extern void mem_cgroup_record_reclaim_priority(struct mem_cgroup *mem,
int priority);
-extern long mem_cgroup_calc_reclaim_active(struct mem_cgroup *mem,
- struct zone *zone, int priority);
-extern long mem_cgroup_calc_reclaim_inactive(struct mem_cgroup *mem,
- struct zone *zone, int priority);
+extern long mem_cgroup_calc_reclaim(struct mem_cgroup *mem, struct zone *zone,
+ int priority, enum lru_list lru);
#else /* CONFIG_CGROUP_MEM_RES_CTLR */
static inline void page_reset_bad_cgroup(struct page *page)
{
}
-static inline long mem_cgroup_calc_reclaim_active(struct mem_cgroup *mem,
- struct zone *zone, int priority)
-{
- return 0;
-}
-
-static inline long mem_cgroup_calc_reclaim_inactive(struct mem_cgroup *mem,
- struct zone *zone, int priority)
+static inline long mem_cgroup_calc_reclaim(struct mem_cgroup *mem,
+ struct zone *zone, int priority,
+ enum lru_list lru)
{
return 0;
}
+static inline void
+add_page_to_lru_list(struct zone *zone, struct page *page, enum lru_list l)
+{
+ list_add(&page->lru, &zone->lru[l].list);
+ __inc_zone_state(zone, NR_LRU_BASE + l);
+}
+
+static inline void
+del_page_from_lru_list(struct zone *zone, struct page *page, enum lru_list l)
+{
+ list_del(&page->lru);
+ __dec_zone_state(zone, NR_LRU_BASE + l);
+}
+
static inline void
add_page_to_active_list(struct zone *zone, struct page *page)
{
- list_add(&page->lru, &zone->active_list);
- __inc_zone_state(zone, NR_ACTIVE);
+ add_page_to_lru_list(zone, page, LRU_ACTIVE);
}
static inline void
add_page_to_inactive_list(struct zone *zone, struct page *page)
{
- list_add(&page->lru, &zone->inactive_list);
- __inc_zone_state(zone, NR_INACTIVE);
+ add_page_to_lru_list(zone, page, LRU_INACTIVE);
}
static inline void
del_page_from_active_list(struct zone *zone, struct page *page)
{
- list_del(&page->lru);
- __dec_zone_state(zone, NR_ACTIVE);
+ del_page_from_lru_list(zone, page, LRU_ACTIVE);
}
static inline void
del_page_from_inactive_list(struct zone *zone, struct page *page)
{
- list_del(&page->lru);
- __dec_zone_state(zone, NR_INACTIVE);
+ del_page_from_lru_list(zone, page, LRU_INACTIVE);
}
static inline void
del_page_from_lru(struct zone *zone, struct page *page)
{
+ enum lru_list l = LRU_INACTIVE;
+
list_del(&page->lru);
if (PageActive(page)) {
__ClearPageActive(page);
- __dec_zone_state(zone, NR_ACTIVE);
- } else {
- __dec_zone_state(zone, NR_INACTIVE);
+ l = LRU_ACTIVE;
}
+ __dec_zone_state(zone, NR_LRU_BASE + l);
}
+/**
+ * page_lru - which LRU list should a page be on?
+ * @page: the page to test
+ *
+ * Returns the LRU list a page should be on, as an index
+ * into the array of LRU lists.
