smp/hotplug: Hotplug state fail injection

Add a sysfs file to one-time fail a specific state. This can be used
to test the state rollback code paths.

Something like this (hotplug-up.sh):

  #!/bin/bash

  echo 0 > /debug/sched_debug
  echo 1 > /debug/tracing/events/cpuhp/enable

  ALL_STATES=`cat /sys/devices/system/cpu/hotplug/states | cut -d':' -f1`
  STATES=${1:-$ALL_STATES}

  for state in $STATES
  do
	  echo 0 > /sys/devices/system/cpu/cpu1/online
	  echo 0 > /debug/tracing/trace
	  echo Fail state: $state
	  echo $state > /sys/devices/system/cpu/cpu1/hotplug/fail
	  cat /sys/devices/system/cpu/cpu1/hotplug/fail
	  echo 1 > /sys/devices/system/cpu/cpu1/online

	  cat /debug/tracing/trace > hotfail-${state}.trace

	  sleep 1
  done

Can be used to test for all possible rollback (barring multi-instance)
scenarios on CPU-up, CPU-down is a trivial modification of the above.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: bigeasy@linutronix.de
Cc: efault@gmx.de
Cc: rostedt@goodmis.org
Cc: max.byungchul.park@gmail.com
Link: https://lkml.kernel.org/r/20170920170546.972581715@infradead.org

diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index 477b2e6f60f72bbfb40ff7370b2a0a768df60e49..6d508767e14455d52470fe806f5f923637561edc 100644 (file)
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -22,7 +22,8 @@
  */
 
 enum cpuhp_state {
-       CPUHP_OFFLINE,
+       CPUHP_INVALID = -1,
+       CPUHP_OFFLINE = 0,
        CPUHP_CREATE_THREADS,
        CPUHP_PERF_PREPARE,
        CPUHP_PERF_X86_PREPARE,

diff --git a/kernel/cpu.c b/kernel/cpu.c
index 6bbe261b851f34b0fc3bb8c419aac8fcdd9489a1..8de11a29e4955d846c0d1d90a2c0b3a207e21a3d 100644 (file)
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -52,6 +52,7 @@
 struct cpuhp_cpu_state {
        enum cpuhp_state        state;
        enum cpuhp_state        target;
+       enum cpuhp_state        fail;
 #ifdef CONFIG_SMP
        struct task_struct      *thread;
        bool                    should_run;
@@ -67,7 +68,9 @@ struct cpuhp_cpu_state {
 #endif
 };
 
-static DEFINE_PER_CPU(struct cpuhp_cpu_state, cpuhp_state);
+static DEFINE_PER_CPU(struct cpuhp_cpu_state, cpuhp_state) = {
+       .fail = CPUHP_INVALID,
+};
 
 #if defined(CONFIG_LOCKDEP) && defined(CONFIG_SMP)
 static struct lockdep_map cpuhp_state_up_map =
@@ -160,6 +163,15 @@ static int cpuhp_invoke_callback(unsigned int cpu, enum cpuhp_state state,
        int (*cb)(unsigned int cpu);
        int ret, cnt;
 
+       if (st->fail == state) {
+               st->fail = CPUHP_INVALID;
+
+               if (!(bringup ? step->startup.single : step->teardown.single))
+                       return 0;
+
+               return -EAGAIN;
+       }
+
        if (!step->multi_instance) {
                WARN_ON_ONCE(lastp && *lastp);
                cb = bringup ? step->startup.single : step->teardown.single;
@@ -1805,9 +1817,55 @@ static ssize_t show_cpuhp_target(struct device *dev,
 }
 static DEVICE_ATTR(target, 0644, show_cpuhp_target, write_cpuhp_target);
 
+
+static ssize_t write_cpuhp_fail(struct device *dev,
+                               struct device_attribute *attr,
+                               const char *buf, size_t count)
+{
+       struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, dev->id);
+       struct cpuhp_step *sp;
+       int fail, ret;
+
+       ret = kstrtoint(buf, 10, &fail);
+       if (ret)
+               return ret;
+
+       /*
+        * Cannot fail STARTING/DYING callbacks.
+        */
+       if (cpuhp_is_atomic_state(fail))
+               return -EINVAL;
+
+       /*
+        * Cannot fail anything that doesn't have callbacks.
+        */
+       mutex_lock(&cpuhp_state_mutex);
+       sp = cpuhp_get_step(fail);
+       if (!sp->startup.single && !sp->teardown.single)
+               ret = -EINVAL;
+       mutex_unlock(&cpuhp_state_mutex);
+       if (ret)
+               return ret;
+
+       st->fail = fail;
+
+       return count;
+}
+
+static ssize_t show_cpuhp_fail(struct device *dev,
+                              struct device_attribute *attr, char *buf)
+{
+       struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, dev->id);
+
+       return sprintf(buf, "%d\n", st->fail);
+}
+
+static DEVICE_ATTR(fail, 0644, show_cpuhp_fail, write_cpuhp_fail);
+
 static struct attribute *cpuhp_cpu_attrs[] = {
        &dev_attr_state.attr,
        &dev_attr_target.attr,
+       &dev_attr_fail.attr,
        NULL
 };