Merge branch 'for-next' of git://git.kernel.org/pub/scm/linux/kernel/git/frederic/linux-dynticks.git

Documentation/arch/arm64/asymmetric-32bit.rst

@@ -153,3 +153,12 @@ asymmetric system, a broken guest at EL1 could still attempt to execute
 mode will return to host userspace with an ``exit_reason`` of
 ``KVM_EXIT_FAIL_ENTRY`` and will remain non-runnable until successfully
 re-initialised by a subsequent ``KVM_ARM_VCPU_INIT`` operation.
+
+NOHZ FULL
+---------
+
+Nohz full CPUs are not a desirable fallback target to run 32bits el0
+applications. If present, a set of housekeeping CPUs that can do
+the job instead is preferred. Otherwise 32-bit EL0 is not supported.
+Should the need arise, appropriate support can be introduced in the
+future.

arch/arm/common/bL_switcher.c

@@ -307,13 +307,11 @@ static struct task_struct *bL_switcher_thread_create(int cpu, void *arg)
 {
 	struct task_struct *task;
 
-	task = kthread_create_on_node(bL_switcher_thread, arg,
+	task = kthread_run_on_cpu(bL_switcher_thread, arg,
-				      cpu_to_node(cpu), "kswitcher_%d", cpu);
+				  cpu, "kswitcher_%d");
-	if (!IS_ERR(task)) {
+	if (IS_ERR(task))
-		kthread_bind(task, cpu);
-		wake_up_process(task);
-	} else
 		pr_err("%s failed for CPU %d\n", __func__, cpu);
+
 	return task;
 }
 

arch/arm64/include/asm/cpufeature.h

@@ -671,6 +671,7 @@ static inline bool supports_clearbhb(int scope)
 }
 
 const struct cpumask *system_32bit_el0_cpumask(void);
+const struct cpumask *fallback_32bit_el0_cpumask(void);
 DECLARE_STATIC_KEY_FALSE(arm64_mismatched_32bit_el0);
 
 static inline bool system_supports_32bit_el0(void)

arch/arm64/include/asm/mmu_context.h

@@ -283,6 +283,8 @@ task_cpu_possible_mask(struct task_struct *p)
 }
 #define task_cpu_possible_mask	task_cpu_possible_mask
 
+const struct cpumask *task_cpu_fallback_mask(struct task_struct *p);
+
 void verify_cpu_asid_bits(void);
 void post_ttbr_update_workaround(void);
 

arch/arm64/kernel/cpufeature.c

@@ -75,6 +75,7 @@
 #include <linux/cpu.h>
 #include <linux/kasan.h>
 #include <linux/percpu.h>
+#include <linux/sched/isolation.h>
 
 #include <asm/cpu.h>
 #include <asm/cpufeature.h>
@@ -1640,6 +1641,17 @@ const struct cpumask *system_32bit_el0_cpumask(void)
 	return cpu_possible_mask;
 }
 
+const struct cpumask *task_cpu_fallback_mask(struct task_struct *p)
+{
+	if (!static_branch_unlikely(&arm64_mismatched_32bit_el0))
+		return housekeeping_cpumask(HK_TYPE_TICK);
+
+	if (!is_compat_thread(task_thread_info(p)))
+		return housekeeping_cpumask(HK_TYPE_TICK);
+
+	return system_32bit_el0_cpumask();
+}
+
 static int __init parse_32bit_el0_param(char *str)
 {
 	allow_mismatched_32bit_el0 = true;
@@ -3741,7 +3753,10 @@ static int enable_mismatched_32bit_el0(unsigned int cpu)
 	static int lucky_winner = -1;
 
 	struct cpuinfo_arm64 *info = &per_cpu(cpu_data, cpu);
-	bool cpu_32bit = id_aa64pfr0_32bit_el0(info->reg_id_aa64pfr0);
+	bool cpu_32bit = false;
+
+	if (id_aa64pfr0_32bit_el0(info->reg_id_aa64pfr0) && housekeeping_cpu(cpu, HK_TYPE_TICK))
+		cpu_32bit = true;
 
 	if (cpu_32bit) {
 		cpumask_set_cpu(cpu, cpu_32bit_el0_mask);

arch/x86/kvm/i8254.c

@@ -681,7 +681,7 @@ struct kvm_pit *kvm_create_pit(struct kvm *kvm, u32 flags)
 	pid_nr = pid_vnr(pid);
 	put_pid(pid);
 
-	pit->worker = kthread_create_worker(0, "kvm-pit/%d", pid_nr);
+	pit->worker = kthread_run_worker(0, "kvm-pit/%d", pid_nr);
 	if (IS_ERR(pit->worker))
 		goto fail_kthread;
 

crypto/crypto_engine.c

@@ -517,7 +517,7 @@ struct crypto_engine *crypto_engine_alloc_init_and_set(struct device *dev,
 	crypto_init_queue(&engine->queue, qlen);
 	spin_lock_init(&engine->queue_lock);
 
-	engine->kworker = kthread_create_worker(0, "%s", engine->name);
+	engine->kworker = kthread_run_worker(0, "%s", engine->name);
 	if (IS_ERR(engine->kworker)) {
 		dev_err(dev, "failed to create crypto request pump task\n");
 		return NULL;

drivers/cpufreq/cppc_cpufreq.c

@@ -225,7 +225,7 @@ static void __init cppc_freq_invariance_init(void)
 	if (fie_disabled)
 		return;
 
-	kworker_fie = kthread_create_worker(0, "cppc_fie");
+	kworker_fie = kthread_run_worker(0, "cppc_fie");
 	if (IS_ERR(kworker_fie)) {
 		pr_warn("%s: failed to create kworker_fie: %ld\n", __func__,
 			PTR_ERR(kworker_fie));

drivers/gpu/drm/drm_vblank_work.c

@@ -277,7 +277,7 @@ int drm_vblank_worker_init(struct drm_vblank_crtc *vblank)
 
 	INIT_LIST_HEAD(&vblank->pending_work);
 	init_waitqueue_head(&vblank->work_wait_queue);
-	worker = kthread_create_worker(0, "card%d-crtc%d",
+	worker = kthread_run_worker(0, "card%d-crtc%d",
 				       vblank->dev->primary->index,
 				       vblank->pipe);
 	if (IS_ERR(worker))

drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c

@@ -369,7 +369,7 @@ static int live_parallel_switch(void *arg)
 		if (!data[n].ce[0])
 			continue;
 
-		worker = kthread_create_worker(0, "igt/parallel:%s",
+		worker = kthread_run_worker(0, "igt/parallel:%s",
 					       data[n].ce[0]->engine->name);
 		if (IS_ERR(worker)) {
 			err = PTR_ERR(worker);

drivers/gpu/drm/i915/gt/selftest_execlists.c

@@ -3574,7 +3574,7 @@ static int smoke_crescendo(struct preempt_smoke *smoke, unsigned int flags)
 			arg[id].batch = NULL;
 		arg[id].count = 0;
 
