#include <linux/pagemap.h>
#include <linux/bootmem.h>
#include <linux/compiler.h>
-#include <linux/module.h>
+#include <linux/export.h>
#include <linux/pagevec.h>
#include <linux/writeback.h>
#include <linux/slab.h>
#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)
+{
+ mutex_lock(&mem_hotplug_mutex);
+
+ /* for exclusive hibernation if CONFIG_HIBERNATION=y */
+ lock_system_sleep();
+}
+
+void unlock_memory_hotplug(void)
+{
+ unlock_system_sleep();
+ mutex_unlock(&mem_hotplug_mutex);
+}
+
+
/* add this memory to iomem resource */
static struct resource *register_memory_resource(u64 start, u64 size)
{
#ifdef CONFIG_MEMORY_HOTPLUG_SPARSE
#ifndef CONFIG_SPARSEMEM_VMEMMAP
-static void get_page_bootmem(unsigned long info, struct page *page, int type)
+static void get_page_bootmem(unsigned long info, struct page *page,
+ unsigned long type)
{
- atomic_set(&page->_mapcount, type);
+ page->lru.next = (struct list_head *) type;
SetPagePrivate(page);
set_page_private(page, info);
atomic_inc(&page->_count);
* so use __ref to tell modpost not to generate a warning */
void __ref put_page_bootmem(struct page *page)
{
- int type;
+ unsigned long type;
- type = atomic_read(&page->_mapcount);
- BUG_ON(type >= -1);
+ type = (unsigned long) page->lru.next;
+ BUG_ON(type < MEMORY_HOTPLUG_MIN_BOOTMEM_TYPE ||
+ type > MEMORY_HOTPLUG_MAX_BOOTMEM_TYPE);
if (atomic_dec_return(&page->_count) == 1) {
ClearPagePrivate(page);
set_page_private(page, 0);
- reset_page_mapcount(page);
+ INIT_LIST_HEAD(&page->lru);
__free_pages_bootmem(page, 0);
}
}
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);
-#ifdef CONFIG_FLATMEM
- max_mapnr = max(page_to_pfn(page), max_mapnr);
-#endif
-
+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)
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;
}
-int online_pages(unsigned long pfn, unsigned long nr_pages)
+int __ref online_pages(unsigned long pfn, unsigned long nr_pages)
{
unsigned long onlined_pages = 0;
struct zone *zone;
int ret;
struct memory_notify arg;
+ lock_memory_hotplug();
arg.start_pfn = pfn;
arg.nr_pages = nr_pages;
arg.status_change_nid = -1;
ret = notifier_to_errno(ret);
if (ret) {
memory_notify(MEM_CANCEL_ONLINE, &arg);
+ unlock_memory_hotplug();
return ret;
}
/*
printk(KERN_DEBUG "online_pages %lx at %lx failed\n",
nr_pages, pfn);
memory_notify(MEM_CANCEL_ONLINE, &arg);
+ unlock_memory_hotplug();
return ret;
}
zone_pcp_update(zone);
mutex_unlock(&zonelists_mutex);
- setup_per_zone_wmarks();
- calculate_zone_inactive_ratio(zone);
+
+ init_per_zone_wmark_min();
+
if (onlined_pages) {
kswapd_run(zone_to_nid(zone));
node_set_state(zone_to_nid(zone), N_HIGH_MEMORY);
if (onlined_pages)
memory_notify(MEM_ONLINE, &arg);
+ unlock_memory_hotplug();
return 0;
}
/* init node's zones as empty zones, we don't have any present pages.*/
free_area_init_node(nid, zones_size, start_pfn, zholes_size);
+ /*
+ * The node we allocated has no zone fallback lists. For avoiding
+ * to access not-initialized zonelist, build here.
+ */
+ mutex_lock(&zonelists_mutex);
+ build_all_zonelists(NULL);
+ mutex_unlock(&zonelists_mutex);
+
return pgdat;
}
pg_data_t *pgdat;
int ret;
- lock_system_sleep();
+ lock_memory_hotplug();
pgdat = hotadd_new_pgdat(nid, 0);
- if (pgdat) {
+ if (!pgdat) {
ret = -ENOMEM;
goto out;
}
BUG_ON(ret);
out:
- unlock_system_sleep();
+ unlock_memory_hotplug();
return ret;
}
struct resource *res;
int ret;
- lock_system_sleep();
+ lock_memory_hotplug();
res = register_memory_resource(start, size);
ret = -EEXIST;
release_memory_resource(res);
out:
- unlock_system_sleep();
+ unlock_memory_hotplug();
return ret;
}
EXPORT_SYMBOL_GPL(add_memory);
/* Return the start of the next active pageblock after a given page */
static struct page *next_active_pageblock(struct page *page)
{
- int pageblocks_stride;
-
/* Ensure the starting page is pageblock-aligned */
BUG_ON(page_to_pfn(page) & (pageblock_nr_pages - 1));
- /* Move forward by at least 1 * pageblock_nr_pages */
- pageblocks_stride = 1;
-
/* If the entire pageblock is free, move to the end of free page */
- if (pageblock_free(page))
- pageblocks_stride += page_order(page) - pageblock_order;
+ if (pageblock_free(page)) {
+ int order;
+ /* be careful. we don't have locks, page_order can be changed.*/
+ order = page_order(page);
+ if ((order < MAX_ORDER) && (order >= pageblock_order))
+ return page + (1 << order);
+ }
- return page + (pageblocks_stride * pageblock_nr_pages);
+ return page + pageblock_nr_pages;
}
/* Checks if this range of memory is likely to be hot-removable. */
int is_mem_section_removable(unsigned long start_pfn, unsigned long nr_pages)
{
- int type;
struct page *page = pfn_to_page(start_pfn);
struct page *end_page = page + nr_pages;
/* Check the starting page of each pageblock within the range */
for (; page < end_page; page = next_active_pageblock(page)) {
- type = get_pageblock_migratetype(page);
-
- /*
- * A pageblock containing MOVABLE or free pages is considered
- * removable
- */
- if (type != MIGRATE_MOVABLE && !pageblock_free(page))
- return 0;
-
- /*
- * A pageblock starting with a PageReserved page is not
- * considered removable.
