#include <linux/freezer.h>
#include <linux/memcontrol.h>
#include <linux/delayacct.h>
+#include <linux/sysctl.h>
#include <asm/tlbflush.h>
#include <asm/div64.h>
return 0;
}
+/**
+ * putback_lru_page - put previously isolated page onto appropriate LRU list
+ * @page: page to be put back to appropriate lru list
+ *
+ * Add previously isolated @page to appropriate LRU list.
+ * Page may still be unevictable for other reasons.
+ *
+ * lru_lock must not be held, interrupts must be enabled.
+ */
+#ifdef CONFIG_UNEVICTABLE_LRU
+void putback_lru_page(struct page *page)
+{
+ int lru;
+ int active = !!TestClearPageActive(page);
+ int was_unevictable = PageUnevictable(page);
+
+ VM_BUG_ON(PageLRU(page));
+
+redo:
+ ClearPageUnevictable(page);
+
+ if (page_evictable(page, NULL)) {
+ /*
+ * For evictable pages, we can use the cache.
+ * In event of a race, worst case is we end up with an
+ * unevictable page on [in]active list.
+ * We know how to handle that.
+ */
+ lru = active + page_is_file_cache(page);
+ lru_cache_add_lru(page, lru);
+ } else {
+ /*
+ * Put unevictable pages directly on zone's unevictable
+ * list.
+ */
+ lru = LRU_UNEVICTABLE;
+ add_page_to_unevictable_list(page);
+ }
+ mem_cgroup_move_lists(page, lru);
+
+ /*
+ * page's status can change while we move it among lru. If an evictable
+ * page is on unevictable list, it never be freed. To avoid that,
+ * check after we added it to the list, again.
+ */
+ if (lru == LRU_UNEVICTABLE && page_evictable(page, NULL)) {
+ if (!isolate_lru_page(page)) {
+ put_page(page);
+ goto redo;
+ }
+ /* This means someone else dropped this page from LRU
+ * So, it will be freed or putback to LRU again. There is
+ * nothing to do here.
+ */
+ }
+
+ if (was_unevictable && lru != LRU_UNEVICTABLE)
+ count_vm_event(UNEVICTABLE_PGRESCUED);
+ else if (!was_unevictable && lru == LRU_UNEVICTABLE)
+ count_vm_event(UNEVICTABLE_PGCULLED);
+
+ put_page(page); /* drop ref from isolate */
+}
+
+#else /* CONFIG_UNEVICTABLE_LRU */
+
+void putback_lru_page(struct page *page)
+{
+ int lru;
+ VM_BUG_ON(PageLRU(page));
+
+ lru = !!TestClearPageActive(page) + page_is_file_cache(page);
+ lru_cache_add_lru(page, lru);
+ mem_cgroup_move_lists(page, lru);
+ put_page(page);
+}
+#endif /* CONFIG_UNEVICTABLE_LRU */
+
+
/*
* shrink_page_list() returns the number of reclaimed pages
*/
sc->nr_scanned++;
+ if (unlikely(!page_evictable(page, NULL)))
+ goto cull_mlocked;
+
if (!sc->may_swap && page_mapped(page))
goto keep_locked;
* Anonymous process memory has backing store?
* Try to allocate it some swap space here.
*/
- if (PageAnon(page) && !PageSwapCache(page))
+ if (PageAnon(page) && !PageSwapCache(page)) {
+ switch (try_to_munlock(page)) {
+ case SWAP_FAIL: /* shouldn't happen */
+ case SWAP_AGAIN:
+ goto keep_locked;
+ case SWAP_MLOCK:
+ goto cull_mlocked;
+ case SWAP_SUCCESS:
+ ; /* fall thru'; add to swap cache */
+ }
if (!add_to_swap(page, GFP_ATOMIC))
goto activate_locked;
+ }
#endif /* CONFIG_SWAP */
mapping = page_mapping(page);
goto activate_locked;
case SWAP_AGAIN:
goto keep_locked;
+ case SWAP_MLOCK:
+ goto cull_mlocked;
case SWAP_SUCCESS:
; /* try to free the page below */
}
* possible for a page to have PageDirty set, but it is actually
* clean (all its buffers are clean). This happens if the
* buffers were written out directly, with submit_bh(). ext3
- * will do this, as well as the blockdev mapping.
