1 files changed, 116 insertions, 31 deletions

diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c
index 0f23d20d485a..e26547b34ad3 100644
--- a/kernel/rcu/srcutree.c
+++ b/kernel/rcu/srcutree.c
@@ -808,6 +808,46 @@ static void srcu_leak_callback(struct rcu_head *rhp)
 }
 
 /*
+ * Start an SRCU grace period, and also queue the callback if non-NULL.
+ */
+static unsigned long srcu_gp_start_if_needed(struct srcu_struct *ssp,
+					     struct rcu_head *rhp, bool do_norm)
+{
+	unsigned long flags;
+	int idx;
+	bool needexp = false;
+	bool needgp = false;
+	unsigned long s;
+	struct srcu_data *sdp;
+
+	check_init_srcu_struct(ssp);
+	idx = srcu_read_lock(ssp);
+	sdp = raw_cpu_ptr(ssp->sda);
+	spin_lock_irqsave_rcu_node(sdp, flags);
+	if (rhp)
+		rcu_segcblist_enqueue(&sdp->srcu_cblist, rhp);
+	rcu_segcblist_advance(&sdp->srcu_cblist,
+			      rcu_seq_current(&ssp->srcu_gp_seq));
+	s = rcu_seq_snap(&ssp->srcu_gp_seq);
+	(void)rcu_segcblist_accelerate(&sdp->srcu_cblist, s);
+	if (ULONG_CMP_LT(sdp->srcu_gp_seq_needed, s)) {
+		sdp->srcu_gp_seq_needed = s;
+		needgp = true;
+	}
+	if (!do_norm && ULONG_CMP_LT(sdp->srcu_gp_seq_needed_exp, s)) {
+		sdp->srcu_gp_seq_needed_exp = s;
+		needexp = true;
+	}
+	spin_unlock_irqrestore_rcu_node(sdp, flags);
+	if (needgp)
+		srcu_funnel_gp_start(ssp, sdp, s, do_norm);
+	else if (needexp)
+		srcu_funnel_exp_start(ssp, sdp->mynode, s);
+	srcu_read_unlock(ssp, idx);
+	return s;
+}
+
+/*
  * Enqueue an SRCU callback on the srcu_data structure associated with
  * the current CPU and the specified srcu_struct structure, initiating
  * grace-period processing if it is not already running.
@@ -838,14 +878,6 @@ static void srcu_leak_callback(struct rcu_head *rhp)
 static void __call_srcu(struct srcu_struct *ssp, struct rcu_head *rhp,
 			rcu_callback_t func, bool do_norm)
 {
-	unsigned long flags;
-	int idx;
-	bool needexp = false;
-	bool needgp = false;
-	unsigned long s;
-	struct srcu_data *sdp;
-
-	check_init_srcu_struct(ssp);
 	if (debug_rcu_head_queue(rhp)) {
 		/* Probable double call_srcu(), so leak the callback. */
 		WRITE_ONCE(rhp->func, srcu_leak_callback);
@@ -853,28 +885,7 @@ static void __call_srcu(struct srcu_struct *ssp, struct rcu_head *rhp,
 		return;
 	}
 	rhp->func = func;
-	idx = srcu_read_lock(ssp);
-	sdp = raw_cpu_ptr(ssp->sda);
-	spin_lock_irqsave_rcu_node(sdp, flags);
-	rcu_segcblist_enqueue(&sdp->srcu_cblist, rhp);
-	rcu_segcblist_advance(&sdp->srcu_cblist,
-			      rcu_seq_current(&ssp->srcu_gp_seq));
-	s = rcu_seq_snap(&ssp->srcu_gp_seq);
-	(void)rcu_segcblist_accelerate(&sdp->srcu_cblist, s);
-	if (ULONG_CMP_LT(sdp->srcu_gp_seq_needed, s)) {
-		sdp->srcu_gp_seq_needed = s;
-		needgp = true;
-	}
-	if (!do_norm && ULONG_CMP_LT(sdp->srcu_gp_seq_needed_exp, s)) {
-		sdp->srcu_gp_seq_needed_exp = s;
-		needexp = true;
-	}
-	spin_unlock_irqrestore_rcu_node(sdp, flags);
-	if (needgp)
-		srcu_funnel_gp_start(ssp, sdp, s, do_norm);
-	else if (needexp)
-		srcu_funnel_exp_start(ssp, sdp->mynode, s);
-	srcu_read_unlock(ssp, idx);
+	(void)srcu_gp_start_if_needed(ssp, rhp, do_norm);
 }
 
 /**
@@ -1003,6 +1014,77 @@ void synchronize_srcu(struct srcu_struct *ssp)
 }
 EXPORT_SYMBOL_GPL(synchronize_srcu);
 
