diff mbox

[RFC,tip/core/rcu,28/41] rcu: Set RCU CPU stall times via sysfs

Message ID 1328125319-5205-28-git-send-email-paulmck@linux.vnet.ibm.com
State Superseded
Headers show

Commit Message

Paul E. McKenney Feb. 1, 2012, 7:41 p.m. UTC 
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>

The default CONFIG_RCU_CPU_STALL_TIMEOUT value of 60 seconds has served
Linux users well for production use for quite some time.  However, for
debugging, there will be more than three minutes between subsequent
stall-warning messages.  This can be an annoyingly long wait if you
are trying to work out where the offending infinite loop is hiding.

Therefore, this commit provides a rcu_cpu_stall_timeout sysfs
parameter that may be adjusted at boot time and at runtime to speed
up debugging.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcutree.c |   31 ++++++++++++++++++++++++++-----
 kernel/rcutree.h |    6 ------
 2 files changed, 26 insertions(+), 11 deletions(-)
diff mbox

Patch

diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index ee45ae7..e82e505 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -208,8 +208,11 @@  module_param(blimit, int, 0);
 module_param(qhimark, int, 0);
 module_param(qlowmark, int, 0);
 
-int rcu_cpu_stall_suppress __read_mostly;
+int rcu_cpu_stall_suppress __read_mostly; /* 1 = suppress stall warnings. */
+int rcu_cpu_stall_timeout __read_mostly = CONFIG_RCU_CPU_STALL_TIMEOUT;
+
 module_param(rcu_cpu_stall_suppress, int, 0644);
+module_param(rcu_cpu_stall_timeout, int, 0644);
 
 static void force_quiescent_state(struct rcu_state *rsp, int relaxed);
 static int rcu_pending(int cpu);
@@ -648,10 +651,28 @@  static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
 	return rcu_implicit_offline_qs(rdp);
 }
 
+static int jiffies_till_stall_check(void)
+{
+	int till_stall_check = ACCESS_ONCE(rcu_cpu_stall_timeout);
+
+	/*
+	 * Limit check must be consistent with the Kconfig limits
+	 * for CONFIG_RCU_CPU_STALL_TIMEOUT.
+	 */
+	if (till_stall_check < 3) {
+		ACCESS_ONCE(rcu_cpu_stall_timeout) = 3;
+		till_stall_check = 3;
+	} else if (till_stall_check > 300) {
+		ACCESS_ONCE(rcu_cpu_stall_timeout) = 300;
+		till_stall_check = 300;
+	}
+	return till_stall_check * HZ + RCU_STALL_DELAY_DELTA;
+}
+
 static void record_gp_stall_check_time(struct rcu_state *rsp)
 {
 	rsp->gp_start = jiffies;
-	rsp->jiffies_stall = jiffies + RCU_SECONDS_TILL_STALL_CHECK;
+	rsp->jiffies_stall = jiffies + jiffies_till_stall_check();
 }
 
 static void print_other_cpu_stall(struct rcu_state *rsp)
@@ -670,7 +691,7 @@  static void print_other_cpu_stall(struct rcu_state *rsp)
 		raw_spin_unlock_irqrestore(&rnp->lock, flags);
 		return;
 	}
-	rsp->jiffies_stall = jiffies + RCU_SECONDS_TILL_STALL_RECHECK;
+	rsp->jiffies_stall = jiffies + 3 * jiffies_till_stall_check() + 3;
 
 	/*
 	 * Now rat on any tasks that got kicked up to the root rcu_node
@@ -729,8 +750,8 @@  static void print_cpu_stall(struct rcu_state *rsp)
 
 	raw_spin_lock_irqsave(&rnp->lock, flags);
 	if (ULONG_CMP_GE(jiffies, rsp->jiffies_stall))
-		rsp->jiffies_stall =
-			jiffies + RCU_SECONDS_TILL_STALL_RECHECK;
+		rsp->jiffies_stall = jiffies +
+				     3 * jiffies_till_stall_check() + 3;
 	raw_spin_unlock_irqrestore(&rnp->lock, flags);
 
 	set_need_resched();  /* kick ourselves to get things going. */
diff --git a/kernel/rcutree.h b/kernel/rcutree.h
index 58c9fc3..0328a53 100644
--- a/kernel/rcutree.h
+++ b/kernel/rcutree.h
@@ -314,12 +314,6 @@  struct rcu_data {
 #else
 #define RCU_STALL_DELAY_DELTA	       0
 #endif
-
-#define RCU_SECONDS_TILL_STALL_CHECK   (CONFIG_RCU_CPU_STALL_TIMEOUT * HZ + \
-					RCU_STALL_DELAY_DELTA)
-						/* for rsp->jiffies_stall */
-#define RCU_SECONDS_TILL_STALL_RECHECK (3 * RCU_SECONDS_TILL_STALL_CHECK + 30)
-						/* for rsp->jiffies_stall */
 #define RCU_STALL_RAT_DELAY		2	/* Allow other CPUs time */
 						/*  to take at least one */
 						/*  scheduling clock irq */