diff --git a/Documentation/RCU/Design/Requirements/Requirements.html b/Documentation/RCU/Design/Requirements/Requirements.html index 5a9238a2883c..467251f7fef6 100644 --- a/Documentation/RCU/Design/Requirements/Requirements.html +++ b/Documentation/RCU/Design/Requirements/Requirements.html @@ -2129,6 +2129,8 @@ Some of the relevant points of interest are as follows:
  • Hotplug CPU.
  • Scheduler and RCU.
  • Tracing and RCU. +
  • +Accesses to User Memory and RCU.
  • Energy Efficiency.
  • Scheduling-Clock Interrupts and RCU. @@ -2512,7 +2514,7 @@ disabled across the entire RCU read-side critical section.

    It is possible to use tracing on RCU code, but tracing itself uses RCU. -For this reason, rcu_dereference_raw_notrace() +For this reason, rcu_dereference_raw_check() is provided for use by tracing, which avoids the destructive recursion that could otherwise ensue. This API is also used by virtualization in some architectures, @@ -2521,6 +2523,75 @@ cannot be used. The tracing folks both located the requirement and provided the needed fix, so this surprise requirement was relatively painless. +

    +Accesses to User Memory and RCU

    + +

    +The kernel needs to access user-space memory, for example, to access +data referenced by system-call parameters. +The get_user() macro does this job. + +

    +However, user-space memory might well be paged out, which means +that get_user() might well page-fault and thus block while +waiting for the resulting I/O to complete. +It would be a very bad thing for the compiler to reorder +a get_user() invocation into an RCU read-side critical +section. +For example, suppose that the source code looked like this: + +

    +
    + 1 rcu_read_lock();
+ 2 p = rcu_dereference(gp);
+ 3 v = p->value;
+ 4 rcu_read_unlock();
+ 5 get_user(user_v, user_p);
+ 6 do_something_with(v, user_v);
+
    +
    + +

    +The compiler must not be permitted to transform this source code into +the following: + +

    +
    + 1 rcu_read_lock();
+ 2 p = rcu_dereference(gp);
+ 3 get_user(user_v, user_p); // BUG: POSSIBLE PAGE FAULT!!!
+ 4 v = p->value;
+ 5 rcu_read_unlock();
+ 6 do_something_with(v, user_v);
+
    +
    + +

    +If the compiler did make this transformation in a +CONFIG_PREEMPT=n kernel build, and if get_user() did +page fault, the result would be a quiescent state in the middle +of an RCU read-side critical section. +This misplaced quiescent state could result in line 4 being +a use-after-free access, which could be bad for your kernel's +actuarial statistics. +Similar examples can be constructed with the call to get_user() +preceding the rcu_read_lock(). + +

    +Unfortunately, get_user() doesn't have any particular +ordering properties, and in some architectures the underlying asm +isn't even marked volatile. +And even if it was marked volatile, the above access to +p->value is not volatile, so the compiler would not have any +reason to keep those two accesses in order. + +

    +Therefore, the Linux-kernel definitions of rcu_read_lock() +and rcu_read_unlock() must act as compiler barriers, +at least for outermost instances of rcu_read_lock() and +rcu_read_unlock() within a nested set of RCU read-side critical +sections. +

    Energy Efficiency

    diff --git a/Documentation/RCU/stallwarn.txt b/Documentation/RCU/stallwarn.txt index 13e88fc00f01..f48f4621ccbc 100644 --- a/Documentation/RCU/stallwarn.txt +++ b/Documentation/RCU/stallwarn.txt @@ -57,6 +57,12 @@ o A CPU-bound real-time task in a CONFIG_PREEMPT_RT kernel that CONFIG_PREEMPT_RCU case, you might see stall-warning messages. + You can use the rcutree.kthread_prio kernel boot parameter to + increase the scheduling priority of RCU's kthreads, which can + help avoid this problem. However, please note that doing this + can increase your system's context-switch rate and thus degrade + performance. + o A periodic interrupt whose handler takes longer than the time interval between successive pairs of interrupts. This can prevent RCU's kthreads and softirq handlers from running. diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 7ccd158b3894..f3fcd6140ee1 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -4047,6 +4047,10 @@ rcutorture.verbose= [KNL] Enable additional printk() statements. + rcupdate.rcu_cpu_stall_ftrace_dump= [KNL] + Dump ftrace buffer after reporting RCU CPU + stall warning. + rcupdate.rcu_cpu_stall_suppress= [KNL] Suppress RCU CPU stall warning messages. diff --git a/MAINTAINERS b/MAINTAINERS index 6426db5198f0..527317026492 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -9326,7 +9326,7 @@ F: drivers/misc/lkdtm/* LINUX KERNEL MEMORY CONSISTENCY MODEL (LKMM) M: Alan Stern -M: Andrea Parri +M: Andrea Parri M: Will Deacon M: Peter Zijlstra M: Boqun Feng diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c index aab8ba40ce38..4b0bab2607e4 100644 --- a/arch/arm/kernel/smp.c +++ b/arch/arm/kernel/smp.c @@ -264,15 +264,13 @@ int __cpu_disable(void) return 0; } -static DECLARE_COMPLETION(cpu_died); - /* * called on the thread which is asking for a CPU to be shutdown - * waits until shutdown has completed, or it is timed out. */ void __cpu_die(unsigned int cpu) { - if (!wait_for_completion_timeout(&cpu_died, msecs_to_jiffies(5000))) { + if (!cpu_wait_death(cpu, 5)) { pr_err("CPU%u: cpu didn't die\n", cpu); return; } @@ -319,7 +317,7 @@ void arch_cpu_idle_dead(void) * this