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

Pull rdma updates from Doug Ledford:
 "Primary 4.7 merge window changes

   - Updates to the new Intel X722 iWARP driver
   - Updates to the hfi1 driver
   - Fixes for the iw_cxgb4 driver
   - Misc core fixes
   - Generic RDMA READ/WRITE API addition
   - SRP updates
   - Misc ipoib updates
   - Minor mlx5 updates"

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/dledford/rdma: (148 commits)
  IB/mlx5: Fire the CQ completion handler from tasklet
  net/mlx5_core: Use tasklet for user-space CQ completion events
  IB/core: Do not require CAP_NET_ADMIN for packet sniffing
  IB/mlx4: Fix unaligned access in send_reply_to_slave
  IB/mlx5: Report Scatter FCS device capability when supported
  IB/mlx5: Add Scatter FCS support for Raw Packet QP
  IB/core: Add Scatter FCS create flag
  IB/core: Add Raw Scatter FCS device capability
  IB/core: Add extended device capability flags
  i40iw: pass hw_stats by reference rather than by value
  i40iw: Remove unnecessary synchronize_irq() before free_irq()
  i40iw: constify i40iw_vf_cqp_ops structure
  IB/mlx5: Add UARs write-combining and non-cached mapping
  IB/mlx5: Allow mapping the free running counter on PROT_EXEC
  IB/mlx4: Use list_for_each_entry_safe
  IB/SA: Use correct free function
  IB/core: Fix a potential array overrun in CMA and SA agent
  IB/core: Remove unnecessary check in ibnl_rcv_msg
  IB/IWPM: Fix a potential skb leak
  RDMA/nes: replace custom print_hex_dump()
  ...

10 files changed, 182 insertions, 19 deletions

diff --git a/include/linux/mlx5/cq.h b/include/linux/mlx5/cq.h
index b2c9fada8eac..2be976dd4966 100644
--- a/include/linux/mlx5/cq.h
+++ b/include/linux/mlx5/cq.h
@@ -53,6 +53,11 @@ struct mlx5_core_cq {
 	unsigned		arm_sn;
 	struct mlx5_rsc_debug	*dbg;
 	int			pid;
+	struct {
+		struct list_head list;
+		void (*comp)(struct mlx5_core_cq *);
+		void		*priv;
+	} tasklet_ctx;
 };
 
 
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 07b504f7eb84..80776d0c52dc 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -42,6 +42,7 @@
 #include <linux/vmalloc.h>
 #include <linux/radix-tree.h>
 #include <linux/workqueue.h>
+#include <linux/interrupt.h>
 
 #include <linux/mlx5/device.h>
 #include <linux/mlx5/doorbell.h>
@@ -312,6 +313,14 @@ struct mlx5_buf {
 	u8			page_shift;
 };
 
+struct mlx5_eq_tasklet {
+	struct list_head list;
+	struct list_head process_list;
+	struct tasklet_struct task;
+	/* lock on completion tasklet list */
+	spinlock_t lock;
+};
+
 struct mlx5_eq {
 	struct mlx5_core_dev   *dev;
 	__be32 __iomem	       *doorbell;
@@ -325,6 +334,7 @@ struct mlx5_eq {
 	struct list_head	list;
 	int			index;
 	struct mlx5_rsc_debug	*dbg;
+	struct mlx5_eq_tasklet	tasklet_ctx;
 };
 
 struct mlx5_core_psv {
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index fb2cef4e9747..fc0320c004a3 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -220,6 +220,7 @@ enum ib_device_cap_flags {
 	IB_DEVICE_ON_DEMAND_PAGING		= (1 << 31),
 	IB_DEVICE_SG_GAPS_REG			= (1ULL << 32),
 	IB_DEVICE_VIRTUAL_FUNCTION		= ((u64)1 << 33),
+	IB_DEVICE_RAW_SCATTER_FCS		= ((u64)1 << 34),
 };
 
 enum ib_signature_prot_cap {
@@ -931,6 +932,13 @@ struct ib_qp_cap {
 	u32	max_send_sge;
 	u32	max_recv_sge;
 	u32	max_inline_data;
+
+	/*
+	 * Maximum number of rdma_rw_ctx structures in flight at a time.
+	 * ib_create_qp() will calculate the right amount of neededed WRs
+	 * and MRs based on this.
+	 */
+	u32	max_rdma_ctxs;
 };
 
