[PATCH v2 for-next 0/6] RDMA/bnxt_re: driver update for supporting low latency push

[PATCH v2 for-next 0/6] RDMA/bnxt_re: driver update for supporting low latency push

[Selvin Xavier]

[-- Attachment #1: Type: text/plain, Size: 1693 bytes --]

The series aims to add support for Low latency push path in
some of the bnxt devices. The low latency implementation is
supported only for the user applications. Also, the code
is modified to use  common mmap helper functions exported
by IB core. 

User library changes are getting submitted in the pull request
https://github.com/linux-rdma/rdma-core/pull/1321

Please review.

Thanks,
Selvin Xavier

v1 - v2:
  - Fixes the review comments from Leon and Jason
  - As suggested by Jason, implements the new uapi
    driver definitions for allocating pages in the
    driver and return the cookie for mmap

Selvin Xavier (6):
  RDMA/bnxt_re: Use the common mmap helper functions
  RDMA/bnxt_re: Add disassociate ucontext support
  RDMA/bnxt_re: Query function capabilities from firmware
  RDMA/bnxt_re: Move the interface version to chip context structure
  RDMA/bnxt_re: Reorg the bar mapping
  RDMA/bnxt_re: Enable low latency push

 drivers/infiniband/hw/bnxt_re/bnxt_re.h    |   3 +
 drivers/infiniband/hw/bnxt_re/ib_verbs.c   | 265 ++++++++++++++++++++++++++---
 drivers/infiniband/hw/bnxt_re/ib_verbs.h   |  19 +++
 drivers/infiniband/hw/bnxt_re/main.c       | 117 ++++++++++++-
 drivers/infiniband/hw/bnxt_re/qplib_fp.c   |  14 +-
 drivers/infiniband/hw/bnxt_re/qplib_rcfw.c |   2 +-
 drivers/infiniband/hw/bnxt_re/qplib_rcfw.h |   1 +
 drivers/infiniband/hw/bnxt_re/qplib_res.c  | 177 ++++++++++++-------
 drivers/infiniband/hw/bnxt_re/qplib_res.h  |  33 +++-
 drivers/infiniband/hw/bnxt_re/qplib_sp.c   |   3 +
 drivers/infiniband/hw/bnxt_re/qplib_sp.h   |   1 +
 include/uapi/rdma/bnxt_re-abi.h            |  32 ++++
 12 files changed, 558 insertions(+), 109 deletions(-)

-- 
2.5.5


[-- Attachment #2: S/MIME Cryptographic Signature --]
[-- Type: application/pkcs7-signature, Size: 4224 bytes --]

[PATCH v2 for-next 1/6] RDMA/bnxt_re: Use the common mmap helper functions

[Selvin Xavier]

[-- Attachment #1: Type: text/plain, Size: 10180 bytes --]

Replace the mmap handling function with common code in
IB core. Create rdma_user_mmap_entry for each mmap
resource and add to the ib_core mmap list. Add mmap_free
verb support. Also, use rdma_user_mmap_io while mapping
Doorbell pages.

Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com>
---
 v1 -> v2:
	- Remove the usage of remap_pfn_range during the
 	  mmap of a kernel page. Use vm_insert_page for the kernel
	  page.
        - Split the definition and allocation of bnxt_re_user_mmap_entry
 drivers/infiniband/hw/bnxt_re/ib_verbs.c  | 113 ++++++++++++++++++++++++------
 drivers/infiniband/hw/bnxt_re/ib_verbs.h  |  15 ++++
 drivers/infiniband/hw/bnxt_re/main.c      |   1 +
 drivers/infiniband/hw/bnxt_re/qplib_fp.c  |  10 +--
 drivers/infiniband/hw/bnxt_re/qplib_res.c |   2 +-
 5 files changed, 110 insertions(+), 31 deletions(-)

diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.c b/drivers/infiniband/hw/bnxt_re/ib_verbs.c
index e86afec..2434174 100644
--- a/drivers/infiniband/hw/bnxt_re/ib_verbs.c
+++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.c
@@ -533,12 +533,43 @@ static int bnxt_re_create_fence_mr(struct bnxt_re_pd *pd)
 	return rc;
 }
 
+static struct bnxt_re_user_mmap_entry*
+bnxt_re_mmap_entry_insert(struct bnxt_re_ucontext *uctx, u64 mem_offset,
+			  enum bnxt_re_mmap_flag mmap_flag, u64 *offset)
+{
+	struct bnxt_re_user_mmap_entry *entry;
+	int ret;
+
+	entry = kzalloc(sizeof(*entry), GFP_KERNEL);
+	if (!entry)
+		return NULL;
+
+	entry->mem_offset = mem_offset;
+	entry->mmap_flag = mmap_flag;
+
+	ret = rdma_user_mmap_entry_insert(&uctx->ib_uctx,
+					  &entry->rdma_entry, PAGE_SIZE);
+	if (ret) {
+		kfree(entry);
+		return NULL;
+	}
+	if (offset)
+		*offset = rdma_user_mmap_get_offset(&entry->rdma_entry);
+
+	return entry;
+}
+
 /* Protection Domains */
 int bnxt_re_dealloc_pd(struct ib_pd *ib_pd, struct ib_udata *udata)
 {
 	struct bnxt_re_pd *pd = container_of(ib_pd, struct bnxt_re_pd, ib_pd);
 	struct bnxt_re_dev *rdev = pd->rdev;
 
+	if (udata) {
+		rdma_user_mmap_entry_remove(pd->pd_db_mmap);
+		pd->pd_db_mmap = NULL;
+	}
+
 	bnxt_re_destroy_fence_mr(pd);
 
 	if (pd->qplib_pd.id) {
@@ -557,7 +588,8 @@ int bnxt_re_alloc_pd(struct ib_pd *ibpd, struct ib_udata *udata)
 	struct bnxt_re_ucontext *ucntx = rdma_udata_to_drv_context(
 		udata, struct bnxt_re_ucontext, ib_uctx);
 	struct bnxt_re_pd *pd = container_of(ibpd, struct bnxt_re_pd, ib_pd);
-	int rc;
+	struct bnxt_re_user_mmap_entry *entry = NULL;
+	int rc = 0;
 
 	pd->rdev = rdev;
 	if (bnxt_qplib_alloc_pd(&rdev->qplib_res.pd_tbl, &pd->qplib_pd)) {
@@ -567,7 +599,7 @@ int bnxt_re_alloc_pd(struct ib_pd *ibpd, struct ib_udata *udata)
 	}
 
 	if (udata) {
-		struct bnxt_re_pd_resp resp;
+		struct bnxt_re_pd_resp resp = {};
 
 		if (!ucntx->dpi.dbr) {
 			/* Allocate DPI in alloc_pd to avoid failing of
@@ -584,12 +616,21 @@ int bnxt_re_alloc_pd(struct ib_pd *ibpd, struct ib_udata *udata)
 		resp.pdid = pd->qplib_pd.id;
 		/* Still allow mapping this DBR to the new user PD. */
 		resp.dpi = ucntx->dpi.dpi;
-		resp.dbr = (u64)ucntx->dpi.umdbr;
 
-		rc = ib_copy_to_udata(udata, &resp, sizeof(resp));
+		entry = bnxt_re_mmap_entry_insert(ucntx, (u64)ucntx->dpi.umdbr,
+						  BNXT_RE_MMAP_UC_DB, &resp.dbr);
+
+		if (!entry) {
+			rc = -ENOMEM;
+			goto dbfail;
+		}
+
+		pd->pd_db_mmap = &entry->rdma_entry;
+
+		rc = ib_copy_to_udata(udata, &resp, min(sizeof(resp), udata->outlen));
 		if (rc) {
-			ibdev_err(&rdev->ibdev,
-				  "Failed to copy user response\n");
+			rdma_user_mmap_entry_remove(pd->pd_db_mmap);
+			rc = -EFAULT;
 			goto dbfail;
 		}
 	}
@@ -3956,6 +3997,7 @@ int bnxt_re_alloc_ucontext(struct ib_ucontext *ctx, struct ib_udata *udata)
 		container_of(ctx, struct bnxt_re_ucontext, ib_uctx);
 	struct bnxt_re_dev *rdev = to_bnxt_re_dev(ibdev, ibdev);
 	struct bnxt_qplib_dev_attr *dev_attr = &rdev->dev_attr;
+	struct bnxt_re_user_mmap_entry *entry;
 	struct bnxt_re_uctx_resp resp = {};
 	u32 chip_met_rev_num = 0;
 	int rc;
@@ -3994,6 +4036,13 @@ int bnxt_re_alloc_ucontext(struct ib_ucontext *ctx, struct ib_udata *udata)
 	resp.comp_mask |= BNXT_RE_UCNTX_CMASK_HAVE_MODE;
 	resp.mode = rdev->chip_ctx->modes.wqe_mode;
 
+	entry = bnxt_re_mmap_entry_insert(uctx, 0, BNXT_RE_MMAP_SH_PAGE, NULL);
+	if (!entry) {
+		rc = -ENOMEM;
+		goto cfail;
+	}
+	uctx->shpage_mmap = &entry->rdma_entry;
+
 	rc = ib_copy_to_udata(udata, &resp, min(udata->outlen, sizeof(resp)));
 	if (rc) {
 		ibdev_err(ibdev, "Failed to copy user context");
@@ -4017,6 +4066,8 @@ void bnxt_re_dealloc_ucontext(struct ib_ucontext *ib_uctx)
 
 	struct bnxt_re_dev *rdev = uctx->rdev;
 
+	rdma_user_mmap_entry_remove(uctx->shpage_mmap);
+	uctx->shpage_mmap = NULL;
 	if (uctx->shpg)
 		free_page((unsigned long)uctx->shpg);
 
@@ -4036,27 +4087,43 @@ int bnxt_re_mmap(struct ib_ucontext *ib_uctx, struct vm_area_struct *vma)
 	struct bnxt_re_ucontext *uctx = container_of(ib_uctx,
 						   struct bnxt_re_ucontext,
 						   ib_uctx);
-	struct bnxt_re_dev *rdev = uctx->rdev;
+	struct bnxt_re_user_mmap_entry *bnxt_entry;
+	struct rdma_user_mmap_entry *rdma_entry;
+	int ret = 0;
 	u64 pfn;
 
