The patch titled
per-zone and reclaim enhancements for memory controller: per-zone-lock for cgroup
has been added to the -mm tree. Its filename is
per-zone-and-reclaim-enhancements-for-memory-controller-take-3-per-zone-lock-for-cgroup.patch
*** Remember to use Documentation/SubmitChecklist when testing your code ***
See http://www.zip.com.au/~akpm/linux/patches/stuff/added-to-mm.txt to find
out what to do about this
------------------------------------------------------
Subject: per-zone and reclaim enhancements for memory controller: per-zone-lock for cgroup
From: KAMEZAWA Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx>
Now, lru is per-zone.
Then, lru_lock can be (should be) per-zone, too.
This patch implementes per-zone lru lock.
lru_lock is placed into mem_cgroup_per_zone struct.
lock can be accessed by
mz = mem_cgroup_zoneinfo(mem_cgroup, node, zone);
&mz->lru_lock
or
mz = page_cgroup_zoneinfo(page_cgroup);
&mz->lru_lock
Signed-off-by: KAMEZAWA hiroyuki <kmaezawa.hiroyu@xxxxxxxxxxxxxx>
Cc: "Eric W. Biederman" <ebiederm@xxxxxxxxxxxx>
Cc: Balbir Singh <balbir@xxxxxxxxxxxxxxxxxx>
Cc: David Rientjes <rientjes@xxxxxxxxxx>
Cc: Herbert Poetzl <herbert@xxxxxxxxxxxx>
Cc: Kirill Korotaev <dev@xxxxx>
Cc: Nick Piggin <nickpiggin@xxxxxxxxxxxx>
Cc: Paul Menage <menage@xxxxxxxxxx>
Cc: Pavel Emelianov <xemul@xxxxxxxxxx>
Cc: Peter Zijlstra <a.p.zijlstra@xxxxxxxxx>
Cc: Vaidyanathan Srinivasan <svaidy@xxxxxxxxxxxxxxxxxx>
Cc: Rik van Riel <riel@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
mm/memcontrol.c | 71 ++++++++++++++++++++++++++++------------------
1 file changed, 44 insertions(+), 27 deletions(-)
diff -puN mm/memcontrol.c~per-zone-and-reclaim-enhancements-for-memory-controller-take-3-per-zone-lock-for-cgroup mm/memcontrol.c
--- a/mm/memcontrol.c~per-zone-and-reclaim-enhancements-for-memory-controller-take-3-per-zone-lock-for-cgroup
+++ a/mm/memcontrol.c
@@ -89,6 +89,10 @@ enum mem_cgroup_zstat_index {
};
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];
@@ -126,10 +130,7 @@ struct mem_cgroup {
* per zone LRU lists.
*/
struct mem_cgroup_lru_info info;
- /*
- * spin_lock to protect the per cgroup LRU
- */
- spinlock_t lru_lock;
+
unsigned long control_type; /* control RSS or RSS+Pagecache */
int prev_priority; /* for recording reclaim priority */
/*
@@ -410,15 +411,16 @@ int task_in_mem_cgroup(struct task_struc
*/
void mem_cgroup_move_lists(struct page_cgroup *pc, bool active)
{
- struct mem_cgroup *mem;
+ struct mem_cgroup_per_zone *mz;
+ unsigned long flags;
+
if (!pc)
return;
- mem = pc->mem_cgroup;
-
- spin_lock(&mem->lru_lock);
+ mz = page_cgroup_zoneinfo(pc);
+ spin_lock_irqsave(&mz->lru_lock, flags);
__mem_cgroup_move_lists(pc, active);
- spin_unlock(&mem->lru_lock);
+ spin_unlock_irqrestore(&mz->lru_lock, flags);
}
/*
@@ -528,7 +530,7 @@ unsigned long mem_cgroup_isolate_pages(u
src = &mz->inactive_list;
- spin_lock(&mem_cont->lru_lock);
+ spin_lock(&mz->lru_lock);
scan = 0;
list_for_each_entry_safe_reverse(pc, tmp, src, lru) {
if (scan >= nr_to_scan)
@@ -558,7 +560,7 @@ unsigned long mem_cgroup_isolate_pages(u
}
list_splice(&pc_list, src);
- spin_unlock(&mem_cont->lru_lock);
+ spin_unlock(&mz->lru_lock);
*scanned = scan;
return nr_taken;
@@ -577,6 +579,7 @@ static int mem_cgroup_charge_common(stru
struct page_cgroup *pc;
unsigned long flags;
unsigned long nr_retries = MEM_CGROUP_RECLAIM_RETRIES;
+ struct mem_cgroup_per_zone *mz;
/*
* Should page_cgroup's go to their own slab?
