diff options
Diffstat (limited to 'kernel')
83 files changed, 5652 insertions, 2349 deletions
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 536edc2be307..504c10b990ef 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -16,6 +16,7 @@ #include <linux/file.h> #include <linux/license.h> #include <linux/filter.h> +#include <linux/version.h> static LIST_HEAD(bpf_map_types); @@ -467,7 +468,7 @@ struct bpf_prog *bpf_prog_get(u32 ufd) } /* last field in 'union bpf_attr' used by this command */ -#define BPF_PROG_LOAD_LAST_FIELD log_buf +#define BPF_PROG_LOAD_LAST_FIELD kern_version static int bpf_prog_load(union bpf_attr *attr) { @@ -492,6 +493,10 @@ static int bpf_prog_load(union bpf_attr *attr) if (attr->insn_cnt >= BPF_MAXINSNS) return -EINVAL; + if (type == BPF_PROG_TYPE_KPROBE && + attr->kern_version != LINUX_VERSION_CODE) + return -EINVAL; + /* plain bpf_prog allocation */ prog = bpf_prog_alloc(bpf_prog_size(attr->insn_cnt), GFP_USER); if (!prog) diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 29a7b2cc593e..a220fdb66568 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -3806,10 +3806,7 @@ static void *pidlist_allocate(int count) static void pidlist_free(void *p) { - if (is_vmalloc_addr(p)) - vfree(p); - else - kfree(p); + kvfree(p); } /* @@ -5040,6 +5037,9 @@ int __init cgroup_init(void) WARN_ON(cgroup_add_dfl_cftypes(ss, ss->dfl_cftypes)); WARN_ON(cgroup_add_legacy_cftypes(ss, ss->legacy_cftypes)); } + + if (ss->bind) + ss->bind(init_css_set.subsys[ssid]); } cgroup_kobj = kobject_create_and_add("cgroup", fs_kobj); diff --git a/kernel/context_tracking.c b/kernel/context_tracking.c index 937ecdfdf258..72d59a1a6eb6 100644 --- a/kernel/context_tracking.c +++ b/kernel/context_tracking.c @@ -39,15 +39,15 @@ void context_tracking_cpu_set(int cpu) } /** - * context_tracking_user_enter - Inform the context tracking that the CPU is going to - * enter userspace mode. + * context_tracking_enter - Inform the context tracking that the CPU is going + * enter user or guest space mode. * * This function must be called right before we switch from the kernel - * to userspace, when it's guaranteed the remaining kernel instructions - * to execute won't use any RCU read side critical section because this - * function sets RCU in extended quiescent state. + * to user or guest space, when it's guaranteed the remaining kernel + * instructions to execute won't use any RCU read side critical section + * because this function sets RCU in extended quiescent state. */ -void context_tracking_user_enter(void) +void context_tracking_enter(enum ctx_state state) { unsigned long flags; @@ -75,9 +75,8 @@ void context_tracking_user_enter(void) WARN_ON_ONCE(!current->mm); local_irq_save(flags); - if ( __this_cpu_read(context_tracking.state) != IN_USER) { + if ( __this_cpu_read(context_tracking.state) != state) { if (__this_cpu_read(context_tracking.active)) { - trace_user_enter(0); /* * At this stage, only low level arch entry code remains and * then we'll run in userspace. We can assume there won't be @@ -85,7 +84,10 @@ void context_tracking_user_enter(void) * user_exit() or rcu_irq_enter(). Let's remove RCU's dependency * on the tick. */ - vtime_user_enter(current); + if (state == CONTEXT_USER) { + trace_user_enter(0); + vtime_user_enter(current); + } rcu_user_enter(); } /* @@ -101,24 +103,32 @@ void context_tracking_user_enter(void) * OTOH we can spare the calls to vtime and RCU when context_tracking.active * is false because we know that CPU is not tickless. */ - __this_cpu_write(context_tracking.state, IN_USER); + __this_cpu_write(context_tracking.state, state); } local_irq_restore(flags); } +NOKPROBE_SYMBOL(context_tracking_enter); +EXPORT_SYMBOL_GPL(context_tracking_enter); + +void context_tracking_user_enter(void) +{ + context_tracking_enter(CONTEXT_USER); +} NOKPROBE_SYMBOL(context_tracking_user_enter); /** - * context_tracking_user_exit - Inform the context tracking that the CPU is - * exiting userspace mode and entering the kernel. + * context_tracking_exit - Inform the context tracking that the CPU is + * exiting user or guest mode and entering the kernel. * - * This function must be called after we entered the kernel from userspace - * before any use of RCU read side critical section. This potentially include - * any high level kernel code like syscalls, exceptions, signal handling, etc... + * This function must be called after we entered the kernel from user or + * guest space before any use of RCU read side critical section. This + * potentially include any high level kernel code like syscalls, exceptions, + * signal handling, etc... * * This call supports re-entrancy. This way it can be called from any exception * handler without needing to know if we came from userspace or not. */ -void context_tracking_user_exit(void) +void context_tracking_exit(enum ctx_state state) { unsigned long flags; @@ -129,20 +139,29 @@ void context_tracking_user_exit(void) return; local_irq_save(flags); - if (__this_cpu_read(context_tracking.state) == IN_USER) { + if (__this_cpu_read(context_tracking.state) == state) { if (__this_cpu_read(context_tracking.active)) { /* * We are going to run code that may use RCU. Inform * RCU core about that (ie: we may need the tick again). */ rcu_user_exit(); - vtime_user_exit(current); - trace_user_exit(0); + if (state == CONTEXT_USER) { + vtime_user_exit(current); + trace_user_exit(0); + } } - __this_cpu_write(context_tracking.state, IN_KERNEL); + __this_cpu_write(context_tracking.state, CONTEXT_KERNEL); } local_irq_restore(flags); } +NOKPROBE_SYMBOL(context_tracking_exit); +EXPORT_SYMBOL_GPL(context_tracking_exit); + +void context_tracking_user_exit(void) +{ + context_tracking_exit(CONTEXT_USER); +} NOKPROBE_SYMBOL(context_tracking_user_exit); /** diff --git a/kernel/cpu.c b/kernel/cpu.c index 1972b161c61e..94bbe4695232 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -20,6 +20,7 @@ #include <linux/gfp.h> #include <linux/suspend.h> #include <linux/lockdep.h> +#include <linux/tick.h> #include <trace/events/power.h> #include "smpboot.h" @@ -338,6 +339,8 @@ static int __ref take_cpu_down(void *_param) return err; cpu_notify(CPU_DYING | param->mod, param->hcpu); + /* Give up timekeeping duties */ + tick_handover_do_timer(); /* Park the stopper thread */ kthread_park(current); return 0; @@ -408,13 +411,17 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen) * * Wait for the stop thread to go away. */ - while (!idle_cpu(cpu)) + while (!per_cpu(cpu_dead_idle, cpu)) cpu_relax(); + smp_mb(); /* Read from cpu_dead_idle before __cpu_die(). */ + per_cpu(cpu_dead_idle, cpu) = false; + hotplug_cpu__broadcast_tick_pull(cpu); /* This actually kills the CPU. */ __cpu_die(cpu); /* CPU is completely dead: tell everyone. Too late to complain. */ + tick_cleanup_dead_cpu(cpu); cpu_notify_nofail(CPU_DEAD | mod, hcpu); check_for_tasks(cpu); @@ -446,6 +453,37 @@ out: EXPORT_SYMBOL(cpu_down); #endif /*CONFIG_HOTPLUG_CPU*/ +/* + * Unpark per-CPU smpboot kthreads at CPU-online time. + */ +static int smpboot_thread_call(struct notifier_block *nfb, + unsigned long action, void *hcpu) +{ + int cpu = (long)hcpu; + + switch (action & ~CPU_TASKS_FROZEN) { + + case CPU_ONLINE: + smpboot_unpark_threads(cpu); + break; + + default: + break; + } + + return NOTIFY_OK; +} + +static struct notifier_block smpboot_thread_notifier = { + .notifier_call = smpboot_thread_call, + .priority = CPU_PRI_SMPBOOT, +}; + +void __cpuinit smpboot_thread_init(void) +{ + register_cpu_notifier(&smpboot_thread_notifier); +} + /* Requires cpu_add_remove_lock to be held */ static int _cpu_up(unsigned int cpu, int tasks_frozen) { @@ -485,9 +523,6 @@ static int _cpu_up(unsigned int cpu, int tasks_frozen) goto out_notify; BUG_ON(!cpu_online(cpu)); - /* Wake the per cpu threads */ - smpboot_unpark_threads(cpu); - /* Now call notifier in preparation. */ cpu_notify(CPU_ONLINE | mod, hcpu); diff --git a/kernel/cpuset.c b/kernel/cpuset.c index fc7f4748d34a..ee14e3a35a29 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -622,6 +622,7 @@ static int generate_sched_domains(cpumask_var_t **domains, int csn; /* how many cpuset ptrs in csa so far */ int i, j, k; /* indices for partition finding loops */ cpumask_var_t *doms; /* resulting partition; i.e. sched domains */ + cpumask_var_t non_isolated_cpus; /* load balanced CPUs */ struct sched_domain_attr *dattr; /* attributes for custom domains */ int ndoms = 0; /* number of sched domains in result */ int nslot; /* next empty doms[] struct cpumask slot */ @@ -631,6 +632,10 @@ static int generate_sched_domains(cpumask_var_t **domains, dattr = NULL; csa = NULL; + if (!alloc_cpumask_var(&non_isolated_cpus, GFP_KERNEL)) + goto done; + cpumask_andnot(non_isolated_cpus, cpu_possible_mask, cpu_isolated_map); + /* Special case for the 99% of systems with one, full, sched domain */ if (is_sched_load_balance(&top_cpuset)) { ndoms = 1; @@ -643,7 +648,8 @@ static int generate_sched_domains(cpumask_var_t **domains, *dattr = SD_ATTR_INIT; update_domain_attr_tree(dattr, &top_cpuset); } - cpumask_copy(doms[0], top_cpuset.effective_cpus); + cpumask_and(doms[0], top_cpuset.effective_cpus, + non_isolated_cpus); goto done; } @@ -666,7 +672,8 @@ static int generate_sched_domains(cpumask_var_t **domains, * the corresponding sched domain. */ if (!cpumask_empty(cp->cpus_allowed) && - !is_sched_load_balance(cp)) + !(is_sched_load_balance(cp) && + cpumask_intersects(cp->cpus_allowed, non_isolated_cpus))) continue; if (is_sched_load_balance(cp)) @@ -748,6 +755,7 @@ restart: if (apn == b->pn) { cpumask_or(dp, dp, b->effective_cpus); + cpumask_and(dp, dp, non_isolated_cpus); if (dattr) update_domain_attr_tree(dattr + nslot, b); @@ -760,6 +768,7 @@ restart: BUG_ON(nslot != ndoms); done: + free_cpumask_var(non_isolated_cpus); kfree(csa); /* @@ -2444,20 +2453,12 @@ static struct cpuset *nearest_hardwall_ancestor(struct cpuset *cs) * @node: is this an allowed node? * @gfp_mask: memory allocation flags * - * If we're in interrupt, yes, we can always allocate. If __GFP_THISNODE is - * set, yes, we can always allocate. If node is in our task's mems_allowed, - * yes. If it's not a __GFP_HARDWALL request and this node is in the nearest - * hardwalled cpuset ancestor to this task's cpuset, yes. If the task has been - * OOM killed and has access to memory reserves as specified by the TIF_MEMDIE - * flag, yes. + * If we're in interrupt, yes, we can always allocate. If @node is set in + * current's mems_allowed, yes. If it's not a __GFP_HARDWALL request and this + * node is set in the nearest hardwalled cpuset ancestor to current's cpuset, + * yes. If current has access to memory reserves due to TIF_MEMDIE, yes. * Otherwise, no. * - * The __GFP_THISNODE placement logic is really handled elsewhere, - * by forcibly using a zonelist starting at a specified node, and by - * (in get_page_from_freelist()) refusing to consider the zones for - * any node on the zonelist except the first. By the time any such - * calls get to this routine, we should just shut up and say 'yes'. - * * GFP_USER allocations are marked with the __GFP_HARDWALL bit, * and do not allow allocations outside the current tasks cpuset * unless the task has been OOM killed as is marked TIF_MEMDIE. @@ -2493,7 +2494,7 @@ int __cpuset_node_allowed(int node, gfp_t gfp_mask) int allowed; /* is allocation in zone z allowed? */ unsigned long flags; - if (in_interrupt() || (gfp_mask & __GFP_THISNODE)) + if (in_interrupt()) return 1; if (node_isset(node, current->mems_allowed)) return 1; diff --git a/kernel/events/core.c b/kernel/events/core.c index f04daabfd1cf..06917d537302 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -34,14 +34,16 @@ #include <linux/syscalls.h> #include <linux/anon_inodes.h> #include <linux/kernel_stat.h> +#include <linux/cgroup.h> #include <linux/perf_event.h> #include <linux/ftrace_event.h> #include <linux/hw_breakpoint.h> #include <linux/mm_types.h> -#include <linux/cgroup.h> #include <linux/module.h> #include <linux/mman.h> #include <linux/compat.h> +#include <linux/bpf.h> +#include <linux/filter.h> #include "internal.h" @@ -153,7 +155,7 @@ enum event_type_t { */ struct static_key_deferred perf_sched_events __read_mostly; static DEFINE_PER_CPU(atomic_t, perf_cgroup_events); -static DEFINE_PER_CPU(atomic_t, perf_branch_stack_events); +static DEFINE_PER_CPU(int, perf_sched_cb_usages); static atomic_t nr_mmap_events __read_mostly; static atomic_t nr_comm_events __read_mostly; @@ -327,6 +329,11 @@ static inline u64 perf_clock(void) return local_clock(); } +static inline u64 perf_event_clock(struct perf_event *event) +{ + return event->clock(); +} + static inline struct perf_cpu_context * __get_cpu_context(struct perf_event_context *ctx) { @@ -351,32 +358,6 @@ static void perf_ctx_unlock(struct perf_cpu_context *cpuctx, #ifdef CONFIG_CGROUP_PERF -/* - * perf_cgroup_info keeps track of time_enabled for a cgroup. - * This is a per-cpu dynamically allocated data structure. - */ -struct perf_cgroup_info { - u64 time; - u64 timestamp; -}; - -struct perf_cgroup { - struct cgroup_subsys_state css; - struct perf_cgroup_info __percpu *info; -}; - -/* - * Must ensure cgroup is pinned (css_get) before calling - * this function. In other words, we cannot call this function - * if there is no cgroup event for the current CPU context. - */ -static inline struct perf_cgroup * -perf_cgroup_from_task(struct task_struct *task) -{ - return container_of(task_css(task, perf_event_cgrp_id), - struct perf_cgroup, css); -} - static inline bool perf_cgroup_match(struct perf_event *event) { @@ -905,6 +886,15 @@ static void get_ctx(struct perf_event_context *ctx) WARN_ON(!atomic_inc_not_zero(&ctx->refcount)); } +static void free_ctx(struct rcu_head *head) +{ + struct perf_event_context *ctx; + + ctx = container_of(head, struct perf_event_context, rcu_head); + kfree(ctx->task_ctx_data); + kfree(ctx); +} + static void put_ctx(struct perf_event_context *ctx) { if (atomic_dec_and_test(&ctx->refcount)) { @@ -912,7 +902,7 @@ static void put_ctx(struct perf_event_context *ctx) put_ctx(ctx->parent_ctx); if (ctx->task) put_task_struct(ctx->task); - kfree_rcu(ctx, rcu_head); + call_rcu(&ctx->rcu_head, free_ctx); } } @@ -1239,9 +1229,6 @@ list_add_event(struct perf_event *event, struct perf_event_context *ctx) if (is_cgroup_event(event)) ctx->nr_cgroups++; - if (has_branch_stack(event)) - ctx->nr_branch_stack++; - list_add_rcu(&event->event_entry, &ctx->event_list); ctx->nr_events++; if (event->attr.inherit_stat) @@ -1408,9 +1395,6 @@ list_del_event(struct perf_event *event, struct perf_event_context *ctx) cpuctx->cgrp = NULL; } - if (has_branch_stack(event)) - ctx->nr_branch_stack--; - ctx->nr_events--; if (event->attr.inherit_stat) ctx->nr_stat--; @@ -1847,6 +1831,7 @@ static void perf_set_shadow_time(struct perf_event *event, #define MAX_INTERRUPTS (~0ULL) static void perf_log_throttle(struct perf_event *event, int enable); +static void perf_log_itrace_start(struct perf_event *event); static int event_sched_in(struct perf_event *event, @@ -1881,6 +1866,12 @@ event_sched_in(struct perf_event *event, perf_pmu_disable(event->pmu); + event->tstamp_running += tstamp - event->tstamp_stopped; + + perf_set_shadow_time(event, ctx, tstamp); + + perf_log_itrace_start(event); + if (event->pmu->add(event, PERF_EF_START)) { event->state = PERF_EVENT_STATE_INACTIVE; event->oncpu = -1; @@ -1888,10 +1879,6 @@ event_sched_in(struct perf_event *event, goto out; } - event->tstamp_running += tstamp - event->tstamp_stopped; - - perf_set_shadow_time(event, ctx, tstamp); - if (!is_software_event(event)) cpuctx->active_oncpu++; if (!ctx->nr_active++) @@ -2559,6 +2546,9 @@ static void perf_event_context_sched_out(struct task_struct *task, int ctxn, next->perf_event_ctxp[ctxn] = ctx; ctx->task = next; next_ctx->task = task; + + swap(ctx->task_ctx_data, next_ctx->task_ctx_data); + do_switch = 0; perf_event_sync_stat(ctx, next_ctx); @@ -2577,6 +2567,56 @@ unlock: } } +void perf_sched_cb_dec(struct pmu *pmu) +{ + this_cpu_dec(perf_sched_cb_usages); +} + +void perf_sched_cb_inc(struct pmu *pmu) +{ + this_cpu_inc(perf_sched_cb_usages); +} + +/* + * This function provides the context switch callback to the lower code + * layer. It is invoked ONLY when the context switch callback is enabled. + */ +static void perf_pmu_sched_task(struct task_struct *prev, + struct task_struct *next, + bool sched_in) +{ + struct perf_cpu_context *cpuctx; + struct pmu *pmu; + unsigned long flags; + + if (prev == next) + return; + + local_irq_save(flags); + + rcu_read_lock(); + + list_for_each_entry_rcu(pmu, &pmus, entry) { + if (pmu->sched_task) { + cpuctx = this_cpu_ptr(pmu->pmu_cpu_context); + + perf_ctx_lock(cpuctx, cpuctx->task_ctx); + + perf_pmu_disable(pmu); + + pmu->sched_task(cpuctx->task_ctx, sched_in); + + perf_pmu_enable(pmu); + + perf_ctx_unlock(cpuctx, cpuctx->task_ctx); + } + } + + rcu_read_unlock(); + + local_irq_restore(flags); +} + #define for_each_task_context_nr(ctxn) \ for ((ctxn) = 0; (ctxn) < perf_nr_task_contexts; (ctxn)++) @@ -2596,6 +2636,9 @@ void __perf_event_task_sched_out(struct task_struct *task, { int ctxn; + if (__this_cpu_read(perf_sched_cb_usages)) + perf_pmu_sched_task(task, next, false); + for_each_task_context_nr(ctxn) perf_event_context_sched_out(task, ctxn, next); @@ -2755,64 +2798,6 @@ static void perf_event_context_sched_in(struct perf_event_context *ctx, } /* - * When sampling the branck stack in system-wide, it may be necessary - * to flush the stack on context switch. This happens when the branch - * stack does not tag its entries with the pid of the current task. - * Otherwise it becomes impossible to associate a branch entry with a - * task. This ambiguity is more likely to appear when the branch stack - * supports priv level filtering and the user sets it to monitor only - * at the user level (which could be a useful measurement in system-wide - * mode). In that case, the risk is high of having a branch stack with - * branch from multiple tasks. Flushing may mean dropping the existing - * entries or stashing them somewhere in the PMU specific code layer. - * - * This function provides the context switch callback to the lower code - * layer. It is invoked ONLY when there is at least one system-wide context - * with at least one active event using taken branch sampling. - */ -static void perf_branch_stack_sched_in(struct task_struct *prev, - struct task_struct *task) -{ - struct perf_cpu_context *cpuctx; - struct pmu *pmu; - unsigned long flags; - - /* no need to flush branch stack if not changing task */ - if (prev == task) - return; - - local_irq_save(flags); - - rcu_read_lock(); - - list_for_each_entry_rcu(pmu, &pmus, entry) { - cpuctx = this_cpu_ptr(pmu->pmu_cpu_context); - - /* - * check if the context has at least one - * event using PERF_SAMPLE_BRANCH_STACK - */ - if (cpuctx->ctx.nr_branch_stack > 0 - && pmu->flush_branch_stack) { - - perf_ctx_lock(cpuctx, cpuctx->task_ctx); - - perf_pmu_disable(pmu); - - pmu->flush_branch_stack(); - - perf_pmu_enable(pmu); - - perf_ctx_unlock(cpuctx, cpuctx->task_ctx); - } - } - - rcu_read_unlock(); - - local_irq_restore(flags); -} - -/* * Called from scheduler to add the events of the current task * with interrupts disabled. * @@ -2844,9 +2829,8 @@ void __perf_event_task_sched_in(struct task_struct *prev, if (atomic_read(this_cpu_ptr(&perf_cgroup_events))) perf_cgroup_sched_in(prev, task); - /* check for system-wide branch_stack events */ - if (atomic_read(this_cpu_ptr(&perf_branch_stack_events))) - perf_branch_stack_sched_in(prev, task); + if (__this_cpu_read(perf_sched_cb_usages)) + perf_pmu_sched_task(prev, task, true); } static u64 perf_calculate_period(struct perf_event *event, u64 nsec, u64 count) @@ -3220,7 +3204,10 @@ static void __perf_event_read(void *info) static inline u64 perf_event_count(struct perf_event *event) { - return local64_read(&event->count) + atomic64_read(&event->child_count); + if (event->pmu->count) + return event->pmu->count(event); + + return __perf_event_count(event); } static u64 perf_event_read(struct perf_event *event) @@ -3321,12 +3308,15 @@ errout: * Returns a matching context with refcount and pincount. */ static struct perf_event_context * -find_get_context(struct pmu *pmu, struct task_struct *task, int cpu) +find_get_context(struct pmu *pmu, struct task_struct *task, + struct perf_event *event) { struct perf_event_context *ctx, *clone_ctx = NULL; struct perf_cpu_context *cpuctx; + void *task_ctx_data = NULL; unsigned long flags; int ctxn, err; + int cpu = event->cpu; if (!task) { /* Must be root to operate on a CPU event: */ @@ -3354,11 +3344,24 @@ find_get_context(struct pmu *pmu, struct task_struct *task, int cpu) if (ctxn < 0) goto errout; + if (event->attach_state & PERF_ATTACH_TASK_DATA) { + task_ctx_data = kzalloc(pmu->task_ctx_size, GFP_KERNEL); + if (!task_ctx_data) { + err = -ENOMEM; + goto errout; + } + } + retry: ctx = perf_lock_task_context(task, ctxn, &flags); if (ctx) { clone_ctx = unclone_ctx(ctx); ++ctx->pin_count; + + if (task_ctx_data && !ctx->task_ctx_data) { + ctx->task_ctx_data = task_ctx_data; + task_ctx_data = NULL; + } raw_spin_unlock_irqrestore(&ctx->lock, flags); if (clone_ctx) @@ -3369,6 +3372,11 @@ retry: if (!ctx) goto errout; + if (task_ctx_data) { + ctx->task_ctx_data = task_ctx_data; + task_ctx_data = NULL; + } + err = 0; mutex_lock(&task->perf_event_mutex); /* @@ -3395,13 +3403,16 @@ retry: } } + kfree(task_ctx_data); return ctx; errout: + kfree(task_ctx_data); return ERR_PTR(err); } static void perf_event_free_filter(struct perf_event *event); +static void perf_event_free_bpf_prog(struct perf_event *event); static void free_event_rcu(struct rcu_head *head) { @@ -3411,10 +3422,10 @@ static void free_event_rcu(struct rcu_head *head) if (event->ns) put_pid_ns(event->ns); perf_event_free_filter(event); + perf_event_free_bpf_prog(event); kfree(event); } -static void ring_buffer_put(struct ring_buffer *rb); static void ring_buffer_attach(struct perf_event *event, struct ring_buffer *rb); @@ -3423,10 +3434,6 @@ static void unaccount_event_cpu(struct perf_event *event, int cpu) if (event->parent) return; - if (has_branch_stack(event)) { - if (!(event->attach_state & PERF_ATTACH_TASK)) - atomic_dec(&per_cpu(perf_branch_stack_events, cpu)); - } if (is_cgroup_event(event)) atomic_dec(&per_cpu(perf_cgroup_events, cpu)); } @@ -3454,6 +3461,91 @@ static void unaccount_event(struct perf_event *event) unaccount_event_cpu(event, event->cpu); } +/* + * The following implement mutual exclusion of events on "exclusive" pmus + * (PERF_PMU_CAP_EXCLUSIVE). Such pmus can only have one event scheduled + * at a time, so we disallow creating events that might conflict, namely: + * + * 1) cpu-wide events in the presence of per-task events, + * 2) per-task events in the presence of cpu-wide events, + * 3) two matching events on the same context. + * + * The former two cases are handled in the allocation path (perf_event_alloc(), + * __free_event()), the latter -- before the first perf_install_in_context(). + */ +static int exclusive_event_init(struct perf_event *event) +{ + struct pmu *pmu = event->pmu; + + if (!(pmu->capabilities & PERF_PMU_CAP_EXCLUSIVE)) + return 0; + + /* + * Prevent co-existence of per-task and cpu-wide events on the + * same exclusive pmu. + * + * Negative pmu::exclusive_cnt means there are cpu-wide + * events on this "exclusive" pmu, positive means there are + * per-task events. + * + * Since this is called in perf_event_alloc() path, event::ctx + * doesn't exist yet; it is, however, safe to use PERF_ATTACH_TASK + * to mean "per-task event", because unlike other attach states it + * never gets cleared. + */ + if (event->attach_state & PERF_ATTACH_TASK) { + if (!atomic_inc_unless_negative(&pmu->exclusive_cnt)) + return -EBUSY; + } else { + if (!atomic_dec_unless_positive(&pmu->exclusive_cnt)) + return -EBUSY; + } + + return 0; +} + +static void exclusive_event_destroy(struct perf_event *event) +{ + struct pmu *pmu = event->pmu; + + if (!(pmu->capabilities & PERF_PMU_CAP_EXCLUSIVE)) + return; + + /* see comment in exclusive_event_init() */ + if (event->attach_state & PERF_ATTACH_TASK) + atomic_dec(&pmu->exclusive_cnt); + else + atomic_inc(&pmu->exclusive_cnt); +} + +static bool exclusive_event_match(struct perf_event *e1, struct perf_event *e2) +{ + if ((e1->pmu->capabilities & PERF_PMU_CAP_EXCLUSIVE) && + (e1->cpu == e2->cpu || + e1->cpu == -1 || + e2->cpu == -1)) + return true; + return false; +} + +/* Called under the same ctx::mutex as perf_install_in_context() */ +static bool exclusive_event_installable(struct perf_event *event, + struct perf_event_context *ctx) +{ + struct perf_event *iter_event; + struct pmu *pmu = event->pmu; + + if (!(pmu->capabilities & PERF_PMU_CAP_EXCLUSIVE)) + return true; + + list_for_each_entry(iter_event, &ctx->event_list, event_entry) { + if (exclusive_event_match(iter_event, event)) + return false; + } + + return true; +} + static void __free_event(struct perf_event *event) { if (!event->parent) { @@ -3467,8 +3559,10 @@ static void __free_event(struct perf_event *event) if (event->ctx) put_ctx(event->ctx); - if (event->pmu) + if (event->pmu) { + exclusive_event_destroy(event); module_put(event->pmu->module); + } call_rcu(&event->rcu_head, free_event_rcu); } @@ -3591,7 +3685,7 @@ static void put_event(struct perf_event *event) ctx = perf_event_ctx_lock_nested(event, SINGLE_DEPTH_NESTING); WARN_ON_ONCE(ctx->parent_ctx); perf_remove_from_context(event, true); - mutex_unlock(&ctx->mutex); + perf_event_ctx_unlock(event, ctx); _free_event(event); } @@ -3927,6 +4021,7 @@ static inline int perf_fget_light(int fd, struct fd *p) static int perf_event_set_output(struct perf_event *event, struct perf_event *output_event); static int perf_event_set_filter(struct perf_event *event, void __user *arg); +static int perf_event_set_bpf_prog(struct perf_event *event, u32 prog_fd); static long _perf_ioctl(struct perf_event *event, unsigned int cmd, unsigned long arg) { @@ -3980,6 +4075,9 @@ static long _perf_ioctl(struct perf_event *event, unsigned int cmd, unsigned lon case PERF_EVENT_IOC_SET_FILTER: return perf_event_set_filter(event, (void __user *)arg); + case PERF_EVENT_IOC_SET_BPF: + return perf_event_set_bpf_prog(event, arg); + default: return -ENOTTY; } @@ -4096,6 +4194,8 @@ static void perf_event_init_userpage(struct perf_event *event) /* Allow new userspace to detect that bit 0 is deprecated */ userpg->cap_bit0_is_deprecated = 1; userpg->size = offsetof(struct perf_event_mmap_page, __reserved); + userpg->data_offset = PAGE_SIZE; + userpg->data_size = perf_data_size(rb); unlock: rcu_read_unlock(); @@ -4263,7 +4363,7 @@ static void rb_free_rcu(struct rcu_head *rcu_head) rb_free(rb); } -static struct ring_buffer *ring_buffer_get(struct perf_event *event) +struct ring_buffer *ring_buffer_get(struct perf_event *event) { struct ring_buffer *rb; @@ -4278,7 +4378,7 @@ static struct ring_buffer *ring_buffer_get(struct perf_event *event) return rb; } -static void ring_buffer_put(struct ring_buffer *rb) +void ring_buffer_put(struct ring_buffer *rb) { if (!atomic_dec_and_test(&rb->refcount)) return; @@ -4295,6 +4395,9 @@ static void perf_mmap_open(struct vm_area_struct *vma) atomic_inc(&event->mmap_count); atomic_inc(&event->rb->mmap_count); + if (vma->vm_pgoff) + atomic_inc(&event->rb->aux_mmap_count); + if (event->pmu->event_mapped) event->pmu->event_mapped(event); } @@ -4319,6 +4422,20 @@ static void perf_mmap_close(struct vm_area_struct *vma) if (event->pmu->event_unmapped) event->pmu->event_unmapped(event); + /* + * rb->aux_mmap_count will always drop before rb->mmap_count and + * event->mmap_count, so it is ok to use event->mmap_mutex to + * serialize with perf_mmap here. + */ + if (rb_has_aux(rb) && vma->vm_pgoff == rb->aux_pgoff && + atomic_dec_and_mutex_lock(&rb->aux_mmap_count, &event->mmap_mutex)) { + atomic_long_sub(rb->aux_nr_pages, &mmap_user->locked_vm); + vma->vm_mm->pinned_vm -= rb->aux_mmap_locked; + + rb_free_aux(rb); + mutex_unlock(&event->mmap_mutex); + } + atomic_dec(&rb->mmap_count); if (!atomic_dec_and_mutex_lock(&event->mmap_count, &event->mmap_mutex)) @@ -4392,7 +4509,7 @@ out_put: static const struct vm_operations_struct perf_mmap_vmops = { .open = perf_mmap_open, - .close = perf_mmap_close, + .close = perf_mmap_close, /* non mergable */ .fault = perf_mmap_fault, .page_mkwrite = perf_mmap_fault, }; @@ -4403,10 +4520,10 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma) unsigned long user_locked, user_lock_limit; struct user_struct *user = current_user(); unsigned long locked, lock_limit; - struct ring_buffer *rb; + struct ring_buffer *rb = NULL; unsigned long vma_size; unsigned long nr_pages; - long user_extra, extra; + long user_extra = 0, extra = 0; int ret = 0, flags = 0; /* @@ -4421,7 +4538,66 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma) return -EINVAL; vma_size = vma->vm_end - vma->vm_start; - nr_pages = (vma_size / PAGE_SIZE) - 1; + + if (vma->vm_pgoff == 0) { + nr_pages = (vma_size / PAGE_SIZE) - 1; + } else { + /* + * AUX area mapping: if rb->aux_nr_pages != 0, it's already + * mapped, all subsequent mappings should have the same size + * and offset. Must be above the normal perf buffer. + */ + u64 aux_offset, aux_size; + + if (!event->rb) + return -EINVAL; + + nr_pages = vma_size / PAGE_SIZE; + + mutex_lock(&event->mmap_mutex); + ret = -EINVAL; + + rb = event->rb; + if (!rb) + goto aux_unlock; + + aux_offset = ACCESS_ONCE(rb->user_page->aux_offset); + aux_size = ACCESS_ONCE(rb->user_page->aux_size); + + if (aux_offset < perf_data_size(rb) + PAGE_SIZE) + goto aux_unlock; + + if (aux_offset != vma->vm_pgoff << PAGE_SHIFT) + goto aux_unlock; + + /* already mapped with a different offset */ + if (rb_has_aux(rb) && rb->aux_pgoff != vma->vm_pgoff) + goto aux_unlock; + + if (aux_size != vma_size || aux_size != nr_pages * PAGE_SIZE) + goto aux_unlock; + + /* already mapped with a different size */ + if (rb_has_aux(rb) && rb->aux_nr_pages != nr_pages) + goto aux_unlock; + + if (!is_power_of_2(nr_pages)) + goto aux_unlock; + + if (!atomic_inc_not_zero(&rb->mmap_count)) + goto aux_unlock; + + if (rb_has_aux(rb)) { + atomic_inc(&rb->aux_mmap_count); + ret = 0; + goto unlock; + } + + atomic_set(&rb->aux_mmap_count, 1); + user_extra = nr_pages; + + goto accounting; + } /* * If we have rb pages ensure they're a power-of-two number, so we @@ -4433,9 +4609,6 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma) if (vma_size != PAGE_SIZE * (1 + nr_pages)) return -EINVAL; - if (vma->vm_pgoff != 0) - return -EINVAL; - WARN_ON_ONCE(event->ctx->parent_ctx); again: mutex_lock(&event->mmap_mutex); @@ -4459,6 +4632,8 @@ again: } user_extra = nr_pages + 1; + +accounting: user_lock_limit = sysctl_perf_event_mlock >> (PAGE_SHIFT - 10); /* @@ -4468,7 +4643,6 @@ again: user_locked = atomic_long_read(&user->locked_vm) + user_extra; - extra = 0; if (user_locked > user_lock_limit) extra = user_locked - user_lock_limit; @@ -4482,35 +4656,46 @@ again: goto unlock; } - WARN_ON(event->rb); + WARN_ON(!rb && event->rb); if (vma->vm_flags & VM_WRITE) flags |= RING_BUFFER_WRITABLE; - rb = rb_alloc(nr_pages, - event->attr.watermark ? event->attr.wakeup_watermark : 0, - event->cpu, flags); - if (!rb) { - ret = -ENOMEM; - goto unlock; - } + rb = rb_alloc(nr_pages, + event->attr.watermark ? event->attr.wakeup_watermark : 0, + event->cpu, flags); - atomic_set(&rb->mmap_count, 1); - rb->mmap_locked = extra; - rb->mmap_user = get_current_user(); + if (!rb) { + ret = -ENOMEM; + goto unlock; + } - atomic_long_add(user_extra, &user->locked_vm); - vma->vm_mm->pinned_vm += extra; + atomic_set(&rb->mmap_count, 1); + rb->mmap_user = get_current_user(); + rb->mmap_locked = extra; - ring_buffer_attach(event, rb); + ring_buffer_attach(event, rb); - perf_event_init_userpage(event); - perf_event_update_userpage(event); + perf_event_init_userpage(event); + perf_event_update_userpage(event); + } else { + ret = rb_alloc_aux(rb, event, vma->vm_pgoff, nr_pages, + event->attr.aux_watermark, flags); + if (!ret) + rb->aux_mmap_locked = extra; + } unlock: - if (!ret) + if (!ret) { + atomic_long_add(user_extra, &user->locked_vm); + vma->vm_mm->pinned_vm += extra; + atomic_inc(&event->mmap_count); + } else if (rb) { + atomic_dec(&rb->mmap_count); + } +aux_unlock: mutex_unlock(&event->mmap_mutex); /* @@ -4574,6 +4759,13 @@ static void perf_pending_event(struct irq_work *entry) { struct perf_event *event = container_of(entry, struct perf_event, pending); + int rctx; + + rctx = perf_swevent_get_recursion_context(); + /* + * If we 'fail' here, that's OK, it means recursion is already disabled + * and we won't recurse 'further'. + */ if (event->pending_disable) { event->pending_disable = 0; @@ -4584,6 +4776,9 @@ static void perf_pending_event(struct irq_work *entry) event->pending_wakeup = 0; perf_event_wakeup(event); } + + if (rctx >= 0) + perf_swevent_put_recursion_context(rctx); } /* @@ -4756,7 +4951,7 @@ static void __perf_event_header__init_id(struct perf_event_header *header, } if (sample_type & PERF_SAMPLE_TIME) - data->time = perf_clock(); + data->time = perf_event_clock(event); if (sample_type & (PERF_SAMPLE_ID | PERF_SAMPLE_IDENTIFIER)) data->id = primary_event_id(event); @@ -5334,6 +5529,8 @@ static void perf_event_task_output(struct perf_event *event, task_event->event_id.tid = perf_event_tid(event, task); task_event->event_id.ptid = perf_event_tid(event, current); + task_event->event_id.time = perf_event_clock(event); + perf_output_put(&handle, task_event->event_id); perf_event__output_id_sample(event, &handle, &sample); @@ -5367,7 +5564,7 @@ static void perf_event_task(struct task_struct *task, /* .ppid */ /* .tid */ /* .ptid */ - .time = perf_clock(), + /* .time */ }, }; @@ -5722,6 +5919,40 @@ void perf_event_mmap(struct vm_area_struct *vma) perf_event_mmap_event(&mmap_event); } +void perf_event_aux_event(struct perf_event *event, unsigned long head, + unsigned long size, u64 flags) +{ + struct perf_output_handle handle; + struct perf_sample_data sample; + struct perf_aux_event { + struct perf_event_header header; + u64 offset; + u64 size; + u64 flags; + } rec = { + .header = { + .type = PERF_RECORD_AUX, + .misc = 0, + .size = sizeof(rec), + }, + .offset = head, + .size = size, + .flags = flags, + }; + int ret; + + perf_event_header__init_id(&rec.header, &sample, event); + ret = perf_output_begin(&handle, event, rec.header.size); + + if (ret) + return; + + perf_output_put(&handle, rec); + perf_event__output_id_sample(event, &handle, &sample); + + perf_output_end(&handle); +} + /* * IRQ throttle logging */ @@ -5743,7 +5974,7 @@ static void perf_log_throttle(struct perf_event *event, int enable) .misc = 0, .size = sizeof(throttle_event), }, - .time = perf_clock(), + .time = perf_event_clock(event), .id = primary_event_id(event), .stream_id = event->id, }; @@ -5763,6 +5994,44 @@ static void perf_log_throttle(struct perf_event *event, int enable) perf_output_end(&handle); } +static void perf_log_itrace_start(struct perf_event *event) +{ + struct perf_output_handle handle; + struct perf_sample_data sample; + struct perf_aux_event { + struct perf_event_header header; + u32 pid; + u32 tid; + } rec; + int ret; + + if (event->parent) + event = event->parent; + + if (!(event->pmu->capabilities & PERF_PMU_CAP_ITRACE) || + event->hw.itrace_started) + return; + + event->hw.itrace_started = 1; + + rec.header.type = PERF_RECORD_ITRACE_START; + rec.header.misc = 0; + rec.header.size = sizeof(rec); + rec.pid = perf_event_pid(event, current); + rec.tid = perf_event_tid(event, current); + + perf_event_header__init_id(&rec.header, &sample, event); + ret = perf_output_begin(&handle, event, rec.header.size); + + if (ret) + return; + + perf_output_put(&handle, rec); + perf_event__output_id_sample(event, &handle, &sample); + + perf_output_end(&handle); +} + /* * Generic event overflow handling, sampling. */ @@ -6123,6 +6392,7 @@ static int perf_swevent_add(struct perf_event *event, int flags) } hlist_add_head_rcu(&event->hlist_entry, head); + perf_event_update_userpage(event); return 0; } @@ -6286,6 +6556,8 @@ static int perf_swevent_init(struct perf_event *event) static struct pmu perf_swevent = { .task_ctx_nr = perf_sw_context, + .capabilities = PERF_PMU_CAP_NO_NMI, + .event_init = perf_swevent_init, .add = perf_swevent_add, .del = perf_swevent_del, @@ -6439,6 +6711,49 @@ static void perf_event_free_filter(struct perf_event *event) ftrace_profile_free_filter(event); } +static int perf_event_set_bpf_prog(struct perf_event *event, u32 prog_fd) +{ + struct bpf_prog *prog; + + if (event->attr.type != PERF_TYPE_TRACEPOINT) + return -EINVAL; + + if (event->tp_event->prog) + return -EEXIST; + + if (!(event->tp_event->flags & TRACE_EVENT_FL_KPROBE)) + /* bpf programs can only be attached to kprobes */ + return -EINVAL; + + prog = bpf_prog_get(prog_fd); + if (IS_ERR(prog)) + return PTR_ERR(prog); + + if (prog->aux->prog_type != BPF_PROG_TYPE_KPROBE) { + /* valid fd, but invalid bpf program type */ + bpf_prog_put(prog); + return -EINVAL; + } + + event->tp_event->prog = prog; + + return 0; +} + +static void perf_event_free_bpf_prog(struct perf_event *event) +{ + struct bpf_prog *prog; + + if (!event->tp_event) + return; + + prog = event->tp_event->prog; + if (prog) { + event->tp_event->prog = NULL; + bpf_prog_put(prog); + } +} + #else static inline void perf_tp_register(void) @@ -6454,6 +6769,14 @@ static void perf_event_free_filter(struct perf_event *event) { } +static int perf_event_set_bpf_prog(struct perf_event *event, u32 prog_fd) +{ + return -ENOENT; +} + +static void perf_event_free_bpf_prog(struct perf_event *event) +{ +} #endif /* CONFIG_EVENT_TRACING */ #ifdef CONFIG_HAVE_HW_BREAKPOINT @@ -6592,6 +6915,7 @@ static int cpu_clock_event_add(struct perf_event *event, int flags) { if (flags & PERF_EF_START) cpu_clock_event_start(event, flags); + perf_event_update_userpage(event); return 0; } @@ -6628,6 +6952,8 @@ static int cpu_clock_event_init(struct perf_event *event) static struct pmu perf_cpu_clock = { .task_ctx_nr = perf_sw_context, + .capabilities = PERF_PMU_CAP_NO_NMI, + .event_init = cpu_clock_event_init, .add = cpu_clock_event_add, .del = cpu_clock_event_del, @@ -6666,6 +6992,7 @@ static int task_clock_event_add(struct perf_event *event, int flags) { if (flags & PERF_EF_START) task_clock_event_start(event, flags); + perf_event_update_userpage(event); return 0; } @@ -6706,6 +7033,8 @@ static int task_clock_event_init(struct perf_event *event) static struct pmu perf_task_clock = { .task_ctx_nr = perf_sw_context, + .capabilities = PERF_PMU_CAP_NO_NMI, + .event_init = task_clock_event_init, .add = task_clock_event_add, .del = task_clock_event_del, @@ -6983,6 +7312,7 @@ got_cpu_context: pmu->event_idx = perf_event_idx_default; list_add_rcu(&pmu->entry, &pmus); + atomic_set(&pmu->exclusive_cnt, 0); ret = 0; unlock: mutex_unlock(&pmus_lock); @@ -7027,12 +7357,23 @@ EXPORT_SYMBOL_GPL(perf_pmu_unregister); static int perf_try_init_event(struct pmu *pmu, struct perf_event *event) { + struct perf_event_context *ctx = NULL; int ret; if (!try_module_get(pmu->module)) return -ENODEV; + + if (event->group_leader != event) { + ctx = perf_event_ctx_lock(event->group_leader); + BUG_ON(!ctx); + } + event->pmu = pmu; ret = pmu->event_init(event); + + if (ctx) + perf_event_ctx_unlock(event->group_leader, ctx); + if (ret) module_put(pmu->module); @@ -7079,10 +7420,6 @@ static void account_event_cpu(struct perf_event *event, int cpu) if (event->parent) return; - if (has_branch_stack(event)) { - if (!(event->attach_state & PERF_ATTACH_TASK)) - atomic_inc(&per_cpu(perf_branch_stack_events, cpu)); - } if (is_cgroup_event(event)) atomic_inc(&per_cpu(perf_cgroup_events, cpu)); } @@ -7121,7 +7458,7 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu, struct perf_event *group_leader, struct perf_event *parent_event, perf_overflow_handler_t overflow_handler, - void *context) + void *context, int cgroup_fd) { struct pmu *pmu; struct perf_event *event; @@ -7176,18 +7513,18 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu, if (task) { event->attach_state = PERF_ATTACH_TASK; - - if (attr->type == PERF_TYPE_TRACEPOINT) - event->hw.tp_target = task; -#ifdef CONFIG_HAVE_HW_BREAKPOINT /* - * hw_breakpoint is a bit difficult here.. + * XXX pmu::event_init needs to know what task to account to + * and we cannot use the ctx information because we need the + * pmu before we get a ctx. */ - else if (attr->type == PERF_TYPE_BREAKPOINT) - event->hw.bp_target = task; -#endif + event->hw.target = task; } + event->clock = &local_clock; + if (parent_event) + event->clock = parent_event->clock; + if (!overflow_handler && parent_event) { overflow_handler = parent_event->overflow_handler; context = parent_event->overflow_handler_context; @@ -7214,6 +7551,15 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu, if (attr->inherit && (attr->read_format & PERF_FORMAT_GROUP)) goto err_ns; + if (!has_branch_stack(event)) + event->attr.branch_sample_type = 0; + + if (cgroup_fd != -1) { + err = perf_cgroup_connect(cgroup_fd, event, attr, group_leader); + if (err) + goto err_ns; + } + pmu = perf_init_event(event); if (!pmu) goto err_ns; @@ -7222,21 +7568,30 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu, goto err_ns; } + err = exclusive_event_init(event); + if (err) + goto err_pmu; + if (!event->parent) { if (event->attr.sample_type & PERF_SAMPLE_CALLCHAIN) { err = get_callchain_buffers(); if (err) - goto err_pmu; + goto err_per_task; } } return event; +err_per_task: + exclusive_event_destroy(event); + err_pmu: if (event->destroy) event->destroy(event); module_put(pmu->module); err_ns: + if (is_cgroup_event(event)) + perf_detach_cgroup(event); if (event->ns) put_pid_ns(event->ns); kfree(event); @@ -7399,6 +7754,19 @@ perf_event_set_output(struct perf_event *event, struct perf_event *output_event) if (output_event->cpu == -1 && output_event->ctx != event->ctx) goto out; + /* + * Mixing clocks in the same buffer is trouble you don't need. + */ + if (output_event->clock != event->clock) + goto out; + + /* + * If both events generate aux data, they must be on the same PMU + */ + if (has_aux(event) && has_aux(output_event) && + event->pmu != output_event->pmu) + goto out; + set: mutex_lock(&event->mmap_mutex); /* Can't redirect output if we've got an active mmap() */ @@ -7431,6 +7799,43 @@ static void mutex_lock_double(struct mutex *a, struct mutex *b) mutex_lock_nested(b, SINGLE_DEPTH_NESTING); } +static int perf_event_set_clock(struct perf_event *event, clockid_t clk_id) +{ + bool nmi_safe = false; + + switch (clk_id) { + case CLOCK_MONOTONIC: + event->clock = &ktime_get_mono_fast_ns; + nmi_safe = true; + break; + + case CLOCK_MONOTONIC_RAW: + event->clock = &ktime_get_raw_fast_ns; + nmi_safe = true; + break; + + case CLOCK_REALTIME: + event->clock = &ktime_get_real_ns; + break; + + case CLOCK_BOOTTIME: + event->clock = &ktime_get_boot_ns; + break; + + case CLOCK_TAI: + event->clock = &ktime_get_tai_ns; + break; + + default: + return -EINVAL; + } + + if (!nmi_safe && !(event->pmu->capabilities & PERF_PMU_CAP_NO_NMI)) + return -EINVAL; + + return 0; +} + /** * sys_perf_event_open - open a performance event, associate it to a task/cpu * @@ -7455,6 +7860,7 @@ SYSCALL_DEFINE5(perf_event_open, int move_group = 0; int err; int f_flags = O_RDWR; + int cgroup_fd = -1; /* for future expandability... */ if (flags & ~PERF_FLAG_ALL) @@ -7520,21 +7926,16 @@ SYSCALL_DEFINE5(perf_event_open, get_online_cpus(); + if (flags & PERF_FLAG_PID_CGROUP) + cgroup_fd = pid; + event = perf_event_alloc(&attr, cpu, task, group_leader, NULL, - NULL, NULL); + NULL, NULL, cgroup_fd); if (IS_ERR(event)) { err = PTR_ERR(event); goto err_cpus; } - if (flags & PERF_FLAG_PID_CGROUP) { - err = perf_cgroup_connect(pid, event, &attr, group_leader); - if (err) { - __free_event(event); - goto err_cpus; - } - } - if (is_sampling_event(event)) { if (event->pmu->capabilities & PERF_PMU_CAP_NO_INTERRUPT) { err = -ENOTSUPP; @@ -7550,6 +7951,12 @@ SYSCALL_DEFINE5(perf_event_open, */ pmu = event->pmu; + if (attr.use_clockid) { + err = perf_event_set_clock(event, attr.clockid); + if (err) + goto err_alloc; + } + if (group_leader && (is_software_event(event) != is_software_event(group_leader))) { if (is_software_event(event)) { @@ -7576,12 +7983,17 @@ SYSCALL_DEFINE5(perf_event_open, /* * Get the target context (task or percpu): */ - ctx = find_get_context(pmu, task, event->cpu); + ctx = find_get_context(pmu, task, event); if (IS_ERR(ctx)) { err = PTR_ERR(ctx); goto err_alloc; } + if ((pmu->capabilities & PERF_PMU_CAP_EXCLUSIVE) && group_leader) { + err = -EBUSY; + goto err_context; + } + if (task) { put_task_struct(task); task = NULL; @@ -7599,6 +8011,11 @@ SYSCALL_DEFINE5(perf_event_open, */ if (group_leader->group_leader != group_leader) goto err_context; + + /* All events in a group should have the same clock */ + if (group_leader->clock != event->clock) + goto err_context; + /* * Do not allow to attach to a group in a different * task or CPU context: @@ -7699,6 +8116,13 @@ SYSCALL_DEFINE5(perf_event_open, get_ctx(ctx); } + if (!exclusive_event_installable(event, ctx)) { + err = -EBUSY; + mutex_unlock(&ctx->mutex); + fput(event_file); + goto err_context; + } + perf_install_in_context(ctx, event, event->cpu); perf_unpin_context(ctx); @@ -7771,7 +8195,7 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu, */ event = perf_event_alloc(attr, cpu, task, NULL, NULL, - overflow_handler, context); + overflow_handler, context, -1); if (IS_ERR(event)) { err = PTR_ERR(event); goto err; @@ -7782,7 +8206,7 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu, account_event(event); - ctx = find_get_context(event->pmu, task, cpu); + ctx = find_get_context(event->pmu, task, event); if (IS_ERR(ctx)) { err = PTR_ERR(ctx); goto err_free; @@ -7790,6 +8214,14 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu, WARN_ON_ONCE(ctx->parent_ctx); mutex_lock(&ctx->mutex); + if (!exclusive_event_installable(event, ctx)) { + mutex_unlock(&ctx->mutex); + perf_unpin_context(ctx); + put_ctx(ctx); + err = -EBUSY; + goto err_free; + } + perf_install_in_context(ctx, event, cpu); perf_unpin_context(ctx); mutex_unlock(&ctx->mutex); @@ -8132,7 +8564,7 @@ inherit_event(struct perf_event *parent_event, parent_event->cpu, child, group_leader, parent_event, - NULL, NULL); + NULL, NULL, -1); if (IS_ERR(child_event)) return child_event; diff --git a/kernel/events/hw_breakpoint.c b/kernel/events/hw_breakpoint.c index 9803a6600d49..92ce5f4ccc26 100644 --- a/kernel/events/hw_breakpoint.c +++ b/kernel/events/hw_breakpoint.c @@ -116,12 +116,12 @@ static unsigned int max_task_bp_pinned(int cpu, enum bp_type_idx type) */ static int task_bp_pinned(int cpu, struct perf_event *bp, enum bp_type_idx type) { - struct task_struct *tsk = bp->hw.bp_target; + struct task_struct *tsk = bp->hw.target; struct perf_event *iter; int count = 0; list_for_each_entry(iter, &bp_task_head, hw.bp_list) { - if (iter->hw.bp_target == tsk && + if (iter->hw.target == tsk && find_slot_idx(iter) == type && (iter->cpu < 0 || cpu == iter->cpu)) count += hw_breakpoint_weight(iter); @@ -153,7 +153,7 @@ fetch_bp_busy_slots(struct bp_busy_slots *slots, struct perf_event *bp, int nr; nr = info->cpu_pinned; - if (!bp->hw.bp_target) + if (!bp->hw.target) nr += max_task_bp_pinned(cpu, type); else nr += task_bp_pinned(cpu, bp, type); @@ -210,7 +210,7 @@ toggle_bp_slot(struct perf_event *bp, bool enable, enum bp_type_idx type, weight = -weight; /* Pinned counter cpu profiling */ - if (!bp->hw.bp_target) { + if (!bp->hw.target) { get_bp_info(bp->cpu, type)->cpu_pinned += weight; return; } diff --git a/kernel/events/internal.h b/kernel/events/internal.h index 569b218782ad..9f6ce9ba4a04 100644 --- a/kernel/events/internal.h +++ b/kernel/events/internal.h @@ -27,6 +27,7 @@ struct ring_buffer { local_t lost; /* nr records lost */ long watermark; /* wakeup watermark */ + long aux_watermark; /* poll crap */ spinlock_t event_lock; struct list_head event_list; @@ -35,6 +36,20 @@ struct ring_buffer { unsigned long mmap_locked; struct user_struct *mmap_user; + /* AUX area */ + local_t aux_head; + local_t aux_nest; + local_t aux_wakeup; + unsigned long aux_pgoff; + int aux_nr_pages; + int aux_overwrite; + atomic_t aux_mmap_count; + unsigned long aux_mmap_locked; + void (*free_aux)(void *); + atomic_t aux_refcount; + void **aux_pages; + void *aux_priv; + struct perf_event_mmap_page *user_page; void *data_pages[0]; }; @@ -43,6 +58,19 @@ extern void rb_free(struct ring_buffer *rb); extern struct ring_buffer * rb_alloc(int nr_pages, long watermark, int cpu, int flags); extern void perf_event_wakeup(struct perf_event *event); +extern int rb_alloc_aux(struct ring_buffer *rb, struct perf_event *event, + pgoff_t pgoff, int nr_pages, long watermark, int flags); +extern void rb_free_aux(struct ring_buffer *rb); +extern struct ring_buffer *ring_buffer_get(struct perf_event *event); +extern void ring_buffer_put(struct ring_buffer *rb); + +static inline bool rb_has_aux(struct ring_buffer *rb) +{ + return !!rb->aux_nr_pages; +} + +void perf_event_aux_event(struct perf_event *event, unsigned long head, + unsigned long size, u64 flags); extern void perf_event_header__init_id(struct perf_event_header *header, @@ -81,6 +109,11 @@ static inline unsigned long perf_data_size(struct ring_buffer *rb) return rb->nr_pages << (PAGE_SHIFT + page_order(rb)); } +static inline unsigned long perf_aux_size(struct ring_buffer *rb) +{ + return rb->aux_nr_pages << PAGE_SHIFT; +} + #define DEFINE_OUTPUT_COPY(func_name, memcpy_func) \ static inline unsigned long \ func_name(struct perf_output_handle *handle, \ diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c index eadb95ce7aac..232f00f273cb 100644 --- a/kernel/events/ring_buffer.c +++ b/kernel/events/ring_buffer.c @@ -243,14 +243,317 @@ ring_buffer_init(struct ring_buffer *rb, long watermark, int flags) spin_lock_init(&rb->event_lock); } +/* + * This is called before hardware starts writing to the AUX area to + * obtain an output handle and make sure there's room in the buffer. + * When the capture completes, call perf_aux_output_end() to commit + * the recorded data to the buffer. + * + * The ordering is similar to that of perf_output_{begin,end}, with + * the exception of (B), which should be taken care of by the pmu + * driver, since ordering rules will differ depending on hardware. + */ +void *perf_aux_output_begin(struct perf_output_handle *handle, + struct perf_event *event) +{ + struct perf_event *output_event = event; + unsigned long aux_head, aux_tail; + struct ring_buffer *rb; + + if (output_event->parent) + output_event = output_event->parent; + + /* + * Since this will typically be open across pmu::add/pmu::del, we + * grab ring_buffer's refcount instead of holding rcu read lock + * to make sure it doesn't disappear under us. + */ + rb = ring_buffer_get(output_event); + if (!rb) + return NULL; + + if (!rb_has_aux(rb) || !atomic_inc_not_zero(&rb->aux_refcount)) + goto err; + + /* + * Nesting is not supported for AUX area, make sure nested + * writers are caught early + */ + if (WARN_ON_ONCE(local_xchg(&rb->aux_nest, 1))) + goto err_put; + + aux_head = local_read(&rb->aux_head); + + handle->rb = rb; + handle->event = event; + handle->head = aux_head; + handle->size = 0; + + /* + * In overwrite mode, AUX data stores do not depend on aux_tail, + * therefore (A) control dependency barrier does not exist. The + * (B) <-> (C) ordering is still observed by the pmu driver. + */ + if (!rb->aux_overwrite) { + aux_tail = ACCESS_ONCE(rb->user_page->aux_tail); + handle->wakeup = local_read(&rb->aux_wakeup) + rb->aux_watermark; + if (aux_head - aux_tail < perf_aux_size(rb)) + handle->size = CIRC_SPACE(aux_head, aux_tail, perf_aux_size(rb)); + + /* + * handle->size computation depends on aux_tail load; this forms a + * control dependency barrier separating aux_tail load from aux data + * store that will be enabled on successful return + */ + if (!handle->size) { /* A, matches D */ + event->pending_disable = 1; + perf_output_wakeup(handle); + local_set(&rb->aux_nest, 0); + goto err_put; + } + } + + return handle->rb->aux_priv; + +err_put: + rb_free_aux(rb); + +err: + ring_buffer_put(rb); + handle->event = NULL; + + return NULL; +} + +/* + * Commit the data written by hardware into the ring buffer by adjusting + * aux_head and posting a PERF_RECORD_AUX into the perf buffer. It is the + * pmu driver's responsibility to observe ordering rules of the hardware, + * so that all the data is externally visible before this is called. + */ +void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size, + bool truncated) +{ + struct ring_buffer *rb = handle->rb; + unsigned long aux_head; + u64 flags = 0; + + if (truncated) + flags |= PERF_AUX_FLAG_TRUNCATED; + + /* in overwrite mode, driver provides aux_head via handle */ + if (rb->aux_overwrite) { + flags |= PERF_AUX_FLAG_OVERWRITE; + + aux_head = handle->head; + local_set(&rb->aux_head, aux_head); + } else { + aux_head = local_read(&rb->aux_head); + local_add(size, &rb->aux_head); + } + + if (size || flags) { + /* + * Only send RECORD_AUX if we have something useful to communicate + */ + + perf_event_aux_event(handle->event, aux_head, size, flags); + } + + aux_head = rb->user_page->aux_head = local_read(&rb->aux_head); + + if (aux_head - local_read(&rb->aux_wakeup) >= rb->aux_watermark) { + perf_output_wakeup(handle); + local_add(rb->aux_watermark, &rb->aux_wakeup); + } + handle->event = NULL; + + local_set(&rb->aux_nest, 0); + rb_free_aux(rb); + ring_buffer_put(rb); +} + +/* + * Skip over a given number of bytes in the AUX buffer, due to, for example, + * hardware's alignment constraints. + */ +int perf_aux_output_skip(struct perf_output_handle *handle, unsigned long size) +{ + struct ring_buffer *rb = handle->rb; + unsigned long aux_head; + + if (size > handle->size) + return -ENOSPC; + + local_add(size, &rb->aux_head); + + aux_head = rb->user_page->aux_head = local_read(&rb->aux_head); + if (aux_head - local_read(&rb->aux_wakeup) >= rb->aux_watermark) { + perf_output_wakeup(handle); + local_add(rb->aux_watermark, &rb->aux_wakeup); + handle->wakeup = local_read(&rb->aux_wakeup) + + rb->aux_watermark; + } + + handle->head = aux_head; + handle->size -= size; + + return 0; +} + +void *perf_get_aux(struct perf_output_handle *handle) +{ + /* this is only valid between perf_aux_output_begin and *_end */ + if (!handle->event) + return NULL; + + return handle->rb->aux_priv; +} + +#define PERF_AUX_GFP (GFP_KERNEL | __GFP_ZERO | __GFP_NOWARN | __GFP_NORETRY) + +static struct page *rb_alloc_aux_page(int node, int order) +{ + struct page *page; + + if (order > MAX_ORDER) + order = MAX_ORDER; + + do { + page = alloc_pages_node(node, PERF_AUX_GFP, order); + } while (!page && order--); + + if (page && order) { + /* + * Communicate the allocation size to the driver + */ + split_page(page, order); + SetPagePrivate(page); + set_page_private(page, order); + } + + return page; +} + +static void rb_free_aux_page(struct ring_buffer *rb, int idx) +{ + struct page *page = virt_to_page(rb->aux_pages[idx]); + + ClearPagePrivate(page); + page->mapping = NULL; + __free_page(page); +} + +int rb_alloc_aux(struct ring_buffer *rb, struct perf_event *event, + pgoff_t pgoff, int nr_pages, long watermark, int flags) +{ + bool overwrite = !