[PATCH tip/core/rcu 22/22] rcu: Add diagnostics for offline CPUs failing to report QS

[Paul E. McKenney]

CPUs are expected to report quiescent states when coming online and
when going offline, and grace-period initialization is supposed to
handle any race conditions where a CPU's ->qsmask bit is set just after
it goes offline.  This commit adds diagnostics for the case where an
offline CPU nevertheless has a grace period waiting on it.

Signed-off-by: Paul E. McKenney <paulmck@xxxxxxxxxxxxxxxxxx>
---
 kernel/rcu/tree.c | 22 ++++++++++++++++++++++
 kernel/rcu/tree.h |  1 +
 2 files changed, 23 insertions(+)

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 9e83743ca9d9..4b0aee4f9318 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -1188,6 +1188,27 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
 		smp_store_release(ruqp, true);
 	}
 
+	/* If waiting too long on an offline CPU, complain. */
+	if (!(rdp->grpmask & rcu_rnp_online_cpus(rnp)) &&
+	    time_after(jiffies, rdp->rsp->gp_start + HZ)) {
+		bool onl;
+		struct rcu_node *rnp1;
+
+		WARN_ON(1);  /* Offline CPUs are supposed to report QS! */
+		pr_info("%s: grp: %d-%d level: %d ->gp_seq %ld ->completedqs %ld\n",
+			__func__, rnp->grplo, rnp->grphi, rnp->level,
+			(long)rnp->gp_seq, (long)rnp->completedqs);
+		for (rnp1 = rnp; rnp1; rnp1 = rnp1->parent)
+			pr_info("%s: %d:%d ->qsmask %#lx ->qsmaskinit %#lx ->qsmaskinitnext %#lx ->rcu_gp_init_mask %#lx\n",
+				__func__, rnp1->grplo, rnp1->grphi, rnp1->qsmask, rnp1->qsmaskinit, rnp1->qsmaskinitnext, rnp1->rcu_gp_init_mask);
+		onl = !!(rdp->grpmask & rcu_rnp_online_cpus(rnp));
+		pr_info("%s %d: %c online: %ld(%d) offline: %ld(%d)\n",
+			__func__, rdp->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);
+		return 1; /* Break things loose after complaining. */
+	}
+
 	/*
 	 * A CPU running for an extended time within the kernel can
 	 * delay RCU grace periods.  When the CPU is in NO_HZ_FULL mode,
@@ -1967,6 +1988,7 @@ static bool rcu_gp_init(struct rcu_state *rsp)
 					    rnp->grphi, rnp->qsmask);
 		/* Quiescent states for tasks on any now-offline CPUs. */
 		mask = rnp->qsmask & ~rnp->qsmaskinitnext;
+		rnp->rcu_gp_init_mask = mask;
 		if ((mask || rnp->wait_blkd_tasks) && rcu_is_leaf_node(rnp))
 			rcu_report_qs_rnp(mask, rsp, rnp, rnp->gp_seq, flags);
 		else
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index 8077aff7ab40..d51e6edc8e83 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -90,6 +90,7 @@ struct rcu_node {
 				/*  an rcu_data structure, otherwise, each */
 				/*  bit corresponds to a child rcu_node */
 				/*  structure. */
+	unsigned long rcu_gp_init_mask;	/* Mask of offline CPUs at GP init. */
 	unsigned long qsmaskinit;
 				/* Per-GP initial value for qsmask. */
 				/*  Initialized from ->qsmaskinitnext at the */
-- 
2.17.1