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;
Date:   Mon, 25 Jul 2022 10:59:52 +0100
Message-Id: <20220725095952.206884-1-vdonnefort@google.com>
Mime-Version: 1.0
Subject: [PATCH v5] cpu/hotplug: Do not bail-out in DYING/STARTING sections
From:   Vincent Donnefort <vdonnefort@google.com>
To:     peterz@infradead.org, tglx@linutronix.de
Cc:     linux-kernel@vger.kernel.org, vschneid@redhat.com,
        regressions@leemhuis.info, kernel-team@android.com,
        Vincent Donnefort <vdonnefort@google.com>,
        Derek Dolney <z23@posteo.net>
Content-Type: text/plain; charset="UTF-8"
Precedence: bulk

The DYING/STARTING callbacks are not expected to fail. However, as reported
by Derek, drivers such as tboot are still free to return errors within
those sections, which halts the hot(un)plug and leaves the CPU in an
unrecoverable state.

No rollback being possible there, let's only log the failures and proceed
with the following steps. This restores the hotplug behaviour prior to
commit 453e41085183 ("cpu/hotplug: Add cpuhp_invoke_callback_range()")

Link: https://bugzilla.kernel.org/show_bug.cgi?id=215867
Fixes: 453e41085183 ("cpu/hotplug: Add cpuhp_invoke_callback_range()")
Reported-by: Derek Dolney <z23@posteo.net>
Signed-off-by: Vincent Donnefort <vdonnefort@google.com>
Tested-by: Derek Dolney <z23@posteo.net>

v4 -> v5:
   - Remove WARN, only log broken states with pr_warn.
v3 -> v4:
   - Sorry ... wrong commit description style ...
v2 -> v3:
   - Tested-by tag.
   - Refine commit description.
   - Bugzilla link.
v1 -> v2:
   - Commit message rewording.
   - More details in the warnings.
   - Some variable renaming

diff --git a/kernel/cpu.c b/kernel/cpu.c
index bbad5e375d3b..621e5af42d57 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -663,21 +663,51 @@ static bool cpuhp_next_state(bool bringup,
 	return true;
 }
 
-static int cpuhp_invoke_callback_range(bool bringup,
-				       unsigned int cpu,
-				       struct cpuhp_cpu_state *st,
-				       enum cpuhp_state target)
+static int __cpuhp_invoke_callback_range(bool bringup,
+					 unsigned int cpu,
+					 struct cpuhp_cpu_state *st,
+					 enum cpuhp_state target,
+					 bool nofail)
 {
 	enum cpuhp_state state;
-	int err = 0;
+	int ret = 0;
 
 	while (cpuhp_next_state(bringup, &state, st, target)) {
+		int err;
+
 		err = cpuhp_invoke_callback(cpu, state, bringup, NULL, NULL);
-		if (err)
+		if (!err)
+			continue;
+
+		if (nofail) {
+			pr_warn("CPU %u %s state %s (%d) failed (%d)\n",
+				cpu, bringup ? "UP" : "DOWN",
+				cpuhp_get_step(st->state)->name,
+				st->state, err);
+			ret = -1;
+		} else {
+			ret = err;
 			break;
+		}
 	}
 
-	return err;
+	return ret;
+}
+
+static inline int cpuhp_invoke_callback_range(bool bringup,
+					      unsigned int cpu,
+					      struct cpuhp_cpu_state *st,
+					      enum cpuhp_state target)
+{
+	return __cpuhp_invoke_callback_range(bringup, cpu, st, target, false);
+}
+
+static inline void cpuhp_invoke_callback_range_nofail(bool bringup,
+						      unsigned int cpu,
+						      struct cpuhp_cpu_state *st,
+						      enum cpuhp_state target)
+{
+	__cpuhp_invoke_callback_range(bringup, cpu, st, target, true);
 }
 
 static inline bool can_rollback_cpu(struct cpuhp_cpu_state *st)
@@ -999,7 +1029,6 @@ static int take_cpu_down(void *_param)
 	struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state);
 	enum cpuhp_state target = max((int)st->target, CPUHP_AP_OFFLINE);
 	int err, cpu = smp_processor_id();
-	int ret;
 
 	/* Ensure this CPU doesn't handle any more interrupts. */
 	err = __cpu_disable();
@@ -1012,13 +1041,11 @@ static int take_cpu_down(void *_param)
 	 */
 	WARN_ON(st->state != (CPUHP_TEARDOWN_CPU - 1));
 
-	/* Invoke the former CPU_DYING callbacks */
-	ret = cpuhp_invoke_callback_range(false, cpu, st, target);
-
 	/*
+	 * Invoke the former CPU_DYING callbacks
 	 * DYING must not fail!
 	 */
-	WARN_ON_ONCE(ret);
+	cpuhp_invoke_callback_range_nofail(false, cpu, st, target);
 
 	/* Give up timekeeping duties */
 	tick_handover_do_timer();
@@ -1296,16 +1323,14 @@ void notify_cpu_starting(unsigned int cpu)
 {
 	struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
 	enum cpuhp_state target = min((int)st->target, CPUHP_AP_ONLINE);
-	int ret;
 
 	rcu_cpu_starting(cpu);	/* Enables RCU usage on this CPU. */
 	cpumask_set_cpu(cpu, &cpus_booted_once_mask);
-	ret = cpuhp_invoke_callback_range(true, cpu, st, target);
 
 	/*
 	 * STARTING must not fail!
 	 */
-	WARN_ON_ONCE(ret);
+	cpuhp_invoke_callback_range_nofail(true, cpu, st, target);
 }
 
 /*
-- 
2.37.1.359.gd136c6c3e2-goog