Merge tag 'for-linus-5.9-rc4-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip

Pull xen updates from Juergen Gross:
 "A small series for fixing a problem with Xen PVH guests when running
  as backends (e.g. as dom0).

  Mapping other guests' memory is now working via ZONE_DEVICE, thus not
  requiring to abuse the memory hotplug functionality for that purpose"

* tag 'for-linus-5.9-rc4-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip:
  xen: add helpers to allocate unpopulated memory
  memremap: rename MEMORY_DEVICE_DEVDAX to MEMORY_DEVICE_GENERIC
  xen/balloon: add header guard

14 files changed, 229 insertions, 22 deletions

diff --git a/drivers/dax/device.c b/drivers/dax/device.c
index 4c0af2eb7e19..1e89513f3c59 100644
--- a/drivers/dax/device.c
+++ b/drivers/dax/device.c
@@ -429,7 +429,7 @@ int dev_dax_probe(struct device *dev)
 		return -EBUSY;
 	}
 
-	dev_dax->pgmap.type = MEMORY_DEVICE_DEVDAX;
+	dev_dax->pgmap.type = MEMORY_DEVICE_GENERIC;
 	addr = devm_memremap_pages(dev, &dev_dax->pgmap);
 	if (IS_ERR(addr))
 		return PTR_ERR(addr);
diff --git a/drivers/gpu/drm/xen/xen_drm_front_gem.c b/drivers/gpu/drm/xen/xen_drm_front_gem.c
index 39ff95b75357..534daf37c97e 100644
--- a/drivers/gpu/drm/xen/xen_drm_front_gem.c
+++ b/drivers/gpu/drm/xen/xen_drm_front_gem.c
@@ -18,6 +18,7 @@
 #include <drm/drm_probe_helper.h>
 
 #include <xen/balloon.h>
+#include <xen/xen.h>
 
 #include "xen_drm_front.h"
 #include "xen_drm_front_gem.h"
@@ -99,8 +100,8 @@ static struct xen_gem_object *gem_create(struct drm_device *dev, size_t size)
 		 * allocate ballooned pages which will be used to map
 		 * grant references provided by the backend
 		 */
-		ret = alloc_xenballooned_pages(xen_obj->num_pages,
-					       xen_obj->pages);
+		ret = xen_alloc_unpopulated_pages(xen_obj->num_pages,
+					          xen_obj->pages);
 		if (ret < 0) {
 			DRM_ERROR("Cannot allocate %zu ballooned pages: %d\n",
 				  xen_obj->num_pages, ret);
@@ -152,8 +153,8 @@ void xen_drm_front_gem_free_object_unlocked(struct drm_gem_object *gem_obj)
 	} else {
 		if (xen_obj->pages) {
 			if (xen_obj->be_alloc) {
-				free_xenballooned_pages(xen_obj->num_pages,
-							xen_obj->pages);
+				xen_free_unpopulated_pages(xen_obj->num_pages,
+							   xen_obj->pages);
 				gem_free_pages_array(xen_obj);
 			} else {
 				drm_gem_put_pages(&xen_obj->base,
diff --git a/drivers/xen/Kconfig b/drivers/xen/Kconfig
index ea6c1e7e3e42..41645fe6ad48 100644
--- a/drivers/xen/Kconfig
+++ b/drivers/xen/Kconfig
@@ -325,4 +325,14 @@ config XEN_HAVE_VPMU
 config XEN_FRONT_PGDIR_SHBUF
 	tristate
 
