1 files changed, 322 insertions, 94 deletions

diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c
index 043af8ad6b6..5c660c77f03 100644
--- a/drivers/xen/balloon.c
+++ b/drivers/xen/balloon.c
@@ -4,6 +4,12 @@
  * Copyright (c) 2003, B Dragovic
  * Copyright (c) 2003-2004, M Williamson, K Fraser
  * Copyright (c) 2005 Dan M. Smith, IBM Corporation
+ * Copyright (c) 2010 Daniel Kiper
+ *
+ * Memory hotplug support was written by Daniel Kiper. Work on
+ * it was sponsored by Google under Google Summer of Code 2010
+ * program. Jeremy Fitzhardinge from Citrix was the mentor for
+ * this project.
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public License version 2
@@ -30,9 +36,13 @@
  * IN THE SOFTWARE.
  */
 
+#define pr_fmt(fmt) "xen:" KBUILD_MODNAME ": " fmt
+
+#include <linux/cpu.h>
 #include <linux/kernel.h>
 #include <linux/sched.h>
 #include <linux/errno.h>
+#include <linux/module.h>
 #include <linux/mm.h>
 #include <linux/bootmem.h>
 #include <linux/pagemap.h>
@@ -40,12 +50,15 @@
 #include <linux/mutex.h>
 #include <linux/list.h>
 #include <linux/gfp.h>
+#include <linux/notifier.h>
+#include <linux/memory.h>
+#include <linux/memory_hotplug.h>
+#include <linux/percpu-defs.h>
 
 #include <asm/page.h>
 #include <asm/pgalloc.h>
 #include <asm/pgtable.h>
 #include <asm/tlb.h>
-#include <asm/e820.h>
 
 #include <asm/xen/hypervisor.h>
 #include <asm/xen/hypercall.h>
@@ -78,15 +91,9 @@ struct balloon_stats balloon_stats;
 EXPORT_SYMBOL_GPL(balloon_stats);
 
 /* We increase/decrease in batches which fit in a page */
-static unsigned long frame_list[PAGE_SIZE / sizeof(unsigned long)];
+static xen_pfn_t frame_list[PAGE_SIZE / sizeof(unsigned long)];
+static DEFINE_PER_CPU(struct page *, balloon_scratch_page);
 
-#ifdef CONFIG_HIGHMEM
-#define inc_totalhigh_pages() (totalhigh_pages++)
-#define dec_totalhigh_pages() (totalhigh_pages--)
-#else
-#define inc_totalhigh_pages() do {} while(0)
-#define dec_totalhigh_pages() do {} while(0)
-#endif
 
 /* List of ballooned pages, threaded through the mem_map array. */
 static LIST_HEAD(ballooned_pages);
@@ -114,7 +121,6 @@ static void __balloon_append(struct page *page)
 	if (PageHighMem(page)) {
 		list_add_tail(&page->lru, &ballooned_pages);
 		balloon_stats.balloon_high++;
-		dec_totalhigh_pages();
 	} else {
 		list_add(&page->lru, &ballooned_pages);
 		balloon_stats.balloon_low++;
@@ -124,7 +130,7 @@ static void __balloon_append(struct page *page)
 static void balloon_append(struct page *page)
 {
 	__balloon_append(page);
-	totalram_pages--;
+	adjust_managed_page_count(page, -1);
 }
 
 /* balloon_retrieve: rescue a page from the balloon, if it is not empty. */
@@ -141,25 +147,16 @@ static struct page *balloon_retrieve(bool prefer_highmem)
 		page = list_entry(ballooned_pages.next, struct page, lru);
 	list_del(&page->lru);
 
-	if (PageHighMem(page)) {
+	if (PageHighMem(page))
 		balloon_stats.balloon_high--;
-		inc_totalhigh_pages();
-	}
 	else
 		balloon_stats.balloon_low--;
 
-	totalram_pages++;
+	adjust_managed_page_count(page, 1);
 
 	return page;
 }
 
-static struct page *balloon_first_page(void)
-{
-	if (list_empty(&ballooned_pages))
-		return NULL;
-	return list_entry(ballooned_pages.next, struct page, lru);
-}
-
 static struct page *balloon_next_page(struct page *page)
 {
 	struct list_head *next = page->lru.next;
@@ -193,7 +190,88 @@ static enum bp_state update_schedule(enum bp_state state)
 	return BP_EAGAIN;
 }
 