-		worker[id] = kthread_create_worker(0, "igt/smoke:%d", id);
+		worker[id] = kthread_run_worker(0, "igt/smoke:%d", id);
 		if (IS_ERR(worker[id])) {
 			err = PTR_ERR(worker[id]);
 			break;

drivers/gpu/drm/i915/gt/selftest_hangcheck.c

@@ -1025,7 +1025,7 @@ static int __igt_reset_engines(struct intel_gt *gt,
 			threads[tmp].engine = other;
 			threads[tmp].flags = flags;
 
-			worker = kthread_create_worker(0, "igt/%s",
+			worker = kthread_run_worker(0, "igt/%s",
 						       other->name);
 			if (IS_ERR(worker)) {
 				err = PTR_ERR(worker);

drivers/gpu/drm/i915/gt/selftest_slpc.c

@@ -489,7 +489,7 @@ static int live_slpc_tile_interaction(void *arg)
 		return -ENOMEM;
 
 	for_each_gt(gt, i915, i) {
-		threads[i].worker = kthread_create_worker(0, "igt/slpc_parallel:%d", gt->info.id);
+		threads[i].worker = kthread_run_worker(0, "igt/slpc_parallel:%d", gt->info.id);
 
 		if (IS_ERR(threads[i].worker)) {
 			ret = PTR_ERR(threads[i].worker);

drivers/gpu/drm/i915/selftests/i915_request.c

@@ -492,7 +492,7 @@ static int mock_breadcrumbs_smoketest(void *arg)
 	for (n = 0; n < ncpus; n++) {
 		struct kthread_worker *worker;
 
-		worker = kthread_create_worker(0, "igt/%d", n);
+		worker = kthread_run_worker(0, "igt/%d", n);
 		if (IS_ERR(worker)) {
 			ret = PTR_ERR(worker);
 			ncpus = n;
@@ -1645,7 +1645,7 @@ static int live_parallel_engines(void *arg)
 		for_each_uabi_engine(engine, i915) {
 			struct kthread_worker *worker;
 
-			worker = kthread_create_worker(0, "igt/parallel:%s",
+			worker = kthread_run_worker(0, "igt/parallel:%s",
 						       engine->name);
 			if (IS_ERR(worker)) {
 				err = PTR_ERR(worker);
@@ -1806,7 +1806,7 @@ static int live_breadcrumbs_smoketest(void *arg)
 			unsigned int i = idx * ncpus + n;
 			struct kthread_worker *worker;
 
-			worker = kthread_create_worker(0, "igt/%d.%d", idx, n);
+			worker = kthread_run_worker(0, "igt/%d.%d", idx, n);
 			if (IS_ERR(worker)) {
 				ret = PTR_ERR(worker);
 				goto out_flush;
@@ -3219,7 +3219,7 @@ static int perf_parallel_engines(void *arg)
 
 			memset(&engines[idx].p, 0, sizeof(engines[idx].p));
 
-			worker = kthread_create_worker(0, "igt:%s",
+			worker = kthread_run_worker(0, "igt:%s",
 						       engine->name);
 			if (IS_ERR(worker)) {
 				err = PTR_ERR(worker);

drivers/gpu/drm/msm/disp/msm_disp_snapshot.c

@@ -109,7 +109,7 @@ int msm_disp_snapshot_init(struct drm_device *drm_dev)
 
 	mutex_init(&kms->dump_mutex);
 
-	kms->dump_worker = kthread_create_worker(0, "%s", "disp_snapshot");
+	kms->dump_worker = kthread_run_worker(0, "%s", "disp_snapshot");
 	if (IS_ERR(kms->dump_worker))
 		DRM_ERROR("failed to create disp state task\n");
 

drivers/gpu/drm/msm/msm_atomic.c

@@ -115,7 +115,7 @@ int msm_atomic_init_pending_timer(struct msm_pending_timer *timer,
 	timer->kms = kms;
 	timer->crtc_idx = crtc_idx;
 
-	timer->worker = kthread_create_worker(0, "atomic-worker-%d", crtc_idx);
+	timer->worker = kthread_run_worker(0, "atomic-worker-%d", crtc_idx);
 	if (IS_ERR(timer->worker)) {
 		int ret = PTR_ERR(timer->worker);
 		timer->worker = NULL;

drivers/gpu/drm/msm/msm_gpu.c

@@ -859,7 +859,7 @@ int msm_gpu_init(struct drm_device *drm, struct platform_device *pdev,
 	gpu->funcs = funcs;
 	gpu->name = name;
 
-	gpu->worker = kthread_create_worker(0, "gpu-worker");
+	gpu->worker = kthread_run_worker(0, "gpu-worker");
 	if (IS_ERR(gpu->worker)) {
 		ret = PTR_ERR(gpu->worker);
 		gpu->worker = NULL;

drivers/gpu/drm/msm/msm_kms.c

@@ -269,7 +269,7 @@ int msm_drm_kms_init(struct device *dev, const struct drm_driver *drv)
 		/* initialize event thread */
 		ev_thread = &priv->event_thread[drm_crtc_index(crtc)];
 		ev_thread->dev = ddev;
-		ev_thread->worker = kthread_create_worker(0, "crtc_event:%d", crtc->base.id);
+		ev_thread->worker = kthread_run_worker(0, "crtc_event:%d", crtc->base.id);
 		if (IS_ERR(ev_thread->worker)) {
 			ret = PTR_ERR(ev_thread->worker);
 			DRM_DEV_ERROR(dev, "failed to create crtc_event kthread\n");

drivers/media/platform/chips-media/wave5/wave5-vpu.c

@@ -271,7 +271,7 @@ static int wave5_vpu_probe(struct platform_device *pdev)
 		dev_err(&pdev->dev, "failed to get irq resource, falling back to polling\n");
 		hrtimer_init(&dev->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_PINNED);
 		dev->hrtimer.function = &wave5_vpu_timer_callback;
-		dev->worker = kthread_create_worker(0, "vpu_irq_thread");
+		dev->worker = kthread_run_worker(0, "vpu_irq_thread");
 		if (IS_ERR(dev->worker)) {
 			dev_err(&pdev->dev, "failed to create vpu irq worker\n");
 			ret = PTR_ERR(dev->worker);

drivers/net/dsa/mv88e6xxx/chip.c

@@ -394,7 +394,7 @@ static int mv88e6xxx_irq_poll_setup(struct mv88e6xxx_chip *chip)
 	kthread_init_delayed_work(&chip->irq_poll_work,
 				  mv88e6xxx_irq_poll);
 