(flags & RING_BUFFER_WRITABLE); + int node = (event->cpu == -1) ? -1 : cpu_to_node(event->cpu); + int ret = -ENOMEM, max_order = 0; + + if (!has_aux(event)) + return -ENOTSUPP; + + if (event->pmu->capabilities & PERF_PMU_CAP_AUX_NO_SG) { + /* + * We need to start with the max_order that fits in nr_pages, + * not the other way around, hence ilog2() and not get_order. + */ + max_order = ilog2(nr_pages); + + /* + * PMU requests more than one contiguous chunks of memory + * for SW double buffering + */ + if ((event->pmu->capabilities & PERF_PMU_CAP_AUX_SW_DOUBLEBUF) && + !overwrite) { + if (!max_order) + return -EINVAL; + + max_order--; + } + } + + rb->aux_pages = kzalloc_node(nr_pages * sizeof(void *), GFP_KERNEL, node); + if (!rb->aux_pages) + return -ENOMEM; + + rb->free_aux = event->pmu->free_aux; + for (rb->aux_nr_pages = 0; rb->aux_nr_pages < nr_pages;) { + struct page *page; + int last, order; + + order = min(max_order, ilog2(nr_pages - rb->aux_nr_pages)); + page = rb_alloc_aux_page(node, order); + if (!page) + goto out; + + for (last = rb->aux_nr_pages + (1 << page_private(page)); + last > rb->aux_nr_pages; rb->aux_nr_pages++) + rb->aux_pages[rb->aux_nr_pages] = page_address(page++); + } + + rb->aux_priv = event->pmu->setup_aux(event->cpu, rb->aux_pages, nr_pages, + overwrite); + if (!rb->aux_priv) + goto out; + + ret = 0; + + /* + * aux_pages (and pmu driver's private data, aux_priv) will be + * referenced in both producer's and consumer's contexts, thus + * we keep a refcount here to make sure either of the two can + * reference them safely. + */ + atomic_set(&rb->aux_refcount, 1); + + rb->aux_overwrite = overwrite; + rb->aux_watermark = watermark; + + if (!rb->aux_watermark && !rb->aux_overwrite) + rb->aux_watermark = nr_pages << (PAGE_SHIFT - 1); + +out: + if (!ret) + rb->aux_pgoff = pgoff; + else + rb_free_aux(rb); + + return ret; +} + +static void __rb_free_aux(struct ring_buffer *rb) +{ + int pg; + + if (rb->aux_priv) { + rb->free_aux(rb->aux_priv); + rb->free_aux = NULL; + rb->aux_priv = NULL; + } + + for (pg = 0; pg < rb->aux_nr_pages; pg++) + rb_free_aux_page(rb, pg); + + kfree(rb->aux_pages); + rb->aux_nr_pages = 0; +} + +void rb_free_aux(struct ring_buffer *rb) +{ + if (atomic_dec_and_test(&rb->aux_refcount)) + __rb_free_aux(rb); +} + #ifndef CONFIG_PERF_USE_VMALLOC /* * Back perf_mmap() with regular GFP_KERNEL-0 pages. */ -struct page * -perf_mmap_to_page(struct ring_buffer *rb, unsigned long pgoff) +static struct page * +__perf_mmap_to_page(struct ring_buffer *rb, unsigned long pgoff) { if (pgoff > rb->nr_pages) return NULL; @@ -340,8 +643,8 @@ static int data_page_nr(struct ring_buffer *rb) return rb->nr_pages << page_order(rb); } -struct page * -perf_mmap_to_page(struct ring_buffer *rb, unsigned long pgoff) +static struct page * +__perf_mmap_to_page(struct ring_buffer *rb, unsigned long pgoff) { /* The '>' counts in the user page. */ if (pgoff > data_page_nr(rb)) @@ -416,3 +719,19 @@ fail: } #endif + +struct page * +perf_mmap_to_page(struct ring_buffer *rb, unsigned long pgoff) +{ + if (rb->aux_nr_pages) { + /* above AUX space */ + if (pgoff > rb->aux_pgoff + rb->aux_nr_pages) + return NULL; + + /* AUX space */ + if (pgoff >= rb->aux_pgoff) + return virt_to_page(rb->aux_pages[pgoff - rb->aux_pgoff]); + } + + return __perf_mmap_to_page(rb, pgoff); +} diff --git a/kernel/futex.c b/kernel/futex.c index 2a5e3830e953..2579e407ff67 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -900,7 +900,7 @@ static int attach_to_pi_owner(u32 uval, union futex_key *key, if (!p) return -ESRCH; - if (!p->mm) { + if (unlikely(p->flags & PF_KTHREAD)) { put_task_struct(p); return -EPERM; } diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index 6f1c7a566b95..eb9a4ea394ab 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -948,6 +948,22 @@ int irq_chip_retrigger_hierarchy(struct irq_data *data) return -ENOSYS; } + +/** + * irq_chip_set_wake_parent - Set/reset wake-up on the parent interrupt + * @data: Pointer to interrupt specific data + * @on: Whether to set or reset the wake-up capability of this irq + * + * Conditional, as the underlying parent chip might not implement it. + */ +int irq_chip_set_wake_parent(struct irq_data *data, unsigned int on) +{ + data = data->parent_data; + if (data->chip->irq_set_wake) + return data->chip->irq_set_wake(data, on); + + return -ENOSYS; +} #endif /** diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 886d09e691d5..e68932bb308e 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -68,14 +68,20 @@ static void __synchronize_hardirq(struct irq_desc *desc) * Do not use this for shutdown scenarios where you must be sure * that all parts (hardirq and threaded handler) have completed. * + * Returns: false if a threaded handler is active. + * * This function may be called - with care - from IRQ context. */ -void synchronize_hardirq(unsigned int irq) +bool synchronize_hardirq(unsigned int irq) { struct irq_desc *desc = irq_to_desc(irq); - if (desc) + if (desc) { __synchronize_hardirq(desc); + return !atomic_read(&desc->threads_active); + } + + return true; } EXPORT_SYMBOL(synchronize_hardirq); @@ -440,6 +446,32 @@ void disable_irq(unsigned int irq) } EXPORT_SYMBOL(disable_irq); +/** + * disable_hardirq - disables an irq and waits for hardirq completion + * @irq: Interrupt to disable + * + * Disable the selected interrupt line. Enables and Disables are + * nested. + * This function waits for any pending hard IRQ handlers for this + * interrupt to complete before returning. If you use this function while + * holding a resource the hard IRQ handler may need you will deadlock. + * + * When used to optimistically disable an interrupt from atomic context + * the return value must be checked. + * + * Returns: false if a threaded handler is active. + * + * This function may be called - with care - from IRQ context. + */ +bool disable_hardirq(unsigned int irq) +{ + if (!__disable_irq_nosync(irq)) + return synchronize_hardirq(irq); + + return false; +} +EXPORT_SYMBOL_GPL(disable_hardirq); + void __enable_irq(struct irq_desc *desc, unsigned int irq) { switch (desc->depth) { @@ -1766,3 +1798,94 @@ int request_percpu_irq(unsigned int irq, irq_handler_t handler, return retval; } + +/** + * irq_get_irqchip_state - returns the irqchip state of a interrupt. + * @irq: Interrupt line that is forwarded to a VM + * @which: One of IRQCHIP_STATE_* the caller wants to know about + * @state: a pointer to a boolean where the state is to be storeed + * + * This call snapshots the internal irqchip state of an + * interrupt, returning into @state the bit corresponding to + * stage @which + * + * This function should be called with preemption disabled if the + * interrupt controller has per-cpu registers. + */ +int irq_get_irqchip_state(unsigned int irq, enum irqchip_irq_state which, + bool *state) +{ + struct irq_desc *desc; + struct irq_data *data; + struct irq_chip *chip; + unsigned long flags; + int err = -EINVAL; + + desc = irq_get_desc_buslock(irq, &flags, 0); + if (!desc) + return err; + + data = irq_desc_get_irq_data(desc); + + do { + chip = irq_data_get_irq_chip(data); + if (chip->irq_get_irqchip_state) + break; +#ifdef CONFIG_IRQ_DOMAIN_HIERARCHY + data = data->parent_data; +#else + data = NULL; +#endif + } while (data); + + if (data) + err = chip->irq_get_irqchip_state(data, which, state); + + irq_put_desc_busunlock(desc, flags); + return err; +} + +/** + * irq_set_irqchip_state - set the state of a forwarded interrupt. + * @irq: Interrupt line that is forwarded to a VM + * @which: State to be restored (one of IRQCHIP_STATE_*) + * @val: Value corresponding to @which + * + * This call sets the internal irqchip state of an interrupt, + * depending on the value of @which. + * + * This function should be called with preemption disabled if the + * interrupt controller has per-cpu registers. + */ +int irq_set_irqchip_state(unsigned int irq, enum irqchip_irq_state which, + bool val) +{ + struct irq_desc *desc; + struct irq_data *data; + struct irq_chip *chip; + unsigned long flags; + int err = -EINVAL; + + desc = irq_get_desc_buslock(irq, &flags, 0); + if (!desc) + return err; + + data = irq_desc_get_irq_data(desc); + + do { + chip = irq_data_get_irq_chip(data); + if (chip->irq_set_irqchip_state) + break; +#ifdef CONFIG_IRQ_DOMAIN_HIERARCHY + data = data->parent_data; +#else + data = NULL; +#endif + } while (data); + + if (data) + err = chip->irq_set_irqchip_state(data, which, val); + + irq_put_desc_busunlock(desc, flags); + return err; +} diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c index 3e18163f336f..474de5cb394d 100644 --- a/kernel/irq/msi.c +++ b/kernel/irq/msi.c @@ -310,8 +310,15 @@ void msi_domain_free_irqs(struct irq_domain *domain, struct device *dev) struct msi_desc *desc; for_each_msi_entry(desc, dev) { - irq_domain_free_irqs(desc->irq, desc->nvec_used); - desc->irq = 0; + /* + * We might have failed to allocate an MSI early + * enough that there is no IRQ associated to this + * entry. If that's the case, don't do anything. + */ + if (desc->irq) { + irq_domain_free_irqs(desc->irq, desc->nvec_used); + desc->irq = 0; + } } } diff --git a/kernel/livepatch/core.c b/kernel/livepatch/core.c index 01ca08804f51..284e2691e380 100644 --- a/kernel/livepatch/core.c +++ b/kernel/livepatch/core.c @@ -89,16 +89,28 @@ static bool klp_is_object_loaded(struct klp_object *obj) /* sets obj->mod if object is not vmlinux and module is found */ static void klp_find_object_module(struct klp_object *obj) { + struct module *mod; + if (!klp_is_module(obj)) return; mutex_lock(&module_mutex); /* - * We don't need to take a reference on the module here because we have - * the klp_mutex, which is also taken by the module notifier. This - * prevents any module from unloading until we release the klp_mutex. + * We do not want to block removal of patched modules and therefore + * we do not take a reference here. The patches are removed by + * a going module handler instead. + */ + mod = find_module(obj->name); + /* + * Do not mess work of the module coming and going notifiers. + * Note that the patch might still be needed before the going handler + * is called. Module functions can be called even in the GOING state + * until mod->exit() finishes. This is especially important for + * patches that modify semantic of the functions. */ - obj->mod = find_module(obj->name); + if (mod && mod->klp_alive) + obj->mod = mod; + mutex_unlock(&module_mutex); } @@ -323,32 +335,20 @@ unlock: rcu_read_unlock(); } -static int klp_disable_func(struct klp_func *func) +static void klp_disable_func(struct klp_func *func) { struct klp_ops *ops; - int ret; - if (WARN_ON(func->state != KLP_ENABLED)) - return -EINVAL; - - if (WARN_ON(!func->old_addr)) - return -EINVAL; + WARN_ON(func->state != KLP_ENABLED); + WARN_ON(!func->old_addr); ops = klp_find_ops(func->old_addr); if (WARN_ON(!ops)) - return -EINVAL; + return; if (list_is_singular(&ops->func_stack)) { - ret = unregister_ftrace_function(&ops->fops); - if (ret) { - pr_err("failed to unregister ftrace handler for function '%s' (%d)\n", - func->old_name, ret); - return ret; - } - - ret = ftrace_set_filter_ip(&ops->fops, func->old_addr, 1, 0); - if (ret) - pr_warn("function unregister succeeded but failed to clear the filter\n"); + WARN_ON(unregister_ftrace_function(&ops->fops)); + WARN_ON(ftrace_set_filter_ip(&ops->fops, func->old_addr, 1, 0)); list_del_rcu(&func->stack_node); list_del(&ops->node); @@ -358,8 +358,6 @@ static int klp_disable_func(struct klp_func *func) } func->state = KLP_DISABLED; - - return 0; } static int klp_enable_func(struct klp_func *func) @@ -420,23 +418,15 @@ err: return ret; } -static int klp_disable_object(struct klp_object *obj) +static void klp_disable_object(struct klp_object *obj) { struct klp_func *func; - int ret; - - for (func = obj->funcs; func->old_name; func++) { - if (func->state != KLP_ENABLED) - continue; - ret = klp_disable_func(func); - if (ret) - return ret; - } + for (func = obj->funcs; func->old_name; func++) + if (func->state == KLP_ENABLED) + klp_disable_func(func); obj->state = KLP_DISABLED; - - return 0; } static int klp_enable_object(struct klp_object *obj) @@ -452,22 +442,19 @@ static int klp_enable_object(struct klp_object *obj) for (func = obj->funcs; func->old_name; func++) { ret = klp_enable_func(func); - if (ret) - goto unregister; + if (ret) { + klp_disable_object(obj); + return ret; + } } obj->state = KLP_ENABLED; return 0; - -unregister: - WARN_ON(klp_disable_object(obj)); - return ret; } static int __klp_disable_patch(struct klp_patch *patch) { struct klp_object *obj; - int ret; /* enforce stacking: only the last enabled patch can be disabled */ if (!list_is_last(&patch->list, &klp_patches) && @@ -477,12 +464,8 @@ static int __klp_disable_patch(struct klp_patch *patch) pr_notice("disabling patch '%s'\n", patch->mod->name); for (obj = patch->objs; obj->funcs; obj++) { - if (obj->state != KLP_ENABLED) - continue; - - ret = klp_disable_object(obj); - if (ret) - return ret; + if (obj->state == KLP_ENABLED) + klp_disable_object(obj); } patch->state = KLP_DISABLED; @@ -541,8 +524,6 @@ static int __klp_enable_patch(struct klp_patch *patch) pr_notice("enabling patch '%s'\n", patch->mod->name); for (obj = patch->objs; obj->funcs; obj++) { - klp_find_object_module(obj); - if (!klp_is_object_loaded(obj)) continue; @@ -767,6 +748,7 @@ static int klp_init_object(struct klp_patch *patch, struct klp_object *obj) return -EINVAL; obj->state = KLP_DISABLED; + obj->mod = NULL; klp_find_object_module(obj); @@ -932,7 +914,6 @@ static void klp_module_notify_going(struct klp_patch *patch, { struct module *pmod = patch->mod; struct module *mod = obj->mod; - int ret; if (patch->state == KLP_DISABLED) goto disabled; @@ -940,10 +921,7 @@ static void klp_module_notify_going(struct klp_patch *patch, pr_notice("reverting patch '%s' on unloading module '%s'\n", pmod->name, mod->name); - ret = klp_disable_object(obj); - if (ret) - pr_warn("failed to revert patch '%s' on module '%s' (%d)\n", - pmod->name, mod->name, ret); + klp_disable_object(obj); disabled: klp_free_object_loaded(obj); @@ -961,6 +939,15 @@ static int klp_module_notify(struct notifier_block *nb, unsigned long action, mutex_lock(&klp_mutex); + /* + * Each module has to know that the notifier has been called. + * We never know what module will get patched by a new patch. + */ + if (action == MODULE_STATE_COMING) + mod->klp_alive = true; + else /* MODULE_STATE_GOING */ + mod->klp_alive = false; + list_for_each_entry(patch, &klp_patches, list) { for (obj = patch->objs; obj->funcs; obj++) { if (!klp_is_module(obj) || strcmp(obj->name, mod->name)) diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index 88d0d4420ad2..ba77ab5f64dd 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -633,7 +633,7 @@ static int count_matching_names(struct lock_class *new_class) if (!new_class->name) return 0; - list_for_each_entry(class, &all_lock_classes, lock_entry) { + list_for_each_entry_rcu(class, &all_lock_classes, lock_entry) { if (new_class->key - new_class->subclass == class->key) return class->name_version; if (class->name && !strcmp(class->name, new_class->name)) @@ -700,10 +700,12 @@ look_up_lock_class(struct lockdep_map *lock, unsigned int subclass) hash_head = classhashentry(key); /* - * We can walk the hash lockfree, because the hash only - * grows, and we are careful when adding entries to the end: + * We do an RCU walk of the hash, see lockdep_free_key_range(). */ - list_for_each_entry(class, hash_head, hash_entry) { + if (DEBUG_LOCKS_WARN_ON(!irqs_disabled())) + return NULL; + + list_for_each_entry_rcu(class, hash_head, hash_entry) { if (class->key == key) { /* * Huh! same key, different name? Did someone trample @@ -728,7 +730,8 @@ register_lock_class(struct lockdep_map *lock, unsigned int subclass, int force) struct lockdep_subclass_key *key; struct list_head *hash_head; struct lock_class *class; - unsigned long flags; + + DEBUG_LOCKS_WARN_ON(!irqs_disabled()); class = look_up_lock_class(lock, subclass); if (likely(class)) @@ -750,28 +753,26 @@ register_lock_class(struct lockdep_map *lock, unsigned int subclass, int force) key = lock->key->subkeys + subclass; hash_head = classhashentry(key); - raw_local_irq_save(flags); if (!graph_lock()) { - raw_local_irq_restore(flags); return NULL; } /* * We have to do the hash-walk again, to avoid races * with another CPU: */ - list_for_each_entry(class, hash_head, hash_entry) + list_for_each_entry_rcu(class, hash_head, hash_entry) { if (class->key == key) goto out_unlock_set; + } + /* * Allocate a new key from the static array, and add it to * the hash: */ if (nr_lock_classes >= MAX_LOCKDEP_KEYS) { if (!debug_locks_off_graph_unlock()) { - raw_local_irq_restore(flags); return NULL; } - raw_local_irq_restore(flags); print_lockdep_off("BUG: MAX_LOCKDEP_KEYS too low!"); dump_stack(); @@ -798,7 +799,6 @@ register_lock_class(struct lockdep_map *lock, unsigned int subclass, int force) if (verbose(class)) { graph_unlock(); - raw_local_irq_restore(flags); printk("\nnew class %p: %s", class->key, class->name); if (class->name_version > 1) @@ -806,15 +806,12 @@ register_lock_class(struct lockdep_map *lock, unsigned int subclass, int force) printk("\n"); dump_stack(); - raw_local_irq_save(flags); if (!graph_lock()) { - raw_local_irq_restore(flags); return NULL; } } out_unlock_set: graph_unlock(); - raw_local_irq_restore(flags); out_set_class_cache: if (!subclass || force) @@ -870,11 +867,9 @@ static int add_lock_to_list(struct lock_class *class, struct lock_class *this, entry->distance = distance; entry->trace = *trace; /* - * Since we never remove from the dependency list, the list can - * be walked lockless by other CPUs, it's only allocation - * that must be protected by the spinlock. But this also means - * we must make new entries visible only once writes to the - * entry become visible - hence the RCU op: + * Both allocation and removal are done under the graph lock; but + * iteration is under RCU-sched; see look_up_lock_class() and + * lockdep_free_key_range(). */ list_add_tail_rcu(&entry->entry, head); @@ -1025,7 +1020,9 @@ static int __bfs(struct lock_list *source_entry, else head = &lock->class->locks_before; - list_for_each_entry(entry, head, entry) { + DEBUG_LOCKS_WARN_ON(!irqs_disabled()); + + list_for_each_entry_rcu(entry, head, entry) { if (!lock_accessed(entry)) { unsigned int cq_depth; mark_lock_accessed(entry, lock); @@ -2022,7 +2019,7 @@ static inline int lookup_chain_cache(struct task_struct *curr, * We can walk it lock-free, because entries only get added * to the hash: */ - list_for_each_entry(chain, hash_head, entry) { + list_for_each_entry_rcu(chain, hash_head, entry) { if (chain->chain_key == chain_key) { cache_hit: debug_atomic_inc(chain_lookup_hits); @@ -2996,8 +2993,18 @@ void lockdep_init_map(struct lockdep_map *lock, const char *name, if (unlikely(!debug_locks)) return; - if (subclass) + if (subclass) { + unsigned long flags; + + if (DEBUG_LOCKS_WARN_ON(current->lockdep_recursion)) + return; + + raw_local_irq_save(flags); + current->lockdep_recursion = 1; register_lock_class(lock, subclass, 1); + current->lockdep_recursion = 0; + raw_local_irq_restore(flags); + } } EXPORT_SYMBOL_GPL(lockdep_init_map); @@ -3887,9 +3894,17 @@ static inline int within(const void *addr, void *start, unsigned long size) return addr >= start && addr < start + size; } +/* + * Used in module.c to remove lock classes from memory that is going to be + * freed; and possibly re-used by other modules. + * + * We will have had one sync_sched() before getting here, so we're guaranteed + * nobody will look up these exact classes -- they're properly dead but still + * allocated. + */ void lockdep_free_key_range(void *start, unsigned long size) { - struct lock_class *class, *next; + struct lock_class *class; struct list_head *head; unsigned long flags; int i; @@ -3905,7 +3920,7 @@ void lockdep_free_key_range(void *start, unsigned long size) head = classhash_table + i; if (list_empty(head)) continue; - list_for_each_entry_safe(class, next, head, hash_entry) { + list_for_each_entry_rcu(class, head, hash_entry) { if (within(class->key, start, size)) zap_class(class); else if (within(class->name, start, size)) @@ -3916,11 +3931,25 @@ void lockdep_free_key_range(void *start, unsigned long size) if (locked) graph_unlock(); raw_local_irq_restore(flags); + + /* + * Wait for any possible iterators from look_up_lock_class() to pass + * before continuing to free the memory they refer to. + * + * sync_sched() is sufficient because the read-side is IRQ disable. + */ + synchronize_sched(); + + /* + * XXX at this point we could return the resources to the pool; + * instead we leak them. We would need to change to bitmap allocators + * instead of the linear allocators we have now. + */ } void lockdep_reset_lock(struct lockdep_map *lock) { - struct lock_class *class, *next; + struct lock_class *class; struct list_head *head; unsigned long flags; int i, j; @@ -3948,7 +3977,7 @@ void lockdep_reset_lock(struct lockdep_map *lock) head = classhash_table + i; if (list_empty(head)) continue; - list_for_each_entry_safe(class, next, head, hash_entry) { + list_for_each_entry_rcu(class, head, hash_entry) { int match = 0; for (j = 0; j < NR_LOCKDEP_CACHING_CLASSES; j++) diff --git a/kernel/locking/mcs_spinlock.h b/kernel/locking/mcs_spinlock.h index d1fe2ba5bac9..75e114bdf3f2 100644 --- a/kernel/locking/mcs_spinlock.h +++ b/kernel/locking/mcs_spinlock.h @@ -78,7 +78,7 @@ void mcs_spin_lock(struct mcs_spinlock **lock, struct mcs_spinlock *node) */ return; } - ACCESS_ONCE(prev->next) = node; + WRITE_ONCE(prev->next, node); /* Wait until the lock holder passes the lock down. */ arch_mcs_spin_lock_contended(&node->locked); @@ -91,7 +91,7 @@ void mcs_spin_lock(struct mcs_spinlock **lock, struct mcs_spinlock *node) static inline void mcs_spin_unlock(struct mcs_spinlock **lock, struct mcs_spinlock *node) { - struct mcs_spinlock *next = ACCESS_ONCE(node->next); + struct mcs_spinlock *next = READ_ONCE(node->next); if (likely(!next)) { /* @@ -100,7 +100,7 @@ void mcs_spin_unlock(struct mcs_spinlock **lock, struct mcs_spinlock *node) if (likely(cmpxchg(lock, node, NULL) == node)) return; /* Wait until the next pointer is set */ - while (!(next = ACCESS_ONCE(node->next))) + while (!(next = READ_ONCE(node->next))) cpu_relax_lowlatency(); } diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c index 94674e5919cb..4cccea6b8934 100644 --- a/kernel/locking/mutex.c +++ b/kernel/locking/mutex.c @@ -25,7 +25,7 @@ #include <linux/spinlock.h> #include <linux/interrupt.h> #include <linux/debug_locks.h> -#include "mcs_spinlock.h" +#include <linux/osq_lock.h> /* * In the DEBUG case we are using the "NULL fastpath" for mutexes, @@ -217,44 +217,35 @@ ww_mutex_set_context_slowpath(struct ww_mutex *lock, } #ifdef CONFIG_MUTEX_SPIN_ON_OWNER -static inline bool owner_running(struct mutex *lock, struct task_struct *owner) -{ - if (lock->owner != owner) - return false; - - /* - * Ensure we emit the owner->on_cpu, dereference _after_ checking - * lock->owner still matches owner, if that fails, owner might - * point to free()d memory, if it still matches, the rcu_read_lock() - * ensures the memory stays valid. - */ - barrier(); - - return owner->on_cpu; -} - /* * Look out! "owner" is an entirely speculative pointer * access and not reliable. */ static noinline -int mutex_spin_on_owner(struct mutex *lock, struct task_struct *owner) +bool mutex_spin_on_owner(struct mutex *lock, struct task_struct *owner) { + bool ret = true; + rcu_read_lock(); - while (owner_running(lock, owner)) { - if (need_resched()) + while (lock->owner == owner) { + /* + * Ensure we emit the owner->on_cpu, dereference _after_ + * checking lock->owner still matches owner. If that fails, + * owner might point to freed memory. If it still matches, + * the rcu_read_lock() ensures the memory stays valid. + */ + barrier(); + + if (!owner->on_cpu || need_resched()) { + ret = false; break; + } cpu_relax_lowlatency(); } rcu_read_unlock(); - /* - * We break out the loop above on need_resched() and when the - * owner changed, which is a sign for heavy contention. Return - * success only when lock->owner is NULL. - */ - return lock->owner == NULL; + return ret; } /* @@ -269,7 +260,7 @@ static inline int mutex_can_spin_on_owner(struct mutex *lock) return 0; rcu_read_lock(); - owner = ACCESS_ONCE(lock->owner); + owner = READ_ONCE(lock->owner); if (owner) retval = owner->on_cpu; rcu_read_unlock(); @@ -343,7 +334,7 @@ static bool mutex_optimistic_spin(struct mutex *lock, * As such, when deadlock detection needs to be * performed the optimistic spinning cannot be done. */ - if (ACCESS_ONCE(ww->ctx)) + if (READ_ONCE(ww->ctx)) break; } @@ -351,7 +342,7 @@ static bool mutex_optimistic_spin(struct mutex *lock, * If there's an owner, wait for it to either * release the lock or go to sleep. */ - owner = ACCESS_ONCE(lock->owner); + owner = READ_ONCE(lock->owner); if (owner && !mutex_spin_on_owner(lock, owner)) break; @@ -490,7 +481,7 @@ static inline int __sched __ww_mutex_lock_check_stamp(struct mutex *lock, struct ww_acquire_ctx *ctx) { struct ww_mutex *ww = container_of(lock, struct ww_mutex, base); - struct ww_acquire_ctx *hold_ctx = ACCESS_ONCE(ww->ctx); + struct ww_acquire_ctx *hold_ctx = READ_ONCE(ww->ctx); if (!hold_ctx) return 0; diff --git a/kernel/locking/osq_lock.c b/kernel/locking/osq_lock.c index c112d00341b0..dc85ee23a26f 100644 --- a/kernel/locking/osq_lock.c +++ b/kernel/locking/osq_lock.c @@ -98,7 +98,7 @@ bool osq_lock(struct optimistic_spin_queue *lock) prev = decode_cpu(old); node->prev = prev; - ACCESS_ONCE(prev->next) = node; + WRITE_ONCE(prev->next, node); /* * Normally @prev is untouchable after the above store; because at that @@ -109,7 +109,7 @@ bool osq_lock(struct optimistic_spin_queue *lock) * cmpxchg in an attempt to undo our queueing. */ - while (!ACCESS_ONCE(node->locked)) { + while (!READ_ONCE(node->locked)) { /* * If we need to reschedule bail... so we can block. */ @@ -148,7 +148,7 @@ unqueue: * Or we race against a concurrent unqueue()'s step-B, in which * case its step-C will write us a new @node->prev pointer. */ - prev = ACCESS_ONCE(node->prev); + prev = READ_ONCE(node->prev); } /* @@ -170,8 +170,8 @@ unqueue: * it will wait in Step-A. */ - ACCESS_ONCE(next->prev) = prev; - ACCESS_ONCE(prev->next) = next; + WRITE_ONCE(next->prev, prev); + WRITE_ONCE(prev->next, next); return false; } @@ -193,11 +193,11 @@ void osq_unlock(struct optimistic_spin_queue *lock) node = this_cpu_ptr(&osq_node); next = xchg(&node->next, NULL); if (next) { - ACCESS_ONCE(next->locked) = 1; + WRITE_ONCE(next->locked, 1); return; } next = osq_wait_next(lock, node, NULL); if (next) - ACCESS_ONCE(next->locked) = 1; + WRITE_ONCE(next->locked, 1); } diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c index 6357265a31ad..b73279367087 100644 --- a/kernel/locking/rtmutex.c +++ b/kernel/locking/rtmutex.c @@ -349,7 +349,7 @@ static inline struct rt_mutex *task_blocked_on_lock(struct task_struct *p) * * @task: the task owning the mutex (owner) for which a chain walk is * probably needed - * @deadlock_detect: do we have to carry out deadlock detection? + * @chwalk: do we have to carry out deadlock detection? * @orig_lock: the mutex (can be NULL if we are walking the chain to recheck * things for a task that has just got its priority adjusted, and * is waiting on a mutex) diff --git a/kernel/locking/rwsem-spinlock.c b/kernel/locking/rwsem-spinlock.c index 2555ae15ec14..3a5048572065 100644 --- a/kernel/locking/rwsem-spinlock.c +++ b/kernel/locking/rwsem-spinlock.c @@ -85,6 +85,13 @@ __rwsem_do_wake(struct rw_semaphore *sem, int wakewrite) list_del(&waiter->list); tsk = waiter->task; + /* + * Make sure we do not wakeup the next reader before + * setting the nil condition to grant the next reader; + * otherwise we could miss the wakeup on the other + * side and end up sleeping again. See the pairing + * in rwsem_down_read_failed(). + */ smp_mb(); waiter->task = NULL; wake_up_process(tsk); diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c index 2f7cc4076f50..3417d0172a5d 100644 --- a/kernel/locking/rwsem-xadd.c +++ b/kernel/locking/rwsem-xadd.c @@ -14,8 +14,9 @@ #include <linux/init.h> #include <linux/export.h> #include <linux/sched/rt.h> +#include <linux/osq_lock.h> -#include "mcs_spinlock.h" +#include "rwsem.h" /* * Guide to the rw_semaphore's count field for common values. @@ -186,6 +187,13 @@ __rwsem_do_wake(struct rw_semaphore *sem, enum rwsem_wake_type wake_type) waiter = list_entry(next, struct rwsem_waiter, list); next = waiter->list.next; tsk = waiter->task; + /* + * Make sure we do not wakeup the next reader before + * setting the nil condition to grant the next reader; + * otherwise we could miss the wakeup on the other + * side and end up sleeping again. See the pairing + * in rwsem_down_read_failed(). + */ smp_mb(); waiter->task = NULL; wake_up_process(tsk); @@ -258,6 +266,7 @@ static inline bool rwsem_try_write_lock(long count, struct rw_semaphore *sem) RWSEM_ACTIVE_WRITE_BIAS) == RWSEM_WAITING_BIAS) { if (!list_is_singular(&sem->wait_list)) rwsem_atomic_update(RWSEM_WAITING_BIAS, sem); + rwsem_set_owner(sem); return true; } @@ -270,15 +279,17 @@ static inline bool rwsem_try_write_lock(long count, struct rw_semaphore *sem) */ static inline bool rwsem_try_write_lock_unqueued(struct rw_semaphore *sem) { - long old, count = ACCESS_ONCE(sem->count); + long old, count = READ_ONCE(sem->count); while (true) { if (!(count == 0 || count == RWSEM_WAITING_BIAS)) return false; old = cmpxchg(&sem->count, count, count + RWSEM_ACTIVE_WRITE_BIAS); - if (old == count) + if (old == count) { + rwsem_set_owner(sem); return true; + } count = old; } @@ -287,60 +298,67 @@ static inline bool rwsem_try_write_lock_unqueued(struct rw_semaphore *sem) static inline bool rwsem_can_spin_on_owner(struct rw_semaphore *sem) { struct task_struct *owner; - bool on_cpu = false; + bool ret = true; if (need_resched()) return false; rcu_read_lock(); - owner = ACCESS_ONCE(sem->owner); - if (owner) - on_cpu = owner->on_cpu; - rcu_read_unlock(); - - /* - * If sem->owner is not set, yet we have just recently entered the - * slowpath, then there is a possibility reader(s) may have the lock. - * To be safe, avoid spinning in these situations. - */ - return on_cpu; -} - -static inline bool owner_running(struct rw_semaphore *sem, - struct task_struct *owner) -{ - if (sem->owner != owner) - return false; - - /* - * Ensure we emit the owner->on_cpu, dereference _after_ checking - * sem->owner still matches owner, if that fails, owner might - * point to free()d memory, if it still matches, the rcu_read_lock() - * ensures the memory stays valid. - */ - barrier(); + owner = READ_ONCE(sem->owner); + if (!owner) { + long count = READ_ONCE(sem->count); + /* + * If sem->owner is not set, yet we have just recently entered the + * slowpath with the lock being active, then there is a possibility + * reader(s) may have the lock. To be safe, bail spinning in these + * situations. + */ + if (count & RWSEM_ACTIVE_MASK) + ret = false; + goto done; + } - return owner->on_cpu; + ret = owner->on_cpu; +done: + rcu_read_unlock(); + return ret; } static noinline bool rwsem_spin_on_owner(struct rw_semaphore *sem, struct task_struct *owner) { + long count; + rcu_read_lock(); - while (owner_running(sem, owner)) { - if (need_resched()) - break; + while (sem->owner == owner) { + /* + * Ensure we emit the owner->on_cpu, dereference _after_ + * checking sem->owner still matches owner, if that fails, + * owner might point to free()d memory, if it still matches, + * the rcu_read_lock() ensures the memory stays valid. + */ + barrier(); + + /* abort spinning when need_resched or owner is not running */ + if (!owner->on_cpu || need_resched()) { + rcu_read_unlock(); + return false; + } cpu_relax_lowlatency(); } rcu_read_unlock(); + if (READ_ONCE(sem->owner)) + return true; /* new owner, continue spinning */ + /* - * We break out the loop above on need_resched() or when the - * owner changed, which is a sign for heavy contention. Return - * success only when sem->owner is NULL. + * When the owner is not set, the lock could be free or + * held by readers. Check the counter to verify the + * state. */ - return sem->owner == NULL; + count = READ_ONCE(sem->count); + return (count == 0 || count == RWSEM_WAITING_BIAS); } static bool rwsem_optimistic_spin(struct rw_semaphore *sem) @@ -358,7 +376,7 @@ static bool rwsem_optimistic_spin(struct rw_semaphore *sem) goto done; while (true) { - owner = ACCESS_ONCE(sem->owner); + owner = READ_ONCE(sem->owner); if (owner && !rwsem_spin_on_owner(sem, owner)) break; @@ -432,7 +450,7 @@ struct rw_semaphore __sched *rwsem_down_write_failed(struct rw_semaphore *sem) /* we're now waiting on the lock, but no longer actively locking */ if (waiting) { - count = ACCESS_ONCE(sem->count); + count = READ_ONCE(sem->count); /* * If there were already threads queued before us and there are diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c index e2d3bc7f03b4..205be0ce34de 100644 --- a/kernel/locking/rwsem.c +++ b/kernel/locking/rwsem.c @@ -9,29 +9,9 @@ #include <linux/sched.h> #include <linux/export.h> #include <linux/rwsem.h> - #include <linux/atomic.h> -#ifdef CONFIG_RWSEM_SPIN_ON_OWNER -static inline void rwsem_set_owner(struct rw_semaphore *sem) -{ - sem->owner = current; -} - -static inline void rwsem_clear_owner(struct rw_semaphore *sem) -{ - sem->owner = NULL; -} - -#else -static inline void rwsem_set_owner(struct rw_semaphore *sem) -{ -} - -static inline void rwsem_clear_owner(struct rw_semaphore *sem) -{ -} -#endif +#include "rwsem.h" /* * lock for reading diff --git a/kernel/locking/rwsem.h b/kernel/locking/rwsem.h new file mode 100644 index 000000000000..870ed9a5b426 --- /dev/null +++ b/kernel/locking/rwsem.h @@ -0,0 +1,20 @@ +#ifdef CONFIG_RWSEM_SPIN_ON_OWNER +static inline void rwsem_set_owner(struct rw_semaphore *sem) +{ + sem->owner = current; +} + +static inline void rwsem_clear_owner(struct rw_semaphore *sem) +{ + sem->owner = NULL; +} + +#else +static inline void rwsem_set_owner(struct rw_semaphore *sem) +{ +} + +static inline void rwsem_clear_owner(struct rw_semaphore *sem) +{ +} +#endif diff --git a/kernel/module.c b/kernel/module.c index b3d634ed06c9..650b038ae520 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -1865,7 +1865,7 @@ static void free_module(struct module *mod) kfree(mod->args); percpu_modfree(mod); - /* Free lock-classes: */ + /* Free lock-classes; relies on the preceding sync_rcu(). */ lockdep_free_key_range(mod->module_core, mod->core_size); /* Finally, free the core (containing the module structure) */ @@ -2479,6 +2479,23 @@ static int elf_header_check(struct load_info *info) return 0; } +#define COPY_CHUNK_SIZE (16*PAGE_SIZE) + +static int copy_chunked_from_user(void *dst, const void __user *usrc, unsigned long len) +{ + do { + unsigned long n = min(len, COPY_CHUNK_SIZE); + + if (copy_from_user(dst, usrc, n) != 0) + return -EFAULT; + cond_resched(); + dst += n; + usrc += n; + len -= n; + } while (len); + return 0; +} + /* Sets info->hdr and info->len. */ static int copy_module_from_user(const void __user *umod, unsigned long len, struct load_info *info) @@ -2498,7 +2515,7 @@ static int copy_module_from_user(const void __user *umod, unsigned long len, if (!info->hdr) return -ENOMEM; - if (copy_from_user(info->hdr, umod, info->len) != 0) { + if (copy_chunked_from_user(info->hdr, umod, info->len) != 0) { vfree(info->hdr); return -EFAULT; } @@ -2753,6 +2770,9 @@ static int find_module_sections(struct module *mod, struct load_info *info) mod->trace_events = section_objs(info, "_ftrace_events", sizeof(*mod->trace_events), &mod->num_trace_events); + mod->trace_enums = section_objs(info, "_ftrace_enum_map", + sizeof(*mod->trace_enums), + &mod->num_trace_enums); #endif #ifdef CONFIG_TRACING mod->trace_bprintk_fmt_start = section_objs(info, "__trace_printk_fmt", @@ -3349,9 +3369,6 @@ static int load_module(struct load_info *info, const char __user *uargs, module_bug_cleanup(mod); mutex_unlock(&module_mutex); - /* Free lock-classes: */ - lockdep_free_key_range(mod->module_core, mod->core_size); - /* we can't deallocate the module until we clear memory protection */ unset_module_init_ro_nx(mod); unset_module_core_ro_nx(mod); @@ -3375,6 +3392,9 @@ static int load_module(struct load_info *info, const char __user *uargs, synchronize_rcu(); mutex_unlock(&module_mutex); free_module: + /* Free lock-classes; relies on the preceding sync_rcu() */ + lockdep_free_key_range(mod->module_core, mod->core_size); + module_deallocate(mod, info); free_copy: free_copy(info); diff --git a/kernel/power/main.c b/kernel/power/main.c index 9a59d042ea84..86e8157a450f 100644 --- a/kernel/power/main.c +++ b/kernel/power/main.c @@ -11,7 +11,7 @@ #include <linux/export.h> #include <linux/kobject.h> #include <linux/string.h> -#include <linux/resume-trace.h> +#include <linux/pm-trace.h> #include <linux/workqueue.h> #include <linux/debugfs.h> #include <linux/seq_file.h> diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c index c24d5a23bf93..5235dd4e1e2f 100644 --- a/kernel/power/snapshot.c +++ b/kernel/power/snapshot.c @@ -955,25 +955,6 @@ static void mark_nosave_pages(struct memory_bitmap *bm) } } -static bool is_nosave_page(unsigned long pfn) -{ - struct nosave_region *region; - - list_for_each_entry(region, &nosave_regions, list) { - if (pfn >= region->start_pfn && pfn < region->end_pfn) { - pr_err("PM: %#010llx in e820 nosave region: " - "[mem %#010llx-%#010llx]\n", - (unsigned long long) pfn << PAGE_SHIFT, - (unsigned long long) region->start_pfn << PAGE_SHIFT, - ((unsigned long long) region->end_pfn << PAGE_SHIFT) - - 1); - return true; - } - } - - return false; -} - /** * create_basic_memory_bitmaps - create bitmaps needed for marking page * frames that should not be saved and free page frames. The pointers @@ -2042,7 +2023,7 @@ static int mark_unsafe_pages(struct memory_bitmap *bm) do { pfn = memory_bm_next_pfn(bm); if (likely(pfn != BM_END_OF_MAP)) { - if (likely(pfn_valid(pfn)) && !is_nosave_page(pfn)) + if (likely(pfn_valid(pfn))) swsusp_set_page_free(pfn_to_page(pfn)); else return -EFAULT; diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c index b7d6b3a721b1..8d7a1ef72758 100644 --- a/kernel/power/suspend.c +++ b/kernel/power/suspend.c @@ -28,6 +28,7 @@ #include <linux/ftrace.h> #include <trace/events/power.h> #include <linux/compiler.h> +#include <linux/moduleparam.h> #include "power.h" @@ -233,12 +234,20 @@ static bool platform_suspend_again(suspend_state_t state) suspend_ops->suspend_again() : false; } +#ifdef CONFIG_PM_DEBUG +static unsigned int pm_test_delay = 5; +module_param(pm_test_delay, uint, 0644); +MODULE_PARM_DESC(pm_test_delay, + "Number of seconds to wait before resuming from suspend test"); +#endif + static int suspend_test(int level) { #ifdef CONFIG_PM_DEBUG if (pm_test_level == level) { - printk(KERN_INFO "suspend debug: Waiting for 5 seconds.\n"); - mdelay(5000); + printk(KERN_INFO "suspend debug: Waiting for %d second(s).\n", + pm_test_delay); + mdelay(pm_test_delay * 1000); return 1; } #endif /* !CONFIG_PM_DEBUG */ diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index bb0635bd74f2..879edfc5ee52 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -32,7 +32,6 @@ #include <linux/security.h> #include <linux/bootmem.h> #include <linux/memblock.h> -#include <linux/aio.h> #include <linux/syscalls.h> #include <linux/kexec.h> #include <linux/kdb.h> @@ -46,6 +45,7 @@ #include <linux/irq_work.h> #include <linux/utsname.h> #include <linux/ctype.h> +#include <linux/uio.h> #include <asm/uaccess.h> @@ -521,7 +521,7 @@ static ssize_t devkmsg_write(struct kiocb *iocb, struct iov_iter *from) int i; int level = default_message_loglevel; int facility = 1; /* LOG_USER */ - size_t len = iocb->ki_nbytes; + size_t len = iov_iter_count(from); ssize_t ret = len; if (len > LOG_LINE_MAX) diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c index 30d42aa55d83..8dbe27611ec3 100644 --- a/kernel/rcu/rcutorture.c +++ b/kernel/rcu/rcutorture.c @@ -853,6 +853,8 @@ rcu_torture_fqs(void *arg) static int rcu_torture_writer(void *arg) { + bool can_expedite = !rcu_gp_is_expedited(); + int expediting = 0; unsigned long gp_snap; bool gp_cond1 = gp_cond, gp_exp1 = gp_exp, gp_normal1 = gp_normal; bool gp_sync1 = gp_sync; @@ -865,9 +867,15 @@ rcu_torture_writer(void *arg) int nsynctypes = 0; VERBOSE_TOROUT_STRING("rcu_torture_writer task started"); + pr_alert("%s" TORTURE_FLAG + " Grace periods expedited from boot/sysfs for %s,\n", + torture_type, cur_ops->name); + pr_alert("%s" TORTURE_FLAG + " Testing of dynamic grace-period expediting diabled.\n", + torture_type); /* Initialize synctype[] array. If none set, take default. */ - if (!gp_cond1 && !gp_exp1 && !gp_normal1 && !gp_sync) + if (!gp_cond1 && !gp_exp1 && !gp_normal1 && !gp_sync1) gp_cond1 = gp_exp1 = gp_normal1 = gp_sync1 = true; if (gp_cond1 && cur_ops->get_state && cur_ops->cond_sync) synctype[nsynctypes++] = RTWS_COND_GET; @@ -949,9 +957,26 @@ rcu_torture_writer(void *arg) } } rcutorture_record_progress(++rcu_torture_current_version); + /* Cycle through nesting levels of rcu_expedite_gp() calls. */ + if (can_expedite && + !