#include <linux/highmem.h>
#include <linux/vmalloc.h>
#include <linux/ioport.h>
-#include <linux/cpuset.h>
#include <linux/delay.h>
#include <linux/migrate.h>
#include <linux/page-isolation.h>
+#include <linux/pfn.h>
+#include <linux/suspend.h>
+#include <linux/mm_inline.h>
+#include <linux/firmware-map.h>
#include <asm/tlbflush.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 magic)
+static void get_page_bootmem(unsigned long info, struct page *page,
+ unsigned long type)
{
- atomic_set(&page->_mapcount, magic);
+ page->lru.next = (struct list_head *) type;
SetPagePrivate(page);
set_page_private(page, info);
atomic_inc(&page->_count);
}
-void put_page_bootmem(struct page *page)
+/* reference to __meminit __free_pages_bootmem is valid
+ * so use __ref to tell modpost not to generate a warning */
+void __ref put_page_bootmem(struct page *page)
{
- int magic;
+ unsigned long type;
- magic = atomic_read(&page->_mapcount);
- BUG_ON(magic >= -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);
}
mapsize = PAGE_ALIGN(usemap_size()) >> PAGE_SHIFT;
for (i = 0; i < mapsize; i++, page++)
- get_page_bootmem(section_nr, page, MIX_INFO);
+ get_page_bootmem(section_nr, page, MIX_SECTION_INFO);
}
pgdat->node_start_pfn;
}
-static int __add_zone(struct zone *zone, unsigned long phys_start_pfn)
+static int __meminit __add_zone(struct zone *zone, unsigned long phys_start_pfn)
{
struct pglist_data *pgdat = zone->zone_pgdat;
int nr_pages = PAGES_PER_SECTION;
return 0;
}
-static int __add_section(struct zone *zone, unsigned long phys_start_pfn)
+static int __meminit __add_section(int nid, struct zone *zone,
+ unsigned long phys_start_pfn)
{
int nr_pages = PAGES_PER_SECTION;
int ret;
if (ret < 0)
return ret;
- return register_new_memory(__pfn_to_section(phys_start_pfn));
+ return register_new_memory(nid, __pfn_to_section(phys_start_pfn));
}
#ifdef CONFIG_SPARSEMEM_VMEMMAP
* call this function after deciding the zone to which to
* add the new pages.
*/
-int __add_pages(struct zone *zone, unsigned long phys_start_pfn,
- unsigned long nr_pages)
+int __ref __add_pages(int nid, struct zone *zone, unsigned long phys_start_pfn,
+ unsigned long nr_pages)
{
unsigned long i;
int err = 0;
end_sec = pfn_to_section_nr(phys_start_pfn + nr_pages - 1);
for (i = start_sec; i <= end_sec; i++) {
- err = __add_section(zone, i << PFN_SECTION_SHIFT);
+ err = __add_section(nid, zone, i << PFN_SECTION_SHIFT);
/*
* EEXIST is finally dealt with by ioresource collision
BUG_ON(phys_start_pfn & ~PAGE_SECTION_MASK);
BUG_ON(nr_pages % PAGES_PER_SECTION);
- release_mem_region(phys_start_pfn << PAGE_SHIFT, nr_pages * PAGE_SIZE);
-
sections_to_remove = nr_pages / PAGES_PER_SECTION;
for (i = 0; i < sections_to_remove; i++) {
unsigned long pfn = phys_start_pfn + i*PAGES_PER_SECTION;
+ release_mem_region(pfn << PAGE_SHIFT,
+ PAGES_PER_SECTION << PAGE_SHIFT);
ret = __remove_section(zone, __pfn_to_section(pfn));
if (ret)
break;
}
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);
+
+ 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++;
- num_physpages++;
#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;
}
/*
* This means the page allocator ignores this zone.
* So, zonelist must be updated after online.
