Merge branch 'wip-2.6.34' into old-private-masterarchived-private-master

1 files changed, 98 insertions, 35 deletions

diff --git a/kernel/rcutree.h b/kernel/rcutree.h
index 1899023b0962..4a525a30e08e 100644
--- a/kernel/rcutree.h
+++ b/kernel/rcutree.h
@@ -34,10 +34,11 @@
  * In practice, this has not been tested, so there is probably some
  * bug somewhere.
  */
-#define MAX_RCU_LVLS 3
+#define MAX_RCU_LVLS 4
 #define RCU_FANOUT            (CONFIG_RCU_FANOUT)
 #define RCU_FANOUT_SQ         (RCU_FANOUT * RCU_FANOUT)
 #define RCU_FANOUT_CUBE       (RCU_FANOUT_SQ * RCU_FANOUT)
+#define RCU_FANOUT_FOURTH     (RCU_FANOUT_CUBE * RCU_FANOUT)
 
 #if NR_CPUS <= RCU_FANOUT
 #  define NUM_RCU_LVLS        1
@@ -45,23 +46,33 @@
 #  define NUM_RCU_LVL_1       (NR_CPUS)
 #  define NUM_RCU_LVL_2       0
 #  define NUM_RCU_LVL_3       0
+#  define NUM_RCU_LVL_4       0
 #elif NR_CPUS <= RCU_FANOUT_SQ
 #  define NUM_RCU_LVLS        2
 #  define NUM_RCU_LVL_0       1
 #  define NUM_RCU_LVL_1       DIV_ROUND_UP(NR_CPUS, RCU_FANOUT)
 #  define NUM_RCU_LVL_2       (NR_CPUS)
 #  define NUM_RCU_LVL_3       0
+#  define NUM_RCU_LVL_4       0
 #elif NR_CPUS <= RCU_FANOUT_CUBE
 #  define NUM_RCU_LVLS        3
 #  define NUM_RCU_LVL_0       1
 #  define NUM_RCU_LVL_1       DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_SQ)
 #  define NUM_RCU_LVL_2       DIV_ROUND_UP(NR_CPUS, RCU_FANOUT)
 #  define NUM_RCU_LVL_3       NR_CPUS
+#  define NUM_RCU_LVL_4       0
+#elif NR_CPUS <= RCU_FANOUT_FOURTH
+#  define NUM_RCU_LVLS        4
+#  define NUM_RCU_LVL_0       1
+#  define NUM_RCU_LVL_1       DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_CUBE)
+#  define NUM_RCU_LVL_2       DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_SQ)
+#  define NUM_RCU_LVL_3       DIV_ROUND_UP(NR_CPUS, RCU_FANOUT)
+#  define NUM_RCU_LVL_4       NR_CPUS
 #else
 # error "CONFIG_RCU_FANOUT insufficient for NR_CPUS"
 #endif /* #if (NR_CPUS) <= RCU_FANOUT */
 
-#define RCU_SUM (NUM_RCU_LVL_0 + NUM_RCU_LVL_1 + NUM_RCU_LVL_2 + NUM_RCU_LVL_3)
+#define RCU_SUM (NUM_RCU_LVL_0 + NUM_RCU_LVL_1 + NUM_RCU_LVL_2 + NUM_RCU_LVL_3 + NUM_RCU_LVL_4)
 #define NUM_RCU_NODES (RCU_SUM - NR_CPUS)
 
 /*
@@ -79,9 +90,12 @@ struct rcu_dynticks {
  * Definition for node within the RCU grace-period-detection hierarchy.
  */
 struct rcu_node {
-        spinlock_t lock;        /* Root rcu_node's lock protects some */
+        raw_spinlock_t lock;    /* Root rcu_node's lock protects some */
                                 /*  rcu_state fields as well as following. */
-        long    gpnum;          /* Current grace period for this node. */
+        unsigned long gpnum;    /* Current grace period for this node. */
+                                /*  This will either be equal to or one */
+                                /*  behind the root rcu_node's gpnum. */
+        unsigned long completed; /* Last GP completed for this node. */
                                 /*  This will either be equal to or one */
                                 /*  behind the root rcu_node's gpnum. */
         unsigned long qsmask;   /* CPUs or groups that need to switch in */
@@ -90,8 +104,12 @@ 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[] */
+                                /*  elements that need to drain to allow the */
+                                /*  current expedited grace period to */
+                                /*  complete (only for TREE_PREEMPT_RCU). */
         unsigned long qsmaskinit;
-                                /* Per-GP initialization for qsmask. */
+                                /* Per-GP initial value for qsmask & expmask. */
         unsigned long grpmask;  /* Mask to apply to parent qsmask. */
                                 /*  Only one bit will be set in this mask. */
         int     grplo;          /* lowest-numbered CPU or group here. */
@@ -99,7 +117,7 @@ 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[2];
+        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 */
@@ -114,6 +132,21 @@ struct rcu_node {
         for ((rnp) = &(rsp)->node[0]; \
              (rnp) < &(rsp)->node[NUM_RCU_NODES]; (rnp)++)
 
