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

Pull virtio updates from Michael Tsirkin:

 - IRQ bypass support for vdpa and IFC

 - MLX5 vdpa driver

 - Endianness fixes for virtio drivers

 - Misc other fixes

* tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost: (71 commits)
  vdpa/mlx5: fix up endian-ness for mtu
  vdpa: Fix pointer math bug in vdpasim_get_config()
  vdpa/mlx5: Fix pointer math in mlx5_vdpa_get_config()
  vdpa/mlx5: fix memory allocation failure checks
  vdpa/mlx5: Fix uninitialised variable in core/mr.c
  vdpa_sim: init iommu lock
  virtio_config: fix up warnings on parisc
  vdpa/mlx5: Add VDPA driver for supported mlx5 devices
  vdpa/mlx5: Add shared memory registration code
  vdpa/mlx5: Add support library for mlx5 VDPA implementation
  vdpa/mlx5: Add hardware descriptive header file
  vdpa: Modify get_vq_state() to return error code
  net/vdpa: Use struct for set/get vq state
  vdpa: remove hard coded virtq num
  vdpasim: support batch updating
  vhost-vdpa: support IOTLB batching hints
  vhost-vdpa: support get/set backend features
  vhost: generialize backend features setting/getting
  vhost-vdpa: refine ioctl pre-processing
  vDPA: dont change vq irq after DRIVER_OK
  ...

arch/um/drivers/virtio_uml.c

@@ -385,7 +385,7 @@ static irqreturn_t vu_req_interrupt(int irq, void *data)
 		}
 		break;
 	case VHOST_USER_SLAVE_IOTLB_MSG:
-		/* not supported - VIRTIO_F_IOMMU_PLATFORM */
+		/* not supported - VIRTIO_F_ACCESS_PLATFORM */
 	case VHOST_USER_SLAVE_VRING_HOST_NOTIFIER_MSG:
 		/* not supported - VHOST_USER_PROTOCOL_F_HOST_NOTIFIER */
 	default:

arch/x86/kvm/x86.c

@@ -10667,11 +10667,17 @@ int kvm_arch_irq_bypass_add_producer(struct irq_bypass_consumer *cons,
 {
 	struct kvm_kernel_irqfd *irqfd =
 		container_of(cons, struct kvm_kernel_irqfd, consumer);
+	int ret;
 
 	irqfd->producer = prod;
-
-	return kvm_x86_ops.update_pi_irte(irqfd->kvm,
+	kvm_arch_start_assignment(irqfd->kvm);
+	ret = kvm_x86_ops.update_pi_irte(irqfd->kvm,
 					 prod->irq, irqfd->gsi, 1);
+
+	if (ret)
+		kvm_arch_end_assignment(irqfd->kvm);
+
+	return ret;
 }
 
 void kvm_arch_irq_bypass_del_producer(struct irq_bypass_consumer *cons,
@@ -10694,6 +10700,8 @@ void kvm_arch_irq_bypass_del_producer(struct irq_bypass_consumer *cons,
 	if (ret)
 		printk(KERN_INFO "irq bypass consumer (token %p) unregistration"
 		       " fails: %d\n", irqfd->consumer.token, ret);
+
+	kvm_arch_end_assignment(irqfd->kvm);
 }
 
 int kvm_arch_update_irqfd_routing(struct kvm *kvm, unsigned int host_irq,

drivers/crypto/virtio/virtio_crypto_core.c

@@ -204,7 +204,7 @@ static int virtcrypto_update_status(struct virtio_crypto *vcrypto)
 	u32 status;
 	int err;
 
-	virtio_cread(vcrypto->vdev,
+	virtio_cread_le(vcrypto->vdev,
 			struct virtio_crypto_config, status, &status);
 
 	/*
@@ -323,30 +323,30 @@ static int virtcrypto_probe(struct virtio_device *vdev)
 	if (!vcrypto)
 		return -ENOMEM;
 
-	virtio_cread(vdev, struct virtio_crypto_config,
+	virtio_cread_le(vdev, struct virtio_crypto_config,
 			max_dataqueues, &max_data_queues);
 	if (max_data_queues < 1)
 		max_data_queues = 1;
 
-	virtio_cread(vdev, struct virtio_crypto_config,
+	virtio_cread_le(vdev, struct virtio_crypto_config,
 			max_cipher_key_len, &max_cipher_key_len);
-	virtio_cread(vdev, struct virtio_crypto_config,
+	virtio_cread_le(vdev, struct virtio_crypto_config,
 			max_auth_key_len, &max_auth_key_len);
-	virtio_cread(vdev, struct virtio_crypto_config,
+	virtio_cread_le(vdev, struct virtio_crypto_config,
 			max_size, &max_size);
-	virtio_cread(vdev, struct virtio_crypto_config,
+	virtio_cread_le(vdev, struct virtio_crypto_config,
 			crypto_services, &crypto_services);
-	virtio_cread(vdev, struct virtio_crypto_config,
+	virtio_cread_le(vdev, struct virtio_crypto_config,
 			cipher_algo_l, &cipher_algo_l);
-	virtio_cread(vdev, struct virtio_crypto_config,
+	virtio_cread_le(vdev, struct virtio_crypto_config,
 			cipher_algo_h, &cipher_algo_h);
-	virtio_cread(vdev, struct virtio_crypto_config,
+	virtio_cread_le(vdev, struct virtio_crypto_config,
 			hash_algo, &hash_algo);
-	virtio_cread(vdev, struct virtio_crypto_config,
+	virtio_cread_le(vdev, struct virtio_crypto_config,
 			mac_algo_l, &mac_algo_l);
-	virtio_cread(vdev, struct virtio_crypto_config,
+	virtio_cread_le(vdev, struct virtio_crypto_config,
 			mac_algo_h, &mac_algo_h);
-	virtio_cread(vdev, struct virtio_crypto_config,
+	virtio_cread_le(vdev, struct virtio_crypto_config,
 			aead_algo, &aead_algo);
 
 	/* Add virtio crypto device to global table */

drivers/gpu/drm/virtio/virtgpu_kms.c

@@ -39,7 +39,7 @@ static void virtio_gpu_config_changed_work_func(struct work_struct *work)
 	u32 events_read, events_clear = 0;
 
 	/* read the config space */
-	virtio_cread(vgdev->vdev, struct virtio_gpu_config,
+	virtio_cread_le(vgdev->vdev, struct virtio_gpu_config,
 			events_read, &events_read);
 	if (events_read & VIRTIO_GPU_EVENT_DISPLAY) {
 		if (vgdev->has_edid)
@@ -49,7 +49,7 @@ static void virtio_gpu_config_changed_work_func(struct work_struct *work)
 		drm_helper_hpd_irq_event(vgdev->ddev);
 		events_clear |= VIRTIO_GPU_EVENT_DISPLAY;
 	}
-	virtio_cwrite(vgdev->vdev, struct virtio_gpu_config,
+	virtio_cwrite_le(vgdev->vdev, struct virtio_gpu_config,
 			 events_clear, &events_clear);
 }
 
@@ -165,7 +165,7 @@ int virtio_gpu_init(struct drm_device *dev)
 	}
 
 	/* get display info */
-	virtio_cread(vgdev->vdev, struct virtio_gpu_config,
+	virtio_cread_le(vgdev->vdev, struct virtio_gpu_config,
 			num_scanouts, &num_scanouts);
 	vgdev->num_scanouts = min_t(uint32_t, num_scanouts,
 				    VIRTIO_GPU_MAX_SCANOUTS);
@@ -176,7 +176,7 @@ int virtio_gpu_init(struct drm_device *dev)
 	}
 	DRM_INFO("number of scanouts: %d\n", num_scanouts);
 
-	virtio_cread(vgdev->vdev, struct virtio_gpu_config,
+	virtio_cread_le(vgdev->vdev, struct virtio_gpu_config,
 			num_capsets, &num_capsets);
 	DRM_INFO("number of cap sets: %d\n", num_capsets);
 

drivers/gpu/drm/virtio/virtgpu_object.c

@@ -141,7 +141,7 @@ static int virtio_gpu_object_shmem_init(struct virtio_gpu_device *vgdev,
 					struct virtio_gpu_mem_entry **ents,
 					unsigned int *nents)
 {
-	bool use_dma_api = !virtio_has_iommu_quirk(vgdev->vdev);
+	bool use_dma_api = !virtio_has_dma_quirk(vgdev->vdev);
 	struct virtio_gpu_object_shmem *shmem = to_virtio_gpu_shmem(bo);
 	struct scatterlist *sg;
 	int si, ret;

drivers/gpu/drm/virtio/virtgpu_vq.c

@@ -599,7 +599,7 @@ void virtio_gpu_cmd_transfer_to_host_2d(struct virtio_gpu_device *vgdev,
 	struct virtio_gpu_object *bo = gem_to_virtio_gpu_obj(objs->objs[0]);
 	struct virtio_gpu_transfer_to_host_2d *cmd_p;
 	struct virtio_gpu_vbuffer *vbuf;
-	bool use_dma_api = !virtio_has_iommu_quirk(vgdev->vdev);
+	bool use_dma_api = !virtio_has_dma_quirk(vgdev->vdev);
 	struct virtio_gpu_object_shmem *shmem = to_virtio_gpu_shmem(bo);
 
 	if (use_dma_api)
@@ -1015,7 +1015,7 @@ void virtio_gpu_cmd_transfer_to_host_3d(struct virtio_gpu_device *vgdev,
 	struct virtio_gpu_object *bo = gem_to_virtio_gpu_obj(objs->objs[0]);
 	struct virtio_gpu_transfer_host_3d *cmd_p;
 	struct virtio_gpu_vbuffer *vbuf;
-	bool use_dma_api = !virtio_has_iommu_quirk(vgdev->vdev);
+	bool use_dma_api = !virtio_has_dma_quirk(vgdev->vdev);
 	struct virtio_gpu_object_shmem *shmem = to_virtio_gpu_shmem(bo);
 
 	if (use_dma_api)

drivers/iommu/virtio-iommu.c

@@ -1010,7 +1010,7 @@ static int viommu_probe(struct virtio_device *vdev)
 	if (ret)
 		return ret;
 
-	virtio_cread(vdev, struct virtio_iommu_config, page_size_mask,
+	virtio_cread_le(vdev, struct virtio_iommu_config, page_size_mask,
 			&viommu->pgsize_bitmap);
 
 	if (!viommu->pgsize_bitmap) {
@@ -1022,23 +1022,23 @@ static int viommu_probe(struct virtio_device *vdev)
 	viommu->last_domain = ~0U;
 
 	/* Optional features */
-	virtio_cread_feature(vdev, VIRTIO_IOMMU_F_INPUT_RANGE,
+	virtio_cread_le_feature(vdev, VIRTIO_IOMMU_F_INPUT_RANGE,
 				struct virtio_iommu_config, input_range.start,
 				&input_start);
 
-	virtio_cread_feature(vdev, VIRTIO_IOMMU_F_INPUT_RANGE,
+	virtio_cread_le_feature(vdev, VIRTIO_IOMMU_F_INPUT_RANGE,
 				struct virtio_iommu_config, input_range.end,
 				&input_end);
 
-	virtio_cread_feature(vdev, VIRTIO_IOMMU_F_DOMAIN_RANGE,
+	virtio_cread_le_feature(vdev, VIRTIO_IOMMU_F_DOMAIN_RANGE,
 				struct virtio_iommu_config, domain_range.start,
 				&viommu->first_domain);
 
