Merge tag 'for-linus-6.1-rc1-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip

Pull xen updates from Juergen Gross:

 - Some minor typo fixes

 - A fix of the Xen pcifront driver for supporting the device model to
   run in a Linux stub domain

 - A cleanup of the pcifront driver

 - A series to enable grant-based virtio with Xen on x86

 - A cleanup of Xen PV guests to distinguish between safe and faulting
   MSR accesses

 - Two fixes of the Xen gntdev driver

 - Two fixes of the new xen grant DMA driver

* tag 'for-linus-6.1-rc1-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip:
  xen: Kconfig: Fix spelling mistake "Maxmium" -> "Maximum"
  xen/pv: support selecting safe/unsafe msr accesses
  xen/pv: refactor msr access functions to support safe and unsafe accesses
  xen/pv: fix vendor checks for pmu emulation
  xen/pv: add fault recovery control to pmu msr accesses
  xen/virtio: enable grant based virtio on x86
  xen/virtio: use dom0 as default backend for CONFIG_XEN_VIRTIO_FORCE_GRANT
  xen/virtio: restructure xen grant dma setup
  xen/pcifront: move xenstore config scanning into sub-function
  xen/gntdev: Accommodate VMA splitting
  xen/gntdev: Prevent leaking grants
  xen/virtio: Fix potential deadlock when accessing xen_grant_dma_devices
  xen/virtio: Fix n_pages calculation in xen_grant_dma_map(unmap)_page()
  xen/xenbus: Fix spelling mistake "hardward" -> "hardware"
  xen-pcifront: Handle missed Connected state

5 files changed, 125 insertions, 74 deletions

diff --git a/drivers/xen/Kconfig b/drivers/xen/Kconfig
index a65bd92121a5..d5d7c402b651 100644
--- a/drivers/xen/Kconfig
+++ b/drivers/xen/Kconfig
@@ -56,7 +56,7 @@ config XEN_MEMORY_HOTPLUG_LIMIT
 	depends on XEN_HAVE_PVMMU
 	depends on MEMORY_HOTPLUG
 	help
-	  Maxmium amount of memory (in GiB) that a PV guest can be
+	  Maximum amount of memory (in GiB) that a PV guest can be
 	  expanded to when using memory hotplug.
 
 	  A PV guest can have more memory than this limit if is
diff --git a/drivers/xen/gntdev-common.h b/drivers/xen/gntdev-common.h
index 40ef379c28ab..9c286b2a1900 100644
--- a/drivers/xen/gntdev-common.h
+++ b/drivers/xen/gntdev-common.h
@@ -44,9 +44,10 @@ struct gntdev_unmap_notify {
 };
 
 struct gntdev_grant_map {
+	atomic_t in_use;
 	struct mmu_interval_notifier notifier;
+	bool notifier_init;
 	struct list_head next;
-	struct vm_area_struct *vma;
 	int index;
 	int count;
 	int flags;
diff --git a/drivers/xen/gntdev.c b/drivers/xen/gntdev.c
index 84b143eef395..4d9a3050de6a 100644
--- a/drivers/xen/gntdev.c
+++ b/drivers/xen/gntdev.c
@@ -286,6 +286,9 @@ void gntdev_put_map(struct gntdev_priv *priv, struct gntdev_grant_map *map)
 		 */
 	}
 
+	if (use_ptemod && map->notifier_init)
+		mmu_interval_notifier_remove(&map->notifier);
+
 	if (map->notify.flags & UNMAP_NOTIFY_SEND_EVENT) {
 		notify_remote_via_evtchn(map->notify.event);
 		evtchn_put(map->notify.event);
@@ -298,7 +301,7 @@ void gntdev_put_map(struct gntdev_priv *priv, struct gntdev_grant_map *map)
 static int find_grant_ptes(pte_t *pte, unsigned long addr, void *data)
 {
 	struct gntdev_grant_map *map = data;
-	unsigned int pgnr = (addr - map->vma->vm_start) >> PAGE_SHIFT;
+	unsigned int pgnr = (addr - map->pages_vm_start) >> PAGE_SHIFT;
 	int flags = map->flags | GNTMAP_application_map | GNTMAP_contains_pte |
 		    (1 << _GNTMAP_guest_avail0);
 	u64 pte_maddr;
@@ -367,8 +370,7 @@ int gntdev_map_grant_pages(struct gntdev_grant_map *map)
 	for (i = 0; i < map->count; i++) {
 		if (map->map_ops[i].status == GNTST_okay) {
 			map->unmap_ops[i].handle = map->map_ops[i].handle;
-			if (!use_ptemod)
-				alloced++;
+			alloced++;
 		} else if (!err)
 			err = -EINVAL;
 
