RDMA: Explicitly pass in the dma_device to ib_register_device

The code in setup_dma_device has become rather convoluted, move all of
this to the drivers. Drives now pass in a DMA capable struct device which
will be used to setup DMA, or drivers must fully configure the ibdev for
DMA and pass in NULL.

Other than setting the masks in rvt all drivers were doing this already
anyhow.

mthca, mlx4 and mlx5 were already setting up maximum DMA segment size for
DMA based on their hardweare limits in:
__mthca_init_one()
  dma_set_max_seg_size (1G)

__mlx4_init_one()
  dma_set_max_seg_size (1G)

mlx5_pci_init()
  set_dma_caps()
    dma_set_max_seg_size (2G)

Other non software drivers (except usnic) were extended to UINT_MAX [1, 2]
instead of 2G as was before.

[1] https://lore.kernel.org/linux-rdma/20200924114940.GE9475@nvidia.com/
[2] https://lore.kernel.org/linux-rdma/20200924114940.GE9475@nvidia.com/

Link: https://lore.kernel.org/r/20201008082752.275846-1-leon@kernel.org
Link: https://lore.kernel.org/r/6b2ed339933d066622d5715903870676d8cc523a.1602590106.git.mchehab+huawei@kernel.org
Suggested-by: Christoph Hellwig <hch@infradead.org>
Signed-off-by: Parav Pandit <parav@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>

drivers/infiniband/core/device.c

@@ -1177,58 +1177,23 @@ static int assign_name(struct ib_device *device, const char *name)
 	return ret;
 }
 
-static void setup_dma_device(struct ib_device *device)
+static void setup_dma_device(struct ib_device *device,
+			     struct device *dma_device)
 {
-	struct device *parent = device->dev.parent;
+	/*
-
+	 * If the caller does not provide a DMA capable device then the IB
-	WARN_ON_ONCE(device->dma_device);
+	 * device will be used. In this case the caller should fully setup the
-
+	 * ibdev for DMA. This usually means using dma_virt_ops.
-#ifdef CONFIG_DMA_OPS
+	 */
-	if (device->dev.dma_ops) {
+#ifdef CONFIG_DMA_VIRT_OPS
-		/*
+	if (!dma_device) {
-		 * The caller provided custom DMA operations. Copy the
+		device->dev.dma_ops = &dma_virt_ops;
-		 * DMA-related fields that are used by e.g. dma_alloc_coherent()
+		dma_device = &device->dev;
-		 * into device->dev.
-		 */
-		device->dma_device = &device->dev;
-		if (!device->dev.dma_mask) {
-			if (parent)
-				device->dev.dma_mask = parent->dma_mask;
-			else
-				WARN_ON_ONCE(true);
-		}
-		if (!device->dev.coherent_dma_mask) {
-			if (parent)
-				device->dev.coherent_dma_mask =
-					parent->coherent_dma_mask;
-			else
-				WARN_ON_ONCE(true);
-		}
-	} else
-#endif /* CONFIG_DMA_OPS */
-	{
-		/*
-		 * The caller did not provide custom DMA operations. Use the
-		 * DMA mapping operations of the parent device.
-		 */
-		WARN_ON_ONCE(!parent);
-		device->dma_device = parent;
-	}
-
-	if (!device->dev.dma_parms) {
-		if (parent) {
-			/*
-			 * The caller did not provide DMA parameters, so
-			 * 'parent' probably represents a PCI device. The PCI
-			 * core sets the maximum segment size to 64
-			 * KB. Increase this parameter to 2 GB.
-			 */
-			device->dev.dma_parms = parent->dma_parms;
-			dma_set_max_seg_size(device->dma_device, SZ_2G);
-		} else {
-			WARN_ON_ONCE(true);
-		}
 	}
+#endif
+	WARN_ON(!dma_device);
+	device->dma_device = dma_device;
+	WARN_ON(!device->dma_device->dma_parms);
 }
 
 /*
@@ -1241,7 +1206,6 @@ static int setup_device(struct ib_device *device)
 	struct ib_udata uhw = {.outlen = 0, .inlen = 0};
 	int ret;
 