@@ -688,10 +691,11 @@ noreclaim:
goto retry;
}
- spin_lock_irqsave(&mem->lru_lock, flags);
+ mz = page_cgroup_zoneinfo(pc);
+ spin_lock_irqsave(&mz->lru_lock, flags);
/* Update statistics vector */
__mem_cgroup_add_list(pc);
- spin_unlock_irqrestore(&mem->lru_lock, flags);
+ spin_unlock_irqrestore(&mz->lru_lock, flags);
done:
return 0;
@@ -733,6 +737,7 @@ int mem_cgroup_cache_charge(struct page
void mem_cgroup_uncharge(struct page_cgroup *pc)
{
struct mem_cgroup *mem;
+ struct mem_cgroup_per_zone *mz;
struct page *page;
unsigned long flags;
@@ -745,6 +750,7 @@ void mem_cgroup_uncharge(struct page_cgr
if (atomic_dec_and_test(&pc->ref_cnt)) {
page = pc->page;
+ mz = page_cgroup_zoneinfo(pc);
/*
* get page->cgroup and clear it under lock.
* force_empty can drop page->cgroup without checking refcnt.
@@ -753,9 +759,9 @@ void mem_cgroup_uncharge(struct page_cgr
mem = pc->mem_cgroup;
css_put(&mem->css);
res_counter_uncharge(&mem->res, PAGE_SIZE);
- spin_lock_irqsave(&mem->lru_lock, flags);
+ spin_lock_irqsave(&mz->lru_lock, flags);
__mem_cgroup_remove_list(pc);
- spin_unlock_irqrestore(&mem->lru_lock, flags);
+ spin_unlock_irqrestore(&mz->lru_lock, flags);
kfree(pc);
}
}
@@ -794,24 +800,29 @@ void mem_cgroup_page_migration(struct pa
struct page_cgroup *pc;
struct mem_cgroup *mem;
unsigned long flags;
+ struct mem_cgroup_per_zone *mz;
retry:
pc = page_get_page_cgroup(page);
if (!pc)
return;
mem = pc->mem_cgroup;
+ mz = page_cgroup_zoneinfo(pc);
if (clear_page_cgroup(page, pc) != pc)
goto retry;
-
- spin_lock_irqsave(&mem->lru_lock, flags);
+ spin_lock_irqsave(&mz->lru_lock, flags);
__mem_cgroup_remove_list(pc);
+ spin_unlock_irqrestore(&mz->lru_lock, flags);
+
pc->page = newpage;
lock_page_cgroup(newpage);
page_assign_page_cgroup(newpage, pc);
unlock_page_cgroup(newpage);
- __mem_cgroup_add_list(pc);
- spin_unlock_irqrestore(&mem->lru_lock, flags);
+ mz = page_cgroup_zoneinfo(pc);
+ spin_lock_irqsave(&mz->lru_lock, flags);
+ __mem_cgroup_add_list(pc);
+ spin_unlock_irqrestore(&mz->lru_lock, flags);
return;
}
@@ -822,18 +833,26 @@ retry:
*/
#define FORCE_UNCHARGE_BATCH (128)
static void
-mem_cgroup_force_empty_list(struct mem_cgroup *mem, struct list_head *list)
+mem_cgroup_force_empty_list(struct mem_cgroup *mem,
+ struct mem_cgroup_per_zone *mz,
+ int active)
{
struct page_cgroup *pc;
struct page *page;
int count;
unsigned long flags;
+ struct list_head *list;
+
+ if (active)
+ list = &mz->active_list;
+ else
+ list = &mz->inactive_list;
if (list_empty(list))
return;
retry:
count = FORCE_UNCHARGE_BATCH;
- spin_lock_irqsave(&mem->lru_lock, flags);
+ spin_lock_irqsave(&mz->lru_lock, flags);
while (--count && !list_empty(list)) {
pc = list_entry(list->prev, struct page_cgroup, lru);
@@ -850,7 +869,7 @@ retry:
} else /* being uncharged ? ...do relax */
break;
}
- spin_unlock_irqrestore(&mem->lru_lock, flags);
+ spin_unlock_irqrestore(&mz->lru_lock, flags);
if (!list_empty(list)) {
cond_resched();
goto retry;
@@ -881,11 +900,9 @@ int mem_cgroup_force_empty(struct mem_cg
struct mem_cgroup_per_zone *mz;
mz = mem_cgroup_zoneinfo(mem, node, zid);
/* drop all page_cgroup in active_list */
- mem_cgroup_force_empty_list(mem,
- &mz->active_list);
+ mem_cgroup_force_empty_list(mem, mz, 1);
/* drop all page_cgroup in inactive_list */
- mem_cgroup_force_empty_list(mem,
- &mz->inactive_list);
+ mem_cgroup_force_empty_list(mem, mz, 0);
}
}
ret = 0;
@@ -1112,6 +1129,7 @@ static int alloc_mem_cgroup_per_zone_inf
mz = &pn->zoneinfo[zone];
INIT_LIST_HEAD(&mz->active_list);
INIT_LIST_HEAD(&mz->inactive_list);
+ spin_lock_init(&mz->lru_lock);
}
return 0;
}
