diff options
27 files changed, 459 insertions, 932 deletions
diff --git a/Documentation/RCU/Design/Requirements/Requirements.rst b/Documentation/RCU/Design/Requirements/Requirements.rst index ba417a08b93d..b5cdbba3ec2e 100644 --- a/Documentation/RCU/Design/Requirements/Requirements.rst +++ b/Documentation/RCU/Design/Requirements/Requirements.rst @@ -2780,12 +2780,12 @@ Tasks Trace RCU ~~~~~~~~~~~~~~~ Some forms of tracing need to sleep in readers, but cannot tolerate -SRCU's read-side overhead, which includes a full memory barrier in both -srcu_read_lock() and srcu_read_unlock(). This need is handled by a -Tasks Trace RCU that uses scheduler locking and IPIs to synchronize with -readers. Real-time systems that cannot tolerate IPIs may build their -kernels with ``CONFIG_TASKS_TRACE_RCU_READ_MB=y``, which avoids the IPIs at -the expense of adding full memory barriers to the read-side primitives. +SRCU's read-side overhead, which includes a full memory barrier in +both srcu_read_lock() and srcu_read_unlock(). This need is handled by +a Tasks Trace RCU API implemented as thin wrappers around SRCU-fast, +which avoids the read-side memory barriers, at least for architectures +that apply noinstr to kernel entry/exit code (or that build with +``CONFIG_TASKS_TRACE_RCU_NO_MB=y``. The tasks-trace-RCU API is also reasonably compact, consisting of rcu_read_lock_trace(), rcu_read_unlock_trace(), diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index aa0031108bc1..7a6acb523774 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -6289,13 +6289,6 @@ Kernel parameters dynamically) adjusted. This parameter is intended for use in testing. - rcupdate.rcu_task_ipi_delay= [KNL] - Set time in jiffies during which RCU tasks will - avoid sending IPIs, starting with the beginning - of a given grace period. Setting a large - number avoids disturbing real-time workloads, - but lengthens grace periods. - rcupdate.rcu_task_lazy_lim= [KNL] Number of callbacks on a given CPU that will cancel laziness on that CPU. Use -1 to disable @@ -6339,14 +6332,6 @@ Kernel parameters of zero will disable batching. Batching is always disabled for synchronize_rcu_tasks(). - rcupdate.rcu_tasks_trace_lazy_ms= [KNL] - Set timeout in milliseconds RCU Tasks - Trace asynchronous callback batching for - call_rcu_tasks_trace(). A negative value - will take the default. A value of zero will - disable batching. Batching is always disabled - for synchronize_rcu_tasks_trace(). - rcupdate.rcu_self_test= [KNL] Run the RCU early boot self tests diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index c5b30054cd01..bd5a420cf09a 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -175,36 +175,7 @@ void rcu_tasks_torture_stats_print(char *tt, char *tf); # define synchronize_rcu_tasks synchronize_rcu # endif -# ifdef CONFIG_TASKS_TRACE_RCU -// Bits for ->trc_reader_special.b.need_qs field. -#define TRC_NEED_QS 0x1 // Task needs a quiescent state. -#define TRC_NEED_QS_CHECKED 0x2 // Task has been checked for needing quiescent state. - -u8 rcu_trc_cmpxchg_need_qs(struct task_struct *t, u8 old, u8 new); -void rcu_tasks_trace_qs_blkd(struct task_struct *t); - -# define rcu_tasks_trace_qs(t) \ - do { \ - int ___rttq_nesting = READ_ONCE((t)->trc_reader_nesting); \ - \ - if (unlikely(READ_ONCE((t)->trc_reader_special.b.need_qs) == TRC_NEED_QS) && \ - likely(!___rttq_nesting)) { \ - rcu_trc_cmpxchg_need_qs((t), TRC_NEED_QS, TRC_NEED_QS_CHECKED); \ - } else if (___rttq_nesting && ___rttq_nesting != INT_MIN && \ - !READ_ONCE((t)->trc_reader_special.b.blocked)) { \ - rcu_tasks_trace_qs_blkd(t); \ - } \ - } while (0) -void rcu_tasks_trace_torture_stats_print(char *tt, char *tf); -# 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) +#define rcu_tasks_qs(t, preempt) rcu_tasks_classic_qs((t), (preempt)) # ifdef CONFIG_TASKS_RUDE_RCU void synchronize_rcu_tasks_rude(void); diff --git a/include/linux/rcupdate_trace.h b/include/linux/rcupdate_trace.h index e6c44eb428ab..cee89e51e45c 100644 --- a/include/linux/rcupdate_trace.h +++ b/include/linux/rcupdate_trace.h @@ -12,27 +12,74 @@ #include <linux/rcupdate.h> #include <linux/cleanup.h> -extern struct lockdep_map rcu_trace_lock_map; +#ifdef CONFIG_TASKS_TRACE_RCU +extern struct srcu_struct rcu_tasks_trace_srcu_struct; +#endif // #ifdef CONFIG_TASKS_TRACE_RCU -#ifdef CONFIG_DEBUG_LOCK_ALLOC +#if defined(CONFIG_DEBUG_LOCK_ALLOC) && defined(CONFIG_TASKS_TRACE_RCU) static inline int rcu_read_lock_trace_held(void) { - return lock_is_held(&rcu_trace_lock_map); + return srcu_read_lock_held(&rcu_tasks_trace_srcu_struct); } -#else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ +#else // #if defined(CONFIG_DEBUG_LOCK_ALLOC) && defined(CONFIG_TASKS_TRACE_RCU) static inline int rcu_read_lock_trace_held(void) { return 1; } -#endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */ +#endif // #else // #if defined(CONFIG_DEBUG_LOCK_ALLOC) && defined(CONFIG_TASKS_TRACE_RCU) #ifdef CONFIG_TASKS_TRACE_RCU -void rcu_read_unlock_trace_special(struct task_struct *t); +/** + * rcu_read_lock_tasks_trace - mark beginning of RCU-trace read-side critical section + * + * When synchronize_rcu_tasks_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 + * srcu_read_lock_fast(). For a description of how implicit RCU + * readers provide the needed ordering for architectures defining the + * ARCH_WANTS_NO_INSTR Kconfig option (and thus promising never to trace + * code where RCU is not watching), please see the __srcu_read_lock_fast() + * (non-kerneldoc) header comment. Otherwise, the smp_mb() below provided + * the needed ordering. + */ +static inline struct srcu_ctr __percpu *rcu_read_lock_tasks_trace(void) +{ + struct srcu_ctr __percpu *ret = __srcu_read_lock_fast(&rcu_tasks_trace_srcu_struct); + + rcu_try_lock_acquire(&rcu_tasks_trace_srcu_struct.dep_map); + if (!IS_ENABLED(CONFIG_TASKS_TRACE_RCU_NO_MB)) + smp_mb(); // Provide ordering on noinstr-incomplete architectures. + return ret; +} + +/** + * rcu_read_unlock_tasks_trace - mark end of RCU-trace read-side critical section + * @scp: return value from corresponding rcu_read_lock_tasks_trace(). + * + * Pairs with the preceding call to rcu_read_lock_tasks_trace() that + * returned the value passed in via scp. + * + * For more details, please see the documentation for rcu_read_unlock(). + * For memory-ordering information, please see the header comment for the + * rcu_read_lock_tasks_trace() function. + */ +static inline void rcu_read_unlock_tasks_trace(struct srcu_ctr __percpu *scp) +{ + if (!IS_ENABLED(CONFIG_TASKS_TRACE_RCU_NO_MB)) + smp_mb(); // Provide ordering on noinstr-incomplete architectures. + __srcu_read_unlock_fast(&rcu_tasks_trace_srcu_struct, scp); + srcu_lock_release(&rcu_tasks_trace_srcu_struct.dep_map); +} /** * rcu_read_lock_trace - mark beginning of RCU-trace read-side critical section @@ -50,12 +97,15 @@ 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); - barrier(); - 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_try_lock_acquire(&rcu_tasks_trace_srcu_struct.dep_map); + if (t->trc_reader_nesting++) { + // In case we interrupted a Tasks Trace RCU reader. + return; + } + barrier(); // nesting before scp to protect against interrupt handler. + t->trc_reader_scp = __srcu_read_lock_fast(&rcu_tasks_trace_srcu_struct); + if (!IS_ENABLED(CONFIG_TASKS_TRACE_RCU_NO_MB)) + smp_mb(); // Placeholder for more selective ordering } /** @@ -69,26 +119,88 @@ static inline void rcu_read_lock_trace(void) */ static inline void rcu_read_unlock_trace(void) { - int nesting; + struct srcu_ctr __percpu *scp; struct task_struct *t = current; - rcu_lock_release(&rcu_trace_lock_map); - nesting = READ_ONCE(t->trc_reader_nesting) - 1; - barrier(); // Critical section before disabling. - // Disable IPI-based setting of .need_qs. - WRITE_ONCE(t->trc_reader_nesting, INT_MIN + nesting); - if (likely(!READ_ONCE(t->trc_reader_special.s)) || nesting) { - WRITE_ONCE(t->trc_reader_nesting, nesting); - return; // We assume shallow reader nesting. + scp = t->trc_reader_scp; + barrier(); // scp before nesting to protect against interrupt handler. + if (!