1 files changed, 1040 insertions, 152 deletions

diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h
index 0e4f420245d9..8aafbb80b8b0 100644
--- a/kernel/rcutree_plugin.h
+++ b/kernel/rcutree_plugin.h
@@ -1,7 +1,7 @@
 /*
  * Read-Copy Update mechanism for mutual exclusion (tree-based version)
  * Internal non-public definitions that provide either classic
- * or preemptable semantics.
+ * or preemptible semantics.
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -25,6 +25,7 @@
  */
 
 #include <linux/delay.h>
+#include <linux/stop_machine.h>
 
 /*
  * Check the RCU kernel configuration parameters and print informative
@@ -53,11 +54,7 @@ static void __init rcu_bootup_announce_oddness(void)
 #ifdef CONFIG_RCU_TORTURE_TEST_RUNNABLE
         printk(KERN_INFO "\tRCU torture testing starts during boot.\n");
 #endif
-#ifndef CONFIG_RCU_CPU_STALL_DETECTOR
-        printk(KERN_INFO
-               "\tRCU-based detection of stalled CPUs is disabled.\n");
-#endif
-#ifndef CONFIG_RCU_CPU_STALL_VERBOSE
+#if defined(CONFIG_TREE_PREEMPT_RCU) && !defined(CONFIG_RCU_CPU_STALL_VERBOSE)
         printk(KERN_INFO "\tVerbose stalled-CPUs detection is disabled.\n");
 #endif
 #if NUM_RCU_LVL_4 != 0
@@ -69,7 +66,9 @@ static void __init rcu_bootup_announce_oddness(void)
 
 struct rcu_state rcu_preempt_state = RCU_STATE_INITIALIZER(rcu_preempt_state);
 DEFINE_PER_CPU(struct rcu_data, rcu_preempt_data);
+static struct rcu_state *rcu_state = &rcu_preempt_state;
 
+static void rcu_read_unlock_special(struct task_struct *t);
 static int rcu_preempted_readers_exp(struct rcu_node *rnp);
 
 /*
@@ -77,7 +76,7 @@ static int rcu_preempted_readers_exp(struct rcu_node *rnp);
  */
 static void __init rcu_bootup_announce(void)
 {
-        printk(KERN_INFO "Preemptable hierarchical RCU implementation.\n");
+        printk(KERN_INFO "Preemptible hierarchical RCU implementation.\n");
         rcu_bootup_announce_oddness();
 }
 
@@ -110,7 +109,7 @@ void rcu_force_quiescent_state(void)
 EXPORT_SYMBOL_GPL(rcu_force_quiescent_state);
 
 /*
- * Record a preemptable-RCU quiescent state for the specified CPU.  Note
+ * Record a preemptible-RCU quiescent state for the specified CPU.  Note
  * that this just means that the task currently running on the CPU is
  * not in a quiescent state.  There might be any number of tasks blocked
  * while in an RCU read-side critical section.
@@ -133,12 +132,12 @@ static void rcu_preempt_qs(int cpu)
  * We have entered the scheduler, and the current task might soon be
  * context-switched away from.  If this task is in an RCU read-side
  * critical section, we will no longer be able to rely on the CPU to
- * record that fact, so we enqueue the task on the appropriate entry
- * of the blocked_tasks[] array.  The task will dequeue itself when
- * it exits the outermost enclosing RCU read-side critical section.
- * Therefore, the current grace period cannot be permitted to complete
- * until the blocked_tasks[] entry indexed by the low-order bit of
- * rnp->gpnum empties.
+ * record that fact, so we enqueue the task on the blkd_tasks list.
+ * The task will dequeue itself when it exits the outermost enclosing
+ * RCU read-side critical section.  Therefore, the current grace period
+ * cannot be permitted to complete until the blkd_tasks list entries
+ * predating the current grace period drain, in other words, until
+ * rnp->gp_tasks becomes NULL.
  *
  * Caller must disable preemption.
  */
@@ -146,15 +145,14 @@ static void rcu_preempt_note_context_switch(int cpu)
 {
         struct task_struct *t = current;
         unsigned long flags;
-        int phase;
         struct rcu_data *rdp;
         struct rcu_node *rnp;
 
-        if (t->rcu_read_lock_nesting &&
+        if (t->rcu_read_lock_nesting > 0 &&
             (t->rcu_read_unlock_special & RCU_READ_UNLOCK_BLOCKED) == 0) {
 
                 /* Possibly blocking in an RCU read-side critical section. */
-                rdp = rcu_preempt_state.rda[cpu];
+                rdp = per_cpu_ptr(rcu_preempt_state.rda, cpu);
                 rnp = rdp->mynode;
                 raw_spin_lock_irqsave(&rnp->lock, flags);
                 t->rcu_read_unlock_special |= RCU_READ_UNLOCK_BLOCKED;
@@ -168,16 +166,39 @@ static void rcu_preempt_note_context_switch(int cpu)
                  * (i.e., this CPU has not yet passed through a quiescent
                  * state for the current grace period), then as long
                  * as that task remains queued, the current grace period
-                 * cannot end.
+                 * cannot end.  Note that there is some uncertainty as
+                 * to exactly when the current grace period started.
+                 * We take a conservative approach, which can result
+                 * in unnecessarily waiting on tasks that started very
+                 * slightly after the current grace period began.  C'est
+                 * la vie!!!
                  *
                  * But first, note that the current CPU must still be
                  * on line!
                  */
                 WARN_ON_ONCE((rdp->grpmask & rnp->qsmaskinit) == 0);
                 WARN_ON_ONCE(!list_empty(&t->rcu_node_entry));
-                phase = (rnp->gpnum + !(rnp->qsmask & rdp->grpmask)) & 0x1;
-                list_add(&t->rcu_node_entry, &rnp->blocked_tasks[phase]);
+                if ((rnp->qsmask & rdp->grpmask) && rnp->gp_tasks != NULL) {
+                        list_add(&t->rcu_node_entry, rnp->gp_tasks->prev);
+                        rnp->gp_tasks = &t->rcu_node_entry;
+#ifdef CONFIG_RCU_BOOST
+                        if (rnp->boost_tasks != NULL)
+                                rnp->boost_tasks = rnp->gp_tasks;
+#endif /* #ifdef CONFIG_RCU_BOOST */
+                } else {
+                        list_add(&t->rcu_node_entry, &rnp->blkd_tasks);
+                        if (rnp->qsmask & rdp->grpmask)
+                                rnp->gp_tasks = &t->rcu_node_entry;
+                }
                 raw_spin_unlock_irqrestore(&rnp->lock, flags);
+        } else if (t->rcu_read_lock_nesting < 0 &&
+                   t->rcu_read_unlock_special) {
+
+                /*
+                 * Complete exit from RCU read-side critical section on
+                 * behalf of preempted instance of __rcu_read_unlock().
+                 */
+                rcu_read_unlock_special(t);
         }
 
         /*
@@ -195,13 +216,13 @@ static void rcu_preempt_note_context_switch(int cpu)
 }
 
 /*
- * Tree-preemptable RCU implementation for rcu_read_lock().
+ * Tree-preemptible RCU implementation for rcu_read_lock().
  * Just increment ->rcu_read_lock_nesting, shared state will be updated
  * if we block.
  */
 void __rcu_read_lock(void)
 {
-        ACCESS_ONCE(current->rcu_read_lock_nesting)++;
+        current->rcu_read_lock_nesting++;
         barrier();  /* needed if we ever invoke rcu_read_lock in rcutree.c */
 }
 EXPORT_SYMBOL_GPL(__rcu_read_lock);
@@ -211,12 +232,9 @@ EXPORT_SYMBOL_GPL(__rcu_read_lock);
  * for the specified rcu_node structure.  If the caller needs a reliable
  * answer, it must hold the rcu_node's ->lock.
  */
-static int rcu_preempted_readers(struct rcu_node *rnp)
+static int rcu_preempt_blocked_readers_cgp(struct rcu_node *rnp)
 {
-        int phase = rnp->gpnum & 0x1;
-
-        return !list_empty(&rnp->blocked_tasks[phase]) ||
-               !list_empty(&rnp->blocked_tasks[phase + 2]);
+        return rnp->gp_tasks != NULL;
 }
 
 /*
@@ -232,7 +250,7 @@ static void rcu_report_unblock_qs_rnp(struct rcu_node *rnp, unsigned long flags)
         unsigned long mask;
         struct rcu_node *rnp_p;
 
-        if (rnp->qsmask != 0 || rcu_preempted_readers(rnp)) {
+        if (rnp->qsmask != 0 || rcu_preempt_blocked_readers_cgp(rnp)) {
                 raw_spin_unlock_irqrestore(&rnp->lock, flags);
                 return;  /* Still need more quiescent states! */
         }
@@ -256,15 +274,31 @@ static void rcu_report_unblock_qs_rnp(struct rcu_node *rnp, unsigned long flags)
 }
 