+ */
+static inline enum lru_list page_lru(struct page *page)
+{
+ enum lru_list lru = LRU_BASE;
+
+ if (PageActive(page))
+ lru += LRU_ACTIVE;
+
+ return lru;
+}
enum zone_stat_item {
/* First 128 byte cacheline (assuming 64 bit words) */
NR_FREE_PAGES,
- NR_INACTIVE,
- NR_ACTIVE,
+ NR_LRU_BASE,
+ NR_INACTIVE = NR_LRU_BASE, /* must match order of LRU_[IN]ACTIVE */
+ NR_ACTIVE, /* " " " " " */
NR_ANON_PAGES, /* Mapped anonymous pages */
NR_FILE_MAPPED, /* pagecache pages mapped into pagetables.
only modified from process context */
#endif
NR_VM_ZONE_STAT_ITEMS };
+enum lru_list {
+ LRU_BASE,
+ LRU_INACTIVE=LRU_BASE, /* must match order of NR_[IN]ACTIVE */
+ LRU_ACTIVE, /* " " " " " */
+ NR_LRU_LISTS };
+
+#define for_each_lru(l) for (l = 0; l < NR_LRU_LISTS; l++)
+
+static inline int is_active_lru(enum lru_list l)
+{
+ return (l == LRU_ACTIVE);
+}
+
struct per_cpu_pages {
int count; /* number of pages in the list */
int high; /* high watermark, emptying needed */
/* Fields commonly accessed by the page reclaim scanner */
spinlock_t lru_lock;
- struct list_head active_list;
- struct list_head inactive_list;
- unsigned long nr_scan_active;
- unsigned long nr_scan_inactive;
+ struct {
+ struct list_head list;
+ unsigned long nr_scan;
+ } lru[NR_LRU_LISTS];
unsigned long pages_scanned; /* since last reclaim */
unsigned long flags; /* zone flags, see below */
#include <linux/fs.h>
#include <linux/seq_file.h>
#include <linux/vmalloc.h>
+#include <linux/mm_inline.h>
#include <asm/uaccess.h>
/*
* per-zone information in memory controller.
*/
-
-enum mem_cgroup_zstat_index {
- MEM_CGROUP_ZSTAT_ACTIVE,
- MEM_CGROUP_ZSTAT_INACTIVE,
-
- NR_MEM_CGROUP_ZSTAT,
-};
-
struct mem_cgroup_per_zone {
/*
* spin_lock to protect the per cgroup LRU
*/
spinlock_t lru_lock;
- struct list_head active_list;
- struct list_head inactive_list;
- unsigned long count[NR_MEM_CGROUP_ZSTAT];
+ struct list_head lists[NR_LRU_LISTS];
+ unsigned long count[NR_LRU_LISTS];
};
/* Macro for accessing counter */
#define MEM_CGROUP_ZSTAT(mz, idx) ((mz)->count[(idx)])
}
static unsigned long mem_cgroup_get_all_zonestat(struct mem_cgroup *mem,
- enum mem_cgroup_zstat_index idx)
+ enum lru_list idx)
{
int nid, zid;
struct mem_cgroup_per_zone *mz;
struct page_cgroup *pc)
{
int from = pc->flags & PAGE_CGROUP_FLAG_ACTIVE;
+ int lru = !!from;
- if (from)
- MEM_CGROUP_ZSTAT(mz, MEM_CGROUP_ZSTAT_ACTIVE) -= 1;
- else
- MEM_CGROUP_ZSTAT(mz, MEM_CGROUP_ZSTAT_INACTIVE) -= 1;
+ MEM_CGROUP_ZSTAT(mz, lru) -= 1;
mem_cgroup_charge_statistics(pc->mem_cgroup, pc->flags, false);
list_del(&pc->lru);
static void __mem_cgroup_add_list(struct mem_cgroup_per_zone *mz,
struct page_cgroup *pc)
{
- int to = pc->flags & PAGE_CGROUP_FLAG_ACTIVE;
+ int lru = LRU_INACTIVE;
+
+ if (pc->flags & PAGE_CGROUP_FLAG_ACTIVE)
+ lru += LRU_ACTIVE;
