| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <cfd5cc6f-5943-2e06-1dbe-f4b4ad5c1fa1@canonical.com>
Date: Fri, 28 Oct 2022 02:34:07 -0700
From: John Johansen <john.johansen@...onical.com>
To: Sergey Senozhatsky <senozhatsky@...omium.org>,
Sebastian Andrzej Siewior <bigeasy@...utronix.de>
Cc: Peter Zijlstra <peterz@...radead.org>,
Tomasz Figa <tfiga@...omium.org>, linux-kernel@...r.kernel.org,
linux-security-module@...r.kernel.org
Subject: Re: apparmor: global buffers spin lock may get contended
On 7/13/21 06:19, Sergey Senozhatsky wrote:
> Hi,
>
> We've notices that apparmor has switched from using per-CPU buffer pool
> and per-CPU spin_lock to a global spin_lock in df323337e507a0009d3db1ea.
>
> This seems to be causing some contention on our build machines (with
> quite a bit of cores). Because that global spin lock is a part of the
> stat() sys call (and perhaps some other)
>
> E.g.
>
> - 9.29% 0.00% clang++ [kernel.vmlinux]
> - 9.28% entry_SYSCALL_64_after_hwframe
> - 8.98% do_syscall_64
> - 7.43% __do_sys_newlstat
> - 7.43% vfs_statx
> - 7.18% security_inode_getattr
> - 7.15% apparmor_inode_getattr
> - aa_path_perm
> - 3.53% aa_get_buffer
> - 3.47% _raw_spin_lock
> 3.44% native_queued_spin_lock_slowpath
> - 3.49% aa_put_buffer.part.0
> - 3.45% _raw_spin_lock
> 3.43% native_queued_spin_lock_slowpath
>
> Can we fix this contention?
sorry for the delay on this. Below is a proposed patch that I have been testing
to deal with this issue.
From d026988196fdbda7234fb87bc3e4aea22edcbaf9 Mon Sep 17 00:00:00 2001
From: John Johansen <john.johansen@...onical.com>
Date: Tue, 25 Oct 2022 01:18:41 -0700
Subject: [PATCH] apparmor: cache buffers on percpu list if there is lock
contention
On a heavily loaded machine there can be lock contention on the
global buffers lock. Add a percpu list to cache buffers on when
lock contention is encountered.
When allocating buffers attempt to use cached buffers first,
before taking the global buffers lock. When freeing buffers
try to put them back to the global list but if contention is
encountered, put the buffer on the percpu list.
The length of time a buffer is held on the percpu list is dynamically
adjusted based on lock contention. The amount of hold time is rapidly
increased and slow ramped down.
Signed-off-by: John Johansen <john.johansen@...onical.com>
---
security/apparmor/lsm.c | 74 ++++++++++++++++++++++++++++++++++++++---
1 file changed, 69 insertions(+), 5 deletions(-)
diff --git a/security/apparmor/lsm.c b/security/apparmor/lsm.c
index 25114735bc11..0ab70171bdb6 100644
--- a/security/apparmor/lsm.c
+++ b/security/apparmor/lsm.c
@@ -49,12 +49,19 @@ union aa_buffer {
char buffer[1];
};
+struct aa_local_cache {
+ unsigned int contention;
+ unsigned int hold;
+ struct list_head head;
+};
+
#define RESERVE_COUNT 2
static int reserve_count = RESERVE_COUNT;
static int buffer_count;
static LIST_HEAD(aa_global_buffers);
static DEFINE_SPINLOCK(aa_buffers_lock);
+static DEFINE_PER_CPU(struct aa_local_cache, aa_local_buffers);
/*
* LSM hook functions
