diff options
Diffstat (limited to 'kernel/rcu/tree.h')
| -rw-r--r-- | kernel/rcu/tree.h | 96 |
1 files changed, 63 insertions, 33 deletions
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h index 4adb7ca0b..2e991f836 100644 --- a/kernel/rcu/tree.h +++ b/kernel/rcu/tree.h @@ -27,6 +27,7 @@ #include <linux/threads.h> #include <linux/cpumask.h> #include <linux/seqlock.h> +#include <linux/stop_machine.h> /* * Define shape of hierarchy based on NR_CPUS, CONFIG_RCU_FANOUT, and @@ -36,8 +37,6 @@ * Of course, your mileage may vary. */ -#define MAX_RCU_LVLS 4 - #ifdef CONFIG_RCU_FANOUT #define RCU_FANOUT CONFIG_RCU_FANOUT #else /* #ifdef CONFIG_RCU_FANOUT */ @@ -66,38 +65,53 @@ #if NR_CPUS <= RCU_FANOUT_1 # define RCU_NUM_LVLS 1 # define NUM_RCU_LVL_0 1 -# 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 +# define NUM_RCU_NODES NUM_RCU_LVL_0 +# define NUM_RCU_LVL_INIT { NUM_RCU_LVL_0 } +# define RCU_NODE_NAME_INIT { "rcu_node_0" } +# define RCU_FQS_NAME_INIT { "rcu_node_fqs_0" } +# define RCU_EXP_NAME_INIT { "rcu_node_exp_0" } +# define RCU_EXP_SCHED_NAME_INIT \ + { "rcu_node_exp_sched_0" } #elif NR_CPUS <= RCU_FANOUT_2 # define RCU_NUM_LVLS 2 # define NUM_RCU_LVL_0 1 # define NUM_RCU_LVL_1 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_1) -# define NUM_RCU_LVL_2 (NR_CPUS) -# define NUM_RCU_LVL_3 0 -# define NUM_RCU_LVL_4 0 +# define NUM_RCU_NODES (NUM_RCU_LVL_0 + NUM_RCU_LVL_1) +# define NUM_RCU_LVL_INIT { NUM_RCU_LVL_0, NUM_RCU_LVL_1 } +# define RCU_NODE_NAME_INIT { "rcu_node_0", "rcu_node_1" } +# define RCU_FQS_NAME_INIT { "rcu_node_fqs_0", "rcu_node_fqs_1" } +# define RCU_EXP_NAME_INIT { "rcu_node_exp_0", "rcu_node_exp_1" } +# define RCU_EXP_SCHED_NAME_INIT \ + { "rcu_node_exp_sched_0", "rcu_node_exp_sched_1" } #elif NR_CPUS <= RCU_FANOUT_3 # define RCU_NUM_LVLS 3 # define NUM_RCU_LVL_0 1 # define NUM_RCU_LVL_1 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_2) # define NUM_RCU_LVL_2 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_1) -# define NUM_RCU_LVL_3 (NR_CPUS) -# define NUM_RCU_LVL_4 0 +# define NUM_RCU_NODES (NUM_RCU_LVL_0 + NUM_RCU_LVL_1 + NUM_RCU_LVL_2) +# define NUM_RCU_LVL_INIT { NUM_RCU_LVL_0, NUM_RCU_LVL_1, NUM_RCU_LVL_2 } +# define RCU_NODE_NAME_INIT { "rcu_node_0", "rcu_node_1", "rcu_node_2" } +# define RCU_FQS_NAME_INIT { "rcu_node_fqs_0", "rcu_node_fqs_1", "rcu_node_fqs_2" } +# define RCU_EXP_NAME_INIT { "rcu_node_exp_0", "rcu_node_exp_1", "rcu_node_exp_2" } +# define RCU_EXP_SCHED_NAME_INIT \ + { "rcu_node_exp_sched_0", "rcu_node_exp_sched_1", "rcu_node_exp_sched_2" } #elif NR_CPUS <= RCU_FANOUT_4 # define RCU_NUM_LVLS 4 # define NUM_RCU_LVL_0 1 # define NUM_RCU_LVL_1 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_3) # define NUM_RCU_LVL_2 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_2) # define NUM_RCU_LVL_3 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_1) -# define NUM_RCU_LVL_4 (NR_CPUS) +# define