+
+ MEM_CGROUP_ZSTAT(mz, lru) += 1;
+ list_add(&pc->lru, &mz->lists[lru]);
- if (!to) {
- MEM_CGROUP_ZSTAT(mz, MEM_CGROUP_ZSTAT_INACTIVE) += 1;
- list_add(&pc->lru, &mz->inactive_list);
- } else {
- MEM_CGROUP_ZSTAT(mz, MEM_CGROUP_ZSTAT_ACTIVE) += 1;
- list_add(&pc->lru, &mz->active_list);
- }
mem_cgroup_charge_statistics(pc->mem_cgroup, pc->flags, true);
}
static void __mem_cgroup_move_lists(struct page_cgroup *pc, bool active)
{
- int from = pc->flags & PAGE_CGROUP_FLAG_ACTIVE;
struct mem_cgroup_per_zone *mz = page_cgroup_zoneinfo(pc);
+ int lru = LRU_INACTIVE;
- if (from)
- MEM_CGROUP_ZSTAT(mz, MEM_CGROUP_ZSTAT_ACTIVE) -= 1;
- else
- MEM_CGROUP_ZSTAT(mz, MEM_CGROUP_ZSTAT_INACTIVE) -= 1;
+ if (pc->flags & PAGE_CGROUP_FLAG_ACTIVE)
+ lru += LRU_ACTIVE;
- if (active) {
- MEM_CGROUP_ZSTAT(mz, MEM_CGROUP_ZSTAT_ACTIVE) += 1;
+ MEM_CGROUP_ZSTAT(mz, lru) -= 1;
+
+ if (active)
pc->flags |= PAGE_CGROUP_FLAG_ACTIVE;
- list_move(&pc->lru, &mz->active_list);
- } else {
- MEM_CGROUP_ZSTAT(mz, MEM_CGROUP_ZSTAT_INACTIVE) += 1;
+ else
pc->flags &= ~PAGE_CGROUP_FLAG_ACTIVE;
- list_move(&pc->lru, &mz->inactive_list);
- }
+
+ lru = !!active;
+ MEM_CGROUP_ZSTAT(mz, lru) += 1;
+ list_move(&pc->lru, &mz->lists[lru]);
}
int task_in_mem_cgroup(struct task_struct *task, const struct mem_cgroup *mem)
{
unsigned long active, inactive;
/* active and inactive are the number of pages. 'long' is ok.*/
- active = mem_cgroup_get_all_zonestat(mem, MEM_CGROUP_ZSTAT_ACTIVE);
- inactive = mem_cgroup_get_all_zonestat(mem, MEM_CGROUP_ZSTAT_INACTIVE);
+ active = mem_cgroup_get_all_zonestat(mem, LRU_ACTIVE);
+ inactive = mem_cgroup_get_all_zonestat(mem, LRU_INACTIVE);
return (long) (active / (inactive + 1));
}
* (see include/linux/mmzone.h)
*/
-long mem_cgroup_calc_reclaim_active(struct mem_cgroup *mem,
- struct zone *zone, int priority)
+long mem_cgroup_calc_reclaim(struct mem_cgroup *mem, struct zone *zone,
+ int priority, enum lru_list lru)
{
- long nr_active;
+ long nr_pages;
int nid = zone->zone_pgdat->node_id;
int zid = zone_idx(zone);
struct mem_cgroup_per_zone *mz = mem_cgroup_zoneinfo(mem, nid, zid);
- nr_active = MEM_CGROUP_ZSTAT(mz, MEM_CGROUP_ZSTAT_ACTIVE);
- return (nr_active >> priority);
-}
-
-long mem_cgroup_calc_reclaim_inactive(struct mem_cgroup *mem,
- struct zone *zone, int priority)
-{
- long nr_inactive;
- int nid = zone->zone_pgdat->node_id;
- int zid = zone_idx(zone);
- struct mem_cgroup_per_zone *mz = mem_cgroup_zoneinfo(mem, nid, zid);
+ nr_pages = MEM_CGROUP_ZSTAT(mz, lru);
- nr_inactive = MEM_CGROUP_ZSTAT(mz, MEM_CGROUP_ZSTAT_INACTIVE);
- return (nr_inactive >> priority);
+ return (nr_pages >> priority);
}
unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan,
int nid = z->zone_pgdat->node_id;
int zid = zone_idx(z);
struct mem_cgroup_per_zone *mz;
