From: "Paul E. McKenney" <paulmck@linux.ibm.com>
To: linux-kernel@vger.kernel.org
Cc: mingo@kernel.org, jiangshanlai@gmail.com, dipankar@in.ibm.com,
akpm@linux-foundation.org, mathieu.desnoyers@efficios.com,
josh@joshtriplett.org, tglx@linutronix.de, peterz@infradead.org,
rostedt@goodmis.org, dhowells@redhat.com, edumazet@google.com,
fweisbec@gmail.com, oleg@redhat.com, joel@joelfernandes.org,
"Paul E. McKenney" <paulmck@linux.ibm.com>
Subject: [PATCH tip/core/rcu 15/17] rcutorture: Recover from OOM during forward-progress tests
Date: Sun, 11 Nov 2018 12:20:25 -0800 [thread overview]
Message-ID: <20181111202027.13585-15-paulmck@linux.ibm.com> (raw)
In-Reply-To: <20181111201956.GA11935@linux.ibm.com>
This commit causes the OOM handler to do rcu_barrier() calls and to
free up forward-progress callbacks in order to recover from OOM events.
The current test is terminated, but subsequent forward-progress tests can
proceed. This allows a long test to result in multiple forward-progress
failures, greatly reducing the required testing time.
Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com>
---
kernel/rcu/rcutorture.c | 60 +++++++++++++++++++++++++++++++++--------
1 file changed, 49 insertions(+), 11 deletions(-)
diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index 080b5ac6340c..afa98162575d 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -1649,13 +1649,14 @@ static void rcu_torture_fwd_cb_hist(void)
/* Callback function for continuous-flood RCU callbacks. */
static void rcu_torture_fwd_cb_cr(struct rcu_head *rhp)
{
+ unsigned long flags;
int i;
struct rcu_fwd_cb *rfcp = container_of(rhp, struct rcu_fwd_cb, rh);
struct rcu_fwd_cb **rfcpp;
rfcp->rfc_next = NULL;
rfcp->rfc_gps++;
- spin_lock(&rcu_fwd_lock);
+ spin_lock_irqsave(&rcu_fwd_lock, flags);
rfcpp = rcu_fwd_cb_tail;
rcu_fwd_cb_tail = &rfcp->rfc_next;
WRITE_ONCE(*rfcpp, rfcp);
@@ -1664,7 +1665,33 @@ static void rcu_torture_fwd_cb_cr(struct rcu_head *rhp)
if (i >= ARRAY_SIZE(n_launders_hist))
i = ARRAY_SIZE(n_launders_hist) - 1;
n_launders_hist[i]++;
- spin_unlock(&rcu_fwd_lock);
+ spin_unlock_irqrestore(&rcu_fwd_lock, flags);
+}
+
+/*
+ * Free all callbacks on the rcu_fwd_cb_head list, either because the
+ * test is over or because we hit an OOM event.
+ */
+static unsigned long rcu_torture_fwd_prog_cbfree(void)
+{
+ unsigned long flags;
+ unsigned long freed = 0;
+ struct rcu_fwd_cb *rfcp;
+
+ for (;;) {
+ spin_lock_irqsave(&rcu_fwd_lock, flags);
+ rfcp = rcu_fwd_cb_head;
+ if (!rfcp)
+ break;
+ rcu_fwd_cb_head = rfcp->rfc_next;
+ if (!rcu_fwd_cb_head)
+ rcu_fwd_cb_tail = &rcu_fwd_cb_head;
+ spin_unlock_irqrestore(&rcu_fwd_lock, flags);
+ kfree(rfcp);
+ freed++;
+ }
+ spin_unlock_irqrestore(&rcu_fwd_lock, flags);
+ return freed;
}
/* Carry out need_resched()/cond_resched() forward-progress testing. */
@@ -1743,6 +1770,9 @@ static void rcu_torture_fwd_prog_cr(void)
unsigned long stopat;
unsigned long stoppedat;
+ if (READ_ONCE(rcu_fwd_emergency_stop))
+ return; /* Get out of the way quickly, no GP wait! */
+
/* Loop continuously posting RCU callbacks. */
WRITE_ONCE(rcu_fwd_cb_nodelay, true);
cur_ops->sync(); /* Later readers see above write. */
@@ -1788,16 +1818,10 @@ static void rcu_torture_fwd_prog_cr(void)
cver = READ_ONCE(rcu_torture_current_version) - cver;
gps = rcutorture_seq_diff(cur_ops->get_gp_seq(), gps);
cur_ops->cb_barrier(); /* Wait for callbacks to be invoked. */
- for (;;) {
- rfcp = rcu_fwd_cb_head;
- if (!rfcp)
- break;
- rcu_fwd_cb_head = rfcp->rfc_next;
- kfree(rfcp);
- }
- rcu_fwd_cb_tail = &rcu_fwd_cb_head;
+ (void)rcu_torture_fwd_prog_cbfree();
+
WRITE_ONCE(rcu_fwd_cb_nodelay, false);
- if (!torture_must_stop()) {
+ if (!torture_must_stop() && !READ_ONCE(rcu_fwd_emergency_stop)) {
WARN_ON(n_max_gps < MIN_FWD_CBS_LAUNDERED);
pr_alert("%s Duration %lu barrier: %lu pending %ld n_launders: %ld n_launders_sa: %ld n_max_gps: %ld n_max_cbs: %ld cver %ld gps %ld\n",
