rcu: Add CPU online/offline state to dump_blkd_tasks()

Interactions between CPU-hotplug operations and grace-period
initialization can result in dump_blkd_tasks().  One of the first
debugging actions in this case is to search back in dmesg to work
out which of the affected rcu_node structure's CPUs are online and to
determine the last CPU-hotplug operation affecting any of those CPUs.
This can be laborious and error-prone, especially when console output
is lost.

This commit therefore causes dump_blkd_tasks() to dump the state of
the affected rcu_node structure's CPUs and the last grace period during
which the last offline and online operation affected each of these CPUs.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>

3 files changed, 39 insertions, 10 deletions

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 5f1a11f1f7bc..a2503ef1bbe2 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -1954,7 +1954,7 @@ static bool rcu_gp_init(struct rcu_state *rsp)
 		rcu_gp_slow(rsp, gp_init_delay);
 		raw_spin_lock_irqsave_rcu_node(rnp, flags);
 		rdp = this_cpu_ptr(rsp->rda);
-		rcu_preempt_check_blocked_tasks(rnp);
+		rcu_preempt_check_blocked_tasks(rsp, rnp);
 		rnp->qsmask = rnp->qsmaskinit;
 		WRITE_ONCE(rnp->gp_seq, rsp->gp_seq);
 		if (rnp == rdp->mynode)
@@ -2063,7 +2063,7 @@ static void rcu_gp_cleanup(struct rcu_state *rsp)
 	rcu_for_each_node_breadth_first(rsp, rnp) {
 		raw_spin_lock_irq_rcu_node(rnp);
 		if (WARN_ON_ONCE(rcu_preempt_blocked_readers_cgp(rnp)))
-			dump_blkd_tasks(rnp, 10);
+			dump_blkd_tasks(rsp, rnp, 10);
 		WARN_ON_ONCE(rnp->qsmask);
 		WRITE_ONCE(rnp->gp_seq, new_gp_seq);
 		rdp = this_cpu_ptr(rsp->rda);
@@ -3516,6 +3516,10 @@ rcu_boot_init_percpu_data(int cpu, struct rcu_state *rsp)
 	rdp->dynticks = &per_cpu(rcu_dynticks, cpu);
 	WARN_ON_ONCE(rdp->dynticks->dynticks_nesting != 1);
 	WARN_ON_ONCE(rcu_dynticks_in_eqs(rcu_dynticks_snap(rdp->dynticks)));
+	rdp->rcu_ofl_gp_seq = rsp->gp_seq;
+	rdp->rcu_ofl_gp_flags = RCU_GP_CLEANED;
+	rdp->rcu_onl_gp_seq = rsp->gp_seq;
+	rdp->rcu_onl_gp_flags = RCU_GP_CLEANED;
 	rdp->cpu = cpu;
 	rdp->rsp = rsp;
 	rcu_boot_init_nocb_percpu_data(rdp);
@@ -3711,6 +3715,8 @@ void rcu_cpu_starting(unsigned int cpu)
 		/* Allow lockless access for expedited grace periods. */
 		smp_store_release(&rsp->ncpus, rsp->ncpus + nbits); /* ^^^ */
 		rcu_gpnum_ovf(rnp, rdp); /* Offline-induced counter wrap? */
+		rdp->rcu_onl_gp_seq = READ_ONCE(rsp->gp_seq);
+		rdp->rcu_onl_gp_flags = READ_ONCE(rsp->gp_flags);
 		if (rnp->qsmask & mask) { /* RCU waiting on incoming CPU? */
 			/* Report QS -after- changing ->qsmaskinitnext! */
 			rcu_report_qs_rnp(mask, rsp, rnp, rnp->gp_seq, flags);
@@ -3738,6 +3744,8 @@ static void rcu_cleanup_dying_idle_cpu(int cpu, struct rcu_state *rsp)
 	mask = rdp->grpmask;
 	spin_lock(&rsp->ofl_lock);
 	raw_spin_lock_irqsave_rcu_node(rnp, flags); /* Enforce GP memory-order guarantee. */
+	rdp->rcu_ofl_gp_seq = READ_ONCE(rsp->gp_seq);
+	rdp->rcu_ofl_gp_flags = READ_ONCE(rsp->gp_flags);
 	if (rnp->qsmask & mask) { /* RCU waiting on outgoing CPU? */
 		/* Report quiescent state -before- changing ->qsmaskinitnext! */
 		rcu_report_qs_rnp(mask, rsp, rnp, rnp->gp_seq, flags);
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index 795d469c6f67..f52bc059bfec 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -255,12 +255,16 @@ struct rcu_data {
 					/* Leader CPU takes GP-end wakeups. */
 #endif /* #ifdef CONFIG_RCU_NOCB_CPU */
 