--t->trc_reader_nesting) { + if (!IS_ENABLED(CONFIG_TASKS_TRACE_RCU_NO_MB)) + smp_mb(); // Placeholder for more selective ordering + __srcu_read_unlock_fast(&rcu_tasks_trace_srcu_struct, scp); } - WARN_ON_ONCE(nesting != 0); - rcu_read_unlock_trace_special(t); + srcu_lock_release(&rcu_tasks_trace_srcu_struct.dep_map); } -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); -struct task_struct *get_rcu_tasks_trace_gp_kthread(void); +/** + * call_rcu_tasks_trace() - Queue a callback trace task-based grace period + * @rhp: structure to be used for queueing the RCU updates. + * @func: actual callback function to be invoked after the grace period + * + * The callback function will be invoked some time after a trace rcu-tasks + * grace period elapses, in other words after all currently executing + * trace rcu-tasks read-side critical sections have completed. These + * read-side critical sections are delimited by calls to rcu_read_lock_trace() + * and rcu_read_unlock_trace(). + * + * See the description of call_rcu() for more detailed information on + * memory ordering guarantees. + */ +static inline void call_rcu_tasks_trace(struct rcu_head *rhp, rcu_callback_t func) +{ + call_srcu(&rcu_tasks_trace_srcu_struct, rhp, func); +} + +/** + * synchronize_rcu_tasks_trace - wait for a trace rcu-tasks grace period + * + * Control will return to the caller some time after a trace rcu-tasks + * grace period has elapsed, in other words after all currently executing + * trace rcu-tasks read-side critical sections have elapsed. These read-side + * critical sections are delimited by calls to rcu_read_lock_trace() + * and rcu_read_unlock_trace(). + * + * This is a very specialized primitive, intended only for a few uses in + * tracing and other situations requiring manipulation of function preambles + * and profiling hooks. The synchronize_rcu_tasks_trace() function is not + * (yet) intended for heavy use from multiple CPUs. + * + * See the description of synchronize_rcu() for more detailed information + * on memory ordering guarantees. + */ +static inline void synchronize_rcu_tasks_trace(void) +{ + synchronize_srcu(&rcu_tasks_trace_srcu_struct); +} + +/** + * rcu_barrier_tasks_trace - Wait for in-flight call_rcu_tasks_trace() callbacks. + * + * Note that rcu_barrier_tasks_trace() is not obligated to actually wait, + * for example, if there are no pending callbacks. + */ +static inline void rcu_barrier_tasks_trace(void) +{ + srcu_barrier(&rcu_tasks_trace_srcu_struct); +} + +/** + * rcu_tasks_trace_expedite_current - Expedite the current Tasks Trace RCU grace period + * + * Cause the current Tasks Trace RCU grace period to become expedited. + * The grace period following the current one might also be expedited. + * If there is no current grace period, one might be created. If the + * current grace period is currently sleeping, that sleep will complete + * before expediting will take effect. + */ +static inline void rcu_tasks_trace_expedite_current(void) +{ + srcu_expedite_current(&rcu_tasks_trace_srcu_struct); +} + +// Placeholders to enable stepwise transition. +void __init rcu_tasks_trace_suppress_unused(void); + #else /* * The BPF JIT forms these addresses even when it doesn't call these diff --git a/include/linux/sched.h b/include/linux/sched.h index 5f00b5ed0f3b..e4d1f4481866 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -945,11 +945,7 @@ struct task_struct { #ifdef CONFIG_TASKS_TRACE_RCU int trc_reader_nesting; - int trc_ipi_to_cpu; - union rcu_special trc_reader_special; - struct list_head trc_holdout_list; - struct list_head trc_blkd_node; - int trc_blkd_cpu; + struct srcu_ctr __percpu *trc_reader_scp; #endif /* #ifdef CONFIG_TASKS_TRACE_RCU */ struct sched_info sched_info; diff --git a/init/init_task.c b/init/init_task.c index 49b13d7c3985..db92c404d59a 100644 --- a/init/init_task.c +++ b/init/init_task.c @@ -195,9 +195,6 @@ struct task_struct init_task __aligned(L1_CACHE_BYTES) = { #endif #ifdef CONFIG_TASKS_TRACE_RCU .trc_reader_nesting = 0, - .trc_reader_special.s = 0, - .trc_holdout_list = LIST_HEAD_INIT(init_task.trc_holdout_list), - .trc_blkd_node = LIST_HEAD_INIT(init_task.trc_blkd_node), #endif #ifdef CONFIG_CPUSETS .mems_allowed_seq = SEQCNT_SPINLOCK_ZERO(init_task.mems_allowed_seq, diff --git a/kernel/context_tracking.c b/kernel/context_tracking.c index fb5be6e9b423..a743e7ffa6c0 100644 --- a/kernel/context_tracking.c +++ b/kernel/context_tracking.c @@ -54,24 +54,6 @@ static __always_inline void rcu_task_enter(void) #endif /* #if defined(CONFIG_TASKS_RCU) && defined(CONFIG_NO_HZ_FULL) */ } -/* Turn on heavyweight RCU tasks trace readers on kernel exit. */ -static __always_inline void rcu_task_trace_heavyweight_enter(void) -{ -#ifdef CONFIG_TASKS_TRACE_RCU - if (IS_ENABLED(CONFIG_TASKS_TRACE_RCU_READ_MB)) - current->trc_reader_special.b.need_mb = true; -#endif /* #ifdef CONFIG_TASKS_TRACE_RCU */ -} - -/* Turn off heavyweight RCU tasks trace readers on kernel entry. */ -static __always_inline void rcu_task_trace_heavyweight_exit(void) -{ -#ifdef CONFIG_TASKS_TRACE_RCU - if (IS_ENABLED(CONFIG_TASKS_TRACE_RCU_READ_MB)) - current->trc_reader_special.b.need_mb = false; -#endif /* #ifdef CONFIG_TASKS_TRACE_RCU */ -} - /* * Record entry into an extended quiescent state. This is only to be * called when not already in an extended quiescent state, that is, @@ -85,7 +67,6 @@ static noinstr void ct_kernel_exit_state(int offset) * critical sections, and we also must force ordering with the * next idle sojourn. */ - rcu_task_trace_heavyweight_enter(); // Before CT state update! // RCU is still watching. Better not be in extended quiescent state! WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && !rcu_is_watching_curr_cpu()); (void)ct_state_inc(offset); @@ -108,7 +89,6 @@ static noinstr void ct_kernel_enter_state(int offset) */ seq = ct_state_inc(offset); // RCU is now watching. Better not be in an extended quiescent state! - rcu_task_trace_heavyweight_exit(); // After CT state update! WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && !(seq & CT_RCU_WATCHING)); } diff --git a/kernel/fork.c b/kernel/fork.c index b1f3915d5f8e..d7ed107cbb47 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1828,9 +1828,6 @@ static inline void rcu_copy_process(struct task_struct *p) #endif /* #ifdef CONFIG_TASKS_RCU */ #ifdef CONFIG_TASKS_TRACE_RCU p->trc_reader_nesting = 0; - p->trc_reader_special.s = 0; - INIT_LIST_HEAD(&p->trc_holdout_list); - INIT_LIST_HEAD(&p->trc_blkd_node); #endif /* #ifdef CONFIG_TASKS_TRACE_RCU */ } diff --git a/kernel/rcu/Kconfig b/kernel/rcu/Kconfig index 4d9b21f69eaa..762299291e09 100644 --- a/kernel/rcu/Kconfig +++ b/kernel/rcu/Kconfig @@ -82,7 +82,7 @@ config NEED_SRCU_NMI_SAFE def_bool HAVE_NMI && !ARCH_HAS_NMI_SAFE_THIS_CPU_OPS && !TINY_SRCU config TASKS_RCU_GENERIC - def_bool TASKS_RCU || TASKS_RUDE_RCU || TASKS_TRACE_RCU + def_bool TASKS_RCU || TASKS_RUDE_RCU help This option enables generic infrastructure code supporting task-based RCU implementations. Not for manual selection. @@ -142,6 +142,29 @@ config TASKS_TRACE_RCU default n select IRQ_WORK +config TASKS_TRACE_RCU_NO_MB + bool "Override RCU Tasks Trace inclusion of read-side memory barriers" + depends on RCU_EXPERT && TASKS_TRACE_RCU + default ARCH_WANTS_NO_INSTR + help + This option prevents the use of read-side memory barriers in + rcu_read_lock_tasks_trace() and rcu_read_unlock_tasks_trace() + even in kernels built with CONFIG_ARCH_WANTS_NO_INSTR=n, that is, + in kernels that do not have noinstr set up in entry/exit code. + By setting this option, you are promising to carefully review + use of ftrace, BPF, and friends to ensure that no tracing + operation is attached to a function that runs in that portion + of the entry/exit code that RCU does not watch, that is, + where rcu_is_watching() returns false. Alternatively, you + might choose to never remove traces except by rebooting. + + Those wishing to disable read-side memory barriers for an entire + architecture can select this Kconfig option, hence the polarity. + + Say Y here if you need speed and will review use of tracing. + Say N here for certain esoteric testing of RCU itself. + Take the default if you are unsure. + config RCU_STALL_COMMON def_bool TREE_RCU help @@ -313,24 +336,6 @@ config RCU_NOCB_CPU_CB_BOOST Say Y here if you want to set RT priority for offloading kthreads. Say N here if you are building a !PREEMPT_RT kernel and are unsure. -config TASKS_TRACE_RCU_READ_MB - bool "Tasks Trace RCU readers use memory barriers in user and idle" - depends on RCU_EXPERT && TASKS_TRACE_RCU - default PREEMPT_RT || NR_CPUS < 8 - help - Use this option to further reduce the number of IPIs sent - to CPUs executing in userspace or idle during tasks trace - RCU grace periods. Given that a reasonable setting of - the rcupdate.rcu_task_ipi_delay kernel boot parameter - eliminates such IPIs for many workloads, proper setting - of this Kconfig option is important mostly for aggressive - real-time installations and for battery-powered devices, - hence the default chosen above. - - Say Y here if you hate IPIs. - Say N here if you hate read-side memory barriers. - Take the default if you are unsure. - config RCU_LAZY bool "RCU callback lazy invocation functionality" depends on RCU_NOCB_CPU diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h index 9cf01832a6c3..dc5d614b372c 100644 --- a/kernel/rcu/rcu.h +++ b/kernel/rcu/rcu.h @@ -544,10 +544,6 @@ struct task_struct *get_rcu_tasks_rude_gp_kthread(void); void rcu_tasks_rude_get_gp_data(int *flags, unsigned long *gp_seq); #endif // # ifdef CONFIG_TASKS_RUDE_RCU -#ifdef CONFIG_TASKS_TRACE_RCU -void rcu_tasks_trace_get_gp_data(int *flags, unsigned long *gp_seq); -#endif - #ifdef CONFIG_TASKS_RCU_GENERIC void tasks_cblist_init_generic(void); #else /* #ifdef CONFIG_TASKS_RCU_GENERIC */ @@ -673,11 +669,6 @@ void show_rcu_tasks_rude_gp_kthread(void); #else static inline void show_rcu_tasks_rude_gp_kthread(void) {} #endif -#if !defined(CONFIG_TINY_RCU) && defined(CONFIG_TASKS_TRACE_RCU) -void show_rcu_tasks_trace_gp_kthread(void); -#else -static inline void show_rcu_tasks_trace_gp_kthread(void) {} -#endif #ifdef CONFIG_TINY_RCU static inline bool rcu_cpu_beenfullyonline(int cpu) { return true; } diff --git a/kernel/rcu/rcuscale.c b/kernel/rcu/rcuscale.c index 7484d8ad5767..1c50f89fbd6f 100644 --- a/kernel/rcu/rcuscale.c +++ b/kernel/rcu/rcuscale.c @@ -400,11 +400,6 @@ static void tasks_trace_scale_read_unlock(int idx) rcu_read_unlock_trace(); } -static void rcu_tasks_trace_scale_stats(void) -{ - rcu_tasks_trace_torture_stats_print(scale_type, SCALE_FLAG); -} - static struct rcu_scale_ops tasks_tracing_ops = { .ptype = RCU_TASKS_FLAVOR, .init = rcu_sync_scale_init, @@ -416,8 +411,6 @@ static struct rcu_scale_ops tasks_tracing_ops = { .gp_barrier = rcu_barrier_tasks_trace, .sync = synchronize_rcu_tasks_trace, .exp_sync = synchronize_rcu_tasks_trace, - .rso_gp_kthread = get_rcu_tasks_trace_gp_kthread, - .stats = IS_ENABLED(CONFIG_TINY_RCU) ? NULL : rcu_tasks_trace_scale_stats, .name = "tasks-tracing" }; diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c index 07e51974b06b..47ce7f49b52c 100644 --- a/kernel/rcu/rcutorture.c +++ b/kernel/rcu/rcutorture.c @@ -1178,10 +1178,9 @@ static struct rcu_torture_ops tasks_tracing_ops = { .deferred_free = rcu_tasks_tracing_torture_deferred_free, .sync = synchronize_rcu_tasks_trace, .exp_sync = synchronize_rcu_tasks_trace, + .exp_current = rcu_tasks_trace_expedite_current, .call = call_rcu_tasks_trace, .cb_barrier = rcu_barrier_tasks_trace, - .gp_kthread_dbg = show_rcu_tasks_trace_gp_kthread, - .get_gp_data = rcu_tasks_trace_get_gp_data, .cbflood_max = 50000, .irq_capable = 1, .slow_gps = 1, @@ -1750,7 +1749,7 @@ rcu_torture_writer(void *arg) ulo[i] = cur_ops->get_comp_state(); gp_snap = cur_ops->start_gp_poll(); rcu_torture_writer_state = RTWS_POLL_WAIT; - if (cur_ops->exp_current && !torture_random(&rand) % 0xff) + if (cur_ops->exp_current && !(torture_random(&rand) & 0xff)) cur_ops->exp_current(); while (!cur_ops->poll_gp_state(gp_snap)) { gp_snap1 = cur_ops->get_gp_state(); @@ -1772,7 +1771,7 @@ rcu_torture_writer(void *arg) cur_ops->get_comp_state_full(&rgo[i]); cur_ops->start_gp_poll_full(&gp_snap_full); rcu_torture_writer_state = RTWS_POLL_WAIT_FULL; - if (cur_ops->exp_current && !torture_random(&rand) % 0xff) + if (cur_ops->exp_current && !(torture_random(&rand) & 0xff)) cur_ops->exp_current(); while (!cur_ops->poll_gp_state_full(&gp_snap_full)) { cur_ops->get_gp_state_full(&gp_snap1_full); @@ -2455,6 +2454,9 @@ static DEFINE_TORTURE_RANDOM_PERCPU(rcu_torture_timer_rand); */ static void rcu_torture_timer(struct timer_list *unused) { + WARN_ON_ONCE(!in_serving_softirq()); + WARN_ON_ONCE(in_hardirq()); + WARN_ON_ONCE(in_nmi()); atomic_long_inc(&n_rcu_torture_timers); (void)rcu_torture_one_read(this_cpu_ptr(&rcu_torture_timer_rand), -1); diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c index ea3f128de06f..c469c708fdd6 100644 --- a/kernel/rcu/srcutree.c +++ b/kernel/rcu/srcutree.c @@ -262,7 +262,7 @@ static int init_srcu_struct_fields(struct srcu_struct *ssp, bool is_static) ssp->srcu_sup->srcu_gp_seq_needed_exp = SRCU_GP_SEQ_INITIAL_VAL; ssp->srcu_sup->srcu_last_gp_end = ktime_get_mono_fast_ns(); if (READ_ONCE(ssp->srcu_sup->srcu_size_state) == SRCU_SIZE_SMALL && SRCU_SIZING_IS_INIT()) { - if (!init_srcu_struct_nodes(ssp, GFP_ATOMIC)) + if (!init_srcu_struct_nodes(ssp, is_static ? GFP_ATOMIC : GFP_KERNEL)) goto err_free_sda; WRITE_ONCE(ssp->srcu_sup->srcu_size_state, SRCU_SIZE_BIG); } diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h index 2dc044fd126e..76f952196a29 100644 --- a/kernel/rcu/tasks.h +++ b/kernel/rcu/tasks.h @@ -161,11 +161,6 @@ static void tasks_rcu_exit_srcu_stall(struct timer_list *unused); static DEFINE_TIMER(tasks_rcu_exit_srcu_stall_timer, tasks_rcu_exit_srcu_stall); #endif -/* Avoid IPIing CPUs early in the grace period. */ -#define RCU_TASK_IPI_DELAY (IS_ENABLED(CONFIG_TASKS_TRACE_RCU_READ_MB) ? HZ / 2 : 0) -static int rcu_task_ipi_delay __read_mostly = RCU_TASK_IPI_DELAY; -module_param(rcu_task_ipi_delay, int, 0644); - /* Control stall timeouts. Disable with <= 0, otherwise jiffies till stall. */ #define RCU_TASK_BOOT_STALL_TIMEOUT (HZ * 30) #define RCU_TASK_STALL_TIMEOUT (HZ * 60 * 10) @@ -718,7 +713,6 @@ static void __init rcu_tasks_bootup_oddness(void) #endif /* #ifdef CONFIG_TASKS_TRACE_RCU */ } - /* Dump out rcutorture-relevant state common to all RCU-tasks flavors. */ static void show_rcu_tasks_generic_gp_kthread(struct rcu_tasks *rtp, char *s) { @@ -801,9 +795,7 @@ static void rcu_tasks_torture_stats_print_generic(struct rcu_tasks *rtp, char *t #endif // #ifndef CONFIG_TINY_RCU -static void exit_tasks_rcu_finish_trace(struct task_struct *t); - -#if defined(CONFIG_TASKS_RCU) || defined(CONFIG_TASKS_TRACE_RCU) +#if defined(CONFIG_TASKS_RCU) //////////////////////////////////////////////////////////////////////// // @@ -898,7 +890,7 @@ static void rcu_tasks_wait_gp(struct rcu_tasks *rtp) rtp->postgp_func(rtp); } -#endif /* #if defined(CONFIG_TASKS_RCU) || defined(CONFIG_TASKS_TRACE_RCU) */ +#endif /* #if defined(CONFIG_TASKS_RCU) */ #ifdef CONFIG_TASKS_RCU @@ -1322,13 +1314,11 @@ void exit_tasks_rcu_finish(void) raw_spin_lock_irqsave_rcu_node(rtpcp, flags); list_del_init(&t->rcu_tasks_exit_list); raw_spin_unlock_irqrestore_rcu_node(rtpcp, flags); - - exit_tasks_rcu_finish_trace(t); } #else /* #ifdef CONFIG_TASKS_RCU */ void exit_tasks_rcu_start(void) { } -void exit_tasks_rcu_finish(void) { exit_tasks_rcu_finish_trace(current); } +void exit_tasks_rcu_finish(void) { } #endif /* #else #ifdef CONFIG_TASKS_RCU */ #ifdef CONFIG_TASKS_RUDE_RCU @@ -1449,682 +1439,11 @@ EXPORT_SYMBOL_GPL(rcu_tasks_rude_get_gp_data); #endif /* #ifdef CONFIG_TASKS_RUDE_RCU */ -//////////////////////////////////////////////////////////////////////// -// -// Tracing variant of Tasks RCU. This variant is designed to be used -// to protect tracing hooks, including those of BPF. This variant -// therefore: -// -// 1. Has explicit read-side markers to allow finite grace periods -// in the face of in-kernel loops for PREEMPT=n builds. -// -// 2. Protects code in the idle loop, exception entry/exit, and -// CPU-hotplug code paths, similar to the capabilities of SRCU. -// -// 3. Avoids expensive read-side instructions, having overhead similar -// to that of Preemptible RCU. -// -// There are of course downsides. For example, the grace-period code -// can send IPIs to CPUs, even when those CPUs are in the idle loop or -// in nohz_full userspace. If needed, these downsides can be at least -// partially remedied. -// -// Perhaps most important, this variant of RCU does not affect the vanilla -// flavors, rcu_preempt and rcu_sched. The fact that RCU Tasks Trace -// readers can operate from idle, offline, and exception entry/exit in no -// way allows rcu_preempt and rcu_sched readers to also do so. -// -// The implementation uses rcu_tasks_wait_gp(), which relies on function -// pointers in the rcu_tasks structure. The rcu_spawn_tasks_trace_kthread() -// function sets these function pointers up so that rcu_tasks_wait_gp() -// invokes these functions in this order: -// -// rcu_tasks_trace_pregp_step(): -// Disables CPU hotplug, adds all currently executing tasks to the -// holdout list, then checks the state of all tasks that blocked -// or were preempted within their current RCU Tasks Trace read-side -// critical section, adding them to the holdout list if appropriate. -// Finally, this function re-enables CPU hotplug. -// The ->pertask_func() pointer is NULL, so there is no per-task processing. -// rcu_tasks_trace_postscan(): -// Invokes synchronize_rcu() to wait for late-stage exiting tasks -// to finish exiting. -// check_all_holdout_tasks_trace(), repeatedly until holdout list is empty: -// Scans the holdout list, attempting to identify a quiescent state -// for each task on the list. If there is a quiescent state, the -// corresponding task is removed from the holdout list. Once this -// list is empty, the grace period has completed. -// rcu_tasks_trace_postgp(): -// Provides the needed full memory barrier and does debug checks. -// -// The exit_tasks_rcu_finish_trace() synchronizes with exiting tasks. -// -// Pre-grace-period update-side code is ordered before the grace period -// via the ->cbs_lock and barriers in rcu_tasks_kthread(). Pre-grace-period -// read-side code is ordered before the grace period by atomic operations -// on .b.need_qs flag of each task involved in this process, or by scheduler -// context-switch ordering (for locked-down non-running readers). - -// The lockdep state must be outside of #ifdef to be useful. -#ifdef CONFIG_DEBUG_LOCK_ALLOC -static struct lock_class_key rcu_lock_trace_key; -struct lockdep_map rcu_trace_lock_map = - STATIC_LOCKDEP_MAP_INIT("rcu_read_lock_trace", &rcu_lock_trace_key); -EXPORT_SYMBOL_GPL(rcu_trace_lock_map); -#endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ - -#ifdef CONFIG_TASKS_TRACE_RCU - -// Record outstanding IPIs to each CPU. No point in sending two... -static DEFINE_PER_CPU(bool, trc_ipi_to_cpu); - -// The number of detections of task quiescent state relying on -// heavyweight readers executing explicit memory barriers. -static unsigned long n_heavy_reader_attempts; -static unsigned long n_heavy_reader_updates; -static unsigned long n_heavy_reader_ofl_updates; -static unsigned long n_trc_holdouts; - -void call_rcu_tasks_trace(struct rcu_head *rhp, rcu_callback_t func); -DEFINE_RCU_TASKS(rcu_tasks_trace, rcu_tasks_wait_gp, call_rcu_tasks_trace, - "RCU