-	virtio_cread_feature(vdev, VIRTIO_IOMMU_F_DOMAIN_RANGE,
+	virtio_cread_le_feature(vdev, VIRTIO_IOMMU_F_DOMAIN_RANGE,
 				struct virtio_iommu_config, domain_range.end,
 				&viommu->last_domain);
 
-	virtio_cread_feature(vdev, VIRTIO_IOMMU_F_PROBE,
+	virtio_cread_le_feature(vdev, VIRTIO_IOMMU_F_PROBE,
 				struct virtio_iommu_config, probe_size,
 				&viommu->probe_size);
 

drivers/net/virtio_net.c

@@ -2264,12 +2264,13 @@ static void virtnet_update_settings(struct virtnet_info *vi)
 	if (!virtio_has_feature(vi->vdev, VIRTIO_NET_F_SPEED_DUPLEX))
 		return;
 
-	speed = virtio_cread32(vi->vdev, offsetof(struct virtio_net_config,
-						  speed));
+	virtio_cread_le(vi->vdev, struct virtio_net_config, speed, &speed);
+
 	if (ethtool_validate_speed(speed))
 		vi->speed = speed;
-	duplex = virtio_cread8(vi->vdev, offsetof(struct virtio_net_config,
-						  duplex));
+
+	virtio_cread_le(vi->vdev, struct virtio_net_config, duplex, &duplex);
+
 	if (ethtool_validate_duplex(duplex))
 		vi->duplex = duplex;
 }

drivers/nvdimm/virtio_pmem.c

@@ -58,9 +58,9 @@ static int virtio_pmem_probe(struct virtio_device *vdev)
 		goto out_err;
 	}
 
-	virtio_cread(vpmem->vdev, struct virtio_pmem_config,
+	virtio_cread_le(vpmem->vdev, struct virtio_pmem_config,
 			start, &vpmem->start);
-	virtio_cread(vpmem->vdev, struct virtio_pmem_config,
+	virtio_cread_le(vpmem->vdev, struct virtio_pmem_config,
 			size, &vpmem->size);
 
 	res.start = vpmem->start;

drivers/platform/mellanox/mlxbf-tmfifo.c

@@ -625,7 +625,10 @@ static void mlxbf_tmfifo_rxtx_header(struct mlxbf_tmfifo_vring *vring,
 			vdev_id = VIRTIO_ID_NET;
 			hdr_len = sizeof(struct virtio_net_hdr);
 			config = &fifo->vdev[vdev_id]->config.net;
-			if (ntohs(hdr.len) > config->mtu +
+			/* A legacy-only interface for now. */
+			if (ntohs(hdr.len) >
+			    __virtio16_to_cpu(virtio_legacy_is_little_endian(),
+					      config->mtu) +
 			    MLXBF_TMFIFO_NET_L2_OVERHEAD)
 				return;
 		} else {
@@ -1231,8 +1234,12 @@ static int mlxbf_tmfifo_probe(struct platform_device *pdev)
 
 	/* Create the network vdev. */
 	memset(&net_config, 0, sizeof(net_config));
-	net_config.mtu = ETH_DATA_LEN;
-	net_config.status = VIRTIO_NET_S_LINK_UP;
+
+	/* A legacy-only interface for now. */
+	net_config.mtu = __cpu_to_virtio16(virtio_legacy_is_little_endian(),
+					   ETH_DATA_LEN);
+	net_config.status = __cpu_to_virtio16(virtio_legacy_is_little_endian(),
+					      VIRTIO_NET_S_LINK_UP);
 	mlxbf_tmfifo_get_cfg_mac(net_config.mac);
 	rc = mlxbf_tmfifo_create_vdev(dev, fifo, VIRTIO_ID_NET,
 				      MLXBF_TMFIFO_NET_FEATURES, &net_config,

drivers/scsi/virtio_scsi.c

@@ -754,14 +754,14 @@ static struct scsi_host_template virtscsi_host_template = {
 
 #define virtscsi_config_get(vdev, fld) \
 	({ \
-		typeof(((struct virtio_scsi_config *)0)->fld) __val; \
+		__virtio_native_type(struct virtio_scsi_config, fld) __val; \
 		virtio_cread(vdev, struct virtio_scsi_config, fld, &__val); \
 		__val; \
 	})
 
 #define virtscsi_config_set(vdev, fld, val) \
 	do { \
-		typeof(((struct virtio_scsi_config *)0)->fld) __val = (val); \
+		__virtio_native_type(struct virtio_scsi_config, fld) __val = (val); \
 		virtio_cwrite(vdev, struct virtio_scsi_config, fld, &__val); \
 	} while(0)
 

drivers/vdpa/Kconfig

@@ -29,4 +29,23 @@ config IFCVF
 	  To compile this driver as a module, choose M here: the module will
 	  be called ifcvf.
 
+config MLX5_VDPA
+	bool "MLX5 VDPA support library for ConnectX devices"
+	depends on MLX5_CORE
+	default n
+	help
+	  Support library for Mellanox VDPA drivers. Provides code that is
+	  common for all types of VDPA drivers. The following drivers are planned:
+	  net, block.
+
+config MLX5_VDPA_NET
+	tristate "vDPA driver for ConnectX devices"
+	depends on MLX5_VDPA
+	default n
+	help
+	  VDPA network driver for ConnectX6 and newer. Provides offloading
+	  of virtio net datapath such that descriptors put on the ring will
+	  be executed by the hardware. It also supports a variety of stateless
+	  offloads depending on the actual device used and firmware version.
+
 endif # VDPA

drivers/vdpa/Makefile

@@ -2,3 +2,4 @@
 obj-$(CONFIG_VDPA) += vdpa.o
 obj-$(CONFIG_VDPA_SIM) += vdpa_sim/
 obj-$(CONFIG_IFCVF)    += ifcvf/
+obj-$(CONFIG_MLX5_VDPA) += mlx5/

drivers/vdpa/ifcvf/ifcvf_base.c

@@ -272,7 +272,7 @@ static int ifcvf_config_features(struct ifcvf_hw *hw)
 	return 0;
 }
 
-u64 ifcvf_get_vq_state(struct ifcvf_hw *hw, u16 qid)
+u16 ifcvf_get_vq_state(struct ifcvf_hw *hw, u16 qid)
 {
 	struct ifcvf_lm_cfg __iomem *ifcvf_lm;
 	void __iomem *avail_idx_addr;
@@ -287,7 +287,7 @@ u64 ifcvf_get_vq_state(struct ifcvf_hw *hw, u16 qid)
 	return last_avail_idx;
 }
 
-int ifcvf_set_vq_state(struct ifcvf_hw *hw, u16 qid, u64 num)
+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;

drivers/vdpa/ifcvf/ifcvf_base.h

@@ -29,7 +29,7 @@
 		 (1ULL << VIRTIO_F_VERSION_1)			| \
 		 (1ULL << VIRTIO_NET_F_STATUS)			| \
 		 (1ULL << VIRTIO_F_ORDER_PLATFORM)		| \
-		 (1ULL << VIRTIO_F_IOMMU_PLATFORM)		| \
+		 (1ULL << VIRTIO_F_ACCESS_PLATFORM)		| \
 		 (1ULL << VIRTIO_NET_F_MRG_RXBUF))
 
 /* Only one queue pair for now. */
@@ -116,7 +116,7 @@ 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_vq_state(struct ifcvf_hw *hw, u16 qid);
-int ifcvf_set_vq_state(struct ifcvf_hw *hw, u16 qid, u64 num);
+u16 ifcvf_get_vq_state(struct ifcvf_hw *hw, u16 qid);
+int ifcvf_set_vq_state(struct ifcvf_hw *hw, u16 qid, u16 num);
 struct ifcvf_adapter *vf_to_adapter(struct ifcvf_hw *hw);
 #endif /* _IFCVF_H_ */

drivers/vdpa/ifcvf/ifcvf_main.c

@@ -50,8 +50,10 @@ static void ifcvf_free_irq(struct ifcvf_adapter *adapter, int queues)
 	int i;
 
 
-	for (i = 0; i < queues; i++)
+	for (i = 0; i < queues; i++) {
 		devm_free_irq(&pdev->dev, vf->vring[i].irq, &vf->vring[i]);
+		vf->vring[i].irq = -EINVAL;
+	}
 
 	ifcvf_free_irq_vectors(pdev);
 }
@@ -235,19 +237,21 @@ static u16 ifcvf_vdpa_get_vq_num_max(struct vdpa_device *vdpa_dev)
 	return IFCVF_QUEUE_MAX;
 }
 
-static u64 ifcvf_vdpa_get_vq_state(struct vdpa_device *vdpa_dev, u16 qid)
+static int ifcvf_vdpa_get_vq_state(struct vdpa_device *vdpa_dev, u16 qid,
+				   struct vdpa_vq_state *state)
 {
 	struct ifcvf_hw *vf = vdpa_to_vf(vdpa_dev);
 
-	return ifcvf_get_vq_state(vf, qid);
+	state->avail_index = ifcvf_get_vq_state(vf, qid);
+	return 0;
 }
 
 static int ifcvf_vdpa_set_vq_state(struct vdpa_device *vdpa_dev, u16 qid,
-				   u64 num)
+				   const struct vdpa_vq_state *state)
 {
 	struct ifcvf_hw *vf = vdpa_to_vf(vdpa_dev);
 
-	return ifcvf_set_vq_state(vf, qid, num);
+	return ifcvf_set_vq_state(vf, qid, state->avail_index);
 }
 
 static void ifcvf_vdpa_set_vq_cb(struct vdpa_device *vdpa_dev, u16 qid,
@@ -352,6 +356,14 @@ static void ifcvf_vdpa_set_config_cb(struct vdpa_device *vdpa_dev,
 	vf->config_cb.private = cb->private;
 }
 
+static int ifcvf_vdpa_get_vq_irq(struct vdpa_device *vdpa_dev,
+				 u16 qid)
+{
+	struct ifcvf_hw *vf = vdpa_to_vf(vdpa_dev);
+
+	return vf->vring[qid].irq;
+}
+
 /*
  * IFCVF currently does't have on-chip IOMMU, so not
  * implemented set_map()/dma_map()/dma_unmap()
@@ -369,6 +381,7 @@ static const struct vdpa_config_ops ifc_vdpa_ops = {
 	.get_vq_ready	= ifcvf_vdpa_get_vq_ready,
 	.set_vq_num	= ifcvf_vdpa_set_vq_num,
 	.set_vq_address	= ifcvf_vdpa_set_vq_address,
+	.get_vq_irq	= ifcvf_vdpa_get_vq_irq,
 	.kick_vq	= ifcvf_vdpa_kick_vq,
 	.get_generation	= ifcvf_vdpa_get_generation,
 	.get_device_id	= ifcvf_vdpa_get_device_id,
@@ -384,7 +397,7 @@ static int ifcvf_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	struct device *dev = &pdev->dev;
 	struct ifcvf_adapter *adapter;
 	struct ifcvf_hw *vf;
-	int ret;
+	int ret, i;
 
 	ret = pcim_enable_device(pdev);
 	if (ret) {
@@ -420,7 +433,8 @@ static int ifcvf_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	}
 
 	adapter = vdpa_alloc_device(struct ifcvf_adapter, vdpa,
-				    dev, &ifc_vdpa_ops);
+				    dev, &ifc_vdpa_ops,
+				    IFCVF_MAX_QUEUE_PAIRS * 2);
 	if (adapter == NULL) {
 		IFCVF_ERR(pdev, "Failed to allocate vDPA structure");
 		return -ENOMEM;
@@ -441,6 +455,9 @@ static int ifcvf_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		goto err;
 	}
 
