rcu: Create transitive rnp->lock acquisition functions

Providing RCU's memory-ordering guarantees requires that the rcu_node
tree's locking provide transitive memory ordering, which the Linux kernel's
spinlocks currently do not provide unless smp_mb__after_unlock_lock()
is used.  Having a separate smp_mb__after_unlock_lock() after each and
every lock acquisition is error-prone, hard to read, and a bit annoying,
so this commit provides wrapper functions that pull in the
smp_mb__after_unlock_lock() invocations.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>

kernel/rcu/tree.c

@@ -1534,10 +1534,8 @@ rcu_start_future_gp(struct rcu_node *rnp, struct rcu_data *rdp,
 	 * hold it, acquire the root rcu_node structure's lock in order to
 	 * start one (if needed).
 	 */
-	if (rnp != rnp_root) {
-		raw_spin_lock(&rnp_root->lock);
-		smp_mb__after_unlock_lock();
-	}
+	if (rnp != rnp_root)
+		raw_spin_lock_rcu_node(rnp_root);
 
 	/*
 	 * Get a new grace-period number.  If there really is no grace
@@ -1786,11 +1784,10 @@ static void note_gp_changes(struct rcu_state *rsp, struct rcu_data *rdp)
 	if ((rdp->gpnum == READ_ONCE(rnp->gpnum) &&
 	     rdp->completed == READ_ONCE(rnp->completed) &&
 	     !unlikely(READ_ONCE(rdp->gpwrap))) || /* w/out lock. */
-	    !raw_spin_trylock(&rnp->lock)) { /* irqs already off, so later. */
+	    !raw_spin_trylock_rcu_node(rnp)) { /* irqs already off, so later. */
 		local_irq_restore(flags);
 		return;
 	}
-	smp_mb__after_unlock_lock();
 	needwake = __note_gp_changes(rsp, rnp, rdp);
 	raw_spin_unlock_irqrestore(&rnp->lock, flags);
 	if (needwake)
@@ -1814,8 +1811,7 @@ static int rcu_gp_init(struct rcu_state *rsp)
 	struct rcu_node *rnp = rcu_get_root(rsp);
 
 	WRITE_ONCE(rsp->gp_activity, jiffies);
-	raw_spin_lock_irq(&rnp->lock);
-	smp_mb__after_unlock_lock();
+	raw_spin_lock_irq_rcu_node(rnp);
 	if (!READ_ONCE(rsp->gp_flags)) {
 		/* Spurious wakeup, tell caller to go back to sleep.  */
 		raw_spin_unlock_irq(&rnp->lock);
@@ -1847,8 +1843,7 @@ static int rcu_gp_init(struct rcu_state *rsp)
 	 */
 	rcu_for_each_leaf_node(rsp, rnp) {
 		rcu_gp_slow(rsp, gp_preinit_delay);
-		raw_spin_lock_irq(&rnp->lock);
-		smp_mb__after_unlock_lock();
+		raw_spin_lock_irq_rcu_node(rnp);
 		if (rnp->qsmaskinit == rnp->qsmaskinitnext &&
 		    !rnp->wait_blkd_tasks) {
 			/* Nothing to do on this leaf rcu_node structure. */
@@ -1904,8 +1899,7 @@ static int rcu_gp_init(struct rcu_state *rsp)
 	 */
 	rcu_for_each_node_breadth_first(rsp, rnp) {
 		rcu_gp_slow(rsp, gp_init_delay);
-		raw_spin_lock_irq(&rnp->lock);
-		smp_mb__after_unlock_lock();
+		raw_spin_lock_irq_rcu_node(rnp);
 		rdp = this_cpu_ptr(rsp->rda);
 		rcu_preempt_check_blocked_tasks(rnp);
 		rnp->qsmask = rnp->qsmaskinit;
@@ -1973,8 +1967,7 @@ static void rcu_gp_fqs(struct rcu_state *rsp, bool first_time)
 	}
 	/* Clear flag to prevent immediate re-entry. */
 	if (READ_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) {
-		raw_spin_lock_irq(&rnp->lock);
-		smp_mb__after_unlock_lock();
+		raw_spin_lock_irq_rcu_node(rnp);
 		WRITE_ONCE(rsp->gp_flags,
 			   READ_ONCE(rsp->gp_flags) & ~RCU_GP_FLAG_FQS);
 		raw_spin_unlock_irq(&rnp->lock);
@@ -1993,8 +1986,7 @@ static void rcu_gp_cleanup(struct rcu_state *rsp)
 	struct rcu_node *rnp = rcu_get_root(rsp);
 
