Merge branch 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu

* 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu: (53 commits)
  iommu/amd: Set IOTLB invalidation timeout
  iommu/amd: Init stats for iommu=pt
  iommu/amd: Remove unnecessary cache flushes in amd_iommu_resume
  iommu/amd: Add invalidate-context call-back
  iommu/amd: Add amd_iommu_device_info() function
  iommu/amd: Adapt IOMMU driver to PCI register name changes
  iommu/amd: Add invalid_ppr callback
  iommu/amd: Implement notifiers for IOMMUv2
  iommu/amd: Implement IO page-fault handler
  iommu/amd: Add routines to bind/unbind a pasid
  iommu/amd: Implement device aquisition code for IOMMUv2
  iommu/amd: Add driver stub for AMD IOMMUv2 support
  iommu/amd: Add stat counter for IOMMUv2 events
  iommu/amd: Add device errata handling
  iommu/amd: Add function to get IOMMUv2 domain for pdev
  iommu/amd: Implement function to send PPR completions
  iommu/amd: Implement functions to manage GCR3 table
  iommu/amd: Implement IOMMUv2 TLB flushing routines
  iommu/amd: Add support for IOMMUv2 domain mode
  iommu/amd: Add amd_iommu_domain_direct_map function
  ...

8 files changed, 214 insertions, 85 deletions

diff --git a/drivers/pci/ats.c b/drivers/pci/ats.c
index b0dd08e6a9d..9dd90b30f91 100644
--- a/drivers/pci/ats.c
+++ b/drivers/pci/ats.c
@@ -175,21 +175,22 @@ int pci_enable_pri(struct pci_dev *pdev, u32 reqs)
 	u32 max_requests;
 	int pos;
 
-	pos = pci_find_ext_capability(pdev, PCI_PRI_CAP);
+	pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_PRI);
 	if (!pos)
 		return -EINVAL;
 
-	pci_read_config_word(pdev, pos + PCI_PRI_CONTROL_OFF, &control);
-	pci_read_config_word(pdev, pos + PCI_PRI_STATUS_OFF,  &status);
-	if ((control & PCI_PRI_ENABLE) || !(status & PCI_PRI_STATUS_STOPPED))
+	pci_read_config_word(pdev, pos + PCI_PRI_CTRL, &control);
+	pci_read_config_word(pdev, pos + PCI_PRI_STATUS, &status);
+	if ((control & PCI_PRI_CTRL_ENABLE) ||
+	    !(status & PCI_PRI_STATUS_STOPPED))
 		return -EBUSY;
 
-	pci_read_config_dword(pdev, pos + PCI_PRI_MAX_REQ_OFF, &max_requests);
+	pci_read_config_dword(pdev, pos + PCI_PRI_MAX_REQ, &max_requests);
 	reqs = min(max_requests, reqs);
-	pci_write_config_dword(pdev, pos + PCI_PRI_ALLOC_REQ_OFF, reqs);
+	pci_write_config_dword(pdev, pos + PCI_PRI_ALLOC_REQ, reqs);
 
-	control |= PCI_PRI_ENABLE;
-	pci_write_config_word(pdev, pos + PCI_PRI_CONTROL_OFF, control);
+	control |= PCI_PRI_CTRL_ENABLE;
+	pci_write_config_word(pdev, pos + PCI_PRI_CTRL, control);
 
 	return 0;
 }
@@ -206,13 +207,13 @@ void pci_disable_pri(struct pci_dev *pdev)
 	u16 control;
 	int pos;
 
-	pos = pci_find_ext_capability(pdev, PCI_PRI_CAP);
+	pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_PRI);
 	if (!pos)
 		return;
 
-	pci_read_config_word(pdev, pos + PCI_PRI_CONTROL_OFF, &control);
-	control &= ~PCI_PRI_ENABLE;
-	pci_write_config_word(pdev, pos + PCI_PRI_CONTROL_OFF, control);
+	pci_read_config_word(pdev, pos + PCI_PRI_CTRL, &control);
+	control &= ~PCI_PRI_CTRL_ENABLE;
+	pci_write_config_word(pdev, pos + PCI_PRI_CTRL, control);
 }
 EXPORT_SYMBOL_GPL(pci_disable_pri);
 