NUM_RCU_NODES (NUM_RCU_LVL_0 + NUM_RCU_LVL_1 + NUM_RCU_LVL_2 + NUM_RCU_LVL_3) +# define NUM_RCU_LVL_INIT { NUM_RCU_LVL_0, NUM_RCU_LVL_1, NUM_RCU_LVL_2, NUM_RCU_LVL_3 } +# define RCU_NODE_NAME_INIT { "rcu_node_0", "rcu_node_1", "rcu_node_2", "rcu_node_3" } +# define RCU_FQS_NAME_INIT { "rcu_node_fqs_0", "rcu_node_fqs_1", "rcu_node_fqs_2", "rcu_node_fqs_3" } +# define RCU_EXP_NAME_INIT { "rcu_node_exp_0", "rcu_node_exp_1", "rcu_node_exp_2", "rcu_node_exp_3" } +# define RCU_EXP_SCHED_NAME_INIT \ + { "rcu_node_exp_sched_0", "rcu_node_exp_sched_1", "rcu_node_exp_sched_2", "rcu_node_exp_sched_3" } #else # error "CONFIG_RCU_FANOUT insufficient for NR_CPUS" #endif /* #if (NR_CPUS) <= RCU_FANOUT_1 */ -#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) - extern int rcu_num_lvls; extern int rcu_num_nodes; @@ -236,6 +250,8 @@ struct rcu_node { int need_future_gp[2]; /* Counts of upcoming no-CB GP requests. */ raw_spinlock_t fqslock ____cacheline_internodealigned_in_smp; + + struct mutex exp_funnel_mutex ____cacheline_internodealigned_in_smp; } ____cacheline_internodealigned_in_smp; /* @@ -287,12 +303,13 @@ struct rcu_data { bool gpwrap; /* Possible gpnum/completed wrap. */ struct rcu_node *mynode; /* This CPU's leaf of hierarchy */ unsigned long grpmask; /* Mask to apply to leaf qsmask. */ -#ifdef CONFIG_RCU_CPU_STALL_INFO unsigned long ticks_this_gp; /* The number of scheduling-clock */ /* ticks this CPU has handled */ /* during and after the last grace */ /* period it is aware of. */ -#endif /* #ifdef CONFIG_RCU_CPU_STALL_INFO */ + struct cpu_stop_work exp_stop_work; + /* Expedited grace-period control */ + /* for CPU stopping. */ /* 2) batch handling */ /* @@ -355,11 +372,13 @@ struct rcu_data { unsigned long n_rp_nocb_defer_wakeup; unsigned long n_rp_need_nothing; - /* 6) _rcu_barrier() and OOM callbacks. */ + /* 6) _rcu_barrier(), OOM callbacks, and expediting. */ struct rcu_head barrier_head; #ifdef CONFIG_RCU_FAST_NO_HZ struct rcu_head oom_head; #endif /* #ifdef CONFIG_RCU_FAST_NO_HZ */ + struct mutex exp_funnel_mutex; + bool exp_done; /* Expedited QS for this CPU? */ /* 7) Callback offloading. */ #ifdef CONFIG_RCU_NOCB_CPU @@ -387,9 +406,7 @@ struct rcu_data { #endif /* #ifdef CONFIG_RCU_NOCB_CPU */ /* 8) RCU CPU stall data. */ -#ifdef CONFIG_RCU_CPU_STALL_INFO unsigned int softirq_snap; /* Snapshot of softirq activity. */ -#endif /* #ifdef CONFIG_RCU_CPU_STALL_INFO */ int cpu; struct rcu_state *rsp; @@ -442,9 +459,9 @@ do { \ */ struct rcu_state { struct rcu_node node[NUM_RCU_NODES]; /* Hierarchy. */ - struct rcu_node *level[RCU_NUM_LVLS]; /* Hierarchy levels. */ - u32 levelcnt[MAX_RCU_LVLS + 1]; /* # nodes in each level. */ - u8 levelspread[RCU_NUM_LVLS]; /* kids/node in each level. */ + struct rcu_node *level[RCU_NUM_LVLS + 1]; + /* Hierarchy levels (+1 to */ + /* shut bogus gcc warning) */ u8 flavor_mask; /* bit in flavor mask. */ struct rcu_data __percpu *rda; /* pointer