*/
/*
- * This file contains the default values for the opereation of the
+ * This file contains the default values for the operation of the
* Linux VM subsystem. Fine-tuning documentation can be found in
* Documentation/sysctl/vm.txt.
* Started 18.12.91
#include <linux/module.h>
#include <linux/mm_inline.h>
#include <linux/buffer_head.h> /* for try_to_release_page() */
-#include <linux/module.h>
#include <linux/percpu_counter.h>
#include <linux/percpu.h>
#include <linux/cpu.h>
#include <linux/notifier.h>
-#include <linux/init.h>
+#include <linux/backing-dev.h>
+#include <linux/memcontrol.h>
/* How many pages do we try to swap or page in/out together? */
int page_cluster;
+static DEFINE_PER_CPU(struct pagevec, lru_add_pvecs);
+static DEFINE_PER_CPU(struct pagevec, lru_add_active_pvecs);
+static DEFINE_PER_CPU(struct pagevec, lru_rotate_pvecs);
+
+/*
+ * This path almost never happens for VM activity - pages are normally
+ * freed via pagevecs. But it gets used by networking.
+ */
+static void __page_cache_release(struct page *page)
+{
+ if (PageLRU(page)) {
+ unsigned long flags;
+ struct zone *zone = page_zone(page);
+
+ spin_lock_irqsave(&zone->lru_lock, flags);
+ VM_BUG_ON(!PageLRU(page));
+ __ClearPageLRU(page);
+ del_page_from_lru(zone, page);
+ spin_unlock_irqrestore(&zone->lru_lock, flags);
+ }
+ free_hot_page(page);
+}
+
static void put_compound_page(struct page *page)
{
- page = (struct page *)page_private(page);
+ page = compound_head(page);
if (put_page_testzero(page)) {
- void (*dtor)(struct page *page);
+ compound_page_dtor *dtor;
- dtor = (void (*)(struct page *))page[1].lru.next;
+ dtor = get_compound_page_dtor(page);
(*dtor)(page);
}
}
}
EXPORT_SYMBOL(put_page);
+/**
+ * put_pages_list() - release a list of pages
+ * @pages: list of pages threaded on page->lru
+ *
+ * Release a list of pages which are strung together on page.lru. Currently
+ * used by read_cache_pages() and related error recovery code.
+ */
+void put_pages_list(struct list_head *pages)
+{
+ while (!list_empty(pages)) {
+ struct page *victim;
+
+ victim = list_entry(pages->prev, struct page, lru);
+ list_del(&victim->lru);
+ page_cache_release(victim);
+ }
+}
+EXPORT_SYMBOL(put_pages_list);
+
+/*
+ * pagevec_move_tail() must be called with IRQ disabled.
+ * Otherwise this may cause nasty races.
+ */
+static void pagevec_move_tail(struct pagevec *pvec)
+{
+ int i;
+ int pgmoved = 0;
+ struct zone *zone = NULL;
+
+ for (i = 0; i < pagevec_count(pvec); i++) {
+ struct page *page = pvec->pages[i];
+ struct zone *pagezone = page_zone(page);
+
+ if (pagezone != zone) {
+ if (zone)
+ spin_unlock(&zone->lru_lock);
+ zone = pagezone;
+ spin_lock(&zone->lru_lock);
+ }
+ if (PageLRU(page) && !PageActive(page)) {
+ list_move_tail(&page->lru, &zone->inactive_list);
+ pgmoved++;
+ }
+ }
+ if (zone)
+ spin_unlock(&zone->lru_lock);
+ __count_vm_events(PGROTATED, pgmoved);
+ release_pages(pvec->pages, pvec->nr, pvec->cold);
+ pagevec_reinit(pvec);
+}
+
/*
* Writeback is about to end against a page which has been marked for immediate
* reclaim. If it still appears to be reclaimable, move it to the tail of the
- * inactive list. The page still has PageWriteback set, which will pin it.
- *
- * We don't expect many pages to come through here, so don't bother batching
- * things up.
