RDMA support for DMA handle

index 77fce5e1b830..cc64f93709a4 100644
@@ -168,7 +168,7 @@ static u32 get_st_table_loc(struct pci_dev *pdev)
  * Return the size of ST table. If ST table is not in TPH Requester Extended
  * Capability space, return 0. Otherwise return the ST Table Size + 1.
  */
-static u16 get_st_table_size(struct pci_dev *pdev)
+u16 pcie_tph_get_st_table_size(struct pci_dev *pdev)
 {
 	u32 reg;
 	u32 loc;

@@ -185,6 +185,7 @@ static u16 get_st_table_size(struct pci_dev *pdev)
 
 	return FIELD_GET(PCI_TPH_CAP_ST_MASK, reg) + 1;
 }
+EXPORT_SYMBOL(pcie_tph_get_st_table_size);
 
 /* Return device's Root Port completer capability */
 static u8 get_rp_completer_type(struct pci_dev *pdev)

@@ -211,7 +212,7 @@ static int write_tag_to_st_table(struct pci_dev *pdev, int index, u16 tag)
 	int offset;
 
 	/* Check if index is out of bound */
-	st_table_size = get_st_table_size(pdev);
+	st_table_size = pcie_tph_get_st_table_size(pdev);
 	if (index >= st_table_size)
 		return -ENXIO;
 

@@ -443,7 +444,7 @@ void pci_restore_tph_state(struct pci_dev *pdev)
 	pci_write_config_dword(pdev, pdev->tph_cap + PCI_TPH_CTRL, *cap++);
 	st_entry = (u16 *)cap;
 	offset = PCI_TPH_BASE_SIZEOF;
-	num_entries = get_st_table_size(pdev);
+	num_entries = pcie_tph_get_st_table_size(pdev);
 	for (i = 0; i < num_entries; i++) {
 		pci_write_config_word(pdev, pdev->tph_cap + offset,
 				      *st_entry++);

@@ -475,7 +476,7 @@ void pci_save_tph_state(struct pci_dev *pdev)
 	/* Save all ST entries in extended capability structure */
 	st_entry = (u16 *)cap;
 	offset = PCI_TPH_BASE_SIZEOF;
-	num_entries = get_st_table_size(pdev);
+	num_entries = pcie_tph_get_st_table_size(pdev);
 	for (i = 0; i < num_entries; i++) {
 		pci_read_config_word(pdev, pdev->tph_cap + offset,
 				     st_entry++);

@@ -499,7 +500,7 @@ void pci_tph_init(struct pci_dev *pdev)
 	if (!pdev->tph_cap)
 		return;
 
-	num_entries = get_st_table_size(pdev);
+	num_entries = pcie_tph_get_st_table_size(pdev);
 	save_size = sizeof(u32) + num_entries * sizeof(u16);
 	pci_add_ext_cap_save_buffer(pdev, PCI_EXT_CAP_ID_TPH, save_size);
 }

index c3e806c13d64..9e4e331b1603 100644
@@ -28,6 +28,7 @@ int pcie_tph_get_cpu_st(struct pci_dev *dev,
 			unsigned int cpu_uid, u16 *tag);
 void pcie_disable_tph(struct pci_dev *pdev);
 int pcie_enable_tph(struct pci_dev *pdev, int mode);
+u16 pcie_tph_get_st_table_size(struct pci_dev *pdev);
 #else
 static inline int pcie_tph_set_st_entry(struct pci_dev *pdev,
 					unsigned int index, u16 tag)

index 0e93f342be09..5bb124b8024c 100644
@@ -1859,7 +1859,9 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 	u8         reserved_at_280[0x10];
 	u8         max_wqe_sz_sq[0x10];
 
-	u8         reserved_at_2a0[0xb];
+	u8         reserved_at_2a0[0x7];
+	u8         mkey_pcie_tph[0x1];
+	u8         reserved_at_2a8[0x3];
 	u8         shampo[0x1];
 	u8         reserved_at_2ac[0x4];
 	u8         max_wqe_sz_rq[0x10];

@@ -4404,6 +4406,10 @@ enum {
 	MLX5_MKC_ACCESS_MODE_CROSSING = 0x6,
 };
 
+enum {
+	MLX5_MKC_PCIE_TPH_NO_STEERING_TAG_INDEX = 0,
+};
+
 struct mlx5_ifc_mkc_bits {
 	u8         reserved_at_0[0x1];
 	u8         free[0x1];

@@ -4455,7 +4461,11 @@ struct mlx5_ifc_mkc_bits {
 	u8         relaxed_ordering_read[0x1];
 	u8         log_page_size[0x6];
 
-	u8         reserved_at_1e0[0x20];
+	u8         reserved_at_1e0[0x5];
+	u8         pcie_tph_en[0x1];
+	u8         pcie_tph_ph[0x2];
+	u8         pcie_tph_steering_tag_index[0x8];
+	u8         reserved_at_1f0[0x10];
 };
 
 struct mlx5_ifc_pkey_bits {

162 lines not on this page · raw message

index b0043cfee29b..be3be043134f 100644
@@ -1102,6 +1102,7 @@ static int mlx5_init_once(struct mlx5_core_dev *dev)
 	}
 
 	dev->dm = mlx5_dm_create(dev);
+	dev->st = mlx5_st_create(dev);
 	dev->tracer = mlx5_fw_tracer_create(dev);
 	dev->hv_vhca = mlx5_hv_vhca_create(dev);
 	dev->rsc_dump = mlx5_rsc_dump_create(dev);

@@ -1150,6 +1151,7 @@ static void mlx5_cleanup_once(struct mlx5_core_dev *dev)
 	mlx5_rsc_dump_destroy(dev);
 	mlx5_hv_vhca_destroy(dev->hv_vhca);
 	mlx5_fw_tracer_destroy(dev->tracer);
+	mlx5_st_destroy(dev);
 	mlx5_dm_cleanup(dev);
 	mlx5_fs_core_free(dev);
 	mlx5_sf_table_cleanup(dev);

index 2e02bdea8361..1cada2f87acf 100644
@@ -300,6 +300,15 @@ int mlx5_set_mtppse(struct mlx5_core_dev *mdev, u8 pin, u8 arm, u8 mode);
 struct mlx5_dm *mlx5_dm_create(struct mlx5_core_dev *dev);
 void mlx5_dm_cleanup(struct mlx5_core_dev *dev);
 
+#ifdef CONFIG_PCIE_TPH
+struct mlx5_st *mlx5_st_create(struct mlx5_core_dev *dev);
+void mlx5_st_destroy(struct mlx5_core_dev *dev);
+#else
+static inline struct mlx5_st *
+mlx5_st_create(struct mlx5_core_dev *dev) { return NULL; }
+static inline void mlx5_st_destroy(struct mlx5_core_dev *dev) { return; }
+#endif
+
 void mlx5_toggle_port_link(struct mlx5_core_dev *dev);
 int mlx5_set_port_admin_status(struct mlx5_core_dev *dev,
 			       enum mlx5_port_status status);

index 3475d33c75f4..8c5fbfb85749 100644
@@ -36,6 +36,7 @@
 #include <linux/kernel.h>
 #include <linux/completion.h>
 #include <linux/pci.h>
+#include <linux/pci-tph.h>
 #include <linux/irq.h>
 #include <linux/spinlock_types.h>
 #include <linux/semaphore.h>

@@ -688,6 +689,7 @@ struct mlx5_fw_tracer;
 struct mlx5_vxlan;
 struct mlx5_geneve;
 struct mlx5_hv_vhca;
+struct mlx5_st;
 
 #define MLX5_LOG_SW_ICM_BLOCK_SIZE(dev) (MLX5_CAP_DEV_MEM(dev, log_sw_icm_alloc_granularity))
 #define MLX5_SW_ICM_BLOCK_SIZE(dev) (1 << MLX5_LOG_SW_ICM_BLOCK_SIZE(dev))

@@ -757,6 +759,7 @@ struct mlx5_core_dev {
 	u32			issi;
 	struct mlx5e_resources  mlx5e_res;
 	struct mlx5_dm          *dm;
+	struct mlx5_st          *st;
 	struct mlx5_vxlan       *vxlan;
 	struct mlx5_geneve      *geneve;
 	struct {

@@ -1160,6 +1163,23 @@ int mlx5_dm_sw_icm_alloc(struct mlx5_core_dev *dev, enum mlx5_sw_icm_type type,
 int mlx5_dm_sw_icm_dealloc(struct mlx5_core_dev *dev, enum mlx5_sw_icm_type type,
 			   u64 length, u16 uid, phys_addr_t addr, u32 obj_id);
 
