Merge branch 'mana-shared-6.2' of https://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma

Long Li says:

====================
Introduce Microsoft Azure Network Adapter (MANA) RDMA driver [netdev prep]

The first 11 patches which modify the MANA Ethernet driver to support
RDMA driver.

* 'mana-shared-6.2' of https://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma:
  net: mana: Define data structures for protection domain and memory registration
  net: mana: Define data structures for allocating doorbell page from GDMA
  net: mana: Define and process GDMA response code GDMA_STATUS_MORE_ENTRIES
  net: mana: Define max values for SGL entries
  net: mana: Move header files to a common location
  net: mana: Record port number in netdev
  net: mana: Export Work Queue functions for use by RDMA driver
  net: mana: Set the DMA device max segment size
  net: mana: Handle vport sharing between devices
  net: mana: Record the physical address for doorbell page region
  net: mana: Add support for auxiliary device
====================

Link: https://lore.kernel.org/all/1667502990-2559-1-git-send-email-longli@linuxonhyperv.com/Signed-off-by: Jakub Kicinski <kuba@kernel.org>

MAINTAINERS

@@ -9543,6 +9543,7 @@ F:	include/asm-generic/hyperv-tlfs.h
 F:	include/asm-generic/mshyperv.h
 F:	include/clocksource/hyperv_timer.h
 F:	include/linux/hyperv.h
+F:	include/net/mana
 F:	include/uapi/linux/hyperv.h
 F:	net/vmw_vsock/hyperv_transport.c
 F:	tools/hv/

drivers/net/ethernet/microsoft/Kconfig

@@ -19,6 +19,7 @@ config MICROSOFT_MANA
 	tristate "Microsoft Azure Network Adapter (MANA) support"
 	depends on PCI_MSI && X86_64
 	depends on PCI_HYPERV
+	select AUXILIARY_BUS
 	help
 	  This driver supports Microsoft Azure Network Adapter (MANA).
 	  So far, the driver is only supported on X86_64.

drivers/net/ethernet/microsoft/mana/gdma_main.c

@@ -6,7 +6,7 @@
 #include <linux/utsname.h>
 #include <linux/version.h>
 
-#include "mana.h"
+#include <net/mana/mana.h>
 
 static u32 mana_gd_r32(struct gdma_context *g, u64 offset)
 {
@@ -44,6 +44,9 @@ static void mana_gd_init_vf_regs(struct pci_dev *pdev)
 	gc->db_page_base = gc->bar0_va +
 				mana_gd_r64(gc, GDMA_REG_DB_PAGE_OFFSET);
 
+	gc->phys_db_page_base = gc->bar0_pa +
+				mana_gd_r64(gc, GDMA_REG_DB_PAGE_OFFSET);
+
 	gc->shm_base = gc->bar0_va + mana_gd_r64(gc, GDMA_REG_SHM_OFFSET);
 }
 
@@ -149,6 +152,7 @@ int mana_gd_send_request(struct gdma_context *gc, u32 req_len, const void *req,
 
 	return mana_hwc_send_request(hwc, req_len, req, resp_len, resp);
 }
+EXPORT_SYMBOL_NS(mana_gd_send_request, NET_MANA);
 
 int mana_gd_alloc_memory(struct gdma_context *gc, unsigned int length,
 			 struct gdma_mem_info *gmi)
@@ -194,7 +198,7 @@ static int mana_gd_create_hw_eq(struct gdma_context *gc,
 	req.type = queue->type;
 	req.pdid = queue->gdma_dev->pdid;
 	req.doolbell_id = queue->gdma_dev->doorbell;
-	req.gdma_region = queue->mem_info.gdma_region;
+	req.gdma_region = queue->mem_info.dma_region_handle;
 	req.queue_size = queue->queue_size;
 	req.log2_throttle_limit = queue->eq.log2_throttle_limit;
 	req.eq_pci_msix_index = queue->eq.msix_index;
@@ -208,7 +212,7 @@ static int mana_gd_create_hw_eq(struct gdma_context *gc,
 
 	queue->id = resp.queue_index;
 	queue->eq.disable_needed = true;
-	queue->mem_info.gdma_region = GDMA_INVALID_DMA_REGION;
+	queue->mem_info.dma_region_handle = GDMA_INVALID_DMA_REGION;
 	return 0;
 }
 
@@ -667,24 +671,30 @@ int mana_gd_create_hwc_queue(struct gdma_dev *gd,
 	return err;
 }
 