@@ -377,8 +379,7 @@ int gntdev_map_grant_pages(struct gntdev_grant_map *map)
 
 		if (use_ptemod) {
 			if (map->kmap_ops[i].status == GNTST_okay) {
-				if (map->map_ops[i].status == GNTST_okay)
-					alloced++;
+				alloced++;
 				map->kunmap_ops[i].handle = map->kmap_ops[i].handle;
 			} else if (!err)
 				err = -EINVAL;
@@ -394,8 +395,14 @@ static void __unmap_grant_pages_done(int result,
 	unsigned int i;
 	struct gntdev_grant_map *map = data->data;
 	unsigned int offset = data->unmap_ops - map->unmap_ops;
+	int successful_unmaps = 0;
+	int live_grants;
 
 	for (i = 0; i < data->count; i++) {
+		if (map->unmap_ops[offset + i].status == GNTST_okay &&
+		    map->unmap_ops[offset + i].handle != INVALID_GRANT_HANDLE)
+			successful_unmaps++;
+
 		WARN_ON(map->unmap_ops[offset + i].status != GNTST_okay &&
 			map->unmap_ops[offset + i].handle != INVALID_GRANT_HANDLE);
 		pr_debug("unmap handle=%d st=%d\n",
@@ -403,6 +410,10 @@ static void __unmap_grant_pages_done(int result,
 			map->unmap_ops[offset+i].status);
 		map->unmap_ops[offset+i].handle = INVALID_GRANT_HANDLE;
 		if (use_ptemod) {
+			if (map->kunmap_ops[offset + i].status == GNTST_okay &&
+			    map->kunmap_ops[offset + i].handle != INVALID_GRANT_HANDLE)
+				successful_unmaps++;
+
 			WARN_ON(map->kunmap_ops[offset + i].status != GNTST_okay &&
 				map->kunmap_ops[offset + i].handle != INVALID_GRANT_HANDLE);
 			pr_debug("kunmap handle=%u st=%d\n",
@@ -411,11 +422,15 @@ static void __unmap_grant_pages_done(int result,
 			map->kunmap_ops[offset+i].handle = INVALID_GRANT_HANDLE;
 		}
 	}
+
 	/*
 	 * Decrease the live-grant counter.  This must happen after the loop to
 	 * prevent premature reuse of the grants by gnttab_mmap().
 	 */
-	atomic_sub(data->count, &map->live_grants);
+	live_grants = atomic_sub_return(successful_unmaps, &map->live_grants);
+	if (WARN_ON(live_grants < 0))
+		pr_err("%s: live_grants became negative (%d) after unmapping %d pages!\n",
+		       __func__, live_grants, successful_unmaps);
 
 	/* Release reference taken by __unmap_grant_pages */
 	gntdev_put_map(NULL, map);
@@ -496,11 +511,7 @@ static void gntdev_vma_close(struct vm_area_struct *vma)
 	struct gntdev_priv *priv = file->private_data;
 
 	pr_debug("gntdev_vma_close %p\n", vma);
-	if (use_ptemod) {
-		WARN_ON(map->vma != vma);
-		mmu_interval_notifier_remove(&map->notifier);
-		map->vma = NULL;
-	}
+
 	vma->vm_private_data = NULL;
 	gntdev_put_map(priv, map);
 }
@@ -528,29 +539,30 @@ static bool gntdev_invalidate(struct mmu_interval_notifier *mn,
 	struct gntdev_grant_map *map =
 		container_of(mn, struct gntdev_grant_map, notifier);
 	unsigned long mstart, mend;
+	unsigned long map_start, map_end;
 
 	if (!mmu_notifier_range_blockable(range))
 		return false;
 
