1 files changed, 62 insertions, 129 deletions

diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index 16ea67925015..e08abb9461ac 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -218,8 +218,8 @@ module_param(blimit, long, 0444);
 module_param(qhimark, long, 0444);
 module_param(qlowmark, long, 0444);
 
-static ulong jiffies_till_first_fqs = RCU_JIFFIES_TILL_FORCE_QS;
-static ulong jiffies_till_next_fqs = RCU_JIFFIES_TILL_FORCE_QS;
+static ulong jiffies_till_first_fqs = ULONG_MAX;
+static ulong jiffies_till_next_fqs = ULONG_MAX;
 
 module_param(jiffies_till_first_fqs, ulong, 0644);
 module_param(jiffies_till_next_fqs, ulong, 0644);
@@ -866,7 +866,7 @@ static void print_other_cpu_stall(struct rcu_state *rsp)
 	 * See Documentation/RCU/stallwarn.txt for info on how to debug
 	 * RCU CPU stall warnings.
 	 */
-	printk(KERN_ERR "INFO: %s detected stalls on CPUs/tasks:",
+	pr_err("INFO: %s detected stalls on CPUs/tasks:",
 	       rsp->name);
 	print_cpu_stall_info_begin();
 	rcu_for_each_leaf_node(rsp, rnp) {
@@ -899,7 +899,7 @@ static void print_other_cpu_stall(struct rcu_state *rsp)
 	       smp_processor_id(), (long)(jiffies - rsp->gp_start),
 	       rsp->gpnum, rsp->completed, totqlen);
 	if (ndetected == 0)
-		printk(KERN_ERR "INFO: Stall ended before state dump start\n");
+		pr_err("INFO: Stall ended before state dump start\n");
 	else if (!trigger_all_cpu_backtrace())
 		rcu_dump_cpu_stacks(rsp);
 
@@ -922,7 +922,7 @@ static void print_cpu_stall(struct rcu_state *rsp)
 	 * See Documentation/RCU/stallwarn.txt for info on how to debug
 	 * RCU CPU stall warnings.
 	 */
-	printk(KERN_ERR "INFO: %s self-detected stall on CPU", rsp->name);
+	pr_err("INFO: %s self-detected stall on CPU", rsp->name);
 	print_cpu_stall_info_begin();
 	print_cpu_stall_info(rsp, smp_processor_id());
 	print_cpu_stall_info_end();
@@ -985,65 +985,6 @@ void rcu_cpu_stall_reset(void)
 }
 
 /*
- * Update CPU-local rcu_data state to record the newly noticed grace period.
- * This is used both when we started the grace period and when we notice
- * that someone else started the grace period.  The caller must hold the
- * ->lock of the leaf rcu_node structure corresponding to the current CPU,
- *  and must have irqs disabled.
- */
-static void __note_new_gpnum(struct rcu_state *rsp, struct rcu_node *rnp, struct rcu_data *rdp)
-{
-	if (rdp->gpnum != rnp->gpnum) {
-		/*
-		 * If the current grace period is waiting for this CPU,
-		 * set up to detect a quiescent state, otherwise don't
-		 * go looking for one.
-		 */
-		rdp->gpnum = rnp->gpnum;
-		trace_rcu_grace_period(rsp->name, rdp->gpnum, "cpustart");
-		rdp->passed_quiesce = 0;
-		rdp->qs_pending = !!(rnp->qsmask & rdp->grpmask);
-		zero_cpu_stall_ticks(rdp);
-	}
-}
-
-static void note_new_gpnum(struct rcu_state *rsp, struct rcu_data *rdp)
-{
-	unsigned long flags;
-	struct rcu_node *rnp;
-
-	local_irq_save(flags);
-	rnp = rdp->mynode;
-	if (rdp->gpnum == ACCESS_ONCE(rnp->gpnum) || /* outside lock. */
-	    !raw_spin_trylock(&rnp->lock)) { /* irqs already off, so later. */
-		local_irq_restore(flags);
-		return;
-	}
-	__note_new_gpnum(rsp, rnp, rdp);
-	raw_spin_unlock_irqrestore(&rnp->lock, flags);
-}
-
-/*
- * Did someone else start a new RCU grace period start since we last
- * checked?  Update local state appropriately if so.  Must be called
- * on the CPU corresponding to rdp.
- */
-static int
-check_for_new_grace_period(struct rcu_state *rsp, struct rcu_data *rdp)
-{
-	unsigned long flags;
-	int ret = 0;
-
-	local_irq_save(flags);
-	if (rdp->gpnum != rsp->gpnum) {
-		note_new_gpnum(rsp, rdp);
-		ret = 1;
-	}
-	local_irq_restore(flags);
-	return ret;
-}
-
-/*
  * Initialize the specified rcu_data structure's callback list to empty.
  */
 static void init_callback_list(struct rcu_data *rdp)
@@ -1313,18 +1254,16 @@ static void rcu_advance_cbs(struct rcu_state *rsp, struct rcu_node *rnp,
 }
 
