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: (87 commits)
  mlx4_core: Fix section mismatches
  IPoIB: Allow setting policy to ignore multicast groups
  IB/mthca: Mark error paths as unlikely() in post_srq_recv functions
  IB/ipath: Minor fix to ordering of freeing and zeroing of tid pages.
  IB/ipath: Remove redundant link state checks
  IB/ipath: Fix IB_EVENT_PORT_ERR event
  IB/ipath: Better handling of unexpected GPIO interrupts
  IB/ipath: Maintain active time on all chips
  IB/ipath: Fix QHT7040 serial number check
  IB/ipath: Indicate a couple of chip bugs to userspace
  IB/ipath: iba6110 rev4 no longer needs recv header overrun workaround
  IB/ipath: Use counters in ipath_poll and cleanup interrupts in ipath_close
  IB/ipath: Remove duplicate copy of LMC
  IB/ipath: Add ability to set the LMC via the sysfs debugging interface
  IB/ipath: Optimize completion queue entry insertion and polling
  IB/ipath: Implement IB_EVENT_QP_LAST_WQE_REACHED
  IB/ipath: Generate flush CQE when QP is in error state
  IB/ipath: Remove redundant code
  IB/ipath: Future proof eeprom checksum code (contents reading)
  IB/ipath: UC RDMA WRITE with IMMEDIATE doesn't send the immediate
  ...

include/linux/mlx4/device.h

@@ -48,6 +48,10 @@ enum {
 	MLX4_MAX_PORTS		= 2
 };
 
+enum {
+	MLX4_BOARD_ID_LEN = 64
+};
+
 enum {
 	MLX4_DEV_CAP_FLAG_RC		= 1 <<  0,
 	MLX4_DEV_CAP_FLAG_UC		= 1 <<  1,
@@ -210,6 +214,17 @@ struct mlx4_mr {
 	int			enabled;
 };
 
+struct mlx4_fmr {
+	struct mlx4_mr		mr;
+	struct mlx4_mpt_entry  *mpt;
+	__be64		       *mtts;
+	dma_addr_t		dma_handle;
+	int			max_pages;
+	int			max_maps;
+	int			maps;
+	u8			page_shift;
+};
+
 struct mlx4_uar {
 	unsigned long		pfn;
 	int			index;
@@ -272,6 +287,8 @@ struct mlx4_dev {
 	unsigned long		flags;
 	struct mlx4_caps	caps;
 	struct radix_tree_root	qp_table_tree;
+	u32			rev_id;
+	char			board_id[MLX4_BOARD_ID_LEN];
 };
 
 struct mlx4_init_port_param {
@@ -331,4 +348,14 @@ int mlx4_CLOSE_PORT(struct mlx4_dev *dev, int port);
 int mlx4_multicast_attach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16]);
 int mlx4_multicast_detach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16]);
 
+int mlx4_map_phys_fmr(struct mlx4_dev *dev, struct mlx4_fmr *fmr, u64 *page_list,
+		      int npages, u64 iova, u32 *lkey, u32 *rkey);
+int mlx4_fmr_alloc(struct mlx4_dev *dev, u32 pd, u32 access, int max_pages,
+		   int max_maps, u8 page_shift, struct mlx4_fmr *fmr);
+int mlx4_fmr_enable(struct mlx4_dev *dev, struct mlx4_fmr *fmr);
+void mlx4_fmr_unmap(struct mlx4_dev *dev, struct mlx4_fmr *fmr,
+		    u32 *lkey, u32 *rkey);
+int mlx4_fmr_free(struct mlx4_dev *dev, struct mlx4_fmr *fmr);
+int mlx4_SYNC_TPT(struct mlx4_dev *dev);
+
 #endif /* MLX4_DEVICE_H */

include/rdma/ib_cm.h

@@ -477,12 +477,15 @@ int ib_send_cm_rej(struct ib_cm_id *cm_id,
 		   const void *private_data,
 		   u8 private_data_len);
 
+#define IB_CM_MRA_FLAG_DELAY 0x80  /* Send MRA only after a duplicate msg */
+
 /**
  * ib_send_cm_mra - Sends a message receipt acknowledgement to a connection
  *   message.
  * @cm_id: Connection identifier associated with the connection message.
- * @service_timeout: The maximum time required for the sender to reply to
- *   to the connection message.
+ * @service_timeout: The lower 5-bits specify the maximum time required for
+ *   the sender to reply to to the connection message.  The upper 3-bits
+ *   specify additional control flags.
  * @private_data: Optional user-defined private data sent with the
  *   message receipt acknowledgement.
  * @private_data_len: Size of the private data buffer, in bytes.