@@ -227,13 +228,13 @@ bool pci_pri_enabled(struct pci_dev *pdev)
 	u16 control;
 	int pos;
 
-	pos = pci_find_ext_capability(pdev, PCI_PRI_CAP);
+	pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_PRI);
 	if (!pos)
 		return false;
 
-	pci_read_config_word(pdev, pos + PCI_PRI_CONTROL_OFF, &control);
+	pci_read_config_word(pdev, pos + PCI_PRI_CTRL, &control);
 
-	return (control & PCI_PRI_ENABLE) ? true : false;
+	return (control & PCI_PRI_CTRL_ENABLE) ? true : false;
 }
 EXPORT_SYMBOL_GPL(pci_pri_enabled);
 
@@ -249,17 +250,17 @@ int pci_reset_pri(struct pci_dev *pdev)
 	u16 control;
 	int pos;
 
-	pos = pci_find_ext_capability(pdev, PCI_PRI_CAP);
+	pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_PRI);
 	if (!pos)
 		return -EINVAL;
 
-	pci_read_config_word(pdev, pos + PCI_PRI_CONTROL_OFF, &control);
-	if (control & PCI_PRI_ENABLE)
+	pci_read_config_word(pdev, pos + PCI_PRI_CTRL, &control);
+	if (control & PCI_PRI_CTRL_ENABLE)
 		return -EBUSY;
 
-	control |= PCI_PRI_RESET;
+	control |= PCI_PRI_CTRL_RESET;
 
-	pci_write_config_word(pdev, pos + PCI_PRI_CONTROL_OFF, control);
+	pci_write_config_word(pdev, pos + PCI_PRI_CTRL, control);
 
 	return 0;
 }
@@ -282,14 +283,14 @@ bool pci_pri_stopped(struct pci_dev *pdev)
 	u16 control, status;
 	int pos;
 
-	pos = pci_find_ext_capability(pdev, PCI_PRI_CAP);
+	pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_PRI);
 	if (!pos)
 		return true;
 
-	pci_read_config_word(pdev, pos + PCI_PRI_CONTROL_OFF, &control);
-	pci_read_config_word(pdev, pos + PCI_PRI_STATUS_OFF,  &status);
+	pci_read_config_word(pdev, pos + PCI_PRI_CTRL, &control);
+	pci_read_config_word(pdev, pos + PCI_PRI_STATUS, &status);
 
-	if (control & PCI_PRI_ENABLE)
+	if (control & PCI_PRI_CTRL_ENABLE)
 		return false;
 
 	return (status & PCI_PRI_STATUS_STOPPED) ? true : false;
@@ -311,15 +312,15 @@ int pci_pri_status(struct pci_dev *pdev)
 	u16 status, control;
 	int pos;
 
-	pos = pci_find_ext_capability(pdev, PCI_PRI_CAP);
+	pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_PRI);
 	if (!pos)
 		return -EINVAL;
 
-	pci_read_config_word(pdev, pos + PCI_PRI_CONTROL_OFF, &control);
-	pci_read_config_word(pdev, pos + PCI_PRI_STATUS_OFF,  &status);
+	pci_read_config_word(pdev, pos + PCI_PRI_CTRL, &control);
+	pci_read_config_word(pdev, pos + PCI_PRI_STATUS, &status);
 
 	/* Stopped bit is undefined when enable == 1, so clear it */
-	if (control & PCI_PRI_ENABLE)
+	if (control & PCI_PRI_CTRL_ENABLE)
 		status &= ~PCI_PRI_STATUS_STOPPED;
 
 	return status;
@@ -342,25 +343,25 @@ int pci_enable_pasid(struct pci_dev *pdev, int features)
 	u16 control, supported;
 	int pos;
 
-	pos = pci_find_ext_capability(pdev, PCI_PASID_CAP);
+	pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_PASID);
 	if (!pos)
 		return -EINVAL;
 
-	pci_read_config_word(pdev, pos + PCI_PASID_CONTROL_OFF, &control);
-	pci_read_config_word(pdev, pos + PCI_PASID_CAP_OFF,     &supported);
+	pci_read_config_word(pdev, pos + PCI_PASID_CTRL, &control);
+	pci_read_config_word(pdev, pos + PCI_PASID_CAP, &supported);
 
-	if (!(supported & PCI_PASID_ENABLE))
+	if (control & PCI_PASID_CTRL_ENABLE)
 		return -EINVAL;
 
