diff options
author | Tejun Heo <tj@kernel.org> | 2015-11-05 18:46:17 -0800 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2015-11-05 19:34:48 -0800 |
commit | 10d53c748bc9531f47e13f98e32ef28be4399862 (patch) | |
tree | e216064fe3e937f5badc231ae6b0986ed5296d52 /mm/memcontrol.c | |
parent | cbfb479809c1b8d871cb9a31832e065e900a24c1 (diff) | |
download | linux-10d53c748bc9531f47e13f98e32ef28be4399862.tar.gz linux-10d53c748bc9531f47e13f98e32ef28be4399862.tar.bz2 linux-10d53c748bc9531f47e13f98e32ef28be4399862.zip |
memcg: ratify and consolidate over-charge handling
try_charge() is the main charging logic of memcg. When it hits the limit
but either can't fail the allocation due to __GFP_NOFAIL or the task is
likely to free memory very soon, being OOM killed, has SIGKILL pending or
exiting, it "bypasses" the charge to the root memcg and returns -EINTR.
While this is one approach which can be taken for these situations, it has
several issues.
* It unnecessarily lies about the reality. The number itself doesn't
go over the limit but the actual usage does. memcg is either forced
to or actively chooses to go over the limit because that is the
right behavior under the circumstances, which is completely fine,
but, if at all avoidable, it shouldn't be misrepresenting what's
happening by sneaking the charges into the root memcg.
* Despite trying, we already do over-charge. kmemcg can't deal with
switching over to the root memcg by the point try_charge() returns
-EINTR, so it open-codes over-charing.
* It complicates the callers. Each try_charge() user has to handle
the weird -EINTR exception. memcg_charge_kmem() does the manual
over-charging. mem_cgroup_do_precharge() performs unnecessary
uncharging of root memcg, which BTW is inconsistent with what
memcg_charge_kmem() does but not broken as [un]charging are noops on
root memcg. mem_cgroup_try_charge() needs to switch the returned
cgroup to the root one.
The reality is that in memcg there are cases where we are forced and/or
willing to go over the limit. Each such case needs to be scrutinized and
justified but there definitely are situations where that is the right
thing to do. We alredy do this but with a superficial and inconsistent
disguise which leads to unnecessary complications.
This patch updates try_charge() so that it over-charges and returns 0 when
deemed necessary. -EINTR return is removed along with all special case
handling in the callers.
While at it, remove the local variable @ret, which was initialized to zero
and never changed, along with done: label which just returned the always
zero @ret.
Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Vladimir Davydov <vdavydov@parallels.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm/memcontrol.c')
-rw-r--r-- | mm/memcontrol.c | 69 |
1 files changed, 20 insertions, 49 deletions
diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 327dcda3ebf6..b952abef6ff0 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -2008,13 +2008,12 @@ static int try_charge(struct mem_cgroup *memcg, gfp_t gfp_mask, unsigned long nr_reclaimed; bool may_swap = true; bool drained = false; - int ret = 0; if (mem_cgroup_is_root(memcg)) - goto done; + return 0; retry: if (consume_stock(memcg, nr_pages)) - goto done; + return 0; if (!do_swap_account || !page_counter_try_charge(&memcg->memsw, batch, &counter)) { @@ -2042,7 +2041,7 @@ retry: if (unlikely(test_thread_flag(TIF_MEMDIE) || fatal_signal_pending(current) || current->flags & PF_EXITING)) - goto bypass; + goto force; if (unlikely(task_in_memcg_oom(current))) goto nomem; @@ -2088,10 +2087,10 @@ retry: goto retry; if (gfp_mask & __GFP_NOFAIL) - goto bypass; + goto force; if (fatal_signal_pending(current)) - goto bypass; + goto force; mem_cgroup_events(mem_over_limit, MEMCG_OOM, 1); @@ -2099,8 +2098,18 @@ retry: nomem: if (!(gfp_mask & __GFP_NOFAIL)) return -ENOMEM; -bypass: - return -EINTR; +force: + /* + * The allocation either can't fail or will lead to more memory + * being freed very soon. Allow memory usage go over the limit + * temporarily by force charging it. + */ + page_counter_charge(&memcg->memory, nr_pages); + if (do_swap_account) + page_counter_charge(&memcg->memsw, nr_pages); + css_get_many(&memcg->css, nr_pages); + + return 0; done_restock: css_get_many(&memcg->css, batch); @@ -2123,8 +2132,8 @@ done_restock: break; } } while ((memcg = parent_mem_cgroup(memcg))); -done: - return ret; + + return 0; } static void cancel_charge(struct mem_cgroup *memcg, unsigned int nr_pages) @@ -2216,28 +2225,7 @@ int memcg_charge_kmem(struct mem_cgroup *memcg, gfp_t gfp, return ret; ret = try_charge(memcg, gfp, nr_pages); - if (ret == -EINTR) { - /* - * try_charge() chose to bypass to root due to OOM kill or - * fatal signal. Since our only options are to either fail - * the allocation or charge it to this cgroup, do it as a - * temporary condition. But we can't fail. From a kmem/slab - * perspective, the cache has already been selected, by - * mem_cgroup_kmem_get_cache(), so it is too late to change - * our minds. - * - * This condition will only trigger if the task entered - * memcg_charge_kmem in a sane state, but was OOM-killed - * during try_charge() above. Tasks that were already dying - * when the allocation triggers should have been already - * directed to the root cgroup in memcontrol.h - */ - page_counter_charge(&memcg->memory, nr_pages); - if (do_swap_account) - page_counter_charge(&memcg->memsw, nr_pages); - css_get_many(&memcg->css, nr_pages); - ret = 0; - } else if (ret) + if (ret) page_counter_uncharge(&memcg->kmem, nr_pages); return ret; @@ -4438,22 +4426,10 @@ static int mem_cgroup_do_precharge(unsigned long count) mc.precharge += count; return ret; } - if (ret == -EINTR) { - cancel_charge(root_mem_cgroup, count); - return ret; - } /* Try charges one by one with reclaim */ while (count--) { ret = try_charge(mc.to, GFP_KERNEL & ~__GFP_NORETRY, 1); - /* - * In case of failure, any residual charges against - * mc.to will be dropped by mem_cgroup_clear_mc() - * later on. However, cancel any charges that are - * bypassed to root right away or they'll be lost. - */ - if (ret == -EINTR) - cancel_charge(root_mem_cgroup, 1); if (ret) return ret; mc.precharge++; @@ -5358,11 +5334,6 @@ int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm, ret = try_charge(memcg, gfp_mask, nr_pages); css_put(&memcg->css); - - if (ret == -EINTR) { - memcg = root_mem_cgroup; - ret = 0; - } out: *memcgp = memcg; return ret; |