| 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
| ||
|
Date: Wed, 22 Jun 2022 22:51:00 +0000
From: "Joel Fernandes (Google)" <joel@...lfernandes.org>
To: rcu@...r.kernel.org
Cc: linux-kernel@...r.kernel.org, rushikesh.s.kadam@...el.com,
urezki@...il.com, neeraj.iitr10@...il.com, frederic@...nel.org,
paulmck@...nel.org, rostedt@...dmis.org, vineeth@...byteword.org,
"Joel Fernandes (Google)" <joel@...lfernandes.org>
Subject: [PATCH v2 6/8] rcuscale: Add test for using call_rcu_lazy() to emulate kfree_rcu()
Reuse the kfree_rcu() test in order to be able to compare the memory reclaiming
properties of call_rcu_lazy() with kfree_rcu().
With this test, we find similar memory footprint and time call_rcu_lazy()
free'ing takes compared to kfree_rcu(). Also we confirm that call_rcu_lazy()
can survive OOM during extremely frequent calls.
If we really push it, i.e. boot system with low memory and compare
kfree_rcu() with call_rcu_lazy(), I find that call_rcu_lazy() is more
resilient and is much harder to produce OOM as compared to kfree_rcu().
Signed-off-by: Joel Fernandes (Google) <joel@...lfernandes.org>
---
kernel/rcu/rcu.h | 6 ++++
kernel/rcu/rcuscale.c | 64 +++++++++++++++++++++++++++++++++++++++++-
kernel/rcu/tree_nocb.h | 17 ++++++++++-
3 files changed, 85 insertions(+), 2 deletions(-)
diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h
index 71c0f45e70c3..436faf80a66b 100644
--- a/kernel/rcu/rcu.h
+++ b/kernel/rcu/rcu.h
@@ -473,6 +473,12 @@ void do_trace_rcu_torture_read(const char *rcutorturename,
unsigned long c);
void rcu_gp_set_torture_wait(int duration);
void rcu_force_call_rcu_to_lazy(bool force);
+
+#if IS_ENABLED(CONFIG_RCU_SCALE_TEST)
+unsigned long rcu_scale_get_jiffies_till_flush(void);
+void rcu_scale_set_jiffies_till_flush(unsigned long j);
+#endif
+
#else
static inline void rcutorture_get_gp_data(enum rcutorture_type test_type,
int *flags, unsigned long *gp_seq)
diff --git a/kernel/rcu/rcuscale.c b/kernel/rcu/rcuscale.c
index 277a5bfb37d4..58ee5c2cb37b 100644
--- a/kernel/rcu/rcuscale.c
+++ b/kernel/rcu/rcuscale.c
@@ -95,6 +95,7 @@ torture_param(int, verbose, 1, "Enable verbose debugging printk()s");
torture_param(int, writer_holdoff, 0, "Holdoff (us) between GPs, zero to disable");
torture_param(int, kfree_rcu_test, 0, "Do we run a kfree_rcu() scale test?");
torture_param(int, kfree_mult, 1, "Multiple of kfree_obj size to allocate.");
+torture_param(int, kfree_rcu_by_lazy, 0, "Use call_rcu_lazy() to emulate kfree_rcu()?");
static char *scale_type = "rcu";
module_param(scale_type, charp, 0444);
@@ -658,6 +659,13 @@ struct kfree_obj {
struct rcu_head rh;
};
+/* Used if doing RCU-kfree'ing via call_rcu_lazy(). */
+void kfree_rcu_lazy(struct rcu_head *rh)
+{
+ struct kfree_obj *obj = container_of(rh, struct kfree_obj, rh);
+ kfree(obj);
+}
+
static int
kfree_scale_thread(void *arg)
{
@@ -695,6 +703,11 @@ kfree_scale_thread(void *arg)
if (!alloc_ptr)
return -ENOMEM;
+ if (kfree_rcu_by_lazy) {
+ call_rcu_lazy(&(alloc_ptr->rh), kfree_rcu_lazy);
+ continue;
+ }
+
// By default kfree_rcu_test_single and kfree_rcu_test_double are
// initialized to false. If both have the same value (false or true)
// both are randomly tested, otherwise only the one with value true
@@ -737,6 +750,9 @@ kfree_scale_cleanup(void)
{
int i;
+ if (kfree_rcu_by_lazy)
+ rcu_force_call_rcu_to_lazy(false);
+
if (torture_cleanup_begin())
return;
@@ -766,11 +782,55 @@ kfree_scale_shutdown(void *arg)
return -EINVAL;
}
+// Used if doing RCU-kfree'ing via call_rcu_lazy().
