diff options
Diffstat (limited to 'include/linux')
-rw-r--r-- | include/linux/ftrace_irq.h | 11 | ||||
-rw-r--r-- | include/linux/hardirq.h | 47 | ||||
-rw-r--r-- | include/linux/lockdep.h | 23 | ||||
-rw-r--r-- | include/linux/preempt.h | 4 | ||||
-rw-r--r-- | include/linux/rculist.h | 4 | ||||
-rw-r--r-- | include/linux/rcupdate.h | 53 | ||||
-rw-r--r-- | include/linux/rcupdate_trace.h | 88 | ||||
-rw-r--r-- | include/linux/rcupdate_wait.h | 19 | ||||
-rw-r--r-- | include/linux/rcutiny.h | 6 | ||||
-rw-r--r-- | include/linux/rcutree.h | 9 | ||||
-rw-r--r-- | include/linux/sched.h | 16 | ||||
-rw-r--r-- | include/linux/torture.h | 2 | ||||
-rw-r--r-- | include/linux/wait.h | 2 |
13 files changed, 239 insertions, 45 deletions
diff --git a/include/linux/ftrace_irq.h b/include/linux/ftrace_irq.h index ccda97dc7f8b..0abd9a1d2852 100644 --- a/include/linux/ftrace_irq.h +++ b/include/linux/ftrace_irq.h @@ -2,15 +2,6 @@ #ifndef _LINUX_FTRACE_IRQ_H #define _LINUX_FTRACE_IRQ_H - -#ifdef CONFIG_FTRACE_NMI_ENTER -extern void arch_ftrace_nmi_enter(void); -extern void arch_ftrace_nmi_exit(void); -#else -static inline void arch_ftrace_nmi_enter(void) { } -static inline void arch_ftrace_nmi_exit(void) { } -#endif - #ifdef CONFIG_HWLAT_TRACER extern bool trace_hwlat_callback_enabled; extern void trace_hwlat_callback(bool enter); @@ -22,12 +13,10 @@ static inline void ftrace_nmi_enter(void) if (trace_hwlat_callback_enabled) trace_hwlat_callback(true); #endif - arch_ftrace_nmi_enter(); } static inline void ftrace_nmi_exit(void) { - arch_ftrace_nmi_exit(); #ifdef CONFIG_HWLAT_TRACER if (trace_hwlat_callback_enabled) trace_hwlat_callback(false); diff --git a/include/linux/hardirq.h b/include/linux/hardirq.h index 7c8b82f69288..e07cf853aa16 100644 --- a/include/linux/hardirq.h +++ b/include/linux/hardirq.h @@ -2,31 +2,28 @@ #ifndef LINUX_HARDIRQ_H #define LINUX_HARDIRQ_H +#include <linux/context_tracking_state.h> #include <linux/preempt.h> #include <linux/lockdep.h> #include <linux/ftrace_irq.h> #include <linux/vtime.h> #include <asm/hardirq.h> - extern void synchronize_irq(unsigned int irq); extern bool synchronize_hardirq(unsigned int irq); -#if defined(CONFIG_TINY_RCU) - -static inline void rcu_nmi_enter(void) -{ -} +#ifdef CONFIG_NO_HZ_FULL +void __rcu_irq_enter_check_tick(void); +#else +static inline void __rcu_irq_enter_check_tick(void) { } +#endif -static inline void rcu_nmi_exit(void) +static __always_inline void rcu_irq_enter_check_tick(void) { + if (context_tracking_enabled()) + __rcu_irq_enter_check_tick(); } -#else -extern void rcu_nmi_enter(void); -extern void rcu_nmi_exit(void); -#endif - /* * It is safe to do non-atomic ops on ->hardirq_context, * because NMI handlers may not preempt and the ops are @@ -65,14 +62,34 @@ extern void irq_exit(void); #define arch_nmi_exit() do { } while (0) #endif +#ifdef CONFIG_TINY_RCU +static inline void rcu_nmi_enter(void) { } +static inline void rcu_nmi_exit(void) { } +#else +extern void rcu_nmi_enter(void); +extern void rcu_nmi_exit(void); +#endif + +/* + * NMI vs Tracing + * -------------- + * + * We must not land in a tracer until (or after) we've changed preempt_count + * such that in_nmi() becomes true. To that effect all NMI C entry points must + * be marked 'notrace' and call nmi_enter() as soon as possible. + */ + +/* + * nmi_enter() can nest up to 15 times; see NMI_BITS. + */ #define nmi_enter() \ do { \ arch_nmi_enter(); \ printk_nmi_enter(); \ lockdep_off(); \ ftrace_nmi_enter(); \ - BUG_ON(in_nmi()); \ - preempt_count_add(NMI_OFFSET + HARDIRQ_OFFSET); \ + BUG_ON(in_nmi() == NMI_MASK); \ + __preempt_count_add(NMI_OFFSET + HARDIRQ_OFFSET); \ rcu_nmi_enter(); \ lockdep_hardirq_enter(); \ } while (0) @@ -82,7 +99,7 @@ extern void irq_exit(void); lockdep_hardirq_exit(); \ rcu_nmi_exit(); \ BUG_ON(!in_nmi()); \ - preempt_count_sub(NMI_OFFSET + HARDIRQ_OFFSET); \ + __preempt_count_sub(NMI_OFFSET + HARDIRQ_OFFSET); \ ftrace_nmi_exit(); \ lockdep_on(); \ printk_nmi_exit(); \ diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index 206774ac6946..8fce5c98a4b0 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -308,8 +308,27 @@ extern void lockdep_set_selftest_task(struct task_struct *task); extern void lockdep_init_task(struct task_struct *task); -extern void lockdep_off(void); -extern void lockdep_on(void); +/* + * Split the recrursion counter in two to readily detect 'off' vs recursion. + */ +#define LOCKDEP_RECURSION_BITS 16 +#define LOCKDEP_OFF (1U << LOCKDEP_RECURSION_BITS) +#define LOCKDEP_RECURSION_MASK (LOCKDEP_OFF - 1) + +/* + * lockdep_{off,on}() are macros to avoid tracing and kprobes; not inlines due + * to header dependencies. + */ + +#define lockdep_off() \ +do { \ + current->lockdep_recursion += LOCKDEP_OFF; \ +} while (0) + +#define lockdep_on() \ +do { \ + current->lockdep_recursion -= LOCKDEP_OFF; \ +} while (0) extern void lockdep_register_key(struct lock_class_key *key); extern void lockdep_unregister_key(struct lock_class_key *key); diff --git a/include/linux/preempt.h b/include/linux/preempt.h index bc3f1aecaa19..7d9c1c0e149c 100644 --- a/include/linux/preempt.h +++ b/include/linux/preempt.h @@ -26,13 +26,13 @@ * PREEMPT_MASK: 0x000000ff * SOFTIRQ_MASK: 0x0000ff00 * HARDIRQ_MASK: 0x000f0000 - * NMI_MASK: 0x00100000 + * NMI_MASK: 0x00f00000 * PREEMPT_NEED_RESCHED: 0x80000000 */ #define PREEMPT_BITS 8 #define SOFTIRQ_BITS 8 #define HARDIRQ_BITS 4 -#define NMI_BITS 1 +#define NMI_BITS 4 #define PREEMPT_SHIFT 0 #define SOFTIRQ_SHIFT (PREEMPT_SHIFT + PREEMPT_BITS) diff --git a/include/linux/rculist.h b/include/linux/rculist.h index 8214cdc715f2..7375bb3da140 100644 --- a/include/linux/rculist.h +++ b/include/linux/rculist.h @@ -371,7 +371,7 @@ static inline void list_splice_tail_init_rcu(struct list_head *list, * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_head within the struct. - * @cond...: optional lockdep expression if called from non-RCU protection. + * @cond: optional lockdep expression if called from non-RCU protection. * * This list-traversal primitive may safely run concurrently with * the _rcu list-mutation primitives such as list_add_rcu() @@ -646,7 +646,7 @@ static inline void hlist_add_behind_rcu(struct hlist_node *n, * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the hlist_node within the struct. - * @cond...: optional lockdep expression if called from non-RCU protection. + * @cond: optional lockdep expression if called from non-RCU protection. * * This list-traversal primitive may safely run concurrently with * the _rcu list-mutation primitives such as hlist_add_head_rcu() diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 2678a37c3169..659cbfa7581a 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -37,6 +37,7 @@ /* Exported common interfaces */ void call_rcu(struct rcu_head *head, rcu_callback_t func); void rcu_barrier_tasks(void); +void rcu_barrier_tasks_rude(void); void synchronize_rcu(void); #ifdef CONFIG_PREEMPT_RCU @@ -129,25 +130,57 @@ static inline void rcu_init_nohz(void) { } * Note a quasi-voluntary context switch for RCU-tasks's benefit. * This is a macro rather than an inline function to avoid #include hell. */ -#ifdef CONFIG_TASKS_RCU -#define rcu_tasks_qs(t) \ - do { \ - if (READ_ONCE((t)->rcu_tasks_holdout)) \ - WRITE_ONCE((t)->rcu_tasks_holdout, false); \ +#ifdef CONFIG_TASKS_RCU_GENERIC + +# ifdef CONFIG_TASKS_RCU +# define rcu_tasks_classic_qs(t, preempt) \ + do { \ + if (!