4 files changed, 540 insertions, 130 deletions

diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c
index 8189cb6a86a..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;
@@ -78,8 +80,8 @@ 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;
@@ -137,8 +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);
 }
@@ -183,29 +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)
 {
@@ -317,6 +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);
@@ -346,6 +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);
@@ -355,7 +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),
@@ -374,9 +501,188 @@ 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;
 }
@@ -485,7 +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;
 
@@ -551,11 +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)
diff --git a/drivers/vfio/pci/vfio_pci_config.c b/drivers/vfio/pci/vfio_pci_config.c
index 964ff22bf28..e50790e91f7 100644
--- a/drivers/vfio/pci/vfio_pci_config.c
+++ b/drivers/vfio/pci/vfio_pci_config.c
@@ -27,6 +27,7 @@
 #include <linux/pci.h>
 #include <linux/uaccess.h>
 #include <linux/vfio.h>
+#include <linux/slab.h>
 
 #include "vfio_pci_private.h"
 
@@ -273,9 +274,10 @@ static int vfio_direct_config_read(struct vfio_pci_device *vdev, int pos,
 	return count;
 }
 
-static int vfio_direct_config_write(struct vfio_pci_device *vdev, int pos,
-				    int count, struct perm_bits *perm,
-				    int offset, __le32 val)
+/* Raw access skips any kind of virtualization */
+static int vfio_raw_config_write(struct vfio_pci_device *vdev, int pos,
+				 int count, struct perm_bits *perm,
+				 int offset, __le32 val)
 {
 	int ret;
 
@@ -286,13 +288,36 @@ static int vfio_direct_config_write(struct vfio_pci_device *vdev, int pos,
 	return count;
 }
 
-/* Default all regions to read-only, no-virtualization */
+static int vfio_raw_config_read(struct vfio_pci_device *vdev, int pos,
+				int count, struct perm_bits *perm,
+				int offset, __le32 *val)
+{
+	int ret;
+
+	ret = vfio_user_config_read(vdev->pdev, pos, val, count);
+	if (ret)
+		return pcibios_err_to_errno(ret);
+
+	return count;
+}
+
+/* Default capability regions to read-only, no-virtualization */
 static struct perm_bits cap_perms[PCI_CAP_ID_MAX + 1] = {
 	[0 ... PCI_CAP_ID_MAX] = { .readfn = vfio_direct_config_read }
 };
 static struct perm_bits ecap_perms[PCI_EXT_CAP_ID_MAX + 1] = {
 	[0 ... PCI_EXT_CAP_ID_MAX] = { .readfn = vfio_direct_config_read }
 };
+/*
+ * Default unassigned regions to raw read-write access.  Some devices
+ * require this to function as they hide registers between the gaps in
+ * config space (be2net).  Like MMIO and I/O port registers, we have
+ * to trust the hardware isolation.
+ */
+static struct perm_bits unassigned_perms = {
+	.readfn = vfio_raw_config_read,
+	.writefn = vfio_raw_config_write
+};
 
 static void free_perm_bits(struct perm_bits *perm)
 {
@@ -778,16 +803,16 @@ int __init vfio_pci_init_perm_bits(void)
 
 	/* Capabilities */
 	ret |= init_pci_cap_pm_perm(&cap_perms[PCI_CAP_ID_PM]);
-	cap_perms[PCI_CAP_ID_VPD].writefn = vfio_direct_config_write;
+	cap_perms[PCI_CAP_ID_VPD].writefn = vfio_raw_config_write;
 	ret |= init_pci_cap_pcix_perm(&cap_perms[PCI_CAP_ID_PCIX]);
-	cap_perms[PCI_CAP_ID_VNDR].writefn = vfio_direct_config_write;
+	cap_perms[PCI_CAP_ID_VNDR].writefn = vfio_raw_config_write;
 	ret |= init_pci_cap_exp_perm(&cap_perms[PCI_CAP_ID_EXP]);
 	ret |= init_pci_cap_af_perm(&cap_perms[PCI_CAP_ID_AF]);
 