*/
+ mutex_lock(&zonelists_mutex);
if (!populated_zone(zone))
need_zonelists_rebuild = 1;
- ret = walk_memory_resource(pfn, nr_pages, &onlined_pages,
+ ret = walk_system_ram_range(pfn, nr_pages, &onlined_pages,
online_pages_range);
if (ret) {
+ mutex_unlock(&zonelists_mutex);
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->present_pages += onlined_pages;
zone->zone_pgdat->node_present_pages += onlined_pages;
+ if (need_zonelists_rebuild)
+ build_all_zonelists(zone);
+ else
+ zone_pcp_update(zone);
+
+ mutex_unlock(&zonelists_mutex);
+
+ init_per_zone_wmark_min();
- setup_per_zone_pages_min();
if (onlined_pages) {
kswapd_run(zone_to_nid(zone));
node_set_state(zone_to_nid(zone), N_HIGH_MEMORY);
}
- if (need_zonelists_rebuild)
- build_all_zonelists();
vm_total_pages = nr_free_pagecache_pages();
+
writeback_set_ratelimit();
if (onlined_pages)
memory_notify(MEM_ONLINE, &arg);
+ unlock_memory_hotplug();
return 0;
}
#endif /* CONFIG_MEMORY_HOTPLUG_SPARSE */
-static pg_data_t *hotadd_new_pgdat(int nid, u64 start)
+/* we are OK calling __meminit stuff here - we have CONFIG_MEMORY_HOTPLUG */
+static pg_data_t __ref *hotadd_new_pgdat(int nid, u64 start)
{
struct pglist_data *pgdat;
unsigned long zones_size[MAX_NR_ZONES] = {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;
}
}
-int add_memory(int nid, u64 start, u64 size)
+/*
+ * called by cpu_up() to online a node without onlined memory.
+ */
+int mem_online_node(int nid)
+{
+ pg_data_t *pgdat;
+ int ret;
+
+ lock_memory_hotplug();
+ pgdat = hotadd_new_pgdat(nid, 0);
+ if (!pgdat) {
+ ret = -ENOMEM;
+ goto out;
+ }
+ node_set_online(nid);
+ ret = register_one_node(nid);
+ BUG_ON(ret);
+
+out:
+ unlock_memory_hotplug();
+ return ret;
+}
+
+/* we are OK calling __meminit stuff here - we have CONFIG_MEMORY_HOTPLUG */
+int __ref add_memory(int nid, u64 start, u64 size)
{
pg_data_t *pgdat = NULL;
int new_pgdat = 0;
struct resource *res;
int ret;
+ lock_memory_hotplug();
+
res = register_memory_resource(start, size);
+ ret = -EEXIST;
if (!res)
- return -EEXIST;
+ goto out;
if (!node_online(nid)) {
pgdat = hotadd_new_pgdat(nid, start);
+ ret = -ENOMEM;
if (!pgdat)
- return -ENOMEM;
+ goto out;
new_pgdat = 1;
}
/* we online node here. we can't roll back from here. */
node_set_online(nid);
- cpuset_track_online_nodes();
-
if (new_pgdat) {
ret = register_one_node(nid);
/*
BUG_ON(ret);
}
- return ret;
+ /* create new memmap entry */
+ firmware_map_add_hotplug(start, start + size, "System RAM");
+
+ goto out;
+
error:
/* rollback pgdat allocation and others */
if (new_pgdat)
if (res)
release_memory_resource(res);
+out:
+ unlock_memory_hotplug();
return ret;
}
EXPORT_SYMBOL_GPL(add_memory);
#ifdef CONFIG_MEMORY_HOTREMOVE
+/*
+ * A free page on the buddy free lists (not the per-cpu lists) has PageBuddy
+ * set and the size of the free page is given by page_order(). Using this,
+ * the function determines if the pageblock contains only free pages.
