rcu: Migrate callbacks earlier in the CPU-offline timeline

RCU callbacks must be migrated away from an outgoing CPU, and this is
done near the end of the CPU-hotplug operation, after the outgoing CPU is
long gone.  Unfortunately, this means that other CPU-hotplug callbacks
can execute while the outgoing CPU's callbacks are still immobilized
on the long-gone CPU's callback lists.  If any of these CPU-hotplug
callbacks must wait, either directly or indirectly, for the invocation
of any of the immobilized RCU callbacks, the system will hang.

This commit avoids such hangs by migrating the callbacks away from the
outgoing CPU immediately upon its departure, shortly after the return
from __cpu_die() in takedown_cpu().  Thus, RCU is able to advance these
callbacks and invoke them, which allows all the after-the-fact CPU-hotplug
callbacks to wait on these RCU callbacks without risk of a hang.

While in the neighborhood, this commit also moves rcu_send_cbs_to_orphanage()
and rcu_adopt_orphan_cbs() under a pre-existing #ifdef to avoid including
dead code on the one hand and to avoid define-without-use warnings on the
other hand.
Reported-by: Jeffrey Hugo <jhugo@codeaurora.org>
Link: http://lkml.kernel.org/r/db9c91f6-1b17-6136-84f0-03c3c2581ab4@codeaurora.orgSigned-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Anna-Maria Gleixner <anna-maria@linutronix.de>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Richard Weinberger <richard@nod.at>

include/linux/rcupdate.h

@@ -110,6 +110,7 @@ void rcu_bh_qs(void);
 void rcu_check_callbacks(int user);
 void rcu_report_dead(unsigned int cpu);
 void rcu_cpu_starting(unsigned int cpu);
+void rcutree_migrate_callbacks(int cpu);
 
 #ifdef CONFIG_RCU_STALL_COMMON
 void rcu_sysrq_start(void);

kernel/cpu.c

@@ -650,6 +650,7 @@ static int takedown_cpu(unsigned int cpu)
 	__cpu_die(cpu);
 
 	tick_cleanup_dead_cpu(cpu);
+	rcutree_migrate_callbacks(cpu);
 	return 0;
 }
 

kernel/rcu/tree.c

@@ -2562,85 +2562,6 @@ rcu_check_quiescent_state(struct rcu_state *rsp, struct rcu_data *rdp)
 	rcu_report_qs_rdp(rdp->cpu, rsp, rdp);
 }
 
-/*
- * Send the specified CPU's RCU callbacks to the orphanage.  The
- * specified CPU must be offline, and the caller must hold the
- * ->orphan_lock.
- */
-static void
-rcu_send_cbs_to_orphanage(int cpu, struct rcu_state *rsp,
-			  struct rcu_node *rnp, struct rcu_data *rdp)
-{
-	lockdep_assert_held(&rsp->orphan_lock);
-
-	/* No-CBs CPUs do not have orphanable callbacks. */
-	if (!IS_ENABLED(CONFIG_HOTPLUG_CPU) || rcu_is_nocb_cpu(rdp->cpu))
-		return;
-
-	/*
-	 * Orphan the callbacks.  First adjust the counts.  This is safe
-	 * because _rcu_barrier() excludes CPU-hotplug operations, so it
-	 * cannot be running now.  Thus no memory barrier is required.
-	 */
-	rdp->n_cbs_orphaned += rcu_segcblist_n_cbs(&rdp->cblist);
-	rcu_segcblist_extract_count(&rdp->cblist, &rsp->orphan_done);
-
-	/*
-	 * Next, move those callbacks still needing a grace period to
-	 * the orphanage, where some other CPU will pick them up.
-	 * Some of the callbacks might have gone partway through a grace
-	 * period, but that is too bad.  They get to start over because we
-	 * cannot assume that grace periods are synchronized across CPUs.
-	 */
-	rcu_segcblist_extract_pend_cbs(&rdp->cblist, &rsp->orphan_pend);
-
-	/*
-	 * Then move the ready-to-invoke callbacks to the orphanage,
-	 * where some other CPU will pick them up.  These will not be
-	 * required to pass though another grace period: They are done.
-	 */
-	rcu_segcblist_extract_done_cbs(&rdp->cblist, &rsp->orphan_done);
-
-	/* Finally, disallow further callbacks on this CPU.  */
-	rcu_segcblist_disable(&rdp->cblist);
-}
-
-/*
- * Adopt the RCU callbacks from the specified rcu_state structure's
- * orphanage.  The caller must hold the ->orphan_lock.
- */
-static void rcu_adopt_orphan_cbs(struct rcu_state *rsp, unsigned long flags)
-{
-	struct rcu_data *rdp = raw_cpu_ptr(rsp->rda);
-
-	lockdep_assert_held(&rsp->orphan_lock);
-
-	/* No-CBs CPUs are handled specially. */
-	if (!IS_ENABLED(CONFIG_HOTPLUG_CPU) ||
-	    rcu_nocb_adopt_orphan_cbs(rsp, rdp, flags))
-		return;
-
-	/* Do the accounting first. */
-	rdp->n_cbs_adopted += rsp->orphan_done.len;
-	if (rsp->orphan_done.len_lazy != rsp->orphan_done.len)
-		rcu_idle_count_callbacks_posted();
-	rcu_segcblist_insert_count(&rdp->cblist, &rsp->orphan_done);
-
-	/*
-	 * We do not need a memory barrier here because the only way we
-	 * can get here if there is an rcu_barrier() in flight is if
-	 * we are the task doing the rcu_barrier().
-	 */
-
-	/* First adopt the ready-to-invoke callbacks, then the done ones. */
-	rcu_segcblist_insert_done_cbs(&rdp->cblist, &rsp->orphan_done);
-	WARN_ON_ONCE(rsp->orphan_done.head);
-	rcu_segcblist_insert_pend_cbs(&rdp->cblist, &rsp->orphan_pend);
-	WARN_ON_ONCE(rsp->orphan_pend.head);
-	WARN_ON_ONCE(rcu_segcblist_empty(&rdp->cblist) !=
-		     !rcu_segcblist_n_cbs(&rdp->cblist));
-}
-
 /*
  * Trace the fact that this CPU is going offline.
  */
@@ -2704,14 +2625,12 @@ static void rcu_cleanup_dead_rnp(struct rcu_node *rnp_leaf)
 
