Merge branches 'v5.10/vfio/bardirty', 'v5.10/vfio/dma_avail',...

Merge branches 'v5.10/vfio/bardirty', 'v5.10/vfio/dma_avail', 'v5.10/vfio/misc', 'v5.10/vfio/no-cmd-mem' and 'v5.10/vfio/yan_zhao_fixes' into v5.10/vfio/next

arch/s390/pci/pci_bus.c

@@ -197,9 +197,10 @@ void pcibios_bus_add_device(struct pci_dev *pdev)
 	 * With pdev->no_vf_scan the common PCI probing code does not
 	 * perform PF/VF linking.
 	 */
-	if (zdev->vfn)
+	if (zdev->vfn) {
 		zpci_bus_setup_virtfn(zdev->zbus, pdev, zdev->vfn);
-
+		pdev->no_command_memory = 1;
+	}
 }
 
 static int zpci_bus_add_device(struct zpci_bus *zbus, struct zpci_dev *zdev)

drivers/pci/iov.c

@@ -180,6 +180,7 @@ int pci_iov_add_virtfn(struct pci_dev *dev, int id)
 	virtfn->device = iov->vf_device;
 	virtfn->is_virtfn = 1;
 	virtfn->physfn = pci_dev_get(dev);
+	virtfn->no_command_memory = 1;
 
 	if (id == 0)
 		pci_read_vf_config_common(virtfn);

drivers/vfio/pci/vfio_pci.c

@@ -1862,7 +1862,6 @@ static const struct vfio_device_ops vfio_pci_ops = {
 
 static int vfio_pci_reflck_attach(struct vfio_pci_device *vdev);
 static void vfio_pci_reflck_put(struct vfio_pci_reflck *reflck);
-static struct pci_driver vfio_pci_driver;
 
 static int vfio_pci_bus_notifier(struct notifier_block *nb,
 				 unsigned long action, void *data)

drivers/vfio/pci/vfio_pci_config.c

@@ -406,7 +406,7 @@ bool __vfio_pci_memory_enabled(struct vfio_pci_device *vdev)
 	 * PF SR-IOV capability, there's therefore no need to trigger
 	 * faults based on the virtual value.
 	 */
-	return pdev->is_virtfn || (cmd & PCI_COMMAND_MEMORY);
+	return pdev->no_command_memory || (cmd & PCI_COMMAND_MEMORY);
 }
 
 /*
@@ -523,8 +523,8 @@ static int vfio_basic_config_read(struct vfio_pci_device *vdev, int pos,
 
 	count = vfio_default_config_read(vdev, pos, count, perm, offset, val);
 
-	/* Mask in virtual memory enable for SR-IOV devices */
-	if (offset == PCI_COMMAND && vdev->pdev->is_virtfn) {
+	/* Mask in virtual memory enable */
+	if (offset == PCI_COMMAND && vdev->pdev->no_command_memory) {
 		u16 cmd = le16_to_cpu(*(__le16 *)&vdev->vconfig[PCI_COMMAND]);
 		u32 tmp_val = le32_to_cpu(*val);
 
@@ -592,9 +592,11 @@ static int vfio_basic_config_write(struct vfio_pci_device *vdev, int pos,
 		 * shows it disabled (phys_mem/io, then the device has
 		 * undergone some kind of backdoor reset and needs to be
 		 * restored before we allow it to enable the bars.
-		 * SR-IOV devices will trigger this, but we catch them later
+		 * SR-IOV devices will trigger this - for mem enable let's
+		 * catch this now and for io enable it will be caught later
 		 */
-		if ((new_mem && virt_mem && !phys_mem) ||
+		if ((new_mem && virt_mem && !phys_mem &&
+		     !pdev->no_command_memory) ||
 		    (new_io && virt_io && !phys_io) ||
 		    vfio_need_bar_restore(vdev))
 			vfio_bar_restore(vdev);
@@ -1737,12 +1739,14 @@ int vfio_config_init(struct vfio_pci_device *vdev)
 				 vconfig[PCI_INTERRUPT_PIN]);
 
 		vconfig[PCI_INTERRUPT_PIN] = 0; /* Gratuitous for good VFs */
-
+	}
+	if (pdev->no_command_memory) {
 		/*
-		 * VFs do no implement the memory enable bit of the COMMAND
-		 * register therefore we'll not have it set in our initial
-		 * copy of config space after pci_enable_device().  For
-		 * consistency with PFs, set the virtual enable bit here.
+		 * VFs and devices that set pdev->no_command_memory do not
+		 * implement the memory enable bit of the COMMAND register
+		 * therefore we'll not have it set in our initial copy of
+		 * config space after pci_enable_device().  For consistency
+		 * with PFs, set the virtual enable bit here.
 		 */
 		*(__le16 *)&vconfig[PCI_COMMAND] |=
 					cpu_to_le16(PCI_COMMAND_MEMORY);

drivers/vfio/vfio.c

@@ -1949,8 +1949,10 @@ int vfio_pin_pages(struct device *dev, unsigned long *user_pfn, int npage,
 	if (!group)
 		return -ENODEV;
 
