[PATCH] xen/balloon: Mark unallocated host memory as UNUSABLE

[Boris Ostrovsky]

Commit f5775e0b6116 ("x86/xen: discard RAM regions above the maximum
reservation") left host memory not assigned to dom0 as available for
memory hotplug.

Unfortunately this also meant that those regions could be used by
others. Specifically, commit fa564ad96366 ("x86/PCI: Enable a 64bit BAR
on AMD Family 15h (Models 00-1f, 30-3f, 60-7f)") may try to map those
addresses as MMIO.

To prevent this mark unallocated host memory as E820_TYPE_UNUSABLE (thus
effectively reverting f5775e0b6116) and keep track of that region as
a hostmem resource that can be used for the hotplug.

Signed-off-by: Boris Ostrovsky <boris.ostrovsky@xxxxxxxxxx>
---
I don't see /proc/meminfo reporting the hotplugged memory (although
internal data such as max_pfn is updated properly). Need to look at
hotplug code some more. But then I didn't see meminfo changing with
existing code either.


 arch/x86/xen/enlighten.c | 69 ++++++++++++++++++++++++++++++++++++++++++++++++
 arch/x86/xen/setup.c     |  6 ++---
 drivers/xen/balloon.c    | 65 ++++++++++++++++++++++++++++++++++++++-------
 3 files changed, 127 insertions(+), 13 deletions(-)

diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index d669e9d..19223b9 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -3,6 +3,7 @@
 
 #include <xen/features.h>
 #include <xen/page.h>
+#include <xen/interface/memory.h>
 
 #include <asm/xen/hypercall.h>
 #include <asm/xen/hypervisor.h>
@@ -331,3 +332,71 @@ void xen_arch_unregister_cpu(int num)
 }
 EXPORT_SYMBOL(xen_arch_unregister_cpu);
 #endif
+
+#ifdef CONFIG_XEN_BALLOON_MEMORY_HOTPLUG
+void __init arch_xen_balloon_init(struct resource *hostmem_resource)
+{
+	struct xen_memory_map memmap;
+	int rc, i, last_guest_ram;
+	unsigned long max_addr = max_pfn << PAGE_SHIFT;
+	struct e820_table *xen_e820_table;
+	struct e820_entry *entry;
+	struct resource *res = NULL;
+
+	if (!xen_initial_domain())
+		return;
+
+	xen_e820_table = kzalloc(sizeof(*xen_e820_table), GFP_KERNEL);
+	if (!xen_e820_table) {
+		pr_warn("%s: Out of memory\n", __func__);
+		return;
+	}
+
+	memmap.nr_entries = ARRAY_SIZE(xen_e820_table->entries);
+	set_xen_guest_handle(memmap.buffer, xen_e820_table->entries);
+	rc = HYPERVISOR_memory_op(XENMEM_machine_memory_map, &memmap);
+	if (rc) {
+		pr_warn("%s: Can't read host e820 (%d)\n", __func__, rc);
+		goto out;
+	}
+
+	last_guest_ram = i = 0;
+	while (xen_e820_table->entries[i].addr < max_addr) {
+		if (xen_e820_table->entries[i].type == E820_TYPE_RAM)
+			last_guest_ram = i;
+		i++;
+	}
+
+	entry = &xen_e820_table->entries[last_guest_ram];
+	if (max_addr >= entry->addr + entry->size)
+		goto out; /* No unallocated host RAM. */
+
+	hostmem_resource->start = max_addr;
+	hostmem_resource->end = entry->addr + entry->size;
+	for (; i < memmap.nr_entries; i++) {
+		entry = &xen_e820_table->entries[i];
+		if (entry->type == E820_TYPE_RAM)
+			continue;
+
+		res = kzalloc(sizeof(*res), GFP_KERNEL);
+		if (!res) {
+			pr_warn("%s: Out of memory\n", __func__);
+			goto out;
+		}
+
+		res->name = "Host memory";
+		res->end = entry->addr + entry->size;
+		res->start = entry->addr;
+		rc = insert_resource(hostmem_resource, res);
+		if (rc) {
+			pr_warn("%s: Can't insert hostmem resource [%llu - %llu] (%d)\n",
+				__func__, res->start, res->end, rc);
+			kfree(res);
+			goto  out;
+		}
+	}
+
+ out:
+	kfree(xen_e820_table);
+}
+#endif /* CONFIG_XEN_BALLOON_MEMORY_HOTPLUG */
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index c114ca7..6e0d208 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -808,7 +808,6 @@ char * __init xen_memory_setup(void)
 	addr = xen_e820_table.entries[0].addr;
 	size = xen_e820_table.entries[0].size;
 	while (i < xen_e820_table.nr_entries) {
-		bool discard = false;
 
 		chunk_size = size;
 		type = xen_e820_table.entries[i].type;
@@ -824,11 +823,10 @@ char * __init xen_memory_setup(void)
 				xen_add_extra_mem(pfn_s, n_pfns);
 				xen_max_p2m_pfn = pfn_s + n_pfns;
 			} else
-				discard = true;
+				type = E820_TYPE_UNUSABLE;
 		}
 
