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

Pull rdma updates from Doug Ledford:
 "This is the complete update for the rdma stack for this release cycle.

  Most of it is typical driver and core updates, but there is the
  entirely new VMWare pvrdma driver. You may have noticed that there
  were changes in DaveM's pull request to the bnxt Ethernet driver to
  support a RoCE RDMA driver. The bnxt_re driver was tentatively set to
  be pulled in this release cycle, but it simply wasn't ready in time
  and was dropped (a few review comments still to address, and some
  multi-arch build issues like prefetch() not working across all
  arches).

  Summary:

   - shared mlx5 updates with net stack (will drop out on merge if
     Dave's tree has already been merged)

   - driver updates: cxgb4, hfi1, hns-roce, i40iw, mlx4, mlx5, qedr, rxe

   - debug cleanups

   - new connection rejection helpers

   - SRP updates

   - various misc fixes

   - new paravirt driver from vmware"

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/dledford/rdma: (210 commits)
  IB: Add vmw_pvrdma driver
  IB/mlx4: fix improper return value
  IB/ocrdma: fix bad initialization
  infiniband: nes: return value of skb_linearize should be handled
  MAINTAINERS: Update Intel RDMA RNIC driver maintainers
  MAINTAINERS: Remove Mitesh Ahuja from emulex maintainers
  IB/core: fix unmap_sg argument
  qede: fix general protection fault may occur on probe
  IB/mthca: Replace pci_pool_alloc by pci_pool_zalloc
  mlx5, calc_sq_size(): Make a debug message more informative
  mlx5: Remove a set-but-not-used variable
  mlx5: Use { } instead of { 0 } to init struct
  IB/srp: Make writing the add_target sysfs attr interruptible
  IB/srp: Make mapping failures easier to debug
  IB/srp: Make login failures easier to debug
  IB/srp: Introduce a local variable in srp_add_one()
  IB/srp: Fix CONFIG_DYNAMIC_DEBUG=n build
  IB/multicast: Check ib_find_pkey() return value
  IPoIB: Avoid reading an uninitialized member variable
  IB/mad: Fix an array index check
  ...

9 files changed, 202 insertions, 42 deletions

diff --git a/include/rdma/ib_cm.h b/include/rdma/ib_cm.h
index 92a7d85917b4..b49258b16f4e 100644
--- a/include/rdma/ib_cm.h
+++ b/include/rdma/ib_cm.h
@@ -603,4 +603,10 @@ struct ib_cm_sidr_rep_param {
 int ib_send_cm_sidr_rep(struct ib_cm_id *cm_id,
 			struct ib_cm_sidr_rep_param *param);
 
+/**
+ * ibcm_reject_msg - return a pointer to a reject message string.
+ * @reason: Value returned in the REJECT event status field.
+ */
+const char *__attribute_const__ ibcm_reject_msg(int reason);
+
 #endif /* IB_CM_H */
diff --git a/include/rdma/ib_mad.h b/include/rdma/ib_mad.h
index c8a773ffe23b..981214b3790c 100644
--- a/include/rdma/ib_mad.h
+++ b/include/rdma/ib_mad.h
@@ -46,7 +46,7 @@
 #define IB_MGMT_BASE_VERSION			1
 #define OPA_MGMT_BASE_VERSION			0x80
 
-#define OPA_SMP_CLASS_VERSION			0x80
+#define OPA_SM_CLASS_VERSION			0x80
 
 /* Management classes */
 #define IB_MGMT_CLASS_SUBN_LID_ROUTED		0x01
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index 5ad43a487745..8029d2a51f14 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -1102,6 +1102,7 @@ enum ib_qp_attr_mask {
 	IB_QP_RESERVED2			= (1<<22),
 	IB_QP_RESERVED3			= (1<<23),
 	IB_QP_RESERVED4			= (1<<24),
+	IB_QP_RATE_LIMIT		= (1<<25),
 };
 
 enum ib_qp_state {
@@ -1151,6 +1152,7 @@ struct ib_qp_attr {
 	u8			rnr_retry;
 	u8			alt_port_num;
 	u8			alt_timeout;
+	u32			rate_limit;
 };
 
