Merge tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost

Pull virtio updates from Michael Tsirkin:

 - resume support in vdpa/solidrun

 - structure size optimizations in virtio_pci

 - new pds_vdpa driver

 - immediate initialization mechanism for vdpa/ifcvf

 - interrupt bypass for vdpa/mlx5

 - multiple worker support for vhost

 - viirtio net in Intel F2000X-PL support for vdpa/ifcvf

 - fixes, cleanups all over the place

* tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost: (48 commits)
  vhost: Make parameter name match of vhost_get_vq_desc()
  vduse: fix NULL pointer dereference
  vhost: Allow worker switching while work is queueing
  vhost_scsi: add support for worker ioctls
  vhost: allow userspace to create workers
  vhost: replace single worker pointer with xarray
  vhost: add helper to parse userspace vring state/file
  vhost: remove vhost_work_queue
  vhost_scsi: flush IO vqs then send TMF rsp
  vhost_scsi: convert to vhost_vq_work_queue
  vhost_scsi: make SCSI cmd completion per vq
  vhost_sock: convert to vhost_vq_work_queue
  vhost: convert poll work to be vq based
  vhost: take worker or vq for flushing
  vhost: take worker or vq instead of dev for queueing
  vhost, vhost_net: add helper to check if vq has work
  vhost: add vhost_worker pointer to vhost_virtqueue
  vhost: dynamically allocate vhost_worker
  vhost: create worker at end of vhost_dev_set_owner
  virtio_bt: call scheduler when we free unused buffs
  ...

Documentation/networking/device_drivers/ethernet/amd/pds_vdpa.rst

+.. SPDX-License-Identifier: GPL-2.0+
+.. note: can be edited and viewed with /usr/bin/formiko-vim
+
+==========================================================
+PCI vDPA driver for the AMD/Pensando(R) DSC adapter family
+==========================================================
+
+AMD/Pensando vDPA VF Device Driver
+
+Copyright(c) 2023 Advanced Micro Devices, Inc
+
+Overview
+========
+
+The ``pds_vdpa`` driver is an auxiliary bus driver that supplies
+a vDPA device for use by the virtio network stack.  It is used with
+the Pensando Virtual Function devices that offer vDPA and virtio queue
+services.  It depends on the ``pds_core`` driver and hardware for the PF
+and VF PCI handling as well as for device configuration services.
+
+Using the device
+================
+
+The ``pds_vdpa`` device is enabled via multiple configuration steps and
+depends on the ``pds_core`` driver to create and enable SR-IOV Virtual
+Function devices.  After the VFs are enabled, we enable the vDPA service
+in the ``pds_core`` device to create the auxiliary devices used by pds_vdpa.
+
+Example steps:
+
+.. code-block:: bash
+
+  #!/bin/bash
+
+  modprobe pds_core
+  modprobe vdpa
+  modprobe pds_vdpa
+
+  PF_BDF=`ls /sys/module/pds_core/drivers/pci\:pds_core/*/sriov_numvfs | awk -F / '{print $7}'`
+
+  # Enable vDPA VF auxiliary device(s) in the PF
+  devlink dev param set pci/$PF_BDF name enable_vnet cmode runtime value true
+
+  # Create a VF for vDPA use
+  echo 1 > /sys/bus/pci/drivers/pds_core/$PF_BDF/sriov_numvfs
+
+  # Find the vDPA services/devices available
+  PDS_VDPA_MGMT=`vdpa mgmtdev show | grep vDPA | head -1 | cut -d: -f1`
+
+  # Create a vDPA device for use in virtio network configurations
+  vdpa dev add name vdpa1 mgmtdev $PDS_VDPA_MGMT mac 00:11:22:33:44:55
+
+  # Set up an ethernet interface on the vdpa device
+  modprobe virtio_vdpa
+
+
+
+Enabling the driver
+===================
+
+The driver is enabled via the standard kernel configuration system,
+using the make command::
+
+  make oldconfig/menuconfig/etc.
+
+The driver is located in the menu structure at:
+
+  -> Device Drivers
+    -> Network device support (NETDEVICES [=y])
+      -> Ethernet driver support
+        -> Pensando devices
+          -> Pensando Ethernet PDS_VDPA Support
+
+Support
+=======
+
+For general Linux networking support, please use the netdev mailing
+list, which is monitored by Pensando personnel::
+
+  netdev@vger.kernel.org
+
+For more specific support needs, please use the Pensando driver support
+email::
+
+  drivers@pensando.io

Documentation/networking/device_drivers/ethernet/index.rst

@@ -15,6 +15,7 @@ Contents:
    amazon/ena
    altera/altera_tse
    amd/pds_core
+   amd/pds_vdpa
    aquantia/atlantic
    chelsio/cxgb
    cirrus/cs89x0

MAINTAINERS

@@ -22535,6 +22535,10 @@ F:	include/linux/vringh.h
 F:	include/uapi/linux/virtio_*.h
 F:	tools/virtio/
 
+PDS DSC VIRTIO DATA PATH ACCELERATOR
+R:	Shannon Nelson <shannon.nelson@amd.com>
+F:	drivers/vdpa/pds/
+
 VIRTIO CRYPTO DRIVER
 M:	Gonglei <arei.gonglei@huawei.com>
 L:	virtualization@lists.linux-foundation.org

drivers/bluetooth/virtio_bt.c

@@ -79,6 +79,7 @@ static int virtbt_close_vdev(struct virtio_bluetooth *vbt)
 
 		while ((skb = virtqueue_detach_unused_buf(vq)))
 			kfree_skb(skb);
+		cond_resched();
 	}
 
 	return 0;

drivers/char/virtio_console.c

@@ -1936,6 +1936,7 @@ static void remove_vqs(struct ports_device *portdev)
 		flush_bufs(vq, true);
 		while ((buf = virtqueue_detach_unused_buf(vq)))
 			free_buf(buf, true);
+		cond_resched();
 	}
 	portdev->vdev->config->del_vqs(portdev->vdev);
 	kfree(portdev->in_vqs);

drivers/crypto/virtio/virtio_crypto_core.c

@@ -480,6 +480,7 @@ static void virtcrypto_free_unused_reqs(struct virtio_crypto *vcrypto)
 			kfree(vc_req->req_data);
 			kfree(vc_req->sgs);
 		}
+		cond_resched();
 	}
 }
 

drivers/vdpa/Kconfig

@@ -116,4 +116,14 @@ config ALIBABA_ENI_VDPA
 	  This driver includes a HW monitor device that
 	  reads health values from the DPU.
 
+config PDS_VDPA
+	tristate "vDPA driver for AMD/Pensando DSC devices"
+	select VIRTIO_PCI_LIB
+	depends on PCI_MSI
+	depends on PDS_CORE
+	help
+	  vDPA network driver for AMD/Pensando's PDS Core devices.
+	  With this driver, the VirtIO dataplane can be
+	  offloaded to an AMD/Pensando DSC device.
+
 endif # VDPA

drivers/vdpa/Makefile

@@ -7,3 +7,4 @@ obj-$(CONFIG_MLX5_VDPA) += mlx5/
 obj-$(CONFIG_VP_VDPA)    += virtio_pci/
 obj-$(CONFIG_ALIBABA_ENI_VDPA) += alibaba/
 obj-$(CONFIG_SNET_VDPA) += solidrun/
+obj-$(CONFIG_PDS_VDPA) += pds/

drivers/vdpa/ifcvf/ifcvf_base.c

@@ -69,6 +69,37 @@ static int ifcvf_read_config_range(struct pci_dev *dev,
 	return 0;
 }
 
+static u16 ifcvf_get_vq_size(struct ifcvf_hw *hw, u16 qid)
+{
+	u16 queue_size;
+
+	vp_iowrite16(qid, &hw->common_cfg->queue_select);
+	queue_size = vp_ioread16(&hw->common_cfg->queue_size);
+
+	return queue_size;
+}
+
+/* This function returns the max allowed safe size for
+ * all virtqueues. It is the minimal size that can be
+ * suppprted by all virtqueues.
+ */
+u16 ifcvf_get_max_vq_size(struct ifcvf_hw *hw)
+{
+	u16 queue_size, max_size, qid;
+
+	max_size = ifcvf_get_vq_size(hw, 0);
+	for (qid = 1; qid < hw->nr_vring; qid++) {
+		queue_size = ifcvf_get_vq_size(hw, qid);
+		/* 0 means the queue is unavailable */
+		if (!queue_size)
+			continue;
+
+		max_size = min(queue_size, max_size);
+	}
+
+	return max_size;
+}
+
 int ifcvf_init_hw(struct ifcvf_hw *hw, struct pci_dev *pdev)
 {
 	struct virtio_pci_cap cap;
@@ -134,6 +165,9 @@ int ifcvf_init_hw(struct ifcvf_hw *hw, struct pci_dev *pdev)
 	}
 
 	hw->nr_vring = vp_ioread16(&hw->common_cfg->num_queues);
+	hw->vring = kzalloc(sizeof(struct vring_info) * hw->nr_vring, GFP_KERNEL);
+	if (!hw->vring)
+		return -ENOMEM;
 
 	for (i = 0; i < hw->nr_vring; i++) {
 		vp_iowrite16(i, &hw->common_cfg->queue_select);
@@ -170,21 +204,9 @@ void ifcvf_set_status(struct ifcvf_hw *hw, u8 status)
 
 void ifcvf_reset(struct ifcvf_hw *hw)
 {
-	hw->config_cb.callback = NULL;
-	hw->config_cb.private = NULL;
-
 	ifcvf_set_status(hw, 0);
-	/* flush set_status, make sure VF is stopped, reset */
-	ifcvf_get_status(hw);
-}
-
-static void ifcvf_add_status(struct ifcvf_hw *hw, u8 status)
-{
-	if (status != 0)
-		status |= ifcvf_get_status(hw);
-
-	ifcvf_set_status(hw, status);
-	ifcvf_get_status(hw);
+	while (ifcvf_get_status(hw))
+		msleep(1);
 }
 
 u64 ifcvf_get_hw_features(struct ifcvf_hw *hw)
@@ -204,11 +226,29 @@ u64 ifcvf_get_hw_features(struct ifcvf_hw *hw)
 	return features;
 }
 
-u64 ifcvf_get_features(struct ifcvf_hw *hw)
+/* return provisioned vDPA dev features */
+u64 ifcvf_get_dev_features(struct ifcvf_hw *hw)
 {
 	return hw->dev_features;
 }
 
+u64 ifcvf_get_driver_features(struct ifcvf_hw *hw)
+{
+	struct virtio_pci_common_cfg __iomem *cfg = hw->common_cfg;
+	u32 features_lo, features_hi;
+	u64 features;
+
+	vp_iowrite32(0, &cfg->device_feature_select);
+	features_lo = vp_ioread32(&cfg->guest_feature);
+
+	vp_iowrite32(1, &cfg->device_feature_select);
+	features_hi = vp_ioread32(&cfg->guest_feature);
+
+	features = ((u64)features_hi << 32) | features_lo;
+
+	return features;
+}
+
 int ifcvf_verify_min_features(struct ifcvf_hw *hw, u64 features)
 {
 	if (!(features & BIT_ULL(VIRTIO_F_ACCESS_PLATFORM)) && features) {
@@ -275,7 +315,7 @@ void ifcvf_write_dev_config(struct ifcvf_hw *hw, u64 offset,
 		vp_iowrite8(*p++, hw->dev_cfg + offset + i);
 }
 
-static void ifcvf_set_features(struct ifcvf_hw *hw, u64 features)
+void ifcvf_set_driver_features(struct ifcvf_hw *hw, u64 features)
 {
 	struct virtio_pci_common_cfg __iomem *cfg = hw->common_cfg;
 
@@ -286,105 +326,104 @@ static void ifcvf_set_features(struct ifcvf_hw *hw, u64 features)
 	vp_iowrite32(features >> 32, &cfg->guest_feature);
 }
 
-static int ifcvf_config_features(struct ifcvf_hw *hw)
-{
-	ifcvf_set_features(hw, hw->req_features);
-	ifcvf_add_status(hw, VIRTIO_CONFIG_S_FEATURES_OK);
-
-	if (!(ifcvf_get_status(hw) & VIRTIO_CONFIG_S_FEATURES_OK)) {
-		IFCVF_ERR(hw->pdev, "Failed to set FEATURES_OK status\n");
-		return -EIO;
-	}
-
-	return 0;
-}
-
 u16 ifcvf_get_vq_state(struct ifcvf_hw *hw, u16 qid)
 {
-	struct ifcvf_lm_cfg __iomem *ifcvf_lm;
-	void __iomem *avail_idx_addr;
+	struct ifcvf_lm_cfg  __iomem *lm_cfg = hw->lm_cfg;
 	u16 last_avail_idx;
-	u32 q_pair_id;
 
-	ifcvf_lm = (struct ifcvf_lm_cfg __iomem *)hw->lm_cfg;
-	q_pair_id = qid / 2;
-	avail_idx_addr = &ifcvf_lm->vring_lm_cfg[q_pair_id].idx_addr[qid % 2];
-	last_avail_idx = vp_ioread16(avail_idx_addr);
+	last_avail_idx = vp_ioread16(&lm_cfg->vq_state_region + qid * 2);
 
 	return last_avail_idx;
 }
 
 int ifcvf_set_vq_state(struct ifcvf_hw *hw, u16 qid, u16 num)
 {
-	struct ifcvf_lm_cfg __iomem *ifcvf_lm;
-	void __iomem *avail_idx_addr;
-	u32 q_pair_id;
+	struct ifcvf_lm_cfg  __iomem *lm_cfg = hw->lm_cfg;
 
-	ifcvf_lm = (struct ifcvf_lm_cfg __iomem *)hw->lm_cfg;
-	q_pair_id = qid / 2;
-	avail_idx_addr = &ifcvf_lm->vring_lm_cfg[q_pair_id].idx_addr[qid % 2];
-	hw->vring[qid].last_avail_idx = num;
-	vp_iowrite16(num, avail_idx_addr);
+	vp_iowrite16(num, &lm_cfg->vq_state_region + qid * 2);
 
 	return 0;
 }
 
-static int ifcvf_hw_enable(struct ifcvf_hw *hw)
+void ifcvf_set_vq_num(struct ifcvf_hw *hw, u16 qid, u32 num)
 {
-	struct virtio_pci_common_cfg __iomem *cfg;
-	u32 i;
+	struct virtio_pci_common_cfg __iomem *cfg = hw->common_cfg;
 
-	cfg = hw->common_cfg;
-	for (i = 0; i < hw->nr_vring; i++) {
-		if (!hw->vring[i].ready)
-			break;
+	vp_iowrite16(qid, &cfg->queue_select);
+	vp_iowrite16(num, &cfg->queue_size);
+}
 
-		vp_iowrite16(i, &cfg->queue_select);
-		vp_iowrite64_twopart(hw->vring[i].desc, &cfg->queue_desc_lo,
-				     &cfg->queue_desc_hi);
-		vp_iowrite64_twopart(hw->vring[i].avail, &cfg->queue_avail_lo,
-				      &cfg->queue_avail_hi);
-		vp_iowrite64_twopart(hw->vring[i].used, &cfg->queue_used_lo,
-				     &cfg->queue_used_hi);
-		vp_iowrite16(hw->vring[i].size, &cfg->queue_size);
-		ifcvf_set_vq_state(hw, i, hw->vring[i].last_avail_idx);
-		vp_iowrite16(1, &cfg->queue_enable);
-	}
+int ifcvf_set_vq_address(struct ifcvf_hw *hw, u16 qid, u64 desc_area,
+			 u64 driver_area, u64 device_area)
+{
+	struct virtio_pci_common_cfg __iomem *cfg = hw->common_cfg;
+
+	vp_iowrite16(qid, &cfg->queue_select);
+	vp_iowrite64_twopart(desc_area, &cfg->queue_desc_lo,
+			     &cfg->queue_desc_hi);
+	vp_iowrite64_twopart(driver_area, &cfg->queue_avail_lo,
+			     &cfg->queue_avail_hi);
+	vp_iowrite64_twopart(device_area, &cfg->queue_used_lo,
+			     &cfg->queue_used_hi);
 
 	return 0;
 }
 
-static void ifcvf_hw_disable(struct ifcvf_hw *hw)
+bool ifcvf_get_vq_ready(struct ifcvf_hw *hw, u16 qid)
 {
-	u32 i;
+	struct virtio_pci_common_cfg __iomem *cfg = hw->common_cfg;
+	u16 queue_enable;
 
