diff mbox

[RFC,tip/core/rcu,2/6] rcu: Inform the user about dynticks-idle mode on PROVE_RCU warning

Message ID 1310139833-20804-2-git-send-email-paulmck@linux.vnet.ibm.com
State New
Headers show

Commit Message

Paul E. McKenney July 8, 2011, 3:43 p.m. UTC 
From: Frederic Weisbecker <fweisbec@gmail.com>

Inform the user if an RCU usage error is detected by lockdep while in
an extended quiescent state (in this case, dyntick-idle mode).  This
is accomplished by adding a line to the RCU lockdep splat indicating
whether or not the splat occurred in dyntick-idle mode.

Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Lai Jiangshan <laijs@cn.fujitsu.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/lockdep.c |   20 ++++++++++++++++++++
 1 files changed, 20 insertions(+), 0 deletions(-)
diff mbox

Patch

diff --git a/kernel/lockdep.c b/kernel/lockdep.c
index 298c927..f2bff04 100644
--- a/kernel/lockdep.c
+++ b/kernel/lockdep.c
@@ -3998,6 +3998,26 @@  void lockdep_rcu_dereference(const char *file, const int line)
 			file, line);
 	printk("\nother info that might help us debug this:\n\n");
 	printk("\nrcu_scheduler_active = %d, debug_locks = %d\n", rcu_scheduler_active, debug_locks);
+
+	/*
+	 * If a CPU is in dyntick-idle mode (CONFIG_NO_HZ), then RCU
+	 * considers that CPU to be in an "extended quiescent state",
+	 * which means that RCU will be completely ignoring that CPU.
+	 * Therefore, rcu_read_lock() and friends have absolutely no
+	 * effect on a dyntick-idle CPU.  In other words, even if a
+	 * dyntick-idle CPU has called rcu_read_lock(), RCU might well
+	 * delete data structures out from under it.  RCU really has no
+	 * choice here: if it were to consult the CPU, that would wake
+	 * the CPU up, and the whole point of dyntick-idle mode is to
+	 * allow CPUs to enter extremely deep sleep states.
+	 *
+	 * So complain bitterly if someone does call rcu_read_lock(),
+	 * rcu_read_lock_bh() and so on from extended quiescent states
+	 * such as dyntick-idle mode.
+	 */
+	if (rcu_check_extended_qs())
+		printk("RCU used illegally from extended quiescent state!\n");
+
 	lockdep_print_held_locks(curr);
 	printk("\nstack backtrace:\n");
 	dump_stack();