linux/mm/swap.c

519 lines
12 KiB
C
Raw Normal View History

/*
* linux/mm/swap.c
*
* Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds
*/
/*
* This file contains the default values for the opereation of the
* Linux VM subsystem. Fine-tuning documentation can be found in
* Documentation/sysctl/vm.txt.
* Started 18.12.91
* Swap aging added 23.2.95, Stephen Tweedie.
* Buffermem limits added 12.3.98, Rik van Riel.
*/
#include <linux/mm.h>
#include <linux/sched.h>
#include <linux/kernel_stat.h>
#include <linux/swap.h>
#include <linux/mman.h>
#include <linux/pagemap.h>
#include <linux/pagevec.h>
#include <linux/init.h>
#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>
/* How many pages do we try to swap or page in/out together? */
int page_cluster;
/*
* This path almost never happens for VM activity - pages are normally
* freed via pagevecs. But it gets used by networking.
*/
static void fastcall __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);
if (put_page_testzero(page)) {
void (*dtor)(struct page *page);
[PATCH] compound page: use page[1].lru If a compound page has its own put_page_testzero destructor (the only current example is free_huge_page), that is noted in page[1].mapping of the compound page. But that's rather a poor place to keep it: functions which call set_page_dirty_lock after get_user_pages (e.g. Infiniband's __ib_umem_release) ought to be checking first, otherwise set_page_dirty is liable to crash on what's not the address of a struct address_space. And now I'm about to make that worse: it turns out that every compound page needs a destructor, so we can no longer rely on hugetlb pages going their own special way, to avoid further problems of page->mapping reuse. For example, not many people know that: on 50% of i386 -Os builds, the first tail page of a compound page purports to be PageAnon (when its destructor has an odd address), which surprises page_add_file_rmap. Keep the compound page destructor in page[1].lru.next instead. And to free up the common pairing of mapping and index, also move compound page order from index to lru.prev. Slab reuses page->lru too: but if we ever need slab to use compound pages, it can easily stack its use above this. (akpm: decoded version of the above: the tail pages of a compound page now have ->mapping==NULL, so there's no need for the set_page_dirty[_lock]() caller to check that they're not compund pages before doing the dirty). Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-02-14 21:52:58 +00:00
dtor = (void (*)(struct page *))page[1].lru.next;
(*dtor)(page);
}
}
void put_page(struct page *page)
{
if (unlikely(PageCompound(page)))
put_compound_page(page);
else if (put_page_testzero(page))
__page_cache_release(page);
}
EXPORT_SYMBOL(put_page);
/**
* put_pages_list(): release a list of pages
*
* Release a list of pages which are strung together on page.lru. Currently
* used by read_cache_pages() and related error recovery code.
*
* @pages: list of pages threaded on page->lru
*/
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);
/*
* 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.
*/
int 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_move_tail(&page->lru, &zone->inactive_list);
[PATCH] Light weight event counters The remaining counters in page_state after the zoned VM counter patches have been applied are all just for show in /proc/vmstat. They have no essential function for the VM. We use a simple increment of per cpu variables. In order to avoid the most severe races we disable preempt. Preempt does not prevent the race between an increment and an interrupt handler incrementing the same statistics counter. However, that race is exceedingly rare, we may only loose one increment or so and there is no requirement (at least not in kernel) that the vm event counters have to be accurate. In the non preempt case this results in a simple increment for each counter. For many architectures this will be reduced by the compiler to a single instruction. This single instruction is atomic for i386 and x86_64. And therefore even the