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

Pull rdma updates from Jason Gunthorpe:
 "A smaller cycle this time. Notably we see another new driver, 'Soft
  iWarp', and the deletion of an ancient unused driver for nes.

   - Revise and simplify the signature offload RDMA MR APIs

   - More progress on hoisting object allocation boiler plate code out
     of the drivers

   - Driver bug fixes and revisions for hns, hfi1, efa, cxgb4, qib,
     i40iw

   - Tree wide cleanups: struct_size, put_user_page, xarray, rst doc
     conversion

   - Removal of obsolete ib_ucm chardev and nes driver

   - netlink based discovery of chardevs and autoloading of the modules
     providing them

   - Move more of the rdamvt/hfi1 uapi to include/uapi/rdma

   - New driver 'siw' for software based iWarp running on top of netdev,
     much like rxe's software RoCE.

   - mlx5 feature to report events in their raw devx format to userspace

   - Expose per-object counters through rdma tool

   - Adaptive interrupt moderation for RDMA (DIM), sharing the DIM core
     from netdev"

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma: (194 commits)
  RMDA/siw: Require a 64 bit arch
  RDMA/siw: Mark expected switch fall-throughs
  RDMA/core: Fix -Wunused-const-variable warnings
  rdma/siw: Remove set but not used variable 's'
  rdma/siw: Add missing dependencies on LIBCRC32C and DMA_VIRT_OPS
  RDMA/siw: Add missing rtnl_lock around access to ifa
  rdma/siw: Use proper enumerated type in map_cqe_status
  RDMA/siw: Remove unnecessary kthread create/destroy printouts
  IB/rdmavt: Fix variable shadowing issue in rvt_create_cq
  RDMA/core: Fix race when resolving IP address
  RDMA/core: Make rdma_counter.h compile stand alone
  IB/core: Work on the caller socket net namespace in nldev_newlink()
  RDMA/rxe: Fill in wc byte_len with IB_WC_RECV_RDMA_WITH_IMM
  RDMA/mlx5: Set RDMA DIM to be enabled by default
  RDMA/nldev: Added configuration of RDMA dynamic interrupt moderation to netlink
  RDMA/core: Provide RDMA DIM support for ULPs
  linux/dim: Implement RDMA adaptive moderation (DIM)
  IB/mlx5: Report correctly tag matching rendezvous capability
  docs: infiniband: add it to the driver-api bookset
  IB/mlx5: Implement VHCA tunnel mechanism in DEVX
  ...

drivers/infiniband/hw/mlx4/cq.c

@@ -172,14 +172,14 @@ err_buf:
 }
 
 #define CQ_CREATE_FLAGS_SUPPORTED IB_UVERBS_CQ_FLAGS_TIMESTAMP_COMPLETION
-struct ib_cq *mlx4_ib_create_cq(struct ib_device *ibdev,
-				const struct ib_cq_init_attr *attr,
-				struct ib_udata *udata)
+int mlx4_ib_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
+		      struct ib_udata *udata)
 {
+	struct ib_device *ibdev = ibcq->device;
 	int entries = attr->cqe;
 	int vector = attr->comp_vector;
 	struct mlx4_ib_dev *dev = to_mdev(ibdev);
-	struct mlx4_ib_cq *cq;
+	struct mlx4_ib_cq *cq = to_mcq(ibcq);
 	struct mlx4_uar *uar;
 	void *buf_addr;
 	int err;
@@ -187,14 +187,10 @@ struct ib_cq *mlx4_ib_create_cq(struct ib_device *ibdev,
 		udata, struct mlx4_ib_ucontext, ibucontext);
 
 	if (entries < 1 || entries > dev->dev->caps.max_cqes)
-		return ERR_PTR(-EINVAL);
+		return -EINVAL;
 
 	if (attr->flags & ~CQ_CREATE_FLAGS_SUPPORTED)
-		return ERR_PTR(-EINVAL);
-
-	cq = kzalloc(sizeof(*cq), GFP_KERNEL);
-	if (!cq)
-		return ERR_PTR(-ENOMEM);
+		return -EINVAL;
 
 	entries      = roundup_pow_of_two(entries + 1);
 	cq->ibcq.cqe = entries - 1;
@@ -269,7 +265,7 @@ struct ib_cq *mlx4_ib_create_cq(struct ib_device *ibdev,
 			goto err_cq_free;
 		}
 