+ * will do this, as well as the blockdev mapping.
* try_to_release_page() will discover that cleanness and will
* drop the buffers and mark the page clean - it can be freed.
*
if (!mapping || !__remove_mapping(mapping, page))
goto keep_locked;
- unlock_page(page);
+ /*
+ * At this point, we have no other references and there is
+ * no way to pick any more up (removed from LRU, removed
+ * from pagecache). Can use non-atomic bitops now (and
+ * we obviously don't have to worry about waking up a process
+ * waiting on the page lock, because there are no references.
+ */
+ __clear_page_locked(page);
free_it:
nr_reclaimed++;
if (!pagevec_add(&freed_pvec, page)) {
}
continue;
+cull_mlocked:
+ unlock_page(page);
+ putback_lru_page(page);
+ continue;
+
activate_locked:
/* Not a candidate for swapping, so reclaim swap space. */
if (PageSwapCache(page) && vm_swap_full())
remove_exclusive_swap_page_ref(page);
+ VM_BUG_ON(PageActive(page));
SetPageActive(page);
pgactivate++;
keep_locked:
unlock_page(page);
keep:
list_add(&page->lru, &ret_pages);
- VM_BUG_ON(PageLRU(page));
+ VM_BUG_ON(PageLRU(page) || PageUnevictable(page));
}
list_splice(&ret_pages, page_list);
if (pagevec_count(&freed_pvec))
if (mode != ISOLATE_BOTH && (!page_is_file_cache(page) != !file))
return ret;
+ /*
+ * When this function is being called for lumpy reclaim, we
+ * initially look into all LRU pages, active, inactive and
+ * unevictable; only give shrink_page_list evictable pages.
+ */
+ if (PageUnevictable(page))
+ return ret;
+
ret = -EBUSY;
if (likely(get_page_unless_zero(page))) {
/*
/* else it is being freed elsewhere */
list_move(&cursor_page->lru, src);
default:
- break;
+ break; /* ! on LRU or wrong list */
}
}
}
* Returns -EBUSY if the page was not on an LRU list.
*
* The returned page will have PageLRU() cleared. If it was found on
- * the active list, it will have PageActive set. That flag may need
- * to be cleared by the caller before letting the page go.
+ * the active list, it will have PageActive set. If it was found on
+ * the unevictable list, it will have the PageUnevictable bit set. That flag
+ * may need to be cleared by the caller before letting the page go.
*
* The vmstat statistic corresponding to the list on which the page was
* found will be decremented.
spin_lock_irq(&zone->lru_lock);
if (PageLRU(page) && get_page_unless_zero(page)) {
- int lru = LRU_BASE;
+ int lru = page_lru(page);
ret = 0;
ClearPageLRU(page);
- lru += page_is_file_cache(page) + !!PageActive(page);
del_page_from_lru_list(zone, page, lru);
}
spin_unlock_irq(&zone->lru_lock);
* of reclaimed pages
*/
static unsigned long shrink_inactive_list(unsigned long max_scan,
- struct zone *zone, struct scan_control *sc, int file)
+ struct zone *zone, struct scan_control *sc,
+ int priority, int file)
{
LIST_HEAD(page_list);
struct pagevec pvec;
unsigned long nr_freed;
unsigned long nr_active;
unsigned int count[NR_LRU_LISTS] = { 0, };
- int mode = (sc->order > PAGE_ALLOC_COSTLY_ORDER) ?
- ISOLATE_BOTH : ISOLATE_INACTIVE;
+ int mode = ISOLATE_INACTIVE;
+
+ /*
+ * If we need a large contiguous chunk of memory, or have
+ * trouble getting a small set of contiguous pages, we
+ * will reclaim both active and inactive pages.