 	/* Extended capabilities */
 	ret |= init_pci_ext_cap_err_perm(&ecap_perms[PCI_EXT_CAP_ID_ERR]);
 	ret |= init_pci_ext_cap_pwr_perm(&ecap_perms[PCI_EXT_CAP_ID_PWR]);
-	ecap_perms[PCI_EXT_CAP_ID_VNDR].writefn = vfio_direct_config_write;
+	ecap_perms[PCI_EXT_CAP_ID_VNDR].writefn = vfio_raw_config_write;
 
 	if (ret)
 		vfio_pci_uninit_perm_bits();
@@ -800,9 +825,6 @@ static int vfio_find_cap_start(struct vfio_pci_device *vdev, int pos)
 	u8 cap;
 	int base = (pos >= PCI_CFG_SPACE_SIZE) ? PCI_CFG_SPACE_SIZE :
 						 PCI_STD_HEADER_SIZEOF;
-	base /= 4;
-	pos /= 4;
-
 	cap = vdev->pci_config_map[pos];
 
 	if (cap == PCI_CAP_ID_BASIC)
@@ -812,7 +834,7 @@ static int vfio_find_cap_start(struct vfio_pci_device *vdev, int pos)
 	while (pos - 1 >= base && vdev->pci_config_map[pos - 1] == cap)
 		pos--;
 
-	return pos * 4;
+	return pos;
 }
 
 static int vfio_msi_config_read(struct vfio_pci_device *vdev, int pos,
@@ -953,20 +975,20 @@ static int vfio_vc_cap_len(struct vfio_pci_device *vdev, u16 pos)
 	int ret, evcc, phases, vc_arb;
 	int len = PCI_CAP_VC_BASE_SIZEOF;
 
-	ret = pci_read_config_dword(pdev, pos + PCI_VC_PORT_REG1, &tmp);
+	ret = pci_read_config_dword(pdev, pos + PCI_VC_PORT_CAP1, &tmp);
 	if (ret)
 		return pcibios_err_to_errno(ret);
 
-	evcc = tmp & PCI_VC_REG1_EVCC; /* extended vc count */
-	ret = pci_read_config_dword(pdev, pos + PCI_VC_PORT_REG2, &tmp);
+	evcc = tmp & PCI_VC_CAP1_EVCC; /* extended vc count */
+	ret = pci_read_config_dword(pdev, pos + PCI_VC_PORT_CAP2, &tmp);
 	if (ret)
 		return pcibios_err_to_errno(ret);
 
-	if (tmp & PCI_VC_REG2_128_PHASE)
+	if (tmp & PCI_VC_CAP2_128_PHASE)
 		phases = 128;
-	else if (tmp & PCI_VC_REG2_64_PHASE)
+	else if (tmp & PCI_VC_CAP2_64_PHASE)
 		phases = 64;
-	else if (tmp & PCI_VC_REG2_32_PHASE)
+	else if (tmp & PCI_VC_CAP2_32_PHASE)
 		phases = 32;
 	else
 		phases = 0;
@@ -990,6 +1012,7 @@ static int vfio_vc_cap_len(struct vfio_pci_device *vdev, u16 pos)
 static int vfio_cap_len(struct vfio_pci_device *vdev, u8 cap, u8 pos)
 {
 	struct pci_dev *pdev = vdev->pdev;
+	u32 dword;
 	u16 word;
 	u8 byte;
 	int ret;
@@ -1003,7 +1026,9 @@ static int vfio_cap_len(struct vfio_pci_device *vdev, u8 cap, u8 pos)
 			return pcibios_err_to_errno(ret);
 
 		if (PCI_X_CMD_VERSION(word)) {
-			vdev->extended_caps = true;
+			/* Test for extended capabilities */
+			pci_read_config_dword(pdev, PCI_CFG_SPACE_SIZE, &dword);
+			vdev->extended_caps = (dword != 0);
 			return PCI_CAP_PCIX_SIZEOF_V2;
 		} else
 			return PCI_CAP_PCIX_SIZEOF_V0;
@@ -1015,14 +1040,12 @@ static int vfio_cap_len(struct vfio_pci_device *vdev, u8 cap, u8 pos)
 
