Merge tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost

Pull virtio/vhost fixes from Michael Tsirkin:

 - Fixes in the iommu and balloon devices.

 - Disable the meta-data optimization for now - I hope we can get it
   fixed shortly, but there's no point in making users suffer crashes
   while we are working on that.

* tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost:
  vhost: disable metadata prefetch optimization
  iommu/virtio: Update to most recent specification
  balloon: fix up comments
  mm/balloon_compaction: avoid duplicate page removal

drivers/iommu/virtio-iommu.c

@@ -2,7 +2,7 @@
 /*
  * Virtio driver for the paravirtualized IOMMU
  *
- * Copyright (C) 2018 Arm Limited
+ * Copyright (C) 2019 Arm Limited
  */
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
@@ -47,7 +47,10 @@ struct viommu_dev {
 	/* Device configuration */
 	struct iommu_domain_geometry	geometry;
 	u64				pgsize_bitmap;
-	u8				domain_bits;
+	u32				first_domain;
+	u32				last_domain;
+	/* Supported MAP flags */
+	u32				map_flags;
 	u32				probe_size;
 };
 
@@ -62,6 +65,7 @@ struct viommu_domain {
 	struct viommu_dev		*viommu;
 	struct mutex			mutex; /* protects viommu pointer */
 	unsigned int			id;
+	u32				map_flags;
 
 	spinlock_t			mappings_lock;
 	struct rb_root_cached		mappings;
@@ -113,6 +117,8 @@ static int viommu_get_req_errno(void *buf, size_t len)
 		return -ENOENT;
 	case VIRTIO_IOMMU_S_FAULT:
 		return -EFAULT;
+	case VIRTIO_IOMMU_S_NOMEM:
+		return -ENOMEM;
 	case VIRTIO_IOMMU_S_IOERR:
 	case VIRTIO_IOMMU_S_DEVERR:
 	default:
@@ -607,15 +613,15 @@ static int viommu_domain_finalise(struct viommu_dev *viommu,
 {
 	int ret;
 	struct viommu_domain *vdomain = to_viommu_domain(domain);
-	unsigned int max_domain = viommu->domain_bits > 31 ? ~0 :
-				  (1U << viommu->domain_bits) - 1;
 
 	vdomain->viommu		= viommu;
+	vdomain->map_flags	= viommu->map_flags;
 
 	domain->pgsize_bitmap	= viommu->pgsize_bitmap;
 	domain->geometry	= viommu->geometry;
 
-	ret = ida_alloc_max(&viommu->domain_ids, max_domain, GFP_KERNEL);
+	ret = ida_alloc_range(&viommu->domain_ids, viommu->first_domain,
+			      viommu->last_domain, GFP_KERNEL);
 	if (ret >= 0)
 		vdomain->id = (unsigned int)ret;
 
@@ -710,7 +716,7 @@ static int viommu_map(struct iommu_domain *domain, unsigned long iova,
 		      phys_addr_t paddr, size_t size, int prot)
 {
 	int ret;
-	int flags;
+	u32 flags;
 	struct virtio_iommu_req_map map;
 	struct viommu_domain *vdomain = to_viommu_domain(domain);
 
@@ -718,6 +724,9 @@ static int viommu_map(struct iommu_domain *domain, unsigned long iova,
 		(prot & IOMMU_WRITE ? VIRTIO_IOMMU_MAP_F_WRITE : 0) |
 		(prot & IOMMU_MMIO ? VIRTIO_IOMMU_MAP_F_MMIO : 0);
 
+	if (flags & ~vdomain->map_flags)
+		return -EINVAL;
+
 	ret = viommu_add_mapping(vdomain, iova, paddr, size, flags);
 	if (ret)
 		return ret;
@@ -1027,7 +1036,8 @@ static int viommu_probe(struct virtio_device *vdev)
 		goto err_free_vqs;
 	}
 
-	viommu->domain_bits = 32;
+	viommu->map_flags = VIRTIO_IOMMU_MAP_F_READ | VIRTIO_IOMMU_MAP_F_WRITE;
+	viommu->last_domain = ~0U;
 