-static void mana_gd_destroy_dma_region(struct gdma_context *gc, u64 gdma_region)
+int mana_gd_destroy_dma_region(struct gdma_context *gc,
+			       gdma_obj_handle_t dma_region_handle)
 {
 	struct gdma_destroy_dma_region_req req = {};
 	struct gdma_general_resp resp = {};
 	int err;
 
-	if (gdma_region == GDMA_INVALID_DMA_REGION)
-		return;
+	if (dma_region_handle == GDMA_INVALID_DMA_REGION)
+		return 0;
 
 	mana_gd_init_req_hdr(&req.hdr, GDMA_DESTROY_DMA_REGION, sizeof(req),
 			     sizeof(resp));
-	req.gdma_region = gdma_region;
+	req.dma_region_handle = dma_region_handle;
 
 	err = mana_gd_send_request(gc, sizeof(req), &req, sizeof(resp), &resp);
-	if (err || resp.hdr.status)
+	if (err || resp.hdr.status) {
 		dev_err(gc->dev, "Failed to destroy DMA region: %d, 0x%x\n",
 			err, resp.hdr.status);
+		return -EPROTO;
+	}
+
+	return 0;
 }
+EXPORT_SYMBOL_NS(mana_gd_destroy_dma_region, NET_MANA);
 
 static int mana_gd_create_dma_region(struct gdma_dev *gd,
 				     struct gdma_mem_info *gmi)
@@ -729,14 +739,15 @@ static int mana_gd_create_dma_region(struct gdma_dev *gd,
 	if (err)
 		goto out;
 
-	if (resp.hdr.status || resp.gdma_region == GDMA_INVALID_DMA_REGION) {
+	if (resp.hdr.status ||
+	    resp.dma_region_handle == GDMA_INVALID_DMA_REGION) {
 		dev_err(gc->dev, "Failed to create DMA region: 0x%x\n",
 			resp.hdr.status);
 		err = -EPROTO;
 		goto out;
 	}
 
-	gmi->gdma_region = resp.gdma_region;
+	gmi->dma_region_handle = resp.dma_region_handle;
 out:
 	kfree(req);
 	return err;
@@ -859,7 +870,7 @@ void mana_gd_destroy_queue(struct gdma_context *gc, struct gdma_queue *queue)
 		return;
 	}
 
-	mana_gd_destroy_dma_region(gc, gmi->gdma_region);
+	mana_gd_destroy_dma_region(gc, gmi->dma_region_handle);
 	mana_gd_free_memory(gmi);
 	kfree(queue);
 }
@@ -1393,6 +1404,12 @@ static int mana_gd_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (err)
 		goto release_region;
 
+	err = dma_set_max_seg_size(&pdev->dev, UINT_MAX);
+	if (err) {
+		dev_err(&pdev->dev, "Failed to set dma device segment size\n");
+		goto release_region;
+	}
+
 	err = -ENOMEM;
 	gc = vzalloc(sizeof(*gc));
 	if (!gc)
@@ -1400,6 +1417,7 @@ static int mana_gd_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	mutex_init(&gc->eq_test_event_mutex);
 	pci_set_drvdata(pdev, gc);
+	gc->bar0_pa = pci_resource_start(pdev, 0);
 
 	bar0_va = pci_iomap(pdev, bar, 0);
 	if (!bar0_va)

drivers/net/ethernet/microsoft/mana/hw_channel.c

 // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
 /* Copyright (c) 2021, Microsoft Corporation. */
 
-#include "gdma.h"
-#include "hw_channel.h"
+#include <net/mana/gdma.h>
+#include <net/mana/hw_channel.h>
 
 static int mana_hwc_get_msg_index(struct hw_channel_context *hwc, u16 *msg_id)
 {
@@ -836,7 +836,7 @@ int mana_hwc_send_request(struct hw_channel_context *hwc, u32 req_len,
 		goto out;
 	}
 
-	if (ctx->status_code) {
+	if (ctx->status_code && ctx->status_code != GDMA_STATUS_MORE_ENTRIES) {
 		dev_err(hwc->dev, "HWC: Failed hw_channel req: 0x%x\n",
 			ctx->status_code);
 		err = -EPROTO;

drivers/net/ethernet/microsoft/mana/mana_bpf.c

@@ -8,7 +8,7 @@
 #include <linux/bpf_trace.h>
 #include <net/xdp.h>
 
-#include "mana.h"
+#include <net/mana/mana.h>
 
 void mana_xdp_tx(struct sk_buff *skb, struct net_device *ndev)
 {

drivers/net/ethernet/microsoft/mana/mana_en.c

@@ -12,7 +12,20 @@
 #include <net/checksum.h>
 #include <net/ip6_checksum.h>
 
-#include "mana.h"
+#include <net/mana/mana.h>
+#include <net/mana/mana_auxiliary.h>
+
+static DEFINE_IDA(mana_adev_ida);
+
+static int mana_adev_idx_alloc(void)
+{
+	return ida_alloc(&mana_adev_ida, GFP_KERNEL);
+}
+
+static void mana_adev_idx_free(int idx)
+{
+	ida_free(&mana_adev_ida, idx);
+}
 