+ * Due to buddy contraints, a free page at least the size of a pageblock will
+ * be located at the start of the pageblock
+ */
+static inline int pageblock_free(struct page *page)
+{
+ return PageBuddy(page) && page_order(page) >= pageblock_order;
+}
+
+/* Return the start of the next active pageblock after a given page */
+static struct page *next_active_pageblock(struct page *page)
+{
+ /* Ensure the starting page is pageblock-aligned */
+ BUG_ON(page_to_pfn(page) & (pageblock_nr_pages - 1));
+
+ /* If the entire pageblock is free, move to the end of free page */
+ 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 + 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)
+{
+ 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)) {
+ if (!is_pageblock_removable_nolock(page))
+ return 0;
+ cond_resched();
+ }
+
+ /* All pageblocks in the memory block are likely to be hot-removable */
+ return 1;
+}
+
/*
* Confirm all pages in a range [start, end) is belongs to the same zone.
*/
* 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;
}
static struct page *
-hotremove_migrate_alloc(struct page *page,
- unsigned long private,
- int **x)
+hotremove_migrate_alloc(struct page *page, unsigned long private, int **x)
{
- /* This should be improoooooved!! */
- return alloc_page(GFP_HIGHUSER_PAGECACHE);
+ /* This should be improooooved!! */
+ return alloc_page(GFP_HIGHUSER_MOVABLE);
}
-
#define NR_OFFLINE_AT_ONCE_PAGES (256)
static int
do_migrate_range(unsigned long start_pfn, unsigned long end_pfn)
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
* LRU.
*/
- ret = isolate_lru_page(page, &source);
+ 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_INFO "removing from LRU failed"
- " %lx/%d/%lx\n",
- pfn, page_count(page), page->flags);
+ 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, true);
+ 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);
-
out:
return ret;
}
static void
offline_isolated_pages(unsigned long start_pfn, unsigned long end_pfn)
{
- walk_memory_resource(start_pfn, end_pfn - start_pfn, NULL,
+ walk_system_ram_range(start_pfn, end_pfn - start_pfn, NULL,
offline_isolated_pages_cb);
}
long offlined = 0;
int ret;
- ret = walk_memory_resource(start_pfn, end_pfn - start_pfn, &offlined,
+ ret = walk_system_ram_range(start_pfn, end_pfn - start_pfn, &offlined,
check_pages_isolated_cb);
if (ret < 0)
offlined = (long)ret;
return offlined;
}
-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_memory_hotplug();
+
zone = page_zone(pfn_to_page(start_pfn));
node = zone_to_nid(zone);
nr_pages = end_pfn - start_pfn;
/* set above range as isolated */
ret = start_isolate_page_range(start_pfn, end_pfn);
if (ret)
- return ret;
+ goto out;
arg.start_pfn = start_pfn;
arg.nr_pages = nr_pages;
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->present_pages -= offlined_pages;
zone->zone_pgdat->node_present_pages -= offlined_pages;
totalram_pages -= offlined_pages;
- num_physpages -= offlined_pages;
+
+ init_per_zone_wmark_min();
+
+ if (!node_present_pages(node)) {
+ node_clear_state(node, N_HIGH_MEMORY);
+ kswapd_stop(node);
+ }
vm_total_pages = nr_free_pagecache_pages();
writeback_set_ratelimit();
memory_notify(MEM_OFFLINE, &arg);
+ unlock_memory_hotplug();
return 0;
failed_removal:
/* pushback to free area */
undo_isolate_page_range(start_pfn, end_pfn);
+out:
+ unlock_memory_hotplug();
return ret;
}
+
+int remove_memory(u64 start, u64 size)
+{
+ unsigned long start_pfn, end_pfn;
+
+ start_pfn = PFN_DOWN(start);
+ end_pfn = start_pfn + PFN_DOWN(size);
+ return offline_pages(start_pfn, end_pfn, 120 * HZ);
+}
#else
int remove_memory(u64 start, u64 size)
{
return -EINVAL;
}
-EXPORT_SYMBOL_GPL(remove_memory);
#endif /* CONFIG_MEMORY_HOTREMOVE */
+EXPORT_SYMBOL_GPL(remove_memory);