+config XEN_UNPOPULATED_ALLOC
+	bool "Use unpopulated memory ranges for guest mappings"
+	depends on X86 && ZONE_DEVICE
+	default XEN_BACKEND || XEN_GNTDEV || XEN_DOM0
+	help
+	  Use unpopulated memory ranges in order to create mappings for guest
+	  memory regions, including grant maps and foreign pages. This avoids
+	  having to balloon out RAM regions in order to obtain physical memory
+	  space to create such mappings.
+
 endmenu
diff --git a/drivers/xen/Makefile b/drivers/xen/Makefile
index c25c9a699b48..babdca808861 100644
--- a/drivers/xen/Makefile
+++ b/drivers/xen/Makefile
@@ -41,3 +41,4 @@ xen-gntdev-$(CONFIG_XEN_GNTDEV_DMABUF)	+= gntdev-dmabuf.o
 xen-gntalloc-y				:= gntalloc.o
 xen-privcmd-y				:= privcmd.o privcmd-buf.o
 obj-$(CONFIG_XEN_FRONT_PGDIR_SHBUF)	+= xen-front-pgdir-shbuf.o
+obj-$(CONFIG_XEN_UNPOPULATED_ALLOC)	+= unpopulated-alloc.o
diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c
index 37ffccda8bb8..51427c752b37 100644
--- a/drivers/xen/balloon.c
+++ b/drivers/xen/balloon.c
@@ -653,7 +653,7 @@ void free_xenballooned_pages(int nr_pages, struct page **pages)
 }
 EXPORT_SYMBOL(free_xenballooned_pages);
 
-#ifdef CONFIG_XEN_PV
+#if defined(CONFIG_XEN_PV) && !defined(CONFIG_XEN_UNPOPULATED_ALLOC)
 static void __init balloon_add_region(unsigned long start_pfn,
 				      unsigned long pages)
 {
@@ -707,7 +707,7 @@ static int __init balloon_init(void)
 	register_sysctl_table(xen_root);
 #endif
 
-#ifdef CONFIG_XEN_PV
+#if defined(CONFIG_XEN_PV) && !defined(CONFIG_XEN_UNPOPULATED_ALLOC)
 	{
 		int i;
 
diff --git a/drivers/xen/grant-table.c b/drivers/xen/grant-table.c
index 8d06bf1cc347..523dcdf39cc9 100644
--- a/drivers/xen/grant-table.c
+++ b/drivers/xen/grant-table.c
@@ -801,7 +801,7 @@ int gnttab_alloc_pages(int nr_pages, struct page **pages)
 {
 	int ret;
 
-	ret = alloc_xenballooned_pages(nr_pages, pages);
+	ret = xen_alloc_unpopulated_pages(nr_pages, pages);
 	if (ret < 0)
 		return ret;
 
@@ -836,7 +836,7 @@ EXPORT_SYMBOL_GPL(gnttab_pages_clear_private);
 void gnttab_free_pages(int nr_pages, struct page **pages)
 {
 	gnttab_pages_clear_private(nr_pages, pages);
-	free_xenballooned_pages(nr_pages, pages);
+	xen_free_unpopulated_pages(nr_pages, pages);
 }
 EXPORT_SYMBOL_GPL(gnttab_free_pages);
 
diff --git a/drivers/xen/privcmd.c b/drivers/xen/privcmd.c
index 63abe6c3642b..b0c73c58f987 100644
--- a/drivers/xen/privcmd.c
+++ b/drivers/xen/privcmd.c
@@ -424,7 +424,7 @@ static int alloc_empty_pages(struct vm_area_struct *vma, int numpgs)
 	if (pages == NULL)
 		return -ENOMEM;
 
-	rc = alloc_xenballooned_pages(numpgs, pages);
+	rc = xen_alloc_unpopulated_pages(numpgs, pages);
 	if (rc != 0) {
 		pr_warn("%s Could not alloc %d pfns rc:%d\n", __func__,
 			numpgs, rc);
@@ -895,7 +895,7 @@ static void privcmd_close(struct vm_area_struct *vma)
 