 		return byte;
 	case PCI_CAP_ID_EXP:
-		/* length based on version */
-		ret = pci_read_config_word(pdev, pos + PCI_EXP_FLAGS, &word);
-		if (ret)
-			return pcibios_err_to_errno(ret);
+		/* Test for extended capabilities */
+		pci_read_config_dword(pdev, PCI_CFG_SPACE_SIZE, &dword);
+		vdev->extended_caps = (dword != 0);
 
-		vdev->extended_caps = true;
-
-		if ((word & PCI_EXP_FLAGS_VERS) == 1)
+		/* length based on version */
+		if ((pcie_caps_reg(pdev) & PCI_EXP_FLAGS_VERS) == 1)
 			return PCI_CAP_EXP_ENDPOINT_SIZEOF_V1;
 		else
 			return PCI_CAP_EXP_ENDPOINT_SIZEOF_V2;
@@ -1103,8 +1126,7 @@ static int vfio_ext_cap_len(struct vfio_pci_device *vdev, u16 ecap, u16 epos)
 			return pcibios_err_to_errno(ret);
 
 		byte &= PCI_DPA_CAP_SUBSTATE_MASK;
-		byte = round_up(byte + 1, 4);
-		return PCI_DPA_BASE_SIZEOF + byte;
+		return PCI_DPA_BASE_SIZEOF + byte + 1;
 	case PCI_EXT_CAP_ID_TPH:
 		ret = pci_read_config_dword(pdev, epos + PCI_TPH_CAP, &dword);
 		if (ret)
@@ -1113,9 +1135,9 @@ static int vfio_ext_cap_len(struct vfio_pci_device *vdev, u16 ecap, u16 epos)
 		if ((dword & PCI_TPH_CAP_LOC_MASK) == PCI_TPH_LOC_CAP) {
 			int sts;
 
-			sts = byte & PCI_TPH_CAP_ST_MASK;
+			sts = dword & PCI_TPH_CAP_ST_MASK;
 			sts >>= PCI_TPH_CAP_ST_SHIFT;
-			return PCI_TPH_BASE_SIZEOF + round_up(sts * 2, 4);
+			return PCI_TPH_BASE_SIZEOF + (sts * 2) + 2;
 		}
 		return PCI_TPH_BASE_SIZEOF;
 	default:
@@ -1229,8 +1251,8 @@ static int vfio_cap_init(struct vfio_pci_device *vdev)
 		}
 
 		/* Sanity check, do we overlap other capabilities? */
-		for (i = 0; i < len; i += 4) {
-			if (likely(map[(pos + i) / 4] == PCI_CAP_ID_INVALID))
+		for (i = 0; i < len; i++) {
+			if (likely(map[pos + i] == PCI_CAP_ID_INVALID))
 				continue;
 
 			pr_warn("%s: %s pci config conflict @0x%x, was cap 0x%x now cap 0x%x\n",
@@ -1238,7 +1260,7 @@ static int vfio_cap_init(struct vfio_pci_device *vdev)
 				pos + i, map[pos + i], cap);
 		}
 
-		memset(map + (pos / 4), cap, len / 4);
+		memset(map + pos, cap, len);
 		ret = vfio_fill_vconfig_bytes(vdev, pos, len);
 		if (ret)
 			return ret;
@@ -1313,8 +1335,8 @@ static int vfio_ecap_init(struct vfio_pci_device *vdev)
 			hidden = true;
 		}
 