 /*
- * Advance this CPU's callbacks, but only if the current grace period
- * has ended.  This may be called only from the CPU to whom the rdp
- * belongs.  In addition, the corresponding leaf rcu_node structure's
- * ->lock must be held by the caller, with irqs disabled.
+ * Update CPU-local rcu_data state to record the beginnings and ends of
+ * grace periods.  The caller must hold the ->lock of the leaf rcu_node
+ * structure corresponding to the current CPU, and must have irqs disabled.
  */
-static void
-__rcu_process_gp_end(struct rcu_state *rsp, struct rcu_node *rnp, struct rcu_data *rdp)
+static void __note_gp_changes(struct rcu_state *rsp, struct rcu_node *rnp, struct rcu_data *rdp)
 {
-	/* Did another grace period end? */
+	/* Handle the ends of any preceding grace periods first. */
 	if (rdp->completed == rnp->completed) {
 
-		/* No, so just accelerate recent callbacks. */
+		/* No grace period end, so just accelerate recent callbacks. */
 		rcu_accelerate_cbs(rsp, rnp, rdp);
 
 	} else {
@@ -1335,68 +1274,40 @@ __rcu_process_gp_end(struct rcu_state *rsp, struct rcu_node *rnp, struct rcu_dat
 		/* Remember that we saw this grace-period completion. */
 		rdp->completed = rnp->completed;
 		trace_rcu_grace_period(rsp->name, rdp->gpnum, "cpuend");
+	}
 
+	if (rdp->gpnum != rnp->gpnum) {
 		/*
-		 * If we were in an extended quiescent state, we may have
-		 * missed some grace periods that others CPUs handled on
-		 * our behalf. Catch up with this state to avoid noting
-		 * spurious new grace periods.  If another grace period
-		 * has started, then rnp->gpnum will have advanced, so
-		 * we will detect this later on.  Of course, any quiescent
-		 * states we found for the old GP are now invalid.
-		 */
-		if (ULONG_CMP_LT(rdp->gpnum, rdp->completed)) {
-			rdp->gpnum = rdp->completed;
-			rdp->passed_quiesce = 0;
-		}
-
-		/*
-		 * If RCU does not need a quiescent state from this CPU,
-		 * then make sure that this CPU doesn't go looking for one.
+		 * If the current grace period is waiting for this CPU,
+		 * set up to detect a quiescent state, otherwise don't
+		 * go looking for one.
 		 */
-		if ((rnp->qsmask & rdp->grpmask) == 0)
-			rdp->qs_pending = 0;
+		rdp->gpnum = rnp->gpnum;
+		trace_rcu_grace_period(rsp->name, rdp->gpnum, "cpustart");
+		rdp->passed_quiesce = 0;
+		rdp->qs_pending = !!(rnp->qsmask & rdp->grpmask);
+		zero_cpu_stall_ticks(rdp);
 	}
 }
 
