Merge tag 'vfio-v5.12-rc1' of git://github.com/awilliam/linux-vfio

Pull VFIO updatesfrom Alex Williamson:

 - Virtual address update handling (Steve Sistare)

 - s390/zpci fixes and cleanups (Max Gurtovoy)

 - Fixes for dirty bitmap handling, non-mdev page pinning, and improved
   pinned dirty scope tracking (Keqian Zhu)

 - Batched page pinning enhancement (Daniel Jordan)

 - Page access permission fix (Alex Williamson)

* tag 'vfio-v5.12-rc1' of git://github.com/awilliam/linux-vfio: (21 commits)
  vfio/type1: Batch page pinning
  vfio/type1: Prepare for batched pinning with struct vfio_batch
  vfio/type1: Change success value of vaddr_get_pfn()
  vfio/type1: Use follow_pte()
  vfio/pci: remove CONFIG_VFIO_PCI_ZDEV from Kconfig
  vfio/iommu_type1: Fix duplicate included kthread.h
  vfio-pci/zdev: fix possible segmentation fault issue
  vfio-pci/zdev: remove unused vdev argument
  vfio/pci: Fix handling of pci use accessor return codes
  vfio/iommu_type1: Mantain a counter for non_pinned_groups
  vfio/iommu_type1: Fix some sanity checks in detach group
  vfio/iommu_type1: Populate full dirty when detach non-pinned group
  vfio/type1: block on invalid vaddr
  vfio/type1: implement notify callback
  vfio: iommu driver notify callback
  vfio/type1: implement interfaces to update vaddr
  vfio/type1: massage unmap iteration
  vfio: interfaces to update vaddr
  vfio/type1: implement unmap all
  vfio/type1: unmap cleanup
  ...

drivers/vfio/pci/Kconfig

@@ -45,15 +45,3 @@ config VFIO_PCI_NVLINK2
 	depends on VFIO_PCI && PPC_POWERNV
 	help
 	  VFIO PCI support for P9 Witherspoon machine with NVIDIA V100 GPUs
-
-config VFIO_PCI_ZDEV
-	bool "VFIO PCI ZPCI device CLP support"
-	depends on VFIO_PCI && S390
-	default y
-	help
-	  Enabling this option exposes VFIO capabilities containing hardware
-	  configuration for zPCI devices. This enables userspace (e.g. QEMU)
-	  to supply proper configuration values instead of hard-coded defaults
-	  for zPCI devices passed through via VFIO on s390.
-
-	  Say Y here.

drivers/vfio/pci/Makefile

@@ -3,6 +3,6 @@
 vfio-pci-y := vfio_pci.o vfio_pci_intrs.o vfio_pci_rdwr.o vfio_pci_config.o
 vfio-pci-$(CONFIG_VFIO_PCI_IGD) += vfio_pci_igd.o
 vfio-pci-$(CONFIG_VFIO_PCI_NVLINK2) += vfio_pci_nvlink2.o
-vfio-pci-$(CONFIG_VFIO_PCI_ZDEV) += vfio_pci_zdev.o
+vfio-pci-$(CONFIG_S390) += vfio_pci_zdev.o
 
 obj-$(CONFIG_VFIO_PCI) += vfio-pci.o

drivers/vfio/pci/vfio_pci.c

@@ -807,6 +807,7 @@ static long vfio_pci_ioctl(void *device_data,
 		struct vfio_device_info info;
 		struct vfio_info_cap caps = { .buf = NULL, .size = 0 };
 		unsigned long capsz;
+		int ret;
 
 		minsz = offsetofend(struct vfio_device_info, num_irqs);
 
@@ -832,13 +833,10 @@ static long vfio_pci_ioctl(void *device_data,
 		info.num_regions = VFIO_PCI_NUM_REGIONS + vdev->num_regions;
 		info.num_irqs = VFIO_PCI_NUM_IRQS;
 
