1 files changed, 143 insertions, 135 deletions

diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c
index 65e7e6b44578..bd7c482c948a 100644
--- a/drivers/vfio/pci/vfio_pci.c
+++ b/drivers/vfio/pci/vfio_pci.c
@@ -378,7 +378,6 @@ static int vfio_pci_enable(struct vfio_pci_device *vdev)
 	if (!vfio_vga_disabled() && vfio_pci_is_vga(pdev))
 		vdev->has_vga = true;
 
-
 	if (vfio_pci_is_vga(pdev) &&
 	    pdev->vendor == PCI_VENDOR_ID_INTEL &&
 	    IS_ENABLED(CONFIG_VFIO_PCI_IGD)) {
@@ -389,24 +388,6 @@ static int vfio_pci_enable(struct vfio_pci_device *vdev)
 		}
 	}
 
-	if (pdev->vendor == PCI_VENDOR_ID_NVIDIA &&
-	    IS_ENABLED(CONFIG_VFIO_PCI_NVLINK2)) {
-		ret = vfio_pci_nvdia_v100_nvlink2_init(vdev);
-		if (ret && ret != -ENODEV) {
-			pci_warn(pdev, "Failed to setup NVIDIA NV2 RAM region\n");
-			goto disable_exit;
-		}
-	}
-
-	if (pdev->vendor == PCI_VENDOR_ID_IBM &&
-	    IS_ENABLED(CONFIG_VFIO_PCI_NVLINK2)) {
-		ret = vfio_pci_ibm_npu2_init(vdev);
-		if (ret && ret != -ENODEV) {
-			pci_warn(pdev, "Failed to setup NVIDIA NV2 ATSD region\n");
-			goto disable_exit;
-		}
-	}
-
 	vfio_pci_probe_mmaps(vdev);
 
 	return 0;
@@ -517,30 +498,29 @@ out:
 
 static struct pci_driver vfio_pci_driver;
 
-static struct vfio_pci_device *get_pf_vdev(struct vfio_pci_device *vdev,
-					   struct vfio_device **pf_dev)
+static struct vfio_pci_device *get_pf_vdev(struct vfio_pci_device *vdev)
 {
 	struct pci_dev *physfn = pci_physfn(vdev->pdev);
+	struct vfio_device *pf_dev;
 
 	if (!vdev->pdev->is_virtfn)
 		return NULL;
 
-	*pf_dev = vfio_device_get_from_dev(&physfn->dev);
-	if (!*pf_dev)
+	pf_dev = vfio_device_get_from_dev(&physfn->dev);
+	if (!pf_dev)
 		return NULL;
 
 	if (pci_dev_driver(physfn) != &vfio_pci_driver) {
-		vfio_device_put(*pf_dev);
+		vfio_device_put(pf_dev);
 		return NULL;
 	}
 
-	return vfio_device_data(*pf_dev);
+	return container_of(pf_dev, struct vfio_pci_device, vdev);
 }
 
 static void vfio_pci_vf_token_user_add(struct vfio_pci_device *vdev, int val)
 {
-	struct vfio_device *pf_dev;
-	struct vfio_pci_device *pf_vdev = get_pf_vdev(vdev, &pf_dev);
+	struct vfio_pci_device *pf_vdev = get_pf_vdev(vdev);
 
 	if (!pf_vdev)
 		return;
@@ -550,12 +530,13 @@ static void vfio_pci_vf_token_user_add(struct vfio_pci_device *vdev, int val)
 	WARN_ON(pf_vdev->vf_token->users < 0);
 	mutex_unlock(&pf_vdev->vf_token->lock);
 
-	vfio_device_put(pf_dev);
+	vfio_device_put(&pf_vdev->vdev);
 }
 
-static void vfio_pci_release(void *device_data)
+static void vfio_pci_release(struct vfio_device *core_vdev)
 {
-	struct vfio_pci_device *vdev = device_data;
+	struct vfio_pci_device *vdev =
+		container_of(core_vdev, struct vfio_pci_device, vdev);
 
 	mutex_lock(&vdev->reflck->lock);
 
