![Lukasz Odzioba](/assets/img/avatar_default.png)
Currently we can have compound pages held on per cpu pagevecs, which leads to a lot of memory unavailable for reclaim when needed. In the systems with hundreads of processors it can be GBs of memory. On of the way of reproducing the problem is to not call munmap explicitly on all mapped regions (i.e. after receiving SIGTERM). After that some pages (with THP enabled also huge pages) may end up on lru_add_pvec, example below. void main() { #pragma omp parallel { size_t size = 55 * 1000 * 1000; // smaller than MEM/CPUS void *p = mmap(NULL, size, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANONYMOUS , -1, 0); if (p != MAP_FAILED) memset(p, 0, size); //munmap(p, size); // uncomment to make the problem go away } } When we run it with THP enabled it will leave significant amount of memory on lru_add_pvec. This memory will be not reclaimed if we hit OOM, so when we run above program in a loop: for i in `seq 100`; do ./a.out; done many processes (95% in my case) will be killed by OOM. The primary point of the LRU add cache is to save the zone lru_lock contention with a hope that more pages will belong to the same zone and so their addition can be batched. The huge page is already a form of batched addition (it will add 512 worth of memory in one go) so skipping the batching seems like a safer option when compared to a potential excess in the caching which can be quite large and much harder to fix because lru_add_drain_all is way to expensive and it is not really clear what would be a good moment to call it. Similarly we can reproduce the problem on lru_deactivate_pvec by adding: madvise(p, size, MADV_FREE); after memset. This patch flushes lru pvecs on compound page arrival making the problem less severe - after applying it kill rate of above example drops to 0%, due to reducing maximum amount of memory held on pvec from 28MB (with THP) to 56kB per CPU. Suggested-by: Michal Hocko <mhocko@suse.com> Link: http://lkml.kernel.org/r/1466180198-18854-1-git-send-email-lukasz.odzioba@intel.com Signed-off-by: Lukasz Odzioba <lukasz.odzioba@intel.com> Acked-by: Michal Hocko <mhocko@suse.com> Cc: Kirill Shutemov <kirill.shutemov@linux.intel.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Vladimir Davydov <vdavydov@parallels.com> Cc: Ming Li <mingli199x@qq.com> Cc: Minchan Kim <minchan@kernel.org> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
989 lines
27 KiB
C
989 lines
27 KiB
C
/*
|
|
* linux/mm/swap.c
|
|
*
|
|
* Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds
|
|
*/
|
|
|
|
/*
|
|
* 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
|
|
* 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/export.h>
|
|
#include <linux/mm_inline.h>
|
|
#include <linux/percpu_counter.h>
|
|
#include <linux/memremap.h>
|
|
#include <linux/percpu.h>
|
|
#include <linux/cpu.h>
|
|
#include <linux/notifier.h>
|
|
#include <linux/backing-dev.h>
|
|
#include <linux/memcontrol.h>
|
|
#include <linux/gfp.h>
|
|
#include <linux/uio.h>
|
|
#include <linux/hugetlb.h>
|
|
#include <linux/page_idle.h>
|
|
|
|
#include "internal.h"
|
|
|
|
#define CREATE_TRACE_POINTS
|
|
#include <trace/events/pagemap.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_pvec);
|
|
static DEFINE_PER_CPU(struct pagevec, lru_rotate_pvecs);
|
|
static DEFINE_PER_CPU(struct pagevec, lru_deactivate_file_pvecs);
|
|
static DEFINE_PER_CPU(struct pagevec, lru_deactivate_pvecs);
|
|
#ifdef CONFIG_SMP
|
|
static DEFINE_PER_CPU(struct pagevec, activate_page_pvecs);
|
|
#endif
|
|
|
|
/*
|
|
* 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)) {
|
|
struct zone *zone = page_zone(page);
|
|
struct lruvec *lruvec;
|
|
unsigned long flags;
|
|
|
|
spin_lock_irqsave(&zone->lru_lock, flags);
|
|
lruvec = mem_cgroup_page_lruvec(page, zone);
|
|
VM_BUG_ON_PAGE(!PageLRU(page), page);
|
|
__ClearPageLRU(page);
|
|
del_page_from_lru_list(page, lruvec, page_off_lru(page));
|
|
spin_unlock_irqrestore(&zone->lru_lock, flags);
|
|
}
|
|
mem_cgroup_uncharge(page);
|
|
}
|
|
|
|
static void __put_single_page(struct page *page)
|
|
{
|
|
__page_cache_release(page);
|
|
free_hot_cold_page(page, false);
|
|
}
|
|
|
|
static void __put_compound_page(struct page *page)
|
|
{
|
|
compound_page_dtor *dtor;
|
|
|
|
/*
|
|
* __page_cache_release() is supposed to be called for thp, not for
|
|
* hugetlb. This is because hugetlb page does never have PageLRU set
|
|
* (it's never listed to any LRU lists) and no memcg routines should
|
|
* be called for hugetlb (it has a separate hugetlb_cgroup.)