-	/* 7) RCU CPU stall data. */
+	/* 7) Diagnostic data, including RCU CPU stall warnings. */
 	unsigned int softirq_snap;	/* Snapshot of softirq activity. */
 	/* ->rcu_iw* fields protected by leaf rcu_node ->lock. */
 	struct irq_work rcu_iw;		/* Check for non-irq activity. */
 	bool rcu_iw_pending;		/* Is ->rcu_iw pending? */
 	unsigned long rcu_iw_gp_seq;	/* ->gp_seq associated with ->rcu_iw. */
+	unsigned long rcu_ofl_gp_seq;	/* ->gp_seq at last offline. */
+	short rcu_ofl_gp_flags;		/* ->gp_flags at last offline. */
+	unsigned long rcu_onl_gp_seq;	/* ->gp_seq at last online. */
+	short rcu_onl_gp_flags;		/* ->gp_flags at last online. */
 
 	int cpu;
 	struct rcu_state *rsp;
@@ -431,11 +435,13 @@ static bool rcu_preempt_has_tasks(struct rcu_node *rnp);
 static void rcu_print_detail_task_stall(struct rcu_state *rsp);
 static int rcu_print_task_stall(struct rcu_node *rnp);
 static int rcu_print_task_exp_stall(struct rcu_node *rnp);
-static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp);
+static void rcu_preempt_check_blocked_tasks(struct rcu_state *rsp,
+					    struct rcu_node *rnp);
 static void rcu_preempt_check_callbacks(void);
 void call_rcu(struct rcu_head *head, rcu_callback_t func);
 static void __init __rcu_init_preempt(void);
-static void dump_blkd_tasks(struct rcu_node *rnp, int ncheck);
+static void dump_blkd_tasks(struct rcu_state *rsp, struct rcu_node *rnp,
+			    int ncheck);
 static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags);
 static void rcu_preempt_boost_start_gp(struct rcu_node *rnp);
 static void invoke_rcu_callbacks_kthread(void);
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index f45ff97b0d51..613372246a07 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -699,13 +699,14 @@ static int rcu_print_task_exp_stall(struct rcu_node *rnp)
  * Also, if there are blocked tasks on the list, they automatically
  * block the newly created grace period, so set up ->gp_tasks accordingly.
  */
-static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp)
+static void
+rcu_preempt_check_blocked_tasks(struct rcu_state *rsp, struct rcu_node *rnp)
 {
 	struct task_struct *t;
 
 	RCU_LOCKDEP_WARN(preemptible(), "rcu_preempt_check_blocked_tasks() invoked with preemption enabled!!!\n");
 	if (WARN_ON_ONCE(rcu_preempt_blocked_readers_cgp(rnp)))
-		dump_blkd_tasks(rnp, 10);
+		dump_blkd_tasks(rsp, rnp, 10);
 	if (rcu_preempt_has_tasks(rnp) &&
 	    (rnp->qsmaskinit || rnp->wait_blkd_tasks)) {
 		rnp->gp_tasks = rnp->blkd_tasks.next;
@@ -854,10 +855,14 @@ void exit_rcu(void)
  * Dump the blocked-tasks state, but limit the list dump to the
  * specified number of elements.
  */
-static void dump_blkd_tasks(struct rcu_node *rnp, int ncheck)
+static void
+dump_blkd_tasks(struct rcu_state *rsp, struct rcu_node *rnp, int ncheck)
 {
+	int cpu;
 	int i;
 	struct list_head *lhp;
+	bool onl;
+	struct rcu_data *rdp;
 	struct rcu_node *rnp1;
 
 	raw_lockdep_assert_held_rcu_node(rnp);
@@ -877,6 +882,14 @@ static void dump_blkd_tasks(struct rcu_node *rnp, int ncheck)
 			break;
 	}
 	pr_cont("\n");
+	for (cpu = rnp->grplo; cpu <= rnp->grphi; cpu++) {
+		rdp = per_cpu_ptr(rsp->rda, cpu);
+		onl = !!(rdp->grpmask & rcu_rnp_online_cpus(rnp));
+		pr_info("\t%d: %c online: %ld(%d) offline: %ld(%d)\n",
+			cpu, ".o"[onl],
+			(long)rdp->rcu_onl_gp_seq, rdp->rcu_onl_gp_flags,
+			(long)rdp->rcu_ofl_gp_seq, rdp->rcu_ofl_gp_flags);
+	}
 }
 
 #else /* #ifdef CONFIG_PREEMPT_RCU */
@@ -949,7 +962,8 @@ static int rcu_print_task_exp_stall(struct rcu_node *rnp)
  * so there is no need to check for blocked tasks.  So check only for
  * bogus qsmask values.
  */
-static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp)
+static void
+rcu_preempt_check_blocked_tasks(struct rcu_state *rsp, struct rcu_node *rnp)
 {
 	WARN_ON_ONCE(rnp->qsmask);
 }
@@ -990,7 +1004,8 @@ void exit_rcu(void)
 /*
  * Dump the guaranteed-empty blocked-tasks state.  Trust but verify.
  */
-static void dump_blkd_tasks(struct rcu_node *rnp, int ncheck)
+static void
+dump_blkd_tasks(struct rcu_state *rsp, struct rcu_node *rnp, int ncheck)
 {
 	WARN_ON_ONCE(!list_empty(&rnp->blkd_tasks));
 }