diff options
25 files changed, 466 insertions, 210 deletions
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 742f69d..d8186da 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -3296,18 +3296,35 @@ bytes respectively. Such letter suffixes can also be entirely omitted. rcutorture.verbose= [KNL] Enable additional printk() statements. + rcupdate.rcu_cpu_stall_suppress= [KNL] + Suppress RCU CPU stall warning messages. + + rcupdate.rcu_cpu_stall_timeout= [KNL] + Set timeout for RCU CPU stall warning messages. + rcupdate.rcu_expedited= [KNL] Use expedited grace-period primitives, for example, synchronize_rcu_expedited() instead of synchronize_rcu(). This reduces latency, but can increase CPU utilization, degrade real-time latency, and degrade energy efficiency. - - rcupdate.rcu_cpu_stall_suppress= [KNL] - Suppress RCU CPU stall warning messages. - - rcupdate.rcu_cpu_stall_timeout= [KNL] - Set timeout for RCU CPU stall warning messages. + No effect on CONFIG_TINY_RCU kernels. + + rcupdate.rcu_normal= [KNL] + Use only normal grace-period primitives, + for example, synchronize_rcu() instead of + synchronize_rcu_expedited(). This improves + real-time latency, CPU utilization, and + energy efficiency, but can expose users to + increased grace-period latency. This parameter + overrides rcupdate.rcu_expedited. No effect on + CONFIG_TINY_RCU kernels. + + rcupdate.rcu_normal_after_boot= [KNL] + Once boot has completed (that is, after + rcu_end_inkernel_boot() has been invoked), use + only normal grace-period primitives. No effect + on CONFIG_TINY_RCU kernels. rcupdate.rcu_task_stall_timeout= [KNL] Set timeout in jiffies for RCU task stall warning diff --git a/include/linux/list.h b/include/linux/list.h index 993395a..5356f4d 100644 --- a/include/linux/list.h +++ b/include/linux/list.h @@ -24,7 +24,7 @@ static inline void INIT_LIST_HEAD(struct list_head *list) { - list->next = list; + WRITE_ONCE(list->next, list); list->prev = list; } @@ -42,7 +42,7 @@ static inline void __list_add(struct list_head *new, next->prev = new; new->next = next; new->prev = prev; - prev->next = new; + WRITE_ONCE(prev->next, new); } #else extern void __list_add(struct list_head *new, @@ -186,7 +186,7 @@ static inline int list_is_last(const struct list_head *list, */ static inline int list_empty(const struct list_head *head) { - return head->next == head; + return READ_ONCE(head->next) == head; } /** @@ -608,7 +608,7 @@ static inline int hlist_unhashed(const struct hlist_node *h) static inline int hlist_empty(const struct hlist_head *h) { - return !h->first; + return !READ_ONCE(h->first); } static inline void __hlist_del(struct hlist_node *n) @@ -642,7 +642,7 @@ static inline void hlist_add_head(struct hlist_node *n, struct hlist_head *h) n->next = first; if (first) first->pprev = &n->next; - h->first = n; + WRITE_ONCE(h->first, n); n->pprev = &h->first; } @@ -653,14 +653,14 @@ static inline void hlist_add_before(struct hlist_node *n, n->pprev = next->pprev; n->next = next; next->pprev = &n->next; - *(n->pprev) = n; + WRITE_ONCE(*(n->pprev), n); } static inline void hlist_add_behind(struct hlist_node *n, struct hlist_node *prev) { n->next = prev->next; - prev->next = n; + WRITE_ONCE(prev->next, n); n->pprev = &prev->next; if (n->next) diff --git a/include/linux/list_bl.h b/include/linux/list_bl.h index 8132214..ee7229a 100644 --- a/include/linux/list_bl.h +++ b/include/linux/list_bl.h @@ -70,7 +70,7 @@ static inline void hlist_bl_set_first(struct hlist_bl_head *h, static inline int hlist_bl_empty(const struct hlist_bl_head *h) { - return !((unsigned long)h->first & ~LIST_BL_LOCKMASK); + return !((unsigned long)READ_ONCE(h->first) & ~LIST_BL_LOCKMASK); } static inline void hlist_bl_add_head(struct hlist_bl_node *n, diff --git a/include/linux/list_nulls.h b/include/linux/list_nulls.h index 444d2b1..b01fe10 100644 --- a/include/linux/list_nulls.h +++ b/include/linux/list_nulls.h @@ -57,7 +57,7 @@ static inline int hlist_nulls_unhashed(const struct hlist_nulls_node *h) static inline int hlist_nulls_empty(const struct hlist_nulls_head *h) { - return is_a_nulls(h->first); + return is_a_nulls(READ_ONCE(h->first)); } static inline void hlist_nulls_add_head(struct hlist_nulls_node *n, diff --git a/include/linux/rculist.h b/include/linux/rculist.h index 5ed5409..14ec165 100644 --- a/include/linux/rculist.h +++ b/include/linux/rculist.h @@ -179,32 +179,31 @@ static inline void list_replace_rcu(struct list_head *old, } /** - * list_splice_init_rcu - splice an RCU-protected list into an existing list. + * __list_splice_init_rcu - join an RCU-protected list into an existing list. * @list: the RCU-protected list to splice - * @head: the place in the list to splice the first list into + * @prev: points to the last element of the existing list + * @next: points to the first element of the existing list * @sync: function to sync: synchronize_rcu(), synchronize_sched(), ... * - * @head can be RCU-read traversed concurrently with this function. + * The list pointed to by @prev and @next can be RCU-read traversed + * concurrently with this function. * * Note that this function blocks. * - * Important note: the caller must take whatever action is necessary to - * prevent any other updates to @head. In principle, it is possible - * to modify the list as soon as sync() begins execution. - * If this sort of thing becomes necessary, an alternative version - * based on call_rcu() could be created. But only if -really- - * needed -- there is no shortage of RCU API members. + * Important note: the caller must take whatever action is necessary to prevent + * any other updates to the existing list. In principle, it is possible to + * modify the list as soon as sync() begins execution. If this sort of thing + * becomes necessary, an alternative version based on call_rcu() could be + * created. But only if -really- needed -- there is no shortage of RCU API + * members. */ -static inline void list_splice_init_rcu(struct list_head *list, - struct list_head *head, - void (*sync)(void)) +static inline void __list_splice_init_rcu(struct list_head *list, + struct list_head *prev, + struct list_head *next, + void (*sync)(void)) { struct list_head *first = list->next; struct list_head *last = list->prev; - struct list_head *at = head->next; - - if (list_empty(list)) - return; /* * "first" and "last" tracking list, so initialize it. RCU readers @@ -231,10 +230,40 @@ static inline void list_splice_init_rcu(struct list_head *list, * this function. */ - last->next = at; - rcu_assign_pointer(list_next_rcu(head), first); - first->prev = head; - at->prev = last; + last->next = next; + rcu_assign_pointer(list_next_rcu(prev), first); + first->prev = prev; + next->prev = last; +} + +/** + * list_splice_init_rcu - splice an RCU-protected list into an existing list, + * designed for stacks. + * @list: the RCU-protected list to splice + * @head: the place in the existing list to splice the first list into + * @sync: function to sync: synchronize_rcu(), synchronize_sched(), ... + */ +static inline void list_splice_init_rcu(struct list_head *list, + struct list_head *head, + void (*sync)(void)) +{ + if (!list_empty(list)) + __list_splice_init_rcu(list, head, head->next, sync); +} + +/** + * list_splice_tail_init_rcu - splice an RCU-protected list into an existing + * list, designed for queues. + * @list: the RCU-protected list to splice + * @head: the place in the existing list to splice the first list into + * @sync: function to sync: synchronize_rcu(), synchronize_sched(), ... + */ +static inline void list_splice_tail_init_rcu(struct list_head *list, + struct list_head *head, + void (*sync)(void)) +{ + if (!list_empty(list)) + __list_splice_init_rcu(list, head->prev, head, sync); } /** @@ -305,6 +334,42 @@ static inline void list_splice_init_rcu(struct list_head *list, pos = list_entry_rcu(pos->member.next, typeof(*pos), member)) /** + * list_entry_lockless - get the struct for this entry + * @ptr: the &struct list_head pointer. + * @type: the type of the struct this is embedded in. + * @member: the name of the list_head within the struct. + * + * This primitive may safely run concurrently with the _rcu list-mutation + * primitives such as list_add_rcu(), but requires some implicit RCU + * read-side guarding. One example is running within a special + * exception-time environment where preemption is disabled and where + * lockdep cannot be invoked (in which case updaters must use RCU-sched, + * as in synchronize_sched(), call_rcu_sched(), and friends). Another + * example is when items are added to the list, but never deleted. + */ +#define list_entry_lockless(ptr, type, member) \ + container_of((typeof(ptr))lockless_dereference(ptr), type, member) + +/** + * list_for_each_entry_lockless - iterate over rcu list of given type + * @pos: the type * to use as a loop cursor. + * @head: the head for your list. + * @member: the name of the list_struct within the struct. + * + * This primitive may safely run concurrently with the _rcu list-mutation + * primitives such as list_add_rcu(), but requires some implicit RCU + * read-side guarding. One example is running within a special + * exception-time environment where preemption is disabled and where + * lockdep cannot be invoked (in which case updaters must use RCU-sched, + * as in synchronize_sched(), call_rcu_sched(), and friends). Another + * example is when items are added to the list, but never deleted. + */ +#define list_for_each_entry_lockless(pos, head, member) \ + for (pos = list_entry_lockless((head)->next, typeof(*pos), member); \ + &pos->member != (head); \ + pos = list_entry_lockless(pos->member.next, typeof(*pos), member)) + +/** * list_for_each_entry_continue_rcu - continue iteration over list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index a0189ba..14e6f47 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -48,10 +48,17 @@ #include <asm/barrier.h> +#ifndef CONFIG_TINY_RCU extern int rcu_expedited; /* for sysctl */ +extern int rcu_normal; /* also for sysctl */ +#endif /* #ifndef CONFIG_TINY_RCU */ #ifdef CONFIG_TINY_RCU /* Tiny RCU doesn't expedite, as its purpose in life is instead to be tiny. */ +static inline bool rcu_gp_is_normal(void) /* Internal RCU use. */ +{ + return true; +} static inline bool rcu_gp_is_expedited(void) /* Internal RCU use. */ { return false; @@ -65,6 +72,7 @@ static inline void rcu_unexpedite_gp(void) { } #else /* #ifdef CONFIG_TINY_RCU */ +bool rcu_gp_is_normal(void); /* Internal RCU use. */ bool rcu_gp_is_expedited(void); /* Internal RCU use. */ void rcu_expedite_gp(void); void rcu_unexpedite_gp(void); @@ -321,7 +329,6 @@ static inline int rcu_preempt_depth(void) /* Internal to kernel */ void rcu_init(void); -void rcu_end_inkernel_boot(void); void rcu_sched_qs(void); void rcu_bh_qs(void); void rcu_check_callbacks(int user); @@ -329,6 +336,12 @@ struct notifier_block; int rcu_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu); +#ifndef CONFIG_TINY_RCU +void rcu_end_inkernel_boot(void); +#else /* #ifndef CONFIG_TINY_RCU */ +static inline void rcu_end_inkernel_boot(void) { } +#endif /* #ifndef CONFIG_TINY_RCU */ + #ifdef CONFIG_RCU_STALL_COMMON void rcu_sysrq_start(void); void rcu_sysrq_end(void); @@ -379,9 +392,9 @@ static inline void rcu_init_nohz(void) */ #define RCU_NONIDLE(a) \ do { \ - rcu_irq_enter(); \ + rcu_irq_enter_irqson(); \ do { a; } while (0); \ - rcu_irq_exit(); \ + rcu_irq_exit_irqson(); \ } while (0) /* @@ -741,7 +754,7 @@ static inline void rcu_preempt_sleep_check(void) * The tracing infrastructure traces RCU (we want that), but unfortunately * some of the RCU checks causes tracing to lock up the system. * - * The tracing version of rcu_dereference_raw() must not call + * The no-tracing version of rcu_dereference_raw() must not call * rcu_read_lock_held(). */ #define rcu_dereference_raw_notrace(p) __rcu_dereference_check((p), 1, __rcu) diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h index 4c1aaf9..64809ae 100644 --- a/include/linux/rcutiny.h +++ b/include/linux/rcutiny.h @@ -181,6 +181,14 @@ static inline void rcu_irq_enter(void) { } +static inline void rcu_irq_exit_irqson(void) +{ +} + +static inline void rcu_irq_enter_irqson(void) +{ +} + static inline void rcu_irq_exit(void) { } diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h index 60d15a0..ad1eda9 100644 --- a/include/linux/rcutree.h +++ b/include/linux/rcutree.h @@ -37,7 +37,7 @@ void rcu_cpu_stall_reset(void); /* * Note a virtualization-based context switch. This is simply a * wrapper around rcu_note_context_switch(), which allows