|
|
*/
|
|
if (!PageHuge(page))
|
|
__page_cache_release(page);
|
|
dtor = get_compound_page_dtor(page);
|
|
(*dtor)(page);
|
|
}
|
|
|
|
void __put_page(struct page *page)
|
|
{
|
|
if (unlikely(PageCompound(page)))
|
|
__put_compound_page(page);
|
|
else
|
|
__put_single_page(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);
|
|
put_page(victim);
|
|
}
|
|
}
|
|
EXPORT_SYMBOL(put_pages_list);
|
|
|
|
/*
|
|
* get_kernel_pages() - pin kernel pages in memory
|
|
* @kiov: An array of struct kvec structures
|
|
* @nr_segs: number of segments to pin
|
|
* @write: pinning for read/write, currently ignored
|
|
* @pages: array that receives pointers to the pages pinned.
|
|
* Should be at least nr_segs long.
|
|
*
|
|
* Returns number of pages pinned. This may be fewer than the number
|
|
* requested. If nr_pages is 0 or negative, returns 0. If no pages
|
|
* were pinned, returns -errno. Each page returned must be released
|
|
* with a put_page() call when it is finished with.
|
|
*/
|
|
int get_kernel_pages(const struct kvec *kiov, int nr_segs, int write,
|
|
struct page **pages)
|
|
{
|
|
int seg;
|
|
|
|
for (seg = 0; seg < nr_segs; seg++) {
|
|
if (WARN_ON(kiov[seg].iov_len != PAGE_SIZE))
|
|
return seg;
|
|
|
|
pages[seg] = kmap_to_page(kiov[seg].iov_base);
|
|
get_page(pages[seg]);
|
|
}
|
|
|
|
return seg;
|
|
}
|
|
EXPORT_SYMBOL_GPL(get_kernel_pages);
|
|
|
|
/*
|
|
* get_kernel_page() - pin a kernel page in memory
|
|
* @start: starting kernel address
|
|
* @write: pinning for read/write, currently ignored
|
|
* @pages: array that receives pointer to the page pinned.
|
|
* Must be at least nr_segs long.
|
|
*
|
|
* Returns 1 if page is pinned. If the page was not pinned, returns
|
|
* -errno. The page returned must be released with a put_page() call
|
|
* when it is finished with.
|
|
*/
|
|
int get_kernel_page(unsigned long start, int write, struct page **pages)
|
|
{
|
|
const struct kvec kiov = {
|
|
.iov_base = (void *)start,
|
|
.iov_len = PAGE_SIZE
|
|
};
|
|
|
|
return get_kernel_pages(&kiov, 1, write, pages);
|
|
}
|
|
EXPORT_SYMBOL_GPL(get_kernel_page);
|
|
|
|
static void pagevec_lru_move_fn(struct pagevec *pvec,
|
|
void (*move_fn)(struct page *page, struct lruvec *lruvec, void *arg),
|
|
void *arg)
|
|
{
|
|
int i;
|
|
struct zone *zone = NULL;
|
|
struct lruvec *lruvec;
|
|
unsigned long flags = 0;
|
|
|
|
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_irqrestore(&zone->lru_lock, flags);
|
|
zone = pagezone;
|
|
spin_lock_irqsave(&zone->lru_lock, flags);
|
|
}
|
|
|
|
lruvec = mem_cgroup_page_lruvec(page, zone);
|
|
(*move_fn)(page, lruvec, arg);
|
|
}
|
|
if (zone)
|
|
spin_unlock_irqrestore(&zone->lru_lock, flags);
|
|
release_pages(pvec->pages, pvec->nr, pvec->cold);
|
|
pagevec_reinit(pvec);
|
|
}
|
|
|
|
static void pagevec_move_tail_fn(struct page *page, struct lruvec *lruvec,
|
|
void *arg)
|
|
{
|
|
int *pgmoved = arg;
|
|
|
|
if (PageLRU(page) && !PageActive(page) && !PageUnevictable(page)) {
|
|
enum lru_list lru = page_lru_base_type(page);
|
|
list_move_tail(&page->lru, &lruvec->lists[lru]);
|
|
(*pgmoved)++;
|
|
}
|
|
}
|
|
|
|
/*
|
|
* pagevec_move_tail() must be called with IRQ disabled.
|
|
* Otherwise this may cause nasty races.