include/rdma/ib_sa.h

@@ -109,8 +109,8 @@ enum ib_sa_selector {
  * Reserved rows are indicated with comments to help maintainability.
  */
 
-/* reserved:								 0 */
-/* reserved:								 1 */
+#define IB_SA_PATH_REC_SERVICE_ID		       (IB_SA_COMP_MASK( 0) |\
+							IB_SA_COMP_MASK( 1))
 #define IB_SA_PATH_REC_DGID				IB_SA_COMP_MASK( 2)
 #define IB_SA_PATH_REC_SGID				IB_SA_COMP_MASK( 3)
 #define IB_SA_PATH_REC_DLID				IB_SA_COMP_MASK( 4)
@@ -123,7 +123,7 @@ enum ib_sa_selector {
 #define IB_SA_PATH_REC_REVERSIBLE			IB_SA_COMP_MASK(11)
 #define IB_SA_PATH_REC_NUMB_PATH			IB_SA_COMP_MASK(12)
 #define IB_SA_PATH_REC_PKEY				IB_SA_COMP_MASK(13)
-/* reserved:								14 */
+#define IB_SA_PATH_REC_QOS_CLASS			IB_SA_COMP_MASK(14)
 #define IB_SA_PATH_REC_SL				IB_SA_COMP_MASK(15)
 #define IB_SA_PATH_REC_MTU_SELECTOR			IB_SA_COMP_MASK(16)
 #define IB_SA_PATH_REC_MTU				IB_SA_COMP_MASK(17)
@@ -134,8 +134,7 @@ enum ib_sa_selector {
 #define IB_SA_PATH_REC_PREFERENCE			IB_SA_COMP_MASK(22)
 
 struct ib_sa_path_rec {
-	/* reserved */
-	/* reserved */
+	__be64       service_id;
 	union ib_gid dgid;
 	union ib_gid sgid;
 	__be16       dlid;
@@ -148,7 +147,7 @@ struct ib_sa_path_rec {
 	int          reversible;
 	u8           numb_path;
 	__be16       pkey;
-	/* reserved */
+	__be16       qos_class;
 	u8           sl;
 	u8           mtu_selector;
 	u8           mtu;

include/rdma/ib_umem.h

@@ -45,6 +45,7 @@ struct ib_umem {
 	int			offset;
 	int			page_size;
 	int                     writable;
+	int                     hugetlb;
 	struct list_head	chunk_list;
 	struct work_struct	work;
 	struct mm_struct       *mm;

include/rdma/ib_user_mad.h

@@ -52,7 +52,7 @@
  */
 
 /**
- * ib_user_mad_hdr - MAD packet header
+ * ib_user_mad_hdr_old - Old version of MAD packet header without pkey_index
  * @id - ID of agent MAD received with/to be sent with
  * @status - 0 on successful receive, ETIMEDOUT if no response
  *   received (transaction ID in data[] will be set to TID of original
@@ -71,7 +71,7 @@
  * @gid - Remote GID in GRH
  * @flow_label - Flow label in GRH
  */
-struct ib_user_mad_hdr {
+struct ib_user_mad_hdr_old {
 	__u32	id;
 	__u32	status;
 	__u32	timeout_ms;
@@ -90,6 +90,52 @@ struct ib_user_mad_hdr {
 	__be32	flow_label;
 };
 
