Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/roland/infiniband

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/roland/infiniband: (63 commits)
  IB/qib: clean up properly if pci_set_consistent_dma_mask() fails
  IB/qib: Allow driver to load if PCIe AER fails
  IB/qib: Fix uninitialized pointer if CONFIG_PCI_MSI not set
  IB/qib: Fix extra log level in qib_early_err()
  RDMA/cxgb4: Remove unnecessary KERN_<level> use
  RDMA/cxgb3: Remove unnecessary KERN_<level> use
  IB/core: Add link layer type information to sysfs
  IB/mlx4: Add VLAN support for IBoE
  IB/core: Add VLAN support for IBoE
  IB/mlx4: Add support for IBoE
  mlx4_en: Change multicast promiscuous mode to support IBoE
  mlx4_core: Update data structures and constants for IBoE
  mlx4_core: Allow protocol drivers to find corresponding interfaces
  IB/uverbs: Return link layer type to userspace for query port operation
  IB/srp: Sync buffer before posting send
  IB/srp: Use list_first_entry()
  IB/srp: Reduce number of BUSY conditions
  IB/srp: Eliminate two forward declarations
  IB/mlx4: Signal node desc changes to SM by using FW to generate trap 144
  IB: Replace EXTRA_CFLAGS with ccflags-y
  ...

9 files changed, 266 insertions, 14 deletions

diff --git a/include/linux/mlx4/cmd.h b/include/linux/mlx4/cmd.h
index 78a1b96..9a18667 100644
--- a/include/linux/mlx4/cmd.h
+++ b/include/linux/mlx4/cmd.h
@@ -58,6 +58,7 @@ enum {
 	MLX4_CMD_SENSE_PORT	 = 0x4d,
 	MLX4_CMD_HW_HEALTH_CHECK = 0x50,
 	MLX4_CMD_SET_PORT	 = 0xc,
+	MLX4_CMD_SET_NODE	 = 0x5a,
 	MLX4_CMD_ACCESS_DDR	 = 0x2e,
 	MLX4_CMD_MAP_ICM	 = 0xffa,
 	MLX4_CMD_UNMAP_ICM	 = 0xff9,
@@ -141,6 +142,7 @@ enum {
 	MLX4_SET_PORT_MAC_TABLE = 0x2,
 	MLX4_SET_PORT_VLAN_TABLE = 0x3,
 	MLX4_SET_PORT_PRIO_MAP  = 0x4,
+	MLX4_SET_PORT_GID_TABLE = 0x5,
 };
 
 struct mlx4_dev;
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index 7338654..a7b15bc 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -67,7 +67,8 @@ enum {
 	MLX4_DEV_CAP_FLAG_ATOMIC	= 1 << 18,
 	MLX4_DEV_CAP_FLAG_RAW_MCAST	= 1 << 19,
 	MLX4_DEV_CAP_FLAG_UD_AV_PORT	= 1 << 20,
-	MLX4_DEV_CAP_FLAG_UD_MCAST	= 1 << 21
+	MLX4_DEV_CAP_FLAG_UD_MCAST	= 1 << 21,
+	MLX4_DEV_CAP_FLAG_IBOE		= 1 << 30
 };
 
 enum {
@@ -171,6 +172,10 @@ enum {
 	MLX4_NUM_FEXCH          = 64 * 1024,
 };
 
+enum {
+	MLX4_MAX_FAST_REG_PAGES = 511,
+};
+
 static inline u64 mlx4_fw_ver(u64 major, u64 minor, u64 subminor)
 {
 	return (major << 32) | (minor << 16) | subminor;
@@ -379,6 +384,27 @@ struct mlx4_av {
 	u8			dgid[16];
 };
 
+struct mlx4_eth_av {
+	__be32		port_pd;
+	u8		reserved1;
+	u8		smac_idx;
+	u16		reserved2;
+	u8		reserved3;
+	u8		gid_index;
+	u8		stat_rate;
+	u8		hop_limit;
+	__be32		sl_tclass_flowlabel;
+	u8		dgid[16];
+	u32		reserved4[2];
+	__be16		vlan;
+	u8		mac[6];
+};
+
+union mlx4_ext_av {
+	struct mlx4_av		ib;
+	struct mlx4_eth_av	eth;
+};
+
 struct mlx4_dev {
 	struct pci_dev	       *pdev;
 	unsigned long		flags;
@@ -407,6 +433,12 @@ struct mlx4_init_port_param {
 		if (((type) == MLX4_PORT_TYPE_IB ? (dev)->caps.port_mask : \
 		     ~(dev)->caps.port_mask) & 1 << ((port) - 1))
 