-	return &cq->ibcq;
+	return 0;
 
 err_cq_free:
 	mlx4_cq_free(dev->dev, &cq->mcq);
@@ -281,19 +277,15 @@ err_dbmap:
 err_mtt:
 	mlx4_mtt_cleanup(dev->dev, &cq->buf.mtt);
 
-	if (udata)
-		ib_umem_release(cq->umem);
-	else
+	ib_umem_release(cq->umem);
+	if (!udata)
 		mlx4_ib_free_cq_buf(dev, &cq->buf, cq->ibcq.cqe);
 
 err_db:
 	if (!udata)
 		mlx4_db_free(dev->dev, &cq->db);
-
 err_cq:
-	kfree(cq);
-
-	return ERR_PTR(err);
+	return err;
 }
 
 static int mlx4_alloc_resize_buf(struct mlx4_ib_dev *dev, struct mlx4_ib_cq *cq,
@@ -475,18 +467,15 @@ err_buf:
 	kfree(cq->resize_buf);
 	cq->resize_buf = NULL;
 
-	if (cq->resize_umem) {
-		ib_umem_release(cq->resize_umem);
-		cq->resize_umem = NULL;
-	}
-
+	ib_umem_release(cq->resize_umem);
+	cq->resize_umem = NULL;
 out:
 	mutex_unlock(&cq->resize_mutex);
 
 	return err;
 }
 
-int mlx4_ib_destroy_cq(struct ib_cq *cq, struct ib_udata *udata)
+void mlx4_ib_destroy_cq(struct ib_cq *cq, struct ib_udata *udata)
 {
 	struct mlx4_ib_dev *dev = to_mdev(cq->device);
 	struct mlx4_ib_cq *mcq = to_mcq(cq);
@@ -501,15 +490,11 @@ int mlx4_ib_destroy_cq(struct ib_cq *cq, struct ib_udata *udata)
 				struct mlx4_ib_ucontext,
 				ibucontext),
 			&mcq->db);
-		ib_umem_release(mcq->umem);
 	} else {
 		mlx4_ib_free_cq_buf(dev, &mcq->buf, cq->cqe);
 		mlx4_db_free(dev->dev, &mcq->db);
 	}
-
-	kfree(mcq);
-
-	return 0;
+	ib_umem_release(mcq->umem);
 }
 
 static void dump_cqe(void *cqe)

drivers/infiniband/hw/mlx4/main.c

@@ -1089,7 +1089,8 @@ static int mlx4_ib_alloc_ucontext(struct ib_ucontext *uctx,
 	if (!dev->ib_active)
 		return -EAGAIN;
 
-	if (ibdev->uverbs_abi_ver == MLX4_IB_UVERBS_NO_DEV_CAPS_ABI_VERSION) {
+	if (ibdev->ops.uverbs_abi_ver ==
+	    MLX4_IB_UVERBS_NO_DEV_CAPS_ABI_VERSION) {
 		resp_v3.qp_tab_size      = dev->dev->caps.num_qps;
 		resp_v3.bf_reg_size      = dev->dev->caps.bf_reg_size;
 		resp_v3.bf_regs_per_page = dev->dev->caps.bf_regs_per_page;
@@ -1111,7 +1112,7 @@ static int mlx4_ib_alloc_ucontext(struct ib_ucontext *uctx,
 	INIT_LIST_HEAD(&context->wqn_ranges_list);
 	mutex_init(&context->wqn_ranges_mutex);
 