-		for (i = 0; i < len; i += 4) {
-			if (likely(map[(epos + i) / 4] == PCI_CAP_ID_INVALID))
+		for (i = 0; i < len; i++) {
+			if (likely(map[epos + i] == PCI_CAP_ID_INVALID))
 				continue;
 
 			pr_warn("%s: %s pci config conflict @0x%x, was ecap 0x%x now ecap 0x%x\n",
@@ -1329,7 +1351,7 @@ static int vfio_ecap_init(struct vfio_pci_device *vdev)
 		 */
 		BUILD_BUG_ON(PCI_EXT_CAP_ID_MAX >= PCI_CAP_ID_INVALID);
 
-		memset(map + (epos / 4), ecap, len / 4);
+		memset(map + epos, ecap, len);
 		ret = vfio_fill_vconfig_bytes(vdev, epos, len);
 		if (ret)
 			return ret;
@@ -1376,10 +1398,12 @@ int vfio_config_init(struct vfio_pci_device *vdev)
 	int ret;
 
 	/*
-	 * Config space, caps and ecaps are all dword aligned, so we can
-	 * use one byte per dword to record the type.
+	 * Config space, caps and ecaps are all dword aligned, so we could
+	 * use one byte per dword to record the type.  However, there are
+	 * no requiremenst on the length of a capability, so the gap between
+	 * capabilities needs byte granularity.
 	 */
-	map = kmalloc(pdev->cfg_size / 4, GFP_KERNEL);
+	map = kmalloc(pdev->cfg_size, GFP_KERNEL);
 	if (!map)
 		return -ENOMEM;
 
@@ -1392,9 +1416,9 @@ int vfio_config_init(struct vfio_pci_device *vdev)
 	vdev->pci_config_map = map;
 	vdev->vconfig = vconfig;
 
-	memset(map, PCI_CAP_ID_BASIC, PCI_STD_HEADER_SIZEOF / 4);
-	memset(map + (PCI_STD_HEADER_SIZEOF / 4), PCI_CAP_ID_INVALID,
-	       (pdev->cfg_size - PCI_STD_HEADER_SIZEOF) / 4);
+	memset(map, PCI_CAP_ID_BASIC, PCI_STD_HEADER_SIZEOF);
+	memset(map + PCI_STD_HEADER_SIZEOF, PCI_CAP_ID_INVALID,
+	       pdev->cfg_size - PCI_STD_HEADER_SIZEOF);
 
 	ret = vfio_fill_vconfig_bytes(vdev, 0, PCI_STD_HEADER_SIZEOF);
 	if (ret)
@@ -1449,6 +1473,22 @@ void vfio_config_free(struct vfio_pci_device *vdev)
 	vdev->msi_perm = NULL;
 }
 
+/*
+ * Find the remaining number of bytes in a dword that match the given
+ * position.  Stop at either the end of the capability or the dword boundary.
+ */
+static size_t vfio_pci_cap_remaining_dword(struct vfio_pci_device *vdev,
+					   loff_t pos)
+{
+	u8 cap = vdev->pci_config_map[pos];
+	size_t i;
+
+	for (i = 1; (pos + i) % 4 && vdev->pci_config_map[pos + i] == cap; i++)
+		/* nop */;
+
+	return i;
+}
+
 static ssize_t vfio_config_do_rw(struct vfio_pci_device *vdev, char __user *buf,
 				 size_t count, loff_t *ppos, bool iswrite)
 {
@@ -1457,55 +1497,48 @@ static ssize_t vfio_config_do_rw(struct vfio_pci_device *vdev, char __user *buf,
 	__le32 val = 0;
 	int cap_start = 0, offset;
 	u8 cap_id;
-	ssize_t ret = count;
+	ssize_t ret;
 
-	if (*ppos < 0 || *ppos + count > pdev->cfg_size)
+	if (*ppos < 0 || *ppos >= pdev->cfg_size ||
+	    *ppos + count > pdev->cfg_size)
 		return -EFAULT;
 