-	ifcvf_set_config_vector(hw, VIRTIO_MSI_NO_VECTOR);
-	for (i = 0; i < hw->nr_vring; i++) {
-		ifcvf_set_vq_vector(hw, i, VIRTIO_MSI_NO_VECTOR);
-	}
+	vp_iowrite16(qid, &cfg->queue_select);
+	queue_enable = vp_ioread16(&cfg->queue_enable);
+
+	return (bool)queue_enable;
 }
 
-int ifcvf_start_hw(struct ifcvf_hw *hw)
+void ifcvf_set_vq_ready(struct ifcvf_hw *hw, u16 qid, bool ready)
 {
-	ifcvf_reset(hw);
-	ifcvf_add_status(hw, VIRTIO_CONFIG_S_ACKNOWLEDGE);
-	ifcvf_add_status(hw, VIRTIO_CONFIG_S_DRIVER);
+	struct virtio_pci_common_cfg __iomem *cfg = hw->common_cfg;
 
-	if (ifcvf_config_features(hw) < 0)
-		return -EINVAL;
+	vp_iowrite16(qid, &cfg->queue_select);
+	vp_iowrite16(ready, &cfg->queue_enable);
+}
 
-	if (ifcvf_hw_enable(hw) < 0)
-		return -EINVAL;
+static void ifcvf_reset_vring(struct ifcvf_hw *hw)
+{
+	u16 qid;
 
-	ifcvf_add_status(hw, VIRTIO_CONFIG_S_DRIVER_OK);
+	for (qid = 0; qid < hw->nr_vring; qid++) {
+		hw->vring[qid].cb.callback = NULL;
+		hw->vring[qid].cb.private = NULL;
+		ifcvf_set_vq_vector(hw, qid, VIRTIO_MSI_NO_VECTOR);
+	}
+}
 
-	return 0;
+static void ifcvf_reset_config_handler(struct ifcvf_hw *hw)
+{
+	hw->config_cb.callback = NULL;
+	hw->config_cb.private = NULL;
+	ifcvf_set_config_vector(hw, VIRTIO_MSI_NO_VECTOR);
+}
+
+static void ifcvf_synchronize_irq(struct ifcvf_hw *hw)
+{
+	u32 nvectors = hw->num_msix_vectors;
+	struct pci_dev *pdev = hw->pdev;
+	int i, irq;
+
+	for (i = 0; i < nvectors; i++) {
+		irq = pci_irq_vector(pdev, i);
+		if (irq >= 0)
+			synchronize_irq(irq);
+	}
 }
 
-void ifcvf_stop_hw(struct ifcvf_hw *hw)
+void ifcvf_stop(struct ifcvf_hw *hw)
 {
-	ifcvf_hw_disable(hw);
-	ifcvf_reset(hw);
+	ifcvf_synchronize_irq(hw);
+	ifcvf_reset_vring(hw);
+	ifcvf_reset_config_handler(hw);
 }
 
 void ifcvf_notify_queue(struct ifcvf_hw *hw, u16 qid)

drivers/vdpa/ifcvf/ifcvf_base.h

@@ -24,15 +24,9 @@
 #define N3000_DEVICE_ID		0x1041
 #define N3000_SUBSYS_DEVICE_ID	0x001A
 
-/* Max 8 data queue pairs(16 queues) and one control vq for now. */
-#define IFCVF_MAX_QUEUES	17
-
 #define IFCVF_QUEUE_ALIGNMENT	PAGE_SIZE
-#define IFCVF_QUEUE_MAX		32768
 #define IFCVF_PCI_MAX_RESOURCE	6
 
-#define IFCVF_LM_CFG_SIZE		0x40
-#define IFCVF_LM_RING_STATE_OFFSET	0x20
 #define IFCVF_LM_BAR			4
 
 #define IFCVF_ERR(pdev, fmt, ...)	dev_err(&pdev->dev, fmt, ##__VA_ARGS__)
@@ -47,12 +41,7 @@
 #define MSIX_VECTOR_DEV_SHARED			3
 
 struct vring_info {
-	u64 desc;
-	u64 avail;
-	u64 used;
-	u16 size;
 	u16 last_avail_idx;
-	bool ready;
 	void __iomem *notify_addr;
 	phys_addr_t notify_pa;
 	u32 irq;
@@ -60,10 +49,18 @@ struct vring_info {
 	char msix_name[256];
 };
 
+struct ifcvf_lm_cfg {
+	__le64 control;
+	__le64 status;
+	__le64 lm_mem_log_start_addr;
+	__le64 lm_mem_log_end_addr;
+	__le16 vq_state_region;
+};
+
 struct ifcvf_hw {
 	u8 __iomem *isr;
 	/* Live migration */
-	u8 __iomem *lm_cfg;
+	struct ifcvf_lm_cfg  __iomem *lm_cfg;
 	/* Notification bar number */
 	u8 notify_bar;
 	u8 msix_vector_status;
@@ -74,13 +71,12 @@ struct ifcvf_hw {
 	phys_addr_t notify_base_pa;
 	u32 notify_off_multiplier;
 	u32 dev_type;
-	u64 req_features;
 	u64 hw_features;
 	/* provisioned device features */
 	u64 dev_features;
 	struct virtio_pci_common_cfg __iomem *common_cfg;
 	void __iomem *dev_cfg;
-	struct vring_info vring[IFCVF_MAX_QUEUES];
+	struct vring_info *vring;
 	void __iomem * const *base;
 	char config_msix_name[256];
 	struct vdpa_callback config_cb;
@@ -88,6 +84,7 @@ struct ifcvf_hw {
 	int vqs_reused_irq;
 	u16 nr_vring;
 	/* VIRTIO_PCI_CAP_DEVICE_CFG size */
+	u32 num_msix_vectors;
 	u32 cap_dev_config_size;
 	struct pci_dev *pdev;
 };
@@ -98,16 +95,6 @@ struct ifcvf_adapter {
 	struct ifcvf_hw *vf;
 };
 
-struct ifcvf_vring_lm_cfg {
-	u32 idx_addr[2];
-	u8 reserved[IFCVF_LM_CFG_SIZE - 8];
-};
-
-struct ifcvf_lm_cfg {
-	u8 reserved[IFCVF_LM_RING_STATE_OFFSET];
-	struct ifcvf_vring_lm_cfg vring_lm_cfg[IFCVF_MAX_QUEUES];
-};
-
 struct ifcvf_vdpa_mgmt_dev {
 	struct vdpa_mgmt_dev mdev;
 	struct ifcvf_hw vf;
@@ -116,8 +103,7 @@ struct ifcvf_vdpa_mgmt_dev {
 };
 
 int ifcvf_init_hw(struct ifcvf_hw *hw, struct pci_dev *dev);
-int ifcvf_start_hw(struct ifcvf_hw *hw);
-void ifcvf_stop_hw(struct ifcvf_hw *hw);
+void ifcvf_stop(struct ifcvf_hw *hw);
 void ifcvf_notify_queue(struct ifcvf_hw *hw, u16 qid);
 void ifcvf_read_dev_config(struct ifcvf_hw *hw, u64 offset,
 			   void *dst, int length);
@@ -127,7 +113,7 @@ u8 ifcvf_get_status(struct ifcvf_hw *hw);
 void ifcvf_set_status(struct ifcvf_hw *hw, u8 status);
 void io_write64_twopart(u64 val, u32 *lo, u32 *hi);
 void ifcvf_reset(struct ifcvf_hw *hw);
-u64 ifcvf_get_features(struct ifcvf_hw *hw);
+u64 ifcvf_get_dev_features(struct ifcvf_hw *hw);
 u64 ifcvf_get_hw_features(struct ifcvf_hw *hw);
 int ifcvf_verify_min_features(struct ifcvf_hw *hw, u64 features);
 u16 ifcvf_get_vq_state(struct ifcvf_hw *hw, u16 qid);
@@ -137,4 +123,12 @@ int ifcvf_probed_virtio_net(struct ifcvf_hw *hw);
 u32 ifcvf_get_config_size(struct ifcvf_hw *hw);
 u16 ifcvf_set_vq_vector(struct ifcvf_hw *hw, u16 qid, int vector);
 u16 ifcvf_set_config_vector(struct ifcvf_hw *hw, int vector);
+void ifcvf_set_vq_num(struct ifcvf_hw *hw, u16 qid, u32 num);
+int ifcvf_set_vq_address(struct ifcvf_hw *hw, u16 qid, u64 desc_area,
+			 u64 driver_area, u64 device_area);
+bool ifcvf_get_vq_ready(struct ifcvf_hw *hw, u16 qid);
+void ifcvf_set_vq_ready(struct ifcvf_hw *hw, u16 qid, bool ready);
+void ifcvf_set_driver_features(struct ifcvf_hw *hw, u64 features);
+u64 ifcvf_get_driver_features(struct ifcvf_hw *hw);
+u16 ifcvf_get_max_vq_size(struct ifcvf_hw *hw);
 #endif /* _IFCVF_H_ */

drivers/vdpa/ifcvf/ifcvf_main.c

@@ -125,6 +125,7 @@ static void ifcvf_free_irq(struct ifcvf_hw *vf)
 	ifcvf_free_vq_irq(vf);
 	ifcvf_free_config_irq(vf);
 	ifcvf_free_irq_vectors(pdev);
+	vf->num_msix_vectors = 0;
 }
 
 /* ifcvf MSIX vectors allocator, this helper tries to allocate
@@ -343,56 +344,11 @@ static int ifcvf_request_irq(struct ifcvf_hw *vf)
 	if (ret)
 		return ret;
 
-	return 0;
-}
-
-static int ifcvf_start_datapath(struct ifcvf_adapter *adapter)
-{
-	struct ifcvf_hw *vf = adapter->vf;
-	u8 status;
-	int ret;
-
-	ret = ifcvf_start_hw(vf);
-	if (ret < 0) {
-		status = ifcvf_get_status(vf);
-		status |= VIRTIO_CONFIG_S_FAILED;
-		ifcvf_set_status(vf, status);
-	}
-
-	return ret;
-}
-
-static int ifcvf_stop_datapath(struct ifcvf_adapter *adapter)
-{
-	struct ifcvf_hw *vf = adapter->vf;
-	int i;
-
-	for (i = 0; i < vf->nr_vring; i++)
-		vf->vring[i].cb.callback = NULL;
-
-	ifcvf_stop_hw(vf);
+	vf->num_msix_vectors = nvectors;
 
 	return 0;
 }
 
-static void ifcvf_reset_vring(struct ifcvf_adapter *adapter)
-{
-	struct ifcvf_hw *vf = adapter->vf;
-	int i;
-
-	for (i = 0; i < vf->nr_vring; i++) {
-		vf->vring[i].last_avail_idx = 0;
-		vf->vring[i].desc = 0;
-		vf->vring[i].avail = 0;
-		vf->vring[i].used = 0;
-		vf->vring[i].ready = 0;
-		vf->vring[i].cb.callback = NULL;
-		vf->vring[i].cb.private = NULL;
-	}
-
-	ifcvf_reset(vf);
-}
-
 static struct ifcvf_adapter *vdpa_to_adapter(struct vdpa_device *vdpa_dev)
 {
 	return container_of(vdpa_dev, struct ifcvf_adapter, vdpa);
@@ -414,7 +370,7 @@ static u64 ifcvf_vdpa_get_device_features(struct vdpa_device *vdpa_dev)
 	u64 features;
 
 	if (type == VIRTIO_ID_NET || type == VIRTIO_ID_BLOCK)
-		features = ifcvf_get_features(vf);
+		features = ifcvf_get_dev_features(vf);
 	else {
 		features = 0;
 		IFCVF_ERR(pdev, "VIRTIO ID %u not supported\n", vf->dev_type);
@@ -432,7 +388,7 @@ static int ifcvf_vdpa_set_driver_features(struct vdpa_device *vdpa_dev, u64 feat
 	if (ret)
 		return ret;
 
-	vf->req_features = features;
+	ifcvf_set_driver_features(vf, features);
 
 	return 0;
 }
@@ -440,8 +396,11 @@ static int ifcvf_vdpa_set_driver_features(struct vdpa_device *vdpa_dev, u64 feat
 static u64 ifcvf_vdpa_get_driver_features(struct vdpa_device *vdpa_dev)
 {
 	struct ifcvf_hw *vf = vdpa_to_vf(vdpa_dev);
+	u64 features;
+
+	features = ifcvf_get_driver_features(vf);
 
-	return vf->req_features;
+	return features;
 }
 
 static u8 ifcvf_vdpa_get_status(struct vdpa_device *vdpa_dev)
@@ -453,13 +412,11 @@ static u8 ifcvf_vdpa_get_status(struct vdpa_device *vdpa_dev)
 
 static void ifcvf_vdpa_set_status(struct vdpa_device *vdpa_dev, u8 status)
 {
-	struct ifcvf_adapter *adapter;
 	struct ifcvf_hw *vf;
 	u8 status_old;
 	int ret;
 
 	vf  = vdpa_to_vf(vdpa_dev);
-	adapter = vdpa_to_adapter(vdpa_dev);
 	status_old = ifcvf_get_status(vf);
 
 	if (status_old == status)
@@ -469,16 +426,9 @@ static void ifcvf_vdpa_set_status(struct vdpa_device *vdpa_dev, u8 status)
 	    !(status_old & VIRTIO_CONFIG_S_DRIVER_OK)) {
 		ret = ifcvf_request_irq(vf);
 		if (ret) {
-			status = ifcvf_get_status(vf);
-			status |= VIRTIO_CONFIG_S_FAILED;
-			ifcvf_set_status(vf, status);
+			IFCVF_ERR(vf->pdev, "failed to request irq with error %d\n", ret);
 			return;
 		}
-
-		if (ifcvf_start_datapath(adapter) < 0)
-			IFCVF_ERR(adapter->pdev,
-				  "Failed to set ifcvf vdpa  status %u\n",
-				  status);
 	}
 
 	ifcvf_set_status(vf, status);
@@ -486,30 +436,24 @@ static void ifcvf_vdpa_set_status(struct vdpa_device *vdpa_dev, u8 status)
 
 static int ifcvf_vdpa_reset(struct vdpa_device *vdpa_dev)
 {
-	struct ifcvf_adapter *adapter;
-	struct ifcvf_hw *vf;
-	u8 status_old;
-
-	vf  = vdpa_to_vf(vdpa_dev);
-	adapter = vdpa_to_adapter(vdpa_dev);
-	status_old = ifcvf_get_status(vf);
+	struct ifcvf_hw *vf = vdpa_to_vf(vdpa_dev);
+	u8 status = ifcvf_get_status(vf);
 
-	if (status_old == 0)
-		return 0;
+	ifcvf_stop(vf);
 
-	if (status_old & VIRTIO_CONFIG_S_DRIVER_OK) {
-		ifcvf_stop_datapath(adapter);
+	if (status & VIRTIO_CONFIG_S_DRIVER_OK)
 		ifcvf_free_irq(vf);
-	}
 
-	ifcvf_reset_vring(adapter);
+	ifcvf_reset(vf);
 
 	return 0;
 }
 
 static u16 ifcvf_vdpa_get_vq_num_max(struct vdpa_device *vdpa_dev)
 {
-	return IFCVF_QUEUE_MAX;
+	struct ifcvf_hw *vf = vdpa_to_vf(vdpa_dev);
+
+	return ifcvf_get_max_vq_size(vf);
 }
 
 static int ifcvf_vdpa_get_vq_state(struct vdpa_device *vdpa_dev, u16 qid,
@@ -542,14 +486,14 @@ static void ifcvf_vdpa_set_vq_ready(struct vdpa_device *vdpa_dev,
 {
 	struct ifcvf_hw *vf = vdpa_to_vf(vdpa_dev);
 