|
|
*/
|
|
static void pagevec_move_tail(struct pagevec *pvec)
|
|
{
|
|
int pgmoved = 0;
|
|
|
|
pagevec_lru_move_fn(pvec, pagevec_move_tail_fn, &pgmoved);
|
|
__count_vm_events(PGROTATED, pgmoved);
|
|
}
|
|
|
|
/*
|
|
* 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.
|
|
*/
|
|
void rotate_reclaimable_page(struct page *page)
|
|
{
|
|
if (!PageLocked(page) && !PageDirty(page) && !PageActive(page) &&
|
|
!PageUnevictable(page) && PageLRU(page)) {
|
|
struct pagevec *pvec;
|
|
unsigned long flags;
|
|
|
|
get_page(page);
|
|
local_irq_save(flags);
|
|
pvec = this_cpu_ptr(&lru_rotate_pvecs);
|
|
if (!pagevec_add(pvec, page) || PageCompound(page))
|
|
pagevec_move_tail(pvec);
|
|
local_irq_restore(flags);
|
|
}
|
|
}
|
|
|
|
static void update_page_reclaim_stat(struct lruvec *lruvec,
|
|
int file, int rotated)
|
|
{
|
|
struct zone_reclaim_stat *reclaim_stat = &lruvec->reclaim_stat;
|
|
|
|
reclaim_stat->recent_scanned[file]++;
|
|
if (rotated)
|
|
reclaim_stat->recent_rotated[file]++;
|
|
}
|
|
|
|
static void __activate_page(struct page *page, struct lruvec *lruvec,
|
|
void *arg)
|
|
{
|
|
if (PageLRU(page) && !PageActive(page) && !PageUnevictable(page)) {
|
|
int file = page_is_file_cache(page);
|
|
int lru = page_lru_base_type(page);
|
|
|
|
del_page_from_lru_list(page, lruvec, lru);
|
|
SetPageActive(page);
|
|
lru += LRU_ACTIVE;
|
|
add_page_to_lru_list(page, lruvec, lru);
|
|
trace_mm_lru_activate(page);
|
|
|
|
__count_vm_event(PGACTIVATE);
|
|
update_page_reclaim_stat(lruvec, file, 1);
|
|
}
|
|
}
|
|
|
|
#ifdef CONFIG_SMP
|
|
static void activate_page_drain(int cpu)
|
|
{
|
|
struct pagevec *pvec = &per_cpu(activate_page_pvecs, cpu);
|
|
|
|
if (pagevec_count(pvec))
|
|
pagevec_lru_move_fn(pvec, __activate_page, NULL);
|
|
}
|
|
|
|
static bool need_activate_page_drain(int cpu)
|
|
{
|
|
return pagevec_count(&per_cpu(activate_page_pvecs, cpu)) != 0;
|
|
}
|
|
|
|
void activate_page(struct page *page)
|
|
{
|
|
if (PageLRU(page) && !PageActive(page) && !PageUnevictable(page)) {
|
|
struct pagevec *pvec = &get_cpu_var(activate_page_pvecs);
|
|
|
|
get_page(page);
|
|
if (!pagevec_add(pvec, page) || PageCompound(page))
|
|
pagevec_lru_move_fn(pvec, __activate_page, NULL);
|
|
put_cpu_var(activate_page_pvecs);
|
|
}
|
|
}
|
|
|
|
#else
|
|
static inline void activate_page_drain(int cpu)
|
|
{
|
|
}
|
|
|
|
static bool need_activate_page_drain(int cpu)
|
|
{
|
|
return false;
|
|
}
|
|
|
|
void activate_page(struct page *page)
|
|
{
|
|
struct zone *zone = page_zone(page);
|
|
|
|
spin_lock_irq(&zone->lru_lock);
|
|
__activate_page(page, mem_cgroup_page_lruvec(page, zone), NULL);
|
|
spin_unlock_irq(&zone->lru_lock);
|
|
}
|
|
#endif
|
|
|
|
static void __lru_cache_activate_page(struct page *page)
|
|
{
|
|
struct pagevec *pvec = &get_cpu_var(lru_add_pvec);
|
|
int i;
|
|
|
|
/*
|
|
* Search backwards on the optimistic assumption that the page being
|
|
* activated has just been added to this pagevec. Note that only
|
|
* the local pagevec is examined as a !PageLRU page could be in the
|
|
* process of being released, reclaimed, migrated or on a remote
|
|
* pagevec that is currently being drained. Furthermore, marking
|
|
* a remote pagevec's page PageActive potentially hits a race where
|
|
* a page is marked PageActive just after it is added to the inactive
|
|
* list causing accounting errors and BUG_ON checks to trigger.