 enum ib_sig_type {
@@ -981,6 +989,7 @@ enum ib_qp_create_flags {
 	IB_QP_CREATE_NETIF_QP			= 1 << 5,
 	IB_QP_CREATE_SIGNATURE_EN		= 1 << 6,
 	IB_QP_CREATE_USE_GFP_NOIO		= 1 << 7,
+	IB_QP_CREATE_SCATTER_FCS		= 1 << 8,
 	/* reserve bits 26-31 for low level drivers' internal use */
 	IB_QP_CREATE_RESERVED_START		= 1 << 26,
 	IB_QP_CREATE_RESERVED_END		= 1 << 31,
@@ -1002,7 +1011,11 @@ struct ib_qp_init_attr {
 	enum ib_sig_type	sq_sig_type;
 	enum ib_qp_type		qp_type;
 	enum ib_qp_create_flags	create_flags;
-	u8			port_num; /* special QP types only */
+
+	/*
+	 * Only needed for special QP types, or when using the RW API.
+	 */
+	u8			port_num;
 };
 
 struct ib_qp_open_attr {
@@ -1421,9 +1434,14 @@ struct ib_qp {
 	struct ib_pd	       *pd;
 	struct ib_cq	       *send_cq;
 	struct ib_cq	       *recv_cq;
+	spinlock_t		mr_lock;
+	int			mrs_used;
+	struct list_head	rdma_mrs;
+	struct list_head	sig_mrs;
 	struct ib_srq	       *srq;
 	struct ib_xrcd	       *xrcd; /* XRC TGT QPs only */
 	struct list_head	xrcd_list;
+
 	/* count times opened, mcast attaches, flow attaches */
 	atomic_t		usecnt;
 	struct list_head	open_list;
@@ -1438,12 +1456,16 @@ struct ib_qp {
 struct ib_mr {
 	struct ib_device  *device;
 	struct ib_pd	  *pd;
-	struct ib_uobject *uobject;
 	u32		   lkey;
 	u32		   rkey;
 	u64		   iova;
 	u32		   length;
 	unsigned int	   page_size;
+	bool		   need_inval;
+	union {
+		struct ib_uobject	*uobject;	/* user */
+		struct list_head	qp_entry;	/* FR */
+	};
 };
 
 struct ib_mw {
@@ -1827,7 +1849,8 @@ struct ib_device {
 					       u32 max_num_sg);
 	int                        (*map_mr_sg)(struct ib_mr *mr,
 						struct scatterlist *sg,
-						int sg_nents);
+						int sg_nents,
+						unsigned int *sg_offset);
 	struct ib_mw *             (*alloc_mw)(struct ib_pd *pd,
 					       enum ib_mw_type type,
 					       struct ib_udata *udata);
@@ -2317,6 +2340,18 @@ static inline bool rdma_cap_roce_gid_table(const struct ib_device *device,
 		device->add_gid && device->del_gid;
 }
 
+/*
+ * 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,
 		 struct ib_gid_attr *attr);
@@ -3111,29 +3146,23 @@ struct net_device *ib_get_net_dev_by_params(struct ib_device *dev, u8 port,
 					    u16 pkey, const union ib_gid *gid,
 					    const struct sockaddr *addr);
 
-int ib_map_mr_sg(struct ib_mr *mr,
-		 struct scatterlist *sg,
-		 int sg_nents,
-		 unsigned int page_size);
+int ib_map_mr_sg(struct ib_mr *mr, struct scatterlist *sg, int sg_nents,
+		 unsigned int *sg_offset, unsigned int page_size);
 
 static inline int
-ib_map_mr_sg_zbva(struct ib_mr *mr,
-		  struct scatterlist *sg,
-		  int sg_nents,
-		  unsigned int page_size)
+ib_map_mr_sg_zbva(struct ib_mr *mr, struct scatterlist *sg, int sg_nents,
+		  unsigned int *sg_offset, unsigned int page_size)
 {
 	int n;
 
-	n = ib_map_mr_sg(mr, sg, sg_nents, page_size);
+	n = ib_map_mr_sg(mr, sg, sg_nents, sg_offset, page_size);
 	mr->iova = 0;
 
 	return n;
 }
 
-int ib_sg_to_pages(struct ib_mr *mr,
-		   struct scatterlist *sgl,
-		   int sg_nents,
-		   int (*set_page)(struct ib_mr *, u64));
+int ib_sg_to_pages(struct ib_mr *mr, struct scatterlist *sgl, int sg_nents,
+		unsigned int *sg_offset, int (*set_page)(struct ib_mr *, u64));
 