- */
- if (PageReserved(page))
+ if (!is_pageblock_removable_nolock(page))
return 0;
+ cond_resched();
}
/* All pageblocks in the memory block are likely to be hot-removable */
* Scanning pfn is much easier than scanning lru list.
* Scan pfn from start to end and Find LRU page.
*/
-int scan_lru_pages(unsigned long start, unsigned long end)
+static unsigned long scan_lru_pages(unsigned long start, unsigned long end)
{
unsigned long pfn;
struct page *page;
if (!pfn_valid(pfn))
continue;
page = pfn_to_page(pfn);
- if (!page_count(page))
+ if (!get_page_unless_zero(page))
continue;
/*
* We can skip free pages. And we can only deal with pages on
*/
ret = isolate_lru_page(page);
if (!ret) { /* Success */
+ put_page(page);
list_add_tail(&page->lru, &source);
move_pages--;
inc_zone_page_state(page, NR_ISOLATED_ANON +
page_is_file_cache(page));
} else {
- /* Becasue we don't have big zone->lock. we should
- check this again here. */
- if (page_count(page))
- not_managed++;
#ifdef CONFIG_DEBUG_VM
printk(KERN_ALERT "removing pfn %lx from LRU failed\n",
pfn);
dump_page(page);
#endif
+ put_page(page);
+ /* Because we don't have big zone->lock. we should
+ check this again here. */
+ if (page_count(page)) {
+ not_managed++;
+ ret = -EBUSY;
+ break;
+ }
}
}
- ret = -EBUSY;
- if (not_managed) {
- if (!list_empty(&source))
+ if (!list_empty(&source)) {
+ if (not_managed) {
+ putback_lru_pages(&source);
+ goto out;
+ }
+ /* this function returns # of failed pages */
+ ret = migrate_pages(&source, hotremove_migrate_alloc, 0,
+ true, MIGRATE_SYNC);
+ if (ret)
putback_lru_pages(&source);
- goto out;
}
- ret = 0;
- if (list_empty(&source))
- goto out;
- /* this function returns # of failed pages */
- ret = migrate_pages(&source, hotremove_migrate_alloc, 0, 1);
-
out:
return ret;
}
return offlined;
}
-static int offline_pages(unsigned long start_pfn,
+static int __ref offline_pages(unsigned long start_pfn,
unsigned long end_pfn, unsigned long timeout)
{
unsigned long pfn, nr_pages, expire;
if (!test_pages_in_a_zone(start_pfn, end_pfn))
return -EINVAL;
- lock_system_sleep();
+ lock_memory_hotplug();
zone = page_zone(pfn_to_page(start_pfn));
node = zone_to_nid(zone);
ret = 0;
if (drain) {
lru_add_drain_all();
- flush_scheduled_work();
cond_resched();
drain_all_pages();
}
}
/* drain all zone's lru pagevec, this is asyncronous... */
lru_add_drain_all();
- flush_scheduled_work();
yield();
/* drain pcp pages , this is synchrouns. */
drain_all_pages();
zone->zone_pgdat->node_present_pages -= offlined_pages;
totalram_pages -= offlined_pages;
- setup_per_zone_wmarks();
- calculate_zone_inactive_ratio(zone);
+ init_per_zone_wmark_min();
+
if (!node_present_pages(node)) {
node_clear_state(node, N_HIGH_MEMORY);
kswapd_stop(node);
writeback_set_ratelimit();
memory_notify(MEM_OFFLINE, &arg);
- unlock_system_sleep();
+ unlock_memory_hotplug();
return 0;
failed_removal:
undo_isolate_page_range(start_pfn, end_pfn);
out:
- unlock_system_sleep();
+ unlock_memory_hotplug();
return ret;
}
projects / linux-flexiantxendom0-3.2.10.git / blobdiff