+	for (i = 0; i < IFCVF_MAX_QUEUE_PAIRS * 2; i++)
+		vf->vring[i].irq = -EINVAL;
+
 	ret = vdpa_register_device(&adapter->vdpa);
 	if (ret) {
 		IFCVF_ERR(pdev, "Failed to register ifcvf to vdpa bus");

drivers/vdpa/mlx5/Makefile

+subdir-ccflags-y += -I$(srctree)/drivers/vdpa/mlx5/core
+
+obj-$(CONFIG_MLX5_VDPA_NET) += mlx5_vdpa.o
+mlx5_vdpa-$(CONFIG_MLX5_VDPA_NET) += net/main.o net/mlx5_vnet.o core/resources.o core/mr.o

drivers/vdpa/mlx5/core/mlx5_vdpa.h

+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2020 Mellanox Technologies Ltd. */
+
+#ifndef __MLX5_VDPA_H__
+#define __MLX5_VDPA_H__
+
+#include <linux/vdpa.h>
+#include <linux/mlx5/driver.h>
+
+struct mlx5_vdpa_direct_mr {
+	u64 start;
+	u64 end;
+	u32 perm;
+	struct mlx5_core_mkey mr;
+	struct sg_table sg_head;
+	int log_size;
+	int nsg;
+	struct list_head list;
+	u64 offset;
+};
+
+struct mlx5_vdpa_mr {
+	struct mlx5_core_mkey mkey;
+
+	/* list of direct MRs descendants of this indirect mr */
+	struct list_head head;
+	unsigned long num_directs;
+	unsigned long num_klms;
+	bool initialized;
+
+	/* serialize mkey creation and destruction */
+	struct mutex mkey_mtx;
+};
+
+struct mlx5_vdpa_resources {
+	u32 pdn;
+	struct mlx5_uars_page *uar;
+	void __iomem *kick_addr;
+	u16 uid;
+	u32 null_mkey;
+	bool valid;
+};
+
+struct mlx5_vdpa_dev {
+	struct vdpa_device vdev;
+	struct mlx5_core_dev *mdev;
+	struct mlx5_vdpa_resources res;
+
+	u64 mlx_features;
+	u64 actual_features;
+	u8 status;
+	u32 max_vqs;
+	u32 generation;
+
+	struct mlx5_vdpa_mr mr;
+};
+
+int mlx5_vdpa_alloc_pd(struct mlx5_vdpa_dev *dev, u32 *pdn, u16 uid);
+int mlx5_vdpa_dealloc_pd(struct mlx5_vdpa_dev *dev, u32 pdn, u16 uid);
+int mlx5_vdpa_get_null_mkey(struct mlx5_vdpa_dev *dev, u32 *null_mkey);
+int mlx5_vdpa_create_tis(struct mlx5_vdpa_dev *mvdev, void *in, u32 *tisn);
+void mlx5_vdpa_destroy_tis(struct mlx5_vdpa_dev *mvdev, u32 tisn);
+int mlx5_vdpa_create_rqt(struct mlx5_vdpa_dev *mvdev, void *in, int inlen, u32 *rqtn);
+void mlx5_vdpa_destroy_rqt(struct mlx5_vdpa_dev *mvdev, u32 rqtn);
+int mlx5_vdpa_create_tir(struct mlx5_vdpa_dev *mvdev, void *in, u32 *tirn);
+void mlx5_vdpa_destroy_tir(struct mlx5_vdpa_dev *mvdev, u32 tirn);
+int mlx5_vdpa_alloc_transport_domain(struct mlx5_vdpa_dev *mvdev, u32 *tdn);
+void mlx5_vdpa_dealloc_transport_domain(struct mlx5_vdpa_dev *mvdev, u32 tdn);
+int mlx5_vdpa_alloc_resources(struct mlx5_vdpa_dev *mvdev);
+void mlx5_vdpa_free_resources(struct mlx5_vdpa_dev *mvdev);
+int mlx5_vdpa_create_mkey(struct mlx5_vdpa_dev *mvdev, struct mlx5_core_mkey *mkey, u32 *in,
+			  int inlen);
+int mlx5_vdpa_destroy_mkey(struct mlx5_vdpa_dev *mvdev, struct mlx5_core_mkey *mkey);
+int mlx5_vdpa_handle_set_map(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb,
+			     bool *change_map);
+int mlx5_vdpa_create_mr(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb);
+void mlx5_vdpa_destroy_mr(struct mlx5_vdpa_dev *mvdev);
+
+#define mlx5_vdpa_warn(__dev, format, ...)                                                         \
+	dev_warn((__dev)->mdev->device, "%s:%d:(pid %d) warning: " format, __func__, __LINE__,     \
+		 current->pid, ##__VA_ARGS__)
+
+#define mlx5_vdpa_info(__dev, format, ...)                                                         \
+	dev_info((__dev)->mdev->device, "%s:%d:(pid %d): " format, __func__, __LINE__,             \
+		 current->pid, ##__VA_ARGS__)
+
+#define mlx5_vdpa_dbg(__dev, format, ...)                                                          \
+	dev_debug((__dev)->mdev->device, "%s:%d:(pid %d): " format, __func__, __LINE__,            \
+		  current->pid, ##__VA_ARGS__)
+
+#endif /* __MLX5_VDPA_H__ */

drivers/vdpa/mlx5/core/mlx5_vdpa_ifc.h

+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2020 Mellanox Technologies Ltd. */
+
+#ifndef __MLX5_VDPA_IFC_H_
+#define __MLX5_VDPA_IFC_H_
+
+#include <linux/mlx5/mlx5_ifc.h>
+
+enum {
+	MLX5_VIRTIO_Q_EVENT_MODE_NO_MSIX_MODE  = 0x0,
+	MLX5_VIRTIO_Q_EVENT_MODE_QP_MODE       = 0x1,
+	MLX5_VIRTIO_Q_EVENT_MODE_MSIX_MODE     = 0x2,
+};
+
+enum {
+	MLX5_VIRTIO_EMULATION_CAP_VIRTIO_QUEUE_TYPE_SPLIT   = 0x1, // do I check this caps?
+	MLX5_VIRTIO_EMULATION_CAP_VIRTIO_QUEUE_TYPE_PACKED  = 0x2,
+};
+
+enum {
+	MLX5_VIRTIO_EMULATION_VIRTIO_QUEUE_TYPE_SPLIT   = 0,
+	MLX5_VIRTIO_EMULATION_VIRTIO_QUEUE_TYPE_PACKED  = 1,
+};
+
+struct mlx5_ifc_virtio_q_bits {
+	u8    virtio_q_type[0x8];
+	u8    reserved_at_8[0x5];
+	u8    event_mode[0x3];
+	u8    queue_index[0x10];
+
+	u8    full_emulation[0x1];
+	u8    virtio_version_1_0[0x1];
+	u8    reserved_at_22[0x2];
+	u8    offload_type[0x4];
+	u8    event_qpn_or_msix[0x18];
+
+	u8    doorbell_stride_index[0x10];
+	u8    queue_size[0x10];
+
+	u8    device_emulation_id[0x20];
+
+	u8    desc_addr[0x40];
+
+	u8    used_addr[0x40];
+
+	u8    available_addr[0x40];
+
+	u8    virtio_q_mkey[0x20];
+
+	u8    max_tunnel_desc[0x10];
+	u8    reserved_at_170[0x8];
+	u8    error_type[0x8];
+
+	u8    umem_1_id[0x20];
+
+	u8    umem_1_size[0x20];
+
+	u8    umem_1_offset[0x40];
+
+	u8    umem_2_id[0x20];
+
+	u8    umem_2_size[0x20];
+
+	u8    umem_2_offset[0x40];
+
+	u8    umem_3_id[0x20];
+
+	u8    umem_3_size[0x20];
+
+	u8    umem_3_offset[0x40];
+
+	u8    counter_set_id[0x20];
+
+	u8    reserved_at_320[0x8];
+	u8    pd[0x18];
+
+	u8    reserved_at_340[0xc0];
+};
+
+struct mlx5_ifc_virtio_net_q_object_bits {
+	u8    modify_field_select[0x40];
+
+	u8    reserved_at_40[0x20];
+
+	u8    vhca_id[0x10];
+	u8    reserved_at_70[0x10];
+
+	u8    queue_feature_bit_mask_12_3[0xa];
+	u8    dirty_bitmap_dump_enable[0x1];
+	u8    vhost_log_page[0x5];
+	u8    reserved_at_90[0xc];
+	u8    state[0x4];
+
+	u8    reserved_at_a0[0x5];
+	u8    queue_feature_bit_mask_2_0[0x3];
+	u8    tisn_or_qpn[0x18];
+
+	u8    dirty_bitmap_mkey[0x20];
+
+	u8    dirty_bitmap_size[0x20];
+
+	u8    dirty_bitmap_addr[0x40];
+
+	u8    hw_available_index[0x10];
+	u8    hw_used_index[0x10];
+
+	u8    reserved_at_160[0xa0];
+
+	struct mlx5_ifc_virtio_q_bits virtio_q_context;
+};
+
+struct mlx5_ifc_create_virtio_net_q_in_bits {
+	struct mlx5_ifc_general_obj_in_cmd_hdr_bits general_obj_in_cmd_hdr;
+
+	struct mlx5_ifc_virtio_net_q_object_bits obj_context;
+};
+
+struct mlx5_ifc_create_virtio_net_q_out_bits {
+	struct mlx5_ifc_general_obj_out_cmd_hdr_bits general_obj_out_cmd_hdr;
+};
+
+struct mlx5_ifc_destroy_virtio_net_q_in_bits {
+	struct mlx5_ifc_general_obj_in_cmd_hdr_bits general_obj_out_cmd_hdr;
+};
+
+struct mlx5_ifc_destroy_virtio_net_q_out_bits {
+	struct mlx5_ifc_general_obj_out_cmd_hdr_bits general_obj_out_cmd_hdr;
+};
+
+struct mlx5_ifc_query_virtio_net_q_in_bits {
+	struct mlx5_ifc_general_obj_in_cmd_hdr_bits general_obj_in_cmd_hdr;
+};
+
+struct mlx5_ifc_query_virtio_net_q_out_bits {
+	struct mlx5_ifc_general_obj_out_cmd_hdr_bits general_obj_out_cmd_hdr;
+
+	struct mlx5_ifc_virtio_net_q_object_bits obj_context;
+};
+
+enum {
+	MLX5_VIRTQ_MODIFY_MASK_STATE                    = (u64)1 << 0,
+	MLX5_VIRTQ_MODIFY_MASK_DIRTY_BITMAP_PARAMS      = (u64)1 << 3,
+	MLX5_VIRTQ_MODIFY_MASK_DIRTY_BITMAP_DUMP_ENABLE = (u64)1 << 4,
+};
+
+enum {
+	MLX5_VIRTIO_NET_Q_OBJECT_STATE_INIT     = 0x0,
+	MLX5_VIRTIO_NET_Q_OBJECT_STATE_RDY      = 0x1,
+	MLX5_VIRTIO_NET_Q_OBJECT_STATE_SUSPEND  = 0x2,
+	MLX5_VIRTIO_NET_Q_OBJECT_STATE_ERR      = 0x3,
+};
+
+enum {
+	MLX5_RQTC_LIST_Q_TYPE_RQ            = 0x0,
+	MLX5_RQTC_LIST_Q_TYPE_VIRTIO_NET_Q  = 0x1,
+};
+
+struct mlx5_ifc_modify_virtio_net_q_in_bits {
+	struct mlx5_ifc_general_obj_in_cmd_hdr_bits general_obj_in_cmd_hdr;
+
+	struct mlx5_ifc_virtio_net_q_object_bits obj_context;
+};
+
+struct mlx5_ifc_modify_virtio_net_q_out_bits {
+	struct mlx5_ifc_general_obj_out_cmd_hdr_bits general_obj_out_cmd_hdr;
+};
+
+#endif /* __MLX5_VDPA_IFC_H_ */