+/*
+ * Do a breadth-first scan of the non-leaf rcu_node structures for the
+ * specified rcu_state structure.  Note that if there is a singleton
+ * rcu_node tree with but one rcu_node structure, this loop is a no-op.
+ */
+#define rcu_for_each_nonleaf_node_breadth_first(rsp, rnp) \
+        for ((rnp) = &(rsp)->node[0]; \
+             (rnp) < (rsp)->level[NUM_RCU_LVLS - 1]; (rnp)++)
+
+/*
+ * Scan the leaves of the rcu_node hierarchy for the specified rcu_state
+ * structure.  Note that if there is a singleton rcu_node tree with but
+ * one rcu_node structure, this loop -will- visit the rcu_node structure.
+ * It is still a leaf node, even if it is also the root node.
+ */
 #define rcu_for_each_leaf_node(rsp, rnp) \
         for ((rnp) = (rsp)->level[NUM_RCU_LVLS - 1]; \
              (rnp) < &(rsp)->node[NUM_RCU_NODES]; (rnp)++)
@@ -128,11 +161,11 @@ struct rcu_node {
 /* Per-CPU data for read-copy update. */
 struct rcu_data {
         /* 1) quiescent-state and grace-period handling : */
-        long            completed;      /* Track rsp->completed gp number */
+        unsigned long   completed;      /* Track rsp->completed gp number */
                                         /*  in order to detect GP end. */
-        long            gpnum;          /* Highest gp number that this CPU */
+        unsigned long   gpnum;          /* Highest gp number that this CPU */
                                         /*  is aware of having started. */
-        long            passed_quiesc_completed;
+        unsigned long   passed_quiesc_completed;
                                         /* Value of completed at time of qs. */
         bool            passed_quiesc;  /* User-mode/idle loop etc. */
         bool            qs_pending;     /* Core waits for quiesc state. */
@@ -188,14 +221,14 @@ struct rcu_data {
         unsigned long resched_ipi;      /* Sent a resched IPI. */
 
         /* 5) __rcu_pending() statistics. */
-        long n_rcu_pending;             /* rcu_pending() calls since boot. */
-        long n_rp_qs_pending;
-        long n_rp_cb_ready;
-        long n_rp_cpu_needs_gp;
-        long n_rp_gp_completed;
-        long n_rp_gp_started;
-        long n_rp_need_fqs;
-        long n_rp_need_nothing;
+        unsigned long n_rcu_pending;    /* rcu_pending() calls since boot. */
+        unsigned long n_rp_qs_pending;
+        unsigned long n_rp_cb_ready;
+        unsigned long n_rp_cpu_needs_gp;
+        unsigned long n_rp_gp_completed;
+        unsigned long n_rp_gp_started;
+        unsigned long n_rp_need_fqs;
+        unsigned long n_rp_need_nothing;
 
         int cpu;
 };
@@ -213,15 +246,27 @@ struct rcu_data {
 
 #define RCU_JIFFIES_TILL_FORCE_QS        3      /* for rsp->jiffies_force_qs */
 #ifdef CONFIG_RCU_CPU_STALL_DETECTOR
-#define RCU_SECONDS_TILL_STALL_CHECK   (10 * HZ)  /* for rsp->jiffies_stall */
-#define RCU_SECONDS_TILL_STALL_RECHECK (30 * HZ)  /* for rsp->jiffies_stall */
-#define RCU_STALL_RAT_DELAY             2         /* Allow other CPUs time */
-                                                  /*  to take at least one */
-                                                  /*  scheduling clock irq */
-                                                  /*  before ratting on them. */
+
+#ifdef CONFIG_PROVE_RCU
+#define RCU_STALL_DELAY_DELTA          (5 * HZ)
+#else
+#define RCU_STALL_DELAY_DELTA          0
+#endif
+
+#define RCU_SECONDS_TILL_STALL_CHECK   (10 * HZ + RCU_STALL_DELAY_DELTA)
+                                                /* for rsp->jiffies_stall */
+#define RCU_SECONDS_TILL_STALL_RECHECK (30 * HZ + RCU_STALL_DELAY_DELTA)
+                                                /* for rsp->jiffies_stall */
+#define RCU_STALL_RAT_DELAY             2       /* Allow other CPUs time */
+                                                /*  to take at least one */
+                                                /*  scheduling clock irq */
+                                                /*  before ratting on them. */
 
