sched: Clean up active_mm reference counting

The current active_mm reference counting is confusing and sub-optimal.

Rewrite the code to explicitly consider the 4 separate cases:

    user -> user

	When switching between two user tasks, all we need to consider
	is switch_mm().

    user -> kernel

	When switching from a user task to a kernel task (which
	doesn't have an associated mm) we retain the last mm in our
	active_mm. Increment a reference count on active_mm.

  kernel -> kernel

	When switching between kernel threads, all we need to do is
	pass along the active_mm reference.

  kernel -> user

	When switching between a kernel and user task, we must switch
	from the last active_mm to the next mm, hoping of course that
	these are the same. Decrement a reference on the active_mm.

The code keeps a different order, because as you'll note, both 'to
user' cases require switch_mm().

And where the old code would increment/decrement for the 'kernel ->
kernel' case, the new code observes this is a neutral operation and
avoids touching the reference count.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Rik van Riel <riel@surriel.com>
Reviewed-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: luto@kernel.org

kernel/sched/core.c

@@ -3214,12 +3214,8 @@ static __always_inline struct rq *
 context_switch(struct rq *rq, struct task_struct *prev,
 	       struct task_struct *next, struct rq_flags *rf)
 {
-	struct mm_struct *mm, *oldmm;
-
 	prepare_task_switch(rq, prev, next);
 
-	mm = next->mm;
-	oldmm = prev->active_mm;
 	/*
 	 * For paravirt, this is coupled with an exit in switch_to to
 	 * combine the page table reload and the switch backend into
@@ -3228,22 +3224,37 @@ context_switch(struct rq *rq, struct task_struct *prev,
 	arch_start_context_switch(prev);
 
 	/*
-	 * If mm is non-NULL, we pass through switch_mm(). If mm is
-	 * NULL, we will pass through mmdrop() in finish_task_switch().
-	 * Both of these contain the full memory barrier required by
-	 * membarrier after storing to rq->curr, before returning to
-	 * user-space.
+	 * kernel -> kernel   lazy + transfer active
+	 *   user -> kernel   lazy + mmgrab() active
+	 *
+	 * kernel ->   user   switch + mmdrop() active
+	 *   user ->   user   switch
 	 */
-	if (!mm) {
-		next->active_mm = oldmm;
-		mmgrab(oldmm);
-		enter_lazy_tlb(oldmm, next);
-	} else
-		switch_mm_irqs_off(oldmm, mm, next);
-
-	if (!prev->mm) {
-		prev->active_mm = NULL;
-		rq->prev_mm = oldmm;
+	if (!next->mm) {                                // to kernel
+		enter_lazy_tlb(prev->active_mm, next);
+
+		next->active_mm = prev->active_mm;
+		if (prev->mm)                           // from user
+			mmgrab(prev->active_mm);
+		else
+			prev->active_mm = NULL;
+	} else {                                        // to user
+		/*
+		 * sys_membarrier() requires an smp_mb() between setting
+		 * rq->curr and returning to userspace.
+		 *
+		 * The below provides this either through switch_mm(), or in
+		 * case 'prev->active_mm == next->mm' through
+		 * finish_task_switch()'s mmdrop().
+		 */
+
+		switch_mm_irqs_off(prev->active_mm, next->mm, next);
+
+		if (!prev->mm) {                        // from kernel
+			/* will mmdrop() in finish_task_switch(). */
+			rq->prev_mm = prev->active_mm;
+			prev->active_mm = NULL;
+		}
 	}
 
 	rq->clock_update_flags &= ~(RQCF_ACT_SKIP|RQCF_REQ_SKIP);