(torture_random(&rand) & 0xff & (!!expediting - 1))) { + WARN_ON_ONCE(expediting == 0 && rcu_gp_is_expedited()); + if (expediting >= 0) + rcu_expedite_gp(); + else + rcu_unexpedite_gp(); + if (++expediting > 3) + expediting = -expediting; + } rcu_torture_writer_state = RTWS_STUTTER; stutter_wait("rcu_torture_writer"); } while (!torture_must_stop()); + /* Reset expediting back to unexpedited. */ + if (expediting > 0) + expediting = -expediting; + while (can_expedite && expediting++ < 0) + rcu_unexpedite_gp(); + WARN_ON_ONCE(can_expedite && rcu_gp_is_expedited()); rcu_torture_writer_state = RTWS_STOPPING; torture_kthread_stopping("rcu_torture_writer"); return 0; diff --git a/kernel/rcu/srcu.c b/kernel/rcu/srcu.c index 445bf8ffe3fb..cad76e76b4e7 100644 --- a/kernel/rcu/srcu.c +++ b/kernel/rcu/srcu.c @@ -402,23 +402,6 @@ void call_srcu(struct srcu_struct *sp, struct rcu_head *head, } EXPORT_SYMBOL_GPL(call_srcu); -struct rcu_synchronize { - struct rcu_head head; - struct completion completion; -}; - -/* - * Awaken the corresponding synchronize_srcu() instance now that a - * grace period has elapsed. - */ -static void wakeme_after_rcu(struct rcu_head *head) -{ - struct rcu_synchronize *rcu; - - rcu = container_of(head, struct rcu_synchronize, head); - complete(&rcu->completion); -} - static void srcu_advance_batches(struct srcu_struct *sp, int trycount); static void srcu_reschedule(struct srcu_struct *sp); @@ -507,7 +490,7 @@ static void __synchronize_srcu(struct srcu_struct *sp, int trycount) */ void synchronize_srcu(struct srcu_struct *sp) { - __synchronize_srcu(sp, rcu_expedited + __synchronize_srcu(sp, rcu_gp_is_expedited() ? SYNCHRONIZE_SRCU_EXP_TRYCOUNT : SYNCHRONIZE_SRCU_TRYCOUNT); } diff --git a/kernel/rcu/tiny.c b/kernel/rcu/tiny.c index cc9ceca7bde1..069742d61c68 100644 --- a/kernel/rcu/tiny.c +++ b/kernel/rcu/tiny.c @@ -103,8 +103,7 @@ EXPORT_SYMBOL(__rcu_is_watching); static int rcu_qsctr_help(struct rcu_ctrlblk *rcp) { RCU_TRACE(reset_cpu_stall_ticks(rcp)); - if (rcp->rcucblist != NULL && - rcp->donetail != rcp->curtail) { + if (rcp->donetail != rcp->curtail) { rcp->donetail = rcp->curtail; return 1; } @@ -169,17 +168,6 @@ static void __rcu_process_callbacks(struct rcu_ctrlblk *rcp) unsigned long flags; RCU_TRACE(int cb_count = 0); - /* If no RCU callbacks ready to invoke, just return. */ - if (&rcp->rcucblist == rcp->donetail) { - RCU_TRACE(trace_rcu_batch_start(rcp->name, 0, 0, -1)); - RCU_TRACE(trace_rcu_batch_end(rcp->name, 0, - !!ACCESS_ONCE(rcp->rcucblist), - need_resched(), - is_idle_task(current), - false)); - return; - } - /* Move the ready-to-invoke callbacks to a local list. */ local_irq_save(flags); RCU_TRACE(trace_rcu_batch_start(rcp->name, 0, rcp->qlen, -1)); diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 48d640ca1a05..233165da782f 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -91,8 +91,10 @@ static const char *tp_##sname##_varname __used __tracepoint_string = sname##_var #define RCU_STATE_INITIALIZER(sname, sabbr, cr) \ DEFINE_RCU_TPS(sname) \ +DEFINE_PER_CPU_SHARED_ALIGNED(struct rcu_data, sname##_data); \ struct rcu_state sname##_state = { \ .level = { &sname##_state.node[0] }, \ + .rda = &sname##_data, \ .call = cr, \ .fqs_state = RCU_GP_IDLE, \ .gpnum = 0UL - 300UL, \ @@ -101,11 +103,9 @@ struct rcu_state sname##_state = { \ .orphan_nxttail = &sname##_state.orphan_nxtlist, \ .orphan_donetail = &sname##_state.orphan_donelist, \ .barrier_mutex = __MUTEX_INITIALIZER(sname##_state.barrier_mutex), \ - .onoff_mutex = __MUTEX_INITIALIZER(sname##_state.onoff_mutex), \ .name = RCU_STATE_NAME(sname), \ .abbr = sabbr, \ -}; \ -DEFINE_PER_CPU_SHARED_ALIGNED(struct rcu_data, sname##_data) +} RCU_STATE_INITIALIZER(rcu_sched, 's', call_rcu_sched); RCU_STATE_INITIALIZER(rcu_bh, 'b', call_rcu_bh); @@ -152,6 +152,8 @@ EXPORT_SYMBOL_GPL(rcu_scheduler_active); */ static int rcu_scheduler_fully_active __read_mostly; +static void rcu_init_new_rnp(struct rcu_node *rnp_leaf); +static void rcu_cleanup_dead_rnp(struct rcu_node *rnp_leaf); static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu); static void invoke_rcu_core(void); static void invoke_rcu_callbacks(struct rcu_state *rsp, struct rcu_data *rdp); @@ -160,6 +162,12 @@ static void invoke_rcu_callbacks(struct rcu_state *rsp, struct rcu_data *rdp); static int kthread_prio = CONFIG_RCU_KTHREAD_PRIO; module_param(kthread_prio, int, 0644); +/* Delay in jiffies for grace-period initialization delays. */ +static int gp_init_delay = IS_ENABLED(CONFIG_RCU_TORTURE_TEST_SLOW_INIT) + ? CONFIG_RCU_TORTURE_TEST_SLOW_INIT_DELAY + : 0; +module_param(gp_init_delay, int, 0644); + /* * Track the rcutorture test sequence number and the update version * number within a given test. The rcutorture_testseq is incremented @@ -173,6 +181,17 @@ unsigned long rcutorture_testseq; unsigned long rcutorture_vernum; /* + * Compute the mask of online CPUs for the specified rcu_node structure. + * This will not be stable unless the rcu_node structure's ->lock is + * held, but the bit corresponding to the current CPU will be stable + * in most contexts. + */ +unsigned long rcu_rnp_online_cpus(struct rcu_node *rnp) +{ + return ACCESS_ONCE(rnp->qsmaskinitnext); +} + +/* * Return true if an RCU grace period is in progress. The ACCESS_ONCE()s * permit this function to be invoked without holding the root rcu_node * structure's ->lock, but of course results can be subject to change. @@ -292,10 +311,10 @@ void rcu_note_context_switch(void) EXPORT_SYMBOL_GPL(rcu_note_context_switch); /* - * Register a quiesecent state for all RCU flavors. If there is an + * Register a quiescent state for all RCU flavors. If there is an * emergency, invoke rcu_momentary_dyntick_idle() to do a heavy-weight * dyntick-idle quiescent state visible to other CPUs (but only for those - * RCU flavors in desparate need of a quiescent state, which will normally + * RCU flavors in desperate need of a quiescent state, which will normally * be none of them). Either way, do a lightweight quiescent state for * all RCU flavors. */ @@ -410,6 +429,15 @@ void rcu_bh_force_quiescent_state(void) EXPORT_SYMBOL_GPL(rcu_bh_force_quiescent_state); /* + * Force a quiescent state for RCU-sched. + */ +void rcu_sched_force_quiescent_state(void) +{ + force_quiescent_state(&rcu_sched_state); +} +EXPORT_SYMBOL_GPL(rcu_sched_force_quiescent_state); + +/* * Show the state of the grace-period kthreads. */ void show_rcu_gp_kthreads(void) @@ -483,15 +511,6 @@ void rcutorture_record_progress(unsigned long vernum) EXPORT_SYMBOL_GPL(rcutorture_record_progress); /* - * Force a quiescent state for RCU-sched. - */ -void rcu_sched_force_quiescent_state(void) -{ - force_quiescent_state(&rcu_sched_state); -} -EXPORT_SYMBOL_GPL(rcu_sched_force_quiescent_state); - -/* * Does the CPU have callbacks ready to be invoked? */ static int @@ -954,7 +973,7 @@ bool rcu_lockdep_current_cpu_online(void) preempt_disable(); rdp = this_cpu_ptr(&rcu_sched_data); rnp = rdp->mynode; - ret = (rdp->grpmask & rnp->qsmaskinit) || + ret = (rdp->grpmask & rcu_rnp_online_cpus(rnp)) || !rcu_scheduler_fully_active; preempt_enable(); return ret; @@ -1196,9 +1215,10 @@ static void print_other_cpu_stall(struct rcu_state *rsp, unsigned long gpnum) } else { j = jiffies; gpa = ACCESS_ONCE(rsp->gp_activity); - pr_err("All QSes seen, last %s kthread activity %ld (%ld-%ld), jiffies_till_next_fqs=%ld\n", + pr_err("All QSes seen, last %s kthread activity %ld (%ld-%ld), jiffies_till_next_fqs=%ld, root ->qsmask %#lx\n", rsp->name, j - gpa, j, gpa, - jiffies_till_next_fqs); + jiffies_till_next_fqs, + rcu_get_root(rsp)->qsmask); /* In this case, the current CPU might be at fault. */ sched_show_task(current); } @@ -1328,20 +1348,30 @@ void rcu_cpu_stall_reset(void) } /* - * Initialize the specified rcu_data structure's callback list to empty. + * Initialize the specified rcu_data structure's default callback list + * to empty. The default callback list is the one that is not used by + * no-callbacks CPUs. */ -static void init_callback_list(struct rcu_data *rdp) +static void init_default_callback_list(struct rcu_data *rdp) { int i; - if (init_nocb_callback_list(rdp)) - return; rdp->nxtlist = NULL; for (i = 0; i < RCU_NEXT_SIZE; i++) rdp->nxttail[i] = &rdp->nxtlist; } /* + * Initialize the specified rcu_data structure's callback list to empty. + */ +static void init_callback_list(struct rcu_data *rdp) +{ + if (init_nocb_callback_list(rdp)) + return; + init_default_callback_list(rdp); +} + +/* * Determine the value that ->completed will have at the end of the * next subsequent grace period. This is used to tag callbacks so that * a CPU can invoke callbacks in a timely fashion even if that CPU has @@ -1703,11 +1733,11 @@ static void note_gp_changes(struct rcu_state *rsp, struct rcu_data *rdp) */ static int rcu_gp_init(struct rcu_state *rsp) { + unsigned long oldmask; struct rcu_data *rdp; struct rcu_node *rnp = rcu_get_root(rsp); ACCESS_ONCE(rsp->gp_activity) = jiffies; - rcu_bind_gp_kthread(); raw_spin_lock_irq(&rnp->lock); smp_mb__after_unlock_lock(); if (!ACCESS_ONCE(rsp->gp_flags)) { @@ -1733,9 +1763,54 @@ static int rcu_gp_init(struct rcu_state *rsp) trace_rcu_grace_period(rsp->name, rsp->gpnum, TPS("start")); raw_spin_unlock_irq(&rnp->lock); - /* Exclude any concurrent CPU-hotplug operations. */ - mutex_lock(&rsp->onoff_mutex); - smp_mb__after_unlock_lock(); /* ->gpnum increment before GP! */ + /* + * Apply per-leaf buffered online and offline operations to the + * rcu_node tree. Note that this new grace period need not wait + * for subsequent online CPUs, and that quiescent-state forcing + * will handle subsequent offline CPUs. + */ + rcu_for_each_leaf_node(rsp, rnp) { + raw_spin_lock_irq(&rnp->lock); + smp_mb__after_unlock_lock(); + if (rnp->qsmaskinit == rnp->qsmaskinitnext && + !rnp->wait_blkd_tasks) { + /* Nothing to do on this leaf rcu_node structure. */ + raw_spin_unlock_irq(&rnp->lock); + continue; + } + + /* Record old state, apply changes to ->qsmaskinit field. */ + oldmask = rnp->qsmaskinit; + rnp->qsmaskinit = rnp->qsmaskinitnext; + + /* If zero-ness of ->qsmaskinit changed, propagate up tree. */ + if (!oldmask != !rnp->qsmaskinit) { + if (!oldmask) /* First online CPU for this rcu_node. */ + rcu_init_new_rnp(rnp); + else if (rcu_preempt_has_tasks(rnp)) /* blocked tasks */ + rnp->wait_blkd_tasks = true; + else /* Last offline CPU and can propagate. */ + rcu_cleanup_dead_rnp(rnp); + } + + /* + * If all waited-on tasks from prior grace period are + * done, and if all this rcu_node structure's CPUs are + * still offline, propagate up the rcu_node tree and + * clear ->wait_blkd_tasks. Otherwise, if one of this + * rcu_node structure's CPUs has since come back online, + * simply clear ->wait_blkd_tasks (but rcu_cleanup_dead_rnp() + * checks for this, so just call it unconditionally). + */ + if (rnp->wait_blkd_tasks && + (!rcu_preempt_has_tasks(rnp) || + rnp->qsmaskinit)) { + rnp->wait_blkd_tasks = false; + rcu_cleanup_dead_rnp(rnp); + } + + raw_spin_unlock_irq(&rnp->lock); + } /* * Set the quiescent-state-needed bits in all the rcu_node @@ -1757,8 +1832,8 @@ static int rcu_gp_init(struct rcu_state *rsp) rcu_preempt_check_blocked_tasks(rnp); rnp->qsmask = rnp->qsmaskinit; ACCESS_ONCE(rnp->gpnum) = rsp->gpnum; - WARN_ON_ONCE(rnp->completed != rsp->completed); - ACCESS_ONCE(rnp->completed) = rsp->completed; + if (WARN_ON_ONCE(rnp->completed != rsp->completed)) + ACCESS_ONCE(rnp->completed) = rsp->completed; if (rnp == rdp->mynode) (void)__note_gp_changes(rsp, rnp, rdp); rcu_preempt_boost_start_gp(rnp); @@ -1768,9 +1843,12 @@ static int rcu_gp_init(struct rcu_state *rsp) raw_spin_unlock_irq(&rnp->lock); cond_resched_rcu_qs(); ACCESS_ONCE(rsp->gp_activity) = jiffies; + if (IS_ENABLED(CONFIG_RCU_TORTURE_TEST_SLOW_INIT) && + gp_init_delay > 0 && + !(rsp->gpnum % (rcu_num_nodes * 10))) + schedule_timeout_uninterruptible(gp_init_delay); } - mutex_unlock(&rsp->onoff_mutex); return 1; } @@ -1798,7 +1876,7 @@ static int rcu_gp_fqs(struct rcu_state *rsp, int fqs_state_in) fqs_state = RCU_FORCE_QS; } else { /* Handle dyntick-idle and offline CPUs. */ - isidle = false; + isidle = true; force_qs_rnp(rsp, rcu_implicit_dynticks_qs, &isidle, &maxj); } /* Clear flag to prevent immediate re-entry. */ @@ -1852,6 +1930,8 @@ static void rcu_gp_cleanup(struct rcu_state *rsp) rcu_for_each_node_breadth_first(rsp, rnp) { raw_spin_lock_irq(&rnp->lock); smp_mb__after_unlock_lock(); + WARN_ON_ONCE(rcu_preempt_blocked_readers_cgp(rnp)); + WARN_ON_ONCE(rnp->qsmask); ACCESS_ONCE(rnp->completed) = rsp->gpnum; rdp = this_cpu_ptr(rsp->rda); if (rnp == rdp->mynode) @@ -1895,6 +1975,7 @@ static int __noreturn rcu_gp_kthread(void *arg) struct rcu_state *rsp = arg; struct rcu_node *rnp = rcu_get_root(rsp); + rcu_bind_gp_kthread(); for (;;) { /* Handle grace-period start. */ @@ -2062,25 +2143,32 @@ static void rcu_report_qs_rsp(struct rcu_state *rsp, unsigned long flags) * Similar to rcu_report_qs_rdp(), for which it is a helper function. * Allows quiescent states for a group of CPUs to be reported at one go * to the specified rcu_node structure, though all the CPUs in the group - * must be represented by the same rcu_node structure (which need not be - * a leaf rcu_node structure, though it often will be). That structure's - * lock must be held upon entry, and it is released before return. + * must be represented by the same rcu_node structure (which need not be a + * leaf rcu_node structure, though it often will be). The gps parameter + * is the grace-period snapshot, which means that the quiescent states + * are valid only if rnp->gpnum is equal to gps. That structure's lock + * must be held upon entry, and it is released before return. */ static void rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp, - struct rcu_node *rnp, unsigned long flags) + struct rcu_node *rnp, unsigned long gps, unsigned long flags) __releases(rnp->lock) { + unsigned long oldmask = 0; struct rcu_node *rnp_c; /* Walk up the rcu_node hierarchy. */ for (;;) { - if (!(rnp->qsmask & mask)) { + if (!(rnp->qsmask & mask) || rnp->gpnum != gps) { - /* Our bit has already been cleared, so done. */ + /* + * Our bit has already been cleared, or the + * relevant grace period is already over, so done. + */ raw_spin_unlock_irqrestore(&rnp->lock, flags); return; } + WARN_ON_ONCE(oldmask); /* Any child must be all zeroed! */ rnp->qsmask &= ~mask; trace_rcu_quiescent_state_report(rsp->name, rnp->gpnum, mask, rnp->qsmask, rnp->level, @@ -2104,7 +2192,7 @@ rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp, rnp = rnp->parent; raw_spin_lock_irqsave(&rnp->lock, flags); smp_mb__after_unlock_lock(); - WARN_ON_ONCE(rnp_c->qsmask); + oldmask = rnp_c->qsmask; } /* @@ -2116,6 +2204,46 @@ rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp, } /* + * Record a quiescent state for all tasks that were previously queued + * on the specified rcu_node structure and that were blocking the current + * RCU grace period. The caller must hold the specified rnp->lock with + * irqs disabled, and this lock is released upon return, but irqs remain + * disabled. + */ +static void rcu_report_unblock_qs_rnp(struct rcu_state *rsp, + struct rcu_node *rnp, unsigned long flags) + __releases(rnp->lock) +{ + unsigned long gps; + unsigned long mask; + struct rcu_node *rnp_p; + + if (rcu_state_p == &rcu_sched_state || rsp != rcu_state_p || + rnp->qsmask != 0 || rcu_preempt_blocked_readers_cgp(rnp)) { + raw_spin_unlock_irqrestore(&rnp->lock, flags); + return; /* Still need more quiescent states! */ + } + + rnp_p = rnp->parent; + if (rnp_p == NULL) { + /* + * Only one rcu_node structure in the tree, so don't + * try to report up to its nonexistent parent! + */ + rcu_report_qs_rsp(rsp, flags); + return; + } + + /* Report up the rest of the hierarchy, tracking current ->gpnum. */ + gps = rnp->gpnum; + mask = rnp->grpmask; + raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */ + raw_spin_lock(&rnp_p->lock); /* irqs already disabled. */ + smp_mb__after_unlock_lock(); + rcu_report_qs_rnp(mask, rsp, rnp_p, gps, flags); +} + +/* * Record a quiescent state for the specified CPU to that CPU's rcu_data * structure. This must be either called from the specified CPU, or * called when the specified CPU is known to be offline (and when it is @@ -2163,7 +2291,8 @@ rcu_report_qs_rdp(int cpu, struct rcu_state *rsp, struct rcu_data *rdp) */ needwake = rcu_accelerate_cbs(rsp, rnp, rdp); - rcu_report_qs_rnp(mask, rsp, rnp, flags); /* rlses rnp->lock */ + rcu_report_qs_rnp(mask, rsp, rnp, rnp->gpnum, flags); + /* ^^^ Released rnp->lock */ if (needwake) rcu_gp_kthread_wake(rsp); } @@ -2256,8 +2385,12 @@ rcu_send_cbs_to_orphanage(int cpu, struct rcu_state *rsp, rsp->orphan_donetail = rdp->nxttail[RCU_DONE_TAIL]; } - /* Finally, initialize the rcu_data structure's list to empty. */ + /* + * Finally, initialize the rcu_data structure's list to empty and + * disallow further callbacks on this CPU. + */ init_callback_list(rdp); + rdp->nxttail[RCU_NEXT_TAIL] = NULL; } /* @@ -2355,6 +2488,7 @@ static void rcu_cleanup_dead_rnp(struct rcu_node *rnp_leaf) raw_spin_lock(&rnp->lock); /* irqs already disabled. */ smp_mb__after_unlock_lock(); /* GP memory ordering. */ rnp->qsmaskinit &= ~mask; + rnp->qsmask &= ~mask; if (rnp->qsmaskinit) { raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */ return; @@ -2364,6 +2498,26 @@ static void rcu_cleanup_dead_rnp(struct rcu_node *rnp_leaf) } /* + * The CPU is exiting the idle loop into the arch_cpu_idle_dead() + * function. We now remove it from the rcu_node tree's ->qsmaskinit + * bit masks. + */ +static void rcu_cleanup_dying_idle_cpu(int cpu, struct rcu_state *rsp) +{ + unsigned long flags; + unsigned long mask; + struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu); + struct rcu_node *rnp = rdp->mynode; /* Outgoing CPU's rdp & rnp. */ + + /* Remove outgoing CPU from mask in the leaf rcu_node structure. */ + mask = rdp->grpmask; + raw_spin_lock_irqsave(&rnp->lock, flags); + smp_mb__after_unlock_lock(); /* Enforce GP memory-order guarantee. */ + rnp->qsmaskinitnext &= ~mask; + raw_spin_unlock_irqrestore(&rnp->lock, flags); +} + +/* * The CPU has been completely removed, and some other CPU is reporting * this fact from process context. Do the remainder of the cleanup, * including orphaning the outgoing CPU's RCU callbacks, and also @@ -2379,29 +2533,15 @@ static void rcu_cleanup_dead_cpu(int cpu, struct rcu_state *rsp) /* Adjust any no-longer-needed kthreads. */ rcu_boost_kthread_setaffinity(rnp, -1); - /* Exclude any attempts to start a new grace period. */ - mutex_lock(&rsp->onoff_mutex); - raw_spin_lock_irqsave(&rsp->orphan_lock, flags); - /* Orphan the dead CPU's callbacks, and adopt them if appropriate. */ + raw_spin_lock_irqsave(&rsp->orphan_lock, flags); rcu_send_cbs_to_orphanage(cpu, rsp, rnp, rdp); rcu_adopt_orphan_cbs(rsp, flags); raw_spin_unlock_irqrestore(&rsp->orphan_lock, flags); - /* Remove outgoing CPU from mask in the leaf rcu_node structure. */ - raw_spin_lock_irqsave(&rnp->lock, flags); - smp_mb__after_unlock_lock(); /* Enforce GP memory-order guarantee. */ - rnp->qsmaskinit &= ~rdp->grpmask; - if (rnp->qsmaskinit == 0 && !rcu_preempt_has_tasks(rnp)) - rcu_cleanup_dead_rnp(rnp); - rcu_report_qs_rnp(rdp->grpmask, rsp, rnp, flags); /* Rlses rnp->lock. */ WARN_ONCE(rdp->qlen != 0 || rdp->nxtlist != NULL, "rcu_cleanup_dead_cpu: Callbacks on offline CPU %d: qlen=%lu, nxtlist=%p\n", cpu, rdp->qlen, rdp->nxtlist); - init_callback_list(rdp); - /* Disallow further callbacks on this CPU. */ - rdp->nxttail[RCU_NEXT_TAIL] = NULL; - mutex_unlock(&rsp->onoff_mutex); } #else /* #ifdef CONFIG_HOTPLUG_CPU */ @@ -2414,6 +2554,10 @@ static void __maybe_unused rcu_cleanup_dead_rnp(struct rcu_node *rnp_leaf) { } +static void rcu_cleanup_dying_idle_cpu(int cpu, struct rcu_state *rsp) +{ +} + static void rcu_cleanup_dead_cpu(int cpu, struct rcu_state *rsp) { } @@ -2589,26 +2733,47 @@ static void force_qs_rnp(struct rcu_state *rsp, return; } if (rnp->qsmask == 0) { - rcu_initiate_boost(rnp, flags); /* releases rnp->lock */ - continue; + if (rcu_state_p == &rcu_sched_state || + rsp != rcu_state_p || + rcu_preempt_blocked_readers_cgp(rnp)) { + /* + * No point in scanning bits because they + * are all zero. But we might need to + * priority-boost blocked readers. + */ + rcu_initiate_boost(rnp, flags); + /* rcu_initiate_boost() releases rnp->lock */ + continue; + } + if (rnp->parent && + (rnp->parent->qsmask & rnp->grpmask)) { + /* + * Race between grace-period + * initialization and task exiting RCU + * read-side critical section: Report. + */ + rcu_report_unblock_qs_rnp(rsp, rnp, flags); + /* rcu_report_unblock_qs_rnp() rlses ->lock */ + continue; + } } cpu = rnp->grplo; bit = 1; for (; cpu <= rnp->grphi; cpu++, bit <<= 1) { if ((rnp->qsmask & bit) != 0) { - if ((rnp->qsmaskinit & bit) != 0) - *isidle = false; + if ((rnp->qsmaskinit & bit) == 0) + *isidle = false; /* Pending hotplug. */ if (f(per_cpu_ptr(rsp->rda, cpu), isidle, maxj)) mask |= bit; } } if (mask != 0) { - - /* rcu_report_qs_rnp() releases rnp->lock. */ - rcu_report_qs_rnp(mask, rsp, rnp, flags); - continue; + /* Idle/offline CPUs, report (releases rnp->lock. */ + rcu_report_qs_rnp(mask, rsp, rnp, rnp->gpnum, flags); + } else { + /* Nothing to do here, so just drop the lock. */ + raw_spin_unlock_irqrestore(&rnp->lock, flags); } - raw_spin_unlock_irqrestore(&rnp->lock, flags); } } @@ -2741,7 +2906,7 @@ static void __call_rcu_core(struct rcu_state *rsp, struct rcu_data *rdp, * If called from an extended quiescent state, invoke the RCU * core in order to force a re-evaluation of RCU's idleness. */ - if (!rcu_is_watching() && cpu_online(smp_processor_id())) + if (!rcu_is_watching()) invoke_rcu_core(); /* If interrupts were disabled or CPU offline, don't invoke RCU core. */ @@ -2827,11 +2992,22 @@ __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu), if (cpu != -1) rdp = per_cpu_ptr(rsp->rda, cpu); - offline = !__call_rcu_nocb(rdp, head, lazy, flags); - WARN_ON_ONCE(offline); - /* _call_rcu() is illegal on offline CPU; leak the callback. */ - local_irq_restore(flags); - return; + if (likely(rdp->mynode)) { + /* Post-boot, so this should be for a no-CBs CPU. */ + offline = !__call_rcu_nocb(rdp, head, lazy, flags); + WARN_ON_ONCE(offline); + /* Offline CPU, _call_rcu() illegal, leak callback. */ + local_irq_restore(flags); + return; + } + /* + * Very early boot, before rcu_init(). Initialize if needed + * and then drop through to queue the callback. + */ + BUG_ON(cpu != -1); + WARN_ON_ONCE(!rcu_is_watching()); + if (!likely(rdp->nxtlist)) + init_default_callback_list(rdp); } ACCESS_ONCE(rdp->qlen) = rdp->qlen + 1; if (lazy) @@ -2954,7 +3130,7 @@ void synchronize_sched(void) "Illegal synchronize_sched() in RCU-sched read-side critical section"); if (rcu_blocking_is_gp()) return; - if (rcu_expedited) + if (rcu_gp_is_expedited()) synchronize_sched_expedited(); else wait_rcu_gp(call_rcu_sched); @@ -2981,7 +3157,7 @@ void synchronize_rcu_bh(void) "Illegal synchronize_rcu_bh() in RCU-bh read-side critical section"); if (rcu_blocking_is_gp()) return; - if (rcu_expedited) + if (rcu_gp_is_expedited()) synchronize_rcu_bh_expedited(); else wait_rcu_gp(call_rcu_bh); @@ -3518,6 +3694,28 @@ void rcu_barrier_sched(void) EXPORT_SYMBOL_GPL(rcu_barrier_sched); /* + * Propagate ->qsinitmask bits up the rcu_node tree to account for the + * first CPU in a given leaf rcu_node structure coming online. The caller + * must hold the corresponding leaf rcu_node ->lock with interrrupts + * disabled. + */ +static void rcu_init_new_rnp(struct rcu_node *rnp_leaf) +{ + long mask; + struct rcu_node *rnp = rnp_leaf; + + for (;;) { + mask = rnp->grpmask; + rnp = rnp->parent; + if (rnp == NULL) + return; + raw_spin_lock(&rnp->lock); /* Interrupts already disabled. */ + rnp->qsmaskinit |= mask; + raw_spin_unlock(&rnp->lock); /* Interrupts remain disabled. */ + } +} + +/* * Do boot-time initialization of a CPU's per-CPU RCU data. */ static void __init @@ -3553,49 +3751,37 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp) struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu); struct rcu_node *rnp = rcu_get_root(rsp); - /* Exclude new grace periods. */ - mutex_lock(&rsp->onoff_mutex); - /* Set up local state, ensuring consistent view of global state. */ raw_spin_lock_irqsave(&rnp->lock, flags); rdp->beenonline = 1; /* We have now been online. */ rdp->qlen_last_fqs_check = 0; rdp->n_force_qs_snap = rsp->n_force_qs; rdp->blimit = blimit; - init_callback_list(rdp); /* Re-enable callbacks on this CPU. */ + if (!rdp->nxtlist) + init_callback_list(rdp); /* Re-enable callbacks on this CPU. */ rdp->dynticks->dynticks_nesting = DYNTICK_TASK_EXIT_IDLE; rcu_sysidle_init_percpu_data(rdp->dynticks); atomic_set(&rdp->dynticks->dynticks, (atomic_read(&rdp->dynticks->dynticks) & ~0x1) + 1); raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */ - /* Add CPU to rcu_node bitmasks. */ + /* + * Add CPU to leaf rcu_node pending-online bitmask. Any needed + * propagation up the rcu_node tree will happen at the beginning + * of the next grace period. + */ rnp = rdp->mynode; mask = rdp->grpmask; - do { - /* Exclude any attempts to start a new GP on small systems. */ - raw_spin_lock(&rnp->lock); /* irqs already disabled. */ - rnp->qsmaskinit |= mask; - mask = rnp->grpmask; - if (rnp == rdp->mynode) { - /* - * If there is a grace period in progress, we will - * set up to wait for it next time we run the - * RCU core code. - */ - rdp->gpnum = rnp->completed; - rdp->completed = rnp->completed; - rdp->passed_quiesce = 0; - rdp->rcu_qs_ctr_snap = __this_cpu_read(rcu_qs_ctr); - rdp->qs_pending = 0; - trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("cpuonl")); - } - raw_spin_unlock(&rnp->lock); /* irqs already disabled. */ - rnp = rnp->parent; - } while (rnp != NULL && !(rnp->qsmaskinit & mask)); - local_irq_restore(flags); - - mutex_unlock(&rsp->onoff_mutex); + raw_spin_lock(&rnp->lock); /* irqs already disabled. */ + smp_mb__after_unlock_lock(); + rnp->qsmaskinitnext |= mask; + rdp->gpnum = rnp->completed; /* Make CPU later note any new GP. */ + rdp->completed = rnp->completed; + rdp->passed_quiesce = false; + rdp->rcu_qs_ctr_snap = __this_cpu_read(rcu_qs_ctr); + rdp->qs_pending = false; + trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("cpuonl")); + raw_spin_unlock_irqrestore(&rnp->lock, flags); } static void rcu_prepare_cpu(int cpu) @@ -3609,15 +3795,14 @@ static void rcu_prepare_cpu(int cpu) /* * Handle CPU online/offline notification events. */ -static int rcu_cpu_notify(struct notifier_block *self, - unsigned long action, void *hcpu) +int rcu_cpu_notify(struct notifier_block *self, + unsigned long action, void *hcpu) { long cpu = (long)hcpu; struct rcu_data *rdp = per_cpu_ptr(rcu_state_p->rda, cpu); struct rcu_node *rnp = rdp->mynode; struct rcu_state *rsp; - trace_rcu_utilization(TPS("Start CPU hotplug")); switch (action) { case CPU_UP_PREPARE: case CPU_UP_PREPARE_FROZEN: @@ -3637,6 +3822,11 @@ static int rcu_cpu_notify(struct notifier_block *self, for_each_rcu_flavor(rsp) rcu_cleanup_dying_cpu(rsp); break; + case CPU_DYING_IDLE: + for_each_rcu_flavor(rsp) { + rcu_cleanup_dying_idle_cpu(cpu, rsp); + } + break; case CPU_DEAD: case CPU_DEAD_FROZEN: case CPU_UP_CANCELED: @@ -3649,7 +3839,6 @@ static int rcu_cpu_notify(struct notifier_block *self, default: break; } - trace_rcu_utilization(TPS("End CPU hotplug")); return NOTIFY_OK; } @@ -3660,11 +3849,12 @@ static int rcu_pm_notify(struct notifier_block *self, case PM_HIBERNATION_PREPARE: case PM_SUSPEND_PREPARE: if (nr_cpu_ids <= 256) /* Expediting bad for large systems. */ - rcu_expedited = 1; + rcu_expedite_gp(); break; case PM_POST_HIBERNATION: case PM_POST_SUSPEND: - rcu_expedited = 0; + if (nr_cpu_ids <= 256) /* Expediting bad for large systems. */ + rcu_unexpedite_gp(); break; default: break; @@ -3734,30 +3924,26 @@ void rcu_scheduler_starting(void) * Compute the per-level fanout, either using the exact fanout specified * or balancing the tree, depending on CONFIG_RCU_FANOUT_EXACT. */ -#ifdef CONFIG_RCU_FANOUT_EXACT -static void __init rcu_init_levelspread(struct rcu_state *rsp) -{ - int i; - - rsp->levelspread[rcu_num_lvls - 1] = rcu_fanout_leaf; - for (i = rcu_num_lvls - 2; i >= 0; i--) - rsp->levelspread[i] = CONFIG_RCU_FANOUT; -} -#else /* #ifdef CONFIG_RCU_FANOUT_EXACT */ static void __init rcu_init_levelspread(struct rcu_state *rsp) { - int ccur; - int cprv; int i; - cprv = nr_cpu_ids; - for (i = rcu_num_lvls - 1; i >= 0; i--) { - ccur = rsp->levelcnt[i]; - rsp->levelspread[i] = (cprv + ccur - 1) / ccur; - cprv = ccur; + if (IS_ENABLED(CONFIG_RCU_FANOUT_EXACT)) { + rsp->levelspread[rcu_num_lvls - 1] = rcu_fanout_leaf; + for (i = rcu_num_lvls - 2; i >= 0; i--) + rsp->levelspread[i] = CONFIG_RCU_FANOUT; + } else { + int ccur; + int cprv; + + cprv = nr_cpu_ids; + for (i = rcu_num_lvls - 1; i >= 0; i--) { + ccur = rsp->levelcnt[i]; + rsp->levelspread[i] = (cprv + ccur - 1) / ccur; + cprv = ccur; + } } } -#endif /* #else #ifdef CONFIG_RCU_FANOUT_EXACT */ /* * Helper function for rcu_init() that initializes one rcu_state structure. @@ -3833,7 +4019,6 @@ static void __init rcu_init_one(struct rcu_state *rsp, } } - rsp->rda = rda; init_waitqueue_head(&rsp->gp_wq); rnp = rsp->level[rcu_num_lvls - 1]; for_each_possible_cpu(i) { @@ -3926,6 +4111,8 @@ void __init rcu_init(void) { int cpu; + rcu_early_boot_tests(); + rcu_bootup_announce(); rcu_init_geometry(); rcu_init_one(&rcu_bh_state, &rcu_bh_data); @@ -3942,8 +4129,6 @@ void __init rcu_init(void) pm_notifier(rcu_pm_notify, 0); for_each_online_cpu(cpu) rcu_cpu_notify(NULL, CPU_UP_PREPARE, (void *)(long)cpu); - - rcu_early_boot_tests(); } #include "tree_plugin.h" diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h index 119de399eb2f..a69d3dab2ec4 100644 --- a/kernel/rcu/tree.h +++ b/kernel/rcu/tree.h @@ -141,12 +141,20 @@ struct rcu_node { /* complete (only for PREEMPT_RCU). */ unsigned long qsmaskinit; /* Per-GP initial value for qsmask & expmask. */ + /* Initialized from ->qsmaskinitnext at the */ + /* beginning of each grace period. */ + unsigned long qsmaskinitnext; + /* Online CPUs for next grace period. */ unsigned long grpmask; /* Mask to apply to parent qsmask. */ /* Only one bit will be set in this mask. */ int grplo; /* lowest-numbered CPU or group here. */ int grphi; /* highest-numbered CPU or group here. */ u8 grpnum; /* CPU/group number for next level up. */ u8 level; /* root is at level 0. */ + bool wait_blkd_tasks;/* Necessary to wait for blocked tasks to */ + /* exit RCU read-side critical sections */ + /* before propagating offline up the */ + /* rcu_node tree? */ struct rcu_node *parent; struct list_head blkd_tasks; /* Tasks blocked in RCU read-side critical */ @@ -448,8 +456,6 @@ struct rcu_state { long qlen; /* Total number of callbacks. */ /* End of fields guarded by orphan_lock. */ - struct mutex onoff_mutex; /* Coordinate hotplug & GPs. */ - struct mutex barrier_mutex; /* Guards barrier fields. */ atomic_t barrier_cpu_count; /* # CPUs waiting on. */ struct completion barrier_completion; /* Wake at barrier end. */ @@ -559,6 +565,7 @@ static void rcu_prepare_kthreads(int cpu); static void rcu_cleanup_after_idle(void); static void rcu_prepare_for_idle(void); static void rcu_idle_count_callbacks_posted(void); +static bool rcu_preempt_has_tasks(struct rcu_node *rnp); static void print_cpu_stall_info_begin(void); static void print_cpu_stall_info(struct rcu_state *rsp, int cpu); static void print_cpu_stall_info_end(void); diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index 0a571e9a0f1d..8c0ec0f5a027 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -58,38 +58,33 @@ static bool __read_mostly rcu_nocb_poll; /* Offload kthread are to poll. */ */ static void __init rcu_bootup_announce_oddness(void) { -#ifdef CONFIG_RCU_TRACE - pr_info("\tRCU debugfs-based tracing is enabled.\n"); -#endif -#if (defined(CONFIG_64BIT) && CONFIG_RCU_FANOUT != 64) || (!defined(CONFIG_64BIT) && CONFIG_RCU_FANOUT != 32) - pr_info("\tCONFIG_RCU_FANOUT set to non-default value of %d\n", - CONFIG_RCU_FANOUT); -#endif -#ifdef CONFIG_RCU_FANOUT_EXACT - pr_info("\tHierarchical RCU autobalancing is disabled.\n"); -#endif -#ifdef CONFIG_RCU_FAST_NO_HZ - pr_info("\tRCU dyntick-idle grace-period acceleration is enabled.\n"); -#endif -#ifdef CONFIG_PROVE_RCU - pr_info("\tRCU lockdep checking is enabled.\n"); -#endif -#ifdef CONFIG_RCU_TORTURE_TEST_RUNNABLE - pr_info("\tRCU torture testing starts during boot.\n"); -#endif -#if defined(CONFIG_RCU_CPU_STALL_INFO) - pr_info("\tAdditional per-CPU info printed with stalls.\n"); -#endif -#if NUM_RCU_LVL_4 != 0 - pr_info("\tFour-level hierarchy is enabled.\n"); -#endif + if (IS_ENABLED(CONFIG_RCU_TRACE)) + pr_info("\tRCU debugfs-based tracing is enabled.\n"); + if ((IS_ENABLED(CONFIG_64BIT) && CONFIG_RCU_FANOUT != 64) || + (!IS_ENABLED(CONFIG_64BIT) && CONFIG_RCU_FANOUT != 32)) + pr_info("\tCONFIG_RCU_FANOUT set to non-default value of %d\n", + CONFIG_RCU_FANOUT); + if (IS_ENABLED(CONFIG_RCU_FANOUT_EXACT)) + pr_info("\tHierarchical RCU autobalancing is disabled.\n"); + if (IS_ENABLED(CONFIG_RCU_FAST_NO_HZ)) + pr_info("\tRCU dyntick-idle grace-period acceleration is enabled.\n"); + if (IS_ENABLED(CONFIG_PROVE_RCU)) + pr_info("\tRCU lockdep checking is enabled.\n"); + if (IS_ENABLED(CONFIG_RCU_TORTURE_TEST_RUNNABLE)) + pr_info("\tRCU torture testing starts during boot.\n"); + if (IS_ENABLED(CONFIG_RCU_CPU_STALL_INFO)) + pr_info("\tAdditional per-CPU info printed with stalls.\n"); + if (NUM_RCU_LVL_4 != 0) + pr_info("\tFour-level hierarchy is enabled.\n"); + if (CONFIG_RCU_FANOUT_LEAF != 16) + pr_info("\tBuild-time adjustment of leaf fanout to %d.\n", + CONFIG_RCU_FANOUT_LEAF); if (rcu_fanout_leaf != CONFIG_RCU_FANOUT_LEAF) pr_info("\tBoot-time adjustment of leaf fanout to %d.\n", rcu_fanout_leaf); if (nr_cpu_ids != NR_CPUS) pr_info("\tRCU restricting CPUs from NR_CPUS=%d to nr_cpu_ids=%d.\n", NR_CPUS, nr_cpu_ids); -#ifdef CONFIG_RCU_BOOST - pr_info("\tRCU kthread priority: %d.\n", kthread_prio); -#endif + if (IS_ENABLED(CONFIG_RCU_BOOST)) + pr_info("\tRCU kthread priority: %d.\n", kthread_prio); } #ifdef CONFIG_PREEMPT_RCU @@ -180,7 +175,7 @@ static void rcu_preempt_note_context_switch(void) * But first, note that the current CPU must still be * on line! */ - WARN_ON_ONCE((rdp->grpmask & rnp->qsmaskinit) == 0); + WARN_ON_ONCE((rdp->grpmask & rcu_rnp_online_cpus(rnp)) == 0); WARN_ON_ONCE(!list_empty(&t->rcu_node_entry)); if ((rnp->qsmask & rdp->grpmask) && rnp->gp_tasks != NULL) { list_add(&t->rcu_node_entry, rnp->gp_tasks->prev); @@ -233,43 +228,6 @@ static int rcu_preempt_blocked_readers_cgp(struct rcu_node *rnp) } /* - * Record a quiescent state for all tasks that were previously queued - * on the specified rcu_node structure and that were blocking the current - * RCU grace period. The caller must hold the specified rnp->lock with - * irqs disabled, and this lock is released upon return, but irqs remain - * disabled. - */ -static void rcu_report_unblock_qs_rnp(struct rcu_node *rnp, unsigned long flags) - __releases(rnp->lock) -{ - unsigned long mask; - struct rcu_node *rnp_p; - - if (rnp->qsmask != 0 || rcu_preempt_blocked_readers_cgp(rnp)) { - raw_spin_unlock_irqrestore(&rnp->lock, flags); - return; /* Still need more quiescent states! */ - } - - rnp_p = rnp->parent; - if (rnp_p == NULL) { - /* - * Either there is only one rcu_node in the tree, - * or tasks were kicked up to root rcu_node due to - * CPUs going offline. - */ - rcu_report_qs_rsp(&rcu_preempt_state, flags); - return; - } - - /* Report up the rest of the hierarchy. */ - mask = rnp->grpmask; - raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */ - raw_spin_lock(&rnp_p->lock); /* irqs already disabled. */ - smp_mb__after_unlock_lock(); - rcu_report_qs_rnp(mask, &rcu_preempt_state, rnp_p, flags); -} - -/* * Advance a ->blkd_tasks-list pointer to the next entry, instead * returning NULL if at the end of the list. */ @@ -300,7 +258,6 @@ static bool rcu_preempt_has_tasks(struct rcu_node *rnp) */ void rcu_read_unlock_special(struct task_struct *t) { - bool empty; bool empty_exp; bool empty_norm; bool empty_exp_now; @@ -334,7 +291,13 @@ void rcu_read_unlock_special(struct task_struct *t) } /* Hardware IRQ handlers cannot block, complain if they get here. */ - if (WARN_ON_ONCE(in_irq() || in_serving_softirq())) { + if (in_irq() || in_serving_softirq()) { + lockdep_rcu_suspicious(__FILE__, __LINE__, + "rcu_read_unlock() from irq or softirq with blocking in critical section!!!\n"); + pr_alert("->rcu_read_unlock_special: %#x (b: %d, nq: %d)\n", + t->rcu_read_unlock_special.s, + t->rcu_read_unlock_special.b.blocked, + t->rcu_read_unlock_special.b.need_qs); local_irq_restore(flags); return; } @@ -356,7 +319,6 @@ void rcu_read_unlock_special(struct task_struct *t) break; raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */ } - empty = !rcu_preempt_has_tasks(rnp); empty_norm = !rcu_preempt_blocked_readers_cgp(rnp); empty_exp = !rcu_preempted_readers_exp(rnp); smp_mb(); /* ensure expedited fastpath sees end of RCU c-s. */ @@ -377,14 +339,6 @@ void rcu_read_unlock_special(struct task_struct *t) #endif /* #ifdef CONFIG_RCU_BOOST */ /* - * If this was the last task on the list, go see if we - * need to propagate ->qsmaskinit bit clearing up the - * rcu_node tree. - */ - if (!empty && !rcu_preempt_has_tasks(rnp)) - rcu_cleanup_dead_rnp(rnp); - - /* * If this was the last task on the current list, and if * we aren't waiting on any CPUs, report the quiescent state. * Note that rcu_report_unblock_qs_rnp() releases rnp->lock, @@ -399,7 +353,8 @@ void rcu_read_unlock_special(struct task_struct *t) rnp->grplo, rnp->grphi, !!rnp->gp_tasks); - rcu_report_unblock_qs_rnp(rnp, flags); + rcu_report_unblock_qs_rnp(&rcu_preempt_state, + rnp, flags); } else { raw_spin_unlock_irqrestore(&rnp->lock, flags); } @@ -520,10 +475,6 @@ static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp) WARN_ON_ONCE(rnp->qsmask); } -#ifdef CONFIG_HOTPLUG_CPU - -#endif /* #ifdef CONFIG_HOTPLUG_CPU */ - /* * Check for a quiescent state from the current CPU. When a task blocks, * the task is recorded in the corresponding CPU's rcu_node structure, @@ -585,7 +536,7 @@ void synchronize_rcu(void) "Illegal synchronize_rcu() in RCU read-side critical section"); if (!rcu_scheduler_active) return; - if (rcu_expedited) + if (rcu_gp_is_expedited()) synchronize_rcu_expedited(); else wait_rcu_gp(call_rcu); @@ -630,9 +581,6 @@ static int sync_rcu_preempt_exp_done(struct rcu_node *rnp) * recursively up the tree. (Calm down, calm down, we do the recursion * iteratively!) * - * Most callers will set the "wake" flag, but the task initiating the - * expedited grace period need not wake itself. - * * Caller must hold sync_rcu_preempt_exp_mutex. */ static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp, @@ -667,29 +615,85 @@ static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp, /* * Snapshot the tasks blocking the newly started preemptible-RCU expedited - * grace period for the specified rcu_node structure. If there are no such - * tasks, report it up the rcu_node hierarchy. + * grace period for the specified rcu_node structure, phase 1. If there + * are such tasks, set the ->expmask bits up the rcu_node tree and also + * set the ->expmask bits on the leaf rcu_node structures to tell phase 2 + * that work is needed here. * - * Caller must hold sync_rcu_preempt_exp_mutex and must exclude - * CPU hotplug operations. + * Caller must hold sync_rcu_preempt_exp_mutex. */ static void -sync_rcu_preempt_exp_init(struct rcu_state *rsp, struct rcu_node *rnp) +sync_rcu_preempt_exp_init1(struct rcu_state *rsp, struct rcu_node *rnp) { unsigned long flags; - int must_wait = 0; + unsigned long mask; + struct rcu_node *rnp_up; raw_spin_lock_irqsave(&rnp->lock, flags); smp_mb__after_unlock_lock(); + WARN_ON_ONCE(rnp->expmask); + WARN_ON_ONCE(rnp->exp_tasks); if (!rcu_preempt_has_tasks(rnp)) { + /* No blocked tasks, nothing to do. */ raw_spin_unlock_irqrestore(&rnp->lock, flags); - } else { + return; + } + /* Call for Phase 2 and propagate ->expmask bits up the tree. */ + rnp->expmask = 1; + rnp_up = rnp; + while (rnp_up->parent) { + mask = rnp_up->grpmask; + rnp_up = rnp_up->parent; + if (rnp_up->expmask & mask) + break; + raw_spin_lock(&rnp_up->lock); /* irqs already off */ + smp_mb__after_unlock_lock(); + rnp_up->expmask |= mask; + raw_spin_unlock(&rnp_up->lock); /* irqs still off */ + } + raw_spin_unlock_irqrestore(&rnp->lock, flags); +} + +/* + * Snapshot the tasks blocking the newly started preemptible-RCU expedited + * grace period for the specified rcu_node structure, phase 2. If the + * leaf rcu_node structure has its ->expmask field set, check for tasks. + * If there are some, clear ->expmask and set ->exp_tasks accordingly, + * then initiate RCU priority boosting. Otherwise, clear ->expmask and + * invoke rcu_report_exp_rnp() to clear out the upper-level ->expmask bits, + * enabling rcu_read_unlock_special() to do the bit-clearing. + * + * Caller must hold sync_rcu_preempt_exp_mutex. + */ +static void +sync_rcu_preempt_exp_init2(struct rcu_state *rsp, struct rcu_node *rnp) +{ + unsigned long flags; + + raw_spin_lock_irqsave(&rnp->lock, flags); + smp_mb__after_unlock_lock(); + if (!rnp->expmask) { + /* Phase 1 didn't do anything, so Phase 2 doesn't either. */ + raw_spin_unlock_irqrestore(&rnp->lock, flags); + return; + } + + /* Phase 1 is over. */ + rnp->expmask = 0; + + /* + * If there are still blocked tasks, set up ->exp_tasks so that + * rcu_read_unlock_special() will wake us and then boost them. + */ + if (rcu_preempt_has_tasks(rnp)) { rnp->exp_tasks = rnp->blkd_tasks.next; rcu_initiate_boost(rnp, flags); /* releases rnp->lock */ - must_wait = 1; + return; } - if (!must_wait) - rcu_report_exp_rnp(rsp, rnp, false); /* Don't wake self. */ + + /* No longer any blocked tasks, so undo bit setting. */ + raw_spin_unlock_irqrestore(&rnp->lock, flags); + rcu_report_exp_rnp(rsp, rnp, false); } /** @@ -706,7 +710,6 @@ sync_rcu_preempt_exp_init(struct rcu_state *rsp, struct rcu_node *rnp) */ void synchronize_rcu_expedited(void) { - unsigned long flags; struct rcu_node *rnp; struct rcu_state *rsp = &rcu_preempt_state; unsigned long snap; @@ -757,19 +760,16 @@ void synchronize_rcu_expedited(void) /* force all RCU readers onto ->blkd_tasks lists. */ synchronize_sched_expedited(); - /* Initialize ->expmask for all non-leaf rcu_node structures. */ - rcu_for_each_nonleaf_node_breadth_first(rsp, rnp) { - raw_spin_lock_irqsave(&rnp->lock, flags); - smp_mb__after_unlock_lock(); - rnp->expmask = rnp->qsmaskinit; - raw_spin_unlock_irqrestore(&rnp->lock, flags); - } - - /* Snapshot current state of ->blkd_tasks lists. */ + /* + * Snapshot current state of ->blkd_tasks lists into ->expmask. + * Phase 1 sets bits and phase 2 permits rcu_read_unlock_special() + * to start clearing them. Doing this in one phase leads to + * strange races between setting and clearing bits, so just say "no"! + */ + rcu_for_each_leaf_node(rsp, rnp) + sync_rcu_preempt_exp_init1(rsp, rnp); rcu_for_each_leaf_node(rsp, rnp) - sync_rcu_preempt_exp_init(rsp, rnp); - if (NUM_RCU_NODES > 1) - sync_rcu_preempt_exp_init(rsp, rcu_get_root(rsp)); + sync_rcu_preempt_exp_init2(rsp, rnp); put_online_cpus(); @@ -859,8 +859,6 @@ static int rcu_preempt_blocked_readers_cgp(struct rcu_node *rnp) return 0; } -#ifdef CONFIG_HOTPLUG_CPU - /* * Because there is no preemptible RCU, there can be no readers blocked. */ @@ -869,8 +867,6 @@ static bool rcu_preempt_has_tasks(struct rcu_node *rnp) return false; } -#endif /* #ifdef CONFIG_HOTPLUG_CPU */ - /* * Because preemptible RCU does not exist, we never have to check for * tasks blocked within RCU read-side critical sections. @@ -1170,7 +1166,7 @@ static void rcu_preempt_boost_start_gp(struct rcu_node *rnp) * Returns zero if all is well, a negated errno otherwise. */ static int rcu_spawn_one_boost_kthread(struct rcu_state *rsp, - struct rcu_node *rnp) + struct rcu_node *rnp) { int rnp_index = rnp - &rsp->node[0]; unsigned long flags; @@ -1180,7 +1176,7 @@ static int rcu_spawn_one_boost_kthread(struct rcu_state *rsp, if (&rcu_preempt_state != rsp) return 0; - if (!rcu_scheduler_fully_active || rnp->qsmaskinit == 0) + if (!rcu_scheduler_fully_active || rcu_rnp_online_cpus(rnp) == 0) return 0; rsp->boost = 1; @@ -1273,7 +1269,7 @@ static void rcu_cpu_kthread(unsigned int cpu) static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu) { struct task_struct *t = rnp->boost_kthread_task; - unsigned long mask = rnp->qsmaskinit; + unsigned long mask = rcu_rnp_online_cpus(rnp); cpumask_var_t cm; int cpu; @@ -1945,7 +1941,8 @@ static bool rcu_nocb_cpu_needs_barrier(struct rcu_state *rsp, int cpu) rhp = ACCESS_ONCE(rdp->nocb_follower_head); /* Having no rcuo kthread but CBs after scheduler starts is bad! */ - if (!ACCESS_ONCE(rdp->nocb_kthread) && rhp) { + if (!ACCESS_ONCE(rdp->nocb_kthread) && rhp && + rcu_scheduler_fully_active) { /* RCU callback enqueued before CPU first came online??? */ pr_err("RCU: Never-onlined no-CBs CPU %d has CB %p\n", cpu, rhp->func); @@ -2392,18 +2389,8 @@ void __init rcu_init_nohz(void) pr_info("\tPoll for callbacks from no-CBs CPUs.\n"); for_each_rcu_flavor(rsp) { - for_each_cpu(cpu, rcu_nocb_mask) { - struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu); - - /* - * If there are early callbacks, they will need - * to be moved to the nocb lists. - */ - WARN_ON_ONCE(rdp->nxttail[RCU_NEXT_TAIL] != - &rdp->nxtlist && - rdp->nxttail[RCU_NEXT_TAIL] != NULL); - init_nocb_callback_list(rdp); - } + for_each_cpu(cpu, rcu_nocb_mask) + init_nocb_callback_list(per_cpu_ptr(rsp->rda, cpu)); rcu_organize_nocb_kthreads(rsp); } } @@ -2540,6 +2527,16 @@ static bool init_nocb_callback_list(struct rcu_data *rdp) if (!rcu_is_nocb_cpu(rdp->cpu)) return false; + /* If there are early-boot callbacks, move them to nocb lists. */ + if (rdp->nxtlist) { + rdp->nocb_head = rdp->nxtlist; + rdp->nocb_tail = rdp->nxttail[RCU_NEXT_TAIL]; + atomic_long_set(&rdp->nocb_q_count, rdp->qlen); + atomic_long_set(&rdp->nocb_q_count_lazy, rdp->qlen_lazy); + rdp->nxtlist = NULL; + rdp->qlen = 0; + rdp->qlen_lazy = 0; + } rdp->nxttail[RCU_NEXT_TAIL] = NULL; return true; } @@ -2763,7 +2760,8 @@ static void rcu_sysidle_exit(int irq) /* * Check to see if the current CPU is idle. Note that usermode execution - * does not count as idle. The caller must have disabled interrupts. + * does not count as idle. The caller must have disabled interrupts, + * and must be running on tick_do_timer_cpu. */ static void rcu_sysidle_check_cpu(struct rcu_data *rdp, bool *isidle, unsigned long *maxj) @@ -2784,8 +2782,8 @@ static void rcu_sysidle_check_cpu(struct rcu_data *rdp, bool *isidle, if (!*isidle || rdp->rsp != rcu_state_p || cpu_is_offline(rdp->cpu) || rdp->cpu == tick_do_timer_cpu) return; - if (rcu_gp_in_progress(rdp->rsp)) - WARN_ON_ONCE(smp_processor_id() != tick_do_timer_cpu); + /* Verify affinity of current kthread. */ + WARN_ON_ONCE(smp_processor_id() != tick_do_timer_cpu); /* Pick up current idle and NMI-nesting counter and check. */ cur = atomic_read(&rdtp->dynticks_idle); @@ -3068,11 +3066,10 @@ static void rcu_bind_gp_kthread(void) return; #ifdef CONFIG_NO_HZ_FULL_SYSIDLE cpu = tick_do_timer_cpu; - if (cpu >= 0 && cpu < nr_cpu_ids && raw_smp_processor_id() != cpu) + if (cpu >= 0 && cpu < nr_cpu_ids) set_cpus_allowed_ptr(current, cpumask_of(cpu)); #else /* #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */ - if (!is_housekeeping_cpu(raw_smp_processor_id())) - housekeeping_affine(current); + housekeeping_affine(current); #endif /* #else #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */ } diff --git a/kernel/rcu/tree_trace.c b/kernel/rcu/tree_trace.c index fbb6240509ea..f92361efd0f5 100644 --- a/kernel/rcu/tree_trace.c +++ b/kernel/rcu/tree_trace.c @@ -283,8 +283,8 @@ static void print_one_rcu_state(struct seq_file *m, struct rcu_state *rsp) seq_puts(m, "\n"); level = rnp->level; } - seq_printf(m, "%lx/%lx %c%c>%c %d:%d ^%d ", - rnp->qsmask, rnp->qsmaskinit, + seq_printf(m, "%lx/%lx->%lx %c%c>%c %d:%d ^%d ", + rnp->qsmask, rnp->qsmaskinit, rnp->qsmaskinitnext, ".G"[rnp->gp_tasks != NULL], ".E"[rnp->exp_tasks != NULL], ".T"[!list_empty(&rnp->blkd_tasks)], diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c index e0d31a345ee6..1f133350da01 100644 --- a/kernel/rcu/update.c +++ b/kernel/rcu/update.c @@ -62,6 +62,63 @@ MODULE_ALIAS("rcupdate"); module_param(rcu_expedited, int, 0); +#ifndef CONFIG_TINY_RCU + +static atomic_t rcu_expedited_nesting = + ATOMIC_INIT(IS_ENABLED(CONFIG_RCU_EXPEDITE_BOOT) ? 1 : 0); + +/* + * Should normal grace-period primitives be expedited? Intended for + * use within RCU. Note that this function takes the rcu_expedited + * sysfs/boot variable into account as well as the rcu_expedite_gp() + * nesting. So looping on rcu_unexpedite_gp() until rcu_gp_is_expedited() + * returns false is a -really- bad idea. + */ +bool rcu_gp_is_expedited(void) +{ + return rcu_expedited || atomic_read(&rcu_expedited_nesting); +} +EXPORT_SYMBOL_GPL(rcu_gp_is_expedited); + +/** + * rcu_expedite_gp - Expedite future RCU grace periods + * + * After a call to this function, future calls to synchronize_rcu() and + * friends act as the corresponding synchronize_rcu_expedited() function + * had instead been called. + */ +void rcu_expedite_gp(void) +{ + atomic_inc(&rcu_expedited_nesting); +} +EXPORT_SYMBOL_GPL(rcu_expedite_gp); + +/** + * rcu_unexpedite_gp - Cancel prior rcu_expedite_gp() invocation + * + * Undo a prior call to rcu_expedite_gp(). If all prior calls to + * rcu_expedite_gp() are undone by a subsequent call to rcu_unexpedite_gp(), + * and if the rcu_expedited sysfs/boot parameter is not set, then all + * subsequent calls to synchronize_rcu() and friends will return to + * their normal non-expedited behavior. + */ +void rcu_unexpedite_gp(void) +{ + atomic_dec(&rcu_expedited_nesting); +} +EXPORT_SYMBOL_GPL(rcu_unexpedite_gp); + +#endif /* #ifndef CONFIG_TINY_RCU */ + +/* + * Inform RCU of the end of the in-kernel boot sequence. + */ +void rcu_end_inkernel_boot(void) +{ + if (IS_ENABLED(CONFIG_RCU_EXPEDITE_BOOT)) + rcu_unexpedite_gp(); +} + #ifdef CONFIG_PREEMPT_RCU /* @@ -199,16 +256,13 @@ EXPORT_SYMBOL_GPL(rcu_read_lock_bh_held); #endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ -struct rcu_synchronize { - struct rcu_head head; - struct completion completion; -}; - -/* - * Awaken the corresponding synchronize_rcu() instance now that a - * grace period has elapsed. +/** + * wakeme_after_rcu() - Callback function to awaken a task after grace period + * @head: Pointer to rcu_head member within rcu_synchronize structure + * + * Awaken the corresponding task now that a grace period has elapsed. */ -static void wakeme_after_rcu(struct rcu_head *head) +void wakeme_after_rcu(struct rcu_head *head) { struct rcu_synchronize *rcu; diff --git a/kernel/sched/core.c b/kernel/sched/core.c index f0f831e8a345..f9123a82cbb6 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -306,6 +306,9 @@ __read_mostly int scheduler_running; */ int sysctl_sched_rt_runtime = 950000; +/* cpus with isolated domains */ +cpumask_var_t cpu_isolated_map; + /* * this_rq_lock - lock this runqueue and disable interrupts. */ @@ -690,6 +693,23 @@ static inline bool got_nohz_idle_kick(void) bool sched_can_stop_tick(void) { /* + * FIFO realtime policy runs the highest priority task. Other runnable + * tasks are of a lower priority. The scheduler tick does nothing. + */ + if (current->policy == SCHED_FIFO) + return true; + + /* + * Round-robin realtime tasks time slice with other tasks at the same + * realtime priority. Is this task the only one at this priority? + */ + if (current->policy == SCHED_RR) { + struct sched_rt_entity *rt_se = ¤t->rt; + + return rt_se->run_list.prev == rt_se->run_list.next; + } + + /* * More than one running task need preemption. * nr_running update is assumed to be visible * after IPI is sent from wakers. @@ -996,6 +1016,13 @@ void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags) rq_clock_skip_update(rq, true); } +static ATOMIC_NOTIFIER_HEAD(task_migration_notifier); + +void register_task_migration_notifier(struct notifier_block *n) +{ + atomic_notifier_chain_register(&task_migration_notifier, n); +} + #ifdef CONFIG_SMP void set_task_cpu(struct task_struct *p, unsigned int new_cpu) { @@ -1026,10 +1053,18 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu) trace_sched_migrate_task(p, new_cpu); if (task_cpu(p) != new_cpu) { + struct task_migration_notifier tmn; + if (p->sched_class->migrate_task_rq) p->sched_class->migrate_task_rq(p, new_cpu); p->se.nr_migrations++; perf_sw_event_sched(PERF_COUNT_SW_CPU_MIGRATIONS, 1, 0); + + tmn.task = p; + tmn.from_cpu = task_cpu(p); + tmn.to_cpu = new_cpu; + + atomic_notifier_call_chain(&task_migration_notifier, 0, &tmn); } __set_task_cpu(p, new_cpu); @@ -2818,7 +2853,7 @@ asmlinkage __visible void __sched schedule_user(void) * we find a better solution. * * NB: There are buggy callers of this function. Ideally we - * should warn if prev_state != IN_USER, but that will trigger + * should warn if prev_state != CONTEXT_USER, but that will trigger * too frequently to make sense yet. */ enum ctx_state prev_state = exception_enter(); @@ -3034,6 +3069,8 @@ void rt_mutex_setprio(struct task_struct *p, int prio) } else { if (dl_prio(oldprio)) p->dl.dl_boosted = 0; + if (rt_prio(oldprio)) + p->rt.timeout = 0; p->sched_class = &fair_sched_class; } @@ -5318,36 +5355,13 @@ static int sched_cpu_active(struct notifier_block *nfb, static int sched_cpu_inactive(struct notifier_block *nfb, unsigned long action, void *hcpu) { - unsigned long flags; - long cpu = (long)hcpu; - struct dl_bw *dl_b; - switch (action & ~CPU_TASKS_FROZEN) { case CPU_DOWN_PREPARE: - set_cpu_active(cpu, false); - - /* explicitly allow suspend */ - if (!