Merge tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma

Pull rdma updates from Jason Gunthorpe:
 "Usual collection of small improvements and fixes:

   - Bug fixes and minor improvments in efa, irdma, mlx4, mlx5, rxe,
     hf1, qib, ocrdma

   - bnxt_re support for MSN, which is a new retransmit logic

   - Initial mana support for RC qps

   - Use after free bug and cleanups in iwcm

   - Reduce resource usage in mlx5 when RDMA verbs features are not used

   - New verb to drain shared recieve queues, similar to normal recieve
     queues. This is necessary to allow ULPs a clean shutdown. Used in
     the iscsi rdma target

   - mlx5 support for more than 16 bits of doorbell indexes

   - Doorbell moderation support for bnxt_re

   - IB multi-plane support for mlx5

   - New EFA adaptor PCI IDs

   - RDMA_NAME_ASSIGN_TYPE_USER to hint to userspace that it shouldn't
     rename the device

   - A collection of hns bugs

   - Fix long standing bug in bnxt_re with incorrect endian handling of
     immediate data"

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma: (65 commits)
  IB/hfi1: Constify struct flag_table
  RDMA/mana_ib: Set correct device into ib
  bnxt_re: Fix imm_data endianness
  RDMA: Fix netdev tracker in ib_device_set_netdev
  RDMA/hns: Fix mbx timing out before CMD execution is completed
  RDMA/hns: Fix insufficient extend DB for VFs.
  RDMA/hns: Fix undifined behavior caused by invalid max_sge
  RDMA/hns: Fix shift-out-bounds when max_inline_data is 0
  RDMA/hns: Fix missing pagesize and alignment check in FRMR
  RDMA/hns: Fix unmatch exception handling when init eq table fails
  RDMA/hns: Fix soft lockup under heavy CEQE load
  RDMA/hns: Check atomic wr length
  RDMA/ocrdma: Don't inline statistics functions
  RDMA/core: Introduce "name_assign_type" for an IB device
  RDMA/qib: Fix truncation compilation warnings in qib_verbs.c
  RDMA/qib: Fix truncation compilation warnings in qib_init.c
  RDMA/efa: Add EFA 0xefa3 PCI ID
  RDMA/mlx5: Support per-plane port IB counters by querying PPCNT register
  net/mlx5: mlx5_ifc update for accessing ppcnt register of plane ports
  RDMA/mlx5: Add plane index support when querying PTYS registers
  ...

13 files changed, 163 insertions, 18 deletions

diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index da09bfaa7b81..ba875a619b97 100644
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -1467,6 +1467,7 @@ enum {
 	MLX5_PER_TRAFFIC_CLASS_CONGESTION_GROUP = 0x13,
 	MLX5_PHYSICAL_LAYER_STATISTICAL_GROUP = 0x16,
 	MLX5_INFINIBAND_PORT_COUNTERS_GROUP   = 0x20,
+	MLX5_INFINIBAND_EXTENDED_PORT_COUNTERS_GROUP = 0x21,
 };
 
 enum {
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 0d31f77396fc..a96438ded15f 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -917,6 +917,7 @@ struct mlx5_hca_vport_context {
 	u16			qkey_violation_counter;
 	u16			pkey_violation_counter;
 	bool			grh_required;
+	u8			num_plane;
 };
 
 #define STRUCT_FIELD(header, field) \
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index c176953edcf8..cab228cf51c6 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -793,7 +793,7 @@ struct mlx5_ifc_ads_bits {
 	u8         reserved_at_2[0xe];
 	u8         pkey_index[0x10];
 
-	u8         reserved_at_20[0x8];
+	u8         plane_index[0x8];
 	u8         grh[0x1];
 	u8         mlid[0x7];
 	u8         rlid[0x10];
@@ -1992,7 +1992,8 @@ struct mlx5_ifc_cmd_hca_cap_2_bits {
 	u8	   reserved_at_c0[0x8];
 	u8	   migration_multi_load[0x1];
 	u8	   migration_tracking_state[0x1];
-	u8	   reserved_at_ca[0x6];
+	u8	   multiplane_qp_ud[0x1];
+	u8	   reserved_at_cb[0x5];
 	u8	   migration_in_chunks[0x1];
 	u8	   reserved_at_d1[0x1];
 	u8	   sf_eq_usage[0x1];
@@ -2663,6 +2664,46 @@ struct mlx5_ifc_ib_port_cntrs_grp_data_layout_bits {
 	u8         port_xmit_wait[0x20];
 };
 
