xen: add helpers to allocate unpopulated memory

To be used in order to create foreign mappings. This is based on the
ZONE_DEVICE facility which is used by persistent memory devices in
order to create struct pages and kernel virtual mappings for the IOMEM
areas of such devices. Note that on kernels without support for
ZONE_DEVICE Xen will fallback to use ballooned pages in order to
create foreign mappings.

The newly added helpers use the same parameters as the existing
{alloc/free}_xenballooned_pages functions, which allows for in-place
replacement of the callers. Once a memory region has been added to be
used as scratch mapping space it will no longer be released, and pages
returned are kept in a linked list. This allows to have a buffer of
pages and prevents resorting to frequent additions and removals of
regions.

If enabled (because ZONE_DEVICE is supported) the usage of the new
functionality untangles Xen balloon and RAM hotplug from the usage of
unpopulated physical memory ranges to map foreign pages, which is the
correct thing to do in order to avoid mappings of foreign pages depend
on memory hotplug.

Note the driver is currently not enabled on Arm platforms because it
would interfere with the identity mapping required on some platforms.

Signed-off-by: Roger Pau Monné <roger.pau@citrix.com>
Reviewed-by: Juergen Gross <jgross@suse.com>
Link: https://lore.kernel.org/r/20200901083326.21264-4-roger.pau@citrix.com
Signed-off-by: Juergen Gross <jgross@suse.com>

8 files changed, 205 insertions, 11 deletions

diff --git a/drivers/xen/Kconfig b/drivers/xen/Kconfig
index 46e7fd099904..0ab54df82520 100644
--- a/drivers/xen/Kconfig
+++ b/drivers/xen/Kconfig
@@ -324,4 +324,14 @@ 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 0d322f3d90cd..3cca2be28824 100644
--- a/drivers/xen/Makefile
+++ b/drivers/xen/Makefile
@@ -42,3 +42,4 @@ 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 b1d8b028bf80..4bfbe71705e4 100644
--- a/drivers/xen/balloon.c
+++ b/drivers/xen/balloon.c
@@ -654,7 +654,7 @@ 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)
 {
@@ -708,7 +708,7 @@ 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 095d683ad574..8bcb0ce223a5 100644
--- a/drivers/xen/privcmd.c
+++ b/drivers/xen/privcmd.c
@@ -425,7 +425,7 @@ 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);
@@ -896,7 +896,7 @@ 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;