The patch titled
memory cgroup enhancements: force_empty interface for dropping all account in empty cgroup
has been added to the -mm tree. Its filename is
memory-cgroup-enhancements-force_empty-interface-for-dropping-all-account-in-empty-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: memory cgroup enhancements: force_empty interface for dropping all account in empty cgroup
From: KAMEZAWA Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx>
This patch adds an interface "memory.force_empty". Any write to this file
will drop all charges in this cgroup if there is no task under.
%echo 1 > /....../memory.force_empty
will drop all charges of memory cgroup if cgroup's tasks is empty.
This is useful to invoke rmdir() against memory cgroup successfully.
Tested and worked well on x86_64/fake-NUMA system.
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx>
Cc: Balbir Singh <balbir@xxxxxxxxxxxxxxxxxx>
Cc: Pavel Emelianov <xemul@xxxxxxxxxx>
Cc: Paul Menage <menage@xxxxxxxxxx>
Cc: Peter Zijlstra <a.p.zijlstra@xxxxxxxxx>
Cc: "Eric W. Biederman" <ebiederm@xxxxxxxxxxxx>
Cc: Nick Piggin <nickpiggin@xxxxxxxxxxxx>
Cc: Kirill Korotaev <dev@xxxxx>
Cc: Herbert Poetzl <herbert@xxxxxxxxxxxx>
Cc: David Rientjes <rientjes@xxxxxxxxxx>
Cc: Vaidyanathan Srinivasan <svaidy@xxxxxxxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
mm/memcontrol.c | 110 +++++++++++++++++++++++++++++++++++++++++++---
1 file changed, 103 insertions(+), 7 deletions(-)
diff -puN mm/memcontrol.c~memory-cgroup-enhancements-force_empty-interface-for-dropping-all-account-in-empty-cgroup mm/memcontrol.c
--- a/mm/memcontrol.c~memory-cgroup-enhancements-force_empty-interface-for-dropping-all-account-in-empty-cgroup
+++ a/mm/memcontrol.c
@@ -480,6 +480,7 @@ void mem_cgroup_uncharge(struct page_cgr
page = pc->page;
/*
* get page->cgroup and clear it under lock.
+ * force_empty can drop page->cgroup without checking refcnt.
*/
if (clear_page_cgroup(page, pc) == pc) {
mem = pc->mem_cgroup;
@@ -489,13 +490,6 @@ void mem_cgroup_uncharge(struct page_cgr
list_del_init(&pc->lru);
spin_unlock_irqrestore(&mem->lru_lock, flags);
kfree(pc);
- } else {
- /*
- * Note:This will be removed when force-empty patch is
- * applied. just show warning here.
- */
- printk(KERN_ERR "Race in mem_cgroup_uncharge() ?");
- dump_stack();
}
}
}
@@ -543,6 +537,76 @@ retry:
return;
}
+/*
+ * This routine traverse page_cgroup in given list and drop them all.
+ * This routine ignores page_cgroup->ref_cnt.
+ * *And* this routine doesn't reclaim page itself, just removes page_cgroup.
+ */
+#define FORCE_UNCHARGE_BATCH (128)
+static void
+mem_cgroup_force_empty_list(struct mem_cgroup *mem, struct list_head *list)
+{
+ struct page_cgroup *pc;
+ struct page *page;
+ int count;
+ unsigned long flags;
+
+retry:
+ count = FORCE_UNCHARGE_BATCH;
+ spin_lock_irqsave(&mem->lru_lock, flags);
+
+ while (--count && !list_empty(list)) {
+ pc = list_entry(list->prev, struct page_cgroup, lru);
+ page = pc->page;
+ /* Avoid race with charge */
+ atomic_set(&pc->ref_cnt, 0);
+ if (clear_page_cgroup(page, pc) == pc) {
+ css_put(&mem->css);
+ res_counter_uncharge(&mem->res, PAGE_SIZE);
+ list_del_init(&pc->lru);
+ kfree(pc);
+ } else /* being uncharged ? ...do relax */
+ break;
+ }
+ spin_unlock_irqrestore(&mem->lru_lock, flags);
+ if (!list_empty(list)) {
+ cond_resched();
+ goto retry;
+ }
+ return;
+}
+
+/*
+ * make mem_cgroup's charge to be 0 if there is no task.
+ * This enables deleting this mem_cgroup.
+ */
+
+int mem_cgroup_force_empty(struct mem_cgroup *mem)
+{
+ int ret = -EBUSY;
+ css_get(&mem->css);
+ /*
+ * page reclaim code (kswapd etc..) will move pages between
+` * active_list <-> inactive_list while we don't take a lock.
+ * So, we have to do loop here until all lists are empty.
+ */
+ while (!(list_empty(&mem->active_list) &&
+ list_empty(&mem->inactive_list))) {
+ if (atomic_read(&mem->css.cgroup->count) > 0)
+ goto out;
+ /* drop all page_cgroup in active_list */
+ mem_cgroup_force_empty_list(mem, &mem->active_list);
+ /* drop all page_cgroup in inactive_list */
+ mem_cgroup_force_empty_list(mem, &mem->inactive_list);
+ }
+ ret = 0;
+out:
+ css_put(&mem->css);
+ return ret;
+}
+
+
+
int mem_cgroup_write_strategy(char *buf, unsigned long long *tmp)
{
*tmp = memparse(buf, &buf);
@@ -628,6 +692,33 @@ static ssize_t mem_control_type_read(str
ppos, buf, s - buf);
}
+
+static ssize_t mem_force_empty_write(struct cgroup *cont,
+ struct cftype *cft, struct file *file,
+ const char __user *userbuf,
+ size_t nbytes, loff_t *ppos)
+{
+ struct mem_cgroup *mem = mem_cgroup_from_cont(cont);
+ int ret;
+ ret = mem_cgroup_force_empty(mem);
+ if (!ret)
+ ret = nbytes;
+ return ret;
+}
+
+/*
+ * Note: This should be removed if cgroup supports write-only file.
+ */
+
+static ssize_t mem_force_empty_read(struct cgroup *cont,
+ struct cftype *cft,
+ struct file *file, char __user *userbuf,
+ size_t nbytes, loff_t *ppos)
+{
+ return -EINVAL;
+}
+
+
static struct cftype mem_cgroup_files[] = {
{
.name = "usage_in_bytes",
@@ -650,6 +741,11 @@ static struct cftype mem_cgroup_files[]
.write = mem_control_type_write,
.read = mem_control_type_read,
},
+ {
+ .name = "force_empty",
+ .write = mem_force_empty_write,
+ .read = mem_force_empty_read,
+ },
};
static struct mem_cgroup init_mem_cgroup;
_
Patches currently in -mm which might be from kamezawa.hiroyu@xxxxxxxxxxxxxx are
git-sh.patch
memory-hotplug-add-removable-to-sysfs-to-show-memblock-removability.patch
pie-executable-randomization.patch
pie-executable-randomization-checkpatch-fixes.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-memorystat-file.patch
memory-cgroup-enhancements-add-pre_destroy-handler.patch
memory-cgroup-enhancements-implicit-force-empty-at-rmdir.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
