linux-kernel - [PATCH tip/core/rcu 3/5] rcu: Exclude near-simultaneous RCU CPU stall warnings

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: <20180625230427.13877-3-paulmck@linux.vnet.ibm.com>
Date:   Mon, 25 Jun 2018 16:04:25 -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,
        fweisbec@...il.com, oleg@...hat.com, joel@...lfernandes.org,
        "Paul E. McKenney" <paulmck@...ux.vnet.ibm.com>
Subject: [PATCH tip/core/rcu 3/5] rcu: Exclude near-simultaneous RCU CPU stall warnings

There is a two-jiffy delay between the time that a CPU will self-report
an RCU CPU stall warning and the time that some other CPU will report a
warning on behalf of the first CPU.  This has worked well in the past,
but on busy systems, it is possible for the two warnings to overlap,
which makes interpreting them extremely difficult.

This commit therefore uses a cmpxchg-based timing decision that
allows only one report in a given one-minute period (assuming default
stall-warning Kconfig parameters).  This approach will of course fail
if you are seeing minute-long vCPU preemption, but in that case the
overlapping RCU CPU stall warnings are the least of your worries.

Reported-by: Dmitry Vyukov <dvyukov@...gle.com>
Signed-off-by: Paul E. McKenney <paulmck@...ux.vnet.ibm.com>
---
 kernel/rcu/tree.c | 26 +++++++++++---------------
 1 file changed, 11 insertions(+), 15 deletions(-)

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 79c7fe978b17..b1fffa21b9e4 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -1368,7 +1368,6 @@ static inline void panic_on_rcu_stall(void)
 static void print_other_cpu_stall(struct rcu_state *rsp, unsigned long gpnum)
 {
 	int cpu;
-	long delta;
 	unsigned long flags;
 	unsigned long gpa;
 	unsigned long j;
@@ -1381,18 +1380,6 @@ static void print_other_cpu_stall(struct rcu_state *rsp, unsigned long gpnum)
 	if (rcu_cpu_stall_suppress)
 		return;
 
-	/* Only let one CPU complain about others per time interval. */
-
-	raw_spin_lock_irqsave_rcu_node(rnp, flags);
-	delta = jiffies - READ_ONCE(rsp->jiffies_stall);
-	if (delta < RCU_STALL_RAT_DELAY || !rcu_gp_in_progress(rsp)) {
-		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
-		return;
-	}
-	WRITE_ONCE(rsp->jiffies_stall,
-		   jiffies + 3 * rcu_jiffies_till_stall_check() + 3);
-	raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
-
 	/*
 	 * OK, time to rat on our buddy...
 	 * See Documentation/RCU/stallwarn.txt for info on how to debug
@@ -1441,6 +1428,10 @@ static void print_other_cpu_stall(struct rcu_state *rsp, unsigned long gpnum)
 			sched_show_task(current);
 		}
 	}
+	/* Rewrite if needed in case of slow consoles. */
+	if (ULONG_CMP_GE(jiffies, READ_ONCE(rsp->jiffies_stall)))
+		WRITE_ONCE(rsp->jiffies_stall,
+			   jiffies + 3 * rcu_jiffies_till_stall_check() + 3);
 
 	rcu_check_gp_kthread_starvation(rsp);
 
@@ -1485,6 +1476,7 @@ static void print_cpu_stall(struct rcu_state *rsp)
 	rcu_dump_cpu_stacks(rsp);
 
 	raw_spin_lock_irqsave_rcu_node(rnp, flags);
+	/* Rewrite if needed in case of slow consoles. */
 	if (ULONG_CMP_GE(jiffies, READ_ONCE(rsp->jiffies_stall)))
 		WRITE_ONCE(rsp->jiffies_stall,
 			   jiffies + 3 * rcu_jiffies_till_stall_check() + 3);
@@ -1508,6 +1500,7 @@ static void check_cpu_stall(struct rcu_state *rsp, struct rcu_data *rdp)
 	unsigned long gpnum;
 	unsigned long gps;
 	unsigned long j;
+	unsigned long jn;
 	unsigned long js;
 	struct rcu_node *rnp;
 
@@ -1546,14 +1539,17 @@ static void check_cpu_stall(struct rcu_state *rsp, struct rcu_data *rdp)
 	    ULONG_CMP_GE(gps, js))
 		return; /* No stall or GP completed since entering function. */
 	rnp = rdp->mynode;
+	jn = jiffies + 3 * rcu_jiffies_till_stall_check() + 3;
 	if (rcu_gp_in_progress(rsp) &&
-	    (READ_ONCE(rnp->qsmask) & rdp->grpmask)) {
+	    (READ_ONCE(rnp->qsmask) & rdp->grpmask) &&
+	    cmpxchg(&rsp->jiffies_stall, js, jn) == js) {
 
 		/* We haven't checked in, so go dump stack. */
 		print_cpu_stall(rsp);
 
 	} else if (rcu_gp_in_progress(rsp) &&
-		   ULONG_CMP_GE(j, js + RCU_STALL_RAT_DELAY)) {
+		   ULONG_CMP_GE(j, js + RCU_STALL_RAT_DELAY) &&
+		   cmpxchg(&rsp->jiffies_stall, js, jn) == js) {
 
 		/* They had a few time units to dump stack, so complain. */
 		print_other_cpu_stall(rsp, gpnum);
-- 
2.17.1