diff options
Diffstat (limited to 'kernel')
86 files changed, 4925 insertions, 2047 deletions
diff --git a/kernel/Makefile b/kernel/Makefile index 988cb3d..e898c5b 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -9,7 +9,7 @@ obj-y = sched.o fork.o exec_domain.o panic.o printk.o \ rcupdate.o extable.o params.o posix-timers.o \ kthread.o wait.o kfifo.o sys_ni.o posix-cpu-timers.o mutex.o \ hrtimer.o rwsem.o nsproxy.o srcu.o semaphore.o \ - notifier.o ksysfs.o pm_qos_params.o sched_clock.o cred.o \ + notifier.o ksysfs.o sched_clock.o cred.o \ async.o range.o obj-y += groups.o diff --git a/kernel/async.c b/kernel/async.c index d5fe7af..4c2843c 100644 --- a/kernel/async.c +++ b/kernel/async.c @@ -120,7 +120,7 @@ static void async_run_entry_fn(struct work_struct *work) struct async_entry *entry = container_of(work, struct async_entry, work); unsigned long flags; - ktime_t calltime, delta, rettime; + ktime_t uninitialized_var(calltime), delta, rettime; /* 1) move self to the running queue */ spin_lock_irqsave(&async_lock, flags); @@ -269,7 +269,7 @@ EXPORT_SYMBOL_GPL(async_synchronize_full_domain); void async_synchronize_cookie_domain(async_cookie_t cookie, struct list_head *running) { - ktime_t starttime, delta, endtime; + ktime_t uninitialized_var(starttime), delta, endtime; if (initcall_debug && system_state == SYSTEM_BOOTING) { printk(KERN_DEBUG "async_waiting @ %i\n", task_pid_nr(current)); diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 1d2b6ce..453100a 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -265,7 +265,7 @@ list_for_each_entry(_root, &roots, root_list) /* the list of cgroups eligible for automatic release. Protected by * release_list_lock */ static LIST_HEAD(release_list); -static DEFINE_SPINLOCK(release_list_lock); +static DEFINE_RAW_SPINLOCK(release_list_lock); static void cgroup_release_agent(struct work_struct *work); static DECLARE_WORK(release_agent_work, cgroup_release_agent); static void check_for_release(struct cgroup *cgrp); @@ -4014,11 +4014,11 @@ again: finish_wait(&cgroup_rmdir_waitq, &wait); clear_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags); - spin_lock(&release_list_lock); + raw_spin_lock(&release_list_lock); set_bit(CGRP_REMOVED, &cgrp->flags); if (!list_empty(&cgrp->release_list)) list_del_init(&cgrp->release_list); - spin_unlock(&release_list_lock); + raw_spin_unlock(&release_list_lock); cgroup_lock_hierarchy(cgrp->root); /* delete this cgroup from parent->children */ @@ -4671,13 +4671,13 @@ static void check_for_release(struct cgroup *cgrp) * already queued for a userspace notification, queue * it now */ int need_schedule_work = 0; - spin_lock(&release_list_lock); + raw_spin_lock(&release_list_lock); if (!cgroup_is_removed(cgrp) && list_empty(&cgrp->release_list)) { list_add(&cgrp->release_list, &release_list); need_schedule_work = 1; } - spin_unlock(&release_list_lock); + raw_spin_unlock(&release_list_lock); if (need_schedule_work) schedule_work(&release_agent_work); } @@ -4729,7 +4729,7 @@ static void cgroup_release_agent(struct work_struct *work) { BUG_ON(work != &release_agent_work); mutex_lock(&cgroup_mutex); - spin_lock(&release_list_lock); + raw_spin_lock(&release_list_lock); while (!list_empty(&release_list)) { char *argv[3], *envp[3]; int i; @@ -4738,7 +4738,7 @@ static void cgroup_release_agent(struct work_struct *work) struct cgroup, release_list); list_del_init(&cgrp->release_list); - spin_unlock(&release_list_lock); + raw_spin_unlock(&release_list_lock); pathbuf = kmalloc(PAGE_SIZE, GFP_KERNEL); if (!pathbuf) goto continue_free; @@ -4768,9 +4768,9 @@ static void cgroup_release_agent(struct work_struct *work) continue_free: kfree(pathbuf); kfree(agentbuf); - spin_lock(&release_list_lock); + raw_spin_lock(&release_list_lock); } - spin_unlock(&release_list_lock); + raw_spin_unlock(&release_list_lock); mutex_unlock(&cgroup_mutex); } diff --git a/kernel/crash_dump.c b/kernel/crash_dump.c index 5f85690..69ebf33 100644 --- a/kernel/crash_dump.c +++ b/kernel/crash_dump.c @@ -20,8 +20,15 @@ unsigned long saved_max_pfn; unsigned long long elfcorehdr_addr = ELFCORE_ADDR_MAX; /* + * stores the size of elf header of crash image + */ +unsigned long long elfcorehdr_size; + +/* * elfcorehdr= specifies the location of elf core header stored by the crashed * kernel. This option will be passed by kexec loader to the capture kernel. + * + * Syntax: elfcorehdr=[size[KMG]@]offset[KMG] */ static int __init setup_elfcorehdr(char *arg) { @@ -29,6 +36,10 @@ static int __init setup_elfcorehdr(char *arg) if (!arg) return -EINVAL; elfcorehdr_addr = memparse(arg, &end); + if (*end == '@') { + elfcorehdr_size = elfcorehdr_addr; + elfcorehdr_addr = memparse(end + 1, &end); + } return end > arg ? 