 enum ib_wr_opcode {
@@ -1592,17 +1594,19 @@ enum ib_flow_attr_type {
 /* Supported steering header types */
 enum ib_flow_spec_type {
 	/* L2 headers*/
-	IB_FLOW_SPEC_ETH	= 0x20,
-	IB_FLOW_SPEC_IB		= 0x22,
+	IB_FLOW_SPEC_ETH		= 0x20,
+	IB_FLOW_SPEC_IB			= 0x22,
 	/* L3 header*/
-	IB_FLOW_SPEC_IPV4	= 0x30,
-	IB_FLOW_SPEC_IPV6	= 0x31,
+	IB_FLOW_SPEC_IPV4		= 0x30,
+	IB_FLOW_SPEC_IPV6		= 0x31,
 	/* L4 headers*/
-	IB_FLOW_SPEC_TCP	= 0x40,
-	IB_FLOW_SPEC_UDP	= 0x41
+	IB_FLOW_SPEC_TCP		= 0x40,
+	IB_FLOW_SPEC_UDP		= 0x41,
+	IB_FLOW_SPEC_VXLAN_TUNNEL	= 0x50,
+	IB_FLOW_SPEC_INNER		= 0x100,
 };
 #define IB_FLOW_SPEC_LAYER_MASK	0xF0
-#define IB_FLOW_SPEC_SUPPORT_LAYERS 4
+#define IB_FLOW_SPEC_SUPPORT_LAYERS 8
 
 /* Flow steering rule priority is set according to it's domain.
  * Lower domain value means higher priority.
@@ -1630,7 +1634,7 @@ struct ib_flow_eth_filter {
 };
 
 struct ib_flow_spec_eth {
-	enum ib_flow_spec_type	  type;
+	u32			  type;
 	u16			  size;
 	struct ib_flow_eth_filter val;
 	struct ib_flow_eth_filter mask;
@@ -1644,7 +1648,7 @@ struct ib_flow_ib_filter {
 };
 
 struct ib_flow_spec_ib {
-	enum ib_flow_spec_type	 type;
+	u32			 type;
 	u16			 size;
 	struct ib_flow_ib_filter val;
 	struct ib_flow_ib_filter mask;
@@ -1669,7 +1673,7 @@ struct ib_flow_ipv4_filter {
 };
 
 struct ib_flow_spec_ipv4 {
-	enum ib_flow_spec_type	   type;
+	u32			   type;
 	u16			   size;
 	struct ib_flow_ipv4_filter val;
 	struct ib_flow_ipv4_filter mask;
@@ -1687,7 +1691,7 @@ struct ib_flow_ipv6_filter {
 };
 
 struct ib_flow_spec_ipv6 {
-	enum ib_flow_spec_type	   type;
+	u32			   type;
 	u16			   size;
 	struct ib_flow_ipv6_filter val;
 	struct ib_flow_ipv6_filter mask;
@@ -1701,15 +1705,30 @@ struct ib_flow_tcp_udp_filter {
 };
 
 struct ib_flow_spec_tcp_udp {
-	enum ib_flow_spec_type	      type;
+	u32			      type;
 	u16			      size;
 	struct ib_flow_tcp_udp_filter val;
 	struct ib_flow_tcp_udp_filter mask;
 };
 
+struct ib_flow_tunnel_filter {
+	__be32	tunnel_id;
+	u8	real_sz[0];
+};
+
+/* ib_flow_spec_tunnel describes the Vxlan tunnel
+ * the tunnel_id from val has the vni value
+ */
+struct ib_flow_spec_tunnel {
+	u32			      type;
+	u16			      size;
+	struct ib_flow_tunnel_filter  val;
+	struct ib_flow_tunnel_filter  mask;
+};
+
 union ib_flow_spec {
 	struct {
-		enum ib_flow_spec_type	type;
+		u32			type;
 		u16			size;
 	};
 	struct ib_flow_spec_eth		eth;
@@ -1717,6 +1736,7 @@ union ib_flow_spec {
 	struct ib_flow_spec_ipv4        ipv4;
 	struct ib_flow_spec_tcp_udp	tcp_udp;
 	struct ib_flow_spec_ipv6        ipv6;
+	struct ib_flow_spec_tunnel      tunnel;
 };
 
 struct ib_flow_attr {
@@ -1933,7 +1953,8 @@ struct ib_device {
 					       struct ib_udata *udata);
 	int                        (*dealloc_pd)(struct ib_pd *pd);
 	struct ib_ah *             (*create_ah)(struct ib_pd *pd,
-						struct ib_ah_attr *ah_attr);
+						struct ib_ah_attr *ah_attr,
+						struct ib_udata *udata);
 	int                        (*modify_ah)(struct ib_ah *ah,
 						struct ib_ah_attr *ah_attr);
 	int                        (*query_ah)(struct ib_ah *ah,
@@ -2581,6 +2602,24 @@ void ib_dealloc_pd(struct ib_pd *pd);
 struct ib_ah *ib_create_ah(struct ib_pd *pd, struct ib_ah_attr *ah_attr);
 