-	if (ibdev->uverbs_abi_ver == MLX4_IB_UVERBS_NO_DEV_CAPS_ABI_VERSION)
+	if (ibdev->ops.uverbs_abi_ver == MLX4_IB_UVERBS_NO_DEV_CAPS_ABI_VERSION)
 		err = ib_copy_to_udata(udata, &resp_v3, sizeof(resp_v3));
 	else
 		err = ib_copy_to_udata(udata, &resp, sizeof(resp));
@@ -2509,6 +2510,10 @@ static void get_fw_ver_str(struct ib_device *device, char *str)
 }
 
 static const struct ib_device_ops mlx4_ib_dev_ops = {
+	.owner = THIS_MODULE,
+	.driver_id = RDMA_DRIVER_MLX4,
+	.uverbs_abi_ver = MLX4_IB_UVERBS_ABI_VERSION,
+
 	.add_gid = mlx4_ib_add_gid,
 	.alloc_mr = mlx4_ib_alloc_mr,
 	.alloc_pd = mlx4_ib_alloc_pd,
@@ -2560,6 +2565,7 @@ static const struct ib_device_ops mlx4_ib_dev_ops = {
 	.resize_cq = mlx4_ib_resize_cq,
 
 	INIT_RDMA_OBJ_SIZE(ib_ah, mlx4_ib_ah, ibah),
+	INIT_RDMA_OBJ_SIZE(ib_cq, mlx4_ib_cq, ibcq),
 	INIT_RDMA_OBJ_SIZE(ib_pd, mlx4_ib_pd, ibpd),
 	INIT_RDMA_OBJ_SIZE(ib_srq, mlx4_ib_srq, ibsrq),
 	INIT_RDMA_OBJ_SIZE(ib_ucontext, mlx4_ib_ucontext, ibucontext),
@@ -2642,7 +2648,6 @@ static void *mlx4_ib_add(struct mlx4_dev *dev)
 	ibdev->dev = dev;
 	ibdev->bond_next_port	= 0;
 
-	ibdev->ib_dev.owner		= THIS_MODULE;
 	ibdev->ib_dev.node_type		= RDMA_NODE_IB_CA;
 	ibdev->ib_dev.local_dma_lkey	= dev->caps.reserved_lkey;
 	ibdev->num_ports		= num_ports;
@@ -2651,11 +2656,6 @@ static void *mlx4_ib_add(struct mlx4_dev *dev)
 	ibdev->ib_dev.num_comp_vectors	= dev->caps.num_comp_vectors;
 	ibdev->ib_dev.dev.parent	= &dev->persist->pdev->dev;
 
-	if (dev->caps.userspace_caps)
-		ibdev->ib_dev.uverbs_abi_ver = MLX4_IB_UVERBS_ABI_VERSION;
-	else
-		ibdev->ib_dev.uverbs_abi_ver = MLX4_IB_UVERBS_NO_DEV_CAPS_ABI_VERSION;
-
 	ibdev->ib_dev.uverbs_cmd_mask	=
 		(1ull << IB_USER_VERBS_CMD_GET_CONTEXT)		|
 		(1ull << IB_USER_VERBS_CMD_QUERY_DEVICE)	|
@@ -2729,6 +2729,10 @@ static void *mlx4_ib_add(struct mlx4_dev *dev)
 		ib_set_device_ops(&ibdev->ib_dev, &mlx4_ib_dev_fs_ops);
 	}
 
+	if (!dev->caps.userspace_caps)
+		ibdev->ib_dev.ops.uverbs_abi_ver =
+			MLX4_IB_UVERBS_NO_DEV_CAPS_ABI_VERSION;
+
 	mlx4_ib_alloc_eqs(dev, ibdev);
 
 	spin_lock_init(&iboe->lock);
@@ -2839,7 +2843,6 @@ static void *mlx4_ib_add(struct mlx4_dev *dev)
 		goto err_steer_free_bitmap;
 
 	rdma_set_device_sysfs_group(&ibdev->ib_dev, &mlx4_attr_group);
-	ibdev->ib_dev.driver_id = RDMA_DRIVER_MLX4;
 	if (ib_register_device(&ibdev->ib_dev, "mlx4_%d"))
 		goto err_diag_counters;
 

