Merge tag 'vfio-v5.4-rc1' of git://github.com/awilliam/linux-vfio

Pull VFIO updates from Alex Williamson:

 - Fix spapr iommu error case case (Alexey Kardashevskiy)

 - Consolidate region type definitions (Cornelia Huck)

 - Restore saved original PCI state on release (hexin)

 - Simplify mtty sample driver interrupt path (Parav Pandit)

 - Support for reporting valid IOVA regions to user (Shameer Kolothum)

* tag 'vfio-v5.4-rc1' of git://github.com/awilliam/linux-vfio:
  vfio_pci: Restore original state on release
  vfio/type1: remove duplicate retrieval of reserved regions
  vfio/type1: Add IOVA range capability support
  vfio/type1: check dma map request is within a valid iova range
  vfio/spapr_tce: Fix incorrect tce_iommu_group memory free
  vfio-mdev/mtty: Simplify interrupt generation
  vfio: re-arrange vfio region definitions
  vfio/type1: Update iova list on detach
  vfio/type1: Check reserved region conflict and update iova list
  vfio/type1: Introduce iova list and add iommu aperture validity check

drivers/vfio/pci/vfio_pci.c

@@ -438,11 +438,20 @@ static void vfio_pci_disable(struct vfio_pci_device *vdev)
 	pci_write_config_word(pdev, PCI_COMMAND, PCI_COMMAND_INTX_DISABLE);
 
 	/*
-	 * Try to reset the device.  The success of this is dependent on
-	 * being able to lock the device, which is not always possible.
+	 * Try to get the locks ourselves to prevent a deadlock. The
+	 * success of this is dependent on being able to lock the device,
+	 * which is not always possible.
+	 * We can not use the "try" reset interface here, which will
+	 * overwrite the previously restored configuration information.
 	 */
-	if (vdev->reset_works && !pci_try_reset_function(pdev))
+	if (vdev->reset_works && pci_cfg_access_trylock(pdev)) {
+		if (device_trylock(&pdev->dev)) {
+			if (!__pci_reset_function_locked(pdev))
 				vdev->needs_reset = false;
+			device_unlock(&pdev->dev);
+		}
+		pci_cfg_access_unlock(pdev);
+	}
 
 	pci_restore_state(pdev);
 out:

drivers/vfio/vfio_iommu_spapr_tce.c

@@ -1240,7 +1240,7 @@ static long tce_iommu_take_ownership_ddw(struct tce_container *container,
 static int tce_iommu_attach_group(void *iommu_data,
 		struct iommu_group *iommu_group)
 {
-	int ret;
+	int ret = 0;
 	struct tce_container *container = iommu_data;
 	struct iommu_table_group *table_group;
 	struct tce_iommu_group *tcegrp = NULL;
@@ -1293,13 +1293,13 @@ static int tce_iommu_attach_group(void *iommu_data,
 			!table_group->ops->release_ownership) {
 		if (container->v2) {
 			ret = -EPERM;
-			goto unlock_exit;
+			goto free_exit;
 		}
 		ret = tce_iommu_take_ownership(container, table_group);
 	} else {
 		if (!container->v2) {
 			ret = -EPERM;
-			goto unlock_exit;
+			goto free_exit;
 		}
 		ret = tce_iommu_take_ownership_ddw(container, table_group);
 		if (!tce_groups_attached(container) && !container->tables[0])
@@ -1311,10 +1311,11 @@ static int tce_iommu_attach_group(void *iommu_data,
 		list_add(&tcegrp->next, &container->group_list);
 	}
 
-unlock_exit:
+free_exit:
 	if (ret && tcegrp)
 		kfree(tcegrp);
 
+unlock_exit:
 	mutex_unlock(&container->lock);
 
 	return ret;

include/uapi/linux/vfio.h

@@ -295,15 +295,38 @@ struct vfio_region_info_cap_type {
 	__u32 subtype;	/* type specific */
 };
 
