[PATCH for-next 0/2] RDMA/hns: Add support for userspace Direct WQE

@@ -338,12 +338,23 @@ static void hns_roce_dealloc_ucontext(struct ib_ucontext *ibcontext)
 	hns_roce_uar_free(to_hr_dev(ibcontext->device), &context->uar);
 }
 
-static int hns_roce_mmap(struct ib_ucontext *context,
-			 struct vm_area_struct *vma)
+/* command value is offset[15:8] */
+static inline int hns_roce_mmap_get_command(unsigned long offset)
+{
+	return (offset >> 8) & 0xff;
+}
+
+/* index value is offset[63:16] | offset[7:0] */
+static inline unsigned long hns_roce_mmap_get_index(unsigned long offset)
+{
+	return ((offset >> 16) << 8) | (offset & 0xff);
+}
+
+static int mmap_uar(struct ib_ucontext *context, struct vm_area_struct *vma)
 {
 	struct hns_roce_dev *hr_dev = to_hr_dev(context->device);
 
-	switch (vma->vm_pgoff) {
+	switch (hns_roce_mmap_get_index(vma->vm_pgoff)) {
 	case 0:
 		return rdma_user_mmap_io(context, vma,
 					 to_hr_ucontext(context)->uar.pfn,

@@ -370,6 +381,16 @@ static int hns_roce_mmap(struct ib_ucontext *context,
 	}
 }
 
+static int hns_roce_mmap(struct ib_ucontext *uctx, struct vm_area_struct *vma)
+{
+	switch (hns_roce_mmap_get_command(vma->vm_pgoff)) {
+	case HNS_ROCE_MMAP_REGULAR_PAGE:
+		return mmap_uar(uctx, vma);
+	default:
+		return -EINVAL;
+	}
+}
+
 static int hns_roce_port_immutable(struct ib_device *ib_dev, u32 port_num,
 				   struct ib_port_immutable *immutable)
 {

@@ -94,4 +94,8 @@ struct hns_roce_ib_alloc_pd_resp {
 	__u32 pdn;
 };
 
+enum {
+	HNS_ROCE_MMAP_REGULAR_PAGE,
+};
+
 #endif /* HNS_ABI_USER_H */

@@ -187,6 +187,7 @@ enum {
 	HNS_ROCE_CAP_FLAG_FRMR                  = BIT(8),
 	HNS_ROCE_CAP_FLAG_QP_FLOW_CTRL		= BIT(9),
 	HNS_ROCE_CAP_FLAG_ATOMIC		= BIT(10),
+	HNS_ROCE_CAP_FLAG_DIRECT_WQE		= BIT(12),
 	HNS_ROCE_CAP_FLAG_SDI_MODE		= BIT(14),
 	HNS_ROCE_CAP_FLAG_STASH			= BIT(17),
 };

@@ -226,6 +227,7 @@ enum {
 
 struct hns_roce_uar {
 	u64		pfn;
+	u64		dwqe_page;
 	unsigned long	index;
 	unsigned long	logic_idx;
 };

@@ -608,10 +610,6 @@ struct hns_roce_work {
 	u32 queue_num;
 };
 
-enum {
-	HNS_ROCE_QP_CAP_DIRECT_WQE = BIT(5),
-};
-
 struct hns_roce_qp {
 	struct ib_qp		ibqp;
 	struct hns_roce_wq	rq;

@@ -656,6 +654,7 @@ struct hns_roce_qp {
 	struct list_head	node;		/* all qps are on a list */
 	struct list_head	rq_node;	/* all recv qps are on a list */
 	struct list_head	sq_node;	/* all send qps are on a list */
+	bool			has_mmaped;	/* mark qp of direct wqe */
 };
 
 struct hns_roce_ib_iboe {

@@ -331,13 +331,6 @@ static int hns_roce_alloc_ucontext(struct ib_ucontext *uctx,
 	return ret;
 }
 
-static void hns_roce_dealloc_ucontext(struct ib_ucontext *ibcontext)
-{
-	struct hns_roce_ucontext *context = to_hr_ucontext(ibcontext);
-
-	hns_roce_uar_free(to_hr_dev(ibcontext->device), &context->uar);
-}
-
 /* command value is offset[15:8] */
 static inline int hns_roce_mmap_get_command(unsigned long offset)
 {

@@ -350,6 +343,56 @@ static inline unsigned long hns_roce_mmap_get_index(unsigned long offset)
 	return ((offset >> 16) << 8) | (offset & 0xff);
 }
 