-	setup_dma_device(device);
 	ib_device_check_mandatory(device);
 
 	ret = setup_port_data(device);
@@ -1354,7 +1318,10 @@ static void prevent_dealloc_device(struct ib_device *ib_dev)
  * ib_register_device - Register an IB device with IB core
  * @device: Device to register
  * @name: unique string device name. This may include a '%' which will
- * cause a unique index to be added to the passed device name.
+ * 	  cause a unique index to be added to the passed device name.
+ * @dma_device: pointer to a DMA-capable device. If %NULL, then the IB
+ *	        device will be used. In this case the caller should fully
+ *		setup the ibdev for DMA. This usually means using dma_virt_ops.
  *
  * Low-level drivers use ib_register_device() to register their
  * devices with the IB core.  All registered clients will receive a
@@ -1365,7 +1332,8 @@ static void prevent_dealloc_device(struct ib_device *ib_dev)
  * asynchronously then the device pointer may become freed as soon as this
  * function returns.
  */
-int ib_register_device(struct ib_device *device, const char *name)
+int ib_register_device(struct ib_device *device, const char *name,
+		       struct device *dma_device)
 {
 	int ret;
 
@@ -1373,6 +1341,7 @@ int ib_register_device(struct ib_device *device, const char *name)
 	if (ret)
 		return ret;
 
+	setup_dma_device(device, dma_device);
 	ret = setup_device(device);
 	if (ret)
 		return ret;

drivers/infiniband/hw/bnxt_re/main.c

@@ -736,7 +736,8 @@ static int bnxt_re_register_ib(struct bnxt_re_dev *rdev)
 	if (ret)
 		return ret;
 
-	return ib_register_device(ibdev, "bnxt_re%d");
+	dma_set_max_seg_size(&rdev->en_dev->pdev->dev, UINT_MAX);
+	return ib_register_device(ibdev, "bnxt_re%d", &rdev->en_dev->pdev->dev);
 }
 
 static void bnxt_re_dev_remove(struct bnxt_re_dev *rdev)

drivers/infiniband/hw/cxgb4/provider.c

@@ -570,7 +570,9 @@ void c4iw_register_device(struct work_struct *work)
 	ret = set_netdevs(&dev->ibdev, &dev->rdev);
 	if (ret)
 		goto err_dealloc_ctx;
-	ret = ib_register_device(&dev->ibdev, "cxgb4_%d");
+	dma_set_max_seg_size(&dev->rdev.lldi.pdev->dev, UINT_MAX);
+	ret = ib_register_device(&dev->ibdev, "cxgb4_%d",
+				 &dev->rdev.lldi.pdev->dev);
 	if (ret)
 		goto err_dealloc_ctx;
 	return;

drivers/infiniband/hw/efa/efa_main.c

@@ -331,7 +331,7 @@ static int efa_ib_device_add(struct efa_dev *dev)
 
 	ib_set_device_ops(&dev->ibdev, &efa_dev_ops);
 
-	err = ib_register_device(&dev->ibdev, "efa_%d");
+	err = ib_register_device(&dev->ibdev, "efa_%d", &pdev->dev);
 	if (err)
 		goto err_release_doorbell_bar;
 
@@ -418,7 +418,7 @@ static int efa_device_init(struct efa_com_dev *edev, struct pci_dev *pdev)
 			err);
 		return err;
 	}
-
+	dma_set_max_seg_size(&pdev->dev, UINT_MAX);
 	return 0;
 }
 

drivers/infiniband/hw/hns/hns_roce_main.c

@@ -549,7 +549,8 @@ static int hns_roce_register_device(struct hns_roce_dev *hr_dev)
 		if (ret)
 			return ret;
 	}
-	ret = ib_register_device(ib_dev, "hns_%d");
+	dma_set_max_seg_size(dev, UINT_MAX);
+	ret = ib_register_device(ib_dev, "hns_%d", dev);
 	if (ret) {
 		dev_err(dev, "ib_register_device failed!\n");
 		return ret;

drivers/infiniband/hw/i40iw/i40iw_verbs.c

@@ -2761,7 +2761,8 @@ int i40iw_register_rdma_device(struct i40iw_device *iwdev)
 	if (ret)
 		goto error;
 