 /*
  * The CPU has been completely removed, and some other CPU is reporting
- * this fact from process context.  Do the remainder of the cleanup,
- * including orphaning the outgoing CPU's RCU callbacks, and also
- * adopting them.  There can only be one CPU hotplug operation at a time,
- * so no other CPU can be attempting to update rcu_cpu_kthread_task.
+ * this fact from process context.  Do the remainder of the cleanup.
+ * There can only be one CPU hotplug operation at a time, so no need for
+ * explicit locking.
  */
 static void rcu_cleanup_dead_cpu(int cpu, struct rcu_state *rsp)
 {
-	unsigned long flags;
 	struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
 	struct rcu_node *rnp = rdp->mynode;  /* Outgoing CPU's rdp & rnp. */
 
@@ -2720,18 +2639,6 @@ static void rcu_cleanup_dead_cpu(int cpu, struct rcu_state *rsp)
 
 	/* Adjust any no-longer-needed kthreads. */
 	rcu_boost_kthread_setaffinity(rnp, -1);
-
-	/* Orphan the dead CPU's callbacks, and adopt them if appropriate. */
-	raw_spin_lock_irqsave(&rsp->orphan_lock, flags);
-	rcu_send_cbs_to_orphanage(cpu, rsp, rnp, rdp);
-	rcu_adopt_orphan_cbs(rsp, flags);
-	raw_spin_unlock_irqrestore(&rsp->orphan_lock, flags);
-
-	WARN_ONCE(rcu_segcblist_n_cbs(&rdp->cblist) != 0 ||
-		  !rcu_segcblist_empty(&rdp->cblist),
-		  "rcu_cleanup_dead_cpu: Callbacks on offline CPU %d: qlen=%lu, 1stCB=%p\n",
-		  cpu, rcu_segcblist_n_cbs(&rdp->cblist),
-		  rcu_segcblist_first_cb(&rdp->cblist));
 }
 
