diff options
Diffstat (limited to 'kernel')
76 files changed, 3443 insertions, 2220 deletions
diff --git a/kernel/Makefile b/kernel/Makefile index 271fd3119af9..35ef1185e359 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -2,14 +2,14 @@ # Makefile for the linux kernel. # -obj-y = fork.o exec_domain.o panic.o printk.o \ +obj-y = fork.o exec_domain.o panic.o \ cpu.o exit.o itimer.o time.o softirq.o resource.o \ sysctl.o sysctl_binary.o capability.o ptrace.o timer.o user.o \ signal.o sys.o kmod.o workqueue.o pid.o task_work.o \ rcupdate.o extable.o params.o posix-timers.o \ kthread.o wait.o sys_ni.o posix-cpu-timers.o mutex.o \ hrtimer.o rwsem.o nsproxy.o srcu.o semaphore.o \ - notifier.o ksysfs.o cred.o \ + notifier.o ksysfs.o cred.o reboot.o \ async.o range.o groups.o lglock.o smpboot.o ifdef CONFIG_FUNCTION_TRACER @@ -24,6 +24,7 @@ endif obj-y += sched/ obj-y += power/ +obj-y += printk/ obj-y += cpu/ obj-$(CONFIG_CHECKPOINT_RESTORE) += kcmp.o diff --git a/kernel/audit.h b/kernel/audit.h index 1c95131ef760..123c9b7c3979 100644 --- a/kernel/audit.h +++ b/kernel/audit.h @@ -85,6 +85,7 @@ struct audit_names { struct filename *name; int name_len; /* number of chars to log */ + bool hidden; /* don't log this record */ bool name_put; /* call __putname()? */ unsigned long ino; diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c index 6bd4a90d1991..f7aee8be7fb2 100644 --- a/kernel/auditfilter.c +++ b/kernel/auditfilter.c @@ -423,7 +423,7 @@ static struct audit_entry *audit_data_to_entry(struct audit_rule_data *data, f->lsm_rule = NULL; /* Support legacy tests for a valid loginuid */ - if ((f->type == AUDIT_LOGINUID) && (f->val == 4294967295)) { + if ((f->type == AUDIT_LOGINUID) && (f->val == ~0U)) { f->type = AUDIT_LOGINUID_SET; f->val = 0; } @@ -865,6 +865,12 @@ static inline int audit_add_rule(struct audit_entry *entry) err = audit_add_watch(&entry->rule, &list); if (err) { mutex_unlock(&audit_filter_mutex); + /* + * normally audit_add_tree_rule() will free it + * on failure + */ + if (tree) + audit_put_tree(tree); goto error; } } diff --git a/kernel/auditsc.c b/kernel/auditsc.c index 3c8a601324a2..9845cb32b60a 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -1399,8 +1399,11 @@ static void audit_log_exit(struct audit_context *context, struct task_struct *ts } i = 0; - list_for_each_entry(n, &context->names_list, list) + list_for_each_entry(n, &context->names_list, list) { + if (n->hidden) + continue; audit_log_name(context, n, NULL, i++, &call_panic); + } /* Send end of event record to help user space know we are finished */ ab = audit_log_start(context, GFP_KERNEL, AUDIT_EOE); @@ -1769,14 +1772,15 @@ void audit_putname(struct filename *name) * __audit_inode - store the inode and device from a lookup * @name: name being audited * @dentry: dentry being audited - * @parent: does this dentry represent the parent? + * @flags: attributes for this particular entry */ void __audit_inode(struct filename *name, const struct dentry *dentry, - unsigned int parent) + unsigned int flags) { struct audit_context *context = current->audit_context; const struct inode *inode = dentry->d_inode; struct audit_names *n; + bool parent = flags & AUDIT_INODE_PARENT; if (!context->in_syscall) return; @@ -1831,6 +1835,8 @@ out: if (parent) { n->name_len = n->name ? parent_len(n->name->name) : AUDIT_NAME_FULL; n->type = AUDIT_TYPE_PARENT; + if (flags & AUDIT_INODE_HIDDEN) + n->hidden = true; } else { n->name_len = AUDIT_NAME_FULL; n->type = AUDIT_TYPE_NORMAL; diff --git a/kernel/cgroup.c b/kernel/cgroup.c index e5583d10a325..781845a013ab 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -802,7 +802,6 @@ static struct cgroup *task_cgroup_from_root(struct task_struct *task, */ static int cgroup_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode); -static struct dentry *cgroup_lookup(struct inode *, struct dentry *, unsigned int); static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry); static int cgroup_populate_dir(struct cgroup *cgrp, bool base_files, unsigned long subsys_mask); @@ -1846,36 +1845,43 @@ out: EXPORT_SYMBOL_GPL(cgroup_path); /** - * task_cgroup_path_from_hierarchy - cgroup path of a task on a hierarchy + * task_cgroup_path - cgroup path of a task in the first cgroup hierarchy * @task: target task - * @hierarchy_id: the hierarchy to look up @task's cgroup from * @buf: the buffer to write the path into * @buflen: the length of the buffer * - * Determine @task's cgroup on the hierarchy specified by @hierarchy_id and - * copy its path into @buf. This function grabs cgroup_mutex and shouldn't - * be used inside locks used by cgroup controller callbacks. + * Determine @task's cgroup on the first (the one with the lowest non-zero + * hierarchy_id) cgroup hierarchy and copy its path into @buf. This + * function grabs cgroup_mutex and shouldn't be used inside locks used by + * cgroup controller callbacks. + * + * Returns 0 on success, fails with -%ENAMETOOLONG if @buflen is too short. */ -int task_cgroup_path_from_hierarchy(struct task_struct *task, int hierarchy_id, - char *buf, size_t buflen) +int task_cgroup_path(struct task_struct *task, char *buf, size_t buflen) { struct cgroupfs_root *root; - struct cgroup *cgrp = NULL; - int ret = -ENOENT; + struct cgroup *cgrp; + int hierarchy_id = 1, ret = 0; + + if (buflen < 2) + return -ENAMETOOLONG; mutex_lock(&cgroup_mutex); - root = idr_find(&cgroup_hierarchy_idr, hierarchy_id); + root = idr_get_next(&cgroup_hierarchy_idr, &hierarchy_id); + if (root) { cgrp = task_cgroup_from_root(task, root); ret = cgroup_path(cgrp, buf, buflen); + } else { + /* if no hierarchy exists, everyone is in "/" */ + memcpy(buf, "/", 2); } mutex_unlock(&cgroup_mutex); - return ret; } -EXPORT_SYMBOL_GPL(task_cgroup_path_from_hierarchy); +EXPORT_SYMBOL_GPL(task_cgroup_path); /* * Control Group taskset @@ -2642,7 +2648,7 @@ static const struct inode_operations cgroup_file_inode_operations = { }; static const struct inode_operations cgroup_dir_inode_operations = { - .lookup = cgroup_lookup, + .lookup = simple_lookup, .mkdir = cgroup_mkdir, .rmdir = cgroup_rmdir, .rename = cgroup_rename, @@ -2652,14 +2658,6 @@ static const struct inode_operations cgroup_dir_inode_operations = { .removexattr = cgroup_removexattr, }; -static struct dentry *cgroup_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) -{ - if (dentry->d_name.len > NAME_MAX) - return ERR_PTR(-ENAMETOOLONG); - d_add(dentry, NULL); - return NULL; -} - /* * Check if a file is a control file */ @@ -4337,8 +4335,10 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry, } err = percpu_ref_init(&css->refcnt, css_release); - if (err) + if (err) { + ss->css_free(cgrp); goto err_free_all; + } init_cgroup_css(css, ss, cgrp); diff --git a/kernel/cpu.c b/kernel/cpu.c index 198a38883e64..b2b227b82123 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -366,7 +366,7 @@ EXPORT_SYMBOL(cpu_down); #endif /*CONFIG_HOTPLUG_CPU*/ /* Requires cpu_add_remove_lock to be held */ -static int __cpuinit _cpu_up(unsigned int cpu, int tasks_frozen) +static int _cpu_up(unsigned int cpu, int tasks_frozen) { int ret, nr_calls = 0; void *hcpu = (void *)(long)cpu; @@ -419,7 +419,7 @@ out: return ret; } -int __cpuinit cpu_up(unsigned int cpu) +int cpu_up(unsigned int cpu) { int err = 0; @@ -618,7 +618,7 @@ core_initcall(cpu_hotplug_pm_sync_init); * It must be called by the arch code on the new cpu, before the new cpu * enables interrupts and before the "boot" cpu returns from __cpu_up(). */ -void __cpuinit notify_cpu_starting(unsigned int cpu) +void notify_cpu_starting(unsigned int cpu) { unsigned long val = CPU_STARTING; diff --git a/kernel/events/core.c b/kernel/events/core.c index 1db3af933704..f86599e8c123 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -182,7 +182,7 @@ void update_perf_cpu_limits(void) u64 tmp = perf_sample_period_ns; tmp *= sysctl_perf_cpu_time_max_percent; - tmp = do_div(tmp, 100); + do_div(tmp, 100); atomic_set(&perf_sample_allowed_ns, tmp); } @@ -232,7 +232,7 @@ DEFINE_PER_CPU(u64, running_sample_length); void perf_sample_event_took(u64 sample_len_ns) { u64 avg_local_sample_len; - u64 local_samples_len = __get_cpu_var(running_sample_length); + u64 local_samples_len; if (atomic_read(&perf_sample_allowed_ns) == 0) return; @@ -947,8 +947,18 @@ perf_lock_task_context(struct task_struct *task, int ctxn, unsigned long *flags) { struct perf_event_context *ctx; - rcu_read_lock(); retry: + /* + * One of the few rules of preemptible RCU is that one cannot do + * rcu_read_unlock() while holding a scheduler (or nested) lock when + * part of the read side critical section was preemptible -- see + * rcu_read_unlock_special(). + * + * Since ctx->lock nests under rq->lock we must ensure the entire read + * side critical section is non-preemptible. + */ + preempt_disable(); + rcu_read_lock(); ctx = rcu_dereference(task->perf_event_ctxp[ctxn]); if (ctx) { /* @@ -964,6 +974,8 @@ retry: raw_spin_lock_irqsave(&ctx->lock, *flags); if (ctx != rcu_dereference(task->perf_event_ctxp[ctxn])) { raw_spin_unlock_irqrestore(&ctx->lock, *flags); + rcu_read_unlock(); + preempt_enable(); goto retry; } @@ -973,6 +985,7 @@ retry: } } rcu_read_unlock(); + preempt_enable(); return ctx; } @@ -1950,7 +1963,16 @@ static int __perf_event_enable(void *info) struct perf_cpu_context *cpuctx = __get_cpu_context(ctx); int err; - if (WARN_ON_ONCE(!ctx->is_active)) + /* + * There's a time window between 'ctx->is_active' check + * in perf_event_enable function and this place having: + * - IRQs on + * - ctx->lock unlocked + * + * where the task could be killed and 'ctx' deactivated + * by perf_event_exit_task. + */ + if (!ctx->is_active) return -EINVAL; raw_spin_lock(&ctx->lock); @@ -6212,8 +6234,6 @@ perf_event_mux_interval_ms_store(struct device *dev, return count; } -#define __ATTR_RW(attr) __ATTR(attr, 0644, attr##_show, attr##_store) - static struct device_attribute pmu_dev_attrs[] = { __ATTR_RO(type), __ATTR_RW(perf_event_mux_interval_ms), @@ -7465,7 +7485,7 @@ inherit_task_group(struct perf_event *event, struct task_struct *parent, * child. */ - child_ctx = alloc_perf_context(event->pmu, child); + child_ctx = alloc_perf_context(parent_ctx->pmu, child); if (!child_ctx) return -ENOMEM; @@ -7608,7 +7628,7 @@ static void __init perf_event_init_all_cpus(void) } } -static void __cpuinit perf_event_init_cpu(int cpu) +static void perf_event_init_cpu(int cpu) { struct swevent_htable *swhash = &per_cpu(swevent_htable, cpu); @@ -7697,7 +7717,7 @@ static struct notifier_block perf_reboot_notifier = { .priority = INT_MIN, }; -static int __cpuinit +static int perf_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu) { unsigned int cpu = (long)hcpu; diff --git a/kernel/exit.c b/kernel/exit.c index fafe75d9e6f6..a949819055d5 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -808,7 +808,7 @@ void do_exit(long code) /* * FIXME: do that only when needed, using sched_exit tracepoint */ - ptrace_put_breakpoints(tsk); + flush_ptrace_hw_breakpoint(tsk); exit_notify(tsk, group_dead); #ifdef CONFIG_NUMA diff --git a/kernel/fork.c b/kernel/fork.c index 6e6a1c11b3e5..403d2bb8a968 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -365,8 +365,6 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm) mm->locked_vm = 0; mm->mmap = NULL; mm->mmap_cache = NULL; - mm->free_area_cache = oldmm->mmap_base; - mm->cached_hole_size = ~0UL; mm->map_count = 0; cpumask_clear(mm_cpumask(mm)); mm->mm_rb = RB_ROOT; @@ -540,8 +538,6 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p) mm->nr_ptes = 0; memset(&mm->rss_stat, 0, sizeof(mm->rss_stat)); spin_lock_init(&mm->page_table_lock); - mm->free_area_cache = TASK_UNMAPPED_BASE; - mm->cached_hole_size = ~0UL; mm_init_aio(mm); mm_init_owner(mm, p); @@ -1550,7 +1546,7 @@ static inline void init_idle_pids(struct pid_link *links) } } -struct task_struct * __cpuinit fork_idle(int cpu) +struct task_struct *fork_idle(int cpu) { struct task_struct *task; task = copy_process(CLONE_VM, 0, 0, NULL, &init_struct_pid, 0); diff --git a/kernel/freezer.c b/kernel/freezer.c index 8b2afc1c9df0..b462fa197517 100644 --- a/kernel/freezer.c +++ b/kernel/freezer.c @@ -33,7 +33,7 @@ static DEFINE_SPINLOCK(freezer_lock); */ bool freezing_slow_path(struct task_struct *p) { - if (p->flags & PF_NOFREEZE) + if (p->flags & (PF_NOFREEZE | PF_SUSPEND_TASK)) return false; if (pm_nosig_freezing || cgroup_freezing(p)) diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c index 3ee4d06c6fc2..383319bae3f7 100644 --- a/kernel/hrtimer.c +++ b/kernel/hrtimer.c @@ -722,17 +722,20 @@ static int hrtimer_switch_to_hres(void) return 1; } +static void clock_was_set_work(struct work_struct *work) +{ + clock_was_set(); +} + +static DECLARE_WORK(hrtimer_work, clock_was_set_work); + /* - * Called from timekeeping code to reprogramm the hrtimer interrupt - * device. If called from the timer interrupt context we defer it to - * softirq context. + * Called from timekeeping and resume code to reprogramm the hrtimer + * interrupt device on all cpus. */ void clock_was_set_delayed(void) { - struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases); - - cpu_base->clock_was_set = 1; - __raise_softirq_irqoff(HRTIMER_SOFTIRQ); + schedule_work(&hrtimer_work); } #else @@ -774,15 +777,19 @@ void clock_was_set(void) /* * During resume we might have to reprogram the high resolution timer - * interrupt (on the local CPU): + * interrupt on all online CPUs. However, all other CPUs will be + * stopped with IRQs interrupts disabled so the clock_was_set() call + * must be deferred. */ void hrtimers_resume(void) { WARN_ONCE(!irqs_disabled(), KERN_INFO "hrtimers_resume() called with IRQs enabled!"); + /* Retrigger on the local CPU */ retrigger_next_event(NULL); - timerfd_clock_was_set(); + /* And schedule a retrigger for all others */ + clock_was_set_delayed(); } static inline void timer_stats_hrtimer_set_start_info(struct hrtimer *timer) @@ -1433,13 +1440,6 @@ void hrtimer_peek_ahead_timers(void) static void run_hrtimer_softirq(struct softirq_action *h) { - struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases); - - if (cpu_base->clock_was_set) { - cpu_base->clock_was_set = 0; - clock_was_set(); - } - hrtimer_peek_ahead_timers(); } @@ -1659,7 +1659,7 @@ SYSCALL_DEFINE2(nanosleep, struct timespec __user *, rqtp, /* * Functions related to boot-time initialization: */ -static void __cpuinit init_hrtimers_cpu(int cpu) +static void init_hrtimers_cpu(int cpu) { struct hrtimer_cpu_base *cpu_base = &per_cpu(hrtimer_bases, cpu); int i; @@ -1740,7 +1740,7 @@ static void migrate_hrtimers(int scpu) #endif /* CONFIG_HOTPLUG_CPU */ -static int __cpuinit hrtimer_cpu_notify(struct notifier_block *self, +static int hrtimer_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu) { int scpu = (long)hcpu; @@ -1773,7 +1773,7 @@ static int __cpuinit hrtimer_cpu_notify(struct notifier_block *self, return NOTIFY_OK; } -static struct notifier_block __cpuinitdata hrtimers_nb = { +static struct notifier_block hrtimers_nb = { .notifier_call = hrtimer_cpu_notify, }; diff --git a/kernel/irq/generic-chip.c b/kernel/irq/generic-chip.c index 1c39eccc1eaf..452d6f2ba21d 100644 --- a/kernel/irq/generic-chip.c +++ b/kernel/irq/generic-chip.c @@ -135,7 +135,7 @@ void irq_gc_ack_clr_bit(struct irq_data *d) } /** - * irq_gc_mask_disable_reg_and_ack- Mask and ack pending interrupt + * irq_gc_mask_disable_reg_and_ack - Mask and ack pending interrupt * @d: irq_data */ void irq_gc_mask_disable_reg_and_ack(struct irq_data *d) @@ -275,10 +275,7 @@ int irq_alloc_domain_generic_chips(struct irq_domain *d, int irqs_per_chip, if (d->gc) return -EBUSY; - if (d->revmap_type != IRQ_DOMAIN_MAP_LINEAR) - return -EINVAL; - - numchips = d->revmap_data.linear.size / irqs_per_chip; + numchips = DIV_ROUND_UP(d->revmap_size, irqs_per_chip); if (!numchips) return -EINVAL; @@ -310,6 +307,7 @@ int irq_alloc_domain_generic_chips(struct irq_domain *d, int irqs_per_chip, /* Calc pointer to the next generic chip */ tmp += sizeof(*gc) + num_ct * sizeof(struct irq_chip_type); } + d->name = name; return 0; } EXPORT_SYMBOL_GPL(irq_alloc_domain_generic_chips); diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c index 1ed8dff17eb9..706724e9835d 100644 --- a/kernel/irq/irqdomain.c +++ b/kernel/irq/irqdomain.c @@ -23,9 +23,11 @@ static DEFINE_MUTEX(revmap_trees_mutex); static struct irq_domain *irq_default_domain; /** - * irq_domain_alloc() - Allocate a new irq_domain data structure + * __irq_domain_add() - Allocate a new irq_domain data structure * @of_node: optional device-tree node of the interrupt controller - * @revmap_type: type of reverse mapping to use + * @size: Size of linear map; 0 for radix mapping only + * @direct_max: Maximum value of direct maps; Use ~0 for no limit; 0 for no + * direct mapping * @ops: map/unmap domain callbacks * @host_data: Controller private data pointer * @@ -33,41 +35,35 @@ static struct irq_domain *irq_default_domain; * register allocated irq_domain with irq_domain_register(). Returns pointer * to IRQ domain, or NULL on failure. */ -static struct irq_domain *irq_domain_alloc(struct device_node *of_node, - unsigned int revmap_type, - const struct irq_domain_ops *ops, - void *host_data) +struct irq_domain *__irq_domain_add(struct device_node *of_node, int size, + irq_hw_number_t hwirq_max, int direct_max, + const struct irq_domain_ops *ops, + void *host_data) { struct irq_domain *domain; - domain = kzalloc_node(sizeof(*domain), GFP_KERNEL, - of_node_to_nid(of_node)); + domain = kzalloc_node(sizeof(*domain) + (sizeof(unsigned int) * size), + GFP_KERNEL, of_node_to_nid(of_node)); if (WARN_ON(!domain)) return NULL; /* Fill structure */ - domain->revmap_type = revmap_type; + INIT_RADIX_TREE(&domain->revmap_tree, GFP_KERNEL); domain->ops = ops; domain->host_data = host_data; domain->of_node = of_node_get(of_node); + domain->hwirq_max = hwirq_max; + domain->revmap_size = size; + domain->revmap_direct_max_irq = direct_max; - return domain; -} - -static void irq_domain_free(struct irq_domain *domain) -{ - of_node_put(domain->of_node); - kfree(domain); -} - -static void irq_domain_add(struct irq_domain *domain) -{ mutex_lock(&irq_domain_mutex); list_add(&domain->link, &irq_domain_list); mutex_unlock(&irq_domain_mutex); - pr_debug("Allocated domain of type %d @0x%p\n", - domain->revmap_type, domain); + + pr_debug("Added domain %s\n", domain->name); + return domain; } +EXPORT_SYMBOL_GPL(__irq_domain_add); /** * irq_domain_remove() - Remove an irq domain. @@ -81,29 +77,12 @@ void irq_domain_remove(struct irq_domain *domain) { mutex_lock(&irq_domain_mutex); - switch (domain->revmap_type) { - case IRQ_DOMAIN_MAP_LEGACY: - /* - * Legacy domains don't manage their own irq_desc - * allocations, we expect the caller to handle irq_desc - * freeing on their own. - */ - break; - case IRQ_DOMAIN_MAP_TREE: - /* - * radix_tree_delete() takes care of destroying the root - * node when all entries are removed. Shout if there are - * any mappings left. - */ - WARN_ON(domain->revmap_data.tree.height); - break; - case IRQ_DOMAIN_MAP_LINEAR: - kfree(domain->revmap_data.linear.revmap); - domain->revmap_data.linear.size = 0; - break; - case IRQ_DOMAIN_MAP_NOMAP: - break; - } + /* + * radix_tree_delete() takes care of destroying the root + * node when all entries are removed. Shout if there are + * any mappings left. + */ + WARN_ON(domain->revmap_tree.height); list_del(&domain->link); @@ -115,44 +94,30 @@ void irq_domain_remove(struct irq_domain *domain) mutex_unlock(&irq_domain_mutex); - pr_debug("Removed domain of type %d @0x%p\n", - domain->revmap_type, domain); + pr_debug("Removed domain %s\n", domain->name); - irq_domain_free(domain); + of_node_put(domain->of_node); + kfree(domain); } EXPORT_SYMBOL_GPL(irq_domain_remove); -static unsigned int irq_domain_legacy_revmap(struct irq_domain *domain, - irq_hw_number_t hwirq) -{ - irq_hw_number_t first_hwirq = domain->revmap_data.legacy.first_hwirq; - int size = domain->revmap_data.legacy.size; - - if (WARN_ON(hwirq < first_hwirq || hwirq >= first_hwirq + size)) - return 0; - return hwirq - first_hwirq + domain->revmap_data.legacy.first_irq; -} - /** - * irq_domain_add_simple() - Allocate and register a simple irq_domain. + * irq_domain_add_simple() - Register an irq_domain and optionally map a range of irqs * @of_node: pointer to interrupt controller's device tree node. * @size: total number of irqs in mapping * @first_irq: first number of irq block assigned to the domain, - * pass zero to assign irqs on-the-fly. This will result in a - * linear IRQ domain so it is important to use irq_create_mapping() - * for each used IRQ, especially when SPARSE_IRQ is enabled. + * pass zero to assign irqs on-the-fly. If first_irq is non-zero, then + * pre-map all of the irqs in the domain to virqs starting at first_irq. * @ops: map/unmap domain callbacks * @host_data: Controller private data pointer * - * Allocates a legacy irq_domain if irq_base is positive or a linear - * domain otherwise. For the legacy domain, IRQ descriptors will also - * be allocated. + * Allocates an irq_domain, and optionally if first_irq is positive then also + * allocate irq_descs and map all of the hwirqs to virqs starting at first_irq. * * This is intended to implement the expected behaviour for most - * interrupt controllers which is that a linear mapping should - * normally be used unless the system requires a legacy mapping in - * order to support supplying interrupt numbers during non-DT - * registration of devices. + * interrupt controllers. If device tree is used, then first_irq will be 0 and + * irqs get mapped dynamically on the fly. However, if the controller requires + * static virq assignments (non-DT boot) then it will set that up correctly. */ struct irq_domain *irq_domain_add_simple(struct device_node *of_node, unsigned int size, @@ -160,33 +125,25 @@ struct irq_domain *irq_domain_add_simple(struct device_node *of_node, const struct irq_domain_ops *ops, void *host_data) { - if (first_irq > 0) { - int irq_base; + struct irq_domain *domain; + + domain = __irq_domain_add(of_node, size, size, 0, ops, host_data); + if (!domain) + return NULL; + if (first_irq > 0) { if (IS_ENABLED(CONFIG_SPARSE_IRQ)) { - /* - * Set the descriptor allocator to search for a - * 1-to-1 mapping, such as irq_alloc_desc_at(). - * Use of_node_to_nid() which is defined to - * numa_node_id() on platforms that have no custom - * implementation. - */ - irq_base = irq_alloc_descs(first_irq, first_irq, size, - of_node_to_nid(of_node)); - if (irq_base < 0) { + /* attempt to allocated irq_descs */ + int rc = irq_alloc_descs(first_irq, first_irq, size, + of_node_to_nid(of_node)); + if (rc < 0) pr_info("Cannot allocate irq_descs @ IRQ%d, assuming pre-allocated\n", first_irq); - irq_base = first_irq; - } - } else - irq_base = first_irq; - - return irq_domain_add_legacy(of_node, size, irq_base, 0, - ops, host_data); + } + irq_domain_associate_many(domain, first_irq, 0, size); } - /* A linear domain is the default */ - return irq_domain_add_linear(of_node, size, ops, host_data); + return domain; } EXPORT_SYMBOL_GPL(irq_domain_add_simple); @@ -213,131 +170,19 @@ struct irq_domain *irq_domain_add_legacy(struct device_node *of_node, void *host_data) { struct irq_domain *domain; - unsigned int i; - domain = irq_domain_alloc(of_node, IRQ_DOMAIN_MAP_LEGACY, ops, host_data); + domain = __irq_domain_add(of_node, first_hwirq + size, + first_hwirq + size, 0, ops, host_data); if (!domain) return NULL; - domain->revmap_data.legacy.first_irq = first_irq; - domain->revmap_data.legacy.first_hwirq = first_hwirq; - domain->revmap_data.legacy.size = size; - - mutex_lock(&irq_domain_mutex); - /* Verify that all the irqs are available */ - for (i = 0; i < size; i++) { - int irq = first_irq + i; - struct irq_data *irq_data = irq_get_irq_data(irq); - - if (WARN_ON(!irq_data || irq_data->domain)) { - mutex_unlock(&irq_domain_mutex); - irq_domain_free(domain); - return NULL; - } - } - - /* Claim all of the irqs before registering a legacy domain */ - for (i = 0; i < size; i++) { - struct irq_data *irq_data = irq_get_irq_data(first_irq + i); - irq_data->hwirq = first_hwirq + i; - irq_data->domain = domain; - } - mutex_unlock(&irq_domain_mutex); - - for (i = 0; i < size; i++) { - int irq = first_irq + i; - int hwirq = first_hwirq + i; - - /* IRQ0 gets ignored */ - if (!irq) - continue; - - /* Legacy flags are left to default at this point, - * one can then use irq_create_mapping() to - * explicitly change them - */ - if (ops->map) - ops->map(domain, irq, hwirq); - - /* Clear norequest flags */ - irq_clear_status_flags(irq, IRQ_NOREQUEST); - } + irq_domain_associate_many(domain, first_irq, first_hwirq, size); - irq_domain_add(domain); return domain; } EXPORT_SYMBOL_GPL(irq_domain_add_legacy); /** - * irq_domain_add_linear() - Allocate and register a linear revmap irq_domain. - * @of_node: pointer to interrupt controller's device tree node. - * @size: Number of interrupts in the domain. - * @ops: map/unmap domain callbacks - * @host_data: Controller private data pointer - */ -struct irq_domain *irq_domain_add_linear(struct device_node *of_node, - unsigned int size, - const struct irq_domain_ops *ops, - void *host_data) -{ - struct irq_domain *domain; - unsigned int *revmap; - - revmap = kzalloc_node(sizeof(*revmap) * size, GFP_KERNEL, - of_node_to_nid(of_node)); - if (WARN_ON(!revmap)) - return NULL; - - domain = irq_domain_alloc(of_node, IRQ_DOMAIN_MAP_LINEAR, ops, host_data); - if (!domain) { - kfree(revmap); - return NULL; - } - domain->revmap_data.linear.size = size; - domain->revmap_data.linear.revmap = revmap; - irq_domain_add(domain); - return domain; -} -EXPORT_SYMBOL_GPL(irq_domain_add_linear); - -struct irq_domain *irq_domain_add_nomap(struct device_node *of_node, - unsigned int max_irq, - const struct irq_domain_ops *ops, - void *host_data) -{ - struct irq_domain *domain = irq_domain_alloc(of_node, - IRQ_DOMAIN_MAP_NOMAP, ops, host_data); - if (domain) { - domain->revmap_data.nomap.max_irq = max_irq ? max_irq : ~0; - irq_domain_add(domain); - } - return domain; -} -EXPORT_SYMBOL_GPL(irq_domain_add_nomap); - -/** - * irq_domain_add_tree() - * @of_node: pointer to interrupt controller's device tree node. - * @ops: map/unmap domain callbacks - * - * Note: The radix tree will be allocated later during boot automatically - * (the reverse mapping will use the slow path until that happens). - */ -struct irq_domain *irq_domain_add_tree(struct device_node *of_node, - const struct irq_domain_ops *ops, - void *host_data) -{ - struct irq_domain *domain = irq_domain_alloc(of_node, - IRQ_DOMAIN_MAP_TREE, ops, host_data); - if (domain) { - INIT_RADIX_TREE(&domain->revmap_data.tree, GFP_KERNEL); - irq_domain_add(domain); - } - return domain; -} -EXPORT_SYMBOL_GPL(irq_domain_add_tree); - -/** * irq_find_host() - Locates a domain for a given device node * @node: device-tree node of the interrupt controller */ @@ -385,125 +230,108 @@ void irq_set_default_host(struct irq_domain *domain) } EXPORT_SYMBOL_GPL(irq_set_default_host); -static void irq_domain_disassociate_many(struct irq_domain *domain, - unsigned int irq_base, int count) +static void irq_domain_disassociate(struct irq_domain *domain, unsigned int irq) { - /* - * disassociate in reverse order; - * not strictly necessary, but nice for unwinding - */ - while (count--) { - int irq = irq_base + count; - struct irq_data *irq_data = irq_get_irq_data(irq); - irq_hw_number_t hwirq; + struct irq_data *irq_data = irq_get_irq_data(irq); + irq_hw_number_t hwirq; - if (WARN_ON(!irq_data || irq_data->domain != domain)) - continue; + if (WARN(!irq_data || irq_data->domain != domain, + "virq%i doesn't exist; cannot disassociate\n", irq)) + return; - hwirq = irq_data->hwirq; - irq_set_status_flags(irq, IRQ_NOREQUEST); + hwirq = irq_data->hwirq; + irq_set_status_flags(irq, IRQ_NOREQUEST); - /* remove chip and handler */ - irq_set_chip_and_handler(irq, NULL, NULL); + /* remove chip and handler */ + irq_set_chip_and_handler(irq, NULL, NULL); - /* Make sure it's completed */ - synchronize_irq(irq); + /* Make sure it's completed */ + synchronize_irq(irq); - /* Tell the PIC about it */ - if (domain->ops->unmap) - domain->ops->unmap(domain, irq); - smp_mb(); + /* Tell the PIC about it */ + if (domain->ops->unmap) + domain->ops->unmap(domain, irq); + smp_mb(); - irq_data->domain = NULL; - irq_data->hwirq = 0; + irq_data->domain = NULL; + irq_data->hwirq = 0; - /* Clear reverse map */ - switch(domain->revmap_type) { - case IRQ_DOMAIN_MAP_LINEAR: - if (hwirq < domain->revmap_data.linear.size) - domain->revmap_data.linear.revmap[hwirq] = 0; - break; - case IRQ_DOMAIN_MAP_TREE: - mutex_lock(&revmap_trees_mutex); - radix_tree_delete(&domain->revmap_data.tree, hwirq); - mutex_unlock(&revmap_trees_mutex); - break; - } + /* Clear reverse map for this hwirq */ + if (hwirq < domain->revmap_size) { + domain->linear_revmap[hwirq] = 0; + } else { + mutex_lock(&revmap_trees_mutex); + radix_tree_delete(&domain->revmap_tree, hwirq); + mutex_unlock(&revmap_trees_mutex); } } -int irq_domain_associate_many(struct irq_domain *domain, unsigned int irq_base, - irq_hw_number_t hwirq_base, int count) +int irq_domain_associate(struct irq_domain *domain, unsigned int virq, + irq_hw_number_t hwirq) { - unsigned int virq = irq_base; - irq_hw_number_t hwirq = hwirq_base; - int i, ret; + struct irq_data *irq_data = irq_get_irq_data(virq); + int ret; - pr_debug("%s(%s, irqbase=%i, hwbase=%i, count=%i)\n", __func__, - of_node_full_name(domain->of_node), irq_base, (int)hwirq_base, count); + if (WARN(hwirq >= domain->hwirq_max, + "error: hwirq 0x%x is too large for %s\n", (int)hwirq, domain->name)) + return -EINVAL; + if (WARN(!irq_data, "error: virq%i is not allocated", virq)) + return -EINVAL; + if (WARN(irq_data->domain, "error: virq%i is already associated", virq)) + return -EINVAL; - for (i = 0; i < count; i++) { - struct irq_data *irq_data = irq_get_irq_data(virq + i); - - if (WARN(!irq_data, "error: irq_desc not allocated; " - "irq=%i hwirq=0x%x\n", virq + i, (int)hwirq + i)) - return -EINVAL; - if (WARN(irq_data->domain, "error: irq_desc already associated; " - "irq=%i hwirq=0x%x\n", virq + i, (int)hwirq + i)) - return -EINVAL; - }; - - for (i = 0; i < count; i++, virq++, hwirq++) { - struct irq_data *irq_data = irq_get_irq_data(virq); - - irq_data->hwirq = hwirq; - irq_data->domain = domain; - if (domain->ops->map) { - ret = domain->ops->map(domain, virq, hwirq); - if (ret != 0) { - /* - * If map() returns -EPERM, this interrupt is protected - * by the firmware or some other service and shall not - * be mapped. - * - * Since on some platforms we blindly try to map everything - * we end up with a log full of backtraces. - * - * So instead, we silently fail on -EPERM, it is the - * responsibility of the PIC driver to display a relevant - * message if needed. - */ - if (ret != -EPERM) { - pr_err("irq-%i==>hwirq-0x%lx mapping failed: %d\n", - virq, hwirq, ret); - WARN_ON(1); - } - irq_data->domain = NULL; - irq_data->hwirq = 0; - goto err_unmap; + mutex_lock(&irq_domain_mutex); + irq_data->hwirq = hwirq; + irq_data->domain = domain; + if (domain->ops->map) { + ret = domain->ops->map(domain, virq, hwirq); + if (ret != 0) { + /* + * If map() returns -EPERM, this interrupt is protected + * by the firmware or some other service and shall not + * be mapped. Don't bother telling the user about it. + */ + if (ret != -EPERM) { + pr_info("%s didn't like hwirq-0x%lx to VIRQ%i mapping (rc=%d)\n", + domain->name, hwirq, virq, ret); } + irq_data->domain = NULL; + irq_data->hwirq = 0; + mutex_unlock(&irq_domain_mutex); + return ret; } - switch (domain->revmap_type) { - case IRQ_DOMAIN_MAP_LINEAR: - if (hwirq < domain->revmap_data.linear.size) - domain->revmap_data.linear.revmap[hwirq] = virq; - break; - case IRQ_DOMAIN_MAP_TREE: - mutex_lock(&revmap_trees_mutex); - radix_tree_insert(&domain->revmap_data.tree, hwirq, irq_data); - mutex_unlock(&revmap_trees_mutex); - break; - } + /* If not already assigned, give the domain the chip's name */ + if (!domain->name && irq_data->chip) + domain->name = irq_data->chip->name; + } - irq_clear_status_flags(virq, IRQ_NOREQUEST); + if (hwirq < domain->revmap_size) { + domain->linear_revmap[hwirq] = virq; + } else { + mutex_lock(&revmap_trees_mutex); + radix_tree_insert(&domain->revmap_tree, hwirq, irq_data); + mutex_unlock(&revmap_trees_mutex); } + mutex_unlock(&irq_domain_mutex); + + irq_clear_status_flags(virq, IRQ_NOREQUEST); return 0; +} +EXPORT_SYMBOL_GPL(irq_domain_associate); - err_unmap: - irq_domain_disassociate_many(domain, irq_base, i); - return -EINVAL; +void irq_domain_associate_many(struct irq_domain *domain, unsigned int irq_base, + irq_hw_number_t hwirq_base, int count) +{ + int i; + + pr_debug("%s(%s, irqbase=%i, hwbase=%i, count=%i)\n", __func__, + of_node_full_name(domain->of_node), irq_base, (int)hwirq_base, count); + + for (i = 0; i < count; i++) { + irq_domain_associate(domain, irq_base + i, hwirq_base + i); + } } EXPORT_SYMBOL_GPL(irq_domain_associate_many); @@ -513,7 +341,9 @@ EXPORT_SYMBOL_GPL(irq_domain_associate_many); * * This routine is used for irq controllers which can choose the hardware * interrupt numbers they generate. In such a case it's simplest to use - * the linux irq as the hardware interrupt number. + * the linux irq as the hardware interrupt number. It still uses the linear + * or radix tree to store the mapping, but the irq controller can optimize + * the revmap path by using the hwirq directly. */ unsigned int irq_create_direct_mapping(struct irq_domain *domain) { @@ -522,17 +352,14 @@ unsigned int irq_create_direct_mapping(struct irq_domain *domain) if (domain == NULL) domain = irq_default_domain; - if (WARN_ON(!domain || domain->revmap_type != IRQ_DOMAIN_MAP_NOMAP)) - return 0; - virq = irq_alloc_desc_from(1, of_node_to_nid(domain->of_node)); if (!virq) { pr_debug("create_direct virq allocation failed\n"); return 0; } - if (virq >= domain->revmap_data.nomap.max_irq) { + if (virq >= domain->revmap_direct_max_irq) { pr_err("ERROR: no free irqs available below %i maximum\n", - domain->revmap_data.nomap.max_irq); + domain->revmap_direct_max_irq); irq_free_desc(virq); return 0; } @@ -569,9 +396,7 @@ unsigned int irq_create_mapping(struct irq_domain *domain, if (domain == NULL) domain = irq_default_domain; if (domain == NULL) { - pr_warning("irq_create_mapping called for" - " NULL domain, hwirq=%lx\n", hwirq); - WARN_ON(1); + WARN(1, "%s(, %lx) called with NULL domain\n", __func__, hwirq); return 0; } pr_debug("-> using domain @%p\n", domain); @@ -583,10 +408,6 @@ unsigned int irq_create_mapping(struct irq_domain *domain, return virq; } - /* Get a virtual interrupt number */ - if (domain->revmap_type == IRQ_DOMAIN_MAP_LEGACY) - return irq_domain_legacy_revmap(domain, hwirq); - /* Allocate a virtual interrupt number */ hint = hwirq % nr_irqs; if (hint == 0) @@ -639,12 +460,7 @@ int irq_create_strict_mappings(struct irq_domain *domain, unsigned int irq_base, if (unlikely(ret < 0)) return ret; - ret = irq_domain_associate_many(domain, irq_base, hwirq_base, count); - if (unlikely(ret < 0)) { - irq_free_descs(irq_base, count); - return ret; - } - + irq_domain_associate_many(domain, irq_base, hwirq_base, count); return 0; } EXPORT_SYMBOL_GPL(irq_create_strict_mappings); @@ -659,20 +475,8 @@ unsigned int irq_create_of_mapping(struct device_node *controller, domain = controller ? irq_find_host(controller) : irq_default_domain; if (!domain) { -#ifdef CONFIG_MIPS - /* - * Workaround to avoid breaking interrupt controller drivers - * that don't yet register an irq_domain. This is temporary - * code. ~~~gcl, Feb 24, 2012 - * - * Scheduled for removal in Linux v3.6. That should be enough - * time. - */ - if (intsize > 0) - return intspec[0]; -#endif - pr_warning("no irq domain found for %s !\n", - of_node_full_name(controller)); + pr_warn("no irq domain found for %s !