-	ret = ib_register_device(&iwibdev->ibdev, "i40iw%d");
+	dma_set_max_seg_size(&iwdev->hw.pcidev->dev, UINT_MAX);
+	ret = ib_register_device(&iwibdev->ibdev, "i40iw%d", &iwdev->hw.pcidev->dev);
 	if (ret)
 		goto error;
 

drivers/infiniband/hw/mlx4/main.c

@@ -2841,7 +2841,8 @@ 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);
-	if (ib_register_device(&ibdev->ib_dev, "mlx4_%d"))
+	if (ib_register_device(&ibdev->ib_dev, "mlx4_%d",
+			       &dev->persist->pdev->dev))
 		goto err_diag_counters;
 
 	if (mlx4_ib_mad_init(ibdev))

drivers/infiniband/hw/mlx5/main.c

@@ -4380,7 +4380,7 @@ static int mlx5_ib_stage_ib_reg_init(struct mlx5_ib_dev *dev)
 		name = "mlx5_%d";
 	else
 		name = "mlx5_bond_%d";
-	return ib_register_device(&dev->ib_dev, name);
+	return ib_register_device(&dev->ib_dev, name, &dev->mdev->pdev->dev);
 }
 
 static void mlx5_ib_stage_pre_ib_reg_umr_cleanup(struct mlx5_ib_dev *dev)

drivers/infiniband/hw/mthca/mthca_provider.c

@@ -1206,7 +1206,7 @@ int mthca_register_device(struct mthca_dev *dev)
 	mutex_init(&dev->cap_mask_mutex);
 
 	rdma_set_device_sysfs_group(&dev->ib_dev, &mthca_attr_group);
-	ret = ib_register_device(&dev->ib_dev, "mthca%d");
+	ret = ib_register_device(&dev->ib_dev, "mthca%d", &dev->pdev->dev);
 	if (ret)
 		return ret;
 

drivers/infiniband/hw/ocrdma/ocrdma_main.c

@@ -255,7 +255,9 @@ static int ocrdma_register_device(struct ocrdma_dev *dev)
 	if (ret)
 		return ret;
 
-	return ib_register_device(&dev->ibdev, "ocrdma%d");
+	dma_set_max_seg_size(&dev->nic_info.pdev->dev, UINT_MAX);
+	return ib_register_device(&dev->ibdev, "ocrdma%d",
+				  &dev->nic_info.pdev->dev);
 }
 
 static int ocrdma_alloc_resources(struct ocrdma_dev *dev)

drivers/infiniband/hw/qedr/main.c

@@ -293,7 +293,8 @@ static int qedr_register_device(struct qedr_dev *dev)
 	if (rc)
 		return rc;
 
-	return ib_register_device(&dev->ibdev, "qedr%d");
+	dma_set_max_seg_size(&dev->pdev->dev, UINT_MAX);
+	return ib_register_device(&dev->ibdev, "qedr%d", &dev->pdev->dev);
 }
 
 /* This function allocates fast-path status block memory */

drivers/infiniband/hw/usnic/usnic_ib_main.c

@@ -425,7 +425,8 @@ static void *usnic_ib_device_add(struct pci_dev *dev)
 	if (ret)
 		goto err_fwd_dealloc;
 
-	if (ib_register_device(&us_ibdev->ib_dev, "usnic_%d"))
+	dma_set_max_seg_size(&dev->dev, SZ_2G);
+	if (ib_register_device(&us_ibdev->ib_dev, "usnic_%d", &dev->dev))
 		goto err_fwd_dealloc;
 
 	usnic_fwd_set_mtu(us_ibdev->ufdev, us_ibdev->netdev->mtu);

drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c

@@ -270,7 +270,7 @@ static int pvrdma_register_device(struct pvrdma_dev *dev)
 	spin_lock_init(&dev->srq_tbl_lock);
 	rdma_set_device_sysfs_group(&dev->ib_dev, &pvrdma_attr_group);
 
-	ret = ib_register_device(&dev->ib_dev, "vmw_pvrdma%d");
+	ret = ib_register_device(&dev->ib_dev, "vmw_pvrdma%d", &dev->pdev->dev);
 	if (ret)
 		goto err_srq_free;
 
@@ -854,7 +854,7 @@ static int pvrdma_pci_probe(struct pci_dev *pdev,
 			goto err_free_resource;
 		}
 	}
-
+	dma_set_max_seg_size(&pdev->dev, UINT_MAX);
 	pci_set_master(pdev);
 
 	/* Map register space */

drivers/infiniband/sw/rdmavt/vt.c

@@ -579,7 +579,9 @@ int rvt_register_device(struct rvt_dev_info *rdi)
 	spin_lock_init(&rdi->n_cqs_lock);
 