+static int mmap_dwqe(struct ib_ucontext *uctx, struct vm_area_struct *vma)
+{
+	struct hns_roce_ucontext *context = to_hr_ucontext(uctx);
+	struct hns_roce_dev *hr_dev = to_hr_dev(uctx->device);
+	struct ib_device *ibdev = &hr_dev->ib_dev;
+	struct hns_roce_qp *hr_qp;
+	unsigned long pgoff;
+	unsigned long qpn;
+	phys_addr_t pfn;
+	pgprot_t prot;
+	int ret;
+
+	pgoff = hns_roce_mmap_get_index(vma->vm_pgoff);
+	qpn = pgoff / (HNS_ROCE_DWQE_SIZE / PAGE_SIZE);
+	hr_qp = __hns_roce_qp_lookup(hr_dev, qpn);
+	if (!hr_qp) {
+		ibdev_err(ibdev, "failed to find QP.\n");
+		return -EINVAL;
+	}
+
+	if (hr_qp->ibqp.pd->uobject->context != uctx) {
+		ibdev_err(ibdev,
+			  "the QP is not owned by the context, QPN = %lu.\n",
+			  hr_qp->qpn);
+		return -EINVAL;
+	}
+
+	if (hr_qp->has_mmaped) {
+		ibdev_err(ibdev,
+			  "the QP has been already mapped, QPN = %lu.\n",
+			  hr_qp->qpn);
+		return -EINVAL;
+	}
+
+	hr_qp->has_mmaped = true;
+	pfn = context->uar.dwqe_page + pgoff;
+	prot = pgprot_device(vma->vm_page_prot);
+
+	ret = rdma_user_mmap_io(uctx, vma, pfn, HNS_ROCE_DWQE_SIZE, prot, NULL);
+
+	return ret;
+}
+
+static void hns_roce_dealloc_ucontext(struct ib_ucontext *ibcontext)
+{
+	struct hns_roce_ucontext *context = to_hr_ucontext(ibcontext);
+
+	hns_roce_uar_free(to_hr_dev(ibcontext->device), &context->uar);
+}
+
 static int mmap_uar(struct ib_ucontext *context, struct vm_area_struct *vma)
 {
 	struct hns_roce_dev *hr_dev = to_hr_dev(context->device);

@@ -386,6 +429,8 @@ static int hns_roce_mmap(struct ib_ucontext *uctx, struct vm_area_struct *vma)
 	switch (hns_roce_mmap_get_command(vma->vm_pgoff)) {
 	case HNS_ROCE_MMAP_REGULAR_PAGE:
 		return mmap_uar(uctx, vma);
+	case HNS_ROCE_MMAP_DWQE_PAGE:
+		return mmap_dwqe(uctx, vma);
 	default:
 		return -EINVAL;
 	}

@@ -112,8 +112,12 @@ int hns_roce_uar_alloc(struct hns_roce_dev *hr_dev, struct hns_roce_uar *uar)
 		}
 		uar->pfn = ((res->start) >> PAGE_SHIFT) + uar->index;
 	} else {
-		uar->pfn = ((pci_resource_start(hr_dev->pci_dev, 2))
-			   >> PAGE_SHIFT);
+		uar->pfn = pci_resource_start(hr_dev->pci_dev, 2) >> PAGE_SHIFT;
+
+		if (hr_dev->caps.flags & HNS_ROCE_CAP_FLAG_DIRECT_WQE)
+			uar->dwqe_page =
+				pci_resource_start(hr_dev->pci_dev, 4) >>
+				PAGE_SHIFT;
 	}
 
 	return 0;

@@ -768,6 +768,10 @@ static int alloc_qp_buf(struct hns_roce_dev *hr_dev, struct hns_roce_qp *hr_qp,
 		goto err_inline;
 	}
 
+	if ((PAGE_SIZE <= HNS_ROCE_DWQE_SIZE) &&
+	    hr_dev->caps.flags & HNS_ROCE_CAP_FLAG_DIRECT_WQE)
+		hr_qp->en_flags |= HNS_ROCE_QP_CAP_DIRECT_WQE;
+
 	return 0;
 err_inline:
 	free_rq_inline_buf(hr_qp);

@@ -1060,6 +1064,7 @@ static int hns_roce_create_qp_common(struct hns_roce_dev *hr_dev,
 	}
 
 	if (udata) {
+		resp.cap_flags = hr_qp->en_flags;
 		ret = ib_copy_to_udata(udata, &resp,
 				       min(udata->outlen, sizeof(resp)));
 		if (ret) {

@@ -77,6 +77,7 @@ enum hns_roce_qp_cap_flags {
 	HNS_ROCE_QP_CAP_RQ_RECORD_DB = 1 << 0,
 	HNS_ROCE_QP_CAP_SQ_RECORD_DB = 1 << 1,
 	HNS_ROCE_QP_CAP_OWNER_DB = 1 << 2,
+	HNS_ROCE_QP_CAP_DIRECT_WQE = 1 << 5,
 };
 
 struct hns_roce_ib_create_qp_resp {

@@ -96,6 +97,7 @@ struct hns_roce_ib_alloc_pd_resp {
 
 enum {
 	HNS_ROCE_MMAP_REGULAR_PAGE,
+	HNS_ROCE_MMAP_DWQE_PAGE,
 };
 
 #endif /* HNS_ABI_USER_H */