1 files changed, 397 insertions, 46 deletions

diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c
index b28e66c4376..010e0f8b8e4 100644
--- a/drivers/vfio/pci/vfio_pci.c
+++ b/drivers/vfio/pci/vfio_pci.c
@@ -13,6 +13,7 @@
 
 #include <linux/device.h>
 #include <linux/eventfd.h>
+#include <linux/file.h>
 #include <linux/interrupt.h>
 #include <linux/iommu.h>
 #include <linux/module.h>
@@ -56,7 +57,8 @@ static int vfio_pci_enable(struct vfio_pci_device *vdev)
 
 	ret = vfio_config_init(vdev);
 	if (ret) {
-		pci_load_and_free_saved_state(pdev, &vdev->pci_saved_state);
+		kfree(vdev->pci_saved_state);
+		vdev->pci_saved_state = NULL;
 		pci_disable_device(pdev);
 		return ret;
 	}
@@ -70,7 +72,7 @@ static int vfio_pci_enable(struct vfio_pci_device *vdev)
 		pci_write_config_word(pdev, PCI_COMMAND, cmd);
 	}
 
-	msix_pos = pci_find_capability(pdev, PCI_CAP_ID_MSIX);
+	msix_pos = pdev->msix_cap;
 	if (msix_pos) {
 		u16 flags;
 		u32 table;
@@ -78,12 +80,17 @@ static int vfio_pci_enable(struct vfio_pci_device *vdev)
 		pci_read_config_word(pdev, msix_pos + PCI_MSIX_FLAGS, &flags);
 		pci_read_config_dword(pdev, msix_pos + PCI_MSIX_TABLE, &table);
 
-		vdev->msix_bar = table & PCI_MSIX_FLAGS_BIRMASK;
-		vdev->msix_offset = table & ~PCI_MSIX_FLAGS_BIRMASK;
+		vdev->msix_bar = table & PCI_MSIX_TABLE_BIR;
+		vdev->msix_offset = table & PCI_MSIX_TABLE_OFFSET;
 		vdev->msix_size = ((flags & PCI_MSIX_FLAGS_QSIZE) + 1) * 16;
 	} else
 		vdev->msix_bar = 0xFF;
 
+#ifdef CONFIG_VFIO_PCI_VGA
+	if ((pdev->class >> 8) == PCI_CLASS_DISPLAY_VGA)
+		vdev->has_vga = true;
+#endif
+
 	return 0;
 }
 
@@ -132,8 +139,16 @@ static void vfio_pci_disable(struct vfio_pci_device *vdev)
 	 */
 	pci_write_config_word(pdev, PCI_COMMAND, PCI_COMMAND_INTX_DISABLE);
 
-	if (vdev->reset_works)
-		__pci_reset_function(pdev);
+	/*
+	 * Try to reset the device.  The success of this is dependent on
+	 * being able to lock the device, which is not always possible.
+	 */
+	if (vdev->reset_works) {
+		int ret = pci_try_reset_function(pdev);
+		if (ret)
+			pr_warn("%s: Failed to reset device %s (%d)\n",
+				__func__, dev_name(&pdev->dev), ret);
+	}
 
 	pci_restore_state(pdev);
 }
@@ -178,29 +193,134 @@ static int vfio_pci_get_irq_count(struct vfio_pci_device *vdev, int irq_type)
 		u8 pos;
 		u16 flags;
 
-		pos = pci_find_capability(vdev->pdev, PCI_CAP_ID_MSI);
+		pos = vdev->pdev->msi_cap;
 		if (pos) {
 			pci_read_config_word(vdev->pdev,
 					     pos + PCI_MSI_FLAGS, &flags);
-
-			return 1 << (flags & PCI_MSI_FLAGS_QMASK);
+			return 1 << ((flags & PCI_MSI_FLAGS_QMASK) >> 1);
 		}
 	} else if (irq_type == VFIO_PCI_MSIX_IRQ_INDEX) {
 		u8 pos;
 		u16 flags;
 
-		pos = pci_find_capability(vdev->pdev, PCI_CAP_ID_MSIX);
+		pos = vdev->pdev->msix_cap;
 		if (pos) {
 			pci_read_config_word(vdev->pdev,
 					     pos + PCI_MSIX_FLAGS, &flags);
 
 			return (flags & PCI_MSIX_FLAGS_QSIZE) + 1;
 		}
-	}
+	} else if (irq_type == VFIO_PCI_ERR_IRQ_INDEX)
+		if (pci_is_pcie(vdev->pdev))
+			return 1;
+
+	return 0;
+}
 