 	rc = xen_unmap_domain_gfn_range(vma, numgfns, pages);
 	if (rc == 0)
-		free_xenballooned_pages(numpgs, pages);
+		xen_free_unpopulated_pages(numpgs, pages);
 	else
 		pr_crit("unable to unmap MFN range: leaking %d pages. rc=%d\n",
 			numpgs, rc);
diff --git a/drivers/xen/unpopulated-alloc.c b/drivers/xen/unpopulated-alloc.c
new file mode 100644
index 000000000000..3b98dc921426
--- /dev/null
+++ b/drivers/xen/unpopulated-alloc.c
@@ -0,0 +1,183 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/errno.h>
+#include <linux/gfp.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/memremap.h>
+#include <linux/slab.h>
+
+#include <asm/page.h>
+
+#include <xen/page.h>
+#include <xen/xen.h>
+
+static DEFINE_MUTEX(list_lock);
+static LIST_HEAD(page_list);
+static unsigned int list_count;
+
+static int fill_list(unsigned int nr_pages)
+{
+	struct dev_pagemap *pgmap;
+	void *vaddr;
+	unsigned int i, alloc_pages = round_up(nr_pages, PAGES_PER_SECTION);
+	int ret;
+
+	pgmap = kzalloc(sizeof(*pgmap), GFP_KERNEL);
+	if (!pgmap)
+		return -ENOMEM;
+
+	pgmap->type = MEMORY_DEVICE_GENERIC;
+	pgmap->res.name = "Xen scratch";
+	pgmap->res.flags = IORESOURCE_MEM | IORESOURCE_BUSY;
+
+	ret = allocate_resource(&iomem_resource, &pgmap->res,
+				alloc_pages * PAGE_SIZE, 0, -1,
+				PAGES_PER_SECTION * PAGE_SIZE, NULL, NULL);
+	if (ret < 0) {
+		pr_err("Cannot allocate new IOMEM resource\n");
+		kfree(pgmap);
+		return ret;
+	}
+
+#ifdef CONFIG_XEN_HAVE_PVMMU
+        /*
+         * memremap will build page tables for the new memory so
+         * the p2m must contain invalid entries so the correct
+         * non-present PTEs will be written.
+         *
+         * If a failure occurs, the original (identity) p2m entries
+         * are not restored since this region is now known not to
+         * conflict with any devices.
+         */
+	if (!xen_feature(XENFEAT_auto_translated_physmap)) {
+		xen_pfn_t pfn = PFN_DOWN(pgmap->res.start);
+
+		for (i = 0; i < alloc_pages; i++) {
+			if (!set_phys_to_machine(pfn + i, INVALID_P2M_ENTRY)) {
+				pr_warn("set_phys_to_machine() failed, no memory added\n");
+				release_resource(&pgmap->res);
+				kfree(pgmap);
+				return -ENOMEM;
+			}
+                }
+	}
+#endif
+
+	vaddr = memremap_pages(pgmap, NUMA_NO_NODE);
+	if (IS_ERR(vaddr)) {
+		pr_err("Cannot remap memory range\n");
+		release_resource(&pgmap->res);
+		kfree(pgmap);
+		return PTR_ERR(vaddr);
+	}
+
+	for (i = 0; i < alloc_pages; i++) {
+		struct page *pg = virt_to_page(vaddr + PAGE_SIZE * i);
