kernel/kernel-rt/debian/patches/0003-affine-compute-kernel-threads.patch

From 0213e30fa1f6d2a9015b4bf136d10f07a6b91d3b Mon Sep 17 00:00:00 2001
From: Chris Friesen <chris.friesen@windriver.com>
Date: Tue, 24 Nov 2015 16:27:28 -0500
Subject: [PATCH 03/16] affine compute kernel threads

This is a kernel enhancement to configure the cpu affinity of kernel
threads via kernel boot option kthread_cpus=<cpulist>. The compute
kickstart file and compute-huge.sh scripts will update grub with the
new option.

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

Note: this is based off of 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: Christoph Lameter <cl@linux.com>
Signed-off-by: Chris Friesen <chris.friesen@windriver.com>
[VT: The existing "isolcpus"
 kernel bootarg, cgroup/cpuset, and taskset might provide the some
 way to have cpu isolation.  However none of them satisfies the requirements.
 Replacing spaces with tabs. Combine two calls of set_cpus_allowed_ptr()
 in kernel_init_freeable() in init/main.c into one.  Performed tests]
Signed-off-by: Vu Tran <vu.tran@windriver.com>

Signed-off-by: Jim Somerville <Jim.Somerville@windriver.com>
Signed-off-by: Zhang Zhiguo <zhangzhg@neusoft.com>
Signed-off-by: Vefa Bicakci <vefa.bicakci@windriver.com>
[jm: Adapted the patch for context changes.]
Signed-off-by: Jiping Ma <jiping.ma2@windriver.com>
[lz: Adapted the patch for upgrading kernel from 5.10 to 6.6]
Signed-off-by: Li Zhou <li.zhou@windriver.com>
[jm: Adapted the patch for upgrading kernel from 6.6 to 6.12]
Signed-off-by: Jiping Ma <jiping.ma2@windriver.com>
---
 .../admin-guide/kernel-parameters.txt         | 10 ++++++++
 include/linux/cpumask.h                       |  3 +++
 init/main.c                                   |  2 ++
 kernel/cpu.c                                  | 23 +++++++++++++++++++
 kernel/kthread.c                              |  4 ++--
 kernel/umh.c                                  |  3 +++
 6 files changed, 43 insertions(+), 2 deletions(-)

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index bf3aacb1ceb7..b6d995d47ea1 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -2637,6 +2637,16 @@
 			See also Documentation/trace/kprobetrace.rst "Kernel
 			Boot Parameter" section.
 
+	kthread_cpus=   [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.
+
 	kpti=		[ARM64,EARLY] Control page table isolation of
 			user and kernel address spaces.
 			Default: enabled on cores which need mitigation.
diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h
index 9278a50d514f..2b91ee73365b 100644
--- a/include/linux/cpumask.h
+++ b/include/linux/cpumask.h
@@ -84,6 +84,7 @@ static __always_inline void set_nr_cpu_ids(unsigned int nr)
  *     cpu_enabled_mask  - has bit 'cpu' set iff cpu can be brought online
  *     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.
  *
@@ -117,12 +118,14 @@ extern struct cpumask __cpu_online_mask;
 extern struct cpumask __cpu_enabled_mask;
 extern struct cpumask __cpu_present_mask;
 extern struct cpumask __cpu_active_mask;
+extern struct cpumask __cpu_kthread_mask;
 extern struct cpumask __cpu_dying_mask;
 #define cpu_possible_mask ((const struct cpumask *)&__cpu_possible_mask)
 #define cpu_online_mask   ((const struct cpumask *)&__cpu_online_mask)
 #define cpu_enabled_mask   ((const struct cpumask *)&__cpu_enabled_mask)
 #define cpu_present_mask  ((const struct cpumask *)&__cpu_present_mask)
 #define cpu_active_mask   ((const struct cpumask *)&__cpu_active_mask)
+#define cpu_kthread_mask  ((const struct cpumask *)&__cpu_kthread_mask)
 #define cpu_dying_mask    ((const struct cpumask *)&__cpu_dying_mask)
 
 extern atomic_t __num_online_cpus;
diff --git a/init/main.c b/init/main.c
index a7aaae73743e..569c18d1622c 100644
--- a/init/main.c
+++ b/init/main.c
@@ -1593,6 +1593,8 @@ static noinline void __init kernel_init_freeable(void)
 
 	do_basic_setup();
 
+	set_cpus_allowed_ptr(current, cpu_kthread_mask);
+
 	kunit_run_all_tests();
 
 	wait_for_initramfs();
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 9ee6c9145b1d..7ab2274c0b8b 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -3121,6 +3121,29 @@ EXPORT_SYMBOL(__cpu_dying_mask);
 atomic_t __num_online_cpus __read_mostly;
 EXPORT_SYMBOL(__num_online_cpus);
 
+struct cpumask __cpu_kthread_mask __read_mostly
+	= {CPU_BITS_ALL};
+EXPORT_SYMBOL(__cpu_kthread_mask);
+
+static int __init kthread_setup(char *str)
+{
+	cpumask_var_t tmp_mask;
+	int err;
+
+	alloc_bootmem_cpumask_var(&tmp_mask);
+
+	err = cpulist_parse(str, tmp_mask);
+	if (!err)
+		cpumask_copy(&__cpu_kthread_mask, tmp_mask);
+	else
+		pr_err("Cannot parse 'kthread_cpus=%s'; error %d\n", str, err);
+
+	free_bootmem_cpumask_var(tmp_mask);
+
+	return 1;
+}
+__setup("kthread_cpus=", kthread_setup);
+
 void init_cpu_present(const struct cpumask *src)
 {
 	cpumask_copy(&__cpu_present_mask, src);
diff --git a/kernel/kthread.c b/kernel/kthread.c
index 9bb36897b6c6..77d2b3f577f4 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -368,7 +368,7 @@ static int kthread(void *_create)
 	 * back to default in case they have been changed.
 	 */
 	sched_setscheduler_nocheck(current, SCHED_NORMAL, &param);
-	set_cpus_allowed_ptr(current, housekeeping_cpumask(HK_TYPE_KTHREAD));
+	set_cpus_allowed_ptr(current, cpu_kthread_mask);
 
 	/* OK, tell user we're spawned, wait for stop or wakeup */
 	__set_current_state(TASK_UNINTERRUPTIBLE);
@@ -743,7 +743,7 @@ 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, housekeeping_cpumask(HK_TYPE_KTHREAD));
+	set_cpus_allowed_ptr(tsk, cpu_kthread_mask);
 	set_mems_allowed(node_states[N_MEMORY]);
 
 	current->flags |= PF_NOFREEZE;
diff --git a/kernel/umh.c b/kernel/umh.c
index ff1f13a27d29..0dec76b539a7 100644
--- a/kernel/umh.c
+++ b/kernel/umh.c
@@ -79,6 +79,9 @@ static int call_usermodehelper_exec_async(void *data)
 	 */
 	current->fs->umask = 0022;
 
+	/* We can run only where init is allowed to run. */
+	set_cpus_allowed_ptr(current, cpu_kthread_mask);
+
 	/*
 	 * Our parent (unbound workqueue) runs with elevated scheduling
 	 * priority. Avoid propagating that into the userspace child.
-- 
2.47.1