+#define mlx4_foreach_ib_transport_port(port, dev)			\
+	for ((port) = 1; (port) <= (dev)->caps.num_ports; (port)++)	\
+		if (((dev)->caps.port_mask & 1 << ((port) - 1)) ||	\
+		    ((dev)->caps.flags & MLX4_DEV_CAP_FLAG_IBOE))
+
+
 int mlx4_buf_alloc(struct mlx4_dev *dev, int size, int max_direct,
 		   struct mlx4_buf *buf);
 void mlx4_buf_free(struct mlx4_dev *dev, int size, struct mlx4_buf *buf);
@@ -474,6 +506,7 @@ int mlx4_multicast_detach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16]);
 int mlx4_register_mac(struct mlx4_dev *dev, u8 port, u64 mac, int *index);
 void mlx4_unregister_mac(struct mlx4_dev *dev, u8 port, int index);
 
+int mlx4_find_cached_vlan(struct mlx4_dev *dev, u8 port, u16 vid, int *idx);
 int mlx4_register_vlan(struct mlx4_dev *dev, u8 port, u16 vlan, int *index);
 void mlx4_unregister_vlan(struct mlx4_dev *dev, u8 port, int index);
 
diff --git a/include/linux/mlx4/driver.h b/include/linux/mlx4/driver.h
index 53c5fdb..f407cd4 100644
--- a/include/linux/mlx4/driver.h
+++ b/include/linux/mlx4/driver.h
@@ -44,15 +44,24 @@ enum mlx4_dev_event {
 	MLX4_DEV_EVENT_PORT_REINIT,
 };
 
+enum mlx4_protocol {
+	MLX4_PROTOCOL_IB,
+	MLX4_PROTOCOL_EN,
+};
+
 struct mlx4_interface {
 	void *			(*add)	 (struct mlx4_dev *dev);
 	void			(*remove)(struct mlx4_dev *dev, void *context);
 	void			(*event) (struct mlx4_dev *dev, void *context,
 					  enum mlx4_dev_event event, int port);
+	void *			(*get_dev)(struct mlx4_dev *dev, void *context, u8 port);
 	struct list_head	list;
+	enum mlx4_protocol	protocol;
 };
 
 int mlx4_register_interface(struct mlx4_interface *intf);
 void mlx4_unregister_interface(struct mlx4_interface *intf);
 
+void *mlx4_get_protocol_dev(struct mlx4_dev *dev, enum mlx4_protocol proto, int port);
+
 #endif /* MLX4_DRIVER_H */
diff --git a/include/linux/mlx4/qp.h b/include/linux/mlx4/qp.h
index 7abe643..0eeb2a1 100644
--- a/include/linux/mlx4/qp.h
+++ b/include/linux/mlx4/qp.h
@@ -109,10 +109,11 @@ struct mlx4_qp_path {
 	__be32			tclass_flowlabel;
 	u8			rgid[16];
 	u8			sched_queue;
-	u8			snooper_flags;
+	u8			vlan_index;
 	u8			reserved3[2];
 	u8			counter_index;
-	u8			reserved4[7];
+	u8			reserved4;
+	u8			dmac[6];
 };
 
 struct mlx4_qp_context {
@@ -166,6 +167,7 @@ enum {
 	MLX4_WQE_CTRL_TCP_UDP_CSUM	= 1 << 5,
 	MLX4_WQE_CTRL_INS_VLAN		= 1 << 6,
 	MLX4_WQE_CTRL_STRONG_ORDER	= 1 << 7,
+	MLX4_WQE_CTRL_FORCE_LOOPBACK	= 1 << 0,
 };
 
 struct mlx4_wqe_ctrl_seg {
@@ -219,7 +221,8 @@ struct mlx4_wqe_datagram_seg {
 	__be32			av[8];
 	__be32			dqpn;
 	__be32			qkey;
-	__be32			reservd[2];
+	__be16			vlan;
+	u8			mac[6];
 };
 
