Merge tag 'stable/for-linus-3.19-rc0-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip

Pull xen features and fixes from David Vrabel:

 - Fully support non-coherent devices on ARM by introducing the
   mechanisms to request the hypervisor to perform the required cache
   maintainance operations.

 - A number of pciback bug fixes and cleanups.  Notably a deadlock fix
   if a PCI device was manually uunbound and a fix for incorrectly
   restoring state after a function reset.

 - In x86 PVHVM guests, use the APIC for interrupts if this has been
   virtualized by the hardware.  This reduces the number of interrupt-
   related VM exits on such hardware.

* tag 'stable/for-linus-3.19-rc0-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip: (26 commits)
  Revert "swiotlb-xen: pass dev_addr to swiotlb_tbl_unmap_single"
  xen/pci: Use APIC directly when APIC virtualization hardware is available
  xen/pci: Defer initialization of MSI ops on HVM guests
  xen-pciback: drop SR-IOV VFs when PF driver unloads
  xen/pciback: Restore configuration space when detaching from a guest.
  PCI: Expose pci_load_saved_state for public consumption.
  xen/pciback: Remove tons of dereferences
  xen/pciback: Print out the domain owning the device.
  xen/pciback: Include the domain id if removing the device whilst still in use
  driver core: Provide an wrapper around the mutex to do lockdep warnings
  xen/pciback: Don't deadlock when unbinding.
  swiotlb-xen: pass dev_addr to swiotlb_tbl_unmap_single
  swiotlb-xen: call xen_dma_sync_single_for_device when appropriate
  swiotlb-xen: remove BUG_ON in xen_bus_to_phys
  swiotlb-xen: pass dev_addr to xen_dma_unmap_page and xen_dma_sync_single_for_cpu
  xen/arm: introduce GNTTABOP_cache_flush
  xen/arm/arm64: introduce xen_arch_need_swiotlb
  xen/arm/arm64: merge xen/mm32.c into xen/mm.c
  xen/arm: use hypercall to flush caches in map_page
  xen: add a dma_addr_t dev_addr argument to xen_dma_map_page
  ...

6 files changed, 130 insertions, 40 deletions

diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c
index ebd8f218a788..810ad419e34c 100644
--- a/drivers/xen/swiotlb-xen.c
+++ b/drivers/xen/swiotlb-xen.c
@@ -96,8 +96,6 @@ static inline phys_addr_t xen_bus_to_phys(dma_addr_t baddr)
 	dma_addr_t dma = (dma_addr_t)pfn << PAGE_SHIFT;
 	phys_addr_t paddr = dma;
 
-	BUG_ON(paddr != dma); /* truncation has occurred, should never happen */
-
 	paddr |= baddr & ~PAGE_MASK;
 
 	return paddr;
@@ -399,11 +397,13 @@ dma_addr_t xen_swiotlb_map_page(struct device *dev, struct page *page,
 	 * buffering it.
 	 */
 	if (dma_capable(dev, dev_addr, size) &&
-	    !range_straddles_page_boundary(phys, size) && !swiotlb_force) {
+	    !range_straddles_page_boundary(phys, size) &&
+		!xen_arch_need_swiotlb(dev, PFN_DOWN(phys), PFN_DOWN(dev_addr)) &&
+		!swiotlb_force) {
 		/* we are not interested in the dma_addr returned by
 		 * xen_dma_map_page, only in the potential cache flushes executed
 		 * by the function. */
-		xen_dma_map_page(dev, page, offset, size, dir, attrs);
+		xen_dma_map_page(dev, page, dev_addr, offset, size, dir, attrs);
 		return dev_addr;
 	}
 
@@ -417,7 +417,7 @@ dma_addr_t xen_swiotlb_map_page(struct device *dev, struct page *page,
 		return DMA_ERROR_CODE;
 
 	xen_dma_map_page(dev, pfn_to_page(map >> PAGE_SHIFT),
-					map & ~PAGE_MASK, size, dir, attrs);
+					dev_addr, map & ~PAGE_MASK, size, dir, attrs);
 	dev_addr = xen_phys_to_bus(map);
 
 	/*
@@ -447,7 +447,7 @@ static void xen_unmap_single(struct device *hwdev, dma_addr_t dev_addr,
 
 	BUG_ON(dir == DMA_NONE);
 
-	xen_dma_unmap_page(hwdev, paddr, size, dir, attrs);
+	xen_dma_unmap_page(hwdev, dev_addr, size, dir, attrs);
 
 	/* NOTE: We use dev_addr here, not paddr! */
 	if (is_xen_swiotlb_buffer(dev_addr)) {
@@ -495,14 +495,14 @@ xen_swiotlb_sync_single(struct device *hwdev, dma_addr_t dev_addr,
 	BUG_ON(dir == DMA_NONE);
 
 	if (target == SYNC_FOR_CPU)
-		xen_dma_sync_single_for_cpu(hwdev, paddr, size, dir);
+		xen_dma_sync_single_for_cpu(hwdev, dev_addr, size, dir);
 
 	/* NOTE: We use dev_addr here, not paddr! */
 	if (is_xen_swiotlb_buffer(dev_addr))
 		swiotlb_tbl_sync_single(hwdev, paddr, size, dir, target);
 
 	if (target == SYNC_FOR_DEVICE)
-		xen_dma_sync_single_for_cpu(hwdev, paddr, size, dir);
+		xen_dma_sync_single_for_device(hwdev, dev_addr, size, dir);
 
 	if (dir != DMA_FROM_DEVICE)
 		return;
@@ -557,6 +557,7 @@ xen_swiotlb_map_sg_attrs(struct device *hwdev, struct scatterlist *sgl,
 		dma_addr_t dev_addr = xen_phys_to_bus(paddr);
 
 		if (swiotlb_force ||
+		    xen_arch_need_swiotlb(hwdev, PFN_DOWN(paddr), PFN_DOWN(dev_addr)) ||
 		    !dma_capable(hwdev, dev_addr, sg->length) ||
 		    range_straddles_page_boundary(paddr, sg->length)) {
 			phys_addr_t map = swiotlb_tbl_map_single(hwdev,
@@ -574,6 +575,7 @@ xen_swiotlb_map_sg_attrs(struct device *hwdev, struct scatterlist *sgl,
 				return 0;
 			}
 			xen_dma_map_page(hwdev, pfn_to_page(map >> PAGE_SHIFT),
+						dev_addr,
 						map & ~PAGE_MASK,
 						sg->length,
 						dir,
@@ -584,6 +586,7 @@ xen_swiotlb_map_sg_attrs(struct device *hwdev, struct scatterlist *sgl,
 			 * xen_dma_map_page, only in the potential cache flushes executed
 			 * by the function. */
 			xen_dma_map_page(hwdev, pfn_to_page(paddr >> PAGE_SHIFT),
+						dev_addr,
 						paddr & ~PAGE_MASK,
 						sg->length,
 						dir,
diff --git a/drivers/xen/xen-pciback/passthrough.c b/drivers/xen/xen-pciback/passthrough.c
index 828dddc360df..f16a30e2a110 100644
--- a/drivers/xen/xen-pciback/passthrough.c
+++ b/drivers/xen/xen-pciback/passthrough.c
@@ -69,7 +69,7 @@ static int __xen_pcibk_add_pci_dev(struct xen_pcibk_device *pdev,
 }
 
 static void __xen_pcibk_release_pci_dev(struct xen_pcibk_device *pdev,
-					struct pci_dev *dev)
+					struct pci_dev *dev, bool lock)
 {
 	struct passthrough_dev_data *dev_data = pdev->pci_dev_data;
 	struct pci_dev_entry *dev_entry, *t;
@@ -87,8 +87,13 @@ static void __xen_pcibk_release_pci_dev(struct xen_pcibk_device *pdev,
 
 	mutex_unlock(&dev_data->lock);
 
-	if (found_dev)
+	if (found_dev) {
+		if (lock)
+			device_lock(&found_dev->dev);
 		pcistub_put_pci_dev(found_dev);
+		if (lock)
+			device_unlock(&found_dev->dev);
+	}
 }
 
 static int __xen_pcibk_init_devices(struct xen_pcibk_device *pdev)
@@ -156,8 +161,11 @@ static void __xen_pcibk_release_devices(struct xen_pcibk_device *pdev)
 	struct pci_dev_entry *dev_entry, *t;
 
 	list_for_each_entry_safe(dev_entry, t, &dev_data->dev_list, list) {
+		struct pci_dev *dev = dev_entry->dev;
 		list_del(&dev_entry->list);
-		pcistub_put_pci_dev(dev_entry->dev);
+		device_lock(&dev->dev);
+		pcistub_put_pci_dev(dev);
+		device_unlock(&dev->dev);
 		kfree(dev_entry);
 	}
 
diff --git a/drivers/xen/xen-pciback/pci_stub.c b/drivers/xen/xen-pciback/pci_stub.c
index 017069a455d4..cc3cbb4435f8 100644
--- a/drivers/xen/xen-pciback/pci_stub.c
+++ b/drivers/xen/xen-pciback/pci_stub.c
@@ -105,7 +105,7 @@ static void pcistub_device_release(struct kref *kref)
 	 */
 	__pci_reset_function_locked(dev);
 	if (pci_load_and_free_saved_state(dev, &dev_data->pci_saved_state))
-		dev_dbg(&dev->dev, "Could not reload PCI state\n");
+		dev_info(&dev->dev, "Could not reload PCI state\n");
 	else
 		pci_restore_state(dev);
 
@@ -250,11 +250,15 @@ struct pci_dev *pcistub_get_pci_dev(struct xen_pcibk_device *pdev,
  *  - 'echo BDF > unbind' with a guest still using it. See pcistub_remove
  *
  *  As such we have to be careful.
+ *
+ *  To make this easier, the caller has to hold the device lock.
  */
 void pcistub_put_pci_dev(struct pci_dev *dev)
 {
 	struct pcistub_device *psdev, *found_psdev = NULL;
 	unsigned long flags;
+	struct xen_pcibk_dev_data *dev_data;
+	int ret;
 
 	spin_lock_irqsave(&pcistub_devices_lock, flags);
 
@@ -276,13 +280,20 @@ void pcistub_put_pci_dev(struct pci_dev *dev)
 	/* Cleanup our device
 	 * (so it's ready for the next domain)
 	 */
+	device_lock_assert(&dev->dev);
+	__pci_reset_function_locked(dev);
 
-	/* This is OK - we are running from workqueue context
-	 * and want to inhibit the user from fiddling with 'reset'
-	 */
-	pci_reset_function(dev);
-	pci_restore_state(dev);
-
+	dev_data = pci_get_drvdata(dev);
+	ret = pci_load_saved_state(dev, dev_data->pci_saved_state);
+	if (!ret) {
+		/*
+		 * The usual sequence is pci_save_state & pci_restore_state
+		 * but the guest might have messed the configuration space up.
+		 * Use the initial version (when device was bound to us).
+		 */
+		pci_restore_state(dev);
+	} else
+		dev_info(&dev->dev, "Could not reload PCI state\n");
 	/* This disables the device. */
 	xen_pcibk_reset_device(dev);
 
@@ -554,12 +565,14 @@ static void pcistub_remove(struct pci_dev *dev)
 	spin_unlock_irqrestore(&pcistub_devices_lock, flags);
 
 	if (found_psdev) {
-		dev_dbg(&dev->dev, "found device to remove - in use? %p\n",
-			found_psdev->pdev);
+		dev_dbg(&dev->dev, "found device to remove %s\n",
+			found_psdev->pdev ? "- in-use" : "");
 
 		if (found_psdev->pdev) {
-			pr_warn("****** removing device %s while still in-use! ******\n",
-			       pci_name(found_psdev->dev));
+			int domid = xen_find_device_domain_owner(dev);
+
+			pr_warn("****** removing device %s while still in-use by domain %d! ******\n",
+			       pci_name(found_psdev->dev), domid);
 			pr_warn("****** driver domain may still access this device's i/o resources!\n");
 			pr_warn("****** shutdown driver domain before binding device\n");
 			pr_warn("****** to other drivers or domains\n");
@@ -567,7 +580,8 @@ static void pcistub_remove(struct pci_dev *dev)
 			/* N.B. This ends up calling pcistub_put_pci_dev which ends up
 			 * doing the FLR. */
 			xen_pcibk_release_pci_dev(found_psdev->pdev,
-						found_psdev->dev);
+						found_psdev->dev,
+						false /* caller holds the lock. */);
 		}
 
 		spin_lock_irqsave(&pcistub_devices_lock, flags);
@@ -629,10 +643,12 @@ static pci_ers_result_t common_process(struct pcistub_device *psdev,
 {
 	pci_ers_result_t res = result;
 	struct xen_pcie_aer_op *aer_op;
+	struct xen_pcibk_device *pdev = psdev->pdev;
+	struct xen_pci_sharedinfo *sh_info = pdev->sh_info;
 	int ret;
 
 	/*with PV AER drivers*/
-	aer_op = &(psdev->pdev->sh_info->aer_op);
+	aer_op = &(sh_info->aer_op);
 	aer_op->cmd = aer_cmd ;
 	/*useful for error_detected callback*/
 	aer_op->err = state;
@@ -653,36 +669,36 @@ static pci_ers_result_t common_process(struct pcistub_device *psdev,
 	* this flag to judge whether we need to check pci-front give aer
 	* service ack signal
 	*/
-	set_bit(_PCIB_op_pending, (unsigned long *)&psdev->pdev->flags);
+	set_bit(_PCIB_op_pending, (unsigned long *)&pdev->flags);
 
 	/*It is possible that a pcifront conf_read_write ops request invokes
 	* the callback which cause the spurious execution of wake_up.
 	* Yet it is harmless and better than a spinlock here
 	*/
 	set_bit(_XEN_PCIB_active,
-		(unsigned long *)&psdev->pdev->sh_info->flags);
+		(unsigned long *)&sh_info->flags);
 	wmb();
-	notify_remote_via_irq(psdev->pdev->evtchn_irq);
+	notify_remote_via_irq(pdev->evtchn_irq);
 
 	ret = wait_event_timeout(xen_pcibk_aer_wait_queue,
 				 !(test_bit(_XEN_PCIB_active, (unsigned long *)
-				 &psdev->pdev->sh_info->flags)), 300*HZ);
+				 &sh_info->flags)), 300*HZ);
 
 	if (!ret) {
 		if (test_bit(_XEN_PCIB_active,
-			(unsigned long *)&psdev->pdev->sh_info->flags)) {
+			(unsigned long *)&sh_info->flags)) {
 			dev_err(&psdev->dev->dev,
 				"pcifront aer process not responding!\n");
 			clear_bit(_XEN_PCIB_active,
-			  (unsigned long *)&psdev->pdev->sh_info->flags);
+			  (unsigned long *)&sh_info->flags);
 			aer_op->err = PCI_ERS_RESULT_NONE;
 			return res;
 		}
 	}
-	clear_bit(_PCIB_op_pending, (unsigned long *)&psdev->pdev->flags);
+	clear_bit(_PCIB_op_pending, (unsigned long *)&pdev->flags);
 
 	if (test_bit(_XEN_PCIF_active,
-		(unsigned long *)&psdev->pdev->sh_info->flags)) {
+		(unsigned long *)&sh_info->flags)) {
 		dev_dbg(&psdev->dev->dev,
 			"schedule pci_conf service in " DRV_NAME "\n");
 		xen_pcibk_test_and_schedule_op(psdev->pdev);
@@ -1502,6 +1518,53 @@ parse_error:
 fs_initcall(pcistub_init);
 #endif
 
+#ifdef CONFIG_PCI_IOV
+static struct pcistub_device *find_vfs(const struct pci_dev *pdev)
+{
+	struct pcistub_device *psdev = NULL;
+	unsigned long flags;
+	bool found = false;
+
+	spin_lock_irqsave(&pcistub_devices_lock, flags);
+	list_for_each_entry(psdev, &pcistub_devices, dev_list) {
+		if (!psdev->pdev && psdev->dev != pdev
+		    && pci_physfn(psdev->dev) == pdev) {
+			found = true;
+			break;
+		}
+	}
+	spin_unlock_irqrestore(&pcistub_devices_lock, flags);
+	if (found)
+		return psdev;
+	return NULL;
+}
+
+static int pci_stub_notifier(struct notifier_block *nb,
+			     unsigned long action, void *data)
+{
+	struct device *dev = data;
+	const struct pci_dev *pdev = to_pci_dev(dev);
+
+	if (action != BUS_NOTIFY_UNBIND_DRIVER)
+		return NOTIFY_DONE;
+
+	if (!pdev->is_physfn)
+		return NOTIFY_DONE;
+
+	for (;;) {
+		struct pcistub_device *psdev = find_vfs(pdev);
+		if (!psdev)
+			break;
+		device_release_driver(&psdev->dev->dev);
+	}
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block pci_stub_nb = {
+	.notifier_call = pci_stub_notifier,
+};
+#endif
+
 static int __init xen_pcibk_init(void)
 {
 	int err;
@@ -1523,12 +1586,19 @@ static int __init xen_pcibk_init(void)
 	err = xen_pcibk_xenbus_register();
 	if (err)
 		pcistub_exit();
+#ifdef CONFIG_PCI_IOV
+	else
+		bus_register_notifier(&pci_bus_type, &pci_stub_nb);
+#endif
 
 	return err;
 }
 
 static void __exit xen_pcibk_cleanup(void)
 {
+#ifdef CONFIG_PCI_IOV
+	bus_unregister_notifier(&pci_bus_type, &pci_stub_nb);
+#endif
 	xen_pcibk_xenbus_unregister();
 	pcistub_exit();
 }
diff --git a/drivers/xen/xen-pciback/pciback.h b/drivers/xen/xen-pciback/pciback.h
index f72af87640e0..58e38d586f52 100644
--- a/drivers/xen/xen-pciback/pciback.h
+++ b/drivers/xen/xen-pciback/pciback.h
@@ -99,7 +99,8 @@ struct xen_pcibk_backend {
 		    unsigned int *domain, unsigned int *bus,
 		    unsigned int *devfn);
 	int (*publish)(struct xen_pcibk_device *pdev, publish_pci_root_cb cb);
-	void (*release)(struct xen_pcibk_device *pdev, struct pci_dev *dev);
+	void (*release)(struct xen_pcibk_device *pdev, struct pci_dev *dev,
+                        bool lock);
 	int (*add)(struct xen_pcibk_device *pdev, struct pci_dev *dev,
 		   int devid, publish_pci_dev_cb publish_cb);
 	struct pci_dev *(*get)(struct xen_pcibk_device *pdev,
@@ -122,10 +123,10 @@ static inline int xen_pcibk_add_pci_dev(struct xen_pcibk_device *pdev,
 }
 
 static inline void xen_pcibk_release_pci_dev(struct xen_pcibk_device *pdev,
-					     struct pci_dev *dev)
+					     struct pci_dev *dev, bool lock)
 {
 	if (xen_pcibk_backend && xen_pcibk_backend->release)
-		return xen_pcibk_backend->release(pdev, dev);
+		return xen_pcibk_backend->release(pdev, dev, lock);
 }
 
 static inline struct pci_dev *
diff --git a/drivers/xen/xen-pciback/vpci.c b/drivers/xen/xen-pciback/vpci.c
index 51afff96c515..c99f8bb1c56c 100644
--- a/drivers/xen/xen-pciback/vpci.c
+++ b/drivers/xen/xen-pciback/vpci.c
@@ -145,7 +145,7 @@ out:
 }
 
 static void __xen_pcibk_release_pci_dev(struct xen_pcibk_device *pdev,
-					struct pci_dev *dev)
+					struct pci_dev *dev, bool lock)
 {
 	int slot;
 	struct vpci_dev_data *vpci_dev = pdev->pci_dev_data;
@@ -169,8 +169,13 @@ static void __xen_pcibk_release_pci_dev(struct xen_pcibk_device *pdev,
 out:
 	mutex_unlock(&vpci_dev->lock);
 
-	if (found_dev)
+	if (found_dev) {
+		if (lock)
+			device_lock(&found_dev->dev);
 		pcistub_put_pci_dev(found_dev);
+		if (lock)
+			device_unlock(&found_dev->dev);
+	}
 }
 
 static int __xen_pcibk_init_devices(struct xen_pcibk_device *pdev)
@@ -208,8 +213,11 @@ static void __xen_pcibk_release_devices(struct xen_pcibk_device *pdev)
 		struct pci_dev_entry *e, *tmp;
 		list_for_each_entry_safe(e, tmp, &vpci_dev->dev_list[slot],
 					 list) {
+			struct pci_dev *dev = e->dev;
 			list_del(&e->list);
-			pcistub_put_pci_dev(e->dev);
+			device_lock(&dev->dev);
+			pcistub_put_pci_dev(dev);
+			device_unlock(&dev->dev);
 			kfree(e);
 		}
 	}
diff --git a/drivers/xen/xen-pciback/xenbus.c b/drivers/xen/xen-pciback/xenbus.c
index ad8d30c088fe..fe17c80ff4b7 100644
--- a/drivers/xen/xen-pciback/xenbus.c
+++ b/drivers/xen/xen-pciback/xenbus.c
@@ -247,7 +247,7 @@ static int xen_pcibk_export_device(struct xen_pcibk_device *pdev,
 	if (err)
 		goto out;
 
-	dev_dbg(&dev->dev, "registering for %d\n", pdev->xdev->otherend_id);
+	dev_info(&dev->dev, "registering for %d\n", pdev->xdev->otherend_id);
 	if (xen_register_device_domain_owner(dev,
 					     pdev->xdev->otherend_id) != 0) {
 		dev_err(&dev->dev, "Stealing ownership from dom%d.\n",
@@ -291,7 +291,7 @@ static int xen_pcibk_remove_device(struct xen_pcibk_device *pdev,
 
 	/* N.B. This ends up calling pcistub_put_pci_dev which ends up
 	 * doing the FLR. */
-	xen_pcibk_release_pci_dev(pdev, dev);
+	xen_pcibk_release_pci_dev(pdev, dev, true /* use the lock. */);
 
 out:
 	return err;