Revision f0a3a24b532d9a7e56a33c5112b2a212ed6ec580 authored by Roman Gushchin on 12 July 2019, 03:56:27 UTC, committed by Linus Torvalds on 12 July 2019, 18:05:44 UTC
Currently each charged slab page holds a reference to the cgroup to which
it's charged. Kmem_caches are held by the memcg and are released all
together with the memory cgroup. It means that none of kmem_caches are
released unless at least one reference to the memcg exists, which is very
far from optimal.
Let's rework it in a way that allows releasing individual kmem_caches as
soon as the cgroup is offline, the kmem_cache is empty and there are no
pending allocations.
To make it possible, let's introduce a new percpu refcounter for non-root
kmem caches. The counter is initialized to the percpu mode, and is
switched to the atomic mode during kmem_cache deactivation. The counter
is bumped for every charged page and also for every running allocation.
So the kmem_cache can't be released unless all allocations complete.
To shutdown non-active empty kmem_caches, let's reuse the work queue,
previously used for the kmem_cache deactivation. Once the reference
counter reaches 0, let's schedule an asynchronous kmem_cache release.
* I used the following simple approach to test the performance
(stolen from another patchset by T. Harding):
time find / -name fname-no-exist
echo 2 > /proc/sys/vm/drop_caches
repeat 10 times
Results:
orig patched
real 0m1.455s real 0m1.355s
user 0m0.206s user 0m0.219s
sys 0m0.855s sys 0m0.807s
real 0m1.487s real 0m1.699s
user 0m0.221s user 0m0.256s
sys 0m0.806s sys 0m0.948s
real 0m1.515s real 0m1.505s
user 0m0.183s user 0m0.215s
sys 0m0.876s sys 0m0.858s
real 0m1.291s real 0m1.380s
user 0m0.193s user 0m0.198s
sys 0m0.843s sys 0m0.786s
real 0m1.364s real 0m1.374s
user 0m0.180s user 0m0.182s
sys 0m0.868s sys 0m0.806s
real 0m1.352s real 0m1.312s
user 0m0.201s user 0m0.212s
sys 0m0.820s sys 0m0.761s
real 0m1.302s real 0m1.349s
user 0m0.205s user 0m0.203s
sys 0m0.803s sys 0m0.792s
real 0m1.334s real 0m1.301s
user 0m0.194s user 0m0.201s
sys 0m0.806s sys 0m0.779s
real 0m1.426s real 0m1.434s
user 0m0.216s user 0m0.181s
sys 0m0.824s sys 0m0.864s
real 0m1.350s real 0m1.295s
user 0m0.200s user 0m0.190s
sys 0m0.842s sys 0m0.811s
So it looks like the difference is not noticeable in this test.
[cai@lca.pw: fix an use-after-free in kmemcg_workfn()]
Link: http://lkml.kernel.org/r/1560977573-10715-1-git-send-email-cai@lca.pw
Link: http://lkml.kernel.org/r/20190611231813.3148843-9-guro@fb.com
Signed-off-by: Roman Gushchin <guro@fb.com>
Signed-off-by: Qian Cai <cai@lca.pw>
Acked-by: Vladimir Davydov <vdavydov.dev@gmail.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Waiman Long <longman@redhat.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Andrei Vagin <avagin@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
1 parent 63b02ef
audit.c
// SPDX-License-Identifier: GPL-2.0
#include <linux/init.h>
#include <linux/types.h>
#include <linux/audit.h>
#include <asm/unistd.h>
static unsigned dir_class[] = {
#include <asm-generic/audit_dir_write.h>
~0U
};
static unsigned read_class[] = {
#include <asm-generic/audit_read.h>
~0U
};
static unsigned write_class[] = {
#include <asm-generic/audit_write.h>
~0U
};
static unsigned chattr_class[] = {
#include <asm-generic/audit_change_attr.h>
~0U
};
static unsigned signal_class[] = {
#include <asm-generic/audit_signal.h>
~0U
};
int audit_classify_arch(int arch)
{
if (audit_is_compat(arch))
return 1;
else
return 0;
}
int audit_classify_syscall(int abi, unsigned syscall)
{
if (audit_is_compat(abi))
return audit_classify_compat_syscall(abi, syscall);
switch(syscall) {
#ifdef __NR_open
case __NR_open:
return 2;
#endif
#ifdef __NR_openat
case __NR_openat:
return 3;
#endif
#ifdef __NR_socketcall
case __NR_socketcall:
return 4;
#endif
#ifdef __NR_execveat
case __NR_execveat:
#endif
case __NR_execve:
return 5;
default:
return 0;
}
}
static int __init audit_classes_init(void)
{
#ifdef CONFIG_AUDIT_COMPAT_GENERIC
audit_register_class(AUDIT_CLASS_WRITE_32, compat_write_class);
audit_register_class(AUDIT_CLASS_READ_32, compat_read_class);
audit_register_class(AUDIT_CLASS_DIR_WRITE_32, compat_dir_class);
audit_register_class(AUDIT_CLASS_CHATTR_32, compat_chattr_class);
audit_register_class(AUDIT_CLASS_SIGNAL_32, compat_signal_class);
#endif
audit_register_class(AUDIT_CLASS_WRITE, write_class);
audit_register_class(AUDIT_CLASS_READ, read_class);
audit_register_class(AUDIT_CLASS_DIR_WRITE, dir_class);
audit_register_class(AUDIT_CLASS_CHATTR, chattr_class);
audit_register_class(AUDIT_CLASS_SIGNAL, signal_class);
return 0;
}
__initcall(audit_classes_init);
Computing file changes ...