-	if (vma->vm_end - vma->vm_start != PAGE_SIZE)
+	rdma_entry = rdma_user_mmap_entry_get(&uctx->ib_uctx, vma);
+	if (!rdma_entry)
 		return -EINVAL;
 
-	if (vma->vm_pgoff) {
-		vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
-		if (io_remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff,
-				       PAGE_SIZE, vma->vm_page_prot)) {
-			ibdev_err(&rdev->ibdev, "Failed to map DPI");
-			return -EAGAIN;
-		}
-	} else {
-		pfn = virt_to_phys(uctx->shpg) >> PAGE_SHIFT;
-		if (remap_pfn_range(vma, vma->vm_start,
-				    pfn, PAGE_SIZE, vma->vm_page_prot)) {
-			ibdev_err(&rdev->ibdev, "Failed to map shared page");
-			return -EAGAIN;
-		}
+	bnxt_entry = container_of(rdma_entry, struct bnxt_re_user_mmap_entry,
+				  rdma_entry);
+
+	switch (bnxt_entry->mmap_flag) {
+	case BNXT_RE_MMAP_UC_DB:
+		pfn = bnxt_entry->mem_offset >> PAGE_SHIFT;
+		ret = rdma_user_mmap_io(ib_uctx, vma, pfn, PAGE_SIZE,
+					pgprot_noncached(vma->vm_page_prot),
+				rdma_entry);
+		break;
+	case BNXT_RE_MMAP_SH_PAGE:
+		ret = vm_insert_page(vma, vma->vm_start, virt_to_page(uctx->shpg));
+		break;
+	default:
+		ret = -EINVAL;
+		break;
 	}
 
-	return 0;
+	rdma_user_mmap_entry_put(rdma_entry);
+	return ret;
+}
+
+void bnxt_re_mmap_free(struct rdma_user_mmap_entry *rdma_entry)
+{
+	struct bnxt_re_user_mmap_entry *bnxt_entry;
+
+	bnxt_entry = container_of(rdma_entry, struct bnxt_re_user_mmap_entry,
+				  rdma_entry);
+
+	kfree(bnxt_entry);
 }
diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.h b/drivers/infiniband/hw/bnxt_re/ib_verbs.h
index 31f7e34..dcd31ae 100644
--- a/drivers/infiniband/hw/bnxt_re/ib_verbs.h
+++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.h
@@ -60,6 +60,7 @@ struct bnxt_re_pd {
 	struct bnxt_re_dev	*rdev;
 	struct bnxt_qplib_pd	qplib_pd;
 	struct bnxt_re_fence_data fence;
+	struct rdma_user_mmap_entry *pd_db_mmap;
 };
 
 struct bnxt_re_ah {
@@ -136,6 +137,18 @@ struct bnxt_re_ucontext {
 	struct bnxt_qplib_dpi	dpi;
 	void			*shpg;
 	spinlock_t		sh_lock;	/* protect shpg */
+	struct rdma_user_mmap_entry *shpage_mmap;
+};
+
+enum bnxt_re_mmap_flag {
+	BNXT_RE_MMAP_SH_PAGE,
+	BNXT_RE_MMAP_UC_DB,
+};
+
+struct bnxt_re_user_mmap_entry {
+	struct rdma_user_mmap_entry rdma_entry;
+	u64 mem_offset;
+	u8 mmap_flag;
 };
 
 static inline u16 bnxt_re_get_swqe_size(int nsge)
@@ -213,6 +226,8 @@ struct ib_mr *bnxt_re_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 int bnxt_re_alloc_ucontext(struct ib_ucontext *ctx, struct ib_udata *udata);
 void bnxt_re_dealloc_ucontext(struct ib_ucontext *context);
 int bnxt_re_mmap(struct ib_ucontext *context, struct vm_area_struct *vma);
+void bnxt_re_mmap_free(struct rdma_user_mmap_entry *rdma_entry);
+
 
 unsigned long bnxt_re_lock_cqs(struct bnxt_re_qp *qp);
 void bnxt_re_unlock_cqs(struct bnxt_re_qp *qp, unsigned long flags);
diff --git a/drivers/infiniband/hw/bnxt_re/main.c b/drivers/infiniband/hw/bnxt_re/main.c
index b9e2f89..1d361eb 100644
--- a/drivers/infiniband/hw/bnxt_re/main.c
+++ b/drivers/infiniband/hw/bnxt_re/main.c
@@ -539,6 +539,7 @@ static const struct ib_device_ops bnxt_re_dev_ops = {
 	.get_port_immutable = bnxt_re_get_port_immutable,
 	.map_mr_sg = bnxt_re_map_mr_sg,
 	.mmap = bnxt_re_mmap,
+	.mmap_free = bnxt_re_mmap_free,
 	.modify_qp = bnxt_re_modify_qp,
 	.modify_srq = bnxt_re_modify_srq,
 	.poll_cq = bnxt_re_poll_cq,
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_fp.c b/drivers/infiniband/hw/bnxt_re/qplib_fp.c
index f139d4c..ade858f 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_fp.c
+++ b/drivers/infiniband/hw/bnxt_re/qplib_fp.c
@@ -471,7 +471,6 @@ static int bnxt_qplib_map_nq_db(struct bnxt_qplib_nq *nq,  u32 reg_offt)
 	resource_size_t reg_base;
 	struct bnxt_qplib_nq_db *nq_db;
 	struct pci_dev *pdev;
-	int rc = 0;
 
 	pdev = nq->pdev;
 	nq_db = &nq->nq_db;
@@ -481,8 +480,7 @@ static int bnxt_qplib_map_nq_db(struct bnxt_qplib_nq *nq,  u32 reg_offt)
 	if (!nq_db->reg.bar_base) {
 		dev_err(&pdev->dev, "QPLIB: NQ BAR region %d resc start is 0!",
 			nq_db->reg.bar_id);
-		rc = -ENOMEM;
-		goto fail;
+		return -ENOMEM;
 	}
 
 	reg_base = nq_db->reg.bar_base + reg_offt;
@@ -492,15 +490,13 @@ static int bnxt_qplib_map_nq_db(struct bnxt_qplib_nq *nq,  u32 reg_offt)
 	if (!nq_db->reg.bar_reg) {
 		dev_err(&pdev->dev, "QPLIB: NQ BAR region %d mapping failed",
 			nq_db->reg.bar_id);
-		rc = -ENOMEM;
-		goto fail;
+		return -ENOMEM;
 	}
 
 	nq_db->dbinfo.db = nq_db->reg.bar_reg;
 	nq_db->dbinfo.hwq = &nq->hwq;
 	nq_db->dbinfo.xid = nq->ring_id;
-fail:
-	return rc;
+	return 0;
 }
 
 int bnxt_qplib_enable_nq(struct pci_dev *pdev, struct bnxt_qplib_nq *nq,
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_res.c b/drivers/infiniband/hw/bnxt_re/qplib_res.c
index 126d4f2..920ab87 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_res.c
+++ b/drivers/infiniband/hw/bnxt_re/qplib_res.c
@@ -813,7 +813,7 @@ static int bnxt_qplib_alloc_dpi_tbl(struct bnxt_qplib_res     *res,
 	return 0;
 
 unmap_io:
-	pci_iounmap(res->pdev, dpit->dbr_bar_reg_iomem);
+	iounmap(dpit->dbr_bar_reg_iomem);
 	dpit->dbr_bar_reg_iomem = NULL;
 	return -ENOMEM;
 }
-- 
2.5.5


[-- Attachment #2: S/MIME Cryptographic Signature --]
[-- Type: application/pkcs7-signature, Size: 4224 bytes --]

[PATCH v2 for-next 2/6] RDMA/bnxt_re: Add disassociate ucontext support

[Selvin Xavier]

[-- Attachment #1: Type: text/plain, Size: 1207 bytes --]

Add driver disassociation support. Driver uses the APIs rdma_user_mmap_io
api while mapping the IO pages to user space.
Add empty stub for disassociate ucontext.

Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com>
---
v1 - v2:
	Updated the commit message
 drivers/infiniband/hw/bnxt_re/main.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/infiniband/hw/bnxt_re/main.c b/drivers/infiniband/hw/bnxt_re/main.c
index 1d361eb..a866951 100644
--- a/drivers/infiniband/hw/bnxt_re/main.c
+++ b/drivers/infiniband/hw/bnxt_re/main.c
@@ -466,6 +466,10 @@ static int bnxt_re_net_stats_ctx_alloc(struct bnxt_re_dev *rdev,
 	return rc;
 }
 
+static void bnxt_re_disassociate_ucontext(struct ib_ucontext *ibcontext)
+{
+}
+
 /* Device */
 
 static struct bnxt_re_dev *bnxt_re_from_netdev(struct net_device *netdev)
@@ -532,6 +536,7 @@ static const struct ib_device_ops bnxt_re_dev_ops = {
 	.destroy_qp = bnxt_re_destroy_qp,
 	.destroy_srq = bnxt_re_destroy_srq,
 	.device_group = &bnxt_re_dev_attr_group,
+	.disassociate_ucontext = bnxt_re_disassociate_ucontext,
 	.get_dev_fw_str = bnxt_re_query_fw_str,
 	.get_dma_mr = bnxt_re_get_dma_mr,
 	.get_hw_stats = bnxt_re_ib_get_hw_stats,
-- 
2.5.5


[-- Attachment #2: S/MIME Cryptographic Signature --]
[-- Type: application/pkcs7-signature, Size: 4224 bytes --]

[PATCH v2 for-next 3/6] RDMA/bnxt_re: Query function capabilities from firmware

[Selvin Xavier]

[-- Attachment #1: Type: text/plain, Size: 2131 bytes --]

Query Function capabilities to enable advanced features.

Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com>
---
v1 - v2:
	- Removed unnecessary error prints
 drivers/infiniband/hw/bnxt_re/main.c | 23 +++++++++++++++++++++++
 1 file changed, 23 insertions(+)

diff --git a/drivers/infiniband/hw/bnxt_re/main.c b/drivers/infiniband/hw/bnxt_re/main.c
index a866951..993fb62 100644
--- a/drivers/infiniband/hw/bnxt_re/main.c
+++ b/drivers/infiniband/hw/bnxt_re/main.c
@@ -83,6 +83,7 @@ static int bnxt_re_netdev_event(struct notifier_block *notifier,
 				unsigned long event, void *ptr);
 static struct bnxt_re_dev *bnxt_re_from_netdev(struct net_device *netdev);
 static void bnxt_re_dev_uninit(struct bnxt_re_dev *rdev);
+static int bnxt_re_hwrm_qcaps(struct bnxt_re_dev *rdev);
 
 static void bnxt_re_set_drv_mode(struct bnxt_re_dev *rdev, u8 mode)
 {
@@ -91,6 +92,9 @@ static void bnxt_re_set_drv_mode(struct bnxt_re_dev *rdev, u8 mode)
 	cctx = rdev->chip_ctx;
 	cctx->modes.wqe_mode = bnxt_qplib_is_chip_gen_p5(rdev->chip_ctx) ?
 			       mode : BNXT_QPLIB_WQE_MODE_STATIC;
+	if (bnxt_re_hwrm_qcaps(rdev))
+		dev_err(rdev_to_dev(rdev),
+			"Failed to query hwrm qcaps\n");
 }
 
 static void bnxt_re_destroy_chip_ctx(struct bnxt_re_dev *rdev)
@@ -334,6 +338,25 @@ static void bnxt_re_fill_fw_msg(struct bnxt_fw_msg *fw_msg, void *msg,
 	fw_msg->timeout = timeout;
 }
 
+/* Query function capabilities using common hwrm */
+int bnxt_re_hwrm_qcaps(struct bnxt_re_dev *rdev)
+{
+	struct bnxt_en_dev *en_dev = rdev->en_dev;
+	struct hwrm_func_qcaps_output resp = {0};
+	struct hwrm_func_qcaps_input req = {0};
+	struct bnxt_qplib_chip_ctx *cctx;
+	struct bnxt_fw_msg fw_msg;
+
+	cctx = rdev->chip_ctx;
+	memset(&fw_msg, 0, sizeof(fw_msg));
+	bnxt_re_init_hwrm_hdr(rdev, (void *)&req,
+			      HWRM_FUNC_QCAPS, -1, -1);
+	req.fid = cpu_to_le16(0xffff);
+	bnxt_re_fill_fw_msg(&fw_msg, (void *)&req, sizeof(req), (void *)&resp,
+			    sizeof(resp), DFLT_HWRM_CMD_TIMEOUT);
+	return bnxt_send_msg(en_dev, &fw_msg);
+}
+
 static int bnxt_re_net_ring_free(struct bnxt_re_dev *rdev,
 				 u16 fw_ring_id, int type)
 {
-- 
2.5.5


[-- Attachment #2: S/MIME Cryptographic Signature --]
[-- Type: application/pkcs7-signature, Size: 4224 bytes --]

[PATCH v2 for-next 4/6] RDMA/bnxt_re: Move the interface version to chip context structure

[Selvin Xavier]

[-- Attachment #1: Type: text/plain, Size: 1503 bytes --]

FW interface version check is required for multiple features. Moving
the interface version to chip context structure.

Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com>
---
 drivers/infiniband/hw/bnxt_re/main.c       | 2 +-
 drivers/infiniband/hw/bnxt_re/qplib_rcfw.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/infiniband/hw/bnxt_re/main.c b/drivers/infiniband/hw/bnxt_re/main.c
index 993fb62..873ee75 100644
--- a/drivers/infiniband/hw/bnxt_re/main.c
+++ b/drivers/infiniband/hw/bnxt_re/main.c
@@ -1087,7 +1087,7 @@ static void bnxt_re_query_hwrm_intf_version(struct bnxt_re_dev *rdev)
 			  rc);
 		return;
 	}
-	rdev->qplib_ctx.hwrm_intf_ver =
+	rdev->chip_ctx->hwrm_intf_ver =
 		(u64)le16_to_cpu(resp.hwrm_intf_major) << 48 |
 		(u64)le16_to_cpu(resp.hwrm_intf_minor) << 32 |
 		(u64)le16_to_cpu(resp.hwrm_intf_build) << 16 |
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c
index de90691..f610199 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c
+++ b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c
@@ -593,7 +593,7 @@ int bnxt_qplib_alloc_rcfw_channel(struct bnxt_qplib_res *res,
 			"HW channel CREQ allocation failed\n");
 		goto fail;
 	}
-	if (ctx->hwrm_intf_ver < HWRM_VERSION_RCFW_CMDQ_DEPTH_CHECK)
+	if (res->cctx->hwrm_intf_ver < HWRM_VERSION_RCFW_CMDQ_DEPTH_CHECK)
 		rcfw->cmdq_depth = BNXT_QPLIB_CMDQE_MAX_CNT_256;
 	else
 		rcfw->cmdq_depth = BNXT_QPLIB_CMDQE_MAX_CNT_8192;
-- 
2.5.5


[-- Attachment #2: S/MIME Cryptographic Signature --]
[-- Type: application/pkcs7-signature, Size: 4224 bytes --]

[PATCH v2 for-next 5/6] RDMA/bnxt_re: Reorg the bar mapping

[Selvin Xavier]

[-- Attachment #1: Type: text/plain, Size: 18819 bytes --]

Reorganize the code for allocation and mapping of
Doorbell pages. Implements new HW command to get the BAR length
used by L2 driver. These changes are used by the future patch
which maps the WC Doorbell pages.

Also, introduced a new lock dpi_tbl_lock for synchronize the
DB page allocation from users.

Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com>
---
v1 - v2:
	- Few generic cleanup based on internal review
 drivers/infiniband/hw/bnxt_re/ib_verbs.c   |   7 +-
 drivers/infiniband/hw/bnxt_re/main.c       |  71 +++++++++++-
 drivers/infiniband/hw/bnxt_re/qplib_fp.c   |   4 +-
 drivers/infiniband/hw/bnxt_re/qplib_rcfw.h |   1 +
 drivers/infiniband/hw/bnxt_re/qplib_res.c  | 174 +++++++++++++++++++----------
 drivers/infiniband/hw/bnxt_re/qplib_res.h  |  30 +++--
 drivers/infiniband/hw/bnxt_re/qplib_sp.c   |   3 +
 drivers/infiniband/hw/bnxt_re/qplib_sp.h   |   1 +
 8 files changed, 213 insertions(+), 78 deletions(-)

diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.c b/drivers/infiniband/hw/bnxt_re/ib_verbs.c
index 2434174..bc85433 100644
--- a/drivers/infiniband/hw/bnxt_re/ib_verbs.c
+++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.c
@@ -606,8 +606,8 @@ int bnxt_re_alloc_pd(struct ib_pd *ibpd, struct ib_udata *udata)
 			 * ibv_devinfo and family of application when DPIs
 			 * are depleted.
 			 */
-			if (bnxt_qplib_alloc_dpi(&rdev->qplib_res.dpi_tbl,
-						 &ucntx->dpi, ucntx)) {
+			if (bnxt_qplib_alloc_dpi(&rdev->qplib_res,
+						 &ucntx->dpi, ucntx, BNXT_QPLIB_DPI_TYPE_UC)) {
 				rc = -ENOMEM;
 				goto dbfail;
 			}
@@ -4075,8 +4075,7 @@ void bnxt_re_dealloc_ucontext(struct ib_ucontext *ib_uctx)
 		/* Free DPI only if this is the first PD allocated by the
 		 * application and mark the context dpi as NULL
 		 */
-		bnxt_qplib_dealloc_dpi(&rdev->qplib_res,
-				       &rdev->qplib_res.dpi_tbl, &uctx->dpi);
+		bnxt_qplib_dealloc_dpi(&rdev->qplib_res, &uctx->dpi);
 		uctx->dpi.dbr = NULL;
 	}
 }
diff --git a/drivers/infiniband/hw/bnxt_re/main.c b/drivers/infiniband/hw/bnxt_re/main.c
index 873ee75..913cb80 100644
--- a/drivers/infiniband/hw/bnxt_re/main.c
+++ b/drivers/infiniband/hw/bnxt_re/main.c
@@ -85,6 +85,40 @@ static struct bnxt_re_dev *bnxt_re_from_netdev(struct net_device *netdev);
 static void bnxt_re_dev_uninit(struct bnxt_re_dev *rdev);
 static int bnxt_re_hwrm_qcaps(struct bnxt_re_dev *rdev);
 
+static int bnxt_re_hwrm_qcfg(struct bnxt_re_dev *rdev, u32 *db_len,
+			     u32 *offset);
+static void bnxt_re_set_db_offset(struct bnxt_re_dev *rdev)
+{
+	struct bnxt_qplib_chip_ctx *cctx;
+	struct bnxt_en_dev *en_dev;
+	struct bnxt_qplib_res *res;
+	u32 l2db_len = 0;
+	u32 offset = 0;
+	u32 barlen;
+	int rc;
+
+	res = &rdev->qplib_res;
+	en_dev = rdev->en_dev;
+	cctx = rdev->chip_ctx;
+
+	/* Issue qcfg */
+	rc = bnxt_re_hwrm_qcfg(rdev, &l2db_len, &offset);
+	if (rc)
+		dev_info(rdev_to_dev(rdev),
+			 "Couldn't get DB bar size, Low latency framework is disabled\n");
+	/* set register offsets for both UC and WC */
+	res->dpi_tbl.ucreg.offset = res->is_vf ? BNXT_QPLIB_DBR_VF_DB_OFFSET :
+						 BNXT_QPLIB_DBR_PF_DB_OFFSET;
+	res->dpi_tbl.wcreg.offset = res->dpi_tbl.ucreg.offset;
+
+	/* If WC mapping is disabled by L2 driver then en_dev->l2_db_size
+	 * is equal to the DB-Bar actual size. This indicates that L2
+	 * is mapping entire bar as UC-. RoCE driver can't enable WC mapping
+	 * in such cases and DB-push will be disabled.
+	 */
+	barlen = pci_resource_len(res->pdev, RCFW_DBR_PCI_BAR_REGION);
+}
+
 static void bnxt_re_set_drv_mode(struct bnxt_re_dev *rdev, u8 mode)
 {
 	struct bnxt_qplib_chip_ctx *cctx;
@@ -116,6 +150,7 @@ static int bnxt_re_setup_chip_ctx(struct bnxt_re_dev *rdev, u8 wqe_mode)
 {
 	struct bnxt_qplib_chip_ctx *chip_ctx;
 	struct bnxt_en_dev *en_dev;
+	int rc;
 
 	en_dev = rdev->en_dev;
 