@@ -1622,14 +1629,44 @@ static int param_set_mode(const char *val, const struct kernel_param *kp)
return 0;
}
+static void update_contention(struct aa_local_cache *cache)
+{
+ cache->contention += 3;
+ if (cache->contention > 9)
+ cache->contention = 9;
+ cache->hold += 1 << cache->contention; /* 8, 64, 512 */
+}
+
char *aa_get_buffer(bool in_atomic)
{
union aa_buffer *aa_buf;
+ struct aa_local_cache *cache;
bool try_again = true;
gfp_t flags = (GFP_KERNEL | __GFP_RETRY_MAYFAIL | __GFP_NOWARN);
+ /* use per cpu cached buffers first */
+ cache = get_cpu_ptr(&aa_local_buffers);
+ if (!list_empty(&cache->head)) {
+ aa_buf = list_first_entry(&cache->head, union aa_buffer, list);
+ list_del(&aa_buf->list);
+ cache->hold--;
+ put_cpu_ptr(&aa_local_buffers);
+ return &aa_buf->buffer[0];
+ }
+ put_cpu_ptr(&aa_local_buffers);
+
+ if (!spin_trylock(&aa_buffers_lock)) {
+ cache = get_cpu_ptr(&aa_local_buffers);
+ update_contention(cache);
+ put_cpu_ptr(&aa_local_buffers);
+ spin_lock(&aa_buffers_lock);
+ } else {
+ cache = get_cpu_ptr(&aa_local_buffers);
+ if (cache->contention)
+ cache->contention--;
+ put_cpu_ptr(&aa_local_buffers);
+ }
retry:
- spin_lock(&aa_buffers_lock);
if (buffer_count > reserve_count ||
(in_atomic && !list_empty(&aa_global_buffers))) {
aa_buf = list_first_entry(&aa_global_buffers, union aa_buffer,
@@ -1655,6 +1692,7 @@ char *aa_get_buffer(bool in_atomic)
if (!aa_buf) {
if (try_again) {
try_again = false;
+ spin_lock(&aa_buffers_lock);
goto retry;
}
pr_warn_once("AppArmor: Failed to allocate a memory buffer.\n");
@@ -1666,15 +1704,32 @@ char *aa_get_buffer(bool in_atomic)
void aa_put_buffer(char *buf)
{
union aa_buffer *aa_buf;
+ struct aa_local_cache *cache;
if (!buf)
return;
aa_buf = container_of(buf, union aa_buffer, buffer[0]);
- spin_lock(&aa_buffers_lock);
- list_add(&aa_buf->list, &aa_global_buffers);
- buffer_count++;
- spin_unlock(&aa_buffers_lock);
+ cache = get_cpu_ptr(&aa_local_buffers);
+ if (!cache->hold) {
+ put_cpu_ptr(&aa_local_buffers);
+ if (spin_trylock(&aa_buffers_lock)) {
+ list_add(&aa_buf->list, &aa_global_buffers);
+ buffer_count++;
+ spin_unlock(&aa_buffers_lock);
+ cache = get_cpu_ptr(&aa_local_buffers);
+ if (cache->contention)
+ cache->contention--;
+ put_cpu_ptr(&aa_local_buffers);
+ return;
+ }
+ cache = get_cpu_ptr(&aa_local_buffers);
+ update_contention(cache);
+ }
+
+ /* cache in percpu list */
+ list_add(&aa_buf->list, &cache->head);
+ put_cpu_ptr(&aa_local_buffers);
}
/*
@@ -1716,6 +1771,15 @@ static int __init alloc_buffers(void)
union aa_buffer *aa_buf;
int i, num;
+ /*
+ * per cpu set of cached allocated buffers used to help reduce
+ * lock contention
+ */
+ for_each_possible_cpu(i) {
+ per_cpu(aa_local_buffers, i).contention = 0;
+ per_cpu(aa_local_buffers, i).hold = 0;
+ INIT_LIST_HEAD(&per_cpu(aa_local_buffers, i).head);
+ }
/*
* A function may require two buffers at once. Usually the buffers are
* used for a short period of time and are shared. On UP kernel buffers
--
2.34.1
Powered by blists - more mailing lists