 	WRITE_ONCE(rsp->gp_activity, jiffies);
-	raw_spin_lock_irq(&rnp->lock);
-	smp_mb__after_unlock_lock();
+	raw_spin_lock_irq_rcu_node(rnp);
 	gp_duration = jiffies - rsp->gp_start;
 	if (gp_duration > rsp->gp_max)
 		rsp->gp_max = gp_duration;
@@ -2019,8 +2011,7 @@ static void rcu_gp_cleanup(struct rcu_state *rsp)
 	 * grace period is recorded in any of the rcu_node structures.
 	 */
 	rcu_for_each_node_breadth_first(rsp, rnp) {
-		raw_spin_lock_irq(&rnp->lock);
-		smp_mb__after_unlock_lock();
+		raw_spin_lock_irq_rcu_node(rnp);
 		WARN_ON_ONCE(rcu_preempt_blocked_readers_cgp(rnp));
 		WARN_ON_ONCE(rnp->qsmask);
 		WRITE_ONCE(rnp->completed, rsp->gpnum);
@@ -2035,8 +2026,7 @@ static void rcu_gp_cleanup(struct rcu_state *rsp)
 		rcu_gp_slow(rsp, gp_cleanup_delay);
 	}
 	rnp = rcu_get_root(rsp);
-	raw_spin_lock_irq(&rnp->lock);
-	smp_mb__after_unlock_lock(); /* Order GP before ->completed update. */
+	raw_spin_lock_irq_rcu_node(rnp); /* Order GP before ->completed update. */
 	rcu_nocb_gp_set(rnp, nocb);
 
 	/* Declare grace period done. */
@@ -2284,8 +2274,7 @@ rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp,
 		raw_spin_unlock_irqrestore(&rnp->lock, flags);
 		rnp_c = rnp;
 		rnp = rnp->parent;
-		raw_spin_lock_irqsave(&rnp->lock, flags);
-		smp_mb__after_unlock_lock();
+		raw_spin_lock_irqsave_rcu_node(rnp, flags);
 		oldmask = rnp_c->qsmask;
 	}
 
@@ -2332,8 +2321,7 @@ static void rcu_report_unblock_qs_rnp(struct rcu_state *rsp,
 	gps = rnp->gpnum;
 	mask = rnp->grpmask;
 	raw_spin_unlock(&rnp->lock);	/* irqs remain disabled. */
-	raw_spin_lock(&rnp_p->lock);	/* irqs already disabled. */
-	smp_mb__after_unlock_lock();
+	raw_spin_lock_rcu_node(rnp_p);	/* irqs already disabled. */
 	rcu_report_qs_rnp(mask, rsp, rnp_p, gps, flags);
 }
 
@@ -2355,8 +2343,7 @@ rcu_report_qs_rdp(int cpu, struct rcu_state *rsp, struct rcu_data *rdp)
 	struct rcu_node *rnp;
 
 	rnp = rdp->mynode;
-	raw_spin_lock_irqsave(&rnp->lock, flags);
-	smp_mb__after_unlock_lock();
+	raw_spin_lock_irqsave_rcu_node(rnp, flags);
 	if ((rdp->cpu_no_qs.b.norm &&
 	     rdp->rcu_qs_ctr_snap == __this_cpu_read(rcu_qs_ctr)) ||
 	    rdp->gpnum != rnp->gpnum || rnp->completed == rnp->gpnum ||
@@ -2582,8 +2569,7 @@ static void rcu_cleanup_dead_rnp(struct rcu_node *rnp_leaf)
 		rnp = rnp->parent;
 		if (!rnp)
 			break;
-		raw_spin_lock(&rnp->lock); /* irqs already disabled. */
-		smp_mb__after_unlock_lock(); /* GP memory ordering. */
+		raw_spin_lock_rcu_node(rnp); /* irqs already disabled. */
 		rnp->qsmaskinit &= ~mask;
 		rnp->qsmask &= ~mask;
 		if (rnp->qsmaskinit) {
@@ -2611,8 +2597,7 @@ static void rcu_cleanup_dying_idle_cpu(int cpu, struct rcu_state *rsp)
 