+unsigned long jiffies_at_lazy_cb;
+struct rcu_head lazy_test1_rh;
+int rcu_lazy_test1_cb_called;
+void call_rcu_lazy_test1(struct rcu_head *rh)
+{
+ jiffies_at_lazy_cb = jiffies;
+ WRITE_ONCE(rcu_lazy_test1_cb_called, 1);
+}
+
static int __init
kfree_scale_init(void)
{
long i;
int firsterr = 0;
+ unsigned long orig_jif, jif_start;
+
+ // Force all call_rcu() to call_rcu_lazy() so that non-lazy CBs
+ // do not remove laziness of the lazy ones (since the test tries
+ // to stress call_rcu_lazy() for OOM).
+ //
+ // Also, do a quick self-test to ensure laziness is as much as
+ // expected.
+ if (kfree_rcu_by_lazy) {
+ /* do a test to check the timeout. */
+ orig_jif = rcu_scale_get_jiffies_till_flush();
+
+ rcu_force_call_rcu_to_lazy(true);
+ rcu_scale_set_jiffies_till_flush(2 * HZ);
+ rcu_barrier();
+
+ jif_start = jiffies;
+ jiffies_at_lazy_cb = 0;
+ call_rcu_lazy(&lazy_test1_rh, call_rcu_lazy_test1);
+
+ smp_cond_load_relaxed(&rcu_lazy_test1_cb_called, VAL == 1);
+
+ rcu_scale_set_jiffies_till_flush(orig_jif);
+
+ if (WARN_ON_ONCE(jiffies_at_lazy_cb - jif_start < 2 * HZ)) {
+ pr_alert("Lazy CBs are not being lazy as expected!\n");
+ return -1;
+ }
+
+ if (WARN_ON_ONCE(jiffies_at_lazy_cb - jif_start > 3 * HZ)) {
+ pr_alert("Lazy CBs are being too lazy!\n");
+ return -1;
+ }
+ }
kfree_nrealthreads = compute_real(kfree_nthreads);
/* Start up the kthreads. */
@@ -783,7 +843,9 @@ kfree_scale_init(void)
schedule_timeout_uninterruptible(1);
}
- pr_alert("kfree object size=%zu\n", kfree_mult * sizeof(struct kfree_obj));
+ pr_alert("kfree object size=%zu, kfree_rcu_by_lazy=%d\n",
+ kfree_mult * sizeof(struct kfree_obj),
+ kfree_rcu_by_lazy);
kfree_reader_tasks = kcalloc(kfree_nrealthreads, sizeof(kfree_reader_tasks[0]),
GFP_KERNEL);
diff --git a/kernel/rcu/tree_nocb.h b/kernel/rcu/tree_nocb.h
index b481f1ea57c0..255f2945b0fc 100644
--- a/kernel/rcu/tree_nocb.h
+++ b/kernel/rcu/tree_nocb.h
@@ -257,6 +257,21 @@ static bool wake_nocb_gp(struct rcu_data *rdp, bool force)
}
#define LAZY_FLUSH_JIFFIES (10 * HZ)
+unsigned long jiffies_till_flush = LAZY_FLUSH_JIFFIES;
+
+#ifdef CONFIG_RCU_SCALE_TEST
+void rcu_scale_set_jiffies_till_flush(unsigned long jif)
+{
+ jiffies_till_flush = jif;
+}
+EXPORT_SYMBOL(rcu_scale_set_jiffies_till_flush);
+
+unsigned long rcu_scale_get_jiffies_till_flush(void)
+{
+ return jiffies_till_flush;
+}
+EXPORT_SYMBOL(rcu_scale_get_jiffies_till_flush);
+#endif
/*
* Arrange to wake the GP kthread for this NOCB group at some future
@@ -275,7 +290,7 @@ static void wake_nocb_gp_defer(struct rcu_data *rdp, int waketype,
* of callback storm, no need to wake up too early.
*/
if (waketype == RCU_NOCB_WAKE_LAZY) {
- mod_timer(&rdp_gp->nocb_timer, jiffies + LAZY_FLUSH_JIFFIES);
+ mod_timer(&rdp_gp->nocb_timer, jiffies + jiffies_till_flush);
WRITE_ONCE(rdp_gp->nocb_defer_wakeup, waketype);
} else if (waketype == RCU_NOCB_WAKE_BYPASS) {
mod_timer(&rdp_gp->nocb_timer, jiffies + 2);
--
2.37.0.rc0.104.g0611611a94-goog
Powered by blists - more mailing lists