drivers/infiniband/hw/mlx4/mlx4_ib.h

@@ -743,10 +743,9 @@ int mlx4_ib_map_mr_sg(struct ib_mr *ibmr, struct scatterlist *sg, int sg_nents,
 		      unsigned int *sg_offset);
 int mlx4_ib_modify_cq(struct ib_cq *cq, u16 cq_count, u16 cq_period);
 int mlx4_ib_resize_cq(struct ib_cq *ibcq, int entries, struct ib_udata *udata);
-struct ib_cq *mlx4_ib_create_cq(struct ib_device *ibdev,
-				const struct ib_cq_init_attr *attr,
-				struct ib_udata *udata);
-int mlx4_ib_destroy_cq(struct ib_cq *cq, struct ib_udata *udata);
+int mlx4_ib_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
+		      struct ib_udata *udata);
+void mlx4_ib_destroy_cq(struct ib_cq *cq, struct ib_udata *udata);
 int mlx4_ib_poll_cq(struct ib_cq *ibcq, int num_entries, struct ib_wc *wc);
 int mlx4_ib_arm_cq(struct ib_cq *cq, enum ib_cq_notify_flags flags);
 void __mlx4_ib_cq_clean(struct mlx4_ib_cq *cq, u32 qpn, struct mlx4_ib_srq *srq);
@@ -907,7 +906,7 @@ void mlx4_ib_sl2vl_update(struct mlx4_ib_dev *mdev, int port);
 struct ib_wq *mlx4_ib_create_wq(struct ib_pd *pd,
 				struct ib_wq_init_attr *init_attr,
 				struct ib_udata *udata);
-int mlx4_ib_destroy_wq(struct ib_wq *wq, struct ib_udata *udata);
+void mlx4_ib_destroy_wq(struct ib_wq *wq, struct ib_udata *udata);
 int mlx4_ib_modify_wq(struct ib_wq *wq, struct ib_wq_attr *wq_attr,
 		      u32 wq_attr_mask, struct ib_udata *udata);
 

drivers/infiniband/hw/mlx4/mr.c

@@ -258,7 +258,7 @@ int mlx4_ib_umem_calc_optimal_mtt_size(struct ib_umem *umem, u64 start_va,
 				       int *num_of_mtts)
 {
 	u64 block_shift = MLX4_MAX_MTT_SHIFT;
-	u64 min_shift = umem->page_shift;
+	u64 min_shift = PAGE_SHIFT;
 	u64 last_block_aligned_end = 0;
 	u64 current_block_start = 0;
 	u64 first_block_start = 0;
@@ -295,8 +295,8 @@ int mlx4_ib_umem_calc_optimal_mtt_size(struct ib_umem *umem, u64 start_va,
 			 * in access to the wrong data.
 			 */
 			misalignment_bits =
-			(start_va & (~(((u64)(BIT(umem->page_shift))) - 1ULL)))
-			^ current_block_start;
+				(start_va & (~(((u64)(PAGE_SIZE)) - 1ULL))) ^
+				current_block_start;
 			block_shift = min(alignment_of(misalignment_bits),
 					  block_shift);
 		}
@@ -368,8 +368,7 @@ end:
 }
 
 static struct ib_umem *mlx4_get_umem_mr(struct ib_udata *udata, u64 start,
-					u64 length, u64 virt_addr,
-					int access_flags)
+					u64 length, int access_flags)
 {
 	/*
 	 * Force registering the memory as writable if the underlying pages
@@ -415,8 +414,7 @@ struct ib_mr *mlx4_ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 	if (!mr)
 		return ERR_PTR(-ENOMEM);
 
-	mr->umem =
-		mlx4_get_umem_mr(udata, start, length, virt_addr, access_flags);
+	mr->umem = mlx4_get_umem_mr(udata, start, length, access_flags);
 	if (IS_ERR(mr->umem)) {
 		err = PTR_ERR(mr->umem);
 		goto err_free;
@@ -505,7 +503,7 @@ int mlx4_ib_rereg_user_mr(struct ib_mr *mr, int flags,
 
 		mlx4_mr_rereg_mem_cleanup(dev->dev, &mmr->mmr);
 		ib_umem_release(mmr->umem);
-		mmr->umem = mlx4_get_umem_mr(udata, start, length, virt_addr,
+		mmr->umem = mlx4_get_umem_mr(udata, start, length,
 					     mr_access_flags);
 		if (IS_ERR(mmr->umem)) {
 			err = PTR_ERR(mmr->umem);
@@ -514,7 +512,7 @@ int mlx4_ib_rereg_user_mr(struct ib_mr *mr, int flags,
 			goto release_mpt_entry;
 		}
 		n = ib_umem_page_count(mmr->umem);
-		shift = mmr->umem->page_shift;
+		shift = PAGE_SHIFT;
 