 /*
@@ -3937,6 +3844,116 @@ void rcu_report_dead(unsigned int cpu)
 	for_each_rcu_flavor(rsp)
 		rcu_cleanup_dying_idle_cpu(cpu, rsp);
 }
+
+/*
+ * Send the specified CPU's RCU callbacks to the orphanage.  The
+ * specified CPU must be offline, and the caller must hold the
+ * ->orphan_lock.
+ */
+static void
+rcu_send_cbs_to_orphanage(int cpu, struct rcu_state *rsp,
+			  struct rcu_node *rnp, struct rcu_data *rdp)
+{
+	lockdep_assert_held(&rsp->orphan_lock);
+
+	/* No-CBs CPUs do not have orphanable callbacks. */
+	if (!IS_ENABLED(CONFIG_HOTPLUG_CPU) || rcu_is_nocb_cpu(rdp->cpu))
+		return;
+
+	/*
+	 * Orphan the callbacks.  First adjust the counts.  This is safe
+	 * because _rcu_barrier() excludes CPU-hotplug operations, so it
+	 * cannot be running now.  Thus no memory barrier is required.
+	 */
+	rdp->n_cbs_orphaned += rcu_segcblist_n_cbs(&rdp->cblist);
+	rcu_segcblist_extract_count(&rdp->cblist, &rsp->orphan_done);
+
+	/*
+	 * Next, move those callbacks still needing a grace period to
+	 * the orphanage, where some other CPU will pick them up.
+	 * Some of the callbacks might have gone partway through a grace
+	 * period, but that is too bad.  They get to start over because we
+	 * cannot assume that grace periods are synchronized across CPUs.
+	 */
+	rcu_segcblist_extract_pend_cbs(&rdp->cblist, &rsp->orphan_pend);
+
+	/*
+	 * Then move the ready-to-invoke callbacks to the orphanage,
+	 * where some other CPU will pick them up.  These will not be
+	 * required to pass though another grace period: They are done.
+	 */
+	rcu_segcblist_extract_done_cbs(&rdp->cblist, &rsp->orphan_done);
+
+	/* Finally, disallow further callbacks on this CPU.  */
+	rcu_segcblist_disable(&rdp->cblist);
+}
+
+/*
+ * Adopt the RCU callbacks from the specified rcu_state structure's
+ * orphanage.  The caller must hold the ->orphan_lock.
+ */
+static void rcu_adopt_orphan_cbs(struct rcu_state *rsp, unsigned long flags)
+{
+	struct rcu_data *rdp = raw_cpu_ptr(rsp->rda);
+
+	lockdep_assert_held(&rsp->orphan_lock);
+
+	/* No-CBs CPUs are handled specially. */
+	if (!IS_ENABLED(CONFIG_HOTPLUG_CPU) ||
+	    rcu_nocb_adopt_orphan_cbs(rsp, rdp, flags))
+		return;
+
+	/* Do the accounting first. */
+	rdp->n_cbs_adopted += rsp->orphan_done.len;
+	if (rsp->orphan_done.len_lazy != rsp->orphan_done.len)
+		rcu_idle_count_callbacks_posted();
+	rcu_segcblist_insert_count(&rdp->cblist, &rsp->orphan_done);
+
+	/*
+	 * We do not need a memory barrier here because the only way we
+	 * can get here if there is an rcu_barrier() in flight is if
+	 * we are the task doing the rcu_barrier().
+	 */
+
+	/* First adopt the ready-to-invoke callbacks, then the done ones. */
+	rcu_segcblist_insert_done_cbs(&rdp->cblist, &rsp->orphan_done);
+	WARN_ON_ONCE(rsp->orphan_done.head);
+	rcu_segcblist_insert_pend_cbs(&rdp->cblist, &rsp->orphan_pend);
+	WARN_ON_ONCE(rsp->orphan_pend.head);
+	WARN_ON_ONCE(rcu_segcblist_empty(&rdp->cblist) !=
+		     !rcu_segcblist_n_cbs(&rdp->cblist));
+}
+
+/* Orphan the dead CPU's callbacks, and then adopt them. */
+static void rcu_migrate_callbacks(int cpu, struct rcu_state *rsp)
+{
+	unsigned long flags;
+	struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
+	struct rcu_node *rnp = rdp->mynode;  /* Outgoing CPU's rdp & rnp. */
+
+	raw_spin_lock_irqsave(&rsp->orphan_lock, flags);
+	rcu_send_cbs_to_orphanage(cpu, rsp, rnp, rdp);
+	rcu_adopt_orphan_cbs(rsp, flags);
+	raw_spin_unlock_irqrestore(&rsp->orphan_lock, flags);
+	WARN_ONCE(rcu_segcblist_n_cbs(&rdp->cblist) != 0 ||
+		  !rcu_segcblist_empty(&rdp->cblist),
+		  "rcu_cleanup_dead_cpu: Callbacks on offline CPU %d: qlen=%lu, 1stCB=%p\n",
+		  cpu, rcu_segcblist_n_cbs(&rdp->cblist),
+		  rcu_segcblist_first_cb(&rdp->cblist));
+}
+
+/*
+ * The outgoing CPU has just passed through the dying-idle state,
+ * and we are being invoked from the CPU that was IPIed to continue the
+ * offline operation.  We need to migrate the outgoing CPU's callbacks.
+ */
+void rcutree_migrate_callbacks(int cpu)
+{
+	struct rcu_state *rsp;
+
+	for_each_rcu_flavor(rsp)
+		rcu_migrate_callbacks(cpu, rsp);
+}
 #endif
 
 /*