X-Git-Url: https://gerrit.opnfv.org/gerrit/gitweb?a=blobdiff_plain;f=kernel%2Fkernel%2Frcu%2Ftree.h;fp=kernel%2Fkernel%2Frcu%2Ftree.h;h=c75834d8de24bec634713c8a5a0e4afee6de8521;hb=e09b41010ba33a20a87472ee821fa407a5b8da36;hp=8a9f0d3640de6ebd8e0b7eb5befd0d01775ea323;hpb=f93b97fd65072de626c074dbe099a1fff05ce060;p=kvmfornfv.git diff --git a/kernel/kernel/rcu/tree.h b/kernel/kernel/rcu/tree.h index 8a9f0d364..c75834d8d 100644 --- a/kernel/kernel/rcu/tree.h +++ b/kernel/kernel/rcu/tree.h @@ -27,7 +27,8 @@ #include #include #include -#include +#include +#include /* * Define shape of hierarchy based on NR_CPUS, CONFIG_RCU_FANOUT, and @@ -36,47 +37,74 @@ * In practice, this did work well going from three levels to four. * Of course, your mileage may vary. */ -#define MAX_RCU_LVLS 4 -#define RCU_FANOUT_1 (CONFIG_RCU_FANOUT_LEAF) -#define RCU_FANOUT_2 (RCU_FANOUT_1 * CONFIG_RCU_FANOUT) -#define RCU_FANOUT_3 (RCU_FANOUT_2 * CONFIG_RCU_FANOUT) -#define RCU_FANOUT_4 (RCU_FANOUT_3 * CONFIG_RCU_FANOUT) + +#ifdef CONFIG_RCU_FANOUT +#define RCU_FANOUT CONFIG_RCU_FANOUT +#else /* #ifdef CONFIG_RCU_FANOUT */ +# ifdef CONFIG_64BIT +# define RCU_FANOUT 64 +# else +# define RCU_FANOUT 32 +# endif +#endif /* #else #ifdef CONFIG_RCU_FANOUT */ + +#ifdef CONFIG_RCU_FANOUT_LEAF +#define RCU_FANOUT_LEAF CONFIG_RCU_FANOUT_LEAF +#else /* #ifdef CONFIG_RCU_FANOUT_LEAF */ +# ifdef CONFIG_64BIT +# define RCU_FANOUT_LEAF 64 +# else +# define RCU_FANOUT_LEAF 32 +# endif +#endif /* #else #ifdef CONFIG_RCU_FANOUT_LEAF */ + +#define RCU_FANOUT_1 (RCU_FANOUT_LEAF) +#define RCU_FANOUT_2 (RCU_FANOUT_1 * RCU_FANOUT) +#define RCU_FANOUT_3 (RCU_FANOUT_2 * RCU_FANOUT) +#define RCU_FANOUT_4 (RCU_FANOUT_3 * RCU_FANOUT) #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" } #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" } #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" } #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" } #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; @@ -136,16 +164,21 @@ struct rcu_node { /* an rcu_data structure, otherwise, each */ /* bit corresponds to a child rcu_node */ /* structure. */ - unsigned long expmask; /* Groups that have ->blkd_tasks */ - /* elements that need to drain to allow the */ - /* current expedited grace period to */ - /* complete (only for PREEMPT_RCU). */ unsigned long qsmaskinit; - /* Per-GP initial value for qsmask & expmask. */ + /* Per-GP initial value for qsmask. */ /* Initialized from ->qsmaskinitnext at the */ /* beginning of each grace period. */ unsigned long qsmaskinitnext; /* Online CPUs for next grace period. */ + unsigned long expmask; /* CPUs or groups that need to check in */ + /* to allow the current expedited GP */ + /* to complete. */ + unsigned long expmaskinit; + /* Per-GP initial values for expmask. */ + /* Initialized from ->expmaskinitnext at the */ + /* beginning of each expedited GP. */ + unsigned long expmaskinitnext; + /* Online CPUs for next expedited GP. */ 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. */ @@ -171,7 +204,6 @@ struct rcu_node { /* 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 */ @@ -209,14 +241,15 @@ struct rcu_node { unsigned long n_balk_nos; /* Refused to boost: not sure why, though. */ /* This can happen due to race conditions. */ -#endif /* #ifdef CONFIG_RCU_BOOST */ #ifdef CONFIG_RCU_NOCB_CPU - struct swait_head nocb_gp_wq[2]; + struct swait_queue_head nocb_gp_wq[2]; /* Place for rcu_nocb_kthread() to wait GP. */ #endif /* #ifdef CONFIG_RCU_NOCB_CPU */ 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; /* @@ -246,6 +279,18 @@ struct rcu_node { for ((rnp) = (rsp)->level[rcu_num_lvls - 1]; \ (rnp) < &(rsp)->node[rcu_num_nodes]; (rnp)++) +/* + * Union to allow "aggregate OR" operation on the need for a quiescent + * state by the normal and expedited grace periods. + */ +union rcu_noqs { + struct { + u8 norm; + u8 exp; + } b; /* Bits. */ + u16 s; /* Set of bits, aggregate OR here. */ +}; + /* Index values for nxttail array in struct rcu_data. */ #define RCU_DONE_TAIL 0 /* Also RCU_WAIT head. */ #define RCU_WAIT_TAIL 1 /* Also RCU_NEXT_READY head. */ @@ -262,18 +307,16 @@ struct rcu_data { /* is aware of having started. */ unsigned long rcu_qs_ctr_snap;/* Snapshot of rcu_qs_ctr to check */ /* for rcu_all_qs() invocations. */ - bool passed_quiesce; /* User-mode/idle loop etc. */ - bool qs_pending; /* Core waits for quiesc state. */ + union rcu_noqs cpu_no_qs; /* No QSes yet for this CPU. */ + bool core_needs_qs; /* Core waits for quiesc state. */ bool beenonline; /* CPU online at least once. */ 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 */ /* 2) batch handling */ /* @@ -327,7 +370,7 @@ struct rcu_data { /* 5) __rcu_pending() statistics. */ unsigned long