+static int vfio_pci_count_devs(struct pci_dev *pdev, void *data)
+{
+	(*(int *)data)++;
 	return 0;
 }
 
+struct vfio_pci_fill_info {
+	int max;
+	int cur;
+	struct vfio_pci_dependent_device *devices;
+};
+
+static int vfio_pci_fill_devs(struct pci_dev *pdev, void *data)
+{
+	struct vfio_pci_fill_info *fill = data;
+	struct iommu_group *iommu_group;
+
+	if (fill->cur == fill->max)
+		return -EAGAIN; /* Something changed, try again */
+
+	iommu_group = iommu_group_get(&pdev->dev);
+	if (!iommu_group)
+		return -EPERM; /* Cannot reset non-isolated devices */
+
+	fill->devices[fill->cur].group_id = iommu_group_id(iommu_group);
+	fill->devices[fill->cur].segment = pci_domain_nr(pdev->bus);
+	fill->devices[fill->cur].bus = pdev->bus->number;
+	fill->devices[fill->cur].devfn = pdev->devfn;
+	fill->cur++;
+	iommu_group_put(iommu_group);
+	return 0;
+}
+
+struct vfio_pci_group_entry {
+	struct vfio_group *group;
+	int id;
+};
+
+struct vfio_pci_group_info {
+	int count;
+	struct vfio_pci_group_entry *groups;
+};
+
+static int vfio_pci_validate_devs(struct pci_dev *pdev, void *data)
+{
+	struct vfio_pci_group_info *info = data;
+	struct iommu_group *group;
+	int id, i;
+
+	group = iommu_group_get(&pdev->dev);
+	if (!group)
+		return -EPERM;
+
+	id = iommu_group_id(group);
+
+	for (i = 0; i < info->count; i++)
+		if (info->groups[i].id == id)
+			break;
+
+	iommu_group_put(group);
+
+	return (i == info->count) ? -EINVAL : 0;
+}
+
+static bool vfio_pci_dev_below_slot(struct pci_dev *pdev, struct pci_slot *slot)
+{
+	for (; pdev; pdev = pdev->bus->self)
+		if (pdev->bus == slot->bus)
+			return (pdev->slot == slot);
+	return false;
+}
+
+struct vfio_pci_walk_info {
+	int (*fn)(struct pci_dev *, void *data);
+	void *data;
+	struct pci_dev *pdev;
+	bool slot;
+	int ret;
+};
+
+static int vfio_pci_walk_wrapper(struct pci_dev *pdev, void *data)
+{
+	struct vfio_pci_walk_info *walk = data;
+
+	if (!walk->slot || vfio_pci_dev_below_slot(pdev, walk->pdev->slot))
+		walk->ret = walk->fn(pdev, walk->data);
+
+	return walk->ret;
+}
+
+static int vfio_pci_for_each_slot_or_bus(struct pci_dev *pdev,
+					 int (*fn)(struct pci_dev *,
+						   void *data), void *data,
+					 bool slot)
+{
+	struct vfio_pci_walk_info walk = {
+		.fn = fn, .data = data, .pdev = pdev, .slot = slot, .ret = 0,
+	};
+
+	pci_walk_bus(pdev->bus, vfio_pci_walk_wrapper, &walk);
+
+	return walk.ret;
+}
+
 static long vfio_pci_ioctl(void *device_data,
 			   unsigned int cmd, unsigned long arg)
 {
@@ -285,6 +405,16 @@ static long vfio_pci_ioctl(void *device_data,
 			info.flags = VFIO_REGION_INFO_FLAG_READ;
 			break;
 		}
+		case VFIO_PCI_VGA_REGION_INDEX:
+			if (!vdev->has_vga)
+				return -EINVAL;
+
+			info.offset = VFIO_PCI_INDEX_TO_OFFSET(info.index);
+			info.size = 0xc0000;
+			info.flags = VFIO_REGION_INFO_FLAG_READ |
+				     VFIO_REGION_INFO_FLAG_WRITE;
+
+			break;
 		default:
 			return -EINVAL;
 		}
@@ -302,6 +432,17 @@ static long vfio_pci_ioctl(void *device_data,
 		if (info.argsz < minsz || info.index >= VFIO_PCI_NUM_IRQS)
 			return -EINVAL;
 
