From: Andy Lutomirski <luto@xxxxxxxxxx>
Subject: mm: fix memcg stack accounting for sub-page stacks
We should account for stacks regardless of stack size, and we need to
account in sub-page units if THREAD_SIZE < PAGE_SIZE. Change the units to
kilobytes and Move it into account_kernel_stack().
Fixes: 12580e4b54ba8 ("mm: memcontrol: report kernel stack usage in cgroup2 memory.stat")
Link: http://lkml.kernel.org/r/9b5314e3ee5eda61b0317ec1563768602c1ef438.1468523549.git.luto@xxxxxxxxxx
Signed-off-by: Andy Lutomirski <luto@xxxxxxxxxx>
Cc: Vladimir Davydov <vdavydov@xxxxxxxxxxxxx>
Acked-by: Johannes Weiner <hannes@xxxxxxxxxxx>
Cc: Michal Hocko <mhocko@xxxxxxxxxx>
Reviewed-by: Josh Poimboeuf <jpoimboe@xxxxxxxxxx>
Reviewed-by: Vladimir Davydov <vdavydov@xxxxxxxxxxxxx>
Acked-by: Michal Hocko <mhocko@xxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
include/linux/memcontrol.h | 2 +-
kernel/fork.c | 19 ++++++++-----------
mm/memcontrol.c | 2 +-
3 files changed, 10 insertions(+), 13 deletions(-)
diff -puN include/linux/memcontrol.h~mm-fix-memcg-stack-accounting-for-sub-page-stacks include/linux/memcontrol.h
--- a/include/linux/memcontrol.h~mm-fix-memcg-stack-accounting-for-sub-page-stacks
+++ a/include/linux/memcontrol.h
@@ -52,7 +52,7 @@ enum mem_cgroup_stat_index {
MEM_CGROUP_STAT_SWAP, /* # of pages, swapped out */
MEM_CGROUP_STAT_NSTATS,
/* default hierarchy stats */
- MEMCG_KERNEL_STACK = MEM_CGROUP_STAT_NSTATS,
+ MEMCG_KERNEL_STACK_KB = MEM_CGROUP_STAT_NSTATS,
MEMCG_SLAB_RECLAIMABLE,
MEMCG_SLAB_UNRECLAIMABLE,
MEMCG_SOCK,
diff -puN kernel/fork.c~mm-fix-memcg-stack-accounting-for-sub-page-stacks kernel/fork.c
--- a/kernel/fork.c~mm-fix-memcg-stack-accounting-for-sub-page-stacks
+++ a/kernel/fork.c
@@ -165,20 +165,12 @@ static unsigned long *alloc_thread_stack
struct page *page = alloc_pages_node(node, THREADINFO_GFP,
THREAD_SIZE_ORDER);
- if (page)
- memcg_kmem_update_page_stat(page, MEMCG_KERNEL_STACK,
- 1 << THREAD_SIZE_ORDER);
-
return page ? page_address(page) : NULL;
}
static inline void free_thread_stack(unsigned long *stack)
{
- struct page *page = virt_to_page(stack);
-
- memcg_kmem_update_page_stat(page, MEMCG_KERNEL_STACK,
- -(1 << THREAD_SIZE_ORDER));
- __free_pages(page, THREAD_SIZE_ORDER);
+ __free_pages(virt_to_page(stack), THREAD_SIZE_ORDER);
}
# else
static struct kmem_cache *thread_stack_cache;
@@ -223,10 +215,15 @@ static struct kmem_cache *mm_cachep;
static void account_kernel_stack(unsigned long *stack, int account)
{
- struct zone *zone = page_zone(virt_to_page(stack));
+ /* All stack pages are in the same zone and belong to the same memcg. */
+ struct page *first_page = virt_to_page(stack);
- mod_zone_page_state(zone, NR_KERNEL_STACK_KB,
+ mod_zone_page_state(page_zone(first_page), NR_KERNEL_STACK_KB,
THREAD_SIZE / 1024 * account);
+
+ memcg_kmem_update_page_stat(
+ first_page, MEMCG_KERNEL_STACK_KB,
+ account * (THREAD_SIZE / 1024));
}
void free_task(struct task_struct *tsk)
diff -puN mm/memcontrol.c~mm-fix-memcg-stack-accounting-for-sub-page-stacks mm/memcontrol.c
--- a/mm/memcontrol.c~mm-fix-memcg-stack-accounting-for-sub-page-stacks
+++ a/mm/memcontrol.c
@@ -5171,7 +5171,7 @@ static int memory_stat_show(struct seq_f
seq_printf(m, "file %llu\n",
(u64)stat[MEM_CGROUP_STAT_CACHE] * PAGE_SIZE);
seq_printf(m, "kernel_stack %llu\n",
- (u64)stat[MEMCG_KERNEL_STACK] * PAGE_SIZE);
+ (u64)stat[MEMCG_KERNEL_STACK_KB] * 1024);
seq_printf(m, "slab %llu\n",
(u64)(stat[MEMCG_SLAB_RECLAIMABLE] +
stat[MEMCG_SLAB_UNRECLAIMABLE]) * PAGE_SIZE);
_
--
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