rare race condition in an interrupt is avoided for both architectures in most cases. The patchset also adds an off switch for embedded systems that allows a building of linux kernels without these counters. The implementation of these counters is through inline code that hopefully results in only a single instruction increment instruction being emitted (i386, x86_64) or in the increment being hidden though instruction concurrency (EPIC architectures such as ia64 can get that done). Benefits: - VM event counter operations usually reduce to a single inline instruction on i386 and x86_64. - No interrupt disable, only preempt disable for the preempt case. Preempt disable can also be avoided by moving the counter into a spinlock. - Handling is similar to zoned VM counters. - Simple and easily extendable. - Can be omitted to reduce memory use for embedded use. References: RFC http://marc.theaimsgroup.com/?l=linux-kernel&m=113512330605497&w=2 RFC http://marc.theaimsgroup.com/?l=linux-kernel&m=114988082814934&w=2 local_t http://marc.theaimsgroup.com/?l=linux-kernel&m=114991748606690&w=2 V2 http://marc.theaimsgroup.com/?t=115014808400007&r=1&w=2 V3 http://marc.theaimsgroup.com/?l=linux-kernel&m=115024767022346&w=2 V4 http://marc.theaimsgroup.com/?l=linux-kernel&m=115047968808926&w=2 Signed-off-by: Christoph Lameter <clameter@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-30 08:55:45 +00:00
__count_vm_event(PGROTATED);
}
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)
{
struct zone *zone = page_zone(page);
spin_lock_irq(&zone->lru_lock);
if (PageLRU(page) && !PageActive(page)) {
del_page_from_inactive_list(zone, page);
SetPageActive(page);
add_page_to_active_list(zone, page);
[PATCH] Light weight event counters The remaining counters in page_state after the zoned VM counter patches have been applied are all just for show in /proc/vmstat. They have no essential function for the VM. We use a simple increment of per cpu variables. In order to avoid the most severe races we disable preempt. Preempt does not prevent the race between an increment and an interrupt handler incrementing the same statistics counter. However, that race is exceedingly rare, we may only loose one increment or so and there is no requirement (at least not in kernel) that the vm event counters have to be accurate. In the non preempt case this results in a simple increment for each counter. For many architectures this will be reduced by the compiler to a single instruction. This single instruction is atomic for i386 and x86_64. And therefore even the rare race condition in an interrupt is avoided for both architectures in most cases. The patchset also adds an off switch for embedded systems that allows a building of linux kernels without these counters. The implementation of these counters is through inline code that hopefully results in only a single instruction increment instruction being emitted (i386, x86_64) or in the increment being hidden though instruction concurrency (EPIC architectures such as ia64 can get that done). Benefits: - VM event counter operations usually reduce to a single inline instruction on i386 and x86_64. - No interrupt disable, only preempt disable for the preempt case. Preempt disable can also be avoided by moving the counter into a spinlock. - Handling is similar to zoned VM counters. - Simple and easily extendable. - Can be omitted to reduce memory use for embedded use. References: RFC http://marc.theaimsgroup.com/?l=linux-kernel&m=113512330605497&w=2 RFC http://marc.theaimsgroup.com/?l=linux-kernel&m=114988082814934&w=2 local_t http://marc.theaimsgroup.com/?l=linux-kernel&m=114991748606690&w=2 V2 http://marc.theaimsgroup.com/?t=115014808400007&r=1&w=2 V3 http://marc.theaimsgroup.com/?l=linux-kernel&m=115024767022346&w=2 V4 http://marc.theaimsgroup.com/?l=linux-kernel&m=115047968808926&w=2 Signed-off-by: Christoph Lameter <clameter@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-30 08:55:45 +00:00
__count_vm_event(PGACTIVATE);
}
spin_unlock_irq(&zone->lru_lock);
}
/*
* Mark a page as having seen activity.
