[Xen-devel] [PATCH V4] mm: Extend memory hotplug API to allow memory hotplug in virtual machines

[Daniel Kiper <dkiper@xxxxxxxxxxxx>]

This patch applies to Linus' git tree, git commit 
98b98d316349e9a028e632629fe813d07fa5afdd
(Merge branch 'drm-core-next' of 
git://git.kernel.org/pub/scm/linux/kernel/git/airlied/drm-2.6)
with a few prerequisite patches available at https://lkml.org/lkml/2011/5/2/296
and https://lkml.org/lkml/2011/5/17/408 (all prerequisite patches were included 
in -mm tree).

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.

Signed-off-by: Daniel Kiper <dkiper@xxxxxxxxxxxx>
Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@xxxxxxxxxx>
---
 include/linux/memory_hotplug.h |   11 +++++-
 mm/memory_hotplug.c            |   68 ++++++++++++++++++++++++++++++++++++++--
 2 files changed, 74 insertions(+), 5 deletions(-)

diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index 8122018..0b8e2a7 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -68,12 +68,19 @@ static inline void zone_seqlock_init(struct zone *zone)
 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);
 #endif /* CONFIG_MEMORY_HOTREMOVE */
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index a807ccb..9d47c39 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -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)
@@ -361,23 +372,74 @@ int __remove_pages(struct zone *zone, unsigned long 
phys_start_pfn,
 }
 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 @@ static int online_pages_range(unsigned long start_pfn, 
unsigned long nr_pages,
        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;
-- 
1.5.6.5

_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-devel