lazy tlb: introduce lazy tlb mm refcount helper functions

Add explicit _lazy_tlb annotated functions for lazy tlb mm refcounting. 
This makes the lazy tlb mm references more obvious, and allows the
refcounting scheme to be modified in later changes.  There is no
functional change with this patch.

Link: https://lkml.kernel.org/r/20230203071837.1136453-3-npiggin@gmail.com
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Christophe Leroy <christophe.leroy@csgroup.eu>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Nadav Amit <nadav.amit@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rik van Riel <riel@redhat.com>
Cc: Will Deacon <will@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

9 files changed, 41 insertions, 16 deletions

diff --git a/arch/arm/mach-rpc/ecard.c b/arch/arm/mach-rpc/ecard.c
index 53813f9464a2..c30df1097c52 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/kernel/smp.c b/arch/powerpc/kernel/smp.c
index 6b90f10a6c81..7db6b3faea65 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -1611,7 +1611,7 @@ void start_secondary(void *unused)
 	if (IS_ENABLED(CONFIG_PPC32))
 		setup_kup();
 
-	mmgrab(&init_mm);
+	mmgrab_lazy_tlb(&init_mm);
 	current->active_mm = &init_mm;
 
 	smp_store_cpu_info(cpu);
diff --git a/arch/powerpc/mm/book3s64/radix_tlb.c b/arch/powerpc/mm/book3s64/radix_tlb.c
index e50bc5fc7ddf..ce804b7bf84e 100644
--- a/arch/powerpc/mm/book3s64/radix_tlb.c
+++ b/arch/powerpc/mm/book3s64/radix_tlb.c
@@ -797,10 +797,10 @@ void exit_lazy_flush_tlb(struct mm_struct *mm, bool always_flush)
 	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);
 	}
 
 	/*
diff --git a/fs/exec.c b/fs/exec.c
index 7c44d0c65b1b..87cf3a2f0e9a 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1034,7 +1034,7 @@ static int exec_mmap(struct mm_struct *mm)
 		mmput(old_mm);
 		return 0;
 	}
-	mmdrop(active_mm);
+	mmdrop_lazy_tlb(active_mm);
 	return 0;
 }
 
diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h
index 2a243616f222..5376caf6fcf3 100644
--- a/include/linux/sched/mm.h
+++ b/include/linux/sched/mm.h
@@ -79,6 +79,22 @@ static inline void mmdrop_sched(struct mm_struct *mm)
 }
 #endif
 
+/* 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);
+}
+
+static inline void mmdrop_lazy_tlb_sched(struct mm_struct *mm)
+{
+	mmdrop_sched(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 6c0a92ca6bb5..189895288d9d 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -623,7 +623,7 @@ 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 f2afdb0add7c..86902cb5ab78 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -537,7 +537,7 @@ static void exit_mm(void)
 		return;
 	sync_mm_rss(mm);
 	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 1f1b60f1a746..470708c205e8 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -1415,6 +1415,11 @@ void kthread_use_mm(struct mm_struct *mm)
 	WARN_ON_ONCE(!(tsk->flags & PF_KTHREAD));
 	WARN_ON_ONCE(tsk->mm);
 
+	/*
+	 * It is possible for mm to be the same as tsk->active_mm, but
+	 * we must still mmgrab(mm) and mmdrop_lazy_tlb(active_mm),
+	 * because these references are not equivalent.
+	 */
 	mmgrab(mm);
 
 	task_lock(tsk);
@@ -1438,9 +1443,9 @@ void kthread_use_mm(struct mm_struct *mm)
 	 * memory barrier after storing to tsk->mm, before accessing
 	 * user-space memory. A full memory barrier for membarrier
 	 * {PRIVATE,GLOBAL}_EXPEDITED is implicitly provided by
-	 * mmdrop().
+	 * mmdrop_lazy_tlb().
 	 */
-	mmdrop(active_mm);
+	mmdrop_lazy_tlb(active_mm);
 }
 EXPORT_SYMBOL_GPL(kthread_use_mm);
 
@@ -1468,10 +1473,13 @@ void kthread_unuse_mm(struct mm_struct *mm)
 	local_irq_disable();
 	tsk->mm = NULL;
 	membarrier_update_current_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 0d18c3969f90..143e46bd2a68 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -5203,13 +5203,14 @@ 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_sched(mm);
+		mmdrop_lazy_tlb_sched(mm);
 	}
+
 	if (unlikely(prev_state == TASK_DEAD)) {
 		if (prev->sched_class->task_dead)
 			prev->sched_class->task_dead(prev);
@@ -5266,9 +5267,9 @@ 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
@@ -5276,7 +5277,7 @@ 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
@@ -5293,7 +5294,7 @@ context_switch(struct rq *rq, struct task_struct *prev,
 		lru_gen_use_mm(next->mm);
 
 		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;
 		}
@@ -9935,7 +9936,7 @@ 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);
 
 	/*