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

Pull base rdma updates from Doug Ledford:
 "Round one of 4.8 code: while this is mostly normal, there is a new
  driver in here (the driver was hosted outside the kernel for several
  years and is actually a fairly mature and well coded driver).  It
  amounts to 13,000 of the 16,000 lines of added code in here.

  Summary:

   - Updates/fixes for iw_cxgb4 driver
   - Updates/fixes for mlx5 driver
   - Add flow steering and RSS API
   - Add hardware stats to mlx4 and mlx5 drivers
   - Add firmware version API for RDMA driver use
   - Add the rxe driver (this is a software RoCE driver that makes any
     Ethernet device a RoCE device)
   - Fixes for i40iw driver
   - Support for send only multicast joins in the cma layer
   - Other minor fixes"

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/dledford/rdma: (72 commits)
  Soft RoCE driver
  IB/core: Support for CMA multicast join flags
  IB/sa: Add cached attribute containing SM information to SA port
  IB/uverbs: Fix race between uverbs_close and remove_one
  IB/mthca: Clean up error unwind flow in mthca_reset()
  IB/mthca: NULL arg to pci_dev_put is OK
  IB/hfi1: NULL arg to sc_return_credits is OK
  IB/mlx4: Add diagnostic hardware counters
  net/mlx4: Query performance and diagnostics counters
  net/mlx4: Add diagnostic counters capability bit
  Use smaller 512 byte messages for portmapper messages
  IB/ipoib: Report SG feature regardless of HW UD CSUM capability
  IB/mlx4: Don't use GFP_ATOMIC for CQ resize struct
  IB/hfi1: Disable by default
  IB/rdmavt: Disable by default
  IB/mlx5: Fix port counter ID association to QP offset
  IB/mlx5: Fix iteration overrun in GSI qps
  i40iw: Add NULL check for puda buffer
  i40iw: Change dup_ack_thresh to u8
  i40iw: Remove unnecessary check for moving CQ head
  ...

3 files changed, 117 insertions, 2 deletions

diff --git a/include/rdma/ib_sa.h b/include/rdma/ib_sa.h
index 384041669489..5ee7aab95eb8 100644
--- a/include/rdma/ib_sa.h
+++ b/include/rdma/ib_sa.h
@@ -94,6 +94,19 @@ enum ib_sa_selector {
 	IB_SA_BEST = 3
 };
 
+/*
+ * There are 4 types of join states:
+ * FullMember, NonMember, SendOnlyNonMember, SendOnlyFullMember.
+ * The order corresponds to JoinState bits in MCMemberRecord.
+ */
+enum ib_sa_mc_join_states {
+	FULLMEMBER_JOIN,
+	NONMEMBER_JOIN,
+	SENDONLY_NONMEBER_JOIN,
+	SENDONLY_FULLMEMBER_JOIN,
+	NUM_JOIN_MEMBERSHIP_TYPES,
+};
+
 #define IB_SA_CAP_MASK2_SENDONLY_FULL_MEM_SUPPORT	BIT(12)
 
 /*
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index a8137dcf5a00..94a0bc5b5bdd 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -562,6 +562,7 @@ enum ib_event_type {
 	IB_EVENT_QP_LAST_WQE_REACHED,
 	IB_EVENT_CLIENT_REREGISTER,
 	IB_EVENT_GID_CHANGE,
+	IB_EVENT_WQ_FATAL,
 };
 
 const char *__attribute_const__ ib_event_msg(enum ib_event_type event);
@@ -572,6 +573,7 @@ struct ib_event {
 		struct ib_cq	*cq;
 		struct ib_qp	*qp;
 		struct ib_srq	*srq;
+		struct ib_wq	*wq;
 		u8		port_num;
 	} element;
 	enum ib_event_type	event;
@@ -1015,6 +1017,7 @@ struct ib_qp_init_attr {
 	 * Only needed for special QP types, or when using the RW API.
 	 */
 	u8			port_num;
+	struct ib_rwq_ind_table *rwq_ind_tbl;
 };
 
 struct ib_qp_open_attr {
@@ -1323,6 +1326,8 @@ struct ib_ucontext {
 	struct list_head	ah_list;
 	struct list_head	xrcd_list;
 	struct list_head	rule_list;
+	struct list_head	wq_list;
+	struct list_head	rwq_ind_tbl_list;
 	int			closing;
 
 	struct pid             *tgid;
@@ -1428,6 +1433,63 @@ struct ib_srq {
 	} ext;
 };
 