@@ -134,6 +169,12 @@ static int bnxt_re_setup_chip_ctx(struct bnxt_re_dev *rdev, u8 wqe_mode)
 	rdev->qplib_res.is_vf = BNXT_EN_VF(en_dev);
 
 	bnxt_re_set_drv_mode(rdev, wqe_mode);
+
+	bnxt_re_set_db_offset(rdev);
+	rc = bnxt_qplib_map_db_bar(&rdev->qplib_res);
+	if (rc)
+		return rc;
+
 	if (bnxt_qplib_determine_atomics(en_dev->pdev))
 		ibdev_info(&rdev->ibdev,
 			   "platform doesn't support global atomics.");
@@ -338,6 +379,30 @@ static void bnxt_re_fill_fw_msg(struct bnxt_fw_msg *fw_msg, void *msg,
 	fw_msg->timeout = timeout;
 }
 
+/* Query device config using common hwrm */
+static int bnxt_re_hwrm_qcfg(struct bnxt_re_dev *rdev, u32 *db_len,
+			     u32 *offset)
+{
+	struct bnxt_en_dev *en_dev = rdev->en_dev;
+	struct hwrm_func_qcfg_output resp = {0};
+	struct hwrm_func_qcfg_input req = {0};
+	struct bnxt_fw_msg fw_msg;
+	int rc;
+
+	memset(&fw_msg, 0, sizeof(fw_msg));
+	bnxt_re_init_hwrm_hdr(rdev, (void *)&req,
+			      HWRM_FUNC_QCFG, -1, -1);
+	req.fid = cpu_to_le16(0xffff);
+	bnxt_re_fill_fw_msg(&fw_msg, (void *)&req, sizeof(req), (void *)&resp,
+			    sizeof(resp), DFLT_HWRM_CMD_TIMEOUT);
+	rc = bnxt_send_msg(en_dev, &fw_msg);
+	if (rc) {
+		*db_len = PAGE_ALIGN(le16_to_cpu(resp.l2_doorbell_bar_size_kb) * 1024);
+		*offset = PAGE_ALIGN(le16_to_cpu(resp.legacy_l2_db_size_kb) * 1024);
+	}
+	return rc;
+}
+
 /* Query function capabilities using common hwrm */
 int bnxt_re_hwrm_qcaps(struct bnxt_re_dev *rdev)
 {
@@ -851,7 +916,6 @@ static void bnxt_re_free_res(struct bnxt_re_dev *rdev)
 
 	if (rdev->qplib_res.dpi_tbl.max) {
 		bnxt_qplib_dealloc_dpi(&rdev->qplib_res,
-				       &rdev->qplib_res.dpi_tbl,
 				       &rdev->dpi_privileged);
 	}
 	if (rdev->qplib_res.rcfw) {
@@ -879,9 +943,9 @@ static int bnxt_re_alloc_res(struct bnxt_re_dev *rdev)
 	if (rc)
 		goto fail;
 
-	rc = bnxt_qplib_alloc_dpi(&rdev->qplib_res.dpi_tbl,
+	rc = bnxt_qplib_alloc_dpi(&rdev->qplib_res,
 				  &rdev->dpi_privileged,
-				  rdev);
+				  rdev, BNXT_QPLIB_DPI_TYPE_KERNEL);
 	if (rc)
 		goto dealloc_res;
 
@@ -921,7 +985,6 @@ static int bnxt_re_alloc_res(struct bnxt_re_dev *rdev)
 		bnxt_qplib_free_nq(&rdev->nq[i]);
 	}
 	bnxt_qplib_dealloc_dpi(&rdev->qplib_res,
-			       &rdev->qplib_res.dpi_tbl,
 			       &rdev->dpi_privileged);
 dealloc_res:
 	bnxt_qplib_free_res(&rdev->qplib_res);
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_fp.c b/drivers/infiniband/hw/bnxt_re/qplib_fp.c
index ade858f..719bdc6 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_fp.c
+++ b/drivers/infiniband/hw/bnxt_re/qplib_fp.c
@@ -655,7 +655,7 @@ int bnxt_qplib_create_srq(struct bnxt_qplib_res *res,
 	srq->dbinfo.xid = srq->id;
 	srq->dbinfo.db = srq->dpi->dbr;
 	srq->dbinfo.max_slot = 1;
-	srq->dbinfo.priv_db = res->dpi_tbl.dbr_bar_reg_iomem;
+	srq->dbinfo.priv_db = res->dpi_tbl.priv_db;
 	if (srq->threshold)
 		bnxt_qplib_armen_db(&srq->dbinfo, DBC_DBC_TYPE_SRQ_ARMENA);
 	srq->arm_req = false;
@@ -2099,7 +2099,7 @@ int bnxt_qplib_create_cq(struct bnxt_qplib_res *res, struct bnxt_qplib_cq *cq)
 	cq->dbinfo.hwq = &cq->hwq;
 	cq->dbinfo.xid = cq->id;
 	cq->dbinfo.db = cq->dpi->dbr;
-	cq->dbinfo.priv_db = res->dpi_tbl.dbr_bar_reg_iomem;
+	cq->dbinfo.priv_db = res->dpi_tbl.priv_db;
 
 	bnxt_qplib_armen_db(&cq->dbinfo, DBC_DBC_TYPE_CQ_ARMENA);
 
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h
index dd56514..4d1ccf1 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h
+++ b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h
@@ -111,6 +111,7 @@ static inline u32 bnxt_qplib_set_cmd_slots(struct cmdq_base *req)
 #define RCFW_BLOCKED_CMD_WAIT_COUNT	20000000UL /* 20 sec */
 
 #define HWRM_VERSION_RCFW_CMDQ_DEPTH_CHECK 0x1000900020011ULL
+#define HWRM_VERSION_DEV_ATTR_MAX_DPI  0x1000A0000000DULL
 
 /* Crsq buf is 1024-Byte */
 struct bnxt_qplib_crsbe {
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_res.c b/drivers/infiniband/hw/bnxt_re/qplib_res.c
index 920ab87..e1cbe59 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_res.c
+++ b/drivers/infiniband/hw/bnxt_re/qplib_res.c
@@ -704,44 +704,73 @@ static int bnxt_qplib_alloc_pd_tbl(struct bnxt_qplib_res *res,
 }
 
 /* DPIs */
-int bnxt_qplib_alloc_dpi(struct bnxt_qplib_dpi_tbl *dpit,
-			 struct bnxt_qplib_dpi     *dpi,
-			 void                      *app)
+int bnxt_qplib_alloc_dpi(struct bnxt_qplib_res *res,
+			 struct bnxt_qplib_dpi *dpi,
+			 void *app, u8 type)
 {
+	struct bnxt_qplib_dpi_tbl *dpit = &res->dpi_tbl;
+	struct bnxt_qplib_reg_desc *reg;
 	u32 bit_num;
+	u64 umaddr;
+
+	reg = &dpit->wcreg;
+	mutex_lock(&res->dpi_tbl_lock);
 
 	bit_num = find_first_bit(dpit->tbl, dpit->max);
-	if (bit_num == dpit->max)
+	if (bit_num == dpit->max) {
+		mutex_unlock(&res->dpi_tbl_lock);
 		return -ENOMEM;
+	}
 
 	/* Found unused DPI */
 	clear_bit(bit_num, dpit->tbl);
 	dpit->app_tbl[bit_num] = app;
 
-	dpi->dpi = bit_num;
-	dpi->dbr = dpit->dbr_bar_reg_iomem + (bit_num * PAGE_SIZE);
-	dpi->umdbr = dpit->unmapped_dbr + (bit_num * PAGE_SIZE);
+	dpi->bit = bit_num;
+	dpi->dpi = bit_num + (reg->offset - dpit->ucreg.offset) / PAGE_SIZE;
+
+	umaddr = reg->bar_base + reg->offset + bit_num * PAGE_SIZE;
+	dpi->umdbr = umaddr;
+
+	switch (type) {
+	case BNXT_QPLIB_DPI_TYPE_KERNEL:
+		/* priviledged dbr was already mapped just initialize it. */
+		dpi->umdbr = dpit->ucreg.bar_base +
+			     dpit->ucreg.offset + bit_num * PAGE_SIZE;
+		dpi->dbr = dpit->priv_db;
+		dpi->dpi = dpi->bit;
+		break;
+	default:
+		dpi->dbr = ioremap(umaddr, PAGE_SIZE);
+		break;
+	}
 