-	vf->vring[qid].ready = ready;
+	ifcvf_set_vq_ready(vf, qid, ready);
 }
 
 static bool ifcvf_vdpa_get_vq_ready(struct vdpa_device *vdpa_dev, u16 qid)
 {
 	struct ifcvf_hw *vf = vdpa_to_vf(vdpa_dev);
 
-	return vf->vring[qid].ready;
+	return ifcvf_get_vq_ready(vf, qid);
 }
 
 static void ifcvf_vdpa_set_vq_num(struct vdpa_device *vdpa_dev, u16 qid,
@@ -557,7 +501,7 @@ static void ifcvf_vdpa_set_vq_num(struct vdpa_device *vdpa_dev, u16 qid,
 {
 	struct ifcvf_hw *vf = vdpa_to_vf(vdpa_dev);
 
-	vf->vring[qid].size = num;
+	ifcvf_set_vq_num(vf, qid, num);
 }
 
 static int ifcvf_vdpa_set_vq_address(struct vdpa_device *vdpa_dev, u16 qid,
@@ -566,11 +510,7 @@ static int ifcvf_vdpa_set_vq_address(struct vdpa_device *vdpa_dev, u16 qid,
 {
 	struct ifcvf_hw *vf = vdpa_to_vf(vdpa_dev);
 
-	vf->vring[qid].desc = desc_area;
-	vf->vring[qid].avail = driver_area;
-	vf->vring[qid].used = device_area;
-
-	return 0;
+	return ifcvf_set_vq_address(vf, qid, desc_area, driver_area, device_area);
 }
 
 static void ifcvf_vdpa_kick_vq(struct vdpa_device *vdpa_dev, u16 qid)
@@ -892,6 +832,7 @@ static int ifcvf_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	return 0;
 
 err:
+	kfree(ifcvf_mgmt_dev->vf.vring);
 	kfree(ifcvf_mgmt_dev);
 	return ret;
 }
@@ -902,6 +843,7 @@ static void ifcvf_remove(struct pci_dev *pdev)
 
 	ifcvf_mgmt_dev = pci_get_drvdata(pdev);
 	vdpa_mgmtdev_unregister(&ifcvf_mgmt_dev->mdev);
+	kfree(ifcvf_mgmt_dev->vf.vring);
 	kfree(ifcvf_mgmt_dev);
 }
 
@@ -911,7 +853,9 @@ static struct pci_device_id ifcvf_pci_ids[] = {
 			 N3000_DEVICE_ID,
 			 PCI_VENDOR_ID_INTEL,
 			 N3000_SUBSYS_DEVICE_ID) },
-	/* C5000X-PL network device */
+	/* C5000X-PL network device
+	 * F2000X-PL network device
+	 */
 	{ PCI_DEVICE_SUB(PCI_VENDOR_ID_REDHAT_QUMRANET,
 			 VIRTIO_TRANS_ID_NET,
 			 PCI_VENDOR_ID_INTEL,

drivers/vdpa/mlx5/net/mlx5_vnet.c

@@ -83,6 +83,7 @@ struct mlx5_vq_restore_info {
 	u64 driver_addr;
 	u16 avail_index;
 	u16 used_index;
+	struct msi_map map;
 	bool ready;
 	bool restore;
 };
@@ -118,6 +119,7 @@ struct mlx5_vdpa_virtqueue {
 	u16 avail_idx;
 	u16 used_idx;
 	int fw_state;
+	struct msi_map map;
 
 	/* keep last in the struct */
 	struct mlx5_vq_restore_info ri;
@@ -808,6 +810,13 @@ static bool counters_supported(const struct mlx5_vdpa_dev *mvdev)
 	       BIT_ULL(MLX5_OBJ_TYPE_VIRTIO_Q_COUNTERS);
 }
 
+static bool msix_mode_supported(struct mlx5_vdpa_dev *mvdev)
+{
+	return MLX5_CAP_DEV_VDPA_EMULATION(mvdev->mdev, event_mode) &
+		(1 << MLX5_VIRTIO_Q_EVENT_MODE_MSIX_MODE) &&
+		pci_msix_can_alloc_dyn(mvdev->mdev->pdev);
+}
+
 static int create_virtqueue(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtqueue *mvq)
 {
 	int inlen = MLX5_ST_SZ_BYTES(create_virtio_net_q_in);
@@ -849,9 +858,15 @@ static int create_virtqueue(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtque
 	if (vq_is_tx(mvq->index))
 		MLX5_SET(virtio_net_q_object, obj_context, tisn_or_qpn, ndev->res.tisn);
 
-	MLX5_SET(virtio_q, vq_ctx, event_mode, MLX5_VIRTIO_Q_EVENT_MODE_QP_MODE);
+	if (mvq->map.virq) {
+		MLX5_SET(virtio_q, vq_ctx, event_mode, MLX5_VIRTIO_Q_EVENT_MODE_MSIX_MODE);
+		MLX5_SET(virtio_q, vq_ctx, event_qpn_or_msix, mvq->map.index);
+	} else {
+		MLX5_SET(virtio_q, vq_ctx, event_mode, MLX5_VIRTIO_Q_EVENT_MODE_QP_MODE);
+		MLX5_SET(virtio_q, vq_ctx, event_qpn_or_msix, mvq->fwqp.mqp.qpn);
+	}
+
 	MLX5_SET(virtio_q, vq_ctx, queue_index, mvq->index);
-	MLX5_SET(virtio_q, vq_ctx, event_qpn_or_msix, mvq->fwqp.mqp.qpn);
 	MLX5_SET(virtio_q, vq_ctx, queue_size, mvq->num_ent);
 	MLX5_SET(virtio_q, vq_ctx, virtio_version_1_0,
 		 !!(ndev->mvdev.actual_features & BIT_ULL(VIRTIO_F_VERSION_1)));
@@ -1194,6 +1209,56 @@ static void counter_set_dealloc(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_vir
 		mlx5_vdpa_warn(&ndev->mvdev, "dealloc counter set 0x%x\n", mvq->counter_set_id);
 }
 
+static irqreturn_t mlx5_vdpa_int_handler(int irq, void *priv)
+{
+	struct vdpa_callback *cb = priv;
+
+	if (cb->callback)
+		return cb->callback(cb->private);
+
+	return IRQ_HANDLED;
+}
+
+static void alloc_vector(struct mlx5_vdpa_net *ndev,
+			 struct mlx5_vdpa_virtqueue *mvq)
+{
+	struct mlx5_vdpa_irq_pool *irqp = &ndev->irqp;
+	struct mlx5_vdpa_irq_pool_entry *ent;
+	int err;
+	int i;
+
+	for (i = 0; i < irqp->num_ent; i++) {
+		ent = &irqp->entries[i];
+		if (!ent->used) {
+			snprintf(ent->name, MLX5_VDPA_IRQ_NAME_LEN, "%s-vq-%d",
+				 dev_name(&ndev->mvdev.vdev.dev), mvq->index);
+			ent->dev_id = &ndev->event_cbs[mvq->index];
+			err = request_irq(ent->map.virq, mlx5_vdpa_int_handler, 0,
+					  ent->name, ent->dev_id);
+			if (err)
+				return;
+
+			ent->used = true;
+			mvq->map = ent->map;
+			return;
+		}
+	}
+}
+
+static void dealloc_vector(struct mlx5_vdpa_net *ndev,
+			   struct mlx5_vdpa_virtqueue *mvq)
+{
+	struct mlx5_vdpa_irq_pool *irqp = &ndev->irqp;
+	int i;
+
+	for (i = 0; i < irqp->num_ent; i++)
+		if (mvq->map.virq == irqp->entries[i].map.virq) {
+			free_irq(mvq->map.virq, irqp->entries[i].dev_id);
+			irqp->entries[i].used = false;
+			return;
+		}
+}
+
 static int setup_vq(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtqueue *mvq)
 {
 	u16 idx = mvq->index;
@@ -1223,27 +1288,31 @@ static int setup_vq(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtqueue *mvq)
 
 	err = counter_set_alloc(ndev, mvq);
 	if (err)
-		goto err_counter;
+		goto err_connect;
 
+	alloc_vector(ndev, mvq);
 	err = create_virtqueue(ndev, mvq);
 	if (err)
-		goto err_connect;
+		goto err_vq;
 
 	if (mvq->ready) {
 		err = modify_virtqueue(ndev, mvq, MLX5_VIRTIO_NET_Q_OBJECT_STATE_RDY);
 		if (err) {
 			mlx5_vdpa_warn(&ndev->mvdev, "failed to modify to ready vq idx %d(%d)\n",
 				       idx, err);
-			goto err_connect;
+			goto err_modify;
 		}
 	}
 
 	mvq->initialized = true;
 	return 0;
 
-err_connect:
+err_modify:
+	destroy_virtqueue(ndev, mvq);
+err_vq:
+	dealloc_vector(ndev, mvq);
 	counter_set_dealloc(ndev, mvq);
-err_counter:
+err_connect:
 	qp_destroy(ndev, &mvq->vqqp);
 err_vqqp:
 	qp_destroy(ndev, &mvq->fwqp);
@@ -1288,6 +1357,7 @@ static void teardown_vq(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtqueue *
 
 	suspend_vq(ndev, mvq);
 	destroy_virtqueue(ndev, mvq);
+	dealloc_vector(ndev, mvq);
 	counter_set_dealloc(ndev, mvq);
 	qp_destroy(ndev, &mvq->vqqp);
 	qp_destroy(ndev, &mvq->fwqp);
@@ -2505,6 +2575,7 @@ static int save_channel_info(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtqu
 	ri->desc_addr = mvq->desc_addr;
 	ri->device_addr = mvq->device_addr;
 	ri->driver_addr = mvq->driver_addr;
+	ri->map = mvq->map;
 	ri->restore = true;
 	return 0;
 }
@@ -2549,6 +2620,7 @@ static void restore_channels_info(struct mlx5_vdpa_net *ndev)
 		mvq->desc_addr = ri->desc_addr;
 		mvq->device_addr = ri->device_addr;
 		mvq->driver_addr = ri->driver_addr;
+		mvq->map = ri->map;
 	}
 }
 
@@ -2833,6 +2905,25 @@ static struct device *mlx5_get_vq_dma_dev(struct vdpa_device *vdev, u16 idx)
 	return mvdev->vdev.dma_dev;
 }
 
+static void free_irqs(struct mlx5_vdpa_net *ndev)
+{
+	struct mlx5_vdpa_irq_pool_entry *ent;
+	int i;
+
+	if (!msix_mode_supported(&ndev->mvdev))
+		return;
+
+	if (!ndev->irqp.entries)
+		return;
+
+	for (i = ndev->irqp.num_ent - 1; i >= 0; i--) {
+		ent = ndev->irqp.entries + i;
+		if (ent->map.virq)
+			pci_msix_free_irq(ndev->mvdev.mdev->pdev, ent->map);
+	}
+	kfree(ndev->irqp.entries);
+}
+
 static void mlx5_vdpa_free(struct vdpa_device *vdev)
 {
 	struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev);
@@ -2848,6 +2939,7 @@ static void mlx5_vdpa_free(struct vdpa_device *vdev)
 		mlx5_mpfs_del_mac(pfmdev, ndev->config.mac);
 	}
 	mlx5_vdpa_free_resources(&ndev->mvdev);
+	free_irqs(ndev);
 	kfree(ndev->event_cbs);
 	kfree(ndev->vqs);
 }
@@ -2876,9 +2968,23 @@ static struct vdpa_notification_area mlx5_get_vq_notification(struct vdpa_device
 	return ret;
 }
 
-static int mlx5_get_vq_irq(struct vdpa_device *vdv, u16 idx)
+static int mlx5_get_vq_irq(struct vdpa_device *vdev, u16 idx)
 {
-	return -EOPNOTSUPP;
+	struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev);
+	struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev);
+	struct mlx5_vdpa_virtqueue *mvq;
+
+	if (!is_index_valid(mvdev, idx))
+		return -EINVAL;
+
+	if (is_ctrl_vq_idx(mvdev, idx))
+		return -EOPNOTSUPP;
+
+	mvq = &ndev->vqs[idx];
+	if (!mvq->map.virq)
+		return -EOPNOTSUPP;
+
+	return mvq->map.virq;
 }
 
 static u64 mlx5_vdpa_get_driver_features(struct vdpa_device *vdev)
@@ -3155,6 +3261,34 @@ static int config_func_mtu(struct mlx5_core_dev *mdev, u16 mtu)
 	return err;
 }
 
+static void allocate_irqs(struct mlx5_vdpa_net *ndev)
+{
+	struct mlx5_vdpa_irq_pool_entry *ent;
+	int i;
+
+	if (!msix_mode_supported(&ndev->mvdev))
+		return;
+
+	if (!ndev->mvdev.mdev->pdev)
+		return;
+
+	ndev->irqp.entries = kcalloc(ndev->mvdev.max_vqs, sizeof(*ndev->irqp.entries), GFP_KERNEL);
+	if (!ndev->irqp.entries)
+		return;
+
+
+	for (i = 0; i < ndev->mvdev.max_vqs; i++) {
+		ent = ndev->irqp.entries + i;
+		snprintf(ent->name, MLX5_VDPA_IRQ_NAME_LEN, "%s-vq-%d",
+			 dev_name(&ndev->mvdev.vdev.dev), i);
+		ent->map = pci_msix_alloc_irq_at(ndev->mvdev.mdev->pdev, MSI_ANY_INDEX, NULL);
+		if (!ent->map.virq)
+			return;
+
+		ndev->irqp.num_ent++;
+	}
+}
+
 static int mlx5_vdpa_dev_add(struct vdpa_mgmt_dev *v_mdev, const char *name,
 			     const struct vdpa_dev_set_config *add_config)
 {
@@ -3233,6 +3367,7 @@ static int mlx5_vdpa_dev_add(struct vdpa_mgmt_dev *v_mdev, const char *name,
 	}
 
 	init_mvqs(ndev);
+	allocate_irqs(ndev);
 	init_rwsem(&ndev->reslock);
 	config = &ndev->config;
 
@@ -3413,6 +3548,17 @@ static void mlx5v_remove(struct auxiliary_device *adev)
 	kfree(mgtdev);
 }
 
+static void mlx5v_shutdown(struct auxiliary_device *auxdev)
+{
+	struct mlx5_vdpa_mgmtdev *mgtdev;
+	struct mlx5_vdpa_net *ndev;
+
+	mgtdev = auxiliary_get_drvdata(auxdev);
+	ndev = mgtdev->ndev;
+
+	free_irqs(ndev);
+}
+
 static const struct auxiliary_device_id mlx5v_id_table[] = {
 	{ .name = MLX5_ADEV_NAME ".vnet", },
 	{},
@@ -3424,6 +3570,7 @@ static struct auxiliary_driver mlx5v_driver = {
 	.name = "vnet",
 	.probe = mlx5v_probe,
 	.remove = mlx5v_remove,
+	.shutdown = mlx5v_shutdown,
 	.id_table = mlx5v_id_table,
 };
 

drivers/vdpa/mlx5/net/mlx5_vnet.h

@@ -26,6 +26,20 @@ static inline u16 key2vid(u64 key)
 	return (u16)(key >> 48) & 0xfff;
 }
 