(action & CPU_TASKS_FROZEN)) { - bool overflow; - int cpus; - - rcu_read_lock_sched(); - dl_b = dl_bw_of(cpu); - - raw_spin_lock_irqsave(&dl_b->lock, flags); - cpus = dl_bw_cpus(cpu); - overflow = __dl_overflow(dl_b, cpus, 0, 0); - raw_spin_unlock_irqrestore(&dl_b->lock, flags); - - rcu_read_unlock_sched(); - - if (overflow) - return notifier_from_errno(-EBUSY); - } + set_cpu_active((long)hcpu, false); return NOTIFY_OK; + default: + return NOTIFY_DONE; } - - return NOTIFY_DONE; } static int __init migration_init(void) @@ -5428,17 +5442,6 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level, break; } - /* - * Even though we initialize ->capacity to something semi-sane, - * we leave capacity_orig unset. This allows us to detect if - * domain iteration is still funny without causing /0 traps. - */ - if (!group->sgc->capacity_orig) { - printk(KERN_CONT "\n"); - printk(KERN_ERR "ERROR: domain->cpu_capacity not set\n"); - break; - } - if (!cpumask_weight(sched_group_cpus(group))) { printk(KERN_CONT "\n"); printk(KERN_ERR "ERROR: empty group\n"); @@ -5811,9 +5814,6 @@ cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu) update_top_cache_domain(cpu); } -/* cpus with isolated domains */ -static cpumask_var_t cpu_isolated_map; - /* Setup the mask of cpus configured for isolated domains */ static int __init isolated_cpu_setup(char *str) { @@ -5922,7 +5922,6 @@ build_overlap_sched_groups(struct sched_domain *sd, int cpu) * die on a /0 trap. */ sg->sgc->capacity = SCHED_CAPACITY_SCALE * cpumask_weight(sg_span); - sg->sgc->capacity_orig = sg->sgc->capacity; /* * Make sure the first group of this domain contains the @@ -6233,6 +6232,7 @@ sd_init(struct sched_domain_topology_level *tl, int cpu) */ if (sd->flags & SD_SHARE_CPUCAPACITY) { + sd->flags |= SD_PREFER_SIBLING; sd->imbalance_pct = 110; sd->smt_gain = 1178; /* ~15% */ @@ -6998,7 +6998,6 @@ static int cpuset_cpu_active(struct notifier_block *nfb, unsigned long action, */ case CPU_ONLINE: - case CPU_DOWN_FAILED: cpuset_update_active_cpus(true); break; default: @@ -7010,8 +7009,30 @@ static int cpuset_cpu_active(struct notifier_block *nfb, unsigned long action, static int cpuset_cpu_inactive(struct notifier_block *nfb, unsigned long action, void *hcpu) { - switch (action) { + unsigned long flags; + long cpu = (long)hcpu; + struct dl_bw *dl_b; + + switch (action & ~CPU_TASKS_FROZEN) { case CPU_DOWN_PREPARE: + /* explicitly allow suspend */ + if (!(action & CPU_TASKS_FROZEN)) { + bool overflow; + int cpus; + + rcu_read_lock_sched(); + dl_b = dl_bw_of(cpu); + + raw_spin_lock_irqsave(&dl_b->lock, flags); + cpus = dl_bw_cpus(cpu); + overflow = __dl_overflow(dl_b, cpus, 0, 0); + raw_spin_unlock_irqrestore(&dl_b->lock, flags); + + rcu_read_unlock_sched(); + + if (overflow) + return notifier_from_errno(-EBUSY); + } cpuset_update_active_cpus(false); break; case CPU_DOWN_PREPARE_FROZEN: @@ -7156,8 +7177,8 @@ void __init sched_init(void) rq->calc_load_active = 0; rq->calc_load_update = jiffies + LOAD_FREQ; init_cfs_rq(&rq->cfs); - init_rt_rq(&rq->rt, rq); - init_dl_rq(&rq->dl, rq); + init_rt_rq(&rq->rt); + init_dl_rq(&rq->dl); #ifdef CONFIG_FAIR_GROUP_SCHED root_task_group.shares = ROOT_TASK_GROUP_LOAD; INIT_LIST_HEAD(&rq->leaf_cfs_rq_list); @@ -7197,7 +7218,7 @@ void __init sched_init(void) #ifdef CONFIG_SMP rq->sd = NULL; rq->rd = NULL; - rq->cpu_capacity = SCHED_CAPACITY_SCALE; + rq->cpu_capacity = rq->cpu_capacity_orig = SCHED_CAPACITY_SCALE; rq->post_schedule = 0; rq->active_balance = 0; rq->next_balance = jiffies; @@ -7796,7 +7817,7 @@ static int sched_rt_global_constraints(void) } #endif /* CONFIG_RT_GROUP_SCHED */ -static int sched_dl_global_constraints(void) +static int sched_dl_global_validate(void) { u64 runtime = global_rt_runtime(); u64 period = global_rt_period(); @@ -7897,11 +7918,11 @@ int sched_rt_handler(struct ctl_table *table, int write, if (ret) goto undo; - ret = sched_rt_global_constraints(); + ret = sched_dl_global_validate(); if (ret) goto undo; - ret = sched_dl_global_constraints(); + ret = sched_rt_global_constraints(); if (ret) goto undo; diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index 3fa8fa6d9403..5e95145088fd 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -69,7 +69,7 @@ void init_dl_bw(struct dl_bw *dl_b) dl_b->total_bw = 0; } -void init_dl_rq(struct dl_rq *dl_rq, struct rq *rq) +void init_dl_rq(struct dl_rq *dl_rq) { dl_rq->rb_root = RB_ROOT; @@ -218,6 +218,52 @@ static inline void set_post_schedule(struct rq *rq) rq->post_schedule = has_pushable_dl_tasks(rq); } +static struct rq *find_lock_later_rq(struct task_struct *task, struct rq *rq); + +static void dl_task_offline_migration(struct rq *rq, struct task_struct *p) +{ + struct rq *later_rq = NULL; + bool fallback = false; + + later_rq = find_lock_later_rq(p, rq); + + if (!later_rq) { + int cpu; + + /* + * If we cannot preempt any rq, fall back to pick any + * online cpu. + */ + fallback = true; + cpu = cpumask_any_and(cpu_active_mask, tsk_cpus_allowed(p)); + if (cpu >= nr_cpu_ids) { + /* + * Fail to find any suitable cpu. + * The task will never come back! + */ + BUG_ON(dl_bandwidth_enabled()); + + /* + * If admission control is disabled we + * try a little harder to let the task + * run. + */ + cpu = cpumask_any(cpu_active_mask); + } + later_rq = cpu_rq(cpu); + double_lock_balance(rq, later_rq); + } + + deactivate_task(rq, p, 0); + set_task_cpu(p, later_rq->cpu); + activate_task(later_rq, p, ENQUEUE_REPLENISH); + + if (!fallback) + resched_curr(later_rq); + + double_unlock_balance(rq, later_rq); +} + #else static inline @@ -514,7 +560,7 @@ static enum hrtimer_restart dl_task_timer(struct hrtimer *timer) unsigned long flags; struct rq *rq; - rq = task_rq_lock(current, &flags); + rq = task_rq_lock(p, &flags); /* * We need to take care of several possible races here: @@ -536,6 +582,17 @@ static enum hrtimer_restart dl_task_timer(struct hrtimer *timer) sched_clock_tick(); update_rq_clock(rq); +#ifdef CONFIG_SMP + /* + * If we find that the rq the task was on is no longer + * available, we need to select a new rq. + */ + if (unlikely(!rq->online)) { + dl_task_offline_migration(rq, p); + goto unlock; + } +#endif + /* * If the throttle happened during sched-out; like: * @@ -569,7 +626,7 @@ static enum hrtimer_restart dl_task_timer(struct hrtimer *timer) push_dl_task(rq); #endif unlock: - task_rq_unlock(rq, current, &flags); + task_rq_unlock(rq, p, &flags); return HRTIMER_NORESTART; } @@ -914,6 +971,12 @@ static void yield_task_dl(struct rq *rq) } update_rq_clock(rq); update_curr_dl(rq); + /* + * Tell update_rq_clock() that we've just updated, + * so we don't do microscopic update in schedule() + * and double the fastpath cost. + */ + rq_clock_skip_update(rq, true); } #ifdef CONFIG_SMP @@ -1659,14 +1722,6 @@ static void switched_to_dl(struct rq *rq, struct task_struct *p) { int check_resched = 1; - /* - * If p is throttled, don't consider the possibility - * of preempting rq->curr, the check will be done right - * after its runtime will get replenished. - */ - if (unlikely(p->dl.dl_throttled)) - return; - if (task_on_rq_queued(p) && rq->curr != p) { #ifdef CONFIG_SMP if (p->nr_cpus_allowed > 1 && rq->dl.overloaded && diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index 8baaf858d25c..a245c1fc6f0a 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -71,7 +71,7 @@ static void print_cfs_group_stats(struct seq_file *m, int cpu, struct task_group if (!se) { struct sched_avg *avg = &cpu_rq(cpu)->avg; P(avg->runnable_avg_sum); - P(avg->runnable_avg_period); + P(avg->avg_period); return; } @@ -94,8 +94,10 @@ static void print_cfs_group_stats(struct seq_file *m, int cpu, struct task_group P(se->load.weight); #ifdef CONFIG_SMP P(se->avg.runnable_avg_sum); - P(se->avg.runnable_avg_period); + P(se->avg.running_avg_sum); + P(se->avg.avg_period); P(se->avg.load_avg_contrib); + P(se->avg.utilization_avg_contrib); P(se->avg.decay_count); #endif #undef PN @@ -214,6 +216,8 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq) cfs_rq->runnable_load_avg); SEQ_printf(m, " .%-30s: %ld\n", "blocked_load_avg", cfs_rq->blocked_load_avg); + SEQ_printf(m, " .%-30s: %ld\n", "utilization_load_avg", + cfs_rq->utilization_load_avg); #ifdef CONFIG_FAIR_GROUP_SCHED SEQ_printf(m, " .%-30s: %ld\n", "tg_load_contrib", cfs_rq->tg_load_contrib); @@ -636,8 +640,10 @@ void proc_sched_show_task(struct task_struct *p, struct seq_file *m) P(se.load.weight); #ifdef CONFIG_SMP P(se.avg.runnable_avg_sum); - P(se.avg.runnable_avg_period); + P(se.avg.running_avg_sum); + P(se.avg.avg_period); P(se.avg.load_avg_contrib); + P(se.avg.utilization_avg_contrib); P(se.avg.decay_count); #endif P(policy); diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 7ce18f3c097a..ffeaa4105e48 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -670,6 +670,7 @@ static int select_idle_sibling(struct task_struct *p, int cpu); static unsigned long task_h_load(struct task_struct *p); static inline void __update_task_entity_contrib(struct sched_entity *se); +static inline void __update_task_entity_utilization(struct sched_entity *se); /* Give new task start runnable values to heavy its load in infant time */ void init_task_runnable_average(struct task_struct *p) @@ -677,9 +678,10 @@ void init_task_runnable_average(struct task_struct *p) u32 slice; slice = sched_slice(task_cfs_rq(p), &p->se) >> 10; - p->se.avg.runnable_avg_sum = slice; - p->se.avg.runnable_avg_period = slice; + p->se.avg.runnable_avg_sum = p->se.avg.running_avg_sum = slice; + p->se.avg.avg_period = slice; __update_task_entity_contrib(&p->se); + __update_task_entity_utilization(&p->se); } #else void init_task_runnable_average(struct task_struct *p) @@ -1196,9 +1198,11 @@ static void task_numa_assign(struct task_numa_env *env, static bool load_too_imbalanced(long src_load, long dst_load, struct task_numa_env *env) { - long imb, old_imb; - long orig_src_load, orig_dst_load; long src_capacity, dst_capacity; + long orig_src_load; + long load_a, load_b; + long moved_load; + long imb; /* * The load is corrected for the CPU capacity available on each node. @@ -1211,30 +1215,39 @@ static bool load_too_imbalanced(long src_load, long dst_load, dst_capacity = env->dst_stats.compute_capacity; /* We care about the slope of the imbalance, not the direction. */ - if (dst_load < src_load) - swap(dst_load, src_load); + load_a = dst_load; + load_b = src_load; + if (load_a < load_b) + swap(load_a, load_b); /* Is the difference below the threshold? */ - imb = dst_load * src_capacity * 100 - - src_load * dst_capacity * env->imbalance_pct; + imb = load_a * src_capacity * 100 - + load_b * dst_capacity * env->imbalance_pct; if (imb <= 0) return false; /* * The imbalance is above the allowed threshold. - * Compare it with the old imbalance. + * Allow a move that brings us closer to a balanced situation, + * without moving things past the point of balance. */ orig_src_load = env->src_stats.load; - orig_dst_load = env->dst_stats.load; - if (orig_dst_load < orig_src_load) - swap(orig_dst_load, orig_src_load); - - old_imb = orig_dst_load * src_capacity * 100 - - orig_src_load * dst_capacity * env->imbalance_pct; + /* + * In a task swap, there will be one load moving from src to dst, + * and another moving back. This is the net sum of both moves. + * A simple task move will always have a positive value. + * Allow the move if it brings the system closer to a balanced + * situation, without crossing over the balance point. + */ + moved_load = orig_src_load - src_load; - /* Would this change make things worse? */ - return (imb > old_imb); + if (moved_load > 0) + /* Moving src -> dst. Did we overshoot balance? */ + return src_load * dst_capacity < dst_load * src_capacity; + else + /* Moving dst -> src. Did we overshoot balance? */ + return dst_load * src_capacity < src_load * dst_capacity; } /* @@ -1609,9 +1622,11 @@ static void update_task_scan_period(struct task_struct *p, /* * If there were no record hinting faults then either the task is * completely idle or all activity is areas that are not of interest - * to automatic numa balancing. Scan slower + * to automatic numa balancing. Related to that, if there were failed + * migration then it implies we are migrating too quickly or the local + * node is overloaded. In either case, scan slower */ - if (local + shared == 0) { + if (local + shared == 0 || p->numa_faults_locality[2]) { p->numa_scan_period = min(p->numa_scan_period_max, p->numa_scan_period << 1); @@ -1673,7 +1688,7 @@ static u64 numa_get_avg_runtime(struct task_struct *p, u64 *period) *period = now - p->last_task_numa_placement; } else { delta = p->se.avg.runnable_avg_sum; - *period = p->se.avg.runnable_avg_period; + *period = p->se.avg.avg_period; } p->last_sum_exec_runtime = runtime; @@ -1763,6 +1778,8 @@ static int preferred_group_nid(struct task_struct *p, int nid) } } /* Next round, evaluate the nodes within max_group. */ + if (!max_faults) + break; nodes = max_group; } return nid; @@ -2080,6 +2097,8 @@ void task_numa_fault(int last_cpupid, int mem_node, int pages, int flags) if (migrated) p->numa_pages_migrated += pages; + if (flags & TNF_MIGRATE_FAIL) + p->numa_faults_locality[2] += pages; p->numa_faults[task_faults_idx(NUMA_MEMBUF, mem_node, priv)] += pages; p->numa_faults[task_faults_idx(NUMA_CPUBUF, cpu_node, priv)] += pages; @@ -2161,8 +2180,10 @@ void task_numa_work(struct callback_head *work) vma = mm->mmap; } for (; vma; vma = vma->vm_next) { - if (!vma_migratable(vma) || !vma_policy_mof(vma)) + if (!vma_migratable(vma) || !vma_policy_mof(vma) || + is_vm_hugetlb_page(vma)) { continue; + } /* * Shared library pages mapped by multiple processes are not @@ -2497,13 +2518,15 @@ static u32 __compute_runnable_contrib(u64 n) * load_avg = u_0` + y*(u_0 + u_1*y + u_2*y^2 + ... ) * = u_0 + u_1*y + u_2*y^2 + ... [re-labeling u_i --> u_{i+1}] */ -static __always_inline int __update_entity_runnable_avg(u64 now, +static __always_inline int __update_entity_runnable_avg(u64 now, int cpu, struct sched_avg *sa, - int runnable) + int runnable, + int running) { u64 delta, periods; u32 runnable_contrib; int delta_w, decayed = 0; + unsigned long scale_freq = arch_scale_freq_capacity(NULL, cpu); delta = now - sa->last_runnable_update; /* @@ -2525,7 +2548,7 @@ static __always_inline int __update_entity_runnable_avg(u64 now, sa->last_runnable_update = now; /* delta_w is the amount already accumulated against our next period */ - delta_w = sa->runnable_avg_period % 1024; + delta_w = sa->avg_period % 1024; if (delta + delta_w >= 1024) { /* period roll-over */ decayed = 1; @@ -2538,7 +2561,10 @@ static __always_inline int __update_entity_runnable_avg(u64 now, delta_w = 1024 - delta_w; if (runnable) sa->runnable_avg_sum += delta_w; - sa->runnable_avg_period += delta_w; + if (running) + sa->running_avg_sum += delta_w * scale_freq + >> SCHED_CAPACITY_SHIFT; + sa->avg_period += delta_w; delta -= delta_w; @@ -2548,20 +2574,28 @@ static __always_inline int __update_entity_runnable_avg(u64 now, sa->runnable_avg_sum = decay_load(sa->runnable_avg_sum, periods + 1); - sa->runnable_avg_period = decay_load(sa->runnable_avg_period, + sa->running_avg_sum = decay_load(sa->running_avg_sum, + periods + 1); + sa->avg_period = decay_load(sa->avg_period, periods + 1); /* Efficiently calculate \sum (1..n_period) 1024*y^i */ runnable_contrib = __compute_runnable_contrib(periods); if (runnable) sa->runnable_avg_sum += runnable_contrib; - sa->runnable_avg_period += runnable_contrib; + if (running) + sa->running_avg_sum += runnable_contrib * scale_freq + >> SCHED_CAPACITY_SHIFT; + sa->avg_period += runnable_contrib; } /* Remainder of delta accrued against u_0` */ if (runnable) sa->runnable_avg_sum += delta; - sa->runnable_avg_period += delta; + if (running) + sa->running_avg_sum += delta * scale_freq + >> SCHED_CAPACITY_SHIFT; + sa->avg_period += delta; return decayed; } @@ -2578,6 +2612,8 @@ static inline u64 __synchronize_entity_decay(struct sched_entity *se) return 0; se->avg.load_avg_contrib = decay_load(se->avg.load_avg_contrib, decays); + se->avg.utilization_avg_contrib = + decay_load(se->avg.utilization_avg_contrib, decays); return decays; } @@ -2613,7 +2649,7 @@ static inline void __update_tg_runnable_avg(struct sched_avg *sa, /* The fraction of a cpu used by this cfs_rq */ contrib = div_u64((u64)sa->runnable_avg_sum << NICE_0_SHIFT, - sa->runnable_avg_period + 1); + sa->avg_period + 1); contrib -= cfs_rq->tg_runnable_contrib; if (abs(contrib) > cfs_rq->tg_runnable_contrib / 64) { @@ -2666,7 +2702,8 @@ static inline void __update_group_entity_contrib(struct sched_entity *se) static inline void update_rq_runnable_avg(struct rq *rq, int runnable) { - __update_entity_runnable_avg(rq_clock_task(rq), &rq->avg, runnable); + __update_entity_runnable_avg(rq_clock_task(rq), cpu_of(rq), &rq->avg, + runnable, runnable); __update_tg_runnable_avg(&rq->avg, &rq->cfs); } #else /* CONFIG_FAIR_GROUP_SCHED */ @@ -2684,7 +2721,7 @@ static inline void __update_task_entity_contrib(struct sched_entity *se) /* avoid overflowing a 32-bit type w/ SCHED_LOAD_SCALE */ contrib = se->avg.runnable_avg_sum * scale_load_down(se->load.weight); - contrib /= (se->avg.runnable_avg_period + 1); + contrib /= (se->avg.avg_period + 1); se->avg.load_avg_contrib = scale_load(contrib); } @@ -2703,6 +2740,30 @@ static long __update_entity_load_avg_contrib(struct sched_entity *se) return se->avg.load_avg_contrib - old_contrib; } + +static inline void __update_task_entity_utilization(struct sched_entity *se) +{ + u32 contrib; + + /* avoid overflowing a 32-bit type w/ SCHED_LOAD_SCALE */ + contrib = se->avg.running_avg_sum * scale_load_down(SCHED_LOAD_SCALE); + contrib /= (se->avg.avg_period + 1); + se->avg.utilization_avg_contrib = scale_load(contrib); +} + +static long __update_entity_utilization_avg_contrib(struct sched_entity *se) +{ + long old_contrib = se->avg.utilization_avg_contrib; + + if (entity_is_task(se)) + __update_task_entity_utilization(se); + else + se->avg.utilization_avg_contrib = + group_cfs_rq(se)->utilization_load_avg; + + return se->avg.utilization_avg_contrib - old_contrib; +} + static inline void subtract_blocked_load_contrib(struct cfs_rq *cfs_rq, long load_contrib) { @@ -2719,7 +2780,8 @@ static inline void update_entity_load_avg(struct sched_entity *se, int update_cfs_rq) { struct cfs_rq *cfs_rq = cfs_rq_of(se); - long contrib_delta; + long contrib_delta, utilization_delta; + int cpu = cpu_of(rq_of(cfs_rq)); u64 now; /* @@ -2731,18 +2793,22 @@ static inline void update_entity_load_avg(struct sched_entity *se, else now = cfs_rq_clock_task(group_cfs_rq(se)); - if (!__update_entity_runnable_avg(now, &se->avg, se->on_rq)) + if (!__update_entity_runnable_avg(now, cpu, &se->avg, se->on_rq, + cfs_rq->curr == se)) return; contrib_delta = __update_entity_load_avg_contrib(se); + utilization_delta = __update_entity_utilization_avg_contrib(se); if (!update_cfs_rq) return; - if (se->on_rq) + if (se->on_rq) { cfs_rq->runnable_load_avg += contrib_delta; - else + cfs_rq->utilization_load_avg += utilization_delta; + } else { subtract_blocked_load_contrib(cfs_rq, -contrib_delta); + } } /* @@ -2817,6 +2883,7 @@ static inline void enqueue_entity_load_avg(struct cfs_rq *cfs_rq, } cfs_rq->runnable_load_avg += se->avg.load_avg_contrib; + cfs_rq->utilization_load_avg += se->avg.utilization_avg_contrib; /* we force update consideration on load-balancer moves */ update_cfs_rq_blocked_load(cfs_rq, !wakeup); } @@ -2835,6 +2902,7 @@ static inline void dequeue_entity_load_avg(struct cfs_rq *cfs_rq, update_cfs_rq_blocked_load(cfs_rq, !sleep); cfs_rq->runnable_load_avg -= se->avg.load_avg_contrib; + cfs_rq->utilization_load_avg -= se->avg.utilization_avg_contrib; if (sleep) { cfs_rq->blocked_load_avg += se->avg.load_avg_contrib; se->avg.decay_count = atomic64_read(&cfs_rq->decay_counter); @@ -3172,6 +3240,7 @@ set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se) */ update_stats_wait_end(cfs_rq, se); __dequeue_entity(cfs_rq, se); + update_entity_load_avg(se, 1); } update_stats_curr_start(cfs_rq, se); @@ -4298,6 +4367,11 @@ static unsigned long capacity_of(int cpu) return cpu_rq(cpu)->cpu_capacity; } +static unsigned long capacity_orig_of(int cpu) +{ + return cpu_rq(cpu)->cpu_capacity_orig; +} + static unsigned long cpu_avg_load_per_task(int cpu) { struct rq *rq = cpu_rq(cpu); @@ -4711,6 +4785,33 @@ next: done: return target; } +/* + * get_cpu_usage returns the amount of capacity of a CPU that is used by CFS + * tasks. The unit of the return value must be the one of capacity so we can + * compare the usage with the capacity of the CPU that is available for CFS + * task (ie cpu_capacity). + * cfs.utilization_load_avg is the sum of running time of runnable tasks on a + * CPU. It represents the amount of utilization of a CPU in the range + * [0..SCHED_LOAD_SCALE]. The usage of a CPU can't be higher than the full + * capacity of the CPU because it's about the running time on this CPU. + * Nevertheless, cfs.utilization_load_avg can be higher than SCHED_LOAD_SCALE + * because of unfortunate rounding in avg_period and running_load_avg or just + * after migrating tasks until the average stabilizes with the new running + * time. So we need to check that the usage stays into the range + * [0..cpu_capacity_orig] and cap if necessary. + * Without capping the usage, a group could be seen as overloaded (CPU0 usage + * at 121% + CPU1 usage at 80%) whereas CPU1 has 20% of available capacity + */ +static int get_cpu_usage(int cpu) +{ + unsigned long usage = cpu_rq(cpu)->cfs.utilization_load_avg; + unsigned long capacity = capacity_orig_of(cpu); + + if (usage >= SCHED_LOAD_SCALE) + return capacity; + + return (usage * capacity) >> SCHED_LOAD_SHIFT; +} /* * select_task_rq_fair: Select target runqueue for the waking task in domains @@ -5837,12 +5938,12 @@ struct sg_lb_stats { unsigned long sum_weighted_load; /* Weighted load of group's tasks */ unsigned long load_per_task; unsigned long group_capacity; + unsigned long group_usage; /* Total usage of the group */ unsigned int sum_nr_running; /* Nr tasks running in the group */ - unsigned int group_capacity_factor; unsigned int idle_cpus; unsigned int group_weight; enum group_type group_type; - int group_has_free_capacity; + int group_no_capacity; #ifdef CONFIG_NUMA_BALANCING unsigned int nr_numa_running; unsigned int nr_preferred_running; @@ -5913,16 +6014,6 @@ static inline int get_sd_load_idx(struct sched_domain *sd, return load_idx; } -static unsigned long default_scale_capacity(struct sched_domain *sd, int cpu) -{ - return SCHED_CAPACITY_SCALE; -} - -unsigned long __weak arch_scale_freq_capacity(struct sched_domain *sd, int cpu) -{ - return default_scale_capacity(sd, cpu); -} - static unsigned long default_scale_cpu_capacity(struct sched_domain *sd, int cpu) { if ((sd->flags & SD_SHARE_CPUCAPACITY) && (sd->span_weight > 1)) @@ -5939,7 +6030,7 @@ unsigned long __weak arch_scale_cpu_capacity(struct sched_domain *sd, int cpu) static unsigned long scale_rt_capacity(int cpu) { struct rq *rq = cpu_rq(cpu); - u64 total, available, age_stamp, avg; + u64 total, used, age_stamp, avg; s64 delta; /* @@ -5955,19 +6046,12 @@ static unsigned long scale_rt_capacity(int cpu) total = sched_avg_period() + delta; - if (unlikely(total < avg)) { - /* Ensures that capacity won't end up being negative */ - available = 0; - } else { - available = total - avg; - } - - if (unlikely((s64)total < SCHED_CAPACITY_SCALE)) - total = SCHED_CAPACITY_SCALE; + used = div_u64(avg, total); - total >>= SCHED_CAPACITY_SHIFT; + if (likely(used < SCHED_CAPACITY_SCALE)) + return SCHED_CAPACITY_SCALE - used; - return div_u64(available, total); + return 1; } static void update_cpu_capacity(struct sched_domain *sd, int cpu) @@ -5982,14 +6066,7 @@ static void update_cpu_capacity(struct sched_domain *sd, int cpu) capacity >>= SCHED_CAPACITY_SHIFT; - sdg->sgc->capacity_orig = capacity; - - if (sched_feat(ARCH_CAPACITY)) - capacity *= arch_scale_freq_capacity(sd, cpu); - else - capacity *= default_scale_capacity(sd, cpu); - - capacity >>= SCHED_CAPACITY_SHIFT; + cpu_rq(cpu)->cpu_capacity_orig = capacity; capacity *= scale_rt_capacity(cpu); capacity >>= SCHED_CAPACITY_SHIFT; @@ -6005,7 +6082,7 @@ void update_group_capacity(struct sched_domain *sd, int cpu) { struct sched_domain *child = sd->child; struct sched_group *group, *sdg = sd->groups; - unsigned long capacity, capacity_orig; + unsigned long capacity; unsigned long interval; interval = msecs_to_jiffies(sd->balance_interval); @@ -6017,7 +6094,7 @@ void update_group_capacity(struct sched_domain *sd, int cpu) return; } - capacity_orig = capacity = 0; + capacity = 0; if (child->flags & SD_OVERLAP) { /* @@ -6037,19 +6114,15 @@ void update_group_capacity(struct sched_domain *sd, int cpu) * Use capacity_of(), which is set irrespective of domains * in update_cpu_capacity(). * - * This avoids capacity/capacity_orig from being 0 and + * This avoids capacity from being 0 and * causing divide-by-zero issues on boot. - * - * Runtime updates will correct capacity_orig. */ if (unlikely(!rq->sd)) { - capacity_orig += capacity_of(cpu); capacity += capacity_of(cpu); continue; } sgc = rq->sd->groups->sgc; - capacity_orig += sgc->capacity_orig; capacity += sgc->capacity; } } else { @@ -6060,39 +6133,24 @@ void update_group_capacity(struct sched_domain *sd, int cpu) group = child->groups; do { - capacity_orig += group->sgc->capacity_orig; capacity += group->sgc->capacity; group = group->next; } while (group != child->groups); } - sdg->sgc->capacity_orig = capacity_orig; sdg->sgc->capacity = capacity; } /* - * Try and fix up capacity for tiny siblings, this is needed when - * things like SD_ASYM_PACKING need f_b_g to select another sibling - * which on its own isn't powerful enough. - * - * See update_sd_pick_busiest() and check_asym_packing(). + * Check whether the capacity of the rq has been noticeably reduced by side + * activity. The imbalance_pct is used for the threshold. + * Return true is the capacity is reduced */ static inline int -fix_small_capacity(struct sched_domain *sd, struct sched_group *group) +check_cpu_capacity(struct rq *rq, struct sched_domain *sd) { - /* - * Only siblings can have significantly less than SCHED_CAPACITY_SCALE - */ - if (!(sd->flags & SD_SHARE_CPUCAPACITY)) - return 0; - - /* - * If ~90% of the cpu_capacity is still there, we're good. - */ - if (group->sgc->capacity * 32 > group->sgc->capacity_orig * 29) - return 1; - - return 0; + return ((rq->cpu_capacity * sd->imbalance_pct) < + (rq->cpu_capacity_orig * 100)); } /* @@ -6130,37 +6188,56 @@ static inline int sg_imbalanced(struct sched_group *group) } /* - * Compute the group capacity factor. - * - * Avoid the issue where N*frac(smt_capacity) >= 1 creates 'phantom' cores by - * first dividing out the smt factor and computing the actual number of cores - * and limit unit capacity with that. + * group_has_capacity returns true if the group has spare capacity that could + * be used by some tasks. + * We consider that a group has spare capacity if the * number of task is + * smaller than the number of CPUs or if the usage is lower than the available + * capacity for CFS tasks. + * For the latter, we use a threshold to stabilize the state, to take into + * account the variance of the tasks' load and to return true if the available + * capacity in meaningful for the load balancer. + * As an example, an available capacity of 1% can appear but it doesn't make + * any benefit for the load balance. */ -static inline int sg_capacity_factor(struct lb_env *env, struct sched_group *group) +static inline bool +group_has_capacity(struct lb_env *env, struct sg_lb_stats *sgs) { - unsigned int capacity_factor, smt, cpus; - unsigned int capacity, capacity_orig; + if (sgs->sum_nr_running < sgs->group_weight) + return true; - capacity = group->sgc->capacity; - capacity_orig = group->sgc->capacity_orig; - cpus = group->group_weight; + if ((sgs->group_capacity * 100) > + (sgs->group_usage * env->sd->imbalance_pct)) + return true; + + return false; +} - /* smt := ceil(cpus / capacity), assumes: 1 < smt_capacity < 2 */ - smt = DIV_ROUND_UP(SCHED_CAPACITY_SCALE * cpus, capacity_orig); - capacity_factor = cpus / smt; /* cores */ +/* + * group_is_overloaded returns true if the group has more tasks than it can + * handle. + * group_is_overloaded is not equals to !group_has_capacity because a group + * with the exact right number of tasks, has no more spare capacity but is not + * overloaded so both group_has_capacity and group_is_overloaded return + * false. + */ +static inline bool +group_is_overloaded(struct lb_env *env, struct sg_lb_stats *sgs) +{ + if (sgs->sum_nr_running <= sgs->group_weight) + return false; - capacity_factor = min_t(unsigned, - capacity_factor, DIV_ROUND_CLOSEST(capacity, SCHED_CAPACITY_SCALE)); - if (!capacity_factor) - capacity_factor = fix_small_capacity(env->sd, group); + if ((sgs->group_capacity * 100) < + (sgs->group_usage * env->sd->imbalance_pct)) + return true; - return capacity_factor; + return false; } -static enum group_type -group_classify(struct sched_group *group, struct sg_lb_stats *sgs) +static enum group_type group_classify(struct lb_env *env, + struct sched_group *group, + struct sg_lb_stats *sgs) { - if (sgs->sum_nr_running > sgs->group_capacity_factor) + if (sgs->group_no_capacity) return group_overloaded; if (sg_imbalanced(group)) @@ -6198,6 +6275,7 @@ static inline void update_sg_lb_stats(struct lb_env *env, load = source_load(i, load_idx); sgs->group_load += load; + sgs->group_usage += get_cpu_usage(i); sgs->sum_nr_running += rq->cfs.h_nr_running; if (rq->nr_running > 1) @@ -6220,11 +6298,9 @@ static inline void update_sg_lb_stats(struct lb_env *env, sgs->load_per_task = sgs->sum_weighted_load / sgs->sum_nr_running; sgs->group_weight = group->group_weight; - sgs->group_capacity_factor = sg_capacity_factor(env, group); - sgs->group_type = group_classify(group, sgs); - if (sgs->group_capacity_factor > sgs->sum_nr_running) - sgs->group_has_free_capacity = 1; + sgs->group_no_capacity = group_is_overloaded(env, sgs); + sgs->group_type = group_classify(env, group, sgs); } /** @@ -6346,18 +6422,19 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd /* * In case the child domain prefers tasks go to siblings - * first, lower the sg capacity factor to one so that we'll try + * first, lower the sg capacity so that we'll try * and move all the excess tasks away. We lower the capacity * of a group only if the local group has the capacity to fit - * these excess tasks, i.e. nr_running < group_capacity_factor. The - * extra check prevents the case where you always pull from the - * heaviest group when it is already under-utilized (possible - * with a large weight task outweighs the tasks on the system). + * these excess tasks. The extra check prevents the case where + * you always pull from the heaviest group when it is already + * under-utilized (possible with a large weight task outweighs + * the tasks on the system). */ if (prefer_sibling && sds->local && - sds->local_stat.group_has_free_capacity) { - sgs->group_capacity_factor = min(sgs->group_capacity_factor, 1U); - sgs->group_type = group_classify(sg, sgs); + group_has_capacity(env, &sds->local_stat) && + (sgs->sum_nr_running > 1)) { + sgs->group_no_capacity = 1; + sgs->group_type = group_overloaded; } if (update_sd_pick_busiest(env, sds, sg, sgs)) { @@ -6537,11 +6614,12 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s */ if (busiest->group_type == group_overloaded && local->group_type == group_overloaded) { - load_above_capacity = - (busiest->sum_nr_running - busiest->group_capacity_factor); - - load_above_capacity *= (SCHED_LOAD_SCALE * SCHED_CAPACITY_SCALE); - load_above_capacity /= busiest->group_capacity; + load_above_capacity = busiest->sum_nr_running * + SCHED_LOAD_SCALE; + if (load_above_capacity > busiest->group_capacity) + load_above_capacity -= busiest->group_capacity; + else + load_above_capacity = ~0UL; } /* @@ -6604,6 +6682,7 @@ static struct sched_group *find_busiest_group(struct lb_env *env) local = &sds.local_stat; busiest = &sds.busiest_stat; + /* ASYM feature bypasses nice load balance check */ if ((env->idle == CPU_IDLE || env->idle == CPU_NEWLY_IDLE) && check_asym_packing(env, &sds)) return sds.busiest; @@ -6624,8 +6703,8 @@ static struct sched_group *find_busiest_group(struct lb_env *env) goto force_balance; /* SD_BALANCE_NEWIDLE trumps SMP nice when underutilized */ - if (env->idle == CPU_NEWLY_IDLE && local->group_has_free_capacity && - !busiest->group_has_free_capacity) + if (env->idle == CPU_NEWLY_IDLE && group_has_capacity(env, local) && + busiest->group_no_capacity) goto force_balance; /* @@ -6684,7 +6763,7 @@ static struct rq *find_busiest_queue(struct lb_env *env, int i; for_each_cpu_and(i, sched_group_cpus(group), env->cpus) { - unsigned long capacity, capacity_factor, wl; + unsigned long capacity, wl; enum fbq_type rt; rq = cpu_rq(i); @@ -6713,9 +6792,6 @@ static struct rq *find_busiest_queue(struct lb_env *env, continue; capacity = capacity_of(i); - capacity_factor = DIV_ROUND_CLOSEST(capacity, SCHED_CAPACITY_SCALE); - if (!capacity_factor) - capacity_factor = fix_small_capacity(env->sd, group); wl = weighted_cpuload(i); @@ -6723,7 +6799,9 @@ static struct rq *find_busiest_queue(struct lb_env *env, * When comparing with imbalance, use weighted_cpuload() * which is not scaled with the cpu capacity. */ - if (capacity_factor && rq->nr_running == 1 && wl > env->imbalance) + + if (rq->nr_running == 1 && wl > env->imbalance && + !check_cpu_capacity(rq, env->sd)) continue; /* @@ -6771,6 +6849,19 @@ static int need_active_balance(struct lb_env *env) return 1; } + /* + * The dst_cpu is idle and the src_cpu CPU has only 1 CFS task. + * It's worth migrating the task if the src_cpu's capacity is reduced + * because of other sched_class or IRQs if more capacity stays + * available on dst_cpu. + */ + if ((env->idle != CPU_NOT_IDLE) && + (env->src_rq->cfs.h_nr_running == 1)) { + if ((check_cpu_capacity(env->src_rq, sd)) && + (capacity_of(env->src_cpu)*sd->imbalance_pct < capacity_of(env->dst_cpu)*100)) + return 1; + } + return unlikely(sd->nr_balance_failed > sd->cache_nice_tries+2); } @@ -6870,6 +6961,9 @@ redo: schedstat_add(sd, lb_imbalance[idle], env.imbalance); + env.src_cpu = busiest->cpu; + env.src_rq = busiest; + ld_moved = 0; if (busiest->nr_running > 1) { /* @@ -6879,8 +6973,6 @@ redo: * correctly treated as an imbalance. */ env.flags |= LBF_ALL_PINNED; - env.src_cpu = busiest->cpu; - env.src_rq = busiest; env.loop_max = min(sysctl_sched_nr_migrate, busiest->nr_running); more_balance: @@ -7580,22 +7672,25 @@ end: /* * Current heuristic for kicking the idle load balancer in the presence - * of an idle cpu is the system. + * of an idle cpu in the system. * - This rq has more than one task. - * - At any scheduler domain level, this cpu's scheduler group has multiple - * busy cpu's exceeding the group's capacity. + * - This rq has at least one CFS task and the capacity of the CPU is + * significantly reduced because of RT tasks or IRQs. + * - At parent of LLC scheduler domain level, this cpu's scheduler group has + * multiple busy cpu. * - For SD_ASYM_PACKING, if the lower numbered cpu's in the scheduler * domain span are idle. */ -static inline int nohz_kick_needed(struct rq *rq) +static inline bool nohz_kick_needed(struct rq *rq) { unsigned long now = jiffies; struct sched_domain *sd; struct sched_group_capacity *sgc; int nr_busy, cpu = rq->cpu; + bool kick = false; if (unlikely(rq->idle_balance)) - return 0; + return false; /* * We may be recently in ticked or tickless idle mode. At the first @@ -7609,38 +7704,46 @@ static inline int nohz_kick_needed(struct rq *rq) * balancing. */ if (likely(!atomic_read(&nohz.nr_cpus))) - return 0; + return false; if (time_before(now, nohz.next_balance)) - return 0; + return false; if (rq->nr_running >= 2) - goto need_kick; + return true; rcu_read_lock(); sd = rcu_dereference(per_cpu(sd_busy, cpu)); - if (sd) { sgc = sd->groups->sgc; nr_busy = atomic_read(&sgc->nr_busy_cpus); - if (nr_busy > 1) - goto need_kick_unlock; + if (nr_busy > 1) { + kick = true; + goto unlock; + } + } - sd = rcu_dereference(per_cpu(sd_asym, cpu)); + sd = rcu_dereference(rq->sd); + if (sd) { + if ((rq->cfs.h_nr_running >= 1) && + check_cpu_capacity(rq, sd)) { + kick = true; + goto unlock; + } + } + sd = rcu_dereference(per_cpu(sd_asym, cpu)); if (sd && (cpumask_first_and(nohz.idle_cpus_mask, - sched_domain_span(sd)) < cpu)) - goto need_kick_unlock; - - rcu_read_unlock(); - return 0; + sched_domain_span(sd)) < cpu)) { + kick = true; + goto unlock; + } -need_kick_unlock: +unlock: rcu_read_unlock(); -need_kick: - return 1; + return kick; } #else static void nohz_idle_balance(struct rq *this_rq, enum cpu_idle_type idle) { } @@ -7656,14 +7759,16 @@ static void run_rebalance_domains(struct softirq_action *h) enum cpu_idle_type idle = this_rq->idle_balance ? CPU_IDLE : CPU_NOT_IDLE; - rebalance_domains(this_rq, idle); - /* * If this cpu has a pending nohz_balance_kick, then do the * balancing on behalf of the other idle cpus whose ticks are - * stopped. + * stopped. Do nohz_idle_balance *before* rebalance_domains to + * give the idle cpus a chance to load balance. Else we may + * load balance only within the local sched_domain hierarchy + * and abort nohz_idle_balance altogether if we pull some load. */ nohz_idle_balance(this_rq, idle); + rebalance_domains(this_rq, idle); } /* diff --git a/kernel/sched/features.h b/kernel/sched/features.h index 90284d117fe6..91e33cd485f6 100644 --- a/kernel/sched/features.h +++ b/kernel/sched/features.h @@ -56,6 +56,19 @@ SCHED_FEAT(NONTASK_CAPACITY, true) */ SCHED_FEAT(TTWU_QUEUE, true) +#ifdef HAVE_RT_PUSH_IPI +/* + * In order to avoid a thundering herd attack of CPUs that are + * lowering their priorities at the same time, and there being + * a single CPU that has an RT task that can migrate and is waiting + * to run, where the other CPUs will try to take that CPUs + * rq lock and possibly create a large contention, sending an + * IPI to that CPU and let that CPU push the RT task to where + * it should go may be a better scenario. + */ +SCHED_FEAT(RT_PUSH_IPI, true) +#endif + SCHED_FEAT(FORCE_SD_OVERLAP, false) SCHED_FEAT(RT_RUNTIME_SHARE, true) SCHED_FEAT(LB_MIN, false) diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index 80014a178342..deef1caa94c6 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -158,8 +158,7 @@ static void cpuidle_idle_call(void) * is used from another cpu as a broadcast timer, this call may * fail if it is not available */ - if (broadcast && - clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_ENTER, &dev->cpu)) + if (broadcast && tick_broadcast_enter()) goto use_default; /* Take note of the planned idle state. */ @@ -176,7 +175,7 @@ static void cpuidle_idle_call(void) idle_set_state(this_rq(), NULL); if (broadcast) - clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_EXIT, &dev->cpu); + tick_broadcast_exit(); /* * Give the governor an opportunity to reflect on the outcome @@ -210,6 +209,8 @@ use_default: goto exit_idle; } +DEFINE_PER_CPU(bool, cpu_dead_idle); + /* * Generic idle loop implementation * @@ -234,8 +235,13 @@ static void cpu_idle_loop(void) check_pgt_cache(); rmb(); - if (cpu_is_offline(smp_processor_id())) + if (cpu_is_offline(smp_processor_id())) { + rcu_cpu_notify(NULL, CPU_DYING_IDLE, + (void *)(long)smp_processor_id()); + smp_mb(); /* all activity before dead. */ + this_cpu_write(cpu_dead_idle, true); arch_cpu_idle_dead(); + } local_irq_disable(); arch_cpu_idle_enter(); diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index f4d4b077eba0..575da76a3874 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -6,6 +6,7 @@ #include "sched.h" #include <linux/slab.h> +#include <linux/irq_work.h> int sched_rr_timeslice = RR_TIMESLICE; @@ -59,7 +60,11 @@ static void start_rt_bandwidth(struct rt_bandwidth *rt_b) raw_spin_unlock(&rt_b->rt_runtime_lock); } -void init_rt_rq(struct rt_rq *rt_rq, struct rq *rq) +#ifdef CONFIG_SMP +static void push_irq_work_func(struct irq_work *work); +#endif + +void init_rt_rq(struct rt_rq *rt_rq) { struct rt_prio_array *array; int i; @@ -78,7 +83,14 @@ void init_rt_rq(struct rt_rq *rt_rq, struct rq *rq) rt_rq->rt_nr_migratory = 0; rt_rq->overloaded = 0; plist_head_init(&rt_rq->pushable_tasks); + +#ifdef HAVE_RT_PUSH_IPI + rt_rq->push_flags = 0; + rt_rq->push_cpu = nr_cpu_ids; + raw_spin_lock_init(&rt_rq->push_lock); + init_irq_work(&rt_rq->push_work, push_irq_work_func); #endif +#endif /* CONFIG_SMP */ /* We start is dequeued state, because no RT tasks are queued */ rt_rq->rt_queued = 0; @@ -193,7 +205,7 @@ int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent) if (!rt_se) goto err_free_rq; - init_rt_rq(rt_rq, cpu_rq(i)); + init_rt_rq(rt_rq); rt_rq->rt_runtime = tg->rt_bandwidth.rt_runtime; init_tg_rt_entry(tg, rt_rq, rt_se, i, parent->rt_se[i]); } @@ -1778,6 +1790,164 @@ static void push_rt_tasks(struct rq *rq) ; } +#ifdef HAVE_RT_PUSH_IPI +/* + * The search for the next cpu always starts at rq->cpu and ends + * when we reach rq->cpu again. It will never return rq->cpu. + * This returns the next cpu to check, or nr_cpu_ids if the loop + * is complete. + * + * rq->rt.push_cpu holds the last cpu returned by this function, + * or if this is the first instance, it must hold rq->cpu. + */ +static int rto_next_cpu(struct rq *rq) +{ + int prev_cpu = rq->rt.push_cpu; + int cpu; + + cpu = cpumask_next(prev_cpu, rq->rd->rto_mask); + + /* + * If the previous cpu is less than the rq's CPU, then it already + * passed the end of the mask, and has started from the beginning. + * We end if the next CPU is greater or equal to rq's CPU. + */ + if (prev_cpu < rq->cpu) { + if (cpu >= rq->cpu) + return nr_cpu_ids; + + } else if (cpu >= nr_cpu_ids) { + /* + * We passed the end of the mask, start at the beginning. + * If the result is greater or equal to the rq's CPU, then + * the loop is finished. + */ + cpu = cpumask_first(rq->rd->rto_mask); + if (cpu >= rq->cpu) + return nr_cpu_ids; + } + rq->rt.push_cpu = cpu; + + /* Return cpu to let the caller know if the loop is finished or not */ + return cpu; +} + +static int find_next_push_cpu(struct rq *rq) +{ + struct rq *next_rq; + int cpu; + + while (1) { + cpu = rto_next_cpu(rq); + if (cpu >= nr_cpu_ids) + break; + next_rq = cpu_rq(cpu); + + /* Make sure the next rq can push to this rq */ + if (next_rq->rt.highest_prio.next < rq->rt.highest_prio.curr) + break; + } + + return cpu; +} + +#define RT_PUSH_IPI_EXECUTING 1 +#define RT_PUSH_IPI_RESTART 2 + +static void tell_cpu_to_push(struct rq *rq) +{ + int cpu; + + if (rq->rt.push_flags & RT_PUSH_IPI_EXECUTING) { + raw_spin_lock(&rq->rt.push_lock); + /* Make sure it's still executing */ + if (rq->rt.push_flags & RT_PUSH_IPI_EXECUTING) { + /* + * Tell the IPI to restart the loop as things have + * changed since it started. + */ + rq->rt.push_flags |= RT_PUSH_IPI_RESTART; + raw_spin_unlock(&rq->rt.push_lock); + return; + } + raw_spin_unlock(&rq->rt.push_lock); + } + + /* When here, there's no IPI going around */ + + rq->rt.push_cpu = rq->cpu; + cpu = find_next_push_cpu(rq); + if (cpu >= nr_cpu_ids) + return; + + rq->rt.push_flags = RT_PUSH_IPI_EXECUTING; + + irq_work_queue_on(&rq->rt.push_work, cpu); +} + +/* Called from hardirq context */ +static void try_to_push_tasks(void *arg) +{ + struct rt_rq *rt_rq = arg; + struct rq *rq, *src_rq; + int this_cpu; + int cpu; + + this_cpu = rt_rq->push_cpu; + + /* Paranoid check */ + BUG_ON(this_cpu != smp_processor_id()); + + rq = cpu_rq(this_cpu); + src_rq = rq_of_rt_rq(rt_rq); + +again: + if (has_pushable_tasks(rq)) { + raw_spin_lock(&rq->lock); + push_rt_task(rq); + raw_spin_unlock(&rq->lock); + } + + /* Pass the IPI to the next rt overloaded queue */ + raw_spin_lock(&rt_rq->push_lock); + /* + * If the source queue changed since the IPI went out, + * we need to restart the search from that CPU again. + */ + if (rt_rq->push_flags & RT_PUSH_IPI_RESTART) { + rt_rq->push_flags &= ~RT_PUSH_IPI_RESTART; + rt_rq->push_cpu = src_rq->cpu; + } + + cpu = find_next_push_cpu(src_rq); + + if (cpu >= nr_cpu_ids) + rt_rq->push_flags &= ~RT_PUSH_IPI_EXECUTING; + raw_spin_unlock(&rt_rq->push_lock); + + if (cpu >= nr_cpu_ids) + return; + + /* + * It is possible that a restart caused this CPU to be + * chosen again. Don't bother with an IPI, just see if we + * have more to push. + */ + if (unlikely(cpu == rq->cpu)) + goto again; + + /* Try the next RT overloaded CPU */ + irq_work_queue_on(&rt_rq->push_work, cpu); +} + +static void push_irq_work_func(struct irq_work *work) +{ + struct rt_rq *rt_rq = container_of(work, struct rt_rq, push_work); + + try_to_push_tasks(rt_rq); +} +#endif /* HAVE_RT_PUSH_IPI */ + static int pull_rt_task(struct rq *this_rq) { int this_cpu = this_rq->cpu, ret = 0, cpu; @@ -1793,6 +1963,13 @@ static int pull_rt_task(struct rq *this_rq) */ smp_rmb(); +#ifdef HAVE_RT_PUSH_IPI + if (sched_feat(RT_PUSH_IPI)) { + tell_cpu_to_push(this_rq); + return 0; + } +#endif + for_each_cpu(cpu, this_rq->rd->rto_mask) { if (this_cpu == cpu) continue; diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index dc0f435a2779..e0e129993958 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -6,6 +6,7 @@ #include <linux/mutex.h> #include <linux/spinlock.h> #include <linux/stop_machine.h> +#include <linux/irq_work.h> #include <linux/tick.h> #include <linux/slab.h> @@ -362,8 +363,14 @@ struct cfs_rq { * Under CFS, load is tracked on a per-entity basis and aggregated up. * This allows for the description of both thread and group usage (in * the FAIR_GROUP_SCHED case). + * runnable_load_avg is the sum of the load_avg_contrib of the + * sched_entities on the rq. + * blocked_load_avg is similar to runnable_load_avg except that its + * the blocked sched_entities on the rq. + * utilization_load_avg is the sum of the average running time of the + * sched_entities on the rq. */ - unsigned long runnable_load_avg, blocked_load_avg; + unsigned long runnable_load_avg, blocked_load_avg, utilization_load_avg; atomic64_t decay_counter; u64 last_decay; atomic_long_t removed_load; @@ -418,6 +425,11 @@ static inline int rt_bandwidth_enabled(void) return sysctl_sched_rt_runtime >= 0; } +/* RT IPI pull logic requires IRQ_WORK */ +#ifdef CONFIG_IRQ_WORK +# define HAVE_RT_PUSH_IPI +#endif + /* Real-Time classes' related field in a runqueue: */ struct rt_rq { struct rt_prio_array active; @@ -435,7 +447,13 @@ struct rt_rq { unsigned long rt_nr_total; int overloaded; struct plist_head pushable_tasks; +#ifdef HAVE_RT_PUSH_IPI + int push_flags; + int push_cpu; + struct irq_work push_work; + raw_spinlock_t push_lock; #endif +#endif /* CONFIG_SMP */ int rt_queued; int rt_throttled; @@ -597,6 +615,7 @@ struct rq { struct sched_domain *sd; unsigned long cpu_capacity; + unsigned long cpu_capacity_orig; unsigned char idle_balance; /* For active balancing */ @@ -807,7 +826,7 @@ struct sched_group_capacity { * CPU capacity of this group, SCHED_LOAD_SCALE being max capacity * for a single CPU. */ - unsigned int capacity, capacity_orig; + unsigned int capacity; unsigned long next_update; int imbalance; /* XXX unrelated to capacity but shared group state */ /* @@ -1368,9 +1387,18 @@ static inline int hrtick_enabled(struct rq *rq) #ifdef CONFIG_SMP extern void sched_avg_update(struct rq *rq); + +#ifndef arch_scale_freq_capacity +static __always_inline +unsigned long arch_scale_freq_capacity(struct sched_domain *sd, int cpu) +{ + return SCHED_CAPACITY_SCALE; +} +#endif + static inline void sched_rt_avg_update(struct rq *rq, u64 rt_delta) { - rq->rt_avg += rt_delta; + rq->rt_avg += rt_delta * arch_scale_freq_capacity(NULL, cpu_of(rq)); sched_avg_update(rq); } #else @@ -1643,8 +1671,8 @@ extern void print_rt_stats(struct seq_file *m, int cpu); extern void print_dl_stats(struct seq_file *m, int cpu); extern void init_cfs_rq(struct cfs_rq *cfs_rq); -extern void init_rt_rq(struct rt_rq *rt_rq, struct rq *rq); -extern void init_dl_rq(struct dl_rq *dl_rq, struct rq *rq); +extern void init_rt_rq(struct rt_rq *rt_rq); +extern void init_dl_rq(struct dl_rq *dl_rq); extern void cfs_bandwidth_usage_inc(void); extern void cfs_bandwidth_usage_dec(void); diff --git a/kernel/smpboot.c b/kernel/smpboot.c index 40190f28db35..c697f73d82d6 100644 --- a/kernel/smpboot.c +++ b/kernel/smpboot.c @@ -4,6 +4,7 @@ #include <linux/cpu.h> #include <linux/err.h> #include <linux/smp.h> +#include <linux/delay.h> #include <linux/init.h> #include <linux/list.h> #include <linux/slab.h> @@ -314,3 +315,158 @@ void smpboot_unregister_percpu_thread(struct smp_hotplug_thread *plug_thread) put_online_cpus(); } EXPORT_SYMBOL_GPL(smpboot_unregister_percpu_thread); + +static DEFINE_PER_CPU(atomic_t, cpu_hotplug_state) = ATOMIC_INIT(CPU_POST_DEAD); + +/* + * Called to poll specified CPU's state, for example, when waiting for + * a CPU to come online. + */ +int cpu_report_state(int cpu) +{ + return atomic_read(&per_cpu(cpu_hotplug_state, cpu)); +} + +/* + * If CPU has died properly, set its state to CPU_UP_PREPARE and + * return success. Otherwise, return -EBUSY if the CPU died after + * cpu_wait_death() timed out. And yet otherwise again, return -EAGAIN + * if cpu_wait_death() timed out and the CPU still hasn't gotten around + * to dying. In the latter two cases, the CPU might not be set up + * properly, but it is up to the arch-specific code to decide. + * Finally, -EIO indicates an unanticipated problem. + * + * Note that it is permissible to omit this call entirely, as is + * done in architectures that do no CPU-hotplug error checking. + */ +int cpu_check_up_prepare(int cpu) +{ + if (!IS_ENABLED(CONFIG_HOTPLUG_CPU)) { + atomic_set(&per_cpu(cpu_hotplug_state, cpu), CPU_UP_PREPARE); + return 0; + } + + switch (atomic_read(&per_cpu(cpu_hotplug_state, cpu))) { + + case CPU_POST_DEAD: + + /* The CPU died properly, so just start it up again. */ + atomic_set(&per_cpu(cpu_hotplug_state, cpu), CPU_UP_PREPARE); + return 0; + + case CPU_DEAD_FROZEN: + + /* + * Timeout during CPU death, so let caller know. + * The outgoing CPU completed its processing, but after + * cpu_wait_death() timed out and reported the error. The + * caller is free to proceed, in which case the state + * will be reset properly by cpu_set_state_online(). + * Proceeding