 struct mlx4_wqe_lso_seg {
diff --git a/include/rdma/ib_addr.h b/include/rdma/ib_addr.h
index fa0d52b..b5fc9f3 100644
--- a/include/rdma/ib_addr.h
+++ b/include/rdma/ib_addr.h
@@ -39,7 +39,9 @@
 #include <linux/if_arp.h>
 #include <linux/netdevice.h>
 #include <linux/socket.h>
+#include <linux/if_vlan.h>
 #include <rdma/ib_verbs.h>
+#include <rdma/ib_pack.h>
 
 struct rdma_addr_client {
 	atomic_t refcount;
@@ -63,6 +65,7 @@ struct rdma_dev_addr {
 	unsigned char broadcast[MAX_ADDR_LEN];
 	unsigned short dev_type;
 	int bound_dev_if;
+	enum rdma_transport_type transport;
 };
 
 /**
@@ -127,9 +130,51 @@ static inline int rdma_addr_gid_offset(struct rdma_dev_addr *dev_addr)
 	return dev_addr->dev_type == ARPHRD_INFINIBAND ? 4 : 0;
 }
 
+static inline void iboe_mac_vlan_to_ll(union ib_gid *gid, u8 *mac, u16 vid)
+{
+	memset(gid->raw, 0, 16);
+	*((__be32 *) gid->raw) = cpu_to_be32(0xfe800000);
+	if (vid < 0x1000) {
+		gid->raw[12] = vid & 0xff;
+		gid->raw[11] = vid >> 8;
+	} else {
+		gid->raw[12] = 0xfe;
+		gid->raw[11] = 0xff;
+	}
+	memcpy(gid->raw + 13, mac + 3, 3);
+	memcpy(gid->raw + 8, mac, 3);
+	gid->raw[8] ^= 2;
+}
+
+static inline u16 rdma_vlan_dev_vlan_id(const struct net_device *dev)
+{
+	return dev->priv_flags & IFF_802_1Q_VLAN ?
+		vlan_dev_vlan_id(dev) : 0xffff;
+}
+
+static inline void iboe_addr_get_sgid(struct rdma_dev_addr *dev_addr,
+				      union ib_gid *gid)
+{
+	struct net_device *dev;
+	u16 vid = 0xffff;
+
+	dev = dev_get_by_index(&init_net, dev_addr->bound_dev_if);
+	if (dev) {
+		vid = rdma_vlan_dev_vlan_id(dev);
+		dev_put(dev);
+	}
+
+	iboe_mac_vlan_to_ll(gid, dev_addr->src_dev_addr, vid);
+}
+
 static inline void rdma_addr_get_sgid(struct rdma_dev_addr *dev_addr, union ib_gid *gid)
 {
-	memcpy(gid, dev_addr->src_dev_addr + rdma_addr_gid_offset(dev_addr), sizeof *gid);
+	if (dev_addr->transport == RDMA_TRANSPORT_IB &&
+	    dev_addr->dev_type != ARPHRD_INFINIBAND)
+		iboe_addr_get_sgid(dev_addr, gid);
+	else
+		memcpy(gid, dev_addr->src_dev_addr +
+		       rdma_addr_gid_offset(dev_addr), sizeof *gid);
 }
 
 static inline void rdma_addr_set_sgid(struct rdma_dev_addr *dev_addr, union ib_gid *gid)
@@ -147,4 +192,91 @@ static inline void rdma_addr_set_dgid(struct rdma_dev_addr *dev_addr, union ib_g
 	memcpy(dev_addr->dst_dev_addr + rdma_addr_gid_offset(dev_addr), gid, sizeof *gid);
 }
 