-	supported &= PCI_PASID_EXEC | PCI_PASID_PRIV;
+	supported &= PCI_PASID_CAP_EXEC | PCI_PASID_CAP_PRIV;
 
 	/* User wants to enable anything unsupported? */
 	if ((supported & features) != features)
 		return -EINVAL;
 
-	control = PCI_PASID_ENABLE | features;
+	control = PCI_PASID_CTRL_ENABLE | features;
 
-	pci_write_config_word(pdev, pos + PCI_PASID_CONTROL_OFF, control);
+	pci_write_config_word(pdev, pos + PCI_PASID_CTRL, control);
 
 	return 0;
 }
@@ -376,11 +377,11 @@ void pci_disable_pasid(struct pci_dev *pdev)
 	u16 control = 0;
 	int pos;
 
-	pos = pci_find_ext_capability(pdev, PCI_PASID_CAP);
+	pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_PASID);
 	if (!pos)
 		return;
 
-	pci_write_config_word(pdev, pos + PCI_PASID_CONTROL_OFF, control);
+	pci_write_config_word(pdev, pos + PCI_PASID_CTRL, control);
 }
 EXPORT_SYMBOL_GPL(pci_disable_pasid);
 
@@ -391,22 +392,21 @@ EXPORT_SYMBOL_GPL(pci_disable_pasid);
  * Returns a negative value when no PASI capability is present.
  * Otherwise is returns a bitmask with supported features. Current
  * features reported are:
- * PCI_PASID_ENABLE - PASID capability can be enabled
- * PCI_PASID_EXEC - Execute permission supported
- * PCI_PASID_PRIV - Priviledged mode supported
+ * PCI_PASID_CAP_EXEC - Execute permission supported
+ * PCI_PASID_CAP_PRIV - Priviledged mode supported
  */
 int pci_pasid_features(struct pci_dev *pdev)
 {
 	u16 supported;
 	int pos;
 
-	pos = pci_find_ext_capability(pdev, PCI_PASID_CAP);
+	pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_PASID);
 	if (!pos)
 		return -EINVAL;
 
-	pci_read_config_word(pdev, pos + PCI_PASID_CAP_OFF, &supported);
+	pci_read_config_word(pdev, pos + PCI_PASID_CAP, &supported);
 
-	supported &= PCI_PASID_ENABLE | PCI_PASID_EXEC | PCI_PASID_PRIV;
+	supported &= PCI_PASID_CAP_EXEC | PCI_PASID_CAP_PRIV;
 
 	return supported;
 }
@@ -426,11 +426,11 @@ int pci_max_pasids(struct pci_dev *pdev)
 	u16 supported;
 	int pos;
 
-	pos = pci_find_ext_capability(pdev, PCI_PASID_CAP);
+	pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_PASID);
 	if (!pos)
 		return -EINVAL;
 
-	pci_read_config_word(pdev, pos + PCI_PASID_CAP_OFF, &supported);
+	pci_read_config_word(pdev, pos + PCI_PASID_CAP, &supported);
 
 	supported = (supported & PASID_NUMBER_MASK) >> PASID_NUMBER_SHIFT;
 
diff --git a/drivers/pci/hotplug/pciehp.h b/drivers/pci/hotplug/pciehp.h
index 838f571027b..9a33fdde2d1 100644
--- a/drivers/pci/hotplug/pciehp.h
+++ b/drivers/pci/hotplug/pciehp.h
@@ -45,7 +45,6 @@ extern int pciehp_poll_time;
 extern int pciehp_debug;
 extern int pciehp_force;
 extern struct workqueue_struct *pciehp_wq;
-extern struct workqueue_struct *pciehp_ordered_wq;
 
 #define dbg(format, arg...)						\
 do {									\
diff --git a/drivers/pci/hotplug/pciehp_core.c b/drivers/pci/hotplug/pciehp_core.c
index 7ac8358df8f..b8c99d35ac9 100644
--- a/drivers/pci/hotplug/pciehp_core.c
+++ b/drivers/pci/hotplug/pciehp_core.c
@@ -43,7 +43,6 @@ int pciehp_poll_mode;
 int pciehp_poll_time;
 int pciehp_force;
 struct workqueue_struct *pciehp_wq;
-struct workqueue_struct *pciehp_ordered_wq;
 