drivers/vdpa/mlx5/core/resources.c

+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2020 Mellanox Technologies Ltd. */
+
+#include <linux/mlx5/driver.h>
+#include "mlx5_vdpa.h"
+
+static int alloc_pd(struct mlx5_vdpa_dev *dev, u32 *pdn, u16 uid)
+{
+	struct mlx5_core_dev *mdev = dev->mdev;
+
+	u32 out[MLX5_ST_SZ_DW(alloc_pd_out)] = {};
+	u32 in[MLX5_ST_SZ_DW(alloc_pd_in)] = {};
+	int err;
+
+	MLX5_SET(alloc_pd_in, in, opcode, MLX5_CMD_OP_ALLOC_PD);
+	MLX5_SET(alloc_pd_in, in, uid, uid);
+
+	err = mlx5_cmd_exec_inout(mdev, alloc_pd, in, out);
+	if (!err)
+		*pdn = MLX5_GET(alloc_pd_out, out, pd);
+
+	return err;
+}
+
+static int dealloc_pd(struct mlx5_vdpa_dev *dev, u32 pdn, u16 uid)
+{
+	u32 in[MLX5_ST_SZ_DW(dealloc_pd_in)] = {};
+	struct mlx5_core_dev *mdev = dev->mdev;
+
+	MLX5_SET(dealloc_pd_in, in, opcode, MLX5_CMD_OP_DEALLOC_PD);
+	MLX5_SET(dealloc_pd_in, in, pd, pdn);
+	MLX5_SET(dealloc_pd_in, in, uid, uid);
+	return mlx5_cmd_exec_in(mdev, dealloc_pd, in);
+}
+
+static int get_null_mkey(struct mlx5_vdpa_dev *dev, u32 *null_mkey)
+{
+	u32 out[MLX5_ST_SZ_DW(query_special_contexts_out)] = {};
+	u32 in[MLX5_ST_SZ_DW(query_special_contexts_in)] = {};
+	struct mlx5_core_dev *mdev = dev->mdev;
+	int err;
+
+	MLX5_SET(query_special_contexts_in, in, opcode, MLX5_CMD_OP_QUERY_SPECIAL_CONTEXTS);
+	err = mlx5_cmd_exec_inout(mdev, query_special_contexts, in, out);
+	if (!err)
+		*null_mkey = MLX5_GET(query_special_contexts_out, out, null_mkey);
+	return err;
+}
+
+static int create_uctx(struct mlx5_vdpa_dev *mvdev, u16 *uid)
+{
+	u32 out[MLX5_ST_SZ_DW(create_uctx_out)] = {};
+	int inlen;
+	void *in;
+	int err;
+
+	/* 0 means not supported */
+	if (!MLX5_CAP_GEN(mvdev->mdev, log_max_uctx))
+		return -EOPNOTSUPP;
+
+	inlen = MLX5_ST_SZ_BYTES(create_uctx_in);
+	in = kzalloc(inlen, GFP_KERNEL);
+	if (!in)
+		return -ENOMEM;
+
+	MLX5_SET(create_uctx_in, in, opcode, MLX5_CMD_OP_CREATE_UCTX);
+	MLX5_SET(create_uctx_in, in, uctx.cap, MLX5_UCTX_CAP_RAW_TX);
+
+	err = mlx5_cmd_exec(mvdev->mdev, in, inlen, out, sizeof(out));
+	kfree(in);
+	if (!err)
+		*uid = MLX5_GET(create_uctx_out, out, uid);
+
+	return err;
+}
+
+static void destroy_uctx(struct mlx5_vdpa_dev *mvdev, u32 uid)
+{
+	u32 out[MLX5_ST_SZ_DW(destroy_uctx_out)] = {};
+	u32 in[MLX5_ST_SZ_DW(destroy_uctx_in)] = {};
+
+	MLX5_SET(destroy_uctx_in, in, opcode, MLX5_CMD_OP_DESTROY_UCTX);
+	MLX5_SET(destroy_uctx_in, in, uid, uid);
+
+	mlx5_cmd_exec(mvdev->mdev, in, sizeof(in), out, sizeof(out));
+}
+
+int mlx5_vdpa_create_tis(struct mlx5_vdpa_dev *mvdev, void *in, u32 *tisn)
+{
+	u32 out[MLX5_ST_SZ_DW(create_tis_out)] = {};
+	int err;
+
+	MLX5_SET(create_tis_in, in, opcode, MLX5_CMD_OP_CREATE_TIS);
+	MLX5_SET(create_tis_in, in, uid, mvdev->res.uid);
+	err = mlx5_cmd_exec_inout(mvdev->mdev, create_tis, in, out);
+	if (!err)
+		*tisn = MLX5_GET(create_tis_out, out, tisn);
+
+	return err;
+}
+
+void mlx5_vdpa_destroy_tis(struct mlx5_vdpa_dev *mvdev, u32 tisn)
+{
+	u32 in[MLX5_ST_SZ_DW(destroy_tis_in)] = {};
+
+	MLX5_SET(destroy_tis_in, in, opcode, MLX5_CMD_OP_DESTROY_TIS);
+	MLX5_SET(destroy_tis_in, in, uid, mvdev->res.uid);
+	MLX5_SET(destroy_tis_in, in, tisn, tisn);
+	mlx5_cmd_exec_in(mvdev->mdev, destroy_tis, in);
+}
+
+int mlx5_vdpa_create_rqt(struct mlx5_vdpa_dev *mvdev, void *in, int inlen, u32 *rqtn)
+{
+	u32 out[MLX5_ST_SZ_DW(create_rqt_out)] = {};
+	int err;
+
+	MLX5_SET(create_rqt_in, in, opcode, MLX5_CMD_OP_CREATE_RQT);
+	err = mlx5_cmd_exec(mvdev->mdev, in, inlen, out, sizeof(out));
+	if (!err)
+		*rqtn = MLX5_GET(create_rqt_out, out, rqtn);
+
+	return err;
+}
+
+void mlx5_vdpa_destroy_rqt(struct mlx5_vdpa_dev *mvdev, u32 rqtn)
+{
+	u32 in[MLX5_ST_SZ_DW(destroy_rqt_in)] = {};
+
+	MLX5_SET(destroy_rqt_in, in, opcode, MLX5_CMD_OP_DESTROY_RQT);
+	MLX5_SET(destroy_rqt_in, in, uid, mvdev->res.uid);
+	MLX5_SET(destroy_rqt_in, in, rqtn, rqtn);
+	mlx5_cmd_exec_in(mvdev->mdev, destroy_rqt, in);
+}
+
+int mlx5_vdpa_create_tir(struct mlx5_vdpa_dev *mvdev, void *in, u32 *tirn)
+{
+	u32 out[MLX5_ST_SZ_DW(create_tir_out)] = {};
+	int err;
+
+	MLX5_SET(create_tir_in, in, opcode, MLX5_CMD_OP_CREATE_TIR);
+	err = mlx5_cmd_exec_inout(mvdev->mdev, create_tir, in, out);
+	if (!err)
+		*tirn = MLX5_GET(create_tir_out, out, tirn);
+
+	return err;
+}
+
+void mlx5_vdpa_destroy_tir(struct mlx5_vdpa_dev *mvdev, u32 tirn)
+{
+	u32 in[MLX5_ST_SZ_DW(destroy_tir_in)] = {};
+
+	MLX5_SET(destroy_tir_in, in, opcode, MLX5_CMD_OP_DESTROY_TIR);
+	MLX5_SET(destroy_tir_in, in, uid, mvdev->res.uid);
+	MLX5_SET(destroy_tir_in, in, tirn, tirn);
+	mlx5_cmd_exec_in(mvdev->mdev, destroy_tir, in);
+}
+
+int mlx5_vdpa_alloc_transport_domain(struct mlx5_vdpa_dev *mvdev, u32 *tdn)
+{
+	u32 out[MLX5_ST_SZ_DW(alloc_transport_domain_out)] = {};
+	u32 in[MLX5_ST_SZ_DW(alloc_transport_domain_in)] = {};
+	int err;
+
+	MLX5_SET(alloc_transport_domain_in, in, opcode, MLX5_CMD_OP_ALLOC_TRANSPORT_DOMAIN);
+	MLX5_SET(alloc_transport_domain_in, in, uid, mvdev->res.uid);
+
+	err = mlx5_cmd_exec_inout(mvdev->mdev, alloc_transport_domain, in, out);
+	if (!err)
+		*tdn = MLX5_GET(alloc_transport_domain_out, out, transport_domain);
+
+	return err;
+}
+
+void mlx5_vdpa_dealloc_transport_domain(struct mlx5_vdpa_dev *mvdev, u32 tdn)
+{
+	u32 in[MLX5_ST_SZ_DW(dealloc_transport_domain_in)] = {};
+
+	MLX5_SET(dealloc_transport_domain_in, in, opcode, MLX5_CMD_OP_DEALLOC_TRANSPORT_DOMAIN);
+	MLX5_SET(dealloc_transport_domain_in, in, uid, mvdev->res.uid);
+	MLX5_SET(dealloc_transport_domain_in, in, transport_domain, tdn);
+	mlx5_cmd_exec_in(mvdev->mdev, dealloc_transport_domain, in);
+}
+
+int mlx5_vdpa_create_mkey(struct mlx5_vdpa_dev *mvdev, struct mlx5_core_mkey *mkey, u32 *in,
+			  int inlen)
+{
+	u32 lout[MLX5_ST_SZ_DW(create_mkey_out)] = {};
+	u32 mkey_index;
+	void *mkc;
+	int err;
+
+	MLX5_SET(create_mkey_in, in, opcode, MLX5_CMD_OP_CREATE_MKEY);
+	MLX5_SET(create_mkey_in, in, uid, mvdev->res.uid);
+
+	err = mlx5_cmd_exec(mvdev->mdev, in, inlen, lout, sizeof(lout));
+	if (err)
+		return err;
+
+	mkc = MLX5_ADDR_OF(create_mkey_in, in, memory_key_mkey_entry);
+	mkey_index = MLX5_GET(create_mkey_out, lout, mkey_index);
+	mkey->iova = MLX5_GET64(mkc, mkc, start_addr);
+	mkey->size = MLX5_GET64(mkc, mkc, len);
+	mkey->key |= mlx5_idx_to_mkey(mkey_index);
+	mkey->pd = MLX5_GET(mkc, mkc, pd);
+	return 0;
+}
+
+int mlx5_vdpa_destroy_mkey(struct mlx5_vdpa_dev *mvdev, struct mlx5_core_mkey *mkey)
+{
+	u32 in[MLX5_ST_SZ_DW(destroy_mkey_in)] = {};
+
+	MLX5_SET(destroy_mkey_in, in, uid, mvdev->res.uid);
+	MLX5_SET(destroy_mkey_in, in, opcode, MLX5_CMD_OP_DESTROY_MKEY);
+	MLX5_SET(destroy_mkey_in, in, mkey_index, mlx5_mkey_to_idx(mkey->key));
+	return mlx5_cmd_exec_in(mvdev->mdev, destroy_mkey, in);
+}
+
+int mlx5_vdpa_alloc_resources(struct mlx5_vdpa_dev *mvdev)
+{
+	u64 offset = MLX5_CAP64_DEV_VDPA_EMULATION(mvdev->mdev, doorbell_bar_offset);
+	struct mlx5_vdpa_resources *res = &mvdev->res;
+	struct mlx5_core_dev *mdev = mvdev->mdev;
+	u64 kick_addr;
+	int err;
+
+	if (res->valid) {
+		mlx5_vdpa_warn(mvdev, "resources already allocated\n");
+		return -EINVAL;
+	}
+	mutex_init(&mvdev->mr.mkey_mtx);
+	res->uar = mlx5_get_uars_page(mdev);
+	if (IS_ERR(res->uar)) {
+		err = PTR_ERR(res->uar);
+		goto err_uars;
+	}
+
+	err = create_uctx(mvdev, &res->uid);
+	if (err)
+		goto err_uctx;
+
+	err = alloc_pd(mvdev, &res->pdn, res->uid);
+	if (err)
+		goto err_pd;
+
+	err = get_null_mkey(mvdev, &res->null_mkey);
+	if (err)
+		goto err_key;
+
+	kick_addr = pci_resource_start(mdev->pdev, 0) + offset;
+	res->kick_addr = ioremap(kick_addr, PAGE_SIZE);
+	if (!res->kick_addr) {
+		err = -ENOMEM;
+		goto err_key;
+	}
+	res->valid = true;
+
+	return 0;
+
+err_key:
+	dealloc_pd(mvdev, res->pdn, res->uid);
+err_pd:
+	destroy_uctx(mvdev, res->uid);
+err_uctx:
+	mlx5_put_uars_page(mdev, res->uar);
+err_uars:
+	mutex_destroy(&mvdev->mr.mkey_mtx);
+	return err;
+}
+
+void mlx5_vdpa_free_resources(struct mlx5_vdpa_dev *mvdev)
+{
+	struct mlx5_vdpa_resources *res = &mvdev->res;
+
+	if (!res->valid)
+		return;
+
+	iounmap(res->kick_addr);
+	res->kick_addr = NULL;
+	dealloc_pd(mvdev, res->pdn, res->uid);
+	destroy_uctx(mvdev, res->uid);
+	mlx5_put_uars_page(mvdev->mdev, res->uar);
+	mutex_destroy(&mvdev->mr.mkey_mtx);
+	res->valid = false;
+}

