Merge branches 'v5.18/vfio/next/mlx5-migration-v10', 'v5.18/vfio/next/pm-fixes' and 'v5.18/vfio/next/uml-build-fix' into v5.18/vfio/next/next

drivers/vfio/pci/vfio_pci_core.c

@@ -228,6 +228,19 @@ int vfio_pci_set_power_state(struct vfio_pci_core_device *vdev, pci_power_t stat
 	if (!ret) {
 		/* D3 might be unsupported via quirk, skip unless in D3 */
 		if (needs_save && pdev->current_state >= PCI_D3hot) {
+			/*
+			 * The current PCI state will be saved locally in
+			 * 'pm_save' during the D3hot transition. When the
+			 * device state is changed to D0 again with the current
+			 * function, then pci_store_saved_state() will restore
+			 * the state and will free the memory pointed by
+			 * 'pm_save'. There are few cases where the PCI power
+			 * state can be changed to D0 without the involvement
+			 * of the driver. For these cases, free the earlier
+			 * allocated memory first before overwriting 'pm_save'
+			 * to prevent the memory leak.
+			 */
+			kfree(vdev->pm_save);
 			vdev->pm_save = pci_store_saved_state(pdev);
 		} else if (needs_restore) {
 			pci_load_and_free_saved_state(pdev, &vdev->pm_save);
@@ -322,6 +335,17 @@ void vfio_pci_core_disable(struct vfio_pci_core_device *vdev)
 	/* For needs_reset */
 	lockdep_assert_held(&vdev->vdev.dev_set->lock);
 
+	/*
+	 * This function can be invoked while the power state is non-D0.
+	 * This function calls __pci_reset_function_locked() which internally
+	 * can use pci_pm_reset() for the function reset. pci_pm_reset() will
+	 * fail if the power state is non-D0. Also, for the devices which
+	 * have NoSoftRst-, the reset function can cause the PCI config space
+	 * reset without restoring the original state (saved locally in
+	 * 'vdev->pm_save').
+	 */
+	vfio_pci_set_power_state(vdev, PCI_D0);
+
 	/* Stop the device from further DMA */
 	pci_clear_master(pdev);
 
@@ -921,6 +945,19 @@ long vfio_pci_core_ioctl(struct vfio_device *core_vdev, unsigned int cmd,
 			return -EINVAL;
 
 		vfio_pci_zap_and_down_write_memory_lock(vdev);
+
+		/*
+		 * This function can be invoked while the power state is non-D0.
+		 * If pci_try_reset_function() has been called while the power
+		 * state is non-D0, then pci_try_reset_function() will
+		 * internally set the power state to D0 without vfio driver
+		 * involvement. For the devices which have NoSoftRst-, the
+		 * reset function can cause the PCI config space reset without
+		 * restoring the original state (saved locally in
+		 * 'vdev->pm_save').
+		 */
+		vfio_pci_set_power_state(vdev, PCI_D0);
+
 		ret = pci_try_reset_function(vdev->pdev);
 		up_write(&vdev->memory_lock);
 
@@ -2036,6 +2073,18 @@ static int vfio_pci_dev_set_hot_reset(struct vfio_device_set *dev_set,
 	}
 	cur_mem = NULL;
 
+	/*
+	 * The pci_reset_bus() will reset all the devices in the bus.
+	 * The power state can be non-D0 for some of the devices in the bus.
+	 * For these devices, the pci_reset_bus() will internally set
+	 * the power state to D0 without vfio driver involvement.
+	 * For the devices which have NoSoftRst-, the reset function can
+	 * cause the PCI config space reset without restoring the original
+	 * state (saved locally in 'vdev->pm_save').
+	 */
+	list_for_each_entry(cur, &dev_set->device_list, vdev.dev_set_list)
+		vfio_pci_set_power_state(cur, PCI_D0);
+
 	ret = pci_reset_bus(pdev);
 
 err_undo:
@@ -2089,6 +2138,18 @@ static bool vfio_pci_dev_set_try_reset(struct vfio_device_set *dev_set)
 	if (!pdev)
 		return false;
 
+	/*
+	 * The pci_reset_bus() will reset all the devices in the bus.
+	 * The power state can be non-D0 for some of the devices in the bus.
+	 * For these devices, the pci_reset_bus() will internally set
+	 * the power state to D0 without vfio driver involvement.
+	 * For the devices which have NoSoftRst-, the reset function can
+	 * cause the PCI config space reset without restoring the original
+	 * state (saved locally in 'vdev->pm_save').
+	 */
+	list_for_each_entry(cur, &dev_set->device_list, vdev.dev_set_list)
+		vfio_pci_set_power_state(cur, PCI_D0);
+
 	ret = pci_reset_bus(pdev);
 	if (ret)
 		return false;

drivers/vfio/pci/vfio_pci_rdwr.c

@@ -288,6 +288,7 @@ ssize_t vfio_pci_bar_rw(struct vfio_pci_core_device *vdev, char __user *buf,
 	return done;
 }
 
+#ifdef CONFIG_VFIO_PCI_VGA
 ssize_t vfio_pci_vga_rw(struct vfio_pci_core_device *vdev, char __user *buf,
 			       size_t count, loff_t *ppos, bool iswrite)
 {
@@ -355,6 +356,7 @@ ssize_t vfio_pci_vga_rw(struct vfio_pci_core_device *vdev, char __user *buf,
 
 	return done;
 }
+#endif
 
 static void vfio_pci_ioeventfd_do_write(struct vfio_pci_ioeventfd *ioeventfd,
 					bool test_mem)

include/linux/vfio_pci_core.h

@@ -159,8 +159,17 @@ extern ssize_t vfio_pci_config_rw(struct vfio_pci_core_device *vdev,
 extern ssize_t vfio_pci_bar_rw(struct vfio_pci_core_device *vdev, char __user *buf,
 			       size_t count, loff_t *ppos, bool iswrite);
 
+#ifdef CONFIG_VFIO_PCI_VGA
 extern ssize_t vfio_pci_vga_rw(struct vfio_pci_core_device *vdev, char __user *buf,
 			       size_t count, loff_t *ppos, bool iswrite);
+#else
+static inline ssize_t vfio_pci_vga_rw(struct vfio_pci_core_device *vdev,
+				      char __user *buf, size_t count,
+				      loff_t *ppos, bool iswrite)
+{
+	return -EINVAL;
+}
+#endif
 
 extern long vfio_pci_ioeventfd(struct vfio_pci_core_device *vdev, loff_t offset,
 			       uint64_t data, int count, int fd);