[PATCH 2/2] lazy tlb: consolidate lazy tlb mm switching

[Nicholas Piggin]

Switching a kernel thread using a "lazy tlb mm" to init_mm is a
relatively common sequence that is not quite trivial. Consolidate this
into a function.

This fixes a bug in do_shoot_lazy_tlb() for any arch that implements
finish_arch_post_lock_switch(). None select MMU_LAZY_TLB_SHOOTDOWN at
the moment.

Fixes: 2655421ae69fa ("lazy tlb: shoot lazies, non-refcounting lazy tlb mm reference handling scheme")
Signed-off-by: Nicholas Piggin <npiggin at gmail.com>
---
 arch/powerpc/mm/book3s64/radix_tlb.c |  6 +----
 include/linux/sched/task.h           |  2 ++
 kernel/fork.c                        |  7 ++----
 kernel/sched/core.c                  | 34 ++++++++++++++++++++--------
 4 files changed, 29 insertions(+), 20 deletions(-)

diff --git a/arch/powerpc/mm/book3s64/radix_tlb.c b/arch/powerpc/mm/book3s64/radix_tlb.c
index ce804b7bf84e..90953cf9f648 100644
--- a/arch/powerpc/mm/book3s64/radix_tlb.c
+++ b/arch/powerpc/mm/book3s64/radix_tlb.c
@@ -795,12 +795,8 @@ void exit_lazy_flush_tlb(struct mm_struct *mm, bool always_flush)
 		goto out;
 
 	if (current->active_mm == mm) {
-		WARN_ON_ONCE(current->mm != NULL);
 		/* Is a kernel thread and is using mm as the lazy tlb */
-		mmgrab_lazy_tlb(&init_mm);
-		current->active_mm = &init_mm;
-		switch_mm_irqs_off(mm, &init_mm, current);
-		mmdrop_lazy_tlb(mm);
+		kthread_end_lazy_tlb_mm();
 	}
 
 	/*
diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h
index 537cbf9a2ade..23693b94a09b 100644
--- a/include/linux/sched/task.h
+++ b/include/linux/sched/task.h
@@ -61,6 +61,8 @@ extern int lockdep_tasklist_lock_is_held(void);
 extern asmlinkage void schedule_tail(struct task_struct *prev);
 extern void init_idle(struct task_struct *idle, int cpu);
 
+extern void kthread_end_lazy_tlb_mm(void);
+
 extern int sched_fork(unsigned long clone_flags, struct task_struct *p);
 extern void sched_cgroup_fork(struct task_struct *p, struct kernel_clone_args *kargs);
 extern void sched_post_fork(struct task_struct *p);
diff --git a/kernel/fork.c b/kernel/fork.c
index ed4e01daccaa..8b005c2c7c3c 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -854,11 +854,8 @@ static void do_shoot_lazy_tlb(void *arg)
 {
 	struct mm_struct *mm = arg;
 
-	if (current->active_mm == mm) {
-		WARN_ON_ONCE(current->mm);
-		current->active_mm = &init_mm;
-		switch_mm(mm, &init_mm, current);
-	}
+	if (current->active_mm == mm)
+		kthread_end_lazy_tlb_mm();
 }
 
 static void cleanup_lazy_tlbs(struct mm_struct *mm)
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index bc4ef1f3394b..71706df22b41 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -5346,6 +5346,29 @@ context_switch(struct rq *rq, struct task_struct *prev,
 	return finish_task_switch(prev);
 }
 
+/*
+ * If this kthread has a user process's mm for its active_mm (aka lazy tlb mm)
+ * then switch away from it, to init_mm. Must not be called while using an
+ * mm with kthread_use_mm().
+ */
+void kthread_end_lazy_tlb_mm(void)
+{
+	struct mm_struct *mm = current->active_mm;
+
+	WARN_ON_ONCE(!irqs_disabled());
+
+	if (WARN_ON_ONCE(current->mm))
+		return; /* Not a kthread or doing kthread_use_mm */
+
+	if (mm != &init_mm) {
+		mmgrab_lazy_tlb(&init_mm);
+		current->active_mm = &init_mm;
+		switch_mm_irqs_off(mm, &init_mm, current);
+		finish_arch_post_lock_switch();
+		mmdrop_lazy_tlb(mm);
+	}
+}
+
 /*
  * nr_running and nr_context_switches:
  *
@@ -9375,17 +9398,8 @@ void sched_setnuma(struct task_struct *p, int nid)
  */
 void idle_task_prepare_exit(void)
 {
-	struct mm_struct *mm = current->active_mm;
-
 	WARN_ON(!irqs_disabled());
-
-	if (mm != &init_mm) {
-		mmgrab_lazy_tlb(&init_mm);
-		current->active_mm = &init_mm;
-		switch_mm_irqs_off(mm, &init_mm, current);
-		finish_arch_post_lock_switch();
-		mmdrop_lazy_tlb(mm);
-	}
+	kthread_end_lazy_tlb_mm();
 	/* finish_cpu() will mmdrop the init_mm ref after this CPU stops */
 }
 
-- 
2.40.1