|
|
*/
|
|
for (i = pagevec_count(pvec) - 1; i >= 0; i--) {
|
|
struct page *pagevec_page = pvec->pages[i];
|
|
|
|
if (pagevec_page == page) {
|
|
SetPageActive(page);
|
|
break;
|
|
}
|
|
}
|
|
|
|
put_cpu_var(lru_add_pvec);
|
|
}
|
|
|
|
/*
|
|
* Mark a page as having seen activity.
|
|
*
|
|
* inactive,unreferenced -> inactive,referenced
|
|
* inactive,referenced -> active,unreferenced
|
|
* active,unreferenced -> active,referenced
|
|
*
|
|
* When a newly allocated page is not yet visible, so safe for non-atomic ops,
|
|
* __SetPageReferenced(page) may be substituted for mark_page_accessed(page).
|
|
*/
|
|
void mark_page_accessed(struct page *page)
|
|
{
|
|
page = compound_head(page);
|
|
if (!PageActive(page) && !PageUnevictable(page) &&
|
|
PageReferenced(page)) {
|
|
|
|
/*
|
|
* If the page is on the LRU, queue it for activation via
|
|
* activate_page_pvecs. Otherwise, assume the page is on a
|
|
* pagevec, mark it active and it'll be moved to the active
|
|
* LRU on the next drain.
|
|
*/
|
|
if (PageLRU(page))
|
|
activate_page(page);
|
|
else
|
|
__lru_cache_activate_page(page);
|
|
ClearPageReferenced(page);
|
|
if (page_is_file_cache(page))
|
|
workingset_activation(page);
|
|
} else if (!PageReferenced(page)) {
|
|
SetPageReferenced(page);
|
|
}
|
|
if (page_is_idle(page))
|
|
clear_page_idle(page);
|
|
}
|
|
EXPORT_SYMBOL(mark_page_accessed);
|
|
|
|
static void __lru_cache_add(struct page *page)
|
|
{
|
|
struct pagevec *pvec = &get_cpu_var(lru_add_pvec);
|
|
|
|
get_page(page);
|
|
if (!pagevec_add(pvec, page) || PageCompound(page))
|
|
__pagevec_lru_add(pvec);
|
|
put_cpu_var(lru_add_pvec);
|
|
}
|
|
|
|
/**
|
|
* lru_cache_add: add a page to the page lists
|
|
* @page: the page to add
|
|
*/
|
|
void lru_cache_add_anon(struct page *page)
|
|
{
|
|
if (PageActive(page))
|
|
ClearPageActive(page);
|
|
__lru_cache_add(page);
|
|
}
|
|
|
|
void lru_cache_add_file(struct page *page)
|
|
{
|
|
if (PageActive(page))
|
|
ClearPageActive(page);
|
|
__lru_cache_add(page);
|
|
}
|
|
EXPORT_SYMBOL(lru_cache_add_file);
|
|
|
|
/**
|
|
* lru_cache_add - add a page to a page list
|
|
* @page: the page to be added to the LRU.
|
|
*
|
|
* Queue the page for addition to the LRU via pagevec. The decision on whether
|
|
* to add the page to the [in]active [file|anon] list is deferred until the
|
|
* pagevec is drained. This gives a chance for the caller of lru_cache_add()
|
|
* have the page added to the active list using mark_page_accessed().
|
|
*/
|
|
void lru_cache_add(struct page *page)
|
|
{
|
|
VM_BUG_ON_PAGE(PageActive(page) && PageUnevictable(page), page);
|
|
VM_BUG_ON_PAGE(PageLRU(page), page);
|
|
__lru_cache_add(page);
|
|
}
|
|
|
|
/**
|
|
* add_page_to_unevictable_list - add a page to the unevictable list
|
|
* @page: the page to be added to the unevictable list
|
|
*
|
|
* Add page directly to its zone's unevictable list. To avoid races with
|
|
* tasks that might be making the page evictable, through eg. munlock,
|
|
* munmap or exit, while it's not on the lru, we want to add the page
|
|
* while it's locked or otherwise "invisible" to other tasks. This is
|
|
* difficult to do when using the pagevec cache, so bypass that.
|
|
*/
|
|
void add_page_to_unevictable_list(struct page *page)
|
|
{
|
|
struct zone *zone = page_zone(page);
|
|
struct lruvec *lruvec;
|
|
|
|
spin_lock_irq(&zone->lru_lock);
|
|
lruvec = mem_cgroup_page_lruvec(page, zone);
|
|
ClearPageActive(page);
|
|
SetPageUnevictable(page);
|
|
SetPageLRU(page);
|
|
add_page_to_lru_list(page, lruvec, LRU_UNEVICTABLE);
|
|
spin_unlock_irq(&zone->lru_lock);
|
|
}
|
|
|
|
/**
|
|
* lru_cache_add_active_or_unevictable
|
|
* @page: the page to be added to LRU
|
|
* @vma: vma in which page is mapped for determining reclaimability
|
|
*
|
|
* Place @page on the active or unevictable LRU list, depending on its
|
|
* evictability. Note that if the page is not evictable, it goes
|
|
* directly back onto it's zone's unevictable list, it does NOT use a
|
|
* per cpu pagevec.
