Merge tag 'kthread-for-6.14-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/frederic/linux-dynticks

Pull kthread updates from Frederic Weisbecker:
 "Kthreads affinity follow either of 4 existing different patterns:

   1) Per-CPU kthreads must stay affine to a single CPU and never
      execute relevant code on any other CPU. This is currently handled
      by smpboot code which takes care of CPU-hotplug operations.
      Affinity here is a correctness constraint.

   2) Some kthreads _have_ to be affine to a specific set of CPUs and
      can't run anywhere else. The affinity is set through
      kthread_bind_mask() and the subsystem takes care by itself to
      handle CPU-hotplug operations. Affinity here is assumed to be a
      correctness constraint.

   3) Per-node kthreads _prefer_ to be affine to a specific NUMA node.
      This is not a correctness constraint but merely a preference in
      terms of memory locality. kswapd and kcompactd both fall into this
      category. The affinity is set manually like for any other task and
      CPU-hotplug is supposed to be handled by the relevant subsystem so
      that the task is properly reaffined whenever a given CPU from the
      node comes up. Also care should be taken so that the node affinity
      doesn't cross isolated (nohz_full) cpumask boundaries.

   4) Similar to the previous point except kthreads have a _preferred_
      affinity different than a node. Both RCU boost kthreads and RCU
      exp kworkers fall into this category as they refer to "RCU nodes"
      from a distinctly distributed tree.

  Currently the preferred affinity patterns (3 and 4) have at least 4
  identified users, with more or less success when it comes to handle
  CPU-hotplug operations and CPU isolation. Each of which do it in its
  own ad-hoc way.

  This is an infrastructure proposal to handle this with the following
  API changes:

   - kthread_create_on_node() automatically affines the created kthread
     to its target node unless it has been set as per-cpu or bound with
     kthread_bind[_mask]() before the first wake-up.

   - kthread_affine_preferred() is a new function that can be called
     right after kthread_create_on_node() to specify a preferred
     affinity different than the specified node.

  When the preferred affinity can't be applied because the possible
  targets are offline or isolated (nohz_full), the kthread is affine to
  the housekeeping CPUs (which means to all online CPUs most of the time
  or only the non-nohz_full CPUs when nohz_full= is set).

  kswapd, kcompactd, RCU boost kthreads and RCU exp kworkers have been
  converted, along with a few old drivers.

  Summary of the changes:

   - Consolidate a bunch of ad-hoc implementations of
     kthread_run_on_cpu()

   - Introduce task_cpu_fallback_mask() that defines the default last
     resort affinity of a task to become nohz_full aware

   - Add some correctness check to ensure kthread_bind() is always
     called before the first kthread wake up.

   - Default affine kthread to its preferred node.

   - Convert kswapd / kcompactd and remove their halfway working ad-hoc
     affinity implementation

   - Implement kthreads preferred affinity

   - Unify kthread worker and kthread API's style

   - Convert RCU kthreads to the new API and remove the ad-hoc affinity
     implementation"

* tag 'kthread-for-6.14-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/frederic/linux-dynticks:
  kthread: modify kernel-doc function name to match code
  rcu: Use kthread preferred affinity for RCU exp kworkers
  treewide: Introduce kthread_run_worker[_on_cpu]()
  kthread: Unify kthread_create_on_cpu() and kthread_create_worker_on_cpu() automatic format
  rcu: Use kthread preferred affinity for RCU boost
  kthread: Implement preferred affinity
  mm: Create/affine kswapd to its preferred node
  mm: Create/affine kcompactd to its preferred node
  kthread: Default affine kthread to its preferred NUMA node
  kthread: Make sure kthread hasn't started while binding it
  sched,arm64: Handle CPU isolation on last resort fallback rq selection
  arm64: Exclude nohz_full CPUs from 32bits el0 support
  lib: test_objpool: Use kthread_run_on_cpu()
  kallsyms: Use kthread_run_on_cpu()
  soc/qman: test: Use kthread_run_on_cpu()
  arm/bL_switcher: Use kthread_run_on_cpu()

3 files changed, 53 insertions, 5 deletions

diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index a04b73c40173..6cc5e484547c 100644
--- a/include/linux/cpuhotplug.h
+++ b/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,
diff --git a/include/linux/kthread.h b/include/linux/kthread.h
index b11f53c1ba2e..8d27403888ce 100644
--- a/include/linux/kthread.h
+++ b/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)
-struct kthread_worker *
-kthread_create_worker(unsigned int flags, const char namefmt[], ...);
+__printf(3, 4)
+struct kthread_worker *kthread_create_worker_on_node(unsigned int flags,
+						     int node,
+						     const char namefmt[], ...);
+
+#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;									\
+})
 
-__printf(3, 4) struct kthread_worker *
+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);
diff --git a/include/linux/mmu_context.h b/include/linux/mmu_context.h
index bbaec80c78c5..ac01dc4eb2ce 100644
--- a/include/linux/mmu_context.h
+++ b/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