configurable cpumask for kthreads

Documentation/kernel-parameters.txt

@@ -1623,6 +1623,16 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 	kstack=N	[X86] Print N words from the kernel stack
 			in oops dumps.
 
+	kthread=	[KNL, SMP] Only run kernel threads on the specified
+			list of processors. The kernel will start threads
+			on the indicated processors only (unless there
+			are specific reasons to run a thread with
+			different affinities). This can be used to make
+			init start on certain processors and also to
+			control where kmod and other user space threads
+			are being spawned. Allows to keep kernel threads
+			away from certain cores unless absoluteluy necessary.
+
 	kvm.ignore_msrs=[KVM] Ignore guest accesses to unhandled MSRs.
 			Default is 0 (don't ignore, but inject #GP)
 

include/linux/cpumask.h

@@ -44,6 +44,7 @@ extern int nr_cpu_ids;
  *     cpu_present_mask - has bit 'cpu' set iff cpu is populated
  *     cpu_online_mask  - has bit 'cpu' set iff cpu available to scheduler
  *     cpu_active_mask  - has bit 'cpu' set iff cpu available to migration
+ *     cpu_kthread_mask -  has bit 'cpu' set iff general kernel threads allowed
  *
  *  If !CONFIG_HOTPLUG_CPU, present == possible, and active == online.
  *
@@ -80,6 +81,7 @@ extern const struct cpumask *const cpu_possible_mask;
 extern const struct cpumask *const cpu_online_mask;
 extern const struct cpumask *const cpu_present_mask;
 extern const struct cpumask *const cpu_active_mask;
+extern const struct cpumask *const cpu_kthread_mask;
 
 #if NR_CPUS > 1
 #define num_online_cpus()	cpumask_weight(cpu_online_mask)

kernel/cpu.c

@@ -754,6 +754,19 @@ static DECLARE_BITMAP(cpu_active_bits, CONFIG_NR_CPUS) __read_mostly;
 const struct cpumask *const cpu_active_mask = to_cpumask(cpu_active_bits);
 EXPORT_SYMBOL(cpu_active_mask);
 
+static DECLARE_BITMAP(cpu_kthread_bits, CONFIG_NR_CPUS) __read_mostly
+	= CPU_BITS_ALL;
+const struct cpumask *const cpu_kthread_mask = to_cpumask(cpu_kthread_bits);
+EXPORT_SYMBOL(cpu_kthread_mask);
+
+static int __init kthread_setup(char *str)
+{
+        cpulist_parse(str, (struct cpumask *)&cpu_kthread_bits);
+        return 1;
+}
+__setup("kthread=", kthread_setup);
+
+
 void set_cpu_possible(unsigned int cpu, bool possible)
 {
 	if (possible)

kernel/kmod.c

@@ -231,8 +231,8 @@ static int ____call_usermodehelper(void *data)
 	flush_signal_handlers(current, 1);
 	spin_unlock_irq(&current->sighand->siglock);
 
-	/* We can run anywhere, unlike our parent keventd(). */
-	set_cpus_allowed_ptr(current, cpu_all_mask);
+	/* We can run only where init is allowed to run. */
+	set_cpus_allowed_ptr(current, cpu_kthread_mask);
 
 	/*
 	 * Our parent is keventd, which runs with elevated scheduling priority.

kernel/kthread.c

@@ -319,6 +319,7 @@ struct task_struct *kthread_create_on_node(int (*threadfn)(void *data),
 		 */
 		sched_setscheduler_nocheck(task, SCHED_NORMAL, &param);
 		set_cpus_allowed_ptr(task, cpu_all_mask);
+		set_cpus_allowed_ptr(task, cpu_kthread_mask);
 	}
 	kfree(create);
 	return task;
@@ -488,6 +489,7 @@ int kthreadd(void *unused)
 	set_task_comm(tsk, "kthreadd");
 	ignore_signals(tsk);
 	set_cpus_allowed_ptr(tsk, cpu_all_mask);
+	set_cpus_allowed_ptr(tsk, cpu_kthread_mask);
 	set_mems_allowed(node_states[N_MEMORY]);
 
 	current->flags |= PF_NOFREEZE;

kernel/workqueue.c

@@ -3815,6 +3815,7 @@ int apply_workqueue_attrs(struct workqueue_struct *wq,
 	/* make a copy of @attrs and sanitize it */
 	copy_workqueue_attrs(new_attrs, attrs);
 	cpumask_and(new_attrs->cpumask, new_attrs->cpumask, cpu_possible_mask);
+	cpumask_and(new_attrs->cpumask, new_attrs->cpumask, cpu_kthread_mask);
 
 	/*
 	 * We may create multiple pwqs with differing cpumasks.  Make a
@@ -4583,6 +4584,7 @@ static void restore_unbound_workers_cpumask(struct worker_pool *pool, int cpu)
 
 	/* is @cpu the only online CPU? */
 	cpumask_and(&cpumask, pool->attrs->cpumask, cpu_online_mask);
+	cpumask_and(&cpumask, pool->attrs->cpumask, cpu_kthread_mask);
 	if (cpumask_weight(&cpumask) != 1)
 		return;