+	dpi->type = type;
+	mutex_unlock(&res->dpi_tbl_lock);
 	return 0;
+
 }
 
 int bnxt_qplib_dealloc_dpi(struct bnxt_qplib_res *res,
-			   struct bnxt_qplib_dpi_tbl *dpit,
-			   struct bnxt_qplib_dpi     *dpi)
+			   struct bnxt_qplib_dpi *dpi)
 {
-	if (dpi->dpi >= dpit->max) {
-		dev_warn(&res->pdev->dev, "Invalid DPI? dpi = %d\n", dpi->dpi);
-		return -EINVAL;
-	}
-	if (test_and_set_bit(dpi->dpi, dpit->tbl)) {
-		dev_warn(&res->pdev->dev, "Freeing an unused DPI? dpi = %d\n",
-			 dpi->dpi);
+	struct bnxt_qplib_dpi_tbl *dpit = &res->dpi_tbl;
+
+	mutex_lock(&res->dpi_tbl_lock);
+	if (dpi->dpi && dpi->type != BNXT_QPLIB_DPI_TYPE_KERNEL)
+		pci_iounmap(res->pdev, dpi->dbr);
+
+	if (test_and_set_bit(dpi->bit, dpit->tbl)) {
+		dev_warn(&res->pdev->dev,
+			 "Freeing an unused DPI? dpi = %d, bit = %d\n",
+				dpi->dpi, dpi->bit);
+		mutex_unlock(&res->dpi_tbl_lock);
 		return -EINVAL;
 	}
 	if (dpit->app_tbl)
-		dpit->app_tbl[dpi->dpi] = NULL;
+		dpit->app_tbl[dpi->bit] = NULL;
 	memset(dpi, 0, sizeof(*dpi));
-
+	mutex_unlock(&res->dpi_tbl_lock);
 	return 0;
 }
 
@@ -750,52 +779,38 @@ static void bnxt_qplib_free_dpi_tbl(struct bnxt_qplib_res     *res,
 {
 	kfree(dpit->tbl);
 	kfree(dpit->app_tbl);
-	if (dpit->dbr_bar_reg_iomem)
-		pci_iounmap(res->pdev, dpit->dbr_bar_reg_iomem);
-	memset(dpit, 0, sizeof(*dpit));
+	dpit->tbl = NULL;
+	dpit->app_tbl = NULL;
+	dpit->max = 0;
 }
 
-static int bnxt_qplib_alloc_dpi_tbl(struct bnxt_qplib_res     *res,
-				    struct bnxt_qplib_dpi_tbl *dpit,
-				    u32                       dbr_offset)
+static int bnxt_qplib_alloc_dpi_tbl(struct bnxt_qplib_res *res,
+				    struct bnxt_qplib_dev_attr *dev_attr)
 {
-	u32 dbr_bar_reg = RCFW_DBR_PCI_BAR_REGION;
-	resource_size_t bar_reg_base;
-	u32 dbr_len, bytes;
-
-	if (dpit->dbr_bar_reg_iomem) {
-		dev_err(&res->pdev->dev, "DBR BAR region %d already mapped\n",
-			dbr_bar_reg);
-		return -EALREADY;
-	}
-
-	bar_reg_base = pci_resource_start(res->pdev, dbr_bar_reg);
-	if (!bar_reg_base) {
-		dev_err(&res->pdev->dev, "BAR region %d resc start failed\n",
-			dbr_bar_reg);
-		return -ENOMEM;
-	}
+	struct bnxt_qplib_dpi_tbl *dpit;
+	struct bnxt_qplib_reg_desc *reg;
+	unsigned long bar_len;
+	u32 dbr_offset;
+	u32 bytes;
 
-	dbr_len = pci_resource_len(res->pdev, dbr_bar_reg) - dbr_offset;
-	if (!dbr_len || ((dbr_len & (PAGE_SIZE - 1)) != 0)) {
-		dev_err(&res->pdev->dev, "Invalid DBR length %d\n", dbr_len);
-		return -ENOMEM;
-	}
+	dpit = &res->dpi_tbl;
+	reg = &dpit->wcreg;
 
-	dpit->dbr_bar_reg_iomem = ioremap(bar_reg_base + dbr_offset,
-						  dbr_len);
-	if (!dpit->dbr_bar_reg_iomem) {
-		dev_err(&res->pdev->dev,
-			"FP: DBR BAR region %d mapping failed\n", dbr_bar_reg);
-		return -ENOMEM;
+	if (!bnxt_qplib_is_chip_gen_p5(res->cctx)) {
+		/* Offest should come from L2 driver */
+		dbr_offset = dev_attr->l2_db_size;
+		dpit->ucreg.offset = dbr_offset;
+		dpit->wcreg.offset = dbr_offset;
 	}
 
-	dpit->unmapped_dbr = bar_reg_base + dbr_offset;
-	dpit->max = dbr_len / PAGE_SIZE;
+	bar_len = pci_resource_len(res->pdev, reg->bar_id);
+	dpit->max = (bar_len - reg->offset) / PAGE_SIZE;
+	if (dev_attr->max_dpi)
+		dpit->max = min_t(u32, dpit->max, dev_attr->max_dpi);
 
-	dpit->app_tbl = kcalloc(dpit->max, sizeof(void *), GFP_KERNEL);
+	dpit->app_tbl = kcalloc(dpit->max,  sizeof(void *), GFP_KERNEL);
 	if (!dpit->app_tbl)
-		goto unmap_io;
+		return -ENOMEM;
 
 	bytes = dpit->max >> 3;
 	if (!bytes)
@@ -805,17 +820,14 @@ static int bnxt_qplib_alloc_dpi_tbl(struct bnxt_qplib_res     *res,
 	if (!dpit->tbl) {
 		kfree(dpit->app_tbl);
 		dpit->app_tbl = NULL;
-		goto unmap_io;
+		return -ENOMEM;
 	}
 
 	memset((u8 *)dpit->tbl, 0xFF, bytes);
+	dpit->priv_db = dpit->ucreg.bar_reg + dpit->ucreg.offset;
 
 	return 0;
 
-unmap_io:
-	iounmap(dpit->dbr_bar_reg_iomem);
-	dpit->dbr_bar_reg_iomem = NULL;
-	return -ENOMEM;
 }
 
 /* Stats */
@@ -882,7 +894,7 @@ int bnxt_qplib_alloc_res(struct bnxt_qplib_res *res, struct pci_dev *pdev,
 	if (rc)
 		goto fail;
 
-	rc = bnxt_qplib_alloc_dpi_tbl(res, &res->dpi_tbl, dev_attr->l2_db_size);
+	rc = bnxt_qplib_alloc_dpi_tbl(res, dev_attr);
 	if (rc)
 		goto fail;
 
@@ -892,6 +904,46 @@ int bnxt_qplib_alloc_res(struct bnxt_qplib_res *res, struct pci_dev *pdev,
 	return rc;
 }
 
+void bnxt_qplib_unmap_db_bar(struct bnxt_qplib_res *res)
+{
+	struct bnxt_qplib_reg_desc *reg;
+
+	reg = &res->dpi_tbl.ucreg;
+	if (reg->bar_reg)
+		pci_iounmap(res->pdev, reg->bar_reg);
+	reg->bar_reg = NULL;
+	reg->bar_base = 0;
+	reg->len = 0;
+	reg->bar_id = 0;
+}
+
+int bnxt_qplib_map_db_bar(struct bnxt_qplib_res *res)
+{
+	struct bnxt_qplib_reg_desc *ucreg;
+	struct bnxt_qplib_reg_desc *wcreg;
+
+	wcreg = &res->dpi_tbl.wcreg;
+	wcreg->bar_id = RCFW_DBR_PCI_BAR_REGION;
+	wcreg->bar_base = pci_resource_start(res->pdev, wcreg->bar_id);
+
+	ucreg = &res->dpi_tbl.ucreg;
+	ucreg->bar_id = RCFW_DBR_PCI_BAR_REGION;
+	ucreg->bar_base = pci_resource_start(res->pdev, ucreg->bar_id);
+	ucreg->len = ucreg->offset + PAGE_SIZE;
+	if (!ucreg->len || ((ucreg->len & (PAGE_SIZE - 1)) != 0)) {
+		dev_err(&res->pdev->dev, "QPLIB: invalid dbr length %d",
+			(int)ucreg->len);
+		return -EINVAL;
+	}
+	ucreg->bar_reg = ioremap(ucreg->bar_base, ucreg->len);
+	if (!ucreg->bar_reg) {
+		dev_err(&res->pdev->dev, "priviledged dpi map failed!");
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
 int bnxt_qplib_determine_atomics(struct pci_dev *dev)
 {
 	int comp;
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_res.h b/drivers/infiniband/hw/bnxt_re/qplib_res.h
index 982e2c9..95b1d6c 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_res.h
+++ b/drivers/infiniband/hw/bnxt_re/qplib_res.h
@@ -56,8 +56,12 @@ struct bnxt_qplib_chip_ctx {
 	u8	chip_metal;
 	u16	hw_stats_size;
 	struct bnxt_qplib_drv_modes modes;
+	u64 hwrm_intf_ver;
 };
 
+#define BNXT_QPLIB_DBR_PF_DB_OFFSET     0x10000
+#define BNXT_QPLIB_DBR_VF_DB_OFFSET     0x4000
+
 #define PTR_CNT_PER_PG		(PAGE_SIZE / sizeof(void *))
 #define PTR_MAX_IDX_PER_PG	(PTR_CNT_PER_PG - 1)
 #define PTR_PG(x)		(((x) & ~PTR_MAX_IDX_PER_PG) / PTR_CNT_PER_PG)
@@ -109,6 +113,7 @@ enum bnxt_qplib_hwrm_pg_size {
 struct bnxt_qplib_reg_desc {
 	u8		bar_id;
 	resource_size_t	bar_base;
+	unsigned long	offset;
 	void __iomem	*bar_reg;
 	size_t		len;
 };
@@ -185,18 +190,26 @@ struct bnxt_qplib_sgid_tbl {
 	u8				*vlan;
 };
 