-	chip->kworker = kthread_create_worker(0, "%s", dev_name(chip->dev));
+	chip->kworker = kthread_run_worker(0, "%s", dev_name(chip->dev));
 	if (IS_ERR(chip->kworker))
 		return PTR_ERR(chip->kworker);
 

drivers/net/ethernet/intel/ice/ice_dpll.c

@@ -2053,7 +2053,7 @@ static int ice_dpll_init_worker(struct ice_pf *pf)
 	struct kthread_worker *kworker;
 
 	kthread_init_delayed_work(&d->work, ice_dpll_periodic_work);
-	kworker = kthread_create_worker(0, "ice-dplls-%s",
+	kworker = kthread_run_worker(0, "ice-dplls-%s",
 					dev_name(ice_pf_to_dev(pf)));
 	if (IS_ERR(kworker))
 		return PTR_ERR(kworker);

drivers/net/ethernet/intel/ice/ice_gnss.c

@@ -182,7 +182,7 @@ static struct gnss_serial *ice_gnss_struct_init(struct ice_pf *pf)
 	pf->gnss_serial = gnss;
 
 	kthread_init_delayed_work(&gnss->read_work, ice_gnss_read);
-	kworker = kthread_create_worker(0, "ice-gnss-%s", dev_name(dev));
+	kworker = kthread_run_worker(0, "ice-gnss-%s", dev_name(dev));
 	if (IS_ERR(kworker)) {
 		kfree(gnss);
 		return NULL;

drivers/net/ethernet/intel/ice/ice_ptp.c

@@ -3080,7 +3080,7 @@ static int ice_ptp_init_work(struct ice_pf *pf, struct ice_ptp *ptp)
 	/* Allocate a kworker for handling work required for the ports
 	 * connected to the PTP hardware clock.
 	 */
-	kworker = kthread_create_worker(0, "ice-ptp-%s",
+	kworker = kthread_run_worker(0, "ice-ptp-%s",
 					dev_name(ice_pf_to_dev(pf)));
 	if (IS_ERR(kworker))
 		return PTR_ERR(kworker);

drivers/platform/chrome/cros_ec_spi.c

@@ -715,7 +715,7 @@ static int cros_ec_spi_devm_high_pri_alloc(struct device *dev,
 	int err;
 
 	ec_spi->high_pri_worker =
-		kthread_create_worker(0, "cros_ec_spi_high_pri");
+		kthread_run_worker(0, "cros_ec_spi_high_pri");
 
 	if (IS_ERR(ec_spi->high_pri_worker)) {
 		err = PTR_ERR(ec_spi->high_pri_worker);

drivers/ptp/ptp_clock.c

@@ -296,7 +296,7 @@ struct ptp_clock *ptp_clock_register(struct ptp_clock_info *info,
 
 	if (ptp->info->do_aux_work) {
 		kthread_init_delayed_work(&ptp->aux_work, ptp_aux_kworker);
-		ptp->kworker = kthread_create_worker(0, "ptp%d", ptp->index);
+		ptp->kworker = kthread_run_worker(0, "ptp%d", ptp->index);
 		if (IS_ERR(ptp->kworker)) {
 			err = PTR_ERR(ptp->kworker);
 			pr_err("failed to create ptp aux_worker %d\n", err);

drivers/scsi/bnx2fc/bnx2fc_fcoe.c

@@ -2610,14 +2610,11 @@ static int bnx2fc_cpu_online(unsigned int cpu)
 
 	p = &per_cpu(bnx2fc_percpu, cpu);
 
-	thread = kthread_create_on_node(bnx2fc_percpu_io_thread,
+	thread = kthread_create_on_cpu(bnx2fc_percpu_io_thread,
-					(void *)p, cpu_to_node(cpu),
+				       (void *)p, cpu, "bnx2fc_thread/%d");
-					"bnx2fc_thread/%d", cpu);
 	if (IS_ERR(thread))
 		return PTR_ERR(thread);
 
-	/* bind thread to the cpu */
-	kthread_bind(thread, cpu);
 	p->iothread = thread;
 	wake_up_process(thread);
 	return 0;

drivers/scsi/bnx2i/bnx2i_init.c

@@ -415,14 +415,11 @@ static int bnx2i_cpu_online(unsigned int cpu)
 
 	p = &per_cpu(bnx2i_percpu, cpu);
 
-	thread = kthread_create_on_node(bnx2i_percpu_io_thread, (void *)p,
+	thread = kthread_create_on_cpu(bnx2i_percpu_io_thread, (void *)p,
-					cpu_to_node(cpu),
+				       cpu, "bnx2i_thread/%d");
-					"bnx2i_thread/%d", cpu);
 	if (IS_ERR(thread))
 		return PTR_ERR(thread);
 
-	/* bind thread to the cpu */
-	kthread_bind(thread, cpu);
 	p->iothread = thread;
 	wake_up_process(thread);
 	return 0;

drivers/scsi/qedi/qedi_main.c

@@ -1961,13 +1961,11 @@ static int qedi_cpu_online(unsigned int cpu)
 	struct qedi_percpu_s *p = this_cpu_ptr(&qedi_percpu);
 	struct task_struct *thread;
 
-	thread = kthread_create_on_node(qedi_percpu_io_thread, (void *)p,
+	thread = kthread_create_on_cpu(qedi_percpu_io_thread, (void *)p,
-					cpu_to_node(cpu),
+				       cpu, "qedi_thread/%d");
-					"qedi_thread/%d", cpu);
 	if (IS_ERR(thread))
 		return PTR_ERR(thread);
 
-	kthread_bind(thread, cpu);
 	p->iothread = thread;
 	wake_up_process(thread);
 	return 0;

drivers/soc/fsl/qbman/qman_test_stash.c

@@ -108,14 +108,12 @@ static int on_all_cpus(int (*fn)(void))
 			.fn = fn,
 			.started = ATOMIC_INIT(0)
 		};
-		struct task_struct *k = kthread_create(bstrap_fn, &bstrap,
+		struct task_struct *k = kthread_run_on_cpu(bstrap_fn, &bstrap,
-			"hotpotato%d", cpu);
+							   cpu, "hotpotato%d");
 		int ret;
 
 		if (IS_ERR(k))
 			return -ENOMEM;
-		kthread_bind(k, cpu);
-		wake_up_process(k);
 		/*
 		 * If we call kthread_stop() before the "wake up" has had an
 		 * effect, then the thread may exit with -EINTR without ever

drivers/spi/spi.c

@@ -2055,7 +2055,7 @@ static int spi_init_queue(struct spi_controller *ctlr)
 	ctlr->busy = false;
 	ctlr->queue_empty = true;
 
-	ctlr->kworker = kthread_create_worker(0, dev_name(&ctlr->dev));
+	ctlr->kworker = kthread_run_worker(0, dev_name(&ctlr->dev));
 	if (IS_ERR(ctlr->kworker)) {
 		dev_err(&ctlr->dev, "failed to create message pump kworker\n");
 		return PTR_ERR(ctlr->kworker);

drivers/usb/typec/tcpm/tcpm.c

@@ -7635,7 +7635,7 @@ struct tcpm_port *tcpm_register_port(struct device *dev, struct tcpc_dev *tcpc)
 	mutex_init(&port->lock);
 	mutex_init(&port->swap_lock);
 
