[PATCH v2 1/5] lazy tlb: introduce lazy mm refcount helper functions

[Nicholas Piggin <npiggin@gmail.com>]

Add explicit _lazy_tlb annotated functions for lazy mm refcounting.
This makes things a bit more explicit, and allows explicit refcounting
to be removed if it is not used.

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
 arch/arm/mach-rpc/ecard.c            |  2 +-
 arch/powerpc/mm/book3s64/radix_tlb.c |  4 ++--
 fs/exec.c                            |  4 ++--
 include/linux/sched/mm.h             | 11 +++++++++++
 kernel/cpu.c                         |  2 +-
 kernel/exit.c                        |  2 +-
 kernel/kthread.c                     | 11 +++++++----
 kernel/sched/core.c                  | 15 ++++++++-------
 8 files changed, 33 insertions(+), 18 deletions(-)

diff --git a/arch/arm/mach-rpc/ecard.c b/arch/arm/mach-rpc/ecard.c
index 827b50f1c73e..1b4a41aad793 100644
--- a/arch/arm/mach-rpc/ecard.c
+++ b/arch/arm/mach-rpc/ecard.c
@@ -253,7 +253,7 @@ static int ecard_init_mm(void)
 	current->mm = mm;
 	current->active_mm = mm;
 	activate_mm(active_mm, mm);
-	mmdrop(active_mm);
+	mmdrop_lazy_tlb(active_mm);
 	ecard_init_pgtables(mm);
 	return 0;
 }
diff --git a/arch/powerpc/mm/book3s64/radix_tlb.c b/arch/powerpc/mm/book3s64/radix_tlb.c
index b487b489d4b6..74708aef333e 100644
--- a/arch/powerpc/mm/book3s64/radix_tlb.c
+++ b/arch/powerpc/mm/book3s64/radix_tlb.c
@@ -658,10 +658,10 @@ static void do_exit_flush_lazy_tlb(void *arg)
 	if (current->active_mm == mm) {
 		WARN_ON_ONCE(current->mm != NULL);
 		/* Is a kernel thread and is using mm as the lazy tlb */
-		mmgrab(&init_mm);
+		mmgrab_lazy_tlb(&init_mm);
 		current->active_mm = &init_mm;
 		switch_mm_irqs_off(mm, &init_mm, current);
-		mmdrop(mm);
+		mmdrop_lazy_tlb(mm);
 	}
 
 	atomic_dec(&mm->context.active_cpus);
diff --git a/fs/exec.c b/fs/exec.c
index 547a2390baf5..56fc23dcbe4d 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1028,9 +1028,9 @@ static int exec_mmap(struct mm_struct *mm)
 		setmax_mm_hiwater_rss(&tsk->signal->maxrss, old_mm);
 		mm_update_next_owner(old_mm);
 		mmput(old_mm);
-		return 0;
+	} else {
+		mmdrop_lazy_tlb(active_mm);
 	}
-	mmdrop(active_mm);
 	return 0;
 }
 
diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h
index d5ece7a9a403..94a117160083 100644
--- a/include/linux/sched/mm.h
+++ b/include/linux/sched/mm.h
@@ -49,6 +49,17 @@ static inline void mmdrop(struct mm_struct *mm)
 		__mmdrop(mm);
 }
 
+/* Helpers for lazy TLB mm refcounting */
+static inline void mmgrab_lazy_tlb(struct mm_struct *mm)
+{
+	mmgrab(mm);
+}
+
+static inline void mmdrop_lazy_tlb(struct mm_struct *mm)
+{
+	mmdrop(mm);
+}
+
 /**
  * mmget() - Pin the address space associated with a &struct mm_struct.
  * @mm: The address space to pin.
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 2b8d7a5db383..a54cdfa08d71 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -576,7 +576,7 @@ static int finish_cpu(unsigned int cpu)
 	 */
 	if (mm != &init_mm)
 		idle->active_mm = &init_mm;
-	mmdrop(mm);
+	mmdrop_lazy_tlb(mm);
 	return 0;
 }
 
diff --git a/kernel/exit.c b/kernel/exit.c
index 1f236ed375f8..3711a74fcf4a 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -474,7 +474,7 @@ static void exit_mm(void)
 		__set_current_state(TASK_RUNNING);
 		mmap_read_lock(mm);
 	}
-	mmgrab(mm);
+	mmgrab_lazy_tlb(mm);
 	BUG_ON(mm != current->active_mm);
 	/* more a memory barrier than a real lock */
 	task_lock(current);
diff --git a/kernel/kthread.c b/kernel/kthread.c
index 933a625621b8..da189e0d26ed 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -1240,14 +1240,14 @@ void kthread_use_mm(struct mm_struct *mm)
 	WARN_ON_ONCE(!(tsk->flags & PF_KTHREAD));
 	WARN_ON_ONCE(tsk->mm);
 