+enum {
+	BNXT_QPLIB_DPI_TYPE_KERNEL      = 0,
+	BNXT_QPLIB_DPI_TYPE_UC          = 1,
+};
+
 struct bnxt_qplib_dpi {
 	u32				dpi;
+	u32				bit;
 	void __iomem			*dbr;
 	u64				umdbr;
+	u8				type;
 };
 
 struct bnxt_qplib_dpi_tbl {
 	void				**app_tbl;
 	unsigned long			*tbl;
 	u16				max;
-	void __iomem			*dbr_bar_reg_iomem;
-	u64				unmapped_dbr;
+	struct bnxt_qplib_reg_desc	ucreg; /* Hold entire DB bar. */
+	struct bnxt_qplib_reg_desc	wcreg;
+	void __iomem			*priv_db;
 };
 
 struct bnxt_qplib_stats {
@@ -241,7 +254,6 @@ struct bnxt_qplib_ctx {
 	struct bnxt_qplib_tqm_ctx	tqm_ctx;
 	struct bnxt_qplib_stats		stats;
 	struct bnxt_qplib_vf_res	vf_res;
-	u64				hwrm_intf_ver;
 };
 
 struct bnxt_qplib_res {
@@ -253,6 +265,8 @@ struct bnxt_qplib_res {
 	struct bnxt_qplib_pd_tbl	pd_tbl;
 	struct bnxt_qplib_sgid_tbl	sgid_tbl;
 	struct bnxt_qplib_dpi_tbl	dpi_tbl;
+	/* To protect the dpi table bit map */
+	struct mutex                    dpi_tbl_lock;
 	bool				prio;
 	bool                            is_vf;
 };
@@ -344,11 +358,10 @@ int bnxt_qplib_alloc_pd(struct bnxt_qplib_pd_tbl *pd_tbl,
 int bnxt_qplib_dealloc_pd(struct bnxt_qplib_res *res,
 			  struct bnxt_qplib_pd_tbl *pd_tbl,
 			  struct bnxt_qplib_pd *pd);
-int bnxt_qplib_alloc_dpi(struct bnxt_qplib_dpi_tbl *dpit,
-			 struct bnxt_qplib_dpi     *dpi,
-			 void                      *app);
+int bnxt_qplib_alloc_dpi(struct bnxt_qplib_res *res,
+			 struct bnxt_qplib_dpi *dpi,
+			 void *app, u8 type);
 int bnxt_qplib_dealloc_dpi(struct bnxt_qplib_res *res,
-			   struct bnxt_qplib_dpi_tbl *dpi_tbl,
 			   struct bnxt_qplib_dpi *dpi);
 void bnxt_qplib_cleanup_res(struct bnxt_qplib_res *res);
 int bnxt_qplib_init_res(struct bnxt_qplib_res *res);
@@ -361,6 +374,9 @@ void bnxt_qplib_free_ctx(struct bnxt_qplib_res *res,
 int bnxt_qplib_alloc_ctx(struct bnxt_qplib_res *res,
 			 struct bnxt_qplib_ctx *ctx,
 			 bool virt_fn, bool is_p5);
+int bnxt_qplib_map_db_bar(struct bnxt_qplib_res *res);
+void bnxt_qplib_unmap_db_bar(struct bnxt_qplib_res *res);
+
 int bnxt_qplib_determine_atomics(struct pci_dev *dev);
 
 static inline void bnxt_qplib_hwq_incr_prod(struct bnxt_qplib_hwq *hwq, u32 cnt)
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_sp.c b/drivers/infiniband/hw/bnxt_re/qplib_sp.c
index 1714a1e..fe3a22d 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_sp.c
+++ b/drivers/infiniband/hw/bnxt_re/qplib_sp.c
@@ -170,6 +170,9 @@ int bnxt_qplib_get_dev_attr(struct bnxt_qplib_rcfw *rcfw,
 		attr->tqm_alloc_reqs[i * 4 + 3] = *(++tqm_alloc);
 	}
 
+	if (rcfw->res->cctx->hwrm_intf_ver >= HWRM_VERSION_DEV_ATTR_MAX_DPI)
+		attr->max_dpi = le32_to_cpu(sb->max_dpi);
+
 	attr->is_atomic = bnxt_qplib_is_atomic_cap(rcfw);
 bail:
 	bnxt_qplib_rcfw_free_sbuf(rcfw, sbuf);
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_sp.h b/drivers/infiniband/hw/bnxt_re/qplib_sp.h
index 5de87465..0efd464 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_sp.h
+++ b/drivers/infiniband/hw/bnxt_re/qplib_sp.h
@@ -72,6 +72,7 @@ struct bnxt_qplib_dev_attr {
 	u8				tqm_alloc_reqs[MAX_TQM_ALLOC_REQ];
 	bool				is_atomic;
 	u16                             dev_cap_flags;
+	u32                             max_dpi;
 };
 
 struct bnxt_qplib_pd {
-- 
2.5.5


[-- Attachment #2: S/MIME Cryptographic Signature --]
[-- Type: application/pkcs7-signature, Size: 4224 bytes --]

[PATCH v2 for-next 6/6] RDMA/bnxt_re: Enable low latency push

[Selvin Xavier]

[-- Attachment #1: Type: text/plain, Size: 13302 bytes --]

Introduce driver specific uapi functionalites. Added
a alloc_page functionality for user library to allocate
specific pages. Currently added support for allocating
write combine pages for push functinality. This interface
shall be extended for other page allocations.

Allocate a WC page using the uapi hook for enabling the low latency
push in Gen P5 adapters for small packets. This is supported only
for the user space QPs.

Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com>
---
 v1 - v2:
	- Implemented the driver defined uapis to allocate page
 	- Few generic code cleanup
 drivers/infiniband/hw/bnxt_re/bnxt_re.h   |   3 +
 drivers/infiniband/hw/bnxt_re/ib_verbs.c  | 149 ++++++++++++++++++++++++++++++
 drivers/infiniband/hw/bnxt_re/ib_verbs.h  |   4 +
 drivers/infiniband/hw/bnxt_re/main.c      |  17 +++-
 drivers/infiniband/hw/bnxt_re/qplib_res.c |   3 +
 drivers/infiniband/hw/bnxt_re/qplib_res.h |   3 +-
 include/uapi/rdma/bnxt_re-abi.h           |  32 +++++++
 7 files changed, 209 insertions(+), 2 deletions(-)

diff --git a/drivers/infiniband/hw/bnxt_re/bnxt_re.h b/drivers/infiniband/hw/bnxt_re/bnxt_re.h
index 5a2baf4..d436327 100644
--- a/drivers/infiniband/hw/bnxt_re/bnxt_re.h
+++ b/drivers/infiniband/hw/bnxt_re/bnxt_re.h
@@ -39,6 +39,7 @@
 
 #ifndef __BNXT_RE_H__
 #define __BNXT_RE_H__
+#include <rdma/uverbs_ioctl.h>
 #include "hw_counters.h"
 #define ROCE_DRV_MODULE_NAME		"bnxt_re"
 
@@ -187,4 +188,6 @@ static inline struct device *rdev_to_dev(struct bnxt_re_dev *rdev)
 		return  &rdev->ibdev.dev;
 	return NULL;
 }
+
+extern const struct uapi_definition bnxt_re_uapi_defs[];
 #endif
diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.c b/drivers/infiniband/hw/bnxt_re/ib_verbs.c
index bc85433..60169fc 100644
--- a/drivers/infiniband/hw/bnxt_re/ib_verbs.c
+++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.c
@@ -61,6 +61,15 @@
 
 #include "bnxt_re.h"
 #include "ib_verbs.h"
+
+#include <rdma/uverbs_types.h>
+#include <rdma/uverbs_std_types.h>
+
+#include <rdma/ib_user_ioctl_cmds.h>
+
+#define UVERBS_MODULE_NAME bnxt_re
+#include <rdma/uverbs_named_ioctl.h>
+
 #include <rdma/bnxt_re-abi.h>
 
 static int __from_ib_access_flags(int iflags)
@@ -546,6 +555,7 @@ bnxt_re_mmap_entry_insert(struct bnxt_re_ucontext *uctx, u64 mem_offset,
 
 	entry->mem_offset = mem_offset;
 	entry->mmap_flag = mmap_flag;
+	entry->uctx = uctx;
 
 	ret = rdma_user_mmap_entry_insert(&uctx->ib_uctx,
 					  &entry->rdma_entry, PAGE_SIZE);
@@ -599,6 +609,7 @@ int bnxt_re_alloc_pd(struct ib_pd *ibpd, struct ib_udata *udata)
 	}
 
 	if (udata) {
+		struct bnxt_qplib_chip_ctx *cctx = rdev->chip_ctx;
 		struct bnxt_re_pd_resp resp = {};
 
 		if (!ucntx->dpi.dbr) {
@@ -611,6 +622,9 @@ int bnxt_re_alloc_pd(struct ib_pd *ibpd, struct ib_udata *udata)
 				rc = -ENOMEM;
 				goto dbfail;
 			}
+			/* Set the comp_mask to indicate users to enable WC DPI */
+			if (cctx->modes.db_push)
+				resp.comp_mask = BNXT_RE_COMP_MASK_PD_WC_DPI_SUP;
 		}
 
 		resp.pdid = pd->qplib_pd.id;
@@ -4036,6 +4050,9 @@ int bnxt_re_alloc_ucontext(struct ib_ucontext *ctx, struct ib_udata *udata)
 	resp.comp_mask |= BNXT_RE_UCNTX_CMASK_HAVE_MODE;
 	resp.mode = rdev->chip_ctx->modes.wqe_mode;
 