despite this -EBUSY return makes sense + * for systems where the outgoing CPUs take themselves + * offline, with no post-death manipulation required from + * a surviving CPU. + */ + return -EBUSY; + + case CPU_BROKEN: + + /* + * The most likely reason we got here is that there was + * a timeout during CPU death, and the outgoing CPU never + * did complete its processing. This could happen on + * a virtualized system if the outgoing VCPU gets preempted + * for more than five seconds, and the user attempts to + * immediately online that same CPU. Trying again later + * might return -EBUSY above, hence -EAGAIN. + */ + return -EAGAIN; + + default: + + /* Should not happen. Famous last words. */ + return -EIO; + } +} + +/* + * Mark the specified CPU online. + * + * Note that it is permissible to omit this call entirely, as is + * done in architectures that do no CPU-hotplug error checking. + */ +void cpu_set_state_online(int cpu) +{ + (void)atomic_xchg(&per_cpu(cpu_hotplug_state, cpu), CPU_ONLINE); +} + +#ifdef CONFIG_HOTPLUG_CPU + +/* + * Wait for the specified CPU to exit the idle loop and die. + */ +bool cpu_wait_death(unsigned int cpu, int seconds) +{ + int jf_left = seconds * HZ; + int oldstate; + bool ret = true; + int sleep_jf = 1; + + might_sleep(); + + /* The outgoing CPU will normally get done quite quickly. */ + if (atomic_read(&per_cpu(cpu_hotplug_state, cpu)) == CPU_DEAD) + goto update_state; + udelay(5); + + /* But if the outgoing CPU dawdles, wait increasingly long times. */ + while (atomic_read(&per_cpu(cpu_hotplug_state, cpu)) != CPU_DEAD) { + schedule_timeout_uninterruptible(sleep_jf); + jf_left -= sleep_jf; + if (jf_left <= 0) + break; + sleep_jf = DIV_ROUND_UP(sleep_jf * 11, 10); + } +update_state: + oldstate = atomic_read(&per_cpu(cpu_hotplug_state, cpu)); + if (oldstate == CPU_DEAD) { + /* Outgoing CPU died normally, update state. */ + smp_mb(); /* atomic_read() before update. */ + atomic_set(&per_cpu(cpu_hotplug_state, cpu), CPU_POST_DEAD); + } else { + /* Outgoing CPU still hasn't died, set state accordingly. */ + if (atomic_cmpxchg(&per_cpu(cpu_hotplug_state, cpu), + oldstate, CPU_BROKEN) != oldstate) + goto update_state; + ret = false; + } + return ret; +} + +/* + * Called by the outgoing CPU to report its successful death. Return + * false if this report follows the surviving CPU's timing out. + * + * A separate "CPU_DEAD_FROZEN" is used when the surviving CPU + * timed out. This approach allows architectures to omit calls to + * cpu_check_up_prepare() and cpu_set_state_online() without defeating + * the next cpu_wait_death()'s polling loop. + */ +bool cpu_report_death(void) +{ + int oldstate; + int newstate; + int cpu = smp_processor_id(); + + do { + oldstate = atomic_read(&per_cpu(cpu_hotplug_state, cpu)); + if (oldstate != CPU_BROKEN) + newstate = CPU_DEAD; + else + newstate = CPU_DEAD_FROZEN; + } while (atomic_cmpxchg(&per_cpu(cpu_hotplug_state, cpu), + oldstate, newstate) != oldstate); + return newstate == CPU_DEAD; +} + +#endif /* #ifdef CONFIG_HOTPLUG_CPU */ diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 88ea2d6e0031..8c0eabd41886 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -19,6 +19,7 @@ */ #include <linux/module.h> +#include <linux/aio.h> #include <linux/mm.h> #include <linux/swap.h> #include <linux/slab.h> @@ -846,7 +847,7 @@ static struct ctl_table kern_table[] = { .data = &watchdog_user_enabled, .maxlen = sizeof (int), .mode = 0644, - .proc_handler = proc_dowatchdog, + .proc_handler = proc_watchdog, .extra1 = &zero, .extra2 = &one, }, @@ -855,11 +856,33 @@ static struct ctl_table kern_table[] = { .data = &watchdog_thresh, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dowatchdog, + .proc_handler = proc_watchdog_thresh, .extra1 = &zero, .extra2 = &sixty, }, { + .procname = "nmi_watchdog", + .data = &nmi_watchdog_enabled, + .maxlen = sizeof (int), + .mode = 0644, + .proc_handler = proc_nmi_watchdog, + .extra1 = &zero, +#if defined(CONFIG_HAVE_NMI_WATCHDOG) || defined(CONFIG_HARDLOCKUP_DETECTOR) + .extra2 = &one, +#else + .extra2 = &zero, +#endif + }, + { + .procname = "soft_watchdog", + .data = &soft_watchdog_enabled, + .maxlen = sizeof (int), + .mode = 0644, + .proc_handler = proc_soft_watchdog, + .extra1 = &zero, + .extra2 = &one, + }, + { .procname = "softlockup_panic", .data = &softlockup_panic, .maxlen = sizeof(int), @@ -879,15 +902,6 @@ static struct ctl_table kern_table[] = { .extra2 = &one, }, #endif /* CONFIG_SMP */ - { - .procname = "nmi_watchdog", - .data = &watchdog_user_enabled, - .maxlen = sizeof (int), - .mode = 0644, - .proc_handler = proc_dowatchdog, - .extra1 = &zero, - .extra2 = &one, - }, #endif #if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86) { @@ -1228,6 +1242,14 @@ static struct ctl_table vm_table[] = { .extra1 = &zero, }, { + .procname = "dirtytime_expire_seconds", + .data = &dirtytime_expire_interval, + .maxlen = sizeof(dirty_expire_interval), + .mode = 0644, + .proc_handler = dirtytime_interval_handler, + .extra1 = &zero, + }, + { .procname = "nr_pdflush_threads", .mode = 0444 /* read-only */, .proc_handler = pdflush_proc_obsolete, diff --git a/kernel/time/Kconfig b/kernel/time/Kconfig index d626dc98e8df..579ce1b929af 100644 --- a/kernel/time/Kconfig +++ b/kernel/time/Kconfig @@ -33,12 +33,6 @@ config ARCH_USES_GETTIMEOFFSET config GENERIC_CLOCKEVENTS bool -# Migration helper. Builds, but does not invoke -config GENERIC_CLOCKEVENTS_BUILD - bool - default y - depends on GENERIC_CLOCKEVENTS - # Architecture can handle broadcast in a driver-agnostic way config ARCH_HAS_TICK_BROADCAST bool diff --git a/kernel/time/Makefile b/kernel/time/Makefile index c09c07817d7a..01f0312419b3 100644 --- a/kernel/time/Makefile +++ b/kernel/time/Makefile @@ -2,15 +2,13 @@ obj-y += time.o timer.o hrtimer.o itimer.o posix-timers.o posix-cpu-timers.o obj-y += timekeeping.o ntp.o clocksource.o jiffies.o timer_list.o obj-y += timeconv.o timecounter.o posix-clock.o alarmtimer.o -obj-$(CONFIG_GENERIC_CLOCKEVENTS_BUILD) += clockevents.o -obj-$(CONFIG_GENERIC_CLOCKEVENTS) += tick-common.o +obj-$(CONFIG_GENERIC_CLOCKEVENTS) += clockevents.o tick-common.o ifeq ($(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST),y) obj-y += tick-broadcast.o obj-$(CONFIG_TICK_ONESHOT) += tick-broadcast-hrtimer.o endif obj-$(CONFIG_GENERIC_SCHED_CLOCK) += sched_clock.o -obj-$(CONFIG_TICK_ONESHOT) += tick-oneshot.o -obj-$(CONFIG_TICK_ONESHOT) += tick-sched.o +obj-$(CONFIG_TICK_ONESHOT) += tick-oneshot.o tick-sched.o obj-$(CONFIG_TIMER_STATS) += timer_stats.o obj-$(CONFIG_DEBUG_FS) += timekeeping_debug.o obj-$(CONFIG_TEST_UDELAY) += test_udelay.o diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c index 55449909f114..25d942d1da27 100644 --- a/kernel/time/clockevents.c +++ b/kernel/time/clockevents.c @@ -94,25 +94,76 @@ u64 clockevent_delta2ns(unsigned long latch, struct clock_event_device *evt) } EXPORT_SYMBOL_GPL(clockevent_delta2ns); +static int __clockevents_set_state(struct clock_event_device *dev, + enum clock_event_state state) +{ + /* Transition with legacy set_mode() callback */ + if (dev->set_mode) { + /* Legacy callback doesn't support new modes */ + if (state > CLOCK_EVT_STATE_ONESHOT) + return -ENOSYS; + /* + * 'clock_event_state' and 'clock_event_mode' have 1-to-1 + * mapping until *_ONESHOT, and so a simple cast will work. + */ + dev->set_mode((enum clock_event_mode)state, dev); + dev->mode = (enum clock_event_mode)state; + return 0; + } + + if (dev->features & CLOCK_EVT_FEAT_DUMMY) + return 0; + + /* Transition with new state-specific callbacks */ + switch (state) { + case CLOCK_EVT_STATE_DETACHED: + /* + * This is an internal state, which is guaranteed to go from + * SHUTDOWN to DETACHED. No driver interaction required. + */ + return 0; + + case CLOCK_EVT_STATE_SHUTDOWN: + return dev->set_state_shutdown(dev); + + case CLOCK_EVT_STATE_PERIODIC: + /* Core internal bug */ + if (!(dev->features & CLOCK_EVT_FEAT_PERIODIC)) + return -ENOSYS; + return dev->set_state_periodic(dev); + + case CLOCK_EVT_STATE_ONESHOT: + /* Core internal bug */ + if (!(dev->features & CLOCK_EVT_FEAT_ONESHOT)) + return -ENOSYS; + return dev->set_state_oneshot(dev); + + default: + return -ENOSYS; + } +} + /** - * clockevents_set_mode - set the operating mode of a clock event device + * clockevents_set_state - set the operating state of a clock event device * @dev: device to modify - * @mode: new mode + * @state: new state * * Must be called with interrupts disabled ! */ -void clockevents_set_mode(struct clock_event_device *dev, - enum clock_event_mode mode) +void clockevents_set_state(struct clock_event_device *dev, + enum clock_event_state state) { - if (dev->mode != mode) { - dev->set_mode(mode, dev); - dev->mode = mode; + if (dev->state != state) { + if (__clockevents_set_state(dev, state)) + return; + + dev->state = state; /* * A nsec2cyc multiplicator of 0 is invalid and we'd crash * on it, so fix it up and emit a warning: */ - if (mode == CLOCK_EVT_MODE_ONESHOT) { + if (state == CLOCK_EVT_STATE_ONESHOT) { if (unlikely(!dev->mult)) { dev->mult = 1; WARN_ON(1); @@ -127,10 +178,28 @@ void clockevents_set_mode(struct clock_event_device *dev, */ void clockevents_shutdown(struct clock_event_device *dev) { - clockevents_set_mode(dev, CLOCK_EVT_MODE_SHUTDOWN); + clockevents_set_state(dev, CLOCK_EVT_STATE_SHUTDOWN); dev->next_event.tv64 = KTIME_MAX; } +/** + * clockevents_tick_resume - Resume the tick device before using it again + * @dev: device to resume + */ +int clockevents_tick_resume(struct clock_event_device *dev) +{ + int ret = 0; + + if (dev->set_mode) { + dev->set_mode(CLOCK_EVT_MODE_RESUME, dev); + dev->mode = CLOCK_EVT_MODE_RESUME; + } else if (dev->tick_resume) { + ret = dev->tick_resume(dev); + } + + return ret; +} + #ifdef CONFIG_GENERIC_CLOCKEVENTS_MIN_ADJUST /* Limit min_delta to a jiffie */ @@ -183,7 +252,7 @@ static int clockevents_program_min_delta(struct clock_event_device *dev) delta = dev->min_delta_ns; dev->next_event = ktime_add_ns(ktime_get(), delta); - if (dev->mode == CLOCK_EVT_MODE_SHUTDOWN) + if (dev->state == CLOCK_EVT_STATE_SHUTDOWN) return 0; dev->retries++; @@ -220,7 +289,7 @@ static int clockevents_program_min_delta(struct clock_event_device *dev) delta = dev->min_delta_ns; dev->next_event = ktime_add_ns(ktime_get(), delta); - if (dev->mode == CLOCK_EVT_MODE_SHUTDOWN) + if (dev->state == CLOCK_EVT_STATE_SHUTDOWN) return 0; dev->retries++; @@ -252,7 +321,7 @@ int clockevents_program_event(struct clock_event_device *dev, ktime_t expires, dev->next_event = expires; - if (dev->mode == CLOCK_EVT_MODE_SHUTDOWN) + if (dev->state == CLOCK_EVT_STATE_SHUTDOWN) return 0; /* Shortcut for clockevent devices that can deal with ktime. */ @@ -297,7 +366,7 @@ static int clockevents_replace(struct clock_event_device *ced) struct clock_event_device *dev, *newdev = NULL; list_for_each_entry(dev, &clockevent_devices, list) { - if (dev == ced || dev->mode != CLOCK_EVT_MODE_UNUSED) + if (dev == ced || dev->state != CLOCK_EVT_STATE_DETACHED) continue; if (!tick_check_replacement(newdev, dev)) @@ -323,7 +392,7 @@ static int clockevents_replace(struct clock_event_device *ced) static int __clockevents_try_unbind(struct clock_event_device *ced, int cpu) { /* Fast track. Device is unused */ - if (ced->mode == CLOCK_EVT_MODE_UNUSED) { + if (ced->state == CLOCK_EVT_STATE_DETACHED) { list_del_init(&ced->list); return 0; } @@ -373,6 +442,37 @@ int clockevents_unbind_device(struct clock_event_device *ced, int cpu) } EXPORT_SYMBOL_GPL(clockevents_unbind); +/* Sanity check of state transition callbacks */ +static int clockevents_sanity_check(struct clock_event_device *dev) +{ + /* Legacy set_mode() callback */ + if (dev->set_mode) { + /* We shouldn't be supporting new modes now */ + WARN_ON(dev->set_state_periodic || dev->set_state_oneshot || + dev->set_state_shutdown || dev->tick_resume); + + BUG_ON(dev->mode != CLOCK_EVT_MODE_UNUSED); + return 0; + } + + if (dev->features & CLOCK_EVT_FEAT_DUMMY) + return 0; + + /* New state-specific callbacks */ + if (!dev->set_state_shutdown) + return -EINVAL; + + if ((dev->features & CLOCK_EVT_FEAT_PERIODIC) && + !dev->set_state_periodic) + return -EINVAL; + + if ((dev->features & CLOCK_EVT_FEAT_ONESHOT) && + !dev->set_state_oneshot) + return -EINVAL; + + return 0; +} + /** * clockevents_register_device - register a clock event device * @dev: device to register @@ -381,7 +481,11 @@ void clockevents_register_device(struct clock_event_device *dev) { unsigned long flags; - BUG_ON(dev->mode != CLOCK_EVT_MODE_UNUSED); + BUG_ON(clockevents_sanity_check(dev)); + + /* Initialize state to DETACHED */ + dev->state = CLOCK_EVT_STATE_DETACHED; + if (!dev->cpumask) { WARN_ON(num_possible_cpus() > 1); dev->cpumask = cpumask_of(smp_processor_id()); @@ -445,11 +549,11 @@ int __clockevents_update_freq(struct clock_event_device *dev, u32 freq) { clockevents_config(dev, freq); - if (dev->mode == CLOCK_EVT_MODE_ONESHOT) + if (dev->state == CLOCK_EVT_STATE_ONESHOT) return clockevents_program_event(dev, dev->next_event, false); - if (dev->mode == CLOCK_EVT_MODE_PERIODIC) - dev->set_mode(CLOCK_EVT_MODE_PERIODIC, dev); + if (dev->state == CLOCK_EVT_STATE_PERIODIC) + return __clockevents_set_state(dev, CLOCK_EVT_STATE_PERIODIC); return 0; } @@ -491,30 +595,27 @@ void clockevents_handle_noop(struct clock_event_device *dev) * @old: device to release (can be NULL) * @new: device to request (can be NULL) * - * Called from the notifier chain. clockevents_lock is held already + * Called from various tick functions with clockevents_lock held and + * interrupts disabled. */ void clockevents_exchange_device(struct clock_event_device *old, struct clock_event_device *new) { - unsigned long flags; - - local_irq_save(flags); /* * Caller releases a clock event device. We queue it into the * released list and do a notify add later. */ if (old) { module_put(old->owner); - clockevents_set_mode(old, CLOCK_EVT_MODE_UNUSED); + clockevents_set_state(old, CLOCK_EVT_STATE_DETACHED); list_del(&old->list); list_add(&old->list, &clockevents_released); } if (new) { - BUG_ON(new->mode != CLOCK_EVT_MODE_UNUSED); + BUG_ON(new->state != CLOCK_EVT_STATE_DETACHED); clockevents_shutdown(new); } - local_irq_restore(flags); } /** @@ -541,74 +642,40 @@ void clockevents_resume(void) dev->resume(dev); } -#ifdef CONFIG_GENERIC_CLOCKEVENTS +#ifdef CONFIG_HOTPLUG_CPU /** - * clockevents_notify - notification about relevant events - * Returns 0 on success, any other value on error + * tick_cleanup_dead_cpu - Cleanup the tick and clockevents of a dead cpu */ -int clockevents_notify(unsigned long reason, void *arg) +void tick_cleanup_dead_cpu(int cpu) { struct clock_event_device *dev, *tmp; unsigned long flags; - int cpu, ret = 0; raw_spin_lock_irqsave(&clockevents_lock, flags); - switch (reason) { - case CLOCK_EVT_NOTIFY_BROADCAST_ON: - case CLOCK_EVT_NOTIFY_BROADCAST_OFF: - case CLOCK_EVT_NOTIFY_BROADCAST_FORCE: - tick_broadcast_on_off(reason, arg); - break; - - case CLOCK_EVT_NOTIFY_BROADCAST_ENTER: - case CLOCK_EVT_NOTIFY_BROADCAST_EXIT: - ret = tick_broadcast_oneshot_control(reason); - break; - - case CLOCK_EVT_NOTIFY_CPU_DYING: - tick_handover_do_timer(arg); - break; - - case CLOCK_EVT_NOTIFY_SUSPEND: - tick_suspend(); - tick_suspend_broadcast(); - break; - - case CLOCK_EVT_NOTIFY_RESUME: - tick_resume(); - break; - - case CLOCK_EVT_NOTIFY_CPU_DEAD: - tick_shutdown_broadcast_oneshot(arg); - tick_shutdown_broadcast(arg); - tick_shutdown(arg); - /* - * Unregister the clock event devices which were - * released from the users in the notify chain. - */ - list_for_each_entry_safe(dev, tmp, &clockevents_released, list) + tick_shutdown_broadcast_oneshot(cpu); + tick_shutdown_broadcast(cpu); + tick_shutdown(cpu); + /* + * Unregister the clock event devices which were + * released from the users in the notify chain. + */ + list_for_each_entry_safe(dev, tmp, &clockevents_released, list) + list_del(&dev->list); + /* + * Now check whether the CPU has left unused per cpu devices + */ + list_for_each_entry_safe(dev, tmp, &clockevent_devices, list) { + if (cpumask_test_cpu(cpu, dev->cpumask) && + cpumask_weight(dev->cpumask) == 1 && + !tick_is_broadcast_device(dev)) { + BUG_ON(dev->state != CLOCK_EVT_STATE_DETACHED); list_del(&dev->list); - /* - * Now check whether the CPU has left unused per cpu devices - */ - cpu = *((int *)arg); - list_for_each_entry_safe(dev, tmp, &clockevent_devices, list) { - if (cpumask_test_cpu(cpu, dev->cpumask) && - cpumask_weight(dev->cpumask) == 1 && - !tick_is_broadcast_device(dev)) { - BUG_ON(dev->mode != CLOCK_EVT_MODE_UNUSED); - list_del(&dev->list); - } } - break; - default: - break; } raw_spin_unlock_irqrestore(&clockevents_lock, flags); - return ret; } -EXPORT_SYMBOL_GPL(clockevents_notify); +#endif #ifdef CONFIG_SYSFS struct bus_type clockevents_subsys = { @@ -727,5 +794,3 @@ static int __init clockevents_init_sysfs(void) } device_initcall(clockevents_init_sysfs); #endif /* SYSFS */ - -#endif /* GENERIC_CLOCK_EVENTS */ diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index 4892352f0e49..15facb1b9c60 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -142,13 +142,6 @@ static void __clocksource_unstable(struct clocksource *cs) schedule_work(&watchdog_work); } -static void clocksource_unstable(struct clocksource *cs, int64_t delta) -{ - printk(KERN_WARNING "Clocksource %s unstable (delta = %Ld ns)\n", - cs->name, delta); - __clocksource_unstable(cs); -} - /** * clocksource_mark_unstable - mark clocksource unstable via watchdog * @cs: clocksource to be marked unstable @@ -174,7 +167,7 @@ void clocksource_mark_unstable(struct clocksource *cs) static void clocksource_watchdog(unsigned long data) { struct clocksource *cs; - cycle_t csnow, wdnow, delta; + cycle_t csnow, wdnow, cslast, wdlast, delta; int64_t wd_nsec, cs_nsec; int next_cpu, reset_pending; @@ -213,6 +206,8 @@ static void clocksource_watchdog(unsigned long data) delta = clocksource_delta(csnow, cs->cs_last, cs->mask); cs_nsec = clocksource_cyc2ns(delta, cs->mult, cs->shift); + wdlast = cs->wd_last; /* save these in case we print them */ + cslast = cs->cs_last; cs->cs_last = csnow; cs->wd_last = wdnow; @@ -221,7 +216,12 @@ static void clocksource_watchdog(unsigned long data) /* Check the deviation from the watchdog clocksource. */ if ((abs(cs_nsec - wd_nsec) > WATCHDOG_THRESHOLD)) { - clocksource_unstable(cs, cs_nsec - wd_nsec); + pr_warn("timekeeping watchdog: Marking clocksource '%s' as unstable, because the skew is too large:\n", cs->name); + pr_warn(" '%s' wd_now: %llx wd_last: %llx mask: %llx\n", + watchdog->name, wdnow, wdlast, watchdog->mask); + pr_warn(" '%s' cs_now: %llx cs_last: %llx mask: %llx\n", + cs->name, csnow, cslast, cs->mask); + __clocksource_unstable(cs); continue; } @@ -469,26 +469,25 @@ static u32 clocksource_max_adjustment(struct clocksource *cs) * @shift: cycle to nanosecond divisor (power of two) * @maxadj: maximum adjustment value to mult (~11%) * @mask: bitmask for two's complement subtraction of non 64 bit counters + * @max_cyc: maximum cycle value before potential overflow (does not include + * any safety margin) + * + * NOTE: This function includes a safety margin of 50%, in other words, we + * return half the number of nanoseconds the hardware counter can technically + * cover. This is done so that we can potentially detect problems caused by + * delayed timers or bad hardware, which might result in time intervals that + * are larger then what the math used can handle without overflows. */ -u64 clocks_calc_max_nsecs(u32 mult, u32 shift, u32 maxadj, u64 mask) +u64 clocks_calc_max_nsecs(u32 mult, u32 shift, u32 maxadj, u64 mask, u64 *max_cyc) { u64 max_nsecs, max_cycles; /* * Calculate the maximum number of cycles that we can pass to the - * cyc2ns function without overflowing a 64-bit signed result. The - * maximum number of cycles is equal to ULLONG_MAX/(mult+maxadj) - * which is equivalent to the below. - * max_cycles < (2^63)/(mult + maxadj) - * max_cycles < 2^(log2((2^63)/(mult + maxadj))) - * max_cycles < 2^(log2(2^63) - log2(mult + maxadj)) - * max_cycles < 2^(63 - log2(mult + maxadj)) - * max_cycles < 1 << (63 - log2(mult + maxadj)) - * Please note that we add 1 to the result of the log2 to account for - * any rounding errors, ensure the above inequality is satisfied and - * no overflow will occur. + * cyc2ns() function without overflowing a 64-bit result. */ - max_cycles = 1ULL << (63 - (ilog2(mult + maxadj) + 1)); + max_cycles = ULLONG_MAX; + do_div(max_cycles, mult+maxadj); /* * The actual maximum number of cycles we can defer the clocksource is @@ -499,27 +498,26 @@ u64 clocks_calc_max_nsecs(u32 mult, u32 shift, u32 maxadj, u64 mask) max_cycles = min(max_cycles, mask); max_nsecs = clocksource_cyc2ns(max_cycles, mult - maxadj, shift); + /* return the max_cycles value as well if requested */ + if (max_cyc) + *max_cyc = max_cycles; + + /* Return 50% of the actual maximum, so we can detect bad values */ + max_nsecs >>= 1; + return max_nsecs; } /** - * clocksource_max_deferment - Returns max time the clocksource can be deferred - * @cs: Pointer to clocksource + * clocksource_update_max_deferment - Updates the clocksource max_idle_ns & max_cycles + * @cs: Pointer to clocksource to be updated * */ -static u64 clocksource_max_deferment(struct clocksource *cs) +static inline void clocksource_update_max_deferment(struct clocksource *cs) { - u64 max_nsecs; - - max_nsecs = clocks_calc_max_nsecs(cs->mult, cs->shift, cs->maxadj, - cs->mask); - /* - * To ensure that the clocksource does not wrap whilst we are idle, - * limit the time the clocksource can be deferred by 12.5%. Please - * note a margin of 12.5% is used because this can be computed with - * a shift, versus say 10% which would require division. - */ - return max_nsecs - (max_nsecs >> 3); + cs->max_idle_ns = clocks_calc_max_nsecs(cs->mult, cs->shift, + cs->maxadj, cs->mask, + &cs->max_cycles); } #ifndef CONFIG_ARCH_USES_GETTIMEOFFSET @@ -648,7 +646,7 @@ static void clocksource_enqueue(struct clocksource *cs) } /** - * __clocksource_updatefreq_scale - Used update clocksource with new freq + * __clocksource_update_freq_scale - Used update clocksource with new freq * @cs: clocksource to be registered * @scale: Scale factor multiplied against freq to get clocksource hz * @freq: clocksource frequency (cycles per second) divided by scale @@ -656,48 +654,64 @@ static void clocksource_enqueue(struct clocksource *cs) * This should only be called from the clocksource->enable() method. * * This *SHOULD NOT* be called directly! Please use the - * clocksource_updatefreq_hz() or clocksource_updatefreq_khz helper functions. + * __clocksource_update_freq_hz() or __clocksource_update_freq_khz() helper + * functions. */ -void __clocksource_updatefreq_scale(struct clocksource *cs, u32 scale, u32 freq) +void __clocksource_update_freq_scale(struct clocksource *cs, u32 scale, u32 freq) { u64 sec; + /* - * Calc the maximum number of seconds which we can run before - * wrapping around. For clocksources which have a mask > 32bit - * we need to limit the max sleep time to have a good - * conversion precision. 10 minutes is still a reasonable - * amount. That results in a shift value of 24 for a - * clocksource with mask >= 40bit and f >= 4GHz. That maps to - * ~ 0.06ppm granularity for NTP. We apply the same 12.5% - * margin as we do in clocksource_max_deferment() + * Default clocksources are *special* and self-define their mult/shift. + * But, you're not special, so you should specify a freq value. */ - sec = (cs->mask - (cs->mask >> 3)); - do_div(sec, freq); - do_div(sec, scale); - if (!sec) - sec = 1; - else if (sec > 600 && cs->mask > UINT_MAX) - sec = 600; - - clocks_calc_mult_shift(&cs->mult, &cs->shift, freq, - NSEC_PER_SEC / scale, sec * scale); - + if (freq) { + /* + * Calc the maximum number of seconds which we can run before + * wrapping around. For clocksources which have a mask > 32-bit + * we need to limit the max sleep time to have a good + * conversion precision. 10 minutes is still a reasonable + * amount. That results in a shift value of 24 for a + * clocksource with mask >= 40-bit and f >= 4GHz. That maps to + * ~ 0.06ppm granularity for NTP. + */ + sec = cs->mask; + do_div(sec, freq); + do_div(sec, scale); + if (!sec) + sec = 1; + else if (sec > 600 && cs->mask > UINT_MAX) + sec = 600; + + clocks_calc_mult_shift(&cs->mult, &cs->shift, freq, + NSEC_PER_SEC / scale, sec * scale); + } /* - * for clocksources that have large mults, to avoid overflow. - * Since mult may be adjusted by ntp, add an safety extra margin - * + * Ensure clocksources that have large 'mult' values don't overflow + * when adjusted. */ cs->maxadj = clocksource_max_adjustment(cs); - while ((cs->mult + cs->maxadj < cs->mult) - || (cs->mult - cs->maxadj > cs->mult)) { + while (freq && ((cs->mult + cs->maxadj < cs->mult) + || (cs->mult - cs->maxadj > cs->mult))) { cs->mult >>= 1; cs->shift--; cs->maxadj = clocksource_max_adjustment(cs); } - cs->max_idle_ns = clocksource_max_deferment(cs); + /* + * Only warn for *special* clocksources that self-define + * their mult/shift values and don't specify a freq. + */ + WARN_ONCE(cs->mult + cs->maxadj < cs->mult, + "timekeeping: Clocksource %s might overflow on 11%% adjustment\n", + cs->name); + + clocksource_update_max_deferment(cs); + + pr_info("clocksource %s: mask: 0x%llx max_cycles: 0x%llx, max_idle_ns: %lld ns\n", + cs->name, cs->mask, cs->max_cycles, cs->max_idle_ns); } -EXPORT_SYMBOL_GPL(__clocksource_updatefreq_scale); +EXPORT_SYMBOL_GPL(__clocksource_update_freq_scale); /** * __clocksource_register_scale - Used to install new clocksources @@ -714,7 +728,7 @@ int __clocksource_register_scale(struct clocksource *cs, u32 scale, u32 freq) { /* Initialize mult/shift and max_idle_ns */ - __clocksource_updatefreq_scale(cs, scale, freq); + __clocksource_update_freq_scale(cs, scale, freq); /* Add clocksource to the clocksource list */ mutex_lock(&clocksource_mutex); @@ -726,33 +740,6 @@ int __clocksource_register_scale(struct clocksource *cs, u32 scale, u32 freq) } EXPORT_SYMBOL_GPL(__clocksource_register_scale); - -/** - * clocksource_register - Used to install new clocksources - * @cs: clocksource to be registered - * - * Returns -EBUSY if registration fails, zero otherwise. - */ -int clocksource_register(struct clocksource *cs) -{ - /* calculate max adjustment for given mult/shift */ - cs->maxadj = clocksource_max_adjustment(cs); - WARN_ONCE(cs->mult + cs->maxadj < cs->mult, - "Clocksource %s might overflow on 11%% adjustment\n", - cs->name); - - /* calculate max idle time permitted for this clocksource */ - cs->max_idle_ns = clocksource_max_deferment(cs); - - mutex_lock(&clocksource_mutex); - clocksource_enqueue(cs); - clocksource_enqueue_watchdog(cs); - clocksource_select(); - mutex_unlock(&clocksource_mutex); - return 0; -} -EXPORT_SYMBOL(clocksource_register); - static void __clocksource_change_rating(struct clocksource *cs, int rating) { list_del(&cs->list); diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index bee0c1f78091..76d4bd962b19 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -54,7 +54,7 @@ #include <trace/events/timer.h> -#include "timekeeping.h" +#include "tick-internal.h" /* * The timer bases: @@ -1707,17 +1707,10 @@ static int hrtimer_cpu_notify(struct notifier_block *self, break; #ifdef CONFIG_HOTPLUG_CPU - case CPU_DYING: - case CPU_DYING_FROZEN: - clockevents_notify(CLOCK_EVT_NOTIFY_CPU_DYING, &scpu); - break; case CPU_DEAD: case CPU_DEAD_FROZEN: - { - clockevents_notify(CLOCK_EVT_NOTIFY_CPU_DEAD, &scpu); migrate_hrtimers(scpu); break; - } #endif default: diff --git a/kernel/time/jiffies.c b/kernel/time/jiffies.c index a6a5bf53e86d..347fecf86a3f 100644 --- a/kernel/time/jiffies.c +++ b/kernel/time/jiffies.c @@ -25,7 +25,7 @@ #include <linux/module.h> #include <linux/init.h> -#include "tick-internal.h" +#include "timekeeping.h" /* The Jiffies based clocksource is the lowest common * denominator clock source which should function on @@ -71,6 +71,7 @@ static struct clocksource clocksource_jiffies = { .mask = 0xffffffff, /*32bits*/ .mult = NSEC_PER_JIFFY << JIFFIES_SHIFT, /* details above */ .shift = JIFFIES_SHIFT, + .max_cycles = 10, }; __cacheline_aligned_in_smp DEFINE_SEQLOCK(jiffies_lock); @@ -94,7 +95,7 @@ EXPORT_SYMBOL(jiffies); static int __init init_jiffies_clocksource(void) { - return clocksource_register(&clocksource_jiffies); + return __clocksource_register(&clocksource_jiffies); } core_initcall(init_jiffies_clocksource); @@ -130,6 +131,6 @@ int register_refined_jiffies(long cycles_per_second) refined_jiffies.mult = ((u32)nsec_per_tick) << JIFFIES_SHIFT; - clocksource_register(&refined_jiffies); + __clocksource_register(&refined_jiffies); return 0; } diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c index 0f60b08a4f07..7a681003001c 100644 --- a/kernel/time/ntp.c +++ b/kernel/time/ntp.c @@ -17,7 +17,6 @@ #include <linux/module.h> #include <linux/rtc.h> -#include "tick-internal.h" #include "ntp_internal.h" /* @@ -459,6 +458,16 @@ out: return leap; } +#ifdef CONFIG_GENERIC_CMOS_UPDATE +int __weak update_persistent_clock64(struct timespec64 now64) +{ + struct timespec now; + + now = timespec64_to_timespec(now64); + return update_persistent_clock(now); +} +#endif + #if defined(CONFIG_GENERIC_CMOS_UPDATE) || defined(CONFIG_RTC_SYSTOHC) static void sync_cmos_clock(struct work_struct *work); @@ -494,8 +503,9 @@ static void sync_cmos_clock(struct work_struct *work) if (persistent_clock_is_local) adjust.tv_sec -= (sys_tz.tz_minuteswest * 60); #ifdef CONFIG_GENERIC_CMOS_UPDATE - fail = update_persistent_clock(timespec64_to_timespec(adjust)); + fail = update_persistent_clock64(adjust); #endif + #ifdef CONFIG_RTC_SYSTOHC if (fail == -ENODEV) fail = rtc_set_ntp_time(adjust); diff --git a/kernel/time/sched_clock.c b/kernel/time/sched_clock.c index 01d2d15aa662..a26036d37a38 100644 --- a/kernel/time/sched_clock.c +++ b/kernel/time/sched_clock.c @@ -1,5 +1,6 @@ /* - * sched_clock.c: support for extending counters to full 64-bit ns counter + * sched_clock.c: Generic sched_clock() support, to extend low level + * hardware time counters to full 64-bit ns values. * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -18,15 +19,53 @@ #include <linux/seqlock.h> #include <linux/bitops.h> -struct clock_data { - ktime_t wrap_kt; +/** + * struct clock_read_data - data required to read from sched_clock() + * + * @epoch_ns: sched_clock() value at last update + * @epoch_cyc: Clock cycle value at last update. + * @sched_clock_mask: Bitmask for two's complement subtraction of non 64bit + * clocks. + * @read_sched_clock: Current clock source (or dummy source when suspended). + * @mult: Multipler for scaled math conversion. + * @shift: Shift value for scaled math conversion. + * + * Care must be taken when updating this structure; it is read by + * some very hot code paths. It occupies <=40 bytes and, when combined + * with the seqcount used to synchronize access, comfortably fits into + * a 64 byte cache line. + */ +struct clock_read_data { u64 epoch_ns; u64 epoch_cyc; - seqcount_t seq; - unsigned long rate; + u64 sched_clock_mask; + u64 (*read_sched_clock)(void); u32 mult; u32 shift; - bool suspended; +}; + +/** + * struct clock_data - all data needed for sched_clock() (including + * registration of a new clock source) + * + * @seq: Sequence counter for protecting updates. The lowest + * bit is the index for @read_data. + * @read_data: Data required to read from sched_clock. + * @wrap_kt: Duration for which clock can run before wrapping. + * @rate: Tick rate of the registered clock. + * @actual_read_sched_clock: Registered hardware level clock read function. + * + * The ordering of this structure has been chosen to optimize cache + * performance. In particular 'seq' and 'read_data[0]' (combined) should fit + * into a single 64-byte cache line. + */ +struct clock_data { + seqcount_t seq; + struct clock_read_data read_data[2]; + ktime_t wrap_kt; + unsigned long rate; + + u64 (*actual_read_sched_clock)(void); }; static struct hrtimer sched_clock_timer; @@ -34,12 +73,6 @@ static int irqtime = -1; core_param(irqtime, irqtime, int, 0400); -static struct clock_data cd = { - .mult = NSEC_PER_SEC / HZ, -}; - -static u64 __read_mostly sched_clock_mask; - static u64 notrace jiffy_sched_clock_read(void) { /* @@ -49,7 +82,11 @@ static u64 notrace jiffy_sched_clock_read(void) return (u64)(jiffies - INITIAL_JIFFIES); } -static u64 __read_mostly (*read_sched_clock)(void) = jiffy_sched_clock_read; +static struct clock_data cd ____cacheline_aligned = { + .read_data[0] = { .mult = NSEC_PER_SEC / HZ, + .read_sched_clock = jiffy_sched_clock_read, }, + .actual_read_sched_clock = jiffy_sched_clock_read, +}; static inline u64 notrace cyc_to_ns(u64 cyc, u32 mult, u32 shift) { @@ -58,111 +95,136 @@ static inline u64 notrace cyc_to_ns(u64 cyc, u32 mult, u32 shift) unsigned long long notrace sched_clock(void) { - u64 epoch_ns; - u64 epoch_cyc; - u64 cyc; + u64 cyc, res; unsigned long seq; - - if (cd.suspended) - return cd.epoch_ns; + struct clock_read_data *rd; do { - seq = raw_read_seqcount_begin(&cd.seq); - epoch_cyc = cd.epoch_cyc; - epoch_ns = cd.epoch_ns; + seq = raw_read_seqcount(&cd.seq); + rd = cd.read_data + (seq & 1); + + cyc = (rd->read_sched_clock() - rd->epoch_cyc) & + rd->sched_clock_mask; + res = rd->epoch_ns + cyc_to_ns(cyc, rd->mult, rd->shift); } while (read_seqcount_retry(&cd.seq, seq)); - cyc = read_sched_clock(); - cyc = (cyc - epoch_cyc) & sched_clock_mask; - return epoch_ns + cyc_to_ns(cyc, cd.mult, cd.shift); + return res; +} + +/* + * Updating the data required to read the clock. + * + * sched_clock() will never observe mis-matched data even if called from + * an NMI. We do this by maintaining an odd/even copy of the data and + * steering sched_clock() to one or the other using a sequence counter. + * In order to preserve the data cache profile of sched_clock() as much + * as possible the system reverts back to the even copy when the update + * completes; the odd copy is used *only* during an update. + */ +static void update_clock_read_data(struct clock_read_data *rd) +{ + /* update the backup (odd) copy with the new data */ + cd.read_data[1] = *rd; + + /* steer readers towards the odd copy */ + raw_write_seqcount_latch(&cd.seq); + + /* now its safe for us to update the normal (even) copy */ + cd.read_data[0] = *rd; + + /* switch readers back to the even copy */ + raw_write_seqcount_latch(&cd.seq); } /* - * Atomically update the sched_clock epoch. + * Atomically update the sched_clock() epoch. */ -static void notrace update_sched_clock(void) +static void update_sched_clock(void) { - unsigned long flags; u64 cyc; u64 ns; + struct clock_read_data rd; + + rd = cd.read_data[0]; + + cyc = cd.actual_read_sched_clock(); + ns = rd.epoch_ns + cyc_to_ns((cyc - rd.epoch_cyc) & rd.sched_clock_mask, rd.mult, rd.shift); + + rd.epoch_ns = ns; + rd.epoch_cyc = cyc; - cyc = read_sched_clock(); - ns = cd.epoch_ns + - cyc_to_ns((cyc - cd.epoch_cyc) & sched_clock_mask, - cd.mult, cd.shift); - - raw_local_irq_save(flags); - raw_write_seqcount_begin(&cd.seq); - cd.epoch_ns = ns; - cd.epoch_cyc = cyc; - raw_write_seqcount_end(&cd.seq); - raw_local_irq_restore(flags); + update_clock_read_data(&rd); } static enum hrtimer_restart sched_clock_poll(struct hrtimer *hrt) { update_sched_clock(); hrtimer_forward_now(hrt, cd.wrap_kt); + return HRTIMER_RESTART; } -void __init sched_clock_register(u64 (*read)(void), int bits, - unsigned long rate) +void __init +sched_clock_register(u64 (*read)(void), int bits, unsigned long rate) { u64 res, wrap, new_mask, new_epoch, cyc, ns; u32 new_mult, new_shift; - ktime_t new_wrap_kt; unsigned long r; char r_unit; + struct clock_read_data rd; if (cd.rate > rate) return; WARN_ON(!irqs_disabled()); - /* calculate the mult/shift to convert counter ticks to ns. */ + /* Calculate the mult/shift to convert counter ticks to ns. */ clocks_calc_mult_shift(&new_mult, &new_shift, rate, NSEC_PER_SEC, 3600); new_mask = CLOCKSOURCE_MASK(bits); + cd.rate = rate; + + /* Calculate how many nanosecs until we risk wrapping */ + wrap = clocks_calc_max_nsecs(new_mult, new_shift, 0, new_mask, NULL); + cd.wrap_kt = ns_to_ktime(wrap); - /* calculate how many ns until we wrap */ - wrap = clocks_calc_max_nsecs(new_mult, new_shift, 0, new_mask); - new_wrap_kt = ns_to_ktime(wrap - (wrap >> 3)); + rd = cd.read_data[0]; - /* update epoch for new counter and update epoch_ns from old counter*/ + /* Update epoch for new counter and update 'epoch_ns' from old counter*/ new_epoch = read(); - cyc = read_sched_clock(); - ns = cd.epoch_ns + cyc_to_ns((cyc - cd.epoch_cyc) & sched_clock_mask, - cd.mult, cd.shift); + cyc = cd.actual_read_sched_clock(); + ns = rd.epoch_ns + cyc_to_ns((cyc - rd.epoch_cyc) & rd.sched_clock_mask, rd.mult, rd.shift); + cd.actual_read_sched_clock = read; - raw_write_seqcount_begin(&cd.seq); - read_sched_clock = read; - sched_clock_mask = new_mask; - cd.rate = rate; - cd.wrap_kt = new_wrap_kt; - cd.mult = new_mult; - cd.shift = new_shift; - cd.epoch_cyc = new_epoch; - cd.epoch_ns = ns; - raw_write_seqcount_end(&cd.seq); + rd.read_sched_clock = read; + rd.sched_clock_mask = new_mask; + rd.mult = new_mult; + rd.shift = new_shift; + rd.epoch_cyc = new_epoch; + rd.epoch_ns = ns; + + update_clock_read_data(&rd); r = rate; if (r >= 4000000) { r /= 1000000; r_unit = 'M'; - } else if (r >= 1000) { - r /= 1000; - r_unit = 'k'; - } else - r_unit = ' '; - - /* calculate the ns resolution of this counter */ + } else { + if (r >= 1000) { + r /= 1000; + r_unit = 'k'; + } else { + r_unit = ' '; + } + } + + /* Calculate the ns resolution of this counter */ res = cyc_to_ns(1ULL, new_mult, new_shift); pr_info("sched_clock: %u bits at %lu%cHz, resolution %lluns, wraps every %lluns\n", bits, r, r_unit, res, wrap); - /* Enable IRQ time accounting if we have a fast enough sched_clock */ + /* Enable IRQ time accounting if we have a fast enough sched_clock() */ if (irqtime > 0 || (irqtime == -1 && rate >= 1000000)) enable_sched_clock_irqtime(); @@ -172,10 +234,10 @@ void __init sched_clock_register(u64 (*read)(void), int bits, void __init sched_clock_postinit(void) { /* - * If no sched_clock function has been provided at that point, + * If no sched_clock() function has been provided at that point, * make it the final one one. */ - if (read_sched_clock == jiffy_sched_clock_read) + if (cd.actual_read_sched_clock == jiffy_sched_clock_read) sched_clock_register(jiffy_sched_clock_read, BITS_PER_LONG, HZ); update_sched_clock(); @@ -189,29 +251,53 @@ void __init sched_clock_postinit(void) hrtimer_start(&sched_clock_timer, cd.wrap_kt, HRTIMER_MODE_REL); } +/* + * Clock read function for use when the clock is suspended. + * + * This function makes it appear to sched_clock() as if the clock + * stopped counting at its last update. + * + * This function must only be called from the critical + * section in sched_clock(). It relies on the read_seqcount_retry() + * at the end of the critical section to be sure we observe the + * correct copy of 'epoch_cyc'. + */ +static u64 notrace suspended_sched_clock_read(void) +{ + unsigned long seq = raw_read_seqcount(&cd.seq); + + return cd.read_data[seq & 1].epoch_cyc; +} + static int sched_clock_suspend(void) { + struct clock_read_data *rd = &cd.read_data[0]; + update_sched_clock(); hrtimer_cancel(&sched_clock_timer); - cd.suspended = true; + rd->read_sched_clock = suspended_sched_clock_read; + return 0; } static void sched_clock_resume(void) { - cd.epoch_cyc = read_sched_clock(); + struct clock_read_data *rd = &cd.read_data[0]; + + rd->epoch_cyc = cd.actual_read_sched_clock(); hrtimer_start(&sched_clock_timer, cd.wrap_kt, HRTIMER_MODE_REL); - cd.suspended = false; + rd->read_sched_clock = cd.actual_read_sched_clock; } static struct syscore_ops sched_clock_ops = { - .suspend = sched_clock_suspend, - .resume = sched_clock_resume, + .suspend = sched_clock_suspend, + .resume = sched_clock_resume, }; static int __init sched_clock_syscore_init(void) { register_syscore_ops(&sched_clock_ops); + return 0; } device_initcall(sched_clock_syscore_init); diff --git a/kernel/time/tick-broadcast-hrtimer.c b/kernel/time/tick-broadcast-hrtimer.c index eb682d5c697c..6aac4beedbbe 100644 --- a/kernel/time/tick-broadcast-hrtimer.c +++ b/kernel/time/tick-broadcast-hrtimer.c @@ -49,6 +49,7 @@ static void bc_set_mode(enum clock_event_mode mode, */ static int bc_set_next(ktime_t expires, struct clock_event_device *bc) { + int bc_moved; /* * We try to cancel the timer first. If the callback is on * flight on some other cpu then we let it handle it. If we @@ -60,9 +61,15 @@ static int bc_set_next(ktime_t expires, struct clock_event_device *bc) * restart the timer because we are in the callback, but we * can set the expiry time and let the callback return * HRTIMER_RESTART. + * + * Since we are in the idle loop at this point and because + * hrtimer_{start/cancel} functions call into tracing, + * calls to these functions must be bound within RCU_NONIDLE. */ - if (hrtimer_try_to_cancel(&bctimer) >= 0) { - hrtimer_start(&bctimer, expires, HRTIMER_MODE_ABS_PINNED); + RCU_NONIDLE(bc_moved = (hrtimer_try_to_cancel(&bctimer) >= 0) ? + !hrtimer_start(&bctimer, expires, HRTIMER_MODE_ABS_PINNED) : + 0); + if (bc_moved) { /* Bind the "device" to the cpu */ bc->bound_on = smp_processor_id(); } else if (bc->bound_on == smp_processor_id()) { diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c index 066f0ec05e48..7e8ca4f448a8 100644 --- a/kernel/time/tick-broadcast.c +++ b/kernel/time/tick-broadcast.c @@ -33,12 +33,14 @@ static cpumask_var_t tick_broadcast_mask; static cpumask_var_t tick_broadcast_on; static cpumask_var_t tmpmask; static DEFINE_RAW_SPINLOCK(tick_broadcast_lock); -static int tick_broadcast_force; +static int tick_broadcast_forced; #ifdef CONFIG_TICK_ONESHOT static void tick_broadcast_clear_oneshot(int cpu); +static void tick_resume_broadcast_oneshot(struct clock_event_device *bc); #else static inline void tick_broadcast_clear_oneshot(int cpu) { } +static inline void tick_resume_broadcast_oneshot(struct clock_event_device *bc) { } #endif /* @@ -303,7 +305,7 @@ static void tick_handle_periodic_broadcast(struct clock_event_device *dev) /* * The device is in periodic mode. No reprogramming necessary: */ - if (dev->mode == CLOCK_EVT_MODE_PERIODIC) + if (dev->state == CLOCK_EVT_STATE_PERIODIC) goto unlock; /* @@ -324,49 +326,54 @@ unlock: raw_spin_unlock(&tick_broadcast_lock); } -/* - * Powerstate information: The system enters/leaves a state, where - * affected devices might stop +/** + * tick_broadcast_control - Enable/disable or force broadcast mode + * @mode: The selected broadcast mode + * + * Called when the system enters a state where affected tick devices + * might stop. Note: TICK_BROADCAST_FORCE cannot be undone. + * + * Called with interrupts disabled, so clockevents_lock is not + * required here because the local clock event device cannot go away + * under us. */ -static void tick_do_broadcast_on_off(unsigned long *reason) +void tick_broadcast_control(enum tick_broadcast_mode mode) { struct clock_event_device *bc, *dev; struct tick_device *td; - unsigned long flags; int cpu, bc_stopped; - raw_spin_lock_irqsave(&tick_broadcast_lock, flags); - - cpu = smp_processor_id(); - td = &per_cpu(tick_cpu_device, cpu); + td = this_cpu_ptr(&tick_cpu_device); dev = td->evtdev; - bc = tick_broadcast_device.evtdev; /* * Is the device not affected by the powerstate ? */ if (!dev || !(dev->features & CLOCK_EVT_FEAT_C3STOP)) - goto out; + return; if (!tick_device_is_functional(dev)) - goto out; + return; + raw_spin_lock(&tick_broadcast_lock); + cpu = smp_processor_id(); + bc = tick_broadcast_device.evtdev; bc_stopped = cpumask_empty(tick_broadcast_mask); - switch (*reason) { - case CLOCK_EVT_NOTIFY_BROADCAST_ON: - case CLOCK_EVT_NOTIFY_BROADCAST_FORCE: + switch (mode) { + case TICK_BROADCAST_FORCE: + tick_broadcast_forced = 1; + case TICK_BROADCAST_ON: cpumask_set_cpu(cpu, tick_broadcast_on); if (!cpumask_test_and_set_cpu(cpu, tick_broadcast_mask)) { if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC) clockevents_shutdown(dev); } - if (*reason == CLOCK_EVT_NOTIFY_BROADCAST_FORCE) - tick_broadcast_force = 1; break; - case CLOCK_EVT_NOTIFY_BROADCAST_OFF: - if (tick_broadcast_force) + + case TICK_BROADCAST_OFF: + if (tick_broadcast_forced) break; cpumask_clear_cpu(cpu, tick_broadcast_on); if (!tick_device_is_functional(dev)) @@ -388,22 +395,9 @@ static void tick_do_broadcast_on_off(unsigned long *reason) else tick_broadcast_setup_oneshot(bc); } -out: - raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags); -} - -/* - * Powerstate information: The system enters/leaves a state, where - * affected devices might stop. - */ -void tick_broadcast_on_off(unsigned long reason, int *oncpu) -{ - if (!cpumask_test_cpu(*oncpu, cpu_online_mask)) - printk(KERN_ERR "tick-broadcast: ignoring broadcast for " - "offline CPU #%d\n", *oncpu); - else - tick_do_broadcast_on_off(&reason); + raw_spin_unlock(&tick_broadcast_lock); } +EXPORT_SYMBOL_GPL(tick_broadcast_control); /* * Set the periodic handler depending on broadcast on/off @@ -416,14 +410,14 @@ void tick_set_periodic_handler(struct clock_event_device *dev, int broadcast) dev->event_handler = tick_handle_periodic_broadcast; } +#ifdef CONFIG_HOTPLUG_CPU /* * Remove a CPU from broadcasting */ -void tick_shutdown_broadcast(unsigned int *cpup) +void tick_shutdown_broadcast(unsigned int cpu) { struct clock_event_device *bc; unsigned long flags; - unsigned int cpu = *cpup; raw_spin_lock_irqsave(&tick_broadcast_lock, flags); @@ -438,6 +432,7 @@ void tick_shutdown_broadcast(unsigned int *cpup) raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags); } +#endif void tick_suspend_broadcast(void) { @@ -453,38 +448,48 @@ void tick_suspend_broadcast(void) raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags); } -int tick_resume_broadcast(void) +/* + * This is called from tick_resume_local() on a resuming CPU. That's + * called from the core resume function, tick_unfreeze() and the magic XEN + * resume hackery. + * + * In none of these cases the broadcast device mode can change and the + * bit of the resuming CPU in the broadcast mask is safe as well. + */ +bool tick_resume_check_broadcast(void) +{ + if (tick_broadcast_device.mode == TICKDEV_MODE_ONESHOT) + return false; + else + return cpumask_test_cpu(smp_processor_id(), tick_broadcast_mask); +} + +void tick_resume_broadcast(void) { struct clock_event_device *bc; unsigned long flags; - int broadcast = 0; raw_spin_lock_irqsave(&tick_broadcast_lock, flags); bc = tick_broadcast_device.evtdev; if (bc) { - clockevents_set_mode(bc, CLOCK_EVT_MODE_RESUME); + clockevents_tick_resume(bc); switch (tick_broadcast_device.mode) { case TICKDEV_MODE_PERIODIC: if (!cpumask_empty(tick_broadcast_mask)) tick_broadcast_start_periodic(bc); - broadcast = cpumask_test_cpu(smp_processor_id(), - tick_broadcast_mask); break; case TICKDEV_MODE_ONESHOT: if (!cpumask_empty(tick_broadcast_mask)) - broadcast = tick_resume_broadcast_oneshot(bc); + tick_resume_broadcast_oneshot(bc); break; } } raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags); - - return broadcast; } - #ifdef CONFIG_TICK_ONESHOT static cpumask_var_t tick_broadcast_oneshot_mask; @@ -532,8 +537,8 @@ static int tick_broadcast_set_event(struct clock_event_device *bc, int cpu, { int ret; - if (bc->mode != CLOCK_EVT_MODE_ONESHOT) - clockevents_set_mode(bc, CLOCK_EVT_MODE_ONESHOT); + if (bc->state != CLOCK_EVT_STATE_ONESHOT) + clockevents_set_state(bc, CLOCK_EVT_STATE_ONESHOT); ret = clockevents_program_event(bc, expires, force); if (!ret) @@ -541,10 +546,9 @@ static int tick_broadcast_set_event(struct clock_event_device *bc, int cpu, return ret; } -int tick_resume_broadcast_oneshot(struct clock_event_device *bc) +static void tick_resume_broadcast_oneshot(struct clock_event_device *bc) { - clockevents_set_mode(bc, CLOCK_EVT_MODE_ONESHOT); - return 0; + clockevents_set_state(bc, CLOCK_EVT_STATE_ONESHOT); } /* @@ -562,8 +566,8 @@ void tick_check_oneshot_broadcast_this_cpu(void) * switched over, leave the device alone. */ if (td->mode == TICKDEV_MODE_ONESHOT) { - clockevents_set_mode(td->evtdev, - CLOCK_EVT_MODE_ONESHOT); + clockevents_set_state(td->evtdev, + CLOCK_EVT_STATE_ONESHOT); } } } @@ -666,31 +670,26 @@ static void broadcast_shutdown_local(struct clock_event_device *bc, if (dev->next_event.tv64 < bc->next_event.tv64) return; } - clockevents_set_mode(dev, CLOCK_EVT_MODE_SHUTDOWN); + clockevents_set_state(dev, CLOCK_EVT_STATE_SHUTDOWN); } -static void broadcast_move_bc(int deadcpu) -{ - struct clock_event_device *bc = tick_broadcast_device.evtdev; - - if (!bc || !broadcast_needs_cpu(bc, deadcpu)) - return; - /* This moves the broadcast assignment to this cpu */ - clockevents_program_event(bc, bc->next_event, 1); -} - -/* - * Powerstate information: The system enters/leaves a state, where - * affected devices might stop +/** + * tick_broadcast_oneshot_control - Enter/exit broadcast oneshot mode + * @state: The target state (enter/exit) + * + * The system enters/leaves a state, where affected devices might stop * Returns 0 on success, -EBUSY if the cpu is used to broadcast wakeups. + * + * Called with interrupts disabled, so clockevents_lock is not + * required here because the local clock event device cannot go away + * under us. */ -int tick_broadcast_oneshot_control(unsigned long reason) +int tick_broadcast_oneshot_control(enum tick_broadcast_state state) { struct clock_event_device *bc, *dev; struct tick_device *td; - unsigned long flags; - ktime_t now; int cpu, ret = 0; + ktime_t now; /* * Periodic mode does not care about the enter/exit of power @@ -703,17 +702,17 @@ int tick_broadcast_oneshot_control(unsigned long reason) * We are called with preemtion disabled from the depth of the * idle code, so we can't be moved away. */ - cpu = smp_processor_id(); - td = &per_cpu(tick_cpu_device, cpu); + td = this_cpu_ptr(&tick_cpu_device); dev = td->evtdev; if (!