drivers/vdpa/mlx5/net/main.c

+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2020 Mellanox Technologies Ltd. */
+
+#include <linux/module.h>
+#include <linux/mlx5/driver.h>
+#include <linux/mlx5/device.h>
+#include "mlx5_vdpa_ifc.h"
+#include "mlx5_vnet.h"
+
+MODULE_AUTHOR("Eli Cohen <eli@mellanox.com>");
+MODULE_DESCRIPTION("Mellanox VDPA driver");
+MODULE_LICENSE("Dual BSD/GPL");
+
+static bool required_caps_supported(struct mlx5_core_dev *mdev)
+{
+	u8 event_mode;
+	u64 got;
+
+	got = MLX5_CAP_GEN_64(mdev, general_obj_types);
+
+	if (!(got & MLX5_GENERAL_OBJ_TYPES_CAP_VIRTIO_NET_Q))
+		return false;
+
+	event_mode = MLX5_CAP_DEV_VDPA_EMULATION(mdev, event_mode);
+	if (!(event_mode & MLX5_VIRTIO_Q_EVENT_MODE_QP_MODE))
+		return false;
+
+	if (!MLX5_CAP_DEV_VDPA_EMULATION(mdev, eth_frame_offload_type))
+		return false;
+
+	return true;
+}
+
+static void *mlx5_vdpa_add(struct mlx5_core_dev *mdev)
+{
+	struct mlx5_vdpa_dev *vdev;
+
+	if (mlx5_core_is_pf(mdev))
+		return NULL;
+
+	if (!required_caps_supported(mdev)) {
+		dev_info(mdev->device, "virtio net emulation not supported\n");
+		return NULL;
+	}
+	vdev = mlx5_vdpa_add_dev(mdev);
+	if (IS_ERR(vdev))
+		return NULL;
+
+	return vdev;
+}
+
+static void mlx5_vdpa_remove(struct mlx5_core_dev *mdev, void *context)
+{
+	struct mlx5_vdpa_dev *vdev = context;
+
+	mlx5_vdpa_remove_dev(vdev);
+}
+
+static struct mlx5_interface mlx5_vdpa_interface = {
+	.add = mlx5_vdpa_add,
+	.remove = mlx5_vdpa_remove,
+	.protocol = MLX5_INTERFACE_PROTOCOL_VDPA,
+};
+
+static int __init mlx5_vdpa_init(void)
+{
+	return mlx5_register_interface(&mlx5_vdpa_interface);
+}
+
+static void __exit mlx5_vdpa_exit(void)
+{
+	mlx5_unregister_interface(&mlx5_vdpa_interface);
+}
+
+module_init(mlx5_vdpa_init);
+module_exit(mlx5_vdpa_exit);

drivers/vdpa/mlx5/net/mlx5_vnet.h

+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2020 Mellanox Technologies Ltd. */
+
+#ifndef __MLX5_VNET_H_
+#define __MLX5_VNET_H_
+
+#include <linux/vdpa.h>
+#include <linux/virtio_net.h>
+#include <linux/vringh.h>
+#include <linux/mlx5/driver.h>
+#include <linux/mlx5/cq.h>
+#include <linux/mlx5/qp.h>
+#include "mlx5_vdpa.h"
+
+static inline u32 mlx5_vdpa_max_qps(int max_vqs)
+{
+	return max_vqs / 2;
+}
+
+#define to_mlx5_vdpa_ndev(__mvdev) container_of(__mvdev, struct mlx5_vdpa_net, mvdev)
+void *mlx5_vdpa_add_dev(struct mlx5_core_dev *mdev);
+void mlx5_vdpa_remove_dev(struct mlx5_vdpa_dev *mvdev);
+
+#endif /* __MLX5_VNET_H_ */

drivers/vdpa/vdpa.c

@@ -61,6 +61,7 @@ static void vdpa_release_dev(struct device *d)
  * initialized but before registered.
  * @parent: the parent device
  * @config: the bus operations that is supported by this device
+ * @nvqs: number of virtqueues supported by this device
  * @size: size of the parent structure that contains private data
  *
  * Driver should use vdpa_alloc_device() wrapper macro instead of
@@ -71,6 +72,7 @@ static void vdpa_release_dev(struct device *d)
  */
 struct vdpa_device *__vdpa_alloc_device(struct device *parent,
 					const struct vdpa_config_ops *config,
+					int nvqs,
 					size_t size)
 {
 	struct vdpa_device *vdev;
@@ -96,6 +98,8 @@ struct vdpa_device *__vdpa_alloc_device(struct device *parent,
 	vdev->dev.release = vdpa_release_dev;
 	vdev->index = err;
 	vdev->config = config;
+	vdev->features_valid = false;
+	vdev->nvqs = nvqs;
 
 	err = dev_set_name(&vdev->dev, "vdpa%u", vdev->index);
 	if (err)

drivers/vhost/Kconfig

@@ -65,6 +65,7 @@ config VHOST_VDPA
 	tristate "Vhost driver for vDPA-based backend"
 	depends on EVENTFD
 	select VHOST
+	select IRQ_BYPASS_MANAGER
 	depends on VDPA
 	help
 	  This kernel module can be loaded in host kernel to accelerate

drivers/vhost/net.c

@@ -73,7 +73,7 @@ enum {
 	VHOST_NET_FEATURES = VHOST_FEATURES |
 			 (1ULL << VHOST_NET_F_VIRTIO_NET_HDR) |
 			 (1ULL << VIRTIO_NET_F_MRG_RXBUF) |
-			 (1ULL << VIRTIO_F_IOMMU_PLATFORM)
+			 (1ULL << VIRTIO_F_ACCESS_PLATFORM)
 };
 
 enum {
@@ -1615,21 +1615,6 @@ static long vhost_net_reset_owner(struct vhost_net *n)
 	return err;
 }
 
-static int vhost_net_set_backend_features(struct vhost_net *n, u64 features)
-{
-	int i;
-
-	mutex_lock(&n->dev.mutex);
-	for (i = 0; i < VHOST_NET_VQ_MAX; ++i) {
-		mutex_lock(&n->vqs[i].vq.mutex);
-		n->vqs[i].vq.acked_backend_features = features;
-		mutex_unlock(&n->vqs[i].vq.mutex);
-	}
-	mutex_unlock(&n->dev.mutex);
-
-	return 0;
-}
-
 static int vhost_net_set_features(struct vhost_net *n, u64 features)
 {
 	size_t vhost_hlen, sock_hlen, hdr_len;
@@ -1653,7 +1638,7 @@ static int vhost_net_set_features(struct vhost_net *n, u64 features)
 	    !vhost_log_access_ok(&n->dev))
 		goto out_unlock;
 
-	if ((features & (1ULL << VIRTIO_F_IOMMU_PLATFORM))) {
+	if ((features & (1ULL << VIRTIO_F_ACCESS_PLATFORM))) {
 		if (vhost_init_device_iotlb(&n->dev, true))
 			goto out_unlock;
 	}
@@ -1730,7 +1715,8 @@ static long vhost_net_ioctl(struct file *f, unsigned int ioctl,
 			return -EFAULT;
 		if (features & ~VHOST_NET_BACKEND_FEATURES)
 			return -EOPNOTSUPP;
-		return vhost_net_set_backend_features(n, features);
+		vhost_set_backend_features(&n->dev, features);
+		return 0;
 	case VHOST_RESET_OWNER:
 		return vhost_net_reset_owner(n);
 	case VHOST_SET_OWNER:

drivers/vhost/vhost.c

@@ -298,6 +298,13 @@ static void vhost_vq_meta_reset(struct vhost_dev *d)
 		__vhost_vq_meta_reset(d->vqs[i]);
 }
 
+static void vhost_vring_call_reset(struct vhost_vring_call *call_ctx)
+{
+	call_ctx->ctx = NULL;
+	memset(&call_ctx->producer, 0x0, sizeof(struct irq_bypass_producer));
+	spin_lock_init(&call_ctx->ctx_lock);
+}
+
 static void vhost_vq_reset(struct vhost_dev *dev,
 			   struct vhost_virtqueue *vq)
 {
@@ -319,13 +326,13 @@ static void vhost_vq_reset(struct vhost_dev *dev,
 	vq->log_base = NULL;
 	vq->error_ctx = NULL;
 	vq->kick = NULL;
-	vq->call_ctx = NULL;
 	vq->log_ctx = NULL;
 	vhost_reset_is_le(vq);
 	vhost_disable_cross_endian(vq);
 	vq->busyloop_timeout = 0;
 	vq->umem = NULL;
 	vq->iotlb = NULL;
+	vhost_vring_call_reset(&vq->call_ctx);
 	__vhost_vq_meta_reset(vq);
 }
 