- *
- * To avoid placing the page at the tail of the LRU while PG_writeback is still
- * set, this function will clear PG_writeback before performing the page
- * motion. Do that inside the lru lock because once PG_writeback is cleared
- * we may not touch the page.
- *
- * Returns zero if it cleared PG_writeback.
+ * inactive list.
*/
-int rotate_reclaimable_page(struct page *page)
+void rotate_reclaimable_page(struct page *page)
{
- struct zone *zone;
- unsigned long flags;
-
- if (PageLocked(page))
- return 1;
- if (PageDirty(page))
- return 1;
- if (PageActive(page))
- return 1;
- if (!PageLRU(page))
- return 1;
-
- zone = page_zone(page);
- spin_lock_irqsave(&zone->lru_lock, flags);
- if (PageLRU(page) && !PageActive(page)) {
- list_del(&page->lru);
- list_add_tail(&page->lru, &zone->inactive_list);
- inc_page_state(pgrotated);
+ if (!PageLocked(page) && !PageDirty(page) && !PageActive(page) &&
+ PageLRU(page)) {
+ struct pagevec *pvec;
+ unsigned long flags;
+
+ page_cache_get(page);
+ local_irq_save(flags);
+ pvec = &__get_cpu_var(lru_rotate_pvecs);
+ if (!pagevec_add(pvec, page))
+ pagevec_move_tail(pvec);
+ local_irq_restore(flags);
}
- if (!test_clear_page_writeback(page))
- BUG();
- spin_unlock_irqrestore(&zone->lru_lock, flags);
- return 0;
}
/*
* FIXME: speed this up?
*/
-void fastcall activate_page(struct page *page)
+void activate_page(struct page *page)
{
struct zone *zone = page_zone(page);
del_page_from_inactive_list(zone, page);
SetPageActive(page);
add_page_to_active_list(zone, page);
- inc_page_state(pgactivate);
+ __count_vm_event(PGACTIVATE);
+ mem_cgroup_move_lists(page, true);
}
spin_unlock_irq(&zone->lru_lock);
}
* inactive,referenced -> active,unreferenced
* active,unreferenced -> active,referenced
*/
-void fastcall mark_page_accessed(struct page *page)
+void mark_page_accessed(struct page *page)
{
if (!PageActive(page) && PageReferenced(page) && PageLRU(page)) {
activate_page(page);
* lru_cache_add: add a page to the page lists
* @page: the page to add
*/
-static DEFINE_PER_CPU(struct pagevec, lru_add_pvecs) = { 0, };
-static DEFINE_PER_CPU(struct pagevec, lru_add_active_pvecs) = { 0, };
-
-void fastcall lru_cache_add(struct page *page)
+void lru_cache_add(struct page *page)
{
struct pagevec *pvec = &get_cpu_var(lru_add_pvecs);
put_cpu_var(lru_add_pvecs);
}
-void fastcall lru_cache_add_active(struct page *page)
+void lru_cache_add_active(struct page *page)
{
struct pagevec *pvec = &get_cpu_var(lru_add_active_pvecs);
put_cpu_var(lru_add_active_pvecs);
}
-static void __lru_add_drain(int cpu)
+/*
+ * Drain pages out of the cpu's pagevecs.
+ * Either "cpu" is the current CPU, and preemption has already been
+ * disabled; or "cpu" is being hot-unplugged, and is already dead.