-	port->wq = kthread_create_worker(0, dev_name(dev));
+	port->wq = kthread_run_worker(0, dev_name(dev));
 	if (IS_ERR(port->wq))
 		return ERR_CAST(port->wq);
 	sched_set_fifo(port->wq->task);

drivers/vdpa/vdpa_sim/vdpa_sim.c

@@ -229,7 +229,7 @@ struct vdpasim *vdpasim_create(struct vdpasim_dev_attr *dev_attr,
 	dev = &vdpasim->vdpa.dev;
 
 	kthread_init_work(&vdpasim->work, vdpasim_work_fn);
-	vdpasim->worker = kthread_create_worker(0, "vDPA sim worker: %s",
+	vdpasim->worker = kthread_run_worker(0, "vDPA sim worker: %s",
 						dev_attr->name);
 	if (IS_ERR(vdpasim->worker))
 		goto err_iommu;

drivers/watchdog/watchdog_dev.c

@@ -1229,7 +1229,7 @@ int __init watchdog_dev_init(void)
 {
 	int err;
 
-	watchdog_kworker = kthread_create_worker(0, "watchdogd");
+	watchdog_kworker = kthread_run_worker(0, "watchdogd");
 	if (IS_ERR(watchdog_kworker)) {
 		pr_err("Failed to create watchdog kworker\n");
 		return PTR_ERR(watchdog_kworker);

fs/erofs/zdata.c

@@ -320,7 +320,7 @@ static void erofs_destroy_percpu_workers(void)
 static struct kthread_worker *erofs_init_percpu_worker(int cpu)
 {
 	struct kthread_worker *worker =
-		kthread_create_worker_on_cpu(cpu, 0, "erofs_worker/%u", cpu);
+		kthread_run_worker_on_cpu(cpu, 0, "erofs_worker/%u");
 
 	if (IS_ERR(worker))
 		return worker;

include/linux/cpuhotplug.h

@@ -240,6 +240,7 @@ enum cpuhp_state {
 	CPUHP_AP_WORKQUEUE_ONLINE,
 	CPUHP_AP_RANDOM_ONLINE,
 	CPUHP_AP_RCUTREE_ONLINE,
+	CPUHP_AP_KTHREADS_ONLINE,
 	CPUHP_AP_BASE_CACHEINFO_ONLINE,
 	CPUHP_AP_ONLINE_DYN,
 	CPUHP_AP_ONLINE_DYN_END		= CPUHP_AP_ONLINE_DYN + 40,

include/linux/kthread.h

@@ -85,6 +85,7 @@ kthread_run_on_cpu(int (*threadfn)(void *data), void *data,
 void free_kthread_struct(struct task_struct *k);
 void kthread_bind(struct task_struct *k, unsigned int cpu);
 void kthread_bind_mask(struct task_struct *k, const struct cpumask *mask);
+int kthread_affine_preferred(struct task_struct *p, const struct cpumask *mask);
 int kthread_stop(struct task_struct *k);
 int kthread_stop_put(struct task_struct *k);
 bool kthread_should_stop(void);
@@ -186,13 +187,58 @@ extern void __kthread_init_worker(struct kthread_worker *worker,
 
 int kthread_worker_fn(void *worker_ptr);
 
-__printf(2, 3)
+__printf(3, 4)
-struct kthread_worker *
+struct kthread_worker *kthread_create_worker_on_node(unsigned int flags,
-kthread_create_worker(unsigned int flags, const char namefmt[], ...);
+						     int node,
+						     const char namefmt[], ...);
 
-__printf(3, 4) struct kthread_worker *
+#define kthread_create_worker(flags, namefmt, ...) \
+	kthread_create_worker_on_node(flags, NUMA_NO_NODE, namefmt, ## __VA_ARGS__);
+
+/**
+ * kthread_run_worker - create and wake a kthread worker.
+ * @flags: flags modifying the default behavior of the worker
+ * @namefmt: printf-style name for the thread.
+ *
+ * Description: Convenient wrapper for kthread_create_worker() followed by
+ * wake_up_process().  Returns the kthread_worker or ERR_PTR(-ENOMEM).
+ */
+#define kthread_run_worker(flags, namefmt, ...)					\
+({										\
+	struct kthread_worker *__kw						\
+		= kthread_create_worker(flags, namefmt, ## __VA_ARGS__);	\
+	if (!IS_ERR(__kw))							\
+		wake_up_process(__kw->task);					\
+	__kw;									\
+})
+
+struct kthread_worker *
 kthread_create_worker_on_cpu(int cpu, unsigned int flags,
-			     const char namefmt[], ...);
+			     const char namefmt[]);
+
+/**
+ * kthread_run_worker_on_cpu - create and wake a cpu bound kthread worker.
+ * @cpu: CPU number
+ * @flags: flags modifying the default behavior of the worker
+ * @namefmt: printf-style name for the thread. Format is restricted
+ *	     to "name.*%u". Code fills in cpu number.
+ *
+ * Description: Convenient wrapper for kthread_create_worker_on_cpu()
+ * followed by wake_up_process().  Returns the kthread_worker or
+ * ERR_PTR(-ENOMEM).
+ */
+static inline struct kthread_worker *
+kthread_run_worker_on_cpu(int cpu, unsigned int flags,
+			  const char namefmt[])
+{
+	struct kthread_worker *kw;
+
+	kw = kthread_create_worker_on_cpu(cpu, flags, namefmt);
+	if (!IS_ERR(kw))
+		wake_up_process(kw->task);
+
+	return kw;
+}
 
 bool kthread_queue_work(struct kthread_worker *worker,
 			struct kthread_work *work);

include/linux/mmu_context.h

@@ -24,6 +24,7 @@ static inline void leave_mm(void) { }
 #ifndef task_cpu_possible_mask
 # define task_cpu_possible_mask(p)	cpu_possible_mask
 # define task_cpu_possible(cpu, p)	true
+# define task_cpu_fallback_mask(p)	housekeeping_cpumask(HK_TYPE_TICK)
 #else
 # define task_cpu_possible(cpu, p)	cpumask_test_cpu((cpu), task_cpu_possible_mask(p))
 #endif

kernel/kallsyms_selftest.c

@@ -435,13 +435,11 @@ static int __init kallsyms_test_init(void)
 {
 	struct task_struct *t;
 
-	t = kthread_create(test_entry, NULL, "kallsyms_test");
+	t = kthread_run_on_cpu(test_entry, NULL, 0, "kallsyms_test");
 	if (IS_ERR(t)) {
 		pr_info("Create kallsyms selftest task failed\n");
 		return PTR_ERR(t);
 	}
-	kthread_bind(t, 0);
-	wake_up_process(t);
 
 	return 0;
 }

kernel/kthread.c

@@ -35,6 +35,9 @@ static DEFINE_SPINLOCK(kthread_create_lock);
 static LIST_HEAD(kthread_create_list);
 struct task_struct *kthreadd_task;
 
