linux-kernel - [PATCH tip/core/rcu 15/19] rcu: Add stall warnings to synchronize_sched

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

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <1437175764-24096-15-git-send-email-paulmck@linux.vnet.ibm.com>
Date:	Fri, 17 Jul 2015 16:29:20 -0700
From:	"Paul E. McKenney" <paulmck@...ux.vnet.ibm.com>
To:	linux-kernel@...r.kernel.org
Cc:	mingo@...nel.org, jiangshanlai@...il.com, dipankar@...ibm.com,
	akpm@...ux-foundation.org, mathieu.desnoyers@...icios.com,
	josh@...htriplett.org, tglx@...utronix.de, peterz@...radead.org,
	rostedt@...dmis.org, dhowells@...hat.com, edumazet@...gle.com,
	dvhart@...ux.intel.com, fweisbec@...il.com, oleg@...hat.com,
	bobby.prani@...il.com,
	"Paul E. McKenney" <paulmck@...ux.vnet.ibm.com>
Subject: [PATCH tip/core/rcu 15/19] rcu: Add stall warnings to synchronize_sched_expedited()

From: "Paul E. McKenney" <paulmck@...ux.vnet.ibm.com>

Although synchronize_sched_expedited() historically has no RCU CPU stall
warnings, the availability of the rcupdate.rcu_expedited boot parameter
invalidates the old assumption that synchronize_sched()'s stall warnings
would suffice.  This commit therefore adds RCU CPU stall warnings to
synchronize_sched_expedited().

Signed-off-by: Paul E. McKenney <paulmck@...ux.vnet.ibm.com>
---
 kernel/rcu/tree.c | 58 +++++++++++++++++++++++++++++++++++++++++++++++++++----
 kernel/rcu/tree.h |  1 +
 2 files changed, 55 insertions(+), 4 deletions(-)

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index e45097fc39fa..4b6594c7db58 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -3369,16 +3369,65 @@ static struct rcu_node *exp_funnel_lock(struct rcu_state *rsp, unsigned long s)
 	return rnp1;
 }
 
+/* Invoked on each online non-idle CPU for expedited quiescent state. */
 static int synchronize_sched_expedited_cpu_stop(void *data)
 {
-	struct rcu_state *rsp = data;
+	struct rcu_data *rdp = data;
+	struct rcu_state *rsp = rdp->rsp;
 
 	/* We are here: If we are last, do the wakeup. */
+	rdp->exp_done = true;
 	if (atomic_dec_and_test(&rsp->expedited_need_qs))
 		wake_up(&rsp->expedited_wq);
 	return 0;
 }
 
+static void synchronize_sched_expedited_wait(struct rcu_state *rsp)
+{
+	int cpu;
+	unsigned long jiffies_stall;
+	unsigned long jiffies_start;
+	struct rcu_data *rdp;
+	int ret;
+
+	jiffies_stall = rcu_jiffies_till_stall_check();
+	jiffies_start = jiffies;
+
+	for (;;) {
+		ret = wait_event_interruptible_timeout(
+				rsp->expedited_wq,
+				!atomic_read(&rsp->expedited_need_qs),
+				jiffies_stall);
+		if (ret > 0)
+			return;
+		if (ret < 0) {
+			/* Hit a signal, disable CPU stall warnings. */
+			wait_event(rsp->expedited_wq,
+				   !atomic_read(&rsp->expedited_need_qs));
+			return;
+		}
+		pr_err("INFO: %s detected expedited stalls on CPUs: {",
+		       rsp->name);
+		for_each_online_cpu(cpu) {
+			rdp = per_cpu_ptr(rsp->rda, cpu);
+
+			if (rdp->exp_done)
+				continue;
+			pr_cont(" %d", cpu);
+		}
+		pr_cont(" } %lu jiffies s: %lu\n",
+			jiffies - jiffies_start, rsp->expedited_sequence);
+		for_each_online_cpu(cpu) {
+			rdp = per_cpu_ptr(rsp->rda, cpu);
+
+			if (rdp->exp_done)
+				continue;
+			dump_cpu_task(cpu);
+		}
+		jiffies_stall = 3 * rcu_jiffies_till_stall_check() + 3;
+	}
+}
+
 /**
  * synchronize_sched_expedited - Brute-force RCU-sched grace period
  *
@@ -3428,19 +3477,20 @@ void synchronize_sched_expedited(void)
 		struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
 		struct rcu_dynticks *rdtp = &per_cpu(rcu_dynticks, cpu);
 
+		rdp->exp_done = false;
+
 		/* Skip our CPU and any idle CPUs. */
 		if (raw_smp_processor_id() == cpu ||
 		    !(atomic_add_return(0, &rdtp->dynticks) & 0x1))
 			continue;
 		atomic_inc(&rsp->expedited_need_qs);
 		stop_one_cpu_nowait(cpu, synchronize_sched_expedited_cpu_stop,
-				    rsp, &rdp->exp_stop_work);
+				    rdp, &rdp->exp_stop_work);
 	}
 
 	/* Remove extra count and, if necessary, wait for CPUs to stop. */
 	if (!atomic_dec_and_test(&rsp->expedited_need_qs))
-		wait_event(rsp->expedited_wq,
-			   !atomic_read(&rsp->expedited_need_qs));
+		synchronize_sched_expedited_wait(rsp);
 
 	rcu_exp_gp_seq_end(rsp);
 	mutex_unlock(&rnp->exp_funnel_mutex);
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index efee84ce1e08..b3ae8d3cffbc 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -370,6 +370,7 @@ struct rcu_data {
 	struct rcu_head oom_head;
 #endif /* #ifdef CONFIG_RCU_FAST_NO_HZ */
 	struct mutex exp_funnel_mutex;
+	bool exp_done;			/* Expedited QS for this CPU? */
 
 	/* 7) Callback offloading. */
 #ifdef CONFIG_RCU_NOCB_CPU
-- 
1.8.1.5

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/