 	/* DMA Operations */
-	rdi->ibdev.dev.dma_ops = rdi->ibdev.dev.dma_ops ? : &dma_virt_ops;
+	rdi->ibdev.dev.dma_parms = rdi->ibdev.dev.parent->dma_parms;
+	dma_set_coherent_mask(&rdi->ibdev.dev,
+			      rdi->ibdev.dev.parent->coherent_dma_mask);
 
 	/* Protection Domain */
 	spin_lock_init(&rdi->n_pds_lock);
@@ -627,7 +629,7 @@ int rvt_register_device(struct rvt_dev_info *rdi)
 		rdi->ibdev.num_comp_vectors = 1;
 
 	/* We are now good to announce we exist */
-	ret = ib_register_device(&rdi->ibdev, dev_name(&rdi->ibdev.dev));
+	ret = ib_register_device(&rdi->ibdev, dev_name(&rdi->ibdev.dev), NULL);
 	if (ret) {
 		rvt_pr_err(rdi, "Failed to register driver with ib core.\n");
 		goto bail_wss;

drivers/infiniband/sw/rxe/rxe_verbs.c

@@ -1128,12 +1128,9 @@ int rxe_register_device(struct rxe_dev *rxe, const char *ibdev_name)
 	dev->local_dma_lkey = 0;
 	addrconf_addr_eui48((unsigned char *)&dev->node_guid,
 			    rxe->ndev->dev_addr);
-	dev->dev.dma_ops = &dma_virt_ops;
 	dev->dev.dma_parms = &rxe->dma_parms;
-	rxe->dma_parms = (struct device_dma_parameters)
+	dma_set_max_seg_size(&dev->dev, UINT_MAX);
-		{ .max_segment_size = SZ_2G };
+	dma_set_coherent_mask(&dev->dev, dma_get_required_mask(&dev->dev));
-	dma_coerce_mask_and_coherent(&dev->dev,
-				     dma_get_required_mask(&dev->dev));
 
 	dev->uverbs_cmd_mask = BIT_ULL(IB_USER_VERBS_CMD_GET_CONTEXT)
 	    | BIT_ULL(IB_USER_VERBS_CMD_CREATE_COMP_CHANNEL)
@@ -1182,7 +1179,7 @@ int rxe_register_device(struct rxe_dev *rxe, const char *ibdev_name)
 	rxe->tfm = tfm;
 
 	rdma_set_device_sysfs_group(dev, &rxe_attr_group);
-	err = ib_register_device(dev, ibdev_name);
+	err = ib_register_device(dev, ibdev_name, NULL);
 	if (err)
 		pr_warn("%s failed with error %d\n", __func__, err);
 

drivers/infiniband/sw/siw/siw_main.c

@@ -69,7 +69,7 @@ static int siw_device_register(struct siw_device *sdev, const char *name)
 
 	sdev->vendor_part_id = dev_id++;
 
-	rv = ib_register_device(base_dev, name);
+	rv = ib_register_device(base_dev, name, NULL);
 	if (rv) {
 		pr_warn("siw: device registration error %d\n", rv);
 		return rv;
@@ -382,10 +382,10 @@ static struct siw_device *siw_device_create(struct net_device *netdev)
 	 */
 	base_dev->phys_port_cnt = 1;
 	base_dev->dev.parent = parent;
-	base_dev->dev.dma_ops = &dma_virt_ops;
 	base_dev->dev.dma_parms = &sdev->dma_parms;
-	sdev->dma_parms = (struct device_dma_parameters)
+	dma_set_max_seg_size(&base_dev->dev, UINT_MAX);
-		{ .max_segment_size = SZ_2G };
+	dma_set_coherent_mask(&base_dev->dev,
+			      dma_get_required_mask(&base_dev->dev));
 	base_dev->num_comp_vectors = num_possible_cpus();
 
 	xa_init_flags(&sdev->qp_xa, XA_FLAGS_ALLOC1);

include/rdma/ib_verbs.h

@@ -2782,7 +2782,8 @@ void ib_dealloc_device(struct ib_device *device);
 
 void ib_get_device_fw_str(struct ib_device *device, char *str);
 
-int ib_register_device(struct ib_device *device, const char *name);
+int ib_register_device(struct ib_device *device, const char *name,
+		       struct device *dma_device);
 void ib_unregister_device(struct ib_device *device);
 void ib_unregister_driver(enum rdma_driver_id driver_id);
 void ib_unregister_device_and_put(struct ib_device *device);