+static LIST_HEAD(kthreads_hotplug);
+static DEFINE_MUTEX(kthreads_hotplug_lock);
+
 struct kthread_create_info
 {
 	/* Information passed to kthread() from kthreadd. */
@@ -53,6 +56,8 @@ struct kthread_create_info
 struct kthread {
 	unsigned long flags;
 	unsigned int cpu;
+	unsigned int node;
+	int started;
 	int result;
 	int (*threadfn)(void *);
 	void *data;
@@ -63,6 +68,9 @@ struct kthread {
 #endif
 	/* To store the full name if task comm is truncated. */
 	char *full_name;
+	struct task_struct *task;
+	struct list_head hotplug_node;
+	struct cpumask *preferred_affinity;
 };
 
 enum KTHREAD_BITS {
@@ -121,8 +129,11 @@ bool set_kthread_struct(struct task_struct *p)
 
 	init_completion(&kthread->exited);
 	init_completion(&kthread->parked);
+	INIT_LIST_HEAD(&kthread->hotplug_node);
 	p->vfork_done = &kthread->exited;
 
+	kthread->task = p;
+	kthread->node = tsk_fork_get_node(current);
 	p->worker_private = kthread;
 	return true;
 }
@@ -313,6 +324,16 @@ void __noreturn kthread_exit(long result)
 {
 	struct kthread *kthread = to_kthread(current);
 	kthread->result = result;
+	if (!list_empty(&kthread->hotplug_node)) {
+		mutex_lock(&kthreads_hotplug_lock);
+		list_del(&kthread->hotplug_node);
+		mutex_unlock(&kthreads_hotplug_lock);
+
+		if (kthread->preferred_affinity) {
+			kfree(kthread->preferred_affinity);
+			kthread->preferred_affinity = NULL;
+		}
+	}
 	do_exit(0);
 }
 EXPORT_SYMBOL(kthread_exit);
@@ -338,6 +359,56 @@ void __noreturn kthread_complete_and_exit(struct completion *comp, long code)
 }
 EXPORT_SYMBOL(kthread_complete_and_exit);
 
+static void kthread_fetch_affinity(struct kthread *kthread, struct cpumask *cpumask)
+{
+	const struct cpumask *pref;
+
+	if (kthread->preferred_affinity) {
+		pref = kthread->preferred_affinity;
+	} else {
+		if (WARN_ON_ONCE(kthread->node == NUMA_NO_NODE))
+			return;
+		pref = cpumask_of_node(kthread->node);
+	}
+
+	cpumask_and(cpumask, pref, housekeeping_cpumask(HK_TYPE_KTHREAD));
+	if (cpumask_empty(cpumask))
+		cpumask_copy(cpumask, housekeeping_cpumask(HK_TYPE_KTHREAD));
+}
+
+static void kthread_affine_node(void)
+{
+	struct kthread *kthread = to_kthread(current);
+	cpumask_var_t affinity;
+
+	WARN_ON_ONCE(kthread_is_per_cpu(current));
+
+	if (kthread->node == NUMA_NO_NODE) {
+		housekeeping_affine(current, HK_TYPE_KTHREAD);
+	} else {
+		if (!zalloc_cpumask_var(&affinity, GFP_KERNEL)) {
+			WARN_ON_ONCE(1);
+			return;
+		}
+
+		mutex_lock(&kthreads_hotplug_lock);
+		WARN_ON_ONCE(!list_empty(&kthread->hotplug_node));
+		list_add_tail(&kthread->hotplug_node, &kthreads_hotplug);
+		/*
+		 * The node cpumask is racy when read from kthread() but:
+		 * - a racing CPU going down will either fail on the subsequent
+		 *   call to set_cpus_allowed_ptr() or be migrated to housekeepers
+		 *   afterwards by the scheduler.
+		 * - a racing CPU going up will be handled by kthreads_online_cpu()
+		 */
+		kthread_fetch_affinity(kthread, affinity);
+		set_cpus_allowed_ptr(current, affinity);
+		mutex_unlock(&kthreads_hotplug_lock);
+
+		free_cpumask_var(affinity);
+	}
+}
+
 static int kthread(void *_create)
 {
 	static const struct sched_param param = { .sched_priority = 0 };
@@ -368,7 +439,6 @@ 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));
 
 	/* OK, tell user we're spawned, wait for stop or wakeup */
 	__set_current_state(TASK_UNINTERRUPTIBLE);
@@ -382,6 +452,11 @@ static int kthread(void *_create)
 	schedule_preempt_disabled();
 	preempt_enable();
 
+	self->started = 1;
+
+	if (!(current->flags & PF_NO_SETAFFINITY) && !self->preferred_affinity)
+		kthread_affine_node();
+
 	ret = -EINTR;
 	if (!test_bit(KTHREAD_SHOULD_STOP, &self->flags)) {
 		cgroup_kthread_ready();
@@ -540,7 +615,9 @@ static void __kthread_bind(struct task_struct *p, unsigned int cpu, unsigned int
 
 void kthread_bind_mask(struct task_struct *p, const struct cpumask *mask)
 {
+	struct kthread *kthread = to_kthread(p);
 	__kthread_bind_mask(p, mask, TASK_UNINTERRUPTIBLE);
+	WARN_ON_ONCE(kthread->started);
 }
 
 /**
@@ -554,7 +631,9 @@ void kthread_bind_mask(struct task_struct *p, const struct cpumask *mask)
  */
 void kthread_bind(struct task_struct *p, unsigned int cpu)
 {
+	struct kthread *kthread = to_kthread(p);
 	__kthread_bind(p, cpu, TASK_UNINTERRUPTIBLE);
+	WARN_ON_ONCE(kthread->started);
 }
 EXPORT_SYMBOL(kthread_bind);
 
@@ -775,6 +854,92 @@ int kthreadd(void *unused)
 	return 0;
 }
 
+int kthread_affine_preferred(struct task_struct *p, const struct cpumask *mask)
+{
+	struct kthread *kthread = to_kthread(p);
+	cpumask_var_t affinity;
+	unsigned long flags;
+	int ret;
+
+	if (!wait_task_inactive(p, TASK_UNINTERRUPTIBLE) || kthread->started) {
+		WARN_ON(1);
+		return -EINVAL;
+	}
+
+	WARN_ON_ONCE(kthread->preferred_affinity);
+
+	if (!zalloc_cpumask_var(&affinity, GFP_KERNEL))
+		return -ENOMEM;
+
+	kthread->preferred_affinity = kzalloc(sizeof(struct cpumask), GFP_KERNEL);
+	if (!kthread->preferred_affinity) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	mutex_lock(&kthreads_hotplug_lock);
+	cpumask_copy(kthread->preferred_affinity, mask);
+	WARN_ON_ONCE(!list_empty(&kthread->hotplug_node));
+	list_add_tail(&kthread->hotplug_node, &kthreads_hotplug);
+	kthread_fetch_affinity(kthread, affinity);
+
+	/* It's safe because the task is inactive. */
+	raw_spin_lock_irqsave(&p->pi_lock, flags);
+	do_set_cpus_allowed(p, affinity);
+	raw_spin_unlock_irqrestore(&p->pi_lock, flags);
+
+	mutex_unlock(&kthreads_hotplug_lock);
+out:
+	free_cpumask_var(affinity);
+
+	return 0;
+}
+
+/*
+ * Re-affine kthreads according to their preferences
+ * and the newly online CPU. The CPU down part is handled
+ * by select_fallback_rq() which default re-affines to
+ * housekeepers from other nodes in case the preferred
+ * affinity doesn't apply anymore.
+ */
+static int kthreads_online_cpu(unsigned int cpu)
+{
+	cpumask_var_t affinity;
+	struct kthread *k;
+	int ret;
+
+	guard(mutex)(&kthreads_hotplug_lock);
+
+	if (list_empty(&kthreads_hotplug))
+		return 0;
+
+	if (!zalloc_cpumask_var(&affinity, GFP_KERNEL))
+		return -ENOMEM;
+
+	ret = 0;
+
+	list_for_each_entry(k, &kthreads_hotplug, hotplug_node) {
+		if (WARN_ON_ONCE((k->task->flags & PF_NO_SETAFFINITY) ||
+				 kthread_is_per_cpu(k->task))) {
+			ret = -EINVAL;
+			continue;
+		}
+		kthread_fetch_affinity(k, affinity);
+		set_cpus_allowed_ptr(k->task, affinity);
+	}
+
+	free_cpumask_var(affinity);
+
+	return ret;
+}
+
+static int kthreads_init(void)
+{
+	return cpuhp_setup_state(CPUHP_AP_KTHREADS_ONLINE, "kthreads:online",
+				kthreads_online_cpu, NULL);
+}
+early_initcall(kthreads_init);
+
 void __kthread_init_worker(struct kthread_worker *worker,
 				const char *name,
 				struct lock_class_key *key)
@@ -866,12 +1031,11 @@ int kthread_worker_fn(void *worker_ptr)
 EXPORT_SYMBOL_GPL(kthread_worker_fn);
 