+	map_start = map->pages_vm_start;
+	map_end = map->pages_vm_start + (map->count << PAGE_SHIFT);
+
 	/*
 	 * If the VMA is split or otherwise changed the notifier is not
 	 * updated, but we don't want to process VA's outside the modified
 	 * VMA. FIXME: It would be much more understandable to just prevent
 	 * modifying the VMA in the first place.
 	 */
-	if (map->vma->vm_start >= range->end ||
-	    map->vma->vm_end <= range->start)
+	if (map_start >= range->end || map_end <= range->start)
 		return true;
 
-	mstart = max(range->start, map->vma->vm_start);
-	mend = min(range->end, map->vma->vm_end);
+	mstart = max(range->start, map_start);
+	mend = min(range->end, map_end);
 	pr_debug("map %d+%d (%lx %lx), range %lx %lx, mrange %lx %lx\n",
-			map->index, map->count,
-			map->vma->vm_start, map->vma->vm_end,
-			range->start, range->end, mstart, mend);
-	unmap_grant_pages(map,
-				(mstart - map->vma->vm_start) >> PAGE_SHIFT,
-				(mend - mstart) >> PAGE_SHIFT);
+		 map->index, map->count, map_start, map_end,
+		 range->start, range->end, mstart, mend);
+	unmap_grant_pages(map, (mstart - map_start) >> PAGE_SHIFT,
+			  (mend - mstart) >> PAGE_SHIFT);
 
 	return true;
 }
@@ -1030,18 +1042,15 @@ static int gntdev_mmap(struct file *flip, struct vm_area_struct *vma)
 		return -EINVAL;
 
 	pr_debug("map %d+%d at %lx (pgoff %lx)\n",
-			index, count, vma->vm_start, vma->vm_pgoff);
+		 index, count, vma->vm_start, vma->vm_pgoff);
 
 	mutex_lock(&priv->lock);
 	map = gntdev_find_map_index(priv, index, count);
 	if (!map)
 		goto unlock_out;
-	if (use_ptemod && map->vma)
+	if (!atomic_add_unless(&map->in_use, 1, 1))
 		goto unlock_out;
-	if (atomic_read(&map->live_grants)) {
-		err = -EAGAIN;
-		goto unlock_out;
-	}
+
 	refcount_inc(&map->users);
 
 	vma->vm_ops = &gntdev_vmops;
@@ -1062,15 +1071,16 @@ static int gntdev_mmap(struct file *flip, struct vm_area_struct *vma)
 			map->flags |= GNTMAP_readonly;
 	}
 
+	map->pages_vm_start = vma->vm_start;
+
 	if (use_ptemod) {
-		map->vma = vma;
 		err = mmu_interval_notifier_insert_locked(
 			&map->notifier, vma->vm_mm, vma->vm_start,
 			vma->vm_end - vma->vm_start, &gntdev_mmu_ops);
-		if (err) {
-			map->vma = NULL;
+		if (err)
 			goto out_unlock_put;
-		}
+
+		map->notifier_init = true;
 	}
 	mutex_unlock(&priv->lock);
 
@@ -1087,7 +1097,6 @@ static int gntdev_mmap(struct file *flip, struct vm_area_struct *vma)
 		 */
 		mmu_interval_read_begin(&map->notifier);
 
-		map->pages_vm_start = vma->vm_start;
 		err = apply_to_page_range(vma->vm_mm, vma->vm_start,
 					  vma->vm_end - vma->vm_start,
 					  find_grant_ptes, map);
@@ -1116,13 +1125,8 @@ unlock_out:
 out_unlock_put:
 	mutex_unlock(&priv->lock);
 out_put_map:
-	if (use_ptemod) {
+	if (use_ptemod)
 		unmap_grant_pages(map, 0, map->count);
-		if (map->vma) {
-			mmu_interval_notifier_remove(&map->notifier);
-			map->vma = NULL;
-		}
-	}
 	gntdev_put_map(priv, map);
 	return err;
 }
diff --git a/drivers/xen/grant-dma-ops.c b/drivers/xen/grant-dma-ops.c
index 8973fc1e9ccc..860f37c93af4 100644
--- a/drivers/xen/grant-dma-ops.c
+++ b/drivers/xen/grant-dma-ops.c
@@ -25,7 +25,7 @@ struct xen_grant_dma_data {
 	bool broken;
 };
 