+ */
+static void drain_cpu_pagevecs(int cpu)
{
- struct pagevec *pvec = &per_cpu(lru_add_pvecs, cpu);
+ struct pagevec *pvec;
- /* CPU is dead, so no locking needed. */
+ pvec = &per_cpu(lru_add_pvecs, cpu);
if (pagevec_count(pvec))
__pagevec_lru_add(pvec);
+
pvec = &per_cpu(lru_add_active_pvecs, cpu);
if (pagevec_count(pvec))
__pagevec_lru_add_active(pvec);
+
+ pvec = &per_cpu(lru_rotate_pvecs, cpu);
+ if (pagevec_count(pvec)) {
+ unsigned long flags;
+
+ /* No harm done if a racing interrupt already did this */
+ local_irq_save(flags);
+ pagevec_move_tail(pvec);
+ local_irq_restore(flags);
+ }
}
void lru_add_drain(void)
{
- __lru_add_drain(get_cpu());
+ drain_cpu_pagevecs(get_cpu());
put_cpu();
}
#ifdef CONFIG_NUMA
-static void lru_add_drain_per_cpu(void *dummy)
+static void lru_add_drain_per_cpu(struct work_struct *dummy)
{
lru_add_drain();
}
*/
int lru_add_drain_all(void)
{
- return schedule_on_each_cpu(lru_add_drain_per_cpu, NULL);
+ return schedule_on_each_cpu(lru_add_drain_per_cpu);
}
#else
#endif
/*
- * This path almost never happens for VM activity - pages are normally
- * freed via pagevecs. But it gets used by networking.
- */
-void fastcall __page_cache_release(struct page *page)
-{
- unsigned long flags;
- struct zone *zone = page_zone(page);
-
- spin_lock_irqsave(&zone->lru_lock, flags);
- if (TestClearPageLRU(page))
- del_page_from_lru(zone, page);
- if (page_count(page) != 0)
- page = NULL;
- spin_unlock_irqrestore(&zone->lru_lock, flags);
- if (page)
- free_hot_page(page);
-}
-
-EXPORT_SYMBOL(__page_cache_release);
-
-/*
* Batched page_cache_release(). Decrement the reference count on all the
* passed pages. If it fell to zero then remove the page from the LRU and
* free it.
* Avoid taking zone->lru_lock if possible, but if it is taken, retain it
* for the remainder of the operation.
*
- * The locking in this function is against shrink_cache(): we recheck the
- * page count inside the lock to see whether shrink_cache grabbed the page
- * via the LRU. If it did, give up: shrink_cache will free it.
+ * The locking in this function is against shrink_inactive_list(): we recheck
+ * the page count inside the lock to see whether shrink_inactive_list()
+ * grabbed the page via the LRU. If it did, give up: shrink_inactive_list()
+ * will free it.
*/
void release_pages(struct page **pages, int nr, int cold)
{
int i;
struct pagevec pages_to_free;
struct zone *zone = NULL;
+ unsigned long uninitialized_var(flags);
pagevec_init(&pages_to_free, cold);
for (i = 0; i < nr; i++) {
struct page *page = pages[i];
- struct zone *pagezone;
if (unlikely(PageCompound(page))) {
if (zone) {
- spin_unlock_irq(&zone->lru_lock);
+ spin_unlock_irqrestore(&zone->lru_lock, flags);
zone = NULL;
}
put_compound_page(page);
if (!put_page_testzero(page))
continue;
- pagezone = page_zone(page);
- if (pagezone != zone) {
- if (zone)
- spin_unlock_irq(&zone->lru_lock);
- zone = pagezone;
- spin_lock_irq(&zone->lru_lock);
- }
- if (TestClearPageLRU(page))
- del_page_from_lru(zone, page);
- if (page_count(page) == 0) {
- if (!pagevec_add(&pages_to_free, page)) {
- spin_unlock_irq(&zone->lru_lock);
- __pagevec_free(&pages_to_free);
- pagevec_reinit(&pages_to_free);
- zone = NULL; /* No lock is held */
+ if (PageLRU(page)) {