+#define MLX5_VDPA_IRQ_NAME_LEN 32
+
+struct mlx5_vdpa_irq_pool_entry {
+	struct msi_map map;
+	bool used;
+	char name[MLX5_VDPA_IRQ_NAME_LEN];
+	void *dev_id;
+};
+
+struct mlx5_vdpa_irq_pool {
+	int num_ent;
+	struct mlx5_vdpa_irq_pool_entry *entries;
+};
+
 struct mlx5_vdpa_net {
 	struct mlx5_vdpa_dev mvdev;
 	struct mlx5_vdpa_net_resources res;
@@ -49,6 +63,7 @@ struct mlx5_vdpa_net {
 	struct vdpa_callback config_cb;
 	struct mlx5_vdpa_wq_ent cvq_ent;
 	struct hlist_head macvlan_hash[MLX5V_MACVLAN_SIZE];
+	struct mlx5_vdpa_irq_pool irqp;
 	struct dentry *debugfs;
 };
 

drivers/vdpa/pds/Makefile

+# SPDX-License-Identifier: GPL-2.0-only
+# Copyright(c) 2023 Advanced Micro Devices, Inc
+
+obj-$(CONFIG_PDS_VDPA) := pds_vdpa.o
+
+pds_vdpa-y := aux_drv.o \
+	      cmds.o \
+	      vdpa_dev.o
+
+pds_vdpa-$(CONFIG_DEBUG_FS) += debugfs.o

drivers/vdpa/pds/aux_drv.c

+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright(c) 2023 Advanced Micro Devices, Inc */
+
+#include <linux/auxiliary_bus.h>
+#include <linux/pci.h>
+#include <linux/vdpa.h>
+#include <linux/virtio_pci_modern.h>
+
+#include <linux/pds/pds_common.h>
+#include <linux/pds/pds_core_if.h>
+#include <linux/pds/pds_adminq.h>
+#include <linux/pds/pds_auxbus.h>
+
+#include "aux_drv.h"
+#include "debugfs.h"
+#include "vdpa_dev.h"
+
+static const struct auxiliary_device_id pds_vdpa_id_table[] = {
+	{ .name = PDS_VDPA_DEV_NAME, },
+	{},
+};
+
+static int pds_vdpa_device_id_check(struct pci_dev *pdev)
+{
+	if (pdev->device != PCI_DEVICE_ID_PENSANDO_VDPA_VF ||
+	    pdev->vendor != PCI_VENDOR_ID_PENSANDO)
+		return -ENODEV;
+
+	return PCI_DEVICE_ID_PENSANDO_VDPA_VF;
+}
+
+static int pds_vdpa_probe(struct auxiliary_device *aux_dev,
+			  const struct auxiliary_device_id *id)
+
+{
+	struct pds_auxiliary_dev *padev =
+		container_of(aux_dev, struct pds_auxiliary_dev, aux_dev);
+	struct device *dev = &aux_dev->dev;
+	struct pds_vdpa_aux *vdpa_aux;
+	int err;
+
+	vdpa_aux = kzalloc(sizeof(*vdpa_aux), GFP_KERNEL);
+	if (!vdpa_aux)
+		return -ENOMEM;
+
+	vdpa_aux->padev = padev;
+	vdpa_aux->vf_id = pci_iov_vf_id(padev->vf_pdev);
+	auxiliary_set_drvdata(aux_dev, vdpa_aux);
+
+	/* Get device ident info and set up the vdpa_mgmt_dev */
+	err = pds_vdpa_get_mgmt_info(vdpa_aux);
+	if (err)
+		goto err_free_mem;
+
+	/* Find the virtio configuration */
+	vdpa_aux->vd_mdev.pci_dev = padev->vf_pdev;
+	vdpa_aux->vd_mdev.device_id_check = pds_vdpa_device_id_check;
+	vdpa_aux->vd_mdev.dma_mask = DMA_BIT_MASK(PDS_CORE_ADDR_LEN);
+	err = vp_modern_probe(&vdpa_aux->vd_mdev);
+	if (err) {
+		dev_err(dev, "Unable to probe for virtio configuration: %pe\n",
+			ERR_PTR(err));
+		goto err_free_mgmt_info;
+	}
+
+	/* Let vdpa know that we can provide devices */
+	err = vdpa_mgmtdev_register(&vdpa_aux->vdpa_mdev);
+	if (err) {
+		dev_err(dev, "%s: Failed to initialize vdpa_mgmt interface: %pe\n",
+			__func__, ERR_PTR(err));
+		goto err_free_virtio;
+	}
+
+	pds_vdpa_debugfs_add_pcidev(vdpa_aux);
+	pds_vdpa_debugfs_add_ident(vdpa_aux);
+
+	return 0;
+
+err_free_virtio:
+	vp_modern_remove(&vdpa_aux->vd_mdev);
+err_free_mgmt_info:
+	pci_free_irq_vectors(padev->vf_pdev);
+err_free_mem:
+	kfree(vdpa_aux);
+	auxiliary_set_drvdata(aux_dev, NULL);
+
+	return err;
+}
+
+static void pds_vdpa_remove(struct auxiliary_device *aux_dev)
+{
+	struct pds_vdpa_aux *vdpa_aux = auxiliary_get_drvdata(aux_dev);
+	struct device *dev = &aux_dev->dev;
+
+	vdpa_mgmtdev_unregister(&vdpa_aux->vdpa_mdev);
+	vp_modern_remove(&vdpa_aux->vd_mdev);
+	pci_free_irq_vectors(vdpa_aux->padev->vf_pdev);
+
+	pds_vdpa_debugfs_del_vdpadev(vdpa_aux);
+	kfree(vdpa_aux);
+	auxiliary_set_drvdata(aux_dev, NULL);
+
+	dev_info(dev, "Removed\n");
+}
+
+static struct auxiliary_driver pds_vdpa_driver = {
+	.name = PDS_DEV_TYPE_VDPA_STR,
+	.probe = pds_vdpa_probe,
+	.remove = pds_vdpa_remove,
+	.id_table = pds_vdpa_id_table,
+};
+
+static void __exit pds_vdpa_cleanup(void)
+{
+	auxiliary_driver_unregister(&pds_vdpa_driver);
+
+	pds_vdpa_debugfs_destroy();
+}
+module_exit(pds_vdpa_cleanup);
+
+static int __init pds_vdpa_init(void)
+{
+	int err;
+
+	pds_vdpa_debugfs_create();
+
+	err = auxiliary_driver_register(&pds_vdpa_driver);
+	if (err) {
+		pr_err("%s: aux driver register failed: %pe\n",
+		       PDS_VDPA_DRV_NAME, ERR_PTR(err));
+		pds_vdpa_debugfs_destroy();
+	}
+
+	return err;
+}
+module_init(pds_vdpa_init);
+
+MODULE_DESCRIPTION(PDS_VDPA_DRV_DESCRIPTION);
+MODULE_AUTHOR("Advanced Micro Devices, Inc");
+MODULE_LICENSE("GPL");

drivers/vdpa/pds/aux_drv.h

+/* SPDX-License-Identifier: GPL-2.0-only */
+/* Copyright(c) 2023 Advanced Micro Devices, Inc */
+
+#ifndef _AUX_DRV_H_
+#define _AUX_DRV_H_
+
+#include <linux/virtio_pci_modern.h>
+
+#define PDS_VDPA_DRV_DESCRIPTION    "AMD/Pensando vDPA VF Device Driver"
+#define PDS_VDPA_DRV_NAME           KBUILD_MODNAME
+
+struct pds_vdpa_aux {
+	struct pds_auxiliary_dev *padev;
+
+	struct vdpa_mgmt_dev vdpa_mdev;
+	struct pds_vdpa_device *pdsv;
+
+	struct pds_vdpa_ident ident;
+
+	int vf_id;
+	struct dentry *dentry;
+	struct virtio_pci_modern_device vd_mdev;
+
+	int nintrs;
+};
+#endif /* _AUX_DRV_H_ */

drivers/vdpa/pds/cmds.c

+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright(c) 2023 Advanced Micro Devices, Inc */
+
+#include <linux/vdpa.h>
+#include <linux/virtio_pci_modern.h>
+
+#include <linux/pds/pds_common.h>
+#include <linux/pds/pds_core_if.h>
+#include <linux/pds/pds_adminq.h>
+#include <linux/pds/pds_auxbus.h>
+
+#include "vdpa_dev.h"
+#include "aux_drv.h"
+#include "cmds.h"
+
+int pds_vdpa_init_hw(struct pds_vdpa_device *pdsv)
+{
+	struct pds_auxiliary_dev *padev = pdsv->vdpa_aux->padev;
+	struct device *dev = &padev->aux_dev.dev;
+	union pds_core_adminq_cmd cmd = {
+		.vdpa_init.opcode = PDS_VDPA_CMD_INIT,
+		.vdpa_init.vdpa_index = pdsv->vdpa_index,
+		.vdpa_init.vf_id = cpu_to_le16(pdsv->vdpa_aux->vf_id),
+	};
+	union pds_core_adminq_comp comp = {};
+	int err;
+
+	/* Initialize the vdpa/virtio device */
+	err = pds_client_adminq_cmd(padev, &cmd, sizeof(cmd.vdpa_init),
+				    &comp, 0);
+	if (err)
+		dev_dbg(dev, "Failed to init hw, status %d: %pe\n",
+			comp.status, ERR_PTR(err));
+
+	return err;
+}
+
+int pds_vdpa_cmd_reset(struct pds_vdpa_device *pdsv)
+{
+	struct pds_auxiliary_dev *padev = pdsv->vdpa_aux->padev;
+	struct device *dev = &padev->aux_dev.dev;
+	union pds_core_adminq_cmd cmd = {
+		.vdpa.opcode = PDS_VDPA_CMD_RESET,
+		.vdpa.vdpa_index = pdsv->vdpa_index,
+		.vdpa.vf_id = cpu_to_le16(pdsv->vdpa_aux->vf_id),
+	};
+	union pds_core_adminq_comp comp = {};
+	int err;
+
+	err = pds_client_adminq_cmd(padev, &cmd, sizeof(cmd.vdpa), &comp, 0);
+	if (err)
+		dev_dbg(dev, "Failed to reset hw, status %d: %pe\n",
+			comp.status, ERR_PTR(err));
+
+	return err;
+}
+
+int pds_vdpa_cmd_set_status(struct pds_vdpa_device *pdsv, u8 status)
+{
+	struct pds_auxiliary_dev *padev = pdsv->vdpa_aux->padev;
+	struct device *dev = &padev->aux_dev.dev;
+	union pds_core_adminq_cmd cmd = {
+		.vdpa_status.opcode = PDS_VDPA_CMD_STATUS_UPDATE,
+		.vdpa_status.vdpa_index = pdsv->vdpa_index,
+		.vdpa_status.vf_id = cpu_to_le16(pdsv->vdpa_aux->vf_id),
+		.vdpa_status.status = status,
+	};
+	union pds_core_adminq_comp comp = {};
+	int err;
+
+	err = pds_client_adminq_cmd(padev, &cmd, sizeof(cmd.vdpa_status), &comp, 0);
+	if (err)
+		dev_dbg(dev, "Failed to set status to %#x, error status %d: %pe\n",
+			status, comp.status, ERR_PTR(err));
+
+	return err;
+}
+
+int pds_vdpa_cmd_set_mac(struct pds_vdpa_device *pdsv, u8 *mac)
+{
+	struct pds_auxiliary_dev *padev = pdsv->vdpa_aux->padev;
+	struct device *dev = &padev->aux_dev.dev;
+	union pds_core_adminq_cmd cmd = {
+		.vdpa_setattr.opcode = PDS_VDPA_CMD_SET_ATTR,
+		.vdpa_setattr.vdpa_index = pdsv->vdpa_index,
+		.vdpa_setattr.vf_id = cpu_to_le16(pdsv->vdpa_aux->vf_id),
+		.vdpa_setattr.attr = PDS_VDPA_ATTR_MAC,
+	};
+	union pds_core_adminq_comp comp = {};
+	int err;
+
+	ether_addr_copy(cmd.vdpa_setattr.mac, mac);
+	err = pds_client_adminq_cmd(padev, &cmd, sizeof(cmd.vdpa_setattr),
+				    &comp, 0);
+	if (err)
+		dev_dbg(dev, "Failed to set mac address %pM, status %d: %pe\n",
+			mac, comp.status, ERR_PTR(err));
+
+	return err;
+}
+
+int pds_vdpa_cmd_set_max_vq_pairs(struct pds_vdpa_device *pdsv, u16 max_vqp)
+{
+	struct pds_auxiliary_dev *padev = pdsv->vdpa_aux->padev;
+	struct device *dev = &padev->aux_dev.dev;
+	union pds_core_adminq_cmd cmd = {
+		.vdpa_setattr.opcode = PDS_VDPA_CMD_SET_ATTR,
+		.vdpa_setattr.vdpa_index = pdsv->vdpa_index,
+		.vdpa_setattr.vf_id = cpu_to_le16(pdsv->vdpa_aux->vf_id),
+		.vdpa_setattr.attr = PDS_VDPA_ATTR_MAX_VQ_PAIRS,
+		.vdpa_setattr.max_vq_pairs = cpu_to_le16(max_vqp),
+	};
+	union pds_core_adminq_comp comp = {};
+	int err;
+
+	err = pds_client_adminq_cmd(padev, &cmd, sizeof(cmd.vdpa_setattr),
+				    &comp, 0);
+	if (err)
+		dev_dbg(dev, "Failed to set max vq pairs %u, status %d: %pe\n",
+			max_vqp, comp.status, ERR_PTR(err));
+
+	return err;
+}
+
+int pds_vdpa_cmd_init_vq(struct pds_vdpa_device *pdsv, u16 qid, u16 invert_idx,
+			 struct pds_vdpa_vq_info *vq_info)
+{
+	struct pds_auxiliary_dev *padev = pdsv->vdpa_aux->padev;
+	struct device *dev = &padev->aux_dev.dev;
+	union pds_core_adminq_cmd cmd = {
+		.vdpa_vq_init.opcode = PDS_VDPA_CMD_VQ_INIT,
+		.vdpa_vq_init.vdpa_index = pdsv->vdpa_index,
+		.vdpa_vq_init.vf_id = cpu_to_le16(pdsv->vdpa_aux->vf_id),
+		.vdpa_vq_init.qid = cpu_to_le16(qid),
+		.vdpa_vq_init.len = cpu_to_le16(ilog2(vq_info->q_len)),
+		.vdpa_vq_init.desc_addr = cpu_to_le64(vq_info->desc_addr),
+		.vdpa_vq_init.avail_addr = cpu_to_le64(vq_info->avail_addr),
+		.vdpa_vq_init.used_addr = cpu_to_le64(vq_info->used_addr),
+		.vdpa_vq_init.intr_index = cpu_to_le16(qid),
+		.vdpa_vq_init.avail_index = cpu_to_le16(vq_info->avail_idx ^ invert_idx),
+		.vdpa_vq_init.used_index = cpu_to_le16(vq_info->used_idx ^ invert_idx),
+	};
+	union pds_core_adminq_comp comp = {};
+	int err;
+
+	dev_dbg(dev, "%s: qid %d len %d desc_addr %#llx avail_addr %#llx used_addr %#llx\n",
+		__func__, qid, ilog2(vq_info->q_len),
+		vq_info->desc_addr, vq_info->avail_addr, vq_info->used_addr);
+
+	err = pds_client_adminq_cmd(padev, &cmd, sizeof(cmd.vdpa_vq_init),
+				    &comp, 0);
+	if (err)
+		dev_dbg(dev, "Failed to init vq %d, status %d: %pe\n",
+			qid, comp.status, ERR_PTR(err));
+
+	return err;
+}
+
+int pds_vdpa_cmd_reset_vq(struct pds_vdpa_device *pdsv, u16 qid, u16 invert_idx,
+			  struct pds_vdpa_vq_info *vq_info)
+{
+	struct pds_auxiliary_dev *padev = pdsv->vdpa_aux->padev;
+	struct device *dev = &padev->aux_dev.dev;
+	union pds_core_adminq_cmd cmd = {
+		.vdpa_vq_reset.opcode = PDS_VDPA_CMD_VQ_RESET,
+		.vdpa_vq_reset.vdpa_index = pdsv->vdpa_index,
+		.vdpa_vq_reset.vf_id = cpu_to_le16(pdsv->vdpa_aux->vf_id),
+		.vdpa_vq_reset.qid = cpu_to_le16(qid),
+	};
+	union pds_core_adminq_comp comp = {};
+	int err;
+
+	err = pds_client_adminq_cmd(padev, &cmd, sizeof(cmd.vdpa_vq_reset),
+				    &comp, 0);
+	if (err) {
+		dev_dbg(dev, "Failed to reset vq %d, status %d: %pe\n",
+			qid, comp.status, ERR_PTR(err));
+		return err;
+	}
+
+	vq_info->avail_idx = le16_to_cpu(comp.vdpa_vq_reset.avail_index) ^ invert_idx;
+	vq_info->used_idx = le16_to_cpu(comp.vdpa_vq_reset.used_index) ^ invert_idx;
+
+	return 0;
+}

