Merge branch 'core-rcu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'core-rcu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (78 commits)
  Revert "rcu: Decrease memory-barrier usage based on semi-formal proof"
  net,rcu: convert call_rcu(prl_entry_destroy_rcu) to kfree
  batman,rcu: convert call_rcu(softif_neigh_free_rcu) to kfree_rcu
  batman,rcu: convert call_rcu(neigh_node_free_rcu) to kfree()
  batman,rcu: convert call_rcu(gw_node_free_rcu) to kfree_rcu
  net,rcu: convert call_rcu(kfree_tid_tx) to kfree_rcu()
  net,rcu: convert call_rcu(xt_osf_finger_free_rcu) to kfree_rcu()
  net/mac80211,rcu: convert call_rcu(work_free_rcu) to kfree_rcu()
  net,rcu: convert call_rcu(wq_free_rcu) to kfree_rcu()
  net,rcu: convert call_rcu(phonet_device_rcu_free) to kfree_rcu()
  perf,rcu: convert call_rcu(swevent_hlist_release_rcu) to kfree_rcu()
  perf,rcu: convert call_rcu(free_ctx) to kfree_rcu()
  net,rcu: convert call_rcu(__nf_ct_ext_free_rcu) to kfree_rcu()
  net,rcu: convert call_rcu(net_generic_release) to kfree_rcu()
  net,rcu: convert call_rcu(netlbl_unlhsh_free_addr6) to kfree_rcu()
  net,rcu: convert call_rcu(netlbl_unlhsh_free_addr4) to kfree_rcu()
  security,rcu: convert call_rcu(sel_netif_free) to kfree_rcu()
  net,rcu: convert call_rcu(xps_dev_maps_release) to kfree_rcu()
  net,rcu: convert call_rcu(xps_map_release) to kfree_rcu()
  net,rcu: convert call_rcu(rps_map_release) to kfree_rcu()
  ...

1 files changed, 84 insertions, 20 deletions

diff --git a/kernel/rcutree.h b/kernel/rcutree.h
index e8f057e44e3e..257664815d5d 100644
--- a/kernel/rcutree.h
+++ b/kernel/rcutree.h
@@ -91,6 +91,14 @@ struct rcu_dynticks {
 				/*  remains even for nmi from irq handler. */
 };
 
+/* RCU's kthread states for tracing. */
+#define RCU_KTHREAD_STOPPED  0
+#define RCU_KTHREAD_RUNNING  1
+#define RCU_KTHREAD_WAITING  2
+#define RCU_KTHREAD_OFFCPU   3
+#define RCU_KTHREAD_YIELDING 4
+#define RCU_KTHREAD_MAX      4
+
 /*
  * Definition for node within the RCU grace-period-detection hierarchy.
  */
@@ -109,10 +117,11 @@ struct rcu_node {
 				/*  an rcu_data structure, otherwise, each */
 				/*  bit corresponds to a child rcu_node */
 				/*  structure. */
-	unsigned long expmask;	/* Groups that have ->blocked_tasks[] */
+	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). */
+	unsigned long wakemask; /* CPUs whose kthread needs to be awakened. */
 	unsigned long qsmaskinit;
 				/* Per-GP initial value for qsmask & expmask. */
 	unsigned long grpmask;	/* Mask to apply to parent qsmask. */
@@ -122,11 +131,68 @@ struct rcu_node {
 	u8	grpnum;		/* CPU/group number for next level up. */
 	u8	level;		/* root is at level 0. */
 	struct rcu_node *parent;
-	struct list_head blocked_tasks[4];
-				/* Tasks blocked in RCU read-side critsect. */
-				/*  Grace period number (->gpnum) x blocked */
-				/*  by tasks on the (x & 0x1) element of the */
-				/*  blocked_tasks[] array. */
+	struct list_head blkd_tasks;
+				/* Tasks blocked in RCU read-side critical */
+				/*  section.  Tasks are placed at the head */
+				/*  of this list and age towards the tail. */
+	struct list_head *gp_tasks;
+				/* Pointer to the first task blocking the */
+				/*  current grace period, or NULL if there */
+				/*  is no such task. */
+	struct list_head *exp_tasks;
+				/* Pointer to the first task blocking the */
+				/*  current expedited grace period, or NULL */
+				/*  if there is no such task.  If there */
+				/*  is no current expedited grace period, */
+				/*  then there can cannot be any such task. */
+#ifdef CONFIG_RCU_BOOST
+	struct list_head *boost_tasks;
+				/* Pointer to first task that needs to be */
+				/*  priority boosted, or NULL if no priority */
+				/*  boosting is needed for this rcu_node */
+				/*  structure.  If there are no tasks */
+				/*  queued on this rcu_node structure that */
+				/*  are blocking the current grace period, */
+				/*  there can be no such task. */
+	unsigned long boost_time;
+				/* When to start boosting (jiffies). */
+	struct task_struct *boost_kthread_task;
+				/* kthread that takes care of priority */
+				/*  boosting for this rcu_node structure. */
+	wait_queue_head_t boost_wq;
+				/* Wait queue on which to park the boost */
+				/*  kthread. */
+	unsigned int boost_kthread_status;
+				/* State of boost_kthread_task for tracing. */
+	unsigned long n_tasks_boosted;
+				/* Total number of tasks boosted. */
+	unsigned long n_exp_boosts;
+				/* Number of tasks boosted for expedited GP. */
+	unsigned long n_normal_boosts;
+				/* Number of tasks boosted for normal GP. */
+	unsigned long n_balk_blkd_tasks;
+				/* Refused to boost: no blocked tasks. */
+	unsigned long n_balk_exp_gp_tasks;
+				/* Refused to boost: nothing blocking GP. */
+	unsigned long n_balk_boost_tasks;
+				/* Refused to boost: already boosting. */
+	unsigned long n_balk_notblocked;
+				/* Refused to boost: RCU RS CS still running. */
+	unsigned long n_balk_notyet;
+				/* Refused to boost: not yet time. */
+	unsigned long n_balk_nos;
+				/* Refused to boost: not sure why, though. */
+				/*  This can happen due to race conditions. */
+#endif /* #ifdef CONFIG_RCU_BOOST */
+	struct task_struct *node_kthread_task;
+				/* kthread that takes care of this rcu_node */
+				/*  structure, for example, awakening the */
+				/*  per-CPU kthreads as needed. */
+	wait_queue_head_t node_wq;
+				/* Wait queue on which to park the per-node */
+				/*  kthread. */
+	unsigned int node_kthread_status;
+				/* State of node_kthread_task for tracing. */
 } ____cacheline_internodealigned_in_smp;
 