n_rcu_pending; /* rcu_pending() calls since boot. */ - unsigned long n_rp_qs_pending; + unsigned long n_rp_core_needs_qs; unsigned long n_rp_report_qs; unsigned long n_rp_cb_ready; unsigned long n_rp_cpu_needs_gp; @@ -336,11 +379,12 @@ 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; /* 7) Callback offloading. */ #ifdef CONFIG_RCU_NOCB_CPU @@ -350,7 +394,7 @@ struct rcu_data { atomic_long_t nocb_q_count_lazy; /* invocation (all stages). */ struct rcu_head *nocb_follower_head; /* CBs ready to invoke. */ struct rcu_head **nocb_follower_tail; - struct swait_head nocb_wq; /* For nocb kthreads to sleep on. */ + struct swait_queue_head nocb_wq; /* For nocb kthreads to sleep on. */ struct task_struct *nocb_kthread; int nocb_defer_wakeup; /* Defer wakeup of nocb_kthread. */ @@ -368,21 +412,12 @@ 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; }; -/* Values for fqs_state field in struct rcu_state. */ -#define RCU_GP_IDLE 0 /* No grace period in progress. */ -#define RCU_GP_INIT 1 /* Grace period being initialized. */ -#define RCU_SAVE_DYNTICK 2 /* Need to scan dyntick state. */ -#define RCU_FORCE_QS 3 /* Need to force quiescent state. */ -#define RCU_SIGNAL_INIT RCU_SAVE_DYNTICK - /* Values for nocb_defer_wakeup field in struct rcu_data. */ #define RCU_NOGP_WAKE_NOT 0 #define RCU_NOGP_WAKE 1 @@ -423,23 +458,22 @@ 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. */ - void (*func)(struct rcu_head *head)); + call_rcu_func_t call; /* call_rcu() flavor. */ + int ncpus; /* # CPUs seen so far. */ /* The following fields are guarded by the root rcu_node's lock. */ - u8 fqs_state ____cacheline_internodealigned_in_smp; - /* Force QS state. */ - u8 boost; /* Subject to priority boost. */ + u8 boost ____cacheline_internodealigned_in_smp; + /* Subject to priority boost. */ unsigned long gpnum; /* Current gp number. */ unsigned long completed; /* # of last completed gp. */ struct task_struct *gp_kthread; /* Task for grace periods. */ - struct swait_head gp_wq; /* Where GP task waits. */ + struct swait_queue_head gp_wq; /* Where GP task waits. */ short gp_flags; /* Commands for GP task. */ short gp_state; /* GP kthread sleep state. */ @@ -460,21 +494,19 @@ 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. */ + struct swait_queue_head expedited_wq; /* Wait for check-ins. */ + int ncpus_snap; /* # CPUs seen last time. */ unsigned long jiffies_force_qs; /* Time at which to invoke */ /* force_quiescent_state(). */ @@ -505,10 +537,14 @@ struct rcu_state { #define RCU_GP_FLAG_INIT 0x1 /* Need grace-period initialization. */ #define RCU_GP_FLAG_FQS 0x2 /* Need grace-period quiescent-state forcing. */ -/* Values for rcu_state structure's gp_flags field. */ -#define RCU_GP_WAIT_INIT 0 /* Initial state. */ +/* Values for rcu_state structure's gp_state field. */ +#define RCU_GP_IDLE 0 /* Initial state and no GP in progress. */ #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; @@ -520,14 +556,13 @@ extern struct list_head rcu_struct_flavors; * RCU implementation internal declarations: */ extern struct rcu_state rcu_sched_state; -DECLARE_PER_CPU(struct rcu_data, rcu_sched_data); +#ifndef CONFIG_PREEMPT_RT_FULL extern struct rcu_state rcu_bh_state; -DECLARE_PER_CPU(struct rcu_data, rcu_bh_data); +#endif #ifdef CONFIG_PREEMPT_RCU extern struct rcu_state rcu_preempt_state; -DECLARE_PER_CPU(struct rcu_data, rcu_preempt_data); #endif /* #ifdef CONFIG_PREEMPT_RCU */ DECLARE_PER_CPU(unsigned int, rcu_cpu_kthread_status); @@ -546,9 +581,10 @@ static bool rcu_preempt_has_tasks(struct rcu_node *rnp); #endif /* #ifdef CONFIG_HOTPLUG_CPU */ static void rcu_print_detail_task_stall(struct rcu_state *rsp); static int rcu_print_task_stall(struct rcu_node *rnp); +static int rcu_print_task_exp_stall(struct rcu_node *rnp); static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp); static void rcu_preempt_check_callbacks(void); -void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu)); +void call_rcu(struct rcu_head *head, rcu_callback_t func); 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); @@ -571,7 +607,8 @@ static void zero_cpu_stall_ticks(struct rcu_data *rdp); static void increment_cpu_stall_ticks(void); static bool rcu_nocb_cpu_needs_barrier(struct rcu_state *rsp, int cpu); static void rcu_nocb_gp_set(struct rcu_node *rnp, int nrq); -static void rcu_nocb_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp); +static struct swait_queue_head *rcu_nocb_gp_get(struct rcu_node *rnp); +static void rcu_nocb_gp_cleanup(struct swait_queue_head *sq); static void rcu_init_one_nocb(struct rcu_node *rnp); static bool __call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *rhp, bool lazy, unsigned long flags); @@ -616,3 +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 */