TINY_RCU - * to save a few bytes. + * to save a few bytes. The caller must have disabled interrupts. */ static inline void rcu_virt_note_context_switch(int cpu) { @@ -97,6 +97,8 @@ void rcu_idle_enter(void); void rcu_idle_exit(void); void rcu_irq_enter(void); void rcu_irq_exit(void); +void rcu_irq_enter_irqson(void); +void rcu_irq_exit_irqson(void); void exit_rcu(void); diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index 696a339c..7834a8a 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -171,8 +171,8 @@ extern void syscall_unregfunc(void); TP_PROTO(data_proto), \ TP_ARGS(data_args), \ TP_CONDITION(cond), \ - rcu_irq_enter(), \ - rcu_irq_exit()); \ + rcu_irq_enter_irqson(), \ + rcu_irq_exit_irqson()); \ } #else #define __DECLARE_TRACE_RCU(name, proto, args, cond, data_proto, data_args) diff --git a/init/main.c b/init/main.c index 9e64d70..c6ebefa 100644 --- a/init/main.c +++ b/init/main.c @@ -943,6 +943,8 @@ static int __ref kernel_init(void *unused) flush_delayed_fput(); + rcu_end_inkernel_boot(); + if (ramdisk_execute_command) { ret = run_init_process(ramdisk_execute_command); if (!ret) diff --git a/kernel/ksysfs.c b/kernel/ksysfs.c index e83b264..152da4a 100644 --- a/kernel/ksysfs.c +++ b/kernel/ksysfs.c @@ -20,7 +20,7 @@ #include <linux/capability.h> #include <linux/compiler.h> -#include <linux/rcupdate.h> /* rcu_expedited */ +#include <linux/rcupdate.h> /* rcu_expedited and rcu_normal */ #define KERNEL_ATTR_RO(_name) \ static struct kobj_attribute _name##_attr = __ATTR_RO(_name) @@ -144,11 +144,12 @@ static ssize_t fscaps_show(struct kobject *kobj, } KERNEL_ATTR_RO(fscaps); +#ifndef CONFIG_TINY_RCU int rcu_expedited; static ssize_t rcu_expedited_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { - return sprintf(buf, "%d\n", rcu_expedited); + return sprintf(buf, "%d\n", READ_ONCE(rcu_expedited)); } static ssize_t rcu_expedited_store(struct kobject *kobj, struct kobj_attribute *attr, @@ -161,6 +162,24 @@ static ssize_t rcu_expedited_store(struct kobject *kobj, } KERNEL_ATTR_RW(rcu_expedited); +int rcu_normal; +static ssize_t rcu_normal_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + return sprintf(buf, "%d\n", READ_ONCE(rcu_normal)); +} +static ssize_t rcu_normal_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t count) +{ + if (kstrtoint(buf, 0, &rcu_normal)) + return -EINVAL; + + return count; +} +KERNEL_ATTR_RW(rcu_normal); +#endif /* #ifndef CONFIG_TINY_RCU */ + /* * Make /sys/kernel/notes give the raw contents of our kernel .notes section. */ @@ -202,7 +221,10 @@ static struct attribute * kernel_attrs[] = { &kexec_crash_size_attr.attr, &vmcoreinfo_attr.attr, #endif +#ifndef CONFIG_TINY_RCU &rcu_expedited_attr.attr, + &rcu_normal_attr.attr, +#endif NULL }; diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c index d89328e..d2988d0 100644 --- a/kernel/rcu/rcutorture.c +++ b/kernel/rcu/rcutorture.c @@ -162,6 +162,27 @@ static int rcu_torture_writer_state; #define RTWS_SYNC 7 #define RTWS_STUTTER 8 #define RTWS_STOPPING 9 +static const char * const rcu_torture_writer_state_names[] = { + "RTWS_FIXED_DELAY", + "RTWS_DELAY", + "RTWS_REPLACE", + "RTWS_DEF_FREE", + "RTWS_EXP_SYNC", + "RTWS_COND_GET", + "RTWS_COND_SYNC", + "RTWS_SYNC", + "RTWS_STUTTER", + "RTWS_STOPPING", +}; + +static const char *rcu_torture_writer_state_getname(void) +{ + unsigned int i = READ_ONCE(rcu_torture_writer_state); + + if (i >= ARRAY_SIZE(rcu_torture_writer_state_names)) + return "???"; + return rcu_torture_writer_state_names[i]; +} #if defined(MODULE) || defined(CONFIG_RCU_TORTURE_TEST_RUNNABLE) #define RCUTORTURE_RUNNABLE_INIT 1 @@ -1307,7 +1328,8 @@ rcu_torture_stats_print(void) rcutorture_get_gp_data(cur_ops->ttype, &flags, &gpnum, &completed); - pr_alert("??? Writer stall state %d g%lu c%lu f%#x\n", + pr_alert("??? Writer stall state %s(%d) g%lu c%lu f%#x\n", + rcu_torture_writer_state_getname(), rcu_torture_writer_state, gpnum, completed, flags); show_rcu_gp_kthreads(); diff --git a/kernel/rcu/srcu.c b/kernel/rcu/srcu.c index a63a1ea..9b9cdd5 100644 --- a/kernel/rcu/srcu.c +++ b/kernel/rcu/srcu.c @@ -489,7 +489,7 @@ static void __synchronize_srcu(struct srcu_struct *sp, int trycount) */ void synchronize_srcu(struct srcu_struct *sp) { - __synchronize_srcu(sp, rcu_gp_is_expedited() + __synchronize_srcu(sp, (rcu_gp_is_expedited() && !rcu_gp_is_normal()) ? SYNCHRONIZE_SRCU_EXP_TRYCOUNT : SYNCHRONIZE_SRCU_TRYCOUNT); } diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 81aa1cd..e41dd41 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -68,10 +68,6 @@ MODULE_ALIAS("rcutree"); /* Data structures. */ -static struct lock_class_key rcu_node_class[RCU_NUM_LVLS]; -static struct lock_class_key rcu_fqs_class[RCU_NUM_LVLS]; -static struct lock_class_key rcu_exp_class[RCU_NUM_LVLS]; - /* * In order to export the rcu_state name to the tracing tools, it * needs to be added in the __tracepoint_string section. @@ -246,24 +242,17 @@ static int rcu_gp_in_progress(struct rcu_state *rsp) */ void rcu_sched_qs(void) { - unsigned long flags; - - if (__this_cpu_read(rcu_sched_data.cpu_no_qs.s)) { - trace_rcu_grace_period(TPS("rcu_sched"), - __this_cpu_read(rcu_sched_data.gpnum), - TPS("cpuqs")); - __this_cpu_write(rcu_sched_data.cpu_no_qs.b.norm, false); - if (!__this_cpu_read(rcu_sched_data.cpu_no_qs.b.exp)) - return; - local_irq_save(flags); - if (__this_cpu_read(rcu_sched_data.cpu_no_qs.b.exp)) { - __this_cpu_write(rcu_sched_data.cpu_no_qs.b.exp, false); - rcu_report_exp_rdp(&rcu_sched_state, - this_cpu_ptr(&rcu_sched_data), - true); - } - local_irq_restore(flags); - } + if (!__this_cpu_read(rcu_sched_data.cpu_no_qs.s)) + return; + trace_rcu_grace_period(TPS("rcu_sched"), + __this_cpu_read(rcu_sched_data.gpnum), + TPS("cpuqs")); + __this_cpu_write(rcu_sched_data.cpu_no_qs.b.norm, false); + if (!