 /*
+ * Advance a ->blkd_tasks-list pointer to the next entry, instead
+ * returning NULL if at the end of the list.
+ */
+static struct list_head *rcu_next_node_entry(struct task_struct *t,
+                                             struct rcu_node *rnp)
+{
+        struct list_head *np;
+
+        np = t->rcu_node_entry.next;
+        if (np == &rnp->blkd_tasks)
+                np = NULL;
+        return np;
+}
+
+/*
  * Handle special cases during rcu_read_unlock(), such as needing to
  * notify RCU core processing or task having blocked during the RCU
  * read-side critical section.
  */
-static void rcu_read_unlock_special(struct task_struct *t)
+static noinline void rcu_read_unlock_special(struct task_struct *t)
 {
         int empty;
         int empty_exp;
         unsigned long flags;
+        struct list_head *np;
         struct rcu_node *rnp;
         int special;
 
@@ -284,7 +318,7 @@ static void rcu_read_unlock_special(struct task_struct *t)
         }
 
         /* Hardware IRQ handlers cannot block. */
-        if (in_irq()) {
+        if (in_irq() || in_serving_softirq()) {
                 local_irq_restore(flags);
                 return;
         }
@@ -305,10 +339,24 @@ static void rcu_read_unlock_special(struct task_struct *t)
                                 break;
                         raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */
                 }
-                empty = !rcu_preempted_readers(rnp);
+                empty = !rcu_preempt_blocked_readers_cgp(rnp);
                 empty_exp = !rcu_preempted_readers_exp(rnp);
                 smp_mb(); /* ensure expedited fastpath sees end of RCU c-s. */
+                np = rcu_next_node_entry(t, rnp);
                 list_del_init(&t->rcu_node_entry);
+                if (&t->rcu_node_entry == rnp->gp_tasks)
+                        rnp->gp_tasks = np;
+                if (&t->rcu_node_entry == rnp->exp_tasks)
+                        rnp->exp_tasks = np;
+#ifdef CONFIG_RCU_BOOST
+                if (&t->rcu_node_entry == rnp->boost_tasks)
+                        rnp->boost_tasks = np;
+                /* Snapshot and clear ->rcu_boosted with rcu_node lock held. */
+                if (t->rcu_boosted) {
+                        special |= RCU_READ_UNLOCK_BOOSTED;
+                        t->rcu_boosted = 0;
+                }
+#endif /* #ifdef CONFIG_RCU_BOOST */
                 t->rcu_blocked_node = NULL;
 
                 /*
@@ -321,6 +369,14 @@ static void rcu_read_unlock_special(struct task_struct *t)
                 else
                         rcu_report_unblock_qs_rnp(rnp, flags);
 
+#ifdef CONFIG_RCU_BOOST
+                /* Unboost if we were boosted. */
+                if (special & RCU_READ_UNLOCK_BOOSTED) {
+                        rt_mutex_unlock(t->rcu_boost_mutex);
+                        t->rcu_boost_mutex = NULL;
+                }
+#endif /* #ifdef CONFIG_RCU_BOOST */
+
                 /*
                  * If this was the last task on the expedited lists,
                  * then we need to report up the rcu_node hierarchy.
@@ -333,7 +389,7 @@ static void rcu_read_unlock_special(struct task_struct *t)
 }
 
 /*
- * Tree-preemptable RCU implementation for rcu_read_unlock().
+ * Tree-preemptible RCU implementation for rcu_read_unlock().
  * Decrement ->rcu_read_lock_nesting.  If the result is zero (outermost
  * rcu_read_unlock()) and ->rcu_read_unlock_special is non-zero, then
  * invoke rcu_read_unlock_special() to clean up after a context switch
@@ -344,17 +400,26 @@ void __rcu_read_unlock(void)
         struct task_struct *t = current;
 
         barrier();  /* needed if we ever invoke rcu_read_unlock in rcutree.c */
-        if (--ACCESS_ONCE(t->rcu_read_lock_nesting) == 0 &&
-            unlikely(ACCESS_ONCE(t->rcu_read_unlock_special)))
-                rcu_read_unlock_special(t);
+        if (t->rcu_read_lock_nesting != 1)
+                --t->rcu_read_lock_nesting;
+        else {
+                t->rcu_read_lock_nesting = INT_MIN;
+                barrier();  /* assign before ->rcu_read_unlock_special load */
+                if (unlikely(ACCESS_ONCE(t->rcu_read_unlock_special)))
+                        rcu_read_unlock_special(t);
+                barrier();  /* ->rcu_read_unlock_special load before assign */
+                t->rcu_read_lock_nesting = 0;
+        }
 #ifdef CONFIG_PROVE_LOCKING
-        WARN_ON_ONCE(ACCESS_ONCE(t->rcu_read_lock_nesting) < 0);
+        {
+                int rrln = ACCESS_ONCE(t->rcu_read_lock_nesting);
+
+                WARN_ON_ONCE(rrln < 0 && rrln > INT_MIN / 2);
+        }
 #endif /* #ifdef CONFIG_PROVE_LOCKING */
 }
 EXPORT_SYMBOL_GPL(__rcu_read_unlock);
 
-#ifdef CONFIG_RCU_CPU_STALL_DETECTOR
-
 #ifdef CONFIG_RCU_CPU_STALL_VERBOSE
 
 /*
@@ -364,18 +429,16 @@ EXPORT_SYMBOL_GPL(__rcu_read_unlock);
 static void rcu_print_detail_task_stall_rnp(struct rcu_node *rnp)
 {
         unsigned long flags;
-        struct list_head *lp;
-        int phase;
         struct task_struct *t;
 
-        if (rcu_preempted_readers(rnp)) {
-                raw_spin_lock_irqsave(&rnp->lock, flags);
-                phase = rnp->gpnum & 0x1;
-                lp = &rnp->blocked_tasks[phase];
-                list_for_each_entry(t, lp, rcu_node_entry)
-                        sched_show_task(t);
-                raw_spin_unlock_irqrestore(&rnp->lock, flags);
-        }
+        if (!rcu_preempt_blocked_readers_cgp(rnp))
+                return;
+        raw_spin_lock_irqsave(&rnp->lock, flags);
+        t = list_entry(rnp->gp_tasks,
+                       struct task_struct, rcu_node_entry);
+        list_for_each_entry_continue(t, &rnp->blkd_tasks, rcu_node_entry)
+                sched_show_task(t);
+        raw_spin_unlock_irqrestore(&rnp->lock, flags);
 }
 
 /*
@@ -405,19 +468,25 @@ static void rcu_print_detail_task_stall(struct rcu_state *rsp)
  */
 static void rcu_print_task_stall(struct rcu_node *rnp)
 {
-        struct list_head *lp;
-        int phase;
         struct task_struct *t;
 
-        if (rcu_preempted_readers(rnp)) {
-                phase = rnp->gpnum & 0x1;
-                lp = &rnp->blocked_tasks[phase];
-                list_for_each_entry(t, lp, rcu_node_entry)
-                        printk(" P%d", t->pid);
-        }
+        if (!rcu_preempt_blocked_readers_cgp(rnp))
+                return;
+        t = list_entry(rnp->gp_tasks,
+                       struct task_struct, rcu_node_entry);
+        list_for_each_entry_continue(t, &rnp->blkd_tasks, rcu_node_entry)
+                printk(" P%d", t->pid);
 }
 
-#endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
+/*
+ * Suppress preemptible RCU's CPU stall warnings by pushing the
+ * time of the next stall-warning message comfortably far into the
+ * future.
+ */
+static void rcu_preempt_stall_reset(void)
+{
+        rcu_preempt_state.jiffies_stall = jiffies + ULONG_MAX / 2;
+}
 
 /*
  * Check that the list of blocked tasks for the newly completed grace
@@ -425,10 +494,15 @@ static void rcu_print_task_stall(struct rcu_node *rnp)
  * period that still has RCU readers blocked!  This function must be
  * invoked -before- updating this rnp's ->gpnum, and the rnp's ->lock
  * must be held by the caller.
+ *
+ * Also, if there are blocked tasks on the list, they automatically
+ * block the newly created grace period, so set up ->gp_tasks accordingly.
  */
 static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp)
 {
-        WARN_ON_ONCE(rcu_preempted_readers(rnp));
+        WARN_ON_ONCE(rcu_preempt_blocked_readers_cgp(rnp));
+        if (!list_empty(&rnp->blkd_tasks))
+                rnp->gp_tasks = rnp->blkd_tasks.next;
         WARN_ON_ONCE(rnp->qsmask);
 }
 