 	/* Optional features */
 	virtio_cread_feature(vdev, VIRTIO_IOMMU_F_INPUT_RANGE,
@@ -1038,9 +1048,13 @@ static int viommu_probe(struct virtio_device *vdev)
 			     struct virtio_iommu_config, input_range.end,
 			     &input_end);
 
-	virtio_cread_feature(vdev, VIRTIO_IOMMU_F_DOMAIN_BITS,
-			     struct virtio_iommu_config, domain_bits,
-			     &viommu->domain_bits);
+	virtio_cread_feature(vdev, VIRTIO_IOMMU_F_DOMAIN_RANGE,
+			     struct virtio_iommu_config, domain_range.start,
+			     &viommu->first_domain);
+
+	virtio_cread_feature(vdev, VIRTIO_IOMMU_F_DOMAIN_RANGE,
+			     struct virtio_iommu_config, domain_range.end,
+			     &viommu->last_domain);
 
 	virtio_cread_feature(vdev, VIRTIO_IOMMU_F_PROBE,
 			     struct virtio_iommu_config, probe_size,
@@ -1052,6 +1066,9 @@ static int viommu_probe(struct virtio_device *vdev)
 		.force_aperture	= true,
 	};
 
+	if (virtio_has_feature(vdev, VIRTIO_IOMMU_F_MMIO))
+		viommu->map_flags |= VIRTIO_IOMMU_MAP_F_MMIO;
+
 	viommu_ops.pgsize_bitmap = viommu->pgsize_bitmap;
 
 	virtio_device_ready(vdev);
@@ -1130,9 +1147,10 @@ static void viommu_config_changed(struct virtio_device *vdev)
 
 static unsigned int features[] = {
 	VIRTIO_IOMMU_F_MAP_UNMAP,
-	VIRTIO_IOMMU_F_DOMAIN_BITS,
 	VIRTIO_IOMMU_F_INPUT_RANGE,
+	VIRTIO_IOMMU_F_DOMAIN_RANGE,
 	VIRTIO_IOMMU_F_PROBE,
+	VIRTIO_IOMMU_F_MMIO,
 };
 
 static struct virtio_device_id id_table[] = {

drivers/vhost/vhost.h

@@ -96,7 +96,7 @@ struct vhost_uaddr {
 };
 
 #if defined(CONFIG_MMU_NOTIFIER) && ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE == 0
-#define VHOST_ARCH_CAN_ACCEL_UACCESS 1
+#define VHOST_ARCH_CAN_ACCEL_UACCESS 0
 #else
 #define VHOST_ARCH_CAN_ACCEL_UACCESS 0
 #endif

include/uapi/linux/virtio_iommu.h

 /* SPDX-License-Identifier: BSD-3-Clause */
 /*
- * Virtio-iommu definition v0.9
+ * Virtio-iommu definition v0.12
  *
- * Copyright (C) 2018 Arm Ltd.
+ * Copyright (C) 2019 Arm Ltd.
  */
 #ifndef _UAPI_LINUX_VIRTIO_IOMMU_H
 #define _UAPI_LINUX_VIRTIO_IOMMU_H
@@ -11,26 +11,31 @@
 
 /* Feature bits */
 #define VIRTIO_IOMMU_F_INPUT_RANGE		0
-#define VIRTIO_IOMMU_F_DOMAIN_BITS		1
+#define VIRTIO_IOMMU_F_DOMAIN_RANGE		1
 #define VIRTIO_IOMMU_F_MAP_UNMAP		2
 #define VIRTIO_IOMMU_F_BYPASS			3
 #define VIRTIO_IOMMU_F_PROBE			4
+#define VIRTIO_IOMMU_F_MMIO			5
 
-struct virtio_iommu_range {
-	__u64					start;
-	__u64					end;
+struct virtio_iommu_range_64 {
+	__le64					start;
+	__le64					end;
+};
+
+struct virtio_iommu_range_32 {
+	__le32					start;
+	__le32					end;
 };
 
 struct virtio_iommu_config {
 	/* Supported page sizes */
-	__u64					page_size_mask;
+	__le64					page_size_mask;
 	/* Supported IOVA range */
-	struct virtio_iommu_range		input_range;
+	struct virtio_iommu_range_64		input_range;
 	/* Max domain ID size */
-	__u8					domain_bits;
-	__u8					padding[3];
+	struct virtio_iommu_range_32		domain_range;
 	/* Probe buffer size */
-	__u32					probe_size;
+	__le32					probe_size;
 };
 
