Merge tag 'vfio-v5.1-rc1' of git://github.com/awilliam/linux-vfio

Pull VFIO updates from Alex Williamson:

 - Switch mdev to generic UUID API (Andy Shevchenko)

 - Fixup platform reset include paths (Masahiro Yamada)

 - Fix usage of MINORMASK (Chengguang Xu)

 - Remove noise from duplicate spapr table unsets (Alexey Kardashevskiy)

 - Restore device state after PM reset (Alex Williamson)

 - Ensure memory translation enabled for PCI ROM access (Eric Auger)

* tag 'vfio-v5.1-rc1' of git://github.com/awilliam/linux-vfio:
  vfio_pci: Enable memory accesses before calling pci_map_rom
  vfio/pci: Restore device state on PM transition
  vfio/spapr_tce: Skip unsetting already unset table
  samples/vfio-mdev/mtty: expand minor range when registering chrdev region
  samples/vfio-mdev/mdpy: expand minor range when registering chrdev region
  samples/vfio-mdev/mbochs: expand minor range when registering chrdev region
  vfio: expand minor range when registering chrdev region
  vfio: platform: reset: fix up include directives to remove ccflags-y
  vfio-mdev: Switch to use new generic UUID API

drivers/vfio/mdev/mdev_core.c

@@ -60,9 +60,9 @@ struct mdev_device *mdev_from_dev(struct device *dev)
 }
 EXPORT_SYMBOL(mdev_from_dev);
 
-uuid_le mdev_uuid(struct mdev_device *mdev)
+const guid_t *mdev_uuid(struct mdev_device *mdev)
 {
-	return mdev->uuid;
+	return &mdev->uuid;
 }
 EXPORT_SYMBOL(mdev_uuid);
 
@@ -88,8 +88,7 @@ static void mdev_release_parent(struct kref *kref)
 	put_device(dev);
 }
 
-static
-inline struct mdev_parent *mdev_get_parent(struct mdev_parent *parent)
+static inline struct mdev_parent *mdev_get_parent(struct mdev_parent *parent)
 {
 	if (parent)
 		kref_get(&parent->ref);
@@ -276,7 +275,8 @@ static void mdev_device_release(struct device *dev)
 	kfree(mdev);
 }
 
-int mdev_device_create(struct kobject *kobj, struct device *dev, uuid_le uuid)
+int mdev_device_create(struct kobject *kobj,
+		       struct device *dev, const guid_t *uuid)
 {
 	int ret;
 	struct mdev_device *mdev, *tmp;
@@ -291,7 +291,7 @@ int mdev_device_create(struct kobject *kobj, struct device *dev, uuid_le uuid)
 
 	/* Check for duplicate */
 	list_for_each_entry(tmp, &mdev_list, next) {
-		if (!uuid_le_cmp(tmp->uuid, uuid)) {
+		if (guid_equal(&tmp->uuid, uuid)) {
 			mutex_unlock(&mdev_list_lock);
 			ret = -EEXIST;
 			goto mdev_fail;
@@ -305,7 +305,7 @@ int mdev_device_create(struct kobject *kobj, struct device *dev, uuid_le uuid)
 		goto mdev_fail;
 	}
 
-	memcpy(&mdev->uuid, &uuid, sizeof(uuid_le));
+	guid_copy(&mdev->uuid, uuid);
 	list_add(&mdev->next, &mdev_list);
 	mutex_unlock(&mdev_list_lock);
 
@@ -315,7 +315,7 @@ int mdev_device_create(struct kobject *kobj, struct device *dev, uuid_le uuid)
 	mdev->dev.parent  = dev;
 	mdev->dev.bus     = &mdev_bus_type;
 	mdev->dev.release = mdev_device_release;
-	dev_set_name(&mdev->dev, "%pUl", uuid.b);
+	dev_set_name(&mdev->dev, "%pUl", uuid);
 
 	ret = device_register(&mdev->dev);
 	if (ret) {

drivers/vfio/mdev/mdev_private.h

@@ -28,7 +28,7 @@ struct mdev_parent {
 struct mdev_device {
 	struct device dev;
 	struct mdev_parent *parent;
-	uuid_le uuid;
+	guid_t uuid;
 	void *driver_data;
 	struct kref ref;
 	struct list_head next;
@@ -58,7 +58,8 @@ void parent_remove_sysfs_files(struct mdev_parent *parent);
 int  mdev_create_sysfs_files(struct device *dev, struct mdev_type *type);
 void mdev_remove_sysfs_files(struct device *dev, struct mdev_type *type);
 