 /*
@@ -175,7 +241,7 @@ struct rcu_data {
 	bool		passed_quiesc;	/* User-mode/idle loop etc. */
 	bool		qs_pending;	/* Core waits for quiesc state. */
 	bool		beenonline;	/* CPU online at least once. */
-	bool		preemptable;	/* Preemptable RCU? */
+	bool		preemptible;	/* Preemptible RCU? */
 	struct rcu_node *mynode;	/* This CPU's leaf of hierarchy */
 	unsigned long grpmask;		/* Mask to apply to leaf qsmask. */
 
@@ -254,7 +320,6 @@ struct rcu_data {
 #endif /* #else #ifdef CONFIG_NO_HZ */
 
 #define RCU_JIFFIES_TILL_FORCE_QS	 3	/* for rsp->jiffies_force_qs */
-#ifdef CONFIG_RCU_CPU_STALL_DETECTOR
 
 #ifdef CONFIG_PROVE_RCU
 #define RCU_STALL_DELAY_DELTA	       (5 * HZ)
@@ -272,13 +337,6 @@ struct rcu_data {
 						/*  scheduling clock irq */
 						/*  before ratting on them. */
 
-#ifdef CONFIG_RCU_CPU_STALL_DETECTOR_RUNNABLE
-#define RCU_CPU_STALL_SUPPRESS_INIT 0
-#else
-#define RCU_CPU_STALL_SUPPRESS_INIT 1
-#endif
-
-#endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
 
 /*
  * RCU global state, including node hierarchy.  This hierarchy is
@@ -325,12 +383,12 @@ struct rcu_state {
 						/*  due to lock unavailable. */
 	unsigned long n_force_qs_ngp;		/* Number of calls leaving */
 						/*  due to no GP active. */
-#ifdef CONFIG_RCU_CPU_STALL_DETECTOR
 	unsigned long gp_start;			/* Time at which GP started, */
 						/*  but in jiffies. */
 	unsigned long jiffies_stall;		/* Time at which to check */
 						/*  for CPU stalls. */
-#endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
+	unsigned long gp_max;			/* Maximum GP duration in */
+						/*  jiffies. */
 	char *name;				/* Name of structure. */
 };
 
@@ -361,16 +419,14 @@ DECLARE_PER_CPU(struct rcu_data, rcu_preempt_data);
 static void rcu_bootup_announce(void);
 long rcu_batches_completed(void);
 static void rcu_preempt_note_context_switch(int cpu);
-static int rcu_preempted_readers(struct rcu_node *rnp);
+static int rcu_preempt_blocked_readers_cgp(struct rcu_node *rnp);
 #ifdef CONFIG_HOTPLUG_CPU
 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
 static void rcu_print_detail_task_stall(struct rcu_state *rsp);
 static void rcu_print_task_stall(struct rcu_node *rnp);
 static void rcu_preempt_stall_reset(void);
-#endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
 static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp);
 #ifdef CONFIG_HOTPLUG_CPU
 static int rcu_preempt_offline_tasks(struct rcu_state *rsp,
@@ -390,5 +446,13 @@ static void __cpuinit rcu_preempt_init_percpu_data(int cpu);
 static void rcu_preempt_send_cbs_to_online(void);
 static void __init __rcu_init_preempt(void);
 static void rcu_needs_cpu_flush(void);
+static void __init rcu_init_boost_waitqueue(struct rcu_node *rnp);
+static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags);
+static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp,
+					  cpumask_var_t cm);
+static void rcu_preempt_boost_start_gp(struct rcu_node *rnp);
+static int __cpuinit rcu_spawn_one_boost_kthread(struct rcu_state *rsp,
+						 struct rcu_node *rnp,
+						 int rnp_index);
 
 #endif /* #ifndef RCU_TREE_NONCORE */