returns, power and/or clocks can be removed at any point * from this CPU and its cache by platform_cpu_kill(). */ - complete(&cpu_died); + (void)cpu_report_death(); /* * Ensure that the cache lines associated with that completion are diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h index bb7c8cc77f1a..04b2b927bb5a 100644 --- a/arch/powerpc/include/asm/kvm_book3s_64.h +++ b/arch/powerpc/include/asm/kvm_book3s_64.h @@ -535,7 +535,7 @@ static inline void note_hpte_modification(struct kvm *kvm, */ static inline struct kvm_memslots *kvm_memslots_raw(struct kvm *kvm) { - return rcu_dereference_raw_notrace(kvm->memslots[0]); + return rcu_dereference_raw_check(kvm->memslots[0]); } extern void kvmppc_mmu_debugfs_init(struct kvm *kvm); diff --git a/arch/x86/pci/mmconfig-shared.c b/arch/x86/pci/mmconfig-shared.c index 7389db538c30..6fa42e9c4e6f 100644 --- a/arch/x86/pci/mmconfig-shared.c +++ b/arch/x86/pci/mmconfig-shared.c @@ -29,6 +29,7 @@ static bool pci_mmcfg_running_state; static bool pci_mmcfg_arch_init_failed; static DEFINE_MUTEX(pci_mmcfg_lock); +#define pci_mmcfg_lock_held() lock_is_held(&(pci_mmcfg_lock).dep_map) LIST_HEAD(pci_mmcfg_list); @@ -54,7 +55,7 @@ static void list_add_sorted(struct pci_mmcfg_region *new) struct pci_mmcfg_region *cfg; /* keep list sorted by segment and starting bus number */ - list_for_each_entry_rcu(cfg, &pci_mmcfg_list, list) { + list_for_each_entry_rcu(cfg, &pci_mmcfg_list, list, pci_mmcfg_lock_held()) { if (cfg->segment > new->segment || (cfg->segment == new->segment && cfg->start_bus >= new->start_bus)) { @@ -118,7 +119,7 @@ struct pci_mmcfg_region *pci_mmconfig_lookup(int segment, int bus) { struct pci_mmcfg_region *cfg; - list_for_each_entry_rcu(cfg, &pci_mmcfg_list, list) + list_for_each_entry_rcu(cfg, &pci_mmcfg_list, list, pci_mmcfg_lock_held()) if (cfg->segment == segment && cfg->start_bus <= bus && bus <= cfg->end_bus) return cfg; diff --git a/drivers/acpi/osl.c b/drivers/acpi/osl.c index 9c0edf2fc0dd..2f9d0d20b836 100644 --- a/drivers/acpi/osl.c +++ b/drivers/acpi/osl.c @@ -14,6 +14,7 @@ #include #include #include +#include #include #include #include @@ -80,6 +81,7 @@ struct acpi_ioremap { static LIST_HEAD(acpi_ioremaps); static DEFINE_MUTEX(acpi_ioremap_lock); +#define acpi_ioremap_lock_held() lock_is_held(&acpi_ioremap_lock.dep_map) static void __init acpi_request_region (struct acpi_generic_address *gas, unsigned int length, char *desc) @@ -206,7 +208,7 @@ acpi_map_lookup(acpi_physical_address phys, acpi_size size) { struct acpi_ioremap *map; - list_for_each_entry_rcu(map, &acpi_ioremaps, list) + list_for_each_entry_rcu(map, &acpi_ioremaps, list, acpi_ioremap_lock_held()) if (map->phys <= phys && phys + size <= map->phys + map->size) return map; @@ -249,7 +251,7 @@ acpi_map_lookup_virt(void __iomem *virt, acpi_size size) { struct acpi_ioremap *map; - list_for_each_entry_rcu(map, &acpi_ioremaps, list) + list_for_each_entry_rcu(map, &acpi_ioremaps, list, acpi_ioremap_lock_held()) if (map->virt <= virt && virt + size <= map->virt + map->size) return map; diff --git a/drivers/base/base.h b/drivers/base/base.h index b405436ee28e..0d32544b6f91 100644 --- a/drivers/base/base.h +++ b/drivers/base/base.h @@ -165,6 +165,7 @@ static inline int devtmpfs_init(void) { return 0; } /* Device links support */ extern int device_links_read_lock(void); extern void device_links_read_unlock(int idx); +extern int device_links_read_lock_held(void); extern int device_links_check_suppliers(struct device *dev); extern void device_links_driver_bound(struct device *dev); extern void device_links_driver_cleanup(struct device *dev); diff --git a/drivers/base/core.c b/drivers/base/core.c index 636058bbf48a..eede79630ceb 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -68,6 +68,11 @@ void device_links_read_unlock(int idx) { srcu_read_unlock(&device_links_srcu, idx); } + +int device_links_read_lock_held(void) +{ + return srcu_read_lock_held(&device_links_srcu); +} #else /* !CONFIG_SRCU */ static DECLARE_RWSEM(device_links_lock); @@ -91,6 +96,13 @@ void device_links_read_unlock(int not_used) { up_read(&device_links_lock); } + +#ifdef CONFIG_DEBUG_LOCK_ALLOC +int device_links_read_lock_held(void) +{ + return lockdep_is_held(&device_links_lock); +} +#endif #endif /* !CONFIG_SRCU */ /** diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c index b75335508d2c..50def99df970 100644 --- a/drivers/base/power/runtime.c +++ b/drivers/base/power/runtime.c @@ -287,7 +287,8 @@ static int rpm_get_suppliers(struct device *dev) { struct device_link *link; - list_for_each_entry_rcu(link, &dev->links.suppliers, c_node) { + list_for_each_entry_rcu(link, &dev->links.suppliers, c_node, + device_links_read_lock_held()) { int retval; if (!(link->flags & DL_FLAG_PM_RUNTIME) || @@ -309,7 +310,8 @@ static void rpm_put_suppliers(struct device *dev) { struct device_link *link; - list_for_each_entry_rcu(link, &dev->links.suppliers, c_node) { + list_for_each_entry_rcu(link, &dev->links.suppliers, c_node, + device_links_read_lock_held()) { if (READ_ONCE(link->status) == DL_STATE_SUPPLIER_UNBIND) continue; @@ -1640,7 +1642,8 @@ void pm_runtime_clean_up_links(struct device *dev) idx = device_links_read_lock(); - list_for_each_entry_rcu(link, &dev->links.consumers, s_node) { + list_for_each_entry_rcu(link, &dev->links.consumers, s_node, + device_links_read_lock_held()) { if (link->flags & DL_FLAG_STATELESS) continue; @@ -1662,7 +1665,8 @@ void pm_runtime_get_suppliers(struct device *dev) idx = device_links_read_lock(); - list_for_each_entry_rcu(link, &dev->links.suppliers, c_node) + list_for_each_entry_rcu(link, &dev->links.suppliers, c_node, + device_links_read_lock_held()) if (link->flags & DL_FLAG_PM_RUNTIME) { link->supplier_preactivated = true; refcount_inc(&link->rpm_active); @@ -1683,7 +1687,8 @@ void pm_runtime_put_suppliers(struct device *dev) idx = device_links_read_lock(); - list_for_each_entry_rcu(link, &dev->links.suppliers, c_node) + list_for_each_entry_rcu(link, &dev->links.suppliers, c_node, + device_links_read_lock_held()) if (link->supplier_preactivated) { link->supplier_preactivated = false; if (refcount_dec_not_one(&link->rpm_active)) diff --git a/include/linux/rcu_sync.h b/include/linux/rcu_sync.h index 9b83865d24f9..0027d4c8087c 100644 --- a/include/linux/rcu_sync.h +++ b/include/linux/rcu_sync.h @@ -31,9 +31,7 @@ struct rcu_sync { */ static inline bool rcu_sync_is_idle(struct rcu_sync *rsp) { - RCU_LOCKDEP_WARN(!rcu_read_lock_held() && - !rcu_read_lock_bh_held() && - !rcu_read_lock_sched_held(), + RCU_LOCKDEP_WARN(!rcu_read_lock_any_held(), "suspicious rcu_sync_is_idle() usage"); return !READ_ONCE(rsp->gp_state); /* GP_IDLE */ } diff --git a/include/linux/rculist.h b/include/linux/rculist.h index e91ec9ddcd30..4158b7212936 100644 --- a/include/linux/rculist.h +++ b/include/linux/rculist.h @@ -40,6 +40,24 @@ static inline void INIT_LIST_HEAD_RCU(struct list_head *list) */ #define list_next_rcu(list) (*((struct list_head __rcu **)(&(list)->next))) +/* + * Check during list traversal that we are within an RCU reader + */ + +#define check_arg_count_one(dummy) + +#ifdef CONFIG_PROVE_RCU_LIST +#define __list_check_rcu(dummy, cond, extra...) \ + ({ \ + check_arg_count_one(extra); \ + RCU_LOCKDEP_WARN(!cond && !rcu_read_lock_any_held(), \ + "RCU-list traversed in non-reader section!"); \ + }) +#else +#define __list_check_rcu(dummy, cond, extra...) \ + ({ check_arg_count_one(extra); }) +#endif + /* * Insert a new entry between two known consecutive entries. * @@ -343,14 +361,16 @@ 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. * * This list-traversal primitive may safely run concurrently with * the _rcu list-mutation primitives such as list_add_rcu() * as long as the traversal is guarded by rcu_read_lock(). */ -#define list_for_each_entry_rcu(pos, head, member) \ - for (pos = list_entry_rcu((head)->next, typeof(*pos), member); \ - &pos->member != (head); \ +#define list_for_each_entry_rcu(pos, head, member, cond...) \ + for (__list_check_rcu(dummy, ## cond, 0), \ + pos = list_entry_rcu((head)->next, typeof(*pos), member); \ + &pos->member != (head); \ pos = list_entry_rcu(pos->member.next, typeof(*pos), member)) /** @@ -616,13 +636,15 @@ 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. * * This list-traversal primitive may safely run concurrently with * the _rcu list-mutation primitives such as hlist_add_head_rcu() * as long as the traversal is guarded by rcu_read_lock(). */ -#define hlist_for_each_entry_rcu(pos, head, member) \ - for (pos = hlist_entry_safe (rcu_dereference_raw(hlist_first_rcu(head)),\ +#define hlist_for_each_entry_rcu(pos, head, member, cond...) \ + for (__list_check_rcu(dummy, ## cond, 0), \ + pos = hlist_entry_safe(rcu_dereference_raw(hlist_first_rcu(head)),\ typeof(*(pos)), member); \ pos; \ pos = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu(\ @@ -642,10 +664,10 @@ static inline void hlist_add_behind_rcu(struct hlist_node *n, * not do any RCU debugging or tracing. */ #define hlist_for_each_entry_rcu_notrace(pos, head, member) \ - for (pos = hlist_entry_safe (rcu_dereference_raw_notrace(hlist_first_rcu(head)),\ + for (pos = hlist_entry_safe(rcu_dereference_raw_check(hlist_first_rcu(head)),\ typeof(*(pos)), member); \ pos; \ - pos = hlist_entry_safe(rcu_dereference_raw_notrace(hlist_next_rcu(\ + pos = hlist_entry_safe(rcu_dereference_raw_check(hlist_next_rcu(\ &(pos)->member)), typeof(*(pos)), member)) /** diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 8f7167478c1d..80d6056f5855 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -221,6 +221,7 @@ int debug_lockdep_rcu_enabled(void); int rcu_read_lock_held(void); int rcu_read_lock_bh_held(void); int rcu_read_lock_sched_held(void); +int rcu_read_lock_any_held(void); #else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ @@ -241,6 +242,12 @@ static inline int rcu_read_lock_sched_held(void) { return !preemptible(); } + +static inline int rcu_read_lock_any_held(void) +{ + return !preemptible(); +} + #endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */ #ifdef CONFIG_PROVE_RCU @@ -476,7 +483,7 @@ do { \ * The no-tracing version of rcu_dereference_raw() must not call * rcu_read_lock_held(). */ -#define rcu_dereference_raw_notrace(p) __rcu_dereference_check((p), 1, __rcu) +#define rcu_dereference_raw_check(p) __rcu_dereference_check((p), 1, __rcu) /** * rcu_dereference_protected() - fetch RCU pointer when updates prevented diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index 4861cf8e274b..4aca3f4379d2 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -620,7 +620,7 @@ static void print_lock(struct held_lock *hlock) return; } - printk(KERN_CONT "%p", hlock->instance); + printk(KERN_CONT "%px", hlock->instance); print_lock_name(lock); printk(KERN_CONT ", at: %pS\n", (void *)hlock->acquire_ip); } diff --git a/kernel/rcu/Kconfig.debug b/kernel/rcu/Kconfig.debug index 5ec3ea4028e2..4aa02eee8f6c 100644 --- a/kernel/rcu/Kconfig.debug +++ b/kernel/rcu/Kconfig.debug @@ -8,6 +8,17 @@ menu "RCU Debugging" config PROVE_RCU def_bool PROVE_LOCKING +config PROVE_RCU_LIST + bool "RCU list lockdep debugging" + depends on PROVE_RCU && RCU_EXPERT + default n + help + Enable RCU lockdep checking for list usages. By default it is + turned off since there are several list RCU users that still + need to be converted to pass a lockdep expression. To prevent + false-positive splats, we keep it default disabled but once all + users are converted, we can remove this config option. + config TORTURE_TEST tristate default n diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h index 5290b01de534..8fd4f82c9b3d 100644 --- a/kernel/rcu/rcu.h +++ b/kernel/rcu/rcu.h @@ -227,6 +227,7 @@ static inline bool __rcu_reclaim(const char *rn, struct rcu_head *head) #ifdef CONFIG_RCU_STALL_COMMON +extern int rcu_cpu_stall_ftrace_dump; extern int rcu_cpu_stall_suppress; extern int rcu_cpu_stall_timeout; int rcu_jiffies_till_stall_check(void); diff --git a/kernel/rcu/rcu_segcblist.h b/kernel/rcu/rcu_segcblist.h index 71b64648464e..822a39da0533 100644 --- a/kernel/rcu/rcu_segcblist.h +++ b/kernel/rcu/rcu_segcblist.h @@ -76,27 +76,6 @@ static inline bool rcu_segcblist_restempty(struct rcu_segcblist *rsclp, int seg) return !*rsclp->tails[seg]; } -/* - * Interim function to return rcu_segcblist head pointer. Longer term, the - * rcu_segcblist will be used more pervasively, removing the need for this - * function. - */ -static inline struct rcu_head *rcu_segcblist_head(struct rcu_segcblist *rsclp) -{ - return rsclp->head; -} - -/* - * Interim function to return rcu_segcblist head pointer. Longer term, the - * rcu_segcblist will be used more pervasively, removing the need for this - * function. - */ -static inline struct rcu_head **rcu_segcblist_tail(struct rcu_segcblist *rsclp) -{ - WARN_ON_ONCE(rcu_segcblist_empty(rsclp)); - return rsclp->tails[RCU_NEXT_TAIL]; -} - void rcu_segcblist_init(struct rcu_segcblist *rsclp); void rcu_segcblist_disable(struct rcu_segcblist *rsclp); bool rcu_segcblist_ready_cbs(struct rcu_segcblist *rsclp); diff --git a/kernel/rcu/rcuperf.c b/kernel/rcu/rcuperf.c index 7a6890b23c5f..5a879d073c1c 100644 --- a/kernel/rcu/rcuperf.c +++ b/kernel/rcu/rcuperf.c @@ -89,7 +89,7 @@ torture_param(int, writer_holdoff, 0, "Holdoff (us) between GPs, zero to disable static char *perf_type = "rcu"; module_param(perf_type, charp, 0444); -MODULE_PARM_DESC(perf_type, "Type of RCU to performance-test (rcu, rcu_bh, ...)"); +MODULE_PARM_DESC(perf_type, "Type of RCU to performance-test (rcu, srcu, ...)"); static int nrealreaders; static int nrealwriters; @@ -375,6 +375,14 @@ rcu_perf_writer(void *arg) if (holdoff) schedule_timeout_uninterruptible(holdoff * HZ); + /* + * Wait until rcu_end_inkernel_boot() is called for normal GP tests + * so that RCU is not always expedited for normal GP tests. + * The system_state test is approximate, but works well in practice. + */ + while (!gp_exp && system_state != SYSTEM_RUNNING) + schedule_timeout_uninterruptible(1); + t = ktime_get_mono_fast_ns(); if (atomic_inc_return(&n_rcu_perf_writer_started) >= nrealwriters) { t_rcu_perf_writer_started = t; diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c index fce4e7e6f502..b22947324423 100644 --- a/kernel/rcu/rcutorture.c +++ b/kernel/rcu/rcutorture.c @@ -161,6 +161,7 @@ static atomic_long_t n_rcu_torture_timers; static long n_barrier_attempts; static long n_barrier_successes; /* did rcu_barrier test succeed? */ static struct list_head rcu_torture_removed; +static unsigned long shutdown_jiffies; static int rcu_torture_writer_state; #define RTWS_FIXED_DELAY 0 @@ -228,6 +229,15 @@ static u64 notrace rcu_trace_clock_local(void) } #endif /* #else #ifdef CONFIG_RCU_TRACE */ +/* + * Stop aggressive CPU-hog tests a bit before the end of the test in order + * to avoid interfering with test shutdown. + */ +static bool shutdown_time_arrived(void) +{ + return shutdown_secs && time_after(jiffies, shutdown_jiffies - 30 * HZ); +} + static unsigned long boost_starttime; /* jiffies of next boost test start. */ static DEFINE_MUTEX(boost_mutex); /* protect setting boost_starttime */ /* and boost task create/destroy. */ @@ -1713,12 +1723,14 @@ static void rcu_torture_fwd_cb_cr(struct rcu_head *rhp) } // Give the scheduler a chance, even on nohz_full CPUs. -static void rcu_torture_fwd_prog_cond_resched(void) +static void rcu_torture_fwd_prog_cond_resched(unsigned long iter) { if (IS_ENABLED(CONFIG_PREEMPT) && IS_ENABLED(CONFIG_NO_HZ_FULL)) { - if (need_resched()) + // Real call_rcu() floods hit userspace, so emulate that. + if (need_resched() || (iter & 0xfff)) schedule(); } else { + // No userspace emulation: CB invocation throttles call_rcu() cond_resched(); } } @@ -1746,7 +1758,7 @@ static unsigned long rcu_torture_fwd_prog_cbfree(void) spin_unlock_irqrestore(&rcu_fwd_lock, flags); kfree(rfcp); freed++; - rcu_torture_fwd_prog_cond_resched(); + rcu_torture_fwd_prog_cond_resched(freed); } return freed; } @@ -1785,15 +1797,17 @@ static void rcu_torture_fwd_prog_nr(int *tested, int *tested_tries) WRITE_ONCE(rcu_fwd_startat, jiffies); stopat = rcu_fwd_startat + dur; while (time_before(jiffies, stopat) && + !shutdown_time_arrived() && !READ_ONCE(rcu_fwd_emergency_stop) && !torture_must_stop()) { idx = cur_ops->readlock(); udelay(10); cur_ops->readunlock(idx); if (!fwd_progress_need_resched || need_resched()) - rcu_torture_fwd_prog_cond_resched(); + rcu_torture_fwd_prog_cond_resched(1); } (*tested_tries)++; if (!time_before(jiffies, stopat) && + !shutdown_time_arrived() && !READ_ONCE(rcu_fwd_emergency_stop) && !torture_must_stop()) { (*tested)++; cver = READ_ONCE(rcu_torture_current_version) - cver; @@ -1852,6 +1866,7 @@ static void rcu_torture_fwd_prog_cr(void) gps = cur_ops->get_gp_seq(); rcu_launder_gp_seq_start = gps; while (time_before(jiffies, stopat) && + !shutdown_time_arrived() && !READ_ONCE(rcu_fwd_emergency_stop) && !torture_must_stop()) { rfcp = READ_ONCE(rcu_fwd_cb_head); rfcpn = NULL; @@ -1875,7 +1890,7 @@ static void rcu_torture_fwd_prog_cr(void) rfcp->rfc_gps = 0; } cur_ops->call(&rfcp->rh, rcu_torture_fwd_cb_cr); - rcu_torture_fwd_prog_cond_resched(); + rcu_torture_fwd_prog_cond_resched(n_launders + n_max_cbs); } stoppedat = jiffies; n_launders_cb_snap = READ_ONCE(n_launders_cb); @@ -1884,7 +1899,8 @@ static void rcu_torture_fwd_prog_cr(void) cur_ops->cb_barrier(); /* Wait for callbacks to be invoked. */ (void)rcu_torture_fwd_prog_cbfree(); - if (!torture_must_stop() && !READ_ONCE(rcu_fwd_emergency_stop)) { + if (!torture_must_stop() && !READ_ONCE(rcu_fwd_emergency_stop) && + !shutdown_time_arrived()) { WARN_ON(n_max_gps < MIN_FWD_CBS_LAUNDERED); pr_alert("%s Duration %lu barrier: %lu pending %ld n_launders: %ld n_launders_sa: %ld n_max_gps: %ld n_max_cbs: %ld cver %ld gps %ld\n", __func__, @@ -2465,6 +2481,7 @@ rcu_torture_init(void) goto unwind; rcutor_hp = firsterr; } + shutdown_jiffies = jiffies + shutdown_secs * HZ; firsterr = torture_shutdown_init(shutdown_secs, rcu_torture_cleanup); if (firsterr) goto unwind; diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c index cf0e886314f2..5dffade2d7cd 100644 --- a/kernel/rcu/srcutree.c +++ b/kernel/rcu/srcutree.c @@ -1279,8 +1279,9 @@ void srcu_torture_stats_print(struct srcu_struct *ssp, char *tt, char *tf) c0 = l0 - u0; c1 = l1 - u1; - pr_cont(" %d(%ld,%ld %1p)", - cpu, c0, c1, rcu_segcblist_head(&sdp->srcu_cblist)); + pr_cont(" %d(%ld,%ld %c)", + cpu, c0, c1, + "C."[rcu_segcblist_empty(&sdp->srcu_cblist)]); s0 += c0; s1 += c1; } diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h index af7e7b9c86af..d632cd019597 100644 --- a/kernel/rcu/tree_exp.h +++ b/kernel/rcu/tree_exp.h @@ -781,7 +781,7 @@ static int rcu_print_task_exp_stall(struct rcu_node *rnp) * other hand, if the CPU is not in an RCU read-side critical section, * the IPI handler reports the quiescent state immediately. * - * Although this is a greate improvement over previous expedited + * Although this is a great improvement over previous expedited * implementations, it is still unfriendly to real-time workloads, so is * thus not recommended for any sort of common-case code. In fact, if * you are using synchronize_rcu_expedited() in a loop, please restructure @@ -792,6 +792,7 @@ static int rcu_print_task_exp_stall(struct rcu_node *rnp) */ void synchronize_rcu_expedited(void) { + bool boottime = (rcu_scheduler_active == RCU_SCHEDULER_INIT); struct rcu_exp_work rew; struct rcu_node *rnp; unsigned long s; @@ -817,7 +818,7 @@ void synchronize_rcu_expedited(void) return; /* Someone else did our work for us. */ /* Ensure that load happens before action based on it. */ - if (unlikely(rcu_scheduler_active == RCU_SCHEDULER_INIT)) { + if (unlikely(boottime)) { /* Direct call during scheduler init and early_initcalls(). */ rcu_exp_sel_wait_wake(s); } else { @@ -835,5 +836,8 @@ void synchronize_rcu_expedited(void) /* Let the next expedited grace period start. */ mutex_unlock(&rcu_state.exp_mutex); + + if (likely(!boottime)) + destroy_work_on_stack(&rew.rew_work); } EXPORT_SYMBOL_GPL(synchronize_rcu_expedited); diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index ce6ef345102b..99e9d952827b 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -288,7 +288,6 @@ void rcu_note_context_switch(bool preempt) struct rcu_data *rdp = this_cpu_ptr(&rcu_data); struct rcu_node *rnp; - barrier(); /* Avoid RCU read-side critical sections leaking down. */ trace_rcu_utilization(TPS("Start context switch")); lockdep_assert_irqs_disabled(); WARN_ON_ONCE(!preempt && t->rcu_read_lock_nesting > 0); @@ -331,7 +330,6 @@ void rcu_note_context_switch(bool preempt) if (rdp->exp_deferred_qs) rcu_report_exp_rdp(rdp); trace_rcu_utilization(TPS("End context switch")); - barrier(); /* Avoid RCU read-side critical sections leaking up. */ } EXPORT_SYMBOL_GPL(rcu_note_context_switch); @@ -815,11 +813,6 @@ static void rcu_qs(void) * dyntick-idle quiescent state visible to other CPUs, which will in * some cases serve for expedited as well as normal grace periods. * Either way, register a lightweight quiescent state. - * - * The barrier() calls are redundant in the common case when this is - * called externally, but just in case this is called from within this - * file. - * */ void rcu_all_qs(void) { @@ -834,14 +827,12 @@ void rcu_all_qs(void) return; } this_cpu_write(rcu_data.rcu_urgent_qs, false); - barrier(); /* Avoid RCU read-side critical sections leaking down. */ if (unlikely(raw_cpu_read(rcu_data.rcu_need_heavy_qs))) { local_irq_save(flags); rcu_momentary_dyntick_idle(); local_irq_restore(flags); } rcu_qs(); - barrier(); /* Avoid