-/*
- * Advance this CPU's callbacks, but only if the current grace period
- * has ended.  This may be called only from the CPU to whom the rdp
- * belongs.
- */
-static void
-rcu_process_gp_end(struct rcu_state *rsp, struct rcu_data *rdp)
+static void note_gp_changes(struct rcu_state *rsp, struct rcu_data *rdp)
 {
 	unsigned long flags;
 	struct rcu_node *rnp;
 
 	local_irq_save(flags);
 	rnp = rdp->mynode;
-	if (rdp->completed == ACCESS_ONCE(rnp->completed) || /* outside lock. */
+	if ((rdp->gpnum == ACCESS_ONCE(rnp->gpnum) &&
+	     rdp->completed == ACCESS_ONCE(rnp->completed)) || /* w/out lock. */
 	    !raw_spin_trylock(&rnp->lock)) { /* irqs already off, so later. */
 		local_irq_restore(flags);
 		return;
 	}
-	__rcu_process_gp_end(rsp, rnp, rdp);
+	__note_gp_changes(rsp, rnp, rdp);
 	raw_spin_unlock_irqrestore(&rnp->lock, flags);
 }
 
 /*
- * Do per-CPU grace-period initialization for running CPU.  The caller
- * must hold the lock of the leaf rcu_node structure corresponding to
- * this CPU.
- */
-static void
-rcu_start_gp_per_cpu(struct rcu_state *rsp, struct rcu_node *rnp, struct rcu_data *rdp)
-{
-	/* Prior grace period ended, so advance callbacks for current CPU. */
-	__rcu_process_gp_end(rsp, rnp, rdp);
-
-	/* Set state so that this CPU will detect the next quiescent state. */
-	__note_new_gpnum(rsp, rnp, rdp);
-}
-
-/*
  * Initialize a new grace period.
  */
 static int rcu_gp_init(struct rcu_state *rsp)
@@ -1444,16 +1355,16 @@ static int rcu_gp_init(struct rcu_state *rsp)
 		WARN_ON_ONCE(rnp->completed != rsp->completed);
 		ACCESS_ONCE(rnp->completed) = rsp->completed;
 		if (rnp == rdp->mynode)
-			rcu_start_gp_per_cpu(rsp, rnp, rdp);
+			__note_gp_changes(rsp, rnp, rdp);
 		rcu_preempt_boost_start_gp(rnp);
 		trace_rcu_grace_period_init(rsp->name, rnp->gpnum,
 					    rnp->level, rnp->grplo,
 					    rnp->grphi, rnp->qsmask);
 		raw_spin_unlock_irq(&rnp->lock);
 #ifdef CONFIG_PROVE_RCU_DELAY
-		if ((prandom_u32() % (rcu_num_nodes * 8)) == 0 &&
+		if ((prandom_u32() % (rcu_num_nodes + 1)) == 0 &&
 		    system_state == SYSTEM_RUNNING)
-			schedule_timeout_uninterruptible(2);
+			udelay(200);
 #endif /* #ifdef CONFIG_PROVE_RCU_DELAY */
 		cond_resched();
 	}
@@ -1527,7 +1438,7 @@ static void rcu_gp_cleanup(struct rcu_state *rsp)
 		ACCESS_ONCE(rnp->completed) = rsp->gpnum;
 		rdp = this_cpu_ptr(rsp->rda);
 		if (rnp == rdp->mynode)
-			__rcu_process_gp_end(rsp, rnp, rdp);
+			__note_gp_changes(rsp, rnp, rdp);
 		nocb += rcu_future_gp_cleanup(rsp, rnp);
 		raw_spin_unlock_irq(&rnp->lock);
 		cond_resched();
@@ -1613,6 +1524,14 @@ static int __noreturn rcu_gp_kthread(void *arg)
 	}
 }
 
+static void rsp_wakeup(struct irq_work *work)
+{
+	struct rcu_state *rsp = container_of(work, struct rcu_state, wakeup_work);
+
+	/* Wake up rcu_gp_kthread() to start the grace period. */
+	wake_up(&rsp->gp_wq);
+}
+
 /*
  * Start a new RCU grace period if warranted, re-initializing the hierarchy
  * in preparation for detecting the next grace period.  The caller must hold
@@ -1637,8 +1556,12 @@ rcu_start_gp_advanced(struct rcu_state *rsp, struct rcu_node *rnp,
 	}
 	rsp->gp_flags = RCU_GP_FLAG_INIT;
 
