8 files changed, 161 insertions, 51 deletions

diff --git a/kernel/rcu/Makefile b/kernel/rcu/Makefile
index 807ccfbf69b3..e6fae503d1bc 100644
--- a/kernel/rcu/Makefile
+++ b/kernel/rcu/Makefile
@@ -1,6 +1,6 @@
 obj-y += update.o srcu.o
 obj-$(CONFIG_RCU_TORTURE_TEST) += rcutorture.o
 obj-$(CONFIG_TREE_RCU) += tree.o
-obj-$(CONFIG_TREE_PREEMPT_RCU) += tree.o
+obj-$(CONFIG_PREEMPT_RCU) += tree.o
 obj-$(CONFIG_TREE_RCU_TRACE) += tree_trace.o
 obj-$(CONFIG_TINY_RCU) += tiny.o
diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h
index ff1a6de62f17..07bb02eda844 100644
--- a/kernel/rcu/rcu.h
+++ b/kernel/rcu/rcu.h
@@ -135,4 +135,6 @@ int rcu_jiffies_till_stall_check(void);
  */
 #define TPS(x)  tracepoint_string(x)
 
+void rcu_early_boot_tests(void);
+
 #endif /* __LINUX_RCU_H */
diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index 240fa9094f83..4d559baf06e0 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -812,6 +812,7 @@ rcu_torture_cbflood(void *arg)
                 cur_ops->cb_barrier();
                 stutter_wait("rcu_torture_cbflood");
         } while (!torture_must_stop());
+        vfree(rhp);
         torture_kthread_stopping("rcu_torture_cbflood");
         return 0;
 }
diff --git a/kernel/rcu/tiny.c b/kernel/rcu/tiny.c
index 01570c68d237..0db5649f8817 100644
--- a/kernel/rcu/tiny.c
+++ b/kernel/rcu/tiny.c
@@ -380,7 +380,9 @@ void call_rcu_bh(struct rcu_head *head, void (*func)(struct rcu_head *rcu))
 }
 EXPORT_SYMBOL_GPL(call_rcu_bh);
 
-void rcu_init(void)
+void __init rcu_init(void)
 {
         open_softirq(RCU_SOFTIRQ, rcu_process_callbacks);
+
+        rcu_early_boot_tests();
 }
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index fa76fd3c219c..7680fc275036 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -152,19 +152,6 @@ EXPORT_SYMBOL_GPL(rcu_scheduler_active);
  */
 static int rcu_scheduler_fully_active __read_mostly;
 
-#ifdef CONFIG_RCU_BOOST
-
-/*
- * Control variables for per-CPU and per-rcu_node kthreads.  These
- * handle all flavors of RCU.
- */
-static DEFINE_PER_CPU(struct task_struct *, rcu_cpu_kthread_task);
-DEFINE_PER_CPU(unsigned int, rcu_cpu_kthread_status);
-DEFINE_PER_CPU(unsigned int, rcu_cpu_kthread_loops);
-DEFINE_PER_CPU(char, rcu_cpu_has_work);
-
-#endif /* #ifdef CONFIG_RCU_BOOST */
-
 static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu);
 static void invoke_rcu_core(void);
 static void invoke_rcu_callbacks(struct rcu_state *rsp, struct rcu_data *rdp);
@@ -2964,6 +2951,9 @@ static int synchronize_sched_expedited_cpu_stop(void *data)
  */
 void synchronize_sched_expedited(void)
 {
+        cpumask_var_t cm;
+        bool cma = false;
+        int cpu;
         long firstsnap, s, snap;
         int trycount = 0;
         struct rcu_state *rsp = &rcu_sched_state;
@@ -2998,11 +2988,26 @@ void synchronize_sched_expedited(void)
         }
         WARN_ON_ONCE(cpu_is_offline(raw_smp_processor_id()));
 
