diff options
Diffstat (limited to 'kernel/rcu/tree.h')
-rw-r--r-- | kernel/rcu/tree.h | 163 |
1 files changed, 20 insertions, 143 deletions
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h index ec62a05bfdb3..ba38262c3554 100644 --- a/kernel/rcu/tree.h +++ b/kernel/rcu/tree.h @@ -30,80 +30,9 @@ #include <linux/seqlock.h> #include <linux/swait.h> #include <linux/stop_machine.h> +#include <linux/rcu_node_tree.h> -/* - * Define shape of hierarchy based on NR_CPUS, CONFIG_RCU_FANOUT, and - * CONFIG_RCU_FANOUT_LEAF. - * In theory, it should be possible to add more levels straightforwardly. - * In practice, this did work well going from three levels to four. - * Of course, your mileage may vary. - */ - -#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_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" } -#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_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" } -#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_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" } -#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_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" } -#else -# error "CONFIG_RCU_FANOUT insufficient for NR_CPUS" -#endif /* #if (NR_CPUS) <= RCU_FANOUT_1 */ - -extern int rcu_num_lvls; -extern int rcu_num_nodes; +#include "rcu_segcblist.h" /* * Dynticks per-CPU state. @@ -113,6 +42,9 @@ struct rcu_dynticks { /* Process level is worth LLONG_MAX/2. */ int dynticks_nmi_nesting; /* Track NMI nesting level. */ atomic_t dynticks; /* Even value for idle, else odd. */ + bool rcu_need_heavy_qs; /* GP old, need heavy quiescent state. */ + unsigned long rcu_qs_ctr; /* Light universal quiescent state ctr. */ + bool rcu_urgent_qs; /* GP old need light quiescent state. */ #ifdef CONFIG_NO_HZ_FULL_SYSIDLE long long dynticks_idle_nesting; /* irq/process nesting level from idle. */ @@ -262,41 +194,6 @@ struct rcu_node { #define leaf_node_cpu_bit(rnp, cpu) (1UL << ((cpu) - (rnp)->grplo)) /* - * Do a full breadth-first scan of the rcu_node structures for the - * specified rcu_state structure. - */ -#define rcu_for_each_node_breadth_first(rsp, rnp) \ - for ((rnp) = &(rsp)->node[0]; \ - (rnp) < &(rsp)->node[rcu_num_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[rcu_num_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[rcu_num_lvls - 1]; \ - (rnp) < &(rsp)->node[rcu_num_nodes]; (rnp)++) - -/* - * Iterate over all possible CPUs in a leaf RCU node. - */ -#define for_each_leaf_node_possible_cpu(rnp, cpu) \ - for ((cpu) = cpumask_next(rnp->grplo - 1, cpu_possible_mask); \ - cpu <= rnp->grphi; \ - cpu = cpumask_next((cpu), cpu_possible_mask)) - -/* * Union to allow "aggregate OR" operation on the need for a quiescent * state by the normal and expedited grace periods. */ @@ -336,34 +233,9 @@ struct rcu_data { /* period it is aware of. */ /* 2) batch handling */ - /* - * If nxtlist is not NULL, it is partitioned as follows. - * Any of the partitions might be empty, in which case the - * pointer to that partition will be equal to the pointer for - * the following partition. When the list is empty, all of - * the nxttail elements point to the ->nxtlist pointer itself, - * which in that case is NULL. - * - * [nxtlist, *nxttail[RCU_DONE_TAIL]): - * Entries that batch # <= ->completed - * The grace period for these entries has completed, and - * the other grace-period-completed entries may be moved - * here temporarily in rcu_process_callbacks(). - * [*nxttail[RCU_DONE_TAIL], *nxttail[RCU_WAIT_TAIL]): - * Entries that batch # <= ->completed - 1: waiting for current GP - * [*nxttail[RCU_WAIT_TAIL], *nxttail[RCU_NEXT_READY_TAIL]): - * Entries known to have arrived before current GP ended - * [*nxttail[RCU_NEXT_READY_TAIL], *nxttail[RCU_NEXT_TAIL]): - * Entries that might have arrived after current GP ended - * Note that the value of *nxttail[RCU_NEXT_TAIL] will - * always be NULL, as this is the end of the list. - */ - struct rcu_head *nxtlist; - struct rcu_head **nxttail[RCU_NEXT_SIZE]; - unsigned long nxtcompleted[RCU_NEXT_SIZE]; - /* grace periods for sublists. */ - long qlen_lazy; /* # of lazy queued callbacks */ - long qlen; /* # of queued callbacks, incl lazy */ + struct rcu_segcblist cblist; /* Segmented callback list, with */ + /* different callbacks waiting for */ + /* different grace periods. */ long qlen_last_fqs_check; /* qlen at last check for QS forcing */ unsigned long n_cbs_invoked; /* count of RCU cbs invoked. */ @@ -482,7 +354,6 @@ struct rcu_state { 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. */ call_rcu_func_t call; /* call_rcu() flavor. */ int ncpus; /* # CPUs seen so far. */ @@ -502,14 +373,11 @@ struct rcu_state { raw_spinlock_t orphan_lock ____cacheline_internodealigned_in_smp; /* Protect following fields. */ - struct rcu_head *orphan_nxtlist; /* Orphaned callbacks that */ + struct rcu_cblist orphan_pend; /* Orphaned callbacks that */ /* need a grace period. */ - struct rcu_head **orphan_nxttail; /* Tail of above. */ - struct rcu_head *orphan_donelist; /* Orphaned callbacks that */ + struct rcu_cblist orphan_done; /* Orphaned callbacks that */ /* are ready to invoke. */ - struct rcu_head **orphan_donetail; /* Tail of above. */ - long qlen_lazy; /* Number of lazy callbacks. */ - long qlen; /* Total number of callbacks. */ + /* (Contains counts.) */ /* End of fields guarded by orphan_lock. */ struct mutex barrier_mutex; /* Guards barrier fields. */ @@ -596,6 +464,7 @@ extern struct rcu_state rcu_preempt_state; #endif /* #ifdef CONFIG_PREEMPT_RCU */ int rcu_dynticks_snap(struct rcu_dynticks *rdtp); +bool rcu_eqs_special_set(int cpu); #ifdef CONFIG_RCU_BOOST DECLARE_PER_CPU(unsigned int, rcu_cpu_kthread_status); @@ -673,6 +542,14 @@ static bool rcu_nohz_full_cpu(struct rcu_state *rsp); static void rcu_dynticks_task_enter(void); static void rcu_dynticks_task_exit(void); +#ifdef CONFIG_SRCU +void srcu_online_cpu(unsigned int cpu); +void srcu_offline_cpu(unsigned int cpu); +#else /* #ifdef CONFIG_SRCU */ +void srcu_online_cpu(unsigned int cpu) { } +void srcu_offline_cpu(unsigned int cpu) { } +#endif /* #else #ifdef CONFIG_SRCU */ + #endif /* #ifndef RCU_TREE_NONCORE */ #ifdef CONFIG_RCU_TRACE |