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()

2 files changed, 6 insertions, 45 deletions

diff --git a/mm/compaction.c b/mm/compaction.c
index a2b16b08cbbf..a31c0f5758cf 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -3154,15 +3154,9 @@ 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;
@@ -3233,10 +3227,12 @@ 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);
 	}
 }
 
@@ -3254,30 +3250,6 @@ 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)
 {
@@ -3337,15 +3309,6 @@ 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);
diff --git a/mm/vmscan.c b/mm/vmscan.c
index b1ec5ece067e..867a2554434a 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -7192,10 +7192,6 @@ 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",
@@ -7364,13 +7360,15 @@ 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);