 void ib_drain_rq(struct ib_qp *qp);
 void ib_drain_sq(struct ib_qp *qp);
diff --git a/include/rdma/mr_pool.h b/include/rdma/mr_pool.h
new file mode 100644
index 000000000000..986010b812eb
--- /dev/null
+++ b/include/rdma/mr_pool.h
@@ -0,0 +1,25 @@
+/*
+ * Copyright (c) 2016 HGST, a Western Digital Company.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ */
+#ifndef _RDMA_MR_POOL_H
+#define _RDMA_MR_POOL_H 1
+
+#include <rdma/ib_verbs.h>
+
+struct ib_mr *ib_mr_pool_get(struct ib_qp *qp, struct list_head *list);
+void ib_mr_pool_put(struct ib_qp *qp, struct list_head *list, struct ib_mr *mr);
+
+int ib_mr_pool_init(struct ib_qp *qp, struct list_head *list, int nr,
+		enum ib_mr_type type, u32 max_num_sg);
+void ib_mr_pool_destroy(struct ib_qp *qp, struct list_head *list);
+
+#endif /* _RDMA_MR_POOL_H */
diff --git a/include/rdma/rdma_vt.h b/include/rdma/rdma_vt.h
index a8696551abb1..d57ceee90d26 100644
--- a/include/rdma/rdma_vt.h
+++ b/include/rdma/rdma_vt.h
@@ -467,6 +467,7 @@ static inline struct rvt_qp *rvt_lookup_qpn(struct rvt_dev_info *rdi,
 }
 
 struct rvt_dev_info *rvt_alloc_device(size_t size, int nports);
+void rvt_dealloc_device(struct rvt_dev_info *rdi);
 int rvt_register_device(struct rvt_dev_info *rvd);
 void rvt_unregister_device(struct rvt_dev_info *rvd);
 int rvt_check_ah(struct ib_device *ibdev, struct ib_ah_attr *ah_attr);
diff --git a/include/rdma/rdmavt_qp.h b/include/rdma/rdmavt_qp.h
index 497e59065c2c..0e1ff2abfe92 100644
--- a/include/rdma/rdmavt_qp.h
+++ b/include/rdma/rdmavt_qp.h
@@ -117,8 +117,9 @@
 /*
  * Wait flags that would prevent any packet type from being sent.
  */
-#define RVT_S_ANY_WAIT_IO (RVT_S_WAIT_PIO | RVT_S_WAIT_TX | \
-	RVT_S_WAIT_DMA_DESC | RVT_S_WAIT_KMEM)
+#define RVT_S_ANY_WAIT_IO \
+	(RVT_S_WAIT_PIO | RVT_S_WAIT_PIO_DRAIN | RVT_S_WAIT_TX | \
+	 RVT_S_WAIT_DMA_DESC | RVT_S_WAIT_KMEM)
 