 static __printf(3, 0) struct kthread_worker *
-__kthread_create_worker(int cpu, unsigned int flags,
+__kthread_create_worker_on_node(unsigned int flags, int node,
-			const char namefmt[], va_list args)
+				const char namefmt[], va_list args)
 {
 	struct kthread_worker *worker;
 	struct task_struct *task;
-	int node = NUMA_NO_NODE;
 
 	worker = kzalloc(sizeof(*worker), GFP_KERNEL);
 	if (!worker)
@@ -879,20 +1043,14 @@ __kthread_create_worker(int cpu, unsigned int flags,
 
 	kthread_init_worker(worker);
 
-	if (cpu >= 0)
-		node = cpu_to_node(cpu);
-
 	task = __kthread_create_on_node(kthread_worker_fn, worker,
-						node, namefmt, args);
+					node, namefmt, args);
 	if (IS_ERR(task))
 		goto fail_task;
 
-	if (cpu >= 0)
-		kthread_bind(task, cpu);
-
 	worker->flags = flags;
 	worker->task = task;
-	wake_up_process(task);
+
 	return worker;
 
 fail_task:
@@ -903,6 +1061,7 @@ __kthread_create_worker(int cpu, unsigned int flags,
 /**
  * kthread_create_worker - create a kthread worker
  * @flags: flags modifying the default behavior of the worker
+ * @node: task structure for the thread is allocated on this node
  * @namefmt: printf-style name for the kthread worker (task).
  *
  * Returns a pointer to the allocated worker on success, ERR_PTR(-ENOMEM)
@@ -910,25 +1069,26 @@ __kthread_create_worker(int cpu, unsigned int flags,
  * when the caller was killed by a fatal signal.
  */
 struct kthread_worker *
-kthread_create_worker(unsigned int flags, const char namefmt[], ...)
+kthread_create_worker_on_node(unsigned int flags, int node, const char namefmt[], ...)
 {
 	struct kthread_worker *worker;
 	va_list args;
 
 	va_start(args, namefmt);
-	worker = __kthread_create_worker(-1, flags, namefmt, args);
+	worker = __kthread_create_worker_on_node(flags, node, namefmt, args);
 	va_end(args);
 
 	return worker;
 }
-EXPORT_SYMBOL(kthread_create_worker);
+EXPORT_SYMBOL(kthread_create_worker_on_node);
 
 /**
  * kthread_create_worker_on_cpu - create a kthread worker and bind it
  *	to a given CPU and the associated NUMA node.
  * @cpu: CPU number
  * @flags: flags modifying the default behavior of the worker
- * @namefmt: printf-style name for the kthread worker (task).
+ * @namefmt: printf-style name for the thread. Format is restricted
+ *	     to "name.*%u". Code fills in cpu number.
  *
  * Use a valid CPU number if you want to bind the kthread worker
  * to the given CPU and the associated NUMA node.
@@ -960,14 +1120,13 @@ EXPORT_SYMBOL(kthread_create_worker);
  */
 struct kthread_worker *
 kthread_create_worker_on_cpu(int cpu, unsigned int flags,
-			     const char namefmt[], ...)
+			     const char namefmt[])
 {
 	struct kthread_worker *worker;
-	va_list args;
 
-	va_start(args, namefmt);
+	worker = kthread_create_worker_on_node(flags, cpu_to_node(cpu), namefmt, cpu);
-	worker = __kthread_create_worker(cpu, flags, namefmt, args);
+	if (!IS_ERR(worker))
-	va_end(args);
+		kthread_bind(worker->task, cpu);
 
 	return worker;
 }

kernel/rcu/tree.c

@@ -149,7 +149,6 @@ static int rcu_scheduler_fully_active __read_mostly;
 
 static void rcu_report_qs_rnp(unsigned long mask, struct rcu_node *rnp,
 			      unsigned long gps, unsigned long flags);
-static struct task_struct *rcu_boost_task(struct rcu_node *rnp);
 static void invoke_rcu_core(void);
 static void rcu_report_exp_rdp(struct rcu_data *rdp);
 static void sync_sched_exp_online_cleanup(int cpu);
@@ -4072,6 +4071,22 @@ rcu_boot_init_percpu_data(int cpu)
 	rcu_boot_init_nocb_percpu_data(rdp);
 }
 
+static void rcu_thread_affine_rnp(struct task_struct *t, struct rcu_node *rnp)
+{
+	cpumask_var_t affinity;
+	int cpu;
+
+	if (!zalloc_cpumask_var(&affinity, GFP_KERNEL))
+		return;
+
+	for_each_leaf_node_possible_cpu(rnp, cpu)
+		cpumask_set_cpu(cpu, affinity);
+
+	kthread_affine_preferred(t, affinity);
+
+	free_cpumask_var(affinity);
+}
+
 struct kthread_worker *rcu_exp_gp_kworker;
 
 static void rcu_spawn_exp_par_gp_kworker(struct rcu_node *rnp)
@@ -4094,16 +4109,9 @@ static void rcu_spawn_exp_par_gp_kworker(struct rcu_node *rnp)
 
 	if (IS_ENABLED(CONFIG_RCU_EXP_KTHREAD))
 		sched_setscheduler_nocheck(kworker->task, SCHED_FIFO, &param);
-}
 