-int  mdev_device_create(struct kobject *kobj, struct device *dev, uuid_le uuid);
+int  mdev_device_create(struct kobject *kobj,
+			struct device *dev, const guid_t *uuid);
 int  mdev_device_remove(struct device *dev, bool force_remove);
 
 #endif /* MDEV_PRIVATE_H */

drivers/vfio/mdev/mdev_sysfs.c

@@ -55,7 +55,7 @@ static ssize_t create_store(struct kobject *kobj, struct device *dev,
 			    const char *buf, size_t count)
 {
 	char *str;
-	uuid_le uuid;
+	guid_t uuid;
 	int ret;
 
 	if ((count < UUID_STRING_LEN) || (count > UUID_STRING_LEN + 1))
@@ -65,12 +65,12 @@ static ssize_t create_store(struct kobject *kobj, struct device *dev,
 	if (!str)
 		return -ENOMEM;
 
-	ret = uuid_le_to_bin(str, &uuid);
+	ret = guid_parse(str, &uuid);
 	kfree(str);
 	if (ret)
 		return ret;
 
-	ret = mdev_device_create(kobj, dev, uuid);
+	ret = mdev_device_create(kobj, dev, &uuid);
 	if (ret)
 		return ret;
 

drivers/vfio/pci/vfio_pci.c

@@ -209,14 +209,65 @@ static bool vfio_pci_nointx(struct pci_dev *pdev)
 	return false;
 }
 
+static void vfio_pci_probe_power_state(struct vfio_pci_device *vdev)
+{
+	struct pci_dev *pdev = vdev->pdev;
+	u16 pmcsr;
+
+	if (!pdev->pm_cap)
+		return;
+
+	pci_read_config_word(pdev, pdev->pm_cap + PCI_PM_CTRL, &pmcsr);
+
+	vdev->needs_pm_restore = !(pmcsr & PCI_PM_CTRL_NO_SOFT_RESET);
+}
+
+/*
+ * pci_set_power_state() wrapper handling devices which perform a soft reset on
+ * D3->D0 transition.  Save state prior to D0/1/2->D3, stash it on the vdev,
+ * restore when returned to D0.  Saved separately from pci_saved_state for use
+ * by PM capability emulation and separately from pci_dev internal saved state
+ * to avoid it being overwritten and consumed around other resets.
+ */
+int vfio_pci_set_power_state(struct vfio_pci_device *vdev, pci_power_t state)
+{
+	struct pci_dev *pdev = vdev->pdev;
+	bool needs_restore = false, needs_save = false;
+	int ret;
+
+	if (vdev->needs_pm_restore) {
+		if (pdev->current_state < PCI_D3hot && state >= PCI_D3hot) {
+			pci_save_state(pdev);
+			needs_save = true;
+		}
+
+		if (pdev->current_state >= PCI_D3hot && state <= PCI_D0)
+			needs_restore = true;
+	}
+
+	ret = pci_set_power_state(pdev, state);
+
+	if (!ret) {
+		/* D3 might be unsupported via quirk, skip unless in D3 */
+		if (needs_save && pdev->current_state >= PCI_D3hot) {
+			vdev->pm_save = pci_store_saved_state(pdev);
+		} else if (needs_restore) {
+			pci_load_and_free_saved_state(pdev, &vdev->pm_save);
+			pci_restore_state(pdev);
+		}
+	}
+
+	return ret;
+}
+
 static int vfio_pci_enable(struct vfio_pci_device *vdev)
 {
 	struct pci_dev *pdev = vdev->pdev;
 	int ret;
 	u16 cmd;
 	u8 msix_pos;
 
-	pci_set_power_state(pdev, PCI_D0);
+	vfio_pci_set_power_state(vdev, PCI_D0);
 
 	/* Don't allow our initial saved state to include busmaster */
 	pci_clear_master(pdev);
@@ -407,7 +458,7 @@ static void vfio_pci_disable(struct vfio_pci_device *vdev)
 	vfio_pci_try_bus_reset(vdev);
 
 	if (!disable_idle_d3)
-		pci_set_power_state(pdev, PCI_D3hot);
+		vfio_pci_set_power_state(vdev, PCI_D3hot);
 }
 
 static void vfio_pci_release(void *device_data)
@@ -708,6 +759,7 @@ static long vfio_pci_ioctl(void *device_data,
 		{
 			void __iomem *io;
 			size_t size;
+			u16 orig_cmd;
 
 			info.offset = VFIO_PCI_INDEX_TO_OFFSET(info.index);
 			info.flags = 0;
@@ -723,15 +775,23 @@ static long vfio_pci_ioctl(void *device_data,
 					break;
 			}
 