+/*
+ * List of region types, global per bus driver.
+ * If you introduce a new type, please add it here.
+ */
+
+/* PCI region type containing a PCI vendor part */
 #define VFIO_REGION_TYPE_PCI_VENDOR_TYPE	(1 << 31)
 #define VFIO_REGION_TYPE_PCI_VENDOR_MASK	(0xffff)
+#define VFIO_REGION_TYPE_GFX                    (1)
+#define VFIO_REGION_TYPE_CCW			(2)
+
+/* sub-types for VFIO_REGION_TYPE_PCI_* */
 
-/* 8086 Vendor sub-types */
+/* 8086 vendor PCI sub-types */
 #define VFIO_REGION_SUBTYPE_INTEL_IGD_OPREGION	(1)
 #define VFIO_REGION_SUBTYPE_INTEL_IGD_HOST_CFG	(2)
 #define VFIO_REGION_SUBTYPE_INTEL_IGD_LPC_CFG	(3)
 
-#define VFIO_REGION_TYPE_GFX                    (1)
+/* 10de vendor PCI sub-types */
+/*
+ * NVIDIA GPU NVlink2 RAM is coherent RAM mapped onto the host address space.
+ */
+#define VFIO_REGION_SUBTYPE_NVIDIA_NVLINK2_RAM	(1)
+
+/* 1014 vendor PCI sub-types */
+/*
+ * IBM NPU NVlink2 ATSD (Address Translation Shootdown) register of NPU
+ * to do TLB invalidation on a GPU.
+ */
+#define VFIO_REGION_SUBTYPE_IBM_NVLINK2_ATSD	(1)
+
+/* sub-types for VFIO_REGION_TYPE_GFX */
 #define VFIO_REGION_SUBTYPE_GFX_EDID            (1)
 
 /**
@@ -353,25 +376,9 @@ struct vfio_region_gfx_edid {
 #define VFIO_DEVICE_GFX_LINK_STATE_DOWN  2
 };
 
-#define VFIO_REGION_TYPE_CCW			(2)
-/* ccw sub-types */
+/* sub-types for VFIO_REGION_TYPE_CCW */
 #define VFIO_REGION_SUBTYPE_CCW_ASYNC_CMD	(1)
 
-/*
- * 10de vendor sub-type
- *
- * NVIDIA GPU NVlink2 RAM is coherent RAM mapped onto the host address space.
- */
-#define VFIO_REGION_SUBTYPE_NVIDIA_NVLINK2_RAM	(1)
-
-/*
- * 1014 vendor sub-type
- *
- * IBM NPU NVlink2 ATSD (Address Translation Shootdown) register of NPU
- * to do TLB invalidation on a GPU.
- */
-#define VFIO_REGION_SUBTYPE_IBM_NVLINK2_ATSD	(1)
-
 /*
  * The MSIX mappable capability informs that MSIX data of a BAR can be mmapped
  * which allows direct access to non-MSIX registers which happened to be within
@@ -714,7 +721,31 @@ struct vfio_iommu_type1_info {
 	__u32	argsz;
 	__u32	flags;
 #define VFIO_IOMMU_INFO_PGSIZES (1 << 0)	/* supported page sizes info */
+#define VFIO_IOMMU_INFO_CAPS	(1 << 1)	/* Info supports caps */
 	__u64	iova_pgsizes;	/* Bitmap of supported page sizes */
+	__u32   cap_offset;	/* Offset within info struct of first cap */
+};
+
+/*
+ * The IOVA capability allows to report the valid IOVA range(s)
+ * excluding any non-relaxable reserved regions exposed by
+ * devices attached to the container. Any DMA map attempt
+ * outside the valid iova range will return error.
+ *
+ * The structures below define version 1 of this capability.
+ */
+#define VFIO_IOMMU_TYPE1_INFO_CAP_IOVA_RANGE  1
+
+struct vfio_iova_range {
+	__u64	start;
+	__u64	end;
+};
+
+struct vfio_iommu_type1_info_cap_iova_range {
+	struct	vfio_info_cap_header header;
+	__u32	nr_iovas;
+	__u32	reserved;
+	struct	vfio_iova_range iova_ranges[];
 };
 