@@ -1136,7 +1154,6 @@ mem_cgroup_create(struct cgroup_subsys *
res_counter_init(&mem->res);
- spin_lock_init(&mem->lru_lock);
mem->control_type = MEM_CGROUP_TYPE_ALL;
memset(&mem->info, 0, sizeof(mem->info));
_
Patches currently in -mm which might be from kamezawa.hiroyu@xxxxxxxxxxxxxx are
memory-hotplug-fix-fix-section-mismatch-in-vmammap_allock_block.patch
memory-hotplug-x86_64-fix-section-mismatch-in-init_memory_mapping.patch
swapoff-scan-ptes-preemptibly.patch
memory-hotplug-add-removable-to-sysfs-to-show-memblock-removability.patch
add-remove_memory-for-ppc64-2.patch
enable-hotplug-memory-remove-for-ppc64.patch
add-arch-specific-walk_memory_remove-for-ppc64.patch
pie-executable-randomization.patch
pie-executable-randomization-uninlining.patch
pie-executable-randomization-checkpatch-fixes.patch
memcgroup-temporarily-revert-swapoff-mod.patch
memory-controller-make-charging-gfp-mask-aware-fix.patch
bugfix-for-memory-cgroup-controller-charge-refcnt-race-fix.patch
bugfix-for-memory-cgroup-controller-fix-error-handling-path-in-mem_charge_cgroup.patch
bugfix-for-memory-controller-add-helper-function-for-assigning-cgroup-to-page.patch
bugfix-for-memory-cgroup-controller-avoid-pagelru-page-in-mem_cgroup_isolate_pages.patch
bugfix-for-memory-cgroup-controller-avoid-pagelru-page-in-mem_cgroup_isolate_pages-fix.patch
bugfix-for-memory-cgroup-controller-migration-under-memory-controller-fix.patch
memory-cgroup-enhancements-fix-zone-handling-in-try_to_free_mem_cgroup_page.patch
memory-cgroup-enhancements-force_empty-interface-for-dropping-all-account-in-empty-cgroup.patch
memory-cgroup-enhancements-remember-a-page-is-charged-as-page-cache.patch
memory-cgroup-enhancements-remember-a-page-is-on-active-list-of-cgroup-or-not.patch
memory-cgroup-enhancements-add-status-accounting-function-for-memory-cgroup.patch
memory-cgroup-enhancements-add-status-accounting-function-for-memory-cgroup-checkpatch-fixes.patch
memory-cgroup-enhancements-add-status-accounting-function-for-memory-cgroup-fix-1.patch
memory-cgroup-enhancements-add-status-accounting-function-for-memory-cgroup-uninlining.patch
memory-cgroup-enhancements-add-status-accounting-function-for-memory-cgroup-fix-2.patch
memory-cgroup-enhancements-add-memorystat-file.patch
memory-cgroup-enhancements-add-memorystat-file-checkpatch-fixes.patch
memory-cgroup-enhancements-add-memorystat-file-printk-fix.patch
memory-cgroup-enhancements-add-pre_destroy-handler.patch
memory-cgroup-enhancements-implicit-force_empty-at-rmdir.patch
per-zone-and-reclaim-enhancements-for-memory-controller-take-3-add-scan_global_lru-macro.patch
per-zone-and-reclaim-enhancements-for-memory-controller-take-3-nid-zid-helper-function-for-cgroup.patch
per-zone-and-reclaim-enhancements-for-memory-controller-take-3-per-zone-active-inactive-counter.patch
per-zone-and-reclaim-enhancements-for-memory-controller-take-3-calculate-mapper_ratio-per-cgroup.patch
per-zone-and-reclaim-enhancements-for-memory-controller-take-3-calculate-active-inactive-imbalance-per-cgroup.patch
per-zone-and-reclaim-enhancements-for-memory-controller-take-3-remember-reclaim-priority-in-memory-cgroup.patch
per-zone-and-reclaim-enhancements-for-memory-controller-take-3-calculate-the-number-of-pages-to-be-scanned-per-cgroup.patch
per-zone-and-reclaim-enhancements-for-memory-controller-take-3-modifies-vmscanc-for-isolate-globa-cgroup-lru-activity.patch
per-zone-and-reclaim-enhancements-for-memory-controller-take-3-per-zone-lru-for-cgroup.patch
per-zone-and-reclaim-enhancements-for-memory-controller-take-3-per-zone-lock-for-cgroup.patch
-
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