 /* Microsoft Azure Network Adapter (MANA) functions */
 
@@ -176,7 +189,7 @@ netdev_tx_t mana_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 	pkg.wqe_req.client_data_unit = 0;
 
 	pkg.wqe_req.num_sge = 1 + skb_shinfo(skb)->nr_frags;
-	WARN_ON_ONCE(pkg.wqe_req.num_sge > 30);
+	WARN_ON_ONCE(pkg.wqe_req.num_sge > MAX_TX_WQE_SGL_ENTRIES);
 
 	if (pkg.wqe_req.num_sge <= ARRAY_SIZE(pkg.sgl_array)) {
 		pkg.wqe_req.sgl = pkg.sgl_array;
@@ -633,13 +646,48 @@ static int mana_query_vport_cfg(struct mana_port_context *apc, u32 vport_index,
 	return 0;
 }
 
-static int mana_cfg_vport(struct mana_port_context *apc, u32 protection_dom_id,
-			  u32 doorbell_pg_id)
+void mana_uncfg_vport(struct mana_port_context *apc)
+{
+	mutex_lock(&apc->vport_mutex);
+	apc->vport_use_count--;
+	WARN_ON(apc->vport_use_count < 0);
+	mutex_unlock(&apc->vport_mutex);
+}
+EXPORT_SYMBOL_NS(mana_uncfg_vport, NET_MANA);
+
+int mana_cfg_vport(struct mana_port_context *apc, u32 protection_dom_id,
+		   u32 doorbell_pg_id)
 {
 	struct mana_config_vport_resp resp = {};
 	struct mana_config_vport_req req = {};
 	int err;
 
+	/* This function is used to program the Ethernet port in the hardware
+	 * table. It can be called from the Ethernet driver or the RDMA driver.
+	 *
+	 * For Ethernet usage, the hardware supports only one active user on a
+	 * physical port. The driver checks on the port usage before programming
+	 * the hardware when creating the RAW QP (RDMA driver) or exposing the
+	 * device to kernel NET layer (Ethernet driver).
+	 *
+	 * Because the RDMA driver doesn't know in advance which QP type the
+	 * user will create, it exposes the device with all its ports. The user
+	 * may not be able to create RAW QP on a port if this port is already
+	 * in used by the Ethernet driver from the kernel.
+	 *
+	 * This physical port limitation only applies to the RAW QP. For RC QP,
+	 * the hardware doesn't have this limitation. The user can create RC
+	 * QPs on a physical port up to the hardware limits independent of the
+	 * Ethernet usage on the same port.
+	 */
+	mutex_lock(&apc->vport_mutex);
+	if (apc->vport_use_count > 0) {
+		mutex_unlock(&apc->vport_mutex);
+		return -EBUSY;
+	}
+	apc->vport_use_count++;
+	mutex_unlock(&apc->vport_mutex);
+
 	mana_gd_init_req_hdr(&req.hdr, MANA_CONFIG_VPORT_TX,
 			     sizeof(req), sizeof(resp));
 	req.vport = apc->port_handle;
@@ -666,9 +714,16 @@ static int mana_cfg_vport(struct mana_port_context *apc, u32 protection_dom_id,
 
 	apc->tx_shortform_allowed = resp.short_form_allowed;
 	apc->tx_vp_offset = resp.tx_vport_offset;
+
+	netdev_info(apc->ndev, "Configured vPort %llu PD %u DB %u\n",
+		    apc->port_handle, protection_dom_id, doorbell_pg_id);
 out:
+	if (err)
+		mana_uncfg_vport(apc);
+
 	return err;
 }
+EXPORT_SYMBOL_NS(mana_cfg_vport, NET_MANA);
 
 static int mana_cfg_vport_steering(struct mana_port_context *apc,
 				   enum TRI_STATE rx,
@@ -729,16 +784,19 @@ static int mana_cfg_vport_steering(struct mana_port_context *apc,
 			   resp.hdr.status);
 		err = -EPROTO;
 	}
+
+	netdev_info(ndev, "Configured steering vPort %llu entries %u\n",
+		    apc->port_handle, num_entries);
 out:
 	kfree(req);
 	return err;
 }
 