@@ -685,8 +692,8 @@ void vhost_dev_cleanup(struct vhost_dev *dev)
 			eventfd_ctx_put(dev->vqs[i]->error_ctx);
 		if (dev->vqs[i]->kick)
 			fput(dev->vqs[i]->kick);
-		if (dev->vqs[i]->call_ctx)
-			eventfd_ctx_put(dev->vqs[i]->call_ctx);
+		if (dev->vqs[i]->call_ctx.ctx)
+			eventfd_ctx_put(dev->vqs[i]->call_ctx.ctx);
 		vhost_vq_reset(dev, dev->vqs[i]);
 	}
 	vhost_dev_free_iovecs(dev);
@@ -1405,7 +1412,7 @@ static long vhost_set_memory(struct vhost_dev *d, struct vhost_memory __user *m)
 
 	memcpy(newmem, &mem, size);
 	if (copy_from_user(newmem->regions, m->regions,
-			   mem.nregions * sizeof *m->regions)) {
+			   flex_array_size(newmem, regions, mem.nregions))) {
 		kvfree(newmem);
 		return -EFAULT;
 	}
@@ -1629,7 +1636,10 @@ long vhost_vring_ioctl(struct vhost_dev *d, unsigned int ioctl, void __user *arg
 			r = PTR_ERR(ctx);
 			break;
 		}
-		swap(ctx, vq->call_ctx);
+
+		spin_lock(&vq->call_ctx.ctx_lock);
+		swap(ctx, vq->call_ctx.ctx);
+		spin_unlock(&vq->call_ctx.ctx_lock);
 		break;
 	case VHOST_SET_VRING_ERR:
 		if (copy_from_user(&f, argp, sizeof f)) {
@@ -2435,8 +2445,8 @@ static bool vhost_notify(struct vhost_dev *dev, struct vhost_virtqueue *vq)
 void vhost_signal(struct vhost_dev *dev, struct vhost_virtqueue *vq)
 {
 	/* Signal the Guest tell them we used something up. */
-	if (vq->call_ctx && vhost_notify(dev, vq))
-		eventfd_signal(vq->call_ctx, 1);
+	if (vq->call_ctx.ctx && vhost_notify(dev, vq))
+		eventfd_signal(vq->call_ctx.ctx, 1);
 }
 EXPORT_SYMBOL_GPL(vhost_signal);
 
@@ -2576,6 +2586,21 @@ struct vhost_msg_node *vhost_dequeue_msg(struct vhost_dev *dev,
 }
 EXPORT_SYMBOL_GPL(vhost_dequeue_msg);
 
+void vhost_set_backend_features(struct vhost_dev *dev, u64 features)
+{
+	struct vhost_virtqueue *vq;
+	int i;
+
+	mutex_lock(&dev->mutex);
+	for (i = 0; i < dev->nvqs; ++i) {
+		vq = dev->vqs[i];
+		mutex_lock(&vq->mutex);
+		vq->acked_backend_features = features;
+		mutex_unlock(&vq->mutex);
+	}
+	mutex_unlock(&dev->mutex);
+}
+EXPORT_SYMBOL_GPL(vhost_set_backend_features);
 
 static int __init vhost_init(void)
 {

drivers/vhost/vhost.h

@@ -13,6 +13,7 @@
 #include <linux/virtio_ring.h>
 #include <linux/atomic.h>
 #include <linux/vhost_iotlb.h>
+#include <linux/irqbypass.h>
 
 struct vhost_work;
 typedef void (*vhost_work_fn_t)(struct vhost_work *work);
@@ -60,6 +61,12 @@ enum vhost_uaddr_type {
 	VHOST_NUM_ADDRS = 3,
 };
 
+struct vhost_vring_call {
+	struct eventfd_ctx *ctx;
+	struct irq_bypass_producer producer;
+	spinlock_t ctx_lock;
+};
+
 /* The virtqueue structure describes a queue attached to a device. */
 struct vhost_virtqueue {
 	struct vhost_dev *dev;
@@ -72,7 +79,7 @@ struct vhost_virtqueue {
 	vring_used_t __user *used;
 	const struct vhost_iotlb_map *meta_iotlb[VHOST_NUM_ADDRS];
 	struct file *kick;
-	struct eventfd_ctx *call_ctx;
+	struct vhost_vring_call call_ctx;
 	struct eventfd_ctx *error_ctx;
 	struct eventfd_ctx *log_ctx;
 
@@ -207,6 +214,8 @@ void vhost_enqueue_msg(struct vhost_dev *dev,
 		       struct vhost_msg_node *node);
 struct vhost_msg_node *vhost_dequeue_msg(struct vhost_dev *dev,
 					 struct list_head *head);
+void vhost_set_backend_features(struct vhost_dev *dev, u64 features);
+
 __poll_t vhost_chr_poll(struct file *file, struct vhost_dev *dev,
 			    poll_table *wait);
 ssize_t vhost_chr_read_iter(struct vhost_dev *dev, struct iov_iter *to,

drivers/virtio/virtio_balloon.c

@@ -398,12 +398,9 @@ static inline s64 towards_target(struct virtio_balloon *vb)
 	s64 target;
 	u32 num_pages;
 
-	virtio_cread(vb->vdev, struct virtio_balloon_config, num_pages,
-		     &num_pages);
-
 	/* Legacy balloon config space is LE, unlike all other devices. */
-	if (!virtio_has_feature(vb->vdev, VIRTIO_F_VERSION_1))
-		num_pages = le32_to_cpu((__force __le32)num_pages);
+	virtio_cread_le(vb->vdev, struct virtio_balloon_config, num_pages,
+			&num_pages);
 
 	target = num_pages;
 	return target - vb->num_pages;
@@ -462,10 +459,7 @@ static void update_balloon_size(struct virtio_balloon *vb)
 	u32 actual = vb->num_pages;
 
 	/* Legacy balloon config space is LE, unlike all other devices. */
-	if (!virtio_has_feature(vb->vdev, VIRTIO_F_VERSION_1))
-		actual = (__force u32)cpu_to_le32(actual);
-
-	virtio_cwrite(vb->vdev, struct virtio_balloon_config, actual,
+	virtio_cwrite_le(vb->vdev, struct virtio_balloon_config, actual,
 			 &actual);
 }
 
@@ -579,12 +573,10 @@ static u32 virtio_balloon_cmd_id_received(struct virtio_balloon *vb)
 {
 	if (test_and_clear_bit(VIRTIO_BALLOON_CONFIG_READ_CMD_ID,
 			       &vb->config_read_bitmap)) {
-		virtio_cread(vb->vdev, struct virtio_balloon_config,
+		/* Legacy balloon config space is LE, unlike all other devices. */
+		virtio_cread_le(vb->vdev, struct virtio_balloon_config,
 				free_page_hint_cmd_id,
 				&vb->cmd_id_received_cache);
-		/* Legacy balloon config space is LE, unlike all other devices. */
-		if (!virtio_has_feature(vb->vdev, VIRTIO_F_VERSION_1))
-			vb->cmd_id_received_cache = le32_to_cpu((__force __le32)vb->cmd_id_received_cache);
 	}
 
 	return vb->cmd_id_received_cache;
@@ -600,7 +592,7 @@ static int send_cmd_id_start(struct virtio_balloon *vb)
 	while (virtqueue_get_buf(vq, &unused))
 		;
 
-	vb->cmd_id_active = virtio32_to_cpu(vb->vdev,
+	vb->cmd_id_active = cpu_to_virtio32(vb->vdev,
 					virtio_balloon_cmd_id_received(vb));
 	sg_init_one(&sg, &vb->cmd_id_active, sizeof(vb->cmd_id_active));
 	err = virtqueue_add_outbuf(vq, &sg, 1, &vb->cmd_id_active, GFP_KERNEL);
@@ -987,7 +979,7 @@ static int virtballoon_probe(struct virtio_device *vdev)
 		if (!want_init_on_free())
 			memset(&poison_val, PAGE_POISON, sizeof(poison_val));
 
-		virtio_cwrite(vb->vdev, struct virtio_balloon_config,
+		virtio_cwrite_le(vb->vdev, struct virtio_balloon_config,
 				 poison_val, &poison_val);
 	}
 
@@ -1129,7 +1121,7 @@ static int virtballoon_validate(struct virtio_device *vdev)
 	else if (!virtio_has_feature(vdev, VIRTIO_BALLOON_F_PAGE_POISON))
 		__virtio_clear_bit(vdev, VIRTIO_BALLOON_F_REPORTING);
 
-	__virtio_clear_bit(vdev, VIRTIO_F_IOMMU_PLATFORM);
+	__virtio_clear_bit(vdev, VIRTIO_F_ACCESS_PLATFORM);
 	return 0;
 }
 

drivers/virtio/virtio_input.c

@@ -113,9 +113,9 @@ static u8 virtinput_cfg_select(struct virtio_input *vi,
 {
 	u8 size;
 
-	virtio_cwrite(vi->vdev, struct virtio_input_config, select, &select);
-	virtio_cwrite(vi->vdev, struct virtio_input_config, subsel, &subsel);
-	virtio_cread(vi->vdev, struct virtio_input_config, size, &size);
+	virtio_cwrite_le(vi->vdev, struct virtio_input_config, select, &select);
+	virtio_cwrite_le(vi->vdev, struct virtio_input_config, subsel, &subsel);
+	virtio_cread_le(vi->vdev, struct virtio_input_config, size, &size);
 	return size;
 }
 
@@ -158,11 +158,11 @@ static void virtinput_cfg_abs(struct virtio_input *vi, int abs)
 	u32 mi, ma, re, fu, fl;
 
 	virtinput_cfg_select(vi, VIRTIO_INPUT_CFG_ABS_INFO, abs);
-	virtio_cread(vi->vdev, struct virtio_input_config, u.abs.min, &mi);
-	virtio_cread(vi->vdev, struct virtio_input_config, u.abs.max, &ma);
-	virtio_cread(vi->vdev, struct virtio_input_config, u.abs.res, &re);
-	virtio_cread(vi->vdev, struct virtio_input_config, u.abs.fuzz, &fu);
-	virtio_cread(vi->vdev, struct virtio_input_config, u.abs.flat, &fl);
+	virtio_cread_le(vi->vdev, struct virtio_input_config, u.abs.min, &mi);
+	virtio_cread_le(vi->vdev, struct virtio_input_config, u.abs.max, &ma);
+	virtio_cread_le(vi->vdev, struct virtio_input_config, u.abs.res, &re);
+	virtio_cread_le(vi->vdev, struct virtio_input_config, u.abs.fuzz, &fu);
+	virtio_cread_le(vi->vdev, struct virtio_input_config, u.abs.flat, &fl);
 	input_set_abs_params(vi->idev, abs, mi, ma, fu, fl);
 	input_abs_set_res(vi->idev, abs, re);
 }
@@ -244,13 +244,13 @@ static int virtinput_probe(struct virtio_device *vdev)
 
 	size = virtinput_cfg_select(vi, VIRTIO_INPUT_CFG_ID_DEVIDS, 0);
 	if (size >= sizeof(struct virtio_input_devids)) {
-		virtio_cread(vi->vdev, struct virtio_input_config,
+		virtio_cread_le(vi->vdev, struct virtio_input_config,
 				u.ids.bustype, &vi->idev->id.bustype);
-		virtio_cread(vi->vdev, struct virtio_input_config,
+		virtio_cread_le(vi->vdev, struct virtio_input_config,
 				u.ids.vendor, &vi->idev->id.vendor);
-		virtio_cread(vi->vdev, struct virtio_input_config,
+		virtio_cread_le(vi->vdev, struct virtio_input_config,
 				u.ids.product, &vi->idev->id.product);
-		virtio_cread(vi->vdev, struct virtio_input_config,
+		virtio_cread_le(vi->vdev, struct virtio_input_config,
 				u.ids.version, &vi->idev->id.version);
 	} else {
 		vi->idev->id.bustype = BUS_VIRTUAL;

drivers/virtio/virtio_mem.c

@@ -1530,20 +1530,20 @@ static void virtio_mem_refresh_config(struct virtio_mem *vm)
 	uint64_t new_plugged_size, usable_region_size, end_addr;
 
