summaryrefslogtreecommitdiffstats
path: root/kernel/cpu.c
diff options
context:
space:
mode:
authorPeter Zijlstra <peterz@infradead.org>2020-04-01 17:40:33 -0400
committerPeter Zijlstra <peterz@infradead.org>2020-04-30 20:14:41 +0200
commitbf2c59fce4074e55d622089b34be3a6bc95484fb (patch)
treeab49a251ee38c0f944ebe73b644829116d93b102 /kernel/cpu.c
parentf38f12d1e0811c0ee59260b2bdadedf99e16c4af (diff)
downloadlinux-bf2c59fce4074e55d622089b34be3a6bc95484fb.tar.bz2
sched/core: Fix illegal RCU from offline CPUs
In the CPU-offline process, it calls mmdrop() after idle entry and the subsequent call to cpuhp_report_idle_dead(). Once execution passes the call to rcu_report_dead(), RCU is ignoring the CPU, which results in lockdep complaining when mmdrop() uses RCU from either memcg or debugobjects below. Fix it by cleaning up the active_mm state from BP instead. Every arch which has CONFIG_HOTPLUG_CPU should have already called idle_task_exit() from AP. The only exception is parisc because it switches them to &init_mm unconditionally (see smp_boot_one_cpu() and smp_cpu_init()), but the patch will still work there because it calls mmgrab(&init_mm) in smp_cpu_init() and then should call mmdrop(&init_mm) in finish_cpu(). WARNING: suspicious RCU usage ----------------------------- kernel/workqueue.c:710 RCU or wq_pool_mutex should be held! other info that might help us debug this: RCU used illegally from offline CPU! Call Trace: dump_stack+0xf4/0x164 (unreliable) lockdep_rcu_suspicious+0x140/0x164 get_work_pool+0x110/0x150 __queue_work+0x1bc/0xca0 queue_work_on+0x114/0x120 css_release+0x9c/0xc0 percpu_ref_put_many+0x204/0x230 free_pcp_prepare+0x264/0x570 free_unref_page+0x38/0xf0 __mmdrop+0x21c/0x2c0 idle_task_exit+0x170/0x1b0 pnv_smp_cpu_kill_self+0x38/0x2e0 cpu_die+0x48/0x64 arch_cpu_idle_dead+0x30/0x50 do_idle+0x2f4/0x470 cpu_startup_entry+0x38/0x40 start_secondary+0x7a8/0xa80 start_secondary_resume+0x10/0x14 Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Signed-off-by: Qian Cai <cai@lca.pw> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Acked-by: Michael Ellerman <mpe@ellerman.id.au> (powerpc) Link: https://lkml.kernel.org/r/20200401214033.8448-1-cai@lca.pw
Diffstat (limited to 'kernel/cpu.c')
-rw-r--r--kernel/cpu.c18
1 files changed, 17 insertions, 1 deletions
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 2371292f30b0..244d30544377 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -3,6 +3,7 @@
*
* This code is licenced under the GPL.
*/
+#include <linux/sched/mm.h>
#include <linux/proc_fs.h>
#include <linux/smp.h>
#include <linux/init.h>
@@ -564,6 +565,21 @@ static int bringup_cpu(unsigned int cpu)
return bringup_wait_for_ap(cpu);
}
+static int finish_cpu(unsigned int cpu)
+{
+ struct task_struct *idle = idle_thread_get(cpu);
+ struct mm_struct *mm = idle->active_mm;
+
+ /*
+ * idle_task_exit() will have switched to &init_mm, now
+ * clean up any remaining active_mm state.
+ */
+ if (mm != &init_mm)
+ idle->active_mm = &init_mm;
+ mmdrop(mm);
+ return 0;
+}
+
/*
* Hotplug state machine related functions
*/
@@ -1549,7 +1565,7 @@ static struct cpuhp_step cpuhp_hp_states[] = {
[CPUHP_BRINGUP_CPU] = {
.name = "cpu:bringup",
.startup.single = bringup_cpu,
- .teardown.single = NULL,
+ .teardown.single = finish_cpu,
.cant_stop = true,
},
/* Final state before CPU kills itself */