2 files changed, 318 insertions, 2 deletions

diff --git a/sys/ofed/include/rdma/ib_mad.h b/sys/ofed/include/rdma/ib_mad.h
index 3d81b90cc315..1a7fb1ae564c 100644
--- a/sys/ofed/include/rdma/ib_mad.h
+++ b/sys/ofed/include/rdma/ib_mad.h
@@ -134,6 +134,7 @@ enum {
 	IB_MGMT_SA_DATA = 200,
 	IB_MGMT_DEVICE_HDR = 64,
 	IB_MGMT_DEVICE_DATA = 192,
+	IB_MGMT_MAD_SIZE = IB_MGMT_MAD_HDR + IB_MGMT_MAD_DATA,
 };
 
 struct ib_mad_hdr {
diff --git a/sys/ofed/include/rdma/ib_verbs.h b/sys/ofed/include/rdma/ib_verbs.h
index 21fe2ffdb3bb..8363b095b232 100644
--- a/sys/ofed/include/rdma/ib_verbs.h
+++ b/sys/ofed/include/rdma/ib_verbs.h
@@ -348,6 +348,56 @@ union rdma_protocol_stats {
 	struct iw_protocol_stats	iw;
 };
 
+/* Define bits for the various functionality this port needs to be supported by
+ * the core.
+ */
+/* Management                           0x00000FFF */
+#define RDMA_CORE_CAP_IB_MAD            0x00000001
+#define RDMA_CORE_CAP_IB_SMI            0x00000002
+#define RDMA_CORE_CAP_IB_CM             0x00000004
+#define RDMA_CORE_CAP_IW_CM             0x00000008
+#define RDMA_CORE_CAP_IB_SA             0x00000010
+#define RDMA_CORE_CAP_OPA_MAD           0x00000020
+
+/* Address format                       0x000FF000 */
+#define RDMA_CORE_CAP_AF_IB             0x00001000
+#define RDMA_CORE_CAP_ETH_AH            0x00002000
+#define RDMA_CORE_CAP_OPA_AH            0x00004000
+
+/* Protocol                             0xFFF00000 */
+#define RDMA_CORE_CAP_PROT_IB           0x00100000
+#define RDMA_CORE_CAP_PROT_ROCE         0x00200000
+#define RDMA_CORE_CAP_PROT_IWARP        0x00400000
+#define RDMA_CORE_CAP_PROT_ROCE_UDP_ENCAP 0x00800000
+#define RDMA_CORE_CAP_PROT_RAW_PACKET   0x01000000
+#define RDMA_CORE_CAP_PROT_USNIC        0x02000000
+
+#define RDMA_CORE_PORT_IBA_IB          (RDMA_CORE_CAP_PROT_IB  \
+					| RDMA_CORE_CAP_IB_MAD \
+					| RDMA_CORE_CAP_IB_SMI \
+					| RDMA_CORE_CAP_IB_CM  \
+					| RDMA_CORE_CAP_IB_SA  \
+					| RDMA_CORE_CAP_AF_IB)
+#define RDMA_CORE_PORT_IBA_ROCE        (RDMA_CORE_CAP_PROT_ROCE \
+					| RDMA_CORE_CAP_IB_MAD  \
+					| RDMA_CORE_CAP_IB_CM   \
+					| RDMA_CORE_CAP_AF_IB   \
+					| RDMA_CORE_CAP_ETH_AH)
+#define RDMA_CORE_PORT_IBA_ROCE_UDP_ENCAP			\
+					(RDMA_CORE_CAP_PROT_ROCE_UDP_ENCAP \
+					| RDMA_CORE_CAP_IB_MAD  \
+					| RDMA_CORE_CAP_IB_CM   \
+					| RDMA_CORE_CAP_AF_IB   \
+					| RDMA_CORE_CAP_ETH_AH)
+#define RDMA_CORE_PORT_IWARP           (RDMA_CORE_CAP_PROT_IWARP \
+					| RDMA_CORE_CAP_IW_CM)
+#define RDMA_CORE_PORT_INTEL_OPA       (RDMA_CORE_PORT_IBA_IB  \
+					| RDMA_CORE_CAP_OPA_MAD)
+
+#define RDMA_CORE_PORT_RAW_PACKET	(RDMA_CORE_CAP_PROT_RAW_PACKET)
+
+#define RDMA_CORE_PORT_USNIC		(RDMA_CORE_CAP_PROT_USNIC)
+
 struct ib_port_attr {
 	enum ib_port_state	state;
 	enum ib_mtu		max_mtu;
@@ -1623,6 +1673,14 @@ struct ib_dma_mapping_ops {
 };
 