|
|
*/
|
|
void lru_cache_add_active_or_unevictable(struct page *page,
|
|
struct vm_area_struct *vma)
|
|
{
|
|
VM_BUG_ON_PAGE(PageLRU(page), page);
|
|
|
|
if (likely((vma->vm_flags & (VM_LOCKED | VM_SPECIAL)) != VM_LOCKED)) {
|
|
SetPageActive(page);
|
|
lru_cache_add(page);
|
|
return;
|
|
}
|
|
|
|
if (!TestSetPageMlocked(page)) {
|
|
/*
|
|
* We use the irq-unsafe __mod_zone_page_stat because this
|
|
* counter is not modified from interrupt context, and the pte
|
|
* lock is held(spinlock), which implies preemption disabled.
|
|
*/
|
|
__mod_zone_page_state(page_zone(page), NR_MLOCK,
|
|
hpage_nr_pages(page));
|
|
count_vm_event(UNEVICTABLE_PGMLOCKED);
|
|
}
|
|
add_page_to_unevictable_list(page);
|
|
}
|
|
|
|
/*
|
|
* If the page can not be invalidated, it is moved to the
|
|
* inactive list to speed up its reclaim. It is moved to the
|
|
* head of the list, rather than the tail, to give the flusher
|
|
* threads some time to write it out, as this is much more
|
|
* effective than the single-page writeout from reclaim.
|
|
*
|
|
* If the page isn't page_mapped and dirty/writeback, the page
|
|
* could reclaim asap using PG_reclaim.
|
|
*
|
|
* 1. active, mapped page -> none
|
|
* 2. active, dirty/writeback page -> inactive, head, PG_reclaim
|
|
* 3. inactive, mapped page -> none
|
|
* 4. inactive, dirty/writeback page -> inactive, head, PG_reclaim
|
|
* 5. inactive, clean -> inactive, tail
|
|
* 6. Others -> none
|
|
*
|
|
* In 4, why it moves inactive's head, the VM expects the page would
|
|
* be write it out by flusher threads as this is much more effective
|
|
* than the single-page writeout from reclaim.
|
|
*/
|
|
static void lru_deactivate_file_fn(struct page *page, struct lruvec *lruvec,
|
|
void *arg)
|
|
{
|
|
int lru, file;
|
|
bool active;
|
|
|
|
if (!PageLRU(page))
|
|
return;
|
|
|
|
if (PageUnevictable(page))
|
|
return;
|
|
|
|
/* Some processes are using the page */
|
|
if (page_mapped(page))
|
|
return;
|
|
|
|
active = PageActive(page);
|
|
file = page_is_file_cache(page);
|
|
lru = page_lru_base_type(page);
|
|
|
|
del_page_from_lru_list(page, lruvec, lru + active);
|
|
ClearPageActive(page);
|
|
ClearPageReferenced(page);
|
|
add_page_to_lru_list(page, lruvec, lru);
|
|
|
|
if (PageWriteback(page) || PageDirty(page)) {
|
|
/*
|
|
* PG_reclaim could be raced with end_page_writeback
|
|
* It can make readahead confusing. But race window
|
|
* is _really_ small and it's non-critical problem.
|
|
*/
|
|
SetPageReclaim(page);
|
|
} else {
|
|
/*
|
|
* The page's writeback ends up during pagevec
|
|
* We moves tha page into tail of inactive.
|
|
*/
|
|
list_move_tail(&page->lru, &lruvec->lists[lru]);
|
|
__count_vm_event(PGROTATED);
|
|
}
|
|
|
|
if (active)
|
|
__count_vm_event(PGDEACTIVATE);
|
|
update_page_reclaim_stat(lruvec, file, 0);
|
|
}
|
|
|
|
|
|
static void lru_deactivate_fn(struct page *page, struct lruvec *lruvec,
|
|
void *arg)
|
|
{
|
|
if (PageLRU(page) && PageActive(page) && !PageUnevictable(page)) {
|
|
int file = page_is_file_cache(page);
|
|
int lru = page_lru_base_type(page);
|
|
|
|
del_page_from_lru_list(page, lruvec, lru + LRU_ACTIVE);
|
|
ClearPageActive(page);
|
|
ClearPageReferenced(page);
|
|
add_page_to_lru_list(page, lruvec, lru);
|
|
|
|
__count_vm_event(PGDEACTIVATE);
|
|
update_page_reclaim_stat(lruvec, file, 0);
|
|
}
|
|
}
|
|
|
|
/*
|
|
* 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.