\n", + of_node_full_name(controller)); return 0; } @@ -714,11 +518,7 @@ void irq_dispose_mapping(unsigned int virq) if (WARN_ON(domain == NULL)) return; - /* Never unmap legacy interrupts */ - if (domain->revmap_type == IRQ_DOMAIN_MAP_LEGACY) - return; - - irq_domain_disassociate_many(domain, virq, 1); + irq_domain_disassociate(domain, virq); irq_free_desc(virq); } EXPORT_SYMBOL_GPL(irq_dispose_mapping); @@ -739,63 +539,51 @@ unsigned int irq_find_mapping(struct irq_domain *domain, if (domain == NULL) return 0; - switch (domain->revmap_type) { - case IRQ_DOMAIN_MAP_LEGACY: - return irq_domain_legacy_revmap(domain, hwirq); - case IRQ_DOMAIN_MAP_LINEAR: - return irq_linear_revmap(domain, hwirq); - case IRQ_DOMAIN_MAP_TREE: - rcu_read_lock(); - data = radix_tree_lookup(&domain->revmap_data.tree, hwirq); - rcu_read_unlock(); - if (data) - return data->irq; - break; - case IRQ_DOMAIN_MAP_NOMAP: + if (hwirq < domain->revmap_direct_max_irq) { data = irq_get_irq_data(hwirq); if (data && (data->domain == domain) && (data->hwirq == hwirq)) return hwirq; - break; } - return 0; -} -EXPORT_SYMBOL_GPL(irq_find_mapping); + /* Check if the hwirq is in the linear revmap. */ + if (hwirq < domain->revmap_size) + return domain->linear_revmap[hwirq]; -/** - * irq_linear_revmap() - Find a linux irq from a hw irq number. - * @domain: domain owning this hardware interrupt - * @hwirq: hardware irq number in that domain space - * - * This is a fast path that can be called directly by irq controller code to - * save a handful of instructions. - */ -unsigned int irq_linear_revmap(struct irq_domain *domain, - irq_hw_number_t hwirq) -{ - BUG_ON(domain->revmap_type != IRQ_DOMAIN_MAP_LINEAR); - - /* Check revmap bounds; complain if exceeded */ - if (WARN_ON(hwirq >= domain->revmap_data.linear.size)) - return 0; - - return domain->revmap_data.linear.revmap[hwirq]; + rcu_read_lock(); + data = radix_tree_lookup(&domain->revmap_tree, hwirq); + rcu_read_unlock(); + return data ? data->irq : 0; } -EXPORT_SYMBOL_GPL(irq_linear_revmap); +EXPORT_SYMBOL_GPL(irq_find_mapping); #ifdef CONFIG_IRQ_DOMAIN_DEBUG static int virq_debug_show(struct seq_file *m, void *private) { unsigned long flags; struct irq_desc *desc; - const char *p; - static const char none[] = "none"; - void *data; + struct irq_domain *domain; + struct radix_tree_iter iter; + void *data, **slot; int i; - seq_printf(m, "%-5s %-7s %-15s %-*s %s\n", "irq", "hwirq", + seq_printf(m, " %-16s %-6s %-10s %-10s %s\n", + "name", "mapped", "linear-max", "direct-max", "devtree-node"); + mutex_lock(&irq_domain_mutex); + list_for_each_entry(domain, &irq_domain_list, link) { + int count = 0; + radix_tree_for_each_slot(slot, &domain->revmap_tree, &iter, 0) + count++; + seq_printf(m, "%c%-16s %6u %10u %10u %s\n", + domain == irq_default_domain ? '*' : ' ', domain->name, + domain->revmap_size + count, domain->revmap_size, + domain->revmap_direct_max_irq, + domain->of_node ? of_node_full_name(domain->of_node) : ""); + } + mutex_unlock(&irq_domain_mutex); + + seq_printf(m, "%-5s %-7s %-15s %-*s %6s %-14s %s\n", "irq", "hwirq", "chip name", (int)(2 * sizeof(void *) + 2), "chip data", - "domain name"); + "active", "type", "domain"); for (i = 1; i < nr_irqs; i++) { desc = irq_to_desc(i); @@ -803,28 +591,28 @@ static int virq_debug_show(struct seq_file *m, void *private) continue; raw_spin_lock_irqsave(&desc->lock, flags); + domain = desc->irq_data.domain; - if (desc->action && desc->action->handler) { + if (domain) { struct irq_chip *chip; + int hwirq = desc->irq_data.hwirq; + bool direct; seq_printf(m, "%5d ", i); - seq_printf(m, "0x%05lx ", desc->irq_data.hwirq); + seq_printf(m, "0x%05x ", hwirq); chip = irq_desc_get_chip(desc); - if (chip && chip->name) - p = chip->name; - else - p = none; - seq_printf(m, "%-15s ", p); + seq_printf(m, "%-15s ", (chip && chip->name) ? chip->name : "none"); data = irq_desc_get_chip_data(desc); seq_printf(m, data ? "0x%p " : " %p ", data); - if (desc->irq_data.domain) - p = of_node_full_name(desc->irq_data.domain->of_node); - else - p = none; - seq_printf(m, "%s\n", p); + seq_printf(m, " %c ", (desc->action && desc->action->handler) ? '*' : ' '); + direct = (i == hwirq) && (i < domain->revmap_direct_max_irq); + seq_printf(m, "%6s%-8s ", + (hwirq < domain->revmap_size) ? "LINEAR" : "RADIX", + direct ? "(DIRECT)" : ""); + seq_printf(m, "%s\n", desc->irq_data.domain->name); } raw_spin_unlock_irqrestore(&desc->lock, flags); @@ -921,18 +709,3 @@ const struct irq_domain_ops irq_domain_simple_ops = { .xlate = irq_domain_xlate_onetwocell, }; EXPORT_SYMBOL_GPL(irq_domain_simple_ops); - -#ifdef CONFIG_OF_IRQ -void irq_domain_generate_simple(const struct of_device_id *match, - u64 phys_base, unsigned int irq_start) -{ - struct device_node *node; - pr_debug("looking for phys_base=%llx, irq_start=%i\n", - (unsigned long long) phys_base, (int) irq_start); - node = of_find_matching_node_by_address(NULL, match, phys_base); - if (node) - irq_domain_add_legacy(node, 32, irq_start, 0, - &irq_domain_simple_ops, NULL); -} -EXPORT_SYMBOL_GPL(irq_domain_generate_simple); -#endif diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c index 19ed5c425c3b..36f6ee181b0c 100644 --- a/kernel/irq/proc.c +++ b/kernel/irq/proc.c @@ -462,6 +462,8 @@ int show_interrupts(struct seq_file *p, void *v) } else { seq_printf(p, " %8s", "None"); } + if (desc->irq_data.domain) + seq_printf(p, " %*d", prec, (int) desc->irq_data.hwirq); #ifdef CONFIG_GENERIC_IRQ_SHOW_LEVEL seq_printf(p, " %-8s", irqd_is_level_type(&desc->irq_data) ? "Level" : "Edge"); #endif diff --git a/kernel/module.c b/kernel/module.c index cab4bce49c23..206915830d29 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -455,7 +455,7 @@ const struct kernel_symbol *find_symbol(const char *name, EXPORT_SYMBOL_GPL(find_symbol); /* Search for module by name: must hold module_mutex. */ -static struct module *find_module_all(const char *name, +static struct module *find_module_all(const char *name, size_t len, bool even_unformed) { struct module *mod; @@ -463,7 +463,7 @@ static struct module *find_module_all(const char *name, list_for_each_entry(mod, &modules, list) { if (!even_unformed && mod->state == MODULE_STATE_UNFORMED) continue; - if (strcmp(mod->name, name) == 0) + if (strlen(mod->name) == len && !memcmp(mod->name, name, len)) return mod; } return NULL; @@ -471,7 +471,7 @@ static struct module *find_module_all(const char *name, struct module *find_module(const char *name) { - return find_module_all(name, false); + return find_module_all(name, strlen(name), false); } EXPORT_SYMBOL_GPL(find_module); @@ -482,23 +482,28 @@ static inline void __percpu *mod_percpu(struct module *mod) return mod->percpu; } -static int percpu_modalloc(struct module *mod, - unsigned long size, unsigned long align) +static int percpu_modalloc(struct module *mod, struct load_info *info) { + Elf_Shdr *pcpusec = &info->sechdrs[info->index.pcpu]; + unsigned long align = pcpusec->sh_addralign; + + if (!pcpusec->sh_size) + return 0; + if (align > PAGE_SIZE) { printk(KERN_WARNING "%s: per-cpu alignment %li > %li\n", mod->name, align, PAGE_SIZE); align = PAGE_SIZE; } - mod->percpu = __alloc_reserved_percpu(size, align); + mod->percpu = __alloc_reserved_percpu(pcpusec->sh_size, align); if (!mod->percpu) { printk(KERN_WARNING "%s: Could not allocate %lu bytes percpu data\n", - mod->name, size); + mod->name, (unsigned long)pcpusec->sh_size); return -ENOMEM; } - mod->percpu_size = size; + mod->percpu_size = pcpusec->sh_size; return 0; } @@ -563,10 +568,12 @@ static inline void __percpu *mod_percpu(struct module *mod) { return NULL; } -static inline int percpu_modalloc(struct module *mod, - unsigned long size, unsigned long align) +static int percpu_modalloc(struct module *mod, struct load_info *info) { - return -ENOMEM; + /* UP modules shouldn't have this section: ENOMEM isn't quite right */ + if (info->sechdrs[info->index.pcpu].sh_size != 0) + return -ENOMEM; + return 0; } static inline void percpu_modfree(struct module *mod) { @@ -2927,7 +2934,6 @@ static struct module *layout_and_allocate(struct load_info *info, int flags) { /* Module within temporary copy. */ struct module *mod; - Elf_Shdr *pcpusec; int err; mod = setup_load_info(info, flags); @@ -2942,17 +2948,10 @@ static struct module *layout_and_allocate(struct load_info *info, int flags) err = module_frob_arch_sections(info->hdr, info->sechdrs, info->secstrings, mod); if (err < 0) - goto out; + return ERR_PTR(err); - pcpusec = &info->sechdrs[info->index.pcpu]; - if (pcpusec->sh_size) { - /* We have a special allocation for this section. */ - err = percpu_modalloc(mod, - pcpusec->sh_size, pcpusec->sh_addralign); - if (err) - goto out; - pcpusec->sh_flags &= ~(unsigned long)SHF_ALLOC; - } + /* We will do a special allocation for per-cpu sections later. */ + info->sechdrs[info->index.pcpu].sh_flags &= ~(unsigned long)SHF_ALLOC; /* Determine total sizes, and put offsets in sh_entsize. For now this is done generically; there doesn't appear to be any @@ -2963,17 +2962,12 @@ static struct module *layout_and_allocate(struct load_info *info, int flags) /* Allocate and move to the final place */ err = move_module(mod, info); if (err) - goto free_percpu; + return ERR_PTR(err); /* Module has been copied to its final place now: return it. */ mod = (void *)info->sechdrs[info->index.mod].sh_addr; kmemleak_load_module(mod, info); return mod; - -free_percpu: - percpu_modfree(mod); -out: - return ERR_PTR(err); } /* mod is no longer valid after this! */ @@ -3014,7 +3008,7 @@ static bool finished_loading(const char *name) bool ret; mutex_lock(&module_mutex); - mod = find_module_all(name, true); + mod = find_module_all(name, strlen(name), true); ret = !mod || mod->state == MODULE_STATE_LIVE || mod->state == MODULE_STATE_GOING; mutex_unlock(&module_mutex); @@ -3152,7 +3146,8 @@ static int add_unformed_module(struct module *mod) again: mutex_lock(&module_mutex); - if ((old = find_module_all(mod->name, true)) != NULL) { + old = find_module_all(mod->name, strlen(mod->name), true); + if (old != NULL) { if (old->state == MODULE_STATE_COMING || old->state == MODULE_STATE_UNFORMED) { /* Wait in case it fails to load. */ @@ -3198,6 +3193,17 @@ out: return err; } +static int unknown_module_param_cb(char *param, char *val, const char *modname) +{ + /* Check for magic 'dyndbg' arg */ + int ret = ddebug_dyndbg_module_param_cb(param, val, modname); + if (ret != 0) { + printk(KERN_WARNING "%s: unknown parameter '%s' ignored\n", + modname, param); + } + return 0; +} + /* Allocate and load the module: note that size of section 0 is always zero, and we rely on this for optional sections. */ static int load_module(struct load_info *info, const char __user *uargs, @@ -3237,6 +3243,11 @@ static int load_module(struct load_info *info, const char __user *uargs, } #endif + /* To avoid stressing percpu allocator, do this once we're unique. */ + err = percpu_modalloc(mod, info); + if (err) + goto unlink_mod; + /* Now module is in final location, initialize linked lists, etc. */ err = module_unload_init(mod); if (err) @@ -3284,7 +3295,7 @@ static int load_module(struct load_info *info, const char __user *uargs, /* Module is ready to execute: parsing args may do that. */ err = parse_args(mod->name, mod->args, mod->kp, mod->num_kp, - -32768, 32767, &ddebug_dyndbg_module_param_cb); + -32768, 32767, unknown_module_param_cb); if (err < 0) goto bug_cleanup; @@ -3563,10 +3574,8 @@ unsigned long module_kallsyms_lookup_name(const char *name) /* Don't lock: we're in enough trouble already. */ preempt_disable(); if ((colon = strchr(name, ':')) != NULL) { - *colon = '\0'; - if ((mod = find_module(name)) != NULL) + if ((mod = find_module_all(name, colon - name, false)) != NULL) ret = mod_find_symname(mod, colon+1); - *colon = ':'; } else { list_for_each_entry_rcu(mod, &modules, list) { if (mod->state == MODULE_STATE_UNFORMED) diff --git a/kernel/mutex.c b/kernel/mutex.c index e581ada5faf4..ff05f4bd86eb 100644 --- a/kernel/mutex.c +++ b/kernel/mutex.c @@ -18,6 +18,7 @@ * Also see Documentation/mutex-design.txt. */ #include <linux/mutex.h> +#include <linux/ww_mutex.h> #include <linux/sched.h> #include <linux/sched/rt.h> #include <linux/export.h> diff --git a/kernel/panic.c b/kernel/panic.c index 167ec097ce8b..801864600514 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -15,6 +15,7 @@ #include <linux/notifier.h> #include <linux/module.h> #include <linux/random.h> +#include <linux/ftrace.h> #include <linux/reboot.h> #include <linux/delay.h> #include <linux/kexec.h> @@ -399,8 +400,11 @@ struct slowpath_args { static void warn_slowpath_common(const char *file, int line, void *caller, unsigned taint, struct slowpath_args *args) { - printk(KERN_WARNING "------------[ cut here ]------------\n"); - printk(KERN_WARNING "WARNING: at %s:%d %pS()\n", file, line, caller); + disable_trace_on_warning(); + + pr_warn("------------[ cut here ]------------\n"); + pr_warn("WARNING: CPU: %d PID: %d at %s:%d %pS()\n", + raw_smp_processor_id(), current->pid, file, line, caller); if (args) vprintk(args->fmt, args->args); diff --git a/kernel/params.c b/kernel/params.c index 53b958fcd639..440e65d1a544 100644 --- a/kernel/params.c +++ b/kernel/params.c @@ -787,7 +787,7 @@ static void __init kernel_add_sysfs_param(const char *name, } /* - * param_sysfs_builtin - add contents in /sys/parameters for built-in modules + * param_sysfs_builtin - add sysfs parameters for built-in modules * * Add module_parameters to sysfs for "modules" built into the kernel. * diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c index 42670e9b44e0..c7f31aa272f7 100644 --- a/kernel/posix-cpu-timers.c +++ b/kernel/posix-cpu-timers.c @@ -51,59 +51,28 @@ static int check_clock(const clockid_t which_clock) return error; } -static inline union cpu_time_count +static inline unsigned long long timespec_to_sample(const clockid_t which_clock, const struct timespec *tp) { - union cpu_time_count ret; - ret.sched = 0; /* high half always zero when .cpu used */ + unsigned long long ret; + + ret = 0; /* high half always zero when .cpu used */ if (CPUCLOCK_WHICH(which_clock) == CPUCLOCK_SCHED) { - ret.sched = (unsigned long long)tp->tv_sec * NSEC_PER_SEC + tp->tv_nsec; + ret = (unsigned long long)tp->tv_sec * NSEC_PER_SEC + tp->tv_nsec; } else { - ret.cpu = timespec_to_cputime(tp); + ret = cputime_to_expires(timespec_to_cputime(tp)); } return ret; } static void sample_to_timespec(const clockid_t which_clock, - union cpu_time_count cpu, + unsigned long long expires, struct timespec *tp) { if (CPUCLOCK_WHICH(which_clock) == CPUCLOCK_SCHED) - *tp = ns_to_timespec(cpu.sched); + *tp = ns_to_timespec(expires); else - cputime_to_timespec(cpu.cpu, tp); -} - -static inline int cpu_time_before(const clockid_t which_clock, - union cpu_time_count now, - union cpu_time_count then) -{ - if (CPUCLOCK_WHICH(which_clock) == CPUCLOCK_SCHED) { - return now.sched < then.sched; - } else { - return now.cpu < then.cpu; - } -} -static inline void cpu_time_add(const clockid_t which_clock, - union cpu_time_count *acc, - union cpu_time_count val) -{ - if (CPUCLOCK_WHICH(which_clock) == CPUCLOCK_SCHED) { - acc->sched += val.sched; - } else { - acc->cpu += val.cpu; - } -} -static inline union cpu_time_count cpu_time_sub(const clockid_t which_clock, - union cpu_time_count a, - union cpu_time_count b) -{ - if (CPUCLOCK_WHICH(which_clock) == CPUCLOCK_SCHED) { - a.sched -= b.sched; - } else { - a.cpu -= b.cpu; - } - return a; + cputime_to_timespec((__force cputime_t)expires, tp); } /* @@ -111,47 +80,31 @@ static inline union cpu_time_count cpu_time_sub(const clockid_t which_clock, * given the current clock sample. */ static void bump_cpu_timer(struct k_itimer *timer, - union cpu_time_count now) + unsigned long long now) { int i; + unsigned long long delta, incr; - if (timer->it.cpu.incr.sched == 0) + if (timer->it.cpu.incr == 0) return; - if (CPUCLOCK_WHICH(timer->it_clock) == CPUCLOCK_SCHED) { - unsigned long long delta, incr; + if (now < timer->it.cpu.expires) + return; - if (now.sched < timer->it.cpu.expires.sched) - return; - incr = timer->it.cpu.incr.sched; - delta = now.sched + incr - timer->it.cpu.expires.sched; - /* Don't use (incr*2 < delta), incr*2 might overflow. */ - for (i = 0; incr < delta - incr; i++) - incr = incr << 1; - for (; i >= 0; incr >>= 1, i--) { - if (delta < incr) - continue; - timer->it.cpu.expires.sched += incr; - timer->it_overrun += 1 << i; - delta -= incr; - } - } else { - cputime_t delta, incr; + incr = timer->it.cpu.incr; + delta = now + incr - timer->it.cpu.expires; - if (now.cpu < timer->it.cpu.expires.cpu) - return; - incr = timer->it.cpu.incr.cpu; - delta = now.cpu + incr - timer->it.cpu.expires.cpu; - /* Don't use (incr*2 < delta), incr*2 might overflow. */ - for (i = 0; incr < delta - incr; i++) - incr += incr; - for (; i >= 0; incr = incr >> 1, i--) { - if (delta < incr) - continue; - timer->it.cpu.expires.cpu += incr; - timer->it_overrun += 1 << i; - delta -= incr; - } + /* Don't use (incr*2 < delta), incr*2 might overflow. */ + for (i = 0; incr < delta - incr; i++) + incr = incr << 1; + + for (; i >= 0; incr >>= 1, i--) { + if (delta < incr) + continue; + + timer->it.cpu.expires += incr; + timer->it_overrun += 1 << i; + delta -= incr; } } @@ -170,21 +123,21 @@ static inline int task_cputime_zero(const struct task_cputime *cputime) return 0; } -static inline cputime_t prof_ticks(struct task_struct *p) +static inline unsigned long long prof_ticks(struct task_struct *p) { cputime_t utime, stime; task_cputime(p, &utime, &stime); - return utime + stime; + return cputime_to_expires(utime + stime); } -static inline cputime_t virt_ticks(struct task_struct *p) +static inline unsigned long long virt_ticks(struct task_struct *p) { cputime_t utime; task_cputime(p, &utime, NULL); - return utime; + return cputime_to_expires(utime); } static int @@ -225,19 +178,19 @@ posix_cpu_clock_set(const clockid_t which_clock, const struct timespec *tp) * Sample a per-thread clock for the given task. */ static int cpu_clock_sample(const clockid_t which_clock, struct task_struct *p, - union cpu_time_count *cpu) + unsigned long long *sample) { switch (CPUCLOCK_WHICH(which_clock)) { default: return -EINVAL; case CPUCLOCK_PROF: - cpu->cpu = prof_ticks(p); + *sample = prof_ticks(p); break; case CPUCLOCK_VIRT: - cpu->cpu = virt_ticks(p); + *sample = virt_ticks(p); break; case CPUCLOCK_SCHED: - cpu->sched = task_sched_runtime(p); + *sample = task_sched_runtime(p); break; } return 0; @@ -284,7 +237,7 @@ void thread_group_cputimer(struct task_struct *tsk, struct task_cputime *times) */ static int cpu_clock_sample_group(const clockid_t which_clock, struct task_struct *p, - union cpu_time_count *cpu) + unsigned long long *sample) { struct task_cputime cputime; @@ -293,15 +246,15 @@ static int cpu_clock_sample_group(const clockid_t which_clock, return -EINVAL; case CPUCLOCK_PROF: thread_group_cputime(p, &cputime); - cpu->cpu = cputime.utime + cputime.stime; + *sample = cputime_to_expires(cputime.utime + cputime.stime); break; case CPUCLOCK_VIRT: thread_group_cputime(p, &cputime); - cpu->cpu = cputime.utime; + *sample = cputime_to_expires(cputime.utime); break; case CPUCLOCK_SCHED: thread_group_cputime(p, &cputime); - cpu->sched = cputime.sum_exec_runtime; + *sample = cputime.sum_exec_runtime; break; } return 0; @@ -312,7 +265,7 @@ static int posix_cpu_clock_get(const clockid_t which_clock, struct timespec *tp) { const pid_t pid = CPUCLOCK_PID(which_clock); int error = -EINVAL; - union cpu_time_count rtn; + unsigned long long rtn; if (pid == 0) { /* @@ -446,6 +399,15 @@ static int posix_cpu_timer_del(struct k_itimer *timer) return ret; } +static void cleanup_timers_list(struct list_head *head, + unsigned long long curr) +{ + struct cpu_timer_list *timer, *next; + + list_for_each_entry_safe(timer, next, head, entry) + list_del_init(&timer->entry); +} + /* * Clean out CPU timers still ticking when a thread exited. The task * pointer is cleared, and the expiry time is replaced with the residual @@ -456,37 +418,12 @@ static void cleanup_timers(struct list_head *head, cputime_t utime, cputime_t stime, unsigned long long sum_exec_runtime) { - struct cpu_timer_list *timer, *next; - cputime_t ptime = utime + stime; - - list_for_each_entry_safe(timer, next, head, entry) { - list_del_init(&timer->entry); - if (timer->expires.cpu < ptime) { - timer->expires.cpu = 0; - } else { - timer->expires.cpu -= ptime; - } - } - ++head; - list_for_each_entry_safe(timer, next, head, entry) { - list_del_init(&timer->entry); - if (timer->expires.cpu < utime) { - timer->expires.cpu = 0; - } else { - timer->expires.cpu -= utime; - } - } + cputime_t ptime = utime + stime; - ++head; - list_for_each_entry_safe(timer, next, head, entry) { - list_del_init(&timer->entry); - if (timer->expires.sched < sum_exec_runtime) { - timer->expires.sched = 0; - } else { - timer->expires.sched -= sum_exec_runtime; - } - } + cleanup_timers_list(head, cputime_to_expires(ptime)); + cleanup_timers_list(++head, cputime_to_expires(utime)); + cleanup_timers_list(++head, sum_exec_runtime); } /* @@ -516,17 +453,21 @@ void posix_cpu_timers_exit_group(struct task_struct *tsk) tsk->se.sum_exec_runtime + sig->sum_sched_runtime); } -static void clear_dead_task(struct k_itimer *timer, union cpu_time_count now) +static void clear_dead_task(struct k_itimer *itimer, unsigned long long now) { + struct cpu_timer_list *timer = &itimer->it.cpu; + /* * That's all for this thread or process. * We leave our residual in expires to be reported. */ - put_task_struct(timer->it.cpu.task); - timer->it.cpu.task = NULL; - timer->it.cpu.expires = cpu_time_sub(timer->it_clock, - timer->it.cpu.expires, - now); + put_task_struct(timer->task); + timer->task = NULL; + if (timer->expires < now) { + timer->expires = 0; + } else { + timer->expires -= now; + } } static inline int expires_gt(cputime_t expires, cputime_t new_exp) @@ -558,14 +499,14 @@ static void arm_timer(struct k_itimer *timer) listpos = head; list_for_each_entry(next, head, entry) { - if (cpu_time_before(timer->it_clock, nt->expires, next->expires)) + if (nt->expires < next->expires) break; listpos = &next->entry; } list_add(&nt->entry, listpos); if (listpos == head) { - union cpu_time_count *exp = &nt->expires; + unsigned long long exp = nt->expires; /* * We are the new earliest-expiring POSIX 1.b timer, hence @@ -576,17 +517,17 @@ static void arm_timer(struct k_itimer *timer) switch (CPUCLOCK_WHICH(timer->it_clock)) { case CPUCLOCK_PROF: - if (expires_gt(cputime_expires->prof_exp, exp->cpu)) - cputime_expires->prof_exp = exp->cpu; + if (expires_gt(cputime_expires->prof_exp, expires_to_cputime(exp))) + cputime_expires->prof_exp = expires_to_cputime(exp); break; case CPUCLOCK_VIRT: - if (expires_gt(cputime_expires->virt_exp, exp->cpu)) - cputime_expires->virt_exp = exp->cpu; + if (expires_gt(cputime_expires->virt_exp, expires_to_cputime(exp))) + cputime_expires->virt_exp = expires_to_cputime(exp); break; case CPUCLOCK_SCHED: if (cputime_expires->sched_exp == 0 || - cputime_expires->sched_exp > exp->sched) - cputime_expires->sched_exp = exp->sched; + cputime_expires->sched_exp > exp) + cputime_expires->sched_exp = exp; break; } } @@ -601,20 +542,20 @@ static void cpu_timer_fire(struct k_itimer *timer) /* * User don't want any signal. */ - timer->it.cpu.expires.sched = 0; + timer->it.cpu.expires = 0; } else if (unlikely(timer->sigq == NULL)) { /* * This a special case for clock_nanosleep, * not a normal timer from sys_timer_create. */ wake_up_process(timer->it_process); - timer->it.cpu.expires.sched = 0; - } else if (timer->it.cpu.incr.sched == 0) { + timer->it.cpu.expires = 0; + } else if (timer->it.cpu.incr == 0) { /* * One-shot timer. Clear it as soon as it's fired. */ posix_timer_event(timer, 0); - timer->it.cpu.expires.sched = 0; + timer->it.cpu.expires = 0; } else if (posix_timer_event(timer, ++timer->it_requeue_pending)) { /* * The signal did not get queued because the signal @@ -632,7 +573,7 @@ static void cpu_timer_fire(struct k_itimer *timer) */ static int cpu_timer_sample_group(const clockid_t which_clock, struct task_struct *p, - union cpu_time_count *cpu) + unsigned long long *sample) { struct task_cputime cputime; @@ -641,13 +582,13 @@ static int cpu_timer_sample_group(const clockid_t which_clock, default: return -EINVAL; case CPUCLOCK_PROF: - cpu->cpu = cputime.utime + cputime.stime; + *sample = cputime_to_expires(cputime.utime + cputime.stime); break; case CPUCLOCK_VIRT: - cpu->cpu = cputime.utime; + *sample = cputime_to_expires(cputime.utime); break; case CPUCLOCK_SCHED: - cpu->sched = cputime.sum_exec_runtime + task_delta_exec(p); + *sample = cputime.sum_exec_runtime + task_delta_exec(p); break; } return 0; @@ -694,7 +635,7 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int flags, struct itimerspec *new, struct itimerspec *old) { struct task_struct *p = timer->it.cpu.task; - union cpu_time_count old_expires, new_expires, old_incr, val; + unsigned long long old_expires, new_expires, old_incr, val; int ret; if (unlikely(p == NULL)) { @@ -749,7 +690,7 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int flags, } if (old) { - if (old_expires.sched == 0) { + if (old_expires == 0) { old->it_value.tv_sec = 0; old->it_value.tv_nsec = 0; } else { @@ -764,11 +705,8 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int flags, * new setting. */ bump_cpu_timer(timer, val); - if (cpu_time_before(timer->it_clock, val, - timer->it.cpu.expires)) { - old_expires = cpu_time_sub( - timer->it_clock, - timer->it.cpu.expires, val); + if (val < timer->it.cpu.expires) { + old_expires = timer->it.cpu.expires - val; sample_to_timespec(timer->it_clock, old_expires, &old->it_value); @@ -791,8 +729,8 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int flags, goto out; } - if (new_expires.sched != 0 && !(flags & TIMER_ABSTIME)) { - cpu_time_add(timer->it_clock, &new_expires, val); + if (new_expires != 0 && !(flags & TIMER_ABSTIME)) { + new_expires += val; } /* @@ -801,8 +739,7 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int flags, * arm the timer (we'll just fake it for timer_gettime). */ timer->it.cpu.expires = new_expires; - if (new_expires.sched != 0 && - cpu_time_before(timer->it_clock, val, new_expires)) { + if (new_expires != 0 && val < new_expires) { arm_timer(timer); } @@ -826,8 +763,7 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int flags, timer->it_overrun_last = 0; timer->it_overrun = -1; - if (new_expires.sched != 0 && - !cpu_time_before(timer->it_clock, val, new_expires)) { + if (new_expires != 0 && !(val < new_expires)) { /* * The designated time already passed, so we notify * immediately, even if the thread never runs to @@ -849,7 +785,7 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int flags, static void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec *itp) { - union cpu_time_count now; + unsigned long long now; struct task_struct *p = timer->it.cpu.task; int clear_dead; @@ -859,7 +795,7 @@ static void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec *itp) sample_to_timespec(timer->it_clock, timer->it.cpu.incr, &itp->it_interval); - if (timer->it.cpu.expires.sched == 0) { /* Timer not armed at all. */ + if (timer->it.cpu.expires == 0) { /* Timer not armed at all. */ itp->it_value.tv_sec = itp->it_value.tv_nsec = 0; return; } @@ -891,7 +827,7 @@ static void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec *itp) */ put_task_struct(p); timer->it.cpu.task = NULL; - timer->it.cpu.expires.sched = 0; + timer->it.cpu.expires = 0; read_unlock(&tasklist_lock); goto dead; } else { @@ -912,10 +848,9 @@ static void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec *itp) goto dead; } - if (cpu_time_before(timer->it_clock, now, timer->it.cpu.expires)) { + if (now < timer->it.cpu.expires) { sample_to_timespec(timer->it_clock, - cpu_time_sub(timer->it_clock, - timer->it.cpu.expires, now), + timer->it.cpu.expires - now, &itp->it_value); } else { /* @@ -927,6 +862,28 @@ static void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec *itp) } } +static unsigned long long +check_timers_list(struct list_head *timers, + struct list_head *firing, + unsigned long long curr) +{ + int maxfire = 20; + + while (!list_empty(timers)) { + struct cpu_timer_list *t; + + t = list_first_entry(timers, struct cpu_timer_list, entry); + + if (!--maxfire || curr < t->expires) + return t->expires; + + t->firing = 1; + list_move_tail(&t->entry, firing); + } + + return 0; +} + /* * Check for any per-thread CPU timers that have fired and move them off * the tsk->cpu_timers[N] list onto the firing list. Here we update the @@ -935,54 +892,20 @@ static void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec *itp) static void check_thread_timers(struct task_struct *tsk, struct list_head *firing) { - int maxfire; struct list_head *timers = tsk->cpu_timers; struct signal_struct *const sig = tsk->signal; + struct task_cputime *tsk_expires = &tsk->cputime_expires; + unsigned long long expires; unsigned long soft; - maxfire = 20; - tsk->cputime_expires.prof_exp = 0; - while (!list_empty(timers)) { - struct cpu_timer_list *t = list_first_entry(timers, - struct cpu_timer_list, - entry); - if (!--maxfire || prof_ticks(tsk) < t->expires.cpu) { - tsk->cputime_expires.prof_exp = t->expires.cpu; - break; - } - t->firing = 1; - list_move_tail(&t->entry, firing); - } + expires = check_timers_list(timers, firing, prof_ticks(tsk)); + tsk_expires->prof_exp = expires_to_cputime(expires); - ++timers; - maxfire = 20; - tsk->cputime_expires.virt_exp = 0; - while (!list_empty(timers)) { - struct cpu_timer_list *t = list_first_entry(timers, - struct cpu_timer_list, - entry); - if (!--maxfire || virt_ticks(tsk) < t->expires.cpu) { - tsk->cputime_expires.virt_exp = t->expires.cpu; - break; - } - t->firing = 1; - list_move_tail(&t->entry, firing); - } + expires = check_timers_list(++timers, firing, virt_ticks(tsk)); + tsk_expires->virt_exp = expires_to_cputime(expires); - ++timers; - maxfire = 20; - tsk->cputime_expires.sched_exp = 0; - while (!list_empty(timers)) { - struct cpu_timer_list *t = list_first_entry(timers, - struct cpu_timer_list, - entry); - if (!--maxfire || tsk->se.sum_exec_runtime < t->expires.sched) { - tsk->cputime_expires.sched_exp = t->expires.sched; - break; - } - t->firing = 1; - list_move_tail(&t->entry, firing); - } + tsk_expires->sched_exp = check_timers_list(++timers, firing, + tsk->se.sum_exec_runtime); /* * Check for the special case thread timers. @@ -1030,7 +953,8 @@ static void stop_process_timers(struct signal_struct *sig) static u32 onecputick; static void check_cpu_itimer(struct task_struct *tsk, struct cpu_itimer *it, - cputime_t *expires, cputime_t cur_time, int signo) + unsigned long long *expires, + unsigned long long cur_time, int signo) { if (!it->expires) return; @@ -1066,9 +990,8 @@ static void check_cpu_itimer(struct task_struct *tsk, struct cpu_itimer *it, static void check_process_timers(struct task_struct *tsk, struct list_head *firing) { - int maxfire; struct signal_struct *const sig = tsk->signal; - cputime_t utime, ptime, virt_expires, prof_expires; + unsigned long long utime, ptime, virt_expires, prof_expires; unsigned long long sum_sched_runtime, sched_expires; struct list_head *timers = sig->cpu_timers; struct task_cputime cputime; @@ -1078,52 +1001,13 @@ static void check_process_timers(struct task_struct *tsk, * Collect the current process totals. */ thread_group_cputimer(tsk, &cputime); - utime = cputime.utime; - ptime = utime + cputime.stime; + utime = cputime_to_expires(cputime.utime); + ptime = utime + cputime_to_expires(cputime.stime); sum_sched_runtime = cputime.sum_exec_runtime; - maxfire = 20; - prof_expires = 0; - while (!list_empty(timers)) { - struct cpu_timer_list *tl = list_first_entry(timers, - struct cpu_timer_list, - entry); - if (!--maxfire || ptime < tl->expires.cpu) { - prof_expires = tl->expires.cpu; - break; - } - tl->firing = 1; - list_move_tail(&tl->entry, firing); - } - ++timers; - maxfire = 20; - virt_expires = 0; - while (!list_empty(timers)) { - struct cpu_timer_list *tl = list_first_entry(timers, - struct cpu_timer_list, - entry); - if (!--maxfire || utime < tl->expires.cpu) { - virt_expires = tl->expires.cpu; - break; - } - tl->firing = 1; - list_move_tail(&tl->entry, firing); - } - - ++timers; - maxfire = 20; - sched_expires = 0; - while (!list_empty(timers)) { - struct cpu_timer_list *tl = list_first_entry(timers, - struct cpu_timer_list, - entry); - if (!--maxfire || sum_sched_runtime < tl->expires.sched) { - sched_expires = tl->expires.sched; - break; - } - tl->firing = 1; - list_move_tail(&tl->entry, firing); - } + prof_expires = check_timers_list(timers, firing, ptime); + virt_expires = check_timers_list(++timers, firing, utime); + sched_expires = check_timers_list(++timers, firing, sum_sched_runtime); /* * Check for the special case process timers. @@ -1162,8 +1046,8 @@ static void check_process_timers(struct task_struct *tsk, } } - sig->cputime_expires.prof_exp = prof_expires; - sig->cputime_expires.virt_exp = virt_expires; + sig->cputime_expires.prof_exp = expires_to_cputime(prof_expires); + sig->cputime_expires.virt_exp = expires_to_cputime(virt_expires); sig->cputime_expires.sched_exp = sched_expires; if (task_cputime_zero(&sig->cputime_expires)) stop_process_timers(sig); @@ -1176,7 +1060,7 @@ static void check_process_timers(struct task_struct *tsk, void posix_cpu_timer_schedule(struct k_itimer *timer) { struct task_struct *p = timer->it.cpu.task; - union cpu_time_count now; + unsigned long long now; if (unlikely(p == NULL)) /* @@ -1205,7 +1089,7 @@ void posix_cpu_timer_schedule(struct k_itimer *timer) */ put_task_struct(p); timer->it.cpu.task = p = NULL; - timer->it.cpu.expires.sched = 0; + timer->it.cpu.expires = 0; goto out_unlock; } else if (unlikely(p->exit_state) && thread_group_empty(p)) { /* @@ -1213,6 +1097,7 @@ void posix_cpu_timer_schedule(struct k_itimer *timer) * not yet reaped. Take this opportunity to * drop our task ref. */ + cpu_timer_sample_group(timer->it_clock, p, &now); clear_dead_task(timer, now); goto out_unlock; } @@ -1387,7 +1272,7 @@ void run_posix_cpu_timers(struct task_struct *tsk) void set_process_cpu_timer(struct task_struct *tsk, unsigned int clock_idx, cputime_t *newval, cputime_t *oldval) { - union cpu_time_count now; + unsigned long long now; BUG_ON(clock_idx == CPUCLOCK_SCHED); cpu_timer_sample_group(clock_idx, tsk, &now); @@ -1399,17 +1284,17 @@ void set_process_cpu_timer(struct task_struct *tsk, unsigned int clock_idx, * it to be absolute. */ if (*oldval) { - if (*oldval <= now.cpu) { + if (*oldval <= now) { /* Just about to fire. */ *oldval = cputime_one_jiffy; } else { - *oldval -= now.cpu; + *oldval -= now; } } if (!*newval) goto out; - *newval += now.cpu; + *newval += now; } /* @@ -1459,7 +1344,7 @@ static int do_cpu_nanosleep(const clockid_t which_clock, int flags, } while (!signal_pending(current)) { - if (timer.it.cpu.expires.sched == 0) { + if (timer.it.cpu.expires == 0) { /* * Our timer fired and was reset, below * deletion can not fail. diff --git a/kernel/power/autosleep.c b/kernel/power/autosleep.c index c6422ffeda9a..9012ecf7b814 100644 --- a/kernel/power/autosleep.c +++ b/kernel/power/autosleep.c @@ -32,7 +32,8 @@ static void try_to_suspend(struct work_struct *work) mutex_lock(&autosleep_lock); - if (!pm_save_wakeup_count(initial_count)) { + if (!pm_save_wakeup_count(initial_count) || + system_state != SYSTEM_RUNNING) { mutex_unlock(&autosleep_lock); goto out; } diff --git a/kernel/power/process.c b/kernel/power/process.c index fc0df8486449..06ec8869dbf1 100644 --- a/kernel/power/process.c +++ b/kernel/power/process.c @@ -109,6 +109,8 @@ static int try_to_freeze_tasks(bool user_only) /** * freeze_processes - Signal user space processes to enter the refrigerator. + * The current thread will not be frozen. The same process that calls + * freeze_processes must later call thaw_processes. * * On success, returns 0. On failure, -errno and system is fully thawed. */ @@ -120,6 +122,9 @@ int freeze_processes(void) if (error) return error; + /* Make sure this task doesn't get frozen */ + current->flags |= PF_SUSPEND_TASK; + if (!pm_freezing) atomic_inc(&system_freezing_cnt); @@ -168,6 +173,7 @@ int freeze_kernel_threads(void) void thaw_processes(void) { struct task_struct *g, *p; + struct task_struct *curr = current; if (pm_freezing) atomic_dec(&system_freezing_cnt); @@ -182,10 +188,15 @@ void thaw_processes(void) read_lock(&tasklist_lock); do_each_thread(g, p) { + /* No other threads should have PF_SUSPEND_TASK set */ + WARN_ON((p != curr) && (p->flags & PF_SUSPEND_TASK)); __thaw_task(p); } while_each_thread(g, p); read_unlock(&tasklist_lock); + WARN_ON(!(curr->flags & PF_SUSPEND_TASK)); + curr->flags &= ~PF_SUSPEND_TASK; + usermodehelper_enable(); schedule(); diff --git a/kernel/printk/Makefile b/kernel/printk/Makefile new file mode 100644 index 000000000000..85405bdcf2b3 --- /dev/null +++ b/kernel/printk/Makefile @@ -0,0 +1,2 @@ +obj-y = printk.o +obj-$(CONFIG_A11Y_BRAILLE_CONSOLE) += braille.o diff --git a/kernel/printk/braille.c b/kernel/printk/braille.c new file mode 100644 index 000000000000..276762f3a460 --- /dev/null +++ b/kernel/printk/braille.c @@ -0,0 +1,49 @@ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/kernel.h> +#include <linux/console.h> +#include <linux/string.h> + +#include "console_cmdline.h" +#include "braille.h" + +char *_braille_console_setup(char **str, char **brl_options) +{ + if (!memcmp(*str, "brl,", 4)) { + *brl_options = ""; + *str += 4; + } else if (!memcmp(str, "brl=", 4)) { + *brl_options = *str + 4; + *str = strchr(*brl_options, ','); + if (!