+ struct zone *pagezone = page_zone(page);
+ if (pagezone != zone) {
+ if (zone)
+ spin_unlock_irqrestore(&zone->lru_lock,
+ flags);
+ zone = pagezone;
+ spin_lock_irqsave(&zone->lru_lock, flags);
}
+ VM_BUG_ON(!PageLRU(page));
+ __ClearPageLRU(page);
+ del_page_from_lru(zone, page);
}
+
+ if (!pagevec_add(&pages_to_free, page)) {
+ if (zone) {
+ spin_unlock_irqrestore(&zone->lru_lock, flags);
+ zone = NULL;
+ }
+ __pagevec_free(&pages_to_free);
+ pagevec_reinit(&pages_to_free);
+ }
}
if (zone)
- spin_unlock_irq(&zone->lru_lock);
+ spin_unlock_irqrestore(&zone->lru_lock, flags);
pagevec_free(&pages_to_free);
}
for (i = 0; i < pagevec_count(pvec); i++) {
struct page *page = pvec->pages[i];
- BUG_ON(PageLRU(page));
+ VM_BUG_ON(PageLRU(page));
if (put_page_testzero(page))
pagevec_add(&pages_to_free, page);
}
zone = pagezone;
spin_lock_irq(&zone->lru_lock);
}
- if (TestSetPageLRU(page))
- BUG();
+ VM_BUG_ON(PageLRU(page));
+ SetPageLRU(page);
add_page_to_inactive_list(zone, page);
}
if (zone)
zone = pagezone;
spin_lock_irq(&zone->lru_lock);
}
- if (TestSetPageLRU(page))
- BUG();
- if (TestSetPageActive(page))
- BUG();
+ VM_BUG_ON(PageLRU(page));
+ SetPageLRU(page);
+ VM_BUG_ON(PageActive(page));
+ SetPageActive(page);
add_page_to_active_list(zone, page);
}
if (zone)
for (i = 0; i < pagevec_count(pvec); i++) {
struct page *page = pvec->pages[i];
- if (PagePrivate(page) && !TestSetPageLocked(page)) {
- try_to_release_page(page, 0);
+ if (PagePrivate(page) && trylock_page(page)) {
+ if (PagePrivate(page))
+ try_to_release_page(page, 0);
unlock_page(page);
}
}
*/
#define ACCT_THRESHOLD max(16, NR_CPUS * 2)
-static DEFINE_PER_CPU(long, committed_space) = 0;
+static DEFINE_PER_CPU(long, committed_space);
void vm_acct_memory(long pages)
{
local = &__get_cpu_var(committed_space);
*local += pages;
if (*local > ACCT_THRESHOLD || *local < -ACCT_THRESHOLD) {
- atomic_add(*local, &vm_committed_space);
+ atomic_long_add(*local, &vm_committed_space);
*local = 0;
}
preempt_enable();
long *committed;
committed = &per_cpu(committed_space, (long)hcpu);
- if (action == CPU_DEAD) {
- atomic_add(*committed, &vm_committed_space);
+ if (action == CPU_DEAD || action == CPU_DEAD_FROZEN) {
+ atomic_long_add(*committed, &vm_committed_space);
*committed = 0;
- __lru_add_drain((long)hcpu);
+ drain_cpu_pagevecs((long)hcpu);
}
return NOTIFY_OK;
}
#endif /* CONFIG_HOTPLUG_CPU */
#endif /* CONFIG_SMP */
-#ifdef CONFIG_SMP
-void percpu_counter_mod(struct percpu_counter *fbc, long amount)
-{
- long count;
- long *pcount;
- int cpu = get_cpu();
-
- pcount = per_cpu_ptr(fbc->counters, cpu);
- count = *pcount + amount;
- if (count >= FBC_BATCH || count <= -FBC_BATCH) {
- spin_lock(&fbc->lock);
- fbc->count += count;
- spin_unlock(&fbc->lock);
- count = 0;
- }
- *pcount = count;
- put_cpu();
-}
-EXPORT_SYMBOL(percpu_counter_mod);
-#endif
-
/*
* Perform any setup for the swap system
*/
{
unsigned long megs = num_physpages >> (20 - PAGE_SHIFT);
+#ifdef CONFIG_SWAP
+ bdi_init(swapper_space.backing_dev_info);
+#endif
+
/* Use a smaller cluster for small-memory machines */
if (megs < 16)
page_cluster = 2;
* Right now other parts of the system means that we
* _really_ don't want to cluster much more
*/
+#ifdef CONFIG_HOTPLUG_CPU
hotcpu_notifier(cpu_swap_callback, 0);
+#endif
}