|
|
*/
|
|
void lru_add_drain_cpu(int cpu)
|
|
{
|
|
struct pagevec *pvec = &per_cpu(lru_add_pvec, cpu);
|
|
|
|
if (pagevec_count(pvec))
|
|
__pagevec_lru_add(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);
|
|
}
|
|
|
|
pvec = &per_cpu(lru_deactivate_file_pvecs, cpu);
|
|
if (pagevec_count(pvec))
|
|
pagevec_lru_move_fn(pvec, lru_deactivate_file_fn, NULL);
|
|
|
|
pvec = &per_cpu(lru_deactivate_pvecs, cpu);
|
|
if (pagevec_count(pvec))
|
|
pagevec_lru_move_fn(pvec, lru_deactivate_fn, NULL);
|
|
|
|
activate_page_drain(cpu);
|
|
}
|
|
|
|
/**
|
|
* deactivate_file_page - forcefully deactivate a file page
|
|
* @page: page to deactivate
|
|
*
|
|
* This function hints the VM that @page is a good reclaim candidate,
|
|
* for example if its invalidation fails due to the page being dirty
|
|
* or under writeback.
|
|
*/
|
|
void deactivate_file_page(struct page *page)
|
|
{
|
|
/*
|
|
* In a workload with many unevictable page such as mprotect,
|
|
* unevictable page deactivation for accelerating reclaim is pointless.
|
|
*/
|
|
if (PageUnevictable(page))
|
|
return;
|
|
|
|
if (likely(get_page_unless_zero(page))) {
|
|
struct pagevec *pvec = &get_cpu_var(lru_deactivate_file_pvecs);
|
|
|
|
if (!pagevec_add(pvec, page) || PageCompound(page))
|
|
pagevec_lru_move_fn(pvec, lru_deactivate_file_fn, NULL);
|
|
put_cpu_var(lru_deactivate_file_pvecs);
|
|
}
|
|
}
|
|
|
|
/**
|
|
* deactivate_page - deactivate a page
|
|
* @page: page to deactivate
|
|
*
|
|
* deactivate_page() moves @page to the inactive list if @page was on the active
|
|
* list and was not an unevictable page. This is done to accelerate the reclaim
|
|
* of @page.
|
|
*/
|
|
void deactivate_page(struct page *page)
|
|
{
|
|
if (PageLRU(page) && PageActive(page) && !PageUnevictable(page)) {
|
|
struct pagevec *pvec = &get_cpu_var(lru_deactivate_pvecs);
|
|
|
|
get_page(page);
|
|
if (!pagevec_add(pvec, page) || PageCompound(page))
|
|
pagevec_lru_move_fn(pvec, lru_deactivate_fn, NULL);
|
|
put_cpu_var(lru_deactivate_pvecs);
|
|
}
|
|
}
|
|
|
|
void lru_add_drain(void)
|
|
{
|
|
lru_add_drain_cpu(get_cpu());
|
|
put_cpu();
|
|
}
|
|
|
|
static void lru_add_drain_per_cpu(struct work_struct *dummy)
|
|
{
|
|
lru_add_drain();
|
|
}
|
|
|
|
static DEFINE_PER_CPU(struct work_struct, lru_add_drain_work);
|
|
|
|
/*
|
|
* lru_add_drain_wq is used to do lru_add_drain_all() from a WQ_MEM_RECLAIM
|
|
* workqueue, aiding in getting memory freed.