 	/* Remove outgoing CPU from mask in the leaf rcu_node structure. */
 	mask = rdp->grpmask;
-	raw_spin_lock_irqsave(&rnp->lock, flags);
-	smp_mb__after_unlock_lock();	/* Enforce GP memory-order guarantee. */
+	raw_spin_lock_irqsave_rcu_node(rnp, flags); /* Enforce GP memory-order guarantee. */
 	rnp->qsmaskinitnext &= ~mask;
 	raw_spin_unlock_irqrestore(&rnp->lock, flags);
 }
@@ -2809,8 +2794,7 @@ static void force_qs_rnp(struct rcu_state *rsp,
 	rcu_for_each_leaf_node(rsp, rnp) {
 		cond_resched_rcu_qs();
 		mask = 0;
-		raw_spin_lock_irqsave(&rnp->lock, flags);
-		smp_mb__after_unlock_lock();
+		raw_spin_lock_irqsave_rcu_node(rnp, flags);
 		if (rnp->qsmask == 0) {
 			if (rcu_state_p == &rcu_sched_state ||
 			    rsp != rcu_state_p ||
@@ -2881,8 +2865,7 @@ static void force_quiescent_state(struct rcu_state *rsp)
 	/* rnp_old == rcu_get_root(rsp), rnp == NULL. */
 
 	/* Reached the root of the rcu_node tree, acquire lock. */
-	raw_spin_lock_irqsave(&rnp_old->lock, flags);
-	smp_mb__after_unlock_lock();
+	raw_spin_lock_irqsave_rcu_node(rnp_old, flags);
 	raw_spin_unlock(&rnp_old->fqslock);
 	if (READ_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) {
 		rsp->n_force_qs_lh++;
@@ -3005,8 +2988,7 @@ static void __call_rcu_core(struct rcu_state *rsp, struct rcu_data *rdp,
 		if (!rcu_gp_in_progress(rsp)) {
 			struct rcu_node *rnp_root = rcu_get_root(rsp);
 
-			raw_spin_lock(&rnp_root->lock);
-			smp_mb__after_unlock_lock();
+			raw_spin_lock_rcu_node(rnp_root);
 			needwake = rcu_start_gp(rsp);
 			raw_spin_unlock(&rnp_root->lock);
 			if (needwake)
@@ -3426,8 +3408,7 @@ static void sync_exp_reset_tree_hotplug(struct rcu_state *rsp)
 	 * CPUs for the current rcu_node structure up the rcu_node tree.
 	 */
 	rcu_for_each_leaf_node(rsp, rnp) {
-		raw_spin_lock_irqsave(&rnp->lock, flags);
-		smp_mb__after_unlock_lock();
+		raw_spin_lock_irqsave_rcu_node(rnp, flags);
 		if (rnp->expmaskinit == rnp->expmaskinitnext) {
 			raw_spin_unlock_irqrestore(&rnp->lock, flags);
 			continue;  /* No new CPUs, nothing to do. */
@@ -3447,8 +3428,7 @@ static void sync_exp_reset_tree_hotplug(struct rcu_state *rsp)
 		rnp_up = rnp->parent;
 		done = false;
 		while (rnp_up) {
-			raw_spin_lock_irqsave(&rnp_up->lock, flags);
-			smp_mb__after_unlock_lock();
+			raw_spin_lock_irqsave_rcu_node(rnp_up, flags);
 			if (rnp_up->expmaskinit)
 				done = true;
 			rnp_up->expmaskinit |= mask;
@@ -3472,8 +3452,7 @@ static void __maybe_unused sync_exp_reset_tree(struct rcu_state *rsp)
 