*str) + pr_err("need port name after brl=\n"); + else + *((*str)++) = 0; + } else + return NULL; + + return *str; +} + +int +_braille_register_console(struct console *console, struct console_cmdline *c) +{ + int rtn = 0; + + if (c->brl_options) { + console->flags |= CON_BRL; + rtn = braille_register_console(console, c->index, c->options, + c->brl_options); + } + + return rtn; +} + +int +_braille_unregister_console(struct console *console) +{ + if (console->flags & CON_BRL) + return braille_unregister_console(console); + + return 0; +} diff --git a/kernel/printk/braille.h b/kernel/printk/braille.h new file mode 100644 index 000000000000..769d771145c8 --- /dev/null +++ b/kernel/printk/braille.h @@ -0,0 +1,48 @@ +#ifndef _PRINTK_BRAILLE_H +#define _PRINTK_BRAILLE_H + +#ifdef CONFIG_A11Y_BRAILLE_CONSOLE + +static inline void +braille_set_options(struct console_cmdline *c, char *brl_options) +{ + c->brl_options = brl_options; +} + +char * +_braille_console_setup(char **str, char **brl_options); + +int +_braille_register_console(struct console *console, struct console_cmdline *c); + +int +_braille_unregister_console(struct console *console); + +#else + +static inline void +braille_set_options(struct console_cmdline *c, char *brl_options) +{ +} + +static inline char * +_braille_console_setup(char **str, char **brl_options) +{ + return NULL; +} + +static inline int +_braille_register_console(struct console *console, struct console_cmdline *c) +{ + return 0; +} + +static inline int +_braille_unregister_console(struct console *console) +{ + return 0; +} + +#endif + +#endif diff --git a/kernel/printk/console_cmdline.h b/kernel/printk/console_cmdline.h new file mode 100644 index 000000000000..cbd69d842341 --- /dev/null +++ b/kernel/printk/console_cmdline.h @@ -0,0 +1,14 @@ +#ifndef _CONSOLE_CMDLINE_H +#define _CONSOLE_CMDLINE_H + +struct console_cmdline +{ + char name[8]; /* Name of the driver */ + int index; /* Minor dev. to use */ + char *options; /* Options for the driver */ +#ifdef CONFIG_A11Y_BRAILLE_CONSOLE + char *brl_options; /* Options for braille driver */ +#endif +}; + +#endif diff --git a/kernel/printk.c b/kernel/printk/printk.c index 8212c1aef125..5b5a7080e2a5 100644 --- a/kernel/printk.c +++ b/kernel/printk/printk.c @@ -51,6 +51,9 @@ #define CREATE_TRACE_POINTS #include <trace/events/printk.h> +#include "console_cmdline.h" +#include "braille.h" + /* printk's without a loglevel use this.. */ #define DEFAULT_MESSAGE_LOGLEVEL CONFIG_DEFAULT_MESSAGE_LOGLEVEL @@ -105,19 +108,11 @@ static struct console *exclusive_console; /* * Array of consoles built from command line options (console=) */ -struct console_cmdline -{ - char name[8]; /* Name of the driver */ - int index; /* Minor dev. to use */ - char *options; /* Options for the driver */ -#ifdef CONFIG_A11Y_BRAILLE_CONSOLE - char *brl_options; /* Options for braille driver */ -#endif -}; #define MAX_CMDLINECONSOLES 8 static struct console_cmdline console_cmdline[MAX_CMDLINECONSOLES]; + static int selected_console = -1; static int preferred_console = -1; int console_set_on_cmdline; @@ -178,7 +173,7 @@ static int console_may_schedule; * 67 "g" * 0032 00 00 00 padding to next message header * - * The 'struct log' buffer header must never be directly exported to + * The 'struct printk_log' buffer header must never be directly exported to * userspace, it is a kernel-private implementation detail that might * need to be changed in the future, when the requirements change. * @@ -200,7 +195,7 @@ enum log_flags { LOG_CONT = 8, /* text is a fragment of a continuation line */ }; -struct log { +struct printk_log { u64 ts_nsec; /* timestamp in nanoseconds */ u16 len; /* length of entire record */ u16 text_len; /* length of text buffer */ @@ -248,7 +243,7 @@ static u32 clear_idx; #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) #define LOG_ALIGN 4 #else -#define LOG_ALIGN __alignof__(struct log) +#define LOG_ALIGN __alignof__(struct printk_log) #endif #define __LOG_BUF_LEN (1 << CONFIG_LOG_BUF_SHIFT) static char __log_buf[__LOG_BUF_LEN] __aligned(LOG_ALIGN); @@ -259,35 +254,35 @@ static u32 log_buf_len = __LOG_BUF_LEN; static volatile unsigned int logbuf_cpu = UINT_MAX; /* human readable text of the record */ -static char *log_text(const struct log *msg) +static char *log_text(const struct printk_log *msg) { - return (char *)msg + sizeof(struct log); + return (char *)msg + sizeof(struct printk_log); } /* optional key/value pair dictionary attached to the record */ -static char *log_dict(const struct log *msg) +static char *log_dict(const struct printk_log *msg) { - return (char *)msg + sizeof(struct log) + msg->text_len; + return (char *)msg + sizeof(struct printk_log) + msg->text_len; } /* get record by index; idx must point to valid msg */ -static struct log *log_from_idx(u32 idx) +static struct printk_log *log_from_idx(u32 idx) { - struct log *msg = (struct log *)(log_buf + idx); + struct printk_log *msg = (struct printk_log *)(log_buf + idx); /* * A length == 0 record is the end of buffer marker. Wrap around and * read the message at the start of the buffer. */ if (!msg->len) - return (struct log *)log_buf; + return (struct printk_log *)log_buf; return msg; } /* get next record; idx must point to valid msg */ static u32 log_next(u32 idx) { - struct log *msg = (struct log *)(log_buf + idx); + struct printk_log *msg = (struct printk_log *)(log_buf + idx); /* length == 0 indicates the end of the buffer; wrap */ /* @@ -296,7 +291,7 @@ static u32 log_next(u32 idx) * return the one after that. */ if (!msg->len) { - msg = (struct log *)log_buf; + msg = (struct printk_log *)log_buf; return msg->len; } return idx + msg->len; @@ -308,11 +303,11 @@ static void log_store(int facility, int level, const char *dict, u16 dict_len, const char *text, u16 text_len) { - struct log *msg; + struct printk_log *msg; u32 size, pad_len; /* number of '\0' padding bytes to next message */ - size = sizeof(struct log) + text_len + dict_len; + size = sizeof(struct printk_log) + text_len + dict_len; pad_len = (-size) & (LOG_ALIGN - 1); size += pad_len; @@ -324,7 +319,7 @@ static void log_store(int facility, int level, else free = log_first_idx - log_next_idx; - if (free > size + sizeof(struct log)) + if (free > size + sizeof(struct printk_log)) break; /* drop old messages until we have enough contiuous space */ @@ -332,18 +327,18 @@ static void log_store(int facility, int level, log_first_seq++; } - if (log_next_idx + size + sizeof(struct log) >= log_buf_len) { + if (log_next_idx + size + sizeof(struct printk_log) >= log_buf_len) { /* * This message + an additional empty header does not fit * at the end of the buffer. Add an empty header with len == 0 * to signify a wrap around. */ - memset(log_buf + log_next_idx, 0, sizeof(struct log)); + memset(log_buf + log_next_idx, 0, sizeof(struct printk_log)); log_next_idx = 0; } /* fill message */ - msg = (struct log *)(log_buf + log_next_idx); + msg = (struct printk_log *)(log_buf + log_next_idx); memcpy(log_text(msg), text, text_len); msg->text_len = text_len; memcpy(log_dict(msg), dict, dict_len); @@ -356,7 +351,7 @@ static void log_store(int facility, int level, else msg->ts_nsec = local_clock(); memset(log_dict(msg) + dict_len, 0, pad_len); - msg->len = sizeof(struct log) + text_len + dict_len + pad_len; + msg->len = sizeof(struct printk_log) + text_len + dict_len + pad_len; /* insert message */ log_next_idx += msg->len; @@ -479,7 +474,7 @@ static ssize_t devkmsg_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { struct devkmsg_user *user = file->private_data; - struct log *msg; + struct printk_log *msg; u64 ts_usec; size_t i; char cont = '-'; @@ -724,14 +719,14 @@ void log_buf_kexec_setup(void) VMCOREINFO_SYMBOL(log_first_idx); VMCOREINFO_SYMBOL(log_next_idx); /* - * Export struct log size and field offsets. User space tools can + * Export struct printk_log size and field offsets. User space tools can * parse it and detect any changes to structure down the line. */ - VMCOREINFO_STRUCT_SIZE(log); - VMCOREINFO_OFFSET(log, ts_nsec); - VMCOREINFO_OFFSET(log, len); - VMCOREINFO_OFFSET(log, text_len); - VMCOREINFO_OFFSET(log, dict_len); + VMCOREINFO_STRUCT_SIZE(printk_log); + VMCOREINFO_OFFSET(printk_log, ts_nsec); + VMCOREINFO_OFFSET(printk_log, len); + VMCOREINFO_OFFSET(printk_log, text_len); + VMCOREINFO_OFFSET(printk_log, dict_len); } #endif @@ -884,7 +879,7 @@ static size_t print_time(u64 ts, char *buf) (unsigned long)ts, rem_nsec / 1000); } -static size_t print_prefix(const struct log *msg, bool syslog, char *buf) +static size_t print_prefix(const struct printk_log *msg, bool syslog, char *buf) { size_t len = 0; unsigned int prefix = (msg->facility << 3) | msg->level; @@ -907,7 +902,7 @@ static size_t print_prefix(const struct log *msg, bool syslog, char *buf) return len; } -static size_t msg_print_text(const struct log *msg, enum log_flags prev, +static size_t msg_print_text(const struct printk_log *msg, enum log_flags prev, bool syslog, char *buf, size_t size) { const char *text = log_text(msg); @@ -969,7 +964,7 @@ static size_t msg_print_text(const struct log *msg, enum log_flags prev, static int syslog_print(char __user *buf, int size) { char *text; - struct log *msg; + struct printk_log *msg; int len = 0; text = kmalloc(LOG_LINE_MAX + PREFIX_MAX, GFP_KERNEL); @@ -1060,7 +1055,7 @@ static int syslog_print_all(char __user *buf, int size, bool clear) idx = clear_idx; prev = 0; while (seq < log_next_seq) { - struct log *msg = log_from_idx(idx); + struct printk_log *msg = log_from_idx(idx); len += msg_print_text(msg, prev, true, NULL, 0); prev = msg->flags; @@ -1073,7 +1068,7 @@ static int syslog_print_all(char __user *buf, int size, bool clear) idx = clear_idx; prev = 0; while (len > size && seq < log_next_seq) { - struct log *msg = log_from_idx(idx); + struct printk_log *msg = log_from_idx(idx); len -= msg_print_text(msg, prev, true, NULL, 0); prev = msg->flags; @@ -1087,7 +1082,7 @@ static int syslog_print_all(char __user *buf, int size, bool clear) len = 0; prev = 0; while (len >= 0 && seq < next_seq) { - struct log *msg = log_from_idx(idx); + struct printk_log *msg = log_from_idx(idx); int textlen; textlen = msg_print_text(msg, prev, true, text, @@ -1233,7 +1228,7 @@ int do_syslog(int type, char __user *buf, int len, bool from_file) error = 0; while (seq < log_next_seq) { - struct log *msg = log_from_idx(idx); + struct printk_log *msg = log_from_idx(idx); error += msg_print_text(msg, prev, true, NULL, 0); idx = log_next(idx); @@ -1369,9 +1364,9 @@ static int console_trylock_for_printk(unsigned int cpu) } } logbuf_cpu = UINT_MAX; + raw_spin_unlock(&logbuf_lock); if (wake) up(&console_sem); - raw_spin_unlock(&logbuf_lock); return retval; } @@ -1719,10 +1714,10 @@ static struct cont { u8 level; bool flushed:1; } cont; -static struct log *log_from_idx(u32 idx) { return NULL; } +static struct printk_log *log_from_idx(u32 idx) { return NULL; } static u32 log_next(u32 idx) { return 0; } static void call_console_drivers(int level, const char *text, size_t len) {} -static size_t msg_print_text(const struct log *msg, enum log_flags prev, +static size_t msg_print_text(const struct printk_log *msg, enum log_flags prev, bool syslog, char *buf, size_t size) { return 0; } static size_t cont_print_text(char *text, size_t size) { return 0; } @@ -1761,23 +1756,23 @@ static int __add_preferred_console(char *name, int idx, char *options, * See if this tty is not yet registered, and * if we have a slot free. */ - for (i = 0; i < MAX_CMDLINECONSOLES && console_cmdline[i].name[0]; i++) - if (strcmp(console_cmdline[i].name, name) == 0 && - console_cmdline[i].index == idx) { - if (!brl_options) - selected_console = i; - return 0; + for (i = 0, c = console_cmdline; + i < MAX_CMDLINECONSOLES && c->name[0]; + i++, c++) { + if (strcmp(c->name, name) == 0 && c->index == idx) { + if (!brl_options) + selected_console = i; + return 0; } + } if (i == MAX_CMDLINECONSOLES) return -E2BIG; if (!brl_options) selected_console = i; - c = &console_cmdline[i]; strlcpy(c->name, name, sizeof(c->name)); c->options = options; -#ifdef CONFIG_A11Y_BRAILLE_CONSOLE - c->brl_options = brl_options; -#endif + braille_set_options(c, brl_options); + c->index = idx; return 0; } @@ -1790,20 +1785,8 @@ static int __init console_setup(char *str) char *s, *options, *brl_options = NULL; int idx; -#ifdef CONFIG_A11Y_BRAILLE_CONSOLE - if (!memcmp(str, "brl,", 4)) { - brl_options = ""; - str += 4; - } else if (!memcmp(str, "brl=", 4)) { - brl_options = str + 4; - str = strchr(brl_options, ','); - if (!str) { - printk(KERN_ERR "need port name after brl=\n"); - return 1; - } - *(str++) = 0; - } -#endif + if (_braille_console_setup(&str, &brl_options)) + return 1; /* * Decode str into name, index, options. @@ -1858,15 +1841,15 @@ int update_console_cmdline(char *name, int idx, char *name_new, int idx_new, cha struct console_cmdline *c; int i; - for (i = 0; i < MAX_CMDLINECONSOLES && console_cmdline[i].name[0]; i++) - if (strcmp(console_cmdline[i].name, name) == 0 && - console_cmdline[i].index == idx) { - c = &console_cmdline[i]; - strlcpy(c->name, name_new, sizeof(c->name)); - c->name[sizeof(c->name) - 1] = 0; - c->options = options; - c->index = idx_new; - return i; + for (i = 0, c = console_cmdline; + i < MAX_CMDLINECONSOLES && c->name[0]; + i++, c++) + if (strcmp(c->name, name) == 0 && c->index == idx) { + strlcpy(c->name, name_new, sizeof(c->name)); + c->name[sizeof(c->name) - 1] = 0; + c->options = options; + c->index = idx_new; + return i; } /* not found */ return -1; @@ -1921,7 +1904,7 @@ void resume_console(void) * called when a new CPU comes online (or fails to come up), and ensures * that any such output gets printed. */ -static int __cpuinit console_cpu_notify(struct notifier_block *self, +static int console_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu) { switch (action) { @@ -2046,7 +2029,7 @@ void console_unlock(void) console_cont_flush(text, sizeof(text)); again: for (;;) { - struct log *msg; + struct printk_log *msg; size_t len; int level; @@ -2241,6 +2224,7 @@ void register_console(struct console *newcon) int i; unsigned long flags; struct console *bcon = NULL; + struct console_cmdline *c; /* * before we register a new CON_BOOT console, make sure we don't @@ -2288,30 +2272,25 @@ void register_console(struct console *newcon) * See if this console matches one we selected on * the command line. */ - for (i = 0; i < MAX_CMDLINECONSOLES && console_cmdline[i].name[0]; - i++) { - if (strcmp(console_cmdline[i].name, newcon->name) != 0) + for (i = 0, c = console_cmdline; + i < MAX_CMDLINECONSOLES && c->name[0]; + i++, c++) { + if (strcmp(c->name, newcon->name) != 0) continue; if (newcon->index >= 0 && - newcon->index != console_cmdline[i].index) + newcon->index != c->index) continue; if (newcon->index < 0) - newcon->index = console_cmdline[i].index; -#ifdef CONFIG_A11Y_BRAILLE_CONSOLE - if (console_cmdline[i].brl_options) { - newcon->flags |= CON_BRL; - braille_register_console(newcon, - console_cmdline[i].index, - console_cmdline[i].options, - console_cmdline[i].brl_options); + newcon->index = c->index; + + if (_braille_register_console(newcon, c)) return; - } -#endif + if (newcon->setup && newcon->setup(newcon, console_cmdline[i].options) != 0) break; newcon->flags |= CON_ENABLED; - newcon->index = console_cmdline[i].index; + newcon->index = c->index; if (i == selected_console) { newcon->flags |= CON_CONSDEV; preferred_console = selected_console; @@ -2394,13 +2373,13 @@ EXPORT_SYMBOL(register_console); int unregister_console(struct console *console) { struct console *a, *b; - int res = 1; + int res; -#ifdef CONFIG_A11Y_BRAILLE_CONSOLE - if (console->flags & CON_BRL) - return braille_unregister_console(console); -#endif + res = _braille_unregister_console(console); + if (res) + return res; + res = 1; console_lock(); if (console_drivers == console) { console_drivers=console->next; @@ -2666,7 +2645,7 @@ void kmsg_dump(enum kmsg_dump_reason reason) bool kmsg_dump_get_line_nolock(struct kmsg_dumper *dumper, bool syslog, char *line, size_t size, size_t *len) { - struct log *msg; + struct printk_log *msg; size_t l = 0; bool ret = false; @@ -2778,7 +2757,7 @@ bool kmsg_dump_get_buffer(struct kmsg_dumper *dumper, bool syslog, idx = dumper->cur_idx; prev = 0; while (seq < dumper->next_seq) { - struct log *msg = log_from_idx(idx); + struct printk_log *msg = log_from_idx(idx); l += msg_print_text(msg, prev, true, NULL, 0); idx = log_next(idx); @@ -2791,7 +2770,7 @@ bool kmsg_dump_get_buffer(struct kmsg_dumper *dumper, bool syslog, idx = dumper->cur_idx; prev = 0; while (l > size && seq < dumper->next_seq) { - struct log *msg = log_from_idx(idx); + struct printk_log *msg = log_from_idx(idx); l -= msg_print_text(msg, prev, true, NULL, 0); idx = log_next(idx); @@ -2806,7 +2785,7 @@ bool kmsg_dump_get_buffer(struct kmsg_dumper *dumper, bool syslog, l = 0; prev = 0; while (seq < dumper->next_seq) { - struct log *msg = log_from_idx(idx); + struct printk_log *msg = log_from_idx(idx); l += msg_print_text(msg, prev, syslog, buf + l, size - l); idx = log_next(idx); diff --git a/kernel/profile.c b/kernel/profile.c index 0bf400737660..6631e1ef55ab 100644 --- a/kernel/profile.c +++ b/kernel/profile.c @@ -331,7 +331,7 @@ out: put_cpu(); } -static int __cpuinit profile_cpu_callback(struct notifier_block *info, +static int profile_cpu_callback(struct notifier_block *info, unsigned long action, void *__cpu) { int node, cpu = (unsigned long)__cpu; diff --git a/kernel/ptrace.c b/kernel/ptrace.c index ba5e6cea181a..a146ee327f6a 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -1221,19 +1221,3 @@ asmlinkage long compat_sys_ptrace(compat_long_t request, compat_long_t pid, return ret; } #endif /* CONFIG_COMPAT */ - -#ifdef CONFIG_HAVE_HW_BREAKPOINT -int ptrace_get_breakpoints(struct task_struct *tsk) -{ - if (atomic_inc_not_zero(&tsk->ptrace_bp_refcnt)) - return 0; - - return -1; -} - -void ptrace_put_breakpoints(struct task_struct *tsk) -{ - if (atomic_dec_and_test(&tsk->ptrace_bp_refcnt)) - flush_ptrace_hw_breakpoint(tsk); -} -#endif /* CONFIG_HAVE_HW_BREAKPOINT */ diff --git a/kernel/rcutorture.c b/kernel/rcutorture.c index b1fa5510388d..f4871e52c546 100644 --- a/kernel/rcutorture.c +++ b/kernel/rcutorture.c @@ -1476,7 +1476,7 @@ rcu_torture_shutdown(void *arg) * Execute random CPU-hotplug operations at the interval specified * by the onoff_interval. */ -static int __cpuinit +static int rcu_torture_onoff(void *arg) { int cpu; @@ -1558,7 +1558,7 @@ rcu_torture_onoff(void *arg) return 0; } -static int __cpuinit +static int rcu_torture_onoff_init(void) { int ret; @@ -1601,7 +1601,7 @@ static void rcu_torture_onoff_cleanup(void) * CPU-stall kthread. It waits as specified by stall_cpu_holdoff, then * induces a CPU stall for the time specified by stall_cpu. */ -static int __cpuinit rcu_torture_stall(void *args) +static int rcu_torture_stall(void *args) { unsigned long stop_at; diff --git a/kernel/rcutree.c b/kernel/rcutree.c index e08abb9461ac..068de3a93606 100644 --- a/kernel/rcutree.c +++ b/kernel/rcutree.c @@ -2910,7 +2910,7 @@ rcu_boot_init_percpu_data(int cpu, struct rcu_state *rsp) * can accept some slop in the rsp->completed access due to the fact * that this CPU cannot possibly have any RCU callbacks in flight yet. */ -static void __cpuinit +static void rcu_init_percpu_data(int cpu, struct rcu_state *rsp, int preemptible) { unsigned long flags; @@ -2962,7 +2962,7 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp, int preemptible) mutex_unlock(&rsp->onoff_mutex); } -static void __cpuinit rcu_prepare_cpu(int cpu) +static void rcu_prepare_cpu(int cpu) { struct rcu_state *rsp; @@ -2974,7 +2974,7 @@ static void __cpuinit rcu_prepare_cpu(int cpu) /* * Handle CPU online/offline notification events. */ -static int __cpuinit rcu_cpu_notify(struct notifier_block *self, +static int rcu_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu) { long cpu = (long)hcpu; diff --git a/kernel/rcutree.h b/kernel/rcutree.h index 4a39d364493c..b3832581043c 100644 --- a/kernel/rcutree.h +++ b/kernel/rcutree.h @@ -521,10 +521,10 @@ static void invoke_rcu_callbacks_kthread(void); static bool rcu_is_callbacks_kthread(void); #ifdef CONFIG_RCU_BOOST static void rcu_preempt_do_callbacks(void); -static int __cpuinit rcu_spawn_one_boost_kthread(struct rcu_state *rsp, +static int rcu_spawn_one_boost_kthread(struct rcu_state *rsp, struct rcu_node *rnp); #endif /* #ifdef CONFIG_RCU_BOOST */ -static void __cpuinit rcu_prepare_kthreads(int cpu); +static void rcu_prepare_kthreads(int cpu); static void rcu_cleanup_after_idle(int cpu); static void rcu_prepare_for_idle(int cpu); static void rcu_idle_count_callbacks_posted(void); diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h index 63098a59216e..769e12e3151b 100644 --- a/kernel/rcutree_plugin.h +++ b/kernel/rcutree_plugin.h @@ -1352,7 +1352,7 @@ static void rcu_preempt_boost_start_gp(struct rcu_node *rnp) * already exist. We only create this kthread for preemptible RCU. * Returns zero if all is well, a negated errno otherwise. */ -static int __cpuinit rcu_spawn_one_boost_kthread(struct rcu_state *rsp, +static int rcu_spawn_one_boost_kthread(struct rcu_state *rsp, struct rcu_node *rnp) { int rnp_index = rnp - &rsp->node[0]; @@ -1507,7 +1507,7 @@ static int __init rcu_spawn_kthreads(void) } early_initcall(rcu_spawn_kthreads); -static void __cpuinit rcu_prepare_kthreads(int cpu) +static void rcu_prepare_kthreads(int cpu) { struct rcu_data *rdp = per_cpu_ptr(rcu_state->rda, cpu); struct rcu_node *rnp = rdp->mynode; @@ -1549,7 +1549,7 @@ static int __init rcu_scheduler_really_started(void) } early_initcall(rcu_scheduler_really_started); -static void __cpuinit rcu_prepare_kthreads(int cpu) +static void rcu_prepare_kthreads(int cpu) { } diff --git a/kernel/reboot.c b/kernel/reboot.c new file mode 100644 index 000000000000..269ed9384cc4 --- /dev/null +++ b/kernel/reboot.c @@ -0,0 +1,419 @@ +/* + * linux/kernel/reboot.c + * + * Copyright (C) 2013 Linus Torvalds + */ + +#define pr_fmt(fmt) "reboot: " fmt + +#include <linux/ctype.h> +#include <linux/export.h> +#include <linux/kexec.h> +#include <linux/kmod.h> +#include <linux/kmsg_dump.h> +#include <linux/reboot.h> +#include <linux/suspend.h> +#include <linux/syscalls.h> +#include <linux/syscore_ops.h> +#include <linux/uaccess.h> + +/* + * this indicates whether you can reboot with ctrl-alt-del: the default is yes + */ + +int C_A_D = 1; +struct pid *cad_pid; +EXPORT_SYMBOL(cad_pid); + +#if defined(CONFIG_ARM) || defined(CONFIG_UNICORE32) +#define DEFAULT_REBOOT_MODE = REBOOT_HARD +#else +#define DEFAULT_REBOOT_MODE +#endif +enum reboot_mode reboot_mode DEFAULT_REBOOT_MODE; + +int reboot_default; +int reboot_cpu; +enum reboot_type reboot_type = BOOT_ACPI; +int reboot_force; + +/* + * If set, this is used for preparing the system to power off. + */ + +void (*pm_power_off_prepare)(void); + +/** + * emergency_restart - reboot the system + * + * Without shutting down any hardware or taking any locks + * reboot the system. This is called when we know we are in + * trouble so this is our best effort to reboot. This is + * safe to call in interrupt context. + */ +void emergency_restart(void) +{ + kmsg_dump(KMSG_DUMP_EMERG); + machine_emergency_restart(); +} +EXPORT_SYMBOL_GPL(emergency_restart); + +void kernel_restart_prepare(char *cmd) +{ + blocking_notifier_call_chain(&reboot_notifier_list, SYS_RESTART, cmd); + system_state = SYSTEM_RESTART; + usermodehelper_disable(); + device_shutdown(); +} + +/** + * register_reboot_notifier - Register function to be called at reboot time + * @nb: Info about notifier function to be called + * + * Registers a function with the list of functions + * to be called at reboot time. + * + * Currently always returns zero, as blocking_notifier_chain_register() + * always returns zero. + */ +int register_reboot_notifier(struct notifier_block *nb) +{ + return blocking_notifier_chain_register(&reboot_notifier_list, nb); +} +EXPORT_SYMBOL(register_reboot_notifier); + +/** + * unregister_reboot_notifier - Unregister previously registered reboot notifier + * @nb: Hook to be unregistered + * + * Unregisters a previously registered reboot + * notifier function. + * + * Returns zero on success, or %-ENOENT on failure. + */ +int unregister_reboot_notifier(struct notifier_block *nb) +{ + return blocking_notifier_chain_unregister(&reboot_notifier_list, nb); +} +EXPORT_SYMBOL(unregister_reboot_notifier); + +static void migrate_to_reboot_cpu(void) +{ + /* The boot cpu is always logical cpu 0 */ + int cpu = reboot_cpu; + + cpu_hotplug_disable(); + + /* Make certain the cpu I'm about to reboot on is online */ + if (!cpu_online(cpu)) + cpu = cpumask_first(cpu_online_mask); + + /* Prevent races with other tasks migrating this task */ + current->flags |= PF_NO_SETAFFINITY; + + /* Make certain I only run on the appropriate processor */ + set_cpus_allowed_ptr(current, cpumask_of(cpu)); +} + +/** + * kernel_restart - reboot the system + * @cmd: pointer to buffer containing command to execute for restart + * or %NULL + * + * Shutdown everything and perform a clean reboot. + * This is not safe to call in interrupt context. + */ +void kernel_restart(char *cmd) +{ + kernel_restart_prepare(cmd); + migrate_to_reboot_cpu(); + syscore_shutdown(); + if (!cmd) + pr_emerg("Restarting system\n"); + else + pr_emerg("Restarting system with command '%s'\n", cmd); + kmsg_dump(KMSG_DUMP_RESTART); + machine_restart(cmd); +} +EXPORT_SYMBOL_GPL(kernel_restart); + +static void kernel_shutdown_prepare(enum system_states state) +{ + blocking_notifier_call_chain(&reboot_notifier_list, + (state == SYSTEM_HALT) ? SYS_HALT : SYS_POWER_OFF, NULL); + system_state = state; + usermodehelper_disable(); + device_shutdown(); +} +/** + * kernel_halt - halt the system + * + * Shutdown everything and perform a clean system halt. + */ +void kernel_halt(void) +{ + kernel_shutdown_prepare(SYSTEM_HALT); + migrate_to_reboot_cpu(); + syscore_shutdown(); + pr_emerg("System halted\n"); + kmsg_dump(KMSG_DUMP_HALT); + machine_halt(); +} +EXPORT_SYMBOL_GPL(kernel_halt); + +/** + * kernel_power_off - power_off the system + * + * Shutdown everything and perform a clean system power_off. + */ +void kernel_power_off(void) +{ + kernel_shutdown_prepare(SYSTEM_POWER_OFF); + if (pm_power_off_prepare) + pm_power_off_prepare(); + migrate_to_reboot_cpu(); + syscore_shutdown(); + pr_emerg("Power down\n"); + kmsg_dump(KMSG_DUMP_POWEROFF); + machine_power_off(); +} +EXPORT_SYMBOL_GPL(kernel_power_off); + +static DEFINE_MUTEX(reboot_mutex); + +/* + * Reboot system call: for obvious reasons only root may call it, + * and even root needs to set up some magic numbers in the registers + * so that some mistake won't make this reboot the whole machine. + * You can also set the meaning of the ctrl-alt-del-key here. + * + * reboot doesn't sync: do that yourself before calling this. + */ +SYSCALL_DEFINE4(reboot, int, magic1, int, magic2, unsigned int, cmd, + void __user *, arg) +{ + struct pid_namespace *pid_ns = task_active_pid_ns(current); + char buffer[256]; + int ret = 0; + + /* We only trust the superuser with rebooting the system. */ + if (!ns_capable(pid_ns->user_ns, CAP_SYS_BOOT)) + return -EPERM; + + /* For safety, we require "magic" arguments. */ + if (magic1 != LINUX_REBOOT_MAGIC1 || + (magic2 != LINUX_REBOOT_MAGIC2 && + magic2 != LINUX_REBOOT_MAGIC2A && + magic2 != LINUX_REBOOT_MAGIC2B && + magic2 != LINUX_REBOOT_MAGIC2C)) + return -EINVAL; + + /* + * If pid namespaces are enabled and the current task is in a child + * pid_namespace, the command is handled by reboot_pid_ns() which will + * call do_exit(). + */ + ret = reboot_pid_ns(pid_ns, cmd); + if (ret) + return ret; + + /* Instead of trying to make the power_off code look like + * halt when pm_power_off is not set do it the easy way. + */ + if ((cmd == LINUX_REBOOT_CMD_POWER_OFF) && !pm_power_off) + cmd = LINUX_REBOOT_CMD_HALT; + + mutex_lock(&reboot_mutex); + switch (cmd) { + case LINUX_REBOOT_CMD_RESTART: + kernel_restart(NULL); + break; + + case LINUX_REBOOT_CMD_CAD_ON: + C_A_D = 1; + break; + + case LINUX_REBOOT_CMD_CAD_OFF: + C_A_D = 0; + break; + + case LINUX_REBOOT_CMD_HALT: + kernel_halt(); + do_exit(0); + panic("cannot halt"); + + case LINUX_REBOOT_CMD_POWER_OFF: + kernel_power_off(); + do_exit(0); + break; + + case LINUX_REBOOT_CMD_RESTART2: + ret = strncpy_from_user(&buffer[0], arg, sizeof(buffer) - 1); + if (ret < 0) { + ret = -EFAULT; + break; + } + buffer[sizeof(buffer) - 1] = '\0'; + + kernel_restart(buffer); + break; + +#ifdef CONFIG_KEXEC + case LINUX_REBOOT_CMD_KEXEC: + ret = kernel_kexec(); + break; +#endif + +#ifdef CONFIG_HIBERNATION + case LINUX_REBOOT_CMD_SW_SUSPEND: + ret = hibernate(); + break; +#endif + + default: + ret = -EINVAL; + break; + } + mutex_unlock(&reboot_mutex); + return ret; +} + +static void deferred_cad(struct work_struct *dummy) +{ + kernel_restart(NULL); +} + +/* + * This function gets called by ctrl-alt-del - ie the keyboard interrupt. + * As it's called within an interrupt, it may NOT sync: the only choice + * is whether to reboot at once, or just ignore the ctrl-alt-del. + */ +void ctrl_alt_del(void) +{ + static DECLARE_WORK(cad_work, deferred_cad); + + if (C_A_D) + schedule_work(&cad_work); + else + kill_cad_pid(SIGINT, 1); +} + +char poweroff_cmd[POWEROFF_CMD_PATH_LEN] = "/sbin/poweroff"; + +static int __orderly_poweroff(bool force) +{ + char **argv; + static char *envp[] = { + "HOME=/", + "PATH=/sbin:/bin:/usr/sbin:/usr/bin", + NULL + }; + int ret; + + argv = argv_split(GFP_KERNEL, poweroff_cmd, NULL); + if (argv) { + ret = call_usermodehelper(argv[0], argv, envp, UMH_WAIT_EXEC); + argv_free(argv); + } else { + ret = -ENOMEM; + } + + if (ret && force) { + pr_warn("Failed to start orderly shutdown: forcing the issue\n"); + /* + * I guess this should try to kick off some daemon to sync and + * poweroff asap. Or not even bother syncing if we're doing an + * emergency shutdown? + */ + emergency_sync(); + kernel_power_off(); + } + + return ret; +} + +static bool poweroff_force; + +static void poweroff_work_func(struct work_struct *work) +{ + __orderly_poweroff(poweroff_force); +} + +static DECLARE_WORK(poweroff_work, poweroff_work_func); + +/** + * orderly_poweroff - Trigger an orderly system poweroff + * @force: force poweroff if command execution fails + * + * This may be called from any context to trigger a system shutdown. + * If the orderly shutdown fails, it will force an immediate shutdown. + */ +int orderly_poweroff(bool force) +{ + if (force) /* do not override the pending "true" */ + poweroff_force = true; + schedule_work(&poweroff_work); + return 0; +} +EXPORT_SYMBOL_GPL(orderly_poweroff); + +static int __init reboot_setup(char *str) +{ + for (;;) { + /* + * Having anything passed on the command line via + * reboot= will cause us to disable DMI checking + * below. + */ + reboot_default = 0; + + switch (*str) { + case 'w': + reboot_mode = REBOOT_WARM; + break; + + case 'c': + reboot_mode = REBOOT_COLD; + break; + + case 'h': + reboot_mode = REBOOT_HARD; + break; + + case 's': + if (isdigit(*(str+1))) + reboot_cpu = simple_strtoul(str+1, NULL, 0); + else if (str[1] == 'm' && str[2] == 'p' && + isdigit(*(str+3))) + reboot_cpu = simple_strtoul(str+3, NULL, 0); + else + reboot_mode = REBOOT_SOFT; + break; + + case 'g': + reboot_mode = REBOOT_GPIO; + break; + + case 'b': + case 'a': + case 'k': + case 't': + case 'e': + case 'p': + reboot_type = *str; + break; + + case 'f': + reboot_force = 1; + break; + } + + str = strchr(str, ','); + if (str) + str++; + else + break; + } + return 1; +} +__setup("reboot=", reboot_setup); diff --git a/kernel/relay.c b/kernel/relay.c index b91488ba2e5a..5001c9887db1 100644 --- a/kernel/relay.c +++ b/kernel/relay.c @@ -516,7 +516,7 @@ static void setup_callbacks(struct rchan *chan, * * Returns the success/failure of the operation. (%NOTIFY_OK, %NOTIFY_BAD) */ -static int __cpuinit relay_hotcpu_callback(struct notifier_block *nb, +static int relay_hotcpu_callback(struct notifier_block *nb, unsigned long action, void *hcpu) { diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 9b1f2e533b95..b7c32cb7bfeb 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -370,13 +370,6 @@ static struct rq *this_rq_lock(void) #ifdef CONFIG_SCHED_HRTICK /* * Use HR-timers to deliver accurate preemption points. - * - * Its all a bit involved since we cannot program an hrt while holding the - * rq->lock. So what we do is store a state in in rq->hrtick_* and ask for a - * reschedule event. - * - * When we get rescheduled we reprogram the hrtick_timer outside of the - * rq->lock. */ static void hrtick_clear(struct rq *rq) @@ -404,6 +397,15 @@ static enum hrtimer_restart hrtick(struct hrtimer *timer) } #ifdef CONFIG_SMP + +static int __hrtick_restart(struct rq *rq) +{ + struct hrtimer *timer = &rq->hrtick_timer; + ktime_t time = hrtimer_get_softexpires(timer); + + return __hrtimer_start_range_ns(timer, time, 0, HRTIMER_MODE_ABS_PINNED, 0); +} + /* * called from hardirq (IPI) context */ @@ -412,7 +414,7 @@ static void __hrtick_start(void *arg) struct rq *rq = arg; raw_spin_lock(&rq->lock); - hrtimer_restart(&rq->hrtick_timer); + __hrtick_restart(rq); rq->hrtick_csd_pending = 0; raw_spin_unlock(&rq->lock); } @@ -430,7 +432,7 @@ void hrtick_start(struct rq *rq, u64 delay) hrtimer_set_expires(timer, time); if (rq == this_rq()) { - hrtimer_restart(timer); + __hrtick_restart(rq); } else if (!rq->hrtick_csd_pending) { __smp_call_function_single(cpu_of(rq), &rq->hrtick_csd, 0); rq->hrtick_csd_pending = 1; @@ -4131,7 +4133,7 @@ void show_state_filter(unsigned long state_filter) debug_show_all_locks(); } -void __cpuinit init_idle_bootup_task(struct task_struct *idle) +void init_idle_bootup_task(struct task_struct *idle) { idle->sched_class = &idle_sched_class; } @@ -4144,7 +4146,7 @@ void __cpuinit init_idle_bootup_task(struct task_struct *idle) * NOTE: this function does not set the idle thread's NEED_RESCHED * flag, to make booting more robust. */ -void __cpuinit init_idle(struct task_struct *idle, int cpu) +void init_idle(struct task_struct *idle, int cpu) { struct rq *rq = cpu_rq(cpu); unsigned long flags; @@ -4628,7 +4630,7 @@ static void set_rq_offline(struct rq *rq) * migration_call - callback that gets triggered when a CPU is added. * Here we can start up the necessary migration thread for the new CPU. */ -static int __cpuinit +static int migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu) { int cpu = (long)hcpu; @@ -4682,12 +4684,12 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu) * happens before everything else. This has to be lower priority than * the notifier in the perf_event subsystem, though. */ -static struct notifier_block __cpuinitdata migration_notifier = { +static struct notifier_block migration_notifier = { .notifier_call = migration_call, .priority = CPU_PRI_MIGRATION, }; -static int __cpuinit sched_cpu_active(struct notifier_block *nfb, +static int sched_cpu_active(struct notifier_block *nfb, unsigned long action, void *hcpu) { switch (action & ~CPU_TASKS_FROZEN) { @@ -4700,7 +4702,7 @@ static int __cpuinit sched_cpu_active(struct notifier_block *nfb, } } -static int __cpuinit sched_cpu_inactive(struct notifier_block *nfb, +static int sched_cpu_inactive(struct notifier_block *nfb, unsigned long action, void *hcpu) { switch (action & ~CPU_TASKS_FROZEN) { diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index f77f9c527449..9565645e3202 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -851,7 +851,7 @@ void task_numa_fault(int node, int pages, bool migrated) { struct task_struct *p = current; - if (!sched_feat_numa(NUMA)) + if (!numabalancing_enabled) return; /* FIXME: Allocate task-specific structure for placement policy here */ @@ -5506,7 +5506,7 @@ void nohz_balance_enter_idle(int cpu) set_bit(NOHZ_TICK_STOPPED, nohz_flags(cpu)); } -static int __cpuinit sched_ilb_notifier(struct notifier_block *nfb, +static int sched_ilb_notifier(struct notifier_block *nfb, unsigned long action, void *hcpu) { switch (action & ~CPU_TASKS_FROZEN) { @@ -5786,7 +5786,7 @@ static void task_tick_fair(struct rq *rq, struct task_struct *curr, int queued) entity_tick(cfs_rq, se, queued); } - if (sched_feat_numa(NUMA)) + if (numabalancing_enabled) task_tick_numa(rq, curr); update_rq_runnable_avg(rq, 1); diff --git a/kernel/sched/stats.h b/kernel/sched/stats.h index 17d7065c3872..5aef494fc8b4 100644 --- a/kernel/sched/stats.h +++ b/kernel/sched/stats.h @@ -162,6 +162,39 @@ sched_info_switch(struct task_struct *prev, struct task_struct *next) */ /** + * cputimer_running - return true if cputimer is running + * + * @tsk: Pointer to target task. + */ +static inline bool cputimer_running(struct task_struct *tsk) + +{ + struct thread_group_cputimer *cputimer = &tsk->signal->cputimer; + + if (!cputimer->running) + return false; + + /* + * After we flush the task's sum_exec_runtime to sig->sum_sched_runtime + * in __exit_signal(), we won't account to the signal struct further + * cputime consumed by that task, even though the task can still be + * ticking after __exit_signal(). + * + * In order to keep a consistent behaviour between thread group cputime + * and thread group cputimer accounting, lets also ignore the cputime + * elapsing after __exit_signal() in any thread group timer running. + * + * This makes sure that POSIX CPU clocks and timers are synchronized, so + * that a POSIX CPU timer won't expire while the corresponding POSIX CPU + * clock delta is behind the expiring timer value. + */ + if (unlikely(!tsk->sighand)) + return false; + + return true; +} + +/** * account_group_user_time - Maintain utime for a thread group. * * @tsk: Pointer to task structure. @@ -176,7 +209,7 @@ static inline void account_group_user_time(struct task_struct *tsk, { struct thread_group_cputimer *cputimer = &tsk->signal->cputimer; - if (!cputimer->running) + if (!cputimer_running(tsk)) return; raw_spin_lock(&cputimer->lock); @@ -199,7 +232,7 @@ static inline void account_group_system_time(struct task_struct *tsk, { struct thread_group_cputimer *cputimer = &tsk->signal->cputimer; - if (!cputimer->running) + if (!cputimer_running(tsk)) return; raw_spin_lock(&cputimer->lock); @@ -222,7 +255,7 @@ static inline void account_group_exec_runtime(struct task_struct *tsk, { struct thread_group_cputimer *cputimer = &tsk->signal->cputimer; - if (!cputimer->running) + if (!cputimer_running(tsk)) return; raw_spin_lock(&cputimer->lock); diff --git a/kernel/smp.c b/kernel/smp.c index 4dba0f7b72ad..fe9f773d7114 100644 --- a/kernel/smp.c +++ b/kernel/smp.c @@ -73,7 +73,7 @@ hotplug_cfd(struct notifier_block *nfb, unsigned long action, void *hcpu) return NOTIFY_OK; } -static struct notifier_block __cpuinitdata hotplug_cfd_notifier = { +static struct notifier_block hotplug_cfd_notifier = { .notifier_call = hotplug_cfd, }; diff --git a/kernel/smpboot.c b/kernel/smpboot.c index 02fc5c933673..eb89e1807408 100644 --- a/kernel/smpboot.c +++ b/kernel/smpboot.c @@ -24,7 +24,7 @@ */ static DEFINE_PER_CPU(struct task_struct *, idle_threads); -struct task_struct * __cpuinit idle_thread_get(unsigned int cpu) +struct task_struct *idle_thread_get(unsigned int cpu) { struct task_struct *tsk = per_cpu(idle_threads, cpu); diff --git a/kernel/softirq.c b/kernel/softirq.c index ca25e6e704a2..be3d3514c325 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -699,7 +699,7 @@ void send_remote_softirq(struct call_single_data *cp, int cpu, int softirq) } EXPORT_SYMBOL(send_remote_softirq); -static int __cpuinit remote_softirq_cpu_notify(struct notifier_block *self, +static int remote_softirq_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu) { /* @@ -728,7 +728,7 @@ static int __cpuinit remote_softirq_cpu_notify(struct notifier_block *self, return NOTIFY_OK; } -static struct notifier_block __cpuinitdata remote_softirq_cpu_notifier = { +static struct notifier_block remote_softirq_cpu_notifier = { .notifier_call = remote_softirq_cpu_notify, }; @@ -830,7 +830,7 @@ static void takeover_tasklets(unsigned int cpu) } #endif /* CONFIG_HOTPLUG_CPU */ -static int __cpuinit cpu_callback(struct notifier_block *nfb, +static int cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu) { @@ -845,7 +845,7 @@ static int __cpuinit cpu_callback(struct notifier_block *nfb, return NOTIFY_OK; } -static struct notifier_block __cpuinitdata cpu_nfb = { +static struct notifier_block cpu_nfb = { .notifier_call = cpu_callback }; diff --git a/kernel/sys.c b/kernel/sys.c index 071de900c824..771129b299f8 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -116,20 +116,6 @@ EXPORT_SYMBOL(fs_overflowuid); EXPORT_SYMBOL(fs_overflowgid); /* - * this indicates whether you can reboot with ctrl-alt-del: the default is yes - */ - -int C_A_D = 1; -struct pid *cad_pid; -EXPORT_SYMBOL(cad_pid); - -/* - * If set, this is used for preparing the system to power off. - */ - -void (*pm_power_off_prepare)(void); - -/* * Returns true if current's euid is same as p's uid or euid, * or has CAP_SYS_NICE to p's user_ns. * @@ -308,266 +294,6 @@ out_unlock: return retval; } -/** - * emergency_restart - reboot the system - * - * Without shutting down any hardware or taking any locks - * reboot the system. This is called when we know we are in - * trouble so this is our best effort to reboot. This is - * safe to call in interrupt context. - */ -void emergency_restart(void) -{ - kmsg_dump(KMSG_DUMP_EMERG); - machine_emergency_restart(); -} -EXPORT_SYMBOL_GPL(emergency_restart); - -void kernel_restart_prepare(char *cmd) -{ - blocking_notifier_call_chain(&reboot_notifier_list, SYS_RESTART, cmd); - system_state = SYSTEM_RESTART; - usermodehelper_disable(); - device_shutdown(); -} - -/** - * register_reboot_notifier - Register function to be called at reboot time - * @nb: Info about notifier function to be called - * - * Registers a function with the list of functions - * to be called at reboot time. - * - * Currently always returns zero, as blocking_notifier_chain_register() - * always returns zero. - */ -int register_reboot_notifier(struct notifier_block *nb) -{ - return blocking_notifier_chain_register(&reboot_notifier_list, nb); -} -EXPORT_SYMBOL(register_reboot_notifier); - -/** - * unregister_reboot_notifier - Unregister previously registered reboot notifier - * @nb: Hook to be unregistered - * - * Unregisters a previously registered reboot - * notifier function. - * - * Returns zero on success, or %-ENOENT on failure. - */ -int unregister_reboot_notifier(struct notifier_block *nb) -{ - return blocking_notifier_chain_unregister(&reboot_notifier_list, nb); -} -EXPORT_SYMBOL(unregister_reboot_notifier); - -/* Add backwards compatibility for stable trees. */ -#ifndef PF_NO_SETAFFINITY -#define PF_NO_SETAFFINITY PF_THREAD_BOUND -#endif - -static void migrate_to_reboot_cpu(void) -{ - /* The boot cpu is always logical cpu 0 */ - int cpu = 0; - - cpu_hotplug_disable(); - - /* Make certain the cpu I'm about to reboot on is online */ - if (!cpu_online(cpu)) - cpu = cpumask_first(cpu_online_mask); - - /* Prevent races with other tasks migrating this task */ - current->flags |= PF_NO_SETAFFINITY; - - /* Make certain I only run on the appropriate processor */ - set_cpus_allowed_ptr(current, cpumask_of(cpu)); -} - -/** - * kernel_restart - reboot the system - * @cmd: pointer to buffer containing command to execute for restart - * or %NULL - * - * Shutdown everything and perform a clean reboot. - * This is not safe to call in interrupt context. - */ -void kernel_restart(char *cmd) -{ - kernel_restart_prepare(cmd); - migrate_to_reboot_cpu(); - syscore_shutdown(); - if (!cmd) - printk(KERN_EMERG "Restarting system.\n"); - else - printk(KERN_EMERG "Restarting system with command '%s'.\n", cmd); - kmsg_dump(KMSG_DUMP_RESTART); - machine_restart(cmd); -} -EXPORT_SYMBOL_GPL(kernel_restart); - -static void kernel_shutdown_prepare(enum system_states state) -{ - blocking_notifier_call_chain(&reboot_notifier_list, - (state == SYSTEM_HALT)?SYS_HALT:SYS_POWER_OFF, NULL); - system_state = state; - usermodehelper_disable(); - device_shutdown(); -} -/** - * kernel_halt - halt the system - * - * Shutdown everything and perform a clean system halt. - */ -void kernel_halt(void) -{ - kernel_shutdown_prepare(SYSTEM_HALT); - migrate_to_reboot_cpu(); - syscore_shutdown(); - printk(KERN_EMERG "System halted.\n"); - kmsg_dump(KMSG_DUMP_HALT); - machine_halt(); -} - -EXPORT_SYMBOL_GPL(kernel_halt); - -/** - * kernel_power_off - power_off the system - * - * Shutdown everything and perform a clean system power_off. - */ -void kernel_power_off(void) -{ - kernel_shutdown_prepare(SYSTEM_POWER_OFF); - if (pm_power_off_prepare) - pm_power_off_prepare(); - migrate_to_reboot_cpu(); - syscore_shutdown(); - printk(KERN_EMERG "Power down.\n"); - kmsg_dump(KMSG_DUMP_POWEROFF); - machine_power_off(); -} -EXPORT_SYMBOL_GPL(kernel_power_off); - -static DEFINE_MUTEX(reboot_mutex); - -/* - * Reboot system call: for obvious reasons only root may call it, - * and even root needs to set up some magic numbers in the registers - * so that some mistake won't make this reboot the whole machine. - * You can also set the meaning of the ctrl-alt-del-key here. - * - * reboot doesn't sync: do that yourself before calling this. - */ -SYSCALL_DEFINE4(reboot, int, magic1, int, magic2, unsigned int, cmd, - void __user *, arg) -{ - struct pid_namespace *pid_ns = task_active_pid_ns(current); - char buffer[256]; - int ret = 0; - - /* We only trust the superuser with rebooting the system. */ - if (!ns_capable(pid_ns->user_ns, CAP_SYS_BOOT)) - return -EPERM; - - /* For safety, we require "magic" arguments. */ - if (magic1 != LINUX_REBOOT_MAGIC1 || - (magic2 != LINUX_REBOOT_MAGIC2 && - magic2 != LINUX_REBOOT_MAGIC2A && - magic2 != LINUX_REBOOT_MAGIC2B && - magic2 != LINUX_REBOOT_MAGIC2C)) - return -EINVAL; - - /* - * If pid namespaces are enabled and the current task is in a child - * pid_namespace, the command is handled by reboot_pid_ns() which will - * call do_exit(). - */ - ret = reboot_pid_ns(pid_ns, cmd); - if (ret) - return ret; - - /* Instead of trying to make the power_off code look like - * halt when pm_power_off is not set do it the easy way. - */ - if ((cmd == LINUX_REBOOT_CMD_POWER_OFF) && !pm_power_off) - cmd = LINUX_REBOOT_CMD_HALT; - - mutex_lock(&reboot_mutex); - switch (cmd) { - case LINUX_REBOOT_CMD_RESTART: - kernel_restart(NULL); - break; - - case LINUX_REBOOT_CMD_CAD_ON: - C_A_D = 1; - break; - - case LINUX_REBOOT_CMD_CAD_OFF: - C_A_D = 0; - break; - - case LINUX_REBOOT_CMD_HALT: - kernel_halt(); - do_exit(0); - panic("cannot halt.\n"); - - case LINUX_REBOOT_CMD_POWER_OFF: - kernel_power_off(); - do_exit(0); - break; - - case LINUX_REBOOT_CMD_RESTART2: - if (strncpy_from_user(&buffer[0], arg, sizeof(buffer) - 1) < 0) { - ret = -EFAULT; - break; - } - buffer[sizeof(buffer) - 1] = '\0'; - - kernel_restart(buffer); - break; - -#ifdef CONFIG_KEXEC - case LINUX_REBOOT_CMD_KEXEC: - ret = kernel_kexec(); - break; -#endif - -#ifdef CONFIG_HIBERNATION - case LINUX_REBOOT_CMD_SW_SUSPEND: - ret = hibernate(); - break; -#endif - - default: - ret = -EINVAL; - break; - } - mutex_unlock(&reboot_mutex); - return ret; -} - -static void deferred_cad(struct work_struct *dummy) -{ - kernel_restart(NULL); -} - -/* - * This function gets called by ctrl-alt-del - ie the keyboard interrupt. - * As it's called within an interrupt, it may NOT sync: the only choice - * is whether to reboot at once, or just ignore the ctrl-alt-del. - */ -void ctrl_alt_del(void) -{ - static DECLARE_WORK(cad_work, deferred_cad); - - if (C_A_D) - schedule_work(&cad_work); - else - kill_cad_pid(SIGINT, 1); -} - /* * Unprivileged users may change the real gid to the effective gid * or vice versa. (BSD-style) @@ -2292,68 +2018,6 @@ SYSCALL_DEFINE3(getcpu, unsigned __user *, cpup, unsigned __user *, nodep, return err ? -EFAULT : 0; } -char poweroff_cmd[POWEROFF_CMD_PATH_LEN] = "/sbin/poweroff"; - -static int __orderly_poweroff(bool force) -{ - char **argv; - static char *envp[] = { - "HOME=/", - "PATH=/sbin:/bin:/usr/sbin:/usr/bin", - NULL - }; - int ret; - - argv = argv_split(GFP_KERNEL, poweroff_cmd, NULL); - if (argv) { - ret = call_usermodehelper(argv[0], argv, envp, UMH_WAIT_EXEC); - argv_free(argv); - } else { - printk(KERN_WARNING "%s failed to allocate memory for \"%s\"\n", - __func__, poweroff_cmd); - ret = -ENOMEM; - } - - if (ret && force) { - printk(KERN_WARNING "Failed to start orderly shutdown: " - "forcing the issue\n"); - /* - * I guess this should try to kick off some daemon to sync and - * poweroff asap. Or not even bother syncing if we're doing an - * emergency shutdown? - */ - emergency_sync(); - kernel_power_off(); - } - - return ret; -} - -static bool poweroff_force; - -static void poweroff_work_func(struct work_struct *work) -{ - __orderly_poweroff(poweroff_force); -} - -static DECLARE_WORK(poweroff_work, poweroff_work_func); - -/** - * orderly_poweroff - Trigger an orderly system poweroff - * @force: force poweroff if command execution fails - * - * This may be called from any context to trigger a system shutdown. - * If the orderly shutdown fails, it will force an immediate shutdown. - */ -int orderly_poweroff(bool force) -{ - if (force) /* do not override the pending "true" */ - poweroff_force = true; - schedule_work(&poweroff_work); - return 0; -} -EXPORT_SYMBOL_GPL(orderly_poweroff); - /** * do_sysinfo - fill in sysinfo struct * @info: pointer to buffer to fill diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 4ce13c3cedb9..07f6fc468e17 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -599,6 +599,13 @@ static struct ctl_table kern_table[] = { .mode = 0644, .proc_handler = proc_dointvec, }, + { + .procname = "traceoff_on_warning", + .data = &__disable_trace_on_warning, + .maxlen = sizeof(__disable_trace_on_warning), + .mode = 0644, + .proc_handler = proc_dointvec, + }, #endif #ifdef CONFIG_MODULES { @@ -800,7 +807,7 @@ static struct ctl_table kern_table[] = { #if defined(CONFIG_LOCKUP_DETECTOR) { .procname = "watchdog", - .data = &watchdog_enabled, + .data = &watchdog_user_enabled, .maxlen = sizeof (int), .mode = 0644, .proc_handler = proc_dowatchdog, @@ -827,7 +834,7 @@ static struct ctl_table kern_table[] = { }, { .procname = "nmi_watchdog", - .data = &watchdog_enabled, + .data = &watchdog_user_enabled, .maxlen = sizeof (int), .mode = 0644, .proc_handler = proc_dowatchdog, @@ -2339,7 +2346,11 @@ static int do_proc_dointvec_ms_jiffies_conv(bool *negp, unsigned long *lvalp, int write, void *data) { if (write) { - *valp = msecs_to_jiffies(*negp ? -*lvalp : *lvalp); + unsigned long jif = msecs_to_jiffies(*negp ? -*lvalp : *lvalp); + + if (jif > INT_MAX) + return 1; + *valp = (int)jif; } else { int val = *valp; unsigned long lval; diff --git a/kernel/sysctl_binary.c b/kernel/sysctl_binary.c index aea4a9ea6fc8..b609213ca9a2 100644 --- a/kernel/sysctl_binary.c +++ b/kernel/sysctl_binary.c @@ -3,7 +3,6 @@ #include "../fs/xfs/xfs_sysctl.h" #include <linux/sunrpc/debug.h> #include <linux/string.h> -#include <net/ip_vs.h> #include <linux/syscalls.h> #include <linux/namei.h> #include <linux/mount.h> diff --git a/kernel/time/Makefile b/kernel/time/Makefile index ff7d9d2ab504..9250130646f5 100644 --- a/kernel/time/Makefile +++ b/kernel/time/Makefile @@ -4,6 +4,8 @@ obj-y += timeconv.o posix-clock.o alarmtimer.o obj-$(CONFIG_GENERIC_CLOCKEVENTS_BUILD) += clockevents.o obj-$(CONFIG_GENERIC_CLOCKEVENTS) += tick-common.o obj-$(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST) += tick-broadcast.o +obj-$(CONFIG_GENERIC_SCHED_CLOCK) += sched_clock.o obj-$(CONFIG_TICK_ONESHOT) += tick-oneshot.o obj-$(CONFIG_TICK_ONESHOT) += tick-sched.o obj-$(CONFIG_TIMER_STATS) += timer_stats.o +obj-$(CONFIG_DEBUG_FS) += timekeeping_debug.o diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c index f11d83b12949..eec50fcef9e4 100644 --- a/kernel/time/alarmtimer.c +++ b/kernel/time/alarmtimer.c @@ -199,6 +199,13 @@ static enum hrtimer_restart alarmtimer_fired(struct hrtimer *timer) } +ktime_t alarm_expires_remaining(const struct alarm *alarm) +{ + struct alarm_base *base = &alarm_bases[alarm->type]; + return ktime_sub(alarm->node.expires, base->gettime()); +} +EXPORT_SYMBOL_GPL(alarm_expires_remaining); + #ifdef CONFIG_RTC_CLASS /** * alarmtimer_suspend - Suspend time callback @@ -303,9 +310,10 @@ void alarm_init(struct alarm *alarm, enum alarmtimer_type type, alarm->type = type; alarm->state = ALARMTIMER_STATE_INACTIVE; } +EXPORT_SYMBOL_GPL(alarm_init); /** - * alarm_start - Sets an alarm to fire + * alarm_start - Sets an absolute alarm to fire * @alarm: ptr to alarm to set * @start: time to run the alarm */ @@ -323,6 +331,34 @@ int alarm_start(struct alarm *alarm, ktime_t start) spin_unlock_irqrestore(&base->lock, flags); return ret; } +EXPORT_SYMBOL_GPL(alarm_start); + +/** + * alarm_start_relative - Sets a relative alarm to fire + * @alarm: ptr to alarm to set + * @start: time relative to now to run the alarm + */ +int alarm_start_relative(struct alarm *alarm, ktime_t start) +{ + struct alarm_base *base = &alarm_bases[alarm->type]; + + start = ktime_add(start, base->gettime()); + return alarm_start(alarm, start); +} +EXPORT_SYMBOL_GPL(alarm_start_relative); + +void alarm_restart(struct alarm *alarm) +{ + struct alarm_base *base = &alarm_bases[alarm->type]; + unsigned long flags; + + spin_lock_irqsave(&base->lock, flags); + hrtimer_set_expires(&alarm->timer, alarm->node.expires); + hrtimer_restart(&alarm->timer); + alarmtimer_enqueue(base, alarm); + spin_unlock_irqrestore(&base->lock, flags); +} +EXPORT_SYMBOL_GPL(alarm_restart); /** * alarm_try_to_cancel - Tries to cancel an alarm timer @@ -344,6 +380,7 @@ int alarm_try_to_cancel(struct alarm *alarm) spin_unlock_irqrestore(&base->lock, flags); return ret; } +EXPORT_SYMBOL_GPL(alarm_try_to_cancel); /** @@ -361,6 +398,7 @@ int alarm_cancel(struct alarm *alarm) cpu_relax(); } } +EXPORT_SYMBOL_GPL(alarm_cancel); u64 alarm_forward(struct alarm *alarm, ktime_t now, ktime_t interval) @@ -393,8 +431,15 @@ u64 alarm_forward(struct alarm *alarm, ktime_t now, ktime_t interval) alarm->node.expires = ktime_add(alarm->node.expires, interval); return overrun; } +EXPORT_SYMBOL_GPL(alarm_forward); +u64 alarm_forward_now(struct alarm *alarm, ktime_t interval) +{ + struct alarm_base *base = &alarm_bases[alarm->type]; + return alarm_forward(alarm, base->gettime(), interval); +} +EXPORT_SYMBOL_GPL(alarm_forward_now); /** diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c index c6d6400ee137..38959c866789 100644 --- a/kernel/time/clockevents.c +++ b/kernel/time/clockevents.c @@ -15,20 +15,23 @@ #include <linux/hrtimer.h> #include <linux/init.h> #include <linux/module.h> -#include <linux/notifier.h> #include <linux/smp.h> +#include <linux/device.h> #include "tick-internal.h" /* The registered clock event devices */ static LIST_HEAD(clockevent_devices); static LIST_HEAD(clockevents_released); - -/* Notification for clock events */ -static RAW_NOTIFIER_HEAD(clockevents_chain); - /* Protection for the above */ static DEFINE_RAW_SPINLOCK(clockevents_lock); +/* Protection for unbind operations */ +static DEFINE_MUTEX(clockevents_mutex); + +struct ce_unbind { + struct clock_event_device *ce; + int res; +}; /** * clockevents_delta2ns - Convert a latch value (device ticks) to nanoseconds @@ -232,47 +235,107 @@ int clockevents_program_event(struct clock_event_device *dev, ktime_t expires, return (rc && force) ? clockevents_program_min_delta(dev) : rc; } -/** - * clockevents_register_notifier - register a clock events change listener +/* + * Called after a notify add to make devices available which were + * released from the notifier call. */ -int clockevents_register_notifier(struct notifier_block *nb) +static void clockevents_notify_released(void) { - unsigned long flags; - int ret; + struct clock_event_device *dev; - raw_spin_lock_irqsave(&clockevents_lock, flags); - ret = raw_notifier_chain_register(&clockevents_chain, nb); - raw_spin_unlock_irqrestore(&clockevents_lock, flags); + while (!list_empty(&clockevents_released)) { + dev = list_entry(clockevents_released.next, + struct clock_event_device, list); + list_del(&dev->list); + list_add(&dev->list, &clockevent_devices); + tick_check_new_device(dev); + } +} - return ret; +/* + * Try to install a replacement clock event device + */ +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) + continue; + + if (!tick_check_replacement(newdev, dev)) + continue; + + if (!try_module_get(dev->owner)) + continue; + + if (newdev) + module_put(newdev->owner); + newdev = dev; + } + if (newdev) { + tick_install_replacement(newdev); + list_del_init(&ced->list); + } + return newdev ? 0 : -EBUSY; } /* - * Notify about a clock event change. Called with clockevents_lock - * held. + * Called with clockevents_mutex and clockevents_lock held */ -static void clockevents_do_notify(unsigned long reason, void *dev) +static int __clockevents_try_unbind(struct clock_event_device *ced, int cpu) { - raw_notifier_call_chain(&clockevents_chain, reason, dev); + /* Fast track. Device is unused */ + if (ced->mode == CLOCK_EVT_MODE_UNUSED) { + list_del_init(&ced->list); + return 0; + } + + return ced == per_cpu(tick_cpu_device, cpu).evtdev ? -EAGAIN : -EBUSY; } /* - * Called after a notify add to make devices available which were - * released from the notifier call. + * SMP function call to unbind a device */ -static void clockevents_notify_released(void) +static void __clockevents_unbind(void *arg) { - struct clock_event_device *dev; + struct ce_unbind *cu = arg; + int res; + + raw_spin_lock(&clockevents_lock); + res = __clockevents_try_unbind(cu->ce, smp_processor_id()); + if (res == -EAGAIN) + res = clockevents_replace(cu->ce); + cu->res = res; + raw_spin_unlock(&clockevents_lock); +} - while (!list_empty(&clockevents_released)) { - dev = list_entry(clockevents_released.next, - struct clock_event_device, list); - list_del(&dev->list); - list_add(&dev->list, &clockevent_devices); - clockevents_do_notify(CLOCK_EVT_NOTIFY_ADD, dev); - } +/* + * Issues smp function call to unbind a per cpu device. Called with + * clockevents_mutex held. + */ +static int clockevents_unbind(struct clock_event_device *ced, int cpu) +{ + struct ce_unbind cu = { .ce = ced, .res = -ENODEV }; + + smp_call_function_single(cpu, __clockevents_unbind, &cu, 1); + return cu.res; } +/* + * Unbind a clockevents device. + */ +int clockevents_unbind_device(struct clock_event_device *ced, int cpu) +{ + int ret; + + mutex_lock(&clockevents_mutex); + ret = clockevents_unbind(ced, cpu); + mutex_unlock(&clockevents_mutex); + return ret; +} +EXPORT_SYMBOL_GPL(clockevents_unbind); + /** * clockevents_register_device - register a clock event device * @dev: device to register @@ -290,7 +353,7 @@ void clockevents_register_device(struct clock_event_device *dev) raw_spin_lock_irqsave(&clockevents_lock, flags); list_add(&dev->list, &clockevent_devices); - clockevents_do_notify(CLOCK_EVT_NOTIFY_ADD, dev); + tick_check_new_device(dev); clockevents_notify_released(); raw_spin_unlock_irqrestore(&clockevents_lock, flags); @@ -386,6 +449,7 @@ void clockevents_exchange_device(struct clock_event_device *old, * released list and do a notify add later. */ if (old) { + module_put(old->owner); clockevents_set_mode(old, CLOCK_EVT_MODE_UNUSED); list_del(&old->list); list_add(&old->list, &clockevents_released); @@ -433,10 +497,36 @@ void clockevents_notify(unsigned long reason, void *arg) int cpu; raw_spin_lock_irqsave(&clockevents_lock, flags); - clockevents_do_notify(reason, arg); 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: + 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. @@ -462,4 +552,123 @@ void clockevents_notify(unsigned long reason, void *arg) raw_spin_unlock_irqrestore(&clockevents_lock, flags); } EXPORT_SYMBOL_GPL(clockevents_notify); + +#ifdef CONFIG_SYSFS +struct bus_type clockevents_subsys = { + .name = "clockevents", + .dev_name = "clockevent", +}; + +static DEFINE_PER_CPU(struct device, tick_percpu_dev); +static struct tick_device *tick_get_tick_dev(struct device *dev); + +static ssize_t sysfs_show_current_tick_dev(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct tick_device *td; + ssize_t count = 0; + + raw_spin_lock_irq(&clockevents_lock); + td = tick_get_tick_dev(dev); + if (td && td->evtdev) + count = snprintf(buf, PAGE_SIZE, "%s\n", td->evtdev->name); + raw_spin_unlock_irq(&clockevents_lock); + return count; +} +static DEVICE_ATTR(current_device, 0444, sysfs_show_current_tick_dev, NULL); + +/* We don't support the abomination of removable broadcast devices */ +static ssize_t sysfs_unbind_tick_dev(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + char name[CS_NAME_LEN]; + size_t ret = sysfs_get_uname(buf, name, count); + struct clock_event_device *ce; + + if (ret < 0) + return ret; + + ret = -ENODEV; + mutex_lock(&clockevents_mutex); + raw_spin_lock_irq(&clockevents_lock); + list_for_each_entry(ce, &clockevent_devices, list) { + if (!strcmp(ce->name, name)) { + ret = __clockevents_try_unbind(ce, dev->id); + break; + } + } + raw_spin_unlock_irq(&clockevents_lock); + /* + * We hold clockevents_mutex, so ce can't go away + */ + if (ret == -EAGAIN) + ret = clockevents_unbind(ce, dev->id); + mutex_unlock(&clockevents_mutex); + return ret ? ret : count; +} +static DEVICE_ATTR(unbind_device, 0200, NULL, sysfs_unbind_tick_dev); + +#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST +static struct device tick_bc_dev = { + .init_name = "broadcast", + .id = 0, + .bus = &clockevents_subsys, +}; + +static struct tick_device *tick_get_tick_dev(struct device *dev) +{ + return dev == &tick_bc_dev ? tick_get_broadcast_device() : + &per_cpu(tick_cpu_device, dev->id); +} + +static __init int tick_broadcast_init_sysfs(void) +{ + int err = device_register(&tick_bc_dev); + + if (!err) + err = device_create_file(&tick_bc_dev, &dev_attr_current_device); + return err; +} +#else +static struct tick_device *tick_get_tick_dev(struct device *dev) +{ + return &per_cpu(tick_cpu_device, dev->id); +} +static inline int tick_broadcast_init_sysfs(void) { return 0; } #endif + +static int __init tick_init_sysfs(void) +{ + int cpu; + + for_each_possible_cpu(cpu) { + struct device *dev = &per_cpu(tick_percpu_dev, cpu); + int err; + + dev->id = cpu; + dev->bus = &clockevents_subsys; + err = device_register(dev); + if (!err) + err = device_create_file(dev, &dev_attr_current_device); + if (!err) + err = device_create_file(dev, &dev_attr_unbind_device); + if (err) + return err; + } + return tick_broadcast_init_sysfs(); +} + +static int __init clockevents_init_sysfs(void) +{ + int err = subsys_system_register(&clockevents_subsys, NULL); + + if (!err) + err = tick_init_sysfs(); + return err; +} +device_initcall(clockevents_init_sysfs); +#endif /* SYSFS */ + +#endif /* GENERIC_CLOCK_EVENTS */ diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index c9583382141a..50a8736757f3 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -31,6 +31,8 @@ #include <linux/tick.h> #include <linux/kthread.h> +#include "tick-internal.h" + void timecounter_init(struct timecounter *tc, const struct cyclecounter *cc, u64 start_tstamp) @@ -174,11 +176,12 @@ clocks_calc_mult_shift(u32 *mult, u32 *shift, u32 from, u32 to, u32 maxsec) static struct clocksource *curr_clocksource; static LIST_HEAD(clocksource_list); static DEFINE_MUTEX(clocksource_mutex); -static char override_name[32]; +static char override_name[CS_NAME_LEN]; static int finished_booting; #ifdef CONFIG_CLOCKSOURCE_WATCHDOG static void clocksource_watchdog_work(struct work_struct *work); +static void clocksource_select(void); static LIST_HEAD(watchdog_list); static struct clocksource *watchdog; @@ -299,13 +302,30 @@ static void clocksource_watchdog(unsigned long data) if (!(cs->flags & CLOCK_SOURCE_VALID_FOR_HRES) && (cs->flags & CLOCK_SOURCE_IS_CONTINUOUS) && (watchdog->flags & CLOCK_SOURCE_IS_CONTINUOUS)) { + /* Mark it valid for high-res. */ cs->flags |= CLOCK_SOURCE_VALID_FOR_HRES; + + /* + * clocksource_done_booting() will sort it if + * finished_booting is not set yet. + */ + if (!finished_booting) + continue; + /* - * We just marked the clocksource as highres-capable, - * notify the rest of the system as well so that we - * transition into high-res mode: + * If this is not the current clocksource let + * the watchdog thread reselect it. Due to the + * change to high res this clocksource might + * be preferred now. If it is the current + * clocksource let the tick code know about + * that change. */ - tick_clock_notify(); + if (cs != curr_clocksource) { + cs->flags |= CLOCK_SOURCE_RESELECT; + schedule_work(&watchdog_work); + } else { + tick_clock_notify(); + } } } @@ -388,44 +408,39 @@ static void clocksource_enqueue_watchdog(struct clocksource *cs) static void clocksource_dequeue_watchdog(struct clocksource *cs) { - struct clocksource *tmp; unsigned long flags; spin_lock_irqsave(&watchdog_lock, flags); - if (cs->flags & CLOCK_SOURCE_MUST_VERIFY) { - /* cs is a watched clocksource. */ - list_del_init(&cs->wd_list); - } else if (cs == watchdog) { - /* Reset watchdog cycles */ - clocksource_reset_watchdog(); - /* Current watchdog is removed. Find an alternative. */ - watchdog = NULL; - list_for_each_entry(tmp, &clocksource_list, list) { - if (tmp == cs || tmp->flags & CLOCK_SOURCE_MUST_VERIFY) - continue; - if (!watchdog || tmp->rating > watchdog->rating) - watchdog = tmp; + if (cs != watchdog) { + if (cs->flags & CLOCK_SOURCE_MUST_VERIFY) { + /* cs is a watched clocksource. */ + list_del_init(&cs->wd_list); + /* Check if the watchdog timer needs to be stopped. */ + clocksource_stop_watchdog(); } } - cs->flags &= ~CLOCK_SOURCE_WATCHDOG; - /* Check if the watchdog timer needs to be stopped. */ - clocksource_stop_watchdog(); spin_unlock_irqrestore(&watchdog_lock, flags); } -static int clocksource_watchdog_kthread(void *data) +static int __clocksource_watchdog_kthread(void) { struct clocksource *cs, *tmp; unsigned long flags; LIST_HEAD(unstable); + int select = 0; - mutex_lock(&clocksource_mutex); spin_lock_irqsave(&watchdog_lock, flags); - list_for_each_entry_safe(cs, tmp, &watchdog_list, wd_list) + list_for_each_entry_safe(cs, tmp, &watchdog_list, wd_list) { if (cs->flags & CLOCK_SOURCE_UNSTABLE) { list_del_init(&cs->wd_list); list_add(&cs->wd_list, &unstable); + select = 1; } + if (cs->flags & CLOCK_SOURCE_RESELECT) { + cs->flags &= ~CLOCK_SOURCE_RESELECT; + select = 1; + } + } /* Check if the watchdog timer needs to be stopped. */ clocksource_stop_watchdog(); spin_unlock_irqrestore(&watchdog_lock, flags); @@ -435,10 +450,23 @@ static int clocksource_watchdog_kthread(void *data) list_del_init(&cs->wd_list); __clocksource_change_rating(cs, 0); } + return select; +} + +static int clocksource_watchdog_kthread(void *data) +{ + mutex_lock(&clocksource_mutex); + if (__clocksource_watchdog_kthread()) + clocksource_select(); mutex_unlock(&clocksource_mutex); return 0; } +static bool clocksource_is_watchdog(struct clocksource *cs) +{ + return cs == watchdog; +} + #else /* CONFIG_CLOCKSOURCE_WATCHDOG */ static void clocksource_enqueue_watchdog(struct clocksource *cs) @@ -449,7 +477,8 @@ static void clocksource_enqueue_watchdog(struct clocksource *cs) static inline void clocksource_dequeue_watchdog(struct clocksource *cs) { } static inline void clocksource_resume_watchdog(void) { } -static inline int clocksource_watchdog_kthread(void *data) { return 0; } +static inline int __clocksource_watchdog_kthread(void) { return 0; } +static bool clocksource_is_watchdog(struct clocksource *cs) { return false; } #endif /* CONFIG_CLOCKSOURCE_WATCHDOG */ @@ -553,24 +582,42 @@ static u64 clocksource_max_deferment(struct clocksource *cs) #ifndef CONFIG_ARCH_USES_GETTIMEOFFSET -/** - * clocksource_select - Select the best clocksource available - * - * Private function. Must hold clocksource_mutex when called. - * - * Select the clocksource with the best rating, or the clocksource, - * which is selected by userspace override. - */ -static void clocksource_select(void) +static struct clocksource *clocksource_find_best(bool oneshot, bool skipcur) { - struct clocksource *best, *cs; + struct clocksource *cs; if (!finished_booting || list_empty(&clocksource_list)) + return NULL; + + /* + * We pick the clocksource with the highest rating. If oneshot + * mode is active, we pick the highres valid clocksource with + * the best rating. + */ + list_for_each_entry(cs, &clocksource_list, list) { + if (skipcur && cs == curr_clocksource) + continue; + if (oneshot && !(cs->flags & CLOCK_SOURCE_VALID_FOR_HRES)) + continue; + return cs; + } + return NULL; +} + +static void __clocksource_select(bool skipcur) +{ + bool oneshot = tick_oneshot_mode_active(); + struct clocksource *best, *cs; + + /* Find the best suitable clocksource */ + best = clocksource_find_best(oneshot, skipcur); + if (!best) return; - /* First clocksource on the list has the best rating. */ - best = list_first_entry(&clocksource_list, struct clocksource, list); + /* Check for the override clocksource. */ list_for_each_entry(cs, &clocksource_list, list) { + if (skipcur && cs == curr_clocksource) + continue; if (strcmp(cs->name, override_name) != 0) continue; /* @@ -578,8 +625,7 @@ static void clocksource_select(void) * capable clocksource if the tick code is in oneshot * mode (highres or nohz) */ - if (!(cs->flags & CLOCK_SOURCE_VALID_FOR_HRES) && - tick_oneshot_mode_active()) { + if (!