-		if (IS_ENABLED(CONFIG_VFIO_PCI_ZDEV)) {
-			int ret = vfio_pci_info_zdev_add_caps(vdev, &caps);
-
-			if (ret && ret != -ENODEV) {
-				pci_warn(vdev->pdev, "Failed to setup zPCI info capabilities\n");
-				return ret;
-			}
+		ret = vfio_pci_info_zdev_add_caps(vdev, &caps);
+		if (ret && ret != -ENODEV) {
+			pci_warn(vdev->pdev, "Failed to setup zPCI info capabilities\n");
+			return ret;
 		}
 
 		if (caps.size) {

drivers/vfio/pci/vfio_pci_igd.c

@@ -127,7 +127,7 @@ static size_t vfio_pci_igd_cfg_rw(struct vfio_pci_device *vdev,
 
 		ret = pci_user_read_config_byte(pdev, pos, &val);
 		if (ret)
-			return pcibios_err_to_errno(ret);
+			return ret;
 
 		if (copy_to_user(buf + count - size, &val, 1))
 			return -EFAULT;
@@ -141,7 +141,7 @@ static size_t vfio_pci_igd_cfg_rw(struct vfio_pci_device *vdev,
 
 		ret = pci_user_read_config_word(pdev, pos, &val);
 		if (ret)
-			return pcibios_err_to_errno(ret);
+			return ret;
 
 		val = cpu_to_le16(val);
 		if (copy_to_user(buf + count - size, &val, 2))
@@ -156,7 +156,7 @@ static size_t vfio_pci_igd_cfg_rw(struct vfio_pci_device *vdev,
 
 		ret = pci_user_read_config_dword(pdev, pos, &val);
 		if (ret)
-			return pcibios_err_to_errno(ret);
+			return ret;
 
 		val = cpu_to_le32(val);
 		if (copy_to_user(buf + count - size, &val, 4))
@@ -171,7 +171,7 @@ static size_t vfio_pci_igd_cfg_rw(struct vfio_pci_device *vdev,
 
 		ret = pci_user_read_config_word(pdev, pos, &val);
 		if (ret)
-			return pcibios_err_to_errno(ret);
+			return ret;
 
 		val = cpu_to_le16(val);
 		if (copy_to_user(buf + count - size, &val, 2))
@@ -186,7 +186,7 @@ static size_t vfio_pci_igd_cfg_rw(struct vfio_pci_device *vdev,
 
 		ret = pci_user_read_config_byte(pdev, pos, &val);
 		if (ret)
-			return pcibios_err_to_errno(ret);
+			return ret;
 
 		if (copy_to_user(buf + count - size, &val, 1))
 			return -EFAULT;

drivers/vfio/pci/vfio_pci_private.h

@@ -214,7 +214,7 @@ static inline int vfio_pci_ibm_npu2_init(struct vfio_pci_device *vdev)
 }
 #endif
 
-#ifdef CONFIG_VFIO_PCI_ZDEV
+#ifdef CONFIG_S390
 extern int vfio_pci_info_zdev_add_caps(struct vfio_pci_device *vdev,
 				       struct vfio_info_cap *caps);
 #else

drivers/vfio/pci/vfio_pci_zdev.c

@@ -24,8 +24,7 @@
 /*
  * Add the Base PCI Function information to the device info region.
  */
-static int zpci_base_cap(struct zpci_dev *zdev, struct vfio_pci_device *vdev,
-			 struct vfio_info_cap *caps)
+static int zpci_base_cap(struct zpci_dev *zdev, struct vfio_info_cap *caps)
 {
 	struct vfio_device_info_cap_zpci_base cap = {
 		.header.id = VFIO_DEVICE_INFO_CAP_ZPCI_BASE,
@@ -45,8 +44,7 @@ static int zpci_base_cap(struct zpci_dev *zdev, struct vfio_pci_device *vdev,
 /*
  * Add the Base PCI Function Group information to the device info region.
  */
-static int zpci_group_cap(struct zpci_dev *zdev, struct vfio_pci_device *vdev,
-			  struct vfio_info_cap *caps)
+static int zpci_group_cap(struct zpci_dev *zdev, struct vfio_info_cap *caps)
 {
 	struct vfio_device_info_cap_zpci_group cap = {
 		.header.id = VFIO_DEVICE_INFO_CAP_ZPCI_GROUP,
@@ -66,14 +64,15 @@ static int zpci_group_cap(struct zpci_dev *zdev, struct vfio_pci_device *vdev,
 /*
  * Add the device utility string to the device info region.
  */
-static int zpci_util_cap(struct zpci_dev *zdev, struct vfio_pci_device *vdev,
-			 struct vfio_info_cap *caps)
+static int zpci_util_cap(struct zpci_dev *zdev, struct vfio_info_cap *caps)
 {
 	struct vfio_device_info_cap_zpci_util *cap;
 	int cap_size = sizeof(*cap) + CLP_UTIL_STR_LEN;
 	int ret;
 