-static unsigned long current_target(void)
+#ifdef CONFIG_XEN_BALLOON_MEMORY_HOTPLUG
+static long current_credit(void)
+{
+	return balloon_stats.target_pages - balloon_stats.current_pages -
+		balloon_stats.hotplug_pages;
+}
+
+static bool balloon_is_inflated(void)
+{
+	if (balloon_stats.balloon_low || balloon_stats.balloon_high ||
+			balloon_stats.balloon_hotplug)
+		return true;
+	else
+		return false;
+}
+
+/*
+ * reserve_additional_memory() adds memory region of size >= credit above
+ * max_pfn. New region is section aligned and size is modified to be multiple
+ * of section size. Those features allow optimal use of address space and
+ * establish proper alignment when this function is called first time after
+ * boot (last section not fully populated at boot time contains unused memory
+ * pages with PG_reserved bit not set; online_pages_range() does not allow page
+ * onlining in whole range if first onlined page does not have PG_reserved
+ * bit set). Real size of added memory is established at page onlining stage.
+ */
+
+static enum bp_state reserve_additional_memory(long credit)
+{
+	int nid, rc;
+	u64 hotplug_start_paddr;
+	unsigned long balloon_hotplug = credit;
+
+	hotplug_start_paddr = PFN_PHYS(SECTION_ALIGN_UP(max_pfn));
+	balloon_hotplug = round_up(balloon_hotplug, PAGES_PER_SECTION);
+	nid = memory_add_physaddr_to_nid(hotplug_start_paddr);
+
+	rc = add_memory(nid, hotplug_start_paddr, balloon_hotplug << PAGE_SHIFT);
+
+	if (rc) {
+		pr_info("%s: add_memory() failed: %i\n", __func__, rc);
+		return BP_EAGAIN;
+	}
+
+	balloon_hotplug -= credit;
+
+	balloon_stats.hotplug_pages += credit;
+	balloon_stats.balloon_hotplug = balloon_hotplug;
+
+	return BP_DONE;
+}
+
+static void xen_online_page(struct page *page)
+{
+	__online_page_set_limits(page);
+
+	mutex_lock(&balloon_mutex);
+
+	__balloon_append(page);
+
+	if (balloon_stats.hotplug_pages)
+		--balloon_stats.hotplug_pages;
+	else
+		--balloon_stats.balloon_hotplug;
+
+	mutex_unlock(&balloon_mutex);
+}
+
+static int xen_memory_notifier(struct notifier_block *nb, unsigned long val, void *v)
+{
+	if (val == MEM_ONLINE)
+		schedule_delayed_work(&balloon_worker, 0);
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block xen_memory_nb = {
+	.notifier_call = xen_memory_notifier,
+	.priority = 0
+};
+#else
+static long current_credit(void)
 {
 	unsigned long target = balloon_stats.target_pages;
 
@@ -202,9 +280,24 @@ static unsigned long current_target(void)
 		     balloon_stats.balloon_low +
 		     balloon_stats.balloon_high);
 
-	return target;
+	return target - balloon_stats.current_pages;
 }
 
+static bool balloon_is_inflated(void)
+{
+	if (balloon_stats.balloon_low || balloon_stats.balloon_high)
+		return true;
+	else
+		return false;
+}
+
+static enum bp_state reserve_additional_memory(long credit)
+{
+	balloon_stats.target_pages = balloon_stats.current_pages;
+	return BP_DONE;
+}
+#endif /* CONFIG_XEN_BALLOON_MEMORY_HOTPLUG */
+
 static enum bp_state increase_reservation(unsigned long nr_pages)
 {
 	int rc;
@@ -216,10 +309,19 @@ static enum bp_state increase_reservation(unsigned long nr_pages)
 		.domid        = DOMID_SELF
 	};
 
+#ifdef CONFIG_XEN_BALLOON_MEMORY_HOTPLUG
+	if (!balloon_stats.balloon_low && !balloon_stats.balloon_high) {
+		nr_pages = min(nr_pages, balloon_stats.balloon_hotplug);
+		balloon_stats.hotplug_pages += nr_pages;
+		balloon_stats.balloon_hotplug -= nr_pages;
+		return BP_DONE;
+	}
+#endif
+
 	if (nr_pages > ARRAY_SIZE(frame_list))
 		nr_pages = ARRAY_SIZE(frame_list);
 