__func__,
@@ -1817,9 +1841,23 @@ static void rcu_torture_fwd_prog_cr(void)
static int rcutorture_oom_notify(struct notifier_block *self,
unsigned long notused, void *nfreed)
{
+ WARN(1, "%s invoked upon OOM during forward-progress testing.\n",
+ __func__);
rcu_torture_fwd_cb_hist();
rcu_fwd_progress_check(1 + (jiffies - READ_ONCE(rcu_fwd_startat) / 2));
WRITE_ONCE(rcu_fwd_emergency_stop, true);
+ smp_mb(); /* Emergency stop before free and wait to avoid hangs. */
+ pr_info("%s: Freed %lu RCU callbacks.\n",
+ __func__, rcu_torture_fwd_prog_cbfree());
+ rcu_barrier();
+ pr_info("%s: Freed %lu RCU callbacks.\n",
+ __func__, rcu_torture_fwd_prog_cbfree());
+ rcu_barrier();
+ pr_info("%s: Freed %lu RCU callbacks.\n",
+ __func__, rcu_torture_fwd_prog_cbfree());
+ smp_mb(); /* Frees before return to avoid redoing OOM. */
+ (*(unsigned long *)nfreed)++; /* Forward progress CBs freed! */
+ pr_info("%s returning after OOM processing.\n", __func__);
return NOTIFY_OK;
}
--
2.17.1
next prev parent reply other threads:[~2018-11-11 20:21 UTC|newest]
Thread overview: 18+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-11-11 20:19 [PATCH tip/core/rcu 0/17] Torture-test updates for v4.21/v5.0 Paul E. McKenney
2018-11-11 20:20 ` [PATCH tip/core/rcu 01/17] rcutorture: Add call_rcu() flooding forward-progress tests Paul E. McKenney
2018-11-11 20:20 ` [PATCH tip/core/rcu 02/17] torture: Bring any extra CPUs online during kernel startup Paul E. McKenney
2018-11-11 20:20 ` [PATCH tip/core/rcu 03/17] rcutorture: Remove cbflood facility Paul E. McKenney
2018-11-11 20:20 ` [PATCH tip/core/rcu 04/17] rcutorture: Break up too-long rcu_torture_fwd_prog() function Paul E. McKenney
2018-11-11 20:20 ` [PATCH tip/core/rcu 05/17] rcutorture: Affinity forward-progress test to avoid housekeeping CPUs Paul E. McKenney
2018-11-11 20:20 ` [PATCH tip/core/rcu 06/17] torture: Remove unnecessary "ret" variables Paul E. McKenney
2018-11-11 20:20 ` [PATCH tip/core/rcu 07/17] rcutorture: Prepare for asynchronous access to rcu_fwd_startat Paul E. McKenney
2018-11-11 20:20 ` [PATCH tip/core/rcu 08/17] rcutorture: Dump grace-period diagnostics upon forward-progress OOM Paul E. McKenney
2018-11-11 20:20 ` [PATCH tip/core/rcu 09/17] rcu: Account for nocb-CPU callback counts in RCU CPU stall warnings Paul E. McKenney
2018-11-11 20:20 ` [PATCH tip/core/rcu 10/17] rcu: Print per-CPU callback counts for forward-progress failures Paul E. McKenney
2018-11-11 20:20 ` [PATCH tip/core/rcu 11/17] rcutorture: Print GP age upon forward-progress failure Paul E. McKenney
2018-11-11 20:20 ` [PATCH tip/core/rcu 12/17] rcutorture: Print histogram of CB invocation at OOM time Paul E. McKenney
2018-11-11 20:20 ` [PATCH tip/core/rcu 13/17] rcutorture: Print time since GP end upon forward-progress failure Paul E. McKenney
2018-11-11 20:20 ` [PATCH tip/core/rcu 14/17] rcutorture: Print forward-progress test age upon failure Paul E. McKenney
2018-11-11 20:20 ` Paul E. McKenney [this message]
2018-11-11 20:20 ` [PATCH tip/core/rcu 16/17] rcutorture: Use 100ms buckets for forward-progress callback histograms Paul E. McKenney
2018-11-11 20:20 ` [PATCH tip/core/rcu 17/17] rcutorture: Don't do busted forward-progress testing Paul E. McKenney
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20181111202027.13585-15-paulmck@linux.ibm.com \
--to=paulmck@linux.ibm.com \
--cc=akpm@linux-foundation.org \
--cc=dhowells@redhat.com \
--cc=dipankar@in.ibm.com \
--cc=edumazet@google.com \
--cc=fweisbec@gmail.com \
--cc=jiangshanlai@gmail.com \
--cc=joel@joelfernandes.org \
--cc=josh@joshtriplett.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mathieu.desnoyers@efficios.com \
--cc=mingo@kernel.org \
--cc=oleg@redhat.com \
--cc=peterz@infradead.org \
--cc=rostedt@goodmis.org \
--cc=tglx@linutronix.de \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox
Powered by JetHome