 	/*
-	 * gcc can't seem to figure out we're a static function, only called
-	 * with count of 1/2/4 and hits copy_from_user_overflow without this.
+	 * Chop accesses into aligned chunks containing no more than a
+	 * single capability.  Caller increments to the next chunk.
 	 */
-	if (count > sizeof(val))
-		return -EINVAL;
-
-	cap_id = vdev->pci_config_map[*ppos / 4];
-
-	if (cap_id == PCI_CAP_ID_INVALID) {
-		if (iswrite)
-			return ret; /* drop */
-
-		/*
-		 * Per PCI spec 3.0, section 6.1, reads from reserved and
-		 * unimplemented registers return 0
-		 */
-		if (copy_to_user(buf, &val, count))
-			return -EFAULT;
-
-		return ret;
-	}
+	count = min(count, vfio_pci_cap_remaining_dword(vdev, *ppos));
+	if (count >= 4 && !(*ppos % 4))
+		count = 4;
+	else if (count >= 2 && !(*ppos % 2))
+		count = 2;
+	else
+		count = 1;
 
-	/*
-	 * All capabilities are minimum 4 bytes and aligned on dword
-	 * boundaries.  Since we don't support unaligned accesses, we're
-	 * only ever accessing a single capability.
-	 */
-	if (*ppos >= PCI_CFG_SPACE_SIZE) {
-		WARN_ON(cap_id > PCI_EXT_CAP_ID_MAX);
+	ret = count;
 
-		perm = &ecap_perms[cap_id];
-		cap_start = vfio_find_cap_start(vdev, *ppos);
+	cap_id = vdev->pci_config_map[*ppos];
 
+	if (cap_id == PCI_CAP_ID_INVALID) {
+		perm = &unassigned_perms;
+		cap_start = *ppos;
 	} else {
-		WARN_ON(cap_id > PCI_CAP_ID_MAX);
+		if (*ppos >= PCI_CFG_SPACE_SIZE) {
+			WARN_ON(cap_id > PCI_EXT_CAP_ID_MAX);
+
+			perm = &ecap_perms[cap_id];
+			cap_start = vfio_find_cap_start(vdev, *ppos);
+		} else {
+			WARN_ON(cap_id > PCI_CAP_ID_MAX);
 
-		perm = &cap_perms[cap_id];
+			perm = &cap_perms[cap_id];
 
-		if (cap_id == PCI_CAP_ID_MSI)
-			perm = vdev->msi_perm;
+			if (cap_id == PCI_CAP_ID_MSI)
+				perm = vdev->msi_perm;
 
-		if (cap_id > PCI_CAP_ID_BASIC)
-			cap_start = vfio_find_cap_start(vdev, *ppos);
+			if (cap_id > PCI_CAP_ID_BASIC)
+				cap_start = vfio_find_cap_start(vdev, *ppos);
+		}
 	}
 
 	WARN_ON(!cap_start && cap_id != PCI_CAP_ID_BASIC);
@@ -1545,20 +1578,8 @@ ssize_t vfio_pci_config_rw(struct vfio_pci_device *vdev, char __user *buf,
 
 	pos &= VFIO_PCI_OFFSET_MASK;
 
-	/*
-	 * We want to both keep the access size the caller users as well as
-	 * support reading large chunks of config space in a single call.
-	 * PCI doesn't support unaligned accesses, so we can safely break
-	 * those apart.
-	 */
 	while (count) {
-		if (count >= 4 && !(pos % 4))
-			ret = vfio_config_do_rw(vdev, buf, 4, &pos, iswrite);
-		else if (count >= 2 && !(pos % 2))
-			ret = vfio_config_do_rw(vdev, buf, 2, &pos, iswrite);
-		else
-			ret = vfio_config_do_rw(vdev, buf, 1, &pos, iswrite);
-
+		ret = vfio_config_do_rw(vdev, buf, count, &pos, iswrite);
 		if (ret < 0)
 			return ret;
 
diff --git a/drivers/vfio/pci/vfio_pci_intrs.c b/drivers/vfio/pci/vfio_pci_intrs.c
index 3639371fa69..9dd49c9839a 100644
--- a/drivers/vfio/pci/vfio_pci_intrs.c
+++ b/drivers/vfio/pci/vfio_pci_intrs.c
@@ -22,6 +22,7 @@
 #include <linux/vfio.h>
 #include <linux/wait.h>
 #include <linux/workqueue.h>
+#include <linux/slab.h>
 
