From 62f250694092dd5fef9900dc3126f07110bf9d48 Mon Sep 17 00:00:00 2001 From: Vincent Donnefort Date: Tue, 16 Feb 2021 10:35:05 +0000 Subject: cpu/hotplug: CPUHP_BRINGUP_CPU failure exception The atomic states (between CPUHP_AP_IDLE_DEAD and CPUHP_AP_ONLINE) are triggered by the CPUHP_BRINGUP_CPU step. If the latter fails, no atomic state can be rolled back. DEAD callbacks too can't fail and disallow recovery. As a consequence, during hotunplug, the fail injection interface should prohibit all states from CPUHP_BRINGUP_CPU to CPUHP_ONLINE. Signed-off-by: Vincent Donnefort Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Ingo Molnar Link: https://lkml.kernel.org/r/20210216103506.416286-3-vincent.donnefort@arm.com --- kernel/cpu.c | 19 ++++++++++++++++--- 1 file changed, 16 insertions(+), 3 deletions(-) (limited to 'kernel/cpu.c') diff --git a/kernel/cpu.c b/kernel/cpu.c index 9121edf5759a..680ed8f427c0 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -1045,9 +1045,13 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen, * to do the further cleanups. */ ret = cpuhp_down_callbacks(cpu, st, target); - if (ret && st->state == CPUHP_TEARDOWN_CPU && st->state < prev_state) { - cpuhp_reset_state(st, prev_state); - __cpuhp_kick_ap(st); + if (ret && st->state < prev_state) { + if (st->state == CPUHP_TEARDOWN_CPU) { + cpuhp_reset_state(st, prev_state); + __cpuhp_kick_ap(st); + } else { + WARN(1, "DEAD callback error for CPU%d", cpu); + } } out: @@ -2221,6 +2225,15 @@ static ssize_t write_cpuhp_fail(struct device *dev, if (cpuhp_is_atomic_state(fail)) return -EINVAL; + /* + * DEAD callbacks cannot fail... + * ... neither can CPUHP_BRINGUP_CPU during hotunplug. The latter + * triggering STARTING callbacks, a failure in this state would + * hinder rollback. + */ + if (fail <= CPUHP_BRINGUP_CPU && st->state > CPUHP_BRINGUP_CPU) + return -EINVAL; + /* * Cannot fail anything that doesn't have callbacks. */ -- cgit