+#ifdef CONFIG_PCIE_TPH
+int mlx5_st_alloc_index(struct mlx5_core_dev *dev, enum tph_mem_type mem_type,
+			unsigned int cpu_uid, u16 *st_index);
+int mlx5_st_dealloc_index(struct mlx5_core_dev *dev, u16 st_index);
+#else
+static inline int mlx5_st_alloc_index(struct mlx5_core_dev *dev,
+				      enum tph_mem_type mem_type,
+				      unsigned int cpu_uid, u16 *st_index)
+{
+	return -EOPNOTSUPP;
+}
+static inline int mlx5_st_dealloc_index(struct mlx5_core_dev *dev, u16 st_index)
+{
+	return -EOPNOTSUPP;
+}
+#endif
+
 struct mlx5_core_dev *mlx5_vf_get_core_dev(struct pci_dev *pdev);
 void mlx5_vf_put_core_dev(struct mlx5_core_dev *mdev);
 

index 7ebc7bd3caae..1bd4b17b5515 100644
@@ -266,6 +266,122 @@ static int UVERBS_HANDLER(UVERBS_METHOD_REG_DMABUF_MR)(
 	return ret;
 }
 
+static int UVERBS_HANDLER(UVERBS_METHOD_REG_MR)(
+	struct uverbs_attr_bundle *attrs)
+{
+	struct ib_uobject *uobj =
+		uverbs_attr_get_uobject(attrs, UVERBS_ATTR_REG_MR_HANDLE);
+	struct ib_pd *pd =
+		uverbs_attr_get_obj(attrs, UVERBS_ATTR_REG_MR_PD_HANDLE);
+	u32 valid_access_flags = IB_ACCESS_SUPPORTED;
+	u64 length, iova, fd_offset = 0, addr = 0;
+	struct ib_device *ib_dev = pd->device;
+	bool has_fd_offset = false;
+	bool has_addr = false;
+	bool has_fd = false;
+	u32 access_flags;
+	struct ib_mr *mr;
+	int fd;
+	int ret;
+
+	ret = uverbs_copy_from(&iova, attrs, UVERBS_ATTR_REG_MR_IOVA);
+	if (ret)
+		return ret;
+
+	ret = uverbs_copy_from(&length, attrs, UVERBS_ATTR_REG_MR_LENGTH);
+	if (ret)
+		return ret;
+
+	if (uverbs_attr_is_valid(attrs, UVERBS_ATTR_REG_MR_ADDR)) {
+		ret = uverbs_copy_from(&addr, attrs,
+				       UVERBS_ATTR_REG_MR_ADDR);
+		if (ret)
+			return ret;
+		has_addr = true;
+	}
+
+	if (uverbs_attr_is_valid(attrs, UVERBS_ATTR_REG_MR_FD_OFFSET)) {
+		ret = uverbs_copy_from(&fd_offset, attrs,
+				       UVERBS_ATTR_REG_MR_FD_OFFSET);
+		if (ret)
+			return ret;
+		has_fd_offset = true;
+	}
+
+	if (uverbs_attr_is_valid(attrs, UVERBS_ATTR_REG_MR_FD)) {
+		ret = uverbs_get_raw_fd(&fd, attrs,
+					UVERBS_ATTR_REG_MR_FD);
+		if (ret)
+			return ret;
+		has_fd = true;
+	}
+
+	if (has_fd) {
+		if (!ib_dev->ops.reg_user_mr_dmabuf)
+			return -EOPNOTSUPP;
+
+		/* FD requires offset and can't come with addr */
+		if (!has_fd_offset || has_addr)
+			return -EINVAL;
+
+		if ((fd_offset & ~PAGE_MASK) != (iova & ~PAGE_MASK))
+			return -EINVAL;
+
+		valid_access_flags = IB_ACCESS_LOCAL_WRITE |
+				     IB_ACCESS_REMOTE_READ |
+				     IB_ACCESS_REMOTE_WRITE |
+				     IB_ACCESS_REMOTE_ATOMIC |
+				     IB_ACCESS_RELAXED_ORDERING;
+	} else {
+		if (!has_addr || has_fd_offset)
+			return -EINVAL;
+
+		if ((addr & ~PAGE_MASK) != (iova & ~PAGE_MASK))
+			return -EINVAL;
+	}
+
+	ret = uverbs_get_flags32(&access_flags, attrs,
+				 UVERBS_ATTR_REG_MR_ACCESS_FLAGS,
+				 valid_access_flags);
+	if (ret)
+		return ret;
+
+	ret = ib_check_mr_access(ib_dev, access_flags);
+	if (ret)
+		return ret;
+
+	if (has_fd)
+		mr = pd->device->ops.reg_user_mr_dmabuf(pd, fd_offset, length, iova,
+							fd, access_flags, attrs);
+	else
+		mr = pd->device->ops.reg_user_mr(pd, addr, length,
+						 iova, access_flags, NULL);
+
+	if (IS_ERR(mr))
+		return PTR_ERR(mr);
+
+	mr->device = pd->device;
+	mr->pd = pd;
+	mr->type = IB_MR_TYPE_USER;
+	mr->uobject = uobj;
+	atomic_inc(&pd->usecnt);
+	rdma_restrack_new(&mr->res, RDMA_RESTRACK_MR);
+	rdma_restrack_set_name(&mr->res, NULL);
+	rdma_restrack_add(&mr->res);
+	uobj->object = mr;
+
+	uverbs_finalize_uobj_create(attrs, UVERBS_ATTR_REG_MR_HANDLE);
+
+	ret = uverbs_copy_to(attrs, UVERBS_ATTR_REG_MR_RESP_LKEY,
+			     &mr->lkey, sizeof(mr->lkey));
+	if (ret)
+		return ret;
+
+	ret = uverbs_copy_to(attrs, UVERBS_ATTR_REG_MR_RESP_RKEY,
+			     &mr->rkey, sizeof(mr->rkey));
+	return ret;
+}
+
 DECLARE_UVERBS_NAMED_METHOD(
 	UVERBS_METHOD_ADVISE_MR,
 	UVERBS_ATTR_IDR(UVERBS_ATTR_ADVISE_MR_PD_HANDLE,

@@ -362,6 +478,40 @@ DECLARE_UVERBS_NAMED_METHOD(
 			    UVERBS_ATTR_TYPE(u32),
 			    UA_MANDATORY));
 
+DECLARE_UVERBS_NAMED_METHOD(
+	UVERBS_METHOD_REG_MR,
+	UVERBS_ATTR_IDR(UVERBS_ATTR_REG_MR_HANDLE,
+			UVERBS_OBJECT_MR,
+			UVERBS_ACCESS_NEW,
+			UA_MANDATORY),
+	UVERBS_ATTR_IDR(UVERBS_ATTR_REG_MR_PD_HANDLE,
+			UVERBS_OBJECT_PD,
+			UVERBS_ACCESS_READ,
+			UA_MANDATORY),
+	UVERBS_ATTR_PTR_IN(UVERBS_ATTR_REG_MR_IOVA,
+			   UVERBS_ATTR_TYPE(u64),
+			   UA_MANDATORY),
+	UVERBS_ATTR_PTR_IN(UVERBS_ATTR_REG_MR_LENGTH,
+			   UVERBS_ATTR_TYPE(u64),
+			   UA_MANDATORY),
+	UVERBS_ATTR_FLAGS_IN(UVERBS_ATTR_REG_MR_ACCESS_FLAGS,
+			     enum ib_access_flags,
+			     UA_MANDATORY),
+	UVERBS_ATTR_PTR_IN(UVERBS_ATTR_REG_MR_ADDR,
+			   UVERBS_ATTR_TYPE(u64),
+			   UA_OPTIONAL),
+	UVERBS_ATTR_PTR_IN(UVERBS_ATTR_REG_MR_FD_OFFSET,
+			   UVERBS_ATTR_TYPE(u64),
+			   UA_OPTIONAL),
+	UVERBS_ATTR_RAW_FD(UVERBS_ATTR_REG_MR_FD,
+			   UA_OPTIONAL),
+	UVERBS_ATTR_PTR_OUT(UVERBS_ATTR_REG_MR_RESP_LKEY,
+			    UVERBS_ATTR_TYPE(u32),
+			    UA_MANDATORY),
+	UVERBS_ATTR_PTR_OUT(UVERBS_ATTR_REG_MR_RESP_RKEY,
+			    UVERBS_ATTR_TYPE(u32),
+			    UA_MANDATORY));
+
 DECLARE_UVERBS_NAMED_METHOD_DESTROY(
 	UVERBS_METHOD_MR_DESTROY,
 	UVERBS_ATTR_IDR(UVERBS_ATTR_DESTROY_MR_HANDLE,

@@ -376,7 +526,8 @@ DECLARE_UVERBS_NAMED_OBJECT(
 	&UVERBS_METHOD(UVERBS_METHOD_DM_MR_REG),
 	&UVERBS_METHOD(UVERBS_METHOD_MR_DESTROY),
 	&UVERBS_METHOD(UVERBS_METHOD_QUERY_MR),
-	&UVERBS_METHOD(UVERBS_METHOD_REG_DMABUF_MR));
+	&UVERBS_METHOD(UVERBS_METHOD_REG_DMABUF_MR),
+	&UVERBS_METHOD(UVERBS_METHOD_REG_MR));
 
 const struct uapi_definition uverbs_def_obj_mr[] = {
 	UAPI_DEF_CHAIN_OBJ_TREE_NAMED(UVERBS_OBJECT_MR,

index ac7b162611ed..e7b827e281d1 100644
@@ -253,6 +253,7 @@ enum uverbs_methods_mr {
 	UVERBS_METHOD_ADVISE_MR,
 	UVERBS_METHOD_QUERY_MR,
 	UVERBS_METHOD_REG_DMABUF_MR,
+	UVERBS_METHOD_REG_MR,
 };
 
 enum uverbs_attrs_mr_destroy_ids {

@@ -286,6 +287,19 @@ enum uverbs_attrs_reg_dmabuf_mr_cmd_attr_ids {
 	UVERBS_ATTR_REG_DMABUF_MR_RESP_RKEY,
 };
 