__this_cpu_read(rcu_sched_data.cpu_no_qs.b.exp)) + return; + __this_cpu_write(rcu_sched_data.cpu_no_qs.b.exp, false); + rcu_report_exp_rdp(&rcu_sched_state, + this_cpu_ptr(&rcu_sched_data), true); } void rcu_bh_qs(void) @@ -300,17 +289,16 @@ EXPORT_PER_CPU_SYMBOL_GPL(rcu_qs_ctr); * We inform the RCU core by emulating a zero-duration dyntick-idle * period, which we in turn do by incrementing the ->dynticks counter * by two. + * + * The caller must have disabled interrupts. */ static void rcu_momentary_dyntick_idle(void) { - unsigned long flags; struct rcu_data *rdp; struct rcu_dynticks *rdtp; int resched_mask; struct rcu_state *rsp; - local_irq_save(flags); - /* * Yes, we can lose flag-setting operations. This is OK, because * the flag will be set again after some delay. @@ -340,13 +328,12 @@ static void rcu_momentary_dyntick_idle(void) smp_mb__after_atomic(); /* Later stuff after QS. */ break; } - local_irq_restore(flags); } /* * Note a context switch. This is a quiescent state for RCU-sched, * and requires special handling for preemptible RCU. - * The caller must have disabled preemption. + * The caller must have disabled interrupts. */ void rcu_note_context_switch(void) { @@ -376,9 +363,14 @@ EXPORT_SYMBOL_GPL(rcu_note_context_switch); */ void rcu_all_qs(void) { + unsigned long flags; + barrier(); /* Avoid RCU read-side critical sections leaking down. */ - if (unlikely(raw_cpu_read(rcu_sched_qs_mask))) + if (unlikely(raw_cpu_read(rcu_sched_qs_mask))) { + local_irq_save(flags); rcu_momentary_dyntick_idle(); + local_irq_restore(flags); + } this_cpu_inc(rcu_qs_ctr); barrier(); /* Avoid RCU read-side critical sections leaking up. */ } @@ -605,25 +597,25 @@ static int rcu_future_needs_gp(struct rcu_state *rsp) * The caller must have disabled interrupts to prevent races with * normal callback registry. */ -static int +static bool cpu_needs_another_gp(struct rcu_state *rsp, struct rcu_data *rdp) { int i; if (rcu_gp_in_progress(rsp)) - return 0; /* No, a grace period is already in progress. */ + return false; /* No, a grace period is already in progress. */ if (rcu_future_needs_gp(rsp)) - return 1; /* Yes, a no-CBs CPU needs one. */ + return true; /* Yes, a no-CBs CPU needs one. */ if (!rdp->nxttail[RCU_NEXT_TAIL]) - return 0; /* No, this is a no-CBs (or offline) CPU. */ + return false; /* No, this is a no-CBs (or offline) CPU. */ if (*rdp->nxttail[RCU_NEXT_READY_TAIL]) - return 1; /* Yes, this CPU has newly registered callbacks. */ + return true; /* Yes, CPU has newly registered callbacks. */ for (i = RCU_WAIT_TAIL; i < RCU_NEXT_TAIL; i++) if (rdp->nxttail[i - 1] != rdp->nxttail[i] && ULONG_CMP_LT(READ_ONCE(rsp->completed), rdp->nxtcompleted[i])) - return 1; /* Yes, CBs for future grace period. */ - return 0; /* No grace period needed. */ + return true; /* Yes, CBs for future grace period. */ + return false; /* No grace period needed. */ } /* @@ -740,7 +732,7 @@ void rcu_user_enter(void) * * Exit from an interrupt handler, which might possibly result in entering * idle mode, in other words, leaving the mode in which read-side critical - * sections can occur. + * sections can occur. The caller must have disabled interrupts. * * This code assumes that the idle loop never does anything that might * result in unbalanced calls to irq_enter() and irq_exit(). If your @@ -753,11 +745,10 @@ void rcu_user_enter(void) */ void rcu_irq_exit(void) { - unsigned long flags; long long oldval; struct rcu_dynticks *rdtp; - local_irq_save(flags); + RCU_LOCKDEP_WARN(!irqs_disabled(), "rcu_irq_exit() invoked with irqs enabled!!!"); rdtp = this_cpu_ptr(&rcu_dynticks); oldval = rdtp->dynticks_nesting; rdtp->dynticks_nesting--; @@ -768,6 +759,17 @@ void rcu_irq_exit(void) else rcu_eqs_enter_common(oldval, true); rcu_sysidle_enter(1); +} + +/* + * Wrapper for rcu_irq_exit() where interrupts are enabled. + */ +void rcu_irq_exit_irqson(void) +{ + unsigned long flags; + + local_irq_save(flags); + rcu_irq_exit(); local_irq_restore(flags); } @@ -865,7 +867,7 @@ void rcu_user_exit(void) * * Enter an interrupt handler, which might possibly result in exiting * idle mode, in other words, entering the mode in which read-side critical - * sections can occur. + * sections can occur. The caller must have disabled interrupts. * * Note that the Linux kernel is fully capable of entering an interrupt * handler that it never exits, for example when doing upcalls to @@ -881,11 +883,10 @@ void rcu_user_exit(void) */ void rcu_irq_enter(void) { - unsigned long flags; struct rcu_dynticks *rdtp; long long oldval; - local_irq_save(flags); + RCU_LOCKDEP_WARN(!irqs_disabled(), "rcu_irq_enter() invoked with irqs enabled!!!"); rdtp = this_cpu_ptr(&rcu_dynticks); oldval = rdtp->dynticks_nesting; rdtp->dynticks_nesting++; @@ -896,6 +897,17 @@ void rcu_irq_enter(void) else rcu_eqs_exit_common(oldval, true); rcu_sysidle_exit(1); +} + +/* + * Wrapper for rcu_irq_enter() where interrupts are enabled. + */ +void rcu_irq_enter_irqson(void) +{ + unsigned long flags; + + local_irq_save(flags); + rcu_irq_enter(); local_irq_restore(flags); } @@ -1187,6 +1199,16 @@ static void record_gp_stall_check_time(struct rcu_state *rsp) } /* + * Convert a ->gp_state value to a character string. + */ +static const char *gp_state_getname(short gs) +{ + if (gs < 0 || gs >= ARRAY_SIZE(gp_state_names)) + return "???"; + return gp_state_names[gs]; +} + +/* * Complain about starvation of grace-period kthread. */ static void rcu_check_gp_kthread_starvation(struct rcu_state *rsp) @@ -1196,12 +1218,16 @@ static void rcu_check_gp_kthread_starvation(struct rcu_state *rsp) j = jiffies; gpa = READ_ONCE(rsp->gp_activity); - if (j - gpa > 2 * HZ) - pr_err("%s kthread starved for %ld jiffies! g%lu c%lu f%#x s%d ->state=%#lx\n", + if (j - gpa > 2 * HZ) { + pr_err("%s kthread starved for %ld jiffies! g%lu c%lu f%#x %s(%d) ->state=%#lx\n", rsp->name, j - gpa, rsp->gpnum, rsp->completed, - rsp->gp_flags, rsp->gp_state, - rsp->gp_kthread ? rsp->gp_kthread->state : 0); + rsp->gp_flags, + gp_state_getname(rsp->gp_state), rsp->gp_state, + rsp->gp_kthread ? rsp->gp_kthread->state : ~0); + if (rsp->gp_kthread) + sched_show_task(rsp->gp_kthread); + } } /* @@ -1802,9 +1828,9 @@ static void rcu_gp_slow(struct rcu_state *rsp, int delay) } /* - * Initialize a new grace period. Return 0 if no grace period required. + * Initialize a new grace period. Return false if no grace period required. */ -static int rcu_gp_init(struct rcu_state *rsp) +static bool rcu_gp_init(struct rcu_state *rsp) { unsigned long oldmask; struct rcu_data *rdp; @@ -1815,7 +1841,7 @@ static int rcu_gp_init(struct rcu_state *rsp) if (!READ_ONCE(rsp->gp_flags)) { /* Spurious wakeup, tell caller to go back to sleep. */ raw_spin_unlock_irq(&rnp->lock); - return 0; + return