(preempt) && READ_ONCE((t)->rcu_tasks_holdout)) \ + WRITE_ONCE((t)->rcu_tasks_holdout, false); \ } while (0) -#define rcu_note_voluntary_context_switch(t) rcu_tasks_qs(t) void call_rcu_tasks(struct rcu_head *head, rcu_callback_t func); void synchronize_rcu_tasks(void); +# else +# define rcu_tasks_classic_qs(t, preempt) do { } while (0) +# define call_rcu_tasks call_rcu +# define synchronize_rcu_tasks synchronize_rcu +# endif + +# ifdef CONFIG_TASKS_RCU_TRACE +# define rcu_tasks_trace_qs(t) \ + do { \ + if (!likely(READ_ONCE((t)->trc_reader_checked)) && \ + !unlikely(READ_ONCE((t)->trc_reader_nesting))) { \ + smp_store_release(&(t)->trc_reader_checked, true); \ + smp_mb(); /* Readers partitioned by store. */ \ + } \ + } while (0) +# else +# define rcu_tasks_trace_qs(t) do { } while (0) +# endif + +#define rcu_tasks_qs(t, preempt) \ +do { \ + rcu_tasks_classic_qs((t), (preempt)); \ + rcu_tasks_trace_qs((t)); \ +} while (0) + +# ifdef CONFIG_TASKS_RUDE_RCU +void call_rcu_tasks_rude(struct rcu_head *head, rcu_callback_t func); +void synchronize_rcu_tasks_rude(void); +# endif + +#define rcu_note_voluntary_context_switch(t) rcu_tasks_qs(t, false) void exit_tasks_rcu_start(void); void exit_tasks_rcu_finish(void); -#else /* #ifdef CONFIG_TASKS_RCU */ -#define rcu_tasks_qs(t) do { } while (0) +#else /* #ifdef CONFIG_TASKS_RCU_GENERIC */ +#define rcu_tasks_qs(t, preempt) do { } while (0) #define rcu_note_voluntary_context_switch(t) do { } while (0) #define call_rcu_tasks call_rcu #define synchronize_rcu_tasks synchronize_rcu static inline void exit_tasks_rcu_start(void) { } static inline void exit_tasks_rcu_finish(void) { } -#endif /* #else #ifdef CONFIG_TASKS_RCU */ +#endif /* #else #ifdef CONFIG_TASKS_RCU_GENERIC */ /** * cond_resched_tasks_rcu_qs - Report potential quiescent states to RCU @@ -158,7 +191,7 @@ static inline void exit_tasks_rcu_finish(void) { } */ #define cond_resched_tasks_rcu_qs() \ do { \ - rcu_tasks_qs(current); \ + rcu_tasks_qs(current, false); \ cond_resched(); \ } while (0) diff --git a/include/linux/rcupdate_trace.h b/include/linux/rcupdate_trace.h new file mode 100644 index 000000000000..4c25a41f8b27 --- /dev/null +++ b/include/linux/rcupdate_trace.h @@ -0,0 +1,88 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * Read-Copy Update mechanism for mutual exclusion, adapted for tracing. + * + * Copyright (C) 2020 Paul E. McKenney. + */ + +#ifndef __LINUX_RCUPDATE_TRACE_H +#define __LINUX_RCUPDATE_TRACE_H + +#include <linux/sched.h> +#include <linux/rcupdate.h> + +#ifdef CONFIG_DEBUG_LOCK_ALLOC + +extern struct lockdep_map rcu_trace_lock_map; + +static inline int rcu_read_lock_trace_held(void) +{ + return lock_is_held(&rcu_trace_lock_map); +} + +#else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ + +static inline int rcu_read_lock_trace_held(void) +{ + return 1; +} + +#endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */ + +#ifdef CONFIG_TASKS_TRACE_RCU + +void rcu_read_unlock_trace_special(struct task_struct *t, int nesting); + +/** + * rcu_read_lock_trace - mark beginning of RCU-trace read-side critical section + * + * When synchronize_rcu_trace() is invoked by one task, then that task + * is guaranteed to block until all other tasks exit their read-side + * critical sections. Similarly, if call_rcu_trace() is invoked on one + * task while other tasks are within RCU read-side critical sections, + * invocation of the corresponding RCU callback is deferred until after + * the all the other tasks exit their critical sections. + * + * For more details, please see the documentation for rcu_read_lock(). + */ +static inline void rcu_read_lock_trace(void) +{ + struct task_struct *t = current; + + WRITE_ONCE(t->trc_reader_nesting, READ_ONCE(t->trc_reader_nesting) + 1); + if (IS_ENABLED(CONFIG_TASKS_TRACE_RCU_READ_MB) && + t->trc_reader_special.b.need_mb) + smp_mb(); // Pairs with update-side barriers + rcu_lock_acquire(&rcu_trace_lock_map); +} + +/** + * rcu_read_unlock_trace - mark end of RCU-trace read-side critical section + * + * Pairs with a preceding call to rcu_read_lock_trace(), and nesting is + * allowed. Invoking a rcu_read_unlock_trace() when there is no matching + * rcu_read_lock_trace() is verboten, and will result in lockdep complaints. + * + * For more details, please see the documentation for rcu_read_unlock(). + */ +static inline void rcu_read_unlock_trace(void) +{ + int nesting; + struct task_struct *t = current; + + rcu_lock_release(&rcu_trace_lock_map); + nesting = READ_ONCE(t->trc_reader_nesting) - 1; + if (likely(!READ_ONCE(t->trc_reader_special.s)) || nesting) { + WRITE_ONCE(t->trc_reader_nesting, nesting); + return; // We assume shallow reader nesting. + } + rcu_read_unlock_trace_special(t, nesting); +} + +void call_rcu_tasks_trace(struct rcu_head *rhp, rcu_callback_t func); +void synchronize_rcu_tasks_trace(void); +void rcu_barrier_tasks_trace(void); + +#endif /* #ifdef CONFIG_TASKS_TRACE_RCU */ + +#endif /* __LINUX_RCUPDATE_TRACE_H */ diff --git a/include/linux/rcupdate_wait.h b/include/linux/rcupdate_wait.h index c0578ba23c1a..699b938358bf 100644 --- a/include/linux/rcupdate_wait.h +++ b/include/linux/rcupdate_wait.h @@ -31,4 +31,23 @@ do { \ #define wait_rcu_gp(...) _wait_rcu_gp(false, __VA_ARGS__) +/** + * synchronize_rcu_mult - Wait concurrently for multiple grace periods + * @...: List of call_rcu() functions for different grace periods to wait on + * + * This macro waits concurrently for multiple types of RCU grace periods. + * For example, synchronize_rcu_mult(call_rcu, call_rcu_tasks) would wait + * on concurrent RCU and RCU-tasks grace periods. Waiting on a given SRCU + * domain requires you to write a wrapper function for that SRCU domain's + * call_srcu() function, with this wrapper supplying the pointer to the + * corresponding srcu_struct. + * + * The first argument tells Tiny RCU's _wait_rcu_gp() not to + * bother waiting for RCU. The reason for this is because anywhere + * synchronize_rcu_mult() can be called is automatically already a full + * grace period. + */ +#define synchronize_rcu_mult(...) \ + _wait_rcu_gp(IS_ENABLED(CONFIG_TINY_RCU), __VA_ARGS__) + #endif /* _LINUX_SCHED_RCUPDATE_WAIT_H */ diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h index 045c28b71f4f..8512caeb7682 100644 --- a/include/linux/rcutiny.h +++ b/include/linux/rcutiny.h @@ -49,7 +49,7 @@ static inline void rcu_softirq_qs(void) #define rcu_note_context_switch(preempt) \ do { \ rcu_qs(); \ - rcu_tasks_qs(current); \ + rcu_tasks_qs(current, (preempt)); \ } while (0) static inline int rcu_needs_cpu(u64 basemono, u64 *nextevt) @@ -71,6 +71,8 @@ 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) { } +static inline void rcu_irq_exit_preempt(void) { } +static inline void rcu_irq_exit_check_preempt(void) { } static inline void exit_rcu(void) { } static inline bool rcu_preempt_need_deferred_qs(struct task_struct *t) { @@ -85,8 +87,10 @@ static inline void rcu_scheduler_starting(void) { } static