 	sync_exp_reset_tree_hotplug(rsp);
 	rcu_for_each_node_breadth_first(rsp, rnp) {
-		raw_spin_lock_irqsave(&rnp->lock, flags);
-		smp_mb__after_unlock_lock();
+		raw_spin_lock_irqsave_rcu_node(rnp, flags);
 		WARN_ON_ONCE(rnp->expmask);
 		rnp->expmask = rnp->expmaskinit;
 		raw_spin_unlock_irqrestore(&rnp->lock, flags);
@@ -3531,8 +3510,7 @@ static void __rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp,
 		mask = rnp->grpmask;
 		raw_spin_unlock(&rnp->lock); /* irqs remain disabled */
 		rnp = rnp->parent;
-		raw_spin_lock(&rnp->lock); /* irqs already disabled */
-		smp_mb__after_unlock_lock();
+		raw_spin_lock_rcu_node(rnp); /* irqs already disabled */
 		WARN_ON_ONCE(!(rnp->expmask & mask));
 		rnp->expmask &= ~mask;
 	}
@@ -3549,8 +3527,7 @@ static void __maybe_unused rcu_report_exp_rnp(struct rcu_state *rsp,
 {
 	unsigned long flags;
 
-	raw_spin_lock_irqsave(&rnp->lock, flags);
-	smp_mb__after_unlock_lock();
+	raw_spin_lock_irqsave_rcu_node(rnp, flags);
 	__rcu_report_exp_rnp(rsp, rnp, wake, flags);
 }
 
@@ -3564,8 +3541,7 @@ static void rcu_report_exp_cpu_mult(struct rcu_state *rsp, struct rcu_node *rnp,
 {
 	unsigned long flags;
 
-	raw_spin_lock_irqsave(&rnp->lock, flags);
-	smp_mb__after_unlock_lock();
+	raw_spin_lock_irqsave_rcu_node(rnp, flags);
 	if (!(rnp->expmask & mask)) {
 		raw_spin_unlock_irqrestore(&rnp->lock, flags);
 		return;
@@ -3708,8 +3684,7 @@ static void sync_rcu_exp_select_cpus(struct rcu_state *rsp,
 
 	sync_exp_reset_tree(rsp);
 	rcu_for_each_leaf_node(rsp, rnp) {
-		raw_spin_lock_irqsave(&rnp->lock, flags);
-		smp_mb__after_unlock_lock();
+		raw_spin_lock_irqsave_rcu_node(rnp, flags);
 
 		/* Each pass checks a CPU for identity, offline, and idle. */
 		mask_ofl_test = 0;
@@ -4198,8 +4173,7 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp)
 	 */
 	rnp = rdp->mynode;
 	mask = rdp->grpmask;
-	raw_spin_lock(&rnp->lock);		/* irqs already disabled. */
-	smp_mb__after_unlock_lock();
+	raw_spin_lock_rcu_node(rnp);		/* irqs already disabled. */
 	rnp->qsmaskinitnext |= mask;
 	rnp->expmaskinitnext |= mask;
 	if (!rdp->beenonline)

kernel/rcu/tree.h

@@ -664,3 +664,42 @@ static inline void rcu_nocb_q_lengths(struct rcu_data *rdp, long *ql, long *qll)
 #else /* #ifdef CONFIG_PPC */
 #define smp_mb__after_unlock_lock()	do { } while (0)
 #endif /* #else #ifdef CONFIG_PPC */
+
+/*
+ * Wrappers for the rcu_node::lock acquire.
+ *
+ * Because the rcu_nodes form a tree, the tree traversal locking will observe
+ * different lock values, this in turn means that an UNLOCK of one level
+ * followed by a LOCK of another level does not imply a full memory barrier;
+ * and most importantly transitivity is lost.
+ *
+ * In order to restore full ordering between tree levels, augment the regular
+ * lock acquire functions with smp_mb__after_unlock_lock().
+ */
+static inline void raw_spin_lock_rcu_node(struct rcu_node *rnp)
+{
+	raw_spin_lock(&rnp->lock);
+	smp_mb__after_unlock_lock();
+}
+
+static inline void raw_spin_lock_irq_rcu_node(struct rcu_node *rnp)
+{
+	raw_spin_lock_irq(&rnp->lock);
+	smp_mb__after_unlock_lock();
+}
+
+#define raw_spin_lock_irqsave_rcu_node(rnp, flags)	\
+do {							\
+	typecheck(unsigned long, flags);		\
+	raw_spin_lock_irqsave(&(rnp)->lock, flags);	\
+	smp_mb__after_unlock_lock();			\
+} while (0)
+
+static inline bool raw_spin_trylock_rcu_node(struct rcu_node *rnp)
+{
+	bool locked = raw_spin_trylock(&rnp->lock);
+
+	if (locked)
+		smp_mb__after_unlock_lock();
+	return locked;
+}