+ *
+ * We use the same threshold as pageout congestion_wait below.
+ */
+ if (sc->order > PAGE_ALLOC_COSTLY_ORDER)
+ mode = ISOLATE_BOTH;
+ else if (sc->order && priority < DEF_PRIORITY - 2)
+ mode = ISOLATE_BOTH;
nr_taken = sc->isolate_pages(sc->swap_cluster_max,
&page_list, &nr_scan, sc->order, mode,
* Put back any unfreeable pages.
*/
while (!list_empty(&page_list)) {
+ int lru;
page = lru_to_page(&page_list);
VM_BUG_ON(PageLRU(page));
- SetPageLRU(page);
list_del(&page->lru);
- add_page_to_lru_list(zone, page, page_lru(page));
+ if (unlikely(!page_evictable(page, NULL))) {
+ spin_unlock_irq(&zone->lru_lock);
+ putback_lru_page(page);
+ spin_lock_irq(&zone->lru_lock);
+ continue;
+ }
+ SetPageLRU(page);
+ lru = page_lru(page);
+ add_page_to_lru_list(zone, page, lru);
+ mem_cgroup_move_lists(page, lru);
if (PageActive(page) && scan_global_lru(sc)) {
int file = !!page_is_file_cache(page);
zone->recent_rotated[file]++;
int pgdeactivate = 0;
unsigned long pgscanned;
LIST_HEAD(l_hold); /* The pages which were snipped off */
- LIST_HEAD(l_active);
LIST_HEAD(l_inactive);
struct page *page;
struct pagevec pvec;
cond_resched();
page = lru_to_page(&l_hold);
list_del(&page->lru);
+
+ if (unlikely(!page_evictable(page, NULL))) {
+ putback_lru_page(page);
+ continue;
+ }
+
+ /* page_referenced clears PageReferenced */
+ if (page_mapping_inuse(page) &&
+ page_referenced(page, 0, sc->mem_cgroup))
+ pgmoved++;
+
list_add(&page->lru, &l_inactive);
}
/*
- * Count the referenced pages as rotated, even when they are moved
- * to the inactive list. This helps balance scan pressure between
- * file and anonymous pages in get_scan_ratio.
- */
+ * Count referenced pages from currently used mappings as
+ * rotated, even though they are moved to the inactive list.
+ * This helps balance scan pressure between file and anonymous
+ * pages in get_scan_ratio.
+ */
zone->recent_rotated[!!file] += pgmoved;
/*
- * Now put the pages back on the appropriate [file or anon] inactive
- * and active lists.
+ * Move the pages to the [file or anon] inactive list.
*/
pagevec_init(&pvec, 1);
+
pgmoved = 0;
lru = LRU_BASE + file * LRU_FILE;
spin_lock_irq(&zone->lru_lock);
ClearPageActive(page);
list_move(&page->lru, &zone->lru[lru].list);
- mem_cgroup_move_lists(page, false);
+ mem_cgroup_move_lists(page, lru);
pgmoved++;
if (!pagevec_add(&pvec, page)) {
__mod_zone_page_state(zone, NR_LRU_BASE + lru, pgmoved);
pagevec_strip(&pvec);
spin_lock_irq(&zone->lru_lock);
}
-
- pgmoved = 0;
- lru = LRU_ACTIVE + file * LRU_FILE;
- while (!list_empty(&l_active)) {
- page = lru_to_page(&l_active);
- prefetchw_prev_lru_page(page, &l_active, flags);
- VM_BUG_ON(PageLRU(page));
- SetPageLRU(page);
- VM_BUG_ON(!PageActive(page));
-
- list_move(&page->lru, &zone->lru[lru].list);
- mem_cgroup_move_lists(page, true);
- pgmoved++;
- if (!pagevec_add(&pvec, page)) {
- __mod_zone_page_state(zone, NR_LRU_BASE + lru, pgmoved);
- pgmoved = 0;
- spin_unlock_irq(&zone->lru_lock);
- if (vm_swap_full())
- pagevec_swap_free(&pvec);
- __pagevec_release(&pvec);
- spin_lock_irq(&zone->lru_lock);
- }
- }
- __mod_zone_page_state(zone, NR_LRU_BASE + lru, pgmoved);
-
__count_zone_vm_events(PGREFILL, zone, pgscanned);
__count_vm_events(PGDEACTIVATE, pgdeactivate);
spin_unlock_irq(&zone->lru_lock);
shrink_active_list(nr_to_scan, zone, sc, priority, file);
return 0;
}
- return shrink_inactive_list(nr_to_scan, zone, sc, file);
+ return shrink_inactive_list(nr_to_scan, zone, sc, priority, file);
}
/*
get_scan_ratio(zone, sc, percent);
- for_each_lru(l) {
+ for_each_evictable_lru(l) {
if (scan_global_lru(sc)) {
int file = is_file_lru(l);
int scan;
- /*
- * Add one to nr_to_scan just to make sure that the
- * kernel will slowly sift through each list.