 #include "vfio_pci_private.h"
 
@@ -129,8 +130,8 @@ static int virqfd_enable(struct vfio_pci_device *vdev,
 			 void (*thread)(struct vfio_pci_device *, void *),
 			 void *data, struct virqfd **pvirqfd, int fd)
 {
-	struct file *file = NULL;
-	struct eventfd_ctx *ctx = NULL;
+	struct fd irqfd;
+	struct eventfd_ctx *ctx;
 	struct virqfd *virqfd;
 	int ret = 0;
 	unsigned int events;
@@ -148,16 +149,16 @@ static int virqfd_enable(struct vfio_pci_device *vdev,
 	INIT_WORK(&virqfd->shutdown, virqfd_shutdown);
 	INIT_WORK(&virqfd->inject, virqfd_inject);
 
-	file = eventfd_fget(fd);
-	if (IS_ERR(file)) {
-		ret = PTR_ERR(file);
-		goto fail;
+	irqfd = fdget(fd);
+	if (!irqfd.file) {
+		ret = -EBADF;
+		goto err_fd;
 	}
 
-	ctx = eventfd_ctx_fileget(file);
+	ctx = eventfd_ctx_fileget(irqfd.file);
 	if (IS_ERR(ctx)) {
 		ret = PTR_ERR(ctx);
-		goto fail;
+		goto err_ctx;
 	}
 
 	virqfd->eventfd = ctx;
@@ -173,7 +174,7 @@ static int virqfd_enable(struct vfio_pci_device *vdev,
 	if (*pvirqfd) {
 		spin_unlock_irq(&vdev->irqlock);
 		ret = -EBUSY;
-		goto fail;
+		goto err_busy;
 	}
 	*pvirqfd = virqfd;
 
@@ -186,7 +187,7 @@ static int virqfd_enable(struct vfio_pci_device *vdev,
 	init_waitqueue_func_entry(&virqfd->wait, virqfd_wakeup);
 	init_poll_funcptr(&virqfd->pt, virqfd_ptable_queue_proc);
 
-	events = file->f_op->poll(file, &virqfd->pt);
+	events = irqfd.file->f_op->poll(irqfd.file, &virqfd->pt);
 
 	/*
 	 * Check if there was an event already pending on the eventfd
@@ -201,17 +202,14 @@ static int virqfd_enable(struct vfio_pci_device *vdev,
 	 * Do not drop the file until the irqfd is fully initialized,
 	 * otherwise we might race against the POLLHUP.
 	 */
-	fput(file);
+	fdput(irqfd);
 
 	return 0;
-
-fail:
-	if (ctx && !IS_ERR(ctx))
-		eventfd_ctx_put(ctx);
-
-	if (file && !IS_ERR(file))
-		fput(file);
-
+err_busy:
+	eventfd_ctx_put(ctx);
+err_ctx:
+	fdput(irqfd);
+err_fd:
 	kfree(virqfd);
 
 	return ret;
@@ -286,7 +284,8 @@ void vfio_pci_intx_mask(struct vfio_pci_device *vdev)
  * a signal is necessary, which can then be handled via a work queue
  * or directly depending on the caller.
  */
-int vfio_pci_intx_unmask_handler(struct vfio_pci_device *vdev, void *unused)
+static int vfio_pci_intx_unmask_handler(struct vfio_pci_device *vdev,
+					void *unused)
 {
 	struct pci_dev *pdev = vdev->pdev;
 	unsigned long flags;
@@ -483,15 +482,19 @@ static int vfio_msi_enable(struct vfio_pci_device *vdev, int nvec, bool msix)
 		for (i = 0; i < nvec; i++)
 			vdev->msix[i].entry = i;
 