0 : -EINVAL; } early_param("elfcorehdr", setup_elfcorehdr); diff --git a/kernel/cred.c b/kernel/cred.c index 8ef31f5..bb55d05 100644 --- a/kernel/cred.c +++ b/kernel/cred.c @@ -644,6 +644,9 @@ void __init cred_init(void) */ struct cred *prepare_kernel_cred(struct task_struct *daemon) { +#ifdef CONFIG_KEYS + struct thread_group_cred *tgcred; +#endif const struct cred *old; struct cred *new; @@ -651,6 +654,14 @@ struct cred *prepare_kernel_cred(struct task_struct *daemon) if (!new) return NULL; +#ifdef CONFIG_KEYS + tgcred = kmalloc(sizeof(*tgcred), GFP_KERNEL); + if (!tgcred) { + kmem_cache_free(cred_jar, new); + return NULL; + } +#endif + kdebug("prepare_kernel_cred() alloc %p", new); if (daemon) @@ -667,8 +678,11 @@ struct cred *prepare_kernel_cred(struct task_struct *daemon) get_group_info(new->group_info); #ifdef CONFIG_KEYS - atomic_inc(&init_tgcred.usage); - new->tgcred = &init_tgcred; + atomic_set(&tgcred->usage, 1); + spin_lock_init(&tgcred->lock); + tgcred->process_keyring = NULL; + tgcred->session_keyring = NULL; + new->tgcred = tgcred; new->request_key_auth = NULL; new->thread_keyring = NULL; new->jit_keyring = KEY_REQKEY_DEFL_THREAD_KEYRING; diff --git a/kernel/debug/gdbstub.c b/kernel/debug/gdbstub.c index 3487248..c22d8c2 100644 --- a/kernel/debug/gdbstub.c +++ b/kernel/debug/gdbstub.c @@ -217,7 +217,7 @@ void gdbstub_msg_write(const char *s, int len) /* Pack in hex chars */ for (i = 0; i < wcount; i++) - bufptr = pack_hex_byte(bufptr, s[i]); + bufptr = hex_byte_pack(bufptr, s[i]); *bufptr = '\0'; /* Move up */ @@ -249,7 +249,7 @@ char *kgdb_mem2hex(char *mem, char *buf, int count) if (err) return NULL; while (count > 0) { - buf = pack_hex_byte(buf, *tmp); + buf = hex_byte_pack(buf, *tmp); tmp++; count--; } @@ -411,14 +411,14 @@ static char *pack_threadid(char *pkt, unsigned char *id) limit = id + (BUF_THREAD_ID_SIZE / 2); while (id < limit) { if (!lzero || *id != 0) { - pkt = pack_hex_byte(pkt, *id); + pkt = hex_byte_pack(pkt, *id); lzero = 0; } id++; } if (lzero) - pkt = pack_hex_byte(pkt, 0); + pkt = hex_byte_pack(pkt, 0); return pkt; } @@ -486,7 +486,7 @@ static void gdb_cmd_status(struct kgdb_state *ks) dbg_remove_all_break(); remcom_out_buffer[0] = 'S'; - pack_hex_byte(&remcom_out_buffer[1], ks->signo); + hex_byte_pack(&remcom_out_buffer[1], ks->signo); } static void gdb_get_regs_helper(struct kgdb_state *ks) @@ -954,7 +954,7 @@ int gdb_serial_stub(struct kgdb_state *ks) /* Reply to host that an exception has occurred */ ptr = remcom_out_buffer; *ptr++ = 'T'; - ptr = pack_hex_byte(ptr, ks->signo); + ptr = hex_byte_pack(ptr, ks->signo); ptr += strlen(strcpy(ptr, "thread:")); int_to_threadref(thref, shadow_pid(current->pid)); ptr = pack_threadid(ptr, thref); diff --git a/kernel/events/core.c b/kernel/events/core.c index fbe38f2..12a0287 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -29,6 +29,7 @@ #include <linux/hardirq.h> #include <linux/rculist.h> #include <linux/uaccess.h> +#include <linux/suspend.h> #include <linux/syscalls.h> #include <linux/anon_inodes.h> #include <linux/kernel_stat.h> @@ -3543,7 +3544,7 @@ static void perf_mmap_close(struct vm_area_struct *vma) struct ring_buffer *rb = event->rb; atomic_long_sub((size >> PAGE_SHIFT) + 1, &user->locked_vm); - vma->vm_mm->locked_vm -= event->mmap_locked; + vma->vm_mm->pinned_vm -= event->mmap_locked; rcu_assign_pointer(event->rb, NULL); mutex_unlock(&event->mmap_mutex); @@ -3624,7 +3625,7 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma) lock_limit = rlimit(RLIMIT_MEMLOCK); lock_limit >>= PAGE_SHIFT; - locked = vma->vm_mm->locked_vm + extra; + locked = vma->vm_mm->pinned_vm + extra; if ((locked > lock_limit) && perf_paranoid_tracepoint_raw() && !capable(CAP_IPC_LOCK)) { @@ -3650,7 +3651,7 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma) atomic_long_add(user_extra, &user->locked_vm); event->mmap_locked = extra; event->mmap_user = get_current_user(); - vma->vm_mm->locked_vm += event->mmap_locked; + vma->vm_mm->pinned_vm += event->mmap_locked; unlock: if (!ret) @@ -6852,7 +6853,7 @@ static void __cpuinit perf_event_init_cpu(int cpu) struct swevent_htable *swhash = &per_cpu(swevent_htable, cpu); mutex_lock(&swhash->hlist_mutex); - if (swhash->hlist_refcount > 0) { + if (swhash->hlist_refcount > 0 && !swhash->swevent_hlist) { struct swevent_hlist *hlist; hlist = kzalloc_node(sizeof(*hlist), GFP_KERNEL, cpu_to_node(cpu)); @@ -6941,7 +6942,14 @@ perf_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu) { unsigned int cpu = (long)hcpu; - switch (action & ~CPU_TASKS_FROZEN) { + /* + * Ignore suspend/resume action, the perf_pm_notifier will + * take care of that. + */ + if (action & CPU_TASKS_FROZEN) + return NOTIFY_OK; + + switch (action) { case CPU_UP_PREPARE: case CPU_DOWN_FAILED: @@ -6960,6 +6968,90 @@ perf_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu) return NOTIFY_OK; } +static void perf_pm_resume_cpu(void *unused) +{ + struct perf_cpu_context *cpuctx; + struct perf_event_context *ctx; + struct pmu *pmu; + int idx; + + idx = srcu_read_lock(&pmus_srcu); + list_for_each_entry_rcu(pmu, &pmus, entry) { + cpuctx = this_cpu_ptr(pmu->pmu_cpu_context); + ctx = cpuctx->task_ctx; + + perf_ctx_lock(cpuctx, ctx); + perf_pmu_disable(cpuctx->ctx.pmu); + + cpu_ctx_sched_out(cpuctx, EVENT_ALL); + if (ctx) + ctx_sched_out(ctx, cpuctx, EVENT_ALL); + + perf_pmu_enable(cpuctx->ctx.pmu); + perf_ctx_unlock(cpuctx, ctx); + } + srcu_read_unlock(&pmus_srcu, idx); +} + +static void perf_pm_suspend_cpu(void *unused) +{ + struct perf_cpu_context *cpuctx; + struct perf_event_context *ctx; + struct pmu *pmu; + int idx; + + idx = srcu_read_lock(&pmus_srcu); + list_for_each_entry_rcu(pmu, &pmus, entry) { + cpuctx = this_cpu_ptr(pmu->pmu_cpu_context); + ctx = cpuctx->task_ctx; + + perf_ctx_lock(cpuctx, ctx); + perf_pmu_disable(cpuctx->ctx.pmu); + + perf_event_sched_in(cpuctx, ctx, current); + + perf_pmu_enable(cpuctx->ctx.pmu); + perf_ctx_unlock(cpuctx, ctx); + } + srcu_read_unlock(&pmus_srcu, idx); +} + +static int perf_resume(void) +{ + get_online_cpus(); + smp_call_function(perf_pm_resume_cpu, NULL, 1); + put_online_cpus(); + + return NOTIFY_OK; +} + +static int perf_suspend(void) +{ + get_online_cpus(); + smp_call_function(perf_pm_suspend_cpu, NULL, 1); + put_online_cpus(); + + return NOTIFY_OK; +} + +static int perf_pm(struct notifier_block *self, unsigned long action, void *ptr) +{ + switch (action) { + case PM_POST_HIBERNATION: + case PM_POST_SUSPEND: + return perf_resume(); + case PM_HIBERNATION_PREPARE: + case PM_SUSPEND_PREPARE: + return perf_suspend(); + default: + return NOTIFY_DONE; + } +} + +static struct notifier_block perf_pm_notifier = { + .notifier_call = perf_pm, +}; + void __init perf_event_init(void) { int ret; @@ -6974,6 +7066,7 @@ void __init perf_event_init(void) perf_tp_register(); perf_cpu_notifier(perf_cpu_notify); register_reboot_notifier(&perf_reboot_notifier); + register_pm_notifier(&perf_pm_notifier); ret = init_hw_breakpoint(); WARN(ret, "hw_breakpoint initialization failed with: %d", ret); diff --git a/kernel/exit.c b/kernel/exit.c index 2913b35..d0b7d98 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -681,8 +681,6 @@ static void exit_mm(struct task_struct * tsk) enter_lazy_tlb(mm, current); /* We don't want this task to be frozen prematurely */ clear_freeze_flag(tsk); - if (tsk->signal->oom_score_adj == OOM_SCORE_ADJ_MIN) - atomic_dec(&mm->oom_disable_count); task_unlock(tsk); mm_update_next_owner(mm); mmput(mm); diff --git a/kernel/fork.c b/kernel/fork.c index 8e6b6f4..70d7619 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -501,7 +501,6 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p) mm->cached_hole_size = ~0UL; mm_init_aio(mm); mm_init_owner(mm, p); - atomic_set(&mm->oom_disable_count, 