*
* inactive,unreferenced -> inactive,referenced
* inactive,referenced -> active,unreferenced
* active,unreferenced -> active,referenced
*/
void fastcall mark_page_accessed(struct page *page)
{
if (!PageActive(page) && PageReferenced(page) && PageLRU(page)) {
activate_page(page);
ClearPageReferenced(page);
} else if (!PageReferenced(page)) {
SetPageReferenced(page);
}
}
EXPORT_SYMBOL(mark_page_accessed);
/**
* 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)
{
struct pagevec *pvec = &get_cpu_var(lru_add_pvecs);
page_cache_get(page);
if (!pagevec_add(pvec, page))
__pagevec_lru_add(pvec);
put_cpu_var(lru_add_pvecs);
}
void fastcall lru_cache_add_active(struct page *page)
{
struct pagevec *pvec = &get_cpu_var(lru_add_active_pvecs);
page_cache_get(page);
if (!pagevec_add(pvec, page))
__pagevec_lru_add_active(pvec);
put_cpu_var(lru_add_active_pvecs);
}
static void __lru_add_drain(int cpu)
{
struct pagevec *pvec = &per_cpu(lru_add_pvecs, cpu);
/* CPU is dead, so no locking needed. */
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);
}
void lru_add_drain(void)
{
__lru_add_drain(get_cpu());
put_cpu();
}
#ifdef CONFIG_NUMA
static void lru_add_drain_per_cpu(void *dummy)
{
lru_add_drain();
}
/*
* Returns 0 for success
*/
int lru_add_drain_all(void)
{
return schedule_on_each_cpu(lru_add_drain_per_cpu, NULL);
}
#else
/*
* Returns 0 for success
*/
int lru_add_drain_all(void)
{
lru_add_drain();
return 0;
}
#endif
/*
* 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.
*/
void release_pages(struct page **pages, int nr, int cold)
{
int i;
struct pagevec pages_to_free;
struct zone *zone = NULL;
pagevec_init(&pages_to_free, cold);
for (i = 0; i < nr; i++) {
struct page *page = pages[i];
if (unlikely(PageCompound(page))) {
if (zone) {
spin_unlock_irq(&zone->lru_lock);
zone = NULL;
}
put_compound_page(page);
continue;
}
2005-10-30 01:16:12 +00:00
if (!put_page_testzero(page))
continue;
if (PageLRU(page)) {
struct zone *pagezone = page_zone(page);
if (pagezone != zone) {
if (zone)
spin_unlock_irq(&zone->lru_lock);
zone = pagezone;
spin_lock_irq(&zone->lru_lock);
}
VM_BUG_ON(!PageLRU(page));
__ClearPageLRU(page);
del_page_from_lru(zone, page);
}
if (!pagevec_add(&pages_to_free, page)) {
if (zone) {
spin_unlock_irq(&zone->lru_lock);
zone = NULL;
}
__pagevec_free(&pages_to_free);
pagevec_reinit(&pages_to_free);
}
}
if (zone)
spin_unlock_irq(&zone->lru_lock);
pagevec_free(&pages_to_free);
}
/*
* The pages which we're about to release may be in the deferred lru-addition
* queues. That would prevent them from really being freed right now. That's
* OK from a correctness point of view but is inefficient - those pages may be
* cache-warm and we want to give them back to the page allocator ASAP.
*
* So __pagevec_release() will drain those queues here. __pagevec_lru_add()
* and __pagevec_lru_add_active() call release_pages() directly to avoid
* mutual recursion.
*/
void __pagevec_release(struct pagevec *pvec)
{
lru_add_drain();
release_pages(pvec->pages, pagevec_count(pvec), pvec->cold);
pagevec_reinit(pvec);
}
EXPORT_SYMBOL(__pagevec_release);
/*
* pagevec_release() for pages which are known to not be on the LRU
*
* This function reinitialises the caller's pagevec.
*/
void __pagevec_release_nonlru(struct pagevec *pvec)
{
int i;
struct pagevec pages_to_free;
pagevec_init(&pages_to_free, pvec->cold);
for (i = 0; i < pagevec_count(pvec); i++) {
struct page *page = pvec->pages[i];
VM_BUG_ON(PageLRU(page));
if (put_page_testzero(page))
pagevec_add(&pages_to_free, page);
}
pagevec_free(&pages_to_free);
pagevec_reinit(pvec);
}
/*
* Add the passed pages to the LRU, then drop the caller's refcount
* on them. Reinitialises the caller's pagevec.