+enum uverbs_attrs_reg_mr_cmd_attr_ids {
+	UVERBS_ATTR_REG_MR_HANDLE,
+	UVERBS_ATTR_REG_MR_PD_HANDLE,
+	UVERBS_ATTR_REG_MR_IOVA,
+	UVERBS_ATTR_REG_MR_ADDR,
+	UVERBS_ATTR_REG_MR_LENGTH,
+	UVERBS_ATTR_REG_MR_ACCESS_FLAGS,
+	UVERBS_ATTR_REG_MR_FD,
+	UVERBS_ATTR_REG_MR_FD_OFFSET,
+	UVERBS_ATTR_REG_MR_RESP_LKEY,
+	UVERBS_ATTR_REG_MR_RESP_RKEY,
+};
+
 enum uverbs_attrs_create_counters_cmd_attr_ids {
 	UVERBS_ATTR_CREATE_COUNTERS_HANDLE,
 };

index 1ca6a9b7ba1a..4a98afbf8430 100644
@@ -2708,6 +2708,7 @@ void ib_set_device_ops(struct ib_device *dev, const struct ib_device_ops *ops)
 	SET_DEVICE_OP(dev_ops, add_sub_dev);
 	SET_DEVICE_OP(dev_ops, advise_mr);
 	SET_DEVICE_OP(dev_ops, alloc_dm);
+	SET_DEVICE_OP(dev_ops, alloc_dmah);
 	SET_DEVICE_OP(dev_ops, alloc_hw_device_stats);
 	SET_DEVICE_OP(dev_ops, alloc_hw_port_stats);
 	SET_DEVICE_OP(dev_ops, alloc_mr);

@@ -2735,6 +2736,7 @@ void ib_set_device_ops(struct ib_device *dev, const struct ib_device_ops *ops)
 	SET_DEVICE_OP(dev_ops, create_user_ah);
 	SET_DEVICE_OP(dev_ops, create_wq);
 	SET_DEVICE_OP(dev_ops, dealloc_dm);
+	SET_DEVICE_OP(dev_ops, dealloc_dmah);
 	SET_DEVICE_OP(dev_ops, dealloc_driver);
 	SET_DEVICE_OP(dev_ops, dealloc_mw);
 	SET_DEVICE_OP(dev_ops, dealloc_pd);

@@ -2832,6 +2834,7 @@ void ib_set_device_ops(struct ib_device *dev, const struct ib_device_ops *ops)
 	SET_OBJ_SIZE(dev_ops, ib_ah);
 	SET_OBJ_SIZE(dev_ops, ib_counters);
 	SET_OBJ_SIZE(dev_ops, ib_cq);
+	SET_OBJ_SIZE(dev_ops, ib_dmah);
 	SET_OBJ_SIZE(dev_ops, ib_mw);
 	SET_OBJ_SIZE(dev_ops, ib_pd);
 	SET_OBJ_SIZE(dev_ops, ib_qp);

index 33706dad6c0f..a59b087611cb 100644
@@ -156,6 +156,7 @@ extern const struct uapi_definition uverbs_def_obj_counters[];
 extern const struct uapi_definition uverbs_def_obj_cq[];
 extern const struct uapi_definition uverbs_def_obj_device[];
 extern const struct uapi_definition uverbs_def_obj_dm[];
+extern const struct uapi_definition uverbs_def_obj_dmah[];
 extern const struct uapi_definition uverbs_def_obj_flow_action[];
 extern const struct uapi_definition uverbs_def_obj_intf[];
 extern const struct uapi_definition uverbs_def_obj_mr[];

index 3313410014cd..a7de6f403fca 100644
@@ -100,6 +100,8 @@ static struct ib_device *res_to_dev(struct rdma_restrack_entry *res)
 		return container_of(res, struct rdma_counter, res)->device;
 	case RDMA_RESTRACK_SRQ:
 		return container_of(res, struct ib_srq, res)->device;
+	case RDMA_RESTRACK_DMAH:
+		return container_of(res, struct ib_dmah, res)->device;
 	default:
 		WARN_ONCE(true, "Wrong resource tracking type %u\n", res->type);
 		return NULL;

151 lines not on this page · raw message

index a02916a3a79c..e00ea63175bd 100644
@@ -631,6 +631,7 @@ static const struct uapi_definition uverbs_core_api[] = {
 	UAPI_DEF_CHAIN(uverbs_def_obj_cq),
 	UAPI_DEF_CHAIN(uverbs_def_obj_device),
 	UAPI_DEF_CHAIN(uverbs_def_obj_dm),
+	UAPI_DEF_CHAIN(uverbs_def_obj_dmah),
 	UAPI_DEF_CHAIN(uverbs_def_obj_flow_action),
 	UAPI_DEF_CHAIN(uverbs_def_obj_intf),
 	UAPI_DEF_CHAIN(uverbs_def_obj_mr),

index 010594dc755b..d7ee762b87e9 100644
@@ -42,6 +42,7 @@
 #include <rdma/signature.h>
 #include <uapi/rdma/rdma_user_ioctl.h>
 #include <uapi/rdma/ib_user_ioctl_verbs.h>
+#include <linux/pci-tph.h>
 
 #define IB_FW_VERSION_NAME_MAX	ETHTOOL_FWVERS_LEN
 

@@ -1846,6 +1847,29 @@ struct ib_dm {
 	atomic_t	   usecnt;
 };
 
+/* bit values to mark existence of ib_dmah fields */
+enum {
+	IB_DMAH_CPU_ID_EXISTS,
+	IB_DMAH_MEM_TYPE_EXISTS,
+	IB_DMAH_PH_EXISTS,
+};
+
+struct ib_dmah {
+	struct ib_device *device;
+	u32 cpu_id;
+	enum tph_mem_type mem_type;
+	u8 ph;
+	struct ib_uobject *uobject;
+
+	u8 valid_fields; /* use IB_DMAH_XXX_EXISTS */
+	atomic_t usecnt;
+
+	/*
+	 * Implementation details of the RDMA core, don't use in drivers:
+	 */
+	struct rdma_restrack_entry res;
+};
+
 struct ib_mr {
 	struct ib_device  *device;
 	struct ib_pd	  *pd;

@@ -2569,6 +2593,9 @@ struct ib_device_ops {
 				  struct ib_dm_alloc_attr *attr,
 				  struct uverbs_attr_bundle *attrs);
 	int (*dealloc_dm)(struct ib_dm *dm, struct uverbs_attr_bundle *attrs);
+	int (*alloc_dmah)(struct ib_dmah *ibdmah,
+			  struct uverbs_attr_bundle *attrs);
+	int (*dealloc_dmah)(struct ib_dmah *dmah, struct uverbs_attr_bundle *attrs);
 	struct ib_mr *(*reg_dm_mr)(struct ib_pd *pd, struct ib_dm *dm,
 				   struct ib_dm_mr_attr *attr,
 				   struct uverbs_attr_bundle *attrs);

@@ -2726,6 +2753,7 @@ struct ib_device_ops {
 	DECLARE_RDMA_OBJ_SIZE(ib_ah);
 	DECLARE_RDMA_OBJ_SIZE(ib_counters);
 	DECLARE_RDMA_OBJ_SIZE(ib_cq);
+	DECLARE_RDMA_OBJ_SIZE(ib_dmah);
 	DECLARE_RDMA_OBJ_SIZE(ib_mw);
 	DECLARE_RDMA_OBJ_SIZE(ib_pd);
 	DECLARE_RDMA_OBJ_SIZE(ib_qp);

index 0d69ded73bf2..8a9bcf77dace 100644
@@ -56,6 +56,10 @@ enum rdma_restrack_type {
 	 * @RDMA_RESTRACK_SRQ: Shared receive queue (SRQ)
 	 */
 	RDMA_RESTRACK_SRQ,
+	/**
+	 * @RDMA_RESTRACK_DMAH: DMA handle
+	 */
+	RDMA_RESTRACK_DMAH,
 	/**
 	 * @RDMA_RESTRACK_MAX: Last entry, used for array dclarations
 	 */

index e7b827e281d1..a0b1130423f0 100644
@@ -55,6 +55,7 @@ enum uverbs_default_objects {
 	UVERBS_OBJECT_DM,
 	UVERBS_OBJECT_COUNTERS,
 	UVERBS_OBJECT_ASYNC_EVENT,
+	UVERBS_OBJECT_DMAH,
 };
 
 enum {

@@ -236,6 +237,22 @@ enum uverbs_methods_dm {
 	UVERBS_METHOD_DM_FREE,
 };
 