 /**
+ * ib_get_gids_from_rdma_hdr - Get sgid and dgid from GRH or IPv4 header
+ *   work completion.
+ * @hdr: the L3 header to parse
+ * @net_type: type of header to parse
+ * @sgid: place to store source gid
+ * @dgid: place to store destination gid
+ */
+int ib_get_gids_from_rdma_hdr(const union rdma_network_hdr *hdr,
+			      enum rdma_network_type net_type,
+			      union ib_gid *sgid, union ib_gid *dgid);
+
+/**
+ * ib_get_rdma_header_version - Get the header version
+ * @hdr: the L3 header to parse
+ */
+int ib_get_rdma_header_version(const union rdma_network_hdr *hdr);
+
+/**
  * ib_init_ah_from_wc - Initializes address handle attributes from a
  *   work completion.
  * @device: Device on which the received message arrived.
@@ -3357,4 +3396,7 @@ int ib_sg_to_pages(struct ib_mr *mr, struct scatterlist *sgl, int sg_nents,
 void ib_drain_rq(struct ib_qp *qp);
 void ib_drain_sq(struct ib_qp *qp);
 void ib_drain_qp(struct ib_qp *qp);
+
+int ib_resolve_eth_dmac(struct ib_device *device,
+			struct ib_ah_attr *ah_attr);
 #endif /* IB_VERBS_H */
diff --git a/include/rdma/iw_cm.h b/include/rdma/iw_cm.h
index 6d0065c322b7..5cd7701db148 100644
--- a/include/rdma/iw_cm.h
+++ b/include/rdma/iw_cm.h
@@ -253,4 +253,10 @@ int iw_cm_disconnect(struct iw_cm_id *cm_id, int abrupt);
 int iw_cm_init_qp_attr(struct iw_cm_id *cm_id, struct ib_qp_attr *qp_attr,
 		       int *qp_attr_mask);
 
+/**
+ * iwcm_reject_msg - return a pointer to a reject message string.
+ * @reason: Value returned in the REJECT event status field.
+ */
+const char *__attribute_const__ iwcm_reject_msg(int reason);
+
 #endif /* IW_CM_H */
diff --git a/include/rdma/opa_smi.h b/include/rdma/opa_smi.h
index 4a529ef47995..f7896117936e 100644
--- a/include/rdma/opa_smi.h
+++ b/include/rdma/opa_smi.h
@@ -44,8 +44,6 @@
 #define OPA_MAX_SLS				32
 #define OPA_MAX_SCS				32
 
-#define OPA_SMI_CLASS_VERSION			0x80
-
 #define OPA_LID_PERMISSIVE			cpu_to_be32(0xFFFFFFFF)
 
 struct opa_smp {
diff --git a/include/rdma/rdma_cm.h b/include/rdma/rdma_cm.h
index 81fb1d15e8bb..d3968b561f86 100644
--- a/include/rdma/rdma_cm.h
+++ b/include/rdma/rdma_cm.h
@@ -388,4 +388,29 @@ int rdma_set_afonly(struct rdma_cm_id *id, int afonly);
  */
 __be64 rdma_get_service_id(struct rdma_cm_id *id, struct sockaddr *addr);
 
+/**
+ * rdma_reject_msg - return a pointer to a reject message string.
+ * @id: Communication identifier that received the REJECT event.
+ * @reason: Value returned in the REJECT event status field.
+ */
+const char *__attribute_const__ rdma_reject_msg(struct rdma_cm_id *id,
+						int reason);
+/**
+ * rdma_is_consumer_reject - return true if the consumer rejected the connect
+ *                           request.
+ * @id: Communication identifier that received the REJECT event.
+ * @reason: Value returned in the REJECT event status field.
+ */
+bool rdma_is_consumer_reject(struct rdma_cm_id *id, int reason);
+
+/**
+ * rdma_consumer_reject_data - return the consumer reject private data and
+ *			       length, if any.
+ * @id: Communication identifier that received the REJECT event.
+ * @ev: RDMA CM reject event.
+ * @data_len: Pointer to the resulting length of the consumer data.
+ */
+const void *rdma_consumer_reject_data(struct rdma_cm_id *id,
+				      struct rdma_cm_event *ev, u8 *data_len);
+
 #endif /* RDMA_CM_H */
diff --git a/include/rdma/rdma_vt.h b/include/rdma/rdma_vt.h
index e31502107a58..861e23eaebda 100644
--- a/include/rdma/rdma_vt.h
+++ b/include/rdma/rdma_vt.h
@@ -185,6 +185,27 @@ struct rvt_driver_provided {
 	 * check_support() for details.
 	 */
 
+	/* hot path calldowns in a single cacheline */
+
+	/*
+	 * Give the driver a notice that there is send work to do. It is up to
+	 * the driver to generally push the packets out, this just queues the
+	 * work with the driver. There are two variants here. The no_lock
+	 * version requires the s_lock not to be held. The other assumes the
+	 * s_lock is held.
+	 */
+	void (*schedule_send)(struct rvt_qp *qp);
+	void (*schedule_send_no_lock)(struct rvt_qp *qp);
+
+	/* Driver specific work request checking */
+	int (*check_send_wqe)(struct rvt_qp *qp, struct rvt_swqe *wqe);
+
+	/*
+	 * Sometimes rdmavt needs to kick the driver's send progress. That is
+	 * done by this call back.
+	 */
+	void (*do_send)(struct rvt_qp *qp);
+
 	/* Passed to ib core registration. Callback to create syfs files */
 	int (*port_callback)(struct ib_device *, u8, struct kobject *);
 
@@ -223,22 +244,6 @@ struct rvt_driver_provided {
 	void (*notify_qp_reset)(struct rvt_qp *qp);
 
 	/*
-	 * Give the driver a notice that there is send work to do. It is up to
-	 * the driver to generally push the packets out, this just queues the
-	 * work with the driver. There are two variants here. The no_lock
-	 * version requires the s_lock not to be held. The other assumes the
-	 * s_lock is held.
-	 */
-	void (*schedule_send)(struct rvt_qp *qp);
-	void (*schedule_send_no_lock)(struct rvt_qp *qp);
-
-	/*
-	 * Sometimes rdmavt needs to kick the driver's send progress. That is
-	 * done by this call back.
-	 */
-	void (*do_send)(struct rvt_qp *qp);
-
-	/*
 	 * Get a path mtu from the driver based on qp attributes.
 	 */
 	int (*get_pmtu_from_attr)(struct rvt_dev_info *rdi, struct rvt_qp *qp,
@@ -324,9 +329,6 @@ struct rvt_driver_provided {
 	void (*modify_qp)(struct rvt_qp *qp, struct ib_qp_attr *attr,
 			  int attr_mask, struct ib_udata *udata);
 
-	/* Driver specific work request checking */
-	int (*check_send_wqe)(struct rvt_qp *qp, struct rvt_swqe *wqe);
-
 	/* Notify driver a mad agent has been created */
 	void (*notify_create_mad_agent)(struct rvt_dev_info *rdi, int port_idx);
 
@@ -355,12 +357,12 @@ struct rvt_dev_info {
 	/* post send table */
 	const struct rvt_operation_params *post_parms;
 
-	struct rvt_mregion __rcu *dma_mr;
-	struct rvt_lkey_table lkey_table;
-
 	/* Driver specific helper functions */
 	struct rvt_driver_provided driver_f;
 