 #endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
 
+#define ULONG_CMP_GE(a, b)      (ULONG_MAX / 2 >= (a) - (b))
+#define ULONG_CMP_LT(a, b)      (ULONG_MAX / 2 < (a) - (b))
+
 /*
  * RCU global state, including node hierarchy.  This hierarchy is
  * represented in "heap" form in a dense array.  The root (first level)
@@ -243,12 +288,19 @@ struct rcu_state {
 
         u8      signaled ____cacheline_internodealigned_in_smp;
                                                 /* Force QS state. */
-        long    gpnum;                          /* Current gp number. */
-        long    completed;                      /* # of last completed gp. */
+        u8      fqs_active;                     /* force_quiescent_state() */
+                                                /*  is running. */
+        u8      fqs_need_gp;                    /* A CPU was prevented from */
+                                                /*  starting a new grace */
+                                                /*  period because */
+                                                /*  force_quiescent_state() */
+                                                /*  was running. */
+        unsigned long gpnum;                    /* Current gp number. */
+        unsigned long completed;                /* # of last completed gp. */
 
-        /* End  of fields guarded by root rcu_node's lock. */
+        /* End of fields guarded by root rcu_node's lock. */
 
-        spinlock_t onofflock;                   /* exclude on/offline and */
+        raw_spinlock_t onofflock;               /* exclude on/offline and */
                                                 /*  starting new GP.  Also */
                                                 /*  protects the following */
                                                 /*  orphan_cbs fields. */
@@ -258,7 +310,7 @@ struct rcu_state {
                                                 /*  going offline. */
         struct rcu_head **orphan_cbs_tail;      /* And tail pointer. */
         long orphan_qlen;                       /* Number of orphaned cbs. */
-        spinlock_t fqslock;                     /* Only one task forcing */
+        raw_spinlock_t fqslock;                 /* Only one task forcing */
                                                 /*  quiescent states. */
         unsigned long jiffies_force_qs;         /* Time at which to invoke */
                                                 /*  force_quiescent_state(). */
@@ -274,12 +326,14 @@ struct rcu_state {
         unsigned long jiffies_stall;            /* Time at which to check */
                                                 /*  for CPU stalls. */
 #endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
-#ifdef CONFIG_NO_HZ
-        long dynticks_completed;                /* Value of completed @ snap. */
-#endif /* #ifdef CONFIG_NO_HZ */
 };
 
-#ifdef RCU_TREE_NONCORE
+/* Return values for rcu_preempt_offline_tasks(). */
+
+#define RCU_OFL_TASKS_NORM_GP   0x1             /* Tasks blocking normal */
+                                                /*  GP were moved to root. */
+#define RCU_OFL_TASKS_EXP_GP    0x2             /* Tasks blocking expedited */
+                                                /*  GP were moved to root. */
 
 /*
  * RCU implementation internal declarations:
@@ -295,14 +349,19 @@ extern struct rcu_state rcu_preempt_state;
 DECLARE_PER_CPU(struct rcu_data, rcu_preempt_data);
 #endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */
 
-#else /* #ifdef RCU_TREE_NONCORE */
+#ifndef RCU_TREE_NONCORE
 
 /* Forward declarations for rcutree_plugin.h */
-static inline void rcu_bootup_announce(void);
+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);
+#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);
 #endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
 static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp);
@@ -315,10 +374,14 @@ static void rcu_preempt_offline_cpu(int cpu);
 static void rcu_preempt_check_callbacks(int cpu);
 static void rcu_preempt_process_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)
+static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp);
+#endif /* #if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_TREE_PREEMPT_RCU) */
 static int rcu_preempt_pending(int cpu);
 static int rcu_preempt_needs_cpu(int cpu);
 static void __cpuinit rcu_preempt_init_percpu_data(int cpu);
 static void rcu_preempt_send_cbs_to_orphanage(void);
 static void __init __rcu_init_preempt(void);
+static void rcu_needs_cpu_flush(void);
 
-#endif /* #else #ifdef RCU_TREE_NONCORE */
+#endif /* #ifndef RCU_TREE_NONCORE */