+		switch (info.index) {
+		case VFIO_PCI_INTX_IRQ_INDEX ... VFIO_PCI_MSIX_IRQ_INDEX:
+			break;
+		case VFIO_PCI_ERR_IRQ_INDEX:
+			if (pci_is_pcie(vdev->pdev))
+				break;
+		/* pass thru to return error */
+		default:
+			return -EINVAL;
+		}
+
 		info.flags = VFIO_IRQ_INFO_EVENTFD;
 
 		info.count = vfio_pci_get_irq_count(vdev, info.index);
@@ -331,6 +472,7 @@ static long vfio_pci_ioctl(void *device_data,
 
 		if (!(hdr.flags & VFIO_IRQ_SET_DATA_NONE)) {
 			size_t size;
+			int max = vfio_pci_get_irq_count(vdev, hdr.index);
 
 			if (hdr.flags & VFIO_IRQ_SET_DATA_BOOL)
 				size = sizeof(uint8_t);
@@ -340,7 +482,7 @@ static long vfio_pci_ioctl(void *device_data,
 				return -EINVAL;
 
 			if (hdr.argsz - minsz < hdr.count * size ||
-			    hdr.count > vfio_pci_get_irq_count(vdev, hdr.index))
+			    hdr.start >= max || hdr.start + hdr.count > max)
 				return -EINVAL;
 
 			data = memdup_user((void __user *)(arg + minsz),
@@ -359,59 +501,236 @@ static long vfio_pci_ioctl(void *device_data,
 
 		return ret;
 