+ int lru = !!active;
BUG_ON(!mem_cont);
mz = mem_cgroup_zoneinfo(mem_cont, nid, zid);
- if (active)
- src = &mz->active_list;
- else
- src = &mz->inactive_list;
-
+ src = &mz->lists[lru];
spin_lock(&mz->lru_lock);
scan = 0;
#define FORCE_UNCHARGE_BATCH (128)
static void mem_cgroup_force_empty_list(struct mem_cgroup *mem,
struct mem_cgroup_per_zone *mz,
- int active)
+ enum lru_list lru)
{
struct page_cgroup *pc;
struct page *page;
unsigned long flags;
struct list_head *list;
- if (active)
- list = &mz->active_list;
- else
- list = &mz->inactive_list;
+ list = &mz->lists[lru];
spin_lock_irqsave(&mz->lru_lock, flags);
while (!list_empty(list)) {
for_each_node_state(node, N_POSSIBLE)
for (zid = 0; zid < MAX_NR_ZONES; zid++) {
struct mem_cgroup_per_zone *mz;
+ enum lru_list l;
mz = mem_cgroup_zoneinfo(mem, node, zid);
- /* drop all page_cgroup in active_list */
- mem_cgroup_force_empty_list(mem, mz, 1);
- /* drop all page_cgroup in inactive_list */
- mem_cgroup_force_empty_list(mem, mz, 0);
+ for_each_lru(l)
+ mem_cgroup_force_empty_list(mem, mz, l);
}
}
ret = 0;
unsigned long active, inactive;
inactive = mem_cgroup_get_all_zonestat(mem_cont,
- MEM_CGROUP_ZSTAT_INACTIVE);
+ LRU_INACTIVE);
active = mem_cgroup_get_all_zonestat(mem_cont,
- MEM_CGROUP_ZSTAT_ACTIVE);
+ LRU_ACTIVE);
cb->fill(cb, "active", (active) * PAGE_SIZE);
cb->fill(cb, "inactive", (inactive) * PAGE_SIZE);
}
{
struct mem_cgroup_per_node *pn;
struct mem_cgroup_per_zone *mz;
+ enum lru_list l;
int zone, tmp = node;
/*
* This routine is called against possible nodes.
for (zone = 0; zone < MAX_NR_ZONES; zone++) {
mz = &pn->zoneinfo[zone];
- INIT_LIST_HEAD(&mz->active_list);
- INIT_LIST_HEAD(&mz->inactive_list);
spin_lock_init(&mz->lru_lock);
+ for_each_lru(l)
+ INIT_LIST_HEAD(&mz->lists[l]);
}
return 0;
}
for (j = 0; j < MAX_NR_ZONES; j++) {
struct zone *zone = pgdat->node_zones + j;
unsigned long size, realsize, memmap_pages;
+ enum lru_list l;
size = zone_spanned_pages_in_node(nid, j, zones_size);
realsize = size - zone_absent_pages_in_node(nid, j,
zone->prev_priority = DEF_PRIORITY;
zone_pcp_init(zone);
- INIT_LIST_HEAD(&zone->active_list);
- INIT_LIST_HEAD(&zone->inactive_list);
- zone->nr_scan_active = 0;
- zone->nr_scan_inactive = 0;
+ for_each_lru(l) {
+ INIT_LIST_HEAD(&zone->lru[l].list);
+ zone->lru[l].nr_scan = 0;
+ }
zap_zone_vm_stats(zone);
zone->flags = 0;
if (!size)
spin_lock(&zone->lru_lock);
}
if (PageLRU(page) && !PageActive(page)) {
- list_move_tail(&page->lru, &zone->inactive_list);
+ list_move_tail(&page->lru, &zone->lru[LRU_INACTIVE].list);
pgmoved++;
}
}
int active)
{
if (active)
- return isolate_lru_pages(nr, &z->active_list, dst,
+ return isolate_lru_pages(nr, &z->lru[LRU_ACTIVE].list, dst,
scanned, order, mode);
else
- return isolate_lru_pages(nr, &z->inactive_list, dst,