Tasks Trace"); - -/* Load from ->trc_reader_special.b.need_qs with proper ordering. */ -static u8 rcu_ld_need_qs(struct task_struct *t) -{ - smp_mb(); // Enforce full grace-period ordering. - return smp_load_acquire(&t->trc_reader_special.b.need_qs); -} - -/* Store to ->trc_reader_special.b.need_qs with proper ordering. */ -static void rcu_st_need_qs(struct task_struct *t, u8 v) -{ - smp_store_release(&t->trc_reader_special.b.need_qs, v); - smp_mb(); // Enforce full grace-period ordering. -} - -/* - * Do a cmpxchg() on ->trc_reader_special.b.need_qs, allowing for - * the four-byte operand-size restriction of some platforms. - * - * Returns the old value, which is often ignored. - */ -u8 rcu_trc_cmpxchg_need_qs(struct task_struct *t, u8 old, u8 new) -{ - return cmpxchg(&t->trc_reader_special.b.need_qs, old, new); -} -EXPORT_SYMBOL_GPL(rcu_trc_cmpxchg_need_qs); - -/* - * If we are the last reader, signal the grace-period kthread. - * Also remove from the per-CPU list of blocked tasks. - */ -void rcu_read_unlock_trace_special(struct task_struct *t) -{ - unsigned long flags; - struct rcu_tasks_percpu *rtpcp; - union rcu_special trs; - - // Open-coded full-word version of rcu_ld_need_qs(). - smp_mb(); // Enforce full grace-period ordering. - trs = smp_load_acquire(&t->trc_reader_special); - - if (IS_ENABLED(CONFIG_TASKS_TRACE_RCU_READ_MB) && t->trc_reader_special.b.need_mb) - smp_mb(); // Pairs with update-side barriers. - // Update .need_qs before ->trc_reader_nesting for irq/NMI handlers. - if (trs.b.need_qs == (TRC_NEED_QS_CHECKED | TRC_NEED_QS)) { - u8 result = rcu_trc_cmpxchg_need_qs(t, TRC_NEED_QS_CHECKED | TRC_NEED_QS, - TRC_NEED_QS_CHECKED); - - WARN_ONCE(result != trs.b.need_qs, "%s: result = %d", __func__, result); - } - if (trs.b.blocked) { - rtpcp = per_cpu_ptr(rcu_tasks_trace.rtpcpu, t->trc_blkd_cpu); - raw_spin_lock_irqsave_rcu_node(rtpcp, flags); - list_del_init(&t->trc_blkd_node); - WRITE_ONCE(t->trc_reader_special.b.blocked, false); - raw_spin_unlock_irqrestore_rcu_node(rtpcp, flags); - } - WRITE_ONCE(t->trc_reader_nesting, 0); -} -EXPORT_SYMBOL_GPL(rcu_read_unlock_trace_special); - -/* Add a newly blocked reader task to its CPU's list. */ -void rcu_tasks_trace_qs_blkd(struct task_struct *t) -{ - unsigned long flags; - struct rcu_tasks_percpu *rtpcp; - - local_irq_save(flags); - rtpcp = this_cpu_ptr(rcu_tasks_trace.rtpcpu); - raw_spin_lock_rcu_node(rtpcp); // irqs already disabled - t->trc_blkd_cpu = smp_processor_id(); - if (!rtpcp->rtp_blkd_tasks.next) - INIT_LIST_HEAD(&rtpcp->rtp_blkd_tasks); - list_add(&t->trc_blkd_node, &rtpcp->rtp_blkd_tasks); - WRITE_ONCE(t->trc_reader_special.b.blocked, true); - raw_spin_unlock_irqrestore_rcu_node(rtpcp, flags); -} -EXPORT_SYMBOL_GPL(rcu_tasks_trace_qs_blkd); - -/* Add a task to the holdout list, if it is not already on the list. */ -static void trc_add_holdout(struct task_struct *t, struct list_head *bhp) -{ - if (list_empty(&t->trc_holdout_list)) { - get_task_struct(t); - list_add(&t->trc_holdout_list, bhp); - n_trc_holdouts++; - } -} - -/* Remove a task from the holdout list, if it is in fact present. */ -static void trc_del_holdout(struct task_struct *t) -{ - if (!list_empty(&t->trc_holdout_list)) { - list_del_init(&t->trc_holdout_list); - put_task_struct(t); - n_trc_holdouts--; - } -} - -/* IPI handler to check task state. */ -static void trc_read_check_handler(void *t_in) -{ - int nesting; - struct task_struct *t = current; - struct task_struct *texp = t_in; - - // If the task is no longer running on this CPU, leave. - if (unlikely(texp != t)) - goto reset_ipi; // Already on holdout list, so will check later. - - // If the task is not in a read-side critical section, and - // if this is the last reader, awaken the grace-period kthread. - nesting = READ_ONCE(t->trc_reader_nesting); - if (likely(!nesting)) { - rcu_trc_cmpxchg_need_qs(t, 0, TRC_NEED_QS_CHECKED); - goto reset_ipi; - } - // If we are racing with an rcu_read_unlock_trace(), try again later. - if (unlikely(nesting < 0)) - goto reset_ipi; - - // Get here if the task is in a read-side critical section. - // Set its state so that it will update state for the grace-period - // kthread upon exit from that critical section. - rcu_trc_cmpxchg_need_qs(t, 0, TRC_NEED_QS | TRC_NEED_QS_CHECKED); - -reset_ipi: - // Allow future IPIs to be sent on CPU and for task. - // Also order this IPI handler against any later manipulations of - // the intended task. - smp_store_release(per_cpu_ptr(&trc_ipi_to_cpu, smp_processor_id()), false); // ^^^ - smp_store_release(&texp->trc_ipi_to_cpu, -1); // ^^^ -} - -/* Callback function for scheduler to check locked-down task. */ -static int trc_inspect_reader(struct task_struct *t, void *bhp_in) -{ - struct list_head *bhp = bhp_in; - int cpu = task_cpu(t); - int nesting; - bool ofl = cpu_is_offline(cpu); - - if (task_curr(t) && !ofl) { - // If no chance of heavyweight readers, do it the hard way. - if (!IS_ENABLED(CONFIG_TASKS_TRACE_RCU_READ_MB)) - return -EINVAL; - - // If heavyweight readers are enabled on the remote task, - // we can inspect its state despite its currently running. - // However, we cannot safely change its state. - n_heavy_reader_attempts++; - // Check for "running" idle tasks on offline CPUs. - if (!rcu_watching_zero_in_eqs(cpu, &t->trc_reader_nesting)) - return -EINVAL; // No quiescent state, do it the hard way. - n_heavy_reader_updates++; - nesting = 0; - } else { - // The task is not running, so C-language access is safe. - nesting = t->trc_reader_nesting; - WARN_ON_ONCE(ofl && task_curr(t) && (t != idle_task(task_cpu(t)))); - if (IS_ENABLED(CONFIG_TASKS_TRACE_RCU_READ_MB) && ofl) - n_heavy_reader_ofl_updates++; - } - - // If not exiting a read-side critical section, mark as checked - // so that the grace-period kthread will remove it from the - // holdout list. - if (!nesting) { - rcu_trc_cmpxchg_need_qs(t, 0, TRC_NEED_QS_CHECKED); - return 0; // In QS, so done. - } - if (nesting < 0) - return -EINVAL; // Reader transitioning, try again later. - - // The task is in a read-side critical section, so set up its - // state so that it will update state upon exit from that critical - // section. - if (!rcu_trc_cmpxchg_need_qs(t, 0, TRC_NEED_QS | TRC_NEED_QS_CHECKED)) - trc_add_holdout(t, bhp); - return 0; -} - -/* Attempt to extract the state for the specified task. */ -static void trc_wait_for_one_reader(struct task_struct *t, - struct list_head *bhp) -{ - int cpu; - - // If a previous IPI is still in flight, let it complete. - if (smp_load_acquire(&t->trc_ipi_to_cpu) != -1) // Order IPI - return; - - // The current task had better be in a quiescent state. - if (t == current) { - rcu_trc_cmpxchg_need_qs(t, 0, TRC_NEED_QS_CHECKED); - WARN_ON_ONCE(READ_ONCE(t->trc_reader_nesting)); - return; - } - - // Attempt to nail down the task for inspection. - get_task_struct(t); - if (!task_call_func(t, trc_inspect_reader, bhp)) { - put_task_struct(t); - return; - } - put_task_struct(t); - - // If this task is not yet on the holdout list, then we are in - // an RCU read-side critical section. Otherwise, the invocation of - // trc_add_holdout() that added it to the list did the necessary - // get_task_struct(). Either way, the task cannot be freed out - // from under this code. - - // If currently running, send an IPI, either way, add to list. - trc_add_holdout(t, bhp); - if (task_curr(t) && - time_after(jiffies + 1, rcu_tasks_trace.gp_start + rcu_task_ipi_delay)) { - // The task is currently running, so try IPIing it. - cpu = task_cpu(t); - - // If there is already an IPI outstanding, let it happen. - if (per_cpu(trc_ipi_to_cpu, cpu) || t->trc_ipi_to_cpu >= 0) - return; - - per_cpu(trc_ipi_to_cpu, cpu) = true; - t->trc_ipi_to_cpu = cpu; - rcu_tasks_trace.n_ipis++; - if (smp_call_function_single(cpu, trc_read_check_handler, t, 0)) { - // Just in case there is some other reason for - // failure than the target CPU being offline. - WARN_ONCE(1, "%s(): smp_call_function_single() failed for CPU: %d\n", - __func__, cpu); - rcu_tasks_trace.n_ipis_fails++; - per_cpu(trc_ipi_to_cpu, cpu) = false; - t->trc_ipi_to_cpu = -1; - } - } -} - -/* - * Initialize for first-round processing for the specified task. - * Return false if task is NULL or already taken care of, true otherwise. - */ -static bool rcu_tasks_trace_pertask_prep(struct task_struct *t, bool notself) -{ - // During early boot when there is only the one boot CPU, there - // is no idle task for the other CPUs. Also, the grace-period - // kthread is always in a quiescent state. In addition, just return - // if this task is already on the list. - if (unlikely(t == NULL) || (t == current && notself) || !list_empty(&t->trc_holdout_list)) - return false; - - rcu_st_need_qs(t, 0); - t->trc_ipi_to_cpu = -1; - return true; -} - -/* Do first-round processing for the specified task. */ -static void rcu_tasks_trace_pertask(struct task_struct *t, struct list_head *hop) -{ - if (rcu_tasks_trace_pertask_prep(t, true)) - trc_wait_for_one_reader(t, hop); -} - -/* Initialize for a new RCU-tasks-trace grace period. */ -static void rcu_tasks_trace_pregp_step(struct list_head *hop) -{ - LIST_HEAD(blkd_tasks); - int cpu; - unsigned long flags; - struct rcu_tasks_percpu *rtpcp; - struct