 struct iw_cm_verbs;
+
+struct ib_port_immutable {
+	int                           pkey_tbl_len;
+	int                           gid_tbl_len;
+	u32                           core_cap_flags;
+	u32                           max_mad_size;
+};
+
 struct ib_exp_device_attr;
 struct ib_exp_qp_init_attr;
 
@@ -1639,8 +1697,10 @@ struct ib_device {
 	struct list_head              client_data_list;
 
 	struct ib_cache               cache;
-	int                          *pkey_tbl_len;
-	int                          *gid_tbl_len;
+	/**
+	 * port_immutable is indexed by port number
+	 */
+	struct ib_port_immutable     *port_immutable;
 
 	int			      num_comp_vectors;
 
@@ -1845,6 +1905,15 @@ struct ib_device {
 	u32			     cmd_n;
 	spinlock_t		     cmd_perf_lock;
 
+
+	/**
+	 * The following mandatory functions are used only at device
+	 * registration.  Keep functions such as these at the end of this
+	 * structure to avoid cache line misses when accessing struct ib_device
+	 * in fast paths.
+	 */
+	int (*get_port_immutable)(struct ib_device *, u8, struct ib_port_immutable *);
+
 	/*
 	 * Experimental data and functions
 	 */
@@ -1928,6 +1997,252 @@ int ib_query_port(struct ib_device *device,
 enum rdma_link_layer rdma_port_get_link_layer(struct ib_device *device,
 					       u8 port_num);
 