- */
+
scan = zone_page_state(zone, NR_LRU_BASE + l);
if (priority) {
scan >>= priority;
scan = (scan * percent[file]) / 100;
}
- zone->lru[l].nr_scan += scan + 1;
+ zone->lru[l].nr_scan += scan;
nr[l] = zone->lru[l].nr_scan;
if (nr[l] >= sc->swap_cluster_max)
zone->lru[l].nr_scan = 0;
while (nr[LRU_INACTIVE_ANON] || nr[LRU_ACTIVE_FILE] ||
nr[LRU_INACTIVE_FILE]) {
- for_each_lru(l) {
+ for_each_evictable_lru(l) {
if (nr[l]) {
nr_to_scan = min(nr[l],
(unsigned long)sc->swap_cluster_max);
if (zone_is_all_unreclaimable(zone) && prio != DEF_PRIORITY)
continue;
- for_each_lru(l) {
- /* For pass = 0 we don't shrink the active list */
+ for_each_evictable_lru(l) {
+ /* For pass = 0, we don't shrink the active list */
if (pass == 0 &&
(l == LRU_ACTIVE || l == LRU_ACTIVE_FILE))
continue;
return ret;
}
#endif
+
+#ifdef CONFIG_UNEVICTABLE_LRU
+/*
+ * page_evictable - test whether a page is evictable
+ * @page: the page to test
+ * @vma: the VMA in which the page is or will be mapped, may be NULL
+ *
+ * Test whether page is evictable--i.e., should be placed on active/inactive
+ * lists vs unevictable list. The vma argument is !NULL when called from the
+ * fault path to determine how to instantate a new page.
+ *
+ * Reasons page might not be evictable:
+ * (1) page's mapping marked unevictable
+ * (2) page is part of an mlocked VMA
+ *
+ */
+int page_evictable(struct page *page, struct vm_area_struct *vma)
+{
+
+ if (mapping_unevictable(page_mapping(page)))
+ return 0;
+
+ if (PageMlocked(page) || (vma && is_mlocked_vma(vma, page)))
+ return 0;
+
+ return 1;
+}
+
+static void show_page_path(struct page *page)
+{
+ char buf[256];
+ if (page_is_file_cache(page)) {
+ struct address_space *mapping = page->mapping;
+ struct dentry *dentry;
+ pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT);
+
+ spin_lock(&mapping->i_mmap_lock);
+ dentry = d_find_alias(mapping->host);
+ printk(KERN_INFO "rescued: %s %lu\n",
+ dentry_path(dentry, buf, 256), pgoff);
+ spin_unlock(&mapping->i_mmap_lock);
+ } else {
+#if defined(CONFIG_MM_OWNER) && defined(CONFIG_MMU)
+ struct anon_vma *anon_vma;
+ struct vm_area_struct *vma;
+
+ anon_vma = page_lock_anon_vma(page);
+ if (!anon_vma)
+ return;
+
+ list_for_each_entry(vma, &anon_vma->head, anon_vma_node) {
+ printk(KERN_INFO "rescued: anon %s\n",
+ vma->vm_mm->owner->comm);
+ break;
+ }
+ page_unlock_anon_vma(anon_vma);
+#endif
+ }
+}
+
+
+/**
+ * check_move_unevictable_page - check page for evictability and move to appropriate zone lru list
+ * @page: page to check evictability and move to appropriate lru list
+ * @zone: zone page is in
+ *
+ * Checks a page for evictability and moves the page to the appropriate
+ * zone lru list.