-static int mana_create_wq_obj(struct mana_port_context *apc,
-			      mana_handle_t vport,
-			      u32 wq_type, struct mana_obj_spec *wq_spec,
-			      struct mana_obj_spec *cq_spec,
-			      mana_handle_t *wq_obj)
+int mana_create_wq_obj(struct mana_port_context *apc,
+		       mana_handle_t vport,
+		       u32 wq_type, struct mana_obj_spec *wq_spec,
+		       struct mana_obj_spec *cq_spec,
+		       mana_handle_t *wq_obj)
 {
 	struct mana_create_wqobj_resp resp = {};
 	struct mana_create_wqobj_req req = {};
@@ -787,9 +845,10 @@ static int mana_create_wq_obj(struct mana_port_context *apc,
 out:
 	return err;
 }
+EXPORT_SYMBOL_NS(mana_create_wq_obj, NET_MANA);
 
-static void mana_destroy_wq_obj(struct mana_port_context *apc, u32 wq_type,
-				mana_handle_t wq_obj)
+void mana_destroy_wq_obj(struct mana_port_context *apc, u32 wq_type,
+			 mana_handle_t wq_obj)
 {
 	struct mana_destroy_wqobj_resp resp = {};
 	struct mana_destroy_wqobj_req req = {};
@@ -814,6 +873,7 @@ static void mana_destroy_wq_obj(struct mana_port_context *apc, u32 wq_type,
 		netdev_err(ndev, "Failed to destroy WQ object: %d, 0x%x\n", err,
 			   resp.hdr.status);
 }
+EXPORT_SYMBOL_NS(mana_destroy_wq_obj, NET_MANA);
 
 static void mana_destroy_eq(struct mana_context *ac)
 {
@@ -1463,10 +1523,10 @@ static int mana_create_txq(struct mana_port_context *apc,
 		memset(&wq_spec, 0, sizeof(wq_spec));
 		memset(&cq_spec, 0, sizeof(cq_spec));
 
-		wq_spec.gdma_region = txq->gdma_sq->mem_info.gdma_region;
+		wq_spec.gdma_region = txq->gdma_sq->mem_info.dma_region_handle;
 		wq_spec.queue_size = txq->gdma_sq->queue_size;
 
-		cq_spec.gdma_region = cq->gdma_cq->mem_info.gdma_region;
+		cq_spec.gdma_region = cq->gdma_cq->mem_info.dma_region_handle;
 		cq_spec.queue_size = cq->gdma_cq->queue_size;
 		cq_spec.modr_ctx_id = 0;
 		cq_spec.attached_eq = cq->gdma_cq->cq.parent->id;
@@ -1481,8 +1541,10 @@ static int mana_create_txq(struct mana_port_context *apc,
 		txq->gdma_sq->id = wq_spec.queue_index;
 		cq->gdma_cq->id = cq_spec.queue_index;
 
-		txq->gdma_sq->mem_info.gdma_region = GDMA_INVALID_DMA_REGION;
-		cq->gdma_cq->mem_info.gdma_region = GDMA_INVALID_DMA_REGION;
+		txq->gdma_sq->mem_info.dma_region_handle =
+			GDMA_INVALID_DMA_REGION;
+		cq->gdma_cq->mem_info.dma_region_handle =
+			GDMA_INVALID_DMA_REGION;
 
 		txq->gdma_txq_id = txq->gdma_sq->id;
 
@@ -1693,10 +1755,10 @@ static struct mana_rxq *mana_create_rxq(struct mana_port_context *apc,
 
 	memset(&wq_spec, 0, sizeof(wq_spec));
 	memset(&cq_spec, 0, sizeof(cq_spec));
-	wq_spec.gdma_region = rxq->gdma_rq->mem_info.gdma_region;
+	wq_spec.gdma_region = rxq->gdma_rq->mem_info.dma_region_handle;
 	wq_spec.queue_size = rxq->gdma_rq->queue_size;
 
