summaryrefslogtreecommitdiffstats
path: root/kernel/rcu
diff options
context:
space:
mode:
authorDaniel Bristot de Oliveira <bristot@redhat.com>2016-06-02 13:51:41 -0300
committerPaul E. McKenney <paulmck@linux.vnet.ibm.com>2016-06-15 16:00:05 -0700
commit088e9d253d3a4ab7e058dd84bb532c32dadf1882 (patch)
treefd8423b8a89ba645d7a2820485309c49c58fbd07 /kernel/rcu
parentaab057382cb9b16249552684c1ebd270f070ec02 (diff)
downloadlinux-stable-088e9d253d3a4ab7e058dd84bb532c32dadf1882.tar.gz
linux-stable-088e9d253d3a4ab7e058dd84bb532c32dadf1882.tar.bz2
linux-stable-088e9d253d3a4ab7e058dd84bb532c32dadf1882.zip
rcu: sysctl: Panic on RCU Stall
It is not always easy to determine the cause of an RCU stall just by analysing the RCU stall messages, mainly when the problem is caused by the indirect starvation of rcu threads. For example, when preempt_rcu is not awakened due to the starvation of a timer softirq. We have been hard coding panic() in the RCU stall functions for some time while testing the kernel-rt. But this is not possible in some scenarios, like when supporting customers. This patch implements the sysctl kernel.panic_on_rcu_stall. If set to 1, the system will panic() when an RCU stall takes place, enabling the capture of a vmcore. The vmcore provides a way to analyze all kernel/tasks states, helping out to point to the culprit and the solution for the stall. The kernel.panic_on_rcu_stall sysctl is disabled by default. Changes from v1: - Fixed a typo in the git log - The if(sysctl_panic_on_rcu_stall) panic() is in a static function - Fixed the CONFIG_TINY_RCU compilation issue - The var sysctl_panic_on_rcu_stall is now __read_mostly Cc: Jonathan Corbet <corbet@lwn.net> Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> Cc: Josh Triplett <josh@joshtriplett.org> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Cc: Lai Jiangshan <jiangshanlai@gmail.com> Acked-by: Christian Borntraeger <borntraeger@de.ibm.com> Reviewed-by: Josh Triplett <josh@joshtriplett.org> Reviewed-by: Arnaldo Carvalho de Melo <acme@kernel.org> Tested-by: "Luis Claudio R. Goncalves" <lgoncalv@redhat.com> Signed-off-by: Daniel Bristot de Oliveira <bristot@redhat.com> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Diffstat (limited to 'kernel/rcu')
-rw-r--r--kernel/rcu/tree.c12
1 files changed, 12 insertions, 0 deletions
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index c844b6142a86..e5ca15a461b9 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -125,6 +125,8 @@ int rcu_num_lvls __read_mostly = RCU_NUM_LVLS;
/* Number of rcu_nodes at specified level. */
static int num_rcu_lvl[] = NUM_RCU_LVL_INIT;
int rcu_num_nodes __read_mostly = NUM_RCU_NODES; /* Total # rcu_nodes in use. */
+/* panic() on RCU Stall sysctl. */
+int sysctl_panic_on_rcu_stall __read_mostly;
/*
* The rcu_scheduler_active variable transitions from zero to one just
@@ -1312,6 +1314,12 @@ static void rcu_stall_kick_kthreads(struct rcu_state *rsp)
}
}
+static inline void panic_on_rcu_stall(void)
+{
+ if (sysctl_panic_on_rcu_stall)
+ panic("RCU Stall\n");
+}
+
static void print_other_cpu_stall(struct rcu_state *rsp, unsigned long gpnum)
{
int cpu;
@@ -1391,6 +1399,8 @@ static void print_other_cpu_stall(struct rcu_state *rsp, unsigned long gpnum)
rcu_check_gp_kthread_starvation(rsp);
+ panic_on_rcu_stall();
+
force_quiescent_state(rsp); /* Kick them all. */
}
@@ -1431,6 +1441,8 @@ static void print_cpu_stall(struct rcu_state *rsp)
jiffies + 3 * rcu_jiffies_till_stall_check() + 3);
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+ panic_on_rcu_stall();
+
/*
* Attempt to revive the RCU machinery by forcing a context switch.
*