drivers/vdpa/pds/cmds.h

+/* SPDX-License-Identifier: GPL-2.0-only */
+/* Copyright(c) 2023 Advanced Micro Devices, Inc */
+
+#ifndef _VDPA_CMDS_H_
+#define _VDPA_CMDS_H_
+
+int pds_vdpa_init_hw(struct pds_vdpa_device *pdsv);
+
+int pds_vdpa_cmd_reset(struct pds_vdpa_device *pdsv);
+int pds_vdpa_cmd_set_status(struct pds_vdpa_device *pdsv, u8 status);
+int pds_vdpa_cmd_set_mac(struct pds_vdpa_device *pdsv, u8 *mac);
+int pds_vdpa_cmd_set_max_vq_pairs(struct pds_vdpa_device *pdsv, u16 max_vqp);
+int pds_vdpa_cmd_init_vq(struct pds_vdpa_device *pdsv, u16 qid, u16 invert_idx,
+			 struct pds_vdpa_vq_info *vq_info);
+int pds_vdpa_cmd_reset_vq(struct pds_vdpa_device *pdsv, u16 qid, u16 invert_idx,
+			  struct pds_vdpa_vq_info *vq_info);
+int pds_vdpa_cmd_set_features(struct pds_vdpa_device *pdsv, u64 features);
+#endif /* _VDPA_CMDS_H_ */

drivers/vdpa/pds/debugfs.c

+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright(c) 2023 Advanced Micro Devices, Inc */
+
+#include <linux/pci.h>
+#include <linux/vdpa.h>
+
+#include <linux/pds/pds_common.h>
+#include <linux/pds/pds_core_if.h>
+#include <linux/pds/pds_adminq.h>
+#include <linux/pds/pds_auxbus.h>
+
+#include "aux_drv.h"
+#include "vdpa_dev.h"
+#include "debugfs.h"
+
+static struct dentry *dbfs_dir;
+
+void pds_vdpa_debugfs_create(void)
+{
+	dbfs_dir = debugfs_create_dir(PDS_VDPA_DRV_NAME, NULL);
+}
+
+void pds_vdpa_debugfs_destroy(void)
+{
+	debugfs_remove_recursive(dbfs_dir);
+	dbfs_dir = NULL;
+}
+
+#define PRINT_SBIT_NAME(__seq, __f, __name)                     \
+	do {                                                    \
+		if ((__f) & (__name))                               \
+			seq_printf(__seq, " %s", &#__name[16]); \
+	} while (0)
+
+static void print_status_bits(struct seq_file *seq, u8 status)
+{
+	seq_puts(seq, "status:");
+	PRINT_SBIT_NAME(seq, status, VIRTIO_CONFIG_S_ACKNOWLEDGE);
+	PRINT_SBIT_NAME(seq, status, VIRTIO_CONFIG_S_DRIVER);
+	PRINT_SBIT_NAME(seq, status, VIRTIO_CONFIG_S_DRIVER_OK);
+	PRINT_SBIT_NAME(seq, status, VIRTIO_CONFIG_S_FEATURES_OK);
+	PRINT_SBIT_NAME(seq, status, VIRTIO_CONFIG_S_NEEDS_RESET);
+	PRINT_SBIT_NAME(seq, status, VIRTIO_CONFIG_S_FAILED);
+	seq_puts(seq, "\n");
+}
+
+static void print_feature_bits_all(struct seq_file *seq, u64 features)
+{
+	int i;
+
+	seq_puts(seq, "features:");
+
+	for (i = 0; i < (sizeof(u64) * 8); i++) {
+		u64 mask = BIT_ULL(i);
+
+		switch (features & mask) {
+		case BIT_ULL(VIRTIO_NET_F_CSUM):
+			seq_puts(seq, " VIRTIO_NET_F_CSUM");
+			break;
+		case BIT_ULL(VIRTIO_NET_F_GUEST_CSUM):
+			seq_puts(seq, " VIRTIO_NET_F_GUEST_CSUM");
+			break;
+		case BIT_ULL(VIRTIO_NET_F_CTRL_GUEST_OFFLOADS):
+			seq_puts(seq, " VIRTIO_NET_F_CTRL_GUEST_OFFLOADS");
+			break;
+		case BIT_ULL(VIRTIO_NET_F_MTU):
+			seq_puts(seq, " VIRTIO_NET_F_MTU");
+			break;
+		case BIT_ULL(VIRTIO_NET_F_MAC):
+			seq_puts(seq, " VIRTIO_NET_F_MAC");
+			break;
+		case BIT_ULL(VIRTIO_NET_F_GUEST_TSO4):
+			seq_puts(seq, " VIRTIO_NET_F_GUEST_TSO4");
+			break;
+		case BIT_ULL(VIRTIO_NET_F_GUEST_TSO6):
+			seq_puts(seq, " VIRTIO_NET_F_GUEST_TSO6");
+			break;
+		case BIT_ULL(VIRTIO_NET_F_GUEST_ECN):
+			seq_puts(seq, " VIRTIO_NET_F_GUEST_ECN");
+			break;
+		case BIT_ULL(VIRTIO_NET_F_GUEST_UFO):
+			seq_puts(seq, " VIRTIO_NET_F_GUEST_UFO");
+			break;
+		case BIT_ULL(VIRTIO_NET_F_HOST_TSO4):
+			seq_puts(seq, " VIRTIO_NET_F_HOST_TSO4");
+			break;
+		case BIT_ULL(VIRTIO_NET_F_HOST_TSO6):
+			seq_puts(seq, " VIRTIO_NET_F_HOST_TSO6");
+			break;
+		case BIT_ULL(VIRTIO_NET_F_HOST_ECN):
+			seq_puts(seq, " VIRTIO_NET_F_HOST_ECN");
+			break;
+		case BIT_ULL(VIRTIO_NET_F_HOST_UFO):
+			seq_puts(seq, " VIRTIO_NET_F_HOST_UFO");
+			break;
+		case BIT_ULL(VIRTIO_NET_F_MRG_RXBUF):
+			seq_puts(seq, " VIRTIO_NET_F_MRG_RXBUF");
+			break;
+		case BIT_ULL(VIRTIO_NET_F_STATUS):
+			seq_puts(seq, " VIRTIO_NET_F_STATUS");
+			break;
+		case BIT_ULL(VIRTIO_NET_F_CTRL_VQ):
+			seq_puts(seq, " VIRTIO_NET_F_CTRL_VQ");
+			break;
+		case BIT_ULL(VIRTIO_NET_F_CTRL_RX):
+			seq_puts(seq, " VIRTIO_NET_F_CTRL_RX");
+			break;
+		case BIT_ULL(VIRTIO_NET_F_CTRL_VLAN):
+			seq_puts(seq, " VIRTIO_NET_F_CTRL_VLAN");
+			break;
+		case BIT_ULL(VIRTIO_NET_F_CTRL_RX_EXTRA):
+			seq_puts(seq, " VIRTIO_NET_F_CTRL_RX_EXTRA");
+			break;
+		case BIT_ULL(VIRTIO_NET_F_GUEST_ANNOUNCE):
+			seq_puts(seq, " VIRTIO_NET_F_GUEST_ANNOUNCE");
+			break;
+		case BIT_ULL(VIRTIO_NET_F_MQ):
+			seq_puts(seq, " VIRTIO_NET_F_MQ");
+			break;
+		case BIT_ULL(VIRTIO_NET_F_CTRL_MAC_ADDR):
+			seq_puts(seq, " VIRTIO_NET_F_CTRL_MAC_ADDR");
+			break;
+		case BIT_ULL(VIRTIO_NET_F_HASH_REPORT):
+			seq_puts(seq, " VIRTIO_NET_F_HASH_REPORT");
+			break;
+		case BIT_ULL(VIRTIO_NET_F_RSS):
+			seq_puts(seq, " VIRTIO_NET_F_RSS");
+			break;
+		case BIT_ULL(VIRTIO_NET_F_RSC_EXT):
+			seq_puts(seq, " VIRTIO_NET_F_RSC_EXT");
+			break;
+		case BIT_ULL(VIRTIO_NET_F_STANDBY):
+			seq_puts(seq, " VIRTIO_NET_F_STANDBY");
+			break;
+		case BIT_ULL(VIRTIO_NET_F_SPEED_DUPLEX):
+			seq_puts(seq, " VIRTIO_NET_F_SPEED_DUPLEX");
+			break;
+		case BIT_ULL(VIRTIO_F_NOTIFY_ON_EMPTY):
+			seq_puts(seq, " VIRTIO_F_NOTIFY_ON_EMPTY");
+			break;
+		case BIT_ULL(VIRTIO_F_ANY_LAYOUT):
+			seq_puts(seq, " VIRTIO_F_ANY_LAYOUT");
+			break;
+		case BIT_ULL(VIRTIO_F_VERSION_1):
+			seq_puts(seq, " VIRTIO_F_VERSION_1");
+			break;
+		case BIT_ULL(VIRTIO_F_ACCESS_PLATFORM):
+			seq_puts(seq, " VIRTIO_F_ACCESS_PLATFORM");
+			break;
+		case BIT_ULL(VIRTIO_F_RING_PACKED):
+			seq_puts(seq, " VIRTIO_F_RING_PACKED");
+			break;
+		case BIT_ULL(VIRTIO_F_ORDER_PLATFORM):
+			seq_puts(seq, " VIRTIO_F_ORDER_PLATFORM");
+			break;
+		case BIT_ULL(VIRTIO_F_SR_IOV):
+			seq_puts(seq, " VIRTIO_F_SR_IOV");
+			break;
+		case 0:
+			break;
+		default:
+			seq_printf(seq, " bit_%d", i);
+			break;
+		}
+	}
+
+	seq_puts(seq, "\n");
+}
+
+void pds_vdpa_debugfs_add_pcidev(struct pds_vdpa_aux *vdpa_aux)
+{
+	vdpa_aux->dentry = debugfs_create_dir(pci_name(vdpa_aux->padev->vf_pdev), dbfs_dir);
+}
+
+static int identity_show(struct seq_file *seq, void *v)
+{
+	struct pds_vdpa_aux *vdpa_aux = seq->private;
+	struct vdpa_mgmt_dev *mgmt;
+
+	seq_printf(seq, "aux_dev:            %s\n",
+		   dev_name(&vdpa_aux->padev->aux_dev.dev));
+
+	mgmt = &vdpa_aux->vdpa_mdev;
+	seq_printf(seq, "max_vqs:            %d\n", mgmt->max_supported_vqs);
+	seq_printf(seq, "config_attr_mask:   %#llx\n", mgmt->config_attr_mask);
+	seq_printf(seq, "supported_features: %#llx\n", mgmt->supported_features);
+	print_feature_bits_all(seq, mgmt->supported_features);
+
+	return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(identity);
+
+void pds_vdpa_debugfs_add_ident(struct pds_vdpa_aux *vdpa_aux)
+{
+	debugfs_create_file("identity", 0400, vdpa_aux->dentry,
+			    vdpa_aux, &identity_fops);
+}
+
+static int config_show(struct seq_file *seq, void *v)
+{
+	struct pds_vdpa_device *pdsv = seq->private;
+	struct virtio_net_config vc;
+	u64 driver_features;
+	u8 status;
+
+	memcpy_fromio(&vc, pdsv->vdpa_aux->vd_mdev.device,
+		      sizeof(struct virtio_net_config));
+
+	seq_printf(seq, "mac:                  %pM\n", vc.mac);
+	seq_printf(seq, "max_virtqueue_pairs:  %d\n",
+		   __virtio16_to_cpu(true, vc.max_virtqueue_pairs));
+	seq_printf(seq, "mtu:                  %d\n", __virtio16_to_cpu(true, vc.mtu));
+	seq_printf(seq, "speed:                %d\n", le32_to_cpu(vc.speed));
+	seq_printf(seq, "duplex:               %d\n", vc.duplex);
+	seq_printf(seq, "rss_max_key_size:     %d\n", vc.rss_max_key_size);
+	seq_printf(seq, "rss_max_indirection_table_length: %d\n",
+		   le16_to_cpu(vc.rss_max_indirection_table_length));
+	seq_printf(seq, "supported_hash_types: %#x\n",
+		   le32_to_cpu(vc.supported_hash_types));
+	seq_printf(seq, "vn_status:            %#x\n",
+		   __virtio16_to_cpu(true, vc.status));
+
+	status = vp_modern_get_status(&pdsv->vdpa_aux->vd_mdev);
+	seq_printf(seq, "dev_status:           %#x\n", status);
+	print_status_bits(seq, status);
+
+	seq_printf(seq, "req_features:         %#llx\n", pdsv->req_features);
+	print_feature_bits_all(seq, pdsv->req_features);
+	driver_features = vp_modern_get_driver_features(&pdsv->vdpa_aux->vd_mdev);
+	seq_printf(seq, "driver_features:      %#llx\n", driver_features);
+	print_feature_bits_all(seq, driver_features);
+	seq_printf(seq, "vdpa_index:           %d\n", pdsv->vdpa_index);
+	seq_printf(seq, "num_vqs:              %d\n", pdsv->num_vqs);
+
+	return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(config);
+
+static int vq_show(struct seq_file *seq, void *v)
+{
+	struct pds_vdpa_vq_info *vq = seq->private;
+
+	seq_printf(seq, "ready:      %d\n", vq->ready);
+	seq_printf(seq, "desc_addr:  %#llx\n", vq->desc_addr);
+	seq_printf(seq, "avail_addr: %#llx\n", vq->avail_addr);
+	seq_printf(seq, "used_addr:  %#llx\n", vq->used_addr);
+	seq_printf(seq, "q_len:      %d\n", vq->q_len);
+	seq_printf(seq, "qid:        %d\n", vq->qid);
+
+	seq_printf(seq, "doorbell:   %#llx\n", vq->doorbell);
+	seq_printf(seq, "avail_idx:  %d\n", vq->avail_idx);
+	seq_printf(seq, "used_idx:   %d\n", vq->used_idx);
+	seq_printf(seq, "irq:        %d\n", vq->irq);
+	seq_printf(seq, "irq-name:   %s\n", vq->irq_name);
+
+	return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(vq);
+
+void pds_vdpa_debugfs_add_vdpadev(struct pds_vdpa_aux *vdpa_aux)
+{
+	int i;
+
+	debugfs_create_file("config", 0400, vdpa_aux->dentry, vdpa_aux->pdsv, &config_fops);
+
+	for (i = 0; i < vdpa_aux->pdsv->num_vqs; i++) {
+		char name[8];
+
+		snprintf(name, sizeof(name), "vq%02d", i);
+		debugfs_create_file(name, 0400, vdpa_aux->dentry,
+				    &vdpa_aux->pdsv->vqs[i], &vq_fops);
+	}
+}
+
+void pds_vdpa_debugfs_del_vdpadev(struct pds_vdpa_aux *vdpa_aux)
+{
+	debugfs_remove_recursive(vdpa_aux->dentry);
+	vdpa_aux->dentry = NULL;
+}
+
+void pds_vdpa_debugfs_reset_vdpadev(struct pds_vdpa_aux *vdpa_aux)
+{
+	/* we don't keep track of the entries, so remove it all
+	 * then rebuild the basics
+	 */
+	pds_vdpa_debugfs_del_vdpadev(vdpa_aux);
+	pds_vdpa_debugfs_add_pcidev(vdpa_aux);
+	pds_vdpa_debugfs_add_ident(vdpa_aux);
+}