+/**
+ * ib_user_mad_hdr - MAD packet header
+ *   This layout allows specifying/receiving the P_Key index.  To use
+ *   this capability, an application must call the
+ *   IB_USER_MAD_ENABLE_PKEY ioctl on the user MAD file handle before
+ *   any other actions with the file handle.
+ * @id - ID of agent MAD received with/to be sent with
+ * @status - 0 on successful receive, ETIMEDOUT if no response
+ *   received (transaction ID in data[] will be set to TID of original
+ *   request) (ignored on send)
+ * @timeout_ms - Milliseconds to wait for response (unset on receive)
+ * @retries - Number of automatic retries to attempt
+ * @qpn - Remote QP number received from/to be sent to
+ * @qkey - Remote Q_Key to be sent with (unset on receive)
+ * @lid - Remote lid received from/to be sent to
+ * @sl - Service level received with/to be sent with
+ * @path_bits - Local path bits received with/to be sent with
+ * @grh_present - If set, GRH was received/should be sent
+ * @gid_index - Local GID index to send with (unset on receive)
+ * @hop_limit - Hop limit in GRH
+ * @traffic_class - Traffic class in GRH
+ * @gid - Remote GID in GRH
+ * @flow_label - Flow label in GRH
+ * @pkey_index - P_Key index
+ */
+struct ib_user_mad_hdr {
+	__u32	id;
+	__u32	status;
+	__u32	timeout_ms;
+	__u32	retries;
+	__u32	length;
+	__be32	qpn;
+	__be32  qkey;
+	__be16	lid;
+	__u8	sl;
+	__u8	path_bits;
+	__u8	grh_present;
+	__u8	gid_index;
+	__u8	hop_limit;
+	__u8	traffic_class;
+	__u8	gid[16];
+	__be32	flow_label;
+	__u16	pkey_index;
+	__u8	reserved[6];
+};
+
 /**
  * ib_user_mad - MAD packet
  * @hdr - MAD packet header
@@ -101,6 +147,26 @@ struct ib_user_mad {
 	__u64	data[0];
 };
 
+/*
+ * Earlier versions of this interface definition declared the
+ * method_mask[] member as an array of __u32 but treated it as a
+ * bitmap made up of longs in the kernel.  This ambiguity meant that
+ * 32-bit big-endian applications that can run on both 32-bit and
+ * 64-bit kernels had no consistent ABI to rely on, and 64-bit
+ * big-endian applications that treated method_mask as being made up
+ * of 32-bit words would have their bitmap misinterpreted.
+ *
+ * To clear up this confusion, we change the declaration of
+ * method_mask[] to use unsigned long and handle the conversion from
+ * 32-bit userspace to 64-bit kernel for big-endian systems in the
+ * compat_ioctl method.  Unfortunately, to keep the structure layout
+ * the same, we need the method_mask[] array to be aligned only to 4
+ * bytes even when long is 64 bits, which forces us into this ugly
+ * typedef.
+ */
+typedef unsigned long __attribute__((aligned(4))) packed_ulong;
+#define IB_USER_MAD_LONGS_PER_METHOD_MASK (128 / (8 * sizeof (long)))
+
 /**
  * ib_user_mad_reg_req - MAD registration request
  * @id - Set by the kernel; used to identify agent in future requests.
@@ -119,7 +185,7 @@ struct ib_user_mad {
  */
 struct ib_user_mad_reg_req {
 	__u32	id;
-	__u32	method_mask[4];
+	packed_ulong method_mask[IB_USER_MAD_LONGS_PER_METHOD_MASK];
 	__u8	qpn;
 	__u8	mgmt_class;
 	__u8	mgmt_class_version;
@@ -134,4 +200,6 @@ struct ib_user_mad_reg_req {
 
 #define IB_USER_MAD_UNREGISTER_AGENT	_IOW(IB_IOCTL_MAGIC, 2, __u32)
 
+#define IB_USER_MAD_ENABLE_PKEY		_IO(IB_IOCTL_MAGIC, 3)
+
 #endif /* IB_USER_MAD_H */

include/rdma/rdma_cm.h

@@ -314,4 +314,18 @@ int rdma_join_multicast(struct rdma_cm_id *id, struct sockaddr *addr,
  */
 void rdma_leave_multicast(struct rdma_cm_id *id, struct sockaddr *addr);
 
+/**
+ * rdma_set_service_type - Set the type of service associated with a
+ *   connection identifier.
+ * @id: Communication identifier to associated with service type.
+ * @tos: Type of service.
+ *
+ * The type of service is interpretted as a differentiated service
+ * field (RFC 2474).  The service type should be specified before
+ * performing route resolution, as existing communication on the
+ * connection identifier may be unaffected.  The type of service
+ * requested may not be supported by the network to all destinations.
+ */
+void rdma_set_service_type(struct rdma_cm_id *id, int tos);
+
 #endif /* RDMA_CM_H */

include/rdma/rdma_user_cm.h

@@ -212,4 +212,22 @@ struct rdma_ucm_event_resp {
 	} param;
 };
 
+/* Option levels */
+enum {
+	RDMA_OPTION_ID		= 0
+};
+
+/* Option details */
+enum {
+	RDMA_OPTION_ID_TOS	= 0
+};
+
+struct rdma_ucm_set_option {
+	__u64 optval;
+	__u32 id;
+	__u32 level;
+	__u32 optname;
+	__u32 optlen;
+};
+
 #endif /* RDMA_USER_CM_H */