-static struct task_struct *rcu_exp_par_gp_task(struct rcu_node *rnp)
+	rcu_thread_affine_rnp(kworker->task, rnp);
-{
+	wake_up_process(kworker->task);
-	struct kthread_worker *kworker = READ_ONCE(rnp->exp_kworker);
-
-	if (!kworker)
-		return NULL;
-
-	return kworker->task;
 }
 
 static void __init rcu_start_exp_gp_kworker(void)
@@ -4111,7 +4119,7 @@ static void __init rcu_start_exp_gp_kworker(void)
 	const char *name = "rcu_exp_gp_kthread_worker";
 	struct sched_param param = { .sched_priority = kthread_prio };
 
-	rcu_exp_gp_kworker = kthread_create_worker(0, name);
+	rcu_exp_gp_kworker = kthread_run_worker(0, name);
 	if (IS_ERR_OR_NULL(rcu_exp_gp_kworker)) {
 		pr_err("Failed to create %s!\n", name);
 		rcu_exp_gp_kworker = NULL;
@@ -4188,67 +4196,6 @@ int rcutree_prepare_cpu(unsigned int cpu)
 	return 0;
 }
 
-/*
- * Update kthreads affinity during CPU-hotplug changes.
- *
- * Set the per-rcu_node kthread's affinity to cover all CPUs that are
- * served by the rcu_node in question.  The CPU hotplug lock is still
- * held, so the value of rnp->qsmaskinit will be stable.
- *
- * We don't include outgoingcpu in the affinity set, use -1 if there is
- * no outgoing CPU.  If there are no CPUs left in the affinity set,
- * this function allows the kthread to execute on any CPU.
- *
- * Any future concurrent calls are serialized via ->kthread_mutex.
- */
-static void rcutree_affinity_setting(unsigned int cpu, int outgoingcpu)
-{
-	cpumask_var_t cm;
-	unsigned long mask;
-	struct rcu_data *rdp;
-	struct rcu_node *rnp;
-	struct task_struct *task_boost, *task_exp;
-
-	rdp = per_cpu_ptr(&rcu_data, cpu);
-	rnp = rdp->mynode;
-
-	task_boost = rcu_boost_task(rnp);
-	task_exp = rcu_exp_par_gp_task(rnp);
-
-	/*
-	 * If CPU is the boot one, those tasks are created later from early
-	 * initcall since kthreadd must be created first.
-	 */
-	if (!task_boost && !task_exp)
-		return;
-
-	if (!zalloc_cpumask_var(&cm, GFP_KERNEL))
-		return;
-
-	mutex_lock(&rnp->kthread_mutex);
-	mask = rcu_rnp_online_cpus(rnp);
-	for_each_leaf_node_possible_cpu(rnp, cpu)
-		if ((mask & leaf_node_cpu_bit(rnp, cpu)) &&
-		    cpu != outgoingcpu)
-			cpumask_set_cpu(cpu, cm);
-	cpumask_and(cm, cm, housekeeping_cpumask(HK_TYPE_RCU));
-	if (cpumask_empty(cm)) {
-		cpumask_copy(cm, housekeeping_cpumask(HK_TYPE_RCU));
-		if (outgoingcpu >= 0)
-			cpumask_clear_cpu(outgoingcpu, cm);
-	}
-
-	if (task_exp)
-		set_cpus_allowed_ptr(task_exp, cm);
-
-	if (task_boost)
-		set_cpus_allowed_ptr(task_boost, cm);
-
-	mutex_unlock(&rnp->kthread_mutex);
-
-	free_cpumask_var(cm);
-}
-
 /*
  * Has the specified (known valid) CPU ever been fully online?
  */
@@ -4277,7 +4224,6 @@ int rcutree_online_cpu(unsigned int cpu)
 	if (rcu_scheduler_active == RCU_SCHEDULER_INACTIVE)
 		return 0; /* Too early in boot for scheduler work. */
 	sync_sched_exp_online_cleanup(cpu);
-	rcutree_affinity_setting(cpu, -1);
 
 	// Stop-machine done, so allow nohz_full to disable tick.
 	tick_dep_clear(TICK_DEP_BIT_RCU);
@@ -4494,8 +4440,6 @@ int rcutree_offline_cpu(unsigned int cpu)
 	rnp->ffmask &= ~rdp->grpmask;
 	raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 
-	rcutree_affinity_setting(cpu, cpu);
-
 	// nohz_full CPUs need the tick for stop-machine to work quickly
 	tick_dep_set(TICK_DEP_BIT_RCU);
 	return 0;

kernel/rcu/tree_plugin.h

@@ -1218,16 +1218,13 @@ static void rcu_spawn_one_boost_kthread(struct rcu_node *rnp)
 	raw_spin_lock_irqsave_rcu_node(rnp, flags);
 	rnp->boost_kthread_task = t;
 	raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+
 	sp.sched_priority = kthread_prio;
 	sched_setscheduler_nocheck(t, SCHED_FIFO, &sp);
+	rcu_thread_affine_rnp(t, rnp);
 	wake_up_process(t); /* get to TASK_INTERRUPTIBLE quickly. */
 }
 
-static struct task_struct *rcu_boost_task(struct rcu_node *rnp)
-{
-	return READ_ONCE(rnp->boost_kthread_task);
-}
-
 #else /* #ifdef CONFIG_RCU_BOOST */
 
 static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags)
@@ -1244,10 +1241,6 @@ static void rcu_spawn_one_boost_kthread(struct rcu_node *rnp)
 {
 }
 
-static struct task_struct *rcu_boost_task(struct rcu_node *rnp)
-{
-	return NULL;
-}
 #endif /* #else #ifdef CONFIG_RCU_BOOST */
 
 /*

kernel/sched/core.c

@@ -3536,7 +3536,7 @@ static int select_fallback_rq(int cpu, struct task_struct *p)
 			 *
 			 * More yuck to audit.
 			 */
-			do_set_cpus_allowed(p, task_cpu_possible_mask(p));
+			do_set_cpus_allowed(p, task_cpu_fallback_mask(p));
 			state = fail;
 			break;
 		case fail:

kernel/sched/ext.c

@@ -5410,7 +5410,7 @@ static struct kthread_worker *scx_create_rt_helper(const char *name)
 {
 	struct kthread_worker *helper;
 
-	helper = kthread_create_worker(0, name);
+	helper = kthread_run_worker(0, name);
 	if (helper)
 		sched_set_fifo(helper->task);
 	return helper;

kernel/workqueue.c

@@ -7832,7 +7832,7 @@ static void __init wq_cpu_intensive_thresh_init(void)
 	unsigned long thresh;
 	unsigned long bogo;
 
-	pwq_release_worker = kthread_create_worker(0, "pool_workqueue_release");
+	pwq_release_worker = kthread_run_worker(0, "pool_workqueue_release");
 	BUG_ON(IS_ERR(pwq_release_worker));
 
 	/* if the user set it to a specific value, keep it */

lib/test_objpool.c

@@ -371,14 +371,10 @@ static int ot_start_sync(struct ot_test *test)
 		if (!cpu_online(cpu))
 			continue;
 