drivers/vdpa/pds/debugfs.h

+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright(c) 2023 Advanced Micro Devices, Inc */
+
+#ifndef _PDS_VDPA_DEBUGFS_H_
+#define _PDS_VDPA_DEBUGFS_H_
+
+#include <linux/debugfs.h>
+
+void pds_vdpa_debugfs_create(void);
+void pds_vdpa_debugfs_destroy(void);
+void pds_vdpa_debugfs_add_pcidev(struct pds_vdpa_aux *vdpa_aux);
+void pds_vdpa_debugfs_add_ident(struct pds_vdpa_aux *vdpa_aux);
+void pds_vdpa_debugfs_add_vdpadev(struct pds_vdpa_aux *vdpa_aux);
+void pds_vdpa_debugfs_del_vdpadev(struct pds_vdpa_aux *vdpa_aux);
+void pds_vdpa_debugfs_reset_vdpadev(struct pds_vdpa_aux *vdpa_aux);
+
+#endif /* _PDS_VDPA_DEBUGFS_H_ */

drivers/vdpa/pds/vdpa_dev.h

+/* SPDX-License-Identifier: GPL-2.0-only */
+/* Copyright(c) 2023 Advanced Micro Devices, Inc */
+
+#ifndef _VDPA_DEV_H_
+#define _VDPA_DEV_H_
+
+#include <linux/pci.h>
+#include <linux/vdpa.h>
+
+struct pds_vdpa_vq_info {
+	bool ready;
+	u64 desc_addr;
+	u64 avail_addr;
+	u64 used_addr;
+	u32 q_len;
+	u16 qid;
+	int irq;
+	char irq_name[32];
+
+	void __iomem *notify;
+	dma_addr_t notify_pa;
+
+	u64 doorbell;
+	u16 avail_idx;
+	u16 used_idx;
+
+	struct vdpa_callback event_cb;
+	struct pds_vdpa_device *pdsv;
+};
+
+#define PDS_VDPA_MAX_QUEUES	65
+#define PDS_VDPA_MAX_QLEN	32768
+struct pds_vdpa_device {
+	struct vdpa_device vdpa_dev;
+	struct pds_vdpa_aux *vdpa_aux;
+
+	struct pds_vdpa_vq_info vqs[PDS_VDPA_MAX_QUEUES];
+	u64 supported_features;		/* specified device features */
+	u64 req_features;		/* features requested by vdpa */
+	u8 vdpa_index;			/* rsvd for future subdevice use */
+	u8 num_vqs;			/* num vqs in use */
+	struct vdpa_callback config_cb;
+	struct notifier_block nb;
+};
+
+#define PDS_VDPA_PACKED_INVERT_IDX	0x8000
+
+int pds_vdpa_get_mgmt_info(struct pds_vdpa_aux *vdpa_aux);
+#endif /* _VDPA_DEV_H_ */

drivers/vdpa/solidrun/snet_ctrl.c

@@ -16,6 +16,7 @@ enum snet_ctrl_opcodes {
 	SNET_CTRL_OP_DESTROY = 1,
 	SNET_CTRL_OP_READ_VQ_STATE,
 	SNET_CTRL_OP_SUSPEND,
+	SNET_CTRL_OP_RESUME,
 };
 
 #define SNET_CTRL_TIMEOUT	        2000000
@@ -328,3 +329,8 @@ int snet_suspend_dev(struct snet *snet)
 {
 	return snet_send_ctrl_msg(snet, SNET_CTRL_OP_SUSPEND, 0);
 }
+
+int snet_resume_dev(struct snet *snet)
+{
+	return snet_send_ctrl_msg(snet, SNET_CTRL_OP_RESUME, 0);
+}

drivers/vdpa/solidrun/snet_hwmon.c

@@ -159,7 +159,7 @@ static const struct hwmon_ops snet_hwmon_ops = {
 	.read_string = snet_hwmon_read_string
 };
 
-static const struct hwmon_channel_info *snet_hwmon_info[] = {
+static const struct hwmon_channel_info * const snet_hwmon_info[] = {
 	HWMON_CHANNEL_INFO(temp, HWMON_T_INPUT | HWMON_T_MAX | HWMON_T_CRIT | HWMON_T_LABEL,
 			   HWMON_T_INPUT | HWMON_T_CRIT | HWMON_T_LABEL),
 	HWMON_CHANNEL_INFO(power, HWMON_P_INPUT | HWMON_P_LABEL),

drivers/vdpa/solidrun/snet_main.c

@@ -509,6 +509,20 @@ static int snet_suspend(struct vdpa_device *vdev)
 	return ret;
 }
 
+static int snet_resume(struct vdpa_device *vdev)
+{
+	struct snet *snet = vdpa_to_snet(vdev);
+	int ret;
+
+	ret = snet_resume_dev(snet);
+	if (ret)
+		SNET_ERR(snet->pdev, "SNET[%u] resume failed, err: %d\n", snet->sid, ret);
+	else
+		SNET_DBG(snet->pdev, "Resume SNET[%u] device\n", snet->sid);
+
+	return ret;
+}
+
 static const struct vdpa_config_ops snet_config_ops = {
 	.set_vq_address         = snet_set_vq_address,
 	.set_vq_num             = snet_set_vq_num,
@@ -536,6 +550,7 @@ static const struct vdpa_config_ops snet_config_ops = {
 	.get_config             = snet_get_config,
 	.set_config             = snet_set_config,
 	.suspend		= snet_suspend,
+	.resume			= snet_resume,
 };
 
 static int psnet_open_pf_bar(struct pci_dev *pdev, struct psnet *psnet)

drivers/vdpa/solidrun/snet_vdpa.h

@@ -204,5 +204,6 @@ void snet_ctrl_clear(struct snet *snet);
 int snet_destroy_dev(struct snet *snet);
 int snet_read_vq_state(struct snet *snet, u16 idx, struct vdpa_vq_state *state);
 int snet_suspend_dev(struct snet *snet);
+int snet_resume_dev(struct snet *snet);
 
 #endif //_SNET_VDPA_H_

drivers/vdpa/vdpa_user/vduse_dev.c

@@ -726,7 +726,11 @@ static int vduse_vdpa_set_vq_affinity(struct vdpa_device *vdpa, u16 idx,
 {
 	struct vduse_dev *dev = vdpa_to_vduse(vdpa);
 
-	cpumask_copy(&dev->vqs[idx]->irq_affinity, cpu_mask);
+	if (cpu_mask)
+		cpumask_copy(&dev->vqs[idx]->irq_affinity, cpu_mask);
+	else
+		cpumask_setall(&dev->vqs[idx]->irq_affinity);
+
 	return 0;
 }
 

drivers/vhost/net.c

@@ -546,7 +546,7 @@ static void vhost_net_busy_poll(struct vhost_net *net,
 	endtime = busy_clock() + busyloop_timeout;
 
 	while (vhost_can_busy_poll(endtime)) {
-		if (vhost_has_work(&net->dev)) {
+		if (vhost_vq_has_work(vq)) {
 			*busyloop_intr = true;
 			break;
 		}
@@ -1347,8 +1347,10 @@ static int vhost_net_open(struct inode *inode, struct file *f)
 		       VHOST_NET_PKT_WEIGHT, VHOST_NET_WEIGHT, true,
 		       NULL);
 
-	vhost_poll_init(n->poll + VHOST_NET_VQ_TX, handle_tx_net, EPOLLOUT, dev);
-	vhost_poll_init(n->poll + VHOST_NET_VQ_RX, handle_rx_net, EPOLLIN, dev);
+	vhost_poll_init(n->poll + VHOST_NET_VQ_TX, handle_tx_net, EPOLLOUT, dev,
+			vqs[VHOST_NET_VQ_TX]);
+	vhost_poll_init(n->poll + VHOST_NET_VQ_RX, handle_rx_net, EPOLLIN, dev,
+			vqs[VHOST_NET_VQ_RX]);
 
 	f->private_data = n;
 	n->page_frag.page = NULL;

drivers/vhost/scsi.c

@@ -167,6 +167,7 @@ MODULE_PARM_DESC(max_io_vqs, "Set the max number of IO virtqueues a vhost scsi d
 
 struct vhost_scsi_virtqueue {
 	struct vhost_virtqueue vq;
+	struct vhost_scsi *vs;
 	/*
 	 * Reference counting for inflight reqs, used for flush operation. At
 	 * each time, one reference tracks new commands submitted, while we
@@ -181,6 +182,9 @@ struct vhost_scsi_virtqueue {
 	struct vhost_scsi_cmd *scsi_cmds;
 	struct sbitmap scsi_tags;
 	int max_cmds;
+
+	struct vhost_work completion_work;
+	struct llist_head completion_list;
 };
 
 struct vhost_scsi {
@@ -190,12 +194,8 @@ struct vhost_scsi {
 
 	struct vhost_dev dev;
 	struct vhost_scsi_virtqueue *vqs;
-	unsigned long *compl_bitmap;
 	struct vhost_scsi_inflight **old_inflight;
 
-	struct vhost_work vs_completion_work; /* cmd completion work item */
-	struct llist_head vs_completion_list; /* cmd completion queue */
-
 	struct vhost_work vs_event_work; /* evt injection work item */
 	struct llist_head vs_event_list; /* evt injection queue */
 
@@ -353,15 +353,17 @@ static void vhost_scsi_release_cmd(struct se_cmd *se_cmd)
 	if (se_cmd->se_cmd_flags & SCF_SCSI_TMR_CDB) {
 		struct vhost_scsi_tmf *tmf = container_of(se_cmd,
 					struct vhost_scsi_tmf, se_cmd);
+		struct vhost_virtqueue *vq = &tmf->svq->vq;
 
-		vhost_work_queue(&tmf->vhost->dev, &tmf->vwork);
+		vhost_vq_work_queue(vq, &tmf->vwork);
 	} else {
 		struct vhost_scsi_cmd *cmd = container_of(se_cmd,
 					struct vhost_scsi_cmd, tvc_se_cmd);
-		struct vhost_scsi *vs = cmd->tvc_vhost;
+		struct vhost_scsi_virtqueue *svq =  container_of(cmd->tvc_vq,
+					struct vhost_scsi_virtqueue, vq);
 
-		llist_add(&cmd->tvc_completion_list, &vs->vs_completion_list);
-		vhost_work_queue(&vs->dev, &vs->vs_completion_work);
+		llist_add(&cmd->tvc_completion_list, &svq->completion_list);
+		vhost_vq_work_queue(&svq->vq, &svq->completion_work);
 	}
 }
 
@@ -509,17 +511,17 @@ static void vhost_scsi_evt_work(struct vhost_work *work)
  */
 static void vhost_scsi_complete_cmd_work(struct vhost_work *work)
 {
-	struct vhost_scsi *vs = container_of(work, struct vhost_scsi,
-					vs_completion_work);
+	struct vhost_scsi_virtqueue *svq = container_of(work,
+				struct vhost_scsi_virtqueue, completion_work);
 	struct virtio_scsi_cmd_resp v_rsp;
 	struct vhost_scsi_cmd *cmd, *t;
 	struct llist_node *llnode;
 	struct se_cmd *se_cmd;
 	struct iov_iter iov_iter;
-	int ret, vq;
+	bool signal = false;
+	int ret;
 
-	bitmap_zero(vs->compl_bitmap, vs->dev.nvqs);
-	llnode = llist_del_all(&vs->vs_completion_list);
+	llnode = llist_del_all(&svq->completion_list);
 	llist_for_each_entry_safe(cmd, t, llnode, tvc_completion_list) {
 		se_cmd = &cmd->tvc_se_cmd;
 
@@ -539,21 +541,17 @@ static void vhost_scsi_complete_cmd_work(struct vhost_work *work)
 			      cmd->tvc_in_iovs, sizeof(v_rsp));
 		ret = copy_to_iter(&v_rsp, sizeof(v_rsp), &iov_iter);
 		if (likely(ret == sizeof(v_rsp))) {
-			struct vhost_scsi_virtqueue *q;
+			signal = true;
+
 			vhost_add_used(cmd->tvc_vq, cmd->tvc_vq_desc, 0);
-			q = container_of(cmd->tvc_vq, struct vhost_scsi_virtqueue, vq);
-			vq = q - vs->vqs;
-			__set_bit(vq, vs->compl_bitmap);
 		} else
 			pr_err("Faulted on virtio_scsi_cmd_resp\n");
 
 		vhost_scsi_release_cmd_res(se_cmd);
 	}
 
-	vq = -1;
-	while ((vq = find_next_bit(vs->compl_bitmap, vs->dev.nvqs, vq + 1))
-		< vs->dev.nvqs)
-		vhost_signal(&vs->dev, &vs->vqs[vq].vq);
+	if (signal)
+		vhost_signal(&svq->vs->dev, &svq->vq);
 }
 
 static struct vhost_scsi_cmd *
@@ -1135,12 +1133,27 @@ static void vhost_scsi_tmf_resp_work(struct vhost_work *work)
 {
 	struct vhost_scsi_tmf *tmf = container_of(work, struct vhost_scsi_tmf,
 						  vwork);
-	int resp_code;
+	struct vhost_virtqueue *ctl_vq, *vq;
+	int resp_code, i;
+
+	if (tmf->scsi_resp == TMR_FUNCTION_COMPLETE) {
+		/*
+		 * Flush IO vqs that don't share a worker with the ctl to make
+		 * sure they have sent their responses before us.
+		 */
+		ctl_vq = &tmf->vhost->vqs[VHOST_SCSI_VQ_CTL].vq;
+		for (i = VHOST_SCSI_VQ_IO; i < tmf->vhost->dev.nvqs; i++) {
+			vq = &tmf->vhost->vqs[i].vq;
+
+			if (vhost_vq_is_setup(vq) &&
+			    vq->worker != ctl_vq->worker)
+				vhost_vq_flush(vq);
+		}
 
-	if (tmf->scsi_resp == TMR_FUNCTION_COMPLETE)
 		resp_code = VIRTIO_SCSI_S_FUNCTION_SUCCEEDED;
-	else
+	} else {
 		resp_code = VIRTIO_SCSI_S_FUNCTION_REJECTED;
+	}
 
 	vhost_scsi_send_tmf_resp(tmf->vhost, &tmf->svq->vq, tmf->in_iovs,
 				 tmf->vq_desc, &tmf->resp_iov, resp_code);
@@ -1335,11 +1348,9 @@ static void vhost_scsi_ctl_handle_kick(struct vhost_work *work)
 }
 
 static void
-vhost_scsi_send_evt(struct vhost_scsi *vs,
-		   struct vhost_scsi_tpg *tpg,
-		   struct se_lun *lun,
-		   u32 event,
-		   u32 reason)
+vhost_scsi_send_evt(struct vhost_scsi *vs, struct vhost_virtqueue *vq,
+		    struct vhost_scsi_tpg *tpg, struct se_lun *lun,
+		    u32 event, u32 reason)
 {
 	struct vhost_scsi_evt *evt;
 
@@ -1361,7 +1372,7 @@ vhost_scsi_send_evt(struct vhost_scsi *vs,
 	}
 
 	llist_add(&evt->list, &vs->vs_event_list);
-	vhost_work_queue(&vs->dev, &vs->vs_event_work);
+	vhost_vq_work_queue(vq, &vs->vs_event_work);
 }
 
 static void vhost_scsi_evt_handle_kick(struct vhost_work *work)
@@ -1375,7 +1386,8 @@ static void vhost_scsi_evt_handle_kick(struct vhost_work *work)
 		goto out;
 
 	if (vs->vs_events_missed)
-		vhost_scsi_send_evt(vs, NULL, NULL, VIRTIO_SCSI_T_NO_EVENT, 0);
+		vhost_scsi_send_evt(vs, vq, NULL, NULL, VIRTIO_SCSI_T_NO_EVENT,
+				    0);
 out:
 	mutex_unlock(&vq->mutex);
 }
@@ -1770,6 +1782,7 @@ static int vhost_scsi_set_features(struct vhost_scsi *vs, u64 features)
 
 static int vhost_scsi_open(struct inode *inode, struct file *f)
 {
+	struct vhost_scsi_virtqueue *svq;
 	struct vhost_scsi *vs;
 	struct vhost_virtqueue **vqs;
 	int r = -ENOMEM, i, nvqs = vhost_scsi_max_io_vqs;
@@ -1788,10 +1801,6 @@ static int vhost_scsi_open(struct inode *inode, struct file *f)
 	}
 	nvqs += VHOST_SCSI_VQ_IO;
 