+        /* Offline CPUs, idle CPUs, and any CPU we run on are quiescent. */
+        cma = zalloc_cpumask_var(&cm, GFP_KERNEL);
+        if (cma) {
+                cpumask_copy(cm, cpu_online_mask);
+                cpumask_clear_cpu(raw_smp_processor_id(), cm);
+                for_each_cpu(cpu, cm) {
+                        struct rcu_dynticks *rdtp = &per_cpu(rcu_dynticks, cpu);
+
+                        if (!(atomic_add_return(0, &rdtp->dynticks) & 0x1))
+                                cpumask_clear_cpu(cpu, cm);
+                }
+                if (cpumask_weight(cm) == 0)
+                        goto all_cpus_idle;
+        }
+
         /*
          * Each pass through the following loop attempts to force a
          * context switch on each CPU.
          */
-        while (try_stop_cpus(cpu_online_mask,
+        while (try_stop_cpus(cma ? cm : cpu_online_mask,
                              synchronize_sched_expedited_cpu_stop,
                              NULL) == -EAGAIN) {
                 put_online_cpus();
@@ -3014,6 +3019,7 @@ void synchronize_sched_expedited(void)
                         /* ensure test happens before caller kfree */
                         smp_mb__before_atomic(); /* ^^^ */
                         atomic_long_inc(&rsp->expedited_workdone1);
+                        free_cpumask_var(cm);
                         return;
                 }
 
@@ -3023,6 +3029,7 @@ void synchronize_sched_expedited(void)
                 } else {
                         wait_rcu_gp(call_rcu_sched);
                         atomic_long_inc(&rsp->expedited_normal);
+                        free_cpumask_var(cm);
                         return;
                 }
 
@@ -3032,6 +3039,7 @@ void synchronize_sched_expedited(void)
                         /* ensure test happens before caller kfree */
                         smp_mb__before_atomic(); /* ^^^ */
                         atomic_long_inc(&rsp->expedited_workdone2);
+                        free_cpumask_var(cm);
                         return;
                 }
 
@@ -3046,6 +3054,7 @@ void synchronize_sched_expedited(void)
                         /* CPU hotplug operation in flight, use normal GP. */
                         wait_rcu_gp(call_rcu_sched);
                         atomic_long_inc(&rsp->expedited_normal);
+                        free_cpumask_var(cm);
                         return;
                 }
                 snap = atomic_long_read(&rsp->expedited_start);
@@ -3053,6 +3062,9 @@ void synchronize_sched_expedited(void)
         }
         atomic_long_inc(&rsp->expedited_stoppedcpus);
 
+all_cpus_idle:
+        free_cpumask_var(cm);
+
         /*
          * Everyone up to our most recent fetch is covered by our grace
          * period.  Update the counter, but only if our work is still
@@ -3486,8 +3498,10 @@ static int rcu_cpu_notify(struct notifier_block *self,
         case CPU_DEAD_FROZEN:
         case CPU_UP_CANCELED:
         case CPU_UP_CANCELED_FROZEN:
-                for_each_rcu_flavor(rsp)
+                for_each_rcu_flavor(rsp) {
                         rcu_cleanup_dead_cpu(cpu, rsp);
+                        do_nocb_deferred_wakeup(per_cpu_ptr(rsp->rda, cpu));
+                }
                 break;
         default:
                 break;
@@ -3767,6 +3781,8 @@ void __init rcu_init(void)
         pm_notifier(rcu_pm_notify, 0);
         for_each_online_cpu(cpu)
                 rcu_cpu_notify(NULL, CPU_UP_PREPARE, (void *)(long)cpu);
+
+        rcu_early_boot_tests();
 }
 