-			/* Is it really there? */
+			/*
+			 * Is it really there?  Enable memory decode for
+			 * implicit access in pci_map_rom().
+			 */
+			pci_read_config_word(pdev, PCI_COMMAND, &orig_cmd);
+			pci_write_config_word(pdev, PCI_COMMAND,
+					      orig_cmd | PCI_COMMAND_MEMORY);
+
 			io = pci_map_rom(pdev, &size);
-			if (!io || !size) {
+			if (io) {
+				info.flags = VFIO_REGION_INFO_FLAG_READ;
+				pci_unmap_rom(pdev, io);
+			} else {
 				info.size = 0;
-				break;
 			}
-			pci_unmap_rom(pdev, io);
 
-			info.flags = VFIO_REGION_INFO_FLAG_READ;
+			pci_write_config_word(pdev, PCI_COMMAND, orig_cmd);
 			break;
 		}
 		case VFIO_PCI_VGA_REGION_INDEX:
@@ -1286,6 +1346,8 @@ static int vfio_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 					vfio_pci_set_vga_decode(vdev, false));
 	}
 
+	vfio_pci_probe_power_state(vdev);
+
 	if (!disable_idle_d3) {
 		/*
 		 * pci-core sets the device power state to an unknown value at
@@ -1296,8 +1358,8 @@ static int vfio_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		 * be able to get to D3.  Therefore first do a D0 transition
 		 * before going to D3.
 		 */
-		pci_set_power_state(pdev, PCI_D0);
-		pci_set_power_state(pdev, PCI_D3hot);
+		vfio_pci_set_power_state(vdev, PCI_D0);
+		vfio_pci_set_power_state(vdev, PCI_D3hot);
 	}
 
 	return ret;
@@ -1316,6 +1378,11 @@ static void vfio_pci_remove(struct pci_dev *pdev)
 	vfio_iommu_group_put(pdev->dev.iommu_group, &pdev->dev);
 	kfree(vdev->region);
 	mutex_destroy(&vdev->ioeventfds_lock);
+
+	if (!disable_idle_d3)
+		vfio_pci_set_power_state(vdev, PCI_D0);
+
+	kfree(vdev->pm_save);
 	kfree(vdev);
 
 	if (vfio_pci_is_vga(pdev)) {
@@ -1324,9 +1391,6 @@ static void vfio_pci_remove(struct pci_dev *pdev)
 				VGA_RSRC_NORMAL_IO | VGA_RSRC_NORMAL_MEM |
 				VGA_RSRC_LEGACY_IO | VGA_RSRC_LEGACY_MEM);
 	}
-
-	if (!disable_idle_d3)
-		pci_set_power_state(pdev, PCI_D0);
 }
 
 static pci_ers_result_t vfio_pci_aer_err_detected(struct pci_dev *pdev,
@@ -1551,7 +1615,7 @@ static void vfio_pci_try_bus_reset(struct vfio_pci_device *vdev)
 			tmp->needs_reset = false;
 
 			if (tmp != vdev && !disable_idle_d3)
-				pci_set_power_state(tmp->pdev, PCI_D3hot);
+				vfio_pci_set_power_state(tmp, PCI_D3hot);
 		}
 
 		vfio_device_put(devs.devices[i]);

drivers/vfio/pci/vfio_pci_config.c

@@ -691,7 +691,7 @@ static int vfio_pm_config_write(struct vfio_pci_device *vdev, int pos,
 			break;
 		}
 
-		pci_set_power_state(vdev->pdev, state);
+		vfio_pci_set_power_state(vdev, state);
 	}
 
 	return count;

drivers/vfio/pci/vfio_pci_private.h

@@ -114,7 +114,9 @@ struct vfio_pci_device {
 	bool			has_vga;
 	bool			needs_reset;
 	bool			nointx;
+	bool			needs_pm_restore;
 	struct pci_saved_state	*pci_saved_state;
+	struct pci_saved_state	*pm_save;
 	struct vfio_pci_reflck	*reflck;
 	int			refcnt;
 	int			ioeventfds_nr;
@@ -161,6 +163,10 @@ extern int vfio_pci_register_dev_region(struct vfio_pci_device *vdev,
 					unsigned int type, unsigned int subtype,
 					const struct vfio_pci_regops *ops,
 					size_t size, u32 flags, void *data);
+
+extern int vfio_pci_set_power_state(struct vfio_pci_device *vdev,
+				    pci_power_t state);
+
 #ifdef CONFIG_VFIO_PCI_IGD
 extern int vfio_pci_igd_init(struct vfio_pci_device *vdev);
 #else

drivers/vfio/platform/reset/Makefile

@@ -2,8 +2,6 @@
 vfio-platform-calxedaxgmac-y := vfio_platform_calxedaxgmac.o
 vfio-platform-amdxgbe-y := vfio_platform_amdxgbe.o
 