-	vs->compl_bitmap = bitmap_alloc(nvqs, GFP_KERNEL);
-	if (!vs->compl_bitmap)
-		goto err_compl_bitmap;
-
 	vs->old_inflight = kmalloc_array(nvqs, sizeof(*vs->old_inflight),
 					 GFP_KERNEL | __GFP_ZERO);
 	if (!vs->old_inflight)
@@ -1806,7 +1815,6 @@ static int vhost_scsi_open(struct inode *inode, struct file *f)
 	if (!vqs)
 		goto err_local_vqs;
 
-	vhost_work_init(&vs->vs_completion_work, vhost_scsi_complete_cmd_work);
 	vhost_work_init(&vs->vs_event_work, vhost_scsi_evt_work);
 
 	vs->vs_events_nr = 0;
@@ -1817,8 +1825,14 @@ static int vhost_scsi_open(struct inode *inode, struct file *f)
 	vs->vqs[VHOST_SCSI_VQ_CTL].vq.handle_kick = vhost_scsi_ctl_handle_kick;
 	vs->vqs[VHOST_SCSI_VQ_EVT].vq.handle_kick = vhost_scsi_evt_handle_kick;
 	for (i = VHOST_SCSI_VQ_IO; i < nvqs; i++) {
-		vqs[i] = &vs->vqs[i].vq;
-		vs->vqs[i].vq.handle_kick = vhost_scsi_handle_kick;
+		svq = &vs->vqs[i];
+
+		vqs[i] = &svq->vq;
+		svq->vs = vs;
+		init_llist_head(&svq->completion_list);
+		vhost_work_init(&svq->completion_work,
+				vhost_scsi_complete_cmd_work);
+		svq->vq.handle_kick = vhost_scsi_handle_kick;
 	}
 	vhost_dev_init(&vs->dev, vqs, nvqs, UIO_MAXIOV,
 		       VHOST_SCSI_WEIGHT, 0, true, NULL);
@@ -1833,8 +1847,6 @@ static int vhost_scsi_open(struct inode *inode, struct file *f)
 err_vqs:
 	kfree(vs->old_inflight);
 err_inflight:
-	bitmap_free(vs->compl_bitmap);
-err_compl_bitmap:
 	kvfree(vs);
 err_vs:
 	return r;
@@ -1854,7 +1866,6 @@ static int vhost_scsi_release(struct inode *inode, struct file *f)
 	kfree(vs->dev.vqs);
 	kfree(vs->vqs);
 	kfree(vs->old_inflight);
-	bitmap_free(vs->compl_bitmap);
 	kvfree(vs);
 	return 0;
 }
@@ -1916,6 +1927,14 @@ vhost_scsi_ioctl(struct file *f,
 		if (copy_from_user(&features, featurep, sizeof features))
 			return -EFAULT;
 		return vhost_scsi_set_features(vs, features);
+	case VHOST_NEW_WORKER:
+	case VHOST_FREE_WORKER:
+	case VHOST_ATTACH_VRING_WORKER:
+	case VHOST_GET_VRING_WORKER:
+		mutex_lock(&vs->dev.mutex);
+		r = vhost_worker_ioctl(&vs->dev, ioctl, argp);
+		mutex_unlock(&vs->dev.mutex);
+		return r;
 	default:
 		mutex_lock(&vs->dev.mutex);
 		r = vhost_dev_ioctl(&vs->dev, ioctl, argp);
@@ -1995,7 +2014,7 @@ vhost_scsi_do_plug(struct vhost_scsi_tpg *tpg,
 		goto unlock;
 
 	if (vhost_has_feature(vq, VIRTIO_SCSI_F_HOTPLUG))
-		vhost_scsi_send_evt(vs, tpg, lun,
+		vhost_scsi_send_evt(vs, vq, tpg, lun,
 				   VIRTIO_SCSI_T_TRANSPORT_RESET, reason);
 unlock:
 	mutex_unlock(&vq->mutex);

drivers/vhost/vhost.h

@@ -28,8 +28,12 @@ struct vhost_work {
 
 struct vhost_worker {
 	struct vhost_task	*vtsk;
+	/* Used to serialize device wide flushing with worker swapping. */
+	struct mutex		mutex;
 	struct llist_head	work_list;
 	u64			kcov_handle;
+	u32			id;
+	int			attachment_cnt;
 };
 
 /* Poll a file (eventfd or socket) */
@@ -41,17 +45,17 @@ struct vhost_poll {
 	struct vhost_work	work;
 	__poll_t		mask;
 	struct vhost_dev	*dev;
+	struct vhost_virtqueue	*vq;
 };
 
-void vhost_work_init(struct vhost_work *work, vhost_work_fn_t fn);
-void vhost_work_queue(struct vhost_dev *dev, struct vhost_work *work);
-bool vhost_has_work(struct vhost_dev *dev);
-
 void vhost_poll_init(struct vhost_poll *poll, vhost_work_fn_t fn,
-		     __poll_t mask, struct vhost_dev *dev);
+		     __poll_t mask, struct vhost_dev *dev,
+		     struct vhost_virtqueue *vq);
 int vhost_poll_start(struct vhost_poll *poll, struct file *file);
 void vhost_poll_stop(struct vhost_poll *poll);
 void vhost_poll_queue(struct vhost_poll *poll);
+
+void vhost_work_init(struct vhost_work *work, vhost_work_fn_t fn);
 void vhost_dev_flush(struct vhost_dev *dev);
 
 struct vhost_log {
@@ -74,6 +78,7 @@ struct vhost_vring_call {
 /* The virtqueue structure describes a queue attached to a device. */
 struct vhost_virtqueue {
 	struct vhost_dev *dev;
+	struct vhost_worker __rcu *worker;
 
 	/* The actual ring of buffers. */
 	struct mutex mutex;
@@ -158,7 +163,6 @@ struct vhost_dev {
 	struct vhost_virtqueue **vqs;
 	int nvqs;
 	struct eventfd_ctx *log_ctx;
-	struct vhost_worker worker;
 	struct vhost_iotlb *umem;
 	struct vhost_iotlb *iotlb;
 	spinlock_t iotlb_lock;
@@ -168,6 +172,7 @@ struct vhost_dev {
 	int iov_limit;
 	int weight;
 	int byte_weight;
+	struct xarray worker_xa;
 	bool use_worker;
 	int (*msg_handler)(struct vhost_dev *dev, u32 asid,
 			   struct vhost_iotlb_msg *msg);
@@ -188,16 +193,21 @@ void vhost_dev_cleanup(struct vhost_dev *);
 void vhost_dev_stop(struct vhost_dev *);
 long vhost_dev_ioctl(struct vhost_dev *, unsigned int ioctl, void __user *argp);
 long vhost_vring_ioctl(struct vhost_dev *d, unsigned int ioctl, void __user *argp);
+long vhost_worker_ioctl(struct vhost_dev *dev, unsigned int ioctl,
+			void __user *argp);
 bool vhost_vq_access_ok(struct vhost_virtqueue *vq);
 bool vhost_log_access_ok(struct vhost_dev *);
 void vhost_clear_msg(struct vhost_dev *dev);
 
 int vhost_get_vq_desc(struct vhost_virtqueue *,
-		      struct iovec iov[], unsigned int iov_count,
+		      struct iovec iov[], unsigned int iov_size,
 		      unsigned int *out_num, unsigned int *in_num,
 		      struct vhost_log *log, unsigned int *log_num);
 void vhost_discard_vq_desc(struct vhost_virtqueue *, int n);
 
+void vhost_vq_flush(struct vhost_virtqueue *vq);
+bool vhost_vq_work_queue(struct vhost_virtqueue *vq, struct vhost_work *work);
+bool vhost_vq_has_work(struct vhost_virtqueue *vq);
 bool vhost_vq_is_setup(struct vhost_virtqueue *vq);
 int vhost_vq_init_access(struct vhost_virtqueue *);
 int vhost_add_used(struct vhost_virtqueue *, unsigned int head, int len);

drivers/vhost/vsock.c

@@ -285,7 +285,7 @@ vhost_transport_send_pkt(struct sk_buff *skb)
 		atomic_inc(&vsock->queued_replies);
 
 	virtio_vsock_skb_queue_tail(&vsock->send_pkt_queue, skb);
-	vhost_work_queue(&vsock->dev, &vsock->send_pkt_work);
+	vhost_vq_work_queue(&vsock->vqs[VSOCK_VQ_RX], &vsock->send_pkt_work);
 
 	rcu_read_unlock();
 	return len;
@@ -583,7 +583,7 @@ static int vhost_vsock_start(struct vhost_vsock *vsock)
 	/* Some packets may have been queued before the device was started,
 	 * let's kick the send worker to send them.
 	 */
-	vhost_work_queue(&vsock->dev, &vsock->send_pkt_work);
+	vhost_vq_work_queue(&vsock->vqs[VSOCK_VQ_RX], &vsock->send_pkt_work);
 
 	mutex_unlock(&vsock->dev.mutex);
 	return 0;

drivers/virtio/virtio_pci_common.h

@@ -45,9 +45,10 @@ struct virtio_pci_vq_info {
 struct virtio_pci_device {
 	struct virtio_device vdev;
 	struct pci_dev *pci_dev;
-	struct virtio_pci_legacy_device ldev;
-	struct virtio_pci_modern_device mdev;
-
+	union {
+		struct virtio_pci_legacy_device ldev;
+		struct virtio_pci_modern_device mdev;
+	};
 	bool is_legacy;
 
 	/* Where to read and clear interrupt */

drivers/virtio/virtio_pci_modern_dev.c

@@ -218,21 +218,29 @@ int vp_modern_probe(struct virtio_pci_modern_device *mdev)
 	int err, common, isr, notify, device;
 	u32 notify_length;
 	u32 notify_offset;
+	int devid;
 
 	check_offsets();
 
-	/* We only own devices >= 0x1000 and <= 0x107f: leave the rest. */
-	if (pci_dev->device < 0x1000 || pci_dev->device > 0x107f)
-		return -ENODEV;
-
-	if (pci_dev->device < 0x1040) {
-		/* Transitional devices: use the PCI subsystem device id as
-		 * virtio device id, same as legacy driver always did.
-		 */
-		mdev->id.device = pci_dev->subsystem_device;
+	if (mdev->device_id_check) {
+		devid = mdev->device_id_check(pci_dev);
+		if (devid < 0)
+			return devid;
+		mdev->id.device = devid;
 	} else {
-		/* Modern devices: simply use PCI device id, but start from 0x1040. */
-		mdev->id.device = pci_dev->device - 0x1040;
+		/* We only own devices >= 0x1000 and <= 0x107f: leave the rest. */
+		if (pci_dev->device < 0x1000 || pci_dev->device > 0x107f)
+			return -ENODEV;
+
+		if (pci_dev->device < 0x1040) {
+			/* Transitional devices: use the PCI subsystem device id as
+			 * virtio device id, same as legacy driver always did.
+			 */
+			mdev->id.device = pci_dev->subsystem_device;
+		} else {
+			/* Modern devices: simply use PCI device id, but start from 0x1040. */
+			mdev->id.device = pci_dev->device - 0x1040;
+		}
 	}
 	mdev->id.vendor = pci_dev->subsystem_vendor;
 
@@ -260,7 +268,8 @@ int vp_modern_probe(struct virtio_pci_modern_device *mdev)
 		return -EINVAL;
 	}
 
-	err = dma_set_mask_and_coherent(&pci_dev->dev, DMA_BIT_MASK(64));
+	err = dma_set_mask_and_coherent(&pci_dev->dev,
+					mdev->dma_mask ? : DMA_BIT_MASK(64));
 	if (err)
 		err = dma_set_mask_and_coherent(&pci_dev->dev,
 						DMA_BIT_MASK(32));

drivers/virtio/virtio_vdpa.c

@@ -385,7 +385,9 @@ static int virtio_vdpa_find_vqs(struct virtio_device *vdev, unsigned int nvqs,
 			err = PTR_ERR(vqs[i]);
 			goto err_setup_vq;
 		}
-		ops->set_vq_affinity(vdpa, i, &masks[i]);
+
+		if (ops->set_vq_affinity)
+			ops->set_vq_affinity(vdpa, i, &masks[i]);
 	}
 
 	cb.callback = virtio_vdpa_config_cb;

include/linux/pds/pds_adminq.h

@@ -222,6 +222,27 @@ enum pds_core_lif_type {
 	PDS_CORE_LIF_TYPE_DEFAULT = 0,
 };
 
+#define PDS_CORE_IFNAMSIZ		16
+
+/**
+ * enum pds_core_logical_qtype - Logical Queue Types
+ * @PDS_CORE_QTYPE_ADMINQ:    Administrative Queue
+ * @PDS_CORE_QTYPE_NOTIFYQ:   Notify Queue
+ * @PDS_CORE_QTYPE_RXQ:       Receive Queue
+ * @PDS_CORE_QTYPE_TXQ:       Transmit Queue
+ * @PDS_CORE_QTYPE_EQ:        Event Queue
+ * @PDS_CORE_QTYPE_MAX:       Max queue type supported
+ */
+enum pds_core_logical_qtype {
+	PDS_CORE_QTYPE_ADMINQ  = 0,
+	PDS_CORE_QTYPE_NOTIFYQ = 1,
+	PDS_CORE_QTYPE_RXQ     = 2,
+	PDS_CORE_QTYPE_TXQ     = 3,
+	PDS_CORE_QTYPE_EQ      = 4,
+
+	PDS_CORE_QTYPE_MAX     = 16   /* don't change - used in struct size */
+};
+
 /**
  * union pds_core_lif_config - LIF configuration
  * @state:	    LIF state (enum pds_core_lif_state)
@@ -584,6 +605,219 @@ struct pds_core_q_init_comp {
 	u8     color;
 };
 
