+	struct mlx5_uars_page  *up;
+	bool			wc;
+	u32			index;
+	unsigned int		offset;
+};
 
 struct mlx5_core_health {
 	struct health_buffer __iomem   *health;
@@ -496,6 +543,7 @@ struct mlx5_fc_stats {
 
 struct mlx5_eswitch;
 struct mlx5_lag;
+struct mlx5_pagefault;
 
 struct mlx5_rl_entry {
 	u32                     rate;
@@ -542,8 +590,6 @@ struct mlx5_priv {
 	struct mlx5_eq_table	eq_table;
 	struct msix_entry	*msix_arr;
 	struct mlx5_irq_info	*irq_info;
-	struct mlx5_uuar_info	uuari;
-	MLX5_DECLARE_DOORBELL_LOCK(cq_uar_lock);
 
 	/* pages stuff */
 	struct workqueue_struct *pg_wq;
@@ -600,6 +646,16 @@ struct mlx5_priv {
 	struct mlx5_rl_table            rl_table;
 
 	struct mlx5_port_module_event_stats  pme_stats;
+
+#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
+	void		      (*pfault)(struct mlx5_core_dev *dev,
+					void *context,
+					struct mlx5_pagefault *pfault);
+	void		       *pfault_ctx;
+	struct srcu_struct      pfault_srcu;
+#endif
+	struct mlx5_bfreg_data		bfregs;
+	struct mlx5_uars_page	       *uar;
 };
 
 enum mlx5_device_state {
@@ -618,13 +674,56 @@ enum mlx5_pci_status {
 	MLX5_PCI_STATUS_ENABLED,
 };
 
+enum mlx5_pagefault_type_flags {
+	MLX5_PFAULT_REQUESTOR = 1 << 0,
+	MLX5_PFAULT_WRITE     = 1 << 1,
+	MLX5_PFAULT_RDMA      = 1 << 2,
+};
+
+/* Contains the details of a pagefault. */
+struct mlx5_pagefault {
+	u32			bytes_committed;
+	u32			token;
+	u8			event_subtype;
+	u8			type;
+	union {
+		/* Initiator or send message responder pagefault details. */
+		struct {
+			/* Received packet size, only valid for responders. */
+			u32	packet_size;
+			/*
+			 * Number of resource holding WQE, depends on type.
+			 */
+			u32	wq_num;
+			/*
+			 * WQE index. Refers to either the send queue or
+			 * receive queue, according to event_subtype.
+			 */
+			u16	wqe_index;
+		} wqe;
+		/* RDMA responder pagefault details */
+		struct {
+			u32	r_key;
+			/*
+			 * Received packet size, minimal size page fault
+			 * resolution required for forward progress.
+			 */
+			u32	packet_size;
+			u32	rdma_op_len;
+			u64	rdma_va;
+		} rdma;
+	};
+
+	struct mlx5_eq	       *eq;
+	struct work_struct	work;
+};
+
 struct mlx5_td {
 	struct list_head tirs_list;
 	u32              tdn;
 };
 
 struct mlx5e_resources {
-	struct mlx5_uar            cq_uar;
 	u32                        pdn;
 	struct mlx5_td             td;
 	struct mlx5_core_mkey      mkey;
@@ -639,8 +738,12 @@ struct mlx5_core_dev {
 	char			board_id[MLX5_BOARD_ID_LEN];
 	struct mlx5_cmd		cmd;
 	struct mlx5_port_caps	port_caps[MLX5_MAX_PORTS];
-	u32 hca_caps_cur[MLX5_CAP_NUM][MLX5_UN_SZ_DW(hca_cap_union)];
-	u32 hca_caps_max[MLX5_CAP_NUM][MLX5_UN_SZ_DW(hca_cap_union)];
+	struct {
+		u32 hca_cur[MLX5_CAP_NUM][MLX5_UN_SZ_DW(hca_cap_union)];
+		u32 hca_max[MLX5_CAP_NUM][MLX5_UN_SZ_DW(hca_cap_union)];
+		u32 pcam[MLX5_ST_SZ_DW(pcam_reg)];
+		u32 mcam[MLX5_ST_SZ_DW(mcam_reg)];
+	} caps;
 	phys_addr_t		iseg_base;
 	struct mlx5_init_seg __iomem *iseg;
 	enum mlx5_device_state	state;
@@ -814,11 +917,6 @@ void mlx5_cmd_mbox_status(void *out, u8 *status, u32 *syndrome);
 int mlx5_core_get_caps(struct mlx5_core_dev *dev, enum mlx5_cap_type cap_type);
 int mlx5_cmd_alloc_uar(struct mlx5_core_dev *dev, u32 *uarn);
 int mlx5_cmd_free_uar(struct mlx5_core_dev *dev, u32 uarn);
-int mlx5_alloc_uuars(struct mlx5_core_dev *dev, struct mlx5_uuar_info *uuari);
-int mlx5_free_uuars(struct mlx5_core_dev *dev, struct mlx5_uuar_info *uuari);
-int mlx5_alloc_map_uar(struct mlx5_core_dev *mdev, struct mlx5_uar *uar,
-		       bool map_wc);
-void mlx5_unmap_free_uar(struct mlx5_core_dev *mdev, struct mlx5_uar *uar);
 void mlx5_health_cleanup(struct mlx5_core_dev *dev);
 int mlx5_health_init(struct mlx5_core_dev *dev);
 void mlx5_start_health_poll(struct mlx5_core_dev *dev);
@@ -878,15 +976,13 @@ void mlx5_fill_page_array(struct mlx5_buf *buf, __be64 *pas);
 void mlx5_fill_page_frag_array(struct mlx5_frag_buf *frag_buf, __be64 *pas);
 void mlx5_cq_completion(struct mlx5_core_dev *dev, u32 cqn);
 void mlx5_rsc_event(struct mlx5_core_dev *dev, u32 rsn, int event_type);
-#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
-void mlx5_eq_pagefault(struct mlx5_core_dev *dev, struct mlx5_eqe *eqe);
-#endif
 void mlx5_srq_event(struct mlx5_core_dev *dev, u32 srqn, int event_type);
 struct mlx5_core_srq *mlx5_core_get_srq(struct mlx5_core_dev *dev, u32 srqn);
 void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec);
 void mlx5_cq_event(struct mlx5_core_dev *dev, u32 cqn, int event_type);
 int mlx5_create_map_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq, u8 vecidx,
-		       int nent, u64 mask, const char *name, struct mlx5_uar *uar);
+		       int nent, u64 mask, const char *name,
+		       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);
@@ -925,12 +1021,19 @@ int mlx5_query_odp_caps(struct mlx5_core_dev *dev,
 			struct mlx5_odp_caps *odp_caps);
 int mlx5_core_query_ib_ppcnt(struct mlx5_core_dev *dev,
 			     u8 port_num, void *out, size_t sz);
+#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
+int mlx5_core_page_fault_resume(struct mlx5_core_dev *dev, u32 token,
+				u32 wq_num, u8 type, int error);
+#endif
 
 int mlx5_init_rl_table(struct mlx5_core_dev *dev);
 void mlx5_cleanup_rl_table(struct mlx5_core_dev *dev);
 int mlx5_rl_add_rate(struct mlx5_core_dev *dev, u32 rate, u16 *index);
 void mlx5_rl_remove_rate(struct mlx5_core_dev *dev, u32 rate);
 bool mlx5_rl_is_in_range(struct mlx5_core_dev *dev, u32 rate);
+int mlx5_alloc_bfreg(struct mlx5_core_dev *mdev, struct mlx5_sq_bfreg *bfreg,
+		     bool map_wc, bool fast_path);
+void mlx5_free_bfreg(struct mlx5_core_dev *mdev, struct mlx5_sq_bfreg *bfreg);
 
 static inline int fw_initializing(struct mlx5_core_dev *dev)
 {
@@ -958,7 +1061,7 @@ enum {
 };
 
 enum {
-	MAX_MR_CACHE_ENTRIES    = 16,
+	MAX_MR_CACHE_ENTRIES    = 21,
 };
 
 enum {
@@ -973,6 +1076,9 @@ struct mlx5_interface {
 	void			(*detach)(struct mlx5_core_dev *dev, void *context);
 	void			(*event)(struct mlx5_core_dev *dev, void *context,
 					 enum mlx5_dev_event event, unsigned long param);
+	void			(*pfault)(struct mlx5_core_dev *dev,
+					  void *context,
+					  struct mlx5_pagefault *pfault);
 	void *                  (*get_dev)(void *context);
 	int			protocol;
 	struct list_head	list;
@@ -987,6 +1093,8 @@ int mlx5_cmd_create_vport_lag(struct mlx5_core_dev *dev);
 int mlx5_cmd_destroy_vport_lag(struct mlx5_core_dev *dev);
 bool mlx5_lag_is_active(struct mlx5_core_dev *dev);
 struct net_device *mlx5_lag_get_roce_netdev(struct mlx5_core_dev *dev);
+struct mlx5_uars_page *mlx5_get_uars_page(struct mlx5_core_dev *mdev);
+void mlx5_put_uars_page(struct mlx5_core_dev *mdev, struct mlx5_uars_page *up);
 
 struct mlx5_profile {
 	u64	mask;
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index a852e9db6f0d..afcd4736d8df 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -328,7 +328,7 @@ struct mlx5_ifc_odp_per_transport_service_cap_bits {
 	u8         receive[0x1];
 	u8         write[0x1];
 	u8         read[0x1];
-	u8         reserved_at_4[0x1];
+	u8         atomic[0x1];
 	u8         srq_receive[0x1];
 	u8         reserved_at_6[0x1a];
 };
@@ -365,8 +365,8 @@ struct mlx5_ifc_fte_match_set_lyr_2_4_bits {
 	u8         ip_protocol[0x8];
 	u8         ip_dscp[0x6];
 	u8         ip_ecn[0x2];
-	u8         vlan_tag[0x1];
-	u8         reserved_at_91[0x1];
+	u8         cvlan_tag[0x1];
+	u8         svlan_tag[0x1];
 	u8         frag[0x1];
 	u8         reserved_at_93[0x4];
 	u8         tcp_flags[0x9];
@@ -398,9 +398,11 @@ struct mlx5_ifc_fte_match_set_misc_bits {
 	u8         inner_second_cfi[0x1];
 	u8         inner_second_vid[0xc];
 
-	u8         outer_second_vlan_tag[0x1];
-	u8         inner_second_vlan_tag[0x1];
-	u8         reserved_at_62[0xe];
+	u8         outer_second_cvlan_tag[0x1];
+	u8         inner_second_cvlan_tag[0x1];
+	u8         outer_second_svlan_tag[0x1];
+	u8         inner_second_svlan_tag[0x1];
+	u8         reserved_at_64[0xc];
 	u8         gre_protocol[0x10];
 
 	u8         gre_key_h[0x18];
@@ -545,7 +547,9 @@ struct mlx5_ifc_e_switch_cap_bits {
 struct mlx5_ifc_qos_cap_bits {
 	u8         packet_pacing[0x1];
 	u8         esw_scheduling[0x1];
-	u8         reserved_at_2[0x1e];
+	u8         esw_bw_share[0x1];
+	u8         esw_rate_limit[0x1];
+	u8         reserved_at_4[0x1c];
 
 	u8         reserved_at_20[0x20];
 
@@ -573,7 +577,8 @@ struct mlx5_ifc_per_protocol_networking_offload_caps_bits {
 	u8         lro_cap[0x1];
 	u8         lro_psh_flag[0x1];
 	u8         lro_time_stamp[0x1];
-	u8         reserved_at_5[0x3];
+	u8         reserved_at_5[0x2];
+	u8         wqe_vlan_insert[0x1];
 	u8         self_lb_en_modifiable[0x1];
 	u8         reserved_at_9[0x2];
 	u8         max_lso_cap[0x5];
@@ -782,11 +787,12 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 	u8         log_max_eq[0x4];
 
 	u8         max_indirection[0x8];
-	u8         reserved_at_108[0x1];
+	u8         fixed_buffer_size[0x1];
 	u8         log_max_mrw_sz[0x7];
 	u8         reserved_at_110[0x2];
 	u8         log_max_bsf_list_size[0x6];
-	u8         reserved_at_118[0x2];
+	u8         umr_extended_translation_offset[0x1];
+	u8         null_mkey[0x1];
 	u8         log_max_klm_list_size[0x6];
 
 	u8         reserved_at_120[0xa];
@@ -799,10 +805,12 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 	u8         reserved_at_150[0xa];
 	u8         log_max_ra_res_qp[0x6];
 
-	u8         pad_cap[0x1];
+	u8         end_pad[0x1];
 	u8         cc_query_allowed[0x1];
 	u8         cc_modify_allowed[0x1];
-	u8         reserved_at_163[0xd];
+	u8         start_pad[0x1];
+	u8         cache_line_128byte[0x1];
+	u8         reserved_at_163[0xb];
 	u8         gid_table_size[0x10];
 
 	u8         out_of_seq_cnt[0x1];
@@ -823,18 +831,21 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 	u8         nic_flow_table[0x1];
 	u8         eswitch_flow_table[0x1];
 	u8	   early_vf_enable[0x1];
-	u8         reserved_at_1a9[0x2];
+	u8         mcam_reg[0x1];
+	u8         pcam_reg[0x1];
 	u8         local_ca_ack_delay[0x5];
 	u8         port_module_event[0x1];
-	u8         reserved_at_1b0[0x1];
+	u8         reserved_at_1b1[0x1];
 	u8         ports_check[0x1];
-	u8         reserved_at_1b2[0x1];
+	u8         reserved_at_1b3[0x1];
 	u8         disable_link_up[0x1];
 	u8         beacon_led[0x1];
 	u8         port_type[0x2];
 	u8         num_ports[0x8];
 
-	u8         reserved_at_1c0[0x3];
+	u8         reserved_at_1c0[0x1];
+	u8         pps[0x1];
+	u8         pps_modify[0x1];
 	u8         log_max_msg[0x5];
 	u8         reserved_at_1c8[0x4];
 	u8         max_tc[0x4];
@@ -858,7 +869,7 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 
 	u8         compact_address_vector[0x1];
 	u8         striding_rq[0x1];
-	u8         reserved_at_201[0x2];
+	u8         reserved_at_202[0x2];
 	u8         ipoib_basic_offloads[0x1];
 	u8         reserved_at_205[0xa];
 	u8         drain_sigerr[0x1];
@@ -904,7 +915,8 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 	u8         uc[0x1];
 	u8         rc[0x1];
 
-	u8         reserved_at_240[0xa];
+	u8         uar_4k[0x1];
+	u8         reserved_at_241[0x9];
 	u8         uar_sz[0x6];
 	u8         reserved_at_250[0x8];
 	u8         log_pg_sz[0x8];
@@ -996,7 +1008,9 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 	u8         device_frequency_mhz[0x20];
 	u8         device_frequency_khz[0x20];
 
-	u8         reserved_at_500[0x80];
+	u8         reserved_at_500[0x20];
+	u8	   num_of_uars_per_page[0x20];
+	u8         reserved_at_540[0x40];
 
 	u8         reserved_at_580[0x3f];
 	u8         cqe_compression[0x1];
@@ -1009,10 +1023,10 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 	u8         rndv_offload_rc[0x1];
 	u8         rndv_offload_dc[0x1];
 	u8         log_tag_matching_list_sz[0x5];
-	u8         reserved_at_5e8[0x3];
+	u8         reserved_at_5f8[0x3];
 	u8         log_max_xrq[0x5];
 
-	u8         reserved_at_5f0[0x200];
+	u8         reserved_at_600[0x200];
 };
 
 enum mlx5_flow_destination_type {
@@ -1375,6 +1389,42 @@ struct mlx5_ifc_phys_layer_cntrs_bits {
 	u8         reserved_at_640[0x180];
 };
 
+struct mlx5_ifc_phys_layer_statistical_cntrs_bits {
+	u8         time_since_last_clear_high[0x20];
+
+	u8         time_since_last_clear_low[0x20];
+
+	u8         phy_received_bits_high[0x20];
+
+	u8         phy_received_bits_low[0x20];
+
+	u8         phy_symbol_errors_high[0x20];
+
+	u8         phy_symbol_errors_low[0x20];
+
+	u8         phy_corrected_bits_high[0x20];
+
+	u8         phy_corrected_bits_low[0x20];
+
+	u8         phy_corrected_bits_lane0_high[0x20];
+
+	u8         phy_corrected_bits_lane0_low[0x20];
+
+	u8         phy_corrected_bits_lane1_high[0x20];
+
+	u8         phy_corrected_bits_lane1_low[0x20];
+
+	u8         phy_corrected_bits_lane2_high[0x20];
+
+	u8         phy_corrected_bits_lane2_low[0x20];
+
+	u8         phy_corrected_bits_lane3_high[0x20];
+
+	u8         phy_corrected_bits_lane3_low[0x20];
+
+	u8         reserved_at_200[0x5c0];
+};
+
 struct mlx5_ifc_ib_port_cntrs_grp_data_layout_bits {
 	u8	   symbol_error_counter[0x10];
 
@@ -1757,6 +1807,30 @@ struct mlx5_ifc_eth_802_3_cntrs_grp_data_layout_bits {
 	u8         reserved_at_4c0[0x300];
 };
 
+struct mlx5_ifc_pcie_perf_cntrs_grp_data_layout_bits {
+	u8         life_time_counter_high[0x20];
+
+	u8         life_time_counter_low[0x20];
+
+	u8         rx_errors[0x20];
+
+	u8         tx_errors[0x20];
+
+	u8         l0_to_recovery_eieos[0x20];
+
+	u8         l0_to_recovery_ts[0x20];
+
+	u8         l0_to_recovery_framing[0x20];
+
+	u8         l0_to_recovery_retrain[0x20];
+
+	u8         crc_error_dllp[0x20];
+
+	u8         crc_error_tlp[0x20];
+
+	u8         reserved_at_140[0x680];
+};
+
 struct mlx5_ifc_cmd_inter_comp_event_bits {
 	u8         command_completion_vector[0x20];
 
@@ -2495,6 +2569,7 @@ enum {
 	MLX5_MKC_ACCESS_MODE_PA    = 0x0,
 	MLX5_MKC_ACCESS_MODE_MTT   = 0x1,
 	MLX5_MKC_ACCESS_MODE_KLMS  = 0x2,
+	MLX5_MKC_ACCESS_MODE_KSM   = 0x3,
 };
 
 struct mlx5_ifc_mkc_bits {
@@ -2918,6 +2993,12 @@ union mlx5_ifc_eth_cntrs_grp_data_layout_auto_bits {
 	struct mlx5_ifc_eth_per_traffic_grp_data_layout_bits eth_per_traffic_grp_data_layout;
 	struct mlx5_ifc_ib_port_cntrs_grp_data_layout_bits ib_port_cntrs_grp_data_layout;
 	struct mlx5_ifc_phys_layer_cntrs_bits phys_layer_cntrs;
+	struct mlx5_ifc_phys_layer_statistical_cntrs_bits phys_layer_statistical_cntrs;
+	u8         reserved_at_0[0x7c0];
+};
+
+union mlx5_ifc_pcie_cntrs_grp_data_layout_auto_bits {
+	struct mlx5_ifc_pcie_perf_cntrs_grp_data_layout_bits pcie_perf_cntrs_grp_data_layout;
 	u8         reserved_at_0[0x7c0];
 };
 
@@ -3597,6 +3678,10 @@ struct mlx5_ifc_query_special_contexts_out_bits {
 	u8         dump_fill_mkey[0x20];
 
 	u8         resd_lkey[0x20];
+
+	u8         null_mkey[0x20];
+
+	u8         reserved_at_a0[0x60];
 };
 
 struct mlx5_ifc_query_special_contexts_in_bits {
@@ -4689,12 +4774,11 @@ struct mlx5_ifc_page_fault_resume_in_bits {
 
 	u8         error[0x1];
 	u8         reserved_at_41[0x4];
-	u8         rdma[0x1];
-	u8         read_write[0x1];
-	u8         req_res[0x1];
-	u8         qpn[0x18];
+	u8         page_fault_type[0x3];
+	u8         wq_number[0x18];
 
-	u8         reserved_at_60[0x20];
+	u8         reserved_at_60[0x8];
+	u8         token[0x18];
 };
 
 struct mlx5_ifc_nop_out_bits {
@@ -7240,6 +7324,18 @@ struct mlx5_ifc_ppcnt_reg_bits {
 	union mlx5_ifc_eth_cntrs_grp_data_layout_auto_bits counter_set;
 };
 
+struct mlx5_ifc_mpcnt_reg_bits {
+	u8         reserved_at_0[0x8];
+	u8         pcie_index[0x8];
+	u8         reserved_at_10[0xa];
+	u8         grp[0x6];
+
+	u8         clr[0x1];
+	u8         reserved_at_21[0x1f];
+
+	union mlx5_ifc_pcie_cntrs_grp_data_layout_auto_bits counter_set;
+};
+
 struct mlx5_ifc_ppad_reg_bits {
 	u8         reserved_at_0[0x3];
 	u8         single_mac[0x1];
@@ -7469,6 +7565,63 @@ struct mlx5_ifc_peir_reg_bits {
 	u8         error_type[0x8];
 };
 
+struct mlx5_ifc_pcam_enhanced_features_bits {
+	u8         reserved_at_0[0x7e];
+
+	u8         ppcnt_discard_group[0x1];
+	u8         ppcnt_statistical_group[0x1];
+};
+
+struct mlx5_ifc_pcam_reg_bits {
+	u8         reserved_at_0[0x8];
+	u8         feature_group[0x8];
+	u8         reserved_at_10[0x8];
+	u8         access_reg_group[0x8];
+
+	u8         reserved_at_20[0x20];
+
+	union {
+		u8         reserved_at_0[0x80];
+	} port_access_reg_cap_mask;
+
+	u8         reserved_at_c0[0x80];
+
+	union {
+		struct mlx5_ifc_pcam_enhanced_features_bits enhanced_features;
+		u8         reserved_at_0[0x80];
+	} feature_cap_mask;
+
+	u8         reserved_at_1c0[0xc0];
+};
+
+struct mlx5_ifc_mcam_enhanced_features_bits {
+	u8         reserved_at_0[0x7f];
+
+	u8         pcie_performance_group[0x1];
+};
+
+struct mlx5_ifc_mcam_reg_bits {
+	u8         reserved_at_0[0x8];
+	u8         feature_group[0x8];
+	u8         reserved_at_10[0x8];
+	u8         access_reg_group[0x8];
+
+	u8         reserved_at_20[0x20];
+
+	union {
+		u8         reserved_at_0[0x80];
+	} mng_access_reg_cap_mask;
+
+	u8         reserved_at_c0[0x80];
+
+	union {
+		struct mlx5_ifc_mcam_enhanced_features_bits enhanced_features;
+		u8         reserved_at_0[0x80];
+	} mng_feature_cap_mask;
+
+	u8         reserved_at_1c0[0x80];
+};
+
 struct mlx5_ifc_pcap_reg_bits {
 	u8         reserved_at_0[0x8];
 	u8         local_port[0x8];
@@ -7813,6 +7966,60 @@ struct mlx5_ifc_initial_seg_bits {
 	u8         reserved_at_80a0[0x17fc0];
 };
 
+struct mlx5_ifc_mtpps_reg_bits {
+	u8         reserved_at_0[0xc];
+	u8         cap_number_of_pps_pins[0x4];
+	u8         reserved_at_10[0x4];
+	u8         cap_max_num_of_pps_in_pins[0x4];
+	u8         reserved_at_18[0x4];
+	u8         cap_max_num_of_pps_out_pins[0x4];
+
+	u8         reserved_at_20[0x24];
+	u8         cap_pin_3_mode[0x4];
+	u8         reserved_at_48[0x4];
+	u8         cap_pin_2_mode[0x4];
+	u8         reserved_at_50[0x4];
+	u8         cap_pin_1_mode[0x4];
+	u8         reserved_at_58[0x4];
+	u8         cap_pin_0_mode[0x4];
+
+	u8         reserved_at_60[0x4];
+	u8         cap_pin_7_mode[0x4];
+	u8         reserved_at_68[0x4];
+	u8         cap_pin_6_mode[0x4];
+	u8         reserved_at_70[0x4];
+	u8         cap_pin_5_mode[0x4];
+	u8         reserved_at_78[0x4];
+	u8         cap_pin_4_mode[0x4];
+
+	u8         reserved_at_80[0x80];
+
+	u8         enable[0x1];
+	u8         reserved_at_101[0xb];
+	u8         pattern[0x4];
+	u8         reserved_at_110[0x4];
+	u8         pin_mode[0x4];
+	u8         pin[0x8];
+
+	u8         reserved_at_120[0x20];
+
+	u8         time_stamp[0x40];
+
+	u8         out_pulse_duration[0x10];
+	u8         out_periodic_adjustment[0x10];
+
+	u8         reserved_at_1a0[0x60];
+};
+
+struct mlx5_ifc_mtppse_reg_bits {
+	u8         reserved_at_0[0x18];
+	u8         pin[0x8];
+	u8         event_arm[0x1];
+	u8         reserved_at_21[0x1b];
+	u8         event_generation_mode[0x4];
+	u8         reserved_at_40[0x40];
+};
+
 union mlx5_ifc_ports_control_registers_document_bits {
 	struct mlx5_ifc_bufferx_reg_bits bufferx_reg;
 	struct mlx5_ifc_eth_2819_cntrs_grp_data_layout_bits eth_2819_cntrs_grp_data_layout;
@@ -7845,6 +8052,7 @@ union mlx5_ifc_ports_control_registers_document_bits {
 	struct mlx5_ifc_pmtu_reg_bits pmtu_reg;
 	struct mlx5_ifc_ppad_reg_bits ppad_reg;
 	struct mlx5_ifc_ppcnt_reg_bits ppcnt_reg;
+	struct mlx5_ifc_mpcnt_reg_bits mpcnt_reg;
 	struct mlx5_ifc_pplm_reg_bits pplm_reg;
 	struct mlx5_ifc_pplr_reg_bits pplr_reg;
 	struct mlx5_ifc_ppsc_reg_bits ppsc_reg;
@@ -7857,6 +8065,8 @@ union mlx5_ifc_ports_control_registers_document_bits {
 	struct mlx5_ifc_pvlc_reg_bits pvlc_reg;
 	struct mlx5_ifc_slrg_reg_bits slrg_reg;
 	struct mlx5_ifc_sltp_reg_bits sltp_reg;
+	struct mlx5_ifc_mtpps_reg_bits mtpps_reg;
+	struct mlx5_ifc_mtppse_reg_bits mtppse_reg;
 	u8         reserved_at_0[0x60e0];
 };
 
diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h
index 0aacb2a7480d..3096370fe831 100644
--- a/include/linux/mlx5/qp.h
+++ b/include/linux/mlx5/qp.h
@@ -50,9 +50,6 @@
 #define MLX5_BSF_APPTAG_ESCAPE	0x1
 #define MLX5_BSF_APPREF_ESCAPE	0x2
 
-#define MLX5_QPN_BITS		24
-#define MLX5_QPN_MASK		((1 << MLX5_QPN_BITS) - 1)
-
 enum mlx5_qp_optpar {
 	MLX5_QP_OPTPAR_ALT_ADDR_PATH		= 1 << 0,
 	MLX5_QP_OPTPAR_RRE			= 1 << 1,
@@ -215,6 +212,7 @@ struct mlx5_wqe_ctrl_seg {
 #define MLX5_WQE_CTRL_OPCODE_MASK 0xff
 #define MLX5_WQE_CTRL_WQE_INDEX_MASK 0x00ffff00
 #define MLX5_WQE_CTRL_WQE_INDEX_SHIFT 8
+#define MLX5_WQE_AV_EXT 0x80000000
 
 enum {
 	MLX5_ETH_WQE_L3_INNER_CSUM      = 1 << 4,
@@ -223,14 +221,26 @@ enum {
 	MLX5_ETH_WQE_L4_CSUM            = 1 << 7,
 };
 
+enum {
+	MLX5_ETH_WQE_INSERT_VLAN        = 1 << 15,
+};
+
 struct mlx5_wqe_eth_seg {
 	u8              rsvd0[4];
 	u8              cs_flags;
 	u8              rsvd1;
 	__be16          mss;
 	__be32          rsvd2;
-	__be16          inline_hdr_sz;
-	u8              inline_hdr_start[2];
+	union {
+		struct {
+			__be16 sz;
+			u8     start[2];
+		} inline_hdr;
+		struct {
+			__be16 type;
+			__be16 vlan_tci;
+		} insert;
+	};
 };
 
 struct mlx5_wqe_xrc_seg {
@@ -245,6 +255,23 @@ struct mlx5_wqe_masked_atomic_seg {
 	__be64			compare_mask;
 };
 
+struct mlx5_base_av {
+	union {
+		struct {
+			__be32	qkey;
+			__be32	reserved;
+		} qkey;
+		__be64	dc_key;
+	} key;
+	__be32	dqp_dct;
+	u8	stat_rate_sl;
+	u8	fl_mlid;
+	union {
+		__be16	rlid;
+		__be16  udp_sport;
+	};
+};
+
 struct mlx5_av {
 	union {
 		struct {
@@ -292,10 +319,14 @@ struct mlx5_wqe_data_seg {
 struct mlx5_wqe_umr_ctrl_seg {
 	u8		flags;
 	u8		rsvd0[3];
-	__be16		klm_octowords;
-	__be16		bsf_octowords;
+	__be16		xlt_octowords;
+	union {
+		__be16	xlt_offset;
+		__be16	bsf_octowords;
+	};
 	__be64		mkey_mask;
-	u8		rsvd1[32];
+	__be32		xlt_offset_47_16;
+	u8		rsvd1[28];
 };
 
 struct mlx5_seg_set_psv {
@@ -389,6 +420,10 @@ struct mlx5_bsf {
 	struct mlx5_bsf_inl	m_inl;
 };
 
+struct mlx5_mtt {
+	__be64		ptag;
+};
+
 struct mlx5_klm {
 	__be32		bcount;
 	__be32		key;
@@ -410,46 +445,9 @@ struct mlx5_stride_block_ctrl_seg {
 	__be16		num_entries;
 };
 
-enum mlx5_pagefault_flags {
-	MLX5_PFAULT_REQUESTOR = 1 << 0,
-	MLX5_PFAULT_WRITE     = 1 << 1,
-	MLX5_PFAULT_RDMA      = 1 << 2,
-};
-
-/* Contains the details of a pagefault. */
-struct mlx5_pagefault {
-	u32			bytes_committed;
-	u8			event_subtype;
-	enum mlx5_pagefault_flags flags;
-	union {
-		/* Initiator or send message responder pagefault details. */
-		struct {
-			/* Received packet size, only valid for responders. */
-			u32	packet_size;
-			/*
-			 * WQE index. Refers to either the send queue or
-			 * receive queue, according to event_subtype.
-			 */
-			u16	wqe_index;
-		} wqe;
-		/* RDMA responder pagefault details */
-		struct {
-			u32	r_key;
-			/*
-			 * Received packet size, minimal size page fault
-			 * resolution required for forward progress.
-			 */
-			u32	packet_size;
-			u32	rdma_op_len;
-			u64	rdma_va;
-		} rdma;
-	};
-};
-
 struct mlx5_core_qp {
 	struct mlx5_core_rsc_common	common; /* must be first */
 	void (*event)		(struct mlx5_core_qp *, int);
-	void (*pfault_handler)(struct mlx5_core_qp *, struct mlx5_pagefault *);
 	int			qpn;
 	struct mlx5_rsc_debug	*dbg;
 	int			pid;
@@ -549,10 +547,6 @@ void mlx5_init_qp_table(struct mlx5_core_dev *dev);
 void mlx5_cleanup_qp_table(struct mlx5_core_dev *dev);
 int mlx5_debug_qp_add(struct mlx5_core_dev *dev, struct mlx5_core_qp *qp);
 void mlx5_debug_qp_remove(struct mlx5_core_dev *dev, struct mlx5_core_qp *qp);
-#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
-int mlx5_core_page_fault_resume(struct mlx5_core_dev *dev, u32 qpn,
-				u8 context, int error);
-#endif
 int mlx5_core_create_rq_tracked(struct mlx5_core_dev *dev, u32 *in, int inlen,
 				struct mlx5_core_qp *rq);
 void mlx5_core_destroy_rq_tracked(struct mlx5_core_dev *dev,
diff --git a/include/linux/mlx5/vport.h b/include/linux/mlx5/vport.h
index ec35157ea725..656c70b65dd2 100644
--- a/include/linux/mlx5/vport.h
+++ b/include/linux/mlx5/vport.h
@@ -51,6 +51,7 @@ int mlx5_query_nic_vport_mac_address(struct mlx5_core_dev *mdev,
 				     u16 vport, u8 *addr);
 int mlx5_query_nic_vport_min_inline(struct mlx5_core_dev *mdev,
 				    u16 vport, u8 *min_inline);
+void mlx5_query_min_inline(struct mlx5_core_dev *mdev, u8 *min_inline);
 int mlx5_modify_nic_vport_min_inline(struct mlx5_core_dev *mdev,
 				     u16 vport, u8 min_inline);
 int mlx5_modify_nic_vport_mac_address(struct mlx5_core_dev *dev,