-	page = balloon_first_page();
+	page = list_first_entry_or_null(&ballooned_pages, struct page, lru);
 	for (i = 0; i < nr_pages; i++) {
 		if (!page) {
 			nr_pages = i;
@@ -240,25 +342,25 @@ static enum bp_state increase_reservation(unsigned long nr_pages)
 		BUG_ON(page == NULL);
 
 		pfn = page_to_pfn(page);
-		BUG_ON(!xen_feature(XENFEAT_auto_translated_physmap) &&
-		       phys_to_machine_mapping_valid(pfn));
-
-		set_phys_to_machine(pfn, frame_list[i]);
-
-		/* Link back into the page tables if not highmem. */
-		if (!xen_hvm_domain() && pfn < max_low_pfn) {
-			int ret;
-			ret = HYPERVISOR_update_va_mapping(
-				(unsigned long)__va(pfn << PAGE_SHIFT),
-				mfn_pte(frame_list[i], PAGE_KERNEL),
-				0);
-			BUG_ON(ret);
+
+#ifdef CONFIG_XEN_HAVE_PVMMU
+		if (!xen_feature(XENFEAT_auto_translated_physmap)) {
+			set_phys_to_machine(pfn, frame_list[i]);
+
+			/* Link back into the page tables if not highmem. */
+			if (!PageHighMem(page)) {
+				int ret;
+				ret = HYPERVISOR_update_va_mapping(
+						(unsigned long)__va(pfn << PAGE_SHIFT),
+						mfn_pte(frame_list[i], PAGE_KERNEL),
+						0);
+				BUG_ON(ret);
+			}
 		}
+#endif
 
 		/* Relinquish the page back to the allocator. */
-		ClearPageReserved(page);
-		init_page_count(page);
-		__free_page(page);
+		__free_reserved_page(page);
 	}
 
 	balloon_stats.current_pages += rc;
@@ -278,41 +380,72 @@ static enum bp_state decrease_reservation(unsigned long nr_pages, gfp_t gfp)
 		.domid        = DOMID_SELF
 	};
 
+#ifdef CONFIG_XEN_BALLOON_MEMORY_HOTPLUG
+	if (balloon_stats.hotplug_pages) {
+		nr_pages = min(nr_pages, balloon_stats.hotplug_pages);
+		balloon_stats.hotplug_pages -= nr_pages;
+		balloon_stats.balloon_hotplug += nr_pages;
+		return BP_DONE;
+	}
+#endif
+
 	if (nr_pages > ARRAY_SIZE(frame_list))
 		nr_pages = ARRAY_SIZE(frame_list);
 
 	for (i = 0; i < nr_pages; i++) {
-		if ((page = alloc_page(gfp)) == NULL) {
+		page = alloc_page(gfp);
+		if (page == NULL) {
 			nr_pages = i;
 			state = BP_EAGAIN;
 			break;
 		}
-
-		pfn = page_to_pfn(page);
-		frame_list[i] = pfn_to_mfn(pfn);
-
 		scrub_page(page);
 
-		if (!xen_hvm_domain() && !PageHighMem(page)) {
-			ret = HYPERVISOR_update_va_mapping(
-				(unsigned long)__va(pfn << PAGE_SHIFT),
-				__pte_ma(0), 0);
-			BUG_ON(ret);
-                }
-
+		frame_list[i] = page_to_pfn(page);
 	}
 
-	/* Ensure that ballooned highmem pages don't have kmaps. */
+	/*
+	 * Ensure that ballooned highmem pages don't have kmaps.
+	 *
+	 * Do this before changing the p2m as kmap_flush_unused()
+	 * reads PTEs to obtain pages (and hence needs the original
+	 * p2m entry).
+	 */
 	kmap_flush_unused();
-	flush_tlb_all();
 
-	/* No more mappings: invalidate P2M and add to balloon. */
+	/* Update direct mapping, invalidate P2M, and add to balloon. */
 	for (i = 0; i < nr_pages; i++) {
-		pfn = mfn_to_pfn(frame_list[i]);
-		__set_phys_to_machine(pfn, INVALID_P2M_ENTRY);
-		balloon_append(pfn_to_page(pfn));
+		pfn = frame_list[i];
+		frame_list[i] = pfn_to_mfn(pfn);
+		page = pfn_to_page(pfn);
+
+#ifdef CONFIG_XEN_HAVE_PVMMU
+		/*
+		 * Ballooned out frames are effectively replaced with
+		 * a scratch frame.  Ensure direct mappings and the
+		 * p2m are consistent.
+		 */
+		if (!xen_feature(XENFEAT_auto_translated_physmap)) {
+			if (!PageHighMem(page)) {
+				struct page *scratch_page = get_balloon_scratch_page();
+
+				ret = HYPERVISOR_update_va_mapping(
+						(unsigned long)__va(pfn << PAGE_SHIFT),
+						pfn_pte(page_to_pfn(scratch_page),
+							PAGE_KERNEL_RO), 0);
+				BUG_ON(ret);
+
+				put_balloon_scratch_page();
+			}
+			__set_phys_to_machine(pfn, INVALID_P2M_ENTRY);
+		}
+#endif
+
+		balloon_append(page);
 	}
 