+/*
+ * enum pds_vdpa_cmd_opcode - vDPA Device commands
+ */
+enum pds_vdpa_cmd_opcode {
+	PDS_VDPA_CMD_INIT		= 48,
+	PDS_VDPA_CMD_IDENT		= 49,
+	PDS_VDPA_CMD_RESET		= 51,
+	PDS_VDPA_CMD_VQ_RESET		= 52,
+	PDS_VDPA_CMD_VQ_INIT		= 53,
+	PDS_VDPA_CMD_STATUS_UPDATE	= 54,
+	PDS_VDPA_CMD_SET_FEATURES	= 55,
+	PDS_VDPA_CMD_SET_ATTR		= 56,
+};
+
+/**
+ * struct pds_vdpa_cmd - generic command
+ * @opcode:	Opcode
+ * @vdpa_index:	Index for vdpa subdevice
+ * @vf_id:	VF id
+ */
+struct pds_vdpa_cmd {
+	u8     opcode;
+	u8     vdpa_index;
+	__le16 vf_id;
+};
+
+/**
+ * struct pds_vdpa_init_cmd - INIT command
+ * @opcode:	Opcode PDS_VDPA_CMD_INIT
+ * @vdpa_index: Index for vdpa subdevice
+ * @vf_id:	VF id
+ */
+struct pds_vdpa_init_cmd {
+	u8     opcode;
+	u8     vdpa_index;
+	__le16 vf_id;
+};
+
+/**
+ * struct pds_vdpa_ident - vDPA identification data
+ * @hw_features:	vDPA features supported by device
+ * @max_vqs:		max queues available (2 queues for a single queuepair)
+ * @max_qlen:		log(2) of maximum number of descriptors
+ * @min_qlen:		log(2) of minimum number of descriptors
+ *
+ * This struct is used in a DMA block that is set up for the PDS_VDPA_CMD_IDENT
+ * transaction.  Set up the DMA block and send the address in the IDENT cmd
+ * data, the DSC will write the ident information, then we can remove the DMA
+ * block after reading the answer.  If the completion status is 0, then there
+ * is valid information, else there was an error and the data should be invalid.
+ */
+struct pds_vdpa_ident {
+	__le64 hw_features;
+	__le16 max_vqs;
+	__le16 max_qlen;
+	__le16 min_qlen;
+};
+
+/**
+ * struct pds_vdpa_ident_cmd - IDENT command
+ * @opcode:	Opcode PDS_VDPA_CMD_IDENT
+ * @rsvd:       Word boundary padding
+ * @vf_id:	VF id
+ * @len:	length of ident info DMA space
+ * @ident_pa:	address for DMA of ident info (struct pds_vdpa_ident)
+ *			only used for this transaction, then forgotten by DSC
+ */
+struct pds_vdpa_ident_cmd {
+	u8     opcode;
+	u8     rsvd;
+	__le16 vf_id;
+	__le32 len;
+	__le64 ident_pa;
+};
+
+/**
+ * struct pds_vdpa_status_cmd - STATUS_UPDATE command
+ * @opcode:	Opcode PDS_VDPA_CMD_STATUS_UPDATE
+ * @vdpa_index: Index for vdpa subdevice
+ * @vf_id:	VF id
+ * @status:	new status bits
+ */
+struct pds_vdpa_status_cmd {
+	u8     opcode;
+	u8     vdpa_index;
+	__le16 vf_id;
+	u8     status;
+};
+
+/**
+ * enum pds_vdpa_attr - List of VDPA device attributes
+ * @PDS_VDPA_ATTR_MAC:          MAC address
+ * @PDS_VDPA_ATTR_MAX_VQ_PAIRS: Max virtqueue pairs
+ */
+enum pds_vdpa_attr {
+	PDS_VDPA_ATTR_MAC          = 1,
+	PDS_VDPA_ATTR_MAX_VQ_PAIRS = 2,
+};
+
+/**
+ * struct pds_vdpa_setattr_cmd - SET_ATTR command
+ * @opcode:		Opcode PDS_VDPA_CMD_SET_ATTR
+ * @vdpa_index:		Index for vdpa subdevice
+ * @vf_id:		VF id
+ * @attr:		attribute to be changed (enum pds_vdpa_attr)
+ * @pad:		Word boundary padding
+ * @mac:		new mac address to be assigned as vdpa device address
+ * @max_vq_pairs:	new limit of virtqueue pairs
+ */
+struct pds_vdpa_setattr_cmd {
+	u8     opcode;
+	u8     vdpa_index;
+	__le16 vf_id;
+	u8     attr;
+	u8     pad[3];
+	union {
+		u8 mac[6];
+		__le16 max_vq_pairs;
+	} __packed;
+};
+
+/**
+ * struct pds_vdpa_vq_init_cmd - queue init command
+ * @opcode: Opcode PDS_VDPA_CMD_VQ_INIT
+ * @vdpa_index:	Index for vdpa subdevice
+ * @vf_id:	VF id
+ * @qid:	Queue id (bit0 clear = rx, bit0 set = tx, qid=N is ctrlq)
+ * @len:	log(2) of max descriptor count
+ * @desc_addr:	DMA address of descriptor area
+ * @avail_addr:	DMA address of available descriptors (aka driver area)
+ * @used_addr:	DMA address of used descriptors (aka device area)
+ * @intr_index:	interrupt index
+ * @avail_index:	initial device position in available ring
+ * @used_index:	initial device position in used ring
+ */
+struct pds_vdpa_vq_init_cmd {
+	u8     opcode;
+	u8     vdpa_index;
+	__le16 vf_id;
+	__le16 qid;
+	__le16 len;
+	__le64 desc_addr;
+	__le64 avail_addr;
+	__le64 used_addr;
+	__le16 intr_index;
+	__le16 avail_index;
+	__le16 used_index;
+};
+
+/**
+ * struct pds_vdpa_vq_init_comp - queue init completion
+ * @status:	Status of the command (enum pds_core_status_code)
+ * @hw_qtype:	HW queue type, used in doorbell selection
+ * @hw_qindex:	HW queue index, used in doorbell selection
+ * @rsvd:	Word boundary padding
+ * @color:	Color bit
+ */
+struct pds_vdpa_vq_init_comp {
+	u8     status;
+	u8     hw_qtype;
+	__le16 hw_qindex;
+	u8     rsvd[11];
+	u8     color;
+};
+
+/**
+ * struct pds_vdpa_vq_reset_cmd - queue reset command
+ * @opcode:	Opcode PDS_VDPA_CMD_VQ_RESET
+ * @vdpa_index:	Index for vdpa subdevice
+ * @vf_id:	VF id
+ * @qid:	Queue id
+ */
+struct pds_vdpa_vq_reset_cmd {
+	u8     opcode;
+	u8     vdpa_index;
+	__le16 vf_id;
+	__le16 qid;
+};
+
+/**
+ * struct pds_vdpa_vq_reset_comp - queue reset completion
+ * @status:	Status of the command (enum pds_core_status_code)
+ * @rsvd0:	Word boundary padding
+ * @avail_index:	current device position in available ring
+ * @used_index:	current device position in used ring
+ * @rsvd:	Word boundary padding
+ * @color:	Color bit
+ */
+struct pds_vdpa_vq_reset_comp {
+	u8     status;
+	u8     rsvd0;
+	__le16 avail_index;
+	__le16 used_index;
+	u8     rsvd[9];
+	u8     color;
+};
+
+/**
+ * struct pds_vdpa_set_features_cmd - set hw features
+ * @opcode: Opcode PDS_VDPA_CMD_SET_FEATURES
+ * @vdpa_index:	Index for vdpa subdevice
+ * @vf_id:	VF id
+ * @rsvd:       Word boundary padding
+ * @features:	Feature bit mask
+ */
+struct pds_vdpa_set_features_cmd {
+	u8     opcode;
+	u8     vdpa_index;
+	__le16 vf_id;
+	__le32 rsvd;
+	__le64 features;
+};
+
 union pds_core_adminq_cmd {
 	u8     opcode;
 	u8     bytes[64];
@@ -600,6 +834,16 @@ union pds_core_adminq_cmd {
 
 	struct pds_core_q_identify_cmd    q_ident;
 	struct pds_core_q_init_cmd        q_init;
+
+	struct pds_vdpa_cmd		  vdpa;
+	struct pds_vdpa_init_cmd	  vdpa_init;
+	struct pds_vdpa_ident_cmd	  vdpa_ident;
+	struct pds_vdpa_status_cmd	  vdpa_status;
+	struct pds_vdpa_setattr_cmd	  vdpa_setattr;
+	struct pds_vdpa_set_features_cmd  vdpa_set_features;
+	struct pds_vdpa_vq_init_cmd	  vdpa_vq_init;
+	struct pds_vdpa_vq_reset_cmd	  vdpa_vq_reset;
+
 };
 
 union pds_core_adminq_comp {
@@ -621,6 +865,9 @@ union pds_core_adminq_comp {
 
 	struct pds_core_q_identify_comp   q_ident;
 	struct pds_core_q_init_comp       q_init;
+
+	struct pds_vdpa_vq_init_comp	  vdpa_vq_init;
+	struct pds_vdpa_vq_reset_comp	  vdpa_vq_reset;
 };
 
 #ifndef __CHECKER__

include/linux/pds/pds_common.h

@@ -39,26 +39,7 @@ enum pds_core_vif_types {
 #define PDS_DEV_TYPE_RDMA_STR	"RDMA"
 #define PDS_DEV_TYPE_LM_STR	"LM"
 
-#define PDS_CORE_IFNAMSIZ		16
-
-/**
- * enum pds_core_logical_qtype - Logical Queue Types
- * @PDS_CORE_QTYPE_ADMINQ:    Administrative Queue
- * @PDS_CORE_QTYPE_NOTIFYQ:   Notify Queue
- * @PDS_CORE_QTYPE_RXQ:       Receive Queue
- * @PDS_CORE_QTYPE_TXQ:       Transmit Queue
- * @PDS_CORE_QTYPE_EQ:        Event Queue
- * @PDS_CORE_QTYPE_MAX:       Max queue type supported
- */
-enum pds_core_logical_qtype {
-	PDS_CORE_QTYPE_ADMINQ  = 0,
-	PDS_CORE_QTYPE_NOTIFYQ = 1,
-	PDS_CORE_QTYPE_RXQ     = 2,
-	PDS_CORE_QTYPE_TXQ     = 3,
-	PDS_CORE_QTYPE_EQ      = 4,
-
-	PDS_CORE_QTYPE_MAX     = 16   /* don't change - used in struct size */
-};
+#define PDS_VDPA_DEV_NAME	PDS_CORE_DRV_NAME "." PDS_DEV_TYPE_VDPA_STR
 
 int pdsc_register_notify(struct notifier_block *nb);
 void pdsc_unregister_notify(struct notifier_block *nb);

include/linux/virtio.h

@@ -103,6 +103,7 @@ int virtqueue_resize(struct virtqueue *vq, u32 num,
  * @config_enabled: configuration change reporting enabled
  * @config_change_pending: configuration change reported while disabled
  * @config_lock: protects configuration change reporting
+ * @vqs_list_lock: protects @vqs.
  * @dev: underlying device.
  * @id: the device type identification (used to match it with a driver).
  * @config: the configuration ops for this device.
@@ -117,7 +118,7 @@ struct virtio_device {
 	bool config_enabled;
 	bool config_change_pending;
 	spinlock_t config_lock;
-	spinlock_t vqs_list_lock; /* Protects VQs list access */
+	spinlock_t vqs_list_lock;
 	struct device dev;
 	struct virtio_device_id id;
 	const struct virtio_config_ops *config;
@@ -160,6 +161,8 @@ size_t virtio_max_dma_size(const struct virtio_device *vdev);
  * @feature_table_size: number of entries in the feature table array.
  * @feature_table_legacy: same as feature_table but when working in legacy mode.
  * @feature_table_size_legacy: number of entries in feature table legacy array.
+ * @validate: the function to call to validate features and config space.
+ *            Returns 0 or -errno.
  * @probe: the function to call when a device is found.  Returns 0 or -errno.
  * @scan: optional function to call after successful probe; intended
  *    for virtio-scsi to invoke a scan.

include/linux/virtio_pci_modern.h

@@ -38,6 +38,12 @@ struct virtio_pci_modern_device {
 	int modern_bars;
 
 	struct virtio_device_id id;
+
+	/* optional check for vendor virtio device, returns dev_id or -ERRNO */
+	int (*device_id_check)(struct pci_dev *pdev);
+
+	/* optional mask for devices with limited DMA space */
+	u64 dma_mask;
 };
 
 /*

include/uapi/linux/vhost.h

@@ -45,6 +45,25 @@
 #define VHOST_SET_LOG_BASE _IOW(VHOST_VIRTIO, 0x04, __u64)
 /* Specify an eventfd file descriptor to signal on log write. */
 #define VHOST_SET_LOG_FD _IOW(VHOST_VIRTIO, 0x07, int)
+/* By default, a device gets one vhost_worker that its virtqueues share. This
+ * command allows the owner of the device to create an additional vhost_worker
+ * for the device. It can later be bound to 1 or more of its virtqueues using
+ * the VHOST_ATTACH_VRING_WORKER command.
+ *
+ * This must be called after VHOST_SET_OWNER and the caller must be the owner
+ * of the device. The new thread will inherit caller's cgroups and namespaces,
+ * and will share the caller's memory space. The new thread will also be
+ * counted against the caller's RLIMIT_NPROC value.
+ *
+ * The worker's ID used in other commands will be returned in
+ * vhost_worker_state.
+ */
+#define VHOST_NEW_WORKER _IOR(VHOST_VIRTIO, 0x8, struct vhost_worker_state)
+/* Free a worker created with VHOST_NEW_WORKER if it's not attached to any
+ * virtqueue. If userspace is not able to call this for workers its created,
+ * the kernel will free all the device's workers when the device is closed.
+ */
+#define VHOST_FREE_WORKER _IOW(VHOST_VIRTIO, 0x9, struct vhost_worker_state)
 
 /* Ring setup. */
 /* Set number of descriptors in ring. This parameter can not
@@ -70,6 +89,18 @@
 #define VHOST_VRING_BIG_ENDIAN 1
 #define VHOST_SET_VRING_ENDIAN _IOW(VHOST_VIRTIO, 0x13, struct vhost_vring_state)
 #define VHOST_GET_VRING_ENDIAN _IOW(VHOST_VIRTIO, 0x14, struct vhost_vring_state)
+/* Attach a vhost_worker created with VHOST_NEW_WORKER to one of the device's
+ * virtqueues.
+ *
+ * This will replace the virtqueue's existing worker. If the replaced worker
+ * is no longer attached to any virtqueues, it can be freed with
+ * VHOST_FREE_WORKER.
+ */
+#define VHOST_ATTACH_VRING_WORKER _IOW(VHOST_VIRTIO, 0x15,		\
+				       struct vhost_vring_worker)
+/* Return the vring worker's ID */
+#define VHOST_GET_VRING_WORKER _IOWR(VHOST_VIRTIO, 0x16,		\
+				     struct vhost_vring_worker)
 
 /* The following ioctls use eventfd file descriptors to signal and poll
  * for events. */

include/uapi/linux/vhost_types.h

@@ -47,6 +47,22 @@ struct vhost_vring_addr {
 	__u64 log_guest_addr;
 };
 
+struct vhost_worker_state {
+	/*
+	 * For VHOST_NEW_WORKER the kernel will return the new vhost_worker id.
+	 * For VHOST_FREE_WORKER this must be set to the id of the vhost_worker
+	 * to free.
+	 */
+	unsigned int worker_id;
+};
+
+struct vhost_vring_worker {
+	/* vring index */
+	unsigned int index;
+	/* The id of the vhost_worker returned from VHOST_NEW_WORKER */
+	unsigned int worker_id;
+};
+
 /* no alignment requirement */
 struct vhost_iotlb_msg {
 	__u64 iova;

tools/virtio/Makefile

@@ -4,7 +4,18 @@ test: virtio_test vringh_test
 virtio_test: virtio_ring.o virtio_test.o
 vringh_test: vringh_test.o vringh.o virtio_ring.o
 
-CFLAGS += -g -O2 -Werror -Wno-maybe-uninitialized -Wall -I. -I../include/ -I ../../usr/include/ -Wno-pointer-sign -fno-strict-overflow -fno-strict-aliasing -fno-common -MMD -U_FORTIFY_SOURCE -include ../../include/linux/kconfig.h -mfunction-return=thunk -fcf-protection=none -mindirect-branch-register
+try-run = $(shell set -e;		\
+	if ($(1)) >/dev/null 2>&1;	\
+	then echo "$(2)";		\
+	else echo "$(3)";		\
+	fi)
+
+__cc-option = $(call try-run,\
+	$(1) -Werror $(2) -c -x c /dev/null -o /dev/null,$(2),)
+cc-option = $(call __cc-option, $(CC),$(1))
+
+CFLAGS += -g -O2 -Werror -Wno-maybe-uninitialized -Wall -I. -I../include/ -I ../../usr/include/ -Wno-pointer-sign -fno-strict-overflow -fno-strict-aliasing -fno-common -MMD -U_FORTIFY_SOURCE -include ../../include/linux/kconfig.h $(call cc-option,-mfunction-return=thunk) $(call cc-option,-fcf-protection=none) $(call cc-option,-mindirect-branch-register)
+
 CFLAGS += -pthread
 LDFLAGS += -pthread
 vpath %.c ../../drivers/virtio ../../drivers/vhost