0); if (likely(!mm_alloc_pgd(mm))) { mm->def_flags = 0; @@ -816,8 +815,6 @@ good_mm: /* Initializing for Swap token stuff */ mm->token_priority = 0; mm->last_interval = 0; - if (tsk->signal->oom_score_adj == OOM_SCORE_ADJ_MIN) - atomic_inc(&mm->oom_disable_count); tsk->mm = mm; tsk->active_mm = mm; @@ -1391,13 +1388,8 @@ bad_fork_cleanup_io: bad_fork_cleanup_namespaces: exit_task_namespaces(p); bad_fork_cleanup_mm: - if (p->mm) { - task_lock(p); - if (p->signal->oom_score_adj == OOM_SCORE_ADJ_MIN) - atomic_dec(&p->mm->oom_disable_count); - task_unlock(p); + if (p->mm) mmput(p->mm); - } bad_fork_cleanup_signal: if (!(clone_flags & CLONE_THREAD)) free_signal_struct(p->signal); diff --git a/kernel/freezer.c b/kernel/freezer.c index 7b01de98..66a594e 100644 --- a/kernel/freezer.c +++ b/kernel/freezer.c @@ -67,7 +67,7 @@ static void fake_signal_wake_up(struct task_struct *p) unsigned long flags; spin_lock_irqsave(&p->sighand->siglock, flags); - signal_wake_up(p, 0); + signal_wake_up(p, 1); spin_unlock_irqrestore(&p->sighand->siglock, flags); } diff --git a/kernel/futex.c b/kernel/futex.c index 11cbe05..1511dff 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -854,7 +854,7 @@ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_q *this) { struct task_struct *new_owner; struct futex_pi_state *pi_state = this->pi_state; - u32 curval, newval; + u32 uninitialized_var(curval), newval; if (!pi_state) return -EINVAL; @@ -916,7 +916,7 @@ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_q *this) static int unlock_futex_pi(u32 __user *uaddr, u32 uval) { - u32 oldval; + u32 uninitialized_var(oldval); /* * There is no waiter, so we unlock the futex. The owner died @@ -1576,7 +1576,7 @@ static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q, u32 newtid = task_pid_vnr(newowner) | FUTEX_WAITERS; struct futex_pi_state *pi_state = q->pi_state; struct task_struct *oldowner = pi_state->owner; - u32 uval, curval, newval; + u32 uval, uninitialized_var(curval), newval; int ret; /* Owner died? */ @@ -1793,7 +1793,7 @@ static void futex_wait_queue_me(struct futex_hash_bucket *hb, struct futex_q *q, * * Returns: * 0 - uaddr contains val and hb has been locked - * <1 - -EFAULT or -EWOULDBLOCK (uaddr does not contain val) and hb is unlcoked + * <1 - -EFAULT or -EWOULDBLOCK (uaddr does not contain val) and hb is unlocked */ static int futex_wait_setup(u32 __user *uaddr, u32 val, unsigned int flags, struct futex_q *q, struct futex_hash_bucket **hb) @@ -2481,7 +2481,7 @@ err_unlock: */ int handle_futex_death(u32 __user *uaddr, struct task_struct *curr, int pi) { - u32 uval, nval, mval; + u32 uval, uninitialized_var(nval), mval; retry: if (get_user(uval, uaddr)) diff --git a/kernel/irq/generic-chip.c b/kernel/irq/generic-chip.c index e38544d..6cb7613 100644 --- a/kernel/irq/generic-chip.c +++ b/kernel/irq/generic-chip.c @@ -211,6 +211,7 @@ irq_alloc_generic_chip(const char *name, int num_ct, unsigned int irq_base, } return gc; } +EXPORT_SYMBOL_GPL(irq_alloc_generic_chip); /* * Separate lockdep class for interrupt chip which can nest irq_desc @@ -258,6 +259,7 @@ void irq_setup_generic_chip(struct irq_chip_generic *gc, u32 msk, } gc->irq_cnt = i - gc->irq_base; } +EXPORT_SYMBOL_GPL(irq_setup_generic_chip); /** * irq_setup_alt_chip - Switch to alternative chip @@ -281,6 +283,7 @@ int irq_setup_alt_chip(struct irq_data *d, unsigned int type) } return -EINVAL; } +EXPORT_SYMBOL_GPL(irq_setup_alt_chip); /** * irq_remove_generic_chip - Remove a chip @@ -311,6 +314,7 @@ void irq_remove_generic_chip(struct irq_chip_generic *gc, u32 msk, irq_modify_status(i, clr, set); } } +EXPORT_SYMBOL_GPL(irq_remove_generic_chip); #ifdef CONFIG_PM static int irq_gc_suspend(void) diff --git a/kernel/irq/pm.c b/kernel/irq/pm.c index f76fc00..15e53b1 100644 --- a/kernel/irq/pm.c +++ b/kernel/irq/pm.c @@ -9,6 +9,7 @@ #include <linux/irq.h> #include <linux/module.h> #include <linux/interrupt.h> +#include <linux/syscore_ops.h> #include "internals.h" @@ -39,25 +40,58 @@ void suspend_device_irqs(void) } EXPORT_SYMBOL_GPL(suspend_device_irqs); -/** - * resume_device_irqs - enable interrupt lines disabled by