+	flush_tlb_all();
+
 	set_xen_guest_handle(reservation.extent_start, frame_list);
 	reservation.nr_extents   = nr_pages;
 	ret = HYPERVISOR_memory_op(XENMEM_decrease_reservation, &reservation);
@@ -337,10 +470,14 @@ static void balloon_process(struct work_struct *work)
 	mutex_lock(&balloon_mutex);
 
 	do {
-		credit = current_target() - balloon_stats.current_pages;
+		credit = current_credit();
 
-		if (credit > 0)
-			state = increase_reservation(credit);
+		if (credit > 0) {
+			if (balloon_is_inflated())
+				state = increase_reservation(credit);
+			else
+				state = reserve_additional_memory(credit);
+		}
 
 		if (credit < 0)
 			state = decrease_reservation(-credit, GFP_BALLOON);
@@ -360,6 +497,18 @@ static void balloon_process(struct work_struct *work)
 	mutex_unlock(&balloon_mutex);
 }
 
+struct page *get_balloon_scratch_page(void)
+{
+	struct page *ret = get_cpu_var(balloon_scratch_page);
+	BUG_ON(ret == NULL);
+	return ret;
+}
+
+void put_balloon_scratch_page(void)
+{
+	put_cpu_var(balloon_scratch_page);
+}
+
 /* Resets the Xen limit, sets new target, and kicks off processing. */
 void balloon_set_new_target(unsigned long target)
 {
@@ -373,20 +522,24 @@ EXPORT_SYMBOL_GPL(balloon_set_new_target);
  * alloc_xenballooned_pages - get pages that have been ballooned out
  * @nr_pages: Number of pages to get
  * @pages: pages returned
+ * @highmem: allow highmem pages
  * @return 0 on success, error otherwise
  */
-int alloc_xenballooned_pages(int nr_pages, struct page** pages)
+int alloc_xenballooned_pages(int nr_pages, struct page **pages, bool highmem)
 {
 	int pgno = 0;
-	struct page* page;
+	struct page *page;
 	mutex_lock(&balloon_mutex);
 	while (pgno < nr_pages) {
-		page = balloon_retrieve(true);
-		if (page) {
+		page = balloon_retrieve(highmem);
+		if (page && (highmem || !PageHighMem(page))) {
 			pages[pgno++] = page;
 		} else {
 			enum bp_state st;
-			st = decrease_reservation(nr_pages - pgno, GFP_HIGHUSER);
+			if (page)
+				balloon_append(page);
+			st = decrease_reservation(nr_pages - pgno,
+					highmem ? GFP_HIGHUSER : GFP_USER);
 			if (st != BP_DONE)
 				goto out_undo;
 		}
@@ -408,7 +561,7 @@ EXPORT_SYMBOL(alloc_xenballooned_pages);
  * @nr_pages: Number of pages
  * @pages: pages to return
  */
-void free_xenballooned_pages(int nr_pages, struct page** pages)
+void free_xenballooned_pages(int nr_pages, struct page **pages)
 {
 	int i;
 
@@ -420,28 +573,95 @@ void free_xenballooned_pages(int nr_pages, struct page** pages)
 	}
 
 	/* The balloon may be too large now. Shrink it if needed. */
-	if (current_target() != balloon_stats.current_pages)
+	if (current_credit())
 		schedule_delayed_work(&balloon_worker, 0);
 
 	mutex_unlock(&balloon_mutex);
 }
 EXPORT_SYMBOL(free_xenballooned_pages);
 
-static int __init balloon_init(void)
+static void __init balloon_add_region(unsigned long start_pfn,
+				      unsigned long pages)
 {
- 	unsigned long pfn, nr_pages, extra_pfn_end;
+	unsigned long pfn, extra_pfn_end;
 	struct page *page;
 