kernel/rcu/tree_plugin.h

@@ -301,8 +301,7 @@ static void rcu_preempt_note_context_switch(void)
 		/* Possibly blocking in an RCU read-side critical section. */
 		rdp = this_cpu_ptr(rcu_state_p->rda);
 		rnp = rdp->mynode;
-		raw_spin_lock_irqsave(&rnp->lock, flags);
-		smp_mb__after_unlock_lock();
+		raw_spin_lock_irqsave_rcu_node(rnp, flags);
 		t->rcu_read_unlock_special.b.blocked = true;
 		t->rcu_blocked_node = rnp;
 
@@ -457,8 +456,7 @@ void rcu_read_unlock_special(struct task_struct *t)
 		 */
 		for (;;) {
 			rnp = t->rcu_blocked_node;
-			raw_spin_lock(&rnp->lock);  /* irqs already disabled. */
-			smp_mb__after_unlock_lock();
+			raw_spin_lock_rcu_node(rnp); /* irqs already disabled. */
 			if (rnp == t->rcu_blocked_node)
 				break;
 			WARN_ON_ONCE(1);
@@ -989,8 +987,7 @@ static int rcu_boost(struct rcu_node *rnp)
 	    READ_ONCE(rnp->boost_tasks) == NULL)
 		return 0;  /* Nothing left to boost. */
 
-	raw_spin_lock_irqsave(&rnp->lock, flags);
-	smp_mb__after_unlock_lock();
+	raw_spin_lock_irqsave_rcu_node(rnp, flags);
 
 	/*
 	 * Recheck under the lock: all tasks in need of boosting
@@ -1176,8 +1173,7 @@ static int rcu_spawn_one_boost_kthread(struct rcu_state *rsp,
 			   "rcub/%d", rnp_index);
 	if (IS_ERR(t))
 		return PTR_ERR(t);
-	raw_spin_lock_irqsave(&rnp->lock, flags);
-	smp_mb__after_unlock_lock();
+	raw_spin_lock_irqsave_rcu_node(rnp, flags);
 	rnp->boost_kthread_task = t;
 	raw_spin_unlock_irqrestore(&rnp->lock, flags);
 	sp.sched_priority = kthread_prio;
@@ -1567,8 +1563,7 @@ static void rcu_prepare_for_idle(void)
 		if (!*rdp->nxttail[RCU_DONE_TAIL])
 			continue;
 		rnp = rdp->mynode;
-		raw_spin_lock(&rnp->lock); /* irqs already disabled. */
-		smp_mb__after_unlock_lock();
+		raw_spin_lock_rcu_node(rnp); /* irqs already disabled. */
 		needwake = rcu_accelerate_cbs(rsp, rnp, rdp);
 		raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */
 		if (needwake)
@@ -2068,8 +2063,7 @@ static void rcu_nocb_wait_gp(struct rcu_data *rdp)
 	bool needwake;
 	struct rcu_node *rnp = rdp->mynode;
 
-	raw_spin_lock_irqsave(&rnp->lock, flags);
-	smp_mb__after_unlock_lock();
+	raw_spin_lock_irqsave_rcu_node(rnp, flags);
 	needwake = rcu_start_future_gp(rnp, rdp, &c);
 	raw_spin_unlock_irqrestore(&rnp->lock, flags);
 	if (needwake)