[RFC PATCH 2/7] mm: dispatch __mmput() to an mm_reaper kthread via llist

Introduce a single dedicated, freezable, sleepable kthread (mm_reaper)
modeled on oom_reaper, and the machinery to route the deferrable unit of
teardown -- __mmput() -- to it through a lock-free llist plus waitqueue.
mmput_exit() does llist_add() and wakes the kthread, which drains with
llist_del_all() and runs __mmput() per entry with cond_resched(). The
drain loop also calls try_to_freeze() after each entry, so a freeze
request is honoured mid-batch rather than only at the wait point.

Nothing calls mmput_exit() yet: exit_mm() is not routed to it, and there
is no eligibility check or gate, so it would queue every final-drop mm
unconditionally if invoked. This changes no behavior -- the function is
built but unreferenced, the kthread receives no work, and __mmput() runs
inline on the exiting CPU exactly as today. The exit_mm() hook and the
eligibility/gating policy follow in later patches.

llist (rather than oom_reaper's spinlock+list) avoids a global lock on
the exit path under many-core parallel exits. llist_for_each_entry_safe()
caches the next pointer before __mmput(), so iteration is safe even when
the final mmdrop() inside __mmput() frees mm.

Lifetime: the mm_count reference that mm_users>0 stands for is released
only by that final mmdrop() inside __mmput(). Deferring __mmput() keeps
the reference held, so the mm_struct and its embedded async_reap_node
stay alive until the kthread runs. No extra mmgrab() is needed, for the
same reason mmput_async() needs none.

The kthread is started at subsys_initcall and set to nice 19 to minimize
competition with other EEVDF tasks. Its affinity is expressed as a
preference via kthread_affine_preferred() over the HK_TYPE_KTHREAD
housekeeping mask, so it keeps off isolcpus= and cpuset-isolated CPUs
without the hard binding kthread_bind_mask() would impose --
PF_NO_SETAFFINITY would otherwise leave admins unable to re-affine it.

Signed-off-by: Aditya Sharma <[email protected]>
---
 kernel/fork.c | 54 +++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 54 insertions(+)

diff --git a/kernel/fork.c b/kernel/fork.c
index f0e2e131a..884e4e767 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -112,6 +112,7 @@
 #include <linux/unwind_deferred.h>
 #include <linux/pgalloc.h>
 #include <linux/uaccess.h>
+#include <linux/sched/isolation.h>
 
 #include <asm/mmu_context.h>
 #include <asm/cacheflush.h>
@@ -3407,3 +3408,56 @@ static int __init init_fork_sysctl(void)
 }
 
 subsys_initcall(init_fork_sysctl);
+
+#ifdef CONFIG_ASYNC_MM_TEARDOWN
+static LLIST_HEAD(mm_reaper_list);
+static DECLARE_WAIT_QUEUE_HEAD(mm_reaper_wait);
+
+static void async_mm_teardown_queue(struct mm_struct *mm)
+{
+	if (llist_add(&mm->async_reap_node, &mm_reaper_list))
+		wake_up(&mm_reaper_wait);
+}
+
+static int mm_reaper(void *unused)
+{
+	set_freezable();
+	while (true) {
+		struct llist_node *batch;
+		struct mm_struct *mm, *n;
+
+		wait_event_freezable(mm_reaper_wait, !llist_empty(&mm_reaper_list));
+		batch = llist_del_all(&mm_reaper_list);
+		llist_for_each_entry_safe(mm, n, batch, async_reap_node) {
+			__mmput(mm); /* may free mm via mmdrop */
+			cond_resched();
+			try_to_freeze();
+		}
+	}
+	return 0;
+}
+
+void mmput_exit(struct mm_struct *mm)
+{
+	might_sleep();
+	if (!atomic_dec_and_test(&mm->mm_users))
+		return;
+	async_mm_teardown_queue(mm);
+}
+
+static int __init mm_reaper_init(void)
+{
+	struct task_struct *th;
+
+	th = kthread_create(mm_reaper, NULL, "mm_reaper");
+	if (IS_ERR(th)) {
+		pr_err("mm_reaper: failed to start kthread: %ld\n", PTR_ERR(th));
+		return PTR_ERR(th);
+	}
+	set_user_nice(th, 19); /* minimize competition with other fair class tasks */
+	kthread_affine_preferred(th, housekeeping_cpumask(HK_TYPE_KTHREAD));
+	wake_up_process(th);
+	return 0;
+}
+subsys_initcall(mm_reaper_init);
+#endif
-- 
2.34.1