From 58056f77502f3567b760c9a8fc8d2e9081515b2d Mon Sep 17 00:00:00 2001
From: Shakeel Butt <shakeelb@google.com>
Date: Fri, 5 Nov 2021 13:37:44 -0700
Subject: [PATCH] memcg, kmem: further deprecate kmem.limit_in_bytes
Git-commit: 58056f77502f3567b760c9a8fc8d2e9081515b2d
Patch-mainline: v5.16-rc1
References: bsc#1206896
mhocko@suse.com:
I am referencing bsc#1206896 although this is not a fix for the reported
CVE. Kmem accounting has never been supported so this patch disables the
feature altogether which also removes the only (remotely) potential
attack vector.
The deprecation process of kmem.limit_in_bytes started with the commit
0158115f702 ("memcg, kmem: deprecate kmem.limit_in_bytes") which also
explains in detail the motivation behind the deprecation. To summarize,
it is the unexpected behavior on hitting the kmem limit. This patch
moves the deprecation process to the next stage by disallowing to set
the kmem limit. In future we might just remove the kmem.limit_in_bytes
file completely.
[akpm@linux-foundation.org: s/ENOTSUPP/EOPNOTSUPP/]
[arnd@arndb.de: mark cancel_charge() inline]
Link: https://lkml.kernel.org/r/20211022070542.679839-1-arnd@kernel.org
Link: https://lkml.kernel.org/r/20211019153408.2916808-1-shakeelb@google.com
Signed-off-by: Shakeel Butt <shakeelb@google.com>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Roman Gushchin <guro@fb.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Reviewed-by: Muchun Song <songmuchun@bytedance.com>
Cc: Vasily Averin <vvs@virtuozzo.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
.../admin-guide/cgroup-v1/memory.rst | 11 +-----
mm/memcontrol.c | 39 +++----------------
2 files changed, 7 insertions(+), 43 deletions(-)
diff --git a/Documentation/admin-guide/cgroup-v1/memory.rst b/Documentation/admin-guide/cgroup-v1/memory.rst
index 41191b5fb69d..faac50149a22 100644
--- a/Documentation/admin-guide/cgroup-v1/memory.rst
+++ b/Documentation/admin-guide/cgroup-v1/memory.rst
@@ -87,10 +87,8 @@ Brief summary of control files.
memory.oom_control set/show oom controls.
memory.numa_stat show the number of memory usage per numa
node
- memory.kmem.limit_in_bytes set/show hard limit for kernel memory
- This knob is deprecated and shouldn't be
- used. It is planned that this be removed in
- the foreseeable future.
+ memory.kmem.limit_in_bytes This knob is deprecated and writing to
+ it will return -ENOTSUPP.
memory.kmem.usage_in_bytes show current kernel memory allocation
memory.kmem.failcnt show the number of kernel memory usage
hits limits
@@ -518,11 +516,6 @@ will be charged as a new owner of it.
charged file caches. Some out-of-use page caches may keep charged until
memory pressure happens. If you want to avoid that, force_empty will be useful.
- Also, note that when memory.kmem.limit_in_bytes is set the charges due to
- kernel pages will still be seen. This is not considered a failure and the
- write will still return success. In this case, it is expected that
- memory.kmem.usage_in_bytes == memory.usage_in_bytes.
-
5.2 stat file
-------------
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index e092cce3c96e..e4fcb6e55f75 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -2771,8 +2771,7 @@ static inline int try_charge(struct mem_cgroup *memcg, gfp_t gfp_mask,
return try_charge_memcg(memcg, gfp_mask, nr_pages);
}
-#if defined(CONFIG_MEMCG_KMEM) || defined(CONFIG_MMU)
-static void cancel_charge(struct mem_cgroup *memcg, unsigned int nr_pages)
+static inline void cancel_charge(struct mem_cgroup *memcg, unsigned int nr_pages)
{
if (mem_cgroup_is_root(memcg))
return;
@@ -2781,7 +2780,6 @@ static void cancel_charge(struct mem_cgroup *memcg, unsigned int nr_pages)
if (do_memsw_account())
page_counter_uncharge(&memcg->memsw, nr_pages);
}
-#endif
static void commit_charge(struct page *page, struct mem_cgroup *memcg)
{
@@ -3000,7 +2998,6 @@ static void obj_cgroup_uncharge_pages(struct obj_cgroup *objcg,
static int obj_cgroup_charge_pages(struct obj_cgroup *objcg, gfp_t gfp,
unsigned int nr_pages)
{
- struct page_counter *counter;
struct mem_cgroup *memcg;
int ret;
@@ -3010,21 +3007,8 @@ static int obj_cgroup_charge_pages(struct obj_cgroup *objcg, gfp_t gfp,
if (ret)
goto out;
- if (!cgroup_subsys_on_dfl(memory_cgrp_subsys) &&
- !page_counter_try_charge(&memcg->kmem, nr_pages, &counter)) {
-
- /*
- * Enforce __GFP_NOFAIL allocation because callers are not
- * prepared to see failures and likely do not have any failure
- * handling code.
- */
- if (gfp & __GFP_NOFAIL) {
- page_counter_charge(&memcg->kmem, nr_pages);
- goto out;
- }
- cancel_charge(memcg, nr_pages);
- ret = -ENOMEM;
- }
+ if (!cgroup_subsys_on_dfl(memory_cgrp_subsys))
+ page_counter_charge(&memcg->kmem, nr_pages);
out:
css_put(&memcg->css);
@@ -3714,17 +3698,6 @@ static void memcg_offline_kmem(struct mem_cgroup *memcg)
}
#endif /* CONFIG_MEMCG_KMEM */
-static int memcg_update_kmem_max(struct mem_cgroup *memcg,
- unsigned long max)
-{
- int ret;
-
- mutex_lock(&memcg_max_mutex);
- ret = page_counter_set_max(&memcg->kmem, max);
- mutex_unlock(&memcg_max_mutex);
- return ret;
-}
-
static int memcg_update_tcp_max(struct mem_cgroup *memcg, unsigned long max)
{
int ret;
@@ -3790,10 +3763,8 @@ static ssize_t mem_cgroup_write(struct kernfs_open_file *of,
ret = mem_cgroup_resize_max(memcg, nr_pages, true);
break;
case _KMEM:
- pr_warn_once("kmem.limit_in_bytes is deprecated and will be removed. "
- "Please report your usecase to linux-mm@kvack.org if you "
- "depend on this functionality.\n");
- ret = memcg_update_kmem_max(memcg, nr_pages);
+ /* kmem.limit_in_bytes is deprecated. */
+ ret = -EOPNOTSUPP;
break;
case _TCP:
ret = memcg_update_tcp_max(memcg, nr_pages);
--
2.35.3