false; } WRITE_ONCE(rsp->gp_flags, 0); /* Clear all flags: New grace period. */ @@ -1825,7 +1851,7 @@ static int rcu_gp_init(struct rcu_state *rsp) * Not supposed to be able to happen. */ raw_spin_unlock_irq(&rnp->lock); - return 0; + return false; } /* Advance to a new grace period and initialize state. */ @@ -1917,7 +1943,7 @@ static int rcu_gp_init(struct rcu_state *rsp) WRITE_ONCE(rsp->gp_activity, jiffies); } - return 1; + return true; } /* @@ -3347,7 +3373,6 @@ static unsigned long rcu_seq_snap(unsigned long *sp) { unsigned long s; - smp_mb(); /* Caller's modifications seen first by other CPUs. */ s = (READ_ONCE(*sp) + 3) & ~0x1; smp_mb(); /* Above access must not bleed into critical section. */ return s; @@ -3374,6 +3399,7 @@ static void rcu_exp_gp_seq_end(struct rcu_state *rsp) } static unsigned long rcu_exp_gp_seq_snap(struct rcu_state *rsp) { + smp_mb(); /* Caller's modifications seen first by other CPUs. */ return rcu_seq_snap(&rsp->expedited_sequence); } static bool rcu_exp_gp_seq_done(struct rcu_state *rsp, unsigned long s) @@ -3585,7 +3611,7 @@ static bool sync_exp_work_done(struct rcu_state *rsp, struct rcu_node *rnp, */ static struct rcu_node *exp_funnel_lock(struct rcu_state *rsp, unsigned long s) { - struct rcu_data *rdp; + struct rcu_data *rdp = per_cpu_ptr(rsp->rda, raw_smp_processor_id()); struct rcu_node *rnp0; struct rcu_node *rnp1 = NULL; @@ -3599,7 +3625,7 @@ static struct rcu_node *exp_funnel_lock(struct rcu_state *rsp, unsigned long s) if (!mutex_is_locked(&rnp0->exp_funnel_mutex)) { if (mutex_trylock(&rnp0->exp_funnel_mutex)) { if (sync_exp_work_done(rsp, rnp0, NULL, - &rsp->expedited_workdone0, s)) + &rdp->expedited_workdone0, s)) return NULL; return rnp0; } @@ -3613,14 +3639,13 @@ static struct rcu_node *exp_funnel_lock(struct rcu_state *rsp, unsigned long s) * can be inexact, as it is just promoting locality and is not * strictly needed for correctness. */ - rdp = per_cpu_ptr(rsp->rda, raw_smp_processor_id()); - if (sync_exp_work_done(rsp, NULL, NULL, &rsp->expedited_workdone1, s)) + if (sync_exp_work_done(rsp, NULL, NULL, &rdp->expedited_workdone1, s)) return NULL; mutex_lock(&rdp->exp_funnel_mutex); rnp0 = rdp->mynode; for (; rnp0 != NULL; rnp0 = rnp0->parent) { if (sync_exp_work_done(rsp, rnp1, rdp, - &rsp->expedited_workdone2, s)) + &rdp->expedited_workdone2, s)) return NULL; mutex_lock(&rnp0->exp_funnel_mutex); if (rnp1) @@ -3630,7 +3655,7 @@ static struct rcu_node *exp_funnel_lock(struct rcu_state *rsp, unsigned long s) rnp1 = rnp0; } if (sync_exp_work_done(rsp, rnp1, rdp, - &rsp->expedited_workdone3, s)) + &rdp->expedited_workdone3, s)) return NULL; return rnp1; } @@ -3716,24 +3741,22 @@ retry_ipi: ret = smp_call_function_single(cpu, func, rsp, 0); if (!ret) { mask_ofl_ipi &= ~mask; - } else { - /* Failed, raced with offline. */ - raw_spin_lock_irqsave_rcu_node(rnp, flags); - if (cpu_online(cpu) && - (rnp->expmask & mask)) { - raw_spin_unlock_irqrestore(&rnp->lock, - flags); - schedule_timeout_uninterruptible(1); - if (cpu_online(cpu) && - (rnp->expmask & mask)) - goto retry_ipi; - raw_spin_lock_irqsave_rcu_node(rnp, - flags); - } - if (!(rnp->expmask & mask)) - mask_ofl_ipi &= ~mask; + continue; + } + /* Failed, raced with offline. */ + raw_spin_lock_irqsave_rcu_node(rnp, flags); + if (cpu_online(cpu) && + (rnp->expmask & mask)) { raw_spin_unlock_irqrestore(&rnp->lock, flags); + schedule_timeout_uninterruptible(1); + if (cpu_online(cpu) && + (rnp->expmask & mask)) + goto retry_ipi; + raw_spin_lock_irqsave_rcu_node(rnp, flags); } + if (!(rnp->expmask & mask)) + mask_ofl_ipi &= ~mask; + raw_spin_unlock_irqrestore(&rnp->lock, flags); } /* Report quiescent states for those that went offline. */ mask_ofl_test |= mask_ofl_ipi; @@ -3748,6 +3771,7 @@ static void synchronize_sched_expedited_wait(struct rcu_state *rsp) unsigned long jiffies_stall; unsigned long jiffies_start; unsigned long mask; + int ndetected; struct rcu_node *rnp; struct rcu_node *rnp_root = rcu_get_root(rsp); int ret; @@ -3760,7 +3784,7 @@ static void synchronize_sched_expedited_wait(struct rcu_state *rsp) rsp->expedited_wq, sync_rcu_preempt_exp_done(rnp_root), jiffies_stall); - if (ret > 0) + if (ret > 0 || sync_rcu_preempt_exp_done(rnp_root)) return; if (ret < 0) { /* Hit a signal, disable CPU stall warnings. */ @@ -3770,14 +3794,16 @@ static void synchronize_sched_expedited_wait(struct rcu_state *rsp) } pr_err("INFO: %s detected expedited stalls on CPUs/tasks: {", rsp->name); + ndetected = 0; rcu_for_each_leaf_node(rsp, rnp) { - (void)rcu_print_task_exp_stall(rnp); + ndetected = rcu_print_task_exp_stall(rnp); mask = 1; for (cpu = rnp->grplo; cpu <= rnp->grphi; cpu++, mask <<= 1) { struct rcu_data *rdp; if (!(rnp->expmask & mask)) continue; + ndetected++; rdp = per_cpu_ptr(rsp->rda, cpu); pr_cont(" %d-%c%c%c", cpu, "O."[cpu_online(cpu)], @@ -3786,8 +3812,23 @@ static void synchronize_sched_expedited_wait(struct rcu_state *rsp) } mask <<= 1; } - pr_cont(" } %lu jiffies s: %lu\n", - jiffies - jiffies_start, rsp->expedited_sequence); + pr_cont(" } %lu jiffies s: %lu root: %#lx/%c\n", + jiffies - jiffies_start, rsp->expedited_sequence, + rnp_root->expmask, ".T"[!!rnp_root->exp_tasks]); + if (!ndetected) { + pr_err("blocking rcu_node structures:"); + rcu_for_each_node_breadth_first(rsp, rnp) { + if (rnp == rnp_root) + continue; /* printed unconditionally */ + if (sync_rcu_preempt_exp_done(rnp)) + continue; + pr_cont(" l=%u:%d-%d:%#lx/%c", + rnp->level, rnp->grplo, rnp->grphi, + rnp->expmask, + ".T"[!!rnp->exp_tasks]); + } + pr_cont("\n"); + } rcu_for_each_leaf_node(rsp, rnp) { mask = 1; for (cpu = rnp->grplo; cpu <= rnp->grphi; cpu++, mask <<= 1) { @@ -3822,6 +3863,16 @@ void synchronize_sched_expedited(void) struct rcu_node *rnp; struct rcu_state *rsp = &rcu_sched_state; + /* If only one CPU, this is automatically a grace period. */ + if (rcu_blocking_is_gp()) + return; + + /* If expedited grace periods are prohibited, fall back to normal. */ + if (rcu_gp_is_normal()) { + wait_rcu_gp(call_rcu_sched); + return; + } + /* Take a snapshot of the sequence number. */ s = rcu_exp_gp_seq_snap(rsp); @@ -4307,8 +4358,8 @@ static int __init rcu_spawn_gp_kthread(void) sp.sched_priority = kthread_prio; sched_setscheduler_nocheck(t, SCHED_FIFO, &sp); } - wake_up_process(t); raw_spin_unlock_irqrestore(&rnp->lock, flags); + wake_up_process(t); } rcu_spawn_nocb_kthreads(); rcu_spawn_boost_kthreads(); @@ -4359,12 +4410,14 @@ static void __init rcu_init_levelspread(int *levelspread, const int *levelcnt) /* * Helper function for rcu_init() that initializes one rcu_state structure. */ -static void __init rcu_init_one(struct rcu_state *rsp, - struct rcu_data __percpu *rda) +static void __init rcu_init_one(struct rcu_state *rsp) { static const char * const buf[] = RCU_NODE_NAME_INIT; static const char * const fqs[] = RCU_FQS_NAME_INIT; static const char * const exp[] = RCU_EXP_NAME_INIT; + static struct lock_class_key rcu_node_class[RCU_NUM_LVLS]; + static struct lock_class_key rcu_fqs_class[RCU_NUM_LVLS]; + static struct lock_class_key rcu_exp_class[RCU_NUM_LVLS]; static u8 fl_mask = 0x1; int levelcnt[RCU_NUM_LVLS]; /* # nodes in each level. */ @@ -4550,8 +4603,8 @@ void __init rcu_init(void) rcu_bootup_announce(); rcu_init_geometry(); - rcu_init_one(&rcu_bh_state, &rcu_bh_data); - rcu_init_one(&rcu_sched_state, &rcu_sched_data); + rcu_init_one(&rcu_bh_state); + rcu_init_one(&rcu_sched_state); if (dump_tree) rcu_dump_rcu_node_tree(&rcu_sched_state); __rcu_init_preempt(); diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h index f32bebb..83360b4 100644 --- a/kernel/rcu/tree.h +++ b/kernel/rcu/tree.h @@ -178,6 +178,8 @@ struct rcu_node { /* beginning of each expedited GP. */ unsigned long expmaskinitnext; /* Online CPUs for next expedited GP. */ + /* Any CPU that has ever been online will */ + /* have its bit set. */ 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. */ @@ -384,6 +386,10 @@ struct rcu_data { struct rcu_head oom_head; #endif /* #ifdef CONFIG_RCU_FAST_NO_HZ */ struct mutex exp_funnel_mutex; + 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. */ /* 7) Callback offloading. */ #ifdef CONFIG_RCU_NOCB_CPU @@ -498,10 +504,6 @@ struct rcu_state { /* End of fields guarded by barrier_mutex. */ 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_t expedited_need_qs; /* # CPUs left to check in. */ wait_queue_head_t expedited_wq; /* Wait for check-ins. */ @@ -545,6 +547,18 @@ struct rcu_state { #define RCU_GP_CLEANUP 5 /* Grace-period cleanup started. */ #define RCU_GP_CLEANED 6 /* Grace-period cleanup complete. */ +#ifndef RCU_TREE_NONCORE +static const char * const gp_state_names[] = { + "RCU_GP_IDLE", + "RCU_GP_WAIT_GPS", + "RCU_GP_DONE_GPS", + "RCU_GP_WAIT_FQS", + "RCU_GP_DOING_FQS", + "RCU_GP_CLEANUP", + "RCU_GP_CLEANED", +}; +#endif /* #ifndef RCU_TREE_NONCORE */ + extern struct list_head rcu_struct_flavors; /* Sequence through rcu_state structures for each RCU flavor. */ diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index 57ba873..9467a8b 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -63,8 +63,7 @@ static bool __read_mostly rcu_nocb_poll; /* Offload kthread are to poll. */ /* * Check the RCU kernel configuration parameters and print informative - * messages about anything out of the ordinary. If you like #ifdef, you - * will love this function. + * messages about anything out of the ordinary. */ static void __init rcu_bootup_announce_oddness(void) { @@ -147,8 +146,8 @@ static void __init rcu_bootup_announce(void) * the corresponding expedited grace period will also be the end of the * normal grace period. */ -static void rcu_preempt_ctxt_queue(struct rcu_node *rnp, struct rcu_data *rdp, - unsigned long flags) __releases(rnp->lock) +static void rcu_preempt_ctxt_queue(struct rcu_node *rnp, struct rcu_data *rdp) + __releases(rnp->lock) /* But leaves rrupts disabled. */ { int blkd_state = (rnp->gp_tasks ? RCU_GP_TASKS : 0) + (rnp->exp_tasks ? RCU_EXP_TASKS : 0) + @@ -236,7 +235,7 @@ static void rcu_preempt_ctxt_queue(struct rcu_node *rnp, struct rcu_data *rdp, rnp->gp_tasks = &t->rcu_node_entry; if (!rnp->exp_tasks && (blkd_state & RCU_EXP_BLKD)) rnp->exp_tasks = &t->rcu_node_entry; - raw_spin_unlock(&rnp->lock); + raw_spin_unlock(&rnp->lock); /* rrupts remain disabled. */ /* * Report the quiescent state for the expedited GP. This expedited @@ -251,7 +250,6 @@ static void rcu_preempt_ctxt_queue(struct rcu_node *rnp, struct rcu_data *rdp, } else { WARN_ON_ONCE(t->rcu_read_unlock_special.b.exp_need_qs); } - local_irq_restore(flags); } /* @@ -286,12 +284,11 @@ static void rcu_preempt_qs(void) * predating the current grace period drain, in other words, until * rnp->gp_tasks becomes NULL. * - * Caller must disable preemption. + * Caller must disable interrupts. */ static void rcu_preempt_note_context_switch(void) { struct task_struct *t = current; - unsigned long flags; struct rcu_data *rdp; struct rcu_node *rnp; @@ -301,7 +298,7 @@ static void rcu_preempt_note_context_switch(void) /* Possibly blocking in an RCU read-side critical section. */ rdp = this_cpu_ptr(rcu_state_p->rda); rnp = rdp->mynode; - raw_spin_lock_irqsave_rcu_node(rnp, flags); + raw_spin_lock_rcu_node(rnp); t->rcu_read_unlock_special.b.blocked = true; t->rcu_blocked_node = rnp; @@ -317,7 +314,7 @@ static void rcu_preempt_note_context_switch(void) (rnp->qsmask & rdp->grpmask) ? rnp->gpnum : rnp->gpnum + 1); - rcu_preempt_ctxt_queue(rnp, rdp, flags); + rcu_preempt_ctxt_queue(rnp, rdp); } else if (t->rcu_read_lock_nesting < 0 && t->rcu_read_unlock_special.s) { @@ -449,19 +446,13 @@ void rcu_read_unlock_special(struct task_struct *t) /* * Remove this task from the list it blocked on. The task - * now remains queued on the rcu_node corresponding to - * the CPU it first blocked on, so the first attempt to - * acquire the task's rcu_node's ->lock will succeed. - * Keep the loop and add a WARN_ON() out of sheer paranoia. + * now remains queued on the rcu_node corresponding to the + * CPU it first blocked on, so there is no longer any need + * to loop. Retain a WARN_ON_ONCE() out of sheer paranoia. */ - for (;;) { - rnp = t->rcu_blocked_node; - raw_spin_lock_rcu_node(rnp); /* irqs already disabled. */ - if (rnp == t->rcu_blocked_node) - break; - WARN_ON_ONCE(1); - raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */ - } + rnp = t->rcu_blocked_node; + raw_spin_lock_rcu_node(rnp); /* irqs already disabled. */ + WARN_ON_ONCE(rnp != t->rcu_blocked_node); empty_norm = !rcu_preempt_blocked_readers_cgp(rnp); empty_exp = sync_rcu_preempt_exp_done(rnp); smp_mb(); /* ensure expedited