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

Pull rdma updates from Doug Ledford:
 "Initial roundup of 4.5 merge window patches

   - Remove usage of ib_query_device and instead store attributes in
     ib_device struct

   - Move iopoll out of block and into lib, rename to irqpoll, and use
     in several places in the rdma stack as our new completion queue
     polling library mechanism.  Update the other block drivers that
     already used iopoll to use the new mechanism too.

   - Replace the per-entry GID table locks with a single GID table lock

   - IPoIB multicast cleanup

   - Cleanups to the IB MR facility

   - Add support for 64bit extended IB counters

   - Fix for netlink oops while parsing RDMA nl messages

   - RoCEv2 support for the core IB code

   - mlx4 RoCEv2 support

   - mlx5 RoCEv2 support

   - Cross Channel support for mlx5

   - Timestamp support for mlx5

   - Atomic support for mlx5

   - Raw QP support for mlx5

   - MAINTAINERS update for mlx4/mlx5

   - Misc ocrdma, qib, nes, usNIC, cxgb3, cxgb4, mlx4, mlx5 updates

   - Add support for remote invalidate to the iSER driver (pushed
     through the RDMA tree due to dependencies, acknowledged by nab)

   - Update to NFSoRDMA (pushed through the RDMA tree due to
     dependencies, acknowledged by Bruce)"

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/dledford/rdma: (169 commits)
  IB/mlx5: Unify CQ create flags check
  IB/mlx5: Expose Raw Packet QP to user space consumers
  {IB, net}/mlx5: Move the modify QP operation table to mlx5_ib
  IB/mlx5: Support setting Ethernet priority for Raw Packet QPs
  IB/mlx5: Add Raw Packet QP query functionality
  IB/mlx5: Add create and destroy functionality for Raw Packet QP
  IB/mlx5: Refactor mlx5_ib_qp to accommodate other QP types
  IB/mlx5: Allocate a Transport Domain for each ucontext
  net/mlx5_core: Warn on unsupported events of QP/RQ/SQ
  net/mlx5_core: Add RQ and SQ event handling
  net/mlx5_core: Export transport objects
  IB/mlx5: Expose CQE version to user-space
  IB/mlx5: Add CQE version 1 support to user QPs and SRQs
  IB/mlx5: Fix data validation in mlx5_ib_alloc_ucontext
  IB/sa: Fix netlink local service GFP crash
  IB/srpt: Remove redundant wc array
  IB/qib: Improve ipoib UD performance
  IB/mlx4: Advertise RoCE v2 support
  IB/mlx4: Create and use another QP1 for RoCEv2
  IB/mlx4: Enable send of RoCE QP1 packets with IP/UDP headers
  ...

1 files changed, 80 insertions, 76 deletions

diff --git a/drivers/infiniband/ulp/iser/iscsi_iser.h b/drivers/infiniband/ulp/iser/iscsi_iser.h
index 8a5998e..95f0a64 100644
--- a/drivers/infiniband/ulp/iser/iscsi_iser.h
+++ b/drivers/infiniband/ulp/iser/iscsi_iser.h
@@ -48,6 +48,7 @@
 #include <scsi/scsi_transport_iscsi.h>
 #include <scsi/scsi_cmnd.h>
 #include <scsi/scsi_device.h>
+#include <scsi/iser.h>
 
 #include <linux/interrupt.h>
 #include <linux/wait.h>
@@ -151,46 +152,10 @@
 					 - ISER_MAX_RX_MISC_PDUS) /	\
 					 (1 + ISER_INFLIGHT_DATAOUTS))
 
-#define ISER_WC_BATCH_COUNT   16
 #define ISER_SIGNAL_CMD_COUNT 32
 
-#define ISER_VER			0x10
-#define ISER_WSV			0x08
-#define ISER_RSV			0x04
-
-#define ISER_FASTREG_LI_WRID		0xffffffffffffffffULL
-#define ISER_BEACON_WRID		0xfffffffffffffffeULL
-
-/**
- * struct iser_hdr - iSER header
- *
- * @flags:        flags support (zbva, remote_inv)
- * @rsvd:         reserved
- * @write_stag:   write rkey
- * @write_va:     write virtual address
- * @reaf_stag:    read rkey
- * @read_va:      read virtual address
- */
-struct iser_hdr {
-	u8      flags;
-	u8      rsvd[3];
-	__be32  write_stag;
-	__be64  write_va;
-	__be32  read_stag;
-	__be64  read_va;
-} __attribute__((packed));
-
-
-#define ISER_ZBVA_NOT_SUPPORTED		0x80
-#define ISER_SEND_W_INV_NOT_SUPPORTED	0x40
-
-struct iser_cm_hdr {
-	u8      flags;
-	u8      rsvd[3];
-} __packed;
-
 /* Constant PDU lengths calculations */
-#define ISER_HEADERS_LEN  (sizeof(struct iser_hdr) + sizeof(struct iscsi_hdr))
+#define ISER_HEADERS_LEN	(sizeof(struct iser_ctrl) + sizeof(struct iscsi_hdr))
 