+	/*
+	 * If the amount of usable memory has been limited (e.g., with
+	 * the 'mem' command line parameter), don't add pages beyond
+	 * this limit.
+	 */
+	extra_pfn_end = min(max_pfn, start_pfn + pages);
+
+	for (pfn = start_pfn; pfn < extra_pfn_end; pfn++) {
+		page = pfn_to_page(pfn);
+		/* totalram_pages and totalhigh_pages do not
+		   include the boot-time balloon extension, so
+		   don't subtract from it. */
+		__balloon_append(page);
+	}
+}
+
+static int alloc_balloon_scratch_page(int cpu)
+{
+	if (per_cpu(balloon_scratch_page, cpu) != NULL)
+		return 0;
+
+	per_cpu(balloon_scratch_page, cpu) = alloc_page(GFP_KERNEL);
+	if (per_cpu(balloon_scratch_page, cpu) == NULL) {
+		pr_warn("Failed to allocate balloon_scratch_page for cpu %d\n", cpu);
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+
+static int balloon_cpu_notify(struct notifier_block *self,
+				    unsigned long action, void *hcpu)
+{
+	int cpu = (long)hcpu;
+	switch (action) {
+	case CPU_UP_PREPARE:
+		if (alloc_balloon_scratch_page(cpu))
+			return NOTIFY_BAD;
+		break;
+	default:
+		break;
+	}
+	return NOTIFY_OK;
+}
+
+static struct notifier_block balloon_cpu_notifier = {
+	.notifier_call	= balloon_cpu_notify,
+};
+
+static int __init balloon_init(void)
+{
+	int i, cpu;
+
 	if (!xen_domain())
 		return -ENODEV;
 
-	pr_info("xen/balloon: Initialising balloon driver.\n");
+	if (!xen_feature(XENFEAT_auto_translated_physmap)) {
+		register_cpu_notifier(&balloon_cpu_notifier);
+
+		get_online_cpus();
+		for_each_online_cpu(cpu) {
+			if (alloc_balloon_scratch_page(cpu)) {
+				put_online_cpus();
+				unregister_cpu_notifier(&balloon_cpu_notifier);
+				return -ENOMEM;
+			}
+		}
+		put_online_cpus();
+	}
+
+	pr_info("Initialising balloon driver\n");
 
- 	if (xen_pv_domain())
- 		nr_pages = xen_start_info->nr_pages;
- 	else
- 		nr_pages = max_pfn;
- 	balloon_stats.current_pages = min(nr_pages, max_pfn);
+	balloon_stats.current_pages = xen_pv_domain()
+		? min(xen_start_info->nr_pages - xen_released_pages, max_pfn)
+		: get_num_physpages();
 	balloon_stats.target_pages  = balloon_stats.current_pages;
 	balloon_stats.balloon_low   = 0;
 	balloon_stats.balloon_high  = 0;
@@ -451,29 +671,37 @@ static int __init balloon_init(void)
 	balloon_stats.retry_count = 1;
 	balloon_stats.max_retry_count = RETRY_UNLIMITED;
 
+#ifdef CONFIG_XEN_BALLOON_MEMORY_HOTPLUG
+	balloon_stats.hotplug_pages = 0;
+	balloon_stats.balloon_hotplug = 0;
+
+	set_online_page_callback(&xen_online_page);
+	register_memory_notifier(&xen_memory_nb);
+#endif
+
 	/*
-	 * Initialise the balloon with excess memory space.  We need
-	 * to make sure we don't add memory which doesn't exist or
-	 * logically exist.  The E820 map can be trimmed to be smaller
-	 * than the amount of physical memory due to the mem= command
-	 * line parameter.  And if this is a 32-bit non-HIGHMEM kernel
-	 * on a system with memory which requires highmem to access,
-	 * don't try to use it.
+	 * Initialize the balloon with pages from the extra memory
+	 * regions (see arch/x86/xen/setup.c).
 	 */
-	extra_pfn_end = min(min(max_pfn, e820_end_of_ram_pfn()),
-			    (unsigned long)PFN_DOWN(xen_extra_mem_start + xen_extra_mem_size));
-	for (pfn = PFN_UP(xen_extra_mem_start);
-	     pfn < extra_pfn_end;
-	     pfn++) {
-		page = pfn_to_page(pfn);
-		/* totalram_pages doesn't include the boot-time
-		   balloon extension, so don't subtract from it. */
-		__balloon_append(page);
-	}
+	for (i = 0; i < XEN_EXTRA_MEM_MAX_REGIONS; i++)
+		if (xen_extra_mem[i].size)
+			balloon_add_region(PFN_UP(xen_extra_mem[i].start),
+					   PFN_DOWN(xen_extra_mem[i].size));
 
 	return 0;
 }
 
 subsys_initcall(balloon_init);
 
+static int __init balloon_clear(void)
+{
+	int cpu;
+
+	for_each_possible_cpu(cpu)
+		per_cpu(balloon_scratch_page, cpu) = NULL;
+
+	return 0;
+}
+early_initcall(balloon_clear);
+
 MODULE_LICENSE("GPL");