-static DEFINE_XARRAY(xen_grant_dma_devices);
+static DEFINE_XARRAY_FLAGS(xen_grant_dma_devices, XA_FLAGS_LOCK_IRQ);
 
 #define XEN_GRANT_DMA_ADDR_OFF	(1ULL << 63)
 
@@ -42,14 +42,29 @@ static inline grant_ref_t dma_to_grant(dma_addr_t dma)
 static struct xen_grant_dma_data *find_xen_grant_dma_data(struct device *dev)
 {
 	struct xen_grant_dma_data *data;
+	unsigned long flags;
 
-	xa_lock(&xen_grant_dma_devices);
+	xa_lock_irqsave(&xen_grant_dma_devices, flags);
 	data = xa_load(&xen_grant_dma_devices, (unsigned long)dev);
-	xa_unlock(&xen_grant_dma_devices);
+	xa_unlock_irqrestore(&xen_grant_dma_devices, flags);
 
 	return data;
 }
 
+static int store_xen_grant_dma_data(struct device *dev,
+				    struct xen_grant_dma_data *data)
+{
+	unsigned long flags;
+	int ret;
+
+	xa_lock_irqsave(&xen_grant_dma_devices, flags);
+	ret = xa_err(__xa_store(&xen_grant_dma_devices, (unsigned long)dev, data,
+			GFP_ATOMIC));
+	xa_unlock_irqrestore(&xen_grant_dma_devices, flags);
+
+	return ret;
+}
+
 /*
  * DMA ops for Xen frontends (e.g. virtio).
  *
@@ -153,7 +168,7 @@ static dma_addr_t xen_grant_dma_map_page(struct device *dev, struct page *page,
 					 unsigned long attrs)
 {
 	struct xen_grant_dma_data *data;
-	unsigned int i, n_pages = PFN_UP(size);
+	unsigned int i, n_pages = PFN_UP(offset + size);
 	grant_ref_t grant;
 	dma_addr_t dma_handle;
 
@@ -185,7 +200,8 @@ static void xen_grant_dma_unmap_page(struct device *dev, dma_addr_t dma_handle,
 				     unsigned long attrs)
 {
 	struct xen_grant_dma_data *data;
-	unsigned int i, n_pages = PFN_UP(size);
+	unsigned long offset = dma_handle & (PAGE_SIZE - 1);
+	unsigned int i, n_pages = PFN_UP(offset + size);
 	grant_ref_t grant;
 
 	if (WARN_ON(dir == DMA_NONE))
@@ -273,72 +289,91 @@ static const struct dma_map_ops xen_grant_dma_ops = {
 	.dma_supported = xen_grant_dma_supported,
 };
 
-bool xen_is_grant_dma_device(struct device *dev)
+static bool xen_is_dt_grant_dma_device(struct device *dev)
 {
 	struct device_node *iommu_np;
 	bool has_iommu;
 
-	/* XXX Handle only DT devices for now */
-	if (!dev->of_node)
-		return false;
-
 	iommu_np = of_parse_phandle(dev->of_node, "iommus", 0);
-	has_iommu = iommu_np && of_device_is_compatible(iommu_np, "xen,grant-dma");
+	has_iommu = iommu_np &&
+		    of_device_is_compatible(iommu_np, "xen,grant-dma");
 	of_node_put(iommu_np);
 
 	return has_iommu;
 }
 
+bool xen_is_grant_dma_device(struct device *dev)
+{
+	/* XXX Handle only DT devices for now */
+	if (dev->of_node)
+		return xen_is_dt_grant_dma_device(dev);
+
+	return false;
+}
+
 bool xen_virtio_mem_acc(struct virtio_device *dev)
 {
-	if (IS_ENABLED(CONFIG_XEN_VIRTIO_FORCE_GRANT))
+	if (IS_ENABLED(CONFIG_XEN_VIRTIO_FORCE_GRANT) || xen_pv_domain())
 		return true;
 
 	return xen_is_grant_dma_device(dev->dev.parent);
 }
 
-void xen_grant_setup_dma_ops(struct device *dev)
+static int xen_dt_grant_init_backend_domid(struct device *dev,
+					   struct xen_grant_dma_data *data)
 {
-	struct xen_grant_dma_data *data;
 	struct of_phandle_args iommu_spec;
 