 #define VFIO_IOMMU_GET_INFO _IO(VFIO_TYPE, VFIO_BASE + 12)

samples/vfio-mdev/mtty.c

@@ -152,20 +152,9 @@ static const struct file_operations vd_fops = {
 
 /* function prototypes */
 
-static int mtty_trigger_interrupt(const guid_t *uuid);
+static int mtty_trigger_interrupt(struct mdev_state *mdev_state);
 
 /* Helper functions */
-static struct mdev_state *find_mdev_state_by_uuid(const guid_t *uuid)
-{
-	struct mdev_state *mds;
-
-	list_for_each_entry(mds, &mdev_devices_list, next) {
-		if (guid_equal(mdev_uuid(mds->mdev), uuid))
-			return mds;
-	}
-
-	return NULL;
-}
 
 static void dump_buffer(u8 *buf, uint32_t count)
 {
@@ -337,8 +326,7 @@ static void handle_bar_write(unsigned int index, struct mdev_state *mdev_state,
 				pr_err("Serial port %d: Fifo level trigger\n",
 					index);
 #endif
-				mtty_trigger_interrupt(
-						mdev_uuid(mdev_state->mdev));
+				mtty_trigger_interrupt(mdev_state);
 			}
 		} else {
 #if defined(DEBUG_INTR)
@@ -352,8 +340,7 @@ static void handle_bar_write(unsigned int index, struct mdev_state *mdev_state,
 			 */
 			if (mdev_state->s[index].uart_reg[UART_IER] &
 								UART_IER_RLSI)
-				mtty_trigger_interrupt(
-						mdev_uuid(mdev_state->mdev));
+				mtty_trigger_interrupt(mdev_state);
 		}
 		mutex_unlock(&mdev_state->rxtx_lock);
 		break;
@@ -372,8 +359,7 @@ static void handle_bar_write(unsigned int index, struct mdev_state *mdev_state,
 				pr_err("Serial port %d: IER_THRI write\n",
 					index);
 #endif
-				mtty_trigger_interrupt(
-						mdev_uuid(mdev_state->mdev));
+				mtty_trigger_interrupt(mdev_state);
 			}
 
 			mutex_unlock(&mdev_state->rxtx_lock);
@@ -444,7 +430,7 @@ static void handle_bar_write(unsigned int index, struct mdev_state *mdev_state,
 #if defined(DEBUG_INTR)
 			pr_err("Serial port %d: MCR_OUT2 write\n", index);
 #endif
-			mtty_trigger_interrupt(mdev_uuid(mdev_state->mdev));
+			mtty_trigger_interrupt(mdev_state);
 		}
 
 		if ((mdev_state->s[index].uart_reg[UART_IER] & UART_IER_MSI) &&
@@ -452,7 +438,7 @@ static void handle_bar_write(unsigned int index, struct mdev_state *mdev_state,
 #if defined(DEBUG_INTR)
 			pr_err("Serial port %d: MCR RTS/DTR write\n", index);
 #endif
-			mtty_trigger_interrupt(mdev_uuid(mdev_state->mdev));
+			mtty_trigger_interrupt(mdev_state);
 		}
 		break;
 
@@ -503,8 +489,7 @@ static void handle_bar_read(unsigned int index, struct mdev_state *mdev_state,
 #endif
 			if (mdev_state->s[index].uart_reg[UART_IER] &
 							 UART_IER_THRI)
-				mtty_trigger_interrupt(
-					mdev_uuid(mdev_state->mdev));
+				mtty_trigger_interrupt(mdev_state);
 		}
 		mutex_unlock(&mdev_state->rxtx_lock);
 
@@ -1028,17 +1013,9 @@ static int mtty_set_irqs(struct mdev_device *mdev, uint32_t flags,
 	return ret;
 }
 
-static int mtty_trigger_interrupt(const guid_t *uuid)
+static int mtty_trigger_interrupt(struct mdev_state *mdev_state)
 {
 	int ret = -1;
-	struct mdev_state *mdev_state;
-
-	mdev_state = find_mdev_state_by_uuid(uuid);
-
-	if (!mdev_state) {
-		pr_info("%s: mdev not found\n", __func__);
-		return -EINVAL;
-	}
 
 	if ((mdev_state->irq_index == VFIO_PCI_MSI_IRQ_INDEX) &&
 	    (!mdev_state->msi_evtfd))