inline void rcu_end_inkernel_boot(void) { } static inline bool rcu_inkernel_boot_has_ended(void) { return true; } static inline bool rcu_is_watching(void) { return true; } +static inline bool __rcu_is_watching(void) { return true; } static inline void rcu_momentary_dyntick_idle(void) { } static inline void kfree_rcu_scheduler_running(void) { } +static inline bool rcu_gp_might_be_stalled(void) { return false; } /* Avoid RCU read-side critical sections leaking across. */ static inline void rcu_all_qs(void) { barrier(); } diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h index 45f3f66bb04d..d5cc9d675987 100644 --- a/include/linux/rcutree.h +++ b/include/linux/rcutree.h @@ -39,6 +39,7 @@ void rcu_barrier(void); bool rcu_eqs_special_set(int cpu); void rcu_momentary_dyntick_idle(void); void kfree_rcu_scheduler_running(void); +bool rcu_gp_might_be_stalled(void); unsigned long get_state_synchronize_rcu(void); void cond_synchronize_rcu(unsigned long oldstate); @@ -46,9 +47,16 @@ void rcu_idle_enter(void); void rcu_idle_exit(void); void rcu_irq_enter(void); void rcu_irq_exit(void); +void rcu_irq_exit_preempt(void); void rcu_irq_enter_irqson(void); void rcu_irq_exit_irqson(void); +#ifdef CONFIG_PROVE_RCU +void rcu_irq_exit_check_preempt(void); +#else +static inline void rcu_irq_exit_check_preempt(void) { } +#endif + void exit_rcu(void); void rcu_scheduler_starting(void); @@ -56,6 +64,7 @@ extern int rcu_scheduler_active __read_mostly; void rcu_end_inkernel_boot(void); bool rcu_inkernel_boot_has_ended(void); bool rcu_is_watching(void); +bool __rcu_is_watching(void); #ifndef CONFIG_PREEMPTION void rcu_all_qs(void); #endif diff --git a/include/linux/sched.h b/include/linux/sched.h index 4418f5cb8324..57d0ed061ae4 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -613,7 +613,7 @@ union rcu_special { u8 blocked; u8 need_qs; u8 exp_hint; /* Hint for performance. */ - u8 deferred_qs; + u8 need_mb; /* Readers need smp_mb(). */ } b; /* Bits. */ u32 s; /* Set of bits. */ }; @@ -724,6 +724,14 @@ struct task_struct { struct list_head rcu_tasks_holdout_list; #endif /* #ifdef CONFIG_TASKS_RCU */ +#ifdef CONFIG_TASKS_TRACE_RCU + int trc_reader_nesting; + int trc_ipi_to_cpu; + union rcu_special trc_reader_special; + bool trc_reader_checked; + struct list_head trc_holdout_list; +#endif /* #ifdef CONFIG_TASKS_TRACE_RCU */ + struct sched_info sched_info; struct list_head tasks; @@ -1289,6 +1297,12 @@ struct task_struct { unsigned long prev_lowest_stack; #endif +#ifdef CONFIG_X86_MCE + u64 mce_addr; + u64 mce_status; + struct callback_head mce_kill_me; +#endif + /* * New fields for task_struct should be added above here, so that * they are included in the randomized portion of task_struct. diff --git a/include/linux/torture.h b/include/linux/torture.h index 6241f59e2d6f..629b66e6c161 100644 --- a/include/linux/torture.h +++ b/include/linux/torture.h @@ -89,7 +89,7 @@ void _torture_stop_kthread(char *m, struct task_struct **tp); #ifdef CONFIG_PREEMPTION #define torture_preempt_schedule() preempt_schedule() #else -#define torture_preempt_schedule() +#define torture_preempt_schedule() do { } while (0) #endif #endif /* __LINUX_TORTURE_H */ diff --git a/include/linux/wait.h b/include/linux/wait.h index feeb6be5cad6..898c890fc153 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -1149,4 +1149,6 @@ int autoremove_wake_function(struct wait_queue_entry *wq_entry, unsigned mode, i (wait)->flags = 0; \ } while (0) +bool try_invoke_on_locked_down_task(struct task_struct *p, bool (*func)(struct task_struct *t, void *arg), void *arg); + #endif /* _LINUX_WAIT_H */ |