-	} else if (cmd == VFIO_DEVICE_RESET)
+	} else if (cmd == VFIO_DEVICE_RESET) {
 		return vdev->reset_works ?
-			pci_reset_function(vdev->pdev) : -EINVAL;
+			pci_try_reset_function(vdev->pdev) : -EINVAL;
+
+	} else if (cmd == VFIO_DEVICE_GET_PCI_HOT_RESET_INFO) {
+		struct vfio_pci_hot_reset_info hdr;
+		struct vfio_pci_fill_info fill = { 0 };
+		struct vfio_pci_dependent_device *devices = NULL;
+		bool slot = false;
+		int ret = 0;
+
+		minsz = offsetofend(struct vfio_pci_hot_reset_info, count);
+
+		if (copy_from_user(&hdr, (void __user *)arg, minsz))
+			return -EFAULT;
+
+		if (hdr.argsz < minsz)
+			return -EINVAL;
+
+		hdr.flags = 0;
+
+		/* Can we do a slot or bus reset or neither? */
+		if (!pci_probe_reset_slot(vdev->pdev->slot))
+			slot = true;
+		else if (pci_probe_reset_bus(vdev->pdev->bus))
+			return -ENODEV;
+
+		/* How many devices are affected? */
+		ret = vfio_pci_for_each_slot_or_bus(vdev->pdev,
+						    vfio_pci_count_devs,
+						    &fill.max, slot);
+		if (ret)
+			return ret;
+
+		WARN_ON(!fill.max); /* Should always be at least one */
+
+		/*
+		 * If there's enough space, fill it now, otherwise return
+		 * -ENOSPC and the number of devices affected.
+		 */
+		if (hdr.argsz < sizeof(hdr) + (fill.max * sizeof(*devices))) {
+			ret = -ENOSPC;
+			hdr.count = fill.max;
+			goto reset_info_exit;
+		}
+
+		devices = kcalloc(fill.max, sizeof(*devices), GFP_KERNEL);
+		if (!devices)
+			return -ENOMEM;
+
+		fill.devices = devices;
+
+		ret = vfio_pci_for_each_slot_or_bus(vdev->pdev,
+						    vfio_pci_fill_devs,
+						    &fill, slot);
+
+		/*
+		 * If a device was removed between counting and filling,
+		 * we may come up short of fill.max.  If a device was
+		 * added, we'll have a return of -EAGAIN above.
+		 */
+		if (!ret)
+			hdr.count = fill.cur;
+
+reset_info_exit:
+		if (copy_to_user((void __user *)arg, &hdr, minsz))
+			ret = -EFAULT;
+
+		if (!ret) {
+			if (copy_to_user((void __user *)(arg + minsz), devices,
+					 hdr.count * sizeof(*devices)))
+				ret = -EFAULT;
+		}
+
+		kfree(devices);
+		return ret;
+
+	} else if (cmd == VFIO_DEVICE_PCI_HOT_RESET) {
+		struct vfio_pci_hot_reset hdr;
+		int32_t *group_fds;
+		struct vfio_pci_group_entry *groups;
+		struct vfio_pci_group_info info;
+		bool slot = false;
+		int i, count = 0, ret = 0;
+
+		minsz = offsetofend(struct vfio_pci_hot_reset, count);
+
+		if (copy_from_user(&hdr, (void __user *)arg, minsz))
+			return -EFAULT;
+
+		if (hdr.argsz < minsz || hdr.flags)
+			return -EINVAL;
+
+		/* Can we do a slot or bus reset or neither? */
+		if (!pci_probe_reset_slot(vdev->pdev->slot))
+			slot = true;
+		else if (pci_probe_reset_bus(vdev->pdev->bus))
+			return -ENODEV;
+
+		/*
+		 * We can't let userspace give us an arbitrarily large
+		 * buffer to copy, so verify how many we think there
+		 * could be.  Note groups can have multiple devices so
+		 * one group per device is the max.
+		 */
+		ret = vfio_pci_for_each_slot_or_bus(vdev->pdev,
+						    vfio_pci_count_devs,
+						    &count, slot);
+		if (ret)
+			return ret;
+
+		/* Somewhere between 1 and count is OK */
+		if (!hdr.count || hdr.count > count)
+			return -EINVAL;
+
+		group_fds = kcalloc(hdr.count, sizeof(*group_fds), GFP_KERNEL);
+		groups = kcalloc(hdr.count, sizeof(*groups), GFP_KERNEL);
+		if (!group_fds || !groups) {
+			kfree(group_fds);
+			kfree(groups);
+			return -ENOMEM;
+		}
+
+		if (copy_from_user(group_fds, (void __user *)(arg + minsz),
+				   hdr.count * sizeof(*group_fds))) {
+			kfree(group_fds);
+			kfree(groups);
+			return -EFAULT;
+		}
+
+		/*
+		 * For each group_fd, get the group through the vfio external
+		 * user interface and store the group and iommu ID.  This
+		 * ensures the group is held across the reset.
+		 */
+		for (i = 0; i < hdr.count; i++) {
+			struct vfio_group *group;
+			struct fd f = fdget(group_fds[i]);
+			if (!f.file) {
+				ret = -EBADF;
+				break;
+			}
+
+			group = vfio_group_get_external_user(f.file);
+			fdput(f);
+			if (IS_ERR(group)) {
+				ret = PTR_ERR(group);
+				break;
+			}
+
+			groups[i].group = group;
+			groups[i].id = vfio_external_user_iommu_id(group);
+		}
+
+		kfree(group_fds);
+
+		/* release reference to groups on error */
+		if (ret)
+			goto hot_reset_release;
+
+		info.count = hdr.count;
+		info.groups = groups;
+
+		/*
+		 * Test whether all the affected devices are contained
+		 * by the set of groups provided by the user.
+		 */
+		ret = vfio_pci_for_each_slot_or_bus(vdev->pdev,
+						    vfio_pci_validate_devs,
+						    &info, slot);
+		if (!ret)
+			/* User has access, do the reset */
+			ret = slot ? pci_try_reset_slot(vdev->pdev->slot) :
+				     pci_try_reset_bus(vdev->pdev->bus);
+
+hot_reset_release:
+		for (i--; i >= 0; i--)
+			vfio_group_put_external_user(groups[i].group);
+
+		kfree(groups);
+		return ret;
+	}
 
 	return -ENOTTY;
 }
 
-static ssize_t vfio_pci_read(void *device_data, char __user *buf,
-			     size_t count, loff_t *ppos)
+static ssize_t vfio_pci_rw(void *device_data, 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;
-	struct pci_dev *pdev = vdev->pdev;
 
 	if (index >= VFIO_PCI_NUM_REGIONS)
 		return -EINVAL;
 
