Merge branch 'rcu/urgent' of git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu

Pull RCU fixes from Paul McKenney:
 "I must confess that this past merge window was not RCU's best showing.
  This series contains three more fixes for RCU regressions:

   1.   A fix to __DECLARE_TRACE_RCU() that causes it to act as an
        interrupt from idle rather than as a task switch from idle.
        This change is needed due to the recent use of _rcuidle()
        tracepoints that can be invoked from interrupt handlers as well
        as from idle.  Without this fix, invoking _rcuidle() tracepoints
        from interrupt handlers results in splats and (more seriously)
        confusion on RCU's part as to whether a given CPU is idle or not.
        This confusion can in turn result in too-short grace periods and
        therefore random memory corruption.

   2.   A fix to a subtle deadlock that could result due to RCU doing
        a wakeup while holding one of its rcu_node structure's locks.
        Although the probability of occurrence is low, it really
        does happen.  The fix, courtesy of Steven Rostedt, uses
        irq_work_queue() to avoid the deadlock.

   3.   A fix to a silent deadlock (invisible to lockdep) due to the
        interaction of timeouts posted by RCU debug code enabled by
        CONFIG_PROVE_RCU_DELAY=y, grace-period initialization, and CPU
        hotplug operations.  This will not occur in production kernels,
        but really does occur in randconfig testing.  Diagnosis courtesy
        of Steven Rostedt"

* 'rcu/urgent' of git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu:
  rcu: Fix deadlock with CPU hotplug, RCU GP init, and timer migration
  rcu: Don't call wakeup() with rcu_node structure ->lock held
  trace: Allow idle-safe tracepoints to be called from irq

4 files changed, 22 insertions, 6 deletions

diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h
index 2f322c38bd4..f8e084d0fc7 100644
--- a/include/linux/tracepoint.h
+++ b/include/linux/tracepoint.h
@@ -145,8 +145,8 @@ static inline void tracepoint_synchronize_unregister(void)
 				TP_PROTO(data_proto),			\
 				TP_ARGS(data_args),			\
 				TP_CONDITION(cond),			\
-				rcu_idle_exit(),			\
-				rcu_idle_enter());			\
+				rcu_irq_enter(),			\
+				rcu_irq_exit());			\
 	}
 #else
 #define __DECLARE_TRACE_RCU(name, proto, args, cond, data_proto, data_args)
diff --git a/init/Kconfig b/init/Kconfig
index 9d3a7887a6d..2d9b83104dc 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -431,6 +431,7 @@ choice
 config TREE_RCU
 	bool "Tree-based hierarchical RCU"
 	depends on !PREEMPT && SMP
+	select IRQ_WORK
 	help
 	  This option selects the RCU implementation that is
 	  designed for very large SMP system with hundreds or
diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index 16ea6792501..35380019f0f 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -1451,9 +1451,9 @@ static int rcu_gp_init(struct rcu_state *rsp)
 					    rnp->grphi, rnp->qsmask);
 		raw_spin_unlock_irq(&rnp->lock);
 #ifdef CONFIG_PROVE_RCU_DELAY
-		if ((prandom_u32() % (rcu_num_nodes * 8)) == 0 &&
+		if ((prandom_u32() % (rcu_num_nodes + 1)) == 0 &&
 		    system_state == SYSTEM_RUNNING)
-			schedule_timeout_uninterruptible(2);
+			udelay(200);
 #endif /* #ifdef CONFIG_PROVE_RCU_DELAY */
 		cond_resched();
 	}
@@ -1613,6 +1613,14 @@ static int __noreturn rcu_gp_kthread(void *arg)
 	}
 }
 
+static void rsp_wakeup(struct irq_work *work)
+{
+	struct rcu_state *rsp = container_of(work, struct rcu_state, wakeup_work);
+
+	/* Wake up rcu_gp_kthread() to start the grace period. */
+	wake_up(&rsp->gp_wq);
+}
+
 /*
  * Start a new RCU grace period if warranted, re-initializing the hierarchy
  * in preparation for detecting the next grace period.  The caller must hold
@@ -1637,8 +1645,12 @@ rcu_start_gp_advanced(struct rcu_state *rsp, struct rcu_node *rnp,
 	}
 	rsp->gp_flags = RCU_GP_FLAG_INIT;
 
-	/* Wake up rcu_gp_kthread() to start the grace period. */
-	wake_up(&rsp->gp_wq);
+	/*
+	 * We can't do wakeups while holding the rnp->lock, as that
+	 * could cause possible deadlocks with the rq->lock. Deter
+	 * the wakeup to interrupt context.
+	 */
+	irq_work_queue(&rsp->wakeup_work);
 }
 
 /*
@@ -3235,6 +3247,7 @@ static void __init rcu_init_one(struct rcu_state *rsp,
 
 	rsp->rda = rda;
 	init_waitqueue_head(&rsp->gp_wq);
+	init_irq_work(&rsp->wakeup_work, rsp_wakeup);
 	rnp = rsp->level[rcu_num_lvls - 1];
 	for_each_possible_cpu(i) {
 		while (i > rnp->grphi)
diff --git a/kernel/rcutree.h b/kernel/rcutree.h
index da77a8f57ff..4df503470e4 100644
--- a/kernel/rcutree.h
+++ b/kernel/rcutree.h
@@ -27,6 +27,7 @@
 #include <linux/threads.h>
 #include <linux/cpumask.h>
 #include <linux/seqlock.h>
+#include <linux/irq_work.h>
 
 /*
  * Define shape of hierarchy based on NR_CPUS, CONFIG_RCU_FANOUT, and
@@ -442,6 +443,7 @@ struct rcu_state {
 	char *name;				/* Name of structure. */
 	char abbr;				/* Abbreviated name. */
 	struct list_head flavors;		/* List of RCU flavors. */
+	struct irq_work wakeup_work;		/* Postponed wakeups */
 };
 
 /* Values for rcu_state structure's gp_flags field. */