+enum uverbs_attrs_alloc_dmah_cmd_attr_ids {
+	UVERBS_ATTR_ALLOC_DMAH_HANDLE,
+	UVERBS_ATTR_ALLOC_DMAH_CPU_ID,
+	UVERBS_ATTR_ALLOC_DMAH_TPH_MEM_TYPE,
+	UVERBS_ATTR_ALLOC_DMAH_PH,
+};
+
+enum uverbs_attrs_free_dmah_cmd_attr_ids {
+	UVERBS_ATTR_FREE_DMA_HANDLE,
+};
+
+enum uverbs_methods_dmah {
+	UVERBS_METHOD_DMAH_ALLOC,
+	UVERBS_METHOD_DMAH_FREE,
+};
+
 enum uverbs_attrs_reg_dm_mr_cmd_attr_ids {
 	UVERBS_ATTR_REG_DM_MR_HANDLE,
 	UVERBS_ATTR_REG_DM_MR_OFFSET,

54 lines not on this page · raw message

new file mode 100644
index 000000000000..68de72b4744a
@@ -0,0 +1,23 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/*
+ * Copyright (c) 2025, NVIDIA CORPORATION & AFFILIATES. All rights reserved
+ */
+
+#ifndef _MLX5_IB_DMAH_H
+#define _MLX5_IB_DMAH_H
+
+#include "mlx5_ib.h"
+
+extern const struct ib_device_ops mlx5_ib_dev_dmah_ops;
+
+struct mlx5_ib_dmah {
+	struct ib_dmah ibdmah;
+	u16 st_index;
+};
+
+static inline struct mlx5_ib_dmah *to_mdmah(struct ib_dmah *ibdmah)
+{
+	return container_of(ibdmah, struct mlx5_ib_dmah, ibdmah);
+}
+
+#endif /* _MLX5_IB_DMAH_H */

index c521bce2eeff..dbe66894b224 100644
@@ -50,6 +50,7 @@
 #include <rdma/ib_ucaps.h>
 #include "macsec.h"
 #include "data_direct.h"
+#include "dmah.h"
 
 #define UVERBS_MODULE_NAME mlx5_ib
 #include <rdma/uverbs_named_ioctl.h>

@@ -4181,6 +4182,7 @@ static const struct ib_device_ops mlx5_ib_dev_ops = {
 	INIT_RDMA_OBJ_SIZE(ib_ah, mlx5_ib_ah, ibah),
 	INIT_RDMA_OBJ_SIZE(ib_counters, mlx5_ib_mcounters, ibcntrs),
 	INIT_RDMA_OBJ_SIZE(ib_cq, mlx5_ib_cq, ibcq),
+	INIT_RDMA_OBJ_SIZE(ib_dmah, mlx5_ib_dmah, ibdmah),
 	INIT_RDMA_OBJ_SIZE(ib_pd, mlx5_ib_pd, ibpd),
 	INIT_RDMA_OBJ_SIZE(ib_qp, mlx5_ib_qp, ibqp),
 	INIT_RDMA_OBJ_SIZE(ib_srq, mlx5_ib_srq, ibsrq),

@@ -4308,6 +4310,9 @@ static int mlx5_ib_stage_caps_init(struct mlx5_ib_dev *dev)
 	    MLX5_GENERAL_OBJ_TYPES_CAP_SW_ICM)
 		ib_set_device_ops(&dev->ib_dev, &mlx5_ib_dev_dm_ops);
 
+	if (mdev->st)
+		ib_set_device_ops(&dev->ib_dev, &mlx5_ib_dev_dmah_ops);
+
 	ib_set_device_ops(&dev->ib_dev, &mlx5_ib_dev_ops);
 
 	if (IS_ENABLED(CONFIG_INFINIBAND_USER_ACCESS))

index 88aa8d4599df..ce16404cdfb8 100644
@@ -741,7 +741,7 @@ static int ib_uverbs_reg_mr(struct uverbs_attr_bundle *attrs)
 	}
 
 	mr = pd->device->ops.reg_user_mr(pd, cmd.start, cmd.length, cmd.hca_va,
-					 cmd.access_flags,
+					 cmd.access_flags, NULL,
 					 &attrs->driver_udata);
 	if (IS_ERR(mr)) {
 		ret = PTR_ERR(mr);

index 1bd4b17b5515..711ae6379509 100644
@@ -238,7 +238,7 @@ static int UVERBS_HANDLER(UVERBS_METHOD_REG_DMABUF_MR)(
 		return ret;
 
 	mr = pd->device->ops.reg_user_mr_dmabuf(pd, offset, length, iova, fd,
-						access_flags,
+						access_flags, NULL,
 						attrs);
 	if (IS_ERR(mr))
 		return PTR_ERR(mr);

@@ -276,6 +276,7 @@ static int UVERBS_HANDLER(UVERBS_METHOD_REG_MR)(
 	u32 valid_access_flags = IB_ACCESS_SUPPORTED;
 	u64 length, iova, fd_offset = 0, addr = 0;
 	struct ib_device *ib_dev = pd->device;
+	struct ib_dmah *dmah = NULL;
 	bool has_fd_offset = false;
 	bool has_addr = false;
 	bool has_fd = false;

@@ -340,6 +341,12 @@ static int UVERBS_HANDLER(UVERBS_METHOD_REG_MR)(
 			return -EINVAL;
 	}
 
+	if (uverbs_attr_is_valid(attrs, UVERBS_ATTR_REG_MR_DMA_HANDLE)) {
+		dmah = uverbs_attr_get_obj(attrs, UVERBS_ATTR_REG_MR_DMA_HANDLE);
+		if (IS_ERR(dmah))
+			return PTR_ERR(dmah);
+	}
+
 	ret = uverbs_get_flags32(&access_flags, attrs,
 				 UVERBS_ATTR_REG_MR_ACCESS_FLAGS,
 				 valid_access_flags);

@@ -352,10 +359,10 @@ static int UVERBS_HANDLER(UVERBS_METHOD_REG_MR)(
 
 	if (has_fd)
 		mr = pd->device->ops.reg_user_mr_dmabuf(pd, fd_offset, length, iova,
-							fd, access_flags, attrs);
+							fd, access_flags, dmah, attrs);
 	else
 		mr = pd->device->ops.reg_user_mr(pd, addr, length,
-						 iova, access_flags, NULL);
+						 iova, access_flags, dmah, NULL);
 
 	if (IS_ERR(mr))
 		return PTR_ERR(mr);

@@ -365,6 +372,10 @@ static int UVERBS_HANDLER(UVERBS_METHOD_REG_MR)(
 	mr->type = IB_MR_TYPE_USER;
 	mr->uobject = uobj;
 	atomic_inc(&pd->usecnt);
+	if (dmah) {
+		mr->dmah = dmah;
+		atomic_inc(&dmah->usecnt);
+	}
 	rdma_restrack_new(&mr->res, RDMA_RESTRACK_MR);
 	rdma_restrack_set_name(&mr->res, NULL);
 	rdma_restrack_add(&mr->res);

@@ -488,6 +499,10 @@ DECLARE_UVERBS_NAMED_METHOD(
 			UVERBS_OBJECT_PD,
 			UVERBS_ACCESS_READ,
 			UA_MANDATORY),
+	UVERBS_ATTR_IDR(UVERBS_ATTR_REG_MR_DMA_HANDLE,
+			UVERBS_OBJECT_DMAH,
+			UVERBS_ACCESS_READ,
+			UA_OPTIONAL),
 	UVERBS_ATTR_PTR_IN(UVERBS_ATTR_REG_MR_IOVA,
 			   UVERBS_ATTR_TYPE(u64),
 			   UA_MANDATORY),

index 75fde0fe9989..3a5f81402d2f 100644
@@ -2223,7 +2223,7 @@ struct ib_mr *ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 	}
 
 	mr = pd->device->ops.reg_user_mr(pd, start, length, virt_addr,
-					 access_flags, NULL);
+					 access_flags, NULL, NULL);
 
 	if (IS_ERR(mr))
 		return mr;

@@ -2262,6 +2262,7 @@ int ib_dereg_mr_user(struct ib_mr *mr, struct ib_udata *udata)
 {
 	struct ib_pd *pd = mr->pd;
 	struct ib_dm *dm = mr->dm;
+	struct ib_dmah *dmah = mr->dmah;
 	struct ib_sig_attrs *sig_attrs = mr->sig_attrs;
 	int ret;
 

@@ -2272,6 +2273,8 @@ int ib_dereg_mr_user(struct ib_mr *mr, struct ib_udata *udata)
 		atomic_dec(&pd->usecnt);
 		if (dm)
 			atomic_dec(&dm->usecnt);
+		if (dmah)
+			atomic_dec(&dmah->usecnt);
 		kfree(sig_attrs);
 	}
 

index 3a627acb82ce..37c2bc3bdba5 100644
@@ -4235,6 +4235,7 @@ static struct ib_mr *__bnxt_re_user_reg_mr(struct ib_pd *ib_pd, u64 length, u64
 
 struct ib_mr *bnxt_re_reg_user_mr(struct ib_pd *ib_pd, u64 start, u64 length,
 				  u64 virt_addr, int mr_access_flags,
+				  struct ib_dmah *dmah,
 				  struct ib_udata *udata)
 {
 	struct bnxt_re_pd *pd = container_of(ib_pd, struct bnxt_re_pd, ib_pd);