RCU read-side critical sections leaking up. */ preempt_enable(); } EXPORT_SYMBOL_GPL(rcu_all_qs); @@ -851,7 +842,6 @@ EXPORT_SYMBOL_GPL(rcu_all_qs); */ void rcu_note_context_switch(bool preempt) { - barrier(); /* Avoid RCU read-side critical sections leaking down. */ trace_rcu_utilization(TPS("Start context switch")); rcu_qs(); /* Load rcu_urgent_qs before other flags. */ @@ -864,7 +854,6 @@ void rcu_note_context_switch(bool preempt) rcu_tasks_qs(current); out: trace_rcu_utilization(TPS("End context switch")); - barrier(); /* Avoid RCU read-side critical sections leaking up. */ } EXPORT_SYMBOL_GPL(rcu_note_context_switch); @@ -1121,7 +1110,7 @@ static void rcu_preempt_boost_start_gp(struct rcu_node *rnp) * already exist. We only create this kthread for preemptible RCU. * Returns zero if all is well, a negated errno otherwise. */ -static int rcu_spawn_one_boost_kthread(struct rcu_node *rnp) +static void rcu_spawn_one_boost_kthread(struct rcu_node *rnp) { int rnp_index = rnp - rcu_get_root(); unsigned long flags; @@ -1129,25 +1118,27 @@ static int rcu_spawn_one_boost_kthread(struct rcu_node *rnp) struct task_struct *t; if (!IS_ENABLED(CONFIG_PREEMPT_RCU)) - return 0; + return; if (!rcu_scheduler_fully_active || rcu_rnp_online_cpus(rnp) == 0) - return 0; + return; rcu_state.boost = 1; + if (rnp->boost_kthread_task != NULL) - return 0; + return; + t = kthread_create(rcu_boost_kthread, (void *)rnp, "rcub/%d", rnp_index); - if (IS_ERR(t)) - return PTR_ERR(t); + if (WARN_ON_ONCE(IS_ERR(t))) + return; + raw_spin_lock_irqsave_rcu_node(rnp, flags); rnp->boost_kthread_task = t; raw_spin_unlock_irqrestore_rcu_node(rnp, flags); sp.sched_priority = kthread_prio; sched_setscheduler_nocheck(t, SCHED_FIFO, &sp); wake_up_process(t); /* get to TASK_INTERRUPTIBLE quickly. */ - return 0; } /* @@ -1188,7 +1179,7 @@ static void __init rcu_spawn_boost_kthreads(void) struct rcu_node *rnp; rcu_for_each_leaf_node(rnp) - (void)rcu_spawn_one_boost_kthread(rnp); + rcu_spawn_one_boost_kthread(rnp); } static void rcu_prepare_kthreads(int cpu) @@ -1198,7 +1189,7 @@ static void rcu_prepare_kthreads(int cpu) /* Fire up the incoming CPU's kthread and leaf rcu_node kthread. */ if (rcu_scheduler_fully_active) - (void)rcu_spawn_one_boost_kthread(rnp); + rcu_spawn_one_boost_kthread(rnp); } #else /* #ifdef CONFIG_RCU_BOOST */ diff --git a/kernel/rcu/tree_stall.h b/kernel/rcu/tree_stall.h index 065183391f75..0627a66699a6 100644 --- a/kernel/rcu/tree_stall.h +++ b/kernel/rcu/tree_stall.h @@ -527,6 +527,8 @@ static void check_cpu_stall(struct rcu_data *rdp) /* We haven't checked in, so go dump stack. */ print_cpu_stall(); + if (rcu_cpu_stall_ftrace_dump) + rcu_ftrace_dump(DUMP_ALL); } else if (rcu_gp_in_progress() && ULONG_CMP_GE(j, js + RCU_STALL_RAT_DELAY) && @@ -534,6 +536,8 @@ static void check_cpu_stall(struct rcu_data *rdp) /* They had a few time units to dump stack, so complain. */ print_other_cpu_stall(gs2); + if (rcu_cpu_stall_ftrace_dump) + rcu_ftrace_dump(DUMP_ALL); } } diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c index 61df2bf08563..1861103662db 100644 --- a/kernel/rcu/update.c +++ b/kernel/rcu/update.c @@ -61,9 +61,15 @@ module_param(rcu_normal_after_boot, int, 0); #ifdef CONFIG_DEBUG_LOCK_ALLOC /** - * rcu_read_lock_sched_held() - might we be in RCU-sched read-side critical section? + * rcu_read_lock_held_common() - might we be in RCU-sched read-side critical section? + * @ret: Best guess answer if lockdep cannot be relied on * - * If CONFIG_DEBUG_LOCK_ALLOC is selected, returns nonzero iff in an + * Returns true if lockdep must be ignored, in which case *ret contains + * the best guess described below. Otherwise returns false, in which + * case *ret tells the caller nothing and the caller should instead + * consult lockdep. + * + * If CONFIG_DEBUG_LOCK_ALLOC is selected, set *ret to nonzero iff in an * RCU-sched read-side critical section. In absence of * CONFIG_DEBUG_LOCK_ALLOC, this assumes we are in an RCU-sched read-side * critical section unless it can prove otherwise. Note that disabling @@ -75,35 +81,45 @@ module_param(rcu_normal_after_boot, int, 0); * Check debug_lockdep_rcu_enabled() to prevent false positives during boot * and while lockdep is disabled. * - * Note that if the CPU is in the idle loop from an RCU point of - * view (ie: that we are in the section between rcu_idle_enter() and - * rcu_idle_exit()) then rcu_read_lock_held() returns false even if the CPU - * did an rcu_read_lock(). The reason for this is that RCU ignores CPUs - * that are in such a section, considering these as in extended quiescent - * state, so such a CPU is effectively never in an RCU read-side critical - * section regardless of what RCU primitives it invokes. This state of - * affairs is required --- we need to keep an RCU-free window in idle - * where the CPU may possibly enter into low power mode. This way we can - * notice an extended quiescent state to other CPUs that started a grace - * period. Otherwise we would delay any grace period as long as we run in - * the idle task. + * Note that if the CPU is in the idle loop from an RCU point of view (ie: + * that we are in the section between rcu_idle_enter() and rcu_idle_exit()) + * then rcu_read_lock_held() sets *ret to false even if the CPU did an + * rcu_read_lock(). The reason for this is that