 	cap = kmalloc(cap_size, GFP_KERNEL);
+	if (!cap)
+		return -ENOMEM;
 
 	cap->header.id = VFIO_DEVICE_INFO_CAP_ZPCI_UTIL;
 	cap->header.version = 1;
@@ -90,14 +89,15 @@ static int zpci_util_cap(struct zpci_dev *zdev, struct vfio_pci_device *vdev,
 /*
  * Add the function path string to the device info region.
  */
-static int zpci_pfip_cap(struct zpci_dev *zdev, struct vfio_pci_device *vdev,
-			 struct vfio_info_cap *caps)
+static int zpci_pfip_cap(struct zpci_dev *zdev, struct vfio_info_cap *caps)
 {
 	struct vfio_device_info_cap_zpci_pfip *cap;
 	int cap_size = sizeof(*cap) + CLP_PFIP_NR_SEGMENTS;
 	int ret;
 
 	cap = kmalloc(cap_size, GFP_KERNEL);
+	if (!cap)
+		return -ENOMEM;
 
 	cap->header.id = VFIO_DEVICE_INFO_CAP_ZPCI_PFIP;
 	cap->header.version = 1;
@@ -123,21 +123,21 @@ int vfio_pci_info_zdev_add_caps(struct vfio_pci_device *vdev,
 	if (!zdev)
 		return -ENODEV;
 
-	ret = zpci_base_cap(zdev, vdev, caps);
+	ret = zpci_base_cap(zdev, caps);
 	if (ret)
 		return ret;
 
-	ret = zpci_group_cap(zdev, vdev, caps);
+	ret = zpci_group_cap(zdev, caps);
 	if (ret)
 		return ret;
 
 	if (zdev->util_str_avail) {
-		ret = zpci_util_cap(zdev, vdev, caps);
+		ret = zpci_util_cap(zdev, caps);
 		if (ret)
 			return ret;
 	}
 
-	ret = zpci_pfip_cap(zdev, vdev, caps);
+	ret = zpci_pfip_cap(zdev, caps);
 
 	return ret;
 }

drivers/vfio/vfio.c

@@ -1220,6 +1220,11 @@ static int vfio_fops_open(struct inode *inode, struct file *filep)
 static int vfio_fops_release(struct inode *inode, struct file *filep)
 {
 	struct vfio_container *container = filep->private_data;
+	struct vfio_iommu_driver *driver = container->iommu_driver;
+
+	if (driver && driver->ops->notify)
+		driver->ops->notify(container->iommu_data,
+				    VFIO_IOMMU_CONTAINER_CLOSE);
 
 	filep->private_data = NULL;
 

include/linux/vfio.h

@@ -57,6 +57,11 @@ extern struct vfio_device *vfio_device_get_from_dev(struct device *dev);
 extern void vfio_device_put(struct vfio_device *device);
 extern void *vfio_device_data(struct vfio_device *device);
 