(cs->flags & CLOCK_SOURCE_VALID_FOR_HRES) && oneshot) { /* Override clocksource cannot be used. */ printk(KERN_WARNING "Override clocksource %s is not " "HRT compatible. Cannot switch while in " @@ -590,16 +636,35 @@ static void clocksource_select(void) best = cs; break; } - if (curr_clocksource != best) { - printk(KERN_INFO "Switching to clocksource %s\n", best->name); + + if (curr_clocksource != best && !timekeeping_notify(best)) { + pr_info("Switched to clocksource %s\n", best->name); curr_clocksource = best; - timekeeping_notify(curr_clocksource); } } +/** + * clocksource_select - Select the best clocksource available + * + * Private function. Must hold clocksource_mutex when called. + * + * Select the clocksource with the best rating, or the clocksource, + * which is selected by userspace override. + */ +static void clocksource_select(void) +{ + return __clocksource_select(false); +} + +static void clocksource_select_fallback(void) +{ + return __clocksource_select(true); +} + #else /* !CONFIG_ARCH_USES_GETTIMEOFFSET */ static inline void clocksource_select(void) { } +static inline void clocksource_select_fallback(void) { } #endif @@ -614,16 +679,11 @@ static int __init clocksource_done_booting(void) { mutex_lock(&clocksource_mutex); curr_clocksource = clocksource_default_clock(); - mutex_unlock(&clocksource_mutex); - finished_booting = 1; - /* * Run the watchdog first to eliminate unstable clock sources */ - clocksource_watchdog_kthread(NULL); - - mutex_lock(&clocksource_mutex); + __clocksource_watchdog_kthread(); clocksource_select(); mutex_unlock(&clocksource_mutex); return 0; @@ -756,7 +816,6 @@ static void __clocksource_change_rating(struct clocksource *cs, int rating) list_del(&cs->list); cs->rating = rating; clocksource_enqueue(cs); - clocksource_select(); } /** @@ -768,21 +827,47 @@ void clocksource_change_rating(struct clocksource *cs, int rating) { mutex_lock(&clocksource_mutex); __clocksource_change_rating(cs, rating); + clocksource_select(); mutex_unlock(&clocksource_mutex); } EXPORT_SYMBOL(clocksource_change_rating); +/* + * Unbind clocksource @cs. Called with clocksource_mutex held + */ +static int clocksource_unbind(struct clocksource *cs) +{ + /* + * I really can't convince myself to support this on hardware + * designed by lobotomized monkeys. + */ + if (clocksource_is_watchdog(cs)) + return -EBUSY; + + if (cs == curr_clocksource) { + /* Select and try to install a replacement clock source */ + clocksource_select_fallback(); + if (curr_clocksource == cs) + return -EBUSY; + } + clocksource_dequeue_watchdog(cs); + list_del_init(&cs->list); + return 0; +} + /** * clocksource_unregister - remove a registered clocksource * @cs: clocksource to be unregistered */ -void clocksource_unregister(struct clocksource *cs) +int clocksource_unregister(struct clocksource *cs) { + int ret = 0; + mutex_lock(&clocksource_mutex); - clocksource_dequeue_watchdog(cs); - list_del(&cs->list); - clocksource_select(); + if (!list_empty(&cs->list)) + ret = clocksource_unbind(cs); mutex_unlock(&clocksource_mutex); + return ret; } EXPORT_SYMBOL(clocksource_unregister); @@ -808,6 +893,23 @@ sysfs_show_current_clocksources(struct device *dev, return count; } +size_t sysfs_get_uname(const char *buf, char *dst, size_t cnt) +{ + size_t ret = cnt; + + /* strings from sysfs write are not 0 terminated! */ + if (!cnt || cnt >= CS_NAME_LEN) + return -EINVAL; + + /* strip of \n: */ + if (buf[cnt-1] == '\n') + cnt--; + if (cnt > 0) + memcpy(dst, buf, cnt); + dst[cnt] = 0; + return ret; +} + /** * sysfs_override_clocksource - interface for manually overriding clocksource * @dev: unused @@ -822,22 +924,13 @@ static ssize_t sysfs_override_clocksource(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { - size_t ret = count; - - /* strings from sysfs write are not 0 terminated! */ - if (count >= sizeof(override_name)) - return -EINVAL; - - /* strip of \n: */ - if (buf[count-1] == '\n') - count--; + size_t ret; mutex_lock(&clocksource_mutex); - if (count > 0) - memcpy(override_name, buf, count); - override_name[count] = 0; - clocksource_select(); + ret = sysfs_get_uname(buf, override_name, count); + if (ret >= 0) + clocksource_select(); mutex_unlock(&clocksource_mutex); @@ -845,6 +938,40 @@ static ssize_t sysfs_override_clocksource(struct device *dev, } /** + * sysfs_unbind_current_clocksource - interface for manually unbinding clocksource + * @dev: unused + * @attr: unused + * @buf: unused + * @count: length of buffer + * + * Takes input from sysfs interface for manually unbinding a clocksource. + */ +static ssize_t sysfs_unbind_clocksource(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct clocksource *cs; + char name[CS_NAME_LEN]; + size_t ret; + + ret = sysfs_get_uname(buf, name, count); + if (ret < 0) + return ret; + + ret = -ENODEV; + mutex_lock(&clocksource_mutex); + list_for_each_entry(cs, &clocksource_list, list) { + if (strcmp(cs->name, name)) + continue; + ret = clocksource_unbind(cs); + break; + } + mutex_unlock(&clocksource_mutex); + + return ret ? ret : count; +} + +/** * sysfs_show_available_clocksources - sysfs interface for listing clocksource * @dev: unused * @attr: unused @@ -886,6 +1013,8 @@ sysfs_show_available_clocksources(struct device *dev, static DEVICE_ATTR(current_clocksource, 0644, sysfs_show_current_clocksources, sysfs_override_clocksource); +static DEVICE_ATTR(unbind_clocksource, 0200, NULL, sysfs_unbind_clocksource); + static DEVICE_ATTR(available_clocksource, 0444, sysfs_show_available_clocksources, NULL); @@ -910,6 +1039,9 @@ static int __init init_clocksource_sysfs(void) &device_clocksource, &dev_attr_current_clocksource); if (!error) + error = device_create_file(&device_clocksource, + &dev_attr_unbind_clocksource); + if (!error) error = device_create_file( &device_clocksource, &dev_attr_available_clocksource); diff --git a/kernel/time/sched_clock.c b/kernel/time/sched_clock.c new file mode 100644 index 000000000000..a326f27d7f09 --- /dev/null +++ b/kernel/time/sched_clock.c @@ -0,0 +1,212 @@ +/* + * sched_clock.c: support for extending counters to full 64-bit ns counter + * + * 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 + * published by the Free Software Foundation. + */ +#include <linux/clocksource.h> +#include <linux/init.h> +#include <linux/jiffies.h> +#include <linux/kernel.h> +#include <linux/moduleparam.h> +#include <linux/sched.h> +#include <linux/syscore_ops.h> +#include <linux/timer.h> +#include <linux/sched_clock.h> + +struct clock_data { + u64 epoch_ns; + u32 epoch_cyc; + u32 epoch_cyc_copy; + unsigned long rate; + u32 mult; + u32 shift; + bool suspended; +}; + +static void sched_clock_poll(unsigned long wrap_ticks); +static DEFINE_TIMER(sched_clock_timer, sched_clock_poll, 0, 0); +static int irqtime = -1; + +core_param(irqtime, irqtime, int, 0400); + +static struct clock_data cd = { + .mult = NSEC_PER_SEC / HZ, +}; + +static u32 __read_mostly sched_clock_mask = 0xffffffff; + +static u32 notrace jiffy_sched_clock_read(void) +{ + return (u32)(jiffies - INITIAL_JIFFIES); +} + +static u32 __read_mostly (*read_sched_clock)(void) = jiffy_sched_clock_read; + +static inline u64 notrace cyc_to_ns(u64 cyc, u32 mult, u32 shift) +{ + return (cyc * mult) >> shift; +} + +static unsigned long long notrace sched_clock_32(void) +{ + u64 epoch_ns; + u32 epoch_cyc; + u32 cyc; + + if (cd.suspended) + return cd.epoch_ns; + + /* + * Load the epoch_cyc and epoch_ns atomically. We do this by + * ensuring that we always write epoch_cyc, epoch_ns and + * epoch_cyc_copy in strict order, and read them in strict order. + * If epoch_cyc and epoch_cyc_copy are not equal, then we're in + * the middle of an update, and we should repeat the load. + */ + do { + epoch_cyc = cd.epoch_cyc; + smp_rmb(); + epoch_ns = cd.epoch_ns; + smp_rmb(); + } while (epoch_cyc != cd.epoch_cyc_copy); + + cyc = read_sched_clock(); + cyc = (cyc - epoch_cyc) & sched_clock_mask; + return epoch_ns + cyc_to_ns(cyc, cd.mult, cd.shift); +} + +/* + * Atomically update the sched_clock epoch. + */ +static void notrace update_sched_clock(void) +{ + unsigned long flags; + u32 cyc; + u64 ns; + + cyc = read_sched_clock(); + ns = cd.epoch_ns + + cyc_to_ns((cyc - cd.epoch_cyc) & sched_clock_mask, + cd.mult, cd.shift); + /* + * Write epoch_cyc and epoch_ns in a way that the update is + * detectable in cyc_to_fixed_sched_clock(). + */ + raw_local_irq_save(flags); + cd.epoch_cyc_copy = cyc; + smp_wmb(); + cd.epoch_ns = ns; + smp_wmb(); + cd.epoch_cyc = cyc; + raw_local_irq_restore(flags); +} + +static void sched_clock_poll(unsigned long wrap_ticks) +{ + mod_timer(&sched_clock_timer, round_jiffies(jiffies + wrap_ticks)); + update_sched_clock(); +} + +void __init setup_sched_clock(u32 (*read)(void), int bits, unsigned long rate) +{ + unsigned long r, w; + u64 res, wrap; + char r_unit; + + if (cd.rate > rate) + return; + + BUG_ON(bits > 32); + WARN_ON(!irqs_disabled()); + read_sched_clock = read; + sched_clock_mask = (1 << bits) - 1; + cd.rate = rate; + + /* calculate the mult/shift to convert counter ticks to ns. */ + clocks_calc_mult_shift(&cd.mult, &cd.shift, rate, NSEC_PER_SEC, 0); + + r = rate; + if (r >= 4000000) { + r /= 1000000; + r_unit = 'M'; + } else if (r >= 1000) { + r /= 1000; + r_unit = 'k'; + } else + r_unit = ' '; + + /* calculate how many ns until we wrap */ + wrap = cyc_to_ns((1ULL << bits) - 1, cd.mult, cd.shift); + do_div(wrap, NSEC_PER_MSEC); + w = wrap; + + /* calculate the ns resolution of this counter */ + res = cyc_to_ns(1ULL, cd.mult, cd.shift); + pr_info("sched_clock: %u bits at %lu%cHz, resolution %lluns, wraps every %lums\n", + bits, r, r_unit, res, w); + + /* + * Start the timer to keep sched_clock() properly updated and + * sets the initial epoch. + */ + sched_clock_timer.data = msecs_to_jiffies(w - (w / 10)); + update_sched_clock(); + + /* + * Ensure that sched_clock() starts off at 0ns + */ + cd.epoch_ns = 0; + + /* Enable IRQ time accounting if we have a fast enough sched_clock */ + if (irqtime > 0 || (irqtime == -1 && rate >= 1000000)) + enable_sched_clock_irqtime(); + + pr_debug("Registered %pF as sched_clock source\n", read); +} + +unsigned long long __read_mostly (*sched_clock_func)(void) = sched_clock_32; + +unsigned long long notrace sched_clock(void) +{ + return sched_clock_func(); +} + +void __init sched_clock_postinit(void) +{ + /* + * 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) + setup_sched_clock(jiffy_sched_clock_read, 32, HZ); + + sched_clock_poll(sched_clock_timer.data); +} + +static int sched_clock_suspend(void) +{ + sched_clock_poll(sched_clock_timer.data); + cd.suspended = true; + return 0; +} + +static void sched_clock_resume(void) +{ + cd.epoch_cyc = read_sched_clock(); + cd.epoch_cyc_copy = cd.epoch_cyc; + cd.suspended = false; +} + +static struct syscore_ops sched_clock_ops = { + .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.c b/kernel/time/tick-broadcast.c index 20d6fba70652..218bcb565fed 100644 --- a/kernel/time/tick-broadcast.c +++ b/kernel/time/tick-broadcast.c @@ -19,6 +19,7 @@ #include <linux/profile.h> #include <linux/sched.h> #include <linux/smp.h> +#include <linux/module.h> #include "tick-internal.h" @@ -29,6 +30,7 @@ static struct tick_device tick_broadcast_device; 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; @@ -64,17 +66,34 @@ static void tick_broadcast_start_periodic(struct clock_event_device *bc) /* * Check, if the device can be utilized as broadcast device: */ -int tick_check_broadcast_device(struct clock_event_device *dev) +static bool tick_check_broadcast_device(struct clock_event_device *curdev, + struct clock_event_device *newdev) +{ + if ((newdev->features & CLOCK_EVT_FEAT_DUMMY) || + (newdev->features & CLOCK_EVT_FEAT_C3STOP)) + return false; + + if (tick_broadcast_device.mode == TICKDEV_MODE_ONESHOT && + !(newdev->features & CLOCK_EVT_FEAT_ONESHOT)) + return false; + + return !curdev || newdev->rating > curdev->rating; +} + +/* + * Conditionally install/replace broadcast device + */ +void tick_install_broadcast_device(struct clock_event_device *dev) { struct clock_event_device *cur = tick_broadcast_device.evtdev; - if ((dev->features & CLOCK_EVT_FEAT_DUMMY) || - (tick_broadcast_device.evtdev && - tick_broadcast_device.evtdev->rating >= dev->rating) || - (dev->features & CLOCK_EVT_FEAT_C3STOP)) - return 0; + if (!tick_check_broadcast_device(cur, dev)) + return; + + if (!try_module_get(dev->owner)) + return; - clockevents_exchange_device(tick_broadcast_device.evtdev, dev); + clockevents_exchange_device(cur, dev); if (cur) cur->event_handler = clockevents_handle_noop; tick_broadcast_device.evtdev = dev; @@ -90,7 +109,6 @@ int tick_check_broadcast_device(struct clock_event_device *dev) */ if (dev->features & CLOCK_EVT_FEAT_ONESHOT) tick_clock_notify(); - return 1; } /* @@ -123,8 +141,9 @@ static void tick_device_setup_broadcast_func(struct clock_event_device *dev) */ int tick_device_uses_broadcast(struct clock_event_device *dev, int cpu) { + struct clock_event_device *bc = tick_broadcast_device.evtdev; unsigned long flags; - int ret = 0; + int ret; raw_spin_lock_irqsave(&tick_broadcast_lock, flags); @@ -138,20 +157,62 @@ int tick_device_uses_broadcast(struct clock_event_device *dev, int cpu) dev->event_handler = tick_handle_periodic; tick_device_setup_broadcast_func(dev); cpumask_set_cpu(cpu, tick_broadcast_mask); - tick_broadcast_start_periodic(tick_broadcast_device.evtdev); + if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC) + tick_broadcast_start_periodic(bc); + else + tick_broadcast_setup_oneshot(bc); ret = 1; } else { /* - * When the new device is not affected by the stop - * feature and the cpu is marked in the broadcast mask - * then clear the broadcast bit. + * Clear the broadcast bit for this cpu if the + * device is not power state affected. */ - if (!(dev->features & CLOCK_EVT_FEAT_C3STOP)) { - int cpu = smp_processor_id(); + if (!(dev->features & CLOCK_EVT_FEAT_C3STOP)) cpumask_clear_cpu(cpu, tick_broadcast_mask); - tick_broadcast_clear_oneshot(cpu); - } else { + else tick_device_setup_broadcast_func(dev); + + /* + * Clear the broadcast bit if the CPU is not in + * periodic broadcast on state. + */ + if (!cpumask_test_cpu(cpu, tick_broadcast_on)) + cpumask_clear_cpu(cpu, tick_broadcast_mask); + + switch (tick_broadcast_device.mode) { + case TICKDEV_MODE_ONESHOT: + /* + * If the system is in oneshot mode we can + * unconditionally clear the oneshot mask bit, + * because the CPU is running and therefore + * not in an idle state which causes the power + * state affected device to stop. Let the + * caller initialize the device. + */ + tick_broadcast_clear_oneshot(cpu); + ret = 0; + break; + + case TICKDEV_MODE_PERIODIC: + /* + * If the system is in periodic mode, check + * whether the broadcast device can be + * switched off now. + */ + if (cpumask_empty(tick_broadcast_mask) && bc) + clockevents_shutdown(bc); + /* + * If we kept the cpu in the broadcast mask, + * tell the caller to leave the per cpu device + * in shutdown state. The periodic interrupt + * is delivered by the broadcast device. + */ + ret = cpumask_test_cpu(cpu, tick_broadcast_mask); + break; + default: + /* Nothing to do */ + ret = 0; + break; } } raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags); @@ -281,6 +342,7 @@ static void tick_do_broadcast_on_off(unsigned long *reason) switch (*reason) { case CLOCK_EVT_NOTIFY_BROADCAST_ON: case CLOCK_EVT_NOTIFY_BROADCAST_FORCE: + 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) @@ -290,8 +352,12 @@ static void tick_do_broadcast_on_off(unsigned long *reason) tick_broadcast_force = 1; break; case CLOCK_EVT_NOTIFY_BROADCAST_OFF: - if (!tick_broadcast_force && - cpumask_test_and_clear_cpu(cpu, tick_broadcast_mask)) { + if (tick_broadcast_force) + break; + cpumask_clear_cpu(cpu, tick_broadcast_on); + if (!tick_device_is_functional(dev)) + break; + if (cpumask_test_and_clear_cpu(cpu, tick_broadcast_mask)) { if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC) tick_setup_periodic(dev, 0); @@ -349,6 +415,7 @@ void tick_shutdown_broadcast(unsigned int *cpup) bc = tick_broadcast_device.evtdev; cpumask_clear_cpu(cpu, tick_broadcast_mask); + cpumask_clear_cpu(cpu, tick_broadcast_on); if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC) { if (bc && cpumask_empty(tick_broadcast_mask)) @@ -475,7 +542,15 @@ void tick_check_oneshot_broadcast(int cpu) if (cpumask_test_cpu(cpu, tick_broadcast_oneshot_mask)) { struct tick_device *td = &per_cpu(tick_cpu_device, cpu); - clockevents_set_mode(td->evtdev, CLOCK_EVT_MODE_ONESHOT); + /* + * We might be in the middle of switching over from + * periodic to oneshot. If the CPU has not yet + * switched over, leave the device alone. + */ + if (td->mode == TICKDEV_MODE_ONESHOT) { + clockevents_set_mode(td->evtdev, + CLOCK_EVT_MODE_ONESHOT); + } } } @@ -522,6 +597,13 @@ again: cpumask_clear(tick_broadcast_force_mask); /* + * Sanity check. Catch the case where we try to broadcast to + * offline cpus. + */ + if (WARN_ON_ONCE(!cpumask_subset(tmpmask, cpu_online_mask))) + cpumask_and(tmpmask, tmpmask, cpu_online_mask); + + /* * Wakeup the cpus which have an expired event. */ tick_do_broadcast(tmpmask); @@ -761,10 +843,12 @@ void tick_shutdown_broadcast_oneshot(unsigned int *cpup) raw_spin_lock_irqsave(&tick_broadcast_lock, flags); /* - * Clear the broadcast mask flag for the dead cpu, but do not - * stop the broadcast device! + * Clear the broadcast masks for the dead cpu, but do not stop + * the broadcast device! */ cpumask_clear_cpu(cpu, tick_broadcast_oneshot_mask); + cpumask_clear_cpu(cpu, tick_broadcast_pending_mask); + cpumask_clear_cpu(cpu, tick_broadcast_force_mask); raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags); } @@ -792,6 +876,7 @@ bool tick_broadcast_oneshot_available(void) void __init tick_broadcast_init(void) { zalloc_cpumask_var(&tick_broadcast_mask, GFP_NOWAIT); + zalloc_cpumask_var(&tick_broadcast_on, GFP_NOWAIT); zalloc_cpumask_var(&tmpmask, GFP_NOWAIT); #ifdef CONFIG_TICK_ONESHOT zalloc_cpumask_var(&tick_broadcast_oneshot_mask, GFP_NOWAIT); diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c index 5d3fb100bc06..64522ecdfe0e 100644 --- a/kernel/time/tick-common.c +++ b/kernel/time/tick-common.c @@ -18,6 +18,7 @@ #include <linux/percpu.h> #include <linux/profile.h> #include <linux/sched.h> +#include <linux/module.h> #include <asm/irq_regs.h> @@ -33,7 +34,6 @@ DEFINE_PER_CPU(struct tick_device, tick_cpu_device); ktime_t tick_next_period; ktime_t tick_period; int tick_do_timer_cpu __read_mostly = TICK_DO_TIMER_BOOT; -static DEFINE_RAW_SPINLOCK(tick_device_lock); /* * Debugging: see timer_list.c @@ -194,7 +194,8 @@ static void tick_setup_device(struct tick_device *td, * When global broadcasting is active, check if the current * device is registered as a placeholder for broadcast mode. * This allows us to handle this x86 misfeature in a generic - * way. + * way. This function also returns !=0 when we keep the + * current active broadcast state for this CPU. */ if (tick_device_uses_broadcast(newdev, cpu)) return; @@ -205,17 +206,75 @@ static void tick_setup_device(struct tick_device *td, tick_setup_oneshot(newdev, handler, next_event); } +void tick_install_replacement(struct clock_event_device *newdev) +{ + struct tick_device *td = &__get_cpu_var(tick_cpu_device); + int cpu = smp_processor_id(); + + clockevents_exchange_device(td->evtdev, newdev); + tick_setup_device(td, newdev, cpu, cpumask_of(cpu)); + if (newdev->features & CLOCK_EVT_FEAT_ONESHOT) + tick_oneshot_notify(); +} + +static bool tick_check_percpu(struct clock_event_device *curdev, + struct clock_event_device *newdev, int cpu) +{ + if (!cpumask_test_cpu(cpu, newdev->cpumask)) + return false; + if (cpumask_equal(newdev->cpumask, cpumask_of(cpu))) + return true; + /* Check if irq affinity can be set */ + if (newdev->irq >= 0 && !irq_can_set_affinity(newdev->irq)) + return false; + /* Prefer an existing cpu local device */ + if (curdev && cpumask_equal(curdev->cpumask, cpumask_of(cpu))) + return false; + return true; +} + +static bool tick_check_preferred(struct clock_event_device *curdev, + struct clock_event_device *newdev) +{ + /* Prefer oneshot capable device */ + if (!(newdev->features & CLOCK_EVT_FEAT_ONESHOT)) { + if (curdev && (curdev->features & CLOCK_EVT_FEAT_ONESHOT)) + return false; + if (tick_oneshot_mode_active()) + return false; + } + + /* + * Use the higher rated one, but prefer a CPU local device with a lower + * rating than a non-CPU local device + */ + return !curdev || + newdev->rating > curdev->rating || + !cpumask_equal(curdev->cpumask, newdev->cpumask); +} + +/* + * Check whether the new device is a better fit than curdev. curdev + * can be NULL ! + */ +bool tick_check_replacement(struct clock_event_device *curdev, + struct clock_event_device *newdev) +{ + if (tick_check_percpu(curdev, newdev, smp_processor_id())) + return false; + + return tick_check_preferred(curdev, newdev); +} + /* - * Check, if the new registered device should be used. + * Check, if the new registered device should be used. Called with + * clockevents_lock held and interrupts disabled. */ -static int tick_check_new_device(struct clock_event_device *newdev) +void tick_check_new_device(struct clock_event_device *newdev) { struct clock_event_device *curdev; struct tick_device *td; - int cpu, ret = NOTIFY_OK; - unsigned long flags; - - raw_spin_lock_irqsave(&tick_device_lock, flags); + int cpu; cpu = smp_processor_id(); if (!cpumask_test_cpu(cpu, newdev->cpumask)) @@ -225,40 +284,15 @@ static int tick_check_new_device(struct clock_event_device *newdev) curdev = td->evtdev; /* cpu local device ? */ - if (!cpumask_equal(newdev->cpumask, cpumask_of(cpu))) { - - /* - * If the cpu affinity of the device interrupt can not - * be set, ignore it. - */ - if (!irq_can_set_affinity(newdev->irq)) - goto out_bc; + if (!tick_check_percpu(curdev, newdev, cpu)) + goto out_bc; - /* - * If we have a cpu local device already, do not replace it - * by a non cpu local device - */ - if (curdev && cpumask_equal(curdev->cpumask, cpumask_of(cpu))) - goto out_bc; - } + /* Preference decision */ + if (!tick_check_preferred(curdev, newdev)) + goto out_bc; - /* - * If we have an active device, then check the rating and the oneshot - * feature. - */ - if (curdev) { - /* - * Prefer one shot capable devices ! - */ - if ((curdev->features & CLOCK_EVT_FEAT_ONESHOT) && - !(newdev->features & CLOCK_EVT_FEAT_ONESHOT)) - goto out_bc; - /* - * Check the rating - */ - if (curdev->rating >= newdev->rating) - goto out_bc; - } + if (!try_module_get(newdev->owner)) + return; /* * Replace the eventually existing device by the new @@ -273,20 +307,13 @@ static int tick_check_new_device(struct clock_event_device *newdev) tick_setup_device(td, newdev, cpu, cpumask_of(cpu)); if (newdev->features & CLOCK_EVT_FEAT_ONESHOT) tick_oneshot_notify(); - - raw_spin_unlock_irqrestore(&tick_device_lock, flags); - return NOTIFY_STOP; + return; out_bc: /* * Can the new device be used as a broadcast device ? */ - if (tick_check_broadcast_device(newdev)) - ret = NOTIFY_STOP; - - raw_spin_unlock_irqrestore(&tick_device_lock, flags); - - return ret; + tick_install_broadcast_device(newdev); } /* @@ -294,7 +321,7 @@ out_bc: * * Called with interrupts disabled. */ -static void tick_handover_do_timer(int *cpup) +void tick_handover_do_timer(int *cpup) { if (*cpup == tick_do_timer_cpu) { int cpu = cpumask_first(cpu_online_mask); @@ -311,13 +338,11 @@ static void tick_handover_do_timer(int *cpup) * access the hardware device itself. * We just set the mode and remove it from the lists. */ -static void tick_shutdown(unsigned int *cpup) +void tick_shutdown(unsigned int *cpup) { struct tick_device *td = &per_cpu(tick_cpu_device, *cpup); struct clock_event_device *dev = td->evtdev; - unsigned long flags; - raw_spin_lock_irqsave(&tick_device_lock, flags); td->mode = TICKDEV_MODE_PERIODIC; if (dev) { /* @@ -329,26 +354,20 @@ static void tick_shutdown(unsigned int *cpup) dev->event_handler = clockevents_handle_noop; td->evtdev = NULL; } - raw_spin_unlock_irqrestore(&tick_device_lock, flags); } -static void tick_suspend(void) +void tick_suspend(void) { struct tick_device *td = &__get_cpu_var(tick_cpu_device); - unsigned long flags; - raw_spin_lock_irqsave(&tick_device_lock, flags); clockevents_shutdown(td->evtdev); - raw_spin_unlock_irqrestore(&tick_device_lock, flags); } -static void tick_resume(void) +void tick_resume(void) { struct tick_device *td = &__get_cpu_var(tick_cpu_device); - unsigned long flags; int broadcast = tick_resume_broadcast(); - raw_spin_lock_irqsave(&tick_device_lock, flags); clockevents_set_mode(td->evtdev, CLOCK_EVT_MODE_RESUME); if (!broadcast) { @@ -357,68 +376,12 @@ static void tick_resume(void) else tick_resume_oneshot(); } - raw_spin_unlock_irqrestore(&tick_device_lock, flags); } -/* - * Notification about clock event devices - */ -static int tick_notify(struct notifier_block *nb, unsigned long reason, - void *dev) -{ - switch (reason) { - - case CLOCK_EVT_NOTIFY_ADD: - return tick_check_new_device(dev); - - case CLOCK_EVT_NOTIFY_BROADCAST_ON: - case CLOCK_EVT_NOTIFY_BROADCAST_OFF: - case CLOCK_EVT_NOTIFY_BROADCAST_FORCE: - tick_broadcast_on_off(reason, dev); - break; - - case CLOCK_EVT_NOTIFY_BROADCAST_ENTER: - case CLOCK_EVT_NOTIFY_BROADCAST_EXIT: - tick_broadcast_oneshot_control(reason); - break; - - case CLOCK_EVT_NOTIFY_CPU_DYING: - tick_handover_do_timer(dev); - break; - - case CLOCK_EVT_NOTIFY_CPU_DEAD: - tick_shutdown_broadcast_oneshot(dev); - tick_shutdown_broadcast(dev); - tick_shutdown(dev); - break; - - case CLOCK_EVT_NOTIFY_SUSPEND: - tick_suspend(); - tick_suspend_broadcast(); - break; - - case CLOCK_EVT_NOTIFY_RESUME: - tick_resume(); - break; - - default: - break; - } - - return NOTIFY_OK; -} - -static struct notifier_block tick_notifier = { - .notifier_call = tick_notify, -}; - /** * tick_init - initialize the tick control - * - * Register the notifier with the clockevents framework */ void __init tick_init(void) { - clockevents_register_notifier(&tick_notifier); tick_broadcast_init(); } diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h index f0299eae4602..bc906cad709b 100644 --- a/kernel/time/tick-internal.h +++ b/kernel/time/tick-internal.h @@ -6,6 +6,8 @@ extern seqlock_t jiffies_lock; +#define CS_NAME_LEN 32 + #ifdef CONFIG_GENERIC_CLOCKEVENTS_BUILD #define TICK_DO_TIMER_NONE -1 @@ -18,9 +20,19 @@ 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_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 void clockevents_shutdown(struct clock_event_device *dev); +extern size_t sysfs_get_uname(const char *buf, char *dst, size_t cnt); + /* * NO_HZ / high resolution timer shared code */ @@ -90,7 +102,7 @@ static inline bool tick_broadcast_oneshot_available(void) { return false; } */ #ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST extern int tick_device_uses_broadcast(struct clock_event_device *dev, int cpu); -extern int tick_check_broadcast_device(struct clock_event_device *dev); +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); @@ -102,9 +114,8 @@ tick_set_periodic_handler(struct clock_event_device *dev, int broadcast); #else /* !BROADCAST */ -static inline int tick_check_broadcast_device(struct clock_event_device *dev) +static inline void tick_install_broadcast_device(struct clock_event_device *dev) { - return 0; } static inline int tick_is_broadcast_device(struct clock_event_device *dev) diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 0cf1c1453181..e77edc97e036 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -178,6 +178,11 @@ static bool can_stop_full_tick(void) */ if (!sched_clock_stable) { trace_tick_stop(0, "unstable sched clock\n"); + /* + * Don't allow the user to think they can get + * full NO_HZ with this machine. + */ + WARN_ONCE(1, "NO_HZ FULL will not work with unstable sched clock"); return false; } #endif @@ -293,7 +298,7 @@ static int __init tick_nohz_full_setup(char *str) } __setup("nohz_full=", tick_nohz_full_setup); -static int __cpuinit tick_nohz_cpu_down_callback(struct notifier_block *nfb, +static int tick_nohz_cpu_down_callback(struct notifier_block *nfb, unsigned long action, void *hcpu) { @@ -346,16 +351,6 @@ void __init tick_nohz_init(void) } cpu_notifier(tick_nohz_cpu_down_callback, 0); - - /* Make sure full dynticks CPU are also RCU nocbs */ - for_each_cpu(cpu, nohz_full_mask) { - if (!rcu_is_nocb_cpu(cpu)) { - pr_warning("NO_HZ: CPU %d is not RCU nocb: " - "cleared from nohz_full range", cpu); - cpumask_clear_cpu(cpu, nohz_full_mask); - } - } - cpulist_scnprintf(nohz_full_buf, sizeof(nohz_full_buf), nohz_full_mask); pr_info("NO_HZ: Full dynticks CPUs: %s.\n", nohz_full_buf); } @@ -832,13 +827,10 @@ void tick_nohz_irq_exit(void) { struct tick_sched *ts = &__get_cpu_var(tick_cpu_sched); - if (ts->inidle) { - /* Cancel the timer because CPU already waken up from the C-states*/ - menu_hrtimer_cancel(); + if (ts->inidle) __tick_nohz_idle_enter(ts); - } else { + else tick_nohz_full_stop_tick(ts); - } } /** @@ -936,8 +928,6 @@ void tick_nohz_idle_exit(void) ts->inidle = 0; - /* Cancel the timer because CPU already waken up from the C-states*/ - menu_hrtimer_cancel(); if (ts->idle_active || ts->tick_stopped) now = ktime_get(); diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index baeeb5c87cf1..48b9fffabdc2 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -25,6 +25,11 @@ #include "tick-internal.h" #include "ntp_internal.h" +#include "timekeeping_internal.h" + +#define TK_CLEAR_NTP (1 << 0) +#define TK_MIRROR (1 << 1) +#define TK_CLOCK_WAS_SET (1 << 2) static struct timekeeper timekeeper; static DEFINE_RAW_SPINLOCK(timekeeper_lock); @@ -200,9 +205,9 @@ static inline s64 timekeeping_get_ns_raw(struct timekeeper *tk) static RAW_NOTIFIER_HEAD(pvclock_gtod_chain); -static void update_pvclock_gtod(struct timekeeper *tk) +static void update_pvclock_gtod(struct timekeeper *tk, bool was_set) { - raw_notifier_call_chain(&pvclock_gtod_chain, 0, tk); + raw_notifier_call_chain(&pvclock_gtod_chain, was_set, tk); } /** @@ -216,7 +221,7 @@ int pvclock_gtod_register_notifier(struct notifier_block *nb) raw_spin_lock_irqsave(&timekeeper_lock, flags); ret = raw_notifier_chain_register(&pvclock_gtod_chain, nb); - update_pvclock_gtod(tk); + update_pvclock_gtod(tk, true); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); return ret; @@ -241,16 +246,16 @@ int pvclock_gtod_unregister_notifier(struct notifier_block *nb) EXPORT_SYMBOL_GPL(pvclock_gtod_unregister_notifier); /* must hold timekeeper_lock */ -static void timekeeping_update(struct timekeeper *tk, bool clearntp, bool mirror) +static void timekeeping_update(struct timekeeper *tk, unsigned int action) { - if (clearntp) { + if (action & TK_CLEAR_NTP) { tk->ntp_error = 0; ntp_clear(); } update_vsyscall(tk); - update_pvclock_gtod(tk); + update_pvclock_gtod(tk, action & TK_CLOCK_WAS_SET); - if (mirror) + if (action & TK_MIRROR) memcpy(&shadow_timekeeper, &timekeeper, sizeof(timekeeper)); } @@ -508,7 +513,7 @@ int do_settimeofday(const struct timespec *tv) tk_set_xtime(tk, tv); - timekeeping_update(tk, true, true); + timekeeping_update(tk, TK_CLEAR_NTP | TK_MIRROR | TK_CLOCK_WAS_SET); write_seqcount_end(&timekeeper_seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); @@ -552,7 +557,7 @@ int timekeeping_inject_offset(struct timespec *ts) tk_set_wall_to_mono(tk, timespec_sub(tk->wall_to_monotonic, *ts)); error: /* even if we error out, we forwarded the time, so call update */ - timekeeping_update(tk, true, true); + timekeeping_update(tk, TK_CLEAR_NTP | TK_MIRROR | TK_CLOCK_WAS_SET); write_seqcount_end(&timekeeper_seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); @@ -627,13 +632,22 @@ static int change_clocksource(void *data) write_seqcount_begin(&timekeeper_seq); timekeeping_forward_now(tk); - if (!new->enable || new->enable(new) == 0) { - old = tk->clock; - tk_setup_internals(tk, new); - if (old->disable) - old->disable(old); + /* + * If the cs is in module, get a module reference. Succeeds + * for built-in code (owner == NULL) as well. + */ + if (try_module_get(new->owner)) { + if (!new->enable || new->enable(new) == 0) { + old = tk->clock; + tk_setup_internals(tk, new); + if (old->disable) + old->disable(old); + module_put(old->owner); + } else { + module_put(new->owner); + } } - timekeeping_update(tk, true, true); + timekeeping_update(tk, TK_CLEAR_NTP | TK_MIRROR | TK_CLOCK_WAS_SET); write_seqcount_end(&timekeeper_seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); @@ -648,14 +662,15 @@ static int change_clocksource(void *data) * This function is called from clocksource.c after a new, better clock * source has been registered. The caller holds the clocksource_mutex. */ -void timekeeping_notify(struct clocksource *clock) +int timekeeping_notify(struct clocksource *clock) { struct timekeeper *tk = &timekeeper; if (tk->clock == clock) - return; + return 0; stop_machine(change_clocksource, clock, NULL); tick_clock_notify(); + return tk->clock == clock ? 0 : -1; } /** @@ -841,6 +856,7 @@ static void __timekeeping_inject_sleeptime(struct timekeeper *tk, tk_xtime_add(tk, delta); tk_set_wall_to_mono(tk, timespec_sub(tk->wall_to_monotonic, *delta)); tk_set_sleep_time(tk, timespec_add(tk->total_sleep_time, *delta)); + tk_debug_account_sleep_time(delta); } /** @@ -872,7 +888,7 @@ void timekeeping_inject_sleeptime(struct timespec *delta) __timekeeping_inject_sleeptime(tk, delta); - timekeeping_update(tk, true, true); + timekeeping_update(tk, TK_CLEAR_NTP | TK_MIRROR | TK_CLOCK_WAS_SET); write_seqcount_end(&timekeeper_seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); @@ -954,7 +970,7 @@ static void timekeeping_resume(void) tk->cycle_last = clock->cycle_last = cycle_now; tk->ntp_error = 0; timekeeping_suspended = 0; - timekeeping_update(tk, false, true); + timekeeping_update(tk, TK_MIRROR | TK_CLOCK_WAS_SET); write_seqcount_end(&timekeeper_seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); @@ -1236,9 +1252,10 @@ out_adjust: * It also calls into the NTP code to handle leapsecond processing. * */ -static inline void accumulate_nsecs_to_secs(struct timekeeper *tk) +static inline unsigned int accumulate_nsecs_to_secs(struct timekeeper *tk) { u64 nsecps = (u64)NSEC_PER_SEC << tk->shift; + unsigned int action = 0; while (tk->xtime_nsec >= nsecps) { int leap; @@ -1261,8 +1278,10 @@ static inline void accumulate_nsecs_to_secs(struct timekeeper *tk) __timekeeping_set_tai_offset(tk, tk->tai_offset - leap); clock_was_set_delayed(); + action = TK_CLOCK_WAS_SET; } } + return action; } /** @@ -1347,6 +1366,7 @@ static void update_wall_time(void) struct timekeeper *tk = &shadow_timekeeper; cycle_t offset; int shift = 0, maxshift; + unsigned int action; unsigned long flags; raw_spin_lock_irqsave(&timekeeper_lock, flags); @@ -1399,7 +1419,7 @@ static void update_wall_time(void) * Finally, make sure that after the rounding * xtime_nsec isn't larger than NSEC_PER_SEC */ - accumulate_nsecs_to_secs(tk); + action = accumulate_nsecs_to_secs(tk); write_seqcount_begin(&timekeeper_seq); /* Update clock->cycle_last with the new value */ @@ -1415,7 +1435,7 @@ static void update_wall_time(void) * updating. */ memcpy(real_tk, tk, sizeof(*tk)); - timekeeping_update(real_tk, false, false); + timekeeping_update(real_tk, action); write_seqcount_end(&timekeeper_seq); out: raw_spin_unlock_irqrestore(&timekeeper_lock, flags); @@ -1677,6 +1697,7 @@ int do_adjtimex(struct timex *txc) if (tai != orig_tai) { __timekeeping_set_tai_offset(tk, tai); + update_pvclock_gtod(tk, true); clock_was_set_delayed(); } write_seqcount_end(&timekeeper_seq); diff --git a/kernel/time/timekeeping_debug.c b/kernel/time/timekeeping_debug.c new file mode 100644 index 000000000000..802433a4f5eb --- /dev/null +++ b/kernel/time/timekeeping_debug.c @@ -0,0 +1,72 @@ +/* + * debugfs file to track time spent in suspend + * + * Copyright (c) 2011, Google, Inc. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + */ + +#include <linux/debugfs.h> +#include <linux/err.h> +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/seq_file.h> +#include <linux/time.h> + +static unsigned int sleep_time_bin[32] = {0}; + +static int tk_debug_show_sleep_time(struct seq_file *s, void *data) +{ + unsigned int bin; + seq_puts(s, " time (secs) count\n"); + seq_puts(s, "------------------------------\n"); + for (bin = 0; bin < 32; bin++) { + if (sleep_time_bin[bin] == 0) + continue; + seq_printf(s, "%10u - %-10u %4u\n", + bin ? 1 << (bin - 1) : 0, 1 << bin, + sleep_time_bin[bin]); + } + return 0; +} + +static int tk_debug_sleep_time_open(struct inode *inode, struct file *file) +{ + return single_open(file, tk_debug_show_sleep_time, NULL); +} + +static const struct file_operations tk_debug_sleep_time_fops = { + .open = tk_debug_sleep_time_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static int __init tk_debug_sleep_time_init(void) +{ + struct dentry *d; + + d = debugfs_create_file("sleep_time", 0444, NULL, NULL, + &tk_debug_sleep_time_fops); + if (!d) { + pr_err("Failed to create sleep_time debug file\n"); + return -ENOMEM; + } + + return 0; +} +late_initcall(tk_debug_sleep_time_init); + +void tk_debug_account_sleep_time(struct timespec *t) +{ + sleep_time_bin[fls(t->tv_sec)]++; +} + diff --git a/kernel/time/timekeeping_internal.h b/kernel/time/timekeeping_internal.h new file mode 100644 index 000000000000..13323ea08ffa --- /dev/null +++ b/kernel/time/timekeeping_internal.h @@ -0,0 +1,14 @@ +#ifndef _TIMEKEEPING_INTERNAL_H +#define _TIMEKEEPING_INTERNAL_H +/* + * timekeeping debug functions + */ +#include <linux/time.h> + +#ifdef CONFIG_DEBUG_FS +extern void tk_debug_account_sleep_time(struct timespec *t); +#else +#define tk_debug_account_sleep_time(x) +#endif + +#endif /* _TIMEKEEPING_INTERNAL_H */ diff --git a/kernel/timer.c b/kernel/timer.c index 15ffdb3f1948..4296d13db3d1 100644 --- a/kernel/timer.c +++ b/kernel/timer.c @@ -149,9 +149,11 @@ static unsigned long round_jiffies_common(unsigned long j, int cpu, /* now that we have rounded, subtract the extra skew again */ j -= cpu * 3; - if (j <= jiffies) /* rounding ate our timeout entirely; */ - return original; - return j; + /* + * Make sure j is still in the future. Otherwise return the + * unmodified value. + */ + return time_is_after_jiffies(j) ? j : original; } /** @@ -1503,11 +1505,11 @@ signed long __sched schedule_timeout_uninterruptible(signed long timeout) } EXPORT_SYMBOL(schedule_timeout_uninterruptible); -static int __cpuinit init_timers_cpu(int cpu) +static int init_timers_cpu(int cpu) { int j; struct tvec_base *base; - static char __cpuinitdata tvec_base_done[NR_CPUS]; + static char tvec_base_done[NR_CPUS]; if (!tvec_base_done[cpu]) { static char boot_done; @@ -1575,7 +1577,7 @@ static void migrate_timer_list(struct tvec_base *new_base, struct list_head *hea } } -static void __cpuinit migrate_timers(int cpu) +static void migrate_timers(int cpu) { struct tvec_base *old_base; struct tvec_base *new_base; @@ -1608,7 +1610,7 @@ static void __cpuinit migrate_timers(int cpu) } #endif /* CONFIG_HOTPLUG_CPU */ -static int __cpuinit timer_cpu_notify(struct notifier_block *self, +static int timer_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu) { long cpu = (long)hcpu; @@ -1633,7 +1635,7 @@ static int __cpuinit timer_cpu_notify(struct notifier_block *self, return NOTIFY_OK; } -static struct notifier_block __cpuinitdata timers_nb = { +static struct notifier_block timers_nb = { .notifier_call = timer_cpu_notify, }; diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 6c508ff33c62..a6d098c6df3f 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -413,6 +413,17 @@ static int __register_ftrace_function(struct ftrace_ops *ops) return 0; } +static void ftrace_sync(struct work_struct *work) +{ + /* + * This function is just a stub to implement a hard force + * of synchronize_sched(). This requires synchronizing + * tasks even in userspace and idle. + * + * Yes, function tracing is rude. + */ +} + static int __unregister_ftrace_function(struct ftrace_ops *ops) { int ret; @@ -440,8 +451,12 @@ static int __unregister_ftrace_function(struct ftrace_ops *ops) * so there'll be no new users. We must ensure * all current users are done before we free * the control data. + * Note synchronize_sched() is not enough, as we + * use preempt_disable() to do RCU, but the function + * tracer can be called where RCU is not active + * (before user_exit()). */ - synchronize_sched(); + schedule_on_each_cpu(ftrace_sync); control_ops_free(ops); } } else @@ -456,9 +471,13 @@ static int __unregister_ftrace_function(struct ftrace_ops *ops) /* * Dynamic ops may be freed, we must make sure that all * callers are done before leaving this function. + * + * Again, normal synchronize_sched() is not good enough. + * We need to do a hard force of sched synchronization. */ if (ops->flags & FTRACE_OPS_FL_DYNAMIC) - synchronize_sched(); + schedule_on_each_cpu(ftrace_sync); + return 0; } @@ -622,12 +641,18 @@ static int function_stat_show(struct seq_file *m, void *v) if (rec->counter <= 1) stddev = 0; else { - stddev = rec->time_squared - rec->counter * avg * avg; + /* + * Apply Welford's method: + * s^2 = 1 / (n * (n-1)) * (n * \Sum (x_i)^2 - (\Sum x_i)^2) + */ + stddev = rec->counter * rec->time_squared - + rec->time * rec->time; + /* * Divide only 1000 for ns^2 -> us^2 conversion. * trace_print_graph_duration will divide 1000 again. */ - do_div(stddev, (rec->counter - 1) * 1000); + do_div(stddev, rec->counter * (rec->counter - 1) * 1000); } trace_seq_init(&s); @@ -1416,12 +1441,22 @@ ftrace_hash_move(struct ftrace_ops *ops, int enable, * the hashes are freed with call_rcu_sched(). */ static int -ftrace_ops_test(struct ftrace_ops *ops, unsigned long ip) +ftrace_ops_test(struct ftrace_ops *ops, unsigned long ip, void *regs) { struct ftrace_hash *filter_hash; struct ftrace_hash *notrace_hash; int ret; +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS + /* + * There's a small race when adding ops that the ftrace handler + * that wants regs, may be called without them. We can not + * allow that handler to be called if regs is NULL. + */ + if (regs == NULL && (ops->flags & FTRACE_OPS_FL_SAVE_REGS)) + return 0; +#endif + filter_hash = rcu_dereference_raw_notrace(ops->filter_hash); notrace_hash = rcu_dereference_raw_notrace(ops->notrace_hash); @@ -2134,12 +2169,57 @@ static cycle_t ftrace_update_time; static unsigned long ftrace_update_cnt; unsigned long ftrace_update_tot_cnt; -static int ops_traces_mod(struct ftrace_ops *ops) +static inline int ops_traces_mod(struct ftrace_ops *ops) { - struct ftrace_hash *hash; + /* + * Filter_hash being empty will default to trace module. + * But notrace hash requires a test of individual module functions. + */ + return ftrace_hash_empty(ops->filter_hash) && + ftrace_hash_empty(ops->notrace_hash); +} + +/* + * Check if the current ops references the record. + * + * If the ops traces all functions, then it was already accounted for. + * If the ops does not trace the current record function, skip it. + * If the ops ignores the function via notrace filter, skip it. + */ +static inline bool +ops_references_rec(struct ftrace_ops *ops, struct dyn_ftrace *rec) +{ + /* If ops isn't enabled, ignore it */ + if (!