+enum ib_wq_type {
+	IB_WQT_RQ
+};
+
+enum ib_wq_state {
+	IB_WQS_RESET,
+	IB_WQS_RDY,
+	IB_WQS_ERR
+};
+
+struct ib_wq {
+	struct ib_device       *device;
+	struct ib_uobject      *uobject;
+	void		    *wq_context;
+	void		    (*event_handler)(struct ib_event *, void *);
+	struct ib_pd	       *pd;
+	struct ib_cq	       *cq;
+	u32		wq_num;
+	enum ib_wq_state       state;
+	enum ib_wq_type	wq_type;
+	atomic_t		usecnt;
+};
+
+struct ib_wq_init_attr {
+	void		       *wq_context;
+	enum ib_wq_type	wq_type;
+	u32		max_wr;
+	u32		max_sge;
+	struct	ib_cq	       *cq;
+	void		    (*event_handler)(struct ib_event *, void *);
+};
+
+enum ib_wq_attr_mask {
+	IB_WQ_STATE	= 1 << 0,
+	IB_WQ_CUR_STATE	= 1 << 1,
+};
+
+struct ib_wq_attr {
+	enum	ib_wq_state	wq_state;
+	enum	ib_wq_state	curr_wq_state;
+};
+
+struct ib_rwq_ind_table {
+	struct ib_device	*device;
+	struct ib_uobject      *uobject;
+	atomic_t		usecnt;
+	u32		ind_tbl_num;
+	u32		log_ind_tbl_size;
+	struct ib_wq	**ind_tbl;
+};
+
+struct ib_rwq_ind_table_init_attr {
+	u32		log_ind_tbl_size;
+	/* Each entry is a pointer to Receive Work Queue */
+	struct ib_wq	**ind_tbl;
+};
+
 struct ib_qp {
 	struct ib_device       *device;
 	struct ib_pd	       *pd;
@@ -1450,6 +1512,7 @@ struct ib_qp {
 	void		       *qp_context;
 	u32			qp_num;
 	enum ib_qp_type		qp_type;
+	struct ib_rwq_ind_table *rwq_ind_tbl;
 };
 
 struct ib_mr {
@@ -1506,6 +1569,7 @@ enum ib_flow_spec_type {
 	IB_FLOW_SPEC_IB		= 0x22,
 	/* L3 header*/
 	IB_FLOW_SPEC_IPV4	= 0x30,
+	IB_FLOW_SPEC_IPV6	= 0x31,
 	/* L4 headers*/
 	IB_FLOW_SPEC_TCP	= 0x40,
 	IB_FLOW_SPEC_UDP	= 0x41
@@ -1567,6 +1631,18 @@ struct ib_flow_spec_ipv4 {
 	struct ib_flow_ipv4_filter mask;
 };
 
+struct ib_flow_ipv6_filter {
+	u8	src_ip[16];
+	u8	dst_ip[16];
+};
+
+struct ib_flow_spec_ipv6 {
+	enum ib_flow_spec_type	   type;
+	u16			   size;
+	struct ib_flow_ipv6_filter val;
+	struct ib_flow_ipv6_filter mask;
+};
+
 struct ib_flow_tcp_udp_filter {
 	__be16	dst_port;
 	__be16	src_port;
@@ -1588,6 +1664,7 @@ union ib_flow_spec {
 	struct ib_flow_spec_ib		ib;
 	struct ib_flow_spec_ipv4        ipv4;
 	struct ib_flow_spec_tcp_udp	tcp_udp;
+	struct ib_flow_spec_ipv6        ipv6;
 };
 
 struct ib_flow_attr {
@@ -1921,7 +1998,18 @@ struct ib_device {
 						   struct ifla_vf_stats *stats);
 	int			   (*set_vf_guid)(struct ib_device *device, int vf, u8 port, u64 guid,
 						  int type);
-
+	struct ib_wq *		   (*create_wq)(struct ib_pd *pd,
+						struct ib_wq_init_attr *init_attr,
+						struct ib_udata *udata);
+	int			   (*destroy_wq)(struct ib_wq *wq);
+	int			   (*modify_wq)(struct ib_wq *wq,
+						struct ib_wq_attr *attr,
+						u32 wq_attr_mask,
+						struct ib_udata *udata);
+	struct ib_rwq_ind_table *  (*create_rwq_ind_table)(struct ib_device *device,
+							   struct ib_rwq_ind_table_init_attr *init_attr,
+							   struct ib_udata *udata);
+	int                        (*destroy_rwq_ind_table)(struct ib_rwq_ind_table *wq_ind_table);
 	struct ib_dma_mapping_ops   *dma_ops;
 
 	struct module               *owner;
@@ -1956,6 +2044,7 @@ struct ib_device {
 	 * in fast paths.
 	 */
 	int (*get_port_immutable)(struct ib_device *, u8, struct ib_port_immutable *);
+	void (*get_dev_fw_str)(struct ib_device *, char *str, size_t str_len);
 };
 
 struct ib_client {
@@ -1991,6 +2080,8 @@ struct ib_client {
 struct ib_device *ib_alloc_device(size_t size);
 void ib_dealloc_device(struct ib_device *device);
 
+void ib_get_device_fw_str(struct ib_device *device, char *str, size_t str_len);
+
 int ib_register_device(struct ib_device *device,
 		       int (*port_callback)(struct ib_device *,
 					    u8, struct kobject *));
@@ -3168,6 +3259,15 @@ int ib_check_mr_status(struct ib_mr *mr, u32 check_mask,
 struct net_device *ib_get_net_dev_by_params(struct ib_device *dev, u8 port,
 					    u16 pkey, const union ib_gid *gid,
 					    const struct sockaddr *addr);
+struct ib_wq *ib_create_wq(struct ib_pd *pd,
+			   struct ib_wq_init_attr *init_attr);
+int ib_destroy_wq(struct ib_wq *wq);
+int ib_modify_wq(struct ib_wq *wq, struct ib_wq_attr *attr,
+		 u32 wq_attr_mask);
+struct ib_rwq_ind_table *ib_create_rwq_ind_table(struct ib_device *device,
+						 struct ib_rwq_ind_table_init_attr*
+						 wq_ind_table_init_attr);
+int ib_destroy_rwq_ind_table(struct ib_rwq_ind_table *wq_ind_table);
 
 int ib_map_mr_sg(struct ib_mr *mr, struct scatterlist *sg, int sg_nents,
 		 unsigned int *sg_offset, unsigned int page_size);
diff --git a/include/rdma/rdma_cm.h b/include/rdma/rdma_cm.h
index afe44fde72a5..81fb1d15e8bb 100644
--- a/include/rdma/rdma_cm.h
+++ b/include/rdma/rdma_cm.h
@@ -333,11 +333,13 @@ int rdma_disconnect(struct rdma_cm_id *id);
  *   address.
  * @id: Communication identifier associated with the request.
  * @addr: Multicast address identifying the group to join.
+ * @join_state: Multicast JoinState bitmap requested by port.
+ *		Bitmap is based on IB_SA_MCMEMBER_REC_JOIN_STATE bits.
  * @context: User-defined context associated with the join request, returned
  * to the user through the private_data pointer in multicast events.
  */
 int rdma_join_multicast(struct rdma_cm_id *id, struct sockaddr *addr,
-			void *context);
+			u8 join_state, void *context);
 
 /**
  * rdma_leave_multicast - Leave the multicast group specified by the given