+ *
+ * Restrictions: zone->lru_lock must be held, page must be on LRU and must
+ * have PageUnevictable set.
+ */
+static void check_move_unevictable_page(struct page *page, struct zone *zone)
+{
+ VM_BUG_ON(PageActive(page));
+
+retry:
+ ClearPageUnevictable(page);
+ if (page_evictable(page, NULL)) {
+ enum lru_list l = LRU_INACTIVE_ANON + page_is_file_cache(page);
+
+ show_page_path(page);
+
+ __dec_zone_state(zone, NR_UNEVICTABLE);
+ list_move(&page->lru, &zone->lru[l].list);
+ __inc_zone_state(zone, NR_INACTIVE_ANON + l);
+ __count_vm_event(UNEVICTABLE_PGRESCUED);
+ } else {
+ /*
+ * rotate unevictable list
+ */
+ SetPageUnevictable(page);
+ list_move(&page->lru, &zone->lru[LRU_UNEVICTABLE].list);
+ if (page_evictable(page, NULL))
+ goto retry;
+ }
+}
+
+/**
+ * scan_mapping_unevictable_pages - scan an address space for evictable pages
+ * @mapping: struct address_space to scan for evictable pages
+ *
+ * Scan all pages in mapping. Check unevictable pages for
+ * evictability and move them to the appropriate zone lru list.
+ */
+void scan_mapping_unevictable_pages(struct address_space *mapping)
+{
+ pgoff_t next = 0;
+ pgoff_t end = (i_size_read(mapping->host) + PAGE_CACHE_SIZE - 1) >>
+ PAGE_CACHE_SHIFT;
+ struct zone *zone;
+ struct pagevec pvec;
+
+ if (mapping->nrpages == 0)
+ return;
+
+ pagevec_init(&pvec, 0);
+ while (next < end &&
+ pagevec_lookup(&pvec, mapping, next, PAGEVEC_SIZE)) {
+ int i;
+ int pg_scanned = 0;
+
+ zone = NULL;
+
+ for (i = 0; i < pagevec_count(&pvec); i++) {
+ struct page *page = pvec.pages[i];
+ pgoff_t page_index = page->index;
+ struct zone *pagezone = page_zone(page);
+
+ pg_scanned++;
+ if (page_index > next)
+ next = page_index;
+ next++;
+
+ if (pagezone != zone) {
+ if (zone)
+ spin_unlock_irq(&zone->lru_lock);
+ zone = pagezone;
+ spin_lock_irq(&zone->lru_lock);
+ }
+
+ if (PageLRU(page) && PageUnevictable(page))
+ check_move_unevictable_page(page, zone);
+ }
+ if (zone)
+ spin_unlock_irq(&zone->lru_lock);
+ pagevec_release(&pvec);
+
+ count_vm_events(UNEVICTABLE_PGSCANNED, pg_scanned);
+ }
+
+}
+
+/**
+ * scan_zone_unevictable_pages - check unevictable list for evictable pages
+ * @zone - zone of which to scan the unevictable list
+ *
+ * Scan @zone's unevictable LRU lists to check for pages that have become
+ * evictable. Move those that have to @zone's inactive list where they
+ * become candidates for reclaim, unless shrink_inactive_zone() decides
+ * to reactivate them. Pages that are still unevictable are rotated
+ * back onto @zone's unevictable list.