-	if (group->dev_counter > 1)
-		return -EINVAL;
+	if (group->dev_counter > 1) {
+		ret = -EINVAL;
+		goto err_pin_pages;
+	}
 
 	ret = vfio_group_add_container_user(group);
 	if (ret)
@@ -2051,6 +2053,9 @@ int vfio_group_pin_pages(struct vfio_group *group,
 	if (!group || !user_iova_pfn || !phys_pfn || !npage)
 		return -EINVAL;
 
+	if (group->dev_counter > 1)
+		return -EINVAL;
+
 	if (npage > VFIO_PIN_PAGES_MAX_ENTRIES)
 		return -E2BIG;
 

drivers/vfio/vfio_iommu_type1.c

@@ -2609,6 +2609,20 @@ static int vfio_iommu_migration_build_caps(struct vfio_iommu *iommu,
 	return vfio_info_add_capability(caps, &cap_mig.header, sizeof(cap_mig));
 }
 
+static int vfio_iommu_dma_avail_build_caps(struct vfio_iommu *iommu,
+					   struct vfio_info_cap *caps)
+{
+	struct vfio_iommu_type1_info_dma_avail cap_dma_avail;
+
+	cap_dma_avail.header.id = VFIO_IOMMU_TYPE1_INFO_DMA_AVAIL;
+	cap_dma_avail.header.version = 1;
+
+	cap_dma_avail.avail = iommu->dma_avail;
+
+	return vfio_info_add_capability(caps, &cap_dma_avail.header,
+					sizeof(cap_dma_avail));
+}
+
 static int vfio_iommu_type1_get_info(struct vfio_iommu *iommu,
 				     unsigned long arg)
 {
@@ -2641,6 +2655,9 @@ static int vfio_iommu_type1_get_info(struct vfio_iommu *iommu,
 
 	ret = vfio_iommu_migration_build_caps(iommu, &caps);
 
+	if (!ret)
+		ret = vfio_iommu_dma_avail_build_caps(iommu, &caps);
+
 	if (!ret)
 		ret = vfio_iommu_iova_build_caps(iommu, &caps);
 
@@ -2933,7 +2950,8 @@ static int vfio_iommu_type1_dma_rw_chunk(struct vfio_iommu *iommu,
 			 * size
 			 */
 			bitmap_set(dma->bitmap, offset >> pgshift,
-				   *copied >> pgshift);
+				   ((offset + *copied - 1) >> pgshift) -
+				   (offset >> pgshift) + 1);
 		}
 	} else
 		*copied = copy_from_user(data, (void __user *)vaddr,

include/linux/pci.h

@@ -445,6 +445,7 @@ struct pci_dev {
 	unsigned int	is_probed:1;		/* Device probing in progress */
 	unsigned int	link_active_reporting:1;/* Device capable of reporting link active */
 	unsigned int	no_vf_scan:1;		/* Don't scan for VFs after IOV enablement */
+	unsigned int	no_command_memory:1;	/* No PCI_COMMAND_MEMORY */
 	pci_dev_flags_t dev_flags;
 	atomic_t	enable_cnt;	/* pci_enable_device has been called */
 

include/uapi/linux/vfio.h

@@ -462,7 +462,7 @@ struct vfio_region_gfx_edid {
  * 5. Resumed
  *                  |--------->|
  *
- * 0. Default state of VFIO device is _RUNNNG when the user application starts.
+ * 0. Default state of VFIO device is _RUNNING when the user application starts.
  * 1. During normal shutdown of the user application, the user application may
  *    optionally change the VFIO device state from _RUNNING to _STOP. This
  *    transition is optional. The vendor driver must support this transition but
@@ -1039,6 +1039,21 @@ struct vfio_iommu_type1_info_cap_migration {
 	__u64	max_dirty_bitmap_size;		/* in bytes */
 };
 
+/*
+ * The DMA available capability allows to report the current number of
+ * simultaneously outstanding DMA mappings that are allowed.
+ *
+ * The structure below defines version 1 of this capability.
+ *
+ * avail: specifies the current number of outstanding DMA mappings allowed.
+ */
+#define VFIO_IOMMU_TYPE1_INFO_DMA_AVAIL 3
+
+struct vfio_iommu_type1_info_dma_avail {
+	struct	vfio_info_cap_header header;
+	__u32	avail;
+};
+
 #define VFIO_IOMMU_GET_INFO _IO(VFIO_TYPE, VFIO_BASE + 12)
 
 /**