Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
From:   Zqiang <qiang1.zhang@intel.com>
To:     paulmck@kernel.org, frederic@kernel.org
Cc:     rcu@vger.kernel.org, linux-kernel@vger.kernel.org
Subject: [PATCH v4 1/2] rcu: Call rcu_nocb_rdp_deoffload() directly after rcuog/op kthreads spawn failed
Date:   Tue, 22 Mar 2022 21:17:52 +0800
Message-Id: <20220322131753.1680329-2-qiang1.zhang@intel.com>
In-Reply-To: <20220322131753.1680329-1-qiang1.zhang@intel.com>
References: <20220322131753.1680329-1-qiang1.zhang@intel.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

If the rcuog/op kthreads spawn failed, the offload rdp need to
be deoffload, otherwise because target rdp is considered offloaded
but nothing actually handles the callbacks.

Signed-off-by: Zqiang <qiang1.zhang@intel.com>
---
 kernel/rcu/tree_nocb.h | 77 +++++++++++++++++++++++++++++++++---------
 1 file changed, 61 insertions(+), 16 deletions(-)

diff --git a/kernel/rcu/tree_nocb.h b/kernel/rcu/tree_nocb.h
index 46694e13398a..154934f3daa9 100644
--- a/kernel/rcu/tree_nocb.h
+++ b/kernel/rcu/tree_nocb.h
@@ -972,10 +972,7 @@ static int rdp_offload_toggle(struct rcu_data *rdp,
 	}
 	raw_spin_unlock_irqrestore(&rdp_gp->nocb_gp_lock, flags);
 
-	if (wake_gp)
-		wake_up_process(rdp_gp->nocb_gp_kthread);
-
-	return 0;
+	return wake_gp;
 }
 
 static long rcu_nocb_rdp_deoffload(void *arg)
@@ -983,9 +980,18 @@ static long rcu_nocb_rdp_deoffload(void *arg)
 	struct rcu_data *rdp = arg;
 	struct rcu_segcblist *cblist = &rdp->cblist;
 	unsigned long flags;
-	int ret;
+	int wake_gp;
+	struct rcu_data *rdp_gp = rdp->nocb_gp_rdp;
+	int condition;
 
-	WARN_ON_ONCE(rdp->cpu != raw_smp_processor_id());
+	/*
+	 * The rcu_nocb_rdp_deoffload() will be called directly when
+	 * rcuog/op spawn failed, because at this time the rdp->cpu
+	 * is not online(cpu_online(rdp->cpu) return false), the deoffload
+	 * operation was not performed on rdp->cpu, to avoid warnings
+	 * add cpu_online(rdp->cpu) condition judgment.
+	 */
+	WARN_ON_ONCE((rdp->cpu != raw_smp_processor_id()) && cpu_online(rdp->cpu));
 
 	pr_info("De-offloading %d\n", rdp->cpu);
 
@@ -1009,10 +1015,35 @@ static long rcu_nocb_rdp_deoffload(void *arg)
 	 */
 	rcu_segcblist_set_flags(cblist, SEGCBLIST_RCU_CORE);
 	invoke_rcu_core();
-	ret = rdp_offload_toggle(rdp, false, flags);
-	swait_event_exclusive(rdp->nocb_state_wq,
-			      !rcu_segcblist_test_flags(cblist, SEGCBLIST_KTHREAD_CB |
-							SEGCBLIST_KTHREAD_GP));
+	wake_gp = rdp_offload_toggle(rdp, false, flags);
+
+	mutex_lock(&rdp_gp->nocb_gp_kthread_mutex);
+	if (rdp_gp->nocb_gp_kthread) {
+		if (wake_gp)
+			wake_up_process(rdp_gp->nocb_gp_kthread);
+
+		if (rdp->nocb_cb_kthread) {
+			condition = SEGCBLIST_KTHREAD_CB | SEGCBLIST_KTHREAD_GP;
+		} else {
+			/*
+			 *If rcuop kthread spawn failed, direct remove SEGCBLIST_KTHREAD_CB
+			 *just wait SEGCBLIST_KTHREAD_GP to be cleared.
+			 */
+			condition = SEGCBLIST_KTHREAD_GP;
+			rcu_nocb_lock_irqsave(rdp, flags);
+			rcu_segcblist_clear_flags(cblist, SEGCBLIST_KTHREAD_CB);
+			rcu_nocb_unlock_irqrestore(rdp, flags);
+		}
+		swait_event_exclusive(rdp->nocb_state_wq,
+					!rcu_segcblist_test_flags(cblist, condition));
+	} else {
+		rcu_nocb_lock_irqsave(rdp, flags);
+		rcu_segcblist_clear_flags(cblist,
+				SEGCBLIST_KTHREAD_CB | SEGCBLIST_KTHREAD_GP);
+		rcu_nocb_unlock_irqrestore(rdp, flags);
+	}
+	mutex_unlock(&rdp_gp->nocb_gp_kthread_mutex);
+
 	/* Stop nocb_gp_wait() from iterating over this structure. */
 	list_del_rcu(&rdp->nocb_entry_rdp);
 	/*
@@ -1035,7 +1066,7 @@ static long rcu_nocb_rdp_deoffload(void *arg)
 	WARN_ON_ONCE(rcu_cblist_n_cbs(&rdp->nocb_bypass));
 