@@ -581,9 +562,10 @@ static void vfio_pci_release(void *device_data)
 	module_put(THIS_MODULE);
 }
 
-static int vfio_pci_open(void *device_data)
+static int vfio_pci_open(struct vfio_device *core_vdev)
 {
-	struct vfio_pci_device *vdev = device_data;
+	struct vfio_pci_device *vdev =
+		container_of(core_vdev, struct vfio_pci_device, vdev);
 	int ret = 0;
 
 	if (!try_module_get(THIS_MODULE))
@@ -792,15 +774,16 @@ int vfio_pci_register_dev_region(struct vfio_pci_device *vdev,
 }
 
 struct vfio_devices {
-	struct vfio_device **devices;
+	struct vfio_pci_device **devices;
 	int cur_index;
 	int max_index;
 };
 
-static long vfio_pci_ioctl(void *device_data,
+static long vfio_pci_ioctl(struct vfio_device *core_vdev,
 			   unsigned int cmd, unsigned long arg)
 {
-	struct vfio_pci_device *vdev = device_data;
+	struct vfio_pci_device *vdev =
+		container_of(core_vdev, struct vfio_pci_device, vdev);
 	unsigned long minsz;
 
 	if (cmd == VFIO_DEVICE_GET_INFO) {
@@ -1280,9 +1263,7 @@ reset_info_exit:
 			goto hot_reset_release;
 
 		for (; mem_idx < devs.cur_index; mem_idx++) {
-			struct vfio_pci_device *tmp;
-
-			tmp = vfio_device_data(devs.devices[mem_idx]);
+			struct vfio_pci_device *tmp = devs.devices[mem_idx];
 
 			ret = down_write_trylock(&tmp->memory_lock);
 			if (!ret) {
@@ -1297,17 +1278,13 @@ reset_info_exit:
 
 hot_reset_release:
 		for (i = 0; i < devs.cur_index; i++) {
-			struct vfio_device *device;
-			struct vfio_pci_device *tmp;
-
-			device = devs.devices[i];
-			tmp = vfio_device_data(device);
+			struct vfio_pci_device *tmp = devs.devices[i];
 
 			if (i < mem_idx)
 				up_write(&tmp->memory_lock);
 			else
 				mutex_unlock(&tmp->vma_lock);
-			vfio_device_put(device);
+			vfio_device_put(&tmp->vdev);
 		}
 		kfree(devs.devices);
 
@@ -1402,11 +1379,10 @@ hot_reset_release:
 	return -ENOTTY;
 }
 
-static ssize_t vfio_pci_rw(void *device_data, char __user *buf,
+static ssize_t vfio_pci_rw(struct vfio_pci_device *vdev, char __user *buf,
 			   size_t count, loff_t *ppos, bool iswrite)
 {
 	unsigned int index = VFIO_PCI_OFFSET_TO_INDEX(*ppos);
-	struct vfio_pci_device *vdev = device_data;
 
 	if (index >= VFIO_PCI_NUM_REGIONS + vdev->num_regions)
 		return -EINVAL;
@@ -1434,22 +1410,28 @@ static ssize_t vfio_pci_rw(void *device_data, char __user *buf,
 	return -EINVAL;
 }
 
-static ssize_t vfio_pci_read(void *device_data, char __user *buf,
+static ssize_t vfio_pci_read(struct vfio_device *core_vdev, char __user *buf,
 			     size_t count, loff_t *ppos)
 {
+	struct vfio_pci_device *vdev =
+		container_of(core_vdev, struct vfio_pci_device, vdev);
+
 	if (!count)
 		return 0;
 
-	return vfio_pci_rw(device_data, buf, count, ppos, false);
+	return vfio_pci_rw(vdev, buf, count, ppos, false);
 }
 
-static ssize_t vfio_pci_write(void *device_data, const char __user *buf,
+static ssize_t vfio_pci_write(struct vfio_device *core_vdev, const char __user *buf,
 			      size_t count, loff_t *ppos)
 {
+	struct vfio_pci_device *vdev =
+		container_of(core_vdev, struct vfio_pci_device, vdev);
+
 	if (!count)
 		return 0;
 