(dev->features & CLOCK_EVT_FEAT_C3STOP)) return 0; + raw_spin_lock(&tick_broadcast_lock); bc = tick_broadcast_device.evtdev; + cpu = smp_processor_id(); - raw_spin_lock_irqsave(&tick_broadcast_lock, flags); - if (reason == CLOCK_EVT_NOTIFY_BROADCAST_ENTER) { + if (state == TICK_BROADCAST_ENTER) { if (!cpumask_test_and_set_cpu(cpu, tick_broadcast_oneshot_mask)) { WARN_ON_ONCE(cpumask_test_cpu(cpu, tick_broadcast_pending_mask)); broadcast_shutdown_local(bc, dev); @@ -741,7 +740,7 @@ int tick_broadcast_oneshot_control(unsigned long reason) cpumask_clear_cpu(cpu, tick_broadcast_oneshot_mask); } else { if (cpumask_test_and_clear_cpu(cpu, tick_broadcast_oneshot_mask)) { - clockevents_set_mode(dev, CLOCK_EVT_MODE_ONESHOT); + clockevents_set_state(dev, CLOCK_EVT_STATE_ONESHOT); /* * The cpu which was handling the broadcast * timer marked this cpu in the broadcast @@ -805,9 +804,10 @@ int tick_broadcast_oneshot_control(unsigned long reason) } } out: - raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags); + raw_spin_unlock(&tick_broadcast_lock); return ret; } +EXPORT_SYMBOL_GPL(tick_broadcast_oneshot_control); /* * Reset the one shot broadcast for a cpu @@ -842,7 +842,7 @@ void tick_broadcast_setup_oneshot(struct clock_event_device *bc) /* Set it up only once ! */ if (bc->event_handler != tick_handle_oneshot_broadcast) { - int was_periodic = bc->mode == CLOCK_EVT_MODE_PERIODIC; + int was_periodic = bc->state == CLOCK_EVT_STATE_PERIODIC; bc->event_handler = tick_handle_oneshot_broadcast; @@ -858,7 +858,7 @@ void tick_broadcast_setup_oneshot(struct clock_event_device *bc) tick_broadcast_oneshot_mask, tmpmask); if (was_periodic && !cpumask_empty(tmpmask)) { - clockevents_set_mode(bc, CLOCK_EVT_MODE_ONESHOT); + clockevents_set_state(bc, CLOCK_EVT_STATE_ONESHOT); tick_broadcast_init_next_event(tmpmask, tick_next_period); tick_broadcast_set_event(bc, cpu, tick_next_period, 1); @@ -894,14 +894,28 @@ void tick_broadcast_switch_to_oneshot(void) raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags); } +#ifdef CONFIG_HOTPLUG_CPU +void hotplug_cpu__broadcast_tick_pull(int deadcpu) +{ + struct clock_event_device *bc; + unsigned long flags; + + raw_spin_lock_irqsave(&tick_broadcast_lock, flags); + bc = tick_broadcast_device.evtdev; + + if (bc && broadcast_needs_cpu(bc, deadcpu)) { + /* This moves the broadcast assignment to this CPU: */ + clockevents_program_event(bc, bc->next_event, 1); + } + raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags); +} /* * Remove a dead CPU from broadcasting */ -void tick_shutdown_broadcast_oneshot(unsigned int *cpup) +void tick_shutdown_broadcast_oneshot(unsigned int cpu) { unsigned long flags; - unsigned int cpu = *cpup; raw_spin_lock_irqsave(&tick_broadcast_lock, flags); @@ -913,10 +927,9 @@ void tick_shutdown_broadcast_oneshot(unsigned int *cpup) cpumask_clear_cpu(cpu, tick_broadcast_pending_mask); cpumask_clear_cpu(cpu, tick_broadcast_force_mask); - broadcast_move_bc(cpu); - raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags); } +#endif /* * Check, whether the broadcast device is in one shot mode diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c index f7c515595b42..3ae6afa1eb98 100644 --- a/kernel/time/tick-common.c +++ b/kernel/time/tick-common.c @@ -102,7 +102,7 @@ void tick_handle_periodic(struct clock_event_device *dev) tick_periodic(cpu); - if (dev->mode != CLOCK_EVT_MODE_ONESHOT) + if (dev->state != CLOCK_EVT_STATE_ONESHOT) return; for (;;) { /* @@ -140,7 +140,7 @@ void tick_setup_periodic(struct clock_event_device *dev, int broadcast) if ((dev->features & CLOCK_EVT_FEAT_PERIODIC) && !tick_broadcast_oneshot_active()) { - clockevents_set_mode(dev, CLOCK_EVT_MODE_PERIODIC); + clockevents_set_state(dev, CLOCK_EVT_STATE_PERIODIC); } else { unsigned long seq; ktime_t next; @@ -150,7 +150,7 @@ void tick_setup_periodic(struct clock_event_device *dev, int broadcast) next = tick_next_period; } while (read_seqretry(&jiffies_lock, seq)); - clockevents_set_mode(dev, CLOCK_EVT_MODE_ONESHOT); + clockevents_set_state(dev, CLOCK_EVT_STATE_ONESHOT); for (;;) { if (!clockevents_program_event(dev, next, false)) @@ -332,14 +332,16 @@ out_bc: tick_install_broadcast_device(newdev); } +#ifdef CONFIG_HOTPLUG_CPU /* * Transfer the do_timer job away from a dying cpu. * - * Called with interrupts disabled. + * Called with interrupts disabled. Not locking required. If + * tick_do_timer_cpu is owned by this cpu, nothing can change it. */ -void tick_handover_do_timer(int *cpup) +void tick_handover_do_timer(void) { - if (*cpup == tick_do_timer_cpu) { + if (tick_do_timer_cpu == smp_processor_id()) { int cpu = cpumask_first(cpu_online_mask); tick_do_timer_cpu = (cpu < nr_cpu_ids) ? cpu : @@ -354,9 +356,9 @@ void tick_handover_do_timer(int *cpup) * access the hardware device itself. * We just set the mode and remove it from the lists. */ -void tick_shutdown(unsigned int *cpup) +void tick_shutdown(unsigned int cpu) { - struct tick_device *td = &per_cpu(tick_cpu_device, *cpup); + struct tick_device *td = &per_cpu(tick_cpu_device, cpu); struct clock_event_device *dev = td->evtdev; td->mode = TICKDEV_MODE_PERIODIC; @@ -365,27 +367,42 @@ void tick_shutdown(unsigned int *cpup) * Prevent that the clock events layer tries to call * the set mode function! */ + dev->state = CLOCK_EVT_STATE_DETACHED; dev->mode = CLOCK_EVT_MODE_UNUSED; clockevents_exchange_device(dev, NULL); dev->event_handler = clockevents_handle_noop; td->evtdev = NULL; } } +#endif -void tick_suspend(void) +/** + * tick_suspend_local - Suspend the local tick device + * + * Called from the local cpu for freeze with interrupts disabled. + * + * No locks required. Nothing can change the per cpu device. + */ +void tick_suspend_local(void) { struct tick_device *td = this_cpu_ptr(&tick_cpu_device); clockevents_shutdown(td->evtdev); } -void tick_resume(void) +/** + * tick_resume_local - Resume the local tick device + * + * Called from the local CPU for unfreeze or XEN resume magic. + * + * No locks required. Nothing can change the per cpu device. + */ +void tick_resume_local(void) { struct tick_device *td = this_cpu_ptr(&tick_cpu_device); - int broadcast = tick_resume_broadcast(); - - clockevents_set_mode(td->evtdev, CLOCK_EVT_MODE_RESUME); + bool broadcast = tick_resume_check_broadcast(); + clockevents_tick_resume(td->evtdev); if (!broadcast) { if (td->mode == TICKDEV_MODE_PERIODIC) tick_setup_periodic(td->evtdev, 0); @@ -394,6 +411,35 @@ void tick_resume(void) } } +/** + * tick_suspend - Suspend the tick and the broadcast device + * + * Called from syscore_suspend() via timekeeping_suspend with only one + * CPU online and interrupts disabled or from tick_unfreeze() under + * tick_freeze_lock. + * + * No locks required. Nothing can change the per cpu device. + */ +void tick_suspend(void) +{ + tick_suspend_local(); + tick_suspend_broadcast(); +} + +/** + * tick_resume - Resume the tick and the broadcast device + * + * Called from syscore_resume() via timekeeping_resume with only one + * CPU online and interrupts disabled. + * + * No locks required. Nothing can change the per cpu device. + */ +void tick_resume(void) +{ + tick_resume_broadcast(); + tick_resume_local(); +} + static DEFINE_RAW_SPINLOCK(tick_freeze_lock); static unsigned int tick_freeze_depth; @@ -411,12 +457,10 @@ void tick_freeze(void) raw_spin_lock(&tick_freeze_lock); tick_freeze_depth++; - if (tick_freeze_depth == num_online_cpus()) { + if (tick_freeze_depth == num_online_cpus()) timekeeping_suspend(); - } else { - tick_suspend(); - tick_suspend_broadcast(); - } + else + tick_suspend_local(); raw_spin_unlock(&tick_freeze_lock); } @@ -437,7 +481,7 @@ void tick_unfreeze(void) if (tick_freeze_depth == num_online_cpus()) timekeeping_resume(); else - tick_resume(); + tick_resume_local(); tick_freeze_depth--; diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h index 366aeb4f2c66..b64fdd8054c5 100644 --- a/kernel/time/tick-internal.h +++ b/kernel/time/tick-internal.h @@ -5,15 +5,12 @@ #include <linux/tick.h> #include "timekeeping.h" +#include "tick-sched.h" -extern seqlock_t jiffies_lock; +#ifdef CONFIG_GENERIC_CLOCKEVENTS -#define CS_NAME_LEN 32 - -#ifdef CONFIG_GENERIC_CLOCKEVENTS_BUILD - -#define TICK_DO_TIMER_NONE -1 -#define TICK_DO_TIMER_BOOT -2 +# define TICK_DO_TIMER_NONE -1 +# define TICK_DO_TIMER_BOOT -2 DECLARE_PER_CPU(struct tick_device, tick_cpu_device); extern ktime_t tick_next_period; @@ -23,21 +20,72 @@ extern int tick_do_timer_cpu __read_mostly; extern void tick_setup_periodic(struct clock_event_device *dev, int broadcast); extern void tick_handle_periodic(struct clock_event_device *dev); extern void tick_check_new_device(struct clock_event_device *dev); -extern void tick_handover_do_timer(int *cpup); -extern void tick_shutdown(unsigned int *cpup); +extern void tick_shutdown(unsigned int cpu); extern void tick_suspend(void); extern void tick_resume(void); extern bool tick_check_replacement(struct clock_event_device *curdev, struct clock_event_device *newdev); extern void tick_install_replacement(struct clock_event_device *dev); +extern int tick_is_oneshot_available(void); +extern struct tick_device *tick_get_device(int cpu); -extern void clockevents_shutdown(struct clock_event_device *dev); +extern int clockevents_tick_resume(struct clock_event_device *dev); +/* Check, if the device is functional or a dummy for broadcast */ +static inline int tick_device_is_functional(struct clock_event_device *dev) +{ + return !(dev->features & CLOCK_EVT_FEAT_DUMMY); +} +extern void clockevents_shutdown(struct clock_event_device *dev); +extern void clockevents_exchange_device(struct clock_event_device *old, + struct clock_event_device *new); +extern void clockevents_set_state(struct clock_event_device *dev, + enum clock_event_state state); +extern int clockevents_program_event(struct clock_event_device *dev, + ktime_t expires, bool force); +extern void clockevents_handle_noop(struct clock_event_device *dev); +extern int __clockevents_update_freq(struct clock_event_device *dev, u32 freq); extern ssize_t sysfs_get_uname(const char *buf, char *dst, size_t cnt); -/* - * NO_HZ / high resolution timer shared code - */ +/* Broadcasting support */ +# ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST +extern int tick_device_uses_broadcast(struct clock_event_device *dev, int cpu); +extern void tick_install_broadcast_device(struct clock_event_device *dev); +extern int tick_is_broadcast_device(struct clock_event_device *dev); +extern void tick_shutdown_broadcast(unsigned int cpu); +extern void tick_suspend_broadcast(void); +extern void tick_resume_broadcast(void); +extern bool tick_resume_check_broadcast(void); +extern void tick_broadcast_init(void); +extern void tick_set_periodic_handler(struct clock_event_device *dev, int broadcast); +extern int tick_broadcast_update_freq(struct clock_event_device *dev, u32 freq); +extern struct tick_device *tick_get_broadcast_device(void); +extern struct cpumask *tick_get_broadcast_mask(void); +# else /* !CONFIG_GENERIC_CLOCKEVENTS_BROADCAST: */ +static inline void tick_install_broadcast_device(struct clock_event_device *dev) { } +static inline int tick_is_broadcast_device(struct clock_event_device *dev) { return 0; } +static inline int tick_device_uses_broadcast(struct clock_event_device *dev, int cpu) { return 0; } +static inline void tick_do_periodic_broadcast(struct clock_event_device *d) { } +static inline void tick_shutdown_broadcast(unsigned int cpu) { } +static inline void tick_suspend_broadcast(void) { } +static inline void tick_resume_broadcast(void) { } +static inline bool tick_resume_check_broadcast(void) { return false; } +static inline void tick_broadcast_init(void) { } +static inline int tick_broadcast_update_freq(struct clock_event_device *dev, u32 freq) { return -ENODEV; } + +/* Set the periodic handler in non broadcast mode */ +static inline void tick_set_periodic_handler(struct clock_event_device *dev, int broadcast) +{ + dev->event_handler = tick_handle_periodic; +} +# endif /* !CONFIG_GENERIC_CLOCKEVENTS_BROADCAST */ + +#else /* !GENERIC_CLOCKEVENTS: */ +static inline void tick_suspend(void) { } +static inline void tick_resume(void) { } +#endif /* !GENERIC_CLOCKEVENTS */ + +/* Oneshot related functions */ #ifdef CONFIG_TICK_ONESHOT extern void tick_setup_oneshot(struct clock_event_device *newdev, void (*handler)(struct clock_event_device *), @@ -46,58 +94,42 @@ extern int tick_program_event(ktime_t expires, int force); extern void tick_oneshot_notify(void); extern int tick_switch_to_oneshot(void (*handler)(struct clock_event_device *)); extern void tick_resume_oneshot(void); -# ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST +static inline bool tick_oneshot_possible(void) { return true; } +extern int tick_oneshot_mode_active(void); +extern void tick_clock_notify(void); +extern int tick_check_oneshot_change(int allow_nohz); +extern int tick_init_highres(void); +#else /* !CONFIG_TICK_ONESHOT: */ +static inline +void tick_setup_oneshot(struct clock_event_device *newdev, + void (*handler)(struct clock_event_device *), + ktime_t nextevt) { BUG(); } +static inline void tick_resume_oneshot(void) { BUG(); } +static inline int tick_program_event(ktime_t expires, int force) { return 0; } +static inline void tick_oneshot_notify(void) { } +static inline bool tick_oneshot_possible(void) { return false; } +static inline int tick_oneshot_mode_active(void) { return 0; } +static inline void tick_clock_notify(void) { } +static inline int tick_check_oneshot_change(int allow_nohz) { return 0; } +#endif /* !CONFIG_TICK_ONESHOT */ + +/* Functions related to oneshot broadcasting */ +#if defined(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST) && defined(CONFIG_TICK_ONESHOT) extern void tick_broadcast_setup_oneshot(struct clock_event_device *bc); -extern int tick_broadcast_oneshot_control(unsigned long reason); extern void tick_broadcast_switch_to_oneshot(void); -extern void tick_shutdown_broadcast_oneshot(unsigned int *cpup); -extern int tick_resume_broadcast_oneshot(struct clock_event_device *bc); +extern void tick_shutdown_broadcast_oneshot(unsigned int cpu); extern int tick_broadcast_oneshot_active(void); extern void tick_check_oneshot_broadcast_this_cpu(void); bool tick_broadcast_oneshot_available(void); -# else /* BROADCAST */ -static inline void tick_broadcast_setup_oneshot(struct clock_event_device *bc) -{ - BUG(); -} -static inline int tick_broadcast_oneshot_control(unsigned long reason) { return 0; } +extern struct cpumask *tick_get_broadcast_oneshot_mask(void); +#else /* !(BROADCAST && ONESHOT): */ +static inline void tick_broadcast_setup_oneshot(struct clock_event_device *bc) { BUG(); } static inline void tick_broadcast_switch_to_oneshot(void) { } -static inline void tick_shutdown_broadcast_oneshot(unsigned int *cpup) { } +static inline void tick_shutdown_broadcast_oneshot(unsigned int cpu) { } static inline int tick_broadcast_oneshot_active(void) { return 0; } static inline void tick_check_oneshot_broadcast_this_cpu(void) { } -static inline bool tick_broadcast_oneshot_available(void) { return true; } -# endif /* !BROADCAST */ - -#else /* !ONESHOT */ -static inline -void tick_setup_oneshot(struct clock_event_device *newdev, - void (*handler)(struct clock_event_device *), - ktime_t nextevt) -{ - BUG(); -} -static inline void tick_resume_oneshot(void) -{ - BUG(); -} -static inline int tick_program_event(ktime_t expires, int force) -{ - return 0; -} -static inline void tick_oneshot_notify(void) { } -static inline void tick_broadcast_setup_oneshot(struct clock_event_device *bc) -{ - BUG(); -} -static inline int tick_broadcast_oneshot_control(unsigned long reason) { return 0; } -static inline void tick_shutdown_broadcast_oneshot(unsigned int *cpup) { } -static inline int tick_resume_broadcast_oneshot(struct clock_event_device *bc) -{ - return 0; -} -static inline int tick_broadcast_oneshot_active(void) { return 0; } -static inline bool tick_broadcast_oneshot_available(void) { return false; } -#endif /* !TICK_ONESHOT */ +static inline bool tick_broadcast_oneshot_available(void) { return tick_oneshot_possible(); } +#endif /* !(BROADCAST && ONESHOT) */ /* NO_HZ_FULL internal */ #ifdef CONFIG_NO_HZ_FULL @@ -105,68 +137,3 @@ extern void tick_nohz_init(void); # else static inline void tick_nohz_init(void) { } #endif - -/* - * Broadcasting support - */ -#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST -extern int tick_device_uses_broadcast(struct clock_event_device *dev, int cpu); -extern void tick_install_broadcast_device(struct clock_event_device *dev); -extern int tick_is_broadcast_device(struct clock_event_device *dev); -extern void tick_broadcast_on_off(unsigned long reason, int *oncpu); -extern void tick_shutdown_broadcast(unsigned int *cpup); -extern void tick_suspend_broadcast(void); -extern int tick_resume_broadcast(void); -extern void tick_broadcast_init(void); -extern void -tick_set_periodic_handler(struct clock_event_device *dev, int broadcast); -int tick_broadcast_update_freq(struct clock_event_device *dev, u32 freq); - -#else /* !BROADCAST */ - -static inline void tick_install_broadcast_device(struct clock_event_device *dev) -{ -} - -static inline int tick_is_broadcast_device(struct clock_event_device *dev) -{ - return 0; -} -static inline int tick_device_uses_broadcast(struct clock_event_device *dev, - int cpu) -{ - return 0; -} -static inline void tick_do_periodic_broadcast(struct clock_event_device *d) { } -static inline void tick_broadcast_on_off(unsigned long reason, int *oncpu) { } -static inline void tick_shutdown_broadcast(unsigned int *cpup) { } -static inline void tick_suspend_broadcast(void) { } -static inline int tick_resume_broadcast(void) { return 0; } -static inline void tick_broadcast_init(void) { } -static inline int tick_broadcast_update_freq(struct clock_event_device *dev, - u32 freq) { return -ENODEV; } - -/* - * Set the periodic handler in non broadcast mode - */ -static inline void tick_set_periodic_handler(struct clock_event_device *dev, - int broadcast) -{ - dev->event_handler = tick_handle_periodic; -} -#endif /* !BROADCAST */ - -/* - * Check, if the device is functional or a dummy for broadcast - */ -static inline int tick_device_is_functional(struct clock_event_device *dev) -{ - return !(dev->features & CLOCK_EVT_FEAT_DUMMY); -} - -int __clockevents_update_freq(struct clock_event_device *dev, u32 freq); - -#endif - -extern void do_timer(unsigned long ticks); -extern void update_wall_time(void); diff --git a/kernel/time/tick-oneshot.c b/kernel/time/tick-oneshot.c index 7ce740e78e1b..67a64b1670bf 100644 --- a/kernel/time/tick-oneshot.c +++ b/kernel/time/tick-oneshot.c @@ -38,7 +38,7 @@ void tick_resume_oneshot(void) { struct clock_event_device *dev = __this_cpu_read(tick_cpu_device.evtdev); - clockevents_set_mode(dev, CLOCK_EVT_MODE_ONESHOT); + clockevents_set_state(dev, CLOCK_EVT_STATE_ONESHOT); clockevents_program_event(dev, ktime_get(), true); } @@ -50,7 +50,7 @@ void tick_setup_oneshot(struct clock_event_device *newdev, ktime_t next_event) { newdev->event_handler = handler; - clockevents_set_mode(newdev, CLOCK_EVT_MODE_ONESHOT); + clockevents_set_state(newdev, CLOCK_EVT_STATE_ONESHOT); clockevents_program_event(newdev, next_event, true); } @@ -81,7 +81,7 @@ int tick_switch_to_oneshot(void (*handler)(struct clock_event_device *)) td->mode = TICKDEV_MODE_ONESHOT; dev->event_handler = handler; - clockevents_set_mode(dev, CLOCK_EVT_MODE_ONESHOT); + clockevents_set_state(dev, CLOCK_EVT_STATE_ONESHOT); tick_broadcast_switch_to_oneshot(); return 0; } diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index a4c4edac4528..914259128145 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -34,7 +34,7 @@ /* * Per cpu nohz control structure */ -DEFINE_PER_CPU(struct tick_sched, tick_cpu_sched); +static DEFINE_PER_CPU(struct tick_sched, tick_cpu_sched); /* * The time, when the last jiffy update happened. Protected by jiffies_lock. @@ -416,6 +416,11 @@ static int __init setup_tick_nohz(char *str) __setup("nohz=", setup_tick_nohz); +int tick_nohz_tick_stopped(void) +{ + return __this_cpu_read(tick_cpu_sched.tick_stopped); +} + /** * tick_nohz_update_jiffies - update jiffies when idle was interrupted * diff --git a/kernel/time/tick-sched.h b/kernel/time/tick-sched.h new file mode 100644 index 000000000000..28b5da3e1a17 --- /dev/null +++ b/kernel/time/tick-sched.h @@ -0,0 +1,74 @@ +#ifndef _TICK_SCHED_H +#define _TICK_SCHED_H + +#include <linux/hrtimer.h> + +enum tick_device_mode { + TICKDEV_MODE_PERIODIC, + TICKDEV_MODE_ONESHOT, +}; + +struct tick_device { + struct clock_event_device *evtdev; + enum tick_device_mode mode; +}; + +enum tick_nohz_mode { + NOHZ_MODE_INACTIVE, + NOHZ_MODE_LOWRES, + NOHZ_MODE_HIGHRES, +}; + +/** + * struct tick_sched - sched tick emulation and no idle tick control/stats + * @sched_timer: hrtimer to schedule the periodic tick in high + * resolution mode + * @last_tick: Store the last tick expiry time when the tick + * timer is modified for nohz sleeps. This is necessary + * to resume the tick timer operation in the timeline + * when the CPU returns from nohz sleep. + * @tick_stopped: Indicator that the idle tick has been stopped + * @idle_jiffies: jiffies at the entry to idle for idle time accounting + * @idle_calls: Total number of idle calls + * @idle_sleeps: Number of idle calls, where the sched tick was stopped + * @idle_entrytime: Time when the idle call was entered + * @idle_waketime: Time when the idle was interrupted + * @idle_exittime: Time when the idle state was left + * @idle_sleeptime: Sum of the time slept in idle with sched tick stopped + * @iowait_sleeptime: Sum of the time slept in idle with sched tick stopped, with IO outstanding + * @sleep_length: Duration of the current idle sleep + * @do_timer_lst: CPU was the last one doing do_timer before going idle + */ +struct tick_sched { + struct hrtimer sched_timer; + unsigned long check_clocks; + enum tick_nohz_mode nohz_mode; + ktime_t last_tick; + int inidle; + int tick_stopped; + unsigned long idle_jiffies; + unsigned long idle_calls; + unsigned long idle_sleeps; + int idle_active; + ktime_t idle_entrytime; + ktime_t idle_waketime; + ktime_t idle_exittime; + ktime_t idle_sleeptime; + ktime_t iowait_sleeptime; + ktime_t sleep_length; + unsigned long last_jiffies; + unsigned long next_jiffies; + ktime_t idle_expires; + int do_timer_last; +}; + +extern struct tick_sched *tick_get_tick_sched(int cpu); + +extern void tick_setup_sched_timer(void); +#if defined CONFIG_NO_HZ_COMMON || defined CONFIG_HIGH_RES_TIMERS +extern void tick_cancel_sched_timer(int cpu); +#else +static inline void tick_cancel_sched_timer(int cpu) { } +#endif + +#endif diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 91db94136c10..946acb72179f 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -59,17 +59,15 @@ struct tk_fast { }; static struct tk_fast tk_fast_mono ____cacheline_aligned; +static struct tk_fast tk_fast_raw ____cacheline_aligned; /* flag for if timekeeping is suspended */ int __read_mostly timekeeping_suspended; -/* Flag for if there is a persistent clock on this platform */ -bool __read_mostly persistent_clock_exist = false; - static inline void tk_normalize_xtime(struct timekeeper *tk) { - while (tk->tkr.xtime_nsec >= ((u64)NSEC_PER_SEC << tk->tkr.shift)) { - tk->tkr.xtime_nsec -= (u64)NSEC_PER_SEC << tk->tkr.shift; + while (tk->tkr_mono.xtime_nsec >= ((u64)NSEC_PER_SEC << tk->tkr_mono.shift)) { + tk->tkr_mono.xtime_nsec -= (u64)NSEC_PER_SEC << tk->tkr_mono.shift; tk->xtime_sec++; } } @@ -79,20 +77,20 @@ static inline struct timespec64 tk_xtime(struct timekeeper *tk) struct timespec64 ts; ts.tv_sec = tk->xtime_sec; - ts.tv_nsec = (long)(tk->tkr.xtime_nsec >> tk->tkr.shift); + ts.tv_nsec = (long)(tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift); return ts; } static void tk_set_xtime(struct timekeeper *tk, const struct timespec64 *ts) { tk->xtime_sec = ts->tv_sec; - tk->tkr.xtime_nsec = (u64)ts->tv_nsec << tk->tkr.shift; + tk->tkr_mono.xtime_nsec = (u64)ts->tv_nsec << tk->tkr_mono.shift; } static void tk_xtime_add(struct timekeeper *tk, const struct timespec64 *ts) { tk->xtime_sec += ts->tv_sec; - tk->tkr.xtime_nsec += (u64)ts->tv_nsec << tk->tkr.shift; + tk->tkr_mono.xtime_nsec += (u64)ts->tv_nsec << tk->tkr_mono.shift; tk_normalize_xtime(tk); } @@ -118,6 +116,117 @@ static inline void tk_update_sleep_time(struct timekeeper *tk, ktime_t delta) tk->offs_boot = ktime_add(tk->offs_boot, delta); } +#ifdef CONFIG_DEBUG_TIMEKEEPING +#define WARNING_FREQ (HZ*300) /* 5 minute rate-limiting */ +/* + * These simple flag variables are managed + * without locks, which is racy, but ok since + * we don't really care about being super + * precise about how many events were seen, + * just that a problem was observed. + */ +static int timekeeping_underflow_seen; +static int timekeeping_overflow_seen; + +/* last_warning is only modified under the timekeeping lock */ +static long timekeeping_last_warning; + +static void timekeeping_check_update(struct timekeeper *tk, cycle_t offset) +{ + + cycle_t max_cycles = tk->tkr_mono.clock->max_cycles; + const char *name = tk->tkr_mono.clock->name; + + if (offset > max_cycles) { + printk_deferred("WARNING: timekeeping: Cycle offset (%lld) is larger than allowed by the '%s' clock's max_cycles value (%lld): time overflow danger\n", + offset, name, max_cycles); + printk_deferred(" timekeeping: Your kernel is sick, but tries to cope by capping time updates\n"); + } else { + if (offset > (max_cycles >> 1)) { + printk_deferred("INFO: timekeeping: Cycle offset (%lld) is larger than the the '%s' clock's 50%% safety margin (%lld)\n", + offset, name, max_cycles >> 1); + printk_deferred(" timekeeping: Your kernel is still fine, but is feeling a bit nervous\n"); + } + } + + if (timekeeping_underflow_seen) { + if (jiffies - timekeeping_last_warning > WARNING_FREQ) { + printk_deferred("WARNING: Underflow in clocksource '%s' observed, time update ignored.\n", name); + printk_deferred(" Please report this, consider using a different clocksource, if possible.\n"); + printk_deferred(" Your kernel is probably still fine.\n"); + timekeeping_last_warning = jiffies; + } + timekeeping_underflow_seen = 0; + } + + if (timekeeping_overflow_seen) { + if (jiffies - timekeeping_last_warning > WARNING_FREQ) { + printk_deferred("WARNING: Overflow in clocksource '%s' observed, time update capped.\n", name); + printk_deferred(" Please report this, consider using a different clocksource, if possible.\n"); + printk_deferred(" Your kernel is probably still fine.\n"); + timekeeping_last_warning = jiffies; + } + timekeeping_overflow_seen = 0; + } +} + +static inline cycle_t timekeeping_get_delta(struct tk_read_base *tkr) +{ + cycle_t now, last, mask, max, delta; + unsigned int seq; + + /* + * Since we're called holding a seqlock, the data may shift + * under us while we're doing the calculation. This can cause + * false positives, since we'd note a problem but throw the + * results away. So nest another seqlock here to atomically + * grab the points we are checking with. + */ + do { + seq = read_seqcount_begin(&tk_core.seq); + now = tkr->read(tkr->clock); + last = tkr->cycle_last; + mask = tkr->mask; + max = tkr->clock->max_cycles; + } while (read_seqcount_retry(&tk_core.seq, seq)); + + delta = clocksource_delta(now, last, mask); + + /* + * Try to catch underflows by checking if we are seeing small + * mask-relative negative values. + */ + if (unlikely((~delta & mask) < (mask >> 3))) { + timekeeping_underflow_seen = 1; + delta = 0; + } + + /* Cap delta value to the max_cycles values to avoid mult overflows */ + if (unlikely(delta > max)) { + timekeeping_overflow_seen = 1; + delta = tkr->clock->max_cycles; + } + + return delta; +} +#else +static inline void timekeeping_check_update(struct timekeeper *tk, cycle_t offset) +{ +} +static inline cycle_t timekeeping_get_delta(struct tk_read_base *tkr) +{ + cycle_t cycle_now, delta; + + /* read clocksource */ + cycle_now = tkr->read(tkr->clock); + + /* calculate the delta since the last update_wall_time */ + delta = clocksource_delta(cycle_now, tkr->cycle_last, tkr->mask); + + return delta; +} +#endif + /** * tk_setup_internals - Set up internals to use clocksource clock. * @@ -135,11 +244,16 @@ static void tk_setup_internals(struct timekeeper *tk, struct clocksource *clock) u64 tmp, ntpinterval; struct clocksource *old_clock; - old_clock = tk->tkr.clock; - tk->tkr.clock = clock; - tk->tkr.read = clock->read; - tk->tkr.mask = clock->mask; - tk->tkr.cycle_last = tk->tkr.read(clock); + old_clock = tk->tkr_mono.clock; + tk->tkr_mono.clock = clock; + tk->tkr_mono.read = clock->read; + tk->tkr_mono.mask = clock->mask; + tk->tkr_mono.cycle_last = tk->tkr_mono.read(clock); + + tk->tkr_raw.clock = clock; + tk->tkr_raw.read = clock->read; + tk->tkr_raw.mask = clock->mask; + tk->tkr_raw.cycle_last = tk->tkr_mono.cycle_last; /* Do the ns -> cycle conversion first, using original mult */ tmp = NTP_INTERVAL_LENGTH; @@ -163,11 +277,14 @@ static void tk_setup_internals(struct timekeeper *tk, struct clocksource *clock) if (old_clock) { int shift_change = clock->shift - old_clock->shift; if (shift_change < 0) - tk->tkr.xtime_nsec >>= -shift_change; + tk->tkr_mono.xtime_nsec >>= -shift_change; else - tk->tkr.xtime_nsec <<= shift_change; + tk->tkr_mono.xtime_nsec <<= shift_change; } - tk->tkr.shift = clock->shift; + tk->tkr_raw.xtime_nsec = 0; + + tk->tkr_mono.shift = clock->shift; + tk->tkr_raw.shift = clock->shift; tk->ntp_error = 0; tk->ntp_error_shift = NTP_SCALE_SHIFT - clock->shift; @@ -178,7 +295,8 @@ static void tk_setup_internals(struct timekeeper *tk, struct clocksource *clock) * active clocksource. These value will be adjusted via NTP * to counteract clock drifting. */ - tk->tkr.mult = clock->mult; + tk->tkr_mono.mult = clock->mult; + tk->tkr_raw.mult = clock->mult; tk->ntp_err_mult = 0; } @@ -193,14 +311,10 @@ static inline u32 arch_gettimeoffset(void) { return 0; } static inline s64 timekeeping_get_ns(struct tk_read_base *tkr) { - cycle_t cycle_now, delta; + cycle_t delta; s64 nsec; - /* read clocksource: */ - cycle_now = tkr->read(tkr->clock); - - /* calculate the delta since the last update_wall_time: */ - delta = clocksource_delta(cycle_now, tkr->cycle_last, tkr->mask); + delta = timekeeping_get_delta(tkr); nsec = delta * tkr->mult + tkr->xtime_nsec; nsec >>= tkr->shift; @@ -209,25 +323,6 @@ static inline s64 timekeeping_get_ns(struct tk_read_base *tkr) return nsec + arch_gettimeoffset(); } -static inline s64 timekeeping_get_ns_raw(struct timekeeper *tk) -{ - struct clocksource *clock = tk->tkr.clock; - cycle_t cycle_now, delta; - s64 nsec; - - /* read clocksource: */ - cycle_now = tk->tkr.read(clock); - - /* calculate the delta since the last update_wall_time: */ - delta = clocksource_delta(cycle_now, tk->tkr.cycle_last, tk->tkr.mask); - - /* convert delta to nanoseconds. */ - nsec = clocksource_cyc2ns(delta, clock->mult, clock->shift); - - /* If arch requires, add in get_arch_timeoffset() */ - return nsec + arch_gettimeoffset(); -} - /** * update_fast_timekeeper - Update the fast and NMI safe monotonic timekeeper. * @tkr: Timekeeping readout base from which we take the update @@ -267,18 +362,18 @@ static inline s64 timekeeping_get_ns_raw(struct timekeeper *tk) * slightly wrong timestamp (a few nanoseconds). See * @ktime_get_mono_fast_ns. */ -static void update_fast_timekeeper(struct tk_read_base *tkr) +static void update_fast_timekeeper(struct tk_read_base *tkr, struct tk_fast *tkf) { - struct tk_read_base *base = tk_fast_mono.base; + struct tk_read_base *base = tkf->base; /* Force readers off to base[1] */ - raw_write_seqcount_latch(&tk_fast_mono.seq); + raw_write_seqcount_latch(&tkf->seq); /* Update base[0] */ memcpy(base, tkr, sizeof(*base)); /* Force readers back to base[0] */ - raw_write_seqcount_latch(&tk_fast_mono.seq); + raw_write_seqcount_latch(&tkf->seq); /* Update base[1] */ memcpy(base + 1, base, sizeof(*base)); @@ -316,22 +411,33 @@ static void update_fast_timekeeper(struct tk_read_base *tkr) * of the following timestamps. Callers need to be aware of that and * deal with it. */ -u64 notrace ktime_get_mono_fast_ns(void) +static __always_inline u64 __ktime_get_fast_ns(struct tk_fast *tkf) { struct tk_read_base *tkr; unsigned int seq; u64 now; do { - seq = raw_read_seqcount(&tk_fast_mono.seq); - tkr = tk_fast_mono.base + (seq & 0x01); - now = ktime_to_ns(tkr->base_mono) + timekeeping_get_ns(tkr); + seq = raw_read_seqcount(&tkf->seq); + tkr = tkf->base + (seq & 0x01); + now = ktime_to_ns(tkr->base) + timekeeping_get_ns(tkr); + } while (read_seqcount_retry(&tkf->seq, seq)); - } while (read_seqcount_retry(&tk_fast_mono.seq, seq)); return now; } + +u64 ktime_get_mono_fast_ns(void) +{ + return __ktime_get_fast_ns(&tk_fast_mono); +} EXPORT_SYMBOL_GPL(ktime_get_mono_fast_ns); +u64 ktime_get_raw_fast_ns(void) +{ + return __ktime_get_fast_ns(&tk_fast_raw); +} +EXPORT_SYMBOL_GPL(ktime_get_raw_fast_ns); + /* Suspend-time cycles value for halted fast timekeeper. */ static cycle_t cycles_at_suspend; @@ -353,12 +459,17 @@ static cycle_t dummy_clock_read(struct clocksource *cs) static void halt_fast_timekeeper(struct timekeeper *tk) { static struct tk_read_base tkr_dummy; - struct tk_read_base *tkr = &tk->tkr; + struct tk_read_base *tkr = &tk->tkr_mono; memcpy(&tkr_dummy, tkr, sizeof(tkr_dummy)); cycles_at_suspend = tkr->read(tkr->clock); tkr_dummy.read = dummy_clock_read; - update_fast_timekeeper(&tkr_dummy); + update_fast_timekeeper(&tkr_dummy, &tk_fast_mono); + + tkr = &tk->tkr_raw; + memcpy(&tkr_dummy, tkr, sizeof(tkr_dummy)); + tkr_dummy.read = dummy_clock_read; + update_fast_timekeeper(&tkr_dummy, &tk_fast_raw); } #ifdef CONFIG_GENERIC_TIME_VSYSCALL_OLD @@ -369,8 +480,8 @@ static inline void update_vsyscall(struct timekeeper *tk) xt = timespec64_to_timespec(tk_xtime(tk)); wm = timespec64_to_timespec(tk->wall_to_monotonic); - update_vsyscall_old(&xt, &wm, tk->tkr.clock, tk->tkr.mult, - tk->tkr.cycle_last); + update_vsyscall_old(&xt, &wm, tk->tkr_mono.clock, tk->tkr_mono.mult, + tk->tkr_mono.cycle_last); } static inline void old_vsyscall_fixup(struct timekeeper *tk) @@ -387,11 +498,11 @@ static inline void old_vsyscall_fixup(struct timekeeper *tk) * (shifted nanoseconds), and CONFIG_GENERIC_TIME_VSYSCALL_OLD * users are removed, this can be killed. */ - remainder = tk->tkr.xtime_nsec & ((1ULL << tk->tkr.shift) - 1); - tk->tkr.xtime_nsec -= remainder; - tk->tkr.xtime_nsec += 1ULL << tk->tkr.shift; + remainder = tk->tkr_mono.xtime_nsec & ((1ULL << tk->tkr_mono.shift) - 1); + tk->tkr_mono.xtime_nsec -= remainder; + tk->tkr_mono.xtime_nsec += 1ULL << tk->tkr_mono.shift; tk->ntp_error += remainder << tk->ntp_error_shift; - tk->ntp_error -= (1ULL << tk->tkr.shift) << tk->ntp_error_shift; + tk->ntp_error -= (1ULL << tk->tkr_mono.shift) << tk->ntp_error_shift; } #else #define old_vsyscall_fixup(tk) @@ -456,17 +567,17 @@ static inline void tk_update_ktime_data(struct timekeeper *tk) */ seconds = (u64)(tk->xtime_sec + tk->wall_to_monotonic.tv_sec); nsec = (u32) tk->wall_to_monotonic.tv_nsec; - tk->tkr.base_mono = ns_to_ktime(seconds * NSEC_PER_SEC + nsec); + tk->tkr_mono.base = ns_to_ktime(seconds * NSEC_PER_SEC + nsec); /* Update the monotonic raw base */ - tk->base_raw = timespec64_to_ktime(tk->raw_time); + tk->tkr_raw.base = timespec64_to_ktime(tk->raw_time); /* * The sum of the nanoseconds portions of xtime and * wall_to_monotonic can be greater/equal one second. Take * this into account before updating tk->ktime_sec. */ - nsec += (u32)(tk->tkr.xtime_nsec >> tk->tkr.shift); + nsec += (u32)(tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift); if (nsec >= NSEC_PER_SEC) seconds++; tk->ktime_sec = seconds; @@ -489,7 +600,8 @@ static void timekeeping_update(struct timekeeper *tk, unsigned int action) memcpy(&shadow_timekeeper, &tk_core.timekeeper, sizeof(tk_core.timekeeper)); - update_fast_timekeeper(&tk->tkr); + update_fast_timekeeper(&tk->tkr_mono, &tk_fast_mono); + update_fast_timekeeper(&tk->tkr_raw, &tk_fast_raw); } /** @@ -501,22 +613,23 @@ static void timekeeping_update(struct timekeeper *tk, unsigned int action) */ static void timekeeping_forward_now(struct timekeeper *tk) { - struct clocksource *clock = tk->tkr.clock; + struct clocksource *clock = tk->tkr_mono.clock; cycle_t cycle_now, delta; s64 nsec; - cycle_now = tk->tkr.read(clock); - delta = clocksource_delta(cycle_now, tk->tkr.cycle_last, tk->tkr.mask); - tk->tkr.cycle_last = cycle_now; + cycle_now = tk->tkr_mono.read(clock); + delta = clocksource_delta(cycle_now, tk->tkr_mono.cycle_last, tk->tkr_mono.mask); + tk->tkr_mono.cycle_last = cycle_now; + tk->tkr_raw.cycle_last = cycle_now; - tk->tkr.xtime_nsec += delta * tk->tkr.mult; + tk->tkr_mono.xtime_nsec += delta * tk->tkr_mono.mult; /* If arch requires, add in get_arch_timeoffset() */ - tk->tkr.xtime_nsec += (u64)arch_gettimeoffset() << tk->tkr.shift; + tk->tkr_mono.xtime_nsec += (u64)arch_gettimeoffset() << tk->tkr_mono.shift; tk_normalize_xtime(tk); - nsec = clocksource_cyc2ns(delta, clock->mult, clock->shift); + nsec = clocksource_cyc2ns(delta, tk->tkr_raw.mult, tk->tkr_raw.shift); timespec64_add_ns(&tk->raw_time, nsec); } @@ -537,7 +650,7 @@ int __getnstimeofday64(struct timespec64 *ts) seq = read_seqcount_begin(&tk_core.seq); ts->tv_sec = tk->xtime_sec; - nsecs = timekeeping_get_ns(&tk->tkr); + nsecs = timekeeping_get_ns(&tk->tkr_mono); } while (read_seqcount_retry(&tk_core.seq, seq)); @@ -577,8 +690,8 @@ ktime_t ktime_get(void) do { seq = read_seqcount_begin(&tk_core.seq); - base = tk->tkr.base_mono; - nsecs = timekeeping_get_ns(&tk->tkr); + base = tk->tkr_mono.base; + nsecs = timekeeping_get_ns(&tk->tkr_mono); } while (read_seqcount_retry(&tk_core.seq, seq)); @@ -603,8 +716,8 @@ ktime_t ktime_get_with_offset(enum tk_offsets offs) do { seq = read_seqcount_begin(&tk_core.seq); - base = ktime_add(tk->tkr.base_mono, *offset); - nsecs = timekeeping_get_ns(&tk->tkr); + base = ktime_add(tk->tkr_mono.base, *offset); + nsecs = timekeeping_get_ns(&tk->tkr_mono); } while (read_seqcount_retry(&tk_core.seq, seq)); @@ -645,8 +758,8 @@ ktime_t ktime_get_raw(void) do { seq = read_seqcount_begin(&tk_core.seq); - base = tk->base_raw; - nsecs = timekeeping_get_ns_raw(tk); + base = tk->tkr_raw.base; + nsecs = timekeeping_get_ns(&tk->tkr_raw); } while (read_seqcount_retry(&tk_core.seq, seq)); @@ -674,7 +787,7 @@ void ktime_get_ts64(struct timespec64 *ts) do { seq = read_seqcount_begin(&tk_core.seq); ts->tv_sec = tk->xtime_sec; - nsec = timekeeping_get_ns(&tk->tkr); + nsec = timekeeping_get_ns(&tk->tkr_mono); tomono = tk->wall_to_monotonic; } while (read_seqcount_retry(&tk_core.seq, seq)); @@ -759,8 +872,8 @@ void getnstime_raw_and_real(struct timespec *ts_raw, struct timespec *ts_real) ts_real->tv_sec = tk->xtime_sec; ts_real->tv_nsec = 0; - nsecs_raw = timekeeping_get_ns_raw(tk); - nsecs_real = timekeeping_get_ns(&tk->tkr); + nsecs_raw = timekeeping_get_ns(&tk->tkr_raw); + nsecs_real = timekeeping_get_ns(&tk->tkr_mono); } while (read_seqcount_retry(&tk_core.seq, seq)); @@ -943,7 +1056,7 @@ static int change_clocksource(void *data) */ if (try_module_get(new->owner)) { if (!new->enable || new->enable(new) == 0) { - old = tk->tkr.clock; + old = tk->tkr_mono.clock; tk_setup_internals(tk, new); if (old->disable) old->disable(old); @@ -971,11 +1084,11 @@ int timekeeping_notify(struct clocksource *clock) { struct timekeeper *tk = &tk_core.timekeeper; - if (tk->tkr.clock == clock) + if (tk->tkr_mono.clock == clock) return 0; stop_machine(change_clocksource, clock, NULL); tick_clock_notify(); - return tk->tkr.clock == clock ? 0 : -1; + return tk->tkr_mono.clock == clock ? 0 : -1; } /** @@ -993,7 +1106,7 @@ void getrawmonotonic64(struct timespec64 *ts) do { seq = read_seqcount_begin(&tk_core.seq); - nsecs = timekeeping_get_ns_raw(tk); + nsecs = timekeeping_get_ns(&tk->tkr_raw); ts64 = tk->raw_time; } while (read_seqcount_retry(&tk_core.seq, seq)); @@ -1016,7 +1129,7 @@ int timekeeping_valid_for_hres(void) do { seq = read_seqcount_begin(&tk_core.seq); - ret = tk->tkr.clock->flags & CLOCK_SOURCE_VALID_FOR_HRES; + ret = tk->tkr_mono.clock->flags & CLOCK_SOURCE_VALID_FOR_HRES; } while (read_seqcount_retry(&tk_core.seq, seq)); @@ -1035,7 +1148,7 @@ u64 timekeeping_max_deferment(void) do { seq = read_seqcount_begin(&tk_core.seq); - ret = tk->tkr.clock->max_idle_ns; + ret = tk->tkr_mono.clock->max_idle_ns; } while (read_seqcount_retry(&tk_core.seq, seq)); @@ -1057,6 +1170,14 @@ void __weak read_persistent_clock(struct timespec *ts) ts->tv_nsec = 0; } +void __weak read_persistent_clock64(struct timespec64 *ts64) +{ + struct timespec ts; + + read_persistent_clock(&ts); + *ts64 = timespec_to_timespec64(ts); +} + /** * read_boot_clock - Return time of the system start. * @@ -1072,6 +1193,20 @@ void __weak read_boot_clock(struct timespec *ts) ts->tv_nsec = 0; } +void __weak read_boot_clock64(struct timespec64 *ts64) +{ + struct timespec ts; + + read_boot_clock(&ts); + *ts64 = timespec_to_timespec64(ts); +} + +/* Flag for if timekeeping_resume() has injected sleeptime */ +static bool sleeptime_injected; + +/* Flag for if there is a persistent clock on this platform */ +static bool persistent_clock_exists; + /* * timekeeping_init - Initializes the clocksource and common timekeeping values */ @@ -1081,20 +1216,17 @@ void __init timekeeping_init(void) struct clocksource *clock; unsigned long flags; struct timespec64 now, boot, tmp; - struct timespec ts; - read_persistent_clock(&ts); - now = timespec_to_timespec64(ts); + read_persistent_clock64(&now); if (!timespec64_valid_strict(&now)) { pr_warn("WARNING: Persistent clock returned invalid value!\n" " Check your CMOS/BIOS settings.\n"); now.tv_sec = 0; now.tv_nsec = 0; } else if (now.tv_sec || now.tv_nsec) - persistent_clock_exist = true; + persistent_clock_exists = true; - read_boot_clock(&ts); - boot = timespec_to_timespec64(ts); + read_boot_clock64(&boot); if (!timespec64_valid_strict(&boot)) { pr_warn("WARNING: Boot clock returned invalid value!\n" " Check your CMOS/BIOS settings.\n"); @@ -1114,7 +1246,6 @@ void __init timekeeping_init(void) tk_set_xtime(tk, &now); tk->raw_time.tv_sec = 0; tk->raw_time.tv_nsec = 0; - tk->base_raw.tv64 = 0; if (boot.tv_sec == 0 && boot.tv_nsec == 0) boot = tk_xtime(tk); @@ -1127,7 +1258,7 @@ void __init timekeeping_init(void) raw_spin_unlock_irqrestore(&timekeeper_lock, flags); } -/* time in seconds when suspend began */ +/* time in seconds when suspend began for persistent clock */ static struct timespec64 timekeeping_suspend_time; /** @@ -1152,12 +1283,49 @@ static void __timekeeping_inject_sleeptime(struct timekeeper *tk, tk_debug_account_sleep_time(delta); } +#if defined(CONFIG_PM_SLEEP) && defined(CONFIG_RTC_HCTOSYS_DEVICE) +/** + * We have three kinds of time sources to use for sleep time + * injection, the preference order is: + * 1) non-stop clocksource + * 2) persistent clock (ie: RTC accessible when irqs are off) + * 3) RTC + * + * 1) and 2) are used by timekeeping, 3) by RTC subsystem. + * If system has neither 1) nor 2), 3) will be used finally. + * + * + * If timekeeping has injected sleeptime via either 1) or 2), + * 3) becomes needless, so in this case we don't need to call + * rtc_resume(), and this is what timekeeping_rtc_skipresume() + * means. + */ +bool timekeeping_rtc_skipresume(void) +{ + return sleeptime_injected; +} + +/** + * 1) can be determined whether to use or not only when doing + * timekeeping_resume() which is invoked after rtc_suspend(), + * so we can't skip rtc_suspend() surely if system has 1). + * + * But if system has 2), 2) will definitely be used, so in this + * case we don't need to call rtc_suspend(), and this is what + * timekeeping_rtc_skipsuspend() means. + */ +bool timekeeping_rtc_skipsuspend(void) +{ + return persistent_clock_exists; +} + /** * timekeeping_inject_sleeptime64 - Adds suspend interval to timeekeeping values * @delta: pointer to a timespec64 delta value * - * This hook is for architectures that cannot support read_persistent_clock + * This hook is for architectures that cannot support read_persistent_clock64 * because their RTC/persistent clock is only accessible when irqs are enabled. + * and also don't have an effective nonstop clocksource. * * This function should only be called by rtc_resume(), and allows * a suspend offset to be injected into the timekeeping values. @@ -1167,13 +1335,6 @@ void timekeeping_inject_sleeptime64(struct timespec64 *delta) struct timekeeper *tk = &tk_core.timekeeper; unsigned long flags; - /* - * Make sure we don't set the clock twice, as timekeeping_resume() - * already did it - */ - if (has_persistent_clock()) - return; - raw_spin_lock_irqsave(&timekeeper_lock, flags); write_seqcount_begin(&tk_core.seq); @@ -1189,26 +1350,21 @@ void timekeeping_inject_sleeptime64(struct timespec64 *delta) /* signal hrtimers about time change */ clock_was_set(); } +#endif /** * timekeeping_resume - Resumes the generic timekeeping subsystem. - * - * This is for the generic clocksource timekeeping. - * xtime/wall_to_monotonic/jiffies/etc are - * still managed by arch specific suspend/resume code. */ void timekeeping_resume(void) { struct timekeeper *tk = &tk_core.timekeeper; - struct clocksource *clock = tk->tkr.clock; + struct clocksource *clock = tk->tkr_mono.clock; unsigned long flags; struct timespec64 ts_new, ts_delta; - struct timespec tmp; cycle_t cycle_now, cycle_delta; - bool suspendtime_found = false; - read_persistent_clock(&tmp); - ts_new = timespec_to_timespec64(tmp); + sleeptime_injected = false; + read_persistent_clock64(&ts_new); clockevents_resume(); clocksource_resume(); @@ -1228,16 +1384,16 @@ void timekeeping_resume(void) * The less preferred source will only be tried if there is no better * usable source. The rtc part is handled separately in rtc core code. */ - cycle_now = tk->tkr.read(clock); + cycle_now = tk->tkr_mono.read(clock); if ((clock->flags & CLOCK_SOURCE_SUSPEND_NONSTOP) && - cycle_now > tk->tkr.cycle_last) { + cycle_now > tk->tkr_mono.cycle_last) { u64 num, max = ULLONG_MAX; u32 mult = clock->mult; u32 shift = clock->shift; s64 nsec = 0; - cycle_delta = clocksource_delta(cycle_now, tk->tkr.cycle_last, - tk->tkr.mask); + cycle_delta = clocksource_delta(cycle_now, tk->tkr_mono.cycle_last, + tk->tkr_mono.mask); /* * "cycle_delta * mutl" may cause 64 bits overflow, if the @@ -1253,17 +1409,19 @@ void timekeeping_resume(void) nsec += ((u64) cycle_delta * mult) >> shift; ts_delta = ns_to_timespec64(nsec); - suspendtime_found = true; + sleeptime_injected = true; } else if (timespec64_compare(&ts_new, &timekeeping_suspend_time) > 0) { ts_delta = timespec64_sub(ts_new, timekeeping_suspend_time); - suspendtime_found = true; + sleeptime_injected = true; } - if (suspendtime_found) + if (sleeptime_injected) __timekeeping_inject_sleeptime(tk, &ts_delta); /* Re-base the last cycle value */ - tk->tkr.cycle_last = cycle_now; + tk->tkr_mono.cycle_last = cycle_now; + tk->tkr_raw.cycle_last = cycle_now; + tk->ntp_error = 0; timekeeping_suspended = 0; timekeeping_update(tk, TK_MIRROR | TK_CLOCK_WAS_SET); @@ -1272,9 +1430,7 @@ void timekeeping_resume(void) touch_softlockup_watchdog(); - clockevents_notify(CLOCK_EVT_NOTIFY_RESUME, NULL); - - /* Resume hrtimers */ + tick_resume(); hrtimers_resume(); } @@ -1284,10 +1440,8 @@ int timekeeping_suspend(void) unsigned long flags; struct timespec64 delta, delta_delta; static struct timespec64 old_delta; - struct timespec tmp; - read_persistent_clock(&tmp); - timekeeping_suspend_time = timespec_to_timespec64(tmp); + read_persistent_clock64(&timekeeping_suspend_time); /* * On some systems the persistent_clock can not be detected at @@ -1295,31 +1449,33 @@ int timekeeping_suspend(void) * value returned, update the persistent_clock_exists flag. */ if (timekeeping_suspend_time.tv_sec || timekeeping_suspend_time.tv_nsec) - persistent_clock_exist = true; + persistent_clock_exists = true; raw_spin_lock_irqsave(&timekeeper_lock, flags); write_seqcount_begin(&tk_core.seq); timekeeping_forward_now(tk); timekeeping_suspended = 1; - /* - * To avoid drift caused by repeated suspend/resumes, - * which each can add ~1 second drift error, - * try to compensate so the difference in system time - * and persistent_clock time stays close to constant. - */ - delta = timespec64_sub(tk_xtime(tk), timekeeping_suspend_time); - delta_delta = timespec64_sub(delta, old_delta); - if (abs(delta_delta.tv_sec) >= 2) { + if (persistent_clock_exists) { /* - * if delta_delta is too large, assume time correction - * has occured and set old_delta to the current delta. + * To avoid drift caused by repeated suspend/resumes, + * which each can add ~1 second drift error, + * try to compensate so the difference in system time + * and persistent_clock time stays close to constant. */ - old_delta = delta; - } else { - /* Otherwise try to adjust old_system to compensate */ - timekeeping_suspend_time = - timespec64_add(timekeeping_suspend_time, delta_delta); + delta = timespec64_sub(tk_xtime(tk), timekeeping_suspend_time); + delta_delta = timespec64_sub(delta, old_delta); + if (abs(delta_delta.tv_sec) >= 2) { + /* + * if delta_delta is too large, assume time correction + * has occurred and set old_delta to the current delta. + */ + old_delta = delta; + } else { + /* Otherwise try to adjust old_system to compensate */ + timekeeping_suspend_time = + timespec64_add(timekeeping_suspend_time, delta_delta); + } } timekeeping_update(tk, TK_MIRROR); @@ -1327,7 +1483,7 @@ int timekeeping_suspend(void) write_seqcount_end(&tk_core.seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); - clockevents_notify(CLOCK_EVT_NOTIFY_SUSPEND, NULL); + tick_suspend(); clocksource_suspend(); clockevents_suspend(); @@ -1416,15 +1572,15 @@ static __always_inline void timekeeping_apply_adjustment(struct timekeeper *tk, * * XXX - TODO: Doc ntp_error calculation. */ - if ((mult_adj > 0) && (tk->tkr.mult + mult_adj < mult_adj)) { + if ((mult_adj > 0) && (tk->tkr_mono.mult + mult_adj < mult_adj)) { /* NTP adjustment caused clocksource mult overflow */ WARN_ON_ONCE(1); return; } - tk->tkr.mult += mult_adj; + tk->tkr_mono.mult += mult_adj; tk->xtime_interval += interval; - tk->tkr.xtime_nsec -= offset; + tk->tkr_mono.xtime_nsec -= offset; tk->ntp_error -= (interval - offset) << tk->ntp_error_shift; } @@ -1486,13 +1642,13 @@ static void timekeeping_adjust(struct