 /*
  * Wait flags that would prevent send work requests from making progress.
diff --git a/include/rdma/rw.h b/include/rdma/rw.h
new file mode 100644
index 000000000000..377d865e506d
--- /dev/null
+++ b/include/rdma/rw.h
@@ -0,0 +1,88 @@
+/*
+ * Copyright (c) 2016 HGST, a Western Digital Company.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ */
+#ifndef _RDMA_RW_H
+#define _RDMA_RW_H
+
+#include <linux/dma-mapping.h>
+#include <linux/scatterlist.h>
+#include <rdma/ib_verbs.h>
+#include <rdma/rdma_cm.h>
+#include <rdma/mr_pool.h>
+
+struct rdma_rw_ctx {
+	/* number of RDMA READ/WRITE WRs (not counting MR WRs) */
+	u32			nr_ops;
+
+	/* tag for the union below: */
+	u8			type;
+
+	union {
+		/* for mapping a single SGE: */
+		struct {
+			struct ib_sge		sge;
+			struct ib_rdma_wr	wr;
+		} single;
+
+		/* for mapping of multiple SGEs: */
+		struct {
+			struct ib_sge		*sges;
+			struct ib_rdma_wr	*wrs;
+		} map;
+
+		/* for registering multiple WRs: */
+		struct rdma_rw_reg_ctx {
+			struct ib_sge		sge;
+			struct ib_rdma_wr	wr;
+			struct ib_reg_wr	reg_wr;
+			struct ib_send_wr	inv_wr;
+			struct ib_mr		*mr;
+		} *reg;
+
+		struct {
+			struct rdma_rw_reg_ctx	data;
+			struct rdma_rw_reg_ctx	prot;
+			struct ib_send_wr	sig_inv_wr;
+			struct ib_mr		*sig_mr;
+			struct ib_sge		sig_sge;
+			struct ib_sig_handover_wr sig_wr;
+		} *sig;
+	};
+};
+
+int rdma_rw_ctx_init(struct rdma_rw_ctx *ctx, struct ib_qp *qp, u8 port_num,
+		struct scatterlist *sg, u32 sg_cnt, u32 sg_offset,
+		u64 remote_addr, u32 rkey, enum dma_data_direction dir);
+void rdma_rw_ctx_destroy(struct rdma_rw_ctx *ctx, struct ib_qp *qp, u8 port_num,
+		struct scatterlist *sg, u32 sg_cnt,
+		enum dma_data_direction dir);
+
+int rdma_rw_ctx_signature_init(struct rdma_rw_ctx *ctx, struct ib_qp *qp,
+		u8 port_num, struct scatterlist *sg, u32 sg_cnt,
+		struct scatterlist *prot_sg, u32 prot_sg_cnt,
+		struct ib_sig_attrs *sig_attrs, u64 remote_addr, u32 rkey,
+		enum dma_data_direction dir);
+void rdma_rw_ctx_destroy_signature(struct rdma_rw_ctx *ctx, struct ib_qp *qp,
+		u8 port_num, struct scatterlist *sg, u32 sg_cnt,
+		struct scatterlist *prot_sg, u32 prot_sg_cnt,
+		enum dma_data_direction dir);
+
+struct ib_send_wr *rdma_rw_ctx_wrs(struct rdma_rw_ctx *ctx, struct ib_qp *qp,
+		u8 port_num, struct ib_cqe *cqe, struct ib_send_wr *chain_wr);
+int rdma_rw_ctx_post(struct rdma_rw_ctx *ctx, struct ib_qp *qp, u8 port_num,
+		struct ib_cqe *cqe, struct ib_send_wr *chain_wr);
+
+void rdma_rw_init_qp(struct ib_device *dev, struct ib_qp_init_attr *attr);
+int rdma_rw_init_mrs(struct ib_qp *qp, struct ib_qp_init_attr *attr);
+void rdma_rw_cleanup_mrs(struct ib_qp *qp);
+
+#endif /* _RDMA_RW_H */
diff --git a/include/target/target_core_backend.h b/include/target/target_core_backend.h
index 28ee5c2e6bcd..d8ab5101fad5 100644
--- a/include/target/target_core_backend.h
+++ b/include/target/target_core_backend.h
@@ -85,7 +85,6 @@ extern struct configfs_attribute *passthrough_attrib_attrs[];
 void	*transport_kmap_data_sg(struct se_cmd *);
 void	transport_kunmap_data_sg(struct se_cmd *);
 /* core helpers also used by xcopy during internal command setup */
-int	target_alloc_sgl(struct scatterlist **, unsigned int *, u32, bool);
 sense_reason_t	transport_generic_map_mem_to_cmd(struct se_cmd *,
 		struct scatterlist *, u32, struct scatterlist *, u32);
 
diff --git a/include/target/target_core_fabric.h b/include/target/target_core_fabric.h
index 8ff6d40a294f..78d88f03b296 100644
--- a/include/target/target_core_fabric.h
+++ b/include/target/target_core_fabric.h
@@ -185,6 +185,10 @@ int	core_tpg_set_initiator_node_tag(struct se_portal_group *,
 int	core_tpg_register(struct se_wwn *, struct se_portal_group *, int);
 int	core_tpg_deregister(struct se_portal_group *);
 
+int	target_alloc_sgl(struct scatterlist **sgl, unsigned int *nents,
+		u32 length, bool zero_page, bool chainable);
+void	target_free_sgl(struct scatterlist *sgl, int nents);
+
 /*
  * The LIO target core uses DMA_TO_DEVICE to mean that data is going
  * to the target (eg handling a WRITE) and DMA_FROM_DEVICE to mean
diff --git a/include/uapi/rdma/ib_user_verbs.h b/include/uapi/rdma/ib_user_verbs.h
index 8126c143a519..b6543d73d20a 100644
--- a/include/uapi/rdma/ib_user_verbs.h
+++ b/include/uapi/rdma/ib_user_verbs.h
@@ -226,6 +226,7 @@ struct ib_uverbs_ex_query_device_resp {
 	struct ib_uverbs_odp_caps odp_caps;
 	__u64 timestamp_mask;
 	__u64 hca_core_clock; /* in KHZ */
+	__u64 device_cap_flags_ex;
 };
 
 struct ib_uverbs_query_port {