+ */
+#define SCAN_UNEVICTABLE_BATCH_SIZE 16UL /* arbitrary lock hold batch size */
+void scan_zone_unevictable_pages(struct zone *zone)
+{
+ struct list_head *l_unevictable = &zone->lru[LRU_UNEVICTABLE].list;
+ unsigned long scan;
+ unsigned long nr_to_scan = zone_page_state(zone, NR_UNEVICTABLE);
+
+ while (nr_to_scan > 0) {
+ unsigned long batch_size = min(nr_to_scan,
+ SCAN_UNEVICTABLE_BATCH_SIZE);
+
+ spin_lock_irq(&zone->lru_lock);
+ for (scan = 0; scan < batch_size; scan++) {
+ struct page *page = lru_to_page(l_unevictable);
+
+ if (!trylock_page(page))
+ continue;
+
+ prefetchw_prev_lru_page(page, l_unevictable, flags);
+
+ if (likely(PageLRU(page) && PageUnevictable(page)))
+ check_move_unevictable_page(page, zone);
+
+ unlock_page(page);
+ }
+ spin_unlock_irq(&zone->lru_lock);
+
+ nr_to_scan -= batch_size;
+ }
+}
+
+
+/**
+ * scan_all_zones_unevictable_pages - scan all unevictable lists for evictable pages
+ *
+ * A really big hammer: scan all zones' unevictable LRU lists to check for
+ * pages that have become evictable. Move those back to the zones'
+ * inactive list where they become candidates for reclaim.
+ * This occurs when, e.g., we have unswappable pages on the unevictable lists,
+ * and we add swap to the system. As such, it runs in the context of a task
+ * that has possibly/probably made some previously unevictable pages
+ * evictable.
+ */
+void scan_all_zones_unevictable_pages(void)
+{
+ struct zone *zone;
+
+ for_each_zone(zone) {
+ scan_zone_unevictable_pages(zone);
+ }
+}
+
+/*
+ * scan_unevictable_pages [vm] sysctl handler. On demand re-scan of
+ * all nodes' unevictable lists for evictable pages
+ */
+unsigned long scan_unevictable_pages;
+
+int scan_unevictable_handler(struct ctl_table *table, int write,
+ struct file *file, void __user *buffer,
+ size_t *length, loff_t *ppos)
+{
+ proc_doulongvec_minmax(table, write, file, buffer, length, ppos);
+
+ if (write && *(unsigned long *)table->data)
+ scan_all_zones_unevictable_pages();
+
+ scan_unevictable_pages = 0;
+ return 0;
+}
+
+/*
+ * per node 'scan_unevictable_pages' attribute. On demand re-scan of
+ * a specified node's per zone unevictable lists for evictable pages.
+ */
+
+static ssize_t read_scan_unevictable_node(struct sys_device *dev,
+ struct sysdev_attribute *attr,
+ char *buf)
+{
+ return sprintf(buf, "0\n"); /* always zero; should fit... */
+}
+
+static ssize_t write_scan_unevictable_node(struct sys_device *dev,
+ struct sysdev_attribute *attr,
+ const char *buf, size_t count)
+{
+ struct zone *node_zones = NODE_DATA(dev->id)->node_zones;
+ struct zone *zone;
+ unsigned long res;
+ unsigned long req = strict_strtoul(buf, 10, &res);
+
+ if (!req)
+ return 1; /* zero is no-op */
+
+ for (zone = node_zones; zone - node_zones < MAX_NR_ZONES; ++zone) {
+ if (!populated_zone(zone))
+ continue;
+ scan_zone_unevictable_pages(zone);
+ }
+ return 1;
+}
+
+
+static SYSDEV_ATTR(scan_unevictable_pages, S_IRUGO | S_IWUSR,
+ read_scan_unevictable_node,
+ write_scan_unevictable_node);
+
+int scan_unevictable_register_node(struct node *node)
+{
+ return sysdev_create_file(&node->sysdev, &attr_scan_unevictable_pages);
+}
+
+void scan_unevictable_unregister_node(struct node *node)
+{
+ sysdev_remove_file(&node->sysdev, &attr_scan_unevictable_pages);
+}
+
+#endif