@@ -452,50 +526,68 @@ static int rcu_preempt_offline_tasks(struct rcu_state *rsp,
                                      struct rcu_node *rnp,
                                      struct rcu_data *rdp)
 {
-        int i;
         struct list_head *lp;
         struct list_head *lp_root;
         int retval = 0;
         struct rcu_node *rnp_root = rcu_get_root(rsp);
-        struct task_struct *tp;
+        struct task_struct *t;
 
         if (rnp == rnp_root) {
                 WARN_ONCE(1, "Last CPU thought to be offlined?");
                 return 0;  /* Shouldn't happen: at least one CPU online. */
         }
-        WARN_ON_ONCE(rnp != rdp->mynode &&
-                     (!list_empty(&rnp->blocked_tasks[0]) ||
-                      !list_empty(&rnp->blocked_tasks[1]) ||
-                      !list_empty(&rnp->blocked_tasks[2]) ||
-                      !list_empty(&rnp->blocked_tasks[3])));
+
+        /* If we are on an internal node, complain bitterly. */
+        WARN_ON_ONCE(rnp != rdp->mynode);
 
         /*
-         * Move tasks up to root rcu_node.  Rely on the fact that the
-         * root rcu_node can be at most one ahead of the rest of the
-         * rcu_nodes in terms of gp_num value.  This fact allows us to
-         * move the blocked_tasks[] array directly, element by element.
+         * Move tasks up to root rcu_node.  Don't try to get fancy for
+         * this corner-case operation -- just put this node's tasks
+         * at the head of the root node's list, and update the root node's
+         * ->gp_tasks and ->exp_tasks pointers to those of this node's,
+         * if non-NULL.  This might result in waiting for more tasks than
+         * absolutely necessary, but this is a good performance/complexity
+         * tradeoff.
          */
-        if (rcu_preempted_readers(rnp))
+        if (rcu_preempt_blocked_readers_cgp(rnp))
                 retval |= RCU_OFL_TASKS_NORM_GP;
         if (rcu_preempted_readers_exp(rnp))
                 retval |= RCU_OFL_TASKS_EXP_GP;
-        for (i = 0; i < 4; i++) {
-                lp = &rnp->blocked_tasks[i];
-                lp_root = &rnp_root->blocked_tasks[i];
-                while (!list_empty(lp)) {
-                        tp = list_entry(lp->next, typeof(*tp), rcu_node_entry);
-                        raw_spin_lock(&rnp_root->lock); /* irqs already disabled */
-                        list_del(&tp->rcu_node_entry);
-                        tp->rcu_blocked_node = rnp_root;
-                        list_add(&tp->rcu_node_entry, lp_root);
-                        raw_spin_unlock(&rnp_root->lock); /* irqs remain disabled */
-                }
+        lp = &rnp->blkd_tasks;
+        lp_root = &rnp_root->blkd_tasks;
+        while (!list_empty(lp)) {
+                t = list_entry(lp->next, typeof(*t), rcu_node_entry);
+                raw_spin_lock(&rnp_root->lock); /* irqs already disabled */
+                list_del(&t->rcu_node_entry);
+                t->rcu_blocked_node = rnp_root;
+                list_add(&t->rcu_node_entry, lp_root);
+                if (&t->rcu_node_entry == rnp->gp_tasks)
+                        rnp_root->gp_tasks = rnp->gp_tasks;
+                if (&t->rcu_node_entry == rnp->exp_tasks)
+                        rnp_root->exp_tasks = rnp->exp_tasks;
+#ifdef CONFIG_RCU_BOOST
+                if (&t->rcu_node_entry == rnp->boost_tasks)
+                        rnp_root->boost_tasks = rnp->boost_tasks;
+#endif /* #ifdef CONFIG_RCU_BOOST */
+                raw_spin_unlock(&rnp_root->lock); /* irqs still disabled */
         }
+
+#ifdef CONFIG_RCU_BOOST
+        /* In case root is being boosted and leaf is not. */
+        raw_spin_lock(&rnp_root->lock); /* irqs already disabled */
+        if (rnp_root->boost_tasks != NULL &&
+            rnp_root->boost_tasks != rnp_root->gp_tasks)
+                rnp_root->boost_tasks = rnp_root->gp_tasks;
+        raw_spin_unlock(&rnp_root->lock); /* irqs still disabled */
+#endif /* #ifdef CONFIG_RCU_BOOST */
+
+        rnp->gp_tasks = NULL;
+        rnp->exp_tasks = NULL;
         return retval;
 }
 
 /*
- * Do CPU-offline processing for preemptable RCU.
+ * Do CPU-offline processing for preemptible RCU.
  */
 static void rcu_preempt_offline_cpu(int cpu)
 {
@@ -519,12 +611,13 @@ static void rcu_preempt_check_callbacks(int cpu)
                 rcu_preempt_qs(cpu);
                 return;
         }
-        if (per_cpu(rcu_preempt_data, cpu).qs_pending)
+        if (t->rcu_read_lock_nesting > 0 &&
+            per_cpu(rcu_preempt_data, cpu).qs_pending)
                 t->rcu_read_unlock_special |= RCU_READ_UNLOCK_NEED_QS;
 }
 
 /*
- * Process callbacks for preemptable RCU.
+ * Process callbacks for preemptible RCU.
  */
 static void rcu_preempt_process_callbacks(void)
 {
@@ -532,8 +625,17 @@ static void rcu_preempt_process_callbacks(void)
                                 &__get_cpu_var(rcu_preempt_data));
 }
 
+#ifdef CONFIG_RCU_BOOST
+
+static void rcu_preempt_do_callbacks(void)
+{
+        rcu_do_batch(&rcu_preempt_state, &__get_cpu_var(rcu_preempt_data));
+}
+
+#endif /* #ifdef CONFIG_RCU_BOOST */
+
 /*
- * Queue a preemptable-RCU callback for invocation after a grace period.
+ * Queue a preemptible-RCU callback for invocation after a grace period.
  */
 void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu))
 {
@@ -546,9 +648,11 @@ EXPORT_SYMBOL_GPL(call_rcu);
  *
  * Control will return to the caller some time after a full grace
  * period has elapsed, in other words after all currently executing RCU
- * read-side critical sections have completed.  RCU read-side critical
- * sections are delimited by rcu_read_lock() and rcu_read_unlock(),
- * and may be nested.
+ * read-side critical sections have completed.  Note, however, that
+ * upon return from synchronize_rcu(), the caller might well be executing
+ * concurrently with new RCU read-side critical sections that began while
+ * synchronize_rcu() was waiting.  RCU read-side critical sections are
+ * delimited by rcu_read_lock() and rcu_read_unlock(), and may be nested.
  */
 void synchronize_rcu(void)
 {
@@ -579,8 +683,7 @@ static DEFINE_MUTEX(sync_rcu_preempt_exp_mutex);
  */
 static int rcu_preempted_readers_exp(struct rcu_node *rnp)
 {
-        return !list_empty(&rnp->blocked_tasks[2]) ||
-               !list_empty(&rnp->blocked_tasks[3]);
+        return rnp->exp_tasks != NULL;
 }
 
 /*
@@ -615,9 +718,12 @@ static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp)
 
         raw_spin_lock_irqsave(&rnp->lock, flags);
         for (;;) {
-                if (!sync_rcu_preempt_exp_done(rnp))
+                if (!sync_rcu_preempt_exp_done(rnp)) {
+                        raw_spin_unlock_irqrestore(&rnp->lock, flags);
                         break;
+                }
                 if (rnp->parent == NULL) {
+                        raw_spin_unlock_irqrestore(&rnp->lock, flags);
                         wake_up(&sync_rcu_preempt_exp_wq);
                         break;
                 }
@@ -627,7 +733,6 @@ static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp)
                 raw_spin_lock(&rnp->lock); /* irqs already disabled */
                 rnp->expmask &= ~mask;
         }
-        raw_spin_unlock_irqrestore(&rnp->lock, flags);
 }
 
 /*
@@ -640,13 +745,17 @@ static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp)
 static void
 sync_rcu_preempt_exp_init(struct rcu_state *rsp, struct rcu_node *rnp)
 {
-        int must_wait;
+        unsigned long flags;
+        int must_wait = 0;
 
-        raw_spin_lock(&rnp->lock); /* irqs already disabled */
-        list_splice_init(&rnp->blocked_tasks[0], &rnp->blocked_tasks[2]);
-        list_splice_init(&rnp->blocked_tasks[1], &rnp->blocked_tasks[3]);
-        must_wait = rcu_preempted_readers_exp(rnp);
-        raw_spin_unlock(&rnp->lock); /* irqs remain disabled */
+        raw_spin_lock_irqsave(&rnp->lock, flags);
+        if (list_empty(&rnp->blkd_tasks))
+                raw_spin_unlock_irqrestore(&rnp->lock, flags);
+        else {
+                rnp->exp_tasks = rnp->blkd_tasks.next;
+                rcu_initiate_boost(rnp, flags);  /* releases rnp->lock */
+                must_wait = 1;
+        }
         if (!must_wait)
                 rcu_report_exp_rnp(rsp, rnp);
 }
@@ -654,9 +763,7 @@ sync_rcu_preempt_exp_init(struct rcu_state *rsp, struct rcu_node *rnp)
 /*
  * Wait for an rcu-preempt grace period, but expedite it.  The basic idea
  * is to invoke synchronize_sched_expedited() to push all the tasks to
- * the ->blocked_tasks[] lists, move all entries from the first set of
- * ->blocked_tasks[] lists to the second set, and finally wait for this
- * second set to drain.
+ * the ->blkd_tasks lists and wait for this list to drain.
  */
 void synchronize_rcu_expedited(void)
 {
@@ -688,7 +795,7 @@ void synchronize_rcu_expedited(void)
         if ((ACCESS_ONCE(sync_rcu_preempt_exp_count) - snap) > 0)
                 goto unlock_mb_ret; /* Others did our work for us. */
 
-        /* force all RCU readers onto blocked_tasks[]. */
+        /* force all RCU readers onto ->blkd_tasks lists. */
         synchronize_sched_expedited();
 
         raw_spin_lock_irqsave(&rsp->onofflock, flags);
@@ -700,7 +807,7 @@ void synchronize_rcu_expedited(void)
                 raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */
         }
 
-        /* Snapshot current state of ->blocked_tasks[] lists. */
+        /* Snapshot current state of ->blkd_tasks lists. */
         rcu_for_each_leaf_node(rsp, rnp)
                 sync_rcu_preempt_exp_init(rsp, rnp);
         if (NUM_RCU_NODES > 1)
@@ -708,7 +815,7 @@ void synchronize_rcu_expedited(void)
 
         raw_spin_unlock_irqrestore(&rsp->onofflock, flags);
 
-        /* Wait for snapshotted ->blocked_tasks[] lists to drain. */
+        /* Wait for snapshotted ->blkd_tasks lists to drain. */
         rnp = rcu_get_root(rsp);
         wait_event(sync_rcu_preempt_exp_wq,
                    sync_rcu_preempt_exp_done(rnp));
@@ -724,7 +831,7 @@ mb_ret:
 EXPORT_SYMBOL_GPL(synchronize_rcu_expedited);
 
 /*
- * Check to see if there is any immediate preemptable-RCU-related work
+ * Check to see if there is any immediate preemptible-RCU-related work
  * to be done.
  */
 static int rcu_preempt_pending(int cpu)
@@ -734,7 +841,7 @@ static int rcu_preempt_pending(int cpu)
 }
 
 /*
- * Does preemptable RCU need the CPU to stay out of dynticks mode?
+ * Does preemptible RCU need the CPU to stay out of dynticks mode?
  */
 static int rcu_preempt_needs_cpu(int cpu)
 {
@@ -751,7 +858,7 @@ void rcu_barrier(void)
 EXPORT_SYMBOL_GPL(rcu_barrier);
 
 /*
- * Initialize preemptable RCU's per-CPU data.
+ * Initialize preemptible RCU's per-CPU data.
  */
 static void __cpuinit rcu_preempt_init_percpu_data(int cpu)
 {
@@ -759,23 +866,23 @@ static void __cpuinit rcu_preempt_init_percpu_data(int cpu)
 }
 
 /*
- * Move preemptable RCU's callbacks to ->orphan_cbs_list.
+ * Move preemptible RCU's callbacks from dying CPU to other online CPU.
  */
-static void rcu_preempt_send_cbs_to_orphanage(void)
+static void rcu_preempt_send_cbs_to_online(void)
 {
-        rcu_send_cbs_to_orphanage(&rcu_preempt_state);
+        rcu_send_cbs_to_online(&rcu_preempt_state);
 }
 
 /*
- * Initialize preemptable RCU's state structures.
+ * Initialize preemptible RCU's state structures.
  */
 static void __init __rcu_init_preempt(void)
 {
-        RCU_INIT_FLAVOR(&rcu_preempt_state, rcu_preempt_data);
+        rcu_init_one(&rcu_preempt_state, &rcu_preempt_data);
 }
 
 /*
- * Check for a task exiting while in a preemptable-RCU read-side
+ * Check for a task exiting while in a preemptible-RCU read-side
  * critical section, clean up if so.  No need to issue warnings,
  * as debug_check_no_locks_held() already does this if lockdep
  * is enabled.
@@ -787,11 +894,13 @@ void exit_rcu(void)
         if (t->rcu_read_lock_nesting == 0)
                 return;
         t->rcu_read_lock_nesting = 1;
-        rcu_read_unlock();
+        __rcu_read_unlock();
 }
 
 #else /* #ifdef CONFIG_TREE_PREEMPT_RCU */
 
+static struct rcu_state *rcu_state = &rcu_sched_state;
+
 /*
  * Tell them what RCU they are running.
  */
@@ -821,7 +930,7 @@ void rcu_force_quiescent_state(void)
 EXPORT_SYMBOL_GPL(rcu_force_quiescent_state);
 
 /*
- * Because preemptable RCU does not exist, we never have to check for
+ * Because preemptible RCU does not exist, we never have to check for
  * CPUs being in quiescent states.
  */
 static void rcu_preempt_note_context_switch(int cpu)
@@ -829,10 +938,10 @@ static void rcu_preempt_note_context_switch(int cpu)
 }
 
 /*
- * Because preemptable RCU does not exist, there are never any preempted
+ * Because preemptible RCU does not exist, there are never any preempted
  * RCU readers.
  */
-static int rcu_preempted_readers(struct rcu_node *rnp)
+static int rcu_preempt_blocked_readers_cgp(struct rcu_node *rnp)
 {
         return 0;
 }
@@ -847,10 +956,8 @@ static void rcu_report_unblock_qs_rnp(struct rcu_node *rnp, unsigned long flags)
 
 #endif /* #ifdef CONFIG_HOTPLUG_CPU */
 
-#ifdef CONFIG_RCU_CPU_STALL_DETECTOR
-
 /*
- * Because preemptable RCU does not exist, we never have to check for
+ * Because preemptible RCU does not exist, we never have to check for
  * tasks blocked within RCU read-side critical sections.
  */
 static void rcu_print_detail_task_stall(struct rcu_state *rsp)
@@ -858,17 +965,23 @@ static void rcu_print_detail_task_stall(struct rcu_state *rsp)
 }
 
 /*
- * Because preemptable RCU does not exist, we never have to check for
+ * Because preemptible RCU does not exist, we never have to check for
  * tasks blocked within RCU read-side critical sections.
  */
 static void rcu_print_task_stall(struct rcu_node *rnp)
 {
 }
 
-#endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
+/*
+ * Because preemptible RCU does not exist, there is no need to suppress
+ * its CPU stall warnings.
+ */
+static void rcu_preempt_stall_reset(void)
+{
+}
 
 /*
- * Because there is no preemptable RCU, there can be no readers blocked,
+ * Because there is no preemptible RCU, there can be no readers blocked,
  * so there is no need to check for blocked tasks.  So check only for
  * bogus qsmask values.
  */
@@ -880,7 +993,7 @@ static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp)
 #ifdef CONFIG_HOTPLUG_CPU
 
 /*
- * Because preemptable RCU does not exist, it never needs to migrate
+ * Because preemptible RCU does not exist, it never needs to migrate
  * tasks that were blocked within RCU read-side critical sections, and
  * such non-existent tasks cannot possibly have been blocking the current
  * grace period.
@@ -893,7 +1006,7 @@ static int rcu_preempt_offline_tasks(struct rcu_state *rsp,
 }
 
 /*
- * Because preemptable RCU does not exist, it never needs CPU-offline
+ * Because preemptible RCU does not exist, it never needs CPU-offline
  * processing.
  */
 static void rcu_preempt_offline_cpu(int cpu)
@@ -903,7 +1016,7 @@ static void rcu_preempt_offline_cpu(int cpu)
 #endif /* #ifdef CONFIG_HOTPLUG_CPU */
 
 /*
- * Because preemptable RCU does not exist, it never has any callbacks
+ * Because preemptible RCU does not exist, it never has any callbacks
  * to check.
  */
 static void rcu_preempt_check_callbacks(int cpu)
@@ -911,7 +1024,7 @@ static void rcu_preempt_check_callbacks(int cpu)
 }
 
 /*
- * Because preemptable RCU does not exist, it never has any callbacks
+ * Because preemptible RCU does not exist, it never has any callbacks
  * to process.
  */
 static void rcu_preempt_process_callbacks(void)
@@ -919,17 +1032,8 @@ static void rcu_preempt_process_callbacks(void)
 }
 
 /*
- * In classic RCU, call_rcu() is just call_rcu_sched().
- */
-void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu))
-{
-        call_rcu_sched(head, func);
-}
-EXPORT_SYMBOL_GPL(call_rcu);
-
-/*
  * Wait for an rcu-preempt grace period, but make it happen quickly.
- * But because preemptable RCU does not exist, map to rcu-sched.
+ * But because preemptible RCU does not exist, map to rcu-sched.
  */
 void synchronize_rcu_expedited(void)
 {
@@ -940,7 +1044,7 @@ EXPORT_SYMBOL_GPL(synchronize_rcu_expedited);
 #ifdef CONFIG_HOTPLUG_CPU
 
 /*
- * Because preemptable RCU does not exist, there is never any need to
+ * Because preemptible RCU does not exist, there is never any need to
  * report on tasks preempted in RCU read-side critical sections during
  * expedited RCU grace periods.
  */
@@ -952,7 +1056,7 @@ static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp)
 #endif /* #ifdef CONFIG_HOTPLUG_CPU */
 
 /*
- * Because preemptable RCU does not exist, it never has any work to do.
+ * Because preemptible RCU does not exist, it never has any work to do.
  */
 static int rcu_preempt_pending(int cpu)
 {
@@ -960,7 +1064,7 @@ static int rcu_preempt_pending(int cpu)
 }
 
 /*
- * Because preemptable RCU does not exist, it never needs any CPU.
+ * Because preemptible RCU does not exist, it never needs any CPU.
  */
 static int rcu_preempt_needs_cpu(int cpu)
 {
@@ -968,7 +1072,7 @@ static int rcu_preempt_needs_cpu(int cpu)
 }
 
 /*
- * Because preemptable RCU does not exist, rcu_barrier() is just
+ * Because preemptible RCU does not exist, rcu_barrier() is just
  * another name for rcu_barrier_sched().
  */
 void rcu_barrier(void)
@@ -978,7 +1082,7 @@ void rcu_barrier(void)
 EXPORT_SYMBOL_GPL(rcu_barrier);
 
 /*
- * Because preemptable RCU does not exist, there is no per-CPU
+ * Because preemptible RCU does not exist, there is no per-CPU
  * data to initialize.
  */
 static void __cpuinit rcu_preempt_init_percpu_data(int cpu)
@@ -986,14 +1090,14 @@ static void __cpuinit rcu_preempt_init_percpu_data(int cpu)
 }
 
 /*
- * Because there is no preemptable RCU, there are no callbacks to move.
+ * Because there is no preemptible RCU, there are no callbacks to move.
  */
-static void rcu_preempt_send_cbs_to_orphanage(void)
+static void rcu_preempt_send_cbs_to_online(void)
 {
 }
 
 /*
- * Because preemptable RCU does not exist, it need not be initialized.
+ * Because preemptible RCU does not exist, it need not be initialized.
  */
 static void __init __rcu_init_preempt(void)
 {
@@ -1001,6 +1105,791 @@ static void __init __rcu_init_preempt(void)
 
 #endif /* #else #ifdef CONFIG_TREE_PREEMPT_RCU */
 
+#ifdef CONFIG_RCU_BOOST
+
+#include "rtmutex_common.h"
+
+#ifdef CONFIG_RCU_TRACE
+
+static void rcu_initiate_boost_trace(struct rcu_node *rnp)
+{
+        if (list_empty(&rnp->blkd_tasks))
+                rnp->n_balk_blkd_tasks++;
+        else if (rnp->exp_tasks == NULL && rnp->gp_tasks == NULL)
+                rnp->n_balk_exp_gp_tasks++;
+        else if (rnp->gp_tasks != NULL && rnp->boost_tasks != NULL)
+                rnp->n_balk_boost_tasks++;
+        else if (rnp->gp_tasks != NULL && rnp->qsmask != 0)
+                rnp->n_balk_notblocked++;
+        else if (rnp->gp_tasks != NULL &&
+                 ULONG_CMP_LT(jiffies, rnp->boost_time))
+                rnp->n_balk_notyet++;
+        else
+                rnp->n_balk_nos++;
+}
+
+#else /* #ifdef CONFIG_RCU_TRACE */
+
+static void rcu_initiate_boost_trace(struct rcu_node *rnp)
+{
+}
+
+#endif /* #else #ifdef CONFIG_RCU_TRACE */
+
+/*
+ * Carry out RCU priority boosting on the task indicated by ->exp_tasks
+ * or ->boost_tasks, advancing the pointer to the next task in the
+ * ->blkd_tasks list.
+ *
+ * Note that irqs must be enabled: boosting the task can block.
+ * Returns 1 if there are more tasks needing to be boosted.
+ */
+static int rcu_boost(struct rcu_node *rnp)
+{
+        unsigned long flags;
+        struct rt_mutex mtx;
+        struct task_struct *t;
+        struct list_head *tb;
+
+        if (rnp->exp_tasks == NULL && rnp->boost_tasks == NULL)
+                return 0;  /* Nothing left to boost. */
+
+        raw_spin_lock_irqsave(&rnp->lock, flags);
+
+        /*
+         * Recheck under the lock: all tasks in need of boosting
+         * might exit their RCU read-side critical sections on their own.
+         */
+        if (rnp->exp_tasks == NULL && rnp->boost_tasks == NULL) {
+                raw_spin_unlock_irqrestore(&rnp->lock, flags);
+                return 0;
+        }
+
+        /*
+         * Preferentially boost tasks blocking expedited grace periods.
+         * This cannot starve the normal grace periods because a second
+         * expedited grace period must boost all blocked tasks, including
+         * those blocking the pre-existing normal grace period.
+         */
+        if (rnp->exp_tasks != NULL) {
+                tb = rnp->exp_tasks;
+                rnp->n_exp_boosts++;
+        } else {
+                tb = rnp->boost_tasks;
+                rnp->n_normal_boosts++;
+        }
+        rnp->n_tasks_boosted++;
+
+        /*
+         * We boost task t by manufacturing an rt_mutex that appears to
+         * be held by task t.  We leave a pointer to that rt_mutex where
+         * task t can find it, and task t will release the mutex when it
+         * exits its outermost RCU read-side critical section.  Then
+         * simply acquiring this artificial rt_mutex will boost task
+         * t's priority.  (Thanks to tglx for suggesting this approach!)
+         *
+         * Note that task t must acquire rnp->lock to remove itself from
+         * the ->blkd_tasks list, which it will do from exit() if from
+         * nowhere else.  We therefore are guaranteed that task t will
+         * stay around at least until we drop rnp->lock.  Note that
+         * rnp->lock also resolves races between our priority boosting
+         * and task t's exiting its outermost RCU read-side critical
+         * section.
+         */
+        t = container_of(tb, struct task_struct, rcu_node_entry);
+        rt_mutex_init_proxy_locked(&mtx, t);
+        t->rcu_boost_mutex = &mtx;
+        t->rcu_boosted = 1;
+        raw_spin_unlock_irqrestore(&rnp->lock, flags);
+        rt_mutex_lock(&mtx);  /* Side effect: boosts task t's priority. */
+        rt_mutex_unlock(&mtx);  /* Keep lockdep happy. */
+
+        return rnp->exp_tasks != NULL || rnp->boost_tasks != NULL;
+}
+
+/*
+ * Timer handler to initiate waking up of boost kthreads that
+ * have yielded the CPU due to excessive numbers of tasks to
+ * boost.  We wake up the per-rcu_node kthread, which in turn
+ * will wake up the booster kthread.
+ */
+static void rcu_boost_kthread_timer(unsigned long arg)
+{
+        invoke_rcu_node_kthread((struct rcu_node *)arg);
+}
+
+/*
+ * Priority-boosting kthread.  One per leaf rcu_node and one for the
+ * root rcu_node.
+ */
+static int rcu_boost_kthread(void *arg)
+{
+        struct rcu_node *rnp = (struct rcu_node *)arg;
+        int spincnt = 0;
+        int more2boost;
+
+        for (;;) {
+                rnp->boost_kthread_status = RCU_KTHREAD_WAITING;
+                rcu_wait(rnp->boost_tasks || rnp->exp_tasks);
+                rnp->boost_kthread_status = RCU_KTHREAD_RUNNING;
+                more2boost = rcu_boost(rnp);
+                if (more2boost)
+                        spincnt++;
+                else
+                        spincnt = 0;
+                if (spincnt > 10) {
+                        rcu_yield(rcu_boost_kthread_timer, (unsigned long)rnp);
+                        spincnt = 0;
+                }
+        }
+        /* NOTREACHED */
+        return 0;
+}
+
+/*
+ * Check to see if it is time to start boosting RCU readers that are
+ * blocking the current grace period, and, if so, tell the per-rcu_node
+ * kthread to start boosting them.  If there is an expedited grace
+ * period in progress, it is always time to boost.
+ *
+ * The caller must hold rnp->lock, which this function releases,
+ * but irqs remain disabled.  The ->boost_kthread_task is immortal,
+ * so we don't need to worry about it going away.
+ */
+static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags)
+{
+        struct task_struct *t;
+
+        if (!rcu_preempt_blocked_readers_cgp(rnp) && rnp->exp_tasks == NULL) {
+                rnp->n_balk_exp_gp_tasks++;
+                raw_spin_unlock_irqrestore(&rnp->lock, flags);
+                return;
+        }
+        if (rnp->exp_tasks != NULL ||
+            (rnp->gp_tasks != NULL &&
+             rnp->boost_tasks == NULL &&
+             rnp->qsmask == 0 &&
+             ULONG_CMP_GE(jiffies, rnp->boost_time))) {
+                if (rnp->exp_tasks == NULL)
+                        rnp->boost_tasks = rnp->gp_tasks;
+                raw_spin_unlock_irqrestore(&rnp->lock, flags);
+                t = rnp->boost_kthread_task;
+                if (t != NULL)
+                        wake_up_process(t);
+        } else {
+                rcu_initiate_boost_trace(rnp);
+                raw_spin_unlock_irqrestore(&rnp->lock, flags);
+        }
+}
+
+/*
+ * Wake up the per-CPU kthread to invoke RCU callbacks.
+ */
+static void invoke_rcu_callbacks_kthread(void)
+{
+        unsigned long flags;
+
+        local_irq_save(flags);
+        __this_cpu_write(rcu_cpu_has_work, 1);
+        if (__this_cpu_read(rcu_cpu_kthread_task) == NULL) {
+                local_irq_restore(flags);
+                return;
+        }
+        wake_up_process(__this_cpu_read(rcu_cpu_kthread_task));
+        local_irq_restore(flags);
+}
+
+/*
+ * Set the affinity of the boost kthread.  The CPU-hotplug locks are
+ * held, so no one should be messing with the existence of the boost
+ * kthread.
+ */
+static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp,
+                                          cpumask_var_t cm)
+{
+        struct task_struct *t;
+
+        t = rnp->boost_kthread_task;
+        if (t != NULL)
+                set_cpus_allowed_ptr(rnp->boost_kthread_task, cm);
+}
+
+#define RCU_BOOST_DELAY_JIFFIES DIV_ROUND_UP(CONFIG_RCU_BOOST_DELAY * HZ, 1000)
+
+/*
+ * Do priority-boost accounting for the start of a new grace period.
+ */
+static void rcu_preempt_boost_start_gp(struct rcu_node *rnp)
+{
+        rnp->boost_time = jiffies + RCU_BOOST_DELAY_JIFFIES;
+}
+
+/*
+ * Create an RCU-boost kthread for the specified node if one does not
+ * already exist.  We only create this kthread for preemptible RCU.
+ * Returns zero if all is well, a negated errno otherwise.
+ */
+static int __cpuinit rcu_spawn_one_boost_kthread(struct rcu_state *rsp,
+                                                 struct rcu_node *rnp,
+                                                 int rnp_index)
+{
+        unsigned long flags;
+        struct sched_param sp;
+        struct task_struct *t;
+
+        if (&rcu_preempt_state != rsp)
+                return 0;
+        rsp->boost = 1;
+        if (rnp->boost_kthread_task != NULL)
+                return 0;
+        t = kthread_create(rcu_boost_kthread, (void *)rnp,
+                           "rcub%d", rnp_index);
+        if (IS_ERR(t))
+                return PTR_ERR(t);
+        raw_spin_lock_irqsave(&rnp->lock, flags);
+        rnp->boost_kthread_task = t;
+        raw_spin_unlock_irqrestore(&rnp->lock, flags);
+        sp.sched_priority = RCU_KTHREAD_PRIO;
+        sched_setscheduler_nocheck(t, SCHED_FIFO, &sp);
+        wake_up_process(t); /* get to TASK_INTERRUPTIBLE quickly. */
+        return 0;
+}
+
+#ifdef CONFIG_HOTPLUG_CPU
+
+/*
+ * Stop the RCU's per-CPU kthread when its CPU goes offline,.
+ */
+static void rcu_stop_cpu_kthread(int cpu)
+{
+        struct task_struct *t;
+
+        /* Stop the CPU's kthread. */
+        t = per_cpu(rcu_cpu_kthread_task, cpu);
+        if (t != NULL) {
+                per_cpu(rcu_cpu_kthread_task, cpu) = NULL;
+                kthread_stop(t);
+        }
+}
+
+#endif /* #ifdef CONFIG_HOTPLUG_CPU */
+
+static void rcu_kthread_do_work(void)
+{
+        rcu_do_batch(&rcu_sched_state, &__get_cpu_var(rcu_sched_data));
+        rcu_do_batch(&rcu_bh_state, &__get_cpu_var(rcu_bh_data));
+        rcu_preempt_do_callbacks();
+}
+
+/*
+ * Wake up the specified per-rcu_node-structure kthread.
+ * Because the per-rcu_node kthreads are immortal, we don't need
+ * to do anything to keep them alive.
+ */
+static void invoke_rcu_node_kthread(struct rcu_node *rnp)
+{
+        struct task_struct *t;
+
+        t = rnp->node_kthread_task;
+        if (t != NULL)
+                wake_up_process(t);
+}
+
+/*
+ * Set the specified CPU's kthread to run RT or not, as specified by
+ * the to_rt argument.  The CPU-hotplug locks are held, so the task
+ * is not going away.
+ */
+static void rcu_cpu_kthread_setrt(int cpu, int to_rt)
+{
+        int policy;
+        struct sched_param sp;
+        struct task_struct *t;
+
+        t = per_cpu(rcu_cpu_kthread_task, cpu);
+        if (t == NULL)
+                return;
+        if (to_rt) {
+                policy = SCHED_FIFO;
+                sp.sched_priority = RCU_KTHREAD_PRIO;
+        } else {
+                policy = SCHED_NORMAL;
+                sp.sched_priority = 0;
+        }
+        sched_setscheduler_nocheck(t, policy, &sp);
+}
+
+/*
+ * Timer handler to initiate the waking up of per-CPU kthreads that
+ * have yielded the CPU due to excess numbers of RCU callbacks.
+ * We wake up the per-rcu_node kthread, which in turn will wake up
+ * the booster kthread.
+ */
+static void rcu_cpu_kthread_timer(unsigned long arg)
+{
+        struct rcu_data *rdp = per_cpu_ptr(rcu_state->rda, arg);
+        struct rcu_node *rnp = rdp->mynode;
+
+        atomic_or(rdp->grpmask, &rnp->wakemask);
+        invoke_rcu_node_kthread(rnp);
+}
+
+/*
+ * Drop to non-real-time priority and yield, but only after posting a
+ * timer that will cause us to regain our real-time priority if we
+ * remain preempted.  Either way, we restore our real-time priority
+ * before returning.
+ */
+static void rcu_yield(void (*f)(unsigned long), unsigned long arg)
+{
+        struct sched_param sp;
+        struct timer_list yield_timer;
+
+        setup_timer_on_stack(&yield_timer, f, arg);
+        mod_timer(&yield_timer, jiffies + 2);
+        sp.sched_priority = 0;
+        sched_setscheduler_nocheck(current, SCHED_NORMAL, &sp);
+        set_user_nice(current, 19);
+        schedule();
+        sp.sched_priority = RCU_KTHREAD_PRIO;
+        sched_setscheduler_nocheck(current, SCHED_FIFO, &sp);
+        del_timer(&yield_timer);
+}
+
+/*
+ * Handle cases where the rcu_cpu_kthread() ends up on the wrong CPU.
+ * This can happen while the corresponding CPU is either coming online
+ * or going offline.  We cannot wait until the CPU is fully online
+ * before starting the kthread, because the various notifier functions
+ * can wait for RCU grace periods.  So we park rcu_cpu_kthread() until
+ * the corresponding CPU is online.
+ *
+ * Return 1 if the kthread needs to stop, 0 otherwise.
+ *
+ * Caller must disable bh.  This function can momentarily enable it.
+ */
+static int rcu_cpu_kthread_should_stop(int cpu)
+{
+        while (cpu_is_offline(cpu) ||
+               !cpumask_equal(&current->cpus_allowed, cpumask_of(cpu)) ||
+               smp_processor_id() != cpu) {
+                if (kthread_should_stop())
+                        return 1;
+                per_cpu(rcu_cpu_kthread_status, cpu) = RCU_KTHREAD_OFFCPU;
+                per_cpu(rcu_cpu_kthread_cpu, cpu) = raw_smp_processor_id();
+                local_bh_enable();
+                schedule_timeout_uninterruptible(1);
+                if (!cpumask_equal(&current->cpus_allowed, cpumask_of(cpu)))
+                        set_cpus_allowed_ptr(current, cpumask_of(cpu));
+                local_bh_disable();
+        }
+        per_cpu(rcu_cpu_kthread_cpu, cpu) = cpu;
+        return 0;
+}
+
+/*
+ * Per-CPU kernel thread that invokes RCU callbacks.  This replaces the
+ * earlier RCU softirq.
+ */
+static int rcu_cpu_kthread(void *arg)
+{
+        int cpu = (int)(long)arg;
+        unsigned long flags;
+        int spincnt = 0;
+        unsigned int *statusp = &per_cpu(rcu_cpu_kthread_status, cpu);
+        char work;
+        char *workp = &per_cpu(rcu_cpu_has_work, cpu);
+
+        for (;;) {
+                *statusp = RCU_KTHREAD_WAITING;
+                rcu_wait(*workp != 0 || kthread_should_stop());
+                local_bh_disable();
+                if (rcu_cpu_kthread_should_stop(cpu)) {
+                        local_bh_enable();
+                        break;
+                }
+                *statusp = RCU_KTHREAD_RUNNING;
+                per_cpu(rcu_cpu_kthread_loops, cpu)++;
+                local_irq_save(flags);
+                work = *workp;
+                *workp = 0;
+                local_irq_restore(flags);
+                if (work)
+                        rcu_kthread_do_work();
+                local_bh_enable();
+                if (*workp != 0)
+                        spincnt++;
+                else
+                        spincnt = 0;
+                if (spincnt > 10) {
+                        *statusp = RCU_KTHREAD_YIELDING;
+                        rcu_yield(rcu_cpu_kthread_timer, (unsigned long)cpu);
+                        spincnt = 0;
+                }
+        }
+        *statusp = RCU_KTHREAD_STOPPED;
+        return 0;
+}
+
+/*
+ * Spawn a per-CPU kthread, setting up affinity and priority.
+ * Because the CPU hotplug lock is held, no other CPU will be attempting
+ * to manipulate rcu_cpu_kthread_task.  There might be another CPU
+ * attempting to access it during boot, but the locking in kthread_bind()
+ * will enforce sufficient ordering.
+ *
+ * Please note that we cannot simply refuse to wake up the per-CPU
+ * kthread because kthreads are created in TASK_UNINTERRUPTIBLE state,
+ * which can result in softlockup complaints if the task ends up being
+ * idle for more than a couple of minutes.
+ *
+ * However, please note also that we cannot bind the per-CPU kthread to its
+ * CPU until that CPU is fully online.  We also cannot wait until the
+ * CPU is fully online before we create its per-CPU kthread, as this would
+ * deadlock the system when CPU notifiers tried waiting for grace
+ * periods.  So we bind the per-CPU kthread to its CPU only if the CPU
+ * is online.  If its CPU is not yet fully online, then the code in
+ * rcu_cpu_kthread() will wait until it is fully online, and then do
+ * the binding.
+ */
+static int __cpuinit rcu_spawn_one_cpu_kthread(int cpu)
+{
+        struct sched_param sp;
+        struct task_struct *t;
+
+        if (!rcu_scheduler_fully_active ||
+            per_cpu(rcu_cpu_kthread_task, cpu) != NULL)
+                return 0;
+        t = kthread_create(rcu_cpu_kthread, (void *)(long)cpu, "rcuc%d", cpu);
+        if (IS_ERR(t))
+                return PTR_ERR(t);
+        if (cpu_online(cpu))
+                kthread_bind(t, cpu);
+        per_cpu(rcu_cpu_kthread_cpu, cpu) = cpu;
+        WARN_ON_ONCE(per_cpu(rcu_cpu_kthread_task, cpu) != NULL);
+        sp.sched_priority = RCU_KTHREAD_PRIO;
+        sched_setscheduler_nocheck(t, SCHED_FIFO, &sp);
+        per_cpu(rcu_cpu_kthread_task, cpu) = t;
+        wake_up_process(t); /* Get to TASK_INTERRUPTIBLE quickly. */
+        return 0;
+}
+
+/*
+ * Per-rcu_node kthread, which is in charge of waking up the per-CPU
+ * kthreads when needed.  We ignore requests to wake up kthreads
+ * for offline CPUs, which is OK because force_quiescent_state()
+ * takes care of this case.
+ */
+static int rcu_node_kthread(void *arg)
+{
+        int cpu;
+        unsigned long flags;
+        unsigned long mask;
+        struct rcu_node *rnp = (struct rcu_node *)arg;
+        struct sched_param sp;
+        struct task_struct *t;
+
+        for (;;) {
+                rnp->node_kthread_status = RCU_KTHREAD_WAITING;
+                rcu_wait(atomic_read(&rnp->wakemask) != 0);
+                rnp->node_kthread_status = RCU_KTHREAD_RUNNING;
+                raw_spin_lock_irqsave(&rnp->lock, flags);
+                mask = atomic_xchg(&rnp->wakemask, 0);
+                rcu_initiate_boost(rnp, flags); /* releases rnp->lock. */
+                for (cpu = rnp->grplo; cpu <= rnp->grphi; cpu++, mask >>= 1) {
+                        if ((mask & 0x1) == 0)
+                                continue;
+                        preempt_disable();
+                        t = per_cpu(rcu_cpu_kthread_task, cpu);
+                        if (!cpu_online(cpu) || t == NULL) {
+                                preempt_enable();
+                                continue;
+                        }
+                        per_cpu(rcu_cpu_has_work, cpu) = 1;
+                        sp.sched_priority = RCU_KTHREAD_PRIO;
+                        sched_setscheduler_nocheck(t, SCHED_FIFO, &sp);
+                        preempt_enable();
+                }
+        }
+        /* NOTREACHED */
+        rnp->node_kthread_status = RCU_KTHREAD_STOPPED;
+        return 0;
+}
+
+/*
+ * Set the per-rcu_node kthread's affinity to cover all CPUs that are
+ * served by the rcu_node in question.  The CPU hotplug lock is still
+ * held, so the value of rnp->qsmaskinit will be stable.
+ *
+ * We don't include outgoingcpu in the affinity set, use -1 if there is
+ * no outgoing CPU.  If there are no CPUs left in the affinity set,
+ * this function allows the kthread to execute on any CPU.
+ */
+static void rcu_node_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu)
+{
+        cpumask_var_t cm;
+        int cpu;
+        unsigned long mask = rnp->qsmaskinit;
+
+        if (rnp->node_kthread_task == NULL)
+                return;
+        if (!alloc_cpumask_var(&cm, GFP_KERNEL))
+                return;
+        cpumask_clear(cm);
+        for (cpu = rnp->grplo; cpu <= rnp->grphi; cpu++, mask >>= 1)
+                if ((mask & 0x1) && cpu != outgoingcpu)
+                        cpumask_set_cpu(cpu, cm);
+        if (cpumask_weight(cm) == 0) {
+                cpumask_setall(cm);
+                for (cpu = rnp->grplo; cpu <= rnp->grphi; cpu++)
+                        cpumask_clear_cpu(cpu, cm);
+                WARN_ON_ONCE(cpumask_weight(cm) == 0);
+        }
+        set_cpus_allowed_ptr(rnp->node_kthread_task, cm);
+        rcu_boost_kthread_setaffinity(rnp, cm);
+        free_cpumask_var(cm);
+}
+
+/*
+ * Spawn a per-rcu_node kthread, setting priority and affinity.
+ * Called during boot before online/offline can happen, or, if
+ * during runtime, with the main CPU-hotplug locks held.  So only
+ * one of these can be executing at a time.
+ */
+static int __cpuinit rcu_spawn_one_node_kthread(struct rcu_state *rsp,
+                                                struct rcu_node *rnp)
+{
+        unsigned long flags;
+        int rnp_index = rnp - &rsp->node[0];
+        struct sched_param sp;
+        struct task_struct *t;
+
+        if (!rcu_scheduler_fully_active ||
+            rnp->qsmaskinit == 0)
+                return 0;
+        if (rnp->node_kthread_task == NULL) {
+                t = kthread_create(rcu_node_kthread, (void *)rnp,
+                                   "rcun%d", rnp_index);
+                if (IS_ERR(t))
+                        return PTR_ERR(t);
+                raw_spin_lock_irqsave(&rnp->lock, flags);
+                rnp->node_kthread_task = t;
+                raw_spin_unlock_irqrestore(&rnp->lock, flags);
+                sp.sched_priority = 99;
+                sched_setscheduler_nocheck(t, SCHED_FIFO, &sp);
+                wake_up_process(t); /* get to TASK_INTERRUPTIBLE quickly. */
+        }
+        return rcu_spawn_one_boost_kthread(rsp, rnp, rnp_index);
+}
+
+/*
+ * Spawn all kthreads -- called as soon as the scheduler is running.
+ */
+static int __init rcu_spawn_kthreads(void)
+{
+        int cpu;
+        struct rcu_node *rnp;
+
+        rcu_scheduler_fully_active = 1;
+        for_each_possible_cpu(cpu) {
+                per_cpu(rcu_cpu_has_work, cpu) = 0;
+                if (cpu_online(cpu))
+                        (void)rcu_spawn_one_cpu_kthread(cpu);
+        }
+        rnp = rcu_get_root(rcu_state);
+        (void)rcu_spawn_one_node_kthread(rcu_state, rnp);
+        if (NUM_RCU_NODES > 1) {
+                rcu_for_each_leaf_node(rcu_state, rnp)
+                        (void)rcu_spawn_one_node_kthread(rcu_state, rnp);
+        }
+        return 0;
+}
+early_initcall(rcu_spawn_kthreads);
+
+static void __cpuinit rcu_prepare_kthreads(int cpu)
+{
+        struct rcu_data *rdp = per_cpu_ptr(rcu_state->rda, cpu);
+        struct rcu_node *rnp = rdp->mynode;
+
+        /* Fire up the incoming CPU's kthread and leaf rcu_node kthread. */
+        if (rcu_scheduler_fully_active) {
+                (void)rcu_spawn_one_cpu_kthread(cpu);
+                if (rnp->node_kthread_task == NULL)
+                        (void)rcu_spawn_one_node_kthread(rcu_state, rnp);
+        }
+}
+
+#else /* #ifdef CONFIG_RCU_BOOST */
+
+static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags)
+{
+        raw_spin_unlock_irqrestore(&rnp->lock, flags);
+}
+
+static void invoke_rcu_callbacks_kthread(void)
+{
+        WARN_ON_ONCE(1);
+}
+
+static void rcu_preempt_boost_start_gp(struct rcu_node *rnp)
+{
+}
+
+#ifdef CONFIG_HOTPLUG_CPU
+
+static void rcu_stop_cpu_kthread(int cpu)
+{
+}
+
+#endif /* #ifdef CONFIG_HOTPLUG_CPU */
+
+static void rcu_node_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu)
+{
+}
+
+static void rcu_cpu_kthread_setrt(int cpu, int to_rt)
+{
+}
+
+static int __init rcu_scheduler_really_started(void)
+{
+        rcu_scheduler_fully_active = 1;
+        return 0;
+}
+early_initcall(rcu_scheduler_really_started);
+
+static void __cpuinit rcu_prepare_kthreads(int cpu)
+{
+}
+
+#endif /* #else #ifdef CONFIG_RCU_BOOST */
+
+#ifndef CONFIG_SMP
+
+void synchronize_sched_expedited(void)
+{
+        cond_resched();
+}
+EXPORT_SYMBOL_GPL(synchronize_sched_expedited);
+
+#else /* #ifndef CONFIG_SMP */
+
+static atomic_t sync_sched_expedited_started = ATOMIC_INIT(0);
+static atomic_t sync_sched_expedited_done = ATOMIC_INIT(0);
+
+static int synchronize_sched_expedited_cpu_stop(void *data)
+{
+        /*
+         * There must be a full memory barrier on each affected CPU
+         * between the time that try_stop_cpus() is called and the
+         * time that it returns.
+         *
+         * In the current initial implementation of cpu_stop, the
+         * above condition is already met when the control reaches
+         * this point and the following smp_mb() is not strictly
+         * necessary.  Do smp_mb() anyway for documentation and
+         * robustness against future implementation changes.
+         */
+        smp_mb(); /* See above comment block. */
+        return 0;
+}
+
+/*
+ * Wait for an rcu-sched grace period to elapse, but use "big hammer"
+ * approach to force grace period to end quickly.  This consumes
+ * significant time on all CPUs, and is thus not recommended for
+ * any sort of common-case code.
+ *
+ * Note that it is illegal to call this function while holding any
+ * lock that is acquired by a CPU-hotplug notifier.  Failing to
+ * observe this restriction will result in deadlock.
+ *
+ * This implementation can be thought of as an application of ticket
+ * locking to RCU, with sync_sched_expedited_started and
+ * sync_sched_expedited_done taking on the roles of the halves
+ * of the ticket-lock word.  Each task atomically increments
+ * sync_sched_expedited_started upon entry, snapshotting the old value,
+ * then attempts to stop all the CPUs.  If this succeeds, then each
+ * CPU will have executed a context switch, resulting in an RCU-sched
+ * grace period.  We are then done, so we use atomic_cmpxchg() to
+ * update sync_sched_expedited_done to match our snapshot -- but
+ * only if someone else has not already advanced past our snapshot.
+ *
+ * On the other hand, if try_stop_cpus() fails, we check the value
+ * of sync_sched_expedited_done.  If it has advanced past our
+ * initial snapshot, then someone else must have forced a grace period
+ * some time after we took our snapshot.  In this case, our work is
+ * done for us, and we can simply return.  Otherwise, we try again,
+ * but keep our initial snapshot for purposes of checking for someone
+ * doing our work for us.
+ *
+ * If we fail too many times in a row, we fall back to synchronize_sched().
+ */
+void synchronize_sched_expedited(void)
+{
+        int firstsnap, s, snap, trycount = 0;
+
+        /* Note that atomic_inc_return() implies full memory barrier. */
+        firstsnap = snap = atomic_inc_return(&sync_sched_expedited_started);
+        get_online_cpus();
+
+        /*
+         * Each pass through the following loop attempts to force a
+         * context switch on each CPU.
+         */
+        while (try_stop_cpus(cpu_online_mask,
+                             synchronize_sched_expedited_cpu_stop,
+                             NULL) == -EAGAIN) {
+                put_online_cpus();
+
+                /* No joy, try again later.  Or just synchronize_sched(). */
+                if (trycount++ < 10)
+                        udelay(trycount * num_online_cpus());
+                else {
+                        synchronize_sched();
+                        return;
+                }
+
+                /* Check to see if someone else did our work for us. */
+                s = atomic_read(&sync_sched_expedited_done);
+                if (UINT_CMP_GE((unsigned)s, (unsigned)firstsnap)) {
+                        smp_mb(); /* ensure test happens before caller kfree */
+                        return;
+                }
+
+                /*
+                 * Refetching sync_sched_expedited_started allows later
+                 * callers to piggyback on our grace period.  We subtract
+                 * 1 to get the same token that the last incrementer got.
+                 * We retry after they started, so our grace period works
+                 * for them, and they started after our first try, so their
+                 * grace period works for us.
+                 */
+                get_online_cpus();
+                snap = atomic_read(&sync_sched_expedited_started) - 1;
+                smp_mb(); /* ensure read is before try_stop_cpus(). */
+        }
+
+        /*
+         * Everyone up to our most recent fetch is covered by our grace
+         * period.  Update the counter, but only if our work is still
+         * relevant -- which it won't be if someone who started later
+         * than we did beat us to the punch.
+         */
+        do {
+                s = atomic_read(&sync_sched_expedited_done);
+                if (UINT_CMP_GE((unsigned)s, (unsigned)snap)) {
+                        smp_mb(); /* ensure test happens before caller kfree */
+                        break;
+                }
+        } while (atomic_cmpxchg(&sync_sched_expedited_done, s, snap) != s);
+
+        put_online_cpus();
+}
+EXPORT_SYMBOL_GPL(synchronize_sched_expedited);
+
+#endif /* #else #ifndef CONFIG_SMP */
+
 #if !defined(CONFIG_RCU_FAST_NO_HZ)
 