of percu rcu_data. */ void (*call)(struct rcu_head *head, /* call_rcu() flavor. */ @@ -479,21 +496,18 @@ struct rcu_state { struct mutex barrier_mutex; /* Guards barrier fields. */ atomic_t barrier_cpu_count; /* # CPUs waiting on. */ struct completion barrier_completion; /* Wake at barrier end. */ - unsigned long n_barrier_done; /* ++ at start and end of */ + unsigned long barrier_sequence; /* ++ at start and end of */ /* _rcu_barrier(). */ /* End of fields guarded by barrier_mutex. */ - atomic_long_t expedited_start; /* Starting ticket. */ - atomic_long_t expedited_done; /* Done ticket. */ - atomic_long_t expedited_wrap; /* # near-wrap incidents. */ - atomic_long_t expedited_tryfail; /* # acquisition failures. */ + unsigned long expedited_sequence; /* Take a ticket. */ + atomic_long_t expedited_workdone0; /* # done by others #0. */ atomic_long_t expedited_workdone1; /* # done by others #1. */ atomic_long_t expedited_workdone2; /* # done by others #2. */ + atomic_long_t expedited_workdone3; /* # done by others #3. */ atomic_long_t expedited_normal; /* # fallbacks to normal. */ - atomic_long_t expedited_stoppedcpus; /* # successful stop_cpus. */ - atomic_long_t expedited_done_tries; /* # tries to update _done. */ - atomic_long_t expedited_done_lost; /* # times beaten to _done. */ - atomic_long_t expedited_done_exit; /* # times exited _done loop. */ + atomic_t expedited_need_qs; /* # CPUs left to check in. */ + wait_queue_head_t expedited_wq; /* Wait for check-ins. */ unsigned long jiffies_force_qs; /* Time at which to invoke */ /* force_quiescent_state(). */ @@ -527,7 +541,11 @@ struct rcu_state { /* Values for rcu_state structure's gp_flags field. */ #define RCU_GP_WAIT_INIT 0 /* Initial state. */ #define RCU_GP_WAIT_GPS 1 /* Wait for grace-period start. */ -#define RCU_GP_WAIT_FQS 2 /* Wait for force-quiescent-state time. */ +#define RCU_GP_DONE_GPS 2 /* Wait done for grace-period start. */ +#define RCU_GP_WAIT_FQS 3 /* Wait for force-quiescent-state time. */ +#define RCU_GP_DOING_FQS 4 /* Wait done for force-quiescent-state time. */ +#define RCU_GP_CLEANUP 5 /* Grace-period cleanup started. */ +#define RCU_GP_CLEANED 6 /* Grace-period cleanup complete. */ extern struct list_head rcu_struct_flavors; @@ -635,3 +653,15 @@ static inline void rcu_nocb_q_lengths(struct rcu_data *rdp, long *ql, long *qll) #endif /* #else #ifdef CONFIG_RCU_NOCB_CPU */ } #endif /* #ifdef CONFIG_RCU_TRACE */ + +/* + * Place this after a lock-acquisition primitive to guarantee that + * an UNLOCK+LOCK pair act as a full barrier. This guarantee applies + * if the UNLOCK and LOCK are executed by the same CPU or if the + * UNLOCK and LOCK operate on the same lock variable. + */ +#ifdef CONFIG_PPC +#define smp_mb__after_unlock_lock() smp_mb() /* Full ordering for lock. */ +#else /* #ifdef CONFIG_PPC */ +#define smp_mb__after_unlock_lock() do { } while (0) +#endif /* #else #ifdef CONFIG_PPC */ |