 #include "tree_plugin.h"
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index 36c30390e4e9..8e7b1843896e 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -139,7 +139,7 @@ struct rcu_node {
         unsigned long expmask;  /* Groups that have ->blkd_tasks */
                                 /*  elements that need to drain to allow the */
                                 /*  current expedited grace period to */
-                                /*  complete (only for TREE_PREEMPT_RCU). */
+                                /*  complete (only for PREEMPT_RCU). */
         unsigned long qsmaskinit;
                                 /* Per-GP initial value for qsmask & expmask. */
         unsigned long grpmask;  /* Mask to apply to parent qsmask. */
@@ -530,10 +530,10 @@ DECLARE_PER_CPU(struct rcu_data, rcu_sched_data);
 extern struct rcu_state rcu_bh_state;
 DECLARE_PER_CPU(struct rcu_data, rcu_bh_data);
 
-#ifdef CONFIG_TREE_PREEMPT_RCU
+#ifdef CONFIG_PREEMPT_RCU
 extern struct rcu_state rcu_preempt_state;
 DECLARE_PER_CPU(struct rcu_data, rcu_preempt_data);
-#endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */
+#endif /* #ifdef CONFIG_PREEMPT_RCU */
 
 #ifdef CONFIG_RCU_BOOST
 DECLARE_PER_CPU(unsigned int, rcu_cpu_kthread_status);
@@ -563,10 +563,10 @@ static int rcu_preempt_offline_tasks(struct rcu_state *rsp,
 #endif /* #ifdef CONFIG_HOTPLUG_CPU */
 static void rcu_preempt_check_callbacks(void);
 void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu));
-#if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_TREE_PREEMPT_RCU)
+#if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_PREEMPT_RCU)
 static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp,
                                bool wake);
-#endif /* #if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_TREE_PREEMPT_RCU) */
+#endif /* #if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_PREEMPT_RCU) */
 static void __init __rcu_init_preempt(void);
 static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags);
 static void rcu_preempt_boost_start_gp(struct rcu_node *rnp);
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 2443282737ba..3ec85cb5d544 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -30,14 +30,24 @@
 #include <linux/smpboot.h>
 #include "../time/tick-internal.h"
 
-#define RCU_KTHREAD_PRIO 1
-
 #ifdef CONFIG_RCU_BOOST
+
 #include "../locking/rtmutex_common.h"
-#define RCU_BOOST_PRIO CONFIG_RCU_BOOST_PRIO
-#else
-#define RCU_BOOST_PRIO RCU_KTHREAD_PRIO
-#endif
+
+/* rcuc/rcub kthread realtime priority */
+static int kthread_prio = CONFIG_RCU_KTHREAD_PRIO;
+module_param(kthread_prio, int, 0644);
+
+/*
+ * Control variables for per-CPU and per-rcu_node kthreads.  These
+ * handle all flavors of RCU.
+ */
+static DEFINE_PER_CPU(struct task_struct *, rcu_cpu_kthread_task);
+DEFINE_PER_CPU(unsigned int, rcu_cpu_kthread_status);
+DEFINE_PER_CPU(unsigned int, rcu_cpu_kthread_loops);
+DEFINE_PER_CPU(char, rcu_cpu_has_work);
+
+#endif /* #ifdef CONFIG_RCU_BOOST */
 
 #ifdef CONFIG_RCU_NOCB_CPU
 static cpumask_var_t rcu_nocb_mask; /* CPUs to have callbacks offloaded. */
@@ -72,9 +82,6 @@ static void __init rcu_bootup_announce_oddness(void)
 #ifdef CONFIG_RCU_TORTURE_TEST_RUNNABLE
         pr_info("\tRCU torture testing starts during boot.\n");
 #endif
-#if defined(CONFIG_TREE_PREEMPT_RCU) && !defined(CONFIG_RCU_CPU_STALL_VERBOSE)
-        pr_info("\tDump stacks of tasks blocking RCU-preempt GP.\n");
-#endif
 #if defined(CONFIG_RCU_CPU_STALL_INFO)
         pr_info("\tAdditional per-CPU info printed with stalls.\n");
 #endif
@@ -85,9 +92,12 @@ static void __init rcu_bootup_announce_oddness(void)
                 pr_info("\tBoot-time adjustment of leaf fanout to %d.\n", rcu_fanout_leaf);
         if (nr_cpu_ids != NR_CPUS)
                 pr_info("\tRCU restricting CPUs from NR_CPUS=%d to nr_cpu_ids=%d.\n", NR_CPUS, nr_cpu_ids);
+#ifdef CONFIG_RCU_BOOST
+        pr_info("\tRCU kthread priority: %d.\n", kthread_prio);
+#endif
 }
 