+static inline bool rdma_protocol_ib(const struct ib_device *device, u8 port_num)
+{
+	return device->port_immutable[port_num].core_cap_flags & RDMA_CORE_CAP_PROT_IB;
+}
+
+static inline bool rdma_protocol_roce(const struct ib_device *device, u8 port_num)
+{
+	return device->port_immutable[port_num].core_cap_flags &
+		(RDMA_CORE_CAP_PROT_ROCE | RDMA_CORE_CAP_PROT_ROCE_UDP_ENCAP);
+}
+
+static inline bool rdma_protocol_roce_udp_encap(const struct ib_device *device, u8 port_num)
+{
+	return device->port_immutable[port_num].core_cap_flags & RDMA_CORE_CAP_PROT_ROCE_UDP_ENCAP;
+}
+
+static inline bool rdma_protocol_roce_eth_encap(const struct ib_device *device, u8 port_num)
+{
+	return device->port_immutable[port_num].core_cap_flags & RDMA_CORE_CAP_PROT_ROCE;
+}
+
+static inline bool rdma_protocol_iwarp(const struct ib_device *device, u8 port_num)
+{
+	return device->port_immutable[port_num].core_cap_flags & RDMA_CORE_CAP_PROT_IWARP;
+}
+
+static inline bool rdma_ib_or_roce(const struct ib_device *device, u8 port_num)
+{
+	return rdma_protocol_ib(device, port_num) ||
+		rdma_protocol_roce(device, port_num);
+}
+
+/**
+ * rdma_cap_ib_mad - Check if the port of a device supports Infiniband
+ * Management Datagrams.
+ * @device: Device to check
+ * @port_num: Port number to check
+ *
+ * Management Datagrams (MAD) are a required part of the InfiniBand
+ * specification and are supported on all InfiniBand devices.  A slightly
+ * extended version are also supported on OPA interfaces.
+ *
+ * Return: true if the port supports sending/receiving of MAD packets.
+ */
+static inline bool rdma_cap_ib_mad(const struct ib_device *device, u8 port_num)
+{
+	return device->port_immutable[port_num].core_cap_flags & RDMA_CORE_CAP_IB_MAD;
+}
+
+/**
+ * rdma_cap_opa_mad - Check if the port of device provides support for OPA
+ * Management Datagrams.
+ * @device: Device to check
+ * @port_num: Port number to check
+ *
+ * Intel OmniPath devices extend and/or replace the InfiniBand Management
+ * datagrams with their own versions.  These OPA MADs share many but not all of
+ * the characteristics of InfiniBand MADs.
+ *
+ * OPA MADs differ in the following ways:
+ *
+ *    1) MADs are variable size up to 2K
+ *       IBTA defined MADs remain fixed at 256 bytes
+ *    2) OPA SMPs must carry valid PKeys
+ *    3) OPA SMP packets are a different format
+ *
+ * Return: true if the port supports OPA MAD packet formats.
+ */
+static inline bool rdma_cap_opa_mad(struct ib_device *device, u8 port_num)
+{
+	return (device->port_immutable[port_num].core_cap_flags & RDMA_CORE_CAP_OPA_MAD)
+		== RDMA_CORE_CAP_OPA_MAD;
+}
+
+/**
+ * rdma_cap_ib_smi - Check if the port of a device provides an Infiniband
+ * Subnet Management Agent (SMA) on the Subnet Management Interface (SMI).
+ * @device: Device to check
+ * @port_num: Port number to check
+ *
+ * Each InfiniBand node is required to provide a Subnet Management Agent
+ * that the subnet manager can access.  Prior to the fabric being fully
+ * configured by the subnet manager, the SMA is accessed via a well known
+ * interface called the Subnet Management Interface (SMI).  This interface
+ * uses directed route packets to communicate with the SM to get around the
+ * chicken and egg problem of the SM needing to know what's on the fabric
+ * in order to configure the fabric, and needing to configure the fabric in
+ * order to send packets to the devices on the fabric.  These directed
+ * route packets do not need the fabric fully configured in order to reach
+ * their destination.  The SMI is the only method allowed to send
+ * directed route packets on an InfiniBand fabric.
+ *
+ * Return: true if the port provides an SMI.
+ */
+static inline bool rdma_cap_ib_smi(const struct ib_device *device, u8 port_num)
+{
+	return device->port_immutable[port_num].core_cap_flags & RDMA_CORE_CAP_IB_SMI;
+}
+
+/**
+ * rdma_cap_ib_cm - Check if the port of device has the capability Infiniband
+ * Communication Manager.
+ * @device: Device to check
+ * @port_num: Port number to check
+ *
+ * The InfiniBand Communication Manager is one of many pre-defined General
+ * Service Agents (GSA) that are accessed via the General Service
+ * Interface (GSI).  It's role is to facilitate establishment of connections
+ * between nodes as well as other management related tasks for established
+ * connections.
+ *
+ * Return: true if the port supports an IB CM (this does not guarantee that
+ * a CM is actually running however).
+ */
+static inline bool rdma_cap_ib_cm(const struct ib_device *device, u8 port_num)
+{
+	return device->port_immutable[port_num].core_cap_flags & RDMA_CORE_CAP_IB_CM;
+}
+
+/**
+ * rdma_cap_iw_cm - Check if the port of device has the capability IWARP
