xen/unpopulated-alloc: Add mechanism to use Xen resource

The main reason of this change is that unpopulated-alloc
code cannot be used in its current form on Arm, but there
is a desire to reuse it to avoid wasting real RAM pages
for the grant/foreign mappings.

The problem is that system "iomem_resource" is used for
the address space allocation, but the really unallocated
space can't be figured out precisely by the domain on Arm
without hypervisor involvement. For example, not all device
I/O regions are known by the time domain starts creating
grant/foreign mappings. And following the advise from
"iomem_resource" we might end up reusing these regions by
a mistake. So, the hypervisor which maintains the P2M for
the domain is in the best position to provide unused regions
of guest physical address space which could be safely used
to create grant/foreign mappings.

Introduce new helper arch_xen_unpopulated_init() which purpose
is to create specific Xen resource based on the memory regions
provided by the hypervisor to be used as unused space for Xen
scratch pages. If arch doesn't define arch_xen_unpopulated_init()
the default "iomem_resource" will be used.

Update the arguments list of allocate_resource() in fill_list()
to always allocate a region from the hotpluggable range
(maximum possible addressable physical memory range for which
the linear mapping could be created). If arch doesn't define
arch_get_mappable_range() the default range (0,-1) will be used.

The behaviour on x86 won't be changed by current patch as both
arch_xen_unpopulated_init() and arch_get_mappable_range()
are not implemented for it.

Also fallback to allocate xenballooned pages (balloon out RAM
pages) if we do not have any suitable resource to work with
(target_resource is invalid) and as the result we won't be able
to provide unpopulated pages on a request.

Signed-off-by: Oleksandr Tyshchenko <oleksandr_tyshchenko@epam.com>
Reviewed-by: Stefano Stabellini <sstabellini@kernel.org>
Link: https://lore.kernel.org/r/1639080336-26573-5-git-send-email-olekstysh@gmail.com
Signed-off-by: Juergen Gross <jgross@suse.com>

1 files changed, 82 insertions, 4 deletions

diff --git a/drivers/xen/unpopulated-alloc.c b/drivers/xen/unpopulated-alloc.c
index a03dc5b1f37b..a8b41057c382 100644
--- a/drivers/xen/unpopulated-alloc.c
+++ b/drivers/xen/unpopulated-alloc.c
@@ -8,6 +8,7 @@
 
 #include <asm/page.h>
 
+#include <xen/balloon.h>
 #include <xen/page.h>
 #include <xen/xen.h>
 
@@ -15,13 +16,29 @@ static DEFINE_MUTEX(list_lock);
 static struct page *page_list;
 static unsigned int list_count;
 
+static struct resource *target_resource;
+
+/*
+ * If arch is not happy with system "iomem_resource" being used for
+ * the region allocation it can provide it's own view by creating specific
+ * Xen resource with unused regions of guest physical address space provided
+ * by the hypervisor.
+ */
+int __weak __init arch_xen_unpopulated_init(struct resource **res)
+{
+	*res = &iomem_resource;
+
+	return 0;
+}
+
 static int fill_list(unsigned int nr_pages)
 {
 	struct dev_pagemap *pgmap;
-	struct resource *res;
+	struct resource *res, *tmp_res = NULL;
 	void *vaddr;
 	unsigned int i, alloc_pages = round_up(nr_pages, PAGES_PER_SECTION);
-	int ret = -ENOMEM;
+	struct range mhp_range;
+	int ret;
 
 	res = kzalloc(sizeof(*res), GFP_KERNEL);
 	if (!res)
@@ -30,14 +47,40 @@ static int fill_list(unsigned int nr_pages)
 	res->name = "Xen scratch";
 	res->flags = IORESOURCE_MEM | IORESOURCE_BUSY;
 
-	ret = allocate_resource(&iomem_resource, res,
-				alloc_pages * PAGE_SIZE, 0, -1,
+	mhp_range = mhp_get_pluggable_range(true);
+
+	ret = allocate_resource(target_resource, res,
+				alloc_pages * PAGE_SIZE, mhp_range.start, mhp_range.end,
 				PAGES_PER_SECTION * PAGE_SIZE, NULL, NULL);
 	if (ret < 0) {
 		pr_err("Cannot allocate new IOMEM resource\n");
 		goto err_resource;
 	}
 
+	/*
+	 * Reserve the region previously allocated from Xen resource to avoid
+	 * re-using it by someone else.
+	 */
+	if (target_resource != &iomem_resource) {
+		tmp_res = kzalloc(sizeof(*tmp_res), GFP_KERNEL);
+		if (!tmp_res) {
+			ret = -ENOMEM;
+			goto err_insert;
+		}
+
+		tmp_res->name = res->name;
+		tmp_res->start = res->start;
+		tmp_res->end = res->end;
+		tmp_res->flags = res->flags;
+
+		ret = request_resource(&iomem_resource, tmp_res);
+		if (ret < 0) {
+			pr_err("Cannot request resource %pR (%d)\n", tmp_res, ret);
+			kfree(tmp_res);
+			goto err_insert;
+		}
+	}
+
 	pgmap = kzalloc(sizeof(*pgmap), GFP_KERNEL);
 	if (!pgmap) {
 		ret = -ENOMEM;
@@ -95,6 +138,11 @@ static int fill_list(unsigned int nr_pages)
 err_memremap:
 	kfree(pgmap);
 err_pgmap:
+	if (tmp_res) {
+		release_resource(tmp_res);
+		kfree(tmp_res);
+	}
+err_insert:
 	release_resource(res);
 err_resource:
 	kfree(res);
@@ -112,6 +160,14 @@ int xen_alloc_unpopulated_pages(unsigned int nr_pages, struct page **pages)
 	unsigned int i;
 	int ret = 0;
 
+	/*
+	 * Fallback to default behavior if we do not have any suitable resource
+	 * to allocate required region from and as the result we won't be able to
+	 * construct pages.
+	 */
+	if (!target_resource)
+		return xen_alloc_ballooned_pages(nr_pages, pages);
+
 	mutex_lock(&list_lock);
 	if (list_count < nr_pages) {
 		ret = fill_list(nr_pages - list_count);
@@ -159,6 +215,11 @@ void xen_free_unpopulated_pages(unsigned int nr_pages, struct page **pages)
 {
 	unsigned int i;
 
+	if (!target_resource) {
+		xen_free_ballooned_pages(nr_pages, pages);
+		return;
+	}
+
 	mutex_lock(&list_lock);
 	for (i = 0; i < nr_pages; i++) {
 		pages[i]->zone_device_data = page_list;
@@ -201,3 +262,20 @@ static int __init init(void)
 }
 subsys_initcall(init);
 #endif
+
+static int __init unpopulated_init(void)
+{
+	int ret;
+
+	if (!xen_domain())
+		return -ENODEV;
+
+	ret = arch_xen_unpopulated_init(&target_resource);
+	if (ret) {
+		pr_err("xen:unpopulated: Cannot initialize target resource\n");
+		target_resource = NULL;
+	}
+
+	return ret;
+}
+early_initcall(unpopulated_init);