-	return vfio_pci_rw(device_data, (char __user *)buf, count, ppos, true);
+	return vfio_pci_rw(vdev, (char __user *)buf, count, ppos, true);
 }
 
 /* Return 1 on zap and vma_lock acquired, 0 on contention (only with @try) */
@@ -1646,9 +1628,10 @@ static const struct vm_operations_struct vfio_pci_mmap_ops = {
 	.fault = vfio_pci_mmap_fault,
 };
 
-static int vfio_pci_mmap(void *device_data, struct vm_area_struct *vma)
+static int vfio_pci_mmap(struct vfio_device *core_vdev, struct vm_area_struct *vma)
 {
-	struct vfio_pci_device *vdev = device_data;
+	struct vfio_pci_device *vdev =
+		container_of(core_vdev, struct vfio_pci_device, vdev);
 	struct pci_dev *pdev = vdev->pdev;
 	unsigned int index;
 	u64 phys_len, req_len, pgoff, req_start;
@@ -1656,6 +1639,8 @@ static int vfio_pci_mmap(void *device_data, struct vm_area_struct *vma)
 
 	index = vma->vm_pgoff >> (VFIO_PCI_OFFSET_SHIFT - PAGE_SHIFT);
 
+	if (index >= VFIO_PCI_NUM_REGIONS + vdev->num_regions)
+		return -EINVAL;
 	if (vma->vm_end < vma->vm_start)
 		return -EINVAL;
 	if ((vma->vm_flags & VM_SHARED) == 0)
@@ -1664,7 +1649,7 @@ static int vfio_pci_mmap(void *device_data, struct vm_area_struct *vma)
 		int regnum = index - VFIO_PCI_NUM_REGIONS;
 		struct vfio_pci_region *region = vdev->region + regnum;
 
-		if (region && region->ops && region->ops->mmap &&
+		if (region->ops && region->ops->mmap &&
 		    (region->flags & VFIO_REGION_INFO_FLAG_MMAP))
 			return region->ops->mmap(vdev, region, vma);
 		return -EINVAL;
@@ -1714,9 +1699,10 @@ static int vfio_pci_mmap(void *device_data, struct vm_area_struct *vma)
 	return 0;
 }
 
-static void vfio_pci_request(void *device_data, unsigned int count)
+static void vfio_pci_request(struct vfio_device *core_vdev, unsigned int count)
 {
-	struct vfio_pci_device *vdev = device_data;
+	struct vfio_pci_device *vdev =
+		container_of(core_vdev, struct vfio_pci_device, vdev);
 	struct pci_dev *pdev = vdev->pdev;
 
 	mutex_lock(&vdev->igate);
@@ -1767,8 +1753,7 @@ static int vfio_pci_validate_vf_token(struct vfio_pci_device *vdev,
 		return 0; /* No VF token provided or required */
 
 	if (vdev->pdev->is_virtfn) {
-		struct vfio_device *pf_dev;
-		struct vfio_pci_device *pf_vdev = get_pf_vdev(vdev, &pf_dev);
+		struct vfio_pci_device *pf_vdev = get_pf_vdev(vdev);
 		bool match;
 
 		if (!pf_vdev) {
@@ -1781,7 +1766,7 @@ static int vfio_pci_validate_vf_token(struct vfio_pci_device *vdev,
 		}
 
 		if (!vf_token) {
-			vfio_device_put(pf_dev);
+			vfio_device_put(&pf_vdev->vdev);
 			pci_info_ratelimited(vdev->pdev,
 				"VF token required to access device\n");
 			return -EACCES;
@@ -1791,7 +1776,7 @@ static int vfio_pci_validate_vf_token(struct vfio_pci_device *vdev,
 		match = uuid_equal(uuid, &pf_vdev->vf_token->uuid);
 		mutex_unlock(&pf_vdev->vf_token->lock);
 
-		vfio_device_put(pf_dev);
+		vfio_device_put(&pf_vdev->vdev);
 
 		if (!match) {
 			pci_info_ratelimited(vdev->pdev,
@@ -1830,9 +1815,10 @@ static int vfio_pci_validate_vf_token(struct vfio_pci_device *vdev,
 
 #define VF_TOKEN_ARG "vf_token="
 