task_struct *t; - - // There shouldn't be any old IPIs, but... - for_each_possible_cpu(cpu) - WARN_ON_ONCE(per_cpu(trc_ipi_to_cpu, cpu)); - - // Disable CPU hotplug across the CPU scan for the benefit of - // any IPIs that might be needed. This also waits for all readers - // in CPU-hotplug code paths. - cpus_read_lock(); - - // These rcu_tasks_trace_pertask_prep() calls are serialized to - // allow safe access to the hop list. - for_each_online_cpu(cpu) { - rcu_read_lock(); - // Note that cpu_curr_snapshot() picks up the target - // CPU's current task while its runqueue is locked with - // an smp_mb__after_spinlock(). This ensures that either - // the grace-period kthread will see that task's read-side - // critical section or the task will see the updater's pre-GP - // accesses. The trailing smp_mb() in cpu_curr_snapshot() - // does not currently play a role other than simplify - // that function's ordering semantics. If these simplified - // ordering semantics continue to be redundant, that smp_mb() - // might be removed. - t = cpu_curr_snapshot(cpu); - if (rcu_tasks_trace_pertask_prep(t, true)) - trc_add_holdout(t, hop); - rcu_read_unlock(); - cond_resched_tasks_rcu_qs(); - } - - // Only after all running tasks have been accounted for is it - // safe to take care of the tasks that have blocked within their - // current RCU tasks trace read-side critical section. - for_each_possible_cpu(cpu) { - rtpcp = per_cpu_ptr(rcu_tasks_trace.rtpcpu, cpu); - raw_spin_lock_irqsave_rcu_node(rtpcp, flags); - list_splice_init(&rtpcp->rtp_blkd_tasks, &blkd_tasks); - while (!list_empty(&blkd_tasks)) { - rcu_read_lock(); - t = list_first_entry(&blkd_tasks, struct task_struct, trc_blkd_node); - list_del_init(&t->trc_blkd_node); - list_add(&t->trc_blkd_node, &rtpcp->rtp_blkd_tasks); - raw_spin_unlock_irqrestore_rcu_node(rtpcp, flags); - rcu_tasks_trace_pertask(t, hop); - rcu_read_unlock(); - raw_spin_lock_irqsave_rcu_node(rtpcp, flags); - } - raw_spin_unlock_irqrestore_rcu_node(rtpcp, flags); - cond_resched_tasks_rcu_qs(); - } - - // Re-enable CPU hotplug now that the holdout list is populated. - cpus_read_unlock(); -} - -/* - * Do intermediate processing between task and holdout scans. - */ -static void rcu_tasks_trace_postscan(struct list_head *hop) -{ - // Wait for late-stage exiting tasks to finish exiting. - // These might have passed the call to exit_tasks_rcu_finish(). - - // If you remove the following line, update rcu_trace_implies_rcu_gp()!!! - synchronize_rcu(); - // Any tasks that exit after this point will set - // TRC_NEED_QS_CHECKED in ->trc_reader_special.b.need_qs. -} - -/* Communicate task state back to the RCU tasks trace stall warning request. */ -struct trc_stall_chk_rdr { - int nesting; - int ipi_to_cpu; - u8 needqs; -}; - -static int trc_check_slow_task(struct task_struct *t, void *arg) -{ - struct trc_stall_chk_rdr *trc_rdrp = arg; - - if (task_curr(t) && cpu_online(task_cpu(t))) - return false; // It is running, so decline to inspect it. - trc_rdrp->nesting = READ_ONCE(t->trc_reader_nesting); - trc_rdrp->ipi_to_cpu = READ_ONCE(t->trc_ipi_to_cpu); - trc_rdrp->needqs = rcu_ld_need_qs(t); - return true; -} - -/* Show the state of a task stalling the current RCU tasks trace GP. */ -static void show_stalled_task_trace(struct task_struct *t, bool *firstreport) -{ - int cpu; - struct trc_stall_chk_rdr trc_rdr; - bool is_idle_tsk = is_idle_task(t); - - if (*firstreport) { - pr_err("INFO: rcu_tasks_trace detected stalls on tasks:\n"); - *firstreport = false; - } - cpu = task_cpu(t); - if (!task_call_func(t, trc_check_slow_task, &trc_rdr)) - pr_alert("P%d: %c%c\n", - t->pid, - ".I"[t->trc_ipi_to_cpu >= 0], - ".i"[is_idle_tsk]); - else - pr_alert("P%d: %c%c%c%c nesting: %d%c%c cpu: %d%s\n", - t->pid, - ".I"[trc_rdr.ipi_to_cpu >= 0], - ".i"[is_idle_tsk], - ".N"[cpu >= 0 && tick_nohz_full_cpu(cpu)], - ".B"[!!data_race(t->trc_reader_special.b.blocked)], - trc_rdr.nesting, - " !CN"[trc_rdr.needqs & 0x3], - " ?"[trc_rdr.needqs > 0x3], - cpu, cpu_online(cpu) ? "" : "(offline)"); - sched_show_task(t); -} - -/* List stalled IPIs for RCU tasks trace. */ -static void show_stalled_ipi_trace(void) -{ - int cpu; - - for_each_possible_cpu(cpu) - if (per_cpu(trc_ipi_to_cpu, cpu)) - pr_alert("\tIPI outstanding to CPU %d\n", cpu); -} - -/* Do one scan of the holdout list. */ -static void check_all_holdout_tasks_trace(struct list_head *hop, - bool needreport, bool *firstreport) -{ - struct task_struct *g, *t; - - // Disable CPU hotplug across the holdout list scan for IPIs. - cpus_read_lock(); - - list_for_each_entry_safe(t, g, hop, trc_holdout_list) { - // If safe and needed, try to check the current task. - if (READ_ONCE(t->trc_ipi_to_cpu) == -1 && - !(rcu_ld_need_qs(t) & TRC_NEED_QS_CHECKED)) - trc_wait_for_one_reader(t, hop); - - // If check succeeded, remove this task from the list. - if (smp_load_acquire(&t->trc_ipi_to_cpu) == -1 && - rcu_ld_need_qs(t) == TRC_NEED_QS_CHECKED) - trc_del_holdout(t); - else if (needreport) - show_stalled_task_trace(t, firstreport); - cond_resched_tasks_rcu_qs(); - } - - // Re-enable CPU hotplug now that the holdout list scan has completed. - cpus_read_unlock(); - - if (needreport) { - if (*firstreport) - pr_err("INFO: rcu_tasks_trace detected stalls? (Late IPI?)\n"); - show_stalled_ipi_trace(); - } -} - -static void rcu_tasks_trace_empty_fn(void *unused) -{ -} - -/* Wait for grace period to complete and provide ordering. */ -static void rcu_tasks_trace_postgp(struct rcu_tasks *rtp) -{ - int cpu; - - // Wait for any lingering IPI handlers to complete. Note that - // if a CPU has gone offline or transitioned to userspace in the - // meantime, all IPI handlers should have been drained beforehand. - // Yes, this assumes that CPUs process IPIs in order. If that ever - // changes, there will need to be a recheck and/or timed wait. - for_each_online_cpu(cpu) - if (WARN_ON_ONCE(smp_load_acquire(per_cpu_ptr(&trc_ipi_to_cpu, cpu)))) - smp_call_function_single(cpu, rcu_tasks_trace_empty_fn, NULL, 1); - - smp_mb(); // Caller's code must be ordered after wakeup. - // Pairs with pretty much every ordering primitive. -} - -/* Report any needed quiescent state for this exiting task. */ -static void exit_tasks_rcu_finish_trace(struct task_struct *t) -{ - union rcu_special trs = READ_ONCE(t->trc_reader_special); - - rcu_trc_cmpxchg_need_qs(t, 0, TRC_NEED_QS_CHECKED); - WARN_ON_ONCE(READ_ONCE(t->trc_reader_nesting)); - if (WARN_ON_ONCE(rcu_ld_need_qs(t) & TRC_NEED_QS || trs.b.blocked)) - rcu_read_unlock_trace_special(t); - else - WRITE_ONCE(t->trc_reader_nesting, 0); -} - -/** - * call_rcu_tasks_trace() - Queue a callback trace task-based grace period - * @rhp: structure to be used for queueing the RCU updates. - * @func: actual callback function to be invoked after the grace period - * - * The callback function will be invoked some time after a trace rcu-tasks - * grace period elapses, in other words after all currently executing - * trace rcu-tasks read-side critical sections have completed. These - * read-side critical sections are delimited by calls to rcu_read_lock_trace() - * and rcu_read_unlock_trace(). - * - * See the description of call_rcu() for more detailed information on - * memory ordering guarantees. - */ -void call_rcu_tasks_trace(struct rcu_head *rhp, rcu_callback_t func) -{ - call_rcu_tasks_generic(rhp, func, &rcu_tasks_trace); -} -EXPORT_SYMBOL_GPL(call_rcu_tasks_trace); - -/** - * synchronize_rcu_tasks_trace - wait for a trace rcu-tasks grace period - * - * Control will return to the caller some time after a trace rcu-tasks - * grace period has elapsed, in other words after all currently executing - * trace rcu-tasks read-side critical sections have elapsed. These read-side - * critical sections are delimited by calls to rcu_read_lock_trace() - * and rcu_read_unlock_trace(). - * - * This is a very specialized primitive, intended only for a few uses in - * tracing and other situations requiring manipulation of function preambles - * and profiling hooks. The synchronize_rcu_tasks_trace() function is not - * (yet) intended for heavy use from multiple CPUs. - * - * See the description of synchronize_rcu() for more detailed information - * on memory ordering guarantees. - */ -void synchronize_rcu_tasks_trace(void) -{ - RCU_LOCKDEP_WARN(lock_is_held(&rcu_trace_lock_map), "Illegal synchronize_rcu_tasks_trace() in RCU Tasks Trace read-side critical section"); - synchronize_rcu_tasks_generic(&rcu_tasks_trace); -} -EXPORT_SYMBOL_GPL(synchronize_rcu_tasks_trace); - -/** - * rcu_barrier_tasks_trace - Wait for in-flight call_rcu_tasks_trace() callbacks. - * - * Although the current implementation is guaranteed to wait, it is not - * obligated to, for example, if there are no pending callbacks. - */ -void rcu_barrier_tasks_trace(void) -{ - rcu_barrier_tasks_generic(&rcu_tasks_trace); -} -EXPORT_SYMBOL_GPL(rcu_barrier_tasks_trace); - -int rcu_tasks_trace_lazy_ms = -1; -module_param(rcu_tasks_trace_lazy_ms, int, 0444); - -static int __init rcu_spawn_tasks_trace_kthread(void) -{ - if (IS_ENABLED(CONFIG_TASKS_TRACE_RCU_READ_MB)) { - rcu_tasks_trace.gp_sleep = HZ / 10; - rcu_tasks_trace.init_fract = HZ / 10; - } else { - rcu_tasks_trace.gp_sleep = HZ / 200; - if (rcu_tasks_trace.gp_sleep <= 0) - rcu_tasks_trace.gp_sleep = 1; - rcu_tasks_trace.init_fract = HZ / 200; - if (rcu_tasks_trace.init_fract <= 0) - rcu_tasks_trace.init_fract = 1; - } - if (rcu_tasks_trace_lazy_ms >= 0) - rcu_tasks_trace.lazy_jiffies = msecs_to_jiffies(rcu_tasks_trace_lazy_ms); - rcu_tasks_trace.pregp_func = rcu_tasks_trace_pregp_step; - rcu_tasks_trace.postscan_func = rcu_tasks_trace_postscan; - rcu_tasks_trace.holdouts_func = check_all_holdout_tasks_trace; - rcu_tasks_trace.postgp_func = rcu_tasks_trace_postgp; - rcu_spawn_tasks_kthread_generic(&rcu_tasks_trace); - return 0; -} - -#if !defined(CONFIG_TINY_RCU) -void show_rcu_tasks_trace_gp_kthread(void) -{ - char buf[64]; - - snprintf(buf, sizeof(buf), "N%lu h:%lu/%lu/%lu", - data_race(n_trc_holdouts), - data_race(n_heavy_reader_ofl_updates), - data_race(n_heavy_reader_updates), - data_race(n_heavy_reader_attempts)); - show_rcu_tasks_generic_gp_kthread(&rcu_tasks_trace, buf); -} -EXPORT_SYMBOL_GPL(show_rcu_tasks_trace_gp_kthread); - -void rcu_tasks_trace_torture_stats_print(char *tt, char *tf) -{ - rcu_tasks_torture_stats_print_generic(&rcu_tasks_trace, tt, tf, ""); -} -EXPORT_SYMBOL_GPL(rcu_tasks_trace_torture_stats_print); -#endif // !defined(CONFIG_TINY_RCU) - -struct task_struct *get_rcu_tasks_trace_gp_kthread(void) -{ - return rcu_tasks_trace.kthread_ptr; -} -EXPORT_SYMBOL_GPL(get_rcu_tasks_trace_gp_kthread); - -void rcu_tasks_trace_get_gp_data(int *flags, unsigned long *gp_seq) -{ - *flags = 0; - *gp_seq = rcu_seq_current(&rcu_tasks_trace.tasks_gp_seq); -} -EXPORT_SYMBOL_GPL(rcu_tasks_trace_get_gp_data); - -#else /* #ifdef CONFIG_TASKS_TRACE_RCU */ -static void exit_tasks_rcu_finish_trace(struct task_struct *t) { } -#endif /* #else #ifdef CONFIG_TASKS_TRACE_RCU */ - #ifndef CONFIG_TINY_RCU void show_rcu_tasks_gp_kthreads(void) { show_rcu_tasks_classic_gp_kthread(); show_rcu_tasks_rude_gp_kthread(); - show_rcu_tasks_trace_gp_kthread(); } #endif /* #ifndef CONFIG_TINY_RCU */ @@ -2251,10 +1570,6 @@ void __init tasks_cblist_init_generic(void) #ifdef CONFIG_TASKS_RUDE_RCU cblist_init_generic(&rcu_tasks_rude); #endif - -#ifdef CONFIG_TASKS_TRACE_RCU - cblist_init_generic(&rcu_tasks_trace); -#endif } static int __init rcu_init_tasks_generic(void) @@ -2267,10 +1582,6 @@ static int __init rcu_init_tasks_generic(void) rcu_spawn_tasks_rude_kthread(); #endif -#ifdef CONFIG_TASKS_TRACE_RCU - rcu_spawn_tasks_trace_kthread(); -#endif - // Run the self-tests. rcu_tasks_initiate_self_tests(); @@ -2281,3 +1592,16 @@ core_initcall(rcu_init_tasks_generic); #else /* #ifdef CONFIG_TASKS_RCU_GENERIC */ static inline void rcu_tasks_bootup_oddness(void) {} #endif /* #else #ifdef CONFIG_TASKS_RCU_GENERIC */ + +#ifdef CONFIG_TASKS_TRACE_RCU + +//////////////////////////////////////////////////////////////////////// +// +// Tracing variant of Tasks RCU. This variant is designed to be used +// to protect tracing hooks, including those of BPF. This variant +// is implemented via a straightforward mapping onto SRCU-fast. + +DEFINE_SRCU_FAST(rcu_tasks_trace_srcu_struct); +EXPORT_SYMBOL_GPL(rcu_tasks_trace_srcu_struct); + +#endif /* #else #ifdef CONFIG_TASKS_TRACE_RCU */ diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 293bbd9ac3f4..55df6d37145e 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -160,6 +160,7 @@ static void rcu_report_qs_rnp(unsigned long mask, struct rcu_node *rnp, unsigned long gps, unsigned long flags); static void invoke_rcu_core(void); static void rcu_report_exp_rdp(struct rcu_data *rdp); +static void rcu_report_qs_rdp(struct rcu_data *rdp); static void check_cb_ovld_locked(struct rcu_data *rdp, struct rcu_node *rnp); static bool rcu_rdp_is_offloaded(struct rcu_data *rdp); static bool rcu_rdp_cpu_online(struct rcu_data *rdp); @@ -1983,6 +1984,17 @@ static noinline_for_stack bool rcu_gp_init(void) if (IS_ENABLED(CONFIG_RCU_STRICT_GRACE_PERIOD)) on_each_cpu(rcu_strict_gp_boundary, NULL, 0); + /* + * Immediately report QS for the GP kthread's CPU. The GP kthread + * cannot be in an RCU read-side critical section while running + * the FQS scan. This eliminates the need for a second FQS wait + * when all CPUs are idle. + */ + preempt_disable(); + rcu_qs(); + rcu_report_qs_rdp(this_cpu_ptr(&rcu_data)); + preempt_enable(); + return true; } @@ -3769,7 +3781,7 @@ static void rcu_barrier_entrain(struct rcu_data *rdp) } rcu_nocb_unlock(rdp); if (wake_nocb) - wake_nocb_gp(rdp, false); + wake_nocb_gp(rdp); smp_store_release(&rdp->barrier_seq_snap, gseq); } diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h index b8bbe7960cda..7dfc57e9adb1 100644 --- a/kernel/rcu/tree.h +++ b/kernel/rcu/tree.h @@ -203,7 +203,7 @@ struct rcu_data { /* during and after the last grace */ /* period it is aware of. */ struct irq_work defer_qs_iw; /* Obtain later scheduler attention. */ - int defer_qs_iw_pending; /* Scheduler attention pending? */ + int defer_qs_pending; /* irqwork or softirq pending? */ struct work_struct strict_work; /* Schedule readers for strict GPs. */ /* 2) batch handling */ @@ -301,7 +301,6 @@ struct rcu_data { #define RCU_NOCB_WAKE_BYPASS 1 #define RCU_NOCB_WAKE_LAZY 2 #define RCU_NOCB_WAKE 3 -#define RCU_NOCB_WAKE_FORCE 4 #define RCU_JIFFIES_TILL_FORCE_QS (1 + (HZ > 250) + (HZ > 500)) /* For jiffies_till_first_fqs and */ @@ -500,7 +499,7 @@ static void zero_cpu_stall_ticks(struct rcu_data *rdp); 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 wake_nocb_gp(struct rcu_data *rdp, bool force); +static bool wake_nocb_gp(struct rcu_data *rdp); static bool rcu_nocb_flush_bypass(struct rcu_data *rdp, struct rcu_head *rhp, unsigned long j, bool lazy); static void call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *head, diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h index 96c49c56fc14..82cada459e5d 100644 --- a/kernel/rcu/tree_exp.h +++ b/kernel/rcu/tree_exp.h @@ -589,7 +589,12 @@ static void synchronize_rcu_expedited_stall(unsigned long jiffies_start, unsigne pr_cont(" } %lu jiffies s: %lu root: %#lx/%c\n", j - jiffies_start, rcu_state.expedited_sequence, data_race(rnp_root->expmask), ".T"[!!data_race(rnp_root->exp_tasks)]); - if (ndetected) { + if (!ndetected) { + // This is invoked from the grace-period worker, so + // a new grace period cannot have started. And if this + // worker were stalled, we would not get here. ;-) + pr_err("INFO: Expedited stall ended before state dump start\n"); + } else { pr_err("blocking rcu_node structures (internal RCU debug):"); rcu_for_each_node_breadth_first(rnp) { if (rnp == rnp_root) diff --git a/kernel/rcu/tree_nocb.h b/kernel/rcu/tree_nocb.h index e6cd56603cad..b3337c7231cc 100644 --- a/kernel/rcu/tree_nocb.h +++ b/kernel/rcu/tree_nocb.h @@ -190,9 +190,18 @@ static void rcu_init_one_nocb(struct rcu_node *rnp) init_swait_queue_head(&rnp->nocb_gp_wq[1]); } +/* Clear any pending deferred wakeup timer (nocb_gp_lock must be held). */ +static void nocb_defer_wakeup_cancel(struct rcu_data *rdp_gp) +{ + if (rdp_gp->nocb_defer_wakeup > RCU_NOCB_WAKE_NOT) { + WRITE_ONCE(rdp_gp->nocb_defer_wakeup, RCU_NOCB_WAKE_NOT); + timer_delete(&rdp_gp->nocb_timer); + } +} + static bool __wake_nocb_gp(struct rcu_data *rdp_gp, struct rcu_data *rdp, - bool force, unsigned long flags) + unsigned long flags) __releases(rdp_gp->nocb_gp_lock) { bool needwake = false; @@ -204,12 +213,9 @@ static bool __wake_nocb_gp(struct rcu_data *rdp_gp, return false; } - if (rdp_gp->nocb_defer_wakeup > RCU_NOCB_WAKE_NOT) { - WRITE_ONCE(rdp_gp->nocb_defer_wakeup, RCU_NOCB_WAKE_NOT); - timer_delete(&rdp_gp->nocb_timer); - } + nocb_defer_wakeup_cancel(rdp_gp); - if (force || READ_ONCE(rdp_gp->nocb_gp_sleep)) { + if (READ_ONCE(rdp_gp->nocb_gp_sleep)) { WRITE_ONCE(rdp_gp->nocb_gp_sleep, false); needwake = true; } @@ -225,13 +231,13 @@ static bool __wake_nocb_gp(struct rcu_data *rdp_gp, /* * Kick the GP kthread for this NOCB group. */ -static bool wake_nocb_gp(struct rcu_data *rdp, bool force) +static bool wake_nocb_gp(struct rcu_data *rdp) { unsigned long flags; struct rcu_data *rdp_gp = rdp->nocb_gp_rdp; raw_spin_lock_irqsave(&rdp_gp->nocb_gp_lock, flags); - return __wake_nocb_gp(rdp_gp, rdp, force, flags); + return __wake_nocb_gp(rdp_gp, rdp, flags); } #ifdef CONFIG_RCU_LAZY @@ -518,22 +524,17 @@ static bool rcu_nocb_try_bypass(struct rcu_data *rdp, struct rcu_head *rhp, } /* - * Awaken the no-CBs grace-period kthread if needed, either due to it - * legitimately being asleep or due to overload conditions. - * - * If warranted, also wake up the kthread servicing this CPUs queues. + * Awaken the no-CBs grace-period kthread if needed due to it legitimately + * being asleep. */ static void __call_rcu_nocb_wake(struct rcu_data *rdp, bool was_alldone, unsigned long flags) __releases(rdp->nocb_lock) { long bypass_len; - unsigned long cur_gp_seq; - unsigned long j; long lazy_len; long len; struct task_struct *t; - struct rcu_data *rdp_gp = rdp->nocb_gp_rdp; // If we are being polled or there is no kthread, just leave. t = READ_ONCE(rdp->nocb_gp_kthread); @@ -549,47 +550,26 @@ static void __call_rcu_nocb_wake(struct rcu_data *rdp, bool was_alldone, lazy_len = READ_ONCE(rdp->lazy_len); if (was_alldone) { rdp->qlen_last_fqs_check = len; + rcu_nocb_unlock(rdp); // Only lazy CBs in bypass list if (lazy_len && bypass_len == lazy_len) { - rcu_nocb_unlock(rdp); wake_nocb_gp_defer(rdp, RCU_NOCB_WAKE_LAZY, TPS("WakeLazy")); } else if (!irqs_disabled_flags(flags)) { /* ... if queue was empty ... */ - rcu_nocb_unlock(rdp); - wake_nocb_gp(rdp, false); + wake_nocb_gp(rdp); trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, TPS("WakeEmpty")); } else { - rcu_nocb_unlock(rdp); wake_nocb_gp_defer(rdp, RCU_NOCB_WAKE, TPS("WakeEmptyIsDeferred")); } - } else if (len > rdp->qlen_last_fqs_check + qhimark) { - /* ... or if many callbacks queued. */ - rdp->qlen_last_fqs_check = len; - j = jiffies; - if (j != rdp->nocb_gp_adv_time && - rcu_segcblist_nextgp(&rdp->cblist, &cur_gp_seq) && - rcu_seq_done(&rdp->mynode->gp_seq, cur_gp_seq)) { - rcu_advance_cbs_nowake(rdp->mynode, rdp); - rdp->nocb_gp_adv_time = j; - } - smp_mb(); /* Enqueue before timer_pending(). */ - if ((rdp->nocb_cb_sleep || - !rcu_segcblist_ready_cbs(&rdp->cblist)) && - !timer_pending(&rdp_gp->nocb_timer)) { - rcu_nocb_unlock(rdp); - wake_nocb_gp_defer(rdp, RCU_NOCB_WAKE_FORCE, - TPS("WakeOvfIsDeferred")); - } else { - rcu_nocb_unlock(rdp); - trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, TPS("WakeNot")); - } - } else { - rcu_nocb_unlock(rdp); - trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, TPS("WakeNot")); + + return; } + + rcu_nocb_unlock(rdp); + trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, TPS("WakeNot")); } static void call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *head, @@ -814,10 +794,7 @@ static void nocb_gp_wait(struct rcu_data *my_rdp) if (rdp_toggling) my_rdp->nocb_toggling_rdp = NULL; - if (my_rdp->nocb_defer_wakeup > RCU_NOCB_WAKE_NOT) { - WRITE_ONCE(my_rdp->nocb_defer_wakeup, RCU_NOCB_WAKE_NOT); - timer_delete(&my_rdp->nocb_timer); - } + nocb_defer_wakeup_cancel(my_rdp); WRITE_ONCE(my_rdp->nocb_gp_sleep, true); raw_spin_unlock_irqrestore(&my_rdp->nocb_gp_lock, flags); } else { @@ -966,7 +943,6 @@ static bool do_nocb_deferred_wakeup_common(struct rcu_data *rdp_gp, unsigned long flags) __releases(rdp_gp->nocb_gp_lock) { - int ndw; int ret; if (!rcu_nocb_need_deferred_wakeup(rdp_gp, level)) { @@ -974,8 +950,7 @@ static bool do_nocb_deferred_wakeup_common(struct rcu_data *rdp_gp, return false; } - ndw = rdp_gp->nocb_defer_wakeup; - ret = __wake_nocb_gp(rdp_gp, rdp, ndw == RCU_NOCB_WAKE_FORCE, flags); + ret = __wake_nocb_gp(rdp_gp, rdp, flags); trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, TPS("DeferredWake")); return ret; @@ -991,7 +966,6 @@ static void do_nocb_deferred_wakeup_timer(struct timer_list *t) trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, TPS("Timer")); raw_spin_lock_irqsave(&rdp->nocb_gp_lock, flags); - smp_mb__after_spinlock(); /* Timer expire before wakeup. */ do_nocb_deferred_wakeup_common(rdp, rdp, RCU_NOCB_WAKE_BYPASS, flags); } @@ -1272,7 +1246,7 @@ lazy_rcu_shrink_scan(struct shrinker *shrink, struct shrink_control *sc) } rcu_nocb_try_flush_bypass(rdp, jiffies); rcu_nocb_unlock_irqrestore(rdp, flags); - wake_nocb_gp(rdp, false); + wake_nocb_gp(rdp); sc->nr_to_scan -= _count; count += _count; if (sc->nr_to_scan <= 0) @@ -1657,7 +1631,7 @@ static void rcu_init_one_nocb(struct rcu_node *rnp) { } -static bool wake_nocb_gp(struct rcu_data *rdp, bool force) +static bool wake_nocb_gp(struct rcu_data *rdp) { return false; } diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index dbe2d02be824..95ad967adcf3 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -487,8 +487,8 @@ rcu_preempt_deferred_qs_irqrestore(struct task_struct *t, unsigned long flags) union rcu_special special; rdp = this_cpu_ptr(&rcu_data); - if (rdp->defer_qs_iw_pending == DEFER_QS_PENDING) - rdp->defer_qs_iw_pending = DEFER_QS_IDLE; + if (rdp->defer_qs_pending == DEFER_QS_PENDING) + rdp->defer_qs_pending = DEFER_QS_IDLE; /* * If RCU core is waiting for this CPU to exit its critical section, @@ -645,7 +645,7 @@ static void rcu_preempt_deferred_qs_handler(struct irq_work *iwp) * 5. Deferred QS reporting does not happen. */ if (rcu_preempt_depth() > 0) - WRITE_ONCE(rdp->defer_qs_iw_pending, DEFER_QS_IDLE); + WRITE_ONCE(rdp->defer_qs_pending, DEFER_QS_IDLE); } /* @@ -747,7 +747,10 @@ static void rcu_read_unlock_special(struct task_struct *t) // Using softirq, safe to awaken, and either the // wakeup is free or there is either an expedited // GP in flight or a potential need to deboost. - raise_softirq_irqoff(RCU_SOFTIRQ); + if (rdp->defer_qs_pending != DEFER_QS_PENDING) { + rdp->defer_qs_pending = DEFER_QS_PENDING; + raise_softirq_irqoff(RCU_SOFTIRQ); + } } else { // Enabling BH or preempt does reschedule, so... // Also if no expediting and no possible deboosting, @@ -755,11 +758,11 @@ static void rcu_read_unlock_special(struct task_struct *t) // tick enabled. set_need_resched_current(); if (IS_ENABLED(CONFIG_IRQ_WORK) && irqs_were_disabled && - needs_exp && rdp->defer_qs_iw_pending != DEFER_QS_PENDING && + needs_exp && rdp->defer_qs_pending != DEFER_QS_PENDING && cpu_online(rdp->cpu)) { // Get scheduler to re-evaluate and call hooks. // If !IRQ_WORK, FQS scan will eventually IPI. - rdp->defer_qs_iw_pending = DEFER_QS_PENDING; + rdp->defer_qs_pending = DEFER_QS_PENDING; irq_work_queue_on(&rdp->defer_qs_iw, rdp->cpu); } } diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl index c0250244cf7a..362a8d1cd327 100755 --- a/scripts/checkpatch.pl +++ b/scripts/checkpatch.pl @@ -863,7 +863,9 @@ our %deprecated_apis = ( #These should be enough to drive away new IDR users "DEFINE_IDR" => "DEFINE_XARRAY", "idr_init" => "xa_init", - "idr_init_base" => "xa_init_flags" + "idr_init_base" => "xa_init_flags", + "rcu_read_lock_trace" => "rcu_read_lock_tasks_trace", + "rcu_read_unlock_trace" => "rcu_read_unlock_tasks_trace", ); #Create a search pattern for all these strings to speed up a loop below diff --git a/tools/testing/selftests/rcutorture/.gitignore b/tools/testing/selftests/rcutorture/.gitignore index f6cbce77460b..b8fd42547a6e 100644 --- a/tools/testing/selftests/rcutorture/.gitignore +++ b/tools/testing/selftests/rcutorture/.gitignore @@ -3,3 +3,4 @@ initrd b[0-9]* res *.swp +.kvm.sh.lock diff --git a/tools/testing/selftests/rcutorture/bin/config2csv.sh b/tools/testing/selftests/rcutorture/bin/config2csv.sh index 0cf55f1bf654..aeab4d6f11ad 100755 --- a/tools/testing/selftests/rcutorture/bin/config2csv.sh +++ b/tools/testing/selftests/rcutorture/bin/config2csv.sh @@ -42,7 +42,7 @@ do grep -v '^#' < $i | grep -v '^ *$' > $T/p if test -r $i.boot then - tr -s ' ' '\012' < $i.boot | grep -v '^#' >> $T/p + sed -e 's/#.*$//' < $i.boot | tr -s ' ' '\012' >> $T/p fi sed -e 's/^[^=]*$/&=?/' < $T/p | sed -e 's/^\([^=]*\)=\(.*\)$/\tp["\1:'"$i"'"] = "\2";\n\tc["\1"] = 1;/' >> $T/p.awk diff --git a/tools/testing/selftests/rcutorture/bin/kvm-series.sh b/tools/testing/selftests/rcutorture/bin/kvm-series.sh index 2ff905a1853b..c4ee5f910931 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-series.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-series.sh @@ -15,7 +15,7 @@ # This script is intended to replace kvm-check-branches.sh by providing # ease of use and faster execution. -T="`mktemp -d ${TMPDIR-/tmp}/kvm-series.sh.XXXXXX`" +T="`mktemp -d ${TMPDIR-/tmp}/kvm-series.sh.XXXXXX`"; export T trap 'rm -rf $T' 0 scriptname=$0 @@ -32,6 +32,7 @@ then echo "$0: Repetition ('*') not allowed in config list." exit 1 fi +config_list_len="`echo ${config_list} | wc -w | awk '{ print $1; }'`" commit_list="${2}" if test -z "${commit_list}" @@ -47,70 +48,209 @@ then exit 2 fi sha1_list=`cat $T/commits` +sha1_list_len="`echo ${sha1_list} | wc -w | awk '{ print $1; }'`" shift shift RCUTORTURE="`pwd`/tools/testing/selftests/rcutorture"; export RCUTORTURE PATH=${RCUTORTURE}/bin:$PATH; export PATH +RES="${RCUTORTURE}/res"; export RES . functions.sh ret=0 -nfail=0 +nbuildfail=0 +nrunfail=0 nsuccess=0 -faillist= +ncpus=0 +buildfaillist= +runfaillist= successlist= cursha1="`git rev-parse --abbrev-ref HEAD`" ds="`date +%Y.%m.%d-%H.%M.%S`-series" +DS="${RES}/${ds}"; export DS startdate="`date`" starttime="`get_starttime`" echo " --- " $scriptname $args | tee -a $T/log echo " --- Results directory: " $ds | tee -a $T/log +# Do all builds. Iterate through commits within a given scenario +# because builds normally go faster from one commit to the next within a +# given scenario. In contrast, switching scenarios on each rebuild will +# often force a full rebuild due to Kconfig differences, for example, +# turning preemption on and off. Defer actual runs in order to run +# lots of them concurrently on large systems. +touch $T/torunlist +n2build="$((config_list_len*sha1_list_len))" +nbuilt=0 for config in ${config_list} do sha_n=0 for sha in ${sha1_list} do sha1=${sha_n}.