+static inline enum ib_mtu iboe_get_mtu(int mtu)
+{
+	/*
+	 * reduce IB headers from effective IBoE MTU. 28 stands for
+	 * atomic header which is the biggest possible header after BTH
+	 */
+	mtu = mtu - IB_GRH_BYTES - IB_BTH_BYTES - 28;
+
+	if (mtu >= ib_mtu_enum_to_int(IB_MTU_4096))
+		return IB_MTU_4096;
+	else if (mtu >= ib_mtu_enum_to_int(IB_MTU_2048))
+		return IB_MTU_2048;
+	else if (mtu >= ib_mtu_enum_to_int(IB_MTU_1024))
+		return IB_MTU_1024;
+	else if (mtu >= ib_mtu_enum_to_int(IB_MTU_512))
+		return IB_MTU_512;
+	else if (mtu >= ib_mtu_enum_to_int(IB_MTU_256))
+		return IB_MTU_256;
+	else
+		return 0;
+}
+
+static inline int iboe_get_rate(struct net_device *dev)
+{
+	struct ethtool_cmd cmd;
+
+	if (!dev->ethtool_ops || !dev->ethtool_ops->get_settings ||
+	    dev->ethtool_ops->get_settings(dev, &cmd))
+		return IB_RATE_PORT_CURRENT;
+
+	if (cmd.speed >= 40000)
+		return IB_RATE_40_GBPS;
+	else if (cmd.speed >= 30000)
+		return IB_RATE_30_GBPS;
+	else if (cmd.speed >= 20000)
+		return IB_RATE_20_GBPS;
+	else if (cmd.speed >= 10000)
+		return IB_RATE_10_GBPS;
+	else
+		return IB_RATE_PORT_CURRENT;
+}
+
+static inline int rdma_link_local_addr(struct in6_addr *addr)
+{
+	if (addr->s6_addr32[0] == htonl(0xfe800000) &&
+	    addr->s6_addr32[1] == 0)
+		return 1;
+
+	return 0;
+}
+
+static inline void rdma_get_ll_mac(struct in6_addr *addr, u8 *mac)
+{
+	memcpy(mac, &addr->s6_addr[8], 3);
+	memcpy(mac + 3, &addr->s6_addr[13], 3);
+	mac[0] ^= 2;
+}
+
+static inline int rdma_is_multicast_addr(struct in6_addr *addr)
+{
+	return addr->s6_addr[0] == 0xff;
+}
+
+static inline void rdma_get_mcast_mac(struct in6_addr *addr, u8 *mac)
+{
+	int i;
+
+	mac[0] = 0x33;
+	mac[1] = 0x33;
+	for (i = 2; i < 6; ++i)
+		mac[i] = addr->s6_addr[i + 10];
+}
+
+static inline u16 rdma_get_vlan_id(union ib_gid *dgid)
+{
+	u16 vid;
+
+	vid = dgid->raw[11] << 8 | dgid->raw[12];
+	return vid < 0x1000 ? vid : 0xffff;
+}
+
+static inline struct net_device *rdma_vlan_dev_real_dev(const struct net_device *dev)
+{
+	return dev->priv_flags & IFF_802_1Q_VLAN ?
+		vlan_dev_real_dev(dev) : 0;
+}
+
 #endif /* IB_ADDR_H */
diff --git a/include/rdma/ib_pack.h b/include/rdma/ib_pack.h
index cbb50f4..b37fe3b 100644
--- a/include/rdma/ib_pack.h
+++ b/include/rdma/ib_pack.h
@@ -37,6 +37,8 @@
 
 enum {
 	IB_LRH_BYTES  = 8,
+	IB_ETH_BYTES  = 14,
+	IB_VLAN_BYTES = 4,
 	IB_GRH_BYTES  = 40,
 	IB_BTH_BYTES  = 12,
 	IB_DETH_BYTES = 8
@@ -210,14 +212,32 @@ struct ib_unpacked_deth {
 	__be32       source_qpn;
 };
 
+struct ib_unpacked_eth {
+	u8	dmac_h[4];
+	u8	dmac_l[2];
+	u8	smac_h[2];
+	u8	smac_l[4];
+	__be16	type;
+};
+
+struct ib_unpacked_vlan {
+	__be16  tag;
+	__be16  type;
+};
+
 struct ib_ud_header {
+	int                     lrh_present;
 	struct ib_unpacked_lrh  lrh;
-	int                     grh_present;
-	struct ib_unpacked_grh  grh;
-	struct ib_unpacked_bth  bth;
+	int			eth_present;
+	struct ib_unpacked_eth	eth;
+	int                     vlan_present;
+	struct ib_unpacked_vlan vlan;
+	int			grh_present;
+	struct ib_unpacked_grh	grh;
+	struct ib_unpacked_bth	bth;
 	struct ib_unpacked_deth deth;
-	int            		immediate_present;
-	__be32         		immediate_data;
+	int			immediate_present;
+	__be32			immediate_data;
 };
 
 void ib_pack(const struct ib_field        *desc,
@@ -230,9 +250,12 @@ void ib_unpack(const struct ib_field        *desc,
 	       void                         *buf,
 	       void                         *structure);
 