 #define DRIVER_VERSION	"0.4"
 #define DRIVER_AUTHOR	"Dan Zink <dan.zink@compaq.com>, Greg Kroah-Hartman <greg@kroah.com>, Dely Sy <dely.l.sy@intel.com>"
@@ -345,18 +344,11 @@ static int __init pcied_init(void)
 	if (!pciehp_wq)
 		return -ENOMEM;
 
-	pciehp_ordered_wq = alloc_ordered_workqueue("pciehp_ordered", 0);
-	if (!pciehp_ordered_wq) {
-		destroy_workqueue(pciehp_wq);
-		return -ENOMEM;
-	}
-
 	pciehp_firmware_init();
 	retval = pcie_port_service_register(&hpdriver_portdrv);
  	dbg("pcie_port_service_register = %d\n", retval);
   	info(DRIVER_DESC " version: " DRIVER_VERSION "\n");
  	if (retval) {
-		destroy_workqueue(pciehp_ordered_wq);
 		destroy_workqueue(pciehp_wq);
 		dbg("Failure to register service\n");
 	}
@@ -366,9 +358,8 @@ static int __init pcied_init(void)
 static void __exit pcied_cleanup(void)
 {
 	dbg("unload_pciehpd()\n");
-	destroy_workqueue(pciehp_ordered_wq);
-	destroy_workqueue(pciehp_wq);
 	pcie_port_service_unregister(&hpdriver_portdrv);
+	destroy_workqueue(pciehp_wq);
 	info(DRIVER_DESC " version: " DRIVER_VERSION " unloaded\n");
 }
 
diff --git a/drivers/pci/hotplug/pciehp_ctrl.c b/drivers/pci/hotplug/pciehp_ctrl.c
index 085dbb5fc16..27f44295a65 100644
--- a/drivers/pci/hotplug/pciehp_ctrl.c
+++ b/drivers/pci/hotplug/pciehp_ctrl.c
@@ -344,7 +344,7 @@ void pciehp_queue_pushbutton_work(struct work_struct *work)
 		kfree(info);
 		goto out;
 	}
-	queue_work(pciehp_ordered_wq, &info->work);
+	queue_work(pciehp_wq, &info->work);
  out:
 	mutex_unlock(&p_slot->lock);
 }
@@ -439,7 +439,7 @@ static void handle_surprise_event(struct slot *p_slot)
 	else
 		p_slot->state = POWERON_STATE;
 
-	queue_work(pciehp_ordered_wq, &info->work);
+	queue_work(pciehp_wq, &info->work);
 }
 
 static void interrupt_event_handler(struct work_struct *work)
diff --git a/drivers/pci/hotplug/pciehp_hpc.c b/drivers/pci/hotplug/pciehp_hpc.c
index 7b1414810ae..bcdbb164362 100644
--- a/drivers/pci/hotplug/pciehp_hpc.c
+++ b/drivers/pci/hotplug/pciehp_hpc.c
@@ -806,7 +806,6 @@ static void pcie_cleanup_slot(struct controller *ctrl)
 	struct slot *slot = ctrl->slot;
 	cancel_delayed_work(&slot->work);
 	flush_workqueue(pciehp_wq);
-	flush_workqueue(pciehp_ordered_wq);
 	kfree(slot);
 }
 
diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c
index 0e6d04d7ba4..337e16ab4a9 100644
--- a/drivers/pci/msi.c
+++ b/drivers/pci/msi.c
@@ -323,6 +323,8 @@ static void free_msi_irqs(struct pci_dev *dev)
 			if (list_is_last(&entry->list, &dev->msi_list))
 				iounmap(entry->mask_base);
 		}
+		kobject_del(&entry->kobj);
+		kobject_put(&entry->kobj);
 		list_del(&entry->list);
 		kfree(entry);
 	}
@@ -403,6 +405,98 @@ void pci_restore_msi_state(struct pci_dev *dev)
 }
 EXPORT_SYMBOL_GPL(pci_restore_msi_state);
 
+
+#define to_msi_attr(obj) container_of(obj, struct msi_attribute, attr)
+#define to_msi_desc(obj) container_of(obj, struct msi_desc, kobj)
+
+struct msi_attribute {
+	struct attribute        attr;
+	ssize_t (*show)(struct msi_desc *entry, struct msi_attribute *attr,
+			char *buf);
+	ssize_t (*store)(struct msi_desc *entry, struct msi_attribute *attr,
+			 const char *buf, size_t count);
+};
+
+static ssize_t show_msi_mode(struct msi_desc *entry, struct msi_attribute *atr,
+			     char *buf)
+{
+	return sprintf(buf, "%s\n", entry->msi_attrib.is_msix ? "msix" : "msi");
+}
+
+static ssize_t msi_irq_attr_show(struct kobject *kobj,
+				 struct attribute *attr, char *buf)
+{
+	struct msi_attribute *attribute = to_msi_attr(attr);
+	struct msi_desc *entry = to_msi_desc(kobj);
+
+	if (!attribute->show)
+		return -EIO;
+
+	return attribute->show(entry, attribute, buf);
+}
+
+static const struct sysfs_ops msi_irq_sysfs_ops = {
+	.show = msi_irq_attr_show,
+};
+
+static struct msi_attribute mode_attribute =
+	__ATTR(mode, S_IRUGO, show_msi_mode, NULL);
+
+
+struct attribute *msi_irq_default_attrs[] = {
+	&mode_attribute.attr,
+	NULL
+};
+
+void msi_kobj_release(struct kobject *kobj)
+{
+	struct msi_desc *entry = to_msi_desc(kobj);
+
+	pci_dev_put(entry->dev);
+}
+
+static struct kobj_type msi_irq_ktype = {
+	.release = msi_kobj_release,
+	.sysfs_ops = &msi_irq_sysfs_ops,
+	.default_attrs = msi_irq_default_attrs,
+};
+
+static int populate_msi_sysfs(struct pci_dev *pdev)
+{
+	struct msi_desc *entry;
+	struct kobject *kobj;
+	int ret;
+	int count = 0;
+
+	pdev->msi_kset = kset_create_and_add("msi_irqs", NULL, &pdev->dev.kobj);
+	if (!pdev->msi_kset)
+		return -ENOMEM;
+
+	list_for_each_entry(entry, &pdev->msi_list, list) {
+		kobj = &entry->kobj;
+		kobj->kset = pdev->msi_kset;
+		pci_dev_get(pdev);
+		ret = kobject_init_and_add(kobj, &msi_irq_ktype, NULL,
+				     "%u", entry->irq);
+		if (ret)
+			goto out_unroll;
+
+		count++;
+	}
+
+	return 0;
+
+out_unroll:
+	list_for_each_entry(entry, &pdev->msi_list, list) {
+		if (!count)
+			break;
+		kobject_del(&entry->kobj);
+		kobject_put(&entry->kobj);
+		count--;
+	}
+	return ret;
+}
+
 /**
  * msi_capability_init - configure device's MSI capability structure
  * @dev: pointer to the pci_dev data structure of MSI device function
@@ -454,6 +548,13 @@ static int msi_capability_init(struct pci_dev *dev, int nvec)
 		return ret;
 	}
 
+	ret = populate_msi_sysfs(dev);
+	if (ret) {
+		msi_mask_irq(entry, mask, ~mask);
+		free_msi_irqs(dev);
+		return ret;
+	}
+
 	/* Set MSI enabled bits	 */
 	pci_intx_for_msi(dev, 0);
 	msi_set_enable(dev, pos, 1);
@@ -574,6 +675,12 @@ static int msix_capability_init(struct pci_dev *dev,
 
 	msix_program_entries(dev, entries);
 
+	ret = populate_msi_sysfs(dev);
+	if (ret) {
+		ret = 0;
+		goto error;
+	}
+
 	/* Set MSI-X enabled bits and unmask the function */
 	pci_intx_for_msi(dev, 0);
 	dev->msix_enabled = 1;
@@ -732,6 +839,8 @@ void pci_disable_msi(struct pci_dev *dev)
 
 	pci_msi_shutdown(dev);
 	free_msi_irqs(dev);
+	kset_unregister(dev->msi_kset);
+	dev->msi_kset = NULL;
 }
 EXPORT_SYMBOL(pci_disable_msi);
 