-	cq_spec.gdma_region = cq->gdma_cq->mem_info.gdma_region;
+	cq_spec.gdma_region = cq->gdma_cq->mem_info.dma_region_handle;
 	cq_spec.queue_size = cq->gdma_cq->queue_size;
 	cq_spec.modr_ctx_id = 0;
 	cq_spec.attached_eq = cq->gdma_cq->cq.parent->id;
@@ -1709,8 +1771,8 @@ static struct mana_rxq *mana_create_rxq(struct mana_port_context *apc,
 	rxq->gdma_rq->id = wq_spec.queue_index;
 	cq->gdma_cq->id = cq_spec.queue_index;
 
-	rxq->gdma_rq->mem_info.gdma_region = GDMA_INVALID_DMA_REGION;
-	cq->gdma_cq->mem_info.gdma_region = GDMA_INVALID_DMA_REGION;
+	rxq->gdma_rq->mem_info.dma_region_handle = GDMA_INVALID_DMA_REGION;
+	cq->gdma_cq->mem_info.dma_region_handle = GDMA_INVALID_DMA_REGION;
 
 	rxq->gdma_id = rxq->gdma_rq->id;
 	cq->gdma_id = cq->gdma_cq->id;
@@ -1791,6 +1853,7 @@ static void mana_destroy_vport(struct mana_port_context *apc)
 	}
 
 	mana_destroy_txq(apc);
+	mana_uncfg_vport(apc);
 
 	if (gd->gdma_context->is_pf)
 		mana_pf_deregister_hw_vport(apc);
@@ -2063,12 +2126,16 @@ static int mana_probe_port(struct mana_context *ac, int port_idx,
 	apc->pf_filter_handle = INVALID_MANA_HANDLE;
 	apc->port_idx = port_idx;
 
+	mutex_init(&apc->vport_mutex);
+	apc->vport_use_count = 0;
+
 	ndev->netdev_ops = &mana_devops;
 	ndev->ethtool_ops = &mana_ethtool_ops;
 	ndev->mtu = ETH_DATA_LEN;
 	ndev->max_mtu = ndev->mtu;
 	ndev->min_mtu = ndev->mtu;
 	ndev->needed_headroom = MANA_HEADROOM;
+	ndev->dev_port = port_idx;
 	SET_NETDEV_DEV(ndev, gc->dev);
 
 	netif_carrier_off(ndev);
@@ -2106,6 +2173,69 @@ static int mana_probe_port(struct mana_context *ac, int port_idx,
 	return err;
 }
 
+static void adev_release(struct device *dev)
+{
+	struct mana_adev *madev = container_of(dev, struct mana_adev, adev.dev);
+
+	kfree(madev);
+}
+
+static void remove_adev(struct gdma_dev *gd)
+{
+	struct auxiliary_device *adev = gd->adev;
+	int id = adev->id;
+
+	auxiliary_device_delete(adev);
+	auxiliary_device_uninit(adev);
+
+	mana_adev_idx_free(id);
+	gd->adev = NULL;
+}
+
+static int add_adev(struct gdma_dev *gd)
+{
+	struct auxiliary_device *adev;
+	struct mana_adev *madev;
+	int ret;
+
+	madev = kzalloc(sizeof(*madev), GFP_KERNEL);
+	if (!madev)
+		return -ENOMEM;
+
+	adev = &madev->adev;
+	ret = mana_adev_idx_alloc();
+	if (ret < 0)
+		goto idx_fail;
+	adev->id = ret;
+
+	adev->name = "rdma";
+	adev->dev.parent = gd->gdma_context->dev;
+	adev->dev.release = adev_release;
+	madev->mdev = gd;
+
+	ret = auxiliary_device_init(adev);
+	if (ret)
+		goto init_fail;
+
+	ret = auxiliary_device_add(adev);
+	if (ret)
+		goto add_fail;
+
+	gd->adev = adev;
+	return 0;
+
+add_fail:
+	auxiliary_device_uninit(adev);
+
+init_fail:
+	mana_adev_idx_free(adev->id);
+
+idx_fail:
+	kfree(madev);
+
+	return ret;
+}
+
 int mana_probe(struct gdma_dev *gd, bool resuming)
 {
 	struct gdma_context *gc = gd->gdma_context;
@@ -2173,6 +2303,8 @@ int mana_probe(struct gdma_dev *gd, bool resuming)
 				break;
 		}
 	}
+
+	err = add_adev(gd);
 out:
 	if (err)
 		mana_remove(gd, false);
@@ -2189,6 +2321,10 @@ void mana_remove(struct gdma_dev *gd, bool suspending)
 	int err;
 	int i;
 