(ops->flags & FTRACE_OPS_FL_ENABLED)) + return 0; - hash = ops->filter_hash; - return ftrace_hash_empty(hash); + /* If ops traces all mods, we already accounted for it */ + if (ops_traces_mod(ops)) + return 0; + + /* The function must be in the filter */ + if (!ftrace_hash_empty(ops->filter_hash) && + !ftrace_lookup_ip(ops->filter_hash, rec->ip)) + return 0; + + /* If in notrace hash, we ignore it too */ + if (ftrace_lookup_ip(ops->notrace_hash, rec->ip)) + return 0; + + return 1; +} + +static int referenced_filters(struct dyn_ftrace *rec) +{ + struct ftrace_ops *ops; + int cnt = 0; + + for (ops = ftrace_ops_list; ops != &ftrace_list_end; ops = ops->next) { + if (ops_references_rec(ops, rec)) + cnt++; + } + + return cnt; } static int ftrace_update_code(struct module *mod) @@ -2148,6 +2228,7 @@ static int ftrace_update_code(struct module *mod) struct dyn_ftrace *p; cycle_t start, stop; unsigned long ref = 0; + bool test = false; int i; /* @@ -2161,9 +2242,12 @@ static int ftrace_update_code(struct module *mod) for (ops = ftrace_ops_list; ops != &ftrace_list_end; ops = ops->next) { - if (ops->flags & FTRACE_OPS_FL_ENABLED && - ops_traces_mod(ops)) - ref++; + if (ops->flags & FTRACE_OPS_FL_ENABLED) { + if (ops_traces_mod(ops)) + ref++; + else + test = true; + } } } @@ -2173,12 +2257,16 @@ static int ftrace_update_code(struct module *mod) for (pg = ftrace_new_pgs; pg; pg = pg->next) { for (i = 0; i < pg->index; i++) { + int cnt = ref; + /* If something went wrong, bail without enabling anything */ if (unlikely(ftrace_disabled)) return -1; p = &pg->records[i]; - p->flags = ref; + if (test) + cnt += referenced_filters(p); + p->flags = cnt; /* * Do the initial record conversion from mcount jump @@ -2198,7 +2286,7 @@ static int ftrace_update_code(struct module *mod) * conversion puts the module to the correct state, thus * passing the ftrace_make_call check. */ - if (ftrace_start_up && ref) { + if (ftrace_start_up && cnt) { int failed = __ftrace_replace_code(p, 1); if (failed) ftrace_bug(failed, p->ip); @@ -3349,6 +3437,12 @@ ftrace_match_addr(struct ftrace_hash *hash, unsigned long ip, int remove) return add_hash_entry(hash, ip); } +static void ftrace_ops_update_code(struct ftrace_ops *ops) +{ + if (ops->flags & FTRACE_OPS_FL_ENABLED && ftrace_enabled) + ftrace_run_update_code(FTRACE_UPDATE_CALLS); +} + static int ftrace_set_hash(struct ftrace_ops *ops, unsigned char *buf, int len, unsigned long ip, int remove, int reset, int enable) @@ -3391,9 +3485,8 @@ ftrace_set_hash(struct ftrace_ops *ops, unsigned char *buf, int len, mutex_lock(&ftrace_lock); ret = ftrace_hash_move(ops, enable, orig_hash, hash); - if (!ret && ops->flags & FTRACE_OPS_FL_ENABLED - && ftrace_enabled) - ftrace_run_update_code(FTRACE_UPDATE_CALLS); + if (!ret) + ftrace_ops_update_code(ops); mutex_unlock(&ftrace_lock); @@ -3512,8 +3605,12 @@ EXPORT_SYMBOL_GPL(ftrace_set_global_notrace); static char ftrace_notrace_buf[FTRACE_FILTER_SIZE] __initdata; static char ftrace_filter_buf[FTRACE_FILTER_SIZE] __initdata; +/* Used by function selftest to not test if filter is set */ +bool ftrace_filter_param __initdata; + static int __init set_ftrace_notrace(char *str) { + ftrace_filter_param = true; strlcpy(ftrace_notrace_buf, str, FTRACE_FILTER_SIZE); return 1; } @@ -3521,6 +3618,7 @@ __setup("ftrace_notrace=", set_ftrace_notrace); static int __init set_ftrace_filter(char *str) { + ftrace_filter_param = true; strlcpy(ftrace_filter_buf, str, FTRACE_FILTER_SIZE); return 1; } @@ -3615,9 +3713,8 @@ int ftrace_regex_release(struct inode *inode, struct file *file) mutex_lock(&ftrace_lock); ret = ftrace_hash_move(iter->ops, filter_hash, orig_hash, iter->hash); - if (!ret && (iter->ops->flags & FTRACE_OPS_FL_ENABLED) - && ftrace_enabled) - ftrace_run_update_code(FTRACE_UPDATE_CALLS); + if (!ret) + ftrace_ops_update_code(iter->ops); mutex_unlock(&ftrace_lock); } @@ -4188,7 +4285,7 @@ static inline void ftrace_startup_enable(int command) { } # define ftrace_shutdown_sysctl() do { } while (0) static inline int -ftrace_ops_test(struct ftrace_ops *ops, unsigned long ip) +ftrace_ops_test(struct ftrace_ops *ops, unsigned long ip, void *regs) { return 1; } @@ -4211,7 +4308,7 @@ ftrace_ops_control_func(unsigned long ip, unsigned long parent_ip, do_for_each_ftrace_op(op, ftrace_control_list) { if (!(op->flags & FTRACE_OPS_FL_STUB) && !ftrace_function_local_disabled(op) && - ftrace_ops_test(op, ip)) + ftrace_ops_test(op, ip, regs)) op->func(ip, parent_ip, op, regs); } while_for_each_ftrace_op(op); trace_recursion_clear(TRACE_CONTROL_BIT); @@ -4244,7 +4341,7 @@ __ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip, */ preempt_disable_notrace(); do_for_each_ftrace_op(op, ftrace_ops_list) { - if (ftrace_ops_test(op, ip)) + if (ftrace_ops_test(op, ip, regs)) op->func(ip, parent_ip, op, regs); } while_for_each_ftrace_op(op); preempt_enable_notrace(); diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index e444ff88f0a4..cc2f66f68dc5 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -36,11 +36,11 @@ int ring_buffer_print_entry_header(struct trace_seq *s) { int ret; - ret = trace_seq_printf(s, "# compressed entry header\n"); - ret = trace_seq_printf(s, "\ttype_len : 5 bits\n"); - ret = trace_seq_printf(s, "\ttime_delta : 27 bits\n"); - ret = trace_seq_printf(s, "\tarray : 32 bits\n"); - ret = trace_seq_printf(s, "\n"); + ret = trace_seq_puts(s, "# compressed entry header\n"); + ret = trace_seq_puts(s, "\ttype_len : 5 bits\n"); + ret = trace_seq_puts(s, "\ttime_delta : 27 bits\n"); + ret = trace_seq_puts(s, "\tarray : 32 bits\n"); + ret = trace_seq_putc(s, '\n'); ret = trace_seq_printf(s, "\tpadding : type == %d\n", RINGBUF_TYPE_PADDING); ret = trace_seq_printf(s, "\ttime_extend : type == %d\n", @@ -1066,7 +1066,7 @@ static int rb_check_list(struct ring_buffer_per_cpu *cpu_buffer, } /** - * check_pages - integrity check of buffer pages + * rb_check_pages - integrity check of buffer pages * @cpu_buffer: CPU buffer with pages to test * * As a safety measure we check to make sure the data pages have not @@ -1258,7 +1258,7 @@ static int rb_cpu_notify(struct notifier_block *self, #endif /** - * ring_buffer_alloc - allocate a new ring_buffer + * __ring_buffer_alloc - allocate a new ring_buffer * @size: the size in bytes per cpu that is needed. * @flags: attributes to set for the ring buffer. * @@ -1607,6 +1607,7 @@ static void update_pages_handler(struct work_struct *work) * ring_buffer_resize - resize the ring buffer * @buffer: the buffer to resize. * @size: the new size. + * @cpu_id: the cpu buffer to resize * * Minimum size is 2 * BUF_PAGE_SIZE. * @@ -3956,11 +3957,11 @@ EXPORT_SYMBOL_GPL(ring_buffer_consume); * expected. * * After a sequence of ring_buffer_read_prepare calls, the user is - * expected to make at least one call to ring_buffer_prepare_sync. + * expected to make at least one call to ring_buffer_read_prepare_sync. * Afterwards, ring_buffer_read_start is invoked to get things going * for real. * - * This overall must be paired with ring_buffer_finish. + * This overall must be paired with ring_buffer_read_finish. */ struct ring_buffer_iter * ring_buffer_read_prepare(struct ring_buffer *buffer, int cpu) @@ -4009,7 +4010,7 @@ EXPORT_SYMBOL_GPL(ring_buffer_read_prepare_sync); * an intervening ring_buffer_read_prepare_sync must have been * performed. * - * Must be paired with ring_buffer_finish. + * Must be paired with ring_buffer_read_finish. */ void ring_buffer_read_start(struct ring_buffer_iter *iter) @@ -4031,7 +4032,7 @@ ring_buffer_read_start(struct ring_buffer_iter *iter) EXPORT_SYMBOL_GPL(ring_buffer_read_start); /** - * ring_buffer_finish - finish reading the iterator of the buffer + * ring_buffer_read_finish - finish reading the iterator of the buffer * @iter: The iterator retrieved by ring_buffer_start * * This re-enables the recording to the buffer, and frees the @@ -4346,6 +4347,7 @@ EXPORT_SYMBOL_GPL(ring_buffer_swap_cpu); /** * ring_buffer_alloc_read_page - allocate a page to read from buffer * @buffer: the buffer to allocate for. + * @cpu: the cpu buffer to allocate. * * This function is used in conjunction with ring_buffer_read_page. * When reading a full page from the ring buffer, these functions @@ -4403,7 +4405,7 @@ EXPORT_SYMBOL_GPL(ring_buffer_free_read_page); * to swap with a page in the ring buffer. * * for example: - * rpage = ring_buffer_alloc_read_page(buffer); + * rpage = ring_buffer_alloc_read_page(buffer, cpu); * if (!rpage) * return error; * ret = ring_buffer_read_page(buffer, &rpage, len, cpu, 0); diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index e71a8be4a6ee..496f94d57698 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -115,6 +115,9 @@ cpumask_var_t __read_mostly tracing_buffer_mask; enum ftrace_dump_mode ftrace_dump_on_oops; +/* When set, tracing will stop when a WARN*() is hit */ +int __disable_trace_on_warning; + static int tracing_set_tracer(const char *buf); #define MAX_TRACER_SIZE 100 @@ -149,6 +152,13 @@ static int __init set_ftrace_dump_on_oops(char *str) } __setup("ftrace_dump_on_oops", set_ftrace_dump_on_oops); +static int __init stop_trace_on_warning(char *str) +{ + __disable_trace_on_warning = 1; + return 1; +} +__setup("traceoff_on_warning=", stop_trace_on_warning); + static int __init boot_alloc_snapshot(char *str) { allocate_snapshot = true; @@ -170,6 +180,7 @@ static int __init set_trace_boot_options(char *str) } __setup("trace_options=", set_trace_boot_options); + unsigned long long ns2usecs(cycle_t nsec) { nsec += 500; @@ -193,6 +204,37 @@ static struct trace_array global_trace; LIST_HEAD(ftrace_trace_arrays); +int trace_array_get(struct trace_array *this_tr) +{ + struct trace_array *tr; + int ret = -ENODEV; + + mutex_lock(&trace_types_lock); + list_for_each_entry(tr, &ftrace_trace_arrays, list) { + if (tr == this_tr) { + tr->ref++; + ret = 0; + break; + } + } + mutex_unlock(&trace_types_lock); + + return ret; +} + +static void __trace_array_put(struct trace_array *this_tr) +{ + WARN_ON(!this_tr->ref); + this_tr->ref--; +} + +void trace_array_put(struct trace_array *this_tr) +{ + mutex_lock(&trace_types_lock); + __trace_array_put(this_tr); + mutex_unlock(&trace_types_lock); +} + int filter_current_check_discard(struct ring_buffer *buffer, struct ftrace_event_call *call, void *rec, struct ring_buffer_event *event) @@ -201,23 +243,43 @@ int filter_current_check_discard(struct ring_buffer *buffer, } EXPORT_SYMBOL_GPL(filter_current_check_discard); -cycle_t ftrace_now(int cpu) +cycle_t buffer_ftrace_now(struct trace_buffer *buf, int cpu) { u64 ts; /* Early boot up does not have a buffer yet */ - if (!global_trace.trace_buffer.buffer) + if (!buf->buffer) return trace_clock_local(); - ts = ring_buffer_time_stamp(global_trace.trace_buffer.buffer, cpu); - ring_buffer_normalize_time_stamp(global_trace.trace_buffer.buffer, cpu, &ts); + ts = ring_buffer_time_stamp(buf->buffer, cpu); + ring_buffer_normalize_time_stamp(buf->buffer, cpu, &ts); return ts; } +cycle_t ftrace_now(int cpu) +{ + return buffer_ftrace_now(&global_trace.trace_buffer, cpu); +} + +/** + * tracing_is_enabled - Show if global_trace has been disabled + * + * Shows if the global trace has been enabled or not. It uses the + * mirror flag "buffer_disabled" to be used in fast paths such as for + * the irqsoff tracer. But it may be inaccurate due to races. If you + * need to know the accurate state, use tracing_is_on() which is a little + * slower, but accurate. + */ int tracing_is_enabled(void) { - return tracing_is_on(); + /* + * For quick access (irqsoff uses this in fast path), just + * return the mirror variable of the state of the ring buffer. + * It's a little racy, but we don't really care. + */ + smp_rmb(); + return !global_trace.buffer_disabled; } /* @@ -240,7 +302,7 @@ static struct tracer *trace_types __read_mostly; /* * trace_types_lock is used to protect the trace_types list. */ -static DEFINE_MUTEX(trace_types_lock); +DEFINE_MUTEX(trace_types_lock); /* * serialize the access of the ring buffer @@ -330,6 +392,23 @@ unsigned long trace_flags = TRACE_ITER_PRINT_PARENT | TRACE_ITER_PRINTK | TRACE_ITER_GRAPH_TIME | TRACE_ITER_RECORD_CMD | TRACE_ITER_OVERWRITE | TRACE_ITER_IRQ_INFO | TRACE_ITER_MARKERS | TRACE_ITER_FUNCTION; +static void tracer_tracing_on(struct trace_array *tr) +{ + if (tr->trace_buffer.buffer) + ring_buffer_record_on(tr->trace_buffer.buffer); + /* + * This flag is looked at when buffers haven't been allocated + * yet, or by some tracers (like irqsoff), that just want to + * know if the ring buffer has been disabled, but it can handle + * races of where it gets disabled but we still do a record. + * As the check is in the fast path of the tracers, it is more + * important to be fast than accurate. + */ + tr->buffer_disabled = 0; + /* Make the flag seen by readers */ + smp_wmb(); +} + /** * tracing_on - enable tracing buffers * @@ -338,15 +417,7 @@ unsigned long trace_flags = TRACE_ITER_PRINT_PARENT | TRACE_ITER_PRINTK | */ void tracing_on(void) { - if (global_trace.trace_buffer.buffer) - ring_buffer_record_on(global_trace.trace_buffer.buffer); - /* - * This flag is only looked at when buffers haven't been - * allocated yet. We don't really care about the race - * between setting this flag and actually turning - * on the buffer. - */ - global_trace.buffer_disabled = 0; + tracer_tracing_on(&global_trace); } EXPORT_SYMBOL_GPL(tracing_on); @@ -540,6 +611,23 @@ void tracing_snapshot_alloc(void) EXPORT_SYMBOL_GPL(tracing_snapshot_alloc); #endif /* CONFIG_TRACER_SNAPSHOT */ +static void tracer_tracing_off(struct trace_array *tr) +{ + if (tr->trace_buffer.buffer) + ring_buffer_record_off(tr->trace_buffer.buffer); + /* + * This flag is looked at when buffers haven't been allocated + * yet, or by some tracers (like irqsoff), that just want to + * know if the ring buffer has been disabled, but it can handle + * races of where it gets disabled but we still do a record. + * As the check is in the fast path of the tracers, it is more + * important to be fast than accurate. + */ + tr->buffer_disabled = 1; + /* Make the flag seen by readers */ + smp_wmb(); +} + /** * tracing_off - turn off tracing buffers * @@ -550,26 +638,35 @@ EXPORT_SYMBOL_GPL(tracing_snapshot_alloc); */ void tracing_off(void) { - if (global_trace.trace_buffer.buffer) - ring_buffer_record_off(global_trace.trace_buffer.buffer); - /* - * This flag is only looked at when buffers haven't been - * allocated yet. We don't really care about the race - * between setting this flag and actually turning - * on the buffer. - */ - global_trace.buffer_disabled = 1; + tracer_tracing_off(&global_trace); } EXPORT_SYMBOL_GPL(tracing_off); +void disable_trace_on_warning(void) +{ + if (__disable_trace_on_warning) + tracing_off(); +} + +/** + * tracer_tracing_is_on - show real state of ring buffer enabled + * @tr : the trace array to know if ring buffer is enabled + * + * Shows real state of the ring buffer if it is enabled or not. + */ +static int tracer_tracing_is_on(struct trace_array *tr) +{ + if (tr->trace_buffer.buffer) + return ring_buffer_record_is_on(tr->trace_buffer.buffer); + return !tr->buffer_disabled; +} + /** * tracing_is_on - show state of ring buffers enabled */ int tracing_is_on(void) { - if (global_trace.trace_buffer.buffer) - return ring_buffer_record_is_on(global_trace.trace_buffer.buffer); - return !global_trace.buffer_disabled; + return tracer_tracing_is_on(&global_trace); } EXPORT_SYMBOL_GPL(tracing_is_on); @@ -1119,7 +1216,7 @@ void tracing_reset_online_cpus(struct trace_buffer *buf) /* Make sure all commits have finished */ synchronize_sched(); - buf->time_start = ftrace_now(buf->cpu); + buf->time_start = buffer_ftrace_now(buf, buf->cpu); for_each_online_cpu(cpu) ring_buffer_reset_cpu(buffer, cpu); @@ -1127,23 +1224,17 @@ void tracing_reset_online_cpus(struct trace_buffer *buf) ring_buffer_record_enable(buffer); } -void tracing_reset_current(int cpu) -{ - tracing_reset(&global_trace.trace_buffer, cpu); -} - +/* Must have trace_types_lock held */ void tracing_reset_all_online_cpus(void) { struct trace_array *tr; - mutex_lock(&trace_types_lock); list_for_each_entry(tr, &ftrace_trace_arrays, list) { tracing_reset_online_cpus(&tr->trace_buffer); #ifdef CONFIG_TRACER_MAX_TRACE tracing_reset_online_cpus(&tr->max_buffer); #endif } - mutex_unlock(&trace_types_lock); } #define SAVED_CMDLINES 128 @@ -1543,15 +1634,6 @@ trace_function(struct trace_array *tr, __buffer_unlock_commit(buffer, event); } -void -ftrace(struct trace_array *tr, struct trace_array_cpu *data, - unsigned long ip, unsigned long parent_ip, unsigned long flags, - int pc) -{ - if (likely(!atomic_read(&data->disabled))) - trace_function(tr, ip, parent_ip, flags, pc); -} - #ifdef CONFIG_STACKTRACE #define FTRACE_STACK_MAX_ENTRIES (PAGE_SIZE / sizeof(unsigned long)) @@ -2760,6 +2842,17 @@ static int s_show(struct seq_file *m, void *v) return 0; } +/* + * Should be used after trace_array_get(), trace_types_lock + * ensures that i_cdev was already initialized. + */ +static inline int tracing_get_cpu(struct inode *inode) +{ + if (inode->i_cdev) /* See trace_create_cpu_file() */ + return (long)inode->i_cdev - 1; + return RING_BUFFER_ALL_CPUS; +} + static const struct seq_operations tracer_seq_ops = { .start = s_start, .next = s_next, @@ -2770,8 +2863,7 @@ static const struct seq_operations tracer_seq_ops = { static struct trace_iterator * __tracing_open(struct inode *inode, struct file *file, bool snapshot) { - struct trace_cpu *tc = inode->i_private; - struct trace_array *tr = tc->tr; + struct trace_array *tr = inode->i_private; struct trace_iterator *iter; int cpu; @@ -2812,8 +2904,8 @@ __tracing_open(struct inode *inode, struct file *file, bool snapshot) iter->trace_buffer = &tr->trace_buffer; iter->snapshot = snapshot; iter->pos = -1; + iter->cpu_file = tracing_get_cpu(inode); mutex_init(&iter->mutex); - iter->cpu_file = tc->cpu; /* Notify the tracer early; before we stop tracing. */ if (iter->trace && iter->trace->open) @@ -2850,8 +2942,6 @@ __tracing_open(struct inode *inode, struct file *file, bool snapshot) tracing_iter_reset(iter, cpu); } - tr->ref++; - mutex_unlock(&trace_types_lock); return iter; @@ -2874,24 +2964,41 @@ int tracing_open_generic(struct inode *inode, struct file *filp) return 0; } +/* + * Open and update trace_array ref count. + * Must have the current trace_array passed to it. + */ +static int tracing_open_generic_tr(struct inode *inode, struct file *filp) +{ + struct trace_array *tr = inode->i_private; + + if (tracing_disabled) + return -ENODEV; + + if (trace_array_get(tr) < 0) + return -ENODEV; + + filp->private_data = inode->i_private; + + return 0; +} + static int tracing_release(struct inode *inode, struct file *file) { + struct trace_array *tr = inode->i_private; struct seq_file *m = file->private_data; struct trace_iterator *iter; - struct trace_array *tr; int cpu; - if (!(file->f_mode & FMODE_READ)) + if (!(file->f_mode & FMODE_READ)) { + trace_array_put(tr); return 0; + } + /* Writes do not use seq_file */ iter = m->private; - tr = iter->tr; - mutex_lock(&trace_types_lock); - WARN_ON(!tr->ref); - tr->ref--; - for_each_tracing_cpu(cpu) { if (iter->buffer_iter[cpu]) ring_buffer_read_finish(iter->buffer_iter[cpu]); @@ -2903,6 +3010,9 @@ static int tracing_release(struct inode *inode, struct file *file) if (!iter->snapshot) /* reenable tracing if it was previously enabled */ tracing_start_tr(tr); + + __trace_array_put(tr); + mutex_unlock(&trace_types_lock); mutex_destroy(&iter->mutex); @@ -2910,24 +3020,44 @@ static int tracing_release(struct inode *inode, struct file *file) kfree(iter->trace); kfree(iter->buffer_iter); seq_release_private(inode, file); + + return 0; +} + +static int tracing_release_generic_tr(struct inode *inode, struct file *file) +{ + struct trace_array *tr = inode->i_private; + + trace_array_put(tr); return 0; } +static int tracing_single_release_tr(struct inode *inode, struct file *file) +{ + struct trace_array *tr = inode->i_private; + + trace_array_put(tr); + + return single_release(inode, file); +} + static int tracing_open(struct inode *inode, struct file *file) { + struct trace_array *tr = inode->i_private; struct trace_iterator *iter; int ret = 0; + if (trace_array_get(tr) < 0) + return -ENODEV; + /* If this file was open for write, then erase contents */ - if ((file->f_mode & FMODE_WRITE) && - (file->f_flags & O_TRUNC)) { - struct trace_cpu *tc = inode->i_private; - struct trace_array *tr = tc->tr; + if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) { + int cpu = tracing_get_cpu(inode); - if (tc->cpu == RING_BUFFER_ALL_CPUS) + if (cpu == RING_BUFFER_ALL_CPUS) tracing_reset_online_cpus(&tr->trace_buffer); else - tracing_reset(&tr->trace_buffer, tc->cpu); + tracing_reset(&tr->trace_buffer, cpu); } if (file->f_mode & FMODE_READ) { @@ -2937,6 +3067,10 @@ static int tracing_open(struct inode *inode, struct file *file) else if (trace_flags & TRACE_ITER_LATENCY_FMT) iter->iter_flags |= TRACE_FILE_LAT_FMT; } + + if (ret < 0) + trace_array_put(tr); + return ret; } @@ -3293,17 +3427,27 @@ tracing_trace_options_write(struct file *filp, const char __user *ubuf, static int tracing_trace_options_open(struct inode *inode, struct file *file) { + struct trace_array *tr = inode->i_private; + int ret; + if (tracing_disabled) return -ENODEV; - return single_open(file, tracing_trace_options_show, inode->i_private); + if (trace_array_get(tr) < 0) + return -ENODEV; + + ret = single_open(file, tracing_trace_options_show, inode->i_private); + if (ret < 0) + trace_array_put(tr); + + return ret; } static const struct file_operations tracing_iter_fops = { .open = tracing_trace_options_open, .read = seq_read, .llseek = seq_lseek, - .release = single_release, + .release = tracing_single_release_tr, .write = tracing_trace_options_write, }; @@ -3379,14 +3523,14 @@ static const char readme_msg[] = "\n snapshot\t\t- Like 'trace' but shows the content of the static snapshot buffer\n" "\t\t\t Read the contents for more information\n" #endif -#ifdef CONFIG_STACKTRACE +#ifdef CONFIG_STACK_TRACER " stack_trace\t\t- Shows the max stack trace when active\n" " stack_max_size\t- Shows current max stack size that was traced\n" "\t\t\t Write into this file to reset the max size (trigger a new trace)\n" #ifdef CONFIG_DYNAMIC_FTRACE " stack_trace_filter\t- Like set_ftrace_filter but limits what stack_trace traces\n" #endif -#endif /* CONFIG_STACKTRACE */ +#endif /* CONFIG_STACK_TRACER */ ; static ssize_t @@ -3783,20 +3927,23 @@ tracing_max_lat_write(struct file *filp, const char __user *ubuf, static int tracing_open_pipe(struct inode *inode, struct file *filp) { - struct trace_cpu *tc = inode->i_private; - struct trace_array *tr = tc->tr; + struct trace_array *tr = inode->i_private; struct trace_iterator *iter; int ret = 0; if (tracing_disabled) return -ENODEV; + if (trace_array_get(tr) < 0) + return -ENODEV; + mutex_lock(&trace_types_lock); /* create a buffer to store the information to pass to userspace */ iter = kzalloc(sizeof(*iter), GFP_KERNEL); if (!iter) { ret = -ENOMEM; + __trace_array_put(tr); goto out; } @@ -3826,9 +3973,9 @@ static int tracing_open_pipe(struct inode *inode, struct file *filp) if (trace_clocks[tr->clock_id].in_ns) iter->iter_flags |= TRACE_FILE_TIME_IN_NS; - iter->cpu_file = tc->cpu; - iter->tr = tc->tr; - iter->trace_buffer = &tc->tr->trace_buffer; + iter->tr = tr; + iter->trace_buffer = &tr->trace_buffer; + iter->cpu_file = tracing_get_cpu(inode); mutex_init(&iter->mutex); filp->private_data = iter; @@ -3843,6 +3990,7 @@ out: fail: kfree(iter->trace); kfree(iter); + __trace_array_put(tr); mutex_unlock(&trace_types_lock); return ret; } @@ -3850,6 +3998,7 @@ fail: static int tracing_release_pipe(struct inode *inode, struct file *file) { struct trace_iterator *iter = file->private_data; + struct trace_array *tr = inode->i_private; mutex_lock(&trace_types_lock); @@ -3863,6 +4012,8 @@ static int tracing_release_pipe(struct inode *inode, struct file *file) kfree(iter->trace); kfree(iter); + trace_array_put(tr); + return 0; } @@ -3939,7 +4090,7 @@ static int tracing_wait_pipe(struct file *filp) * * iter->pos will be 0 if we haven't read anything. */ - if (!tracing_is_enabled() && iter->pos) + if (!tracing_is_on() && iter->pos) break; } @@ -4000,6 +4151,7 @@ waitagain: memset(&iter->seq, 0, sizeof(struct trace_iterator) - offsetof(struct trace_iterator, seq)); + cpumask_clear(iter->started); iter->pos = -1; trace_event_read_lock(); @@ -4200,15 +4352,16 @@ static ssize_t tracing_entries_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) { - struct trace_cpu *tc = filp->private_data; - struct trace_array *tr = tc->tr; + struct inode *inode = file_inode(filp); + struct trace_array *tr = inode->i_private; + int cpu = tracing_get_cpu(inode); char buf[64]; int r = 0; ssize_t ret; mutex_lock(&trace_types_lock); - if (tc->cpu == RING_BUFFER_ALL_CPUS) { + if (cpu == RING_BUFFER_ALL_CPUS) { int cpu, buf_size_same; unsigned long size; @@ -4235,7 +4388,7 @@ tracing_entries_read(struct file *filp, char __user *ubuf, } else r = sprintf(buf, "X\n"); } else - r = sprintf(buf, "%lu\n", per_cpu_ptr(tr->trace_buffer.data, tc->cpu)->entries >> 10); + r = sprintf(buf, "%lu\n", per_cpu_ptr(tr->trace_buffer.data, cpu)->entries >> 10); mutex_unlock(&trace_types_lock); @@ -4247,7 +4400,8 @@ static ssize_t tracing_entries_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *ppos) { - struct trace_cpu *tc = filp->private_data; + struct inode *inode = file_inode(filp); + struct trace_array *tr = inode->i_private; unsigned long val; int ret; @@ -4261,8 +4415,7 @@ tracing_entries_write(struct file *filp, const char __user *ubuf, /* value is in KB */ val <<= 10; - - ret = tracing_resize_ring_buffer(tc->tr, val, tc->cpu); + ret = tracing_resize_ring_buffer(tr, val, tracing_get_cpu(inode)); if (ret < 0) return ret; @@ -4316,10 +4469,12 @@ tracing_free_buffer_release(struct inode *inode, struct file *filp) /* disable tracing ? */ if (trace_flags & TRACE_ITER_STOP_ON_FREE) - tracing_off(); + tracer_tracing_off(tr); /* resize the ring buffer to 0 */ tracing_resize_ring_buffer(tr, 0, RING_BUFFER_ALL_CPUS); + trace_array_put(tr); + return 0; } @@ -4328,6 +4483,7 @@ tracing_mark_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *fpos) { unsigned long addr = (unsigned long)ubuf; + struct trace_array *tr = filp->private_data; struct ring_buffer_event *event; struct ring_buffer *buffer; struct print_entry *entry; @@ -4387,7 +4543,7 @@ tracing_mark_write(struct file *filp, const char __user *ubuf, local_save_flags(irq_flags); size = sizeof(*entry) + cnt + 2; /* possible \n added */ - buffer = global_trace.trace_buffer.buffer; + buffer = tr->trace_buffer.buffer; event = trace_buffer_lock_reserve(buffer, TRACE_PRINT, size, irq_flags, preempt_count()); if (!event) { @@ -4478,12 +4634,12 @@ static ssize_t tracing_clock_write(struct file *filp, const char __user *ubuf, * New clock may not be consistent with the previous clock. * Reset the buffer so that it doesn't have incomparable timestamps. */ - tracing_reset_online_cpus(&global_trace.trace_buffer); + tracing_reset_online_cpus(&tr->trace_buffer); #ifdef CONFIG_TRACER_MAX_TRACE if (tr->flags & TRACE_ARRAY_FL_GLOBAL && tr->max_buffer.buffer) ring_buffer_set_clock(tr->max_buffer.buffer, trace_clocks[i].func); - tracing_reset_online_cpus(&global_trace.max_buffer); + tracing_reset_online_cpus(&tr->max_buffer); #endif mutex_unlock(&trace_types_lock); @@ -4495,10 +4651,20 @@ static ssize_t tracing_clock_write(struct file *filp, const char __user *ubuf, static int tracing_clock_open(struct inode *inode, struct file *file) { + struct trace_array *tr = inode->i_private; + int ret; + if (tracing_disabled) return -ENODEV; - return single_open(file, tracing_clock_show, inode->i_private); + if (trace_array_get(tr)) + return -ENODEV; + + ret = single_open(file, tracing_clock_show, inode->i_private); + if (ret < 0) + trace_array_put(tr); + + return ret; } struct ftrace_buffer_info { @@ -4510,31 +4676,40 @@ struct ftrace_buffer_info { #ifdef CONFIG_TRACER_SNAPSHOT static int tracing_snapshot_open(struct inode *inode, struct file *file) { - struct trace_cpu *tc = inode->i_private; + struct trace_array *tr = inode->i_private; struct trace_iterator *iter; struct seq_file *m; int ret = 0; + if (trace_array_get(tr) < 0) + return -ENODEV; + if (file->f_mode & FMODE_READ) { iter = __tracing_open(inode, file, true); if (IS_ERR(iter)) ret = PTR_ERR(iter); } else { /* Writes still need the seq_file to hold the private data */ + ret = -ENOMEM; m = kzalloc(sizeof(*m), GFP_KERNEL); if (!m) - return -ENOMEM; + goto out; iter = kzalloc(sizeof(*iter), GFP_KERNEL); if (!iter) { kfree(m); - return -ENOMEM; + goto out; } - iter->tr = tc->tr; - iter->trace_buffer = &tc->tr->max_buffer; - iter->cpu_file = tc->cpu; + ret = 0; + + iter->tr = tr; + iter->trace_buffer = &tr->max_buffer; + iter->cpu_file = tracing_get_cpu(inode); m->private = iter; file->private_data = m; } +out: + if (ret < 0) + trace_array_put(tr); return ret; } @@ -4616,9 +4791,12 @@ out: static int tracing_snapshot_release(struct inode *inode, struct file *file) { struct seq_file *m = file->private_data; + int ret; + + ret = tracing_release(inode, file); if (file->f_mode & FMODE_READ) - return tracing_release(inode, file); + return ret; /* If write only, the seq_file is just a stub */ if (m) @@ -4684,34 +4862,38 @@ static const struct file_operations tracing_pipe_fops = { }; static const struct file_operations tracing_entries_fops = { - .open = tracing_open_generic, + .open = tracing_open_generic_tr, .read = tracing_entries_read, .write = tracing_entries_write, .llseek = generic_file_llseek, + .release = tracing_release_generic_tr, }; static const struct file_operations tracing_total_entries_fops = { - .open = tracing_open_generic, + .open = tracing_open_generic_tr, .read = tracing_total_entries_read, .llseek = generic_file_llseek, + .release = tracing_release_generic_tr, }; static const struct file_operations tracing_free_buffer_fops = { + .open = tracing_open_generic_tr, .write = tracing_free_buffer_write, .release = tracing_free_buffer_release, }; static const struct file_operations tracing_mark_fops = { - .open = tracing_open_generic, + .open = tracing_open_generic_tr, .write = tracing_mark_write, .llseek = generic_file_llseek, + .release = tracing_release_generic_tr, }; static const struct file_operations trace_clock_fops = { .open = tracing_clock_open, .read = seq_read, .llseek = seq_lseek, - .release = single_release, + .release = tracing_single_release_tr, .write = tracing_clock_write, }; @@ -4736,23 +4918,26 @@ static const struct file_operations snapshot_raw_fops = { static int tracing_buffers_open(struct inode *inode, struct file *filp) { - struct trace_cpu *tc = inode->i_private; - struct trace_array *tr = tc->tr; + struct trace_array *tr = inode->i_private; struct ftrace_buffer_info *info; + int ret; if (tracing_disabled) return -ENODEV; + if (trace_array_get(tr) < 0) + return -ENODEV; + info = kzalloc(sizeof(*info), GFP_KERNEL); - if (!info) + if (!info) { + trace_array_put(tr); return -ENOMEM; + } mutex_lock(&trace_types_lock); - tr->ref++; - info->iter.tr = tr; - info->iter.cpu_file = tc->cpu; + info->iter.cpu_file = tracing_get_cpu(inode); info->iter.trace = tr->current_trace; info->iter.trace_buffer = &tr->trace_buffer; info->spare = NULL; @@ -4763,7 +4948,11 @@ static int tracing_buffers_open(struct inode *inode, struct file *filp) mutex_unlock(&trace_types_lock); - return nonseekable_open(inode, filp); + ret = nonseekable_open(inode, filp); + if (ret < 0) + trace_array_put(tr); + + return ret; } static unsigned int @@ -4863,8 +5052,7 @@ static int tracing_buffers_release(struct inode *inode, struct file *file) mutex_lock(&trace_types_lock); - WARN_ON(!iter->tr->ref); - iter->tr->ref--; + __trace_array_put(iter->tr); if (info->spare) ring_buffer_free_read_page(iter->trace_buffer->buffer, info->spare); @@ -5066,14 +5254,14 @@ static ssize_t tracing_stats_read(struct file *filp, char __user *ubuf, size_t count, loff_t *ppos) { - struct trace_cpu *tc = filp->private_data; - struct trace_array *tr = tc->tr; + struct inode *inode = file_inode(filp); + struct trace_array *tr = inode->i_private; struct trace_buffer *trace_buf = &tr->trace_buffer; + int cpu = tracing_get_cpu(inode); struct trace_seq *s; unsigned long cnt; unsigned long long t; unsigned long usec_rem; - int cpu = tc->cpu; s = kmalloc(sizeof(*s), GFP_KERNEL); if (!s) @@ -5126,9 +5314,10 @@ tracing_stats_read(struct file *filp, char __user *ubuf, } static const struct file_operations tracing_stats_fops = { - .open = tracing_open_generic, + .open = tracing_open_generic_tr, .read = tracing_stats_read, .llseek = generic_file_llseek, + .release = tracing_release_generic_tr, }; #ifdef CONFIG_DYNAMIC_FTRACE @@ -5317,10 +5506,20 @@ static struct dentry *tracing_dentry_percpu(struct trace_array *tr, int cpu) return tr->percpu_dir; } +static struct dentry * +trace_create_cpu_file(const char *name, umode_t mode, struct dentry *parent, + void *data, long cpu, const struct file_operations *fops) +{ + struct dentry *ret = trace_create_file(name, mode, parent, data, fops); + + if (ret) /* See tracing_get_cpu() */ + ret->d_inode->i_cdev = (void *)(cpu + 1); + return ret; +} + static void tracing_init_debugfs_percpu(struct trace_array *tr, long cpu) { - struct trace_array_cpu *data = per_cpu_ptr(tr->trace_buffer.data, cpu); struct dentry *d_percpu = tracing_dentry_percpu(tr, cpu); struct dentry *d_cpu; char cpu_dir[30]; /* 30 characters should be more than enough */ @@ -5336,28 +5535,28 @@ tracing_init_debugfs_percpu(struct trace_array *tr, long cpu) } /* per cpu trace_pipe */ - trace_create_file("trace_pipe", 0444, d_cpu, - (void *)&data->trace_cpu, &tracing_pipe_fops); + trace_create_cpu_file("trace_pipe", 0444, d_cpu, + tr, cpu, &tracing_pipe_fops); /* per cpu trace */ - trace_create_file("trace", 0644, d_cpu, - (void *)&data->trace_cpu, &tracing_fops); + trace_create_cpu_file("trace", 0644, d_cpu, + tr, cpu, &tracing_fops); - trace_create_file("trace_pipe_raw", 0444, d_cpu, - (void *)&data->trace_cpu, &tracing_buffers_fops); + trace_create_cpu_file("trace_pipe_raw", 0444, d_cpu, + tr, cpu, &tracing_buffers_fops); - trace_create_file("stats", 0444, d_cpu, - (void *)&data->trace_cpu, &tracing_stats_fops); + trace_create_cpu_file("stats", 0444, d_cpu, + tr, cpu, &tracing_stats_fops); - trace_create_file("buffer_size_kb", 0444, d_cpu, - (void *)&data->trace_cpu, &tracing_entries_fops); + trace_create_cpu_file("buffer_size_kb", 0444, d_cpu, + tr, cpu, &tracing_entries_fops); #ifdef CONFIG_TRACER_SNAPSHOT - trace_create_file("snapshot", 0644, d_cpu, - (void *)&data->trace_cpu, &snapshot_fops); + trace_create_cpu_file("snapshot", 0644, d_cpu, + tr, cpu, &snapshot_fops); - trace_create_file("snapshot_raw", 0444, d_cpu, - (void *)&data->trace_cpu, &snapshot_raw_fops); + trace_create_cpu_file("snapshot_raw", 0444, d_cpu, + tr, cpu, &snapshot_raw_fops); #endif } @@ -5612,15 +5811,10 @@ rb_simple_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) { struct trace_array *tr = filp->private_data; - struct ring_buffer *buffer = tr->trace_buffer.buffer; char buf[64]; int r; - if (buffer) - r = ring_buffer_record_is_on(buffer); - else - r = 0; - + r = tracer_tracing_is_on(tr); r = sprintf(buf, "%d\n", r); return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); @@ -5642,11 +5836,11 @@ rb_simple_write(struct file *filp, const char __user *ubuf, if (buffer) { mutex_lock(&trace_types_lock); if (val) { - ring_buffer_record_on(buffer); + tracer_tracing_on(tr); if (tr->current_trace->start) tr->current_trace->start(tr); } else { - ring_buffer_record_off(buffer); + tracer_tracing_off(tr); if (tr->current_trace->stop) tr->current_trace->stop(tr); } @@ -5659,9 +5853,10 @@ rb_simple_write(struct file *filp, const char __user *ubuf, } static const struct file_operations rb_simple_fops = { - .open = tracing_open_generic, + .open = tracing_open_generic_tr, .read = rb_simple_read, .write = rb_simple_write, + .release = tracing_release_generic_tr, .llseek = default_llseek, }; @@ -5670,17 +5865,6 @@ struct dentry *trace_instance_dir; static void init_tracer_debugfs(struct trace_array *tr, struct dentry *d_tracer); -static void init_trace_buffers(struct trace_array *tr, struct trace_buffer *buf) -{ - int cpu; - - for_each_tracing_cpu(cpu) { - memset(per_cpu_ptr(buf->data, cpu), 0, sizeof(struct trace_array_cpu)); - per_cpu_ptr(buf->data, cpu)->trace_cpu.cpu = cpu; - per_cpu_ptr(buf->data, cpu)->trace_cpu.tr = tr; - } -} - static int allocate_trace_buffer(struct trace_array *tr, struct trace_buffer *buf, int size) { @@ -5698,8 +5882,6 @@ allocate_trace_buffer(struct trace_array *tr, struct trace_buffer *buf, int size return -ENOMEM; } - init_trace_buffers(tr, buf); - /* Allocate the first page for all buffers */ set_buffer_entries(&tr->trace_buffer, ring_buffer_size(tr->trace_buffer.buffer, 0)); @@ -5766,17 +5948,15 @@ static int new_instance_create(const char *name) if (allocate_trace_buffers(tr, trace_buf_size) < 0) goto out_free_tr; - /* Holder for file callbacks */ - tr->trace_cpu.cpu = RING_BUFFER_ALL_CPUS; - tr->trace_cpu.tr = tr; - tr->dir = debugfs_create_dir(name, trace_instance_dir); if (!tr->dir) goto out_free_tr; ret = event_trace_add_tracer(tr->dir, tr); - if (ret) + if (ret) { + debugfs_remove_recursive(tr->dir); goto out_free_tr; + } init_tracer_debugfs(tr, tr->dir); @@ -5922,18 +6102,18 @@ init_tracer_debugfs(struct trace_array *tr, struct dentry *d_tracer) tr, &tracing_iter_fops); trace_create_file("trace", 0644, d_tracer, - (void *)&tr->trace_cpu, &tracing_fops); + tr, &tracing_fops); trace_create_file("trace_pipe", 0444, d_tracer, - (void *)&tr->trace_cpu, &tracing_pipe_fops); + tr, &tracing_pipe_fops); trace_create_file("buffer_size_kb", 0644, d_tracer, - (void *)&tr->trace_cpu, &tracing_entries_fops); + tr, &tracing_entries_fops); trace_create_file("buffer_total_size_kb", 0444, d_tracer, tr, &tracing_total_entries_fops); - trace_create_file("free_buffer", 0644, d_tracer, + trace_create_file("free_buffer", 0200, d_tracer, tr, &tracing_free_buffer_fops); trace_create_file("trace_marker", 0220, d_tracer, @@ -5943,11 +6123,11 @@ init_tracer_debugfs(struct trace_array *tr, struct dentry *d_tracer) &trace_clock_fops); trace_create_file("tracing_on", 0644, d_tracer, - tr, &rb_simple_fops); + tr, &rb_simple_fops); #ifdef CONFIG_TRACER_SNAPSHOT trace_create_file("snapshot", 0644, d_tracer, - (void *)&tr->trace_cpu, &snapshot_fops); + tr, &snapshot_fops); #endif for_each_tracing_cpu(cpu) @@ -6241,10 +6421,6 @@ __init static int tracer_alloc_buffers(void) global_trace.flags = TRACE_ARRAY_FL_GLOBAL; - /* Holder for file callbacks */ - global_trace.trace_cpu.cpu = RING_BUFFER_ALL_CPUS; - global_trace.trace_cpu.tr = &global_trace; - INIT_LIST_HEAD(&global_trace.systems); INIT_LIST_HEAD(&global_trace.events); list_add(&global_trace.list, &ftrace_trace_arrays); diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 20572ed88c5c..afaae41b0a02 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -130,19 +130,12 @@ enum trace_flag_type { struct trace_array; -struct trace_cpu { - struct trace_array *tr; - struct dentry *dir; - int cpu; -}; - /* * The CPU trace array - it consists of thousands of trace entries * plus some other descriptor data: (for example which task started * the trace, etc.) */ struct trace_array_cpu { - struct trace_cpu trace_cpu; atomic_t disabled; void *buffer_page; /* ring buffer spare */ @@ -196,7 +189,6 @@ struct trace_array { bool allocated_snapshot; #endif int buffer_disabled; - struct trace_cpu trace_cpu; /* place holder */ #ifdef CONFIG_FTRACE_SYSCALLS int sys_refcount_enter; int sys_refcount_exit; @@ -214,7 +206,6 @@ struct trace_array { struct dentry *event_dir; struct list_head systems; struct list_head events; - struct task_struct *waiter; int ref; }; @@ -224,6 +215,11 @@ enum { extern struct list_head ftrace_trace_arrays; +extern struct mutex trace_types_lock; + +extern int trace_array_get(struct trace_array *tr); +extern void trace_array_put(struct trace_array *tr); + /* * The global tracer (top) should be the first trace array added, * but we check the flag anyway. @@ -554,11 +550,6 @@ void tracing_iter_reset(struct trace_iterator *iter, int cpu); void poll_wait_pipe(struct trace_iterator *iter); -void ftrace(struct trace_array *tr, - struct trace_array_cpu *data, - unsigned long ip, - unsigned long parent_ip, - unsigned long flags, int pc); void tracing_sched_switch_trace(struct trace_array *tr, struct task_struct *prev, struct task_struct *next, @@ -680,6 +671,15 @@ extern int trace_selftest_startup_sched_switch(struct tracer *trace, struct trace_array *tr); extern int trace_selftest_startup_branch(struct tracer *trace, struct trace_array *tr); +/* + * Tracer data references selftest functions that only occur + * on boot up. These can be __init functions. Thus, when selftests + * are enabled, then the tracers need to reference __init functions. + */ +#define __tracer_data __refdata +#else +/* Tracers are seldom changed. Optimize when selftests are disabled. */ +#define __tracer_data __read_mostly #endif /* CONFIG_FTRACE_STARTUP_TEST */ extern void *head_page(struct trace_array_cpu *data); @@ -774,6 +774,7 @@ print_graph_function_flags(struct trace_iterator *iter, u32 flags) extern struct list_head ftrace_pids; #ifdef CONFIG_FUNCTION_TRACER +extern bool ftrace_filter_param __initdata; static inline int ftrace_trace_task(struct task_struct *task) { if (list_empty(&ftrace_pids)) @@ -899,12 +900,6 @@ static inline void trace_branch_disable(void) /* set ring buffers to default size if not already done so */ int tracing_update_buffers(void); -/* trace event type bit fields, not numeric */ -enum { - TRACE_EVENT_TYPE_PRINTF = 1, - TRACE_EVENT_TYPE_RAW = 2, -}; - struct ftrace_event_field { struct list_head link; const char *name; diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c index 84b1e045faba..80c36bcf66e8 100644 --- a/kernel/trace/trace_event_perf.c +++ b/kernel/trace/trace_event_perf.c @@ -236,6 +236,10 @@ __kprobes void *perf_trace_buf_prepare(int size, unsigned short type, BUILD_BUG_ON(PERF_MAX_TRACE_SIZE % sizeof(unsigned long)); + if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE, + "perf buffer not large enough")) + return NULL; + pc = preempt_count(); *rctxp = perf_swevent_get_recursion_context(); @@ -266,6 +270,10 @@ perf_ftrace_function_call(unsigned long ip, unsigned long parent_ip, struct pt_regs regs; int rctx; + head = this_cpu_ptr(event_function.perf_events); + if (hlist_empty(head)) + return; + #define ENTRY_SIZE (ALIGN(sizeof(struct ftrace_entry) + sizeof(u32), \ sizeof(u64)) - sizeof(u32)) @@ -279,8 +287,6 @@ perf_ftrace_function_call(unsigned long ip, unsigned long parent_ip, entry->ip = ip; entry->parent_ip = parent_ip; - - head = this_cpu_ptr(event_function.perf_events); perf_trace_buf_submit(entry, ENTRY_SIZE, rctx, 0, 1, ®s, head, NULL); diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 27963e2bf4bf..29a7ebcfb426 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -41,6 +41,23 @@ static LIST_HEAD(ftrace_common_fields); static struct kmem_cache *field_cachep; static struct kmem_cache *file_cachep; +#define SYSTEM_FL_FREE_NAME (1 << 31) + +static inline int system_refcount(struct event_subsystem *system) +{ + return system->ref_count & ~SYSTEM_FL_FREE_NAME; +} + +static int system_refcount_inc(struct event_subsystem *system) +{ + return (system->ref_count++) & ~SYSTEM_FL_FREE_NAME; +} + +static int system_refcount_dec(struct event_subsystem *system) +{ + return (--system->ref_count) & ~SYSTEM_FL_FREE_NAME; +} + /* Double loops, do not use break, only goto's work */ #define do_for_each_event_file(tr, file) \ list_for_each_entry(tr, &ftrace_trace_arrays, list) { \ @@ -97,7 +114,7 @@ static int __trace_define_field(struct list_head *head, const char *type, field = kmem_cache_alloc(field_cachep, GFP_TRACE); if (!field) - goto err; + return -ENOMEM; field->name = name; field->type = type; @@ -114,11 +131,6 @@ static int __trace_define_field(struct list_head *head, const char *type, list_add(&field->link, head); return 0; - -err: - kmem_cache_free(field_cachep, field); - - return -ENOMEM; } int trace_define_field(struct ftrace_event_call *call, const char *type, @@ -279,9 +291,11 @@ static int __ftrace_event_enable_disable(struct ftrace_event_file *file, } call->class->reg(call, TRACE_REG_UNREGISTER, file); } - /* If in SOFT_MODE, just set the SOFT_DISABLE_BIT */ + /* If in SOFT_MODE, just set the SOFT_DISABLE_BIT, else clear it */ if (file->flags & FTRACE_EVENT_FL_SOFT_MODE) set_bit(FTRACE_EVENT_FL_SOFT_DISABLED_BIT, &file->flags); + else + clear_bit(FTRACE_EVENT_FL_SOFT_DISABLED_BIT, &file->flags); break; case 1: /* @@ -349,8 +363,8 @@ static void __put_system(struct event_subsystem *system) { struct event_filter *filter = system->filter; - WARN_ON_ONCE(system->ref_count == 0); - if (--system->ref_count) + WARN_ON_ONCE(system_refcount(system) == 0); + if (system_refcount_dec(system)) return; list_del(&system->list); @@ -359,13 +373,15 @@ static void __put_system(struct event_subsystem *system) kfree(filter->filter_string); kfree(filter); } + if (system->ref_count & SYSTEM_FL_FREE_NAME) + kfree(system->name); kfree(system); } static void __get_system(struct event_subsystem *system) { - WARN_ON_ONCE(system->ref_count == 0); - system->ref_count++; + WARN_ON_ONCE(system_refcount(system) == 0); + system_refcount_inc(system); } static void __get_system_dir(struct ftrace_subsystem_dir *dir) @@ -379,7 +395,7 @@ static void __put_system_dir(struct ftrace_subsystem_dir *dir) { WARN_ON_ONCE(dir->ref_count == 0); /* If the subsystem is about to be freed, the dir must be too */ - WARN_ON_ONCE(dir->subsystem->ref_count == 1 && dir->ref_count != 1); + WARN_ON_ONCE(system_refcount(dir->subsystem) == 1 && dir->ref_count != 1); __put_system(dir->subsystem); if (!--dir->ref_count) @@ -393,17 +409,55 @@ static void put_system(struct ftrace_subsystem_dir *dir) mutex_unlock(&event_mutex); } +static void remove_subsystem(struct ftrace_subsystem_dir *dir) +{ + if (!dir) + return; + + if (!--dir->nr_events) { + debugfs_remove_recursive(dir->entry); + list_del(&dir->list); + __put_system_dir(dir); + } +} + +static void *event_file_data(struct file *filp) +{ + return ACCESS_ONCE(file_inode(filp)->i_private); +} + +static void remove_event_file_dir(struct ftrace_event_file *file) +{ + struct dentry *dir = file->dir; + struct dentry *child; + + if (dir) { + spin_lock(&dir->d_lock); /* probably unneeded */ + list_for_each_entry(child, &dir->d_subdirs, d_u.d_child) { + if (child->d_inode) /* probably unneeded */ + child->d_inode->i_private = NULL; + } + spin_unlock(&dir->d_lock); + + debugfs_remove_recursive(dir); + } + + list_del(&file->list); + remove_subsystem(file->system); + kmem_cache_free(file_cachep, file); +} + /* * __ftrace_set_clr_event(NULL, NULL, NULL, set) will set/unset all events. */ -static int __ftrace_set_clr_event(struct trace_array *tr, const char *match, - const char *sub, const char *event, int set) +static int +__ftrace_set_clr_event_nolock(struct trace_array *tr, const char *match, + const char *sub, const char *event, int set) { struct ftrace_event_file *file; struct ftrace_event_call *call; int ret = -EINVAL; - mutex_lock(&event_mutex); list_for_each_entry(file, &tr->events, list) { call = file->event_call; @@ -429,6 +483,17 @@ static int __ftrace_set_clr_event(struct trace_array *tr, const char *match, ret = 0; } + + return ret; +} + +static int __ftrace_set_clr_event(struct trace_array *tr, const char *match, + const char *sub, const char *event, int set) +{ + int ret; + + mutex_lock(&event_mutex); + ret = __ftrace_set_clr_event_nolock(tr, match, sub, event, set); mutex_unlock(&event_mutex); return ret; @@ -623,18 +688,28 @@ static ssize_t event_enable_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) { - struct ftrace_event_file *file = filp->private_data; - char *buf; + struct ftrace_event_file *file; + unsigned long flags; + char buf[4] = "0"; - if (file->flags & FTRACE_EVENT_FL_ENABLED) { - if (file->flags & FTRACE_EVENT_FL_SOFT_DISABLED) - buf = "0*\n"; - else if (file->flags & FTRACE_EVENT_FL_SOFT_MODE) - buf = "1*\n"; - else - buf = "1\n"; - } else - buf = "0\n"; + mutex_lock(&event_mutex); + file = event_file_data(filp); + if (likely(file)) + flags = file->flags; + mutex_unlock(&event_mutex); + + if (!file) + return -ENODEV; + + if (flags & FTRACE_EVENT_FL_ENABLED && + !(flags & FTRACE_EVENT_FL_SOFT_DISABLED)) + strcpy(buf, "1"); + + if (flags & FTRACE_EVENT_FL_SOFT_DISABLED || + flags & FTRACE_EVENT_FL_SOFT_MODE) + strcat(buf, "*"); + + strcat(buf, "\n"); return simple_read_from_buffer(ubuf, cnt, ppos, buf, strlen(buf)); } @@ -643,13 +718,10 @@ static ssize_t event_enable_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *ppos) { - struct ftrace_event_file *file = filp->private_data; + struct ftrace_event_file *file; unsigned long val; int ret; - if (!file) - return -EINVAL; - ret = kstrtoul_from_user(ubuf, cnt, 10, &val); if (ret) return ret; @@ -661,8 +733,11 @@ event_enable_write(struct file *filp, const char __user *ubuf, size_t cnt, switch (val) { case 0: case 1: + ret = -ENODEV; mutex_lock(&event_mutex); - ret = ftrace_event_enable_disable(file, val); + file = event_file_data(filp); + if (likely(file)) + ret = ftrace_event_enable_disable(file, val); mutex_unlock(&event_mutex); break; @@ -769,65 +844,39 @@ enum { static void *f_next(struct seq_file *m, void *v, loff_t *pos) { - struct ftrace_event_call *call = m->private; - struct ftrace_event_field *field; + struct ftrace_event_call *call = event_file_data(m->private); struct list_head *common_head = &ftrace_common_fields; struct list_head *head = trace_get_fields(call); + struct list_head *node = v; (*pos)++; switch ((unsigned long)v) { case FORMAT_HEADER: - if (unlikely(list_empty(common_head))) - return NULL; - - field = list_entry(common_head->prev, - struct ftrace_event_field, link); - return field; + node = common_head; + break; case FORMAT_FIELD_SEPERATOR: - if (unlikely(list_empty(head))) - return NULL; - - field = list_entry(head->prev, struct ftrace_event_field, link); - return field; + node = head; + break; case FORMAT_PRINTFMT: /* all done */ return NULL; } - field = v; - if (field->link.prev == common_head) + node = node->prev; + if (node == common_head) return (void *)FORMAT_FIELD_SEPERATOR; - else if (field->link.prev == head) + else if (node == head) return (void *)FORMAT_PRINTFMT; - - field = list_entry(field->link.prev, struct ftrace_event_field, link); - - return field; -} - -static void *f_start(struct seq_file *m, loff_t *pos) -{ - loff_t l = 0; - void *p; - - /* Start by showing the header */ - if (!*pos) - return (void *)FORMAT_HEADER; - - p = (void *)FORMAT_HEADER; - do { - p = f_next(m, p, &l); - } while (p && l < *pos); - - return p; + else + return node; } static int f_show(struct seq_file *m, void *v) { - struct ftrace_event_call *call = m->private; + struct ftrace_event_call *call = event_file_data(m->private); struct ftrace_event_field *field; const char *array_descriptor; @@ -848,8 +897,7 @@ static int f_show(struct seq_file *m, void *v) return 0; } - field = v; - + field = list_entry(v, struct ftrace_event_field, link); /* * Smartly shows the array type(except dynamic array). * Normal: @@ -876,8 +924,25 @@ static int f_show(struct seq_file *m, void *v) return 0; } +static void *f_start(struct seq_file *m, loff_t *pos) +{ + void *p = (void *)FORMAT_HEADER; + loff_t l = 0; + + /* ->stop() is called even if ->start() fails */ + mutex_lock(&event_mutex); + if (!event_file_data(m->private)) + return ERR_PTR(-ENODEV); + + while (l < *pos && p) + p = f_next(m, p, &l); + + return p; +} + static void f_stop(struct seq_file *m, void *p) { + mutex_unlock(&event_mutex); } static const struct seq_operations trace_format_seq_ops = { @@ -889,7 +954,6 @@ static const struct seq_operations trace_format_seq_ops = { static int trace_format_open(struct inode *inode, struct file *file) { - struct ftrace_event_call *call = inode->i_private; struct seq_file *m; int ret; @@ -898,7 +962,7 @@ static int trace_format_open(struct inode *inode, struct file *file) return ret; m = file->private_data; - m->private = call; + m->private = file; return 0; } @@ -906,45 +970,47 @@ static int trace_format_open(struct inode *inode, struct file *file) static ssize_t event_id_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) { - struct ftrace_event_call *call = filp->private_data; - struct trace_seq *s; - int r; + int id = (long)event_file_data(filp); + char buf[32]; + int len; if (*ppos) return 0; - s = kmalloc(sizeof(*s), GFP_KERNEL); - if (!s) - return -ENOMEM; + if (unlikely(!id)) + return -ENODEV; - trace_seq_init(s); - trace_seq_printf(s, "%d\n", call->event.type); + len = sprintf(buf, "%d\n", id); - r = simple_read_from_buffer(ubuf, cnt, ppos, - s->buffer, s->len); - kfree(s); - return r; + return simple_read_from_buffer(ubuf, cnt, ppos, buf, len); } static ssize_t event_filter_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) { - struct ftrace_event_call *call = filp->private_data; + struct ftrace_event_call *call; struct trace_seq *s; - int r; + int r = -ENODEV; if (*ppos) return 0; s = kmalloc(sizeof(*s), GFP_KERNEL); + if (!s) return -ENOMEM; trace_seq_init(s); - print_event_filter(call, s); - r = simple_read_from_buffer(ubuf, cnt, ppos, s->buffer, s->len); + mutex_lock(&event_mutex); + call = event_file_data(filp); + if (call) + print_event_filter(call, s); + mutex_unlock(&event_mutex); + + if (call) + r = simple_read_from_buffer(ubuf, cnt, ppos, s->buffer, s->len); kfree(s); @@ -955,9 +1021,9 @@ static ssize_t event_filter_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *ppos) { - struct ftrace_event_call *call = filp->private_data; + struct ftrace_event_call *call; char *buf; - int err; + int err = -ENODEV; if (cnt >= PAGE_SIZE) return -EINVAL; @@ -972,7 +1038,12 @@ event_filter_write(struct file *filp, const char __user *ubuf, size_t cnt, } buf[cnt] = '\0'; - err = apply_event_filter(call, buf); + mutex_lock(&event_mutex); + call = event_file_data(filp); + if (call) + err = apply_event_filter(call, buf); + mutex_unlock(&event_mutex); + free_page((unsigned long) buf); if (err < 0) return err; @@ -992,6 +1063,7 @@ static int subsystem_open(struct inode *inode, struct file *filp) int ret; /* Make sure the system still exists */ + mutex_lock(&trace_types_lock); mutex_lock(&event_mutex); list_for_each_entry(tr, &ftrace_trace_arrays, list) { list_for_each_entry(dir, &tr->systems, list) { @@ -1007,6 +1079,7 @@ static int subsystem_open(struct inode *inode, struct file *filp) } exit_loop: mutex_unlock(&event_mutex); + mutex_unlock(&trace_types_lock); if (!system) return -ENODEV; @@ -1014,9 +1087,17 @@ static int subsystem_open(struct inode *inode, struct file *filp) /* Some versions of gcc think dir can be uninitialized here */ WARN_ON(!dir); + /* Still need to increment the ref count of the system */ + if (trace_array_get(tr) < 0) { + put_system(dir); + return -ENODEV; + } + ret = tracing_open_generic(inode, filp); - if (ret < 0) + if (ret < 0) { + trace_array_put(tr); put_system(dir); + } return ret; } @@ -1027,16 +1108,23 @@ static int system_tr_open(struct inode *inode, struct file *filp) struct trace_array *tr = inode->i_private; int ret; + if (trace_array_get(tr) < 0) + return -ENODEV; + /* Make a temporary dir that has no system but points to tr */ dir = kzalloc(sizeof(*dir), GFP_KERNEL); - if (!dir) + if (!dir) { + trace_array_put(tr); return -ENOMEM; + } dir->tr = tr; ret = tracing_open_generic(inode, filp); - if (ret < 0) + if (ret < 0) { + trace_array_put(tr); kfree(dir); + } filp->private_data = dir; @@ -1047,6 +1135,8 @@ static int subsystem_release(struct inode *inode, struct file *file) { struct ftrace_subsystem_dir *dir = file->private_data; + trace_array_put(dir->tr); + /* * If dir->subsystem is NULL, then this is a temporary * descriptor that was made for a trace_array to enable @@ -1143,6 +1233,7 @@ show_header(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) static int ftrace_event_avail_open(struct inode *inode, struct file *file); static int ftrace_event_set_open(struct inode *inode, struct file *file); +static int ftrace_event_release(struct inode *inode, struct file *file); static const struct seq_operations show_event_seq_ops = { .start = t_start, @@ -1170,7 +1261,7 @@ static const struct file_operations ftrace_set_event_fops = { .read = seq_read, .write = ftrace_event_write, .llseek = seq_lseek, - .release = seq_release, + .release = ftrace_event_release, }; static const struct file_operations ftrace_enable_fops = { @@ -1188,7 +1279,6 @@ static const struct file_operations ftrace_event_format_fops = { }; static const struct file_operations ftrace_event_id_fops = { - .open = tracing_open_generic, .read = event_id_read, .llseek = default_llseek, }; @@ -1247,6 +1337,15 @@ ftrace_event_open(struct inode *inode, struct file *file, return ret; } +static int ftrace_event_release(struct inode *inode, struct file *file) +{ + struct trace_array *tr = inode->i_private; + + trace_array_put(tr); + + return seq_release(inode, file); +} + static int ftrace_event_avail_open(struct inode *inode, struct file *file) { @@ -1260,12 +1359,19 @@ ftrace_event_set_open(struct inode *inode, struct file *file) { const struct seq_operations *seq_ops = &show_set_event_seq_ops; struct trace_array *tr = inode->i_private; + int ret; + + if (trace_array_get(tr) < 0) + return -ENODEV; if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) ftrace_clear_events(tr); - return ftrace_event_open(inode, file, seq_ops); + ret = ftrace_event_open(inode, file, seq_ops); + if (ret < 0) + trace_array_put(tr); + return ret; } static struct event_subsystem * @@ -1279,7 +1385,15 @@ create_new_subsystem(const char *name) return NULL; system->ref_count = 1; - system->name = name; + + /* Only allocate if dynamic (kprobes and modules) */ + if (!core_kernel_data((unsigned long)name)) { + system->ref_count |= SYSTEM_FL_FREE_NAME; + system->name = kstrdup(name, GFP_KERNEL); + if (!system->name) + goto out_free; + } else + system->name = name; system->filter = NULL; @@ -1292,6 +1406,8 @@ create_new_subsystem(const char *name) return system; out_free: + if (system->ref_count & SYSTEM_FL_FREE_NAME) + kfree(system->name); kfree(system); return NULL; } @@ -1410,8 +1526,8 @@ event_create_dir(struct dentry *parent, #ifdef CONFIG_PERF_EVENTS if (call->event.type && call->class->reg) - trace_create_file("id", 0444, file->dir, call, - id); + trace_create_file("id", 0444, file->dir, + (void *)(long)call->event.type, id); #endif /* @@ -1436,33 +1552,16 @@ event_create_dir(struct dentry *parent, return 0; } -static void remove_subsystem(struct ftrace_subsystem_dir *dir) -{ - if (!dir) - return; - - if (!--dir->nr_events) { - debugfs_remove_recursive(dir->entry); - list_del(&dir->list); - __put_system_dir(dir); - } -} - static void remove_event_from_tracers(struct ftrace_event_call *call) { struct ftrace_event_file *file; struct trace_array *tr; do_for_each_event_file_safe(tr, file) { - if (file->event_call != call) continue; - list_del(&file->list); - debugfs_remove_recursive(file->dir); - remove_subsystem(file->system); - kmem_cache_free(file_cachep, file); - + remove_event_file_dir(file); /* * The do_for_each_event_file_safe() is * a double loop. After finding the call for this @@ -1591,6 +1690,7 @@ static void __add_event_to_tracers(struct ftrace_event_call *call, int trace_add_event_call(struct ftrace_event_call *call) { int ret; + mutex_lock(&trace_types_lock); mutex_lock(&event_mutex); ret = __register_event(call, NULL); @@ -1598,11 +1698,13 @@ int trace_add_event_call(struct ftrace_event_call *call) __add_event_to_tracers(call, NULL); mutex_unlock(&event_mutex); + mutex_unlock(&trace_types_lock); return ret; } /* - * Must be called under locking both of event_mutex and trace_event_sem. + * Must be called under locking of trace_types_lock, event_mutex and + * trace_event_sem. */ static void __trace_remove_event_call(struct ftrace_event_call *call) { @@ -1611,14 +1713,53 @@ static void __trace_remove_event_call(struct ftrace_event_call *call) destroy_preds(call); } +static int probe_remove_event_call(struct ftrace_event_call *call) +{ + struct trace_array *tr; + struct ftrace_event_file *file; + +#ifdef CONFIG_PERF_EVENTS + if (call->perf_refcount) + return -EBUSY; +#endif + do_for_each_event_file(tr, file) { + if (file->event_call != call) + continue; + /* + * We can't rely on ftrace_event_enable_disable(enable => 0) + * we are going to do, FTRACE_EVENT_FL_SOFT_MODE can suppress + * TRACE_REG_UNREGISTER. + */ + if (file->flags & FTRACE_EVENT_FL_ENABLED) + return -EBUSY; + /* + * The do_for_each_event_file_safe() is + * a double loop. After finding the call for this + * trace_array, we use break to jump to the next + * trace_array. + */ + break; + } while_for_each_event_file(); + + __trace_remove_event_call(call); + + return 0; +} + /* Remove an event_call */ -void trace_remove_event_call(struct ftrace_event_call *call) +int trace_remove_event_call(struct ftrace_event_call *call) { + int ret; + + mutex_lock(&trace_types_lock); mutex_lock(&event_mutex); down_write(&trace_event_sem); - __trace_remove_event_call(call); + ret = probe_remove_event_call(call); up_write(&trace_event_sem); mutex_unlock(&event_mutex); + mutex_unlock(&trace_types_lock); + + return ret; } #define for_each_event(event, start, end) \ @@ -1762,6 +1903,7 @@ static int trace_module_notify(struct notifier_block *self, { struct module *mod = data; + mutex_lock(&trace_types_lock); mutex_lock(&event_mutex); switch (val) { case MODULE_STATE_COMING: @@ -1772,6 +1914,7 @@ static int trace_module_notify(struct notifier_block *self, break; } mutex_unlock(&event_mutex); + mutex_unlock(&trace_types_lock); return 0; } @@ -2011,10 +2154,7 @@ event_enable_func(struct ftrace_hash *hash, int ret; /* hash funcs only work with set_ftrace_filter */ - if (!enabled) - return -EINVAL; - - if (!param) + if (!enabled || !param) return -EINVAL; system = strsep(¶m, ":"); @@ -2188,12 +2328,8 @@ __trace_remove_event_dirs(struct trace_array *tr) { struct ftrace_event_file *file, *next; - list_for_each_entry_safe(file, next, &tr->events, list) { - list_del(&file->list); - debugfs_remove_recursive(file->dir); - remove_subsystem(file->system); - kmem_cache_free(file_cachep, file); - } + list_for_each_entry_safe(file, next, &tr->events, list) + remove_event_file_dir(file); } static void @@ -2329,11 +2465,11 @@ early_event_add_tracer(struct dentry *parent, struct trace_array *tr) int event_trace_del_tracer(struct trace_array *tr) { - /* Disable any running events */ - __ftrace_set_clr_event(tr, NULL, NULL, NULL, 0); - mutex_lock(&event_mutex); + /* Disable any running events */ + __ftrace_set_clr_event_nolock(tr, NULL, NULL, NULL, 0); + down_write(&trace_event_sem); __trace_remove_event_dirs(tr); debugfs_remove_recursive(tr->event_dir); diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index e1b653f7e1ca..97daa8cf958d 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -44,6 +44,7 @@ enum filter_op_ids OP_LE, OP_GT, OP_GE, + OP_BAND, OP_NONE, OP_OPEN_PAREN, }; @@ -54,6 +55,7 @@ struct filter_op { int precedence; }; +/* Order must be the same as enum filter_op_ids above */ static struct filter_op filter_ops[] = { { OP_OR, "||", 1 }, { OP_AND, "&&", 2 }, @@ -64,6 +66,7 @@ static struct filter_op filter_ops[] = { { OP_LE, "<=", 5 }, { OP_GT, ">", 5 }, { OP_GE, ">=", 5 }, + { OP_BAND, "&", 6 }, { OP_NONE, "OP_NONE", 0 }, { OP_OPEN_PAREN, "(", 0 }, }; @@ -156,6 +159,9 @@ static int filter_pred_##type(struct filter_pred *pred, void *event) \ case OP_GE: \ match = (*addr >= val); \ break; \ + case OP_BAND: \ + match = (*addr & val); \ + break; \ default: \ break; \ } \ @@ -631,17 +637,15 @@ static void append_filter_err(struct filter_parse_state *ps, free_page((unsigned long) buf); } +/* caller must hold event_mutex */ void print_event_filter(struct ftrace_event_call *call, struct trace_seq *s) { - struct event_filter *filter; + struct event_filter *filter = call->filter; - mutex_lock(&event_mutex); - filter = call->filter; if (filter && filter->filter_string) trace_seq_printf(s, "%s\n", filter->filter_string); else - trace_seq_printf(s, "none\n"); - mutex_unlock(&event_mutex); + trace_seq_puts(s, "none\n"); } void print_subsystem_event_filter(struct event_subsystem *system, @@ -654,7 +658,7 @@ void print_subsystem_event_filter(struct event_subsystem *system, if (filter && filter->filter_string) trace_seq_printf(s, "%s\n", filter->filter_string); else - trace_seq_printf(s, DEFAULT_SYS_FILTER_MESSAGE "\n"); + trace_seq_puts(s, DEFAULT_SYS_FILTER_MESSAGE "\n"); mutex_unlock(&event_mutex); } @@ -1835,23 +1839,22 @@ static int create_system_filter(struct event_subsystem *system, return err; } +/* caller must hold event_mutex */ int apply_event_filter(struct ftrace_event_call *call, char *filter_string) { struct event_filter *filter; - int err = 0; - - mutex_lock(&event_mutex); + int err; if (!strcmp(strstrip(filter_string), "0")) { filter_disable(call); filter = call->filter; if (!filter) - goto out_unlock; + return 0; RCU_INIT_POINTER(call->filter, NULL); /* Make sure the filter is not being used */ synchronize_sched(); __free_filter(filter); - goto out_unlock; + return 0; } err = create_filter(call, filter_string, true, &filter); @@ -1878,8 +1881,6 @@ int apply_event_filter(struct ftrace_event_call *call, char *filter_string) __free_filter(tmp); } } -out_unlock: - mutex_unlock(&event_mutex); return err; } diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c index c4d6d7191988..38fe1483c508 100644 --- a/kernel/trace/trace_functions.c +++ b/kernel/trace/trace_functions.c @@ -199,7 +199,7 @@ static int func_set_flag(u32 old_flags, u32 bit, int set) return 0; } -static struct tracer function_trace __read_mostly = +static struct tracer function_trace __tracer_data = { .name = "function", .init = function_trace_init, @@ -290,6 +290,21 @@ ftrace_stacktrace_count(unsigned long ip, unsigned long parent_ip, void **data) trace_dump_stack(STACK_SKIP); } +static void +ftrace_dump_probe(unsigned long ip, unsigned long parent_ip, void **data) +{ + if (update_count(data)) + ftrace_dump(DUMP_ALL); +} + +/* Only dump the current CPU buffer. */ +static void +ftrace_cpudump_probe(unsigned long ip, unsigned long parent_ip, void **data) +{ + if (update_count(data)) + ftrace_dump(DUMP_ORIG); +} + static int ftrace_probe_print(const char *name, struct seq_file *m, unsigned long ip, void *data) @@ -327,6 +342,20 @@ ftrace_stacktrace_print(struct seq_file *m, unsigned long ip, return ftrace_probe_print("stacktrace", m, ip, data); } +static int +ftrace_dump_print(struct seq_file *m, unsigned long ip, + struct ftrace_probe_ops *ops, void *data) +{ + return ftrace_probe_print("dump", m, ip, data); +} + +static int +ftrace_cpudump_print(struct seq_file *m, unsigned long ip, + struct ftrace_probe_ops *ops, void *data) +{ + return ftrace_probe_print("cpudump", m, ip, data); +} + static struct ftrace_probe_ops traceon_count_probe_ops = { .func = ftrace_traceon_count, .print = ftrace_traceon_print, @@ -342,6 +371,16 @@ static struct ftrace_probe_ops stacktrace_count_probe_ops = { .print = ftrace_stacktrace_print, }; +static struct ftrace_probe_ops dump_probe_ops = { + .func = ftrace_dump_probe, + .print = ftrace_dump_print, +}; + +static struct ftrace_probe_ops cpudump_probe_ops = { + .func = ftrace_cpudump_probe, + .print = ftrace_cpudump_print, +}; + static struct ftrace_probe_ops traceon_probe_ops = { .func = ftrace_traceon, .print = ftrace_traceon_print, @@ -425,6 +464,32 @@ ftrace_stacktrace_callback(struct ftrace_hash *hash, param, enable); } +static int +ftrace_dump_callback(struct ftrace_hash *hash, + char *glob, char *cmd, char *param, int enable) +{ + struct ftrace_probe_ops *ops; + + ops = &dump_probe_ops; + + /* Only dump once. */ + return ftrace_trace_probe_callback(ops, hash, glob, cmd, + "1", enable); +} + +static int +ftrace_cpudump_callback(struct ftrace_hash *hash, + char *glob, char *cmd, char *param, int enable) +{ + struct ftrace_probe_ops *ops; + + ops = &cpudump_probe_ops; + + /* Only dump once. */ + return ftrace_trace_probe_callback(ops, hash, glob, cmd, + "1", enable); +} + static struct ftrace_func_command ftrace_traceon_cmd = { .name = "traceon", .func = ftrace_trace_onoff_callback, @@ -440,6 +505,16 @@ static struct ftrace_func_command ftrace_stacktrace_cmd = { .func = ftrace_stacktrace_callback, }; +static struct ftrace_func_command ftrace_dump_cmd = { + .name = "dump", + .func = ftrace_dump_callback, +}; + +static struct ftrace_func_command ftrace_cpudump_cmd = { + .name = "cpudump", + .func = ftrace_cpudump_callback, +}; + static int __init init_func_cmd_traceon(void) { int ret; @@ -450,13 +525,31 @@ static int __init init_func_cmd_traceon(void) ret = register_ftrace_command(&ftrace_traceon_cmd); if (ret) - unregister_ftrace_command(&ftrace_traceoff_cmd); + goto out_free_traceoff; ret = register_ftrace_command(&ftrace_stacktrace_cmd); - if (ret) { - unregister_ftrace_command(&ftrace_traceoff_cmd); - unregister_ftrace_command(&ftrace_traceon_cmd); - } + if (ret) + goto out_free_traceon; + + ret = register_ftrace_command(&ftrace_dump_cmd); + if (ret) + goto out_free_stacktrace; + + ret = register_ftrace_command(&ftrace_cpudump_cmd); + if (ret) + goto out_free_dump; + + return 0; + + out_free_dump: + unregister_ftrace_command(&ftrace_dump_cmd); + out_free_stacktrace: + unregister_ftrace_command(&ftrace_stacktrace_cmd); + out_free_traceon: + unregister_ftrace_command(&ftrace_traceon_cmd); + out_free_traceoff: + unregister_ftrace_command(&ftrace_traceoff_cmd); + return ret; } #else diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c index 8388bc99f2ee..b5c09242683d 100644 --- a/kernel/trace/trace_functions_graph.c +++ b/kernel/trace/trace_functions_graph.c @@ -446,7 +446,7 @@ print_graph_proc(struct trace_seq *s, pid_t pid) /* First spaces to align center */ for (i = 0; i < spaces / 2; i++) { - ret = trace_seq_printf(s, " "); + ret = trace_seq_putc(s, ' '); if (!ret) return TRACE_TYPE_PARTIAL_LINE; } @@ -457,7 +457,7 @@ print_graph_proc(struct trace_seq *s, pid_t pid) /* Last spaces to align center */ for (i = 0; i < spaces - (spaces / 2); i++) { - ret = trace_seq_printf(s, " "); + ret = trace_seq_putc(s, ' '); if (!ret) return TRACE_TYPE_PARTIAL_LINE; } @@ -503,7 +503,7 @@ verif_pid(struct trace_seq *s, pid_t pid, int cpu, struct fgraph_data *data) ------------------------------------------ */ - ret = trace_seq_printf(s, + ret = trace_seq_puts(s, " ------------------------------------------\n"); if (!ret) return TRACE_TYPE_PARTIAL_LINE; @@ -516,7 +516,7 @@ verif_pid(struct trace_seq *s, pid_t pid, int cpu, struct fgraph_data *data) if (ret == TRACE_TYPE_PARTIAL_LINE) return TRACE_TYPE_PARTIAL_LINE; - ret = trace_seq_printf(s, " => "); + ret = trace_seq_puts(s, " => "); if (!ret) return TRACE_TYPE_PARTIAL_LINE; @@ -524,7 +524,7 @@ verif_pid(struct trace_seq *s, pid_t pid, int cpu, struct fgraph_data *data) if (ret == TRACE_TYPE_PARTIAL_LINE) return TRACE_TYPE_PARTIAL_LINE; - ret = trace_seq_printf(s, + ret = trace_seq_puts(s, "\n ------------------------------------------\n\n"); if (!ret) return TRACE_TYPE_PARTIAL_LINE; @@ -645,7 +645,7 @@ print_graph_irq(struct trace_iterator *iter, unsigned long addr, ret = print_graph_proc(s, pid); if (ret == TRACE_TYPE_PARTIAL_LINE) return TRACE_TYPE_PARTIAL_LINE; - ret = trace_seq_printf(s, " | "); + ret = trace_seq_puts(s, " | "); if (!ret) return TRACE_TYPE_PARTIAL_LINE; } @@ -657,9 +657,9 @@ print_graph_irq(struct trace_iterator *iter, unsigned long addr, return ret; if (type == TRACE_GRAPH_ENT) - ret = trace_seq_printf(s, "==========>"); + ret = trace_seq_puts(s, "==========>"); else - ret = trace_seq_printf(s, "<=========="); + ret = trace_seq_puts(s, "<=========="); if (!ret) return TRACE_TYPE_PARTIAL_LINE; @@ -668,7 +668,7 @@ print_graph_irq(struct trace_iterator *iter, unsigned long addr, if (ret != TRACE_TYPE_HANDLED) return ret; - ret = trace_seq_printf(s, "\n"); + ret = trace_seq_putc(s, '\n'); if (!ret) return TRACE_TYPE_PARTIAL_LINE; @@ -705,13 +705,13 @@ trace_print_graph_duration(unsigned long long duration, struct trace_seq *s) len += strlen(nsecs_str); } - ret = trace_seq_printf(s, " us "); + ret = trace_seq_puts(s, " us "); if (!ret) return TRACE_TYPE_PARTIAL_LINE; /* Print remaining spaces to fit the row's width */ for (i = len; i < 7; i++) { - ret = trace_seq_printf(s, " "); + ret = trace_seq_putc(s, ' '); if (!ret) return TRACE_TYPE_PARTIAL_LINE; } @@ -731,13 +731,13 @@ print_graph_duration(unsigned long long duration, struct trace_seq *s, /* No real adata, just filling the column with spaces */ switch (duration) { case DURATION_FILL_FULL: - ret = trace_seq_printf(s, " | "); + ret = trace_seq_puts(s, " | "); return ret ? TRACE_TYPE_HANDLED : TRACE_TYPE_PARTIAL_LINE; case DURATION_FILL_START: - ret = trace_seq_printf(s, " "); + ret = trace_seq_puts(s, " "); return ret ? TRACE_TYPE_HANDLED : TRACE_TYPE_PARTIAL_LINE; case DURATION_FILL_END: - ret = trace_seq_printf(s, " |"); + ret = trace_seq_puts(s, " |"); return ret ? TRACE_TYPE_HANDLED : TRACE_TYPE_PARTIAL_LINE; } @@ -745,10 +745,10 @@ print_graph_duration(unsigned long long duration, struct