+ lazy-tlb-consolidate-lazy-tlb-mm-switching.patch added to mm-hotfixes-unstable branch

+ lazy-tlb-consolidate-lazy-tlb-mm-switching.patch added to mm-hotfixes-unstable branch

[Andrew Morton]

The patch titled
     Subject: lazy tlb: consolidate lazy tlb mm switching
has been added to the -mm mm-hotfixes-unstable branch.  Its filename is
     lazy-tlb-consolidate-lazy-tlb-mm-switching.patch

This patch will shortly appear at
     https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/lazy-tlb-consolidate-lazy-tlb-mm-switching.patch

This patch will later appear in the mm-hotfixes-unstable branch at
    git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Before you just go and hit "reply", please:
   a) Consider who else should be cc'ed
   b) Prefer to cc a suitable mailing list as well
   c) Ideally: find the original patch on the mailing list and do a
      reply-to-all to that, adding suitable additional cc's

*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***

The -mm tree is included into linux-next via the mm-everything
branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
and is updated there every 2-3 working days

------------------------------------------------------
From: Nicholas Piggin <npiggin@gmail.com>
Subject: lazy tlb: consolidate lazy tlb mm switching
Date: Wed, 24 May 2023 16:04:55 +1000

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.

Link: https://lkml.kernel.org/r/20230524060455.147699-2-npiggin@gmail.com
Fixes: 2655421ae69fa ("lazy tlb: shoot lazies, non-refcounting lazy tlb mm reference handling scheme")
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 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(-)

--- a/arch/powerpc/mm/book3s64/radix_tlb.c~lazy-tlb-consolidate-lazy-tlb-mm-switching
+++ a/arch/powerpc/mm/book3s64/radix_tlb.c
@@ -795,12 +795,8 @@ void exit_lazy_flush_tlb(struct mm_struc
 		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();
 	}
 
 	/*
--- a/include/linux/sched/task.h~lazy-tlb-consolidate-lazy-tlb-mm-switching
+++ a/include/linux/sched/task.h
@@ -61,6 +61,8 @@ extern int lockdep_tasklist_lock_is_held
 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);
--- a/kernel/fork.c~lazy-tlb-consolidate-lazy-tlb-mm-switching
+++ a/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)
--- a/kernel/sched/core.c~lazy-tlb-consolidate-lazy-tlb-mm-switching
+++ a/kernel/sched/core.c
@@ -5347,6 +5347,29 @@ context_switch(struct rq *rq, struct tas
 }
 
 /*
+ * 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:
  *
  * externally visible scheduler statistics: current number of runnable
@@ -9375,17 +9398,8 @@ void sched_setnuma(struct task_struct *p
  */
 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 */
 }
 
_

Patches currently in -mm which might be from npiggin@gmail.com are

lazy-tlb-fix-hotplug-exit-race-with-mmu_lazy_tlb_shootdown.patch
lazy-tlb-consolidate-lazy-tlb-mm-switching.patch