@@ -830,6 +939,8 @@ void pci_disable_msix(struct pci_dev *dev)
 
 	pci_msix_shutdown(dev);
 	free_msi_irqs(dev);
+	kset_unregister(dev->msi_kset);
+	dev->msi_kset = NULL;
 }
 EXPORT_SYMBOL(pci_disable_msix);
 
@@ -870,5 +981,15 @@ EXPORT_SYMBOL(pci_msi_enabled);
 
 void pci_msi_init_pci_dev(struct pci_dev *dev)
 {
+	int pos;
 	INIT_LIST_HEAD(&dev->msi_list);
+
+	/* Disable the msi hardware to avoid screaming interrupts
+	 * during boot.  This is the power on reset default so
+	 * usually this should be a noop.
+	 */
+	pos = pci_find_capability(dev, PCI_CAP_ID_MSI);
+	if (pos)
+		msi_set_enable(dev, pos, 0);
+	msix_set_enable(dev, 0);
 }
diff --git a/drivers/pci/pci-acpi.c b/drivers/pci/pci-acpi.c
index 4ecb6408b0d..060fd22a110 100644
--- a/drivers/pci/pci-acpi.c
+++ b/drivers/pci/pci-acpi.c
@@ -45,16 +45,20 @@ static void pci_acpi_wake_dev(acpi_handle handle, u32 event, void *context)
 {
 	struct pci_dev *pci_dev = context;
 
-	if (event == ACPI_NOTIFY_DEVICE_WAKE && pci_dev) {
+	if (event != ACPI_NOTIFY_DEVICE_WAKE || !pci_dev)
+		return;
+
+	if (!pci_dev->pm_cap || !pci_dev->pme_support
+	     || pci_check_pme_status(pci_dev)) {
 		if (pci_dev->pme_poll)
 			pci_dev->pme_poll = false;
 
 		pci_wakeup_event(pci_dev);
-		pci_check_pme_status(pci_dev);
 		pm_runtime_resume(&pci_dev->dev);
-		if (pci_dev->subordinate)
-			pci_pme_wakeup_bus(pci_dev->subordinate);
 	}
+
+	if (pci_dev->subordinate)
+		pci_pme_wakeup_bus(pci_dev->subordinate);
 }
 
 /**
@@ -395,7 +399,6 @@ static int __init acpi_pci_init(void)
 
 	if (acpi_gbl_FADT.boot_flags & ACPI_FADT_NO_ASPM) {
 		printk(KERN_INFO"ACPI FADT declares the system doesn't support PCIe ASPM, so disable it\n");
-		pcie_clear_aspm();
 		pcie_no_aspm();
 	}
 
diff --git a/drivers/pci/pcie/aspm.c b/drivers/pci/pcie/aspm.c
index cbfbab18be9..1cfbf228fbb 100644
--- a/drivers/pci/pcie/aspm.c
+++ b/drivers/pci/pcie/aspm.c
@@ -68,7 +68,7 @@ struct pcie_link_state {
 	struct aspm_latency acceptable[8];
 };
 
-static int aspm_disabled, aspm_force, aspm_clear_state;
+static int aspm_disabled, aspm_force;
 static bool aspm_support_enabled = true;
 static DEFINE_MUTEX(aspm_lock);
 static LIST_HEAD(link_list);
@@ -500,9 +500,6 @@ static int pcie_aspm_sanity_check(struct pci_dev *pdev)
 	int pos;
 	u32 reg32;
 
-	if (aspm_clear_state)
-		return -EINVAL;
-
 	/*
 	 * Some functions in a slot might not all be PCIe functions,
 	 * very strange. Disable ASPM for the whole slot
@@ -574,9 +571,6 @@ void pcie_aspm_init_link_state(struct pci_dev *pdev)
 	    pdev->pcie_type != PCI_EXP_TYPE_DOWNSTREAM)
 		return;
 
-	if (aspm_disabled && !aspm_clear_state)
-		return;
-
 	/* VIA has a strange chipset, root port is under a bridge */
 	if (pdev->pcie_type == PCI_EXP_TYPE_ROOT_PORT &&
 	    pdev->bus->self)
@@ -608,7 +602,7 @@ void pcie_aspm_init_link_state(struct pci_dev *pdev)
 	 * the BIOS's expectation, we'll do so once pci_enable_device() is
 	 * called.
 	 */
-	if (aspm_policy != POLICY_POWERSAVE || aspm_clear_state) {
+	if (aspm_policy != POLICY_POWERSAVE) {
 		pcie_config_aspm_path(link);
 		pcie_set_clkpm(link, policy_to_clkpm_state(link));
 	}
@@ -649,8 +643,7 @@ void pcie_aspm_exit_link_state(struct pci_dev *pdev)
 	struct pci_dev *parent = pdev->bus->self;
 	struct pcie_link_state *link, *root, *parent_link;
 