-static int vfio_pci_match(void *device_data, char *buf)
+static int vfio_pci_match(struct vfio_device *core_vdev, char *buf)
 {
-	struct vfio_pci_device *vdev = device_data;
+	struct vfio_pci_device *vdev =
+		container_of(core_vdev, struct vfio_pci_device, vdev);
 	bool vf_token = false;
 	uuid_t uuid;
 	int ret;
@@ -1922,6 +1908,68 @@ static int vfio_pci_bus_notifier(struct notifier_block *nb,
 	return 0;
 }
 
+static int vfio_pci_vf_init(struct vfio_pci_device *vdev)
+{
+	struct pci_dev *pdev = vdev->pdev;
+	int ret;
+
+	if (!pdev->is_physfn)
+		return 0;
+
+	vdev->vf_token = kzalloc(sizeof(*vdev->vf_token), GFP_KERNEL);
+	if (!vdev->vf_token)
+		return -ENOMEM;
+
+	mutex_init(&vdev->vf_token->lock);
+	uuid_gen(&vdev->vf_token->uuid);
+
+	vdev->nb.notifier_call = vfio_pci_bus_notifier;
+	ret = bus_register_notifier(&pci_bus_type, &vdev->nb);
+	if (ret) {
+		kfree(vdev->vf_token);
+		return ret;
+	}
+	return 0;
+}
+
+static void vfio_pci_vf_uninit(struct vfio_pci_device *vdev)
+{
+	if (!vdev->vf_token)
+		return;
+
+	bus_unregister_notifier(&pci_bus_type, &vdev->nb);
+	WARN_ON(vdev->vf_token->users);
+	mutex_destroy(&vdev->vf_token->lock);
+	kfree(vdev->vf_token);
+}
+
+static int vfio_pci_vga_init(struct vfio_pci_device *vdev)
+{
+	struct pci_dev *pdev = vdev->pdev;
+	int ret;
+
+	if (!vfio_pci_is_vga(pdev))
+		return 0;
+
+	ret = vga_client_register(pdev, vdev, NULL, vfio_pci_set_vga_decode);
+	if (ret)
+		return ret;
+	vga_set_legacy_decoding(pdev, vfio_pci_set_vga_decode(vdev, false));
+	return 0;
+}
+
+static void vfio_pci_vga_uninit(struct vfio_pci_device *vdev)
+{
+	struct pci_dev *pdev = vdev->pdev;
+
+	if (!vfio_pci_is_vga(pdev))
+		return;
+	vga_client_register(pdev, NULL, NULL, NULL);
+	vga_set_legacy_decoding(pdev, VGA_RSRC_NORMAL_IO | VGA_RSRC_NORMAL_MEM |
+					      VGA_RSRC_LEGACY_IO |
+					      VGA_RSRC_LEGACY_MEM);
+}
+
 static int vfio_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 {
 	struct vfio_pci_device *vdev;
@@ -1957,6 +2005,7 @@ static int vfio_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		goto out_group_put;
 	}
 
+	vfio_init_group_dev(&vdev->vdev, &pdev->dev, &vfio_pci_ops);
 	vdev->pdev = pdev;
 	vdev->irq_type = VFIO_PCI_NUM_IRQS;
 	mutex_init(&vdev->igate);
@@ -1968,35 +2017,15 @@ static int vfio_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	INIT_LIST_HEAD(&vdev->vma_list);
 	init_rwsem(&vdev->memory_lock);
 