+	/* adev currently doesn't support suspending, always remove it */
+	if (gd->adev)
+		remove_adev(gd);
+
 	for (i = 0; i < ac->num_ports; i++) {
 		ndev = ac->ports[i];
 		if (!ndev) {
@@ -2221,7 +2357,6 @@ void mana_remove(struct gdma_dev *gd, bool suspending)
 	}
 
 	mana_destroy_eq(ac);
-
 out:
 	mana_gd_deregister_device(gd);
 

drivers/net/ethernet/microsoft/mana/mana_ethtool.c

@@ -5,7 +5,7 @@
 #include <linux/etherdevice.h>
 #include <linux/ethtool.h>
 
-#include "mana.h"
+#include <net/mana/mana.h>
 
 static const struct {
 	char name[ETH_GSTRING_LEN];

drivers/net/ethernet/microsoft/mana/shm_channel.c

@@ -6,7 +6,7 @@
 #include <linux/io.h>
 #include <linux/mm.h>
 
-#include "shm_channel.h"
+#include <net/mana/shm_channel.h>
 
 #define PAGE_FRAME_L48_WIDTH_BYTES 6
 #define PAGE_FRAME_L48_WIDTH_BITS (PAGE_FRAME_L48_WIDTH_BYTES * 8)

drivers/net/ethernet/microsoft/mana/gdma.h → include/net/mana/gdma.h

@@ -9,6 +9,8 @@
 
 #include "shm_channel.h"
 
+#define GDMA_STATUS_MORE_ENTRIES	0x00000105
+
 /* Structures labeled with "HW DATA" are exchanged with the hardware. All of
  * them are naturally aligned and hence don't need __packed.
  */
@@ -22,11 +24,19 @@ enum gdma_request_type {
 	GDMA_GENERATE_TEST_EQE		= 10,
 	GDMA_CREATE_QUEUE		= 12,
 	GDMA_DISABLE_QUEUE		= 13,
+	GDMA_ALLOCATE_RESOURCE_RANGE	= 22,
+	GDMA_DESTROY_RESOURCE_RANGE	= 24,
 	GDMA_CREATE_DMA_REGION		= 25,
 	GDMA_DMA_REGION_ADD_PAGES	= 26,
 	GDMA_DESTROY_DMA_REGION		= 27,
+	GDMA_CREATE_PD			= 29,
+	GDMA_DESTROY_PD			= 30,
+	GDMA_CREATE_MR			= 31,
+	GDMA_DESTROY_MR			= 32,
 };
 
+#define GDMA_RESOURCE_DOORBELL_PAGE	27
+
 enum gdma_queue_type {
 	GDMA_INVALID_QUEUE,
 	GDMA_SQ,
@@ -55,6 +65,8 @@ enum {
 	GDMA_DEVICE_MANA	= 2,
 };
 
+typedef u64 gdma_obj_handle_t;
+
 struct gdma_resource {
 	/* Protect the bitmap */
 	spinlock_t lock;
@@ -188,7 +200,7 @@ struct gdma_mem_info {
 	u64 length;
 
 	/* Allocated by the PF driver */
-	u64 gdma_region;
+	gdma_obj_handle_t dma_region_handle;
 };
 
 #define REGISTER_ATB_MST_MKEY_LOWER_SIZE 8
@@ -204,6 +216,8 @@ struct gdma_dev {
 
 	/* GDMA driver specific pointer */
 	void *driver_data;
+
+	struct auxiliary_device *adev;
 };
 
 #define MINIMUM_SUPPORTED_PAGE_SIZE PAGE_SIZE
@@ -349,9 +363,11 @@ struct gdma_context {
 	u32			test_event_eq_id;
 
 	bool			is_pf;
+	phys_addr_t		bar0_pa;
 	void __iomem		*bar0_va;
 	void __iomem		*shm_base;
 	void __iomem		*db_page_base;
+	phys_addr_t		phys_db_page_base;
 	u32 db_page_size;
 	int                     numa_node;
 
@@ -424,6 +440,13 @@ struct gdma_wqe {
 #define MAX_TX_WQE_SIZE 512
 #define MAX_RX_WQE_SIZE 256
 
+#define MAX_TX_WQE_SGL_ENTRIES	((GDMA_MAX_SQE_SIZE -			   \
+			sizeof(struct gdma_sge) - INLINE_OOB_SMALL_SIZE) / \
+			sizeof(struct gdma_sge))
+
+#define MAX_RX_WQE_SGL_ENTRIES	((GDMA_MAX_RQE_SIZE -			   \
+			sizeof(struct gdma_sge)) / sizeof(struct gdma_sge))
+
 struct gdma_cqe {
 	u32 cqe_data[GDMA_COMP_DATA_SIZE / 4];
 