+	struct rvt_mregion __rcu *dma_mr;
+	struct rvt_lkey_table lkey_table;
+
 	/* Internal use */
 	int n_pds_allocated;
 	spinlock_t n_pds_lock; /* Protect pd allocated count */
diff --git a/include/rdma/rdmavt_mr.h b/include/rdma/rdmavt_mr.h
index 6b3c6c8b6b77..de59de28b6a2 100644
--- a/include/rdma/rdmavt_mr.h
+++ b/include/rdma/rdmavt_mr.h
@@ -90,11 +90,15 @@ struct rvt_mregion {
 #define RVT_MAX_LKEY_TABLE_BITS 23
 
 struct rvt_lkey_table {
-	spinlock_t lock; /* protect changes in this struct */
-	u32 next;               /* next unused index (speeds search) */
-	u32 gen;                /* generation count */
+	/* read mostly fields */
 	u32 max;                /* size of the table */
+	u32 shift;              /* lkey/rkey shift */
 	struct rvt_mregion __rcu **table;
+	/* writeable fields */
+	/* protect changes in this struct */
+	spinlock_t lock ____cacheline_aligned_in_smp;
+	u32 next;               /* next unused index (speeds search) */
+	u32 gen;                /* generation count */
 };
 
 /*
diff --git a/include/rdma/rdmavt_qp.h b/include/rdma/rdmavt_qp.h
index 2c5183ef0243..f3dbd157ae5c 100644
--- a/include/rdma/rdmavt_qp.h
+++ b/include/rdma/rdmavt_qp.h
@@ -51,6 +51,7 @@
 #include <rdma/rdma_vt.h>
 #include <rdma/ib_pack.h>
 #include <rdma/ib_verbs.h>
+#include <rdma/rdmavt_cq.h>
 /*
  * Atomic bit definitions for r_aflags.
  */
@@ -485,6 +486,23 @@ static inline void rvt_put_qp(struct rvt_qp *qp)
 }
 
 /**
+ * rvt_put_swqe - drop mr refs held by swqe
+ * @wqe - the send wqe
+ *
+ * This drops any mr references held by the swqe
+ */
+static inline void rvt_put_swqe(struct rvt_swqe *wqe)
+{
+	int i;
+
+	for (i = 0; i < wqe->wr.num_sge; i++) {
+		struct rvt_sge *sge = &wqe->sg_list[i];
+
+		rvt_put_mr(sge->mr);
+	}
+}
+
+/**
  * rvt_qp_wqe_reserve - reserve operation
  * @qp - the rvt qp
  * @wqe - the send wqe
@@ -527,6 +545,65 @@ static inline void rvt_qp_wqe_unreserve(
 	}
 }
 
+extern const enum ib_wc_opcode ib_rvt_wc_opcode[];
+
+/**
+ * rvt_qp_swqe_complete() - insert send completion
+ * @qp - the qp
+ * @wqe - the send wqe
+ * @status - completion status
+ *
+ * Insert a send completion into the completion
+ * queue if the qp indicates it should be done.
+ *
+ * See IBTA 10.7.3.1 for info on completion
+ * control.
+ */
+static inline void rvt_qp_swqe_complete(
+	struct rvt_qp *qp,
+	struct rvt_swqe *wqe,
+	enum ib_wc_status status)
+{
+	if (unlikely(wqe->wr.send_flags & RVT_SEND_RESERVE_USED))
+		return;
+	if (!(qp->s_flags & RVT_S_SIGNAL_REQ_WR) ||
+	    (wqe->wr.send_flags & IB_SEND_SIGNALED) ||
+	     status != IB_WC_SUCCESS) {
+		struct ib_wc wc;
+
+		memset(&wc, 0, sizeof(wc));
+		wc.wr_id = wqe->wr.wr_id;
+		wc.status = status;
+		wc.opcode = ib_rvt_wc_opcode[wqe->wr.opcode];
+		wc.qp = &qp->ibqp;
+		wc.byte_len = wqe->length;
+		rvt_cq_enter(ibcq_to_rvtcq(qp->ibqp.send_cq), &wc,
+			     status != IB_WC_SUCCESS);
+	}
+}
+
+/**
+ * @qp - the qp pair
+ * @len - the length
+ *
+ * Perform a shift based mtu round up divide
+ */
+static inline u32 rvt_div_round_up_mtu(struct rvt_qp *qp, u32 len)
+{
+	return (len + qp->pmtu - 1) >> qp->log_pmtu;
+}
+
+/**
+ * @qp - the qp pair
+ * @len - the length
+ *
+ * Perform a shift based mtu divide
+ */
+static inline u32 rvt_div_mtu(struct rvt_qp *qp, u32 len)
+{
+	return len >> qp->log_pmtu;
+}
+
 extern const int  ib_rvt_state_ops[];
 
 struct rvt_dev_info;