 #define ISER_RECV_DATA_SEG_LEN	128
 #define ISER_RX_PAYLOAD_SIZE	(ISER_HEADERS_LEN + ISER_RECV_DATA_SEG_LEN)
@@ -269,7 +234,7 @@ enum iser_desc_type {
 #define ISER_MAX_WRS 7
 
 /**
- * struct iser_tx_desc - iSER TX descriptor (for send wr_id)
+ * struct iser_tx_desc - iSER TX descriptor
  *
  * @iser_header:   iser header
  * @iscsi_header:  iscsi header
@@ -287,12 +252,13 @@ enum iser_desc_type {
  * @sig_attrs:     Signature attributes
  */
 struct iser_tx_desc {
-	struct iser_hdr              iser_header;
+	struct iser_ctrl             iser_header;
 	struct iscsi_hdr             iscsi_header;
 	enum   iser_desc_type        type;
 	u64		             dma_addr;
 	struct ib_sge		     tx_sg[2];
 	int                          num_sge;
+	struct ib_cqe		     cqe;
 	bool			     mapped;
 	u8                           wr_idx;
 	union iser_wr {
@@ -306,9 +272,10 @@ struct iser_tx_desc {
 };
 
 #define ISER_RX_PAD_SIZE	(256 - (ISER_RX_PAYLOAD_SIZE + \
-					sizeof(u64) + sizeof(struct ib_sge)))
+				 sizeof(u64) + sizeof(struct ib_sge) + \
+				 sizeof(struct ib_cqe)))
 /**
- * struct iser_rx_desc - iSER RX descriptor (for recv wr_id)
+ * struct iser_rx_desc - iSER RX descriptor
  *
  * @iser_header:   iser header
  * @iscsi_header:  iscsi header
@@ -318,12 +285,32 @@ struct iser_tx_desc {
  * @pad:           for sense data TODO: Modify to maximum sense length supported
  */
 struct iser_rx_desc {
-	struct iser_hdr              iser_header;
+	struct iser_ctrl             iser_header;
 	struct iscsi_hdr             iscsi_header;
 	char		             data[ISER_RECV_DATA_SEG_LEN];
 	u64		             dma_addr;
 	struct ib_sge		     rx_sg;
+	struct ib_cqe		     cqe;
 	char		             pad[ISER_RX_PAD_SIZE];
+} __packed;
+
+/**
+ * struct iser_login_desc - iSER login descriptor
+ *
+ * @req:           pointer to login request buffer
+ * @resp:          pointer to login response buffer
+ * @req_dma:       DMA address of login request buffer
+ * @rsp_dma:      DMA address of login response buffer
+ * @sge:           IB sge for login post recv
+ * @cqe:           completion handler
+ */
+struct iser_login_desc {
+	void                         *req;
+	void                         *rsp;
+	u64                          req_dma;
+	u64                          rsp_dma;
+	struct ib_sge                sge;
+	struct ib_cqe		     cqe;
 } __attribute__((packed));
 
 struct iser_conn;
@@ -333,18 +320,12 @@ struct iscsi_iser_task;
 /**
  * struct iser_comp - iSER completion context
  *
- * @device:     pointer to device handle
  * @cq:         completion queue
- * @wcs:        work completion array
- * @tasklet:    Tasklet handle
  * @active_qps: Number of active QPs attached
  *              to completion context
  */
 struct iser_comp {
-	struct iser_device      *device;
 	struct ib_cq		*cq;
-	struct ib_wc		 wcs[ISER_WC_BATCH_COUNT];
-	struct tasklet_struct	 tasklet;
 	int                      active_qps;
 };
 
@@ -380,7 +361,6 @@ struct iser_reg_ops {
  *
  * @ib_device:     RDMA device
  * @pd:            Protection Domain for this device
- * @dev_attr:      Device attributes container
  * @mr:            Global DMA memory region
  * @event_handler: IB events handle routine
  * @ig_list:	   entry in devices list
@@ -389,18 +369,19 @@ struct iser_reg_ops {
  *                 cpus and device max completion vectors
  * @comps:         Dinamically allocated array of completion handlers
  * @reg_ops:       Registration ops
+ * @remote_inv_sup: Remote invalidate is supported on this device
  */
 struct iser_device {
 	struct ib_device             *ib_device;
 	struct ib_pd	             *pd;
-	struct ib_device_attr	     dev_attr;
 	struct ib_mr	             *mr;
 	struct ib_event_handler      event_handler;
 	struct list_head             ig_list;
 	int                          refcount;
 	int			     comps_used;
 	struct iser_comp	     *comps;
-	struct iser_reg_ops          *reg_ops;
+	const struct iser_reg_ops    *reg_ops;
+	bool                         remote_inv_sup;
 };
 