+
+		BUG_ON(!virt_addr_valid(vaddr + PAGE_SIZE * i));
+		list_add(&pg->lru, &page_list);
+		list_count++;
+	}
+
+	return 0;
+}
+
+/**
+ * xen_alloc_unpopulated_pages - alloc unpopulated pages
+ * @nr_pages: Number of pages
+ * @pages: pages returned
+ * @return 0 on success, error otherwise
+ */
+int xen_alloc_unpopulated_pages(unsigned int nr_pages, struct page **pages)
+{
+	unsigned int i;
+	int ret = 0;
+
+	mutex_lock(&list_lock);
+	if (list_count < nr_pages) {
+		ret = fill_list(nr_pages - list_count);
+		if (ret)
+			goto out;
+	}
+
+	for (i = 0; i < nr_pages; i++) {
+		struct page *pg = list_first_entry_or_null(&page_list,
+							   struct page,
+							   lru);
+
+		BUG_ON(!pg);
+		list_del(&pg->lru);
+		list_count--;
+		pages[i] = pg;
+
+#ifdef CONFIG_XEN_HAVE_PVMMU
+		if (!xen_feature(XENFEAT_auto_translated_physmap)) {
+			ret = xen_alloc_p2m_entry(page_to_pfn(pg));
+			if (ret < 0) {
+				unsigned int j;
+
+				for (j = 0; j <= i; j++) {
+					list_add(&pages[j]->lru, &page_list);
+					list_count++;
+				}
+				goto out;
+			}
+		}
+#endif
+	}
+
+out:
+	mutex_unlock(&list_lock);
+	return ret;
+}
+EXPORT_SYMBOL(xen_alloc_unpopulated_pages);
+
+/**
+ * xen_free_unpopulated_pages - return unpopulated pages
+ * @nr_pages: Number of pages
+ * @pages: pages to return
+ */
+void xen_free_unpopulated_pages(unsigned int nr_pages, struct page **pages)
+{
+	unsigned int i;
+
+	mutex_lock(&list_lock);
+	for (i = 0; i < nr_pages; i++) {
+		list_add(&pages[i]->lru, &page_list);
+		list_count++;
+	}
+	mutex_unlock(&list_lock);
+}
+EXPORT_SYMBOL(xen_free_unpopulated_pages);
+
+#ifdef CONFIG_XEN_PV
+static int __init init(void)
+{
+	unsigned int i;
+
+	if (!xen_domain())
+		return -ENODEV;
+
+	if (!xen_pv_domain())
+		return 0;
+
+	/*
+	 * Initialize with pages from the extra memory regions (see
+	 * arch/x86/xen/setup.c).
+	 */
+	for (i = 0; i < XEN_EXTRA_MEM_MAX_REGIONS; i++) {
+		unsigned int j;
+
+		for (j = 0; j < xen_extra_mem[i].n_pfns; j++) {
+			struct page *pg =
+				pfn_to_page(xen_extra_mem[i].start_pfn + j);
+
+			list_add(&pg->lru, &page_list);
+			list_count++;
+		}
+	}
+
+	return 0;
+}
+subsys_initcall(init);
+#endif
diff --git a/drivers/xen/xenbus/xenbus_client.c b/drivers/xen/xenbus/xenbus_client.c
index 907bcbb93afb..2690318ad50f 100644
--- a/drivers/xen/xenbus/xenbus_client.c
+++ b/drivers/xen/xenbus/xenbus_client.c
@@ -621,7 +621,7 @@ static int xenbus_map_ring_hvm(struct xenbus_device *dev,
 	bool leaked = false;
 	unsigned int nr_pages = XENBUS_PAGES(nr_grefs);
 