+struct mlx5_ifc_ib_ext_port_cntrs_grp_data_layout_bits {
+	u8         reserved_at_0[0x300];
+
+	u8         port_xmit_data_high[0x20];
+
+	u8         port_xmit_data_low[0x20];
+
+	u8         port_rcv_data_high[0x20];
+
+	u8         port_rcv_data_low[0x20];
+
+	u8         port_xmit_pkts_high[0x20];
+
+	u8         port_xmit_pkts_low[0x20];
+
+	u8         port_rcv_pkts_high[0x20];
+
+	u8         port_rcv_pkts_low[0x20];
+
+	u8         reserved_at_400[0x80];
+
+	u8         port_unicast_xmit_pkts_high[0x20];
+
+	u8         port_unicast_xmit_pkts_low[0x20];
+
+	u8         port_multicast_xmit_pkts_high[0x20];
+
+	u8         port_multicast_xmit_pkts_low[0x20];
+
+	u8         port_unicast_rcv_pkts_high[0x20];
+
+	u8         port_unicast_rcv_pkts_low[0x20];
+
+	u8         port_multicast_rcv_pkts_high[0x20];
+
+	u8         port_multicast_rcv_pkts_low[0x20];
+
+	u8         reserved_at_580[0x240];
+};
+
 struct mlx5_ifc_eth_per_tc_prio_grp_data_layout_bits {
 	u8         transmit_queue_high[0x20];
 
@@ -4185,7 +4226,8 @@ struct mlx5_ifc_hca_vport_context_bits {
 	u8         has_smi[0x1];
 	u8         has_raw[0x1];
 	u8         grh_required[0x1];
-	u8         reserved_at_104[0xc];
+	u8         reserved_at_104[0x4];
+	u8         num_port_plane[0x8];
 	u8         port_physical_state[0x4];
 	u8         vport_state_policy[0x4];
 	u8         port_state[0x4];
@@ -4554,6 +4596,7 @@ union mlx5_ifc_eth_cntrs_grp_data_layout_auto_bits {
 	struct mlx5_ifc_eth_per_tc_prio_grp_data_layout_bits eth_per_tc_prio_grp_data_layout;
 	struct mlx5_ifc_eth_per_tc_congest_prio_grp_data_layout_bits eth_per_tc_congest_prio_grp_data_layout;
 	struct mlx5_ifc_ib_port_cntrs_grp_data_layout_bits ib_port_cntrs_grp_data_layout;
+	struct mlx5_ifc_ib_ext_port_cntrs_grp_data_layout_bits ib_ext_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];
@@ -7705,7 +7748,7 @@ struct mlx5_ifc_mad_ifc_in_bits {
 	u8         op_mod[0x10];
 
 	u8         remote_lid[0x10];
-	u8         reserved_at_50[0x8];
+	u8         plane_index[0x8];
 	u8         port[0x8];
 
 	u8         reserved_at_60[0x20];
@@ -9634,7 +9677,9 @@ struct mlx5_ifc_ptys_reg_bits {
 	u8         an_disable_cap[0x1];
 	u8         reserved_at_3[0x5];
 	u8         local_port[0x8];
-	u8         reserved_at_10[0xd];
+	u8         reserved_at_10[0x8];
+	u8         plane_ind[0x4];
+	u8         reserved_at_1c[0x1];
 	u8         proto_mask[0x3];
 
 	u8         an_status[0x4];
@@ -9860,8 +9905,10 @@ struct mlx5_ifc_ppcnt_reg_bits {
 	u8         grp[0x6];
 
 	u8         clr[0x1];
-	u8         reserved_at_21[0x1c];
-	u8         prio_tc[0x3];
+	u8         reserved_at_21[0x13];
+	u8         plane_ind[0x4];
+	u8         reserved_at_38[0x3];
+	u8         prio_tc[0x5];
 
 	union mlx5_ifc_eth_cntrs_grp_data_layout_auto_bits counter_set;
 };
diff --git a/include/linux/mlx5/port.h b/include/linux/mlx5/port.h
index 26092c78a985..e68d42b8ce65 100644
--- a/include/linux/mlx5/port.h
+++ b/include/linux/mlx5/port.h
@@ -155,10 +155,11 @@ struct mlx5_port_eth_proto {
 
 int mlx5_set_port_caps(struct mlx5_core_dev *dev, u8 port_num, u32 caps);
 int mlx5_query_port_ptys(struct mlx5_core_dev *dev, u32 *ptys,
-			 int ptys_size, int proto_mask, u8 local_port);
+			 int ptys_size, int proto_mask,
+			 u8 local_port, u8 plane_index);
 