suspend_device_irqs() - * - * Enable all interrupt lines previously disabled by suspend_device_irqs() that - * have the IRQS_SUSPENDED flag set. - */ -void resume_device_irqs(void) +static void resume_irqs(bool want_early) { struct irq_desc *desc; int irq; for_each_irq_desc(irq, desc) { unsigned long flags; + bool is_early = desc->action && + desc->action->flags & IRQF_EARLY_RESUME; + + if (is_early != want_early) + continue; raw_spin_lock_irqsave(&desc->lock, flags); __enable_irq(desc, irq, true); raw_spin_unlock_irqrestore(&desc->lock, flags); } } + +/** + * irq_pm_syscore_ops - enable interrupt lines early + * + * Enable all interrupt lines with %IRQF_EARLY_RESUME set. + */ +static void irq_pm_syscore_resume(void) +{ + resume_irqs(true); +} + +static struct syscore_ops irq_pm_syscore_ops = { + .resume = irq_pm_syscore_resume, +}; + +static int __init irq_pm_init_ops(void) +{ + register_syscore_ops(&irq_pm_syscore_ops); + return 0; +} + +device_initcall(irq_pm_init_ops); + +/** + * resume_device_irqs - enable interrupt lines disabled by suspend_device_irqs() + * + * Enable all non-%IRQF_EARLY_RESUME interrupt lines previously + * disabled by suspend_device_irqs() that have the IRQS_SUSPENDED flag + * set as well as those with %IRQF_FORCE_RESUME. + */ +void resume_device_irqs(void) +{ + resume_irqs(false); +} EXPORT_SYMBOL_GPL(resume_device_irqs); /** diff --git a/kernel/irq_work.c b/kernel/irq_work.c index c58fa7d..0e2cde4 100644 --- a/kernel/irq_work.c +++ b/kernel/irq_work.c @@ -17,54 +17,34 @@ * claimed NULL, 3 -> {pending} : claimed to be enqueued * pending next, 3 -> {busy} : queued, pending callback * busy NULL, 2 -> {free, claimed} : callback in progress, can be claimed - * - * We use the lower two bits of the next pointer to keep PENDING and BUSY - * flags. */ #define IRQ_WORK_PENDING 1UL #define IRQ_WORK_BUSY 2UL #define IRQ_WORK_FLAGS 3UL -static inline bool irq_work_is_set(struct irq_work *entry, int flags) -{ - return (unsigned long)entry->next & flags; -} - -static inline struct irq_work *irq_work_next(struct irq_work *entry) -{ - unsigned long next = (unsigned long)entry->next; - next &= ~IRQ_WORK_FLAGS; - return (struct irq_work *)next; -} - -static inline struct irq_work *next_flags(struct irq_work *entry, int flags) -{ - unsigned long next = (unsigned long)entry; - next |= flags; - return (struct irq_work *)next; -} - -static DEFINE_PER_CPU(struct irq_work *, irq_work_list); +static DEFINE_PER_CPU(struct llist_head, irq_work_list); /* * Claim the entry so that no one else will poke at it. */ -static bool irq_work_claim(struct irq_work *entry) +static bool irq_work_claim(struct irq_work *work) { - struct irq_work *next, *nflags; + unsigned long flags, nflags; - do { - next = entry->next; - if ((unsigned long)next & IRQ_WORK_PENDING) + for (;;) { + flags = work->flags; + if (flags & IRQ_WORK_PENDING) return false; - nflags = next_flags(next, IRQ_WORK_FLAGS); - } while (cmpxchg(&entry->next, next, nflags) != next); + nflags = flags | IRQ_WORK_FLAGS; + if (cmpxchg(&work->flags, flags, nflags) == flags) + break; + cpu_relax(); + } return true; } - void __weak arch_irq_work_raise(void) { /* @@ -75,20 +55,15 @@ void __weak arch_irq_work_raise(void) /* * Queue the entry and raise the IPI if needed. */ -static void __irq_work_queue(struct irq_work *entry) +static void __irq_work_queue(struct irq_work *work) { - struct irq_work *next; + bool empty; preempt_disable(); - do { - next = __this_cpu_read(irq_work_list); - /* Can assign non-atomic because we keep the flags set. */ - entry->next = next_flags(next, IRQ_WORK_FLAGS); - } while (this_cpu_cmpxchg(irq_work_list, next, entry) != next); - + empty = llist_add(&work->llnode, &__get_cpu_var(irq_work_list)); /* The list was empty, raise self-interrupt to start processing. */ - if (!irq_work_next(entry)) + if (empty) arch_irq_work_raise(); preempt_enable(); @@ -100,16 +75,16 @@ static void __irq_work_queue(struct irq_work *entry) * * Can be re-enqueued while the callback is still in progress. */ -bool irq_work_queue(struct irq_work *entry) +bool irq_work_queue(struct irq_work *work) { - if (!irq_work_claim(entry)) { + if (!irq_work_claim(work)) { /* * Already enqueued, can't do! */ return false; } - __irq_work_queue(entry); + __irq_work_queue(work); return true; } EXPORT_SYMBOL_GPL(irq_work_queue); @@ -120,34 +95,34 @@ EXPORT_SYMBOL_GPL(irq_work_queue); */ void irq_work_run(void) { - struct irq_work *list; + struct irq_work *work; + struct llist_head *this_list; + struct llist_node *llnode; - if (this_cpu_read(irq_work_list) == NULL) + this_list = &__get_cpu_var(irq_work_list); + if (llist_empty(this_list)) return; BUG_ON(!in_irq()); BUG_ON(!irqs_disabled()); - list = this_cpu_xchg(irq_work_list, NULL); - - while (list != NULL) { - struct irq_work *entry = list; + llnode = llist_del_all(this_list); + while (llnode != NULL) { + work = llist_entry(llnode, struct irq_work, llnode); - list = irq_work_next(list); + llnode = llist_next(llnode); /* - * Clear the PENDING bit, after this point the @entry + * Clear the PENDING bit, after this point the @work * can be re-used. */ - entry->next = next_flags(NULL, IRQ_WORK_BUSY); - entry->func(entry); + work->flags = IRQ_WORK_BUSY; + work->func(work); /* * Clear the BUSY bit and return to the free state if * no-one else claimed it meanwhile. */ - (void)cmpxchg(&entry->next, - next_flags(NULL, IRQ_WORK_BUSY), - NULL); + (void)cmpxchg(&work->flags, IRQ_WORK_BUSY, 0); } } EXPORT_SYMBOL_GPL(irq_work_run); @@ -156,11 +131,11 @@ EXPORT_SYMBOL_GPL(irq_work_run); * Synchronize against the irq_work @entry, ensures the entry is not * currently in use. */ -void irq_work_sync(struct irq_work *entry) +void irq_work_sync(struct irq_work *work) { WARN_ON_ONCE(irqs_disabled()); - while (irq_work_is_set(entry, IRQ_WORK_BUSY)) + while (work->flags & IRQ_WORK_BUSY) cpu_relax(); } EXPORT_SYMBOL_GPL(irq_work_sync); diff --git a/kernel/kexec.c b/kernel/kexec.c index 296fbc8..dc7bc08 100644 --- a/kernel/kexec.c +++ b/kernel/kexec.c @@ -498,7 +498,7 @@ static struct page *kimage_alloc_crash_control_pages(struct kimage *image, while (hole_end <= crashk_res.end) { unsigned long i; - if (hole_end > KEXEC_CONTROL_MEMORY_LIMIT) + if (hole_end > KEXEC_CRASH_CONTROL_MEMORY_LIMIT) break; if (hole_end > crashk_res.end) break; @@ -999,6 +999,7 @@ SYSCALL_DEFINE4(kexec_load, unsigned long, entry, unsigned long, nr_segments, kimage_free(xchg(&kexec_crash_image, NULL)); result = kimage_crash_alloc(&image, entry, nr_segments, segments); + crash_map_reserved_pages(); } if (result) goto out; @@ -1015,6 +1016,8 @@ SYSCALL_DEFINE4(kexec_load, unsigned long, entry, unsigned long, nr_segments, goto out; } kimage_terminate(image); + if (flags & KEXEC_ON_CRASH) + crash_unmap_reserved_pages(); } /* Install the new kernel, and Uninstall the old */ image = xchg(dest_image, image); @@ -1026,6 +1029,18 @@ out: return result; } +/* + * Add and remove page tables for crashkernel memory + * + * Provide an empty default implementation here -- architecture + * code may override this + */ +void __weak crash_map_reserved_pages(void) +{} + +void __weak crash_unmap_reserved_pages(void) +{} + #ifdef CONFIG_COMPAT asmlinkage long compat_sys_kexec_load(unsigned long entry, unsigned long nr_segments, @@ -1134,14 +1149,16 @@ int crash_shrink_memory(unsigned long new_size) goto unlock; } - start = roundup(start, PAGE_SIZE); - end = roundup(start + new_size, PAGE_SIZE); + start = roundup(start, KEXEC_CRASH_MEM_ALIGN); + end = roundup(start + new_size, KEXEC_CRASH_MEM_ALIGN); + crash_map_reserved_pages(); crash_free_reserved_phys_range(end, crashk_res.end); if ((start == end) && (crashk_res.parent != NULL)) release_resource(&crashk_res); crashk_res.end = end - 1; + crash_unmap_reserved_pages(); unlock: mutex_unlock(&kexec_mutex); @@ -1380,24 +1397,23 @@ int __init parse_crashkernel(char *cmdline, } - -void crash_save_vmcoreinfo(void) +static void update_vmcoreinfo_note(void) { - u32 *buf; + u32 *buf = vmcoreinfo_note; if (!vmcoreinfo_size) return; - - vmcoreinfo_append_str("CRASHTIME=%ld", get_seconds()); - - buf = (u32 *)vmcoreinfo_note; - buf = append_elf_note(buf, VMCOREINFO_NOTE_NAME, 0, vmcoreinfo_data, vmcoreinfo_size); - final_note(buf); } +void crash_save_vmcoreinfo(void) +{ + vmcoreinfo_append_str("CRASHTIME=%ld", get_seconds()); + update_vmcoreinfo_note(); +} + void vmcoreinfo_append_str(const char *fmt, ...) { va_list args; @@ -1483,6 +1499,7 @@ static int __init crash_save_vmcoreinfo_init(void) VMCOREINFO_NUMBER(PG_swapcache); arch_crash_save_vmcoreinfo(); + update_vmcoreinfo_note(); return 0; } diff --git a/kernel/kmod.c b/kernel/kmod.c index ddc7644..a4bea97 100644 --- a/kernel/kmod.c +++ b/kernel/kmod.c @@ -114,10 +114,12 @@ int __request_module(bool wait, const char *fmt, ...) atomic_inc(&kmod_concurrent); if (atomic_read(&kmod_concurrent) > max_modprobes) { /* We may be blaming an innocent here, but unlikely */ - if (kmod_loop_msg++ < 5) + if (kmod_loop_msg < 5) { printk(KERN_ERR "request_module: runaway loop modprobe %s\n", module_name); + kmod_loop_msg++; + } atomic_dec(&kmod_concurrent); return -ENOMEM; } diff --git a/kernel/kprobes.c b/kernel/kprobes.c index b30fd54..2f193d0 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -78,10 +78,10 @@ static bool kprobes_all_disarmed; static DEFINE_MUTEX(kprobe_mutex); static DEFINE_PER_CPU(struct kprobe *, kprobe_instance) = NULL; static struct { - spinlock_t lock ____cacheline_aligned_in_smp; + raw_spinlock_t lock ____cacheline_aligned_in_smp; } kretprobe_table_locks[KPROBE_TABLE_SIZE]; -static spinlock_t *kretprobe_table_lock_ptr(unsigned long hash) +static raw_spinlock_t *kretprobe_table_lock_ptr(unsigned long hash) { return &(kretprobe_table_locks[hash].lock); } @@ -1013,9 +1013,9 @@ void __kprobes recycle_rp_inst(struct kretprobe_instance *ri, hlist_del(&ri->hlist); INIT_HLIST_NODE(&ri->hlist); if (likely(rp)) { - spin_lock(&rp->lock); + raw_spin_lock(&rp->lock); hlist_add_head(&ri->hlist, &rp->free_instances); - spin_unlock(&rp->lock); + raw_spin_unlock(&rp->lock); } else /* Unregistering */ hlist_add_head(&ri->hlist, head); @@ -1026,19 +1026,19 @@ void __kprobes kretprobe_hash_lock(struct task_struct *tsk, __acquires(hlist_lock) { unsigned long hash = hash_ptr(tsk, KPROBE_HASH_BITS); - spinlock_t *hlist_lock; + raw_spinlock_t *hlist_lock; *head = &kretprobe_inst_table[hash]; hlist_lock = kretprobe_table_lock_ptr(hash); - spin_lock_irqsave(hlist_lock, *flags); + raw_spin_lock_irqsave(hlist_lock, *flags); } static void __kprobes kretprobe_table_lock(unsigned long hash, unsigned long *flags) __acquires(hlist_lock) { - spinlock_t *hlist_lock = kretprobe_table_lock_ptr(hash); - spin_lock_irqsave(hlist_lock, *flags); + raw_spinlock_t *hlist_lock = kretprobe_table_lock_ptr(hash); + raw_spin_lock_irqsave(hlist_lock, *flags); } void __kprobes kretprobe_hash_unlock(struct task_struct *tsk, @@ -1046,18 +1046,18 @@ void __kprobes kretprobe_hash_unlock(struct task_struct *tsk, __releases(hlist_lock) { unsigned long hash = hash_ptr(tsk, KPROBE_HASH_BITS); - spinlock_t *hlist_lock; + raw_spinlock_t *hlist_lock; hlist_lock = kretprobe_table_lock_ptr(hash); - spin_unlock_irqrestore(hlist_lock, *flags); + raw_spin_unlock_irqrestore(hlist_lock, *flags); } static void __kprobes kretprobe_table_unlock(unsigned long hash, unsigned long *flags) __releases(hlist_lock) { - spinlock_t *hlist_lock = kretprobe_table_lock_ptr(hash); - spin_unlock_irqrestore(hlist_lock, *flags); + raw_spinlock_t *hlist_lock = kretprobe_table_lock_ptr(hash); + raw_spin_unlock_irqrestore(hlist_lock, *flags); } /* @@ -1663,12 +1663,12 @@ static int __kprobes pre_handler_kretprobe(struct kprobe *p, /*TODO: consider to only swap the RA after the last pre_handler fired */ hash = hash_ptr(current, KPROBE_HASH_BITS); - spin_lock_irqsave(&rp->lock, flags); + raw_spin_lock_irqsave(&rp->lock, flags); if (!hlist_empty(&rp->free_instances)) { ri = hlist_entry(rp->free_instances.first, struct kretprobe_instance, hlist); hlist_del(&ri->hlist); - spin_unlock_irqrestore(&rp->lock, flags); + raw_spin_unlock_irqrestore(&rp->lock, flags); ri->rp = rp; ri->task = current; @@ -1685,7 +1685,7 @@ static int __kprobes pre_handler_kretprobe(struct kprobe *p, kretprobe_table_unlock(hash, &flags); } else { rp->nmissed++; - spin_unlock_irqrestore(&rp->lock, flags); + raw_spin_unlock_irqrestore(&rp->lock, flags); } return 0; } @@ -1721,7 +1721,7 @@ int __kprobes register_kretprobe(struct kretprobe *rp) rp->maxactive = num_possible_cpus(); #endif } - spin_lock_init(&rp->lock); + raw_spin_lock_init(&rp->lock); INIT_HLIST_HEAD(&rp->free_instances); for (i = 0; i < rp->maxactive; i++) { inst = kmalloc(sizeof(struct kretprobe_instance) + @@ -1959,7 +1959,7 @@ static int __init init_kprobes(void) for (i = 0; i < KPROBE_TABLE_SIZE; i++) { INIT_HLIST_HEAD(&kprobe_table[i]); INIT_HLIST_HEAD(&kretprobe_inst_table[i]); - spin_lock_init(&(kretprobe_table_locks[i].lock)); + raw_spin_lock_init(&(kretprobe_table_locks[i].lock)); } /* diff --git a/kernel/latencytop.c b/kernel/latencytop.c index 376066e..4ac8ebf 100644 --- a/kernel/latencytop.c +++ b/kernel/latencytop.c @@ -58,7 +58,7 @@ #include <linux/list.h> #include <linux/stacktrace.h> -static DEFINE_SPINLOCK(latency_lock); +static DEFINE_RAW_SPINLOCK(latency_lock); #define MAXLR 128 static struct latency_record latency_record[MAXLR]; @@ -72,19 +72,19 @@ void clear_all_latency_tracing(struct task_struct *p) if (!latencytop_enabled) return; - spin_lock_irqsave(&latency_lock, flags); + raw_spin_lock_irqsave(&latency_lock, flags); memset(&p->latency_record, 0, sizeof(p->latency_record)); p->latency_record_count = 0; - spin_unlock_irqrestore(&latency_lock, flags); + raw_spin_unlock_irqrestore(&latency_lock, flags); } static void clear_global_latency_tracing(void) { unsigned long flags; - spin_lock_irqsave(&latency_lock, flags); + raw_spin_lock_irqsave(&latency_lock, flags); memset(&latency_record, 0, sizeof(latency_record)); - spin_unlock_irqrestore(&latency_lock, flags); + raw_spin_unlock_irqrestore(&latency_lock, flags); } static void __sched @@ -190,7 +190,7 @@ __account_scheduler_latency(struct task_struct *tsk, int usecs, int inter) lat.max = usecs; store_stacktrace(tsk, &lat); - spin_lock_irqsave(&latency_lock, flags); + raw_spin_lock_irqsave(&latency_lock, flags); account_global_scheduler_latency(tsk, &lat); @@ -231,7 +231,7 @@ __account_scheduler_latency(struct task_struct *tsk, int usecs, int inter) memcpy(&tsk->latency_record[i], &lat, sizeof(struct latency_record)); out_unlock: - spin_unlock_irqrestore(&latency_lock, flags); + raw_spin_unlock_irqrestore(&latency_lock, flags); } static int lstats_show(struct seq_file *m, void *v) diff --git a/kernel/lockdep.c b/kernel/lockdep.c index 91d67ce..e69434b 100644 --- a/kernel/lockdep.c +++ b/kernel/lockdep.c @@ -96,8 +96,13 @@ static int graph_lock(void) static inline int graph_unlock(void) { - if (debug_locks && !arch_spin_is_locked(&lockdep_lock)) + if (debug_locks && !arch_spin_is_locked(&lockdep_lock)) { + /* + * The lockdep graph lock isn't locked while we expect it to + * be, we're confused now, bye! + */ return DEBUG_LOCKS_WARN_ON(1); + } current->lockdep_recursion--; arch_spin_unlock(&lockdep_lock); @@ -134,6 +139,9 @@ static struct lock_class lock_classes[MAX_LOCKDEP_KEYS]; static inline struct lock_class *hlock_class(struct held_lock *hlock) { if (!hlock->class_idx) { + /* + * Someone passed in garbage, we give up. + */ DEBUG_LOCKS_WARN_ON(1); return NULL; } @@ -687,6 +695,10 @@ look_up_lock_class(struct lockdep_map *lock, unsigned int subclass) */ list_for_each_entry(class, hash_head, hash_entry) { if (class->key == key) { + /* + * Huh! same key, different name? Did someone trample + * on some memory? We're most confused. + */ WARN_ON_ONCE(class->name != lock->name); return class; } @@ -800,6 +812,10 @@ out_unlock_set: else if (subclass < NR_LOCKDEP_CACHING_CLASSES) lock->class_cache[subclass] = class; + /* + * Hash collision, did we smoke some? We found a class with a matching + * hash but the subclass -- which is hashed in -- didn't match. + */ if (DEBUG_LOCKS_WARN_ON(class->subclass != subclass)) return NULL; @@ -926,7 +942,7 @@ static inline void mark_lock_accessed(struct lock_list *lock, unsigned long nr; nr = lock - list_entries; - WARN_ON(nr >= nr_list_entries); + WARN_ON(nr >= nr_list_entries); /* Out-of-bounds, input fail */ lock->parent = parent; lock->class->dep_gen_id = lockdep_dependency_gen_id; } @@ -936,7 +952,7 @@ static inline unsigned long lock_accessed(struct lock_list *lock) unsigned long nr; nr = lock - list_entries; - WARN_ON(nr >= nr_list_entries); + WARN