${sha} # Enable "sort -k1nr" to list commits in order. - echo Starting ${config}/${sha1} at `date` | tee -a $T/log - git checkout "${sha}" - time tools/testing/selftests/rcutorture/bin/kvm.sh --configs "$config" --datestamp "$ds/${config}/${sha1}" --duration 1 "$@" + echo + echo Starting ${config}/${sha1} "($((nbuilt+1)) of ${n2build})" at `date` | tee -a $T/log + git checkout --detach "${sha}" + tools/testing/selftests/rcutorture/bin/kvm.sh --configs "$config" --datestamp "$ds/${config}/${sha1}" --duration 1 --build-only --trust-make "$@" curret=$? if test "${curret}" -ne 0 then - nfail=$((nfail+1)) - faillist="$faillist ${config}/${sha1}(${curret})" + nbuildfail=$((nbuildfail+1)) + buildfaillist="$buildfaillist ${config}/${sha1}(${curret})" else - nsuccess=$((nsuccess+1)) - successlist="$successlist ${config}/${sha1}" - # Successful run, so remove large files. - rm -f ${RCUTORTURE}/$ds/${config}/${sha1}/{vmlinux,bzImage,System.map,Module.symvers} + batchncpus="`grep -v "^# cpus=" "${DS}/${config}/${sha1}/batches" | awk '{ sum += $3 } END { print sum }'`" + echo run_one_qemu ${sha_n} ${config}/${sha1} ${batchncpus} >> $T/torunlist + if test "${ncpus}" -eq 0 + then + ncpus="`grep "^# cpus=" "${DS}/${config}/${sha1}/batches" | sed -e 's/^# cpus=//'`" + case "${ncpus}" in + ^[0-9]*$) + ;; + *) + ncpus=0 + ;; + esac + fi fi if test "${ret}" -eq 0 then ret=${curret} fi sha_n=$((sha_n+1)) + nbuilt=$((nbuilt+1)) done done + +# If the user did not specify the number of CPUs, use them all. +if test "${ncpus}" -eq 0 +then + ncpus="`identify_qemu_vcpus`" +fi + +cpusused=0 +touch $T/successlistfile +touch $T/faillistfile +n2run="`wc -l $T/torunlist | awk '{ print $1; }'`" +nrun=0 + +# do_run_one_qemu ds resultsdir qemu_curout +# +# Start the specified qemu run and record its success or failure. +do_run_one_qemu () { + local ret + local ds="$1" + local resultsdir="$2" + local qemu_curout="$3" + + tools/testing/selftests/rcutorture/bin/kvm-again.sh "${DS}/${resultsdir}" --link inplace-force > ${qemu_curout} 2>&1 + ret=$? + if test "${ret}" -eq 0 + then + echo ${resultsdir} >> $T/successlistfile + # Successful run, so remove large files. + rm -f ${DS}/${resultsdir}/{vmlinux,bzImage,System.map,Module.symvers} + else + echo "${resultsdir}(${ret})" >> $T/faillistfile + fi +} + +# cleanup_qemu_batch batchncpus +# +# Update success and failure lists, files, and counts at the end of +# a batch. +cleanup_qemu_batch () { + local batchncpus="$1" + + echo Waiting, cpusused=${cpusused}, ncpus=${ncpus} `date` | tee -a $T/log + wait + cpusused="${batchncpus}" + nsuccessbatch="`wc -l $T/successlistfile | awk '{ print $1 }'`" + nsuccess=$((nsuccess+nsuccessbatch)) + successlist="$successlist `cat $T/successlistfile`" + rm $T/successlistfile + touch $T/successlistfile + nfailbatch="`wc -l $T/faillistfile | awk '{ print $1 }'`" + nrunfail=$((nrunfail+nfailbatch)) + runfaillist="$runfaillist `cat $T/faillistfile`" + rm $T/faillistfile + touch $T/faillistfile +} + +# run_one_qemu sha_n config/sha1 batchncpus +# +# Launch into the background the sha_n-th qemu job whose results directory +# is config/sha1 and which uses batchncpus CPUs. Once we reach a job that +# would overflow the number of available CPUs, wait for the previous jobs +# to complete and record their results. +run_one_qemu () { + local sha_n="$1" + local config_sha1="$2" + local batchncpus="$3" + local qemu_curout + + cpusused=$((cpusused+batchncpus)) + if test "${cpusused}" -gt $ncpus + then + cleanup_qemu_batch "${batchncpus}" + fi + echo Starting ${config_sha1} using ${batchncpus} CPUs "($((nrun+1)) of ${n2run})" `date` + qemu_curout="${DS}/${config_sha1}/qemu-series" + do_run_one_qemu "$ds" "${config_sha1}" ${qemu_curout} & + nrun="$((nrun+1))" +} + +# Re-ordering the runs will mess up the affinity chosen at build time +# (among other things, over-using CPU 0), so suppress it. +TORTURE_NO_AFFINITY="no-affinity"; export TORTURE_NO_AFFINITY + +# Run the kernels (if any) that built correctly. +echo | tee -a $T/log # Put a blank line between build and run messages. +. $T/torunlist +cleanup_qemu_batch "${batchncpus}" + +# Get back to initial checkout/SHA-1. git checkout "${cursha1}" -echo ${nsuccess} SUCCESSES: | tee -a $T/log -echo ${successlist} | fmt | tee -a $T/log -echo | tee -a $T/log -echo ${nfail} FAILURES: | tee -a $T/log -echo ${faillist} | fmt | tee -a $T/log -if test -n "${faillist}" +# Throw away leading and trailing space characters for fmt. +successlist="`echo ${successlist} | sed -e 's/^ *//' -e 's/ *$//'`" +buildfaillist="`echo ${buildfaillist} | sed -e 's/^ *//' -e 's/ *$//'`" +runfaillist="`echo ${runfaillist} | sed -e 's/^ *//' -e 's/ *$//'`" + +# Print lists of successes, build failures, and run failures, if any. +if test "${nsuccess}" -gt 0 +then + echo | tee -a $T/log + echo ${nsuccess} SUCCESSES: | tee -a $T/log + echo ${successlist} | fmt | tee -a $T/log +fi +if test "${nbuildfail}" -gt 0 then echo | tee -a $T/log - echo Failures across commits: | tee -a $T/log - echo ${faillist} | tr ' ' '\012' | sed -e 's,^[^/]*/,,' -e 's/([0-9]*)//' | + echo ${nbuildfail} BUILD FAILURES: | tee -a $T/log + echo ${buildfaillist} | fmt | tee -a $T/log +fi +if test "${nrunfail}" -gt 0 +then + echo | tee -a $T/log + echo ${nrunfail} RUN FAILURES: | tee -a $T/log + echo ${runfaillist} | fmt | tee -a $T/log +fi + +# If there were build or runtime failures, map them to commits. +if test "${nbuildfail}" -gt 0 || test "${nrunfail}" -gt 0 +then + echo | tee -a $T/log + echo Build failures across commits: | tee -a $T/log + echo ${buildfaillist} | tr ' ' '\012' | sed -e 's,^[^/]*/,,' -e 's/([0-9]*)//' | sort | uniq -c | sort -k2n | tee -a $T/log fi + +# Print run summary. +echo | tee -a $T/log echo Started at $startdate, ended at `date`, duration `get_starttime_duration $starttime`. | tee -a $T/log -echo Summary: Successes: ${nsuccess} Failures: ${nfail} | tee -a $T/log -cp $T/log tools/testing/selftests/rcutorture/res/${ds} +echo Summary: Successes: ${nsuccess} " "Build Failures: ${nbuildfail} " "Runtime Failures: ${nrunfail}| tee -a $T/log +cp $T/log ${DS} exit "${ret}" diff --git a/tools/testing/selftests/rcutorture/bin/kvm.sh b/tools/testing/selftests/rcutorture/bin/kvm.sh index fff15821c44c..65b04b832733 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm.sh @@ -80,6 +80,7 @@ usage () { echo " --kasan" echo " --kconfig Kconfig-options" echo " --kcsan" + echo " --kill-previous" echo " --kmake-arg kernel-make-arguments" echo " --mac nn:nn:nn:nn:nn:nn" echo " --memory megabytes|nnnG" @@ -206,6 +207,9 @@ do --kcsan) TORTURE_KCONFIG_KCSAN_ARG="$debuginfo CONFIG_KCSAN=y CONFIG_KCSAN_STRICT=y CONFIG_KCSAN_REPORT_ONCE_IN_MS=100000 CONFIG_KCSAN_VERBOSE=y CONFIG_DEBUG_LOCK_ALLOC=y CONFIG_PROVE_LOCKING=y"; export TORTURE_KCONFIG_KCSAN_ARG ;; + --kill-previous) + TORTURE_KILL_PREVIOUS=1 + ;; --kmake-arg|--kmake-args) checkarg --kmake-arg "(kernel make arguments)" $# "$2" '.*' '^error$' TORTURE_KMAKE_ARG="`echo "$TORTURE_KMAKE_ARG $2" | sed -e 's/^ *//' -e 's/ *$//'`" @@ -275,6 +279,42 @@ do shift done +# Prevent concurrent kvm.sh runs on the same source tree. The flock +# is automatically released when the script exits, even if killed. +TORTURE_LOCK="$RCUTORTURE/.kvm.sh.lock" + +# Terminate any processes holding the lock file, if requested. +if test -n "$TORTURE_KILL_PREVIOUS" +then + if test -e "$TORTURE_LOCK" + then + echo "Killing processes holding $TORTURE_LOCK..." + if fuser -k "$TORTURE_LOCK" >/dev/null 2>&1 + then + sleep 2 + echo "Previous kvm.sh processes killed." + else + echo "No processes were holding the lock." + fi + else + echo "No lock file exists, nothing to kill." + fi +fi + +if test -z "$dryrun" +then + # Create a file descriptor and flock it, so that when kvm.sh (and its + # children) exit, the flock is released by the kernel automatically. + exec 9>"$TORTURE_LOCK" + if ! flock -n 9 + then + echo "ERROR: Another kvm.sh instance is already running on this tree." + echo " Lock file: $TORTURE_LOCK" + echo " To run kvm.sh, kill all existing kvm.sh runs first (--kill-previous)." + exit 1 + fi +fi + if test -n "$dryrun" || test -z "$TORTURE_INITRD" || tools/testing/selftests/rcutorture/bin/mkinitrd.sh then : diff --git a/tools/testing/selftests/rcutorture/bin/mktestid.sh b/tools/testing/selftests/rcutorture/bin/mktestid.sh index 16f9907a4dae..24f6261dab6a 100755 --- a/tools/testing/selftests/rcutorture/bin/mktestid.sh +++ b/tools/testing/selftests/rcutorture/bin/mktestid.sh @@ -18,7 +18,7 @@ fi echo Build directory: `pwd` > ${resdir}/testid.txt if test -d .git then - echo Current commit: `git rev-parse HEAD` >> ${resdir}/testid.txt + echo Current commit: `git show --oneline --no-patch HEAD` >> ${resdir}/testid.txt echo >> ${resdir}/testid.txt echo ' ---' Output of "'"git status"'": >> ${resdir}/testid.txt git status >> ${resdir}/testid.txt diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TRACE01 b/tools/testing/selftests/rcutorture/configs/rcu/TRACE01 index 85b407467454..18efab346381 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TRACE01 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TRACE01 @@ -10,5 +10,4 @@ CONFIG_PROVE_LOCKING=n #CHECK#CONFIG_PROVE_RCU=n CONFIG_FORCE_TASKS_TRACE_RCU=y #CHECK#CONFIG_TASKS_TRACE_RCU=y -CONFIG_TASKS_TRACE_RCU_READ_MB=y CONFIG_RCU_EXPERT=y diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TRACE02 b/tools/testing/selftests/rcutorture/configs/rcu/TRACE02 index 9003c56cd764..8da390e82829 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TRACE02 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TRACE02 @@ -9,6 +9,5 @@ CONFIG_PROVE_LOCKING=y #CHECK#CONFIG_PROVE_RCU=y CONFIG_FORCE_TASKS_TRACE_RCU=y #CHECK#CONFIG_TASKS_TRACE_RCU=y -CONFIG_TASKS_TRACE_RCU_READ_MB=n CONFIG_RCU_EXPERT=y CONFIG_DEBUG_OBJECTS=y |