*/
void __pagevec_lru_add(struct pagevec *pvec)
{
int i;
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_irq(&zone->lru_lock);
zone = pagezone;
spin_lock_irq(&zone->lru_lock);
}
VM_BUG_ON(PageLRU(page));
SetPageLRU(page);
add_page_to_inactive_list(zone, page);
}
if (zone)
spin_unlock_irq(&zone->lru_lock);
release_pages(pvec->pages, pvec->nr, pvec->cold);
pagevec_reinit(pvec);
}
EXPORT_SYMBOL(__pagevec_lru_add);
void __pagevec_lru_add_active(struct pagevec *pvec)
{
int i;
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_irq(&zone->lru_lock);
zone = pagezone;
spin_lock_irq(&zone->lru_lock);
}
VM_BUG_ON(PageLRU(page));
SetPageLRU(page);
VM_BUG_ON(PageActive(page));
SetPageActive(page);
add_page_to_active_list(zone, page);
}
if (zone)
spin_unlock_irq(&zone->lru_lock);
release_pages(pvec->pages, pvec->nr, pvec->cold);
pagevec_reinit(pvec);
}
/*
* Try to drop buffers from the pages in a pagevec
*/
void pagevec_strip(struct pagevec *pvec)
{
int i;
for (i = 0; i < pagevec_count(pvec); i++) {
struct page *page = pvec->pages[i];
if (PagePrivate(page) && !TestSetPageLocked(page)) {
if (PagePrivate(page))
try_to_release_page(page, 0);
unlock_page(page);
}
}
}
/**
* pagevec_lookup - gang pagecache lookup
* @pvec: Where the resulting pages are placed
* @mapping: The address_space to search
* @start: The starting page index
* @nr_pages: The maximum number of pages
*
* pagevec_lookup() will search for and return a group of up to @nr_pages pages
* in the mapping. The pages are placed in @pvec. pagevec_lookup() takes a
* reference against the pages in @pvec.
*
* The search returns a group of mapping-contiguous pages with ascending
* indexes. There may be holes in the indices due to not-present pages.
*
* pagevec_lookup() returns the number of pages which were found.
*/
unsigned pagevec_lookup(struct pagevec *pvec, struct address_space *mapping,
pgoff_t start, unsigned nr_pages)
{
pvec->nr = find_get_pages(mapping, start, nr_pages, pvec->pages);
return pagevec_count(pvec);
}
EXPORT_SYMBOL(pagevec_lookup);
unsigned pagevec_lookup_tag(struct pagevec *pvec, struct address_space *mapping,
pgoff_t *index, int tag, unsigned nr_pages)
{
pvec->nr = find_get_pages_tag(mapping, index, tag,
nr_pages, pvec->pages);
return pagevec_count(pvec);
}
EXPORT_SYMBOL(pagevec_lookup_tag);
#ifdef CONFIG_SMP
/*
* We tolerate a little inaccuracy to avoid ping-ponging the counter between
* CPUs
*/
#define ACCT_THRESHOLD max(16, NR_CPUS * 2)
static DEFINE_PER_CPU(long, committed_space) = 0;
void vm_acct_memory(long pages)
{
long *local;
preempt_disable();
local = &__get_cpu_var(committed_space);
*local += pages;
if (*local > ACCT_THRESHOLD || *local < -ACCT_THRESHOLD) {
atomic_add(*local, &vm_committed_space);
*local = 0;
}
preempt_enable();
}
#ifdef CONFIG_HOTPLUG_CPU
/* Drop the CPU's cached committed space back into the central pool. */
static int cpu_swap_callback(struct notifier_block *nfb,
unsigned long action,
void *hcpu)
{
long *committed;
committed = &per_cpu(committed_space, (long)hcpu);
if (action == CPU_DEAD) {
atomic_add(*committed, &vm_committed_space);
*committed = 0;
__lru_add_drain((long)hcpu);
}
return NOTIFY_OK;
}
#endif /* CONFIG_HOTPLUG_CPU */
#endif /* CONFIG_SMP */
/*
* Perform any setup for the swap system
*/
void __init swap_setup(void)
{
unsigned long megs = num_physpages >> (20 - PAGE_SHIFT);
/* Use a smaller cluster for small-memory machines */
if (megs < 16)
page_cluster = 2;
else
page_cluster = 3;
/*
* Right now other parts of the system means that we
* _really_ don't want to cluster much more
*/
hotcpu_notifier(cpu_swap_callback, 0);
}