-	err = alloc_xenballooned_pages(nr_pages, node->hvm.pages);
+	err = xen_alloc_unpopulated_pages(nr_pages, node->hvm.pages);
 	if (err)
 		goto out_err;
 
@@ -662,7 +662,7 @@ static int xenbus_map_ring_hvm(struct xenbus_device *dev,
 			 addr, nr_pages);
  out_free_ballooned_pages:
 	if (!leaked)
-		free_xenballooned_pages(nr_pages, node->hvm.pages);
+		xen_free_unpopulated_pages(nr_pages, node->hvm.pages);
  out_err:
 	return err;
 }
@@ -858,7 +858,7 @@ static int xenbus_unmap_ring_hvm(struct xenbus_device *dev, void *vaddr)
 			       info.addrs);
 	if (!rv) {
 		vunmap(vaddr);
-		free_xenballooned_pages(nr_pages, node->hvm.pages);
+		xen_free_unpopulated_pages(nr_pages, node->hvm.pages);
 	}
 	else
 		WARN(1, "Leaking %p, size %u page(s)\n", vaddr, nr_pages);
diff --git a/drivers/xen/xlate_mmu.c b/drivers/xen/xlate_mmu.c
index 7b1077f0abcb..34742c6e189e 100644
--- a/drivers/xen/xlate_mmu.c
+++ b/drivers/xen/xlate_mmu.c
@@ -232,7 +232,7 @@ int __init xen_xlate_map_ballooned_pages(xen_pfn_t **gfns, void **virt,
 		kfree(pages);
 		return -ENOMEM;
 	}
-	rc = alloc_xenballooned_pages(nr_pages, pages);
+	rc = xen_alloc_unpopulated_pages(nr_pages, pages);
 	if (rc) {
 		pr_warn("%s Couldn't balloon alloc %ld pages rc:%d\n", __func__,
 			nr_pages, rc);
@@ -249,7 +249,7 @@ int __init xen_xlate_map_ballooned_pages(xen_pfn_t **gfns, void **virt,
 	if (!vaddr) {
 		pr_warn("%s Couldn't map %ld pages rc:%d\n", __func__,
 			nr_pages, rc);
-		free_xenballooned_pages(nr_pages, pages);
+		xen_free_unpopulated_pages(nr_pages, pages);
 		kfree(pages);
 		kfree(pfns);
 		return -ENOMEM;
diff --git a/include/linux/memremap.h b/include/linux/memremap.h
index 5f5b2df06e61..e5862746751b 100644
--- a/include/linux/memremap.h
+++ b/include/linux/memremap.h
@@ -46,11 +46,10 @@ struct vmem_altmap {
  * wakeup is used to coordinate physical address space management (ex:
  * fs truncate/hole punch) vs pinned pages (ex: device dma).
  *
- * MEMORY_DEVICE_DEVDAX:
+ * MEMORY_DEVICE_GENERIC:
  * Host memory that has similar access semantics as System RAM i.e. DMA
- * coherent and supports page pinning. In contrast to
- * MEMORY_DEVICE_FS_DAX, this memory is access via a device-dax
- * character device.
+ * coherent and supports page pinning. This is for example used by DAX devices
+ * that expose memory using a character device.
  *
  * MEMORY_DEVICE_PCI_P2PDMA:
  * Device memory residing in a PCI BAR intended for use with Peer-to-Peer
@@ -60,7 +59,7 @@ enum memory_type {
 	/* 0 is reserved to catch uninitialized type fields */
 	MEMORY_DEVICE_PRIVATE = 1,
 	MEMORY_DEVICE_FS_DAX,
-	MEMORY_DEVICE_DEVDAX,
+	MEMORY_DEVICE_GENERIC,
 	MEMORY_DEVICE_PCI_P2PDMA,
 };
 
diff --git a/include/xen/balloon.h b/include/xen/balloon.h
index 6fb95aa19405..6dbdb0b3fd03 100644
--- a/include/xen/balloon.h
+++ b/include/xen/balloon.h
@@ -2,6 +2,8 @@
 /******************************************************************************
  * Xen balloon functionality
  */
+#ifndef _XEN_BALLOON_H
+#define _XEN_BALLOON_H
 
 #define RETRY_UNLIMITED	0
 
@@ -34,3 +36,5 @@ static inline void xen_balloon_init(void)
 {
 }
 #endif
+
+#endif	/* _XEN_BALLOON_H */
diff --git a/include/xen/xen.h b/include/xen/xen.h
index 19a72f591e2b..43efba045acc 100644
--- a/include/xen/xen.h
+++ b/include/xen/xen.h
@@ -52,4 +52,13 @@ bool xen_biovec_phys_mergeable(const struct bio_vec *vec1,
 extern u64 xen_saved_max_mem_size;
 #endif
 
+#ifdef CONFIG_XEN_UNPOPULATED_ALLOC
+int xen_alloc_unpopulated_pages(unsigned int nr_pages, struct page **pages);
+void xen_free_unpopulated_pages(unsigned int nr_pages, struct page **pages);
+#else
+#define xen_alloc_unpopulated_pages alloc_xenballooned_pages
+#define xen_free_unpopulated_pages free_xenballooned_pages
+#include <xen/balloon.h>
+#endif
+
 #endif	/* _XEN_XEN_H */
diff --git a/mm/memremap.c b/mm/memremap.c
index 03e38b7a38f1..006dace60b1a 100644
--- a/mm/memremap.c
+++ b/mm/memremap.c
@@ -216,7 +216,7 @@ void *memremap_pages(struct dev_pagemap *pgmap, int nid)
 			return ERR_PTR(-EINVAL);
 		}
 		break;
-	case MEMORY_DEVICE_DEVDAX:
+	case MEMORY_DEVICE_GENERIC:
 		need_devmap_managed = false;
 		break;
 	case MEMORY_DEVICE_PCI_P2PDMA: