mm: extend memory hotplug API to allow memory hotplug in virtual machines

This patch contains online_page_callback and apropriate functions for registering/unregistering online page callbacks. It allows to do some machine specific tasks during online page stage which is required to implement memory hotplug in virtual machines. Currently this patch is required by latest memory hotplug support for Xen balloon driver patch which will be posted soon. Additionally, originial online_page() function was splited into following functions doing "atomic" operations: - __online_page_set_limits() - set new limits for memory management code, - __online_page_increment_counters() - increment totalram_pages and totalhigh_pages, - __online_page_free() - free page to allocator. It was done to: - not duplicate existing code, - ease hotplug code devolpment by usage of well defined interface, - avoid stupid bugs which are unavoidable when the same code (by design) is developed in many places. [akpm@linux-foundation.org: use explicit indirect-call syntax] Signed-off-by: Daniel Kiper <dkiper@net-space.pl> Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Ian Campbell <ian.campbell@citrix.com> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

mm: extend memory hotplug API to allow memory hotplug in virtual machines
This patch contains online_page_callback and apropriate functions for registering/unregistering online page callbacks. It allows to do some machine specific tasks during online page stage which is required to implement memory hotplug in virtual machines. Currently this patch is required by latest memory hotplug support for Xen balloon driver patch which will be posted soon. Additionally, originial online_page() function was splited into following functions doing "atomic" operations: - __online_page_set_limits() - set new limits for memory management code, - __online_page_increment_counters() - increment totalram_pages and totalhigh_pages, - __online_page_free() - free page to allocator. It was done to: - not duplicate existing code, - ease hotplug code devolpment by usage of well defined interface, - avoid stupid bugs which are unavoidable when the same code (by design) is developed in many places. [akpm@linux-foundation.org: use explicit indirect-call syntax] Signed-off-by: Daniel Kiper <dkiper@net-space.pl> Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Ian Campbell <ian.campbell@citrix.com> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Daniel Kiper · Linus Torvalds
1 parent ef22f6a70c
Showing 2 changed files with 74 additions and 5 deletions Side-by-side Diff
include/linux/memory_hotplug.h
mm/memory_hotplug.c
@@ -68,11 +68,18 @@
 extern int zone_grow_free_lists(struct zone *zone, unsigned long new_nr_pages);
 extern int zone_grow_waitqueues(struct zone *zone, unsigned long nr_pages);
 extern int add_one_highpage(struct page *page, int pfn, int bad_ppro);
-/* need some defines for these for archs that don't support it */
-extern void online_page(struct page *page);
 /* VM interface that may be used by firmware interface */
 extern int online_pages(unsigned long, unsigned long);
 extern void __offline_isolated_pages(unsigned long, unsigned long);
+
+typedef void (*online_page_callback_t)(struct page *page);
+
+extern int set_online_page_callback(online_page_callback_t callback);
+extern int restore_online_page_callback(online_page_callback_t callback);
+
+extern void __online_page_set_limits(struct page *page);
+extern void __online_page_increment_counters(struct page *page);
+extern void __online_page_free(struct page *page);
  
 #ifdef CONFIG_MEMORY_HOTREMOVE
 extern bool is_pageblock_removable_nolock(struct page *page);
@@ -34,6 +34,17 @@
  
 #include "internal.h"
  
+/*
+ * online_page_callback contains pointer to current page onlining function.
+ * Initially it is generic_online_page(). If it is required it could be
+ * changed by calling set_online_page_callback() for callback registration
+ * and restore_online_page_callback() for generic callback restore.
+ */
+
+static void generic_online_page(struct page *page);
+
+static online_page_callback_t online_page_callback = generic_online_page;
+
 DEFINE_MUTEX(mem_hotplug_mutex);
  
 void lock_memory_hotplug(void)
  
  
  
  
  
  
  
  
@@ -361,24 +372,75 @@
 }
 EXPORT_SYMBOL_GPL(__remove_pages);
  
-void online_page(struct page *page)
+int set_online_page_callback(online_page_callback_t callback)
 {
+	int rc = -EINVAL;
+
+	lock_memory_hotplug();
+
+	if (online_page_callback == generic_online_page) {
+		online_page_callback = callback;
+		rc = 0;
+	}
+
+	unlock_memory_hotplug();
+
+	return rc;
+}
+EXPORT_SYMBOL_GPL(set_online_page_callback);
+
+int restore_online_page_callback(online_page_callback_t callback)
+{
+	int rc = -EINVAL;
+
+	lock_memory_hotplug();
+
+	if (online_page_callback == callback) {
+		online_page_callback = generic_online_page;
+		rc = 0;
+	}
+
+	unlock_memory_hotplug();
+
+	return rc;
+}
+EXPORT_SYMBOL_GPL(restore_online_page_callback);
+
+void __online_page_set_limits(struct page *page)
+{
 	unsigned long pfn = page_to_pfn(page);
  
-	totalram_pages++;
 	if (pfn >= num_physpages)
 		num_physpages = pfn + 1;
+}
+EXPORT_SYMBOL_GPL(__online_page_set_limits);
  
+void __online_page_increment_counters(struct page *page)
+{
+	totalram_pages++;
+
 #ifdef CONFIG_HIGHMEM
 	if (PageHighMem(page))
 		totalhigh_pages++;
 #endif
+}
+EXPORT_SYMBOL_GPL(__online_page_increment_counters);
  
+void __online_page_free(struct page *page)
+{
 	ClearPageReserved(page);
 	init_page_count(page);
 	__free_page(page);
 }
+EXPORT_SYMBOL_GPL(__online_page_free);
  
+static void generic_online_page(struct page *page)
+{
+	__online_page_set_limits(page);
+	__online_page_increment_counters(page);
+	__online_page_free(page);
+}
+
 static int online_pages_range(unsigned long start_pfn, unsigned long nr_pages,
 			void *arg)
 {
@@ -388,7 +450,7 @@
 	if (PageReserved(pfn_to_page(start_pfn)))
 		for (i = 0; i < nr_pages; i++) {
 			page = pfn_to_page(start_pfn + i);
-			online_page(page);
+			(*online_page_callback)(page);
 			onlined_pages++;
 		}
 	*(unsigned long *)arg = onlined_pages;
...	...	@@ -68,11 +68,18 @@
68	68	extern int zone_grow_free_lists(struct zone *zone, unsigned long new_nr_pages);
69	69	extern int zone_grow_waitqueues(struct zone *zone, unsigned long nr_pages);
70	70	extern int add_one_highpage(struct page *page, int pfn, int bad_ppro);
71		-/* need some defines for these for archs that don't support it */
72		-extern void online_page(struct page *page);
73	71	/* VM interface that may be used by firmware interface */
74	72	extern int online_pages(unsigned long, unsigned long);
75	73	extern void __offline_isolated_pages(unsigned long, unsigned long);
	74	+
	75	+typedef void (online_page_callback_t)(struct page page);
	76	+
	77	+extern int set_online_page_callback(online_page_callback_t callback);
	78	+extern int restore_online_page_callback(online_page_callback_t callback);
	79	+
	80	+extern void __online_page_set_limits(struct page *page);
	81	+extern void __online_page_increment_counters(struct page *page);
	82	+extern void __online_page_free(struct page *page);
76	83
77	84	#ifdef CONFIG_MEMORY_HOTREMOVE
78	85	extern bool is_pageblock_removable_nolock(struct page *page);
...	...	@@ -34,6 +34,17 @@
34	34
35	35	#include "internal.h"
36	36
	37	+/*
	38	+ * online_page_callback contains pointer to current page onlining function.
	39	+ * Initially it is generic_online_page(). If it is required it could be
	40	+ * changed by calling set_online_page_callback() for callback registration
	41	+ * and restore_online_page_callback() for generic callback restore.
	42	+ */
	43	+
	44	+static void generic_online_page(struct page *page);
	45	+
	46	+static online_page_callback_t online_page_callback = generic_online_page;
	47	+
37	48	DEFINE_MUTEX(mem_hotplug_mutex);
38	49
39	50	void lock_memory_hotplug(void)
40	51
41	52
42	53
43	54
44	55
45	56
46	57
47	58
...	...	@@ -361,24 +372,75 @@
361	372	}
362	373	EXPORT_SYMBOL_GPL(__remove_pages);
363	374
364		-void online_page(struct page *page)
	375	+int set_online_page_callback(online_page_callback_t callback)
365	376	{
	377	+ int rc = -EINVAL;
	378	+
	379	+ lock_memory_hotplug();
	380	+
	381	+ if (online_page_callback == generic_online_page) {
	382	+ online_page_callback = callback;
	383	+ rc = 0;
	384	+ }
	385	+
	386	+ unlock_memory_hotplug();
	387	+
	388	+ return rc;
	389	+}
	390	+EXPORT_SYMBOL_GPL(set_online_page_callback);
	391	+
	392	+int restore_online_page_callback(online_page_callback_t callback)
	393	+{
	394	+ int rc = -EINVAL;
	395	+
	396	+ lock_memory_hotplug();
	397	+
	398	+ if (online_page_callback == callback) {
	399	+ online_page_callback = generic_online_page;
	400	+ rc = 0;
	401	+ }
	402	+
	403	+ unlock_memory_hotplug();
	404	+
	405	+ return rc;
	406	+}
	407	+EXPORT_SYMBOL_GPL(restore_online_page_callback);
	408	+
	409	+void __online_page_set_limits(struct page *page)
	410	+{
366	411	unsigned long pfn = page_to_pfn(page);
367	412
368		- totalram_pages++;
369	413	if (pfn >= num_physpages)
370	414	num_physpages = pfn + 1;
	415	+}
	416	+EXPORT_SYMBOL_GPL(__online_page_set_limits);
371	417
	418	+void __online_page_increment_counters(struct page *page)
	419	+{
	420	+ totalram_pages++;
	421	+
372	422	#ifdef CONFIG_HIGHMEM
373	423	if (PageHighMem(page))
374	424	totalhigh_pages++;
375	425	#endif
	426	+}
	427	+EXPORT_SYMBOL_GPL(__online_page_increment_counters);
376	428
	429	+void __online_page_free(struct page *page)
	430	+{
377	431	ClearPageReserved(page);
378	432	init_page_count(page);
379	433	__free_page(page);
380	434	}
	435	+EXPORT_SYMBOL_GPL(__online_page_free);
381	436
	437	+static void generic_online_page(struct page *page)
	438	+{
	439	+ __online_page_set_limits(page);
	440	+ __online_page_increment_counters(page);
	441	+ __online_page_free(page);
	442	+}
	443	+
382	444	static int online_pages_range(unsigned long start_pfn, unsigned long nr_pages,
383	445	void *arg)
384	446	{
...	...	@@ -388,7 +450,7 @@
388	450	if (PageReserved(pfn_to_page(start_pfn)))
389	451	for (i = 0; i < nr_pages; i++) {
390	452	page = pfn_to_page(start_pfn + i);
391		- online_page(page);
	453	+ (*online_page_callback)(page);
392	454	onlined_pages++;
393	455	}
394	456	(unsigned long )arg = onlined_pages;