|
|
*/
|
|
static struct workqueue_struct *lru_add_drain_wq;
|
|
|
|
static int __init lru_init(void)
|
|
{
|
|
lru_add_drain_wq = alloc_workqueue("lru-add-drain", WQ_MEM_RECLAIM, 0);
|
|
|
|
if (WARN(!lru_add_drain_wq,
|
|
"Failed to create workqueue lru_add_drain_wq"))
|
|
return -ENOMEM;
|
|
|
|
return 0;
|
|
}
|
|
early_initcall(lru_init);
|
|
|
|
void lru_add_drain_all(void)
|
|
{
|
|
static DEFINE_MUTEX(lock);
|
|
static struct cpumask has_work;
|
|
int cpu;
|
|
|
|
mutex_lock(&lock);
|
|
get_online_cpus();
|
|
cpumask_clear(&has_work);
|
|
|
|
for_each_online_cpu(cpu) {
|
|
struct work_struct *work = &per_cpu(lru_add_drain_work, cpu);
|
|
|
|
if (pagevec_count(&per_cpu(lru_add_pvec, cpu)) ||
|
|
pagevec_count(&per_cpu(lru_rotate_pvecs, cpu)) ||
|
|
pagevec_count(&per_cpu(lru_deactivate_file_pvecs, cpu)) ||
|
|
pagevec_count(&per_cpu(lru_deactivate_pvecs, cpu)) ||
|
|
need_activate_page_drain(cpu)) {
|
|
INIT_WORK(work, lru_add_drain_per_cpu);
|
|
queue_work_on(cpu, lru_add_drain_wq, work);
|
|
cpumask_set_cpu(cpu, &has_work);
|
|
}
|
|
}
|
|
|
|
for_each_cpu(cpu, &has_work)
|
|
flush_work(&per_cpu(lru_add_drain_work, cpu));
|
|
|
|
put_online_cpus();
|
|
mutex_unlock(&lock);
|
|
}
|
|
|
|
/**
|
|
* release_pages - batched put_page()
|
|
* @pages: array of pages to release
|
|
* @nr: number of pages
|
|
* @cold: whether the pages are cache cold
|
|
*
|
|
* Decrement the reference count on all the pages in @pages. If it
|
|
* fell to zero, remove the page from the LRU and free it.
|
|
*/
|
|
void release_pages(struct page **pages, int nr, bool cold)
|
|
{
|
|
int i;
|
|
LIST_HEAD(pages_to_free);
|
|
struct zone *zone = NULL;
|
|
struct lruvec *lruvec;
|
|
unsigned long uninitialized_var(flags);
|
|
unsigned int uninitialized_var(lock_batch);
|
|
|
|
for (i = 0; i < nr; i++) {
|
|
struct page *page = pages[i];
|
|
|
|
/*
|
|
* Make sure the IRQ-safe lock-holding time does not get
|
|
* excessive with a continuous string of pages from the
|
|
* same zone. The lock is held only if zone != NULL.
|
|
*/
|
|
if (zone && ++lock_batch == SWAP_CLUSTER_MAX) {
|
|
spin_unlock_irqrestore(&zone->lru_lock, flags);
|
|
zone = NULL;
|
|
}
|
|
|
|
if (is_huge_zero_page(page)) {
|
|
put_huge_zero_page();
|
|
continue;
|
|
}
|
|
|
|
page = compound_head(page);
|
|
if (!put_page_testzero(page))
|
|
continue;
|
|
|
|
if (PageCompound(page)) {
|
|
if (zone) {
|
|
spin_unlock_irqrestore(&zone->lru_lock, flags);
|
|
zone = NULL;
|
|
}
|
|
__put_compound_page(page);
|
|
continue;
|
|
}
|
|
|
|
if (PageLRU(page)) {
|
|
struct zone *pagezone = page_zone(page);
|
|
|
|
if (pagezone != zone) {
|
|
if (zone)
|
|
spin_unlock_irqrestore(&zone->lru_lock,
|
|
flags);
|
|
lock_batch = 0;
|
|
zone = pagezone;
|
|
spin_lock_irqsave(&zone->lru_lock, flags);
|
|
}
|
|
|
|
lruvec = mem_cgroup_page_lruvec(page, zone);
|
|
VM_BUG_ON_PAGE(!PageLRU(page), page);
|
|
__ClearPageLRU(page);
|
|
del_page_from_lru_list(page, lruvec, page_off_lru(page));
|
|
}
|
|
|
|
/* Clear Active bit in case of parallel mark_page_accessed */
|
|
__ClearPageActive(page);
|
|
|
|
list_add(&page->lru, &pages_to_free);
|
|
}
|
|
if (zone)
|
|
spin_unlock_irqrestore(&zone->lru_lock, flags);
|
|
|
|
mem_cgroup_uncharge_list(&pages_to_free);
|
|
free_hot_cold_page_list(&pages_to_free, cold);
|
|
}
|
|
EXPORT_SYMBOL(release_pages);
|
|
|
|
/*
|
|
* 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);
|
|
|
|
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
|
|
/* used by __split_huge_page_refcount() */
|
|
void lru_add_page_tail(struct page *page, struct page *page_tail,
|
|
struct lruvec *lruvec, struct list_head *list)
|
|
{
|
|
const int file = 0;
|
|
|
|
VM_BUG_ON_PAGE(!PageHead(page), page);
|
|
VM_BUG_ON_PAGE(PageCompound(page_tail), page);
|
|
VM_BUG_ON_PAGE(PageLRU(page_tail), page);
|
|
VM_BUG_ON(NR_CPUS != 1 &&
|
|
!spin_is_locked(&lruvec_zone(lruvec)->lru_lock));
|
|
|
|
if (!list)
|
|
SetPageLRU(page_tail);
|
|
|
|
if (likely(PageLRU(page)))
|
|
list_add_tail(&page_tail->lru, &page->lru);
|
|
else if (list) {
|
|
/* page reclaim is reclaiming a huge page */
|
|
get_page(page_tail);
|
|
list_add_tail(&page_tail->lru, list);
|
|
} else {
|
|
struct list_head *list_head;
|
|
/*
|
|
* Head page has not yet been counted, as an hpage,
|
|
* so we must account for each subpage individually.