 	/* the plugged_size is just a reflection of what _we_ did previously */
-	virtio_cread(vm->vdev, struct virtio_mem_config, plugged_size,
+	virtio_cread_le(vm->vdev, struct virtio_mem_config, plugged_size,
 			&new_plugged_size);
 	if (WARN_ON_ONCE(new_plugged_size != vm->plugged_size))
 		vm->plugged_size = new_plugged_size;
 
 	/* calculate the last usable memory block id */
-	virtio_cread(vm->vdev, struct virtio_mem_config,
+	virtio_cread_le(vm->vdev, struct virtio_mem_config,
 			usable_region_size, &usable_region_size);
 	end_addr = vm->addr + usable_region_size;
 	end_addr = min(end_addr, phys_limit);
 	vm->last_usable_mb_id = virtio_mem_phys_to_mb_id(end_addr) - 1;
 
 	/* see if there is a request to change the size */
-	virtio_cread(vm->vdev, struct virtio_mem_config, requested_size,
+	virtio_cread_le(vm->vdev, struct virtio_mem_config, requested_size,
 			&vm->requested_size);
 
 	dev_info(&vm->vdev->dev, "plugged size: 0x%llx", vm->plugged_size);
@@ -1677,15 +1677,15 @@ static int virtio_mem_init(struct virtio_mem *vm)
 	}
 
 	/* Fetch all properties that can't change. */
-	virtio_cread(vm->vdev, struct virtio_mem_config, plugged_size,
+	virtio_cread_le(vm->vdev, struct virtio_mem_config, plugged_size,
 			&vm->plugged_size);
-	virtio_cread(vm->vdev, struct virtio_mem_config, block_size,
+	virtio_cread_le(vm->vdev, struct virtio_mem_config, block_size,
 			&vm->device_block_size);
-	virtio_cread(vm->vdev, struct virtio_mem_config, node_id,
+	virtio_cread_le(vm->vdev, struct virtio_mem_config, node_id,
 			&node_id);
 	vm->nid = virtio_mem_translate_node_id(vm, node_id);
-	virtio_cread(vm->vdev, struct virtio_mem_config, addr, &vm->addr);
-	virtio_cread(vm->vdev, struct virtio_mem_config, region_size,
+	virtio_cread_le(vm->vdev, struct virtio_mem_config, addr, &vm->addr);
+	virtio_cread_le(vm->vdev, struct virtio_mem_config, region_size,
 			&vm->region_size);
 
 	/*

drivers/virtio/virtio_pci_modern.c

@@ -481,6 +481,7 @@ static const struct virtio_config_ops virtio_pci_config_ops = {
  * @dev: the pci device
  * @cfg_type: the VIRTIO_PCI_CAP_* value we seek
  * @ioresource_types: IORESOURCE_MEM and/or IORESOURCE_IO.
+ * @bars: the bitmask of BARs
  *
  * Returns offset of the capability, or 0.
  */

drivers/virtio/virtio_ring.c

@@ -240,7 +240,7 @@ static inline bool virtqueue_use_indirect(struct virtqueue *_vq,
 
 static bool vring_use_dma_api(struct virtio_device *vdev)
 {
-	if (!virtio_has_iommu_quirk(vdev))
+	if (!virtio_has_dma_quirk(vdev))
 		return true;
 
 	/* Otherwise, we are left to guess. */
@@ -1960,6 +1960,9 @@ bool virtqueue_poll(struct virtqueue *_vq, unsigned last_used_idx)
 {
 	struct vring_virtqueue *vq = to_vvq(_vq);
 
+	if (unlikely(vq->broken))
+		return false;
+
 	virtio_mb(vq->weak_barriers);
 	return vq->packed_ring ? virtqueue_poll_packed(_vq, last_used_idx) :
 				 virtqueue_poll_split(_vq, last_used_idx);
@@ -2225,7 +2228,7 @@ void vring_transport_features(struct virtio_device *vdev)
 			break;
 		case VIRTIO_F_VERSION_1:
 			break;
-		case VIRTIO_F_IOMMU_PLATFORM:
+		case VIRTIO_F_ACCESS_PLATFORM:
 			break;
 		case VIRTIO_F_RING_PACKED:
 			break;

drivers/virtio/virtio_vdpa.c

@@ -57,9 +57,8 @@ static void virtio_vdpa_get(struct virtio_device *vdev, unsigned offset,
 			    void *buf, unsigned len)
 {
 	struct vdpa_device *vdpa = vd_get_vdpa(vdev);
-	const struct vdpa_config_ops *ops = vdpa->config;
 
-	ops->get_config(vdpa, offset, buf, len);
+	vdpa_get_config(vdpa, offset, buf, len);
 }
 
 static void virtio_vdpa_set(struct virtio_device *vdev, unsigned offset,
@@ -101,9 +100,8 @@ static void virtio_vdpa_set_status(struct virtio_device *vdev, u8 status)
 static void virtio_vdpa_reset(struct virtio_device *vdev)
 {
 	struct vdpa_device *vdpa = vd_get_vdpa(vdev);
-	const struct vdpa_config_ops *ops = vdpa->config;
 
-	return ops->set_status(vdpa, 0);
+	vdpa_reset(vdpa);
 }
 
 static bool virtio_vdpa_notify(struct virtqueue *vq)
@@ -294,12 +292,11 @@ static u64 virtio_vdpa_get_features(struct virtio_device *vdev)
 static int virtio_vdpa_finalize_features(struct virtio_device *vdev)
 {
 	struct vdpa_device *vdpa = vd_get_vdpa(vdev);
-	const struct vdpa_config_ops *ops = vdpa->config;
 
 	/* Give virtio_ring a chance to accept features. */
 	vring_transport_features(vdev);
 
-	return ops->set_features(vdpa, vdev->features);
+	return vdpa_set_features(vdpa, vdev->features);
 }
 
 static const char *virtio_vdpa_bus_name(struct virtio_device *vdev)

fs/fuse/virtio_fs.c

@@ -606,7 +606,7 @@ static int virtio_fs_setup_vqs(struct virtio_device *vdev,
 	unsigned int i;
 	int ret = 0;
 
-	virtio_cread(vdev, struct virtio_fs_config, num_request_queues,
+	virtio_cread_le(vdev, struct virtio_fs_config, num_request_queues,
 			&fs->num_request_queues);
 	if (fs->num_request_queues == 0)
 		return -EINVAL;

include/linux/vdpa.h

@@ -27,18 +27,29 @@ struct vdpa_notification_area {
 	resource_size_t size;
 };
 
+/**
+ * vDPA vq_state definition
+ * @avail_index: available index
+ */
+struct vdpa_vq_state {
+	u16	avail_index;
+};
+
 /**
  * vDPA device - representation of a vDPA device
  * @dev: underlying device
  * @dma_dev: the actual device that is performing DMA
  * @config: the configuration ops for this device.
  * @index: device index
+ * @features_valid: were features initialized? for legacy guests
  */
 struct vdpa_device {
 	struct device dev;
 	struct device *dma_dev;
 	const struct vdpa_config_ops *config;
 	unsigned int index;
+	bool features_valid;
+	int nvqs;
 };
 
 /**
@@ -77,16 +88,22 @@ struct vdpa_device {
  * @set_vq_state:		Set the state for a virtqueue
  *				@vdev: vdpa device
  *				@idx: virtqueue index
- *				@state: virtqueue state (last_avail_idx)
+ *				@state: pointer to set virtqueue state (last_avail_idx)
  *				Returns integer: success (0) or error (< 0)
  * @get_vq_state:		Get the state for a virtqueue
  *				@vdev: vdpa device
  *				@idx: virtqueue index
- *				Returns virtqueue state (last_avail_idx)
+ *				@state: pointer to returned state (last_avail_idx)
  * @get_vq_notification: 	Get the notification area for a virtqueue
  *				@vdev: vdpa device
  *				@idx: virtqueue index
  *				Returns the notifcation area
+ * @get_vq_irq:			Get the irq number of a virtqueue (optional,
+ *				but must implemented if require vq irq offloading)
+ *				@vdev: vdpa device
+ *				@idx: virtqueue index
+ *				Returns int: irq number of a virtqueue,
+ *				negative number if no irq assigned.
  * @get_vq_align:		Get the virtqueue align requirement
  *				for the device
  *				@vdev: vdpa device
@@ -174,10 +191,14 @@ struct vdpa_config_ops {
 			  struct vdpa_callback *cb);
 	void (*set_vq_ready)(struct vdpa_device *vdev, u16 idx, bool ready);
 	bool (*get_vq_ready)(struct vdpa_device *vdev, u16 idx);
-	int (*set_vq_state)(struct vdpa_device *vdev, u16 idx, u64 state);
-	u64 (*get_vq_state)(struct vdpa_device *vdev, u16 idx);
+	int (*set_vq_state)(struct vdpa_device *vdev, u16 idx,
+			    const struct vdpa_vq_state *state);
+	int (*get_vq_state)(struct vdpa_device *vdev, u16 idx,
+			    struct vdpa_vq_state *state);
 	struct vdpa_notification_area
 	(*get_vq_notification)(struct vdpa_device *vdev, u16 idx);
+	/* vq irq is not expected to be changed once DRIVER_OK is set */
+	int (*get_vq_irq)(struct vdpa_device *vdv, u16 idx);
 
 	/* Device ops */
 	u32 (*get_vq_align)(struct vdpa_device *vdev);
@@ -208,11 +229,12 @@ struct vdpa_config_ops {
 
 struct vdpa_device *__vdpa_alloc_device(struct device *parent,
 					const struct vdpa_config_ops *config,
+					int nvqs,
 					size_t size);
 
-#define vdpa_alloc_device(dev_struct, member, parent, config)   \
+#define vdpa_alloc_device(dev_struct, member, parent, config, nvqs)   \
 			  container_of(__vdpa_alloc_device( \
-				       parent, config, \
+				       parent, config, nvqs, \
 				       sizeof(dev_struct) + \
 				       BUILD_BUG_ON_ZERO(offsetof( \
 				       dev_struct, member))), \
@@ -266,4 +288,36 @@ static inline struct device *vdpa_get_dma_dev(struct vdpa_device *vdev)
 {
 	return vdev->dma_dev;
 }
+
+static inline void vdpa_reset(struct vdpa_device *vdev)
+{
+        const struct vdpa_config_ops *ops = vdev->config;
+
+	vdev->features_valid = false;
+        ops->set_status(vdev, 0);
+}
+
+static inline int vdpa_set_features(struct vdpa_device *vdev, u64 features)
+{
+        const struct vdpa_config_ops *ops = vdev->config;
+
+	vdev->features_valid = true;
+        return ops->set_features(vdev, features);
+}
+
+
+static inline void vdpa_get_config(struct vdpa_device *vdev, unsigned offset,
+				   void *buf, unsigned int len)
+{
+        const struct vdpa_config_ops *ops = vdev->config;
+
+	/*
+	 * Config accesses aren't supposed to trigger before features are set.
+	 * If it does happen we assume a legacy guest.
+	 */
+	if (!vdev->features_valid)
+		vdpa_set_features(vdev, 0);
+	ops->get_config(vdev, offset, buf, len);
+}
+
 #endif /* _LINUX_VDPA_H */

include/linux/virtio_caif.h

@@ -11,9 +11,9 @@
 
 #include <linux/types.h>
 struct virtio_caif_transf_config {
-	u16 headroom;
-	u16 tailroom;
-	u32 mtu;
+	__virtio16 headroom;
+	__virtio16 tailroom;
+	__virtio32 mtu;
 	u8 reserved[4];
 };
 

include/linux/virtio_config.h

@@ -6,6 +6,7 @@
 #include <linux/bug.h>
 #include <linux/virtio.h>
 #include <linux/virtio_byteorder.h>
+#include <linux/compiler_types.h>
 #include <uapi/linux/virtio_config.h>
 
 struct irq_affinity;
@@ -162,16 +163,16 @@ static inline bool virtio_has_feature(const struct virtio_device *vdev,
 }
 