-void ib_ud_header_init(int     		   payload_bytes,
-		       int    		   grh_present,
-		       int		   immediate_present,
+void ib_ud_header_init(int		    payload_bytes,
+		       int		    lrh_present,
+		       int		    eth_present,
+		       int		    vlan_present,
+		       int		    grh_present,
+		       int		    immediate_present,
 		       struct ib_ud_header *header);
 
 int ib_ud_header_pack(struct ib_ud_header *header,
diff --git a/include/rdma/ib_user_verbs.h b/include/rdma/ib_user_verbs.h
index a17f771..fe5b051 100644
--- a/include/rdma/ib_user_verbs.h
+++ b/include/rdma/ib_user_verbs.h
@@ -205,7 +205,8 @@ struct ib_uverbs_query_port_resp {
 	__u8  active_width;
 	__u8  active_speed;
 	__u8  phys_state;
-	__u8  reserved[3];
+	__u8  link_layer;
+	__u8  reserved[2];
 };
 
 struct ib_uverbs_alloc_pd {
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index 857b3b9..e04c488 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -75,6 +75,12 @@ enum rdma_transport_type {
 enum rdma_transport_type
 rdma_node_get_transport(enum rdma_node_type node_type) __attribute_const__;
 
+enum rdma_link_layer {
+	IB_LINK_LAYER_UNSPECIFIED,
+	IB_LINK_LAYER_INFINIBAND,
+	IB_LINK_LAYER_ETHERNET,
+};
+
 enum ib_device_cap_flags {
 	IB_DEVICE_RESIZE_MAX_WR		= 1,
 	IB_DEVICE_BAD_PKEY_CNTR		= (1<<1),
@@ -1010,6 +1016,8 @@ struct ib_device {
 	int		           (*query_port)(struct ib_device *device,
 						 u8 port_num,
 						 struct ib_port_attr *port_attr);
+	enum rdma_link_layer	   (*get_link_layer)(struct ib_device *device,
+						     u8 port_num);
 	int		           (*query_gid)(struct ib_device *device,
 						u8 port_num, int index,
 						union ib_gid *gid);
@@ -1222,6 +1230,9 @@ int ib_query_device(struct ib_device *device,
 int ib_query_port(struct ib_device *device,
 		  u8 port_num, struct ib_port_attr *port_attr);
 
+enum rdma_link_layer rdma_port_get_link_layer(struct ib_device *device,
+					       u8 port_num);
+
 int ib_query_gid(struct ib_device *device,
 		 u8 port_num, int index, union ib_gid *gid);
 
diff --git a/include/scsi/srp.h b/include/scsi/srp.h
index ad178fa..1ae84db 100644
--- a/include/scsi/srp.h
+++ b/include/scsi/srp.h
@@ -239,4 +239,42 @@ struct srp_rsp {
 	u8	data[0];
 } __attribute__((packed));
 
+struct srp_cred_req {
+	u8	opcode;
+	u8	sol_not;
+	u8	reserved[2];
+	__be32	req_lim_delta;
+	u64	tag;
+};
+
+struct srp_cred_rsp {
+	u8	opcode;
+	u8	reserved[7];
+	u64	tag;
+};
+
+/*
+ * The SRP spec defines the fixed portion of the AER_REQ structure to be
+ * 36 bytes, so it needs to be packed to avoid having it padded to 40 bytes
+ * on 64-bit architectures.
+ */
+struct srp_aer_req {
+	u8	opcode;
+	u8	sol_not;
+	u8	reserved[2];
+	__be32	req_lim_delta;
+	u64	tag;
+	u32	reserved2;
+	__be64	lun;
+	__be32	sense_data_len;
+	u32	reserved3;
+	u8	sense_data[0];
+} __attribute__((packed));
+
+struct srp_aer_rsp {
+	u8	opcode;
+	u8	reserved[7];
+	u64	tag;
+};
+
 #endif /* SCSI_SRP_H */