-	ret = vfio_add_group_dev(&pdev->dev, &vfio_pci_ops, vdev);
+	ret = vfio_pci_reflck_attach(vdev);
 	if (ret)
 		goto out_free;
-
-	ret = vfio_pci_reflck_attach(vdev);
+	ret = vfio_pci_vf_init(vdev);
 	if (ret)
-		goto out_del_group_dev;
-
-	if (pdev->is_physfn) {
-		vdev->vf_token = kzalloc(sizeof(*vdev->vf_token), GFP_KERNEL);
-		if (!vdev->vf_token) {
-			ret = -ENOMEM;
-			goto out_reflck;
-		}
-
-		mutex_init(&vdev->vf_token->lock);
-		uuid_gen(&vdev->vf_token->uuid);
-
-		vdev->nb.notifier_call = vfio_pci_bus_notifier;
-		ret = bus_register_notifier(&pci_bus_type, &vdev->nb);
-		if (ret)
-			goto out_vf_token;
-	}
-
-	if (vfio_pci_is_vga(pdev)) {
-		vga_client_register(pdev, vdev, NULL, vfio_pci_set_vga_decode);
-		vga_set_legacy_decoding(pdev,
-					vfio_pci_set_vga_decode(vdev, false));
-	}
+		goto out_reflck;
+	ret = vfio_pci_vga_init(vdev);
+	if (ret)
+		goto out_vf;
 
 	vfio_pci_probe_power_state(vdev);
 
@@ -2014,15 +2043,21 @@ static int vfio_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		vfio_pci_set_power_state(vdev, PCI_D3hot);
 	}
 
-	return ret;
+	ret = vfio_register_group_dev(&vdev->vdev);
+	if (ret)
+		goto out_power;
+	dev_set_drvdata(&pdev->dev, vdev);
+	return 0;
 
-out_vf_token:
-	kfree(vdev->vf_token);
+out_power:
+	if (!disable_idle_d3)
+		vfio_pci_set_power_state(vdev, PCI_D0);
+out_vf:
+	vfio_pci_vf_uninit(vdev);
 out_reflck:
 	vfio_pci_reflck_put(vdev->reflck);
-out_del_group_dev:
-	vfio_del_group_dev(&pdev->dev);
 out_free:
+	kfree(vdev->pm_save);
 	kfree(vdev);
 out_group_put:
 	vfio_iommu_group_put(group, &pdev->dev);
@@ -2031,41 +2066,25 @@ out_group_put:
 
 static void vfio_pci_remove(struct pci_dev *pdev)
 {
-	struct vfio_pci_device *vdev;
+	struct vfio_pci_device *vdev = dev_get_drvdata(&pdev->dev);
 
 	pci_disable_sriov(pdev);
 
-	vdev = vfio_del_group_dev(&pdev->dev);
-	if (!vdev)
-		return;
-
-	if (vdev->vf_token) {
-		WARN_ON(vdev->vf_token->users);
-		mutex_destroy(&vdev->vf_token->lock);
-		kfree(vdev->vf_token);
-	}
-
-	if (vdev->nb.notifier_call)
-		bus_unregister_notifier(&pci_bus_type, &vdev->nb);
+	vfio_unregister_group_dev(&vdev->vdev);
 
+	vfio_pci_vf_uninit(vdev);
 	vfio_pci_reflck_put(vdev->reflck);
+	vfio_pci_vga_uninit(vdev);
 
 	vfio_iommu_group_put(pdev->dev.iommu_group, &pdev->dev);
-	kfree(vdev->region);
-	mutex_destroy(&vdev->ioeventfds_lock);
 
 	if (!disable_idle_d3)
 		vfio_pci_set_power_state(vdev, PCI_D0);
 
+	mutex_destroy(&vdev->ioeventfds_lock);
+	kfree(vdev->region);
 	kfree(vdev->pm_save);
 	kfree(vdev);
-
-	if (vfio_pci_is_vga(pdev)) {
-		vga_client_register(pdev, NULL, NULL, NULL);
-		vga_set_legacy_decoding(pdev,
-				VGA_RSRC_NORMAL_IO | VGA_RSRC_NORMAL_MEM |
-				VGA_RSRC_LEGACY_IO | VGA_RSRC_LEGACY_MEM);
-	}
 }
 
 static pci_ers_result_t vfio_pci_aer_err_detected(struct pci_dev *pdev,
@@ -2078,11 +2097,7 @@ static pci_ers_result_t vfio_pci_aer_err_detected(struct pci_dev *pdev,
 	if (device == NULL)
 		return PCI_ERS_RESULT_DISCONNECT;
 
-	vdev = vfio_device_data(device);
-	if (vdev == NULL) {
-		vfio_device_put(device);
-		return PCI_ERS_RESULT_DISCONNECT;
-	}
+	vdev = container_of(device, struct vfio_pci_device, vdev);
 
 	mutex_lock(&vdev->igate);
 