@@ -4242,6 +4243,9 @@ struct ib_mr *bnxt_re_reg_user_mr(struct ib_pd *ib_pd, u64 start, u64 length,
 	struct ib_umem *umem;
 	struct ib_mr *ib_mr;
 
+	if (dmah)
+		return ERR_PTR(-EOPNOTSUPP);
+
 	umem = ib_umem_get(&rdev->ibdev, start, length, mr_access_flags);
 	if (IS_ERR(umem))
 		return ERR_CAST(umem);

@@ -4255,6 +4259,7 @@ struct ib_mr *bnxt_re_reg_user_mr(struct ib_pd *ib_pd, u64 start, u64 length,
 struct ib_mr *bnxt_re_reg_user_mr_dmabuf(struct ib_pd *ib_pd, u64 start,
 					 u64 length, u64 virt_addr, int fd,
 					 int mr_access_flags,
+					 struct ib_dmah *dmah,
 					 struct uverbs_attr_bundle *attrs)
 {
 	struct bnxt_re_pd *pd = container_of(ib_pd, struct bnxt_re_pd, ib_pd);

@@ -4263,6 +4268,9 @@ struct ib_mr *bnxt_re_reg_user_mr_dmabuf(struct ib_pd *ib_pd, u64 start,
 	struct ib_umem *umem;
 	struct ib_mr *ib_mr;
 
+	if (dmah)
+		return ERR_PTR(-EOPNOTSUPP);
+
 	umem_dmabuf = ib_umem_dmabuf_get_pinned(&rdev->ibdev, start, length,
 						fd, mr_access_flags);
 	if (IS_ERR(umem_dmabuf))

index 22c9eb8e9cfc..fe00ab691a51 100644
@@ -258,10 +258,12 @@ struct ib_mw *bnxt_re_alloc_mw(struct ib_pd *ib_pd, enum ib_mw_type type,
 int bnxt_re_dealloc_mw(struct ib_mw *mw);
 struct ib_mr *bnxt_re_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 				  u64 virt_addr, int mr_access_flags,
+				  struct ib_dmah *dmah,
 				  struct ib_udata *udata);
 struct ib_mr *bnxt_re_reg_user_mr_dmabuf(struct ib_pd *ib_pd, u64 start,
 					 u64 length, u64 virt_addr,
 					 int fd, int mr_access_flags,
+					 struct ib_dmah *dmah,
 					 struct uverbs_attr_bundle *attrs);
 int bnxt_re_alloc_ucontext(struct ib_ucontext *ctx, struct ib_udata *udata);
 void bnxt_re_dealloc_ucontext(struct ib_ucontext *context);

index 5b3007acaa1f..e17c1252536b 100644
@@ -1006,6 +1006,7 @@ int c4iw_map_mr_sg(struct ib_mr *ibmr, struct scatterlist *sg, int sg_nents,
 void c4iw_dealloc(struct uld_ctx *ctx);
 struct ib_mr *c4iw_reg_user_mr(struct ib_pd *pd, u64 start,
 					   u64 length, u64 virt, int acc,
+					   struct ib_dmah *dmah,
 					   struct ib_udata *udata);
 struct ib_mr *c4iw_get_dma_mr(struct ib_pd *pd, int acc);
 int c4iw_dereg_mr(struct ib_mr *ib_mr, struct ib_udata *udata);

index a2c71a1d93d5..dcdfe250bdbe 100644
@@ -489,7 +489,8 @@ struct ib_mr *c4iw_get_dma_mr(struct ib_pd *pd, int acc)
 }
 
 struct ib_mr *c4iw_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
-			       u64 virt, int acc, struct ib_udata *udata)
+			       u64 virt, int acc, struct ib_dmah *dmah,
+			       struct ib_udata *udata)
 {
 	__be64 *pages;
 	int shift, n, i;

@@ -501,6 +502,9 @@ struct ib_mr *c4iw_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 
 	pr_debug("ib_pd %p\n", pd);
 
+	if (dmah)
+		return ERR_PTR(-EOPNOTSUPP);
+
 	if (length == ~0ULL)
 		return ERR_PTR(-EINVAL);
 

index 838182d0409c..15cfca04fab8 100644
@@ -164,10 +164,12 @@ int efa_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
 		  struct uverbs_attr_bundle *attrs);
 struct ib_mr *efa_reg_mr(struct ib_pd *ibpd, u64 start, u64 length,
 			 u64 virt_addr, int access_flags,
+			 struct ib_dmah *dmah,
 			 struct ib_udata *udata);
 struct ib_mr *efa_reg_user_mr_dmabuf(struct ib_pd *ibpd, u64 start,
 				     u64 length, u64 virt_addr,
 				     int fd, int access_flags,
+				     struct ib_dmah *dmah,
 				     struct uverbs_attr_bundle *attrs);
 int efa_dereg_mr(struct ib_mr *ibmr, struct ib_udata *udata);
 int efa_get_port_immutable(struct ib_device *ibdev, u32 port_num,

index a8645a40730f..9cc5b224995f 100644
@@ -1727,6 +1727,7 @@ static int efa_register_mr(struct ib_pd *ibpd, struct efa_mr *mr, u64 start,
 struct ib_mr *efa_reg_user_mr_dmabuf(struct ib_pd *ibpd, u64 start,
 				     u64 length, u64 virt_addr,
 				     int fd, int access_flags,
+				     struct ib_dmah *dmah,
 				     struct uverbs_attr_bundle *attrs)
 {
 	struct efa_dev *dev = to_edev(ibpd->device);

@@ -1734,6 +1735,9 @@ struct ib_mr *efa_reg_user_mr_dmabuf(struct ib_pd *ibpd, u64 start,
 	struct efa_mr *mr;
 	int err;
 
+	if (dmah)
+		return ERR_PTR(-EOPNOTSUPP);
+
 	mr = efa_alloc_mr(ibpd, access_flags, &attrs->driver_udata);
 	if (IS_ERR(mr)) {
 		err = PTR_ERR(mr);

@@ -1766,12 +1770,16 @@ struct ib_mr *efa_reg_user_mr_dmabuf(struct ib_pd *ibpd, u64 start,
 
 struct ib_mr *efa_reg_mr(struct ib_pd *ibpd, u64 start, u64 length,
 			 u64 virt_addr, int access_flags,
+			 struct ib_dmah *dmah,
 			 struct ib_udata *udata)
 {
 	struct efa_dev *dev = to_edev(ibpd->device);
 	struct efa_mr *mr;
 	int err;
 
+	if (dmah)
+		return ERR_PTR(-EOPNOTSUPP);
+
 	mr = efa_alloc_mr(ibpd, access_flags, udata);
 	if (IS_ERR(mr)) {
 		err = PTR_ERR(mr);

index ec0ad4086066..94c211df09d8 100644
@@ -1200,13 +1200,17 @@ int erdma_map_mr_sg(struct ib_mr *ibmr, struct scatterlist *sg, int sg_nents,
 }
 
 struct ib_mr *erdma_reg_user_mr(struct ib_pd *ibpd, u64 start, u64 len,
-				u64 virt, int access, struct ib_udata *udata)
+				u64 virt, int access, struct ib_dmah *dmah,
+				struct ib_udata *udata)
 {
 	struct erdma_mr *mr = NULL;
 	struct erdma_dev *dev = to_edev(ibpd->device);
 	u32 stag;
 	int ret;
 
+	if (dmah)
+		return ERR_PTR(-EOPNOTSUPP);
+
 	if (!len || len > dev->attrs.max_mr_size)
 		return ERR_PTR(-EINVAL);
 

index f9408ccc8bad..ef411b81fbd7 100644
@@ -452,7 +452,8 @@ int erdma_destroy_cq(struct ib_cq *ibcq, struct ib_udata *udata);
 void erdma_disassociate_ucontext(struct ib_ucontext *ibcontext);
 int erdma_req_notify_cq(struct ib_cq *ibcq, enum ib_cq_notify_flags flags);
 struct ib_mr *erdma_reg_user_mr(struct ib_pd *ibpd, u64 start, u64 len,
-				u64 virt, int access, struct ib_udata *udata);
+				u64 virt, int access, struct ib_dmah *dmah,
+				struct ib_udata *udata);
 struct ib_mr *erdma_get_dma_mr(struct ib_pd *ibpd, int rights);
 int erdma_dereg_mr(struct ib_mr *ibmr, struct ib_udata *data);
 int erdma_mmap(struct ib_ucontext *ctx, struct vm_area_struct *vma);

index 25f77b1fa773..78ee04a48a74 100644
@@ -1219,6 +1219,7 @@ int hns_roce_dealloc_pd(struct ib_pd *pd, struct ib_udata *udata);
 struct ib_mr *hns_roce_get_dma_mr(struct ib_pd *pd, int acc);
 struct ib_mr *hns_roce_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 				   u64 virt_addr, int access_flags,
+				   struct ib_dmah *dmah,
 				   struct ib_udata *udata);
 struct ib_mr *hns_roce_rereg_user_mr(struct ib_mr *mr, int flags, u64 start,
 				     u64 length, u64 virt_addr,

index ebef93559225..03af842dd9d3 100644
@@ -231,12 +231,16 @@ struct ib_mr *hns_roce_get_dma_mr(struct ib_pd *pd, int acc)
 
 struct ib_mr *hns_roce_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 				   u64 virt_addr, int access_flags,
+				   struct ib_dmah *dmah,
 				   struct ib_udata *udata)
 {
 	struct hns_roce_dev *hr_dev = to_hr_dev(pd->device);
 	struct hns_roce_mr *mr;
 	int ret;
 