 #define ISER_CHECK_GUARD	0xc0
@@ -475,10 +456,11 @@ struct iser_fr_pool {
  * @rx_wr:               receive work request for batch posts
  * @device:              reference to iser device
  * @comp:                iser completion context
- * @pi_support:          Indicate device T10-PI support
- * @beacon:              beacon send wr to signal all flush errors were drained
- * @flush_comp:          completes when all connection completions consumed
  * @fr_pool:             connection fast registration poool
+ * @pi_support:          Indicate device T10-PI support
+ * @last:                last send wr to signal all flush errors were drained
+ * @last_cqe:            cqe handler for last wr
+ * @last_comp:           completes when all connection completions consumed
  */
 struct ib_conn {
 	struct rdma_cm_id           *cma_id;
@@ -488,10 +470,12 @@ struct ib_conn {
 	struct ib_recv_wr	     rx_wr[ISER_MIN_POSTED_RX];
 	struct iser_device          *device;
 	struct iser_comp	    *comp;
-	bool			     pi_support;
-	struct ib_send_wr	     beacon;
-	struct completion	     flush_comp;
 	struct iser_fr_pool          fr_pool;
+	bool			     pi_support;
+	struct ib_send_wr	     last;
+	struct ib_cqe		     last_cqe;
+	struct ib_cqe		     reg_cqe;
+	struct completion	     last_comp;
 };
 
 /**
@@ -514,11 +498,7 @@ struct ib_conn {
  * @up_completion:    connection establishment completed
  *                    (state is ISER_CONN_UP)
  * @conn_list:        entry in ig conn list
- * @login_buf:        login data buffer (stores login parameters)
- * @login_req_buf:    login request buffer
- * @login_req_dma:    login request buffer dma address
- * @login_resp_buf:   login response buffer
- * @login_resp_dma:   login response buffer dma address
+ * @login_desc:       login descriptor
  * @rx_desc_head:     head of rx_descs cyclic buffer
  * @rx_descs:         rx buffers array (cyclic buffer)
  * @num_rx_descs:     number of rx descriptors
@@ -541,15 +521,13 @@ struct iser_conn {
 	struct completion	     ib_completion;
 	struct completion	     up_completion;
 	struct list_head	     conn_list;
-
-	char  			     *login_buf;
-	char			     *login_req_buf, *login_resp_buf;
-	u64			     login_req_dma, login_resp_dma;
+	struct iser_login_desc       login_desc;
 	unsigned int 		     rx_desc_head;
 	struct iser_rx_desc	     *rx_descs;
 	u32                          num_rx_descs;
 	unsigned short               scsi_sg_tablesize;
 	unsigned int                 scsi_max_sectors;
+	bool			     snd_w_inv;
 };
 
 /**
@@ -579,9 +557,8 @@ struct iscsi_iser_task {
 
 struct iser_page_vec {
 	u64 *pages;
-	int length;
-	int offset;
-	int data_size;
+	int npages;
+	struct ib_mr fake_mr;
 };
 
 /**
@@ -633,12 +610,14 @@ int iser_conn_terminate(struct iser_conn *iser_conn);
 
 void iser_release_work(struct work_struct *work);
 
-void iser_rcv_completion(struct iser_rx_desc *desc,
-			 unsigned long dto_xfer_len,
-			 struct ib_conn *ib_conn);
-
-void iser_snd_completion(struct iser_tx_desc *desc,
-			 struct ib_conn *ib_conn);
+void iser_err_comp(struct ib_wc *wc, const char *type);
+void iser_login_rsp(struct ib_cq *cq, struct ib_wc *wc);
+void iser_task_rsp(struct ib_cq *cq, struct ib_wc *wc);
+void iser_cmd_comp(struct ib_cq *cq, struct ib_wc *wc);
+void iser_ctrl_comp(struct ib_cq *cq, struct ib_wc *wc);
+void iser_dataout_comp(struct ib_cq *cq, struct ib_wc *wc);
+void iser_reg_comp(struct ib_cq *cq, struct ib_wc *wc);
+void iser_last_comp(struct ib_cq *cq, struct ib_wc *wc);
 
 void iser_task_rdma_init(struct iscsi_iser_task *task);
 
@@ -651,7 +630,8 @@ void iser_finalize_rdma_unaligned_sg(struct iscsi_iser_task *iser_task,
 				     enum iser_data_dir cmd_dir);
 
 int iser_reg_rdma_mem(struct iscsi_iser_task *task,
-		      enum iser_data_dir dir);
+		      enum iser_data_dir dir,
+		      bool all_imm);
 void iser_unreg_rdma_mem(struct iscsi_iser_task *task,
 			 enum iser_data_dir dir);
 
@@ -719,4 +699,28 @@ iser_tx_next_wr(struct iser_tx_desc *tx_desc)
 	return cur_wr;
 }
 
+static inline struct iser_conn *
+to_iser_conn(struct ib_conn *ib_conn)
+{
+	return container_of(ib_conn, struct iser_conn, ib_conn);
+}
+
+static inline struct iser_rx_desc *
+iser_rx(struct ib_cqe *cqe)
+{
+	return container_of(cqe, struct iser_rx_desc, cqe);
+}
+
+static inline struct iser_tx_desc *
+iser_tx(struct ib_cqe *cqe)
+{
+	return container_of(cqe, struct iser_tx_desc, cqe);
+}
+
+static inline struct iser_login_desc *
+iser_login(struct ib_cqe *cqe)
+{
+	return container_of(cqe, struct iser_login_desc, cqe);
+}
+
 #endif