 		err = mlx4_mr_rereg_mem_write(dev->dev, &mmr->mmr,
 					      virt_addr, length, n, shift,

drivers/infiniband/hw/mlx4/qp.c

@@ -1207,10 +1207,9 @@ err_mtt:
 	mlx4_mtt_cleanup(dev->dev, &qp->mtt);
 
 err_buf:
-	if (qp->umem)
-		ib_umem_release(qp->umem);
-	else
+	if (!qp->umem)
 		mlx4_buf_free(dev->dev, qp->buf_size, &qp->buf);
+	ib_umem_release(qp->umem);
 
 err_db:
 	if (!udata && qp_has_rq(init_attr))
@@ -1421,7 +1420,6 @@ static void destroy_qp_common(struct mlx4_ib_dev *dev, struct mlx4_ib_qp *qp,
 
 			mlx4_ib_db_unmap_user(mcontext, &qp->db);
 		}
-		ib_umem_release(qp->umem);
 	} else {
 		kvfree(qp->sq.wrid);
 		kvfree(qp->rq.wrid);
@@ -1432,6 +1430,7 @@ static void destroy_qp_common(struct mlx4_ib_dev *dev, struct mlx4_ib_qp *qp,
 		if (qp->rq.wqe_cnt)
 			mlx4_db_free(dev->dev, &qp->db);
 	}
+	ib_umem_release(qp->umem);
 
 	del_gid_entries(qp);
 }
@@ -4248,7 +4247,7 @@ int mlx4_ib_modify_wq(struct ib_wq *ibwq, struct ib_wq_attr *wq_attr,
 	return err;
 }
 
-int mlx4_ib_destroy_wq(struct ib_wq *ibwq, struct ib_udata *udata)
+void mlx4_ib_destroy_wq(struct ib_wq *ibwq, struct ib_udata *udata)
 {
 	struct mlx4_ib_dev *dev = to_mdev(ibwq->device);
 	struct mlx4_ib_qp *qp = to_mqp((struct ib_qp *)ibwq);
@@ -4259,8 +4258,6 @@ int mlx4_ib_destroy_wq(struct ib_wq *ibwq, struct ib_udata *udata)
 	destroy_qp_common(dev, qp, MLX4_IB_RWQ_SRC, udata);
 
 	kfree(qp);
-
-	return 0;
 }
 
 struct ib_rwq_ind_table

drivers/infiniband/hw/mlx4/srq.c

@@ -115,7 +115,7 @@ int mlx4_ib_create_srq(struct ib_srq *ib_srq,
 			return PTR_ERR(srq->umem);
 
 		err = mlx4_mtt_init(dev->dev, ib_umem_page_count(srq->umem),
-				    srq->umem->page_shift, &srq->mtt);
+				    PAGE_SHIFT, &srq->mtt);
 		if (err)
 			goto err_buf;
 
@@ -204,10 +204,9 @@ err_mtt:
 	mlx4_mtt_cleanup(dev->dev, &srq->mtt);
 
 err_buf:
-	if (srq->umem)
-		ib_umem_release(srq->umem);
-	else
+	if (!srq->umem)
 		mlx4_buf_free(dev->dev, buf_size, &srq->buf);
+	ib_umem_release(srq->umem);
 
 err_db:
 	if (!udata)
@@ -275,13 +274,13 @@ void mlx4_ib_destroy_srq(struct ib_srq *srq, struct ib_udata *udata)
 				struct mlx4_ib_ucontext,
 				ibucontext),
 			&msrq->db);
-		ib_umem_release(msrq->umem);
 	} else {
 		kvfree(msrq->wrid);
 		mlx4_buf_free(dev->dev, msrq->msrq.max << msrq->msrq.wqe_shift,
 			      &msrq->buf);
 		mlx4_db_free(dev->dev, &msrq->db);
 	}
+	ib_umem_release(msrq->umem);
 }
 
 void mlx4_ib_free_srq_wqe(struct mlx4_ib_srq *srq, int wqe_index)