fastpath sees end of RCU c-s. */ @@ -746,6 +737,12 @@ void synchronize_rcu_expedited(void) struct rcu_state *rsp = rcu_state_p; unsigned long s; + /* If expedited grace periods are prohibited, fall back to normal. */ + if (rcu_gp_is_normal()) { + wait_rcu_gp(call_rcu); + return; + } + s = rcu_exp_gp_seq_snap(rsp); rnp_unlock = exp_funnel_lock(rsp, s); @@ -786,7 +783,7 @@ EXPORT_SYMBOL_GPL(rcu_barrier); */ static void __init __rcu_init_preempt(void) { - rcu_init_one(rcu_state_p, rcu_data_p); + rcu_init_one(rcu_state_p); } /* @@ -1520,7 +1517,8 @@ static void rcu_prepare_for_idle(void) struct rcu_state *rsp; int tne; - if (IS_ENABLED(CONFIG_RCU_NOCB_CPU_ALL)) + if (IS_ENABLED(CONFIG_RCU_NOCB_CPU_ALL) || + rcu_is_nocb_cpu(smp_processor_id())) return; /* Handle nohz enablement switches conservatively. */ @@ -1534,10 +1532,6 @@ static void rcu_prepare_for_idle(void) if (!tne) return; - /* If this is a no-CBs CPU, no callbacks, just return. */ - if (rcu_is_nocb_cpu(smp_processor_id())) - return; - /* * If a non-lazy callback arrived at a CPU having only lazy * callbacks, invoke RCU core for the side-effect of recalculating diff --git a/kernel/rcu/tree_trace.c b/kernel/rcu/tree_trace.c index 8efaba8..1088e64 100644 --- a/kernel/rcu/tree_trace.c +++ b/kernel/rcu/tree_trace.c @@ -1,5 +1,5 @@ /* - * Read-Copy Update tracing for classic implementation + * Read-Copy Update tracing for hierarchical implementation. * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by @@ -16,6 +16,7 @@ * http://www.gnu.org/licenses/gpl-2.0.html. * * Copyright IBM Corporation, 2008 + * Author: Paul E. McKenney * * Papers: http://www.rdrop.com/users/paulmck/RCU * @@ -33,9 +34,7 @@ #include <linux/sched.h> #include <linux/atomic.h> #include <linux/bitops.h> -#include <linux/module.h> #include <linux/completion.h> -#include <linux/moduleparam.h> #include <linux/percpu.h> #include <linux/notifier.h> #include <linux/cpu.h> @@ -183,14 +182,20 @@ static const struct file_operations rcudata_fops = { static int show_rcuexp(struct seq_file *m, void *v) { + int cpu; struct rcu_state *rsp = (struct rcu_state *)m->private; - + struct rcu_data *rdp; + unsigned long s0 = 0, s1 = 0, s2 = 0, s3 = 0; + + for_each_possible_cpu(cpu) { + rdp = per_cpu_ptr(rsp->rda, cpu); + s0 += atomic_long_read(&rdp->expedited_workdone0); + s1 += atomic_long_read(&rdp->expedited_workdone1); + s2 += atomic_long_read(&rdp->expedited_workdone2); + s3 += atomic_long_read(&rdp->expedited_workdone3); + } seq_printf(m, "s=%lu wd0=%lu wd1=%lu wd2=%lu wd3=%lu n=%lu enq=%d sc=%lu\n", - rsp->expedited_sequence, - atomic_long_read(&rsp->expedited_workdone0), - atomic_long_read(&rsp->expedited_workdone1), - atomic_long_read(&rsp->expedited_workdone2), - atomic_long_read(&rsp->expedited_workdone3), + rsp->expedited_sequence, s0, s1, s2, s3, atomic_long_read(&rsp->expedited_normal), atomic_read(&rsp->expedited_need_qs), rsp->expedited_sequence / 2); @@ -487,16 +492,4 @@ free_out: debugfs_remove_recursive(rcudir); return 1; } - -static void __exit rcutree_trace_cleanup(void) -{ - debugfs_remove_recursive(rcudir); -} - - -module_init(rcutree_trace_init); -module_exit(rcutree_trace_cleanup); - -MODULE_AUTHOR("Paul E. McKenney"); -MODULE_DESCRIPTION("Read-Copy Update tracing for hierarchical implementation"); -MODULE_LICENSE("GPL"); +device_initcall(rcutree_trace_init); diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c index 5f748c5..76b94e1 100644 --- a/kernel/rcu/update.c +++ b/kernel/rcu/update.c @@ -60,7 +60,12 @@ MODULE_ALIAS("rcupdate"); #endif #define MODULE_PARAM_PREFIX "rcupdate." +#ifndef CONFIG_TINY_RCU module_param(rcu_expedited, int, 0); +module_param(rcu_normal, int, 0); +static int rcu_normal_after_boot; +module_param(rcu_normal_after_boot, int, 0); +#endif /* #ifndef CONFIG_TINY_RCU */ #if defined(CONFIG_DEBUG_LOCK_ALLOC) && defined(CONFIG_PREEMPT_COUNT) /** @@ -113,6 +118,17 @@ EXPORT_SYMBOL(rcu_read_lock_sched_held); #ifndef CONFIG_TINY_RCU +/* + * Should expedited grace-period primitives always fall back to their + * non-expedited counterparts? Intended for use within RCU. Note + * that if the user specifies both rcu_expedited and rcu_normal, then + * rcu_normal wins. + */ +bool rcu_gp_is_normal(void) +{ + return READ_ONCE(rcu_normal); +} + static atomic_t rcu_expedited_nesting = ATOMIC_INIT(IS_ENABLED(CONFIG_RCU_EXPEDITE_BOOT) ? 1 : 0); @@ -157,8 +173,6 @@ void rcu_unexpedite_gp(void) } EXPORT_SYMBOL_GPL(rcu_unexpedite_gp); -#endif /* #ifndef CONFIG_TINY_RCU */ - /* * Inform RCU of the end of the in-kernel boot sequence. */ @@ -166,8 +180,12 @@ void rcu_end_inkernel_boot(void) { if (IS_ENABLED(CONFIG_RCU_EXPEDITE_BOOT)) rcu_unexpedite_gp(); + if (rcu_normal_after_boot) + WRITE_ONCE(rcu_normal, 1); } +#endif /* #ifndef CONFIG_TINY_RCU */ + #ifdef CONFIG_PREEMPT_RCU /* diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 4d568ac..ec72de2 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -3085,7 +3085,6 @@ static void __sched notrace __schedule(bool preempt) cpu = smp_processor_id(); rq = cpu_rq(cpu); - rcu_note_context_switch(); prev = rq->curr; /* @@ -3104,13 +3103,16 @@ static void __sched notrace __schedule(bool preempt) if (sched_feat(HRTICK)) hrtick_clear(rq); + local_irq_disable(); + rcu_note_context_switch(); + /* * Make sure that signal_pending_state()->signal_pending() below * can't be reordered with __set_current_state(TASK_INTERRUPTIBLE) * done by the caller to avoid the race with signal_wake_up(). */ smp_mb__before_spinlock(); - raw_spin_lock_irq(&rq->lock); + raw_spin_lock(&rq->lock); lockdep_pin_lock(&rq->lock); rq->clock_skip_update <<= 1; /* promote REQ to ACT */ diff --git a/lib/list_debug.c b/lib/list_debug.c index c24c2f7..3859bf6 100644 --- a/lib/list_debug.c +++ b/lib/list_debug.c @@ -37,7 +37,7 @@ void __list_add(struct list_head *new, next->prev = new; new->next = next; new->prev = prev; - prev->next = new; + WRITE_ONCE(prev->next, new); } EXPORT_SYMBOL(__list_add); diff --git a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh index 5236e07..0f80eef 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh @@ -38,8 +38,6 @@ # # Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com> -grace=120 - T=/tmp/kvm-test-1-run.sh.