+	if (dmah)
+		return ERR_PTR(-EOPNOTSUPP);
+
 	mr = kzalloc(sizeof(*mr), GFP_KERNEL);
 	if (!mr) {
 		ret = -ENOMEM;

index 1e8c92826de2..da5a41b275d8 100644
@@ -3013,10 +3013,12 @@ static int irdma_reg_user_mr_type_cq(struct irdma_mem_reg_req req,
  * @len: length of mr
  * @virt: virtual address
  * @access: access of mr
+ * @dmah: dma handle
  * @udata: user data
  */
 static struct ib_mr *irdma_reg_user_mr(struct ib_pd *pd, u64 start, u64 len,
 				       u64 virt, int access,
+				       struct ib_dmah *dmah,
 				       struct ib_udata *udata)
 {
 #define IRDMA_MEM_REG_MIN_REQ_LEN offsetofend(struct irdma_mem_reg_req, sq_pages)

@@ -3026,6 +3028,9 @@ static struct ib_mr *irdma_reg_user_mr(struct ib_pd *pd, u64 start, u64 len,
 	struct irdma_mr *iwmr = NULL;
 	int err;
 
+	if (dmah)
+		return ERR_PTR(-EOPNOTSUPP);
+
 	if (len > iwdev->rf->sc_dev.hw_attrs.max_mr_size)
 		return ERR_PTR(-EINVAL);
 

@@ -3085,6 +3090,7 @@ static struct ib_mr *irdma_reg_user_mr(struct ib_pd *pd, u64 start, u64 len,
 static struct ib_mr *irdma_reg_user_mr_dmabuf(struct ib_pd *pd, u64 start,
 					      u64 len, u64 virt,
 					      int fd, int access,
+					      struct ib_dmah *dmah,
 					      struct uverbs_attr_bundle *attrs)
 {
 	struct irdma_device *iwdev = to_iwdev(pd->device);

@@ -3092,6 +3098,9 @@ static struct ib_mr *irdma_reg_user_mr_dmabuf(struct ib_pd *pd, u64 start,
 	struct irdma_mr *iwmr;
 	int err;
 
+	if (dmah)
+		return ERR_PTR(-EOPNOTSUPP);
+
 	if (len > iwdev->rf->sc_dev.hw_attrs.max_mr_size)
 		return ERR_PTR(-EINVAL);
 

index eddd0a83b97e..03a1cb039343 100644
@@ -624,6 +624,7 @@ struct ib_mr *mana_ib_get_dma_mr(struct ib_pd *ibpd, int access_flags);
 
 struct ib_mr *mana_ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 				  u64 iova, int access_flags,
+				  struct ib_dmah *dmah,
 				  struct ib_udata *udata);
 
 int mana_ib_dereg_mr(struct ib_mr *ibmr, struct ib_udata *udata);

@@ -713,5 +714,6 @@ int mana_ib_arm_cq(struct ib_cq *ibcq, enum ib_cq_notify_flags flags);
 
 struct ib_mr *mana_ib_reg_user_mr_dmabuf(struct ib_pd *ibpd, u64 start, u64 length,
 					 u64 iova, int fd, int mr_access_flags,
+					 struct ib_dmah *dmah,
 					 struct uverbs_attr_bundle *attrs);
 #endif

index 6d974d0a8400..55701046ffba 100644
@@ -106,6 +106,7 @@ static int mana_ib_gd_destroy_mr(struct mana_ib_dev *dev, u64 mr_handle)
 
 struct ib_mr *mana_ib_reg_user_mr(struct ib_pd *ibpd, u64 start, u64 length,
 				  u64 iova, int access_flags,
+				  struct ib_dmah *dmah,
 				  struct ib_udata *udata)
 {
 	struct mana_ib_pd *pd = container_of(ibpd, struct mana_ib_pd, ibpd);

@@ -116,6 +117,9 @@ struct ib_mr *mana_ib_reg_user_mr(struct ib_pd *ibpd, u64 start, u64 length,
 	u64 dma_region_handle;
 	int err;
 
+	if (dmah)
+		return ERR_PTR(-EOPNOTSUPP);
+
 	dev = container_of(ibdev, struct mana_ib_dev, ib_dev);
 
 	ibdev_dbg(ibdev,

@@ -188,6 +192,7 @@ struct ib_mr *mana_ib_reg_user_mr(struct ib_pd *ibpd, u64 start, u64 length,
 
 struct ib_mr *mana_ib_reg_user_mr_dmabuf(struct ib_pd *ibpd, u64 start, u64 length,
 					 u64 iova, int fd, int access_flags,
+					 struct ib_dmah *dmah,
 					 struct uverbs_attr_bundle *attrs)
 {
 	struct mana_ib_pd *pd = container_of(ibpd, struct mana_ib_pd, ibpd);

@@ -199,6 +204,9 @@ struct ib_mr *mana_ib_reg_user_mr_dmabuf(struct ib_pd *ibpd, u64 start, u64 leng
 	u64 dma_region_handle;
 	int err;
 
+	if (dmah)
+		return ERR_PTR(-EOPNOTSUPP);
+
 	dev = container_of(ibdev, struct mana_ib_dev, ib_dev);
 
 	access_flags &= ~IB_ACCESS_OPTIONAL;

index f53b1846594c..5df5b955114e 100644
@@ -759,6 +759,7 @@ int mlx4_ib_umem_write_mtt(struct mlx4_ib_dev *dev, struct mlx4_mtt *mtt,
 			   struct ib_umem *umem);
 struct ib_mr *mlx4_ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 				  u64 virt_addr, int access_flags,
+				  struct ib_dmah *dmah,
 				  struct ib_udata *udata);
 int mlx4_ib_dereg_mr(struct ib_mr *mr, struct ib_udata *udata);
 int mlx4_ib_alloc_mw(struct ib_mw *mw, struct ib_udata *udata);

index e77645a673fb..94464f1694d9 100644
@@ -139,6 +139,7 @@ static struct ib_umem *mlx4_get_umem_mr(struct ib_device *device, u64 start,
 
 struct ib_mr *mlx4_ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 				  u64 virt_addr, int access_flags,
+				  struct ib_dmah *dmah,
 				  struct ib_udata *udata)
 {
 	struct mlx4_ib_dev *dev = to_mdev(pd->device);

@@ -147,6 +148,9 @@ struct ib_mr *mlx4_ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 	int err;
 	int n;
 
+	if (dmah)
+		return ERR_PTR(-EOPNOTSUPP);
+
 	mr = kzalloc(sizeof(*mr), GFP_KERNEL);
 	if (!mr)
 		return ERR_PTR(-ENOMEM);

index a012e24d3afe..71916d730be0 100644
@@ -1380,10 +1380,12 @@ int mlx5_ib_resize_cq(struct ib_cq *ibcq, int entries, struct ib_udata *udata);
 struct ib_mr *mlx5_ib_get_dma_mr(struct ib_pd *pd, int acc);
 struct ib_mr *mlx5_ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 				  u64 virt_addr, int access_flags,
+				  struct ib_dmah *dmah,
 				  struct ib_udata *udata);
 struct ib_mr *mlx5_ib_reg_user_mr_dmabuf(struct ib_pd *pd, u64 start,
 					 u64 length, u64 virt_addr,
 					 int fd, int access_flags,
+					 struct ib_dmah *dmah,
 					 struct uverbs_attr_bundle *attrs);
 int mlx5_ib_advise_mr(struct ib_pd *pd,
 		      enum ib_uverbs_advise_mr_advice advice,

index 41e897a7e652..8deff7cdf048 100644
@@ -1564,13 +1564,14 @@ static struct ib_mr *create_user_odp_mr(struct ib_pd *pd, u64 start, u64 length,
 
 struct ib_mr *mlx5_ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 				  u64 iova, int access_flags,
+				  struct ib_dmah *dmah,
 				  struct ib_udata *udata)
 {
 	struct mlx5_ib_dev *dev = to_mdev(pd->device);
 	struct ib_umem *umem;
 	int err;
 