-		work = kthread_create_on_node(ot_thread_worker, item,
+		work = kthread_run_on_cpu(ot_thread_worker, item,
-				cpu_to_node(cpu), "ot_worker_%d", cpu);
+					  cpu, "ot_worker_%d");
-		if (IS_ERR(work)) {
+		if (IS_ERR(work))
 			pr_err("failed to create thread for cpu %d\n", cpu);
-		} else {
-			kthread_bind(work, cpu);
-			wake_up_process(work);
-		}
 	}
 
 	/* wait a while to make sure all threads waiting at start line */
@@ -562,14 +558,9 @@ static int ot_start_async(struct ot_test *test)
 		if (!cpu_online(cpu))
 			continue;
 
-		work = kthread_create_on_node(ot_thread_worker, item,
+		work = kthread_run_on_cpu(ot_thread_worker, item, cpu, "ot_worker_%d");
-				cpu_to_node(cpu), "ot_worker_%d", cpu);
+		if (IS_ERR(work))
-		if (IS_ERR(work)) {
 			pr_err("failed to create thread for cpu %d\n", cpu);
-		} else {
-			kthread_bind(work, cpu);
-			wake_up_process(work);
-		}
 	}
 
 	/* wait a while to make sure all threads waiting at start line */

mm/compaction.c

@@ -3156,15 +3156,9 @@ void wakeup_kcompactd(pg_data_t *pgdat, int order, int highest_zoneidx)
 static int kcompactd(void *p)
 {
 	pg_data_t *pgdat = (pg_data_t *)p;
-	struct task_struct *tsk = current;
 	long default_timeout = msecs_to_jiffies(HPAGE_FRAG_CHECK_INTERVAL_MSEC);
 	long timeout = default_timeout;
 
-	const struct cpumask *cpumask = cpumask_of_node(pgdat->node_id);
-
-	if (!cpumask_empty(cpumask))
-		set_cpus_allowed_ptr(tsk, cpumask);
-
 	set_freezable();
 
 	pgdat->kcompactd_max_order = 0;
@@ -3235,10 +3229,12 @@ void __meminit kcompactd_run(int nid)
 	if (pgdat->kcompactd)
 		return;
 
-	pgdat->kcompactd = kthread_run(kcompactd, pgdat, "kcompactd%d", nid);
+	pgdat->kcompactd = kthread_create_on_node(kcompactd, pgdat, nid, "kcompactd%d", nid);
 	if (IS_ERR(pgdat->kcompactd)) {
 		pr_err("Failed to start kcompactd on node %d\n", nid);
 		pgdat->kcompactd = NULL;
+	} else {
+		wake_up_process(pgdat->kcompactd);
 	}
 }
 
@@ -3256,30 +3252,6 @@ void __meminit kcompactd_stop(int nid)
 	}
 }
 
-/*
- * It's optimal to keep kcompactd on the same CPUs as their memory, but
- * not required for correctness. So if the last cpu in a node goes
- * away, we get changed to run anywhere: as the first one comes back,
- * restore their cpu bindings.
- */
-static int kcompactd_cpu_online(unsigned int cpu)
-{
-	int nid;
-
-	for_each_node_state(nid, N_MEMORY) {
-		pg_data_t *pgdat = NODE_DATA(nid);
-		const struct cpumask *mask;
-
-		mask = cpumask_of_node(pgdat->node_id);
-
-		if (cpumask_any_and(cpu_online_mask, mask) < nr_cpu_ids)
-			/* One of our CPUs online: restore mask */
-			if (pgdat->kcompactd)
-				set_cpus_allowed_ptr(pgdat->kcompactd, mask);
-	}
-	return 0;
-}
-
 static int proc_dointvec_minmax_warn_RT_change(const struct ctl_table *table,
 		int write, void *buffer, size_t *lenp, loff_t *ppos)
 {
@@ -3339,15 +3311,6 @@ static struct ctl_table vm_compaction[] = {
 static int __init kcompactd_init(void)
 {
 	int nid;
-	int ret;
-
-	ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
-					"mm/compaction:online",
-					kcompactd_cpu_online, NULL);
-	if (ret < 0) {
-		pr_err("kcompactd: failed to register hotplug callbacks.\n");
-		return ret;
-	}
 
 	for_each_node_state(nid, N_MEMORY)
 		kcompactd_run(nid);

mm/vmscan.c

@@ -7151,10 +7151,6 @@ static int kswapd(void *p)
 	unsigned int highest_zoneidx = MAX_NR_ZONES - 1;
 	pg_data_t *pgdat = (pg_data_t *)p;
 	struct task_struct *tsk = current;
-	const struct cpumask *cpumask = cpumask_of_node(pgdat->node_id);
-
-	if (!cpumask_empty(cpumask))
-		set_cpus_allowed_ptr(tsk, cpumask);
 
 	/*
 	 * Tell the memory management that we're a "memory allocator",
@@ -7323,13 +7319,15 @@ void __meminit kswapd_run(int nid)
 
 	pgdat_kswapd_lock(pgdat);
 	if (!pgdat->kswapd) {
-		pgdat->kswapd = kthread_run(kswapd, pgdat, "kswapd%d", nid);
+		pgdat->kswapd = kthread_create_on_node(kswapd, pgdat, nid, "kswapd%d", nid);
 		if (IS_ERR(pgdat->kswapd)) {
 			/* failure at boot is fatal */
 			pr_err("Failed to start kswapd on node %d，ret=%ld\n",
 				   nid, PTR_ERR(pgdat->kswapd));
 			BUG_ON(system_state < SYSTEM_RUNNING);
 			pgdat->kswapd = NULL;
+		} else {
+			wake_up_process(pgdat->kswapd);
 		}
 	}
 	pgdat_kswapd_unlock(pgdat);

net/dsa/tag_ksz.c

@@ -66,7 +66,7 @@ static int ksz_connect(struct dsa_switch *ds)
 	if (!priv)
 		return -ENOMEM;
 
-	xmit_worker = kthread_create_worker(0, "dsa%d:%d_xmit",
+	xmit_worker = kthread_run_worker(0, "dsa%d:%d_xmit",
 					    ds->dst->index, ds->index);
 	if (IS_ERR(xmit_worker)) {
 		ret = PTR_ERR(xmit_worker);

net/dsa/tag_ocelot_8021q.c

@@ -110,7 +110,7 @@ static int ocelot_connect(struct dsa_switch *ds)
 	if (!priv)
 		return -ENOMEM;
 
-	priv->xmit_worker = kthread_create_worker(0, "felix_xmit");
+	priv->xmit_worker = kthread_run_worker(0, "felix_xmit");
 	if (IS_ERR(priv->xmit_worker)) {
 		err = PTR_ERR(priv->xmit_worker);
 		kfree(priv);

net/dsa/tag_sja1105.c

@@ -707,7 +707,7 @@ static int sja1105_connect(struct dsa_switch *ds)
 
 	spin_lock_init(&priv->meta_lock);
 
-	xmit_worker = kthread_create_worker(0, "dsa%d:%d_xmit",
+	xmit_worker = kthread_run_worker(0, "dsa%d:%d_xmit",
 					    ds->dst->index, ds->index);
 	if (IS_ERR(xmit_worker)) {
 		err = PTR_ERR(xmit_worker);