-	if ((aspm_disabled && !aspm_clear_state) || !pci_is_pcie(pdev) ||
-	    !parent || !parent->link_state)
+	if (!pci_is_pcie(pdev) || !parent || !parent->link_state)
 		return;
 	if ((parent->pcie_type != PCI_EXP_TYPE_ROOT_PORT) &&
 	    (parent->pcie_type != PCI_EXP_TYPE_DOWNSTREAM))
@@ -734,13 +727,18 @@ void pcie_aspm_powersave_config_link(struct pci_dev *pdev)
  * pci_disable_link_state - disable pci device's link state, so the link will
  * never enter specific states
  */
-static void __pci_disable_link_state(struct pci_dev *pdev, int state, bool sem)
+static void __pci_disable_link_state(struct pci_dev *pdev, int state, bool sem,
+				     bool force)
 {
 	struct pci_dev *parent = pdev->bus->self;
 	struct pcie_link_state *link;
 
-	if (aspm_disabled || !pci_is_pcie(pdev))
+	if (aspm_disabled && !force)
+		return;
+
+	if (!pci_is_pcie(pdev))
 		return;
+
 	if (pdev->pcie_type == PCI_EXP_TYPE_ROOT_PORT ||
 	    pdev->pcie_type == PCI_EXP_TYPE_DOWNSTREAM)
 		parent = pdev;
@@ -768,16 +766,31 @@ static void __pci_disable_link_state(struct pci_dev *pdev, int state, bool sem)
 
 void pci_disable_link_state_locked(struct pci_dev *pdev, int state)
 {
-	__pci_disable_link_state(pdev, state, false);
+	__pci_disable_link_state(pdev, state, false, false);
 }
 EXPORT_SYMBOL(pci_disable_link_state_locked);
 
 void pci_disable_link_state(struct pci_dev *pdev, int state)
 {
-	__pci_disable_link_state(pdev, state, true);
+	__pci_disable_link_state(pdev, state, true, false);
 }
 EXPORT_SYMBOL(pci_disable_link_state);
 
+void pcie_clear_aspm(struct pci_bus *bus)
+{
+	struct pci_dev *child;
+
+	/*
+	 * Clear any ASPM setup that the firmware has carried out on this bus
+	 */
+	list_for_each_entry(child, &bus->devices, bus_list) {
+		__pci_disable_link_state(child, PCIE_LINK_STATE_L0S |
+					 PCIE_LINK_STATE_L1 |
+					 PCIE_LINK_STATE_CLKPM,
+					 false, true);
+	}
+}
+
 static int pcie_aspm_set_policy(const char *val, struct kernel_param *kp)
 {
 	int i;
@@ -935,6 +948,7 @@ void pcie_aspm_remove_sysfs_dev_files(struct pci_dev *pdev)
 static int __init pcie_aspm_disable(char *str)
 {
 	if (!strcmp(str, "off")) {
+		aspm_policy = POLICY_DEFAULT;
 		aspm_disabled = 1;
 		aspm_support_enabled = false;
 		printk(KERN_INFO "PCIe ASPM is disabled\n");
@@ -947,16 +961,18 @@ static int __init pcie_aspm_disable(char *str)
 
 __setup("pcie_aspm=", pcie_aspm_disable);
 
-void pcie_clear_aspm(void)
-{
-	if (!aspm_force)
-		aspm_clear_state = 1;
-}
-
 void pcie_no_aspm(void)
 {
-	if (!aspm_force)
+	/*
+	 * Disabling ASPM is intended to prevent the kernel from modifying
+	 * existing hardware state, not to clear existing state. To that end:
+	 * (a) set policy to POLICY_DEFAULT in order to avoid changing state
+	 * (b) prevent userspace from changing policy
+	 */
+	if (!aspm_force) {
+		aspm_policy = POLICY_DEFAULT;
 		aspm_disabled = 1;
+	}
 }
 
 /**