|
|
*
|
|
* Use the standard add function to put page_tail on the list,
|
|
* but then correct its position so they all end up in order.
|
|
*/
|
|
add_page_to_lru_list(page_tail, lruvec, page_lru(page_tail));
|
|
list_head = page_tail->lru.prev;
|
|
list_move_tail(&page_tail->lru, list_head);
|
|
}
|
|
|
|
if (!PageUnevictable(page))
|
|
update_page_reclaim_stat(lruvec, file, PageActive(page_tail));
|
|
}
|
|
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
|
|
|
|
static void __pagevec_lru_add_fn(struct page *page, struct lruvec *lruvec,
|
|
void *arg)
|
|
{
|
|
int file = page_is_file_cache(page);
|
|
int active = PageActive(page);
|
|
enum lru_list lru = page_lru(page);
|
|
|
|
VM_BUG_ON_PAGE(PageLRU(page), page);
|
|
|
|
SetPageLRU(page);
|
|
add_page_to_lru_list(page, lruvec, lru);
|
|
update_page_reclaim_stat(lruvec, file, active);
|
|
trace_mm_lru_insertion(page, lru);
|
|
}
|
|
|
|
/*
|
|
* 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)
|
|
{
|
|
pagevec_lru_move_fn(pvec, __pagevec_lru_add_fn, NULL);
|
|
}
|
|
EXPORT_SYMBOL(__pagevec_lru_add);
|
|
|
|
/**
|
|
* pagevec_lookup_entries - gang pagecache lookup
|
|
* @pvec: Where the resulting entries are placed
|
|
* @mapping: The address_space to search
|
|
* @start: The starting entry index
|
|
* @nr_entries: The maximum number of entries
|
|
* @indices: The cache indices corresponding to the entries in @pvec
|
|
*
|
|
* pagevec_lookup_entries() will search for and return a group of up
|
|
* to @nr_entries pages and shadow entries in the mapping. All
|
|
* entries are placed in @pvec. pagevec_lookup_entries() takes a
|
|
* reference against actual pages in @pvec.
|
|
*
|
|
* The search returns a group of mapping-contiguous entries with
|
|
* ascending indexes. There may be holes in the indices due to
|
|
* not-present entries.
|
|
*
|
|
* pagevec_lookup_entries() returns the number of entries which were
|
|
* found.
|
|
*/
|
|
unsigned pagevec_lookup_entries(struct pagevec *pvec,
|
|
struct address_space *mapping,
|
|
pgoff_t start, unsigned nr_pages,
|
|
pgoff_t *indices)
|
|
{
|
|
pvec->nr = find_get_entries(mapping, start, nr_pages,
|
|
pvec->pages, indices);
|
|
return pagevec_count(pvec);
|
|
}
|
|
|
|
/**
|
|
* pagevec_remove_exceptionals - pagevec exceptionals pruning
|
|
* @pvec: The pagevec to prune
|
|
*
|
|
* pagevec_lookup_entries() fills both pages and exceptional radix
|
|
* tree entries into the pagevec. This function prunes all
|
|
* exceptionals from @pvec without leaving holes, so that it can be
|
|
* passed on to page-only pagevec operations.
|
|
*/
|
|
void pagevec_remove_exceptionals(struct pagevec *pvec)
|
|
{
|
|
int i, j;
|
|
|
|
for (i = 0, j = 0; i < pagevec_count(pvec); i++) {
|
|
struct page *page = pvec->pages[i];
|
|
if (!radix_tree_exceptional_entry(page))
|
|
pvec->pages[j++] = page;
|
|
}
|
|
pvec->nr = j;
|
|
}
|
|
|
|
/**
|
|
* 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);
|
|
|
|
/*
|
|
* Perform any setup for the swap system
|
|
*/
|
|
void __init swap_setup(void)
|
|
{
|
|
unsigned long megs = totalram_pages >> (20 - PAGE_SHIFT);
|
|
#ifdef CONFIG_SWAP
|
|
int i;
|
|
|
|
for (i = 0; i < MAX_SWAPFILES; i++)
|
|
spin_lock_init(&swapper_spaces[i].tree_lock);
|
|
#endif
|
|
|
|
/* 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
|
|
*/
|
|
}
|