+	if (rdev->chip_ctx->modes.db_push)
+		resp.comp_mask |= BNXT_RE_UCNTX_CMASK_WC_DPI_ENABLED;
+
 	entry = bnxt_re_mmap_entry_insert(uctx, 0, BNXT_RE_MMAP_SH_PAGE, NULL);
 	if (!entry) {
 		rc = -ENOMEM;
@@ -4099,6 +4116,12 @@ int bnxt_re_mmap(struct ib_ucontext *ib_uctx, struct vm_area_struct *vma)
 				  rdma_entry);
 
 	switch (bnxt_entry->mmap_flag) {
+	case BNXT_RE_MMAP_WC_DB:
+		pfn = bnxt_entry->mem_offset >> PAGE_SHIFT;
+		ret = rdma_user_mmap_io(ib_uctx, vma, pfn, PAGE_SIZE,
+					pgprot_writecombine(vma->vm_page_prot),
+					rdma_entry);
+		break;
 	case BNXT_RE_MMAP_UC_DB:
 		pfn = bnxt_entry->mem_offset >> PAGE_SHIFT;
 		ret = rdma_user_mmap_io(ib_uctx, vma, pfn, PAGE_SIZE,
@@ -4126,3 +4149,129 @@ void bnxt_re_mmap_free(struct rdma_user_mmap_entry *rdma_entry)
 
 	kfree(bnxt_entry);
 }
+
+static int UVERBS_HANDLER(BNXT_RE_METHOD_ALLOC_PAGE)(struct uverbs_attr_bundle *attrs)
+{
+	struct ib_uobject *uobj = uverbs_attr_get_uobject(attrs, BNXT_RE_ALLOC_PAGE_HANDLE);
+	enum bnxt_re_alloc_page_type alloc_type;
+	struct bnxt_re_user_mmap_entry *entry;
+	enum bnxt_re_mmap_flag mmap_flag;
+	struct bnxt_qplib_chip_ctx *cctx;
+	struct bnxt_re_ucontext *uctx;
+	struct bnxt_re_dev *rdev;
+	u64 mmap_offset;
+	u32 length;
+	u32 dpi;
+	u64 dbr;
+	int err;
+
+	uctx = container_of(ib_uverbs_get_ucontext(attrs), struct bnxt_re_ucontext, ib_uctx);
+	if (IS_ERR(uctx))
+		return PTR_ERR(uctx);
+
+	err = uverbs_get_const(&alloc_type, attrs, BNXT_RE_ALLOC_PAGE_TYPE);
+	if (err)
+		return err;
+
+	rdev = uctx->rdev;
+	cctx = rdev->chip_ctx;
+
+	switch (alloc_type) {
+	case BNXT_RE_ALLOC_WC_PAGE:
+		if (cctx->modes.db_push)  {
+			if (bnxt_qplib_alloc_dpi(&rdev->qplib_res, &uctx->wcdpi,
+						 uctx, BNXT_QPLIB_DPI_TYPE_WC))
+				return -ENOMEM;
+		}
+		length = PAGE_SIZE;
+		dpi = uctx->wcdpi.dpi;
+		dbr = (u64)uctx->wcdpi.umdbr;
+		mmap_flag = BNXT_RE_MMAP_WC_DB;
+
+		break;
+
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	entry = bnxt_re_mmap_entry_insert(uctx, dbr, mmap_flag, &mmap_offset);
+	if (IS_ERR(entry))
+		return PTR_ERR(entry);
+
+	uobj->object = entry;
+	uverbs_finalize_uobj_create(attrs, BNXT_RE_ALLOC_PAGE_HANDLE);
+	err = uverbs_copy_to(attrs, BNXT_RE_ALLOC_PAGE_MMAP_OFFSET,
+			     &mmap_offset, sizeof(mmap_offset));
+	if (err)
+		return err;
+
+	err = uverbs_copy_to(attrs, BNXT_RE_ALLOC_PAGE_MMAP_LENGTH,
+			     &length, sizeof(length));
+	if (err)
+		return err;
+
+	err = uverbs_copy_to(attrs, BNXT_RE_ALLOC_PAGE_DPI,
+			     &dpi, sizeof(length));
+	if (err)
+		return err;
+
+	return 0;
+}
+
+static int alloc_page_obj_cleanup(struct ib_uobject *uobject,
+				  enum rdma_remove_reason why,
+			    struct uverbs_attr_bundle *attrs)
+{
+	struct  bnxt_re_user_mmap_entry *entry = uobject->object;
+	struct bnxt_re_ucontext *uctx = entry->uctx;
+
+	switch (entry->mmap_flag) {
+	case BNXT_RE_MMAP_WC_DB:
+		if (uctx && uctx->wcdpi.dbr) {
+			struct bnxt_re_dev *rdev = uctx->rdev;
+
+			bnxt_qplib_dealloc_dpi(&rdev->qplib_res, &uctx->wcdpi);
+			uctx->wcdpi.dbr = NULL;
+		}
+		break;
+	default:
+		goto exit;
+	}
+	rdma_user_mmap_entry_remove(&entry->rdma_entry);
+exit:
+	return 0;
+}
+
+DECLARE_UVERBS_NAMED_METHOD(BNXT_RE_METHOD_ALLOC_PAGE,
+			    UVERBS_ATTR_IDR(BNXT_RE_ALLOC_PAGE_HANDLE,
+					    BNXT_RE_OBJECT_ALLOC_PAGE,
+					    UVERBS_ACCESS_NEW,
+					    UA_MANDATORY),
+			    UVERBS_ATTR_CONST_IN(BNXT_RE_ALLOC_PAGE_TYPE,
+						 enum bnxt_re_alloc_page_type,
+						 UA_MANDATORY),
+			    UVERBS_ATTR_PTR_OUT(BNXT_RE_ALLOC_PAGE_MMAP_OFFSET,
+						UVERBS_ATTR_TYPE(u64),
+						UA_MANDATORY),
+			    UVERBS_ATTR_PTR_OUT(BNXT_RE_ALLOC_PAGE_MMAP_LENGTH,
+						UVERBS_ATTR_TYPE(u32),
+						UA_MANDATORY),
+			    UVERBS_ATTR_PTR_OUT(BNXT_RE_ALLOC_PAGE_DPI,
+						UVERBS_ATTR_TYPE(u32),
+						UA_MANDATORY));
+
+DECLARE_UVERBS_NAMED_METHOD_DESTROY(BNXT_RE_METHOD_DESTROY_PAGE,
+				    UVERBS_ATTR_IDR(BNXT_RE_DESTROY_PAGE_HANDLE,
+						    BNXT_RE_OBJECT_ALLOC_PAGE,
+						    UVERBS_ACCESS_DESTROY,
+						    UA_MANDATORY));
+
+DECLARE_UVERBS_NAMED_OBJECT(BNXT_RE_OBJECT_ALLOC_PAGE,
+			    UVERBS_TYPE_ALLOC_IDR(alloc_page_obj_cleanup),
+			    &UVERBS_METHOD(BNXT_RE_METHOD_ALLOC_PAGE),
+			    &UVERBS_METHOD(BNXT_RE_METHOD_DESTROY_PAGE));
+
+const struct uapi_definition bnxt_re_uapi_defs[] = {
+	UAPI_DEF_CHAIN_OBJ_TREE_NAMED(BNXT_RE_OBJECT_ALLOC_PAGE),
+	{}
+};
diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.h b/drivers/infiniband/hw/bnxt_re/ib_verbs.h
index dcd31ae..32d9e9d 100644
--- a/drivers/infiniband/hw/bnxt_re/ib_verbs.h
+++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.h
@@ -61,6 +61,7 @@ struct bnxt_re_pd {
 	struct bnxt_qplib_pd	qplib_pd;
 	struct bnxt_re_fence_data fence;
 	struct rdma_user_mmap_entry *pd_db_mmap;
+	struct rdma_user_mmap_entry *pd_wcdb_mmap;
 };
 
 struct bnxt_re_ah {
@@ -135,6 +136,7 @@ struct bnxt_re_ucontext {
 	struct ib_ucontext      ib_uctx;
 	struct bnxt_re_dev	*rdev;
 	struct bnxt_qplib_dpi	dpi;
+	struct bnxt_qplib_dpi   wcdpi;
 	void			*shpg;
 	spinlock_t		sh_lock;	/* protect shpg */
 	struct rdma_user_mmap_entry *shpage_mmap;
@@ -143,10 +145,12 @@ struct bnxt_re_ucontext {
 enum bnxt_re_mmap_flag {
 	BNXT_RE_MMAP_SH_PAGE,
 	BNXT_RE_MMAP_UC_DB,
+	BNXT_RE_MMAP_WC_DB,
 };
 
 struct bnxt_re_user_mmap_entry {
 	struct rdma_user_mmap_entry rdma_entry;
+	struct bnxt_re_ucontext *uctx;
 	u64 mem_offset;
 	u8 mmap_flag;
 };
diff --git a/drivers/infiniband/hw/bnxt_re/main.c b/drivers/infiniband/hw/bnxt_re/main.c
index 913cb80..2a6e98e 100644
--- a/drivers/infiniband/hw/bnxt_re/main.c
+++ b/drivers/infiniband/hw/bnxt_re/main.c
@@ -66,6 +66,7 @@
 #include <rdma/bnxt_re-abi.h>
 #include "bnxt.h"
 #include "hw_counters.h"
+#include "ib_verbs.h"
 
 static char version[] =
 		BNXT_RE_DESC "\n";
@@ -117,6 +118,10 @@ static void bnxt_re_set_db_offset(struct bnxt_re_dev *rdev)
 	 * in such cases and DB-push will be disabled.
 	 */
 	barlen = pci_resource_len(res->pdev, RCFW_DBR_PCI_BAR_REGION);
+	if (cctx->modes.db_push && l2db_len && en_dev->l2_db_size != barlen) {
+		res->dpi_tbl.wcreg.offset = en_dev->l2_db_size;
+		dev_info(rdev_to_dev(rdev),  "Low latency framework is enabled\n");
+	}
 }
 
 static void bnxt_re_set_drv_mode(struct bnxt_re_dev *rdev, u8 mode)
@@ -411,6 +416,7 @@ int bnxt_re_hwrm_qcaps(struct bnxt_re_dev *rdev)
 	struct hwrm_func_qcaps_input req = {0};
 	struct bnxt_qplib_chip_ctx *cctx;
 	struct bnxt_fw_msg fw_msg;
+	int rc;
 
 	cctx = rdev->chip_ctx;
 	memset(&fw_msg, 0, sizeof(fw_msg));
@@ -419,7 +425,13 @@ int bnxt_re_hwrm_qcaps(struct bnxt_re_dev *rdev)
 	req.fid = cpu_to_le16(0xffff);
 	bnxt_re_fill_fw_msg(&fw_msg, (void *)&req, sizeof(req), (void *)&resp,
 			    sizeof(resp), DFLT_HWRM_CMD_TIMEOUT);
-	return bnxt_send_msg(en_dev, &fw_msg);
+
+	rc = bnxt_send_msg(en_dev, &fw_msg);
+	if (rc)
+		return rc;
+	cctx->modes.db_push = le32_to_cpu(resp.flags) & FUNC_QCAPS_RESP_FLAGS_WCB_PUSH_MODE;
+
+	return 0;
 }
 
 static int bnxt_re_net_ring_free(struct bnxt_re_dev *rdev,
@@ -673,6 +685,9 @@ static int bnxt_re_register_ib(struct bnxt_re_dev *rdev)
 	ibdev->dev.parent = &rdev->en_dev->pdev->dev;
 	ibdev->local_dma_lkey = BNXT_QPLIB_RSVD_LKEY;
 