RCU ignores CPUs that are + * in such a section, considering these as in extended quiescent state, + * so such a CPU is effectively never in an RCU read-side critical section + * regardless of what RCU primitives it invokes. This state of affairs is + * required --- we need to keep an RCU-free window in idle where the CPU may + * possibly enter into low power mode. This way we can notice an extended + * quiescent state to other CPUs that started a grace period. Otherwise + * we would delay any grace period as long as we run in the idle task. * - * Similarly, we avoid claiming an SRCU read lock held if the current + * Similarly, we avoid claiming an RCU read lock held if the current * CPU is offline. */ +static bool rcu_read_lock_held_common(bool *ret) +{ + if (!debug_lockdep_rcu_enabled()) { + *ret = 1; + return true; + } + if (!rcu_is_watching()) { + *ret = 0; + return true; + } + if (!rcu_lockdep_current_cpu_online()) { + *ret = 0; + return true; + } + return false; +} + int rcu_read_lock_sched_held(void) { - int lockdep_opinion = 0; + bool ret; - if (!debug_lockdep_rcu_enabled()) - return 1; - if (!rcu_is_watching()) - return 0; - if (!rcu_lockdep_current_cpu_online()) - return 0; - if (debug_locks) - lockdep_opinion = lock_is_held(&rcu_sched_lock_map); - return lockdep_opinion || !preemptible(); + if (rcu_read_lock_held_common(&ret)) + return ret; + return lock_is_held(&rcu_sched_lock_map) || !preemptible(); } EXPORT_SYMBOL(rcu_read_lock_sched_held); #endif @@ -136,8 +152,7 @@ static atomic_t rcu_expedited_nesting = ATOMIC_INIT(1); */ bool rcu_gp_is_expedited(void) { - return rcu_expedited || atomic_read(&rcu_expedited_nesting) || - rcu_scheduler_active == RCU_SCHEDULER_INIT; + return rcu_expedited || atomic_read(&rcu_expedited_nesting); } EXPORT_SYMBOL_GPL(rcu_gp_is_expedited); @@ -261,12 +276,10 @@ NOKPROBE_SYMBOL(debug_lockdep_rcu_enabled); */ int rcu_read_lock_held(void) { - if (!debug_lockdep_rcu_enabled()) - return 1; - if (!rcu_is_watching()) - return 0; - if (!rcu_lockdep_current_cpu_online()) - return 0; + bool ret; + + if (rcu_read_lock_held_common(&ret)) + return ret; return lock_is_held(&rcu_lock_map); } EXPORT_SYMBOL_GPL(rcu_read_lock_held); @@ -288,16 +301,28 @@ EXPORT_SYMBOL_GPL(rcu_read_lock_held); */ int rcu_read_lock_bh_held(void) { - if (!debug_lockdep_rcu_enabled()) - return 1; - if (!rcu_is_watching()) - return 0; - if (!rcu_lockdep_current_cpu_online()) - return 0; + bool ret; + + if (rcu_read_lock_held_common(&ret)) + return ret; return in_softirq() || irqs_disabled(); } EXPORT_SYMBOL_GPL(rcu_read_lock_bh_held); +int rcu_read_lock_any_held(void) +{ + bool ret; + + if (rcu_read_lock_held_common(&ret)) + return ret; + if (lock_is_held(&rcu_lock_map) || + lock_is_held(&rcu_bh_lock_map) || + lock_is_held(&rcu_sched_lock_map)) + return 1; + return !preemptible(); +} +EXPORT_SYMBOL_GPL(rcu_read_lock_any_held); + #endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ /** @@ -437,6 +462,8 @@ EXPORT_SYMBOL_GPL(rcutorture_sched_setaffinity); #endif #ifdef CONFIG_RCU_STALL_COMMON +int rcu_cpu_stall_ftrace_dump __read_mostly; +module_param(rcu_cpu_stall_ftrace_dump, int, 0644); int rcu_cpu_stall_suppress __read_mostly; /* 1 = suppress stall warnings. */ EXPORT_SYMBOL_GPL(rcu_cpu_stall_suppress); module_param(rcu_cpu_stall_suppress, int, 0644); diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 2b037f195473..0b22e55cebe8 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -3486,8 +3486,36 @@ void scheduler_tick(void) struct tick_work { int cpu; + atomic_t state; struct delayed_work work; }; +/* Values for ->state, see diagram below. */ +#define TICK_SCHED_REMOTE_OFFLINE 0 +#define TICK_SCHED_REMOTE_OFFLINING 1 +#define TICK_SCHED_REMOTE_RUNNING 2 + +/* + * State diagram for ->state: + * + * + * TICK_SCHED_REMOTE_OFFLINE + * | ^ + * | | + * | | sched_tick_remote() + * | | + * | | + * +--TICK_SCHED_REMOTE_OFFLINING + * | ^ + * | | + * sched_tick_start() | | sched_tick_stop() + * | | + * V | + * TICK_SCHED_REMOTE_RUNNING + * + * + * Other transitions get WARN_ON_ONCE(), except that sched_tick_remote() + * and sched_tick_start() are happy to leave the state in RUNNING. + */ static struct tick_work __percpu *tick_work_cpu; @@ -3500,6 +3528,7 @@ static void sched_tick_remote(struct work_struct *work) struct task_struct *curr; struct rq_flags rf; u64 delta; + int os; /* * Handle the tick only if it appears the remote CPU is running in full @@ -3513,7 +3542,7 @@ static void sched_tick_remote(struct work_struct *work) rq_lock_irq(rq, &rf); curr = rq->curr; - if (is_idle_task(curr)) + if (is_idle_task(curr) || cpu_is_offline(cpu)) goto out_unlock; update_rq_clock(rq); @@ -3533,13 +3562,18 @@ out_requeue: /* * Run the remote tick once per second (1Hz). This arbitrary * frequency is large enough to avoid overload but short enough - * to keep scheduler internal stats reasonably up to date. + * to keep scheduler internal stats reasonably up to date. But + * first update state to reflect hotplug activity if required. */ - queue_delayed_work(system_unbound_wq, dwork, HZ); + os = atomic_fetch_add_unless(&twork->state, -1, TICK_SCHED_REMOTE_RUNNING); + WARN_ON_ONCE(os == TICK_SCHED_REMOTE_OFFLINE); + if (os == TICK_SCHED_REMOTE_RUNNING) + queue_delayed_work(system_unbound_wq, dwork, HZ); } static void sched_tick_start(int cpu) { + int os; struct tick_work *twork; if (housekeeping_cpu(cpu, HK_FLAG_TICK)) @@ -3548,15 +3582,20 @@ static void sched_tick_start(int cpu) WARN_ON_ONCE(!tick_work_cpu); twork = per_cpu_ptr(tick_work_cpu, cpu); - twork->cpu = cpu; - INIT_DELAYED_WORK(&twork->work, sched_tick_remote); - queue_delayed_work(system_unbound_wq, &twork->work, HZ); + os = atomic_xchg(&twork->state, TICK_SCHED_REMOTE_RUNNING); + WARN_ON_ONCE(os == TICK_SCHED_REMOTE_RUNNING); + if (os == TICK_SCHED_REMOTE_OFFLINE) { + twork->cpu = cpu; + INIT_DELAYED_WORK(&twork->work, sched_tick_remote); + queue_delayed_work(system_unbound_wq, &twork->work, HZ); + } } #ifdef CONFIG_HOTPLUG_CPU static void sched_tick_stop(int cpu) { struct tick_work *twork; + int os; if (housekeeping_cpu(cpu, HK_FLAG_TICK)) return; @@ -3564,7 +3603,10 @@ static void sched_tick_stop(int cpu) WARN_ON_ONCE(!tick_work_cpu); twork = per_cpu_ptr(tick_work_cpu, cpu); - cancel_delayed_work_sync(&twork->work); + /* There cannot be competing actions, but don't rely on stop-machine. */ + os = atomic_xchg(&twork->state, TICK_SCHED_REMOTE_OFFLINING); + WARN_ON_ONCE(os != TICK_SCHED_REMOTE_RUNNING); + /* Don't cancel, as this would mess up the state machine. */ } #endif /* CONFIG_HOTPLUG_CPU */ @@ -3572,7 +3614,6 @@ int __init sched_tick_offload_init(void) { tick_work_cpu = alloc_percpu(struct tick_work); BUG_ON(!tick_work_cpu); - return 0; } diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index 80940939b733..e4bc4aa739b8 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -241,13 +241,14 @@ static void do_idle(void) check_pgt_cache(); rmb(); + local_irq_disable(); + if (cpu_is_offline(cpu)) { - tick_nohz_idle_stop_tick_protected(); + tick_nohz_idle_stop_tick(); cpuhp_report_idle_dead(); arch_cpu_idle_dead(); } - local_irq_disable(); arch_cpu_idle_enter(); /* diff --git a/kernel/torture.c b/kernel/torture.c index a8d9bdfba7c3..7c13f5558b71 100644 --- a/kernel/torture.c +++ b/kernel/torture.c @@ -263,7 +263,6 @@ static void torture_onoff_cleanup(void) onoff_task = NULL; #endif /* #ifdef CONFIG_HOTPLUG_CPU */ } -EXPORT_SYMBOL_GPL(torture_onoff_cleanup); /* * Print online/offline testing statistics. @@ -449,7 +448,6 @@ static void torture_shuffle_cleanup(void) } shuffler_task = NULL; } -EXPORT_SYMBOL_GPL(torture_shuffle_cleanup); /* * Variables for auto-shutdown. This allows "lights out" torture runs diff --git a/kernel/trace/ftrace_internal.h b/kernel/trace/ftrace_internal.h index 0515a2096f90..0456e0a3dab1 100644 --- a/kernel/trace/ftrace_internal.h +++ b/kernel/trace/ftrace_internal.h @@ -6,22 +6,22 @@ /* * Traverse the ftrace_global_list, invoking all entries. The reason that we - * can use rcu_dereference_raw_notrace() is that elements removed from this list + * can use rcu_dereference_raw_check() is that elements removed from this list * are simply leaked, so there is no need to interact with a grace-period - * mechanism. The rcu_dereference_raw_notrace() calls are needed to handle + * mechanism. The rcu_dereference_raw_check() calls are needed to handle * concurrent insertions into the ftrace_global_list. * * Silly Alpha and silly pointer-speculation compiler optimizations! */ #define do_for_each_ftrace_op(op, list) \ - op = rcu_dereference_raw_notrace(list); \ + op = rcu_dereference_raw_check(list); \ do /* * Optimized for just a single item in the list (as that is the normal case). */ #define while_for_each_ftrace_op(op) \ - while (likely(op = rcu_dereference_raw_notrace((op)->next)) && \ + while (likely(op = rcu_dereference_raw_check((op)->next)) && \ unlikely((op) != &ftrace_list_end)) extern struct ftrace_ops __rcu *ftrace_ops_list; diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 525a97fbbc60..642474b26ba7 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -2642,10 +2642,10 @@ static void ftrace_exports(struct ring_buffer_event *event) preempt_disable_notrace(); - export = rcu_dereference_raw_notrace(ftrace_exports_list); + export = rcu_dereference_raw_check(ftrace_exports_list); while (export) { trace_process_export(export, event); - export = rcu_dereference_raw_notrace(export->next); + export = rcu_dereference_raw_check(export->next); } preempt_enable_notrace(); diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index e8bc939b56dd..dde77f72e03e 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -124,7 +124,8 @@ struct fib_table *fib_get_table(struct net *net, u32 id) h = id & (FIB_TABLE_HASHSZ - 1); head = &net->ipv4.fib_table_hash[h]; - hlist_for_each_entry_rcu(tb, head, tb_hlist) { + hlist_for_each_entry_rcu(tb, head, tb_hlist, + lockdep_rtnl_is_held()) { if (tb->tb_id == id) return tb; } diff --git a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh index 27b7b5693ede..33c669619736 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh @@ -227,7 +227,7 @@ then must_continue=yes fi last_ts="`tail $resdir/console.log | grep '^\[ *[0-9]\+\.[0-9]\+]' | tail -1 | sed -e 's/^\[ *//' -e 's/\..*$//'`" - if test -z "last_ts" + if test -z "$last_ts" then last_ts=0 fi diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE03.boot b/tools/testing/selftests/rcutorture/configs/rcu/TREE03.boot index 5c3213cc3ad7..1c218944b1e9 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE03.boot +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE03.boot @@ -3,3 +3,4 @@ rcutree.gp_preinit_delay=12 rcutree.gp_init_delay=3 rcutree.gp_cleanup_delay=3 rcutree.kthread_prio=2 +threadirqs