 /*
@@ -1047,14 +1936,13 @@ static DEFINE_PER_CPU(unsigned long, rcu_dyntick_holdoff);
  *
  * Because it is not legal to invoke rcu_process_callbacks() with irqs
  * disabled, we do one pass of force_quiescent_state(), then do a
- * raise_softirq() to cause rcu_process_callbacks() to be invoked later.
- * The per-cpu rcu_dyntick_drain variable controls the sequencing.
+ * invoke_rcu_core() to cause rcu_process_callbacks() to be invoked
+ * later.  The per-cpu rcu_dyntick_drain variable controls the sequencing.
  */
 int rcu_needs_cpu(int cpu)
 {
         int c = 0;
         int snap;
-        int snap_nmi;
         int thatcpu;
 
         /* Check for being in the holdoff period. */
@@ -1065,10 +1953,10 @@ int rcu_needs_cpu(int cpu)
         for_each_online_cpu(thatcpu) {
                 if (thatcpu == cpu)
                         continue;
-                snap = per_cpu(rcu_dynticks, thatcpu).dynticks;
-                snap_nmi = per_cpu(rcu_dynticks, thatcpu).dynticks_nmi;
+                snap = atomic_add_return(0, &per_cpu(rcu_dynticks,
+                                                     thatcpu).dynticks);
                 smp_mb(); /* Order sampling of snap with end of grace period. */
-                if (((snap & 0x1) != 0) || ((snap_nmi & 0x1) != 0)) {
+                if ((snap & 0x1) != 0) {
                         per_cpu(rcu_dyntick_drain, cpu) = 0;
                         per_cpu(rcu_dyntick_holdoff, cpu) = jiffies - 1;
                         return rcu_needs_cpu_quick_check(cpu);
@@ -1099,7 +1987,7 @@ int rcu_needs_cpu(int cpu)
 
         /* If RCU callbacks are still pending, RCU still needs this CPU. */
         if (c)
-                raise_softirq(RCU_SOFTIRQ);
+                invoke_rcu_core();
         return c;
 }