timekeeper *tk, s64 offset) tk->ntp_err_mult = 0; } - if (unlikely(tk->tkr.clock->maxadj && - (abs(tk->tkr.mult - tk->tkr.clock->mult) - > tk->tkr.clock->maxadj))) { + if (unlikely(tk->tkr_mono.clock->maxadj && + (abs(tk->tkr_mono.mult - tk->tkr_mono.clock->mult) + > tk->tkr_mono.clock->maxadj))) { printk_once(KERN_WARNING "Adjusting %s more than 11%% (%ld vs %ld)\n", - tk->tkr.clock->name, (long)tk->tkr.mult, - (long)tk->tkr.clock->mult + tk->tkr.clock->maxadj); + tk->tkr_mono.clock->name, (long)tk->tkr_mono.mult, + (long)tk->tkr_mono.clock->mult + tk->tkr_mono.clock->maxadj); } /* @@ -1509,9 +1665,9 @@ static void timekeeping_adjust(struct timekeeper *tk, s64 offset) * We'll correct this error next time through this function, when * xtime_nsec is not as small. */ - if (unlikely((s64)tk->tkr.xtime_nsec < 0)) { - s64 neg = -(s64)tk->tkr.xtime_nsec; - tk->tkr.xtime_nsec = 0; + if (unlikely((s64)tk->tkr_mono.xtime_nsec < 0)) { + s64 neg = -(s64)tk->tkr_mono.xtime_nsec; + tk->tkr_mono.xtime_nsec = 0; tk->ntp_error += neg << tk->ntp_error_shift; } } @@ -1526,13 +1682,13 @@ static void timekeeping_adjust(struct timekeeper *tk, s64 offset) */ static inline unsigned int accumulate_nsecs_to_secs(struct timekeeper *tk) { - u64 nsecps = (u64)NSEC_PER_SEC << tk->tkr.shift; + u64 nsecps = (u64)NSEC_PER_SEC << tk->tkr_mono.shift; unsigned int clock_set = 0; - while (tk->tkr.xtime_nsec >= nsecps) { + while (tk->tkr_mono.xtime_nsec >= nsecps) { int leap; - tk->tkr.xtime_nsec -= nsecps; + tk->tkr_mono.xtime_nsec -= nsecps; tk->xtime_sec++; /* Figure out if its a leap sec and apply if needed */ @@ -1577,9 +1733,10 @@ static cycle_t logarithmic_accumulation(struct timekeeper *tk, cycle_t offset, /* Accumulate one shifted interval */ offset -= interval; - tk->tkr.cycle_last += interval; + tk->tkr_mono.cycle_last += interval; + tk->tkr_raw.cycle_last += interval; - tk->tkr.xtime_nsec += tk->xtime_interval << shift; + tk->tkr_mono.xtime_nsec += tk->xtime_interval << shift; *clock_set |= accumulate_nsecs_to_secs(tk); /* Accumulate raw time */ @@ -1622,14 +1779,17 @@ void update_wall_time(void) #ifdef CONFIG_ARCH_USES_GETTIMEOFFSET offset = real_tk->cycle_interval; #else - offset = clocksource_delta(tk->tkr.read(tk->tkr.clock), - tk->tkr.cycle_last, tk->tkr.mask); + offset = clocksource_delta(tk->tkr_mono.read(tk->tkr_mono.clock), + tk->tkr_mono.cycle_last, tk->tkr_mono.mask); #endif /* Check if there's really nothing to do */ if (offset < real_tk->cycle_interval) goto out; + /* Do some additional sanity checking */ + timekeeping_check_update(real_tk, offset); + /* * With NO_HZ we may have to accumulate many cycle_intervals * (think "ticks") worth of time at once. To do this efficiently, @@ -1784,8 +1944,8 @@ ktime_t ktime_get_update_offsets_tick(ktime_t *offs_real, ktime_t *offs_boot, do { seq = read_seqcount_begin(&tk_core.seq); - base = tk->tkr.base_mono; - nsecs = tk->tkr.xtime_nsec >> tk->tkr.shift; + base = tk->tkr_mono.base; + nsecs = tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift; *offs_real = tk->offs_real; *offs_boot = tk->offs_boot; @@ -1816,8 +1976,8 @@ ktime_t ktime_get_update_offsets_now(ktime_t *offs_real, ktime_t *offs_boot, do { seq = read_seqcount_begin(&tk_core.seq); - base = tk->tkr.base_mono; - nsecs = timekeeping_get_ns(&tk->tkr); + base = tk->tkr_mono.base; + nsecs = timekeeping_get_ns(&tk->tkr_mono); *offs_real = tk->offs_real; *offs_boot = tk->offs_boot; diff --git a/kernel/time/timekeeping.h b/kernel/time/timekeeping.h index 1d91416055d5..ead8794b9a4e 100644 --- a/kernel/time/timekeeping.h +++ b/kernel/time/timekeeping.h @@ -19,4 +19,11 @@ extern void timekeeping_clocktai(struct timespec *ts); extern int timekeeping_suspend(void); extern void timekeeping_resume(void); +extern void do_timer(unsigned long ticks); +extern void update_wall_time(void); + +extern seqlock_t jiffies_lock; + +#define CS_NAME_LEN 32 + #endif diff --git a/kernel/time/timer.c b/kernel/time/timer.c index 2d3f5c504939..2ece3aa5069c 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -90,8 +90,18 @@ struct tvec_base { struct tvec tv5; } ____cacheline_aligned; +/* + * __TIMER_INITIALIZER() needs to set ->base to a valid pointer (because we've + * made NULL special, hint: lock_timer_base()) and we cannot get a compile time + * pointer to per-cpu entries because we don't know where we'll map the section, + * even for the boot cpu. + * + * And so we use boot_tvec_bases for boot CPU and per-cpu __tvec_bases for the + * rest of them. + */ struct tvec_base boot_tvec_bases; EXPORT_SYMBOL(boot_tvec_bases); + static DEFINE_PER_CPU(struct tvec_base *, tvec_bases) = &boot_tvec_bases; /* Functions below help us manage 'deferrable' flag */ @@ -1027,6 +1037,8 @@ int try_to_del_timer_sync(struct timer_list *timer) EXPORT_SYMBOL(try_to_del_timer_sync); #ifdef CONFIG_SMP +static DEFINE_PER_CPU(struct tvec_base, __tvec_bases); + /** * del_timer_sync - deactivate a timer and wait for the handler to finish. * @timer: the timer to be deactivated @@ -1532,64 +1544,6 @@ signed long __sched schedule_timeout_uninterruptible(signed long timeout) } EXPORT_SYMBOL(schedule_timeout_uninterruptible); -static int init_timers_cpu(int cpu) -{ - int j; - struct tvec_base *base; - static char tvec_base_done[NR_CPUS]; - - if (!tvec_base_done[cpu]) { - static char boot_done; - - if (boot_done) { - /* - * The APs use this path later in boot - */ - base = kzalloc_node(sizeof(*base), GFP_KERNEL, - cpu_to_node(cpu)); - if (!base) - return -ENOMEM; - - /* Make sure tvec_base has TIMER_FLAG_MASK bits free */ - if (WARN_ON(base != tbase_get_base(base))) { - kfree(base); - return -ENOMEM; - } - per_cpu(tvec_bases, cpu) = base; - } else { - /* - * This is for the boot CPU - we use compile-time - * static initialisation because per-cpu memory isn't - * ready yet and because the memory allocators are not - * initialised either. - */ - boot_done = 1; - base = &boot_tvec_bases; - } - spin_lock_init(&base->lock); - tvec_base_done[cpu] = 1; - base->cpu = cpu; - } else { - base = per_cpu(tvec_bases, cpu); - } - - - for (j = 0; j < TVN_SIZE; j++) { - INIT_LIST_HEAD(base->tv5.vec + j); - INIT_LIST_HEAD(base->tv4.vec + j); - INIT_LIST_HEAD(base->tv3.vec + j); - INIT_LIST_HEAD(base->tv2.vec + j); - } - for (j = 0; j < TVR_SIZE; j++) - INIT_LIST_HEAD(base->tv1.vec + j); - - base->timer_jiffies = jiffies; - base->next_timer = base->timer_jiffies; - base->active_timers = 0; - base->all_timers = 0; - return 0; -} - #ifdef CONFIG_HOTPLUG_CPU static void migrate_timer_list(struct tvec_base *new_base, struct list_head *head) { @@ -1631,55 +1585,86 @@ static void migrate_timers(int cpu) migrate_timer_list(new_base, old_base->tv5.vec + i); } + old_base->active_timers = 0; + old_base->all_timers = 0; + spin_unlock(&old_base->lock); spin_unlock_irq(&new_base->lock); put_cpu_var(tvec_bases); } -#endif /* CONFIG_HOTPLUG_CPU */ static int timer_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu) { - long cpu = (long)hcpu; - int err; - - switch(action) { - case CPU_UP_PREPARE: - case CPU_UP_PREPARE_FROZEN: - err = init_timers_cpu(cpu); - if (err < 0) - return notifier_from_errno(err); - break; -#ifdef CONFIG_HOTPLUG_CPU + switch (action) { case CPU_DEAD: case CPU_DEAD_FROZEN: - migrate_timers(cpu); + migrate_timers((long)hcpu); break; -#endif default: break; } + return NOTIFY_OK; } -static struct notifier_block timers_nb = { - .notifier_call = timer_cpu_notify, -}; +static inline void timer_register_cpu_notifier(void) +{ + cpu_notifier(timer_cpu_notify, 0); +} +#else +static inline void timer_register_cpu_notifier(void) { } +#endif /* CONFIG_HOTPLUG_CPU */ +static void __init init_timer_cpu(struct tvec_base *base, int cpu) +{ + int j; -void __init init_timers(void) + BUG_ON(base != tbase_get_base(base)); + + base->cpu = cpu; + per_cpu(tvec_bases, cpu) = base; + spin_lock_init(&base->lock); + + for (j = 0; j < TVN_SIZE; j++) { + INIT_LIST_HEAD(base->tv5.vec + j); + INIT_LIST_HEAD(base->tv4.vec + j); + INIT_LIST_HEAD(base->tv3.vec + j); + INIT_LIST_HEAD(base->tv2.vec + j); + } + for (j = 0; j < TVR_SIZE; j++) + INIT_LIST_HEAD(base->tv1.vec + j); + + base->timer_jiffies = jiffies; + base->next_timer = base->timer_jiffies; +} + +static void __init init_timer_cpus(void) { - int err; + struct tvec_base *base; + int local_cpu = smp_processor_id(); + int cpu; + for_each_possible_cpu(cpu) { + if (cpu == local_cpu) + base = &boot_tvec_bases; +#ifdef CONFIG_SMP + else + base = per_cpu_ptr(&__tvec_bases, cpu); +#endif + + init_timer_cpu(base, cpu); + } +} + +void __init init_timers(void) +{ /* ensure there are enough low bits for flags in timer->base pointer */ BUILD_BUG_ON(__alignof__(struct tvec_base) & TIMER_FLAG_MASK); - err = timer_cpu_notify(&timers_nb, (unsigned long)CPU_UP_PREPARE, - (void *)(long)smp_processor_id()); - BUG_ON(err != NOTIFY_OK); - + init_timer_cpus(); init_timer_stats(); - register_cpu_notifier(&timers_nb); + timer_register_cpu_notifier(); open_softirq(TIMER_SOFTIRQ, run_timer_softirq); } diff --git a/kernel/time/timer_list.c b/kernel/time/timer_list.c index 61ed862cdd37..e878c2e0ba45 100644 --- a/kernel/time/timer_list.c +++ b/kernel/time/timer_list.c @@ -16,10 +16,10 @@ #include <linux/sched.h> #include <linux/seq_file.h> #include <linux/kallsyms.h> -#include <linux/tick.h> #include <asm/uaccess.h> +#include "tick-internal.h" struct timer_list_iter { int cpu; @@ -228,9 +228,35 @@ print_tickdevice(struct seq_file *m, struct tick_device *td, int cpu) print_name_offset(m, dev->set_next_event); SEQ_printf(m, "\n"); - SEQ_printf(m, " set_mode: "); - print_name_offset(m, dev->set_mode); - SEQ_printf(m, "\n"); + if (dev->set_mode) { + SEQ_printf(m, " set_mode: "); + print_name_offset(m, dev->set_mode); + SEQ_printf(m, "\n"); + } else { + if (dev->set_state_shutdown) { + SEQ_printf(m, " shutdown: "); + print_name_offset(m, dev->set_state_shutdown); + SEQ_printf(m, "\n"); + } + + if (dev->set_state_periodic) { + SEQ_printf(m, " periodic: "); + print_name_offset(m, dev->set_state_periodic); + SEQ_printf(m, "\n"); + } + + if (dev->set_state_oneshot) { + SEQ_printf(m, " oneshot: "); + print_name_offset(m, dev->set_state_oneshot); + SEQ_printf(m, "\n"); + } + + if (dev->tick_resume) { + SEQ_printf(m, " resume: "); + print_name_offset(m, dev->tick_resume); + SEQ_printf(m, "\n"); + } + } SEQ_printf(m, " event_handler: "); print_name_offset(m, dev->event_handler); diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index a5da09c899dd..3b9a48ae153a 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -432,6 +432,14 @@ config UPROBE_EVENT This option is required if you plan to use perf-probe subcommand of perf tools on user space applications. +config BPF_EVENTS + depends on BPF_SYSCALL + depends on KPROBE_EVENT + bool + default y + help + This allows the user to attach BPF programs to kprobe events. + config PROBE_EVENTS def_bool n @@ -599,6 +607,34 @@ config RING_BUFFER_STARTUP_TEST If unsure, say N +config TRACE_ENUM_MAP_FILE + bool "Show enum mappings for trace events" + depends on TRACING + help + The "print fmt" of the trace events will show the enum names instead + of their values. This can cause problems for user space tools that + use this string to parse the raw data as user space does not know + how to convert the string to its value. + + To fix this, there's a special macro in the kernel that can be used + to convert the enum into its value. If this macro is used, then the + print fmt strings will have the enums converted to their values. + + If something does not get converted properly, this option can be + used to show what enums the kernel tried to convert. + + This option is for debugging the enum conversions. A file is created + in the tracing directory called "enum_map" that will show the enum + names matched with their values and what trace event system they + belong too. + + Normally, the mapping of the strings to values will be freed after + boot up or module load. With this option, they will not be freed, as + they are needed for the "enum_map" file. Enabling this option will + increase the memory footprint of the running kernel. + + If unsure, say N + endif # FTRACE endif # TRACING_SUPPORT diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile index 98f26588255e..9b1044e936a6 100644 --- a/kernel/trace/Makefile +++ b/kernel/trace/Makefile @@ -53,6 +53,7 @@ obj-$(CONFIG_EVENT_TRACING) += trace_event_perf.o endif obj-$(CONFIG_EVENT_TRACING) += trace_events_filter.o obj-$(CONFIG_EVENT_TRACING) += trace_events_trigger.o +obj-$(CONFIG_BPF_EVENTS) += bpf_trace.o obj-$(CONFIG_KPROBE_EVENT) += trace_kprobe.o obj-$(CONFIG_TRACEPOINTS) += power-traces.o ifeq ($(CONFIG_PM),y) diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c new file mode 100644 index 000000000000..2d56ce501632 --- /dev/null +++ b/kernel/trace/bpf_trace.c @@ -0,0 +1,222 @@ +/* Copyright (c) 2011-2015 PLUMgrid, http://plumgrid.com + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + */ +#include <linux/kernel.h> +#include <linux/types.h> +#include <linux/slab.h> +#include <linux/bpf.h> +#include <linux/filter.h> +#include <linux/uaccess.h> +#include <linux/ctype.h> +#include "trace.h" + +static DEFINE_PER_CPU(int, bpf_prog_active); + +/** + * trace_call_bpf - invoke BPF program + * @prog: BPF program + * @ctx: opaque context pointer + * + * kprobe handlers execute BPF programs via this helper. + * Can be used from static tracepoints in the future. + * + * Return: BPF programs always return an integer which is interpreted by + * kprobe handler as: + * 0 - return from kprobe (event is filtered out) + * 1 - store kprobe event into ring buffer + * Other values are reserved and currently alias to 1 + */ +unsigned int trace_call_bpf(struct bpf_prog *prog, void *ctx) +{ + unsigned int ret; + + if (in_nmi()) /* not supported yet */ + return 1; + + preempt_disable(); + + if (unlikely(__this_cpu_inc_return(bpf_prog_active) != 1)) { + /* + * since some bpf program is already running on this cpu, + * don't call into another bpf program (same or different) + * and don't send kprobe event into ring-buffer, + * so return zero here + */ + ret = 0; + goto out; + } + + rcu_read_lock(); + ret = BPF_PROG_RUN(prog, ctx); + rcu_read_unlock(); + + out: + __this_cpu_dec(bpf_prog_active); + preempt_enable(); + + return ret; +} +EXPORT_SYMBOL_GPL(trace_call_bpf); + +static u64 bpf_probe_read(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) +{ + void *dst = (void *) (long) r1; + int size = (int) r2; + void *unsafe_ptr = (void *) (long) r3; + + return probe_kernel_read(dst, unsafe_ptr, size); +} + +static const struct bpf_func_proto bpf_probe_read_proto = { + .func = bpf_probe_read, + .gpl_only = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_STACK, + .arg2_type = ARG_CONST_STACK_SIZE, + .arg3_type = ARG_ANYTHING, +}; + +static u64 bpf_ktime_get_ns(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) +{ + /* NMI safe access to clock monotonic */ + return ktime_get_mono_fast_ns(); +} + +static const struct bpf_func_proto bpf_ktime_get_ns_proto = { + .func = bpf_ktime_get_ns, + .gpl_only = true, + .ret_type = RET_INTEGER, +}; + +/* + * limited trace_printk() + * only %d %u %x %ld %lu %lx %lld %llu %llx %p conversion specifiers allowed + */ +static u64 bpf_trace_printk(u64 r1, u64 fmt_size, u64 r3, u64 r4, u64 r5) +{ + char *fmt = (char *) (long) r1; + int mod[3] = {}; + int fmt_cnt = 0; + int i; + + /* + * bpf_check()->check_func_arg()->check_stack_boundary() + * guarantees that fmt points to bpf program stack, + * fmt_size bytes of it were initialized and fmt_size > 0 + */ + if (fmt[--fmt_size] != 0) + return -EINVAL; + + /* check format string for allowed specifiers */ + for (i = 0; i < fmt_size; i++) { + if ((!isprint(fmt[i]) && !isspace(fmt[i])) || !isascii(fmt[i])) + return -EINVAL; + + if (fmt[i] != '%') + continue; + + if (fmt_cnt >= 3) + return -EINVAL; + + /* fmt[i] != 0 && fmt[last] == 0, so we can access fmt[i + 1] */ + i++; + if (fmt[i] == 'l') { + mod[fmt_cnt]++; + i++; + } else if (fmt[i] == 'p') { + mod[fmt_cnt]++; + i++; + if (!isspace(fmt[i]) && !ispunct(fmt[i]) && fmt[i] != 0) + return -EINVAL; + fmt_cnt++; + continue; + } + + if (fmt[i] == 'l') { + mod[fmt_cnt]++; + i++; + } + + if (fmt[i] != 'd' && fmt[i] != 'u' && fmt[i] != 'x') + return -EINVAL; + fmt_cnt++; + } + + return __trace_printk(1/* fake ip will not be printed */, fmt, + mod[0] == 2 ? r3 : mod[0] == 1 ? (long) r3 : (u32) r3, + mod[1] == 2 ? r4 : mod[1] == 1 ? (long) r4 : (u32) r4, + mod[2] == 2 ? r5 : mod[2] == 1 ? (long) r5 : (u32) r5); +} + +static const struct bpf_func_proto bpf_trace_printk_proto = { + .func = bpf_trace_printk, + .gpl_only = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_STACK, + .arg2_type = ARG_CONST_STACK_SIZE, +}; + +static const struct bpf_func_proto *kprobe_prog_func_proto(enum bpf_func_id func_id) +{ + switch (func_id) { + case BPF_FUNC_map_lookup_elem: + return &bpf_map_lookup_elem_proto; + case BPF_FUNC_map_update_elem: + return &bpf_map_update_elem_proto; + case BPF_FUNC_map_delete_elem: + return &bpf_map_delete_elem_proto; + case BPF_FUNC_probe_read: + return &bpf_probe_read_proto; + case BPF_FUNC_ktime_get_ns: + return &bpf_ktime_get_ns_proto; + + case BPF_FUNC_trace_printk: + /* + * this program might be calling bpf_trace_printk, + * so allocate per-cpu printk buffers + */ + trace_printk_init_buffers(); + + return &bpf_trace_printk_proto; + default: + return NULL; + } +} + +/* bpf+kprobe programs can access fields of 'struct pt_regs' */ +static bool kprobe_prog_is_valid_access(int off, int size, enum bpf_access_type type) +{ + /* check bounds */ + if (off < 0 || off >= sizeof(struct pt_regs)) + return false; + + /* only read is allowed */ + if (type != BPF_READ) + return false; + + /* disallow misaligned access */ + if (off % size != 0) + return false; + + return true; +} + +static struct bpf_verifier_ops kprobe_prog_ops = { + .get_func_proto = kprobe_prog_func_proto, + .is_valid_access = kprobe_prog_is_valid_access, +}; + +static struct bpf_prog_type_list kprobe_tl = { + .ops = &kprobe_prog_ops, + .type = BPF_PROG_TYPE_KPROBE, +}; + +static int __init register_kprobe_prog_ops(void) +{ + bpf_register_prog_type(&kprobe_tl); + return 0; +} +late_initcall(register_kprobe_prog_ops); diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 4f228024055b..02bece4a99ea 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -18,7 +18,7 @@ #include <linux/kallsyms.h> #include <linux/seq_file.h> #include <linux/suspend.h> -#include <linux/debugfs.h> +#include <linux/tracefs.h> #include <linux/hardirq.h> #include <linux/kthread.h> #include <linux/uaccess.h> @@ -249,6 +249,19 @@ static void update_function_graph_func(void); static inline void update_function_graph_func(void) { } #endif + +static ftrace_func_t ftrace_ops_get_list_func(struct ftrace_ops *ops) +{ + /* + * If this is a dynamic ops or we force list func, + * then it needs to call the list anyway. + */ + if (ops->flags & FTRACE_OPS_FL_DYNAMIC || FTRACE_FORCE_LIST_FUNC) + return ftrace_ops_list_func; + + return ftrace_ops_get_func(ops); +} + static void update_ftrace_function(void) { ftrace_func_t func; @@ -270,7 +283,7 @@ static void update_ftrace_function(void) * then have the mcount trampoline call the function directly. */ } else if (ftrace_ops_list->next == &ftrace_list_end) { - func = ftrace_ops_get_func(ftrace_ops_list); + func = ftrace_ops_get_list_func(ftrace_ops_list); } else { /* Just use the default ftrace_ops */ @@ -1008,7 +1021,7 @@ static struct tracer_stat function_stats __initdata = { .stat_show = function_stat_show }; -static __init void ftrace_profile_debugfs(struct dentry *d_tracer) +static __init void ftrace_profile_tracefs(struct dentry *d_tracer) { struct ftrace_profile_stat *stat; struct dentry *entry; @@ -1044,15 +1057,15 @@ static __init void ftrace_profile_debugfs(struct dentry *d_tracer) } } - entry = debugfs_create_file("function_profile_enabled", 0644, + entry = tracefs_create_file("function_profile_enabled", 0644, d_tracer, NULL, &ftrace_profile_fops); if (!entry) - pr_warning("Could not create debugfs " + pr_warning("Could not create tracefs " "'function_profile_enabled' entry\n"); } #else /* CONFIG_FUNCTION_PROFILER */ -static __init void ftrace_profile_debugfs(struct dentry *d_tracer) +static __init void ftrace_profile_tracefs(struct dentry *d_tracer) { } #endif /* CONFIG_FUNCTION_PROFILER */ @@ -4712,7 +4725,7 @@ void ftrace_destroy_filter_files(struct ftrace_ops *ops) mutex_unlock(&ftrace_lock); } -static __init int ftrace_init_dyn_debugfs(struct dentry *d_tracer) +static __init int ftrace_init_dyn_tracefs(struct dentry *d_tracer) { trace_create_file("available_filter_functions", 0444, @@ -5020,7 +5033,7 @@ static int __init ftrace_nodyn_init(void) } core_initcall(ftrace_nodyn_init); -static inline int ftrace_init_dyn_debugfs(struct dentry *d_tracer) { return 0; } +static inline int ftrace_init_dyn_tracefs(struct dentry *d_tracer) { return 0; } static inline void ftrace_startup_enable(int command) { } static inline void ftrace_startup_all(int command) { } /* Keep as macros so we do not need to define the commands */ @@ -5209,13 +5222,6 @@ static void ftrace_ops_recurs_func(unsigned long ip, unsigned long parent_ip, ftrace_func_t ftrace_ops_get_func(struct ftrace_ops *ops) { /* - * If this is a dynamic ops or we force list func, - * then it needs to call the list anyway. - */ - if (ops->flags & FTRACE_OPS_FL_DYNAMIC || FTRACE_FORCE_LIST_FUNC) - return ftrace_ops_list_func; - - /* * If the func handles its own recursion, call it directly. * Otherwise call the recursion protected function that * will call the ftrace ops function. @@ -5473,7 +5479,7 @@ static const struct file_operations ftrace_pid_fops = { .release = ftrace_pid_release, }; -static __init int ftrace_init_debugfs(void) +static __init int ftrace_init_tracefs(void) { struct dentry *d_tracer; @@ -5481,16 +5487,16 @@ static __init int ftrace_init_debugfs(void) if (IS_ERR(d_tracer)) return 0; - ftrace_init_dyn_debugfs(d_tracer); + ftrace_init_dyn_tracefs(d_tracer); trace_create_file("set_ftrace_pid", 0644, d_tracer, NULL, &ftrace_pid_fops); - ftrace_profile_debugfs(d_tracer); + ftrace_profile_tracefs(d_tracer); return 0; } -fs_initcall(ftrace_init_debugfs); +fs_initcall(ftrace_init_tracefs); /** * ftrace_kill - kill ftrace diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 5040d44fe5a3..0315d43176d8 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -2679,7 +2679,7 @@ static DEFINE_PER_CPU(unsigned int, current_context); static __always_inline int trace_recursive_lock(void) { - unsigned int val = this_cpu_read(current_context); + unsigned int val = __this_cpu_read(current_context); int bit; if (in_interrupt()) { @@ -2696,18 +2696,14 @@ static __always_inline int trace_recursive_lock(void) return 1; val |= (1 << bit); - this_cpu_write(current_context, val); + __this_cpu_write(current_context, val); return 0; } static __always_inline void trace_recursive_unlock(void) { - unsigned int val = this_cpu_read(current_context); - - val--; - val &= this_cpu_read(current_context); - this_cpu_write(current_context, val); + __this_cpu_and(current_context, __this_cpu_read(current_context) - 1); } #else diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 62c6506d663f..91eecaaa43e0 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -20,6 +20,7 @@ #include <linux/notifier.h> #include <linux/irqflags.h> #include <linux/debugfs.h> +#include <linux/tracefs.h> #include <linux/pagemap.h> #include <linux/hardirq.h> #include <linux/linkage.h> @@ -31,6 +32,7 @@ #include <linux/splice.h> #include <linux/kdebug.h> #include <linux/string.h> +#include <linux/mount.h> #include <linux/rwsem.h> #include <linux/slab.h> #include <linux/ctype.h> @@ -123,6 +125,42 @@ enum ftrace_dump_mode ftrace_dump_on_oops; /* When set, tracing will stop when a WARN*() is hit */ int __disable_trace_on_warning; +#ifdef CONFIG_TRACE_ENUM_MAP_FILE +/* Map of enums to their values, for "enum_map" file */ +struct trace_enum_map_head { + struct module *mod; + unsigned long length; +}; + +union trace_enum_map_item; + +struct trace_enum_map_tail { + /* + * "end" is first and points to NULL as it must be different + * than "mod" or "enum_string" + */ + union trace_enum_map_item *next; + const char *end; /* points to NULL */ +}; + +static DEFINE_MUTEX(trace_enum_mutex); + +/* + * The trace_enum_maps are saved in an array with two extra elements, + * one at the beginning, and one at the end. The beginning item contains + * the count of the saved maps (head.length), and the module they + * belong to if not built in (head.mod). The ending item contains a + * pointer to the next array of saved enum_map items. + */ +union trace_enum_map_item { + struct trace_enum_map map; + struct trace_enum_map_head head; + struct trace_enum_map_tail tail; +}; + +static union trace_enum_map_item *trace_enum_maps; +#endif /* CONFIG_TRACE_ENUM_MAP_FILE */ + static int tracing_set_tracer(struct trace_array *tr, const char *buf); #define MAX_TRACER_SIZE 100 @@ -3908,6 +3946,182 @@ static const struct file_operations tracing_saved_cmdlines_size_fops = { .write = tracing_saved_cmdlines_size_write, }; +#ifdef CONFIG_TRACE_ENUM_MAP_FILE +static union trace_enum_map_item * +update_enum_map(union trace_enum_map_item *ptr) +{ + if (!ptr->map.enum_string) { + if (ptr->tail.next) { + ptr = ptr->tail.next; + /* Set ptr to the next real item (skip head) */ + ptr++; + } else + return NULL; + } + return ptr; +} + +static void *enum_map_next(struct seq_file *m, void *v, loff_t *pos) +{ + union trace_enum_map_item *ptr = v; + + /* + * Paranoid! If ptr points to end, we don't want to increment past it. + * This really should never happen. + */ + ptr = update_enum_map(ptr); + if (WARN_ON_ONCE(!ptr)) + return NULL; + + ptr++; + + (*pos)++; + + ptr = update_enum_map(ptr); + + return ptr; +} + +static void *enum_map_start(struct seq_file *m, loff_t *pos) +{ + union trace_enum_map_item *v; + loff_t l = 0; + + mutex_lock(&trace_enum_mutex); + + v = trace_enum_maps; + if (v) + v++; + + while (v && l < *pos) { + v = enum_map_next(m, v, &l); + } + + return v; +} + +static void enum_map_stop(struct seq_file *m, void *v) +{ + mutex_unlock(&trace_enum_mutex); +} + +static int enum_map_show(struct seq_file *m, void *v) +{ + union trace_enum_map_item *ptr = v; + + seq_printf(m, "%s %ld (%s)\n", + ptr->map.enum_string, ptr->map.enum_value, + ptr->map.system); + + return 0; +} + +static const struct seq_operations tracing_enum_map_seq_ops = { + .start = enum_map_start, + .next = enum_map_next, + .stop = enum_map_stop, + .show = enum_map_show, +}; + +static int tracing_enum_map_open(struct inode *inode, struct file *filp) +{ + if (tracing_disabled) + return -ENODEV; + + return seq_open(filp, &tracing_enum_map_seq_ops); +} + +static const struct file_operations tracing_enum_map_fops = { + .open = tracing_enum_map_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release, +}; + +static inline union trace_enum_map_item * +trace_enum_jmp_to_tail(union trace_enum_map_item *ptr) +{ + /* Return tail of array given the head */ + return ptr + ptr->head.length + 1; +} + +static void +trace_insert_enum_map_file(struct module *mod, struct trace_enum_map **start, + int len) +{ + struct trace_enum_map **stop; + struct trace_enum_map **map; + union trace_enum_map_item *map_array; + union trace_enum_map_item *ptr; + + stop = start + len; + + /* + * The trace_enum_maps contains the map plus a head and tail item, + * where the head holds the module and length of array, and the + * tail holds a pointer to the next list. + */ + map_array = kmalloc(sizeof(*map_array) * (len + 2), GFP_KERNEL); + if (!map_array) { + pr_warning("Unable to allocate trace enum mapping\n"); + return; + } + + mutex_lock(&trace_enum_mutex); + + if (!trace_enum_maps) + trace_enum_maps = map_array; + else { + ptr = trace_enum_maps; + for (;;) { + ptr = trace_enum_jmp_to_tail(ptr); + if (!ptr->tail.next) + break; + ptr = ptr->tail.next; + + } + ptr->tail.next = map_array; + } + map_array->head.mod = mod; + map_array->head.length = len; + map_array++; + + for (map = start; (unsigned long)map < (unsigned long)stop; map++) { + map_array->map = **map; + map_array++; + } + memset(map_array, 0, sizeof(*map_array)); + + mutex_unlock(&trace_enum_mutex); +} + +static void trace_create_enum_file(struct dentry *d_tracer) +{ + trace_create_file("enum_map", 0444, d_tracer, + NULL, &tracing_enum_map_fops); +} + +#else /* CONFIG_TRACE_ENUM_MAP_FILE */ +static inline void trace_create_enum_file(struct dentry *d_tracer) { } +static inline void trace_insert_enum_map_file(struct module *mod, + struct trace_enum_map **start, int len) { } +#endif /* !CONFIG_TRACE_ENUM_MAP_FILE */ + +static void trace_insert_enum_map(struct module *mod, + struct trace_enum_map **start, int len) +{ + struct trace_enum_map **map; + + if (len <= 0) + return; + + map = start; + + trace_event_enum_update(map, len); + + trace_insert_enum_map_file(mod, start, len); +} + static ssize_t tracing_set_trace_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) @@ -4105,9 +4319,24 @@ static void tracing_set_nop(struct trace_array *tr) tr->current_trace = &nop_trace; } -static int tracing_set_tracer(struct trace_array *tr, const char *buf) +static void update_tracer_options(struct trace_array *tr, struct tracer *t) { static struct trace_option_dentry *topts; + + /* Only enable if the directory has been created already. */ + if (!tr->dir) + return; + + /* Currently, only the top instance has options */ + if (!(tr->flags & TRACE_ARRAY_FL_GLOBAL)) + return; + + destroy_trace_option_files(topts); + topts = create_trace_option_files(tr, t); +} + +static int tracing_set_tracer(struct trace_array *tr, const char *buf) +{ struct tracer *t; #ifdef CONFIG_TRACER_MAX_TRACE bool had_max_tr; @@ -4172,11 +4401,7 @@ static int tracing_set_tracer(struct trace_array *tr, const char *buf) free_snapshot(tr); } #endif - /* Currently, only the top instance has options */ - if (tr->flags & TRACE_ARRAY_FL_GLOBAL) { - destroy_trace_option_files(topts); - topts = create_trace_option_files(tr, t); - } + update_tracer_options(tr, t); #ifdef CONFIG_TRACER_MAX_TRACE if (t->use_max_tr && !had_max_tr) { @@ -5817,6 +6042,14 @@ static inline __init int register_snapshot_cmd(void) { return 0; } static struct dentry *tracing_get_dentry(struct trace_array *tr) { + if (WARN_ON(!tr->dir)) + return ERR_PTR(-ENODEV); + + /* Top directory uses NULL as the parent */ + if (tr->flags & TRACE_ARRAY_FL_GLOBAL) + return NULL; + + /* All sub buffers have a descriptor */ return tr->dir; } @@ -5831,10 +6064,10 @@ static struct dentry *tracing_dentry_percpu(struct trace_array *tr, int cpu) if (IS_ERR(d_tracer)) return NULL; - tr->percpu_dir = debugfs_create_dir("per_cpu", d_tracer); + tr->percpu_dir = tracefs_create_dir("per_cpu", d_tracer); WARN_ONCE(!tr->percpu_dir, - "Could not create debugfs directory 'per_cpu/%d'\n", cpu); + "Could not create tracefs directory 'per_cpu/%d'\n", cpu); return tr->percpu_dir; } @@ -5851,7 +6084,7 @@ trace_create_cpu_file(const char *name, umode_t mode, struct dentry *parent, } static void -tracing_init_debugfs_percpu(struct trace_array *tr, long cpu) +tracing_init_tracefs_percpu(struct trace_array *tr, long cpu) { struct dentry *d_percpu = tracing_dentry_percpu(tr, cpu); struct dentry *d_cpu; @@ -5861,9 +6094,9 @@ tracing_init_debugfs_percpu(struct trace_array *tr, long cpu) return; snprintf(cpu_dir, 30, "cpu%ld", cpu); - d_cpu = debugfs_create_dir(cpu_dir, d_percpu); + d_cpu = tracefs_create_dir(cpu_dir, d_percpu); if (!d_cpu) { - pr_warning("Could not create debugfs '%s' entry\n", cpu_dir); + pr_warning("Could not create tracefs '%s' entry\n", cpu_dir); return; } @@ -6015,9 +6248,9 @@ struct dentry *trace_create_file(const char *name, { struct dentry *ret; - ret = debugfs_create_file(name, mode, parent, data, fops); + ret = tracefs_create_file(name, mode, parent, data, fops); if (!ret) - pr_warning("Could not create debugfs '%s' entry\n", name); + pr_warning("Could not create tracefs '%s' entry\n", name); return ret; } @@ -6034,9 +6267,9 @@ static struct dentry *trace_options_init_dentry(struct trace_array *tr) if (IS_ERR(d_tracer)) return NULL; - tr->options = debugfs_create_dir("options", d_tracer); + tr->options = tracefs_create_dir("options", d_tracer); if (!tr->options) { - pr_warning("Could not create debugfs directory 'options'\n"); + pr_warning("Could not create tracefs directory 'options'\n"); return NULL; } @@ -6105,7 +6338,7 @@ destroy_trace_option_files(struct trace_option_dentry *topts) return; for (cnt = 0; topts[cnt].opt; cnt++) - debugfs_remove(topts[cnt].entry); + tracefs_remove(topts[cnt].entry); kfree(topts); } @@ -6194,7 +6427,7 @@ static const struct file_operations rb_simple_fops = { struct dentry *trace_instance_dir; static void -init_tracer_debugfs(struct trace_array *tr, struct dentry *d_tracer); +init_tracer_tracefs(struct trace_array *tr, struct dentry *d_tracer); static int allocate_trace_buffer(struct trace_array *tr, struct trace_buffer *buf, int size) @@ -6271,7 +6504,7 @@ static void free_trace_buffers(struct trace_array *tr) #endif } -static int new_instance_create(const char *name) +static int instance_mkdir(const char *name) { struct trace_array *tr; int ret; @@ -6310,17 +6543,17 @@ static int new_instance_create(const char *name) if (allocate_trace_buffers(tr, trace_buf_size) < 0) goto out_free_tr; - tr->dir = debugfs_create_dir(name, trace_instance_dir); + tr->dir = tracefs_create_dir(name, trace_instance_dir); if (!tr->dir) goto out_free_tr; ret = event_trace_add_tracer(tr->dir, tr); if (ret) { - debugfs_remove_recursive(tr->dir); + tracefs_remove_recursive(tr->dir); goto out_free_tr; } - init_tracer_debugfs(tr, tr->dir); + init_tracer_tracefs(tr, tr->dir); list_add(&tr->list, &ftrace_trace_arrays); @@ -6341,7 +6574,7 @@ static int new_instance_create(const char *name) } -static int instance_delete(const char *name) +static int instance_rmdir(const char *name) { struct trace_array *tr; int found = 0; @@ -6382,82 +6615,17 @@ static int instance_delete(const char *name) return ret; } -static int instance_mkdir (struct inode *inode, struct dentry *dentry, umode_t mode) -{ - struct dentry *parent; - int ret; - - /* Paranoid: Make sure the parent is the "instances" directory */ - parent = hlist_entry(inode->i_dentry.first, struct dentry, d_u.d_alias); - if (WARN_ON_ONCE(parent != trace_instance_dir)) - return -ENOENT; - - /* - * The inode mutex is locked, but debugfs_create_dir() will also - * take the mutex. As the instances directory can not be destroyed - * or changed in any other way, it is safe to unlock it, and - * let the dentry try. If two users try to make the same dir at - * the same time, then the new_instance_create() will determine the - * winner. - */ - mutex_unlock(&inode->i_mutex); - - ret = new_instance_create(dentry->d_iname); - - mutex_lock(&inode->i_mutex); - - return ret; -} - -static int instance_rmdir(struct inode *inode, struct dentry *dentry) -{ - struct dentry *parent; - int ret; - - /* Paranoid: Make sure the parent is the "instances" directory */ - parent = hlist_entry(inode->i_dentry.first, struct dentry, d_u.d_alias); - if (WARN_ON_ONCE(parent != trace_instance_dir)) - return -ENOENT; - - /* The caller did a dget() on dentry */ - mutex_unlock(&dentry->d_inode->i_mutex); - - /* - * The inode mutex is locked, but debugfs_create_dir() will also - * take the mutex. As the instances directory can not be destroyed - * or changed in any other way, it is safe to unlock it, and - * let the dentry try. If two users try to make the same dir at - * the same time, then the instance_delete() will determine the - * winner. - */ - mutex_unlock(&inode->i_mutex); - - ret = instance_delete(dentry->d_iname); - - mutex_lock_nested(&inode->i_mutex, I_MUTEX_PARENT); - mutex_lock(&dentry->d_inode->i_mutex); - - return ret; -} - -static const struct inode_operations instance_dir_inode_operations = { - .lookup = simple_lookup, - .mkdir = instance_mkdir, - .rmdir = instance_rmdir, -}; - static __init void create_trace_instances(struct dentry *d_tracer) { - trace_instance_dir = debugfs_create_dir("instances", d_tracer); + trace_instance_dir = tracefs_create_instance_dir("instances", d_tracer, + instance_mkdir, + instance_rmdir); if (WARN_ON(!trace_instance_dir)) return; - - /* Hijack the dir inode operations, to allow mkdir */ - trace_instance_dir->d_inode->i_op = &instance_dir_inode_operations; } static void -init_tracer_debugfs(struct trace_array *tr, struct dentry *d_tracer) +init_tracer_tracefs(struct trace_array *tr, struct dentry *d_tracer) { int cpu; @@ -6511,10 +6679,32 @@ init_tracer_debugfs(struct trace_array *tr, struct dentry *d_tracer) #endif for_each_tracing_cpu(cpu) - tracing_init_debugfs_percpu(tr, cpu); + tracing_init_tracefs_percpu(tr, cpu); } +static struct vfsmount *trace_automount(void *ingore) +{ + struct vfsmount *mnt; + struct file_system_type *type; + + /* + * To maintain backward compatibility for tools that mount + * debugfs to get to the tracing facility, tracefs is automatically + * mounted to the debugfs/tracing directory. + */ + type = get_fs_type("tracefs"); + if (!type) + return NULL; + mnt = vfs_kern_mount(type, 0, "tracefs", NULL); + put_filesystem(type); + if (IS_ERR(mnt)) + return NULL; + mntget(mnt); + + return mnt; +} + /** * tracing_init_dentry - initialize top level trace array * @@ -6526,23 +6716,112 @@ struct dentry *tracing_init_dentry(void) { struct trace_array *tr = &global_trace; + /* The top level trace array uses NULL as parent */ if (tr->dir) - return tr->dir; + return NULL; if (WARN_ON(!debugfs_initialized())) return ERR_PTR(-ENODEV); - tr->dir = debugfs_create_dir("tracing", NULL); - + /* + * As there may still be users that expect the tracing + * files to exist in debugfs/tracing, we must automount + * the tracefs file system there, so older tools still + * work with the newer kerenl. + */ + tr->dir = debugfs_create_automount("tracing", NULL, + trace_automount, NULL); if (!tr->dir) { pr_warn_once("Could not create debugfs directory 'tracing'\n"); return ERR_PTR(-ENOMEM); } - return tr->dir; + return NULL; +} + +extern struct trace_enum_map *__start_ftrace_enum_maps[]; +extern struct trace_enum_map *__stop_ftrace_enum_maps[]; + +static void __init trace_enum_init(void) +{ + int len; + + len = __stop_ftrace_enum_maps - __start_ftrace_enum_maps; + trace_insert_enum_map(NULL, __start_ftrace_enum_maps, len); +} + +#ifdef CONFIG_MODULES +static void trace_module_add_enums(struct module *mod) +{ + if (!mod->num_trace_enums) + return; + + /* + * Modules with bad taint do not have events created, do + * not bother with enums either. + */ + if (trace_module_has_bad_taint(mod)) + return; + + trace_insert_enum_map(mod, mod->trace_enums, mod->num_trace_enums); } -static __init int tracer_init_debugfs(void) +#ifdef CONFIG_TRACE_ENUM_MAP_FILE +static void trace_module_remove_enums(struct module *mod) +{ + union trace_enum_map_item *map; + union trace_enum_map_item **last = &trace_enum_maps; + + if (!mod->num_trace_enums) + return; + + mutex_lock(&trace_enum_mutex); + + map = trace_enum_maps; + + while (map) { + if (map->head.mod == mod) + break; + map = trace_enum_jmp_to_tail(map); + last = &map->tail.next; + map = map->tail.next; + } + if (!map) + goto out; + + *last = trace_enum_jmp_to_tail(map)->tail.next; + kfree(map); + out: + mutex_unlock(&trace_enum_mutex); +} +#else +static inline void trace_module_remove_enums(struct module *mod) { } +#endif /* CONFIG_TRACE_ENUM_MAP_FILE */ + +static int trace_module_notify(struct notifier_block *self, + unsigned long val, void *data) +{ + struct module *mod = data; + + switch (val) { + case MODULE_STATE_COMING: + trace_module_add_enums(mod); + break; + case MODULE_STATE_GOING: + trace_module_remove_enums(mod); + break; + } + + return 0; +} + +static struct notifier_block trace_module_nb = { + .notifier_call = trace_module_notify, + .priority = 0, +}; +#endif /* CONFIG_MODULES */ + +static __init int tracer_init_tracefs(void) { struct dentry *d_tracer; @@ -6552,7 +6831,7 @@ static __init int tracer_init_debugfs(void) if (IS_ERR(d_tracer)) return 0; - init_tracer_debugfs(&global_trace, d_tracer); + init_tracer_tracefs(&global_trace, d_tracer); trace_create_file("tracing_thresh", 0644, d_tracer, &global_trace, &tracing_thresh_fops); @@ -6566,6 +6845,14 @@ static __init int tracer_init_debugfs(void) trace_create_file("saved_cmdlines_size", 0644, d_tracer, NULL, &tracing_saved_cmdlines_size_fops); + trace_enum_init(); + + trace_create_enum_file(d_tracer); + +#ifdef CONFIG_MODULES + register_module_notifier(&trace_module_nb); +#endif + #ifdef CONFIG_DYNAMIC_FTRACE trace_create_file("dyn_ftrace_total_info", 0444, d_tracer, &ftrace_update_tot_cnt, &tracing_dyn_info_fops); @@ -6575,6 +6862,10 @@ static __init int tracer_init_debugfs(void) create_trace_options_dir(&global_trace); + /* If the tracer was started via cmdline, create options for it here */ + if (global_trace.current_trace != &nop_trace) + update_tracer_options(&global_trace, global_trace.current_trace); + return 0; } @@ -6888,7 +7179,7 @@ void __init trace_init(void) tracepoint_printk = 0; } tracer_alloc_buffers(); - trace_event_init(); + trace_event_init(); } __init static int clear_boot_tracer(void) @@ -6910,5 +7201,5 @@ __init static int clear_boot_tracer(void) return 0; } -fs_initcall(tracer_init_debugfs); +fs_initcall(tracer_init_tracefs); late_initcall(clear_boot_tracer); diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index dd8205a35760..d2612016de94 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -334,7 +334,7 @@ struct tracer_flags { /** - * struct tracer - a specific tracer and its callbacks to interact with debugfs + * struct tracer - a specific tracer and its callbacks to interact with tracefs * @name: the name chosen to select it on the available_tracers file * @init: called when one switches to this tracer (echo name > current_tracer) * @reset: called when one switches to another tracer @@ -1309,8 +1309,10 @@ static inline void init_ftrace_syscalls(void) { } #ifdef CONFIG_EVENT_TRACING void trace_event_init(void); +void trace_event_enum_update(struct trace_enum_map **map, int len); #else static inline void __init trace_event_init(void) { } +static inlin void trace_event_enum_update(struct trace_enum_map **map, int len) { } #endif extern struct trace_iterator *tracepoint_print_iter; diff --git a/kernel/trace/trace_entries.h b/kernel/trace/trace_entries.h index e2d027ac66a2..ee7b94a4810a 100644 --- a/kernel/trace/trace_entries.h +++ b/kernel/trace/trace_entries.h @@ -223,7 +223,7 @@ FTRACE_ENTRY(bprint, bprint_entry, __dynamic_array( u32, buf ) ), - F_printk("%pf: %s", + F_printk("%ps: %s", (void *)__entry->ip, __entry->fmt), FILTER_OTHER @@ -238,7 +238,7 @@ FTRACE_ENTRY(print, print_entry, __dynamic_array( char, buf ) ), - F_printk("%pf: %s", + F_printk("%ps: %s", (void *)__entry->ip, __entry->buf), FILTER_OTHER @@ -253,7 +253,7 @@ FTRACE_ENTRY(bputs, bputs_entry, __field( const char *, str ) ), - F_printk("%pf: %s", + F_printk("%ps: %s", (void *)__entry->ip, __entry->str), FILTER_OTHER diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index db54dda10ccc..7da1dfeb322e 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -13,7 +13,7 @@ #include <linux/workqueue.h> #include <linux/spinlock.h> #include <linux/kthread.h> -#include <linux/debugfs.h> +#include <linux/tracefs.h> #include <linux/uaccess.h> #include <linux/module.h> #include <linux/ctype.h> @@ -480,7 +480,7 @@ static void remove_subsystem(struct ftrace_subsystem_dir *dir) return; if (!--dir->nr_events) { - debugfs_remove_recursive(dir->entry); + tracefs_remove_recursive(dir->entry); list_del(&dir->list); __put_system_dir(dir); } @@ -499,7 +499,7 @@ static void remove_event_file_dir(struct ftrace_event_file *file) } spin_unlock(&dir->d_lock); - debugfs_remove_recursive(dir); + tracefs_remove_recursive(dir); } list_del(&file->list); @@ -1526,7 +1526,7 @@ event_subsystem_dir(struct trace_array *tr, const char *name, } else __get_system(system); - dir->entry = debugfs_create_dir(name, parent); + dir->entry = tracefs_create_dir(name, parent); if (!dir->entry) { pr_warn("Failed to create system directory %s\n", name); __put_system(system); @@ -1539,12 +1539,12 @@ event_subsystem_dir(struct trace_array *tr, const char *name, dir->subsystem = system; file->system = dir; - entry = debugfs_create_file("filter", 0644, dir->entry, dir, + entry = tracefs_create_file("filter", 0644, dir->entry, dir, &ftrace_subsystem_filter_fops); if (!entry) { kfree(system->filter); system->filter = NULL; - pr_warn("Could not create debugfs '%s/filter' entry\n", name); + pr_warn("Could not create tracefs '%s/filter' entry\n", name); } trace_create_file("enable", 0644, dir->entry, dir, @@ -1585,9 +1585,9 @@ event_create_dir(struct dentry *parent, struct ftrace_event_file *file) d_events = parent; name = ftrace_event_name(call); - file->dir = debugfs_create_dir(name, d_events); + file->dir = tracefs_create_dir(name, d_events); if (!file->dir) { - pr_warn("Could not create debugfs '%s' directory\n", name); + pr_warn("Could not create tracefs '%s' directory\n", name); return -1; } @@ -1704,6 +1704,125 @@ __register_event(struct ftrace_event_call *call, struct module *mod) return 0; } +static char *enum_replace(char *ptr, struct trace_enum_map *map, int len) +{ + int rlen; + int elen; + + /* Find the length of the enum value as a string */ + elen = snprintf(ptr, 0, "%ld", map->enum_value); + /* Make sure there's enough room to replace the string with the value */ + if (len < elen) + return NULL; + + snprintf(ptr, elen + 1, "%ld", map->enum_value); + + /* Get the rest of the string of ptr */ + rlen = strlen(ptr + len); + memmove(ptr + elen, ptr + len, rlen); + /* Make sure we end the new string */ + ptr[elen + rlen] = 0; + + return ptr + elen; +} + +static void update_event_printk(struct ftrace_event_call *call, + struct trace_enum_map *map) +{ + char *ptr; + int quote = 0; + int len = strlen(map->enum_string); + + for (ptr = call->print_fmt; *ptr; ptr++) { + if (*ptr == '\\') { + ptr++; + /* paranoid */ + if (!*ptr) + break; + continue; + } + if (*ptr == '"') { + quote ^= 1; + continue; + } + if (quote) + continue; + if (isdigit(*ptr)) { + /* skip numbers */ + do { + ptr++; + /* Check for alpha chars like ULL */ + } while (isalnum(*ptr)); + /* + * A number must have some kind of delimiter after + * it, and we can ignore that too. + */ + continue; + } + if (isalpha(*ptr) || *ptr == '_') { + if (strncmp(map->enum_string, ptr, len) == 0 && + !isalnum(ptr[len]) && ptr[len] != '_') { + ptr = enum_replace(ptr, map, len); + /* Hmm, enum string smaller than value */ + if (WARN_ON_ONCE(!ptr)) + return; + /* + * No need to decrement here, as enum_replace() + * returns the pointer to the character passed + * the enum, and two enums can not be placed + * back to back without something in between. + * We can skip that something in between. + */ + continue; + } + skip_more: + do { + ptr++; + } while (isalnum(*ptr) || *ptr == '_'); + /* + * If what comes after this variable is a '.' or + * '->' then we can continue to ignore that string. + */ + if (*ptr == '.' || (ptr[0] == '-' && ptr[1] == '>')) { + ptr += *ptr == '.' ? 