 
-	return ret;
+	return 0;
 }
 
 int rcu_nocb_cpu_deoffload(int cpu)
@@ -1067,7 +1098,8 @@ static long rcu_nocb_rdp_offload(void *arg)
 	struct rcu_data *rdp = arg;
 	struct rcu_segcblist *cblist = &rdp->cblist;
 	unsigned long flags;
-	int ret;
+	int wake_gp;
+	struct rcu_data *rdp_gp = rdp->nocb_gp_rdp;
 
 	WARN_ON_ONCE(rdp->cpu != raw_smp_processor_id());
 	/*
@@ -1077,6 +1109,9 @@ static long rcu_nocb_rdp_offload(void *arg)
 	if (!rdp->nocb_gp_rdp)
 		return -EINVAL;
 
+	if (WARN_ON_ONCE(!rdp_gp->nocb_gp_kthread))
+		return -EINVAL;
+
 	pr_info("Offloading %d\n", rdp->cpu);
 
 	/*
@@ -1111,7 +1146,9 @@ static long rcu_nocb_rdp_offload(void *arg)
 	 *      WRITE flags               READ callbacks
 	 *      rcu_nocb_unlock()         rcu_nocb_unlock()
 	 */
-	ret = rdp_offload_toggle(rdp, true, flags);
+	wake_gp = rdp_offload_toggle(rdp, true, flags);
+	if (wake_gp)
+		wake_up_process(rdp_gp->nocb_gp_kthread);
 	swait_event_exclusive(rdp->nocb_state_wq,
 			      rcu_segcblist_test_flags(cblist, SEGCBLIST_KTHREAD_CB) &&
 			      rcu_segcblist_test_flags(cblist, SEGCBLIST_KTHREAD_GP));
@@ -1124,7 +1161,7 @@ static long rcu_nocb_rdp_offload(void *arg)
 	rcu_segcblist_clear_flags(cblist, SEGCBLIST_RCU_CORE);
 	rcu_nocb_unlock_irqrestore(rdp, flags);
 
-	return ret;
+	return 0;
 }
 
 int rcu_nocb_cpu_offload(int cpu)
@@ -1246,7 +1283,7 @@ static void rcu_spawn_cpu_nocb_kthread(int cpu)
 				"rcuog/%d", rdp_gp->cpu);
 		if (WARN_ONCE(IS_ERR(t), "%s: Could not start rcuo GP kthread, OOM is now expected behavior\n", __func__)) {
 			mutex_unlock(&rdp_gp->nocb_gp_kthread_mutex);
-			return;
+			goto end;
 		}
 		WRITE_ONCE(rdp_gp->nocb_gp_kthread, t);
 		if (kthread_prio)
@@ -1258,12 +1295,20 @@ static void rcu_spawn_cpu_nocb_kthread(int cpu)
 	t = kthread_run(rcu_nocb_cb_kthread, rdp,
 			"rcuo%c/%d", rcu_state.abbr, cpu);
 	if (WARN_ONCE(IS_ERR(t), "%s: Could not start rcuo CB kthread, OOM is now expected behavior\n", __func__))
-		return;
+		goto end;
 
 	if (kthread_prio)
 		sched_setscheduler_nocheck(t, SCHED_FIFO, &sp);
 	WRITE_ONCE(rdp->nocb_cb_kthread, t);
 	WRITE_ONCE(rdp->nocb_gp_kthread, rdp_gp->nocb_gp_kthread);
+	return;
+end:
+	mutex_lock(&rcu_state.barrier_mutex);
+	if (rcu_rdp_is_offloaded(rdp)) {
+		rcu_nocb_rdp_deoffload(rdp);
+		cpumask_clear_cpu(cpu, rcu_nocb_mask);
+	}
+	mutex_unlock(&rcu_state.barrier_mutex);
 }
 
 /* How many CB CPU IDs per GP kthread?  Default of -1 for sqrt(nr_cpu_ids). */
-- 
2.25.1