+	if (IS_ENABLED(CONFIG_INFINIBAND_USER_ACCESS))
+		ibdev->driver_def = bnxt_re_uapi_defs;
+
 	ib_set_device_ops(ibdev, &bnxt_re_dev_ops);
 	ret = ib_device_set_netdev(&rdev->ibdev, rdev->netdev, 1);
 	if (ret)
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_res.c b/drivers/infiniband/hw/bnxt_re/qplib_res.c
index e1cbe59..174db83 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_res.c
+++ b/drivers/infiniband/hw/bnxt_re/qplib_res.c
@@ -740,6 +740,9 @@ int bnxt_qplib_alloc_dpi(struct bnxt_qplib_res *res,
 		dpi->dbr = dpit->priv_db;
 		dpi->dpi = dpi->bit;
 		break;
+	case BNXT_QPLIB_DPI_TYPE_WC:
+		dpi->dbr = ioremap_wc(umaddr, PAGE_SIZE);
+		break;
 	default:
 		dpi->dbr = ioremap(umaddr, PAGE_SIZE);
 		break;
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_res.h b/drivers/infiniband/hw/bnxt_re/qplib_res.h
index 95b1d6c..dc39f67 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_res.h
+++ b/drivers/infiniband/hw/bnxt_re/qplib_res.h
@@ -47,7 +47,7 @@ extern const struct bnxt_qplib_gid bnxt_qplib_gid_zero;
 
 struct bnxt_qplib_drv_modes {
 	u8	wqe_mode;
-	/* Other modes to follow here */
+	bool db_push;
 };
 
 struct bnxt_qplib_chip_ctx {
@@ -193,6 +193,7 @@ struct bnxt_qplib_sgid_tbl {
 enum {
 	BNXT_QPLIB_DPI_TYPE_KERNEL      = 0,
 	BNXT_QPLIB_DPI_TYPE_UC          = 1,
+	BNXT_QPLIB_DPI_TYPE_WC          = 2
 };
 
 struct bnxt_qplib_dpi {
diff --git a/include/uapi/rdma/bnxt_re-abi.h b/include/uapi/rdma/bnxt_re-abi.h
index c4e9077..3efc068 100644
--- a/include/uapi/rdma/bnxt_re-abi.h
+++ b/include/uapi/rdma/bnxt_re-abi.h
@@ -41,6 +41,7 @@
 #define __BNXT_RE_UVERBS_ABI_H__
 
 #include <linux/types.h>
+#include <rdma/ib_user_ioctl_cmds.h>
 
 #define BNXT_RE_ABI_VERSION	1
 
@@ -51,6 +52,7 @@
 enum {
 	BNXT_RE_UCNTX_CMASK_HAVE_CCTX = 0x1ULL,
 	BNXT_RE_UCNTX_CMASK_HAVE_MODE = 0x02ULL,
+	BNXT_RE_UCNTX_CMASK_WC_DPI_ENABLED = 0x04ULL,
 };
 
 enum bnxt_re_wqe_mode {
@@ -78,10 +80,15 @@ struct bnxt_re_uctx_resp {
  * not 8 byted aligned. To avoid undesired padding in various cases we have to
  * set this struct to packed.
  */
+enum {
+	BNXT_RE_COMP_MASK_PD_WC_DPI_SUP = 0x01,
+};
+
 struct bnxt_re_pd_resp {
 	__u32 pdid;
 	__u32 dpi;
 	__u64 dbr;
+	__u64 comp_mask;
 } __attribute__((packed, aligned(4)));
 
 struct bnxt_re_cq_req {
@@ -127,4 +134,29 @@ enum bnxt_re_shpg_offt {
 	BNXT_RE_END_RESV_OFFT	= 0xFF0
 };
 
+enum bnxt_re_objects {
+	BNXT_RE_OBJECT_ALLOC_PAGE = (1U << UVERBS_ID_NS_SHIFT),
+};
+
+enum bnxt_re_alloc_page_type {
+	BNXT_RE_ALLOC_WC_PAGE = 0,
+};
+
+enum bnxt_re_var_alloc_page_attrs {
+	BNXT_RE_ALLOC_PAGE_HANDLE = (1U << UVERBS_ID_NS_SHIFT),
+	BNXT_RE_ALLOC_PAGE_TYPE,
+	BNXT_RE_ALLOC_PAGE_DPI,
+	BNXT_RE_ALLOC_PAGE_MMAP_OFFSET,
+	BNXT_RE_ALLOC_PAGE_MMAP_LENGTH,
+};
+
+enum bnxt_re_alloc_page_attrs {
+	BNXT_RE_DESTROY_PAGE_HANDLE = (1U << UVERBS_ID_NS_SHIFT),
+};
+
+enum bnxt_re_alloc_page_methods {
+	BNXT_RE_METHOD_ALLOC_PAGE = (1U << UVERBS_ID_NS_SHIFT),
+	BNXT_RE_METHOD_DESTROY_PAGE,
+};
+
 #endif /* __BNXT_RE_UVERBS_ABI_H__*/
-- 
2.5.5


[-- Attachment #2: S/MIME Cryptographic Signature --]
[-- Type: application/pkcs7-signature, Size: 4224 bytes --]

Re: [PATCH v2 for-next 3/6] RDMA/bnxt_re: Query function capabilities from firmware

[kernel test robot]

Hi Selvin,

kernel test robot noticed the following build warnings:

[auto build test WARNING on rdma/for-next]
[also build test WARNING on linus/master v6.3 next-20230425]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch#_base_tree_information]

url:    https://github.com/intel-lab-lkp/linux/commits/Selvin-Xavier/RDMA-bnxt_re-Use-the-common-mmap-helper-functions/20230426-033131
base:   https://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma.git for-next
patch link:    https://lore.kernel.org/r/1682450993-17711-4-git-send-email-selvin.xavier%40broadcom.com
patch subject: [PATCH v2 for-next 3/6] RDMA/bnxt_re: Query function capabilities from firmware
config: ia64-allyesconfig (https://download.01.org/0day-ci/archive/20230426/202304260421.Wr6M1Ys9-lkp@intel.com/config)
compiler: ia64-linux-gcc (GCC) 12.1.0
reproduce (this is a W=1 build):
        wget https://raw.githubusercontent.com/intel/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross
        chmod +x ~/bin/make.cross
        # https://github.com/intel-lab-lkp/linux/commit/2e3cab6bf041dd376d6aeae617adfdcdd68f8a4b
        git remote add linux-review https://github.com/intel-lab-lkp/linux
        git fetch --no-tags linux-review Selvin-Xavier/RDMA-bnxt_re-Use-the-common-mmap-helper-functions/20230426-033131
        git checkout 2e3cab6bf041dd376d6aeae617adfdcdd68f8a4b
        # save the config file
        mkdir build_dir && cp config build_dir/.config
        COMPILER_INSTALL_PATH=$HOME/0day COMPILER=gcc-12.1.0 make.cross W=1 O=build_dir ARCH=ia64 olddefconfig
        COMPILER_INSTALL_PATH=$HOME/0day COMPILER=gcc-12.1.0 make.cross W=1 O=build_dir ARCH=ia64 SHELL=/bin/bash drivers/infiniband/

If you fix the issue, kindly add following tag where applicable
| Reported-by: kernel test robot <lkp@intel.com>
| Link: https://lore.kernel.org/oe-kbuild-all/202304260421.Wr6M1Ys9-lkp@intel.com/

All warnings (new ones prefixed by >>):

   drivers/infiniband/hw/bnxt_re/main.c: In function 'bnxt_re_hwrm_qcaps':
>> drivers/infiniband/hw/bnxt_re/main.c:347:37: warning: variable 'cctx' set but not used [-Wunused-but-set-variable]
     347 |         struct bnxt_qplib_chip_ctx *cctx;
         |                                     ^~~~


vim +/cctx +347 drivers/infiniband/hw/bnxt_re/main.c

   340	
   341	/* Query function capabilities using common hwrm */
   342	int bnxt_re_hwrm_qcaps(struct bnxt_re_dev *rdev)
   343	{
   344		struct bnxt_en_dev *en_dev = rdev->en_dev;
   345		struct hwrm_func_qcaps_output resp = {0};
   346		struct hwrm_func_qcaps_input req = {0};
 > 347		struct bnxt_qplib_chip_ctx *cctx;
   348		struct bnxt_fw_msg fw_msg;
   349	
   350		cctx = rdev->chip_ctx;
   351		memset(&fw_msg, 0, sizeof(fw_msg));
   352		bnxt_re_init_hwrm_hdr(rdev, (void *)&req,
   353				      HWRM_FUNC_QCAPS, -1, -1);
   354		req.fid = cpu_to_le16(0xffff);
   355		bnxt_re_fill_fw_msg(&fw_msg, (void *)&req, sizeof(req), (void *)&resp,
   356				    sizeof(resp), DFLT_HWRM_CMD_TIMEOUT);
   357		return bnxt_send_msg(en_dev, &fw_msg);
   358	}
   359	

-- 
0-DAY CI Kernel Test Service
https://github.com/intel/lkp-tests

Re: [PATCH v2 for-next 0/6] RDMA/bnxt_re: driver update for supporting low latency push

[Leon Romanovsky]

On Tue, Apr 25, 2023 at 12:29:47PM -0700, Selvin Xavier wrote:
> The series aims to add support for Low latency push path in
> some of the bnxt devices. The low latency implementation is
> supported only for the user applications. Also, the code
> is modified to use  common mmap helper functions exported
> by IB core. 
> 
> User library changes are getting submitted in the pull request
> https://github.com/linux-rdma/rdma-core/pull/1321
> 
> Please review.
> 
> Thanks,
> Selvin Xavier
> 

We are in merge window now.

Thanks