[patch 3/4] isolcpus: affine kernel threads to housekeeping cpus

[Marcelo Tosatti]

This is a kernel enhancement that configures the cpu affinity of kernel
threads via kernel boot option nohz_full=.

When this option is specified, the cpumask is immediately applied upon
thread launch. This does not affect kernel threads that specify cpu
and node.

This allows CPU isolation (that is not allowing certain threads
to execute on certain CPUs) without using the isolcpus=domain parameter,
making it possible to enable load balancing on such CPUs
during runtime (see kernel-parameters.txt).

Note-1: this is based off on Wind River's patch at
https://github.com/starlingx-staging/stx-integ/blob/master/kernel/kernel-std/centos/patches/affine-compute-kernel-threads.patch

Difference being that this patch is limited to modifying
kernel thread cpumask: Behaviour of other threads can
be controlled via cgroups or sched_setaffinity.

Note-2: Wind River's patch was based off Christoph Lameter's patch at
https://lwn.net/Articles/565932/ with the only difference being
the kernel parameter changed from kthread to kthread_cpus.

Signed-off-by: Marcelo Tosatti <mtosatti@xxxxxxxxxx>

---
 Documentation/admin-guide/kernel-parameters.txt |    8 ++++++++
 include/linux/sched/isolation.h                 |    1 +
 kernel/kthread.c                                |    6 ++++--
 kernel/sched/isolation.c                        |    6 ++++++
 4 files changed, 19 insertions(+), 2 deletions(-)

Index: linux-2.6/include/linux/sched/isolation.h
===================================================================
--- linux-2.6.orig/include/linux/sched/isolation.h
+++ linux-2.6/include/linux/sched/isolation.h
@@ -14,6 +14,7 @@ enum hk_flags {
 	HK_FLAG_DOMAIN		= (1 << 5),
 	HK_FLAG_WQ		= (1 << 6),
 	HK_FLAG_MANAGED_IRQ	= (1 << 7),
+	HK_FLAG_KTHREAD		= (1 << 8),
 };
 
 #ifdef CONFIG_CPU_ISOLATION
Index: linux-2.6/kernel/kthread.c
===================================================================
--- linux-2.6.orig/kernel/kthread.c
+++ linux-2.6/kernel/kthread.c
@@ -23,6 +23,7 @@
 #include <linux/ptrace.h>
 #include <linux/uaccess.h>
 #include <linux/numa.h>
+#include <linux/sched/isolation.h>
 #include <trace/events/sched.h>
 
 static DEFINE_SPINLOCK(kthread_create_lock);
@@ -347,7 +348,8 @@ struct task_struct *__kthread_create_on_
 		 * The kernel thread should not inherit these properties.
 		 */
 		sched_setscheduler_nocheck(task, SCHED_NORMAL, &param);
-		set_cpus_allowed_ptr(task, cpu_possible_mask);
+		set_cpus_allowed_ptr(task,
+				     housekeeping_cpumask(HK_FLAG_KTHREAD));
 	}
 	kfree(create);
 	return task;
@@ -572,7 +574,7 @@ int kthreadd(void *unused)
 	/* Setup a clean context for our children to inherit. */
 	set_task_comm(tsk, "kthreadd");
 	ignore_signals(tsk);
-	set_cpus_allowed_ptr(tsk, cpu_possible_mask);
+	set_cpus_allowed_ptr(tsk, housekeeping_cpumask(HK_FLAG_KTHREAD));
 	set_mems_allowed(node_states[N_MEMORY]);
 
 	current->flags |= PF_NOFREEZE;
Index: linux-2.6/kernel/sched/isolation.c
===================================================================
--- linux-2.6.orig/kernel/sched/isolation.c
+++ linux-2.6/kernel/sched/isolation.c
@@ -141,7 +141,7 @@ static int __init housekeeping_nohz_full
 	unsigned int flags;
 
 	flags = HK_FLAG_TICK | HK_FLAG_WQ | HK_FLAG_TIMER | HK_FLAG_RCU |
-		HK_FLAG_MISC | HK_FLAG_SCHED;
+		HK_FLAG_MISC | HK_FLAG_SCHED | HK_FLAG_KTHREAD;
 
 	return housekeeping_setup(str, flags);
 }