+/* events for the backend driver notify callback */
+enum vfio_iommu_notify_type {
+	VFIO_IOMMU_CONTAINER_CLOSE = 0,
+};
+
 /**
  * struct vfio_iommu_driver_ops - VFIO IOMMU driver callbacks
  */
@@ -92,6 +97,8 @@ struct vfio_iommu_driver_ops {
 				  void *data, size_t count, bool write);
 	struct iommu_domain *(*group_iommu_domain)(void *iommu_data,
 						   struct iommu_group *group);
+	void		(*notify)(void *iommu_data,
+				  enum vfio_iommu_notify_type event);
 };
 
 extern int vfio_register_iommu_driver(const struct vfio_iommu_driver_ops *ops);

include/uapi/linux/vfio.h

@@ -46,6 +46,12 @@
  */
 #define VFIO_NOIOMMU_IOMMU		8
 
+/* Supports VFIO_DMA_UNMAP_FLAG_ALL */
+#define VFIO_UNMAP_ALL			9
+
+/* Supports the vaddr flag for DMA map and unmap */
+#define VFIO_UPDATE_VADDR		10
+
 /*
  * The IOCTL interface is designed for extensibility by embedding the
  * structure length (argsz) and flags into structures passed between
@@ -1074,12 +1080,22 @@ struct vfio_iommu_type1_info_dma_avail {
  *
  * Map process virtual addresses to IO virtual addresses using the
  * provided struct vfio_dma_map. Caller sets argsz. READ &/ WRITE required.
+ *
+ * If flags & VFIO_DMA_MAP_FLAG_VADDR, update the base vaddr for iova, and
+ * unblock translation of host virtual addresses in the iova range.  The vaddr
+ * must have previously been invalidated with VFIO_DMA_UNMAP_FLAG_VADDR.  To
+ * maintain memory consistency within the user application, the updated vaddr
+ * must address the same memory object as originally mapped.  Failure to do so
+ * will result in user memory corruption and/or device misbehavior.  iova and
+ * size must match those in the original MAP_DMA call.  Protection is not
+ * changed, and the READ & WRITE flags must be 0.
  */
 struct vfio_iommu_type1_dma_map {
 	__u32	argsz;
 	__u32	flags;
 #define VFIO_DMA_MAP_FLAG_READ (1 << 0)		/* readable from device */
 #define VFIO_DMA_MAP_FLAG_WRITE (1 << 1)	/* writable from device */
+#define VFIO_DMA_MAP_FLAG_VADDR (1 << 2)
 	__u64	vaddr;				/* Process virtual address */
 	__u64	iova;				/* IO virtual address */
 	__u64	size;				/* Size of mapping (bytes) */
@@ -1102,6 +1118,7 @@ struct vfio_bitmap {
  * field.  No guarantee is made to the user that arbitrary unmaps of iova
  * or size different from those used in the original mapping call will
  * succeed.
+ *
  * VFIO_DMA_UNMAP_FLAG_GET_DIRTY_BITMAP should be set to get the dirty bitmap
  * before unmapping IO virtual addresses. When this flag is set, the user must
  * provide a struct vfio_bitmap in data[]. User must provide zero-allocated
@@ -1111,11 +1128,21 @@ struct vfio_bitmap {
  * indicates that the page at that offset from iova is dirty. A Bitmap of the
  * pages in the range of unmapped size is returned in the user-provided
  * vfio_bitmap.data.
+ *
+ * If flags & VFIO_DMA_UNMAP_FLAG_ALL, unmap all addresses.  iova and size
+ * must be 0.  This cannot be combined with the get-dirty-bitmap flag.
+ *
+ * If flags & VFIO_DMA_UNMAP_FLAG_VADDR, do not unmap, but invalidate host
+ * virtual addresses in the iova range.  Tasks that attempt to translate an
+ * iova's vaddr will block.  DMA to already-mapped pages continues.  This
+ * cannot be combined with the get-dirty-bitmap flag.
  */
 struct vfio_iommu_type1_dma_unmap {
 	__u32	argsz;
 	__u32	flags;
 #define VFIO_DMA_UNMAP_FLAG_GET_DIRTY_BITMAP (1 << 0)
+#define VFIO_DMA_UNMAP_FLAG_ALL		     (1 << 1)
+#define VFIO_DMA_UNMAP_FLAG_VADDR	     (1 << 2)
 	__u64	iova;				/* IO virtual address */
 	__u64	size;				/* Size of mapping (bytes) */
 	__u8    data[];