@@ -575,6 +598,26 @@ struct gdma_register_device_resp {
 	u32 db_id;
 }; /* HW DATA */
 
+struct gdma_allocate_resource_range_req {
+	struct gdma_req_hdr hdr;
+	u32 resource_type;
+	u32 num_resources;
+	u32 alignment;
+	u32 allocated_resources;
+};
+
+struct gdma_allocate_resource_range_resp {
+	struct gdma_resp_hdr hdr;
+	u32 allocated_resources;
+};
+
+struct gdma_destroy_resource_range_req {
+	struct gdma_req_hdr hdr;
+	u32 resource_type;
+	u32 num_resources;
+	u32 allocated_resources;
+};
+
 /* GDMA_CREATE_QUEUE */
 struct gdma_create_queue_req {
 	struct gdma_req_hdr hdr;
@@ -582,7 +625,7 @@ struct gdma_create_queue_req {
 	u32 reserved1;
 	u32 pdid;
 	u32 doolbell_id;
-	u64 gdma_region;
+	gdma_obj_handle_t gdma_region;
 	u32 reserved2;
 	u32 queue_size;
 	u32 log2_throttle_limit;
@@ -609,6 +652,28 @@ struct gdma_disable_queue_req {
 	u32 alloc_res_id_on_creation;
 }; /* HW DATA */
 
+enum atb_page_size {
+	ATB_PAGE_SIZE_4K,
+	ATB_PAGE_SIZE_8K,
+	ATB_PAGE_SIZE_16K,
+	ATB_PAGE_SIZE_32K,
+	ATB_PAGE_SIZE_64K,
+	ATB_PAGE_SIZE_128K,
+	ATB_PAGE_SIZE_256K,
+	ATB_PAGE_SIZE_512K,
+	ATB_PAGE_SIZE_1M,
+	ATB_PAGE_SIZE_2M,
+	ATB_PAGE_SIZE_MAX,
+};
+
+enum gdma_mr_access_flags {
+	GDMA_ACCESS_FLAG_LOCAL_READ = BIT_ULL(0),
+	GDMA_ACCESS_FLAG_LOCAL_WRITE = BIT_ULL(1),
+	GDMA_ACCESS_FLAG_REMOTE_READ = BIT_ULL(2),
+	GDMA_ACCESS_FLAG_REMOTE_WRITE = BIT_ULL(3),
+	GDMA_ACCESS_FLAG_REMOTE_ATOMIC = BIT_ULL(4),
+};
+
 /* GDMA_CREATE_DMA_REGION */
 struct gdma_create_dma_region_req {
 	struct gdma_req_hdr hdr;
@@ -635,14 +700,14 @@ struct gdma_create_dma_region_req {
 
 struct gdma_create_dma_region_resp {
 	struct gdma_resp_hdr hdr;
-	u64 gdma_region;
+	gdma_obj_handle_t dma_region_handle;
 }; /* HW DATA */
 
 /* GDMA_DMA_REGION_ADD_PAGES */
 struct gdma_dma_region_add_pages_req {
 	struct gdma_req_hdr hdr;
 
-	u64 gdma_region;
+	gdma_obj_handle_t dma_region_handle;
 
 	u32 page_addr_list_len;
 	u32 reserved3;
@@ -654,9 +719,88 @@ struct gdma_dma_region_add_pages_req {
 struct gdma_destroy_dma_region_req {
 	struct gdma_req_hdr hdr;
 