-	if (index == VFIO_PCI_CONFIG_REGION_INDEX)
-		return vfio_pci_config_readwrite(vdev, buf, count, ppos, false);
-	else if (index == VFIO_PCI_ROM_REGION_INDEX)
-		return vfio_pci_mem_readwrite(vdev, buf, count, ppos, false);
-	else if (pci_resource_flags(pdev, index) & IORESOURCE_IO)
-		return vfio_pci_io_readwrite(vdev, buf, count, ppos, false);
-	else if (pci_resource_flags(pdev, index) & IORESOURCE_MEM)
-		return vfio_pci_mem_readwrite(vdev, buf, count, ppos, false);
+	switch (index) {
+	case VFIO_PCI_CONFIG_REGION_INDEX:
+		return vfio_pci_config_rw(vdev, buf, count, ppos, iswrite);
+
+	case VFIO_PCI_ROM_REGION_INDEX:
+		if (iswrite)
+			return -EINVAL;
+		return vfio_pci_bar_rw(vdev, buf, count, ppos, false);
+
+	case VFIO_PCI_BAR0_REGION_INDEX ... VFIO_PCI_BAR5_REGION_INDEX:
+		return vfio_pci_bar_rw(vdev, buf, count, ppos, iswrite);
+
+	case VFIO_PCI_VGA_REGION_INDEX:
+		return vfio_pci_vga_rw(vdev, buf, count, ppos, iswrite);
+	}
 
 	return -EINVAL;
 }
 
-static ssize_t vfio_pci_write(void *device_data, const char __user *buf,
-			      size_t count, loff_t *ppos)
+static ssize_t vfio_pci_read(void *device_data, char __user *buf,
+			     size_t count, loff_t *ppos)
 {
-	unsigned int index = VFIO_PCI_OFFSET_TO_INDEX(*ppos);
-	struct vfio_pci_device *vdev = device_data;
-	struct pci_dev *pdev = vdev->pdev;
+	if (!count)
+		return 0;
 
-	if (index >= VFIO_PCI_NUM_REGIONS)
-		return -EINVAL;
+	return vfio_pci_rw(device_data, buf, count, ppos, false);
+}
 
-	if (index == VFIO_PCI_CONFIG_REGION_INDEX)
-		return vfio_pci_config_readwrite(vdev, (char __user *)buf,
-						 count, ppos, true);
-	else if (index == VFIO_PCI_ROM_REGION_INDEX)
-		return -EINVAL;
-	else if (pci_resource_flags(pdev, index) & IORESOURCE_IO)
-		return vfio_pci_io_readwrite(vdev, (char __user *)buf,
-					     count, ppos, true);
-	else if (pci_resource_flags(pdev, index) & IORESOURCE_MEM) {
-		return vfio_pci_mem_readwrite(vdev, (char __user *)buf,
-					      count, ppos, true);
-	}
+static ssize_t vfio_pci_write(void *device_data, const char __user *buf,
+			      size_t count, loff_t *ppos)
+{
+	if (!count)
+		return 0;
 
-	return -EINVAL;
+	return vfio_pci_rw(device_data, (char __user *)buf, count, ppos, true);
 }
 
 static int vfio_pci_mmap(void *device_data, struct vm_area_struct *vma)
@@ -472,7 +791,6 @@ static int vfio_pci_mmap(void *device_data, struct vm_area_struct *vma)
 	}
 
 	vma->vm_private_data = vdev;
-	vma->vm_flags |= VM_IO | VM_DONTEXPAND | VM_DONTDUMP;
 	vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
 	vma->vm_pgoff = (pci_resource_start(pdev, index) >> PAGE_SHIFT) + pgoff;
 
@@ -538,11 +856,44 @@ static void vfio_pci_remove(struct pci_dev *pdev)
 	kfree(vdev);
 }
 
+static pci_ers_result_t vfio_pci_aer_err_detected(struct pci_dev *pdev,
+						  pci_channel_state_t state)
+{
+	struct vfio_pci_device *vdev;
+	struct vfio_device *device;
+
+	device = vfio_device_get_from_dev(&pdev->dev);
+	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;
+	}
+
+	mutex_lock(&vdev->igate);
+
+	if (vdev->err_trigger)
+		eventfd_signal(vdev->err_trigger, 1);
+
+	mutex_unlock(&vdev->igate);
+
+	vfio_device_put(device);
+
+	return PCI_ERS_RESULT_CAN_RECOVER;
+}
+
+static struct pci_error_handlers vfio_err_handlers = {
+	.error_detected = vfio_pci_aer_err_detected,
+};
+
 static struct pci_driver vfio_pci_driver = {
 	.name		= "vfio-pci",
 	.id_table	= NULL, /* only dynamic ids */
 	.probe		= vfio_pci_probe,
 	.remove		= vfio_pci_remove,
+	.err_handler	= &vfio_err_handlers,
 };
 
 static void __exit vfio_pci_cleanup(void)