 /* Request types */
@@ -49,6 +54,7 @@ struct virtio_iommu_config {
 #define VIRTIO_IOMMU_S_RANGE			0x05
 #define VIRTIO_IOMMU_S_NOENT			0x06
 #define VIRTIO_IOMMU_S_FAULT			0x07
+#define VIRTIO_IOMMU_S_NOMEM			0x08
 
 struct virtio_iommu_req_head {
 	__u8					type;
@@ -78,12 +84,10 @@ struct virtio_iommu_req_detach {
 
 #define VIRTIO_IOMMU_MAP_F_READ			(1 << 0)
 #define VIRTIO_IOMMU_MAP_F_WRITE		(1 << 1)
-#define VIRTIO_IOMMU_MAP_F_EXEC			(1 << 2)
-#define VIRTIO_IOMMU_MAP_F_MMIO			(1 << 3)
+#define VIRTIO_IOMMU_MAP_F_MMIO			(1 << 2)
 
 #define VIRTIO_IOMMU_MAP_F_MASK			(VIRTIO_IOMMU_MAP_F_READ |	\
 						 VIRTIO_IOMMU_MAP_F_WRITE |	\
-						 VIRTIO_IOMMU_MAP_F_EXEC |	\
 						 VIRTIO_IOMMU_MAP_F_MMIO)
 
 struct virtio_iommu_req_map {

mm/balloon_compaction.c

@@ -21,7 +21,6 @@ static void balloon_page_enqueue_one(struct balloon_dev_info *b_dev_info,
 	 * memory corruption is possible and we should stop execution.
 	 */
 	BUG_ON(!trylock_page(page));
-	list_del(&page->lru);
 	balloon_page_insert(b_dev_info, page);
 	unlock_page(page);
 	__count_vm_event(BALLOON_INFLATE);
@@ -33,8 +32,8 @@ static void balloon_page_enqueue_one(struct balloon_dev_info *b_dev_info,
  * @b_dev_info: balloon device descriptor where we will insert a new page to
  * @pages: pages to enqueue - allocated using balloon_page_alloc.
  *
- * Driver must call it to properly enqueue a balloon pages before definitively
- * removing it from the guest system.
+ * Driver must call this function to properly enqueue balloon pages before
+ * definitively removing them from the guest system.
  *
  * Return: number of pages that were enqueued.
  */
@@ -47,6 +46,7 @@ size_t balloon_page_list_enqueue(struct balloon_dev_info *b_dev_info,
 
 	spin_lock_irqsave(&b_dev_info->pages_lock, flags);
 	list_for_each_entry_safe(page, tmp, pages, lru) {
+		list_del(&page->lru);
 		balloon_page_enqueue_one(b_dev_info, page);
 		n_pages++;
 	}
@@ -63,12 +63,13 @@ EXPORT_SYMBOL_GPL(balloon_page_list_enqueue);
  * @n_req_pages: number of requested pages.
  *
  * Driver must call this function to properly de-allocate a previous enlisted
- * balloon pages before definetively releasing it back to the guest system.
+ * balloon pages before definitively releasing it back to the guest system.
  * This function tries to remove @n_req_pages from the ballooned pages and
  * return them to the caller in the @pages list.
  *
- * Note that this function may fail to dequeue some pages temporarily empty due
- * to compaction isolated pages.
+ * Note that this function may fail to dequeue some pages even if the balloon
+ * isn't empty - since the page list can be temporarily empty due to compaction
+ * of isolated pages.
  *
  * Return: number of pages that were added to the @pages list.
  */
@@ -114,10 +115,11 @@ EXPORT_SYMBOL_GPL(balloon_page_list_dequeue);
  * balloon_page_alloc - allocates a new page for insertion into the balloon
  *			page list.
  *
- * Driver must call it to properly allocate a new enlisted balloon page.
- * Driver must call balloon_page_enqueue before definitively removing it from
- * the guest system.  This function returns the page address for the recently
- * allocated page or NULL in the case we fail to allocate a new page this turn.
+ * Driver must call this function to properly allocate a new balloon page.
+ * Driver must call balloon_page_enqueue before definitively removing the page
+ * from the guest system.
+ *
+ * Return: struct page for the allocated page or NULL on allocation failure.
  */
 struct page *balloon_page_alloc(void)
 {
@@ -128,15 +130,17 @@ struct page *balloon_page_alloc(void)
 EXPORT_SYMBOL_GPL(balloon_page_alloc);
 