$$ trap 'rm -rf $T' 0 touch $T @@ -152,7 +150,7 @@ fi qemu_args="`specify_qemu_cpus "$QEMU" "$qemu_args" "$cpu_count"`" # Generate architecture-specific and interaction-specific qemu arguments -qemu_args="$qemu_args `identify_qemu_args "$QEMU" "$builddir/console.log"`" +qemu_args="$qemu_args `identify_qemu_args "$QEMU" "$resdir/console.log"`" # Generate qemu -append arguments qemu_append="`identify_qemu_append "$QEMU"`" @@ -168,7 +166,7 @@ then touch $resdir/buildonly exit 0 fi -echo "NOTE: $QEMU either did not run or was interactive" > $builddir/console.log +echo "NOTE: $QEMU either did not run or was interactive" > $resdir/console.log echo $QEMU $qemu_args -m 512 -kernel $resdir/bzImage -append \"$qemu_append $boot_args\" > $resdir/qemu-cmd ( $QEMU $qemu_args -m 512 -kernel $resdir/bzImage -append "$qemu_append $boot_args"; echo $? > $resdir/qemu-retval ) & qemu_pid=$! @@ -214,7 +212,7 @@ then else break fi - if test $kruntime -ge $((seconds + grace)) + if test $kruntime -ge $((seconds + $TORTURE_SHUTDOWN_GRACE)) then echo "!!! PID $qemu_pid hung at $kruntime vs. $seconds seconds" >> $resdir/Warnings 2>&1 kill -KILL $qemu_pid @@ -224,6 +222,5 @@ then done fi -cp $builddir/console.log $resdir parse-torture.sh $resdir/console.log $title parse-console.sh $resdir/console.log $title diff --git a/tools/testing/selftests/rcutorture/bin/kvm.sh b/tools/testing/selftests/rcutorture/bin/kvm.sh index f648360..4a43176 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm.sh @@ -42,6 +42,7 @@ TORTURE_DEFCONFIG=defconfig TORTURE_BOOT_IMAGE="" TORTURE_INITRD="$KVM/initrd"; export TORTURE_INITRD TORTURE_KMAKE_ARG="" +TORTURE_SHUTDOWN_GRACE=180 TORTURE_SUITE=rcu resdir="" configs="" @@ -149,6 +150,11 @@ do resdir=$2 shift ;; + --shutdown-grace) + checkarg --shutdown-grace "(seconds)" "$#" "$2" '^[0-9]*$' '^error' + TORTURE_SHUTDOWN_GRACE=$2 + shift + ;; --torture) checkarg --torture "(suite name)" "$#" "$2" '^\(lock\|rcu\)$' '^--' TORTURE_SUITE=$2 @@ -266,6 +272,7 @@ TORTURE_KMAKE_ARG="$TORTURE_KMAKE_ARG"; export TORTURE_KMAKE_ARG TORTURE_QEMU_CMD="$TORTURE_QEMU_CMD"; export TORTURE_QEMU_CMD TORTURE_QEMU_INTERACTIVE="$TORTURE_QEMU_INTERACTIVE"; export TORTURE_QEMU_INTERACTIVE TORTURE_QEMU_MAC="$TORTURE_QEMU_MAC"; export TORTURE_QEMU_MAC +TORTURE_SHUTDOWN_GRACE="$TORTURE_SHUTDOWN_GRACE"; export TORTURE_SHUTDOWN_GRACE TORTURE_SUITE="$TORTURE_SUITE"; export TORTURE_SUITE if ! test -e $resdir then @@ -307,10 +314,10 @@ awk < $T/cfgcpu.pack \ } # Dump out the scripting required to run one test batch. -function dump(first, pastlast) +function dump(first, pastlast, batchnum) { - print "echo ----Start batch: `date`"; - print "echo ----Start batch: `date` >> " rd "/log"; + print "echo ----Start batch " batchnum ": `date`"; + print "echo ----Start batch " batchnum ": `date` >> " rd "/log"; jn=1 for (j = first; j < pastlast; j++) { builddir=KVM "/b" jn @@ -371,25 +378,28 @@ END { njobs = i; nc = ncpus; first = 0; + batchnum = 1; # Each pass through the following loop considers one test. for (i = 0; i < njobs; i++) { if (ncpus == 0) { # Sequential test specified, each test its own batch. - dump(i, i + 1); + dump(i, i + 1, batchnum); first = i; + batchnum++; } else if (nc < cpus[i] && i != 0) { # Out of CPUs, dump out a batch. - dump(first, i); + dump(first, i, batchnum); first = i; nc = ncpus; + batchnum++; } # Account for the CPUs needed by the current test. nc -= cpus[i]; } # Dump the last batch. if (ncpus != 0) - dump(first, i); + dump(first, i, batchnum); }' >> $T/script cat << ___EOF___ >> $T/script diff --git a/tools/testing/selftests/rcutorture/bin/parse-console.sh b/tools/testing/selftests/rcutorture/bin/parse-console.sh index d8f35cf..844787a 100755 --- a/tools/testing/selftests/rcutorture/bin/parse-console.sh +++ b/tools/testing/selftests/rcutorture/bin/parse-console.sh @@ -24,9 +24,6 @@ # # Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com> -T=/tmp/abat-chk-badness.sh.$$ -trap 'rm -f $T' 0 - file="$1" title="$2" @@ -36,9 +33,41 @@ if grep -Pq '\x00' < $file then print_warning Console output contains nul bytes, old qemu still running? fi -egrep 'Badness|WARNING:|Warn|BUG|===========|Call Trace:|Oops:|Stall ended before state dump start' < $file | grep -v 'ODEBUG: ' | grep -v 'Warning: unable to open an initial console' > $T -if test -s $T +egrep 'Badness|WARNING:|Warn|BUG|===========|Call Trace:|Oops:|detected stalls on CPUs/tasks:|Stall ended before state dump start' < $file | grep -v 'ODEBUG: ' | grep -v 'Warning: unable to open an initial console' > $1.diags +if test -s $1.diags then print_warning Assertion failure in $file $title - cat $T + # cat $1.diags + summary="" + n_badness=`grep -c Badness $1` + if test "$n_badness" -ne 0 + then + summary="$summary Badness: $n_badness" + fi + n_warn=`grep -v 'Warning: unable to open an initial console' $1 | egrep -c 'WARNING:|Warn'` + if test "$n_warn" -ne 0 + then + summary="$summary Warnings: $n_warn" + fi + n_bugs=`egrep -c 'BUG|Oops:' $1` + if test "$n_bugs" -ne 0 + then + summary="$summary Bugs: $n_bugs" + fi + n_calltrace=`grep -c 'Call Trace:' $1` + if test "$n_calltrace" -ne 0 + then + summary="$summary Call Traces: $n_calltrace" + fi + n_lockdep=`grep -c =========== $1` + if test "$n_badness" -ne 0 + then + summary="$summary lockdep: $n_badness" + fi + n_stalls=`egrep -c 'detected stalls on CPUs/tasks:|Stall ended before state dump start' $1` + if test "$n_stalls" -ne 0 + then + summary="$summary Stalls: $n_stalls" + fi + print_warning Summary: $summary fi diff --git a/tools/testing/selftests/rcutorture/doc/TINY_RCU.txt b/tools/testing/selftests/rcutorture/doc/TINY_RCU.txt index 9ef33a7..24396ae 100644 --- a/tools/testing/selftests/rcutorture/doc/TINY_RCU.txt +++ b/tools/testing/selftests/rcutorture/doc/TINY_RCU.txt @@ -20,7 +20,6 @@ CONFIG_PROVE_RCU CONFIG_NO_HZ_FULL_SYSIDLE CONFIG_RCU_NOCB_CPU -CONFIG_RCU_USER_QS Meaningless for TINY_RCU. diff --git a/tools/testing/selftests/rcutorture/doc/TREE_RCU-kconfig.txt b/tools/testing/selftests/rcutorture/doc/TREE_RCU-kconfig.txt index 657f3a0..4e2b189 100644 --- a/tools/testing/selftests/rcutorture/doc/TREE_RCU-kconfig.txt +++ b/tools/testing/selftests/rcutorture/doc/TREE_RCU-kconfig.txt @@ -72,10 +72,6 @@ CONFIG_RCU_TORTURE_TEST_RUNNABLE Always used in KVM testing. -CONFIG_RCU_USER_QS - - Redundant with CONFIG_NO_HZ_FULL. - CONFIG_PREEMPT_RCU CONFIG_TREE_RCU |