-	if (!IS_ENABLED(CONFIG_INFINIBAND_USER_MEM))
+	if (!IS_ENABLED(CONFIG_INFINIBAND_USER_MEM) || dmah)
 		return ERR_PTR(-EOPNOTSUPP);
 
 	mlx5_ib_dbg(dev, "start 0x%llx, iova 0x%llx, length 0x%llx, access_flags 0x%x\n",

@@ -1724,6 +1725,7 @@ reg_user_mr_dmabuf_by_data_direct(struct ib_pd *pd, u64 offset,
 struct ib_mr *mlx5_ib_reg_user_mr_dmabuf(struct ib_pd *pd, u64 offset,
 					 u64 length, u64 virt_addr,
 					 int fd, int access_flags,
+					 struct ib_dmah *dmah,
 					 struct uverbs_attr_bundle *attrs)
 {
 	struct mlx5_ib_dev *dev = to_mdev(pd->device);

@@ -1731,7 +1733,7 @@ struct ib_mr *mlx5_ib_reg_user_mr_dmabuf(struct ib_pd *pd, u64 offset,
 	int err;
 
 	if (!IS_ENABLED(CONFIG_INFINIBAND_USER_MEM) ||
-	    !IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING))
+	    !IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING) || dmah)
 		return ERR_PTR(-EOPNOTSUPP);
 
 	if (uverbs_attr_is_valid(attrs, MLX5_IB_ATTR_REG_DMABUF_MR_ACCESS_FLAGS)) {

@@ -1937,7 +1939,7 @@ struct ib_mr *mlx5_ib_rereg_user_mr(struct ib_mr *ib_mr, int flags, u64 start,
 	 */
 recreate:
 	return mlx5_ib_reg_user_mr(new_pd, start, length, iova,
-				   new_access_flags, udata);
+				   new_access_flags, NULL, udata);
 }
 
 static int

index 6a1e2e79ddc3..dd572d76866c 100644
@@ -825,7 +825,8 @@ static struct ib_mr *mthca_get_dma_mr(struct ib_pd *pd, int acc)
 }
 
 static struct ib_mr *mthca_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
-				       u64 virt, int acc, struct ib_udata *udata)
+				       u64 virt, int acc, struct ib_dmah *dmah,
+				       struct ib_udata *udata)
 {
 	struct mthca_dev *dev = to_mdev(pd->device);
 	struct ib_block_iter biter;

@@ -838,6 +839,9 @@ static struct ib_mr *mthca_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 	int err = 0;
 	int write_mtt_size;
 
+	if (dmah)
+		return ERR_PTR(-EOPNOTSUPP);
+
 	if (udata->inlen < sizeof ucmd) {
 		if (!context->reg_mr_warned) {
 			mthca_warn(dev, "Process '%s' did not pass in MR attrs.\n",

index 979de8f8df14..46d911fd38de 100644
@@ -847,13 +847,17 @@ static void build_user_pbes(struct ocrdma_dev *dev, struct ocrdma_mr *mr)
 }
 
 struct ib_mr *ocrdma_reg_user_mr(struct ib_pd *ibpd, u64 start, u64 len,
-				 u64 usr_addr, int acc, struct ib_udata *udata)
+				 u64 usr_addr, int acc, struct ib_dmah *dmah,
+				 struct ib_udata *udata)
 {
 	int status = -ENOMEM;
 	struct ocrdma_dev *dev = get_ocrdma_dev(ibpd->device);
 	struct ocrdma_mr *mr;
 	struct ocrdma_pd *pd;
 
+	if (dmah)
+		return ERR_PTR(-EOPNOTSUPP);
+
 	pd = get_ocrdma_pd(ibpd);
 
 	if (acc & IB_ACCESS_REMOTE_WRITE && !(acc & IB_ACCESS_LOCAL_WRITE))

index 0644346d8d98..6c5c3755b8a9 100644
@@ -98,7 +98,8 @@ int ocrdma_post_srq_recv(struct ib_srq *, const struct ib_recv_wr *,
 int ocrdma_dereg_mr(struct ib_mr *ib_mr, struct ib_udata *udata);
 struct ib_mr *ocrdma_get_dma_mr(struct ib_pd *, int acc);
 struct ib_mr *ocrdma_reg_user_mr(struct ib_pd *, u64 start, u64 length,
-				 u64 virt, int acc, struct ib_udata *);
+				 u64 virt, int acc, struct ib_dmah *dmah,
+				 struct ib_udata *);
 struct ib_mr *ocrdma_alloc_mr(struct ib_pd *pd, enum ib_mr_type mr_type,
 			      u32 max_num_sg);
 int ocrdma_map_mr_sg(struct ib_mr *ibmr, struct scatterlist *sg, int sg_nents,

index 568a5b18803f..ab9bf0922979 100644
@@ -2953,13 +2953,17 @@ static int init_mr_info(struct qedr_dev *dev, struct mr_info *info,
 }
 
 struct ib_mr *qedr_reg_user_mr(struct ib_pd *ibpd, u64 start, u64 len,
-			       u64 usr_addr, int acc, struct ib_udata *udata)
+			       u64 usr_addr, int acc, struct ib_dmah *dmah,
+			       struct ib_udata *udata)
 {
 	struct qedr_dev *dev = get_qedr_dev(ibpd->device);
 	struct qedr_mr *mr;
 	struct qedr_pd *pd;
 	int rc = -ENOMEM;
 
+	if (dmah)
+		return ERR_PTR(-EOPNOTSUPP);
+
 	pd = get_qedr_pd(ibpd);
 	DP_DEBUG(dev, QEDR_MSG_MR,
 		 "qedr_register user mr pd = %d start = %lld, len = %lld, usr_addr = %lld, acc = %d\n",

index 5731458abb06..62420a15101b 100644
@@ -79,7 +79,8 @@ int qedr_dereg_mr(struct ib_mr *ib_mr, struct ib_udata *udata);
 struct ib_mr *qedr_get_dma_mr(struct ib_pd *, int acc);
 
 struct ib_mr *qedr_reg_user_mr(struct ib_pd *, u64 start, u64 length,
-			       u64 virt, int acc, struct ib_udata *);
+			       u64 virt, int acc, struct ib_dmah *dmah,
+			       struct ib_udata *);
 
 int qedr_map_mr_sg(struct ib_mr *ibmr, struct scatterlist *sg,
 		   int sg_nents, unsigned int *sg_offset);

index 217af34e82b3..ae5df96589d9 100644
@@ -592,6 +592,7 @@ int usnic_ib_destroy_cq(struct ib_cq *cq, struct ib_udata *udata)
 
 struct ib_mr *usnic_ib_reg_mr(struct ib_pd *pd, u64 start, u64 length,
 					u64 virt_addr, int access_flags,
+					struct ib_dmah *dmah,
 					struct ib_udata *udata)
 {
 	struct usnic_ib_mr *mr;

@@ -600,6 +601,9 @@ struct ib_mr *usnic_ib_reg_mr(struct ib_pd *pd, u64 start, u64 length,
 	usnic_dbg("start 0x%llx va 0x%llx length 0x%llx\n", start,
 			virt_addr, length);
 
+	if (dmah)
+		return ERR_PTR(-EOPNOTSUPP);
+
 	mr = kzalloc(sizeof(*mr), GFP_KERNEL);
 	if (!mr)
 		return ERR_PTR(-ENOMEM);

index 53f53f2d53be..e3031ac32488 100644
@@ -60,6 +60,7 @@ int usnic_ib_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
 int usnic_ib_destroy_cq(struct ib_cq *cq, struct ib_udata *udata);
 struct ib_mr *usnic_ib_reg_mr(struct ib_pd *pd, u64 start, u64 length,
 				u64 virt_addr, int access_flags,
+				struct ib_dmah *dmah,
 				struct ib_udata *udata);
 int usnic_ib_dereg_mr(struct ib_mr *ibmr, struct ib_udata *udata);
 int usnic_ib_alloc_ucontext(struct ib_ucontext *uctx, struct ib_udata *udata);

index e80848bfb3bd..ec7a00c8285b 100644
@@ -104,12 +104,14 @@ struct ib_mr *pvrdma_get_dma_mr(struct ib_pd *pd, int acc)
  * @length: length of region
  * @virt_addr: I/O virtual address
  * @access_flags: access flags for memory region
+ * @dmah: dma handle
  * @udata: user data
  *
  * @return: ib_mr pointer on success, otherwise returns an errno.
  */
 struct ib_mr *pvrdma_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 				 u64 virt_addr, int access_flags,
+				 struct ib_dmah *dmah,
 				 struct ib_udata *udata)
 {
 	struct pvrdma_dev *dev = to_vdev(pd->device);

@@ -121,6 +123,9 @@ struct ib_mr *pvrdma_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 	struct pvrdma_cmd_create_mr_resp *resp = &rsp.create_mr_resp;
 	int ret, npages;
 