 /*
- * balloon_page_enqueue - allocates a new page and inserts it into the balloon
- *			  page list.
- * @b_dev_info: balloon device descriptor where we will insert a new page to
+ * balloon_page_enqueue - inserts a new page into the balloon page list.
+ *
+ * @b_dev_info: balloon device descriptor where we will insert a new page
  * @page: new page to enqueue - allocated using balloon_page_alloc.
  *
- * Driver must call it to properly enqueue a new allocated balloon page
- * before definitively removing it from the guest system.
- * This function returns the page address for the recently enqueued page or
- * NULL in the case we fail to allocate a new page this turn.
+ * Drivers must call this function to properly enqueue a new allocated balloon
+ * page before definitively removing the page from the guest system.
+ *
+ * Drivers must not call balloon_page_enqueue on pages that have been pushed to
+ * a list with balloon_page_push before removing them with balloon_page_pop. To
+ * enqueue a list of pages, use balloon_page_list_enqueue instead.
  */
 void balloon_page_enqueue(struct balloon_dev_info *b_dev_info,
 			  struct page *page)
@@ -151,14 +155,23 @@ EXPORT_SYMBOL_GPL(balloon_page_enqueue);
 
 /*
  * balloon_page_dequeue - removes a page from balloon's page list and returns
- *			  the its address to allow the driver release the page.
+ *			  its address to allow the driver to release the page.
  * @b_dev_info: balloon device decriptor where we will grab a page from.
  *
- * Driver must call it to properly de-allocate a previous enlisted balloon page
- * before definetively releasing it back to the guest system.
- * This function returns the page address for the recently dequeued page or
- * NULL in the case we find balloon's page list temporarily empty due to
- * compaction isolated pages.
+ * Driver must call this function to properly dequeue a previously enqueued page
+ * before definitively releasing it back to the guest system.
+ *
+ * Caller must perform its own accounting to ensure that this
+ * function is called only if some pages are actually enqueued.
+ *
+ * Note that this function may fail to dequeue some pages even if there are
+ * some enqueued pages - since the page list can be temporarily empty due to
+ * the compaction of isolated pages.
+ *
+ * TODO: remove the caller accounting requirements, and allow caller to wait
+ * until all pages can be dequeued.
+ *
+ * Return: struct page for the dequeued page, or NULL if no page was dequeued.
  */
 struct page *balloon_page_dequeue(struct balloon_dev_info *b_dev_info)
 {
@@ -171,9 +184,9 @@ struct page *balloon_page_dequeue(struct balloon_dev_info *b_dev_info)
 	if (n_pages != 1) {
 		/*
 		 * If we are unable to dequeue a balloon page because the page
-		 * list is empty and there is no isolated pages, then something
+		 * list is empty and there are no isolated pages, then something
 		 * went out of track and some balloon pages are lost.
-		 * BUG() here, otherwise the balloon driver may get stuck into
+		 * BUG() here, otherwise the balloon driver may get stuck in
 		 * an infinite loop while attempting to release all its pages.
 		 */
 		spin_lock_irqsave(&b_dev_info->pages_lock, flags);
@@ -224,8 +237,8 @@ int balloon_page_migrate(struct address_space *mapping,
 
 	/*
 	 * We can not easily support the no copy case here so ignore it as it
-	 * is unlikely to be use with ballon pages. See include/linux/hmm.h for
-	 * user of the MIGRATE_SYNC_NO_COPY mode.
+	 * is unlikely to be used with balloon pages. See include/linux/hmm.h
+	 * for a user of the MIGRATE_SYNC_NO_COPY mode.
 	 */
 	if (mode == MIGRATE_SYNC_NO_COPY)
 		return -EINVAL;