@@ -2098,7 +2113,6 @@ static pci_ers_result_t vfio_pci_aer_err_detected(struct pci_dev *pdev,
 
 static int vfio_pci_sriov_configure(struct pci_dev *pdev, int nr_virtfn)
 {
-	struct vfio_pci_device *vdev;
 	struct vfio_device *device;
 	int ret = 0;
 
@@ -2111,12 +2125,6 @@ static int vfio_pci_sriov_configure(struct pci_dev *pdev, int nr_virtfn)
 	if (!device)
 		return -ENODEV;
 
-	vdev = vfio_device_data(device);
-	if (!vdev) {
-		vfio_device_put(device);
-		return -ENODEV;
-	}
-
 	if (nr_virtfn == 0)
 		pci_disable_sriov(pdev);
 	else
@@ -2176,7 +2184,7 @@ static int vfio_pci_reflck_find(struct pci_dev *pdev, void *data)
 		return 0;
 	}
 
-	vdev = vfio_device_data(device);
+	vdev = container_of(device, struct vfio_pci_device, vdev);
 
 	if (vdev->reflck) {
 		vfio_pci_reflck_get(vdev->reflck);
@@ -2238,7 +2246,7 @@ static int vfio_pci_get_unused_devs(struct pci_dev *pdev, void *data)
 		return -EBUSY;
 	}
 
-	vdev = vfio_device_data(device);
+	vdev = container_of(device, struct vfio_pci_device, vdev);
 
 	/* Fault if the device is not unused */
 	if (vdev->refcnt) {
@@ -2246,7 +2254,7 @@ static int vfio_pci_get_unused_devs(struct pci_dev *pdev, void *data)
 		return -EBUSY;
 	}
 
-	devs->devices[devs->cur_index++] = device;
+	devs->devices[devs->cur_index++] = vdev;
 	return 0;
 }
 
@@ -2268,7 +2276,7 @@ static int vfio_pci_try_zap_and_vma_lock_cb(struct pci_dev *pdev, void *data)
 		return -EBUSY;
 	}
 
-	vdev = vfio_device_data(device);
+	vdev = container_of(device, struct vfio_pci_device, vdev);
 
 	/*
 	 * Locking multiple devices is prone to deadlock, runaway and
@@ -2279,7 +2287,7 @@ static int vfio_pci_try_zap_and_vma_lock_cb(struct pci_dev *pdev, void *data)
 		return -EBUSY;
 	}
 
-	devs->devices[devs->cur_index++] = device;
+	devs->devices[devs->cur_index++] = vdev;
 	return 0;
 }
 
@@ -2327,7 +2335,7 @@ static void vfio_pci_try_bus_reset(struct vfio_pci_device *vdev)
 
 	/* Does at least one need a reset? */
 	for (i = 0; i < devs.cur_index; i++) {
-		tmp = vfio_device_data(devs.devices[i]);
+		tmp = devs.devices[i];
 		if (tmp->needs_reset) {
 			ret = pci_reset_bus(vdev->pdev);
 			break;
@@ -2336,7 +2344,7 @@ static void vfio_pci_try_bus_reset(struct vfio_pci_device *vdev)
 
 put_devs:
 	for (i = 0; i < devs.cur_index; i++) {
-		tmp = vfio_device_data(devs.devices[i]);
+		tmp = devs.devices[i];
 
 		/*
 		 * If reset was successful, affected devices no longer need
@@ -2352,7 +2360,7 @@ put_devs:
 				vfio_pci_set_power_state(tmp, PCI_D3hot);
 		}
 
-		vfio_device_put(devs.devices[i]);
+		vfio_device_put(&tmp->vdev);
 	}
 
 	kfree(devs.devices);
@@ -2409,7 +2417,7 @@ static int __init vfio_pci_init(void)
 {
 	int ret;
 
-	/* Allocate shared config space permision data used by all devices */
+	/* Allocate shared config space permission data used by all devices */
 	ret = vfio_pci_init_perm_bits();
 	if (ret)
 		return ret;