+	mmgrab(mm);
+
 	task_lock(tsk);
 	/* Hold off tlb flush IPIs while switching mm's */
 	local_irq_disable();
 	active_mm = tsk->active_mm;
-	if (active_mm != mm) {
-		mmgrab(mm);
+	if (active_mm != mm)
 		tsk->active_mm = mm;
-	}
 	tsk->mm = mm;
 	switch_mm_irqs_off(active_mm, mm, tsk);
 	local_irq_enable();
@@ -1257,7 +1257,7 @@ void kthread_use_mm(struct mm_struct *mm)
 #endif
 
 	if (active_mm != mm)
-		mmdrop(active_mm);
+		mmdrop_lazy_tlb(active_mm);
 
 	to_kthread(tsk)->oldfs = force_uaccess_begin();
 }
@@ -1280,10 +1280,13 @@ void kthread_unuse_mm(struct mm_struct *mm)
 	sync_mm_rss(mm);
 	local_irq_disable();
 	tsk->mm = NULL;
+	mmgrab_lazy_tlb(mm);
 	/* active_mm is still 'mm' */
 	enter_lazy_tlb(mm, tsk);
 	local_irq_enable();
 	task_unlock(tsk);
+
+	mmdrop(mm);
 }
 EXPORT_SYMBOL_GPL(kthread_unuse_mm);
 
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index e7e453492cff..c2f8ea43d29b 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -3629,13 +3629,14 @@ static struct rq *finish_task_switch(struct task_struct *prev)
 	 * rq->curr, before returning to userspace, so provide them here:
 	 *
 	 * - a full memory barrier for {PRIVATE,GLOBAL}_EXPEDITED, implicitly
-	 *   provided by mmdrop(),
+	 *   provided by mmdrop_lazy_tlb(),
 	 * - a sync_core for SYNC_CORE.
 	 */
 	if (mm) {
 		membarrier_mm_sync_core_before_usermode(mm);
-		mmdrop(mm);
+		mmdrop_lazy_tlb(mm);
 	}
+
 	if (unlikely(prev_state == TASK_DEAD)) {
 		if (prev->sched_class->task_dead)
 			prev->sched_class->task_dead(prev);
@@ -3739,9 +3740,9 @@ context_switch(struct rq *rq, struct task_struct *prev,
 
 	/*
 	 * kernel -> kernel   lazy + transfer active
-	 *   user -> kernel   lazy + mmgrab() active
+	 *   user -> kernel   lazy + mmgrab_lazy_tlb() active
 	 *
-	 * kernel ->   user   switch + mmdrop() active
+	 * kernel ->   user   switch + mmdrop_lazy_tlb() active
 	 *   user ->   user   switch
 	 */
 	if (!next->mm) {                                // to kernel
@@ -3749,7 +3750,7 @@ context_switch(struct rq *rq, struct task_struct *prev,
 
 		next->active_mm = prev->active_mm;
 		if (prev->mm)                           // from user
-			mmgrab(prev->active_mm);
+			mmgrab_lazy_tlb(prev->active_mm);
 		else
 			prev->active_mm = NULL;
 	} else {                                        // to user
@@ -3765,7 +3766,7 @@ context_switch(struct rq *rq, struct task_struct *prev,
 		switch_mm_irqs_off(prev->active_mm, next->mm, next);
 
 		if (!prev->mm) {                        // from kernel
-			/* will mmdrop() in finish_task_switch(). */
+			/* will mmdrop_lazy_tlb() in finish_task_switch(). */
 			rq->prev_mm = prev->active_mm;
 			prev->active_mm = NULL;
 		}
@@ -7206,7 +7207,7 @@ void __init sched_init(void)
 	/*
 	 * The boot idle thread does lazy MMU switching as well:
 	 */
-	mmgrab(&init_mm);
+	mmgrab_lazy_tlb(&init_mm);
 	enter_lazy_tlb(&init_mm, current);
 
 	/*
-- 
2.23.0