+/**
+ * get_state_synchronize_srcu - Provide an end-of-grace-period cookie
+ * @ssp: srcu_struct to provide cookie for.
+ *
+ * This function returns a cookie that can be passed to
+ * poll_state_synchronize_srcu(), which will return true if a full grace
+ * period has elapsed in the meantime.  It is the caller's responsibility
+ * to make sure that grace period happens, for example, by invoking
+ * call_srcu() after return from get_state_synchronize_srcu().
+ */
+unsigned long get_state_synchronize_srcu(struct srcu_struct *ssp)
+{
+	// Any prior manipulation of SRCU-protected data must happen
+	// before the load from ->srcu_gp_seq.
+	smp_mb();
+	return rcu_seq_snap(&ssp->srcu_gp_seq);
+}
+EXPORT_SYMBOL_GPL(get_state_synchronize_srcu);
+
+/**
+ * start_poll_synchronize_srcu - Provide cookie and start grace period
+ * @ssp: srcu_struct to provide cookie for.
+ *
+ * This function returns a cookie that can be passed to
+ * poll_state_synchronize_srcu(), which will return true if a full grace
+ * period has elapsed in the meantime.  Unlike get_state_synchronize_srcu(),
+ * this function also ensures that any needed SRCU grace period will be
+ * started.  This convenience does come at a cost in terms of CPU overhead.
+ */
+unsigned long start_poll_synchronize_srcu(struct srcu_struct *ssp)
+{
+	return srcu_gp_start_if_needed(ssp, NULL, true);
+}
+EXPORT_SYMBOL_GPL(start_poll_synchronize_srcu);
+
+/**
+ * poll_state_synchronize_srcu - Has cookie's grace period ended?
+ * @ssp: srcu_struct to provide cookie for.
+ * @cookie: Return value from get_state_synchronize_srcu() or start_poll_synchronize_srcu().
+ *
+ * This function takes the cookie that was returned from either
+ * get_state_synchronize_srcu() or start_poll_synchronize_srcu(), and
+ * returns @true if an SRCU grace period elapsed since the time that the
+ * cookie was created.
+ *
+ * Because cookies are finite in size, wrapping/overflow is possible.
+ * This is more pronounced on 32-bit systems where cookies are 32 bits,
+ * where in theory wrapping could happen in about 14 hours assuming
+ * 25-microsecond expedited SRCU grace periods.  However, a more likely
+ * overflow lower bound is on the order of 24 days in the case of
+ * one-millisecond SRCU grace periods.  Of course, wrapping in a 64-bit
+ * system requires geologic timespans, as in more than seven million years
+ * even for expedited SRCU grace periods.
+ *
+ * Wrapping/overflow is much more of an issue for CONFIG_SMP=n systems
+ * that also have CONFIG_PREEMPTION=n, which selects Tiny SRCU.  This uses
+ * a 16-bit cookie, which rcutorture routinely wraps in a matter of a
+ * few minutes.  If this proves to be a problem, this counter will be
+ * expanded to the same size as for Tree SRCU.
+ */
+bool poll_state_synchronize_srcu(struct srcu_struct *ssp, unsigned long cookie)
+{
+	if (!rcu_seq_done(&ssp->srcu_gp_seq, cookie))
+		return false;
+	// Ensure that the end of the SRCU grace period happens before
+	// any subsequent code that the caller might execute.
+	smp_mb(); // ^^^
+	return true;
+}
+EXPORT_SYMBOL_GPL(poll_state_synchronize_srcu);
+
 /*
  * Callback function for srcu_barrier() use.
  */
@@ -1160,6 +1242,7 @@ static void srcu_advance_state(struct srcu_struct *ssp)
  */
 static void srcu_invoke_callbacks(struct work_struct *work)
 {
+	long len;
 	bool more;
 	struct rcu_cblist ready_cbs;
 	struct rcu_head *rhp;
@@ -1182,6 +1265,7 @@ static void srcu_invoke_callbacks(struct work_struct *work)
 	/* We are on the job!  Extract and invoke ready callbacks. */
 	sdp->srcu_cblist_invoking = true;
 	rcu_segcblist_extract_done_cbs(&sdp->srcu_cblist, &ready_cbs);
+	len = ready_cbs.len;
 	spin_unlock_irq_rcu_node(sdp);
 	rhp = rcu_cblist_dequeue(&ready_cbs);
 	for (; rhp != NULL; rhp = rcu_cblist_dequeue(&ready_cbs)) {
@@ -1190,13 +1274,14 @@ static void srcu_invoke_callbacks(struct work_struct *work)
 		rhp->func(rhp);
 		local_bh_enable();
 	}
+	WARN_ON_ONCE(ready_cbs.len);
 
 	/*
 	 * Update counts, accelerate new callbacks, and if needed,
 	 * schedule another round of callback invocation.
 	 */
 	spin_lock_irq_rcu_node(sdp);
-	rcu_segcblist_insert_count(&sdp->srcu_cblist, &ready_cbs);
+	rcu_segcblist_add_len(&sdp->srcu_cblist, -len);
 	(void)rcu_segcblist_accelerate(&sdp->srcu_cblist,
 				       rcu_seq_snap(&ssp->srcu_gp_seq));
 	sdp->srcu_cblist_invoking = false;