+ return isolate_lru_pages(nr, &z->lru[LRU_INACTIVE].list, dst,
scanned, order, mode);
}
VM_BUG_ON(PageLRU(page));
SetPageLRU(page);
list_del(&page->lru);
- if (PageActive(page))
- add_page_to_active_list(zone, page);
- else
- add_page_to_inactive_list(zone, page);
+ add_page_to_lru_list(zone, page, page_lru(page));
if (!pagevec_add(&pvec, page)) {
spin_unlock_irq(&zone->lru_lock);
__pagevec_release(&pvec);
int pgdeactivate = 0;
unsigned long pgscanned;
LIST_HEAD(l_hold); /* The pages which were snipped off */
- LIST_HEAD(l_inactive); /* Pages to go onto the inactive_list */
- LIST_HEAD(l_active); /* Pages to go onto the active_list */
+ LIST_HEAD(l_active);
+ LIST_HEAD(l_inactive);
struct page *page;
struct pagevec pvec;
int reclaim_mapped = 0;
VM_BUG_ON(!PageActive(page));
ClearPageActive(page);
- list_move(&page->lru, &zone->inactive_list);
+ list_move(&page->lru, &zone->lru[LRU_INACTIVE].list);
mem_cgroup_move_lists(page, false);
pgmoved++;
if (!pagevec_add(&pvec, page)) {
SetPageLRU(page);
VM_BUG_ON(!PageActive(page));
- list_move(&page->lru, &zone->active_list);
+ list_move(&page->lru, &zone->lru[LRU_ACTIVE].list);
mem_cgroup_move_lists(page, true);
pgmoved++;
if (!pagevec_add(&pvec, page)) {
pagevec_release(&pvec);
}
+static unsigned long shrink_list(enum lru_list l, unsigned long nr_to_scan,
+ struct zone *zone, struct scan_control *sc, int priority)
+{
+ if (l == LRU_ACTIVE) {
+ shrink_active_list(nr_to_scan, zone, sc, priority);
+ return 0;
+ }
+ return shrink_inactive_list(nr_to_scan, zone, sc);
+}
+
/*
* This is a basic per-zone page freer. Used by both kswapd and direct reclaim.
*/
static unsigned long shrink_zone(int priority, struct zone *zone,
struct scan_control *sc)
{
- unsigned long nr_active;
- unsigned long nr_inactive;
+ unsigned long nr[NR_LRU_LISTS];
unsigned long nr_to_scan;
unsigned long nr_reclaimed = 0;
+ enum lru_list l;
if (scan_global_lru(sc)) {
/*
* Add one to nr_to_scan just to make sure that the kernel
* will slowly sift through the active list.
*/
- zone->nr_scan_active +=
- (zone_page_state(zone, NR_ACTIVE) >> priority) + 1;
- nr_active = zone->nr_scan_active;
- zone->nr_scan_inactive +=
- (zone_page_state(zone, NR_INACTIVE) >> priority) + 1;
- nr_inactive = zone->nr_scan_inactive;
- if (nr_inactive >= sc->swap_cluster_max)
- zone->nr_scan_inactive = 0;
- else
- nr_inactive = 0;
-
- if (nr_active >= sc->swap_cluster_max)
- zone->nr_scan_active = 0;
- else
- nr_active = 0;
+ for_each_lru(l) {
+ zone->lru[l].nr_scan += (zone_page_state(zone,
+ NR_LRU_BASE + l) >> priority) + 1;
+ nr[l] = zone->lru[l].nr_scan;
+ if (nr[l] >= sc->swap_cluster_max)
+ zone->lru[l].nr_scan = 0;
+ else
+ nr[l] = 0;
+ }
} else {
/*
* This reclaim occurs not because zone memory shortage but
* because memory controller hits its limit.