-		ret = pci_enable_msix(pdev, vdev->msix, nvec);
-		if (ret) {
+		ret = pci_enable_msix_range(pdev, vdev->msix, 1, nvec);
+		if (ret < nvec) {
+			if (ret > 0)
+				pci_disable_msix(pdev);
 			kfree(vdev->msix);
 			kfree(vdev->ctx);
 			return ret;
 		}
 	} else {
-		ret = pci_enable_msi_block(pdev, nvec);
-		if (ret) {
+		ret = pci_enable_msi_range(pdev, 1, nvec);
+		if (ret < nvec) {
+			if (ret > 0)
+				pci_disable_msi(pdev);
 			kfree(vdev->ctx);
 			return ret;
 		}
@@ -745,6 +748,46 @@ static int vfio_pci_set_msi_trigger(struct vfio_pci_device *vdev,
 	return 0;
 }
 
+static int vfio_pci_set_err_trigger(struct vfio_pci_device *vdev,
+				    unsigned index, unsigned start,
+				    unsigned count, uint32_t flags, void *data)
+{
+	int32_t fd = *(int32_t *)data;
+
+	if ((index != VFIO_PCI_ERR_IRQ_INDEX) ||
+	    !(flags & VFIO_IRQ_SET_DATA_TYPE_MASK))
+		return -EINVAL;
+
+	/* DATA_NONE/DATA_BOOL enables loopback testing */
+	if (flags & VFIO_IRQ_SET_DATA_NONE) {
+		if (vdev->err_trigger)
+			eventfd_signal(vdev->err_trigger, 1);
+		return 0;
+	} else if (flags & VFIO_IRQ_SET_DATA_BOOL) {
+		uint8_t trigger = *(uint8_t *)data;
+		if (trigger && vdev->err_trigger)
+			eventfd_signal(vdev->err_trigger, 1);
+		return 0;
+	}
+
+	/* Handle SET_DATA_EVENTFD */
+	if (fd == -1) {
+		if (vdev->err_trigger)
+			eventfd_ctx_put(vdev->err_trigger);
+		vdev->err_trigger = NULL;
+		return 0;
+	} else if (fd >= 0) {
+		struct eventfd_ctx *efdctx;
+		efdctx = eventfd_ctx_fdget(fd);
+		if (IS_ERR(efdctx))
+			return PTR_ERR(efdctx);
+		if (vdev->err_trigger)
+			eventfd_ctx_put(vdev->err_trigger);
+		vdev->err_trigger = efdctx;
+		return 0;
+	} else
+		return -EINVAL;
+}
 int vfio_pci_set_irqs_ioctl(struct vfio_pci_device *vdev, uint32_t flags,
 			    unsigned index, unsigned start, unsigned count,
 			    void *data)
@@ -779,6 +822,13 @@ int vfio_pci_set_irqs_ioctl(struct vfio_pci_device *vdev, uint32_t flags,
 			break;
 		}
 		break;
+	case VFIO_PCI_ERR_IRQ_INDEX:
+		switch (flags & VFIO_IRQ_SET_ACTION_TYPE_MASK) {
+		case VFIO_IRQ_SET_ACTION_TRIGGER:
+			if (pci_is_pcie(vdev->pdev))
+				func = vfio_pci_set_err_trigger;
+			break;
+		}
 	}
 
 	if (!func)
diff --git a/drivers/vfio/pci/vfio_pci_private.h b/drivers/vfio/pci/vfio_pci_private.h
index d7e55d03f49..9c6d5d0f3b0 100644
--- a/drivers/vfio/pci/vfio_pci_private.h
+++ b/drivers/vfio/pci/vfio_pci_private.h
@@ -56,6 +56,7 @@ struct vfio_pci_device {
 	bool			has_vga;
 	struct pci_saved_state	*pci_saved_state;
 	atomic_t		refcnt;
+	struct eventfd_ctx	*err_trigger;
 };
 
 #define is_intx(vdev) (vdev->irq_type == VFIO_PCI_INTX_IRQ_INDEX)