 /**
- * virtio_has_iommu_quirk - determine whether this device has the iommu quirk
+ * virtio_has_dma_quirk - determine whether this device has the DMA quirk
  * @vdev: the device
  */
-static inline bool virtio_has_iommu_quirk(const struct virtio_device *vdev)
+static inline bool virtio_has_dma_quirk(const struct virtio_device *vdev)
 {
 	/*
 	 * Note the reverse polarity of the quirk feature (compared to most
 	 * other features), this is for compatibility with legacy systems.
 	 */
-	return !virtio_has_feature(vdev, VIRTIO_F_IOMMU_PLATFORM);
+	return !virtio_has_feature(vdev, VIRTIO_F_ACCESS_PLATFORM);
 }
 
 static inline
@@ -287,70 +288,133 @@ static inline __virtio64 cpu_to_virtio64(struct virtio_device *vdev, u64 val)
 	return __cpu_to_virtio64(virtio_is_little_endian(vdev), val);
 }
 
+#define virtio_to_cpu(vdev, x) \
+	_Generic((x), \
+		__u8: (x), \
+		__virtio16: virtio16_to_cpu((vdev), (x)), \
+		__virtio32: virtio32_to_cpu((vdev), (x)), \
+		__virtio64: virtio64_to_cpu((vdev), (x)) \
+		)
+
+#define cpu_to_virtio(vdev, x, m) \
+	_Generic((m), \
+		__u8: (x), \
+		__virtio16: cpu_to_virtio16((vdev), (x)), \
+		__virtio32: cpu_to_virtio32((vdev), (x)), \
+		__virtio64: cpu_to_virtio64((vdev), (x)) \
+		)
+
+#define __virtio_native_type(structname, member) \
+	typeof(virtio_to_cpu(NULL, ((structname*)0)->member))
+
 /* Config space accessors. */
 #define virtio_cread(vdev, structname, member, ptr)			\
 	do {								\
+		typeof(((structname*)0)->member) virtio_cread_v;	\
+									\
 		might_sleep();						\
-		/* Must match the member's type, and be integer */	\
-		if (!typecheck(typeof((((structname*)0)->member)), *(ptr))) \
-			(*ptr) = 1;					\
+		/* Sanity check: must match the member's type */	\
+		typecheck(typeof(virtio_to_cpu((vdev), virtio_cread_v)), *(ptr)); \
 									\
-		switch (sizeof(*ptr)) {					\
+		switch (sizeof(virtio_cread_v)) {			\
 		case 1:							\
-			*(ptr) = virtio_cread8(vdev,			\
-					       offsetof(structname, member)); \
-			break;						\
 		case 2:							\
-			*(ptr) = virtio_cread16(vdev,			\
-						offsetof(structname, member)); \
-			break;						\
 		case 4:							\
-			*(ptr) = virtio_cread32(vdev,			\
-						offsetof(structname, member)); \
-			break;						\
-		case 8:							\
-			*(ptr) = virtio_cread64(vdev,			\
-						offsetof(structname, member)); \
+			vdev->config->get((vdev), 			\
+					  offsetof(structname, member), \
+					  &virtio_cread_v,		\
+					  sizeof(virtio_cread_v));	\
 			break;						\
 		default:						\
-			BUG();						\
+			__virtio_cread_many((vdev), 			\
+					  offsetof(structname, member), \
+					  &virtio_cread_v,		\
+					  1,				\
+					  sizeof(virtio_cread_v));	\
+			break;						\
 		}							\
+		*(ptr) = virtio_to_cpu(vdev, virtio_cread_v);		\
 	} while(0)
 
 /* Config space accessors. */
 #define virtio_cwrite(vdev, structname, member, ptr)			\
 	do {								\
+		typeof(((structname*)0)->member) virtio_cwrite_v =	\
+			cpu_to_virtio(vdev, *(ptr), ((structname*)0)->member); \
+									\
+		might_sleep();						\
+		/* Sanity check: must match the member's type */	\
+		typecheck(typeof(virtio_to_cpu((vdev), virtio_cwrite_v)), *(ptr)); \
+									\
+		vdev->config->set((vdev), offsetof(structname, member),	\
+				  &virtio_cwrite_v,			\
+				  sizeof(virtio_cwrite_v));		\
+	} while(0)
+
+/*
+ * Nothing virtio-specific about these, but let's worry about generalizing
+ * these later.
+ */
+#define virtio_le_to_cpu(x) \
+	_Generic((x), \
+		__u8: (u8)(x), \
+		 __le16: (u16)le16_to_cpu(x), \
+		 __le32: (u32)le32_to_cpu(x), \
+		 __le64: (u64)le64_to_cpu(x) \
+		)
+
+#define virtio_cpu_to_le(x, m) \
+	_Generic((m), \
+		 __u8: (x), \
+		 __le16: cpu_to_le16(x), \
+		 __le32: cpu_to_le32(x), \
+		 __le64: cpu_to_le64(x) \
+		)
+
+/* LE (e.g. modern) Config space accessors. */
+#define virtio_cread_le(vdev, structname, member, ptr)			\
+	do {								\
+		typeof(((structname*)0)->member) virtio_cread_v;	\
+									\
 		might_sleep();						\
-		/* Must match the member's type, and be integer */	\
-		if (!typecheck(typeof((((structname*)0)->member)), *(ptr))) \
-			BUG_ON((*ptr) == 1);				\
+		/* Sanity check: must match the member's type */	\
+		typecheck(typeof(virtio_le_to_cpu(virtio_cread_v)), *(ptr)); \
 									\
-		switch (sizeof(*ptr)) {					\
+		switch (sizeof(virtio_cread_v)) {			\
 		case 1:							\
-			virtio_cwrite8(vdev,				\
-				       offsetof(structname, member),	\
-				       *(ptr));				\
-			break;						\
 		case 2:							\
-			virtio_cwrite16(vdev,				\
-					offsetof(structname, member),	\
-					*(ptr));			\
-			break;						\
 		case 4:							\
-			virtio_cwrite32(vdev,				\
+			vdev->config->get((vdev), 			\
 					  offsetof(structname, member), \
-					*(ptr));			\
+					  &virtio_cread_v,		\
+					  sizeof(virtio_cread_v));	\
 			break;						\
-		case 8:							\
-			virtio_cwrite64(vdev,				\
+		default:						\
+			__virtio_cread_many((vdev), 			\
 					  offsetof(structname, member), \
-					*(ptr));			\
+					  &virtio_cread_v,		\
+					  1,				\
+					  sizeof(virtio_cread_v));	\
 			break;						\
-		default:						\
-			BUG();						\
 		}							\
+		*(ptr) = virtio_le_to_cpu(virtio_cread_v);		\
 	} while(0)
 
+#define virtio_cwrite_le(vdev, structname, member, ptr)			\
+	do {								\
+		typeof(((structname*)0)->member) virtio_cwrite_v =	\
+			virtio_cpu_to_le(*(ptr), ((structname*)0)->member); \
+									\
+		might_sleep();						\
+		/* Sanity check: must match the member's type */	\
+		typecheck(typeof(virtio_le_to_cpu(virtio_cwrite_v)), *(ptr)); \
+									\
+		vdev->config->set((vdev), offsetof(structname, member),	\
+				  &virtio_cwrite_v,			\
+				  sizeof(virtio_cwrite_v));		\
+	} while(0)
+
+
 /* Read @count fields, @bytes each. */
 static inline void __virtio_cread_many(struct virtio_device *vdev,
 				       unsigned int offset,
@@ -399,53 +463,60 @@ static inline void virtio_cwrite8(struct virtio_device *vdev,
 static inline u16 virtio_cread16(struct virtio_device *vdev,
 				 unsigned int offset)
 {
-	u16 ret;
+	__virtio16 ret;
 
 	might_sleep();
 	vdev->config->get(vdev, offset, &ret, sizeof(ret));
-	return virtio16_to_cpu(vdev, (__force __virtio16)ret);
+	return virtio16_to_cpu(vdev, ret);
 }
 
 static inline void virtio_cwrite16(struct virtio_device *vdev,
 				   unsigned int offset, u16 val)
 {
+	__virtio16 v;
+
 	might_sleep();
-	val = (__force u16)cpu_to_virtio16(vdev, val);
-	vdev->config->set(vdev, offset, &val, sizeof(val));
+	v = cpu_to_virtio16(vdev, val);
+	vdev->config->set(vdev, offset, &v, sizeof(v));
 }
 
 static inline u32 virtio_cread32(struct virtio_device *vdev,
 				 unsigned int offset)
 {
-	u32 ret;
+	__virtio32 ret;
 
 	might_sleep();
 	vdev->config->get(vdev, offset, &ret, sizeof(ret));
-	return virtio32_to_cpu(vdev, (__force __virtio32)ret);
+	return virtio32_to_cpu(vdev, ret);
 }
 
 static inline void virtio_cwrite32(struct virtio_device *vdev,
 				   unsigned int offset, u32 val)
 {
+	__virtio32 v;
+
 	might_sleep();
-	val = (__force u32)cpu_to_virtio32(vdev, val);
-	vdev->config->set(vdev, offset, &val, sizeof(val));
+	v = cpu_to_virtio32(vdev, val);
+	vdev->config->set(vdev, offset, &v, sizeof(v));
 }
 
 static inline u64 virtio_cread64(struct virtio_device *vdev,
 				 unsigned int offset)
 {
-	u64 ret;
+	__virtio64 ret;
+
 	__virtio_cread_many(vdev, offset, &ret, 1, sizeof(ret));
-	return virtio64_to_cpu(vdev, (__force __virtio64)ret);
+	return virtio64_to_cpu(vdev, ret);
 }
 
 static inline void virtio_cwrite64(struct virtio_device *vdev,
 				   unsigned int offset, u64 val)
 {
+	__virtio64 v;
+
 	might_sleep();
-	val = (__force u64)cpu_to_virtio64(vdev, val);
-	vdev->config->set(vdev, offset, &val, sizeof(val));
+	v = cpu_to_virtio64(vdev, val);
+	vdev->config->set(vdev, offset, &v, sizeof(v));
 }
 
 /* Conditional config space accessors. */
@@ -459,4 +530,14 @@ static inline void virtio_cwrite64(struct virtio_device *vdev,
 		_r;							\
 	})
 
+/* Conditional config space accessors. */
+#define virtio_cread_le_feature(vdev, fbit, structname, member, ptr)	\
+	({								\
+		int _r = 0;						\
+		if (!virtio_has_feature(vdev, fbit))			\
+			_r = -ENOENT;					\
+		else							\
+			virtio_cread_le((vdev), structname, member, ptr); \
+		_r;							\
+	})
 #endif /* _LINUX_VIRTIO_CONFIG_H */

include/uapi/linux/vhost.h

@@ -91,6 +91,8 @@
 
 /* Use message type V2 */
 #define VHOST_BACKEND_F_IOTLB_MSG_V2 0x1
+/* IOTLB can accept batching hints */
+#define VHOST_BACKEND_F_IOTLB_BATCH  0x2
 
 #define VHOST_SET_BACKEND_FEATURES _IOW(VHOST_VIRTIO, 0x25, __u64)
 #define VHOST_GET_BACKEND_FEATURES _IOR(VHOST_VIRTIO, 0x26, __u64)