* Then, don't modify zone reclaim related data.
*/
- nr_active = mem_cgroup_calc_reclaim_active(sc->mem_cgroup,
- zone, priority);
+ nr[LRU_ACTIVE] = mem_cgroup_calc_reclaim(sc->mem_cgroup,
+ zone, priority, LRU_ACTIVE);
- nr_inactive = mem_cgroup_calc_reclaim_inactive(sc->mem_cgroup,
- zone, priority);
+ nr[LRU_INACTIVE] = mem_cgroup_calc_reclaim(sc->mem_cgroup,
+ zone, priority, LRU_INACTIVE);
}
-
- while (nr_active || nr_inactive) {
- if (nr_active) {
- nr_to_scan = min(nr_active,
+ while (nr[LRU_ACTIVE] || nr[LRU_INACTIVE]) {
+ for_each_lru(l) {
+ if (nr[l]) {
+ nr_to_scan = min(nr[l],
(unsigned long)sc->swap_cluster_max);
- nr_active -= nr_to_scan;
- shrink_active_list(nr_to_scan, zone, sc, priority);
- }
+ nr[l] -= nr_to_scan;
- if (nr_inactive) {
- nr_to_scan = min(nr_inactive,
- (unsigned long)sc->swap_cluster_max);
- nr_inactive -= nr_to_scan;
- nr_reclaimed += shrink_inactive_list(nr_to_scan, zone,
- sc);
+ nr_reclaimed += shrink_list(l, nr_to_scan,
+ zone, sc, priority);
+ }
}
}
{
struct zone *zone;
unsigned long nr_to_scan, ret = 0;
+ enum lru_list l;
for_each_zone(zone) {
if (zone_is_all_unreclaimable(zone) && prio != DEF_PRIORITY)
continue;
- /* For pass = 0 we don't shrink the active list */
- if (pass > 0) {
- zone->nr_scan_active +=
- (zone_page_state(zone, NR_ACTIVE) >> prio) + 1;
- if (zone->nr_scan_active >= nr_pages || pass > 3) {
- zone->nr_scan_active = 0;
+ for_each_lru(l) {
+ /* For pass = 0 we don't shrink the active list */
+ if (pass == 0 && l == LRU_ACTIVE)
+ continue;
+
+ zone->lru[l].nr_scan +=
+ (zone_page_state(zone, NR_LRU_BASE + l)
+ >> prio) + 1;
+ if (zone->lru[l].nr_scan >= nr_pages || pass > 3) {
+ zone->lru[l].nr_scan = 0;
nr_to_scan = min(nr_pages,
- zone_page_state(zone, NR_ACTIVE));
- shrink_active_list(nr_to_scan, zone, sc, prio);
+ zone_page_state(zone,
+ NR_LRU_BASE + l));
+ ret += shrink_list(l, nr_to_scan, zone,
+ sc, prio);
+ if (ret >= nr_pages)
+ return ret;
}
}
-
- zone->nr_scan_inactive +=
- (zone_page_state(zone, NR_INACTIVE) >> prio) + 1;
- if (zone->nr_scan_inactive >= nr_pages || pass > 3) {
- zone->nr_scan_inactive = 0;
- nr_to_scan = min(nr_pages,
- zone_page_state(zone, NR_INACTIVE));
- ret += shrink_inactive_list(nr_to_scan, zone, sc);
- if (ret >= nr_pages)
- return ret;
- }
}
return ret;
zone->pages_low,
zone->pages_high,
zone->pages_scanned,
- zone->nr_scan_active, zone->nr_scan_inactive,
+ zone->lru[LRU_ACTIVE].nr_scan,
+ zone->lru[LRU_INACTIVE].nr_scan,
zone->spanned_pages,
zone->present_pages);