-#ifdef CONFIG_TREE_PREEMPT_RCU
+#ifdef CONFIG_PREEMPT_RCU
 
 RCU_STATE_INITIALIZER(rcu_preempt, 'p', call_rcu);
 static struct rcu_state *rcu_state_p = &rcu_preempt_state;
@@ -415,8 +425,6 @@ void rcu_read_unlock_special(struct task_struct *t)
         }
 }
 
-#ifdef CONFIG_RCU_CPU_STALL_VERBOSE
-
 /*
  * Dump detailed information for all tasks blocking the current RCU
  * grace period on the specified rcu_node structure.
@@ -451,14 +459,6 @@ static void rcu_print_detail_task_stall(struct rcu_state *rsp)
                 rcu_print_detail_task_stall_rnp(rnp);
 }
 
-#else /* #ifdef CONFIG_RCU_CPU_STALL_VERBOSE */
-
-static void rcu_print_detail_task_stall(struct rcu_state *rsp)
-{
-}
-
-#endif /* #else #ifdef CONFIG_RCU_CPU_STALL_VERBOSE */
-
 #ifdef CONFIG_RCU_CPU_STALL_INFO
 
 static void rcu_print_task_stall_begin(struct rcu_node *rnp)
@@ -919,7 +919,7 @@ void exit_rcu(void)
         __rcu_read_unlock();
 }
 
-#else /* #ifdef CONFIG_TREE_PREEMPT_RCU */
+#else /* #ifdef CONFIG_PREEMPT_RCU */
 
 static struct rcu_state *rcu_state_p = &rcu_sched_state;
 
@@ -1070,7 +1070,7 @@ void exit_rcu(void)
 {
 }
 
-#endif /* #else #ifdef CONFIG_TREE_PREEMPT_RCU */
+#endif /* #else #ifdef CONFIG_PREEMPT_RCU */
 
 #ifdef CONFIG_RCU_BOOST
 
@@ -1326,7 +1326,7 @@ static int rcu_spawn_one_boost_kthread(struct rcu_state *rsp,
         smp_mb__after_unlock_lock();
         rnp->boost_kthread_task = t;
         raw_spin_unlock_irqrestore(&rnp->lock, flags);
-        sp.sched_priority = RCU_BOOST_PRIO;
+        sp.sched_priority = kthread_prio;
         sched_setscheduler_nocheck(t, SCHED_FIFO, &sp);
         wake_up_process(t); /* get to TASK_INTERRUPTIBLE quickly. */
         return 0;
@@ -1343,7 +1343,7 @@ static void rcu_cpu_kthread_setup(unsigned int cpu)
 {
         struct sched_param sp;
 
-        sp.sched_priority = RCU_KTHREAD_PRIO;
+        sp.sched_priority = kthread_prio;
         sched_setscheduler_nocheck(current, SCHED_FIFO, &sp);
 }
 
@@ -2573,9 +2573,13 @@ static void rcu_spawn_one_nocb_kthread(struct rcu_state *rsp, int cpu)
                         rdp->nocb_leader = rdp_spawn;
                         if (rdp_last && rdp != rdp_spawn)
                                 rdp_last->nocb_next_follower = rdp;
-                        rdp_last = rdp;
-                        rdp = rdp->nocb_next_follower;
-                        rdp_last->nocb_next_follower = NULL;
+                        if (rdp == rdp_spawn) {
+                                rdp = rdp->nocb_next_follower;
+                        } else {
+                                rdp_last = rdp;
+                                rdp = rdp->nocb_next_follower;
+                                rdp_last->nocb_next_follower = NULL;
+                        }
                 } while (rdp);
                 rdp_spawn->nocb_next_follower = rdp_old_leader;
         }
diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c
index 3ef8ba58694e..e0d31a345ee6 100644
--- a/kernel/rcu/update.c
+++ b/kernel/rcu/update.c
@@ -306,7 +306,7 @@ struct debug_obj_descr rcuhead_debug_descr = {
 EXPORT_SYMBOL_GPL(rcuhead_debug_descr);
 #endif /* #ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD */
 