-	u64 gdma_region;
+	gdma_obj_handle_t dma_region_handle;
 }; /* HW DATA */
 
+enum gdma_pd_flags {
+	GDMA_PD_FLAG_INVALID = 0,
+};
+
+struct gdma_create_pd_req {
+	struct gdma_req_hdr hdr;
+	enum gdma_pd_flags flags;
+	u32 reserved;
+};/* HW DATA */
+
+struct gdma_create_pd_resp {
+	struct gdma_resp_hdr hdr;
+	gdma_obj_handle_t pd_handle;
+	u32 pd_id;
+	u32 reserved;
+};/* HW DATA */
+
+struct gdma_destroy_pd_req {
+	struct gdma_req_hdr hdr;
+	gdma_obj_handle_t pd_handle;
+};/* HW DATA */
+
+struct gdma_destory_pd_resp {
+	struct gdma_resp_hdr hdr;
+};/* HW DATA */
+
+enum gdma_mr_type {
+	/* Guest Virtual Address - MRs of this type allow access
+	 * to memory mapped by PTEs associated with this MR using a virtual
+	 * address that is set up in the MST
+	 */
+	GDMA_MR_TYPE_GVA = 2,
+};
+
+struct gdma_create_mr_params {
+	gdma_obj_handle_t pd_handle;
+	enum gdma_mr_type mr_type;
+	union {
+		struct {
+			gdma_obj_handle_t dma_region_handle;
+			u64 virtual_address;
+			enum gdma_mr_access_flags access_flags;
+		} gva;
+	};
+};
+
+struct gdma_create_mr_request {
+	struct gdma_req_hdr hdr;
+	gdma_obj_handle_t pd_handle;
+	enum gdma_mr_type mr_type;
+	u32 reserved_1;
+
+	union {
+		struct {
+			gdma_obj_handle_t dma_region_handle;
+			u64 virtual_address;
+			enum gdma_mr_access_flags access_flags;
+		} gva;
+
+	};
+	u32 reserved_2;
+};/* HW DATA */
+
+struct gdma_create_mr_response {
+	struct gdma_resp_hdr hdr;
+	gdma_obj_handle_t mr_handle;
+	u32 lkey;
+	u32 rkey;
+};/* HW DATA */
+
+struct gdma_destroy_mr_request {
+	struct gdma_req_hdr hdr;
+	gdma_obj_handle_t mr_handle;
+};/* HW DATA */
+
+struct gdma_destroy_mr_response {
+	struct gdma_resp_hdr hdr;
+};/* HW DATA */
+
 int mana_gd_verify_vf_version(struct pci_dev *pdev);
 
 int mana_gd_register_device(struct gdma_dev *gd);
@@ -683,4 +827,8 @@ void mana_gd_free_memory(struct gdma_mem_info *gmi);
 
 int mana_gd_send_request(struct gdma_context *gc, u32 req_len, const void *req,
 			 u32 resp_len, void *resp);
+
+int mana_gd_destroy_dma_region(struct gdma_context *gc,
+			       gdma_obj_handle_t dma_region_handle);
+
 #endif /* _GDMA_H */

drivers/net/ethernet/microsoft/mana/mana.h → include/net/mana/mana.h

@@ -265,8 +265,6 @@ struct mana_cq {
 	int budget;
 };
 
-#define GDMA_MAX_RQE_SGES 15
-
 struct mana_recv_buf_oob {
 	/* A valid GDMA work request representing the data buffer. */
 	struct gdma_wqe_request wqe_req;
@@ -276,7 +274,7 @@ struct mana_recv_buf_oob {
 
 	/* SGL of the buffer going to be sent has part of the work request. */
 	u32 num_sge;
-	struct gdma_sge sgl[GDMA_MAX_RQE_SGES];
+	struct gdma_sge sgl[MAX_RX_WQE_SGL_ENTRIES];
 
 	/* Required to store the result of mana_gd_post_work_request.
 	 * gdma_posted_wqe_info.wqe_size_in_bu is required for progressing the
@@ -380,6 +378,10 @@ struct mana_port_context {
 	mana_handle_t port_handle;
 	mana_handle_t pf_filter_handle;
 
+	/* Mutex for sharing access to vport_use_count */
+	struct mutex vport_mutex;
+	int vport_use_count;
+
 	u16 port_idx;
 
 	bool port_is_up;
@@ -631,4 +633,16 @@ struct mana_tx_package {
 	struct gdma_posted_wqe_info wqe_info;
 };
 
+int mana_create_wq_obj(struct mana_port_context *apc,
+		       mana_handle_t vport,
+		       u32 wq_type, struct mana_obj_spec *wq_spec,
+		       struct mana_obj_spec *cq_spec,
+		       mana_handle_t *wq_obj);
+
+void mana_destroy_wq_obj(struct mana_port_context *apc, u32 wq_type,
+			 mana_handle_t wq_obj);
+
+int mana_cfg_vport(struct mana_port_context *apc, u32 protection_dom_id,
+		   u32 doorbell_pg_id);
+void mana_uncfg_vport(struct mana_port_context *apc);
 #endif /* _MANA_H */

include/net/mana/mana_auxiliary.h

+/* SPDX-License-Identifier: GPL-2.0-only */
+/* Copyright (c) 2022, Microsoft Corporation. */
+
+#include "mana.h"
+#include <linux/auxiliary_bus.h>
+
+struct mana_adev {
+	struct auxiliary_device adev;
+	struct gdma_dev *mdev;
+};