-ccflags-y += -Idrivers/vfio/platform
-
 obj-$(CONFIG_VFIO_PLATFORM_CALXEDAXGMAC_RESET) += vfio-platform-calxedaxgmac.o
 obj-$(CONFIG_VFIO_PLATFORM_AMDXGBE_RESET) += vfio-platform-amdxgbe.o
 obj-$(CONFIG_VFIO_PLATFORM_BCMFLEXRM_RESET) += vfio_platform_bcmflexrm.o

drivers/vfio/platform/reset/vfio_platform_amdxgbe.c

@@ -25,7 +25,7 @@
 #include <uapi/linux/mdio.h>
 #include <linux/delay.h>
 
-#include "vfio_platform_private.h"
+#include "../vfio_platform_private.h"
 
 #define DMA_MR			0x3000
 #define MAC_VR			0x0110

drivers/vfio/platform/reset/vfio_platform_bcmflexrm.c

@@ -23,7 +23,7 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 
-#include "vfio_platform_private.h"
+#include "../vfio_platform_private.h"
 
 /* FlexRM configuration */
 #define RING_REGS_SIZE					0x10000

drivers/vfio/platform/reset/vfio_platform_calxedaxgmac.c

@@ -24,7 +24,7 @@
 #include <linux/init.h>
 #include <linux/io.h>
 
-#include "vfio_platform_private.h"
+#include "../vfio_platform_private.h"
 
 #define DRIVER_VERSION  "0.1"
 #define DRIVER_AUTHOR   "Eric Auger <[email protected]>"

drivers/vfio/vfio.c

@@ -2219,12 +2219,12 @@ static int __init vfio_init(void)
 
 	vfio.class->devnode = vfio_devnode;
 
-	ret = alloc_chrdev_region(&vfio.group_devt, 0, MINORMASK, "vfio");
+	ret = alloc_chrdev_region(&vfio.group_devt, 0, MINORMASK + 1, "vfio");
 	if (ret)
 		goto err_alloc_chrdev;
 
 	cdev_init(&vfio.group_cdev, &vfio_group_fops);
-	ret = cdev_add(&vfio.group_cdev, vfio.group_devt, MINORMASK);
+	ret = cdev_add(&vfio.group_cdev, vfio.group_devt, MINORMASK + 1);
 	if (ret)
 		goto err_cdev_add;
 
@@ -2236,7 +2236,7 @@ static int __init vfio_init(void)
 	return 0;
 
 err_cdev_add:
-	unregister_chrdev_region(vfio.group_devt, MINORMASK);
+	unregister_chrdev_region(vfio.group_devt, MINORMASK + 1);
 err_alloc_chrdev:
 	class_destroy(vfio.class);
 	vfio.class = NULL;
@@ -2254,7 +2254,7 @@ static void __exit vfio_cleanup(void)
 #endif
 	idr_destroy(&vfio.group_idr);
 	cdev_del(&vfio.group_cdev);
-	unregister_chrdev_region(vfio.group_devt, MINORMASK);
+	unregister_chrdev_region(vfio.group_devt, MINORMASK + 1);
 	class_destroy(vfio.class);
 	vfio.class = NULL;
 	misc_deregister(&vfio_dev);

drivers/vfio/vfio_iommu_spapr_tce.c

@@ -1235,7 +1235,8 @@ static void tce_iommu_release_ownership_ddw(struct tce_container *container,
 	}
 
 	for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i)
-		table_group->ops->unset_window(table_group, i);
+		if (container->tables[i])
+			table_group->ops->unset_window(table_group, i);
 
 	table_group->ops->release_ownership(table_group);
 }

include/linux/mdev.h

@@ -120,7 +120,7 @@ struct mdev_driver {
 
 extern void *mdev_get_drvdata(struct mdev_device *mdev);
 extern void mdev_set_drvdata(struct mdev_device *mdev, void *data);
-extern uuid_le mdev_uuid(struct mdev_device *mdev);
+extern const guid_t *mdev_uuid(struct mdev_device *mdev);
 
 extern struct bus_type mdev_bus_type;