+	if (dmah)
+		return ERR_PTR(-EOPNOTSUPP);
+
 	if (length == 0 || length > dev->dsr->caps.max_mr_size) {
 		dev_warn(&dev->pdev->dev, "invalid mem region length\n");
 		return ERR_PTR(-EINVAL);

index fd47b0b1df5c..603e5a9311eb 100644
@@ -366,6 +366,7 @@ int pvrdma_dealloc_pd(struct ib_pd *ibpd, struct ib_udata *udata);
 struct ib_mr *pvrdma_get_dma_mr(struct ib_pd *pd, int acc);
 struct ib_mr *pvrdma_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 				 u64 virt_addr, int access_flags,
+				 struct ib_dmah *dmah,
 				 struct ib_udata *udata);
 int pvrdma_dereg_mr(struct ib_mr *mr, struct ib_udata *udata);
 struct ib_mr *pvrdma_alloc_mr(struct ib_pd *pd, enum ib_mr_type mr_type,

index 5ed5cfc2b280..86e482593a85 100644
@@ -329,12 +329,14 @@ struct ib_mr *rvt_get_dma_mr(struct ib_pd *pd, int acc)
  * @length: length of region to register
  * @virt_addr: associated virtual address
  * @mr_access_flags: access flags for this memory region
+ * @dmah: dma handle
  * @udata: unused by the driver
  *
  * Return: the memory region on success, otherwise returns an errno.
  */
 struct ib_mr *rvt_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 			      u64 virt_addr, int mr_access_flags,
+			      struct ib_dmah *dmah,
 			      struct ib_udata *udata)
 {
 	struct rvt_mr *mr;

@@ -343,6 +345,9 @@ struct ib_mr *rvt_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 	int n, m;
 	struct ib_mr *ret;
 
+	if (dmah)
+		return ERR_PTR(-EOPNOTSUPP);
+
 	if (length == 0)
 		return ERR_PTR(-EINVAL);
 

index 44afe2731741..72dab48307b7 100644
@@ -26,6 +26,7 @@ void rvt_mr_exit(struct rvt_dev_info *rdi);
 struct ib_mr *rvt_get_dma_mr(struct ib_pd *pd, int acc);
 struct ib_mr *rvt_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 			      u64 virt_addr, int mr_access_flags,
+			      struct ib_dmah *dmah,
 			      struct ib_udata *udata);
 int rvt_dereg_mr(struct ib_mr *ibmr, struct ib_udata *udata);
 struct ib_mr *rvt_alloc_mr(struct ib_pd *pd, enum ib_mr_type mr_type,

index 2331e698a65b..f48d6e132954 100644
@@ -1271,6 +1271,7 @@ static struct ib_mr *rxe_get_dma_mr(struct ib_pd *ibpd, int access)
 
 static struct ib_mr *rxe_reg_user_mr(struct ib_pd *ibpd, u64 start,
 				     u64 length, u64 iova, int access,
+				     struct ib_dmah *dmah,
 				     struct ib_udata *udata)
 {
 	struct rxe_dev *rxe = to_rdev(ibpd->device);

@@ -1278,6 +1279,9 @@ static struct ib_mr *rxe_reg_user_mr(struct ib_pd *ibpd, u64 start,
 	struct rxe_mr *mr;
 	int err, cleanup_err;
 
+	if (dmah)
+		return ERR_PTR(-EOPNOTSUPP);
+
 	if (access & ~RXE_ACCESS_SUPPORTED_MR) {
 		rxe_err_pd(pd, "access = %#x not supported (%#x)\n", access,
 				RXE_ACCESS_SUPPORTED_MR);

index 2b2a7b8e93b0..b784e18db463 100644
@@ -1321,10 +1321,12 @@ int siw_dereg_mr(struct ib_mr *base_mr, struct ib_udata *udata)
  * @len:	len of MR
  * @rnic_va:	not used by siw
  * @rights:	MR access rights
+ * @dmah:	dma handle
  * @udata:	user buffer to communicate STag and Key.
  */
 struct ib_mr *siw_reg_user_mr(struct ib_pd *pd, u64 start, u64 len,
-			      u64 rnic_va, int rights, struct ib_udata *udata)
+			      u64 rnic_va, int rights,  struct ib_dmah *dmah,
+			      struct ib_udata *udata)
 {
 	struct siw_mr *mr = NULL;
 	struct siw_umem *umem = NULL;

@@ -1332,6 +1334,9 @@ struct ib_mr *siw_reg_user_mr(struct ib_pd *pd, u64 start, u64 len,
 	struct siw_device *sdev = to_siw_dev(pd->device);
 	int rv;
 
+	if (dmah)
+		return ERR_PTR(-EOPNOTSUPP);
+
 	siw_dbg_pd(pd, "start: 0x%p, va: 0x%p, len: %llu\n",
 		   (void *)(uintptr_t)start, (void *)(uintptr_t)rnic_va,
 		   (unsigned long long)len);

index 1f1a305540af..e9f4463aecdc 100644
@@ -65,7 +65,8 @@ int siw_destroy_cq(struct ib_cq *base_cq, struct ib_udata *udata);
 int siw_poll_cq(struct ib_cq *base_cq, int num_entries, struct ib_wc *wc);
 int siw_req_notify_cq(struct ib_cq *base_cq, enum ib_cq_notify_flags flags);
 struct ib_mr *siw_reg_user_mr(struct ib_pd *base_pd, u64 start, u64 len,
-			      u64 rnic_va, int rights, struct ib_udata *udata);
+			      u64 rnic_va, int rights, struct ib_dmah *dmah,
+			      struct ib_udata *udata);
 struct ib_mr *siw_alloc_mr(struct ib_pd *base_pd, enum ib_mr_type mr_type,
 			   u32 max_sge);
 struct ib_mr *siw_get_dma_mr(struct ib_pd *base_pd, int rights);

index d7ee762b87e9..c263327a0205 100644
@@ -1887,6 +1887,7 @@ struct ib_mr {
 
 	struct ib_dm      *dm;
 	struct ib_sig_attrs *sig_attrs; /* only for IB_MR_TYPE_INTEGRITY MRs */
+	struct ib_dmah *dmah;
 	/*
 	 * Implementation details of the RDMA core, don't use in drivers:
 	 */

@@ -2525,10 +2526,12 @@ struct ib_device_ops {
 	struct ib_mr *(*get_dma_mr)(struct ib_pd *pd, int mr_access_flags);
 	struct ib_mr *(*reg_user_mr)(struct ib_pd *pd, u64 start, u64 length,
 				     u64 virt_addr, int mr_access_flags,
+				     struct ib_dmah *dmah,
 				     struct ib_udata *udata);
 	struct ib_mr *(*reg_user_mr_dmabuf)(struct ib_pd *pd, u64 offset,
 					    u64 length, u64 virt_addr, int fd,
 					    int mr_access_flags,
+					    struct ib_dmah *dmah,
 					    struct uverbs_attr_bundle *attrs);
 	struct ib_mr *(*rereg_user_mr)(struct ib_mr *mr, int flags, u64 start,
 				       u64 length, u64 virt_addr,

index a0b1130423f0..17f963014eca 100644
@@ -307,6 +307,7 @@ enum uverbs_attrs_reg_dmabuf_mr_cmd_attr_ids {
 enum uverbs_attrs_reg_mr_cmd_attr_ids {
 	UVERBS_ATTR_REG_MR_HANDLE,
 	UVERBS_ATTR_REG_MR_PD_HANDLE,
+	UVERBS_ATTR_REG_MR_DMA_HANDLE,
 	UVERBS_ATTR_REG_MR_IOVA,
 	UVERBS_ATTR_REG_MR_ADDR,
 	UVERBS_ATTR_REG_MR_LENGTH,

index c03fe5414b9a..c6ced06111dd 100644
@@ -1393,6 +1393,10 @@ static int devx_handle_mkey_create(struct mlx5_ib_dev *dev,
 	}
 
 	MLX5_SET(create_mkey_in, in, mkey_umem_valid, 1);
+	/* TPH is not allowed to bypass the regular kernel's verbs flow */
+	MLX5_SET(mkc, mkc, pcie_tph_en, 0);
+	MLX5_SET(mkc, mkc, pcie_tph_steering_tag_index,
+		 MLX5_MKC_PCIE_TPH_NO_STEERING_TAG_INDEX);
 	return 0;
 }
 

index 71916d730be0..3452695944e8 100644
@@ -650,8 +650,13 @@ enum mlx5_mkey_type {
 	MLX5_MKEY_IMPLICIT_CHILD,
 };
 
+/* Used for non-existent ph value */
+#define MLX5_IB_NO_PH 0xff
+
 struct mlx5r_cache_rb_key {
 	u8 ats:1;
+	u8 ph;
+	u16 st_index;
 	unsigned int access_mode;
 	unsigned int access_flags;
 	unsigned int ndescs;

266 lines not on this page · raw message

index f6abd64f07f7..2cfe66a9839c 100644
@@ -1866,6 +1866,7 @@ int mlx5_odp_init_mkey_cache(struct mlx5_ib_dev *dev)
 	struct mlx5r_cache_rb_key rb_key = {
 		.access_mode = MLX5_MKC_ACCESS_MODE_KSM,
 		.ndescs = mlx5_imr_ksm_entries,
+		.ph = MLX5_IB_NO_PH,
 	};
 	struct mlx5_cache_ent *ent;