trace_seq *s, if (flags & TRACE_GRAPH_PRINT_OVERHEAD) { /* Duration exceeded 100 msecs */ if (duration > 100000ULL) - ret = trace_seq_printf(s, "! "); + ret = trace_seq_puts(s, "! "); /* Duration exceeded 10 msecs */ else if (duration > 10000ULL) - ret = trace_seq_printf(s, "+ "); + ret = trace_seq_puts(s, "+ "); } /* @@ -757,7 +757,7 @@ print_graph_duration(unsigned long long duration, struct trace_seq *s, * to fill out the space. */ if (ret == -1) - ret = trace_seq_printf(s, " "); + ret = trace_seq_puts(s, " "); /* Catching here any failure happenned above */ if (!ret) @@ -767,7 +767,7 @@ print_graph_duration(unsigned long long duration, struct trace_seq *s, if (ret != TRACE_TYPE_HANDLED) return ret; - ret = trace_seq_printf(s, "| "); + ret = trace_seq_puts(s, "| "); if (!ret) return TRACE_TYPE_PARTIAL_LINE; @@ -817,7 +817,7 @@ print_graph_entry_leaf(struct trace_iterator *iter, /* Function */ for (i = 0; i < call->depth * TRACE_GRAPH_INDENT; i++) { - ret = trace_seq_printf(s, " "); + ret = trace_seq_putc(s, ' '); if (!ret) return TRACE_TYPE_PARTIAL_LINE; } @@ -858,7 +858,7 @@ print_graph_entry_nested(struct trace_iterator *iter, /* Function */ for (i = 0; i < call->depth * TRACE_GRAPH_INDENT; i++) { - ret = trace_seq_printf(s, " "); + ret = trace_seq_putc(s, ' '); if (!ret) return TRACE_TYPE_PARTIAL_LINE; } @@ -917,7 +917,7 @@ print_graph_prologue(struct trace_iterator *iter, struct trace_seq *s, if (ret == TRACE_TYPE_PARTIAL_LINE) return TRACE_TYPE_PARTIAL_LINE; - ret = trace_seq_printf(s, " | "); + ret = trace_seq_puts(s, " | "); if (!ret) return TRACE_TYPE_PARTIAL_LINE; } @@ -1117,7 +1117,7 @@ print_graph_return(struct ftrace_graph_ret *trace, struct trace_seq *s, /* Closing brace */ for (i = 0; i < trace->depth * TRACE_GRAPH_INDENT; i++) { - ret = trace_seq_printf(s, " "); + ret = trace_seq_putc(s, ' '); if (!ret) return TRACE_TYPE_PARTIAL_LINE; } @@ -1129,7 +1129,7 @@ print_graph_return(struct ftrace_graph_ret *trace, struct trace_seq *s, * belongs to, write out the function name. */ if (func_match) { - ret = trace_seq_printf(s, "}\n"); + ret = trace_seq_puts(s, "}\n"); if (!ret) return TRACE_TYPE_PARTIAL_LINE; } else { @@ -1179,13 +1179,13 @@ print_graph_comment(struct trace_seq *s, struct trace_entry *ent, /* Indentation */ if (depth > 0) for (i = 0; i < (depth + 1) * TRACE_GRAPH_INDENT; i++) { - ret = trace_seq_printf(s, " "); + ret = trace_seq_putc(s, ' '); if (!ret) return TRACE_TYPE_PARTIAL_LINE; } /* The comment */ - ret = trace_seq_printf(s, "/* "); + ret = trace_seq_puts(s, "/* "); if (!ret) return TRACE_TYPE_PARTIAL_LINE; @@ -1216,7 +1216,7 @@ print_graph_comment(struct trace_seq *s, struct trace_entry *ent, s->len--; } - ret = trace_seq_printf(s, " */\n"); + ret = trace_seq_puts(s, " */\n"); if (!ret) return TRACE_TYPE_PARTIAL_LINE; @@ -1448,7 +1448,7 @@ static struct trace_event graph_trace_ret_event = { .funcs = &graph_functions }; -static struct tracer graph_trace __read_mostly = { +static struct tracer graph_trace __tracer_data = { .name = "function_graph", .open = graph_trace_open, .pipe_open = graph_trace_open, diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c index b19d065a28cb..2aefbee93a6d 100644 --- a/kernel/trace/trace_irqsoff.c +++ b/kernel/trace/trace_irqsoff.c @@ -373,7 +373,7 @@ start_critical_timing(unsigned long ip, unsigned long parent_ip) struct trace_array_cpu *data; unsigned long flags; - if (likely(!tracer_enabled)) + if (!tracer_enabled || !tracing_is_enabled()) return; cpu = raw_smp_processor_id(); @@ -416,7 +416,7 @@ stop_critical_timing(unsigned long ip, unsigned long parent_ip) else return; - if (!tracer_enabled) + if (!tracer_enabled || !tracing_is_enabled()) return; data = per_cpu_ptr(tr->trace_buffer.data, cpu); diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 9f46e98ba8f2..243f6834d026 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -35,12 +35,17 @@ struct trace_probe { const char *symbol; /* symbol name */ struct ftrace_event_class class; struct ftrace_event_call call; - struct ftrace_event_file * __rcu *files; + struct list_head files; ssize_t size; /* trace entry size */ unsigned int nr_args; struct probe_arg args[]; }; +struct event_file_link { + struct ftrace_event_file *file; + struct list_head list; +}; + #define SIZEOF_TRACE_PROBE(n) \ (offsetof(struct trace_probe, args) + \ (sizeof(struct probe_arg) * (n))) @@ -90,7 +95,7 @@ static __kprobes bool trace_probe_is_on_module(struct trace_probe *tp) } static int register_probe_event(struct trace_probe *tp); -static void unregister_probe_event(struct trace_probe *tp); +static int unregister_probe_event(struct trace_probe *tp); static DEFINE_MUTEX(probe_lock); static LIST_HEAD(probe_list); @@ -150,6 +155,7 @@ static struct trace_probe *alloc_trace_probe(const char *group, goto error; INIT_LIST_HEAD(&tp->list); + INIT_LIST_HEAD(&tp->files); return tp; error: kfree(tp->call.name); @@ -183,25 +189,6 @@ static struct trace_probe *find_trace_probe(const char *event, return NULL; } -static int trace_probe_nr_files(struct trace_probe *tp) -{ - struct ftrace_event_file **file; - int ret = 0; - - /* - * Since all tp->files updater is protected by probe_enable_lock, - * we don't need to lock an rcu_read_lock. - */ - file = rcu_dereference_raw(tp->files); - if (file) - while (*(file++)) - ret++; - - return ret; -} - -static DEFINE_MUTEX(probe_enable_lock); - /* * Enable trace_probe * if the file is NULL, enable "perf" handler, or enable "trace" handler. @@ -211,67 +198,42 @@ enable_trace_probe(struct trace_probe *tp, struct ftrace_event_file *file) { int ret = 0; - mutex_lock(&probe_enable_lock); - if (file) { - struct ftrace_event_file **new, **old; - int n = trace_probe_nr_files(tp); - - old = rcu_dereference_raw(tp->files); - /* 1 is for new one and 1 is for stopper */ - new = kzalloc((n + 2) * sizeof(struct ftrace_event_file *), - GFP_KERNEL); - if (!new) { + struct event_file_link *link; + + link = kmalloc(sizeof(*link), GFP_KERNEL); + if (!link) { ret = -ENOMEM; - goto out_unlock; + goto out; } - memcpy(new, old, n * sizeof(struct ftrace_event_file *)); - new[n] = file; - /* The last one keeps a NULL */ - rcu_assign_pointer(tp->files, new); - tp->flags |= TP_FLAG_TRACE; + link->file = file; + list_add_tail_rcu(&link->list, &tp->files); - if (old) { - /* Make sure the probe is done with old files */ - synchronize_sched(); - kfree(old); - } + tp->flags |= TP_FLAG_TRACE; } else tp->flags |= TP_FLAG_PROFILE; - if (trace_probe_is_enabled(tp) && trace_probe_is_registered(tp) && - !trace_probe_has_gone(tp)) { + if (trace_probe_is_registered(tp) && !trace_probe_has_gone(tp)) { if (trace_probe_is_return(tp)) ret = enable_kretprobe(&tp->rp); else ret = enable_kprobe(&tp->rp.kp); } - - out_unlock: - mutex_unlock(&probe_enable_lock); - + out: return ret; } -static int -trace_probe_file_index(struct trace_probe *tp, struct ftrace_event_file *file) +static struct event_file_link * +find_event_file_link(struct trace_probe *tp, struct ftrace_event_file *file) { - struct ftrace_event_file **files; - int i; + struct event_file_link *link; - /* - * Since all tp->files updater is protected by probe_enable_lock, - * we don't need to lock an rcu_read_lock. - */ - files = rcu_dereference_raw(tp->files); - if (files) { - for (i = 0; files[i]; i++) - if (files[i] == file) - return i; - } + list_for_each_entry(link, &tp->files, list) + if (link->file == file) + return link; - return -1; + return NULL; } /* @@ -281,43 +243,23 @@ trace_probe_file_index(struct trace_probe *tp, struct ftrace_event_file *file) static int disable_trace_probe(struct trace_probe *tp, struct ftrace_event_file *file) { + struct event_file_link *link = NULL; + int wait = 0; int ret = 0; - mutex_lock(&probe_enable_lock); - if (file) { - struct ftrace_event_file **new, **old; - int n = trace_probe_nr_files(tp); - int i, j; - - old = rcu_dereference_raw(tp->files); - if (n == 0 || trace_probe_file_index(tp, file) < 0) { + link = find_event_file_link(tp, file); + if (!link) { ret = -EINVAL; - goto out_unlock; + goto out; } - if (n == 1) { /* Remove the last file */ - tp->flags &= ~TP_FLAG_TRACE; - new = NULL; - } else { - new = kzalloc(n * sizeof(struct ftrace_event_file *), - GFP_KERNEL); - if (!new) { - ret = -ENOMEM; - goto out_unlock; - } - - /* This copy & check loop copies the NULL stopper too */ - for (i = 0, j = 0; j < n && i < n + 1; i++) - if (old[i] != file) - new[j++] = old[i]; - } - - rcu_assign_pointer(tp->files, new); + list_del_rcu(&link->list); + wait = 1; + if (!list_empty(&tp->files)) + goto out; - /* Make sure the probe is done with old files */ - synchronize_sched(); - kfree(old); + tp->flags &= ~TP_FLAG_TRACE; } else tp->flags &= ~TP_FLAG_PROFILE; @@ -326,10 +268,21 @@ disable_trace_probe(struct trace_probe *tp, struct ftrace_event_file *file) disable_kretprobe(&tp->rp); else disable_kprobe(&tp->rp.kp); + wait = 1; + } + out: + if (wait) { + /* + * Synchronize with kprobe_trace_func/kretprobe_trace_func + * to ensure disabled (all running handlers are finished). + * This is not only for kfree(), but also the caller, + * trace_remove_event_call() supposes it for releasing + * event_call related objects, which will be accessed in + * the kprobe_trace_func/kretprobe_trace_func. + */ + synchronize_sched(); + kfree(link); /* Ignored if link == NULL */ } - - out_unlock: - mutex_unlock(&probe_enable_lock); return ret; } @@ -398,9 +351,12 @@ static int unregister_trace_probe(struct trace_probe *tp) if (trace_probe_is_enabled(tp)) return -EBUSY; + /* Will fail if probe is being used by ftrace or perf */ + if (unregister_probe_event(tp)) + return -EBUSY; + __unregister_trace_probe(tp); list_del(&tp->list); - unregister_probe_event(tp); return 0; } @@ -679,7 +635,9 @@ static int release_all_trace_probes(void) /* TODO: Use batch unregistration */ while (!list_empty(&probe_list)) { tp = list_entry(probe_list.next, struct trace_probe, list); - unregister_trace_probe(tp); + ret = unregister_trace_probe(tp); + if (ret) + goto end; free_trace_probe(tp); } @@ -885,20 +843,10 @@ __kprobe_trace_func(struct trace_probe *tp, struct pt_regs *regs, static __kprobes void kprobe_trace_func(struct trace_probe *tp, struct pt_regs *regs) { - /* - * Note: preempt is already disabled around the kprobe handler. - * However, we still need an smp_read_barrier_depends() corresponding - * to smp_wmb() in rcu_assign_pointer() to access the pointer. - */ - struct ftrace_event_file **file = rcu_dereference_raw(tp->files); - - if (unlikely(!file)) - return; + struct event_file_link *link; - while (*file) { - __kprobe_trace_func(tp, regs, *file); - file++; - } + list_for_each_entry_rcu(link, &tp->files, list) + __kprobe_trace_func(tp, regs, link->file); } /* Kretprobe handler */ @@ -945,20 +893,10 @@ static __kprobes void kretprobe_trace_func(struct trace_probe *tp, struct kretprobe_instance *ri, struct pt_regs *regs) { - /* - * Note: preempt is already disabled around the kprobe handler. - * However, we still need an smp_read_barrier_depends() corresponding - * to smp_wmb() in rcu_assign_pointer() to access the pointer. - */ - struct ftrace_event_file **file = rcu_dereference_raw(tp->files); - - if (unlikely(!file)) - return; + struct event_file_link *link; - while (*file) { - __kretprobe_trace_func(tp, ri, regs, *file); - file++; - } + list_for_each_entry_rcu(link, &tp->files, list) + __kretprobe_trace_func(tp, ri, regs, link->file); } /* Event entry printers */ @@ -1157,13 +1095,14 @@ kprobe_perf_func(struct trace_probe *tp, struct pt_regs *regs) int size, __size, dsize; int rctx; + head = this_cpu_ptr(call->perf_events); + if (hlist_empty(head)) + return; + dsize = __get_data_size(tp, regs); __size = sizeof(*entry) + tp->size + dsize; size = ALIGN(__size + sizeof(u32), sizeof(u64)); size -= sizeof(u32); - if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE, - "profile buffer not large enough")) - return; entry = perf_trace_buf_prepare(size, call->event.type, regs, &rctx); if (!entry) @@ -1172,10 +1111,7 @@ kprobe_perf_func(struct trace_probe *tp, struct pt_regs *regs) entry->ip = (unsigned long)tp->rp.kp.addr; memset(&entry[1], 0, dsize); store_trace_args(sizeof(*entry), tp, regs, (u8 *)&entry[1], dsize); - - head = this_cpu_ptr(call->perf_events); - perf_trace_buf_submit(entry, size, rctx, - entry->ip, 1, regs, head, NULL); + perf_trace_buf_submit(entry, size, rctx, 0, 1, regs, head, NULL); } /* Kretprobe profile handler */ @@ -1189,13 +1125,14 @@ kretprobe_perf_func(struct trace_probe *tp, struct kretprobe_instance *ri, int size, __size, dsize; int rctx; + head = this_cpu_ptr(call->perf_events); + if (hlist_empty(head)) + return; + dsize = __get_data_size(tp, regs); __size = sizeof(*entry) + tp->size + dsize; size = ALIGN(__size + sizeof(u32), sizeof(u64)); size -= sizeof(u32); - if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE, - "profile buffer not large enough")) - return; entry = perf_trace_buf_prepare(size, call->event.type, regs, &rctx); if (!entry) @@ -1204,13 +1141,16 @@ kretprobe_perf_func(struct trace_probe *tp, struct kretprobe_instance *ri, entry->func = (unsigned long)tp->rp.kp.addr; entry->ret_ip = (unsigned long)ri->ret_addr; store_trace_args(sizeof(*entry), tp, regs, (u8 *)&entry[1], dsize); - - head = this_cpu_ptr(call->perf_events); - perf_trace_buf_submit(entry, size, rctx, - entry->ret_ip, 1, regs, head, NULL); + perf_trace_buf_submit(entry, size, rctx, 0, 1, regs, head, NULL); } #endif /* CONFIG_PERF_EVENTS */ +/* + * called by perf_trace_init() or __ftrace_set_clr_event() under event_mutex. + * + * kprobe_trace_self_tests_init() does enable_trace_probe/disable_trace_probe + * lockless, but we can't race with this __init function. + */ static __kprobes int kprobe_register(struct ftrace_event_call *event, enum trace_reg type, void *data) @@ -1312,11 +1252,15 @@ static int register_probe_event(struct trace_probe *tp) return ret; } -static void unregister_probe_event(struct trace_probe *tp) +static int unregister_probe_event(struct trace_probe *tp) { + int ret; + /* tp->event is unregistered in trace_remove_event_call() */ - trace_remove_event_call(&tp->call); - kfree(tp->call.print_fmt); + ret = trace_remove_event_call(&tp->call); + if (!ret) + kfree(tp->call.print_fmt); + return ret; } /* Make a debugfs interface for controlling probe points */ @@ -1376,6 +1320,10 @@ find_trace_probe_file(struct trace_probe *tp, struct trace_array *tr) return NULL; } +/* + * Nobody but us can call enable_trace_probe/disable_trace_probe at this + * stage, we can do this lockless. + */ static __init int kprobe_trace_self_tests_init(void) { int ret, warn = 0; diff --git a/kernel/trace/trace_mmiotrace.c b/kernel/trace/trace_mmiotrace.c index a5e8f4878bfa..b3dcfb2f0fef 100644 --- a/kernel/trace/trace_mmiotrace.c +++ b/kernel/trace/trace_mmiotrace.c @@ -90,7 +90,7 @@ static int mmio_print_pcidev(struct trace_seq *s, const struct pci_dev *dev) if (drv) ret += trace_seq_printf(s, " %s\n", drv->name); else - ret += trace_seq_printf(s, " \n"); + ret += trace_seq_puts(s, " \n"); return ret; } @@ -107,7 +107,7 @@ static void mmio_pipe_open(struct trace_iterator *iter) struct header_iter *hiter; struct trace_seq *s = &iter->seq; - trace_seq_printf(s, "VERSION 20070824\n"); + trace_seq_puts(s, "VERSION 20070824\n"); hiter = kzalloc(sizeof(*hiter), GFP_KERNEL); if (!hiter) @@ -209,7 +209,7 @@ static enum print_line_t mmio_print_rw(struct trace_iterator *iter) (rw->value >> 0) & 0xff, rw->pc, 0); break; default: - ret = trace_seq_printf(s, "rw what?\n"); + ret = trace_seq_puts(s, "rw what?\n"); break; } if (ret) @@ -245,7 +245,7 @@ static enum print_line_t mmio_print_map(struct trace_iterator *iter) secs, usec_rem, m->map_id, 0UL, 0); break; default: - ret = trace_seq_printf(s, "map what?\n"); + ret = trace_seq_puts(s, "map what?\n"); break; } if (ret) diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c index bb922d9ee51b..34e7cbac0c9c 100644 --- a/kernel/trace/trace_output.c +++ b/kernel/trace/trace_output.c @@ -78,7 +78,7 @@ enum print_line_t trace_print_printk_msg_only(struct trace_iterator *iter) trace_assign_type(field, entry); - ret = trace_seq_printf(s, "%s", field->buf); + ret = trace_seq_puts(s, field->buf); if (!ret) return TRACE_TYPE_PARTIAL_LINE; @@ -558,14 +558,14 @@ seq_print_userip_objs(const struct userstack_entry *entry, struct trace_seq *s, if (ret) ret = trace_seq_puts(s, "??"); if (ret) - ret = trace_seq_puts(s, "\n"); + ret = trace_seq_putc(s, '\n'); continue; } if (!ret) break; if (ret) ret = seq_print_user_ip(s, mm, ip, sym_flags); - ret = trace_seq_puts(s, "\n"); + ret = trace_seq_putc(s, '\n'); } if (mm) @@ -579,7 +579,7 @@ seq_print_ip_sym(struct trace_seq *s, unsigned long ip, unsigned long sym_flags) int ret; if (!ip) - return trace_seq_printf(s, "0"); + return trace_seq_putc(s, '0'); if (sym_flags & TRACE_ITER_SYM_OFFSET) ret = seq_print_sym_offset(s, "%s", ip); @@ -964,14 +964,14 @@ static enum print_line_t trace_fn_trace(struct trace_iterator *iter, int flags, goto partial; if ((flags & TRACE_ITER_PRINT_PARENT) && field->parent_ip) { - if (!trace_seq_printf(s, " <-")) + if (!trace_seq_puts(s, " <-")) goto partial; if (!seq_print_ip_sym(s, field->parent_ip, flags)) goto partial; } - if (!trace_seq_printf(s, "\n")) + if (!trace_seq_putc(s, '\n')) goto partial; return TRACE_TYPE_HANDLED; @@ -1210,7 +1210,7 @@ static enum print_line_t trace_stack_print(struct trace_iterator *iter, if (!seq_print_ip_sym(s, *p, flags)) goto partial; - if (!trace_seq_puts(s, "\n")) + if (!trace_seq_putc(s, '\n')) goto partial; } diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c index 2901e3b88590..a7329b7902f8 100644 --- a/kernel/trace/trace_selftest.c +++ b/kernel/trace/trace_selftest.c @@ -640,13 +640,20 @@ out: * Enable ftrace, sleep 1/10 second, and then read the trace * buffer to see if all is in order. */ -int +__init int trace_selftest_startup_function(struct tracer *trace, struct trace_array *tr) { int save_ftrace_enabled = ftrace_enabled; unsigned long count; int ret; +#ifdef CONFIG_DYNAMIC_FTRACE + if (ftrace_filter_param) { + printk(KERN_CONT " ... kernel command line filter set: force PASS ... "); + return 0; + } +#endif + /* make sure msleep has been recorded */ msleep(1); @@ -727,13 +734,20 @@ static int trace_graph_entry_watchdog(struct ftrace_graph_ent *trace) * Pretty much the same than for the function tracer from which the selftest * has been borrowed. */ -int +__init int trace_selftest_startup_function_graph(struct tracer *trace, struct trace_array *tr) { int ret; unsigned long count; +#ifdef CONFIG_DYNAMIC_FTRACE + if (ftrace_filter_param) { + printk(KERN_CONT " ... kernel command line filter set: force PASS ... "); + return 0; + } +#endif + /* * Simulate the init() callback but we attach a watchdog callback * to detect and recover from possible hangs diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c index 8f2ac73c7a5f..8fd03657bc7d 100644 --- a/kernel/trace/trace_syscalls.c +++ b/kernel/trace/trace_syscalls.c @@ -175,7 +175,7 @@ print_syscall_exit(struct trace_iterator *iter, int flags, entry = syscall_nr_to_meta(syscall); if (!entry) { - trace_seq_printf(s, "\n"); + trace_seq_putc(s, '\n'); return TRACE_TYPE_HANDLED; } @@ -306,6 +306,8 @@ static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id) struct syscall_metadata *sys_data; struct ring_buffer_event *event; struct ring_buffer *buffer; + unsigned long irq_flags; + int pc; int syscall_nr; int size; @@ -321,9 +323,12 @@ static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id) size = sizeof(*entry) + sizeof(unsigned long) * sys_data->nb_args; + local_save_flags(irq_flags); + pc = preempt_count(); + buffer = tr->trace_buffer.buffer; event = trace_buffer_lock_reserve(buffer, - sys_data->enter_event->event.type, size, 0, 0); + sys_data->enter_event->event.type, size, irq_flags, pc); if (!event) return; @@ -333,7 +338,8 @@ static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id) if (!filter_current_check_discard(buffer, sys_data->enter_event, entry, event)) - trace_current_buffer_unlock_commit(buffer, event, 0, 0); + trace_current_buffer_unlock_commit(buffer, event, + irq_flags, pc); } static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret) @@ -343,6 +349,8 @@ static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret) struct syscall_metadata *sys_data; struct ring_buffer_event *event; struct ring_buffer *buffer; + unsigned long irq_flags; + int pc; int syscall_nr; syscall_nr = trace_get_syscall_nr(current, regs); @@ -355,9 +363,13 @@ static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret) if (!sys_data) return; + local_save_flags(irq_flags); + pc = preempt_count(); + buffer = tr->trace_buffer.buffer; event = trace_buffer_lock_reserve(buffer, - sys_data->exit_event->event.type, sizeof(*entry), 0, 0); + sys_data->exit_event->event.type, sizeof(*entry), + irq_flags, pc); if (!event) return; @@ -367,7 +379,8 @@ static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret) if (!filter_current_check_discard(buffer, sys_data->exit_event, entry, event)) - trace_current_buffer_unlock_commit(buffer, event, 0, 0); + trace_current_buffer_unlock_commit(buffer, event, + irq_flags, pc); } static int reg_event_syscall_enter(struct ftrace_event_file *file, @@ -553,15 +566,15 @@ static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id) if (!sys_data) return; + head = this_cpu_ptr(sys_data->enter_event->perf_events); + if (hlist_empty(head)) + return; + /* get the size after alignment with the u32 buffer size field */ size = sizeof(unsigned long) * sys_data->nb_args + sizeof(*rec); size = ALIGN(size + sizeof(u32), sizeof(u64)); size -= sizeof(u32); - if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE, - "perf buffer not large enough")) - return; - rec = (struct syscall_trace_enter *)perf_trace_buf_prepare(size, sys_data->enter_event->event.type, regs, &rctx); if (!rec) @@ -570,8 +583,6 @@ static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id) rec->nr = syscall_nr; syscall_get_arguments(current, regs, 0, sys_data->nb_args, (unsigned long *)&rec->args); - - head = this_cpu_ptr(sys_data->enter_event->perf_events); perf_trace_buf_submit(rec, size, rctx, 0, 1, regs, head, NULL); } @@ -629,18 +640,14 @@ static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret) if (!sys_data) return; + head = this_cpu_ptr(sys_data->exit_event->perf_events); + if (hlist_empty(head)) + return; + /* We can probably do that at build time */ size = ALIGN(sizeof(*rec) + sizeof(u32), sizeof(u64)); size -= sizeof(u32); - /* - * Impossible, but be paranoid with the future - * How to put this check outside runtime? - */ - if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE, - "exit event has grown above perf buffer size")) - return; - rec = (struct syscall_trace_exit *)perf_trace_buf_prepare(size, sys_data->exit_event->event.type, regs, &rctx); if (!rec) @@ -648,8 +655,6 @@ static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret) rec->nr = syscall_nr; rec->ret = syscall_get_return_value(current, regs); - - head = this_cpu_ptr(sys_data->exit_event->perf_events); perf_trace_buf_submit(rec, size, rctx, 0, 1, regs, head, NULL); } diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index 32494fb0ee64..272261b5f94f 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -70,7 +70,7 @@ struct trace_uprobe { (sizeof(struct probe_arg) * (n))) static int register_uprobe_event(struct trace_uprobe *tu); -static void unregister_uprobe_event(struct trace_uprobe *tu); +static int unregister_uprobe_event(struct trace_uprobe *tu); static DEFINE_MUTEX(uprobe_lock); static LIST_HEAD(uprobe_list); @@ -164,11 +164,17 @@ static struct trace_uprobe *find_probe_event(const char *event, const char *grou } /* Unregister a trace_uprobe and probe_event: call with locking uprobe_lock */ -static void unregister_trace_uprobe(struct trace_uprobe *tu) +static int unregister_trace_uprobe(struct trace_uprobe *tu) { + int ret; + + ret = unregister_uprobe_event(tu); + if (ret) + return ret; + list_del(&tu->list); - unregister_uprobe_event(tu); free_trace_uprobe(tu); + return 0; } /* Register a trace_uprobe and probe_event */ @@ -181,9 +187,12 @@ static int register_trace_uprobe(struct trace_uprobe *tu) /* register as an event */ old_tp = find_probe_event(tu->call.name, tu->call.class->system); - if (old_tp) + if (old_tp) { /* delete old event */ - unregister_trace_uprobe(old_tp); + ret = unregister_trace_uprobe(old_tp); + if (ret) + goto end; + } ret = register_uprobe_event(tu); if (ret) { @@ -256,6 +265,8 @@ static int create_trace_uprobe(int argc, char **argv) group = UPROBE_EVENT_SYSTEM; if (is_delete) { + int ret; + if (!event) { pr_info("Delete command needs an event name.\n"); return -EINVAL; @@ -269,9 +280,9 @@ static int create_trace_uprobe(int argc, char **argv) return -ENOENT; } /* delete an event */ - unregister_trace_uprobe(tu); + ret = unregister_trace_uprobe(tu); mutex_unlock(&uprobe_lock); - return 0; + return ret; } if (argc < 2) { @@ -283,8 +294,10 @@ static int create_trace_uprobe(int argc, char **argv) return -EINVAL; } arg = strchr(argv[1], ':'); - if (!arg) + if (!arg) { + ret = -EINVAL; goto fail_address_parse; + } *arg++ = '\0'; filename = argv[1]; @@ -406,16 +419,20 @@ fail_address_parse: return ret; } -static void cleanup_all_probes(void) +static int cleanup_all_probes(void) { struct trace_uprobe *tu; + int ret = 0; mutex_lock(&uprobe_lock); while (!list_empty(&uprobe_list)) { tu = list_entry(uprobe_list.next, struct trace_uprobe, list); - unregister_trace_uprobe(tu); + ret = unregister_trace_uprobe(tu); + if (ret) + break; } mutex_unlock(&uprobe_lock); + return ret; } /* Probes listing interfaces */ @@ -460,8 +477,13 @@ static const struct seq_operations probes_seq_op = { static int probes_open(struct inode *inode, struct file *file) { - if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) - cleanup_all_probes(); + int ret; + + if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) { + ret = cleanup_all_probes(); + if (ret) + return ret; + } return seq_open(file, &probes_seq_op); } @@ -816,8 +838,6 @@ static void uprobe_perf_print(struct trace_uprobe *tu, size = SIZEOF_TRACE_ENTRY(is_ret_probe(tu)); size = ALIGN(size + tu->size + sizeof(u32), sizeof(u64)) - sizeof(u32); - if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE, "profile buffer not large enough")) - return; preempt_disable(); head = this_cpu_ptr(call->perf_events); @@ -968,12 +988,17 @@ static int register_uprobe_event(struct trace_uprobe *tu) return ret; } -static void unregister_uprobe_event(struct trace_uprobe *tu) +static int unregister_uprobe_event(struct trace_uprobe *tu) { + int ret; + /* tu->event is unregistered in trace_remove_event_call() */ - trace_remove_event_call(&tu->call); + ret = trace_remove_event_call(&tu->call); + if (ret) + return ret; kfree(tu->call.print_fmt); tu->call.print_fmt = NULL; + return 0; } /* Make a trace interface for controling probe points */ diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c index d8c30db06c5b..9064b919a406 100644 --- a/kernel/user_namespace.c +++ b/kernel/user_namespace.c @@ -62,6 +62,9 @@ int create_user_ns(struct cred *new) kgid_t group = new->egid; int ret; + if (parent_ns->level > 32) + return -EUSERS; + /* * Verify that we can not violate the policy of which files * may be accessed that is specified by the root directory, @@ -92,6 +95,7 @@ int create_user_ns(struct cred *new) atomic_set(&ns->count, 1); /* Leave the new->user_ns reference with the new user namespace. */ ns->parent = parent_ns; + ns->level = parent_ns->level + 1; ns->owner = owner; ns->group = group; @@ -105,16 +109,21 @@ int create_user_ns(struct cred *new) int unshare_userns(unsigned long unshare_flags, struct cred **new_cred) { struct cred *cred; + int err = -ENOMEM; if (!(unshare_flags & CLONE_NEWUSER)) return 0; cred = prepare_creds(); - if (!cred) - return -ENOMEM; + if (cred) { + err = create_user_ns(cred); + if (err) + put_cred(cred); + else + *new_cred = cred; + } - *new_cred = cred; - return create_user_ns(cred); + return err; } void free_user_ns(struct user_namespace *ns) diff --git a/kernel/wait.c b/kernel/wait.c index ce0daa320a26..dec68bd4e9d8 100644 --- a/kernel/wait.c +++ b/kernel/wait.c @@ -333,7 +333,8 @@ int __wait_on_atomic_t(wait_queue_head_t *wq, struct wait_bit_queue *q, prepare_to_wait(wq, &q->wait, mode); val = q->key.flags; if (atomic_read(val) == 0) - ret = (*action)(val); + break; + ret = (*action)(val); } while (!ret && atomic_read(val) != 0); finish_wait(wq, &q->wait); return ret; diff --git a/kernel/watchdog.c b/kernel/watchdog.c index 05039e348f07..1241d8c91d5e 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -29,9 +29,9 @@ #include <linux/kvm_para.h> #include <linux/perf_event.h> -int watchdog_enabled = 1; +int watchdog_user_enabled = 1; int __read_mostly watchdog_thresh = 10; -static int __read_mostly watchdog_disabled; +static int __read_mostly watchdog_running; static u64 __read_mostly sample_period; static DEFINE_PER_CPU(unsigned long, watchdog_touch_ts); @@ -63,7 +63,7 @@ static int __init hardlockup_panic_setup(char *str) else if (!strncmp(str, "nopanic", 7)) hardlockup_panic = 0; else if (!strncmp(str, "0", 1)) - watchdog_enabled = 0; + watchdog_user_enabled = 0; return 1; } __setup("nmi_watchdog=", hardlockup_panic_setup); @@ -82,7 +82,7 @@ __setup("softlockup_panic=", softlockup_panic_setup); static int __init nowatchdog_setup(char *str) { - watchdog_enabled = 0; + watchdog_user_enabled = 0; return 1; } __setup("nowatchdog", nowatchdog_setup); @@ -90,7 +90,7 @@ __setup("nowatchdog", nowatchdog_setup); /* deprecated */ static int __init nosoftlockup_setup(char *str) { - watchdog_enabled = 0; + watchdog_user_enabled = 0; return 1; } __setup("nosoftlockup", nosoftlockup_setup); @@ -158,7 +158,7 @@ void touch_all_softlockup_watchdogs(void) #ifdef CONFIG_HARDLOCKUP_DETECTOR void touch_nmi_watchdog(void) { - if (watchdog_enabled) { + if (watchdog_user_enabled) { unsigned cpu; for_each_present_cpu(cpu) { @@ -347,11 +347,6 @@ static void watchdog_enable(unsigned int cpu) hrtimer_init(hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); hrtimer->function = watchdog_timer_fn; - if (!watchdog_enabled) { - kthread_park(current); - return; - } - /* Enable the perf event */ watchdog_nmi_enable(cpu); @@ -374,6 +369,11 @@ static void watchdog_disable(unsigned int cpu) watchdog_nmi_disable(cpu); } +static void watchdog_cleanup(unsigned int cpu, bool online) +{ + watchdog_disable(cpu); +} + static int watchdog_should_run(unsigned int cpu) { return __this_cpu_read(hrtimer_interrupts) != @@ -475,28 +475,40 @@ static int watchdog_nmi_enable(unsigned int cpu) { return 0; } static void watchdog_nmi_disable(unsigned int cpu) { return; } #endif /* CONFIG_HARDLOCKUP_DETECTOR */ -/* prepare/enable/disable routines */ -/* sysctl functions */ -#ifdef CONFIG_SYSCTL -static void watchdog_enable_all_cpus(void) +static struct smp_hotplug_thread watchdog_threads = { + .store = &softlockup_watchdog, + .thread_should_run = watchdog_should_run, + .thread_fn = watchdog, + .thread_comm = "watchdog/%u", + .setup = watchdog_enable, + .cleanup = watchdog_cleanup, + .park = watchdog_disable, + .unpark = watchdog_enable, +}; + +static int watchdog_enable_all_cpus(void) { - unsigned int cpu; + int err = 0; - if (watchdog_disabled) { - watchdog_disabled = 0; - for_each_online_cpu(cpu) - kthread_unpark(per_cpu(softlockup_watchdog, cpu)); + if (!watchdog_running) { + err = smpboot_register_percpu_thread(&watchdog_threads); + if (err) + pr_err("Failed to create watchdog threads, disabled\n"); + else + watchdog_running = 1; } + + return err; } +/* prepare/enable/disable routines */ +/* sysctl functions */ +#ifdef CONFIG_SYSCTL static void watchdog_disable_all_cpus(void) { - unsigned int cpu; - - if (!watchdog_disabled) { - watchdog_disabled = 1; - for_each_online_cpu(cpu) - kthread_park(per_cpu(softlockup_watchdog, cpu)); + if (watchdog_running) { + watchdog_running = 0; + smpboot_unregister_percpu_thread(&watchdog_threads); } } @@ -507,45 +519,48 @@ static void watchdog_disable_all_cpus(void) int proc_dowatchdog(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { - int ret; + int err, old_thresh, old_enabled; - if (watchdog_disabled < 0) - return -ENODEV; + old_thresh = ACCESS_ONCE(watchdog_thresh); + old_enabled = ACCESS_ONCE(watchdog_user_enabled); - ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); - if (ret || !write) - return ret; + err = proc_dointvec_minmax(table, write, buffer, lenp, ppos); + if (err || !write) + return err; set_sample_period(); /* * Watchdog threads shouldn't be enabled if they are - * disabled. The 'watchdog_disabled' variable check in + * disabled. The 'watchdog_running' variable check in * watchdog_*_all_cpus() function takes care of this. */ - if (watchdog_enabled && watchdog_thresh) - watchdog_enable_all_cpus(); + if (watchdog_user_enabled && watchdog_thresh) + err = watchdog_enable_all_cpus(); else watchdog_disable_all_cpus(); - return ret; + /* Restore old values on failure */ + if (err) { + watchdog_thresh = old_thresh; + watchdog_user_enabled = old_enabled; + } + + return err; } #endif /* CONFIG_SYSCTL */ -static struct smp_hotplug_thread watchdog_threads = { - .store = &softlockup_watchdog, - .thread_should_run = watchdog_should_run, - .thread_fn = watchdog, - .thread_comm = "watchdog/%u", - .setup = watchdog_enable, - .park = watchdog_disable, - .unpark = watchdog_enable, -}; - void __init lockup_detector_init(void) { set_sample_period(); - if (smpboot_register_percpu_thread(&watchdog_threads)) { - pr_err("Failed to create watchdog threads, disabled\n"); - watchdog_disabled = -ENODEV; + +#ifdef CONFIG_NO_HZ_FULL + if (watchdog_user_enabled) { + watchdog_user_enabled = 0; + pr_warning("Disabled lockup detectors by default for full dynticks\n"); + pr_warning("You can reactivate it with 'sysctl -w kernel.watchdog=1'\n"); } +#endif + + if (watchdog_user_enabled) + watchdog_enable_all_cpus(); } diff --git a/kernel/workqueue.c b/kernel/workqueue.c index f02c4a4a0c3c..7f5d4be22034 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -2817,6 +2817,19 @@ already_gone: return false; } +static bool __flush_work(struct work_struct *work) +{ + struct wq_barrier barr; + + if (start_flush_work(work, &barr)) { + wait_for_completion(&barr.done); + destroy_work_on_stack(&barr.work); + return true; + } else { + return false; + } +} + /** * flush_work - wait for a work to finish executing the last queueing instance * @work: the work to flush @@ -2830,18 +2843,10 @@ already_gone: */ bool flush_work(struct work_struct *work) { - struct wq_barrier barr; - lock_map_acquire(&work->lockdep_map); lock_map_release(&work->lockdep_map); - if (start_flush_work(work, &barr)) { - wait_for_completion(&barr.done); - destroy_work_on_stack(&barr.work); - return true; - } else { - return false; - } + return __flush_work(work); } EXPORT_SYMBOL_GPL(flush_work); @@ -3411,6 +3416,12 @@ static void copy_workqueue_attrs(struct workqueue_attrs *to, { to->nice = from->nice; cpumask_copy(to->cpumask, from->cpumask); + /* + * Unlike hash and equality test, this function doesn't ignore + * ->no_numa as it is used for both pool and wq attrs. Instead, + * get_unbound_pool() explicitly clears ->no_numa after copying. + */ + to->no_numa = from->no_numa; } /* hash value of the content of @attr */ @@ -3578,6 +3589,12 @@ static struct worker_pool *get_unbound_pool(const struct workqueue_attrs *attrs) lockdep_set_subclass(&pool->lock, 1); /* see put_pwq() */ copy_workqueue_attrs(pool->attrs, attrs); + /* + * no_numa isn't a worker_pool attribute, always clear it. See + * 'struct workqueue_attrs' comments for detail. + */ + pool->attrs->no_numa = false; + /* if cpumask is contained inside a NUMA node, we belong to that node */ if (wq_numa_enabled) { for_each_node(node) { @@ -4644,7 +4661,7 @@ static void restore_unbound_workers_cpumask(struct worker_pool *pool, int cpu) * Workqueues should be brought up before normal priority CPU notifiers. * This will be registered high priority CPU notifier. */ -static int __cpuinit workqueue_cpu_up_callback(struct notifier_block *nfb, +static int workqueue_cpu_up_callback(struct notifier_block *nfb, unsigned long action, void *hcpu) { @@ -4697,7 +4714,7 @@ static int __cpuinit workqueue_cpu_up_callback(struct notifier_block *nfb, * Workqueues should be brought down after normal priority CPU notifiers. * This will be registered as low priority CPU notifier. */ -static int __cpuinit workqueue_cpu_down_callback(struct notifier_block *nfb, +static int workqueue_cpu_down_callback(struct notifier_block *nfb, unsigned long action, void *hcpu) { @@ -4756,7 +4773,14 @@ long work_on_cpu(int cpu, long (*fn)(void *), void *arg) INIT_WORK_ONSTACK(&wfc.work, work_for_cpu_fn); schedule_work_on(cpu, &wfc.work); - flush_work(&wfc.work); + + /* + * The work item is on-stack and can't lead to deadlock through + * flushing. Use __flush_work() to avoid spurious lockdep warnings + * when work_on_cpu()s are nested. + */ + __flush_work(&wfc.work); + return wfc.ret; } EXPORT_SYMBOL_GPL(work_on_cpu); |