-#if defined(CONFIG_TREE_RCU) || defined(CONFIG_TREE_PREEMPT_RCU) || defined(CONFIG_RCU_TRACE)
+#if defined(CONFIG_TREE_RCU) || defined(CONFIG_PREEMPT_RCU) || defined(CONFIG_RCU_TRACE)
 void do_trace_rcu_torture_read(const char *rcutorturename, struct rcu_head *rhp,
                                unsigned long secs,
                                unsigned long c_old, unsigned long c)
@@ -531,7 +531,8 @@ static int __noreturn rcu_tasks_kthread(void *arg)
         struct rcu_head *next;
         LIST_HEAD(rcu_tasks_holdouts);
 
-        /* FIXME: Add housekeeping affinity. */
+        /* Run on housekeeping CPUs by default.  Sysadm can move if desired. */
+        housekeeping_affine(current);
 
         /*
          * Each pass through the following loop makes one check for
@@ -690,3 +691,87 @@ static void rcu_spawn_tasks_kthread(void)
 }
 
 #endif /* #ifdef CONFIG_TASKS_RCU */
+
+#ifdef CONFIG_PROVE_RCU
+
+/*
+ * Early boot self test parameters, one for each flavor
+ */
+static bool rcu_self_test;
+static bool rcu_self_test_bh;
+static bool rcu_self_test_sched;
+
+module_param(rcu_self_test, bool, 0444);
+module_param(rcu_self_test_bh, bool, 0444);
+module_param(rcu_self_test_sched, bool, 0444);
+
+static int rcu_self_test_counter;
+
+static void test_callback(struct rcu_head *r)
+{
+        rcu_self_test_counter++;
+        pr_info("RCU test callback executed %d\n", rcu_self_test_counter);
+}
+
+static void early_boot_test_call_rcu(void)
+{
+        static struct rcu_head head;
+
+        call_rcu(&head, test_callback);
+}
+
+static void early_boot_test_call_rcu_bh(void)
+{
+        static struct rcu_head head;
+
+        call_rcu_bh(&head, test_callback);
+}
+
+static void early_boot_test_call_rcu_sched(void)
+{
+        static struct rcu_head head;
+
+        call_rcu_sched(&head, test_callback);
+}
+
+void rcu_early_boot_tests(void)
+{
+        pr_info("Running RCU self tests\n");
+
+        if (rcu_self_test)
+                early_boot_test_call_rcu();
+        if (rcu_self_test_bh)
+                early_boot_test_call_rcu_bh();
+        if (rcu_self_test_sched)
+                early_boot_test_call_rcu_sched();
+}
+
+static int rcu_verify_early_boot_tests(void)
+{
+        int ret = 0;
+        int early_boot_test_counter = 0;
+
+        if (rcu_self_test) {
+                early_boot_test_counter++;
+                rcu_barrier();
+        }
+        if (rcu_self_test_bh) {
+                early_boot_test_counter++;
+                rcu_barrier_bh();
+        }
+        if (rcu_self_test_sched) {
+                early_boot_test_counter++;
+                rcu_barrier_sched();
+        }
+
+        if (rcu_self_test_counter != early_boot_test_counter) {
+                WARN_ON(1);
+                ret = -1;
+        }
+
+        return ret;
+}
+late_initcall(rcu_verify_early_boot_tests);
+#else
+void rcu_early_boot_tests(void) {}
+#endif /* CONFIG_PROVE_RCU */