-		if (!discard)
-			xen_align_and_add_e820_region(addr, chunk_size, type);
+		xen_align_and_add_e820_region(addr, chunk_size, type);
 
 		addr += chunk_size;
 		size -= chunk_size;
diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c
index f77e499..fb5aa7c 100644
--- a/drivers/xen/balloon.c
+++ b/drivers/xen/balloon.c
@@ -257,10 +257,25 @@ static void release_memory_resource(struct resource *resource)
 	kfree(resource);
 }
 
+/*
+ * Host memory not allocated to dom0. We can use this range for hotplug-based
+ * ballooning.
+ *
+ * It's a type-less resource. Setting IORESOURCE_MEM will make resource
+ * management algorithms (arch_remove_reservations()) look into guest e820,
+ * which we don't want.
+ */
+static struct resource hostmem_resource = {
+	.name   = "Host memory",
+};
+
+void __attribute__((weak)) __init arch_xen_balloon_init(struct resource *res)
+{}
+
 static struct resource *additional_memory_resource(phys_addr_t size)
 {
-	struct resource *res;
-	int ret;
+	struct resource *res, *res_hostmem;
+	int ret = -ENOMEM;
 
 	res = kzalloc(sizeof(*res), GFP_KERNEL);
 	if (!res)
@@ -269,13 +284,42 @@ static struct resource *additional_memory_resource(phys_addr_t size)
 	res->name = "System RAM";
 	res->flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
 
-	ret = allocate_resource(&iomem_resource, res,
-				size, 0, -1,
-				PAGES_PER_SECTION * PAGE_SIZE, NULL, NULL);
-	if (ret < 0) {
-		pr_err("Cannot allocate new System RAM resource\n");
-		kfree(res);
-		return NULL;
+	res_hostmem = kzalloc(sizeof(*res), GFP_KERNEL);
+	if (res_hostmem) {
+		/* Try to grab a range from hostmem */
+		res_hostmem->name = "Host memory";
+		ret = allocate_resource(&hostmem_resource, res_hostmem,
+					size, 0, -1,
+					PAGES_PER_SECTION * PAGE_SIZE, NULL, NULL);
+	}
+
+	if (!ret) {
+		/*
+		 * Insert this resource into iomem. Because hostmem_resource
+		 * tracks portion of guest e820 marked as UNUSABLE noone else
+		 * should try to use it.
+		 */
+		res->start = res_hostmem->start;
+		res->end = res_hostmem->end;
+		ret = insert_resource(&iomem_resource, res);
+		if (ret < 0) {
+			pr_err("Can't insert iomem_resource [%llx - %llx]\n",
+				res->start, res->end);
+			release_memory_resource(res_hostmem);
+			res_hostmem = NULL;
+			res->start = res->end = 0;
+		}
+	}
+
+	if (ret) {
+		ret = allocate_resource(&iomem_resource, res,
+					size, 0, -1,
+					PAGES_PER_SECTION * PAGE_SIZE, NULL, NULL);
+		if (ret < 0) {
+			pr_err("Cannot allocate new System RAM resource\n");
+			kfree(res);
+			return NULL;
+		}
 	}
 
 #ifdef CONFIG_SPARSEMEM
@@ -287,6 +331,7 @@ static struct resource *additional_memory_resource(phys_addr_t size)
 			pr_err("New System RAM resource outside addressable RAM (%lu > %lu)\n",
 			       pfn, limit);
 			release_memory_resource(res);
+			release_memory_resource(res_hostmem);
 			return NULL;
 		}
 	}
@@ -765,6 +810,8 @@ static int __init balloon_init(void)
 	set_online_page_callback(&xen_online_page);
 	register_memory_notifier(&xen_memory_nb);
 	register_sysctl_table(xen_root);
+
+	arch_xen_balloon_init(&hostmem_resource);
 #endif
 
 #ifdef CONFIG_XEN_PV
-- 
2.7.4