 int mlx5_query_ib_port_oper(struct mlx5_core_dev *dev, u16 *link_width_oper,
-			    u16 *proto_oper, u8 local_port);
+			    u16 *proto_oper, u8 local_port, u8 plane_index);
 void mlx5_toggle_port_link(struct mlx5_core_dev *dev);
 int mlx5_set_port_admin_status(struct mlx5_core_dev *dev,
 			       enum mlx5_port_status status);
diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h
index f0e55bf3ec8b..ad1ce650146c 100644
--- a/include/linux/mlx5/qp.h
+++ b/include/linux/mlx5/qp.h
@@ -576,9 +576,12 @@ static inline const char *mlx5_qp_state_str(int state)
 
 static inline int mlx5_get_qp_default_ts(struct mlx5_core_dev *dev)
 {
-	return !MLX5_CAP_ROCE(dev, qp_ts_format) ?
-		       MLX5_TIMESTAMP_FORMAT_FREE_RUNNING :
-		       MLX5_TIMESTAMP_FORMAT_DEFAULT;
+	u8 supported_ts_cap = mlx5_get_roce_state(dev) ?
+			      MLX5_CAP_ROCE(dev, qp_ts_format) :
+			      MLX5_CAP_GEN(dev, sq_ts_format);
+
+	return supported_ts_cap ? MLX5_TIMESTAMP_FORMAT_DEFAULT :
+	       MLX5_TIMESTAMP_FORMAT_FREE_RUNNING;
 }
 
 #endif /* MLX5_QP_H */
diff --git a/include/net/mana/gdma.h b/include/net/mana/gdma.h
index 83963d9e804d..de47fa533b15 100644
--- a/include/net/mana/gdma.h
+++ b/include/net/mana/gdma.h
@@ -60,6 +60,7 @@ enum gdma_eqe_type {
 	GDMA_EQE_HWC_INIT_DONE		= 131,
 	GDMA_EQE_HWC_SOC_RECONFIG	= 132,
 	GDMA_EQE_HWC_SOC_RECONFIG_DATA	= 133,
+	GDMA_EQE_RNIC_QP_FATAL		= 176,
 };
 
 enum {
diff --git a/include/net/mana/mana.h b/include/net/mana/mana.h
index e39b8676fe54..6439fd8b437b 100644
--- a/include/net/mana/mana.h
+++ b/include/net/mana/mana.h
@@ -798,4 +798,6 @@ void mana_destroy_wq_obj(struct mana_port_context *apc, u32 wq_type,
 int mana_cfg_vport(struct mana_port_context *apc, u32 protection_dom_id,
 		   u32 doorbell_pg_id);
 void mana_uncfg_vport(struct mana_port_context *apc);
+
+struct net_device *mana_get_primary_netdev_rcu(struct mana_context *ac, u32 port_index);
 #endif /* _MANA_H */
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index 477bf9dd5e71..6c5712ae559d 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -1788,6 +1788,7 @@ struct ib_qp {
 	struct list_head	rdma_mrs;
 	struct list_head	sig_mrs;
 	struct ib_srq	       *srq;
+	struct completion	srq_completion;
 	struct ib_xrcd	       *xrcd; /* XRC TGT QPs only */
 	struct list_head	xrcd_list;
 
@@ -1797,6 +1798,7 @@ struct ib_qp {
 	struct ib_qp           *real_qp;
 	struct ib_uqp_object   *uobject;
 	void                  (*event_handler)(struct ib_event *, void *);
+	void                  (*registered_event_handler)(struct ib_event *, void *);
 	void		       *qp_context;
 	/* sgid_attrs associated with the AV's */
 	const struct ib_gid_attr *av_sgid_attr;
@@ -2463,7 +2465,7 @@ struct ib_device_ops {
 			int qp_attr_mask, struct ib_qp_init_attr *qp_init_attr);
 	int (*destroy_qp)(struct ib_qp *qp, struct ib_udata *udata);
 	int (*create_cq)(struct ib_cq *cq, const struct ib_cq_init_attr *attr,
-			 struct ib_udata *udata);
+			 struct uverbs_attr_bundle *attrs);
 	int (*modify_cq)(struct ib_cq *cq, u16 cq_count, u16 cq_period);
 	int (*destroy_cq)(struct ib_cq *cq, struct ib_udata *udata);
 	int (*resize_cq)(struct ib_cq *cq, int cqe, struct ib_udata *udata);
@@ -2661,6 +2663,18 @@ struct ib_device_ops {
 	 */
 	int (*get_numa_node)(struct ib_device *dev);
 
+	/**
+	 * add_sub_dev - Add a sub IB device
+	 */
+	struct ib_device *(*add_sub_dev)(struct ib_device *parent,
+					 enum rdma_nl_dev_type type,
+					 const char *name);
+
+	/**
+	 * del_sub_dev - Delete a sub IB device
+	 */
+	void (*del_sub_dev)(struct ib_device *sub_dev);
+
 	DECLARE_RDMA_OBJ_SIZE(ib_ah);
 	DECLARE_RDMA_OBJ_SIZE(ib_counters);
 	DECLARE_RDMA_OBJ_SIZE(ib_cq);
@@ -2771,6 +2785,17 @@ struct ib_device {
 	char iw_ifname[IFNAMSIZ];
 	u32 iw_driver_flags;
 	u32 lag_flags;
+
+	/* A parent device has a list of sub-devices */
+	struct mutex subdev_lock;
+	struct list_head subdev_list_head;
+
+	/* A sub device has a type and a parent */
+	enum rdma_nl_dev_type type;
+	struct ib_device *parent;
+	struct list_head subdev_list;
+
+	enum rdma_nl_name_assign_type name_assign_type;
 };
 
 static inline void *rdma_zalloc_obj(struct ib_device *dev, size_t size,
@@ -4639,6 +4664,8 @@ static inline enum rdma_ah_attr_type rdma_ah_find_type(struct ib_device *dev,
 			return RDMA_AH_ATTR_TYPE_OPA;
 		return RDMA_AH_ATTR_TYPE_IB;
 	}
+	if (dev->type == RDMA_DEVICE_TYPE_SMI)
+		return RDMA_AH_ATTR_TYPE_IB;
 
 	return RDMA_AH_ATTR_TYPE_UNDEFINED;
 }
@@ -4820,4 +4847,32 @@ static inline u16 rdma_get_udp_sport(u32 fl, u32 lqpn, u32 rqpn)
 
 const struct ib_port_immutable*
 ib_port_immutable_read(struct ib_device *dev, unsigned int port);
+
+/** ib_add_sub_device - Add a sub IB device on an existing one
+ *
+ * @parent: The IB device that needs to add a sub device
+ * @type: The type of the new sub device
+ * @name: The name of the new sub device
+ *
+ *
+ * Return 0 on success, an error code otherwise
+ */
+int ib_add_sub_device(struct ib_device *parent,
+		      enum rdma_nl_dev_type type,
+		      const char *name);
+
+
+/** ib_del_sub_device_and_put - Delect an IB sub device while holding a 'get'
+ *
+ * @sub: The sub device that is going to be deleted
+ *
+ * Return 0 on success, an error code otherwise
+ */
+int ib_del_sub_device_and_put(struct ib_device *sub);
+
+static inline void ib_mark_name_assigned_by_user(struct ib_device *ibdev)
+{
+	ibdev->name_assign_type = RDMA_NAME_ASSIGN_TYPE_USER;
+}
+
 #endif /* IB_VERBS_H */
diff --git a/include/uapi/rdma/bnxt_re-abi.h b/include/uapi/rdma/bnxt_re-abi.h
index c0c34aca90ec..e61104f35d73 100644
--- a/include/uapi/rdma/bnxt_re-abi.h
+++ b/include/uapi/rdma/bnxt_re-abi.h
@@ -55,7 +55,7 @@ enum {
 	BNXT_RE_UCNTX_CMASK_WC_DPI_ENABLED = 0x04ULL,
 	BNXT_RE_UCNTX_CMASK_DBR_PACING_ENABLED = 0x08ULL,
 	BNXT_RE_UCNTX_CMASK_POW2_DISABLED = 0x10ULL,
-	BNXT_RE_COMP_MASK_UCNTX_HW_RETX_ENABLED = 0x40,
+	BNXT_RE_UCNTX_CMASK_MSN_TABLE_ENABLED = 0x40,
 };
 
 enum bnxt_re_wqe_mode {
diff --git a/include/uapi/rdma/ib_user_ioctl_cmds.h b/include/uapi/rdma/ib_user_ioctl_cmds.h
index dafc7ebe545b..ec719053aab9 100644
--- a/include/uapi/rdma/ib_user_ioctl_cmds.h
+++ b/include/uapi/rdma/ib_user_ioctl_cmds.h
@@ -37,9 +37,6 @@
 #define UVERBS_ID_NS_MASK 0xF000
 #define UVERBS_ID_NS_SHIFT 12
 
-#define UVERBS_UDATA_DRIVER_DATA_NS	1
-#define UVERBS_UDATA_DRIVER_DATA_FLAG	(1UL << UVERBS_ID_NS_SHIFT)
-
 enum uverbs_default_objects {
 	UVERBS_OBJECT_DEVICE, /* No instances of DEVICE are allowed */
 	UVERBS_OBJECT_PD,
@@ -61,8 +58,10 @@ enum uverbs_default_objects {
 };
 
 enum {
-	UVERBS_ATTR_UHW_IN = UVERBS_UDATA_DRIVER_DATA_FLAG,
+	UVERBS_ID_DRIVER_NS = 1UL << UVERBS_ID_NS_SHIFT,
+	UVERBS_ATTR_UHW_IN = UVERBS_ID_DRIVER_NS,
 	UVERBS_ATTR_UHW_OUT,
+	UVERBS_ID_DRIVER_NS_WITH_UHW,
 };
 
 enum uverbs_methods_device {
diff --git a/include/uapi/rdma/mana-abi.h b/include/uapi/rdma/mana-abi.h
index 2c41cc315218..45c2df619f07 100644
--- a/include/uapi/rdma/mana-abi.h
+++ b/include/uapi/rdma/mana-abi.h
@@ -45,6 +45,15 @@ struct mana_ib_create_qp_resp {
 	__u32 reserved;
 };
 
+struct mana_ib_create_rc_qp {
+	__aligned_u64 queue_buf[4];
+	__u32 queue_size[4];
+};
+
+struct mana_ib_create_rc_qp_resp {
+	__u32 queue_id[4];
+};
+
 struct mana_ib_create_wq {
 	__aligned_u64 wq_buf_addr;
 	__u32 wq_buf_size;
diff --git a/include/uapi/rdma/mlx5_user_ioctl_cmds.h b/include/uapi/rdma/mlx5_user_ioctl_cmds.h
index 595edad03dfe..5b74d6534899 100644
--- a/include/uapi/rdma/mlx5_user_ioctl_cmds.h
+++ b/include/uapi/rdma/mlx5_user_ioctl_cmds.h
@@ -270,6 +270,10 @@ enum mlx5_ib_device_query_context_attrs {
 	MLX5_IB_ATTR_QUERY_CONTEXT_RESP_UCTX = (1U << UVERBS_ID_NS_SHIFT),
 };
 
+enum mlx5_ib_create_cq_attrs {
+	MLX5_IB_ATTR_CREATE_CQ_UAR_INDEX = UVERBS_ID_DRIVER_NS_WITH_UHW,
+};
+
 #define MLX5_IB_DW_MATCH_PARAM 0xA0
 
 struct mlx5_ib_match_params {
diff --git a/include/uapi/rdma/rdma_netlink.h b/include/uapi/rdma/rdma_netlink.h
index a214fc259f28..2f37568f5556 100644
--- a/include/uapi/rdma/rdma_netlink.h
+++ b/include/uapi/rdma/rdma_netlink.h
@@ -301,6 +301,10 @@ enum rdma_nldev_command {
 
 	RDMA_NLDEV_CMD_RES_SRQ_GET_RAW,
 
+	RDMA_NLDEV_CMD_NEWDEV,
+
+	RDMA_NLDEV_CMD_DELDEV,
+
 	RDMA_NLDEV_NUM_OPS
 };
 
@@ -564,6 +568,12 @@ enum rdma_nldev_attr {
 	 */
 	RDMA_NLDEV_ATTR_RES_SUBTYPE,		/* string */
 
+	RDMA_NLDEV_ATTR_DEV_TYPE,		/* u8 */
+
+	RDMA_NLDEV_ATTR_PARENT_NAME,		/* string */
+
+	RDMA_NLDEV_ATTR_NAME_ASSIGN_TYPE,	/* u8 */
+
 	/*
 	 * Always the end
 	 */
@@ -602,4 +612,16 @@ enum rdma_nl_counter_mask {
 	RDMA_COUNTER_MASK_QP_TYPE = 1,
 	RDMA_COUNTER_MASK_PID = 1 << 1,
 };
+
+/* Supported rdma device types. */
+enum rdma_nl_dev_type {
+	RDMA_DEVICE_TYPE_SMI = 1,
+};
+
+/* RDMA device name assignment types */
+enum rdma_nl_name_assign_type {
+	RDMA_NAME_ASSIGN_TYPE_UNKNOWN = 0,
+	RDMA_NAME_ASSIGN_TYPE_USER = 1, /* Provided by user-space */
+};
+
 #endif /* _UAPI_RDMA_NETLINK_H */