-	data = find_xen_grant_dma_data(dev);
-	if (data) {
-		dev_err(dev, "Xen grant DMA data is already created\n");
-		return;
-	}
-
-	/* XXX ACPI device unsupported for now */
-	if (!dev->of_node)
-		goto err;
-
 	if (of_parse_phandle_with_args(dev->of_node, "iommus", "#iommu-cells",
 			0, &iommu_spec)) {
 		dev_err(dev, "Cannot parse iommus property\n");
-		goto err;
+		return -ESRCH;
 	}
 
 	if (!of_device_is_compatible(iommu_spec.np, "xen,grant-dma") ||
 			iommu_spec.args_count != 1) {
 		dev_err(dev, "Incompatible IOMMU node\n");
 		of_node_put(iommu_spec.np);
-		goto err;
+		return -ESRCH;
 	}
 
 	of_node_put(iommu_spec.np);
 
+	/*
+	 * The endpoint ID here means the ID of the domain where the
+	 * corresponding backend is running
+	 */
+	data->backend_domid = iommu_spec.args[0];
+
+	return 0;
+}
+
+void xen_grant_setup_dma_ops(struct device *dev)
+{
+	struct xen_grant_dma_data *data;
+
+	data = find_xen_grant_dma_data(dev);
+	if (data) {
+		dev_err(dev, "Xen grant DMA data is already created\n");
+		return;
+	}
+
 	data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL);
 	if (!data)
 		goto err;
 
-	/*
-	 * The endpoint ID here means the ID of the domain where the corresponding
-	 * backend is running
-	 */
-	data->backend_domid = iommu_spec.args[0];
+	if (dev->of_node) {
+		if (xen_dt_grant_init_backend_domid(dev, data))
+			goto err;
+	} else if (IS_ENABLED(CONFIG_XEN_VIRTIO_FORCE_GRANT)) {
+		dev_info(dev, "Using dom0 as backend\n");
+		data->backend_domid = 0;
+	} else {
+		/* XXX ACPI device unsupported for now */
+		goto err;
+	}
 
-	if (xa_err(xa_store(&xen_grant_dma_devices, (unsigned long)dev, data,
-			GFP_KERNEL))) {
+	if (store_xen_grant_dma_data(dev, data)) {
 		dev_err(dev, "Cannot store Xen grant DMA data\n");
 		goto err;
 	}
@@ -348,9 +383,20 @@ void xen_grant_setup_dma_ops(struct device *dev)
 	return;
 
 err:
+	devm_kfree(dev, data);
 	dev_err(dev, "Cannot set up Xen grant DMA ops, retain platform DMA ops\n");
 }
 
+bool xen_virtio_restricted_mem_acc(struct virtio_device *dev)
+{
+	bool ret = xen_virtio_mem_acc(dev);
+
+	if (ret)
+		xen_grant_setup_dma_ops(dev->dev.parent);
+
+	return ret;
+}
+
 MODULE_DESCRIPTION("Xen grant DMA-mapping layer");
 MODULE_AUTHOR("Juergen Gross <jgross@suse.com>");
 MODULE_LICENSE("GPL");
diff --git a/drivers/xen/xen-pciback/xenbus.c b/drivers/xen/xen-pciback/xenbus.c
index bde63ef677b8..d171091eec12 100644
--- a/drivers/xen/xen-pciback/xenbus.c
+++ b/drivers/xen/xen-pciback/xenbus.c
@@ -31,7 +31,7 @@ MODULE_PARM_DESC(passthrough,
 	"   frontend (for example, a device at 06:01.b will still appear at\n"\
 	"   06:01.b to the frontend). This is similar to how Xen 2.0.x\n"\
 	"   exposed PCI devices to its driver domains. This may be required\n"\
-	"   for drivers which depend on finding their hardward in certain\n"\
+	"   for drivers which depend on finding their hardware in certain\n"\
 	"   bus/slot locations.");
 
 static struct xen_pcibk_device *alloc_pdev(struct xenbus_device *xdev)