1 : 2; + goto skip_more; + } + /* + * Once again, we can skip the delimiter that came + * after the string. + */ + continue; + } + } +} + +void trace_event_enum_update(struct trace_enum_map **map, int len) +{ + struct ftrace_event_call *call, *p; + const char *last_system = NULL; + int last_i; + int i; + + down_write(&trace_event_sem); + list_for_each_entry_safe(call, p, &ftrace_events, list) { + /* events are usually grouped together with systems */ + if (!last_system || call->class->system != last_system) { + last_i = 0; + last_system = call->class->system; + } + + for (i = last_i; i < len; i++) { + if (call->class->system == map[i]->system) { + /* Save the first system if need be */ + if (!last_i) + last_i = i; + update_event_printk(call, map[i]); + } + } + } + up_write(&trace_event_sem); +} + static struct ftrace_event_file * trace_create_new_event(struct ftrace_event_call *call, struct trace_array *tr) @@ -1915,7 +2034,7 @@ static int trace_module_notify(struct notifier_block *self, static struct notifier_block trace_module_nb = { .notifier_call = trace_module_notify, - .priority = 0, + .priority = 1, /* higher than trace.c module notify */ }; #endif /* CONFIG_MODULES */ @@ -2228,7 +2347,7 @@ static inline int register_event_cmds(void) { return 0; } /* * The top level array has already had its ftrace_event_file * descriptors created in order to allow for early events to - * be recorded. This function is called after the debugfs has been + * be recorded. This function is called after the tracefs has been * initialized, and we now have to create the files associated * to the events. */ @@ -2311,16 +2430,16 @@ create_event_toplevel_files(struct dentry *parent, struct trace_array *tr) struct dentry *d_events; struct dentry *entry; - entry = debugfs_create_file("set_event", 0644, parent, + entry = tracefs_create_file("set_event", 0644, parent, tr, &ftrace_set_event_fops); if (!entry) { - pr_warn("Could not create debugfs 'set_event' entry\n"); + pr_warn("Could not create tracefs 'set_event' entry\n"); return -ENOMEM; } - d_events = debugfs_create_dir("events", parent); + d_events = tracefs_create_dir("events", parent); if (!d_events) { - pr_warn("Could not create debugfs 'events' directory\n"); + pr_warn("Could not create tracefs 'events' directory\n"); return -ENOMEM; } @@ -2412,7 +2531,7 @@ int event_trace_del_tracer(struct trace_array *tr) down_write(&trace_event_sem); __trace_remove_event_dirs(tr); - debugfs_remove_recursive(tr->event_dir); + tracefs_remove_recursive(tr->event_dir); up_write(&trace_event_sem); tr->event_dir = NULL; @@ -2534,10 +2653,10 @@ static __init int event_trace_init(void) if (IS_ERR(d_tracer)) return 0; - entry = debugfs_create_file("available_events", 0444, d_tracer, + entry = tracefs_create_file("available_events", 0444, d_tracer, tr, &ftrace_avail_fops); if (!entry) - pr_warn("Could not create debugfs 'available_events' entry\n"); + pr_warn("Could not create tracefs 'available_events' entry\n"); if (trace_define_common_fields()) pr_warn("tracing: Failed to allocate common fields"); diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c index 12e2b99be862..174a6a71146c 100644 --- a/kernel/trace/trace_export.c +++ b/kernel/trace/trace_export.c @@ -177,7 +177,7 @@ struct ftrace_event_call __used event_##call = { \ }, \ .event.type = etype, \ .print_fmt = print, \ - .flags = TRACE_EVENT_FL_IGNORE_ENABLE | TRACE_EVENT_FL_USE_CALL_FILTER, \ + .flags = TRACE_EVENT_FL_IGNORE_ENABLE, \ }; \ struct ftrace_event_call __used \ __attribute__((section("_ftrace_events"))) *__event_##call = &event_##call; diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c index 2d25ad1526bb..9cfea4c6d314 100644 --- a/kernel/trace/trace_functions_graph.c +++ b/kernel/trace/trace_functions_graph.c @@ -6,7 +6,6 @@ * is Copyright (c) Steven Rostedt <srostedt@redhat.com> * */ -#include <linux/debugfs.h> #include <linux/uaccess.h> #include <linux/ftrace.h> #include <linux/slab.h> @@ -151,7 +150,7 @@ ftrace_push_return_trace(unsigned long ret, unsigned long func, int *depth, * The curr_ret_stack is initialized to -1 and get increased * in this function. So it can be less than -1 only if it was * filtered out via ftrace_graph_notrace_addr() which can be - * set from set_graph_notrace file in debugfs by user. + * set from set_graph_notrace file in tracefs by user. */ if (current->curr_ret_stack < -1) return -EBUSY; @@ -1432,7 +1431,7 @@ static const struct file_operations graph_depth_fops = { .llseek = generic_file_llseek, }; -static __init int init_graph_debugfs(void) +static __init int init_graph_tracefs(void) { struct dentry *d_tracer; @@ -1445,7 +1444,7 @@ static __init int init_graph_debugfs(void) return 0; } -fs_initcall(init_graph_debugfs); +fs_initcall(init_graph_tracefs); static __init int init_graph_trace(void) { diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index d73f565b4e06..d0ce590f06e1 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -250,7 +250,7 @@ DEFINE_FETCH_symbol(string_size) #define fetch_file_offset_string_size NULL /* Fetch type information table */ -const struct fetch_type kprobes_fetch_type_table[] = { +static const struct fetch_type kprobes_fetch_type_table[] = { /* Special types */ [FETCH_TYPE_STRING] = __ASSIGN_FETCH_TYPE("string", string, string, sizeof(u32), 1, "__data_loc char[]"), @@ -760,7 +760,8 @@ static int create_trace_kprobe(int argc, char **argv) /* Parse fetch argument */ ret = traceprobe_parse_probe_arg(arg, &tk->tp.size, parg, - is_return, true); + is_return, true, + kprobes_fetch_type_table); if (ret) { pr_info("Parse error at argument[%d]. (%d)\n", i, ret); goto error; @@ -1134,11 +1135,15 @@ static void kprobe_perf_func(struct trace_kprobe *tk, struct pt_regs *regs) { struct ftrace_event_call *call = &tk->tp.call; + struct bpf_prog *prog = call->prog; struct kprobe_trace_entry_head *entry; struct hlist_head *head; int size, __size, dsize; int rctx; + if (prog && !trace_call_bpf(prog, regs)) + return; + head = this_cpu_ptr(call->perf_events); if (hlist_empty(head)) return; @@ -1165,11 +1170,15 @@ kretprobe_perf_func(struct trace_kprobe *tk, struct kretprobe_instance *ri, struct pt_regs *regs) { struct ftrace_event_call *call = &tk->tp.call; + struct bpf_prog *prog = call->prog; struct kretprobe_trace_entry_head *entry; struct hlist_head *head; int size, __size, dsize; int rctx; + if (prog && !trace_call_bpf(prog, regs)) + return; + head = this_cpu_ptr(call->perf_events); if (hlist_empty(head)) return; @@ -1286,7 +1295,7 @@ static int register_kprobe_event(struct trace_kprobe *tk) kfree(call->print_fmt); return -ENODEV; } - call->flags = 0; + call->flags = TRACE_EVENT_FL_KPROBE; call->class->reg = kprobe_register; call->data = tk; ret = trace_add_event_call(call); @@ -1310,7 +1319,7 @@ static int unregister_kprobe_event(struct trace_kprobe *tk) return ret; } -/* Make a debugfs interface for controlling probe points */ +/* Make a tracefs interface for controlling probe points */ static __init int init_kprobe_trace(void) { struct dentry *d_tracer; @@ -1323,20 +1332,20 @@ static __init int init_kprobe_trace(void) if (IS_ERR(d_tracer)) return 0; - entry = debugfs_create_file("kprobe_events", 0644, d_tracer, + entry = tracefs_create_file("kprobe_events", 0644, d_tracer, NULL, &kprobe_events_ops); /* Event list interface */ if (!entry) - pr_warning("Could not create debugfs " + pr_warning("Could not create tracefs " "'kprobe_events' entry\n"); /* Profile interface */ - entry = debugfs_create_file("kprobe_profile", 0444, d_tracer, + entry = tracefs_create_file("kprobe_profile", 0444, d_tracer, NULL, &kprobe_profile_ops); if (!entry) - pr_warning("Could not create debugfs " + pr_warning("Could not create tracefs " "'kprobe_profile' entry\n"); return 0; } diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c index b983b2fd2ca1..1769a81da8a7 100644 --- a/kernel/trace/trace_probe.c +++ b/kernel/trace/trace_probe.c @@ -356,17 +356,14 @@ static int parse_probe_vars(char *arg, const struct fetch_type *t, /* Recursive argument parser */ static int parse_probe_arg(char *arg, const struct fetch_type *t, - struct fetch_param *f, bool is_return, bool is_kprobe) + struct fetch_param *f, bool is_return, bool is_kprobe, + const struct fetch_type *ftbl) { - const struct fetch_type *ftbl; unsigned long param; long offset; char *tmp; int ret = 0; - ftbl = is_kprobe ? kprobes_fetch_type_table : uprobes_fetch_type_table; - BUG_ON(ftbl == NULL); - switch (arg[0]) { case '$': ret = parse_probe_vars(arg + 1, t, f, is_return, is_kprobe); @@ -447,7 +444,7 @@ static int parse_probe_arg(char *arg, const struct fetch_type *t, dprm->fetch_size = get_fetch_size_function(t, dprm->fetch, ftbl); ret = parse_probe_arg(arg, t2, &dprm->orig, is_return, - is_kprobe); + is_kprobe, ftbl); if (ret) kfree(dprm); else { @@ -505,15 +502,12 @@ static int __parse_bitfield_probe_arg(const char *bf, /* String length checking wrapper */ int traceprobe_parse_probe_arg(char *arg, ssize_t *size, - struct probe_arg *parg, bool is_return, bool is_kprobe) + struct probe_arg *parg, bool is_return, bool is_kprobe, + const struct fetch_type *ftbl) { - const struct fetch_type *ftbl; const char *t; int ret; - ftbl = is_kprobe ? kprobes_fetch_type_table : uprobes_fetch_type_table; - BUG_ON(ftbl == NULL); - if (strlen(arg) > MAX_ARGSTR_LEN) { pr_info("Argument is too long.: %s\n", arg); return -ENOSPC; @@ -535,7 +529,8 @@ int traceprobe_parse_probe_arg(char *arg, ssize_t *size, } parg->offset = *size; *size += parg->type->size; - ret = parse_probe_arg(arg, parg->type, &parg->fetch, is_return, is_kprobe); + ret = parse_probe_arg(arg, parg->type, &parg->fetch, is_return, + is_kprobe, ftbl); if (ret >= 0 && t != NULL) ret = __parse_bitfield_probe_arg(t, parg->type, &parg->fetch); diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h index 4f815fbce16d..ab283e146b70 100644 --- a/kernel/trace/trace_probe.h +++ b/kernel/trace/trace_probe.h @@ -25,7 +25,7 @@ #include <linux/seq_file.h> #include <linux/slab.h> #include <linux/smp.h> -#include <linux/debugfs.h> +#include <linux/tracefs.h> #include <linux/types.h> #include <linux/string.h> #include <linux/ctype.h> @@ -229,13 +229,6 @@ ASSIGN_FETCH_FUNC(file_offset, ftype), \ #define FETCH_TYPE_STRING 0 #define FETCH_TYPE_STRSIZE 1 -/* - * Fetch type information table. - * It's declared as a weak symbol due to conditional compilation. - */ -extern __weak const struct fetch_type kprobes_fetch_type_table[]; -extern __weak const struct fetch_type uprobes_fetch_type_table[]; - #ifdef CONFIG_KPROBE_EVENT struct symbol_cache; unsigned long update_symbol_cache(struct symbol_cache *sc); @@ -333,7 +326,8 @@ find_event_file_link(struct trace_probe *tp, struct ftrace_event_file *file) } extern int traceprobe_parse_probe_arg(char *arg, ssize_t *size, - struct probe_arg *parg, bool is_return, bool is_kprobe); + struct probe_arg *parg, bool is_return, bool is_kprobe, + const struct fetch_type *ftbl); extern int traceprobe_conflict_field_name(const char *name, struct probe_arg *args, int narg); diff --git a/kernel/trace/trace_stat.c b/kernel/trace/trace_stat.c index 75e19e86c954..6cf935316769 100644 --- a/kernel/trace/trace_stat.c +++ b/kernel/trace/trace_stat.c @@ -12,7 +12,7 @@ #include <linux/list.h> #include <linux/slab.h> #include <linux/rbtree.h> -#include <linux/debugfs.h> +#include <linux/tracefs.h> #include "trace_stat.h" #include "trace.h" @@ -65,7 +65,7 @@ static void reset_stat_session(struct stat_session *session) static void destroy_session(struct stat_session *session) { - debugfs_remove(session->file); + tracefs_remove(session->file); __reset_stat_session(session); mutex_destroy(&session->stat_mutex); kfree(session); @@ -279,9 +279,9 @@ static int tracing_stat_init(void) if (IS_ERR(d_tracing)) return 0; - stat_dir = debugfs_create_dir("trace_stat", d_tracing); + stat_dir = tracefs_create_dir("trace_stat", d_tracing); if (!stat_dir) - pr_warning("Could not create debugfs " + pr_warning("Could not create tracefs " "'trace_stat' entry\n"); return 0; } @@ -291,7 +291,7 @@ static int init_stat_file(struct stat_session *session) if (!stat_dir && tracing_stat_init()) return -ENODEV; - session->file = debugfs_create_file(session->ts->name, 0644, + session->file = tracefs_create_file(session->ts->name, 0644, stat_dir, session, &tracing_stat_fops); if (!session->file) diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index 7dc1c8abecd6..d60fe62ec4fa 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -196,7 +196,7 @@ DEFINE_FETCH_file_offset(string) DEFINE_FETCH_file_offset(string_size) /* Fetch type information table */ -const struct fetch_type uprobes_fetch_type_table[] = { +static const struct fetch_type uprobes_fetch_type_table[] = { /* Special types */ [FETCH_TYPE_STRING] = __ASSIGN_FETCH_TYPE("string", string, string, sizeof(u32), 1, "__data_loc char[]"), @@ -535,7 +535,8 @@ static int create_trace_uprobe(int argc, char **argv) /* Parse fetch argument */ ret = traceprobe_parse_probe_arg(arg, &tu->tp.size, parg, - is_return, false); + is_return, false, + uprobes_fetch_type_table); if (ret) { pr_info("Parse error at argument[%d]. (%d)\n", i, ret); goto error; @@ -1005,7 +1006,7 @@ __uprobe_perf_filter(struct trace_uprobe_filter *filter, struct mm_struct *mm) return true; list_for_each_entry(event, &filter->perf_events, hw.tp_list) { - if (event->hw.tp_target->mm == mm) + if (event->hw.target->mm == mm) return true; } @@ -1015,7 +1016,7 @@ __uprobe_perf_filter(struct trace_uprobe_filter *filter, struct mm_struct *mm) static inline bool uprobe_filter_event(struct trace_uprobe *tu, struct perf_event *event) { - return __uprobe_perf_filter(&tu->filter, event->hw.tp_target->mm); + return __uprobe_perf_filter(&tu->filter, event->hw.target->mm); } static int uprobe_perf_close(struct trace_uprobe *tu, struct perf_event *event) @@ -1023,10 +1024,10 @@ static int uprobe_perf_close(struct trace_uprobe *tu, struct perf_event *event) bool done; write_lock(&tu->filter.rwlock); - if (event->hw.tp_target) { + if (event->hw.target) { list_del(&event->hw.tp_list); done = tu->filter.nr_systemwide || - (event->hw.tp_target->flags & PF_EXITING) || + (event->hw.target->flags & PF_EXITING) || uprobe_filter_event(tu, event); } else { tu->filter.nr_systemwide--; @@ -1046,7 +1047,7 @@ static int uprobe_perf_open(struct trace_uprobe *tu, struct perf_event *event) int err; write_lock(&tu->filter.rwlock); - if (event->hw.tp_target) { + if (event->hw.target) { /* * event->parent != NULL means copy_process(), we can avoid * uprobe_apply(). current->mm must be probed and we can rely diff --git a/kernel/watchdog.c b/kernel/watchdog.c index 3174bf8e3538..2316f50b07a4 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -24,8 +24,33 @@ #include <linux/kvm_para.h> #include <linux/perf_event.h> -int watchdog_user_enabled = 1; +/* + * The run state of the lockup detectors is controlled by the content of the + * 'watchdog_enabled' variable. Each lockup detector has its dedicated bit - + * bit 0 for the hard lockup detector and bit 1 for the soft lockup detector. + * + * 'watchdog_user_enabled', 'nmi_watchdog_enabled' and 'soft_watchdog_enabled' + * are variables that are only used as an 'interface' between the parameters + * in /proc/sys/kernel and the internal state bits in 'watchdog_enabled'. The + * 'watchdog_thresh' variable is handled differently because its value is not + * boolean, and the lockup detectors are 'suspended' while 'watchdog_thresh' + * is equal zero. + */ +#define NMI_WATCHDOG_ENABLED_BIT 0 +#define SOFT_WATCHDOG_ENABLED_BIT 1 +#define NMI_WATCHDOG_ENABLED (1 << NMI_WATCHDOG_ENABLED_BIT) +#define SOFT_WATCHDOG_ENABLED (1 << SOFT_WATCHDOG_ENABLED_BIT) + +#ifdef CONFIG_HARDLOCKUP_DETECTOR +static unsigned long __read_mostly watchdog_enabled = SOFT_WATCHDOG_ENABLED|NMI_WATCHDOG_ENABLED; +#else +static unsigned long __read_mostly watchdog_enabled = SOFT_WATCHDOG_ENABLED; +#endif +int __read_mostly nmi_watchdog_enabled; +int __read_mostly soft_watchdog_enabled; +int __read_mostly watchdog_user_enabled; int __read_mostly watchdog_thresh = 10; + #ifdef CONFIG_SMP int __read_mostly sysctl_softlockup_all_cpu_backtrace; #else @@ -58,8 +83,6 @@ static unsigned long soft_lockup_nmi_warn; #ifdef CONFIG_HARDLOCKUP_DETECTOR static int hardlockup_panic = CONFIG_BOOTPARAM_HARDLOCKUP_PANIC_VALUE; - -static bool hardlockup_detector_enabled = true; /* * We may not want to enable hard lockup detection by default in all cases, * for example when running the kernel as a guest on a hypervisor. In these @@ -68,14 +91,9 @@ static bool hardlockup_detector_enabled = true; * kernel command line parameters are parsed, because otherwise it is not * possible to override this in hardlockup_panic_setup(). */ -void watchdog_enable_hardlockup_detector(bool val) -{ - hardlockup_detector_enabled = val; -} - -bool watchdog_hardlockup_detector_is_enabled(void) +void hardlockup_detector_disable(void) { - return hardlockup_detector_enabled; + watchdog_enabled &= ~NMI_WATCHDOG_ENABLED; } static int __init hardlockup_panic_setup(char *str) @@ -85,15 +103,9 @@ static int __init hardlockup_panic_setup(char *str) else if (!strncmp(str, "nopanic", 7)) hardlockup_panic = 0; else if (!strncmp(str, "0", 1)) - watchdog_user_enabled = 0; - else if (!strncmp(str, "1", 1) || !strncmp(str, "2", 1)) { - /* - * Setting 'nmi_watchdog=1' or 'nmi_watchdog=2' (legacy option) - * has the same effect. - */ - watchdog_user_enabled = 1; - watchdog_enable_hardlockup_detector(true); - } + watchdog_enabled &= ~NMI_WATCHDOG_ENABLED; + else if (!strncmp(str, "1", 1)) + watchdog_enabled |= NMI_WATCHDOG_ENABLED; return 1; } __setup("nmi_watchdog=", hardlockup_panic_setup); @@ -112,19 +124,18 @@ __setup("softlockup_panic=", softlockup_panic_setup); static int __init nowatchdog_setup(char *str) { - watchdog_user_enabled = 0; + watchdog_enabled = 0; return 1; } __setup("nowatchdog", nowatchdog_setup); -/* deprecated */ static int __init nosoftlockup_setup(char *str) { - watchdog_user_enabled = 0; + watchdog_enabled &= ~SOFT_WATCHDOG_ENABLED; return 1; } __setup("nosoftlockup", nosoftlockup_setup); -/* */ + #ifdef CONFIG_SMP static int __init softlockup_all_cpu_backtrace_setup(char *str) { @@ -239,10 +250,11 @@ static int is_softlockup(unsigned long touch_ts) { unsigned long now = get_timestamp(); - /* Warn about unreasonable delays: */ - if (time_after(now, touch_ts + get_softlockup_thresh())) - return now - touch_ts; - + if (watchdog_enabled & SOFT_WATCHDOG_ENABLED) { + /* Warn about unreasonable delays. */ + if (time_after(now, touch_ts + get_softlockup_thresh())) + return now - touch_ts; + } return 0; } @@ -477,6 +489,21 @@ static void watchdog(unsigned int cpu) __this_cpu_write(soft_lockup_hrtimer_cnt, __this_cpu_read(hrtimer_interrupts)); __touch_watchdog(); + + /* + * watchdog_nmi_enable() clears the NMI_WATCHDOG_ENABLED bit in the + * failure path. Check for failures that can occur asynchronously - + * for example, when CPUs are on-lined - and shut down the hardware + * perf event on each CPU accordingly. + * + * The only non-obvious place this bit can be cleared is through + * watchdog_nmi_enable(), so a pr_info() is placed there. Placing a + * pr_info here would be too noisy as it would result in a message + * every few seconds if the hardlockup was disabled but the softlockup + * enabled. + */ + if (!(watchdog_enabled & NMI_WATCHDOG_ENABLED)) + watchdog_nmi_disable(cpu); } #ifdef CONFIG_HARDLOCKUP_DETECTOR @@ -492,14 +519,9 @@ static int watchdog_nmi_enable(unsigned int cpu) struct perf_event_attr *wd_attr; struct perf_event *event = per_cpu(watchdog_ev, cpu); - /* - * Some kernels need to default hard lockup detection to - * 'disabled', for example a guest on a hypervisor. - */ - if (!watchdog_hardlockup_detector_is_enabled()) { - event = ERR_PTR(-ENOENT); - goto handle_err; - } + /* nothing to do if the hard lockup detector is disabled */ + if (!(watchdog_enabled & NMI_WATCHDOG_ENABLED)) + goto out; /* is it already setup and enabled? */ if (event && event->state > PERF_EVENT_STATE_OFF) @@ -515,7 +537,6 @@ static int watchdog_nmi_enable(unsigned int cpu) /* Try to register using hardware perf events */ event = perf_event_create_kernel_counter(wd_attr, cpu, NULL, watchdog_overflow_callback, NULL); -handle_err: /* save cpu0 error for future comparision */ if (cpu == 0 && IS_ERR(event)) cpu0_err = PTR_ERR(event); @@ -527,6 +548,18 @@ handle_err: goto out_save; } + /* + * Disable the hard lockup detector if _any_ CPU fails to set up + * set up the hardware perf event. The watchdog() function checks + * the NMI_WATCHDOG_ENABLED bit periodically. + * + * The barriers are for syncing up watchdog_enabled across all the + * cpus, as clear_bit() does not use barriers. + */ + smp_mb__before_atomic(); + clear_bit(NMI_WATCHDOG_ENABLED_BIT, &watchdog_enabled); + smp_mb__after_atomic(); + /* skip displaying the same error again */ if (cpu > 0 && (PTR_ERR(event) == cpu0_err)) return PTR_ERR(event); @@ -540,6 +573,9 @@ handle_err: else pr_err("disabled (cpu%i): unable to create perf event: %ld\n", cpu, PTR_ERR(event)); + + pr_info("Shutting down hard lockup detector on all cpus\n"); + return PTR_ERR(event); /* success path */ @@ -567,9 +603,37 @@ static void watchdog_nmi_disable(unsigned int cpu) cpu0_err = 0; } } + +void watchdog_nmi_enable_all(void) +{ + int cpu; + + if (!watchdog_user_enabled) + return; + + get_online_cpus(); + for_each_online_cpu(cpu) + watchdog_nmi_enable(cpu); + put_online_cpus(); +} + +void watchdog_nmi_disable_all(void) +{ + int cpu; + + if (!watchdog_running) + return; + + get_online_cpus(); + for_each_online_cpu(cpu) + watchdog_nmi_disable(cpu); + put_online_cpus(); +} #else static int watchdog_nmi_enable(unsigned int cpu) { return 0; } static void watchdog_nmi_disable(unsigned int cpu) { return; } +void watchdog_nmi_enable_all(void) {} +void watchdog_nmi_disable_all(void) {} #endif /* CONFIG_HARDLOCKUP_DETECTOR */ static struct smp_hotplug_thread watchdog_threads = { @@ -600,7 +664,7 @@ static void restart_watchdog_hrtimer(void *info) HRTIMER_MODE_REL_PINNED); } -static void update_timers(int cpu) +static void update_watchdog(int cpu) { /* * Make sure that perf event counter will adopt to a new @@ -615,17 +679,17 @@ static void update_timers(int cpu) watchdog_nmi_enable(cpu); } -static void update_timers_all_cpus(void) +static void update_watchdog_all_cpus(void) { int cpu; get_online_cpus(); for_each_online_cpu(cpu) - update_timers(cpu); + update_watchdog(cpu); put_online_cpus(); } -static int watchdog_enable_all_cpus(bool sample_period_changed) +static int watchdog_enable_all_cpus(void) { int err = 0; @@ -635,8 +699,12 @@ static int watchdog_enable_all_cpus(bool sample_period_changed) pr_err("Failed to create watchdog threads, disabled\n"); else watchdog_running = 1; - } else if (sample_period_changed) { - update_timers_all_cpus(); + } else { + /* + * Enable/disable the lockup detectors or + * change the sample period 'on the fly'. + */ + update_watchdog_all_cpus(); } return err; @@ -654,58 +722,159 @@ static void watchdog_disable_all_cpus(void) } /* - * proc handler for /proc/sys/kernel/nmi_watchdog,watchdog_thresh + * Update the run state of the lockup detectors. */ +static int proc_watchdog_update(void) +{ + int err = 0; -int proc_dowatchdog(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, loff_t *ppos) + /* + * Watchdog threads won't be started if they are already active. + * The 'watchdog_running' variable in watchdog_*_all_cpus() takes + * care of this. If those threads are already active, the sample + * period will be updated and the lockup detectors will be enabled + * or disabled 'on the fly'. + */ + if (watchdog_enabled && watchdog_thresh) + err = watchdog_enable_all_cpus(); + else + watchdog_disable_all_cpus(); + + return err; + +} + +static DEFINE_MUTEX(watchdog_proc_mutex); + +/* + * common function for watchdog, nmi_watchdog and soft_watchdog parameter + * + * caller | table->data points to | 'which' contains the flag(s) + * -------------------|-----------------------|----------------------------- + * proc_watchdog | watchdog_user_enabled | NMI_WATCHDOG_ENABLED or'ed + * | | with SOFT_WATCHDOG_ENABLED + * -------------------|-----------------------|----------------------------- + * proc_nmi_watchdog | nmi_watchdog_enabled | NMI_WATCHDOG_ENABLED + * -------------------|-----------------------|----------------------------- + * proc_soft_watchdog | soft_watchdog_enabled | SOFT_WATCHDOG_ENABLED + */ +static int proc_watchdog_common(int which, struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) { - int err, old_thresh, old_enabled; - bool old_hardlockup; - static DEFINE_MUTEX(watchdog_proc_mutex); + int err, old, new; + int *watchdog_param = (int *)table->data; mutex_lock(&watchdog_proc_mutex); - old_thresh = ACCESS_ONCE(watchdog_thresh); - old_enabled = ACCESS_ONCE(watchdog_user_enabled); - old_hardlockup = watchdog_hardlockup_detector_is_enabled(); - err = proc_dointvec_minmax(table, write, buffer, lenp, ppos); - if (err || !write) - goto out; - - set_sample_period(); /* - * Watchdog threads shouldn't be enabled if they are - * disabled. The 'watchdog_running' variable check in - * watchdog_*_all_cpus() function takes care of this. + * If the parameter is being read return the state of the corresponding + * bit(s) in 'watchdog_enabled', else update 'watchdog_enabled' and the + * run state of the lockup detectors. */ - if (watchdog_user_enabled && watchdog_thresh) { + if (!write) { + *watchdog_param = (watchdog_enabled & which) != 0; + err = proc_dointvec_minmax(table, write, buffer, lenp, ppos); + } else { + err = proc_dointvec_minmax(table, write, buffer, lenp, ppos); + if (err) + goto out; + /* - * Prevent a change in watchdog_thresh accidentally overriding - * the enablement of the hardlockup detector. + * There is a race window between fetching the current value + * from 'watchdog_enabled' and storing the new value. During + * this race window, watchdog_nmi_enable() can sneak in and + * clear the NMI_WATCHDOG_ENABLED bit in 'watchdog_enabled'. + * The 'cmpxchg' detects this race and the loop retries. */ - if (watchdog_user_enabled != old_enabled) - watchdog_enable_hardlockup_detector(true); - err = watchdog_enable_all_cpus(old_thresh != watchdog_thresh); - } else - watchdog_disable_all_cpus(); + do { + old = watchdog_enabled; + /* + * If the parameter value is not zero set the + * corresponding bit(s), else clear it(them). + */ + if (*watchdog_param) + new = old | which; + else + new = old & ~which; + } while (cmpxchg(&watchdog_enabled, old, new) != old); - /* Restore old values on failure */ - if (err) { - watchdog_thresh = old_thresh; - watchdog_user_enabled = old_enabled; - watchdog_enable_hardlockup_detector(old_hardlockup); + /* + * Update the run state of the lockup detectors. + * Restore 'watchdog_enabled' on failure. + */ + err = proc_watchdog_update(); + if (err) + watchdog_enabled = old; } out: mutex_unlock(&watchdog_proc_mutex); return err; } + +/* + * /proc/sys/kernel/watchdog + */ +int proc_watchdog(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + return proc_watchdog_common(NMI_WATCHDOG_ENABLED|SOFT_WATCHDOG_ENABLED, + table, write, buffer, lenp, ppos); +} + +/* + * /proc/sys/kernel/nmi_watchdog + */ +int proc_nmi_watchdog(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + return proc_watchdog_common(NMI_WATCHDOG_ENABLED, + table, write, buffer, lenp, ppos); +} + +/* + * /proc/sys/kernel/soft_watchdog + */ +int proc_soft_watchdog(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + return proc_watchdog_common(SOFT_WATCHDOG_ENABLED, + table, write, buffer, lenp, ppos); +} + +/* + * /proc/sys/kernel/watchdog_thresh + */ +int proc_watchdog_thresh(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + int err, old; + + mutex_lock(&watchdog_proc_mutex); + + old = ACCESS_ONCE(watchdog_thresh); + err = proc_dointvec_minmax(table, write, buffer, lenp, ppos); + + if (err || !write) + goto out; + + /* + * Update the sample period. + * Restore 'watchdog_thresh' on failure. + */ + set_sample_period(); + err = proc_watchdog_update(); + if (err) + watchdog_thresh = old; +out: + mutex_unlock(&watchdog_proc_mutex); + return err; +} #endif /* CONFIG_SYSCTL */ void __init lockup_detector_init(void) { set_sample_period(); - if (watchdog_user_enabled) - watchdog_enable_all_cpus(false); + if (watchdog_enabled) + watchdog_enable_all_cpus(); } diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 41ff75b478c6..586ad91300b0 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -159,6 +159,7 @@ struct worker_pool { /* see manage_workers() for details on the two manager mutexes */ struct mutex manager_arb; /* manager arbitration */ + struct worker *manager; /* L: purely informational */ struct mutex attach_mutex; /* attach/detach exclusion */ struct list_head workers; /* A: attached workers */ struct completion *detach_completion; /* all workers detached */ @@ -230,7 +231,7 @@ struct wq_device; */ struct workqueue_struct { struct list_head pwqs; /* WR: all pwqs of this wq */ - struct list_head list; /* PL: list of all workqueues */ + struct list_head list; /* PR: list of all workqueues */ struct mutex mutex; /* protects this wq */ int work_color; /* WQ: current work color */ @@ -257,6 +258,13 @@ struct workqueue_struct { #endif char name[WQ_NAME_LEN]; /* I: workqueue name */ + /* + * Destruction of workqueue_struct is sched-RCU protected to allow + * walking the workqueues list without grabbing wq_pool_mutex. + * This is used to dump all workqueues from sysrq. + */ + struct rcu_head rcu; + /* hot fields used during command issue, aligned to cacheline */ unsigned int flags ____cacheline_aligned; /* WQ: WQ_* flags */ struct pool_workqueue __percpu *cpu_pwqs; /* I: per-cpu pwqs */ @@ -288,7 +296,7 @@ static struct workqueue_attrs *wq_update_unbound_numa_attrs_buf; static DEFINE_MUTEX(wq_pool_mutex); /* protects pools and workqueues list */ static DEFINE_SPINLOCK(wq_mayday_lock); /* protects wq->maydays list */ -static LIST_HEAD(workqueues); /* PL: list of all workqueues */ +static LIST_HEAD(workqueues); /* PR: list of all workqueues */ static bool workqueue_freezing; /* PL: have wqs started freezing? */ /* the per-cpu worker pools */ @@ -324,6 +332,7 @@ EXPORT_SYMBOL_GPL(system_freezable_power_efficient_wq); static int worker_thread(void *__worker); static void copy_workqueue_attrs(struct workqueue_attrs *to, const struct workqueue_attrs *from); +static void workqueue_sysfs_unregister(struct workqueue_struct *wq); #define CREATE_TRACE_POINTS #include <trace/events/workqueue.h> @@ -1911,9 +1920,11 @@ static bool manage_workers(struct worker *worker) */ if (!mutex_trylock(&pool->manager_arb)) return false; + pool->manager = worker; maybe_create_worker(pool); + pool->manager = NULL; mutex_unlock(&pool->manager_arb); return true; } @@ -2303,6 +2314,7 @@ repeat: struct wq_barrier { struct work_struct work; struct completion done; + struct task_struct *task; /* purely informational */ }; static void wq_barrier_func(struct work_struct *work) @@ -2351,6 +2363,7 @@ static void insert_wq_barrier(struct pool_workqueue *pwq, INIT_WORK_ONSTACK(&barr->work, wq_barrier_func); __set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(&barr->work)); init_completion(&barr->done); + barr->task = current; /* * If @target is currently being executed, schedule the @@ -2989,323 +3002,6 @@ int execute_in_process_context(work_func_t fn, struct execute_work *ew) } EXPORT_SYMBOL_GPL(execute_in_process_context); -#ifdef CONFIG_SYSFS -/* - * Workqueues with WQ_SYSFS flag set is visible to userland via - * /sys/bus/workqueue/devices/WQ_NAME. All visible workqueues have the - * following attributes. - * - * per_cpu RO bool : whether the workqueue is per-cpu or unbound - * max_active RW int : maximum number of in-flight work items - * - * Unbound workqueues have the following extra attributes. - * - * id RO int : the associated pool ID - * nice RW int : nice value of the workers - * cpumask RW mask : bitmask of allowed CPUs for the workers - */ -struct wq_device { - struct workqueue_struct *wq; - struct device dev; -}; - -static struct workqueue_struct *dev_to_wq(struct device *dev) -{ - struct wq_device *wq_dev = container_of(dev, struct wq_device, dev); - - return wq_dev->wq; -} - -static ssize_t per_cpu_show(struct device *dev, struct device_attribute *attr, - char *buf) -{ - struct workqueue_struct *wq = dev_to_wq(dev); - - return scnprintf(buf, PAGE_SIZE, "%d\n", (bool)!(wq->flags & WQ_UNBOUND)); -} -static DEVICE_ATTR_RO(per_cpu); - -static ssize_t max_active_show(struct device *dev, - struct device_attribute *attr, char *buf) -{ - struct workqueue_struct *wq = dev_to_wq(dev); - - return scnprintf(buf, PAGE_SIZE, "%d\n", wq->saved_max_active); -} - -static ssize_t max_active_store(struct device *dev, - struct device_attribute *attr, const char *buf, - size_t count) -{ - struct workqueue_struct *wq = dev_to_wq(dev); - int val; - - if (sscanf(buf, "%d", &val) != 1 || val <= 0) - return -EINVAL; - - workqueue_set_max_active(wq, val); - return count; -} -static DEVICE_ATTR_RW(max_active); - -static struct attribute *wq_sysfs_attrs[] = { - &dev_attr_per_cpu.attr, - &dev_attr_max_active.attr, - NULL, -}; -ATTRIBUTE_GROUPS(wq_sysfs); - -static ssize_t wq_pool_ids_show(struct device *dev, - struct device_attribute *attr, char *buf) -{ - struct workqueue_struct *wq = dev_to_wq(dev); - const char *delim = ""; - int node, written = 0; - - rcu_read_lock_sched(); - for_each_node(node) { - written += scnprintf(buf + written, PAGE_SIZE - written, - "%s%d:%d", delim, node, - unbound_pwq_by_node(wq, node)->pool->id); - delim = " "; - } - written += scnprintf(buf + written, PAGE_SIZE - written, "\n"); - rcu_read_unlock_sched(); - - return written; -} - -static ssize_t wq_nice_show(struct device *dev, struct device_attribute *attr, - char *buf) -{ - struct workqueue_struct *wq = dev_to_wq(dev); - int written; - - mutex_lock(&wq->mutex); - written = scnprintf(buf, PAGE_SIZE, "%d\n", wq->unbound_attrs->nice); - mutex_unlock(&wq->mutex); - - return written; -} - -/* prepare workqueue_attrs for sysfs store operations */ -static struct workqueue_attrs *wq_sysfs_prep_attrs(struct workqueue_struct *wq) -{ - struct workqueue_attrs *attrs; - - attrs = alloc_workqueue_attrs(GFP_KERNEL); - if (!attrs) - return NULL; - - mutex_lock(&wq->mutex); - copy_workqueue_attrs(attrs, wq->unbound_attrs); - mutex_unlock(&wq->mutex); - return attrs; -} - -static ssize_t wq_nice_store(struct device *dev, struct device_attribute *attr, - const char *buf, size_t count) -{ - struct workqueue_struct *wq = dev_to_wq(dev); - struct workqueue_attrs *attrs; - int ret; - - attrs = wq_sysfs_prep_attrs(wq); - if (!attrs) - return -ENOMEM; - - if (sscanf(buf, "%d", &attrs->nice) == 1 && - attrs->nice >= MIN_NICE && attrs->nice <= MAX_NICE) - ret = apply_workqueue_attrs(wq, attrs); - else - ret = -EINVAL; - - free_workqueue_attrs(attrs); - return ret ?: count; -} - -static ssize_t wq_cpumask_show(struct device *dev, - struct device_attribute *attr, char *buf) -{ - struct workqueue_struct *wq = dev_to_wq(dev); - int written; - - mutex_lock(&wq->mutex); - written = scnprintf(buf, PAGE_SIZE, "%*pb\n", - cpumask_pr_args(wq->unbound_attrs->cpumask)); - mutex_unlock(&wq->mutex); - return written; -} - -static ssize_t wq_cpumask_store(struct device *dev, - struct device_attribute *attr, - const char *buf, size_t count) -{ - struct workqueue_struct *wq = dev_to_wq(dev); - struct workqueue_attrs *attrs; - int ret; - - attrs = wq_sysfs_prep_attrs(wq); - if (!attrs) - return -ENOMEM; - - ret = cpumask_parse(buf, attrs->cpumask); - if (!ret) - ret = apply_workqueue_attrs(wq, attrs); - - free_workqueue_attrs(attrs); - return ret ?: count; -} - -static ssize_t wq_numa_show(struct device *dev, struct device_attribute *attr, - char *buf) -{ - struct workqueue_struct *wq = dev_to_wq(dev); - int written; - - mutex_lock(&wq->mutex); - written = scnprintf(buf, PAGE_SIZE, "%d\n", - !wq->unbound_attrs->no_numa); - mutex_unlock(&wq->mutex); - - return written; -} - -static ssize_t wq_numa_store(struct device *dev, struct device_attribute *attr, - const char *buf, size_t count) -{ - struct workqueue_struct *wq = dev_to_wq(dev); - struct workqueue_attrs *attrs; - int v, ret; - - attrs = wq_sysfs_prep_attrs(wq); - if (!attrs) - return -ENOMEM; - - ret = -EINVAL; - if (sscanf(buf, "%d", &v) == 1) { - attrs->no_numa = !v; - ret = apply_workqueue_attrs(wq, attrs); - } - - free_workqueue_attrs(attrs); - return ret ?: count; -} - -static struct device_attribute wq_sysfs_unbound_attrs[] = { - __ATTR(pool_ids, 0444, wq_pool_ids_show, NULL), - __ATTR(nice, 0644, wq_nice_show, wq_nice_store), - __ATTR(cpumask, 0644, wq_cpumask_show, wq_cpumask_store), - __ATTR(numa, 0644, wq_numa_show, wq_numa_store), - __ATTR_NULL, -}; - -static struct bus_type wq_subsys = { - .name = "workqueue", - .dev_groups = wq_sysfs_groups, -}; - -static int __init wq_sysfs_init(void) -{ - return subsys_virtual_register(&wq_subsys, NULL); -} -core_initcall(wq_sysfs_init); - -static void wq_device_release(struct device *dev) -{ - struct wq_device *wq_dev = container_of(dev, struct wq_device, dev); - - kfree(wq_dev); -} - -/** - * workqueue_sysfs_register - make a workqueue visible in sysfs - * @wq: the workqueue to register - * - * Expose @wq in sysfs under /sys/bus/workqueue/devices. - * alloc_workqueue*() automatically calls this function if WQ_SYSFS is set - * which is the preferred method. - * - * Workqueue user should use this function directly iff it wants to apply - * workqueue_attrs before making the workqueue visible in sysfs; otherwise, - * apply_workqueue_attrs() may race against userland updating the - * attributes. - * - * Return: 0 on success, -errno on failure. - */ -int workqueue_sysfs_register(struct workqueue_struct *wq) -{ - struct wq_device *wq_dev; - int ret; - - /* - * Adjusting max_active or creating new pwqs by applyting - * attributes breaks ordering guarantee. Disallow exposing ordered - * workqueues. - */ - if (WARN_ON(wq->flags & __WQ_ORDERED)) - return -EINVAL; - - wq->wq_dev = wq_dev = kzalloc(sizeof(*wq_dev), GFP_KERNEL); - if (!wq_dev) - return -ENOMEM; - - wq_dev->wq = wq; - wq_dev->dev.bus = &wq_subsys; - wq_dev->dev.init_name = wq->name; - wq_dev->dev.release = wq_device_release; - - /* - * unbound_attrs are created separately. Suppress uevent until - * everything is ready. - */ - dev_set_uevent_suppress(&wq_dev->dev, true); - - ret = device_register(&wq_dev->dev); - if (ret) { - kfree(wq_dev); - wq->wq_dev = NULL; - return ret; - } - - if (wq->flags & WQ_UNBOUND) { - struct device_attribute *attr; - - for (attr = wq_sysfs_unbound_attrs; attr->attr.name; attr++) { - ret = device_create_file(&wq_dev->dev, attr); - if (ret) { - device_unregister(&wq_dev->dev); - wq->wq_dev = NULL; - return ret; - } - } - } - - dev_set_uevent_suppress(&wq_dev->dev, false); - kobject_uevent(&wq_dev->dev.kobj, KOBJ_ADD); - return 0; -} - -/** - * workqueue_sysfs_unregister - undo workqueue_sysfs_register() - * @wq: the workqueue to unregister - * - * If @wq is registered to sysfs by workqueue_sysfs_register(), unregister. - */ -static void workqueue_sysfs_unregister(struct workqueue_struct *wq) -{ - struct wq_device *wq_dev = wq->wq_dev; - - if (!wq->wq_dev) - return; - - wq->wq_dev = NULL; - device_unregister(&wq_dev->dev); -} -#else /* CONFIG_SYSFS */ -static void workqueue_sysfs_unregister(struct workqueue_struct *wq) { } -#endif /* CONFIG_SYSFS */ - /** * free_workqueue_attrs - free a workqueue_attrs * @attrs: workqueue_attrs to free @@ -3424,6 +3120,20 @@ static int init_worker_pool(struct worker_pool *pool) return 0; } +static void rcu_free_wq(struct rcu_head *rcu) +{ + struct workqueue_struct *wq = + container_of(rcu, struct workqueue_struct, rcu); + + if (!(wq->flags & WQ_UNBOUND)) + free_percpu(wq->cpu_pwqs); + else + free_workqueue_attrs(wq->unbound_attrs); + + kfree(wq->rescuer); + kfree(wq); +} + static void rcu_free_pool(struct rcu_head *rcu) { struct worker_pool *pool = container_of(rcu, struct worker_pool, rcu); @@ -3601,12 +3311,10 @@ static void pwq_unbound_release_workfn(struct work_struct *work) /* * If we're the last pwq going away, @wq is already dead and no one - * is gonna access it anymore. Free it. + * is gonna access it anymore. Schedule RCU free. */ - if (is_last) { - free_workqueue_attrs(wq->unbound_attrs); - kfree(wq); - } + if (is_last) + call_rcu_sched(&wq->rcu, rcu_free_wq); } /** @@ -4143,7 +3851,7 @@ struct workqueue_struct *__alloc_workqueue_key(const char *fmt, pwq_adjust_max_active(pwq); mutex_unlock(&wq->mutex); - list_add(&wq->list, &workqueues); + list_add_tail_rcu(&wq->list, &workqueues); mutex_unlock(&wq_pool_mutex); @@ -4199,24 +3907,20 @@ void destroy_workqueue(struct workqueue_struct *wq) * flushing is complete in case freeze races us. */ mutex_lock(&wq_pool_mutex); - list_del_init(&wq->list); + list_del_rcu(&wq->list); mutex_unlock(&wq_pool_mutex); workqueue_sysfs_unregister(wq); - if (wq->rescuer) { + if (wq->rescuer) kthread_stop(wq->rescuer->task); - kfree(wq->rescuer); - wq->rescuer = NULL; - } if (!(wq->flags & WQ_UNBOUND)) { /* * The base ref is never dropped on per-cpu pwqs. Directly - * free the pwqs and wq. + * schedule RCU free. */ - free_percpu(wq->cpu_pwqs); - kfree(wq); + call_rcu_sched(&wq->rcu, rcu_free_wq); } else { /* * We're the sole accessor of @wq at this point. Directly @@ -4437,6 +4141,166 @@ void print_worker_info(const char *log_lvl, struct task_struct *task) } } +static void pr_cont_pool_info(struct worker_pool *pool) +{ + pr_cont(" cpus=%*pbl", nr_cpumask_bits, pool->attrs->cpumask); + if (pool->node != NUMA_NO_NODE) + pr_cont(" node=%d", pool->node); + pr_cont(" flags=0x%x nice=%d", pool->flags, pool->attrs->nice); +} + +static void pr_cont_work(bool comma, struct work_struct *work) +{ + if (work->func == wq_barrier_func) { + struct wq_barrier *barr; + + barr = container_of(work, struct wq_barrier, work); + + pr_cont("%s BAR(%d)", comma ? "," : "", + task_pid_nr(barr->task)); + } else { + pr_cont("%s %pf", comma ? "," : "", work->func); + } +} + +static void show_pwq(struct pool_workqueue *pwq) +{ + struct worker_pool *pool = pwq->pool; + struct work_struct *work; + struct worker *worker; + bool has_in_flight = false, has_pending = false; + int bkt; + + pr_info(" pwq %d:", pool->id); + pr_cont_pool_info(pool); + + pr_cont(" active=%d/%d%s\n", pwq->nr_active, pwq->max_active, + !list_empty(&pwq->mayday_node) ? " MAYDAY" : ""); + + hash_for_each(pool->busy_hash, bkt, worker, hentry) { + if (worker->current_pwq == pwq) { + has_in_flight = true; + break; + } + } + if (has_in_flight) { + bool comma = false; + + pr_info(" in-flight:"); + hash_for_each(pool->busy_hash, bkt, worker, hentry) { + if (worker->current_pwq != pwq) + continue; + + pr_cont("%s %d%s:%pf", comma ? "," : "", + task_pid_nr(worker->task), + worker == pwq->wq->rescuer ? "(RESCUER)" : "", + worker->current_func); + list_for_each_entry(work, &worker->scheduled, entry) + pr_cont_work(false, work); + comma = true; + } + pr_cont("\n"); + } + + list_for_each_entry(work, &pool->worklist, entry) { + if (get_work_pwq(work) == pwq) { + has_pending = true; + break; + } + } + if (has_pending) { + bool comma = false; + + pr_info(" pending:"); + list_for_each_entry(work, &pool->worklist, entry) { + if (get_work_pwq(work) != pwq) + continue; + + pr_cont_work(comma, work); + comma = !(*work_data_bits(work) & WORK_STRUCT_LINKED); + } + pr_cont("\n"); + } + + if (!list_empty(&pwq->delayed_works)) { + bool comma = false; + + pr_info(" delayed:"); + list_for_each_entry(work, &pwq->delayed_works, entry) { + pr_cont_work(comma, work); + comma = !(*work_data_bits(work) & WORK_STRUCT_LINKED); + } + pr_cont("\n"); + } +} + +/** + * show_workqueue_state - dump workqueue state + * + * Called from a sysrq handler and prints out all busy workqueues and + * pools. + */ +void show_workqueue_state(void) +{ + struct workqueue_struct *wq; + struct worker_pool *pool; + unsigned long flags; + int pi; + + rcu_read_lock_sched(); + + pr_info("Showing busy workqueues and worker pools:\n"); + + list_for_each_entry_rcu(wq, &workqueues, list) { + struct pool_workqueue *pwq; + bool idle = true; + + for_each_pwq(pwq, wq) { + if (pwq->nr_active || !list_empty(&pwq->delayed_works)) { + idle = false; + break; + } + } + if (idle) + continue; + + pr_info("workqueue %s: flags=0x%x\n", wq->name, wq->flags); + + for_each_pwq(pwq, wq) { + spin_lock_irqsave(&pwq->pool->lock, flags); + if (pwq->nr_active || !list_empty(&pwq->delayed_works)) + show_pwq(pwq); + spin_unlock_irqrestore(&pwq->pool->lock, flags); + } + } + + for_each_pool(pool, pi) { + struct worker *worker; + bool first = true; + + spin_lock_irqsave(&pool->lock, flags); + if (pool->nr_workers == pool->nr_idle) + goto next_pool; + + pr_info("pool %d:", pool->id); + pr_cont_pool_info(pool); + pr_cont(" workers=%d", pool->nr_workers); + if (pool->manager) + pr_cont(" manager: %d", + task_pid_nr(pool->manager->task)); + list_for_each_entry(worker, &pool->idle_list, entry) { + pr_cont(" %s%d", first ? "idle: " : "", + task_pid_nr(worker->task)); + first = false; + } + pr_cont("\n"); + next_pool: + spin_unlock_irqrestore(&pool->lock, flags); + } + + rcu_read_unlock_sched(); +} + /* * CPU hotplug. * @@ -4834,6 +4698,323 @@ out_unlock: } #endif /* CONFIG_FREEZER */ +#ifdef CONFIG_SYSFS +/* + * Workqueues with WQ_SYSFS flag set is visible to userland via + * /sys/bus/workqueue/devices/WQ_NAME. All visible workqueues have the + * following attributes. + * + * per_cpu RO bool : whether the workqueue is per-cpu or unbound + * max_active RW int : maximum number of in-flight work items + * + * Unbound workqueues have the following extra attributes. + * + * id RO int : the associated pool ID + * nice RW int : nice value of the workers + * cpumask RW mask : bitmask of allowed CPUs for the workers + */ +struct wq_device { + struct workqueue_struct *wq; + struct device dev; +}; + +static struct workqueue_struct *dev_to_wq(struct device *dev) +{ + struct wq_device *wq_dev = container_of(dev, struct wq_device, dev); + + return wq_dev->wq; +} + +static ssize_t per_cpu_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct workqueue_struct *wq = dev_to_wq(dev); + + return scnprintf(buf, PAGE_SIZE, "%d\n", (bool)!(wq->flags & WQ_UNBOUND)); +} +static DEVICE_ATTR_RO(per_cpu); + +static ssize_t max_active_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct workqueue_struct *wq = dev_to_wq(dev); + + return scnprintf(buf, PAGE_SIZE, "%d\n", wq->saved_max_active); +} + +static ssize_t max_active_store(struct device *dev, + struct device_attribute *attr, const char *buf, + size_t count) +{ + struct workqueue_struct *wq = dev_to_wq(dev); + int val; + + if (sscanf(buf, "%d", &val) != 1 || val <= 0) + return -EINVAL; + + workqueue_set_max_active(wq, val); + return count; +} +static DEVICE_ATTR_RW(max_active); + +static struct attribute *wq_sysfs_attrs[] = { + &dev_attr_per_cpu.attr, + &dev_attr_max_active.attr, + NULL, +}; +ATTRIBUTE_GROUPS(wq_sysfs); + +static ssize_t wq_pool_ids_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct workqueue_struct *wq = dev_to_wq(dev); + const char *delim = ""; + int node, written = 0; + + rcu_read_lock_sched(); + for_each_node(node) { + written += scnprintf(buf + written, PAGE_SIZE - written, + "%s%d:%d", delim, node, + unbound_pwq_by_node(wq, node)->pool->id); + delim = " "; + } + written += scnprintf(buf + written, PAGE_SIZE - written, "\n"); + rcu_read_unlock_sched(); + + return written; +} + +static ssize_t wq_nice_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct workqueue_struct *wq = dev_to_wq(dev); + int written; + + mutex_lock(&wq->mutex); + written = scnprintf(buf, PAGE_SIZE, "%d\n", wq->unbound_attrs->nice); + mutex_unlock(&wq->mutex); + + return written; +} + +/* prepare workqueue_attrs for sysfs store operations */ +static struct workqueue_attrs *wq_sysfs_prep_attrs(struct workqueue_struct *wq) +{ + struct workqueue_attrs *attrs; + + attrs = alloc_workqueue_attrs(GFP_KERNEL); + if (!attrs) + return NULL; + + mutex_lock(&wq->mutex); + copy_workqueue_attrs(attrs, wq->unbound_attrs); + mutex_unlock(&wq->mutex); + return attrs; +} + +static ssize_t wq_nice_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) +{ + struct workqueue_struct *wq = dev_to_wq(dev); + struct workqueue_attrs *attrs; + int ret; + + attrs = wq_sysfs_prep_attrs(wq); + if (!attrs) + return -ENOMEM; + + if (sscanf(buf, "%d", &attrs->nice) == 1 && + attrs->nice >= MIN_NICE && attrs->nice <= MAX_NICE) + ret = apply_workqueue_attrs(wq, attrs); + else + ret = -EINVAL; + + free_workqueue_attrs(attrs); + return ret ?: count; +} + +static ssize_t wq_cpumask_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct workqueue_struct *wq = dev_to_wq(dev); + int written; + + mutex_lock(&wq->mutex); + written = scnprintf(buf, PAGE_SIZE, "%*pb\n", + cpumask_pr_args(wq->unbound_attrs->cpumask)); + mutex_unlock(&wq->mutex); + return written; +} + +static ssize_t wq_cpumask_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct workqueue_struct *wq = dev_to_wq(dev); + struct workqueue_attrs *attrs; + int ret; + + attrs = wq_sysfs_prep_attrs(wq); + if (!attrs) + return -ENOMEM; + + ret = cpumask_parse(buf, attrs->cpumask); + if (!ret) + ret = apply_workqueue_attrs(wq, attrs); + + free_workqueue_attrs(attrs); + return ret ?: count; +} + +static ssize_t wq_numa_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct workqueue_struct *wq = dev_to_wq(dev); + int written; + + mutex_lock(&wq->mutex); + written = scnprintf(buf, PAGE_SIZE, "%d\n", + !wq->unbound_attrs->no_numa); + mutex_unlock(&wq->mutex); + + return written; +} + +static ssize_t wq_numa_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) +{ + struct workqueue_struct *wq = dev_to_wq(dev); + struct workqueue_attrs *attrs; + int v, ret; + + attrs = wq_sysfs_prep_attrs(wq); + if (!attrs) + return -ENOMEM; + + ret = -EINVAL; + if (sscanf(buf, "%d", &v) == 1) { + attrs->no_numa = !v; + ret = apply_workqueue_attrs(wq, attrs); + } + + free_workqueue_attrs(attrs); + return ret ?: count; +} + +static struct device_attribute wq_sysfs_unbound_attrs[] = { + __ATTR(pool_ids, 0444, wq_pool_ids_show, NULL), + __ATTR(nice, 0644, wq_nice_show, wq_nice_store), + __ATTR(cpumask, 0644, wq_cpumask_show, wq_cpumask_store), + __ATTR(numa, 0644, wq_numa_show, wq_numa_store), + __ATTR_NULL, +}; + +static struct bus_type wq_subsys = { + .name = "workqueue", + .dev_groups = wq_sysfs_groups, +}; + +static int __init wq_sysfs_init(void) +{ + return subsys_virtual_register(&wq_subsys, NULL); +} +core_initcall(wq_sysfs_init); + +static void wq_device_release(struct device *dev) +{ + struct wq_device *wq_dev = container_of(dev, struct wq_device, dev); + + kfree(wq_dev); +} + +/** + * workqueue_sysfs_register - make a workqueue visible in sysfs + * @wq: the workqueue to register + * + * Expose @wq in sysfs under /sys/bus/workqueue/devices. + * alloc_workqueue*() automatically calls this function if WQ_SYSFS is set + * which is the preferred method. + * + * Workqueue user should use this function directly iff it wants to apply + * workqueue_attrs before making the workqueue visible in sysfs; otherwise, + * apply_workqueue_attrs() may race against userland updating the + * attributes. + * + * Return: 0 on success, -errno on failure. + */ +int workqueue_sysfs_register(struct workqueue_struct *wq) +{ + struct wq_device *wq_dev; + int ret; + + /* + * Adjusting max_active or creating new pwqs by applyting + * attributes breaks ordering guarantee. Disallow exposing ordered + * workqueues. + */ + if (WARN_ON(wq->flags & __WQ_ORDERED)) + return -EINVAL; + + wq->wq_dev = wq_dev = kzalloc(sizeof(*wq_dev), GFP_KERNEL); + if (!wq_dev) + return -ENOMEM; + + wq_dev->wq = wq; + wq_dev->dev.bus = &wq_subsys; + wq_dev->dev.init_name = wq->name; + wq_dev->dev.release = wq_device_release; + + /* + * unbound_attrs are created separately. Suppress uevent until + * everything is ready. + */ + dev_set_uevent_suppress(&wq_dev->dev, true); + + ret = device_register(&wq_dev->dev); + if (ret) { + kfree(wq_dev); + wq->wq_dev = NULL; + return ret; + } + + if (wq->flags & WQ_UNBOUND) { + struct device_attribute *attr; + + for (attr = wq_sysfs_unbound_attrs; attr->attr.name; attr++) { + ret = device_create_file(&wq_dev->dev, attr); + if (ret) { + device_unregister(&wq_dev->dev); + wq->wq_dev = NULL; + return ret; + } + } + } + + dev_set_uevent_suppress(&wq_dev->dev, false); + kobject_uevent(&wq_dev->dev.kobj, KOBJ_ADD); + return 0; +} + +/** + * workqueue_sysfs_unregister - undo workqueue_sysfs_register() + * @wq: the workqueue to unregister + * + * If @wq is registered to sysfs by workqueue_sysfs_register(), unregister. + */ +static void workqueue_sysfs_unregister(struct workqueue_struct *wq) +{ + struct wq_device *wq_dev = wq->wq_dev; + + if (!wq->wq_dev) + return; + + wq->wq_dev = NULL; + device_unregister(&wq_dev->dev); +} +#else /* CONFIG_SYSFS */ +static void workqueue_sysfs_unregister(struct workqueue_struct *wq) { } +#endif /* CONFIG_SYSFS */ + static void __init wq_numa_init(void) { cpumask_var_t *tbl; |