-	/* Wake up rcu_gp_kthread() to start the grace period. */
-	wake_up(&rsp->gp_wq);
+	/*
+	 * We can't do wakeups while holding the rnp->lock, as that
+	 * could cause possible deadlocks with the rq->lock. Deter
+	 * the wakeup to interrupt context.
+	 */
+	irq_work_queue(&rsp->wakeup_work);
 }
 
 /*
@@ -1793,9 +1716,8 @@ rcu_report_qs_rdp(int cpu, struct rcu_state *rsp, struct rcu_data *rdp)
 static void
 rcu_check_quiescent_state(struct rcu_state *rsp, struct rcu_data *rdp)
 {
-	/* If there is now a new grace period, record and return. */
-	if (check_for_new_grace_period(rsp, rdp))
-		return;
+	/* Check for grace-period ends and beginnings. */
+	note_gp_changes(rsp, rdp);
 
 	/*
 	 * Does this CPU still need to do its part for current grace period?
@@ -2259,9 +2181,6 @@ __rcu_process_callbacks(struct rcu_state *rsp)
 
 	WARN_ON_ONCE(rdp->beenonline == 0);
 
-	/* Handle the end of a grace period that some other CPU ended.  */
-	rcu_process_gp_end(rsp, rdp);
-
 	/* Update RCU state based on any recent quiescent states. */
 	rcu_check_quiescent_state(rsp, rdp);
 
@@ -2346,8 +2265,7 @@ static void __call_rcu_core(struct rcu_state *rsp, struct rcu_data *rdp,
 	if (unlikely(rdp->qlen > rdp->qlen_last_fqs_check + qhimark)) {
 
 		/* Are we ignoring a completed grace period? */
-		rcu_process_gp_end(rsp, rdp);
-		check_for_new_grace_period(rsp, rdp);
+		note_gp_changes(rsp, rdp);
 
 		/* Start a new grace period if one not already started. */
 		if (!rcu_gp_in_progress(rsp)) {
@@ -3108,7 +3026,7 @@ static int __init rcu_spawn_gp_kthread(void)
 	struct task_struct *t;
 
 	for_each_rcu_flavor(rsp) {
-		t = kthread_run(rcu_gp_kthread, rsp, rsp->name);
+		t = kthread_run(rcu_gp_kthread, rsp, "%s", rsp->name);
 		BUG_ON(IS_ERR(t));
 		rnp = rcu_get_root(rsp);
 		raw_spin_lock_irqsave(&rnp->lock, flags);
@@ -3235,6 +3153,7 @@ static void __init rcu_init_one(struct rcu_state *rsp,
 
 	rsp->rda = rda;
 	init_waitqueue_head(&rsp->gp_wq);
+	init_irq_work(&rsp->wakeup_work, rsp_wakeup);
 	rnp = rsp->level[rcu_num_lvls - 1];
 	for_each_possible_cpu(i) {
 		while (i > rnp->grphi)
@@ -3252,11 +3171,25 @@ static void __init rcu_init_one(struct rcu_state *rsp,
  */
 static void __init rcu_init_geometry(void)
 {
+	ulong d;
 	int i;
 	int j;
 	int n = nr_cpu_ids;
 	int rcu_capacity[MAX_RCU_LVLS + 1];
 
+	/*
+	 * Initialize any unspecified boot parameters.
+	 * The default values of jiffies_till_first_fqs and
+	 * jiffies_till_next_fqs are set to the RCU_JIFFIES_TILL_FORCE_QS
+	 * value, which is a function of HZ, then adding one for each
+	 * RCU_JIFFIES_FQS_DIV CPUs that might be on the system.
+	 */
+	d = RCU_JIFFIES_TILL_FORCE_QS + nr_cpu_ids / RCU_JIFFIES_FQS_DIV;
+	if (jiffies_till_first_fqs == ULONG_MAX)
+		jiffies_till_first_fqs = d;
+	if (jiffies_till_next_fqs == ULONG_MAX)
+		jiffies_till_next_fqs = d;
+
 	/* If the compile-time values are accurate, just leave. */
 	if (rcu_fanout_leaf == CONFIG_RCU_FANOUT_LEAF &&
 	    nr_cpu_ids == NR_CPUS)