+ * Communication Manager.
+ * @device: Device to check
+ * @port_num: Port number to check
+ *
+ * Similar to above, but specific to iWARP connections which have a different
+ * managment protocol than InfiniBand.
+ *
+ * Return: true if the port supports an iWARP CM (this does not guarantee that
+ * a CM is actually running however).
+ */
+static inline bool rdma_cap_iw_cm(const struct ib_device *device, u8 port_num)
+{
+	return device->port_immutable[port_num].core_cap_flags & RDMA_CORE_CAP_IW_CM;
+}
+
+/**
+ * rdma_cap_ib_sa - Check if the port of device has the capability Infiniband
+ * Subnet Administration.
+ * @device: Device to check
+ * @port_num: Port number to check
+ *
+ * An InfiniBand Subnet Administration (SA) service is a pre-defined General
+ * Service Agent (GSA) provided by the Subnet Manager (SM).  On InfiniBand
+ * fabrics, devices should resolve routes to other hosts by contacting the
+ * SA to query the proper route.
+ *
+ * Return: true if the port should act as a client to the fabric Subnet
+ * Administration interface.  This does not imply that the SA service is
+ * running locally.
+ */
+static inline bool rdma_cap_ib_sa(const struct ib_device *device, u8 port_num)
+{
+	return device->port_immutable[port_num].core_cap_flags & RDMA_CORE_CAP_IB_SA;
+}
+
+/**
+ * rdma_cap_ib_mcast - Check if the port of device has the capability Infiniband
+ * Multicast.
+ * @device: Device to check
+ * @port_num: Port number to check
+ *
+ * InfiniBand multicast registration is more complex than normal IPv4 or
+ * IPv6 multicast registration.  Each Host Channel Adapter must register
+ * with the Subnet Manager when it wishes to join a multicast group.  It
+ * should do so only once regardless of how many queue pairs it subscribes
+ * to this group.  And it should leave the group only after all queue pairs
+ * attached to the group have been detached.
+ *
+ * Return: true if the port must undertake the additional adminstrative
+ * overhead of registering/unregistering with the SM and tracking of the
+ * total number of queue pairs attached to the multicast group.
+ */
+static inline bool rdma_cap_ib_mcast(const struct ib_device *device, u8 port_num)
+{
+	return rdma_cap_ib_sa(device, port_num);
+}
+
+/**
+ * rdma_cap_af_ib - Check if the port of device has the capability
+ * Native Infiniband Address.
+ * @device: Device to check
+ * @port_num: Port number to check
+ *
+ * InfiniBand addressing uses a port's GUID + Subnet Prefix to make a default
+ * GID.  RoCE uses a different mechanism, but still generates a GID via
+ * a prescribed mechanism and port specific data.
+ *
+ * Return: true if the port uses a GID address to identify devices on the
+ * network.
+ */
+static inline bool rdma_cap_af_ib(const struct ib_device *device, u8 port_num)
+{
+	return device->port_immutable[port_num].core_cap_flags & RDMA_CORE_CAP_AF_IB;
+}
+
+/**
+ * rdma_cap_eth_ah - Check if the port of device has the capability
+ * Ethernet Address Handle.
+ * @device: Device to check
+ * @port_num: Port number to check
+ *
+ * RoCE is InfiniBand over Ethernet, and it uses a well defined technique
+ * to fabricate GIDs over Ethernet/IP specific addresses native to the
+ * port.  Normally, packet headers are generated by the sending host
+ * adapter, but when sending connectionless datagrams, we must manually
+ * inject the proper headers for the fabric we are communicating over.
+ *
+ * Return: true if we are running as a RoCE port and must force the
+ * addition of a Global Route Header built from our Ethernet Address
+ * Handle into our header list for connectionless packets.
+ */
+static inline bool rdma_cap_eth_ah(const struct ib_device *device, u8 port_num)
+{
+	return device->port_immutable[port_num].core_cap_flags & RDMA_CORE_CAP_ETH_AH;
+}
+
+/**
+ * rdma_max_mad_size - Return the max MAD size required by this RDMA Port.
+ *
+ * @device: Device
+ * @port_num: Port number
+ *
+ * This MAD size includes the MAD headers and MAD payload.  No other headers
+ * are included.
+ *
+ * Return the max MAD size required by the Port.  Will return 0 if the port
+ * does not support MADs
+ */
+static inline size_t rdma_max_mad_size(const struct ib_device *device, u8 port_num)
+{
+	return device->port_immutable[port_num].max_mad_size;
+}
+
+/*
+ * Check if the device supports READ W/ INVALIDATE.
+ */
+static inline bool rdma_cap_read_inv(struct ib_device *dev, u32 port_num)
+{
+	/*
+	 * iWarp drivers must support READ W/ INVALIDATE.  No other protocol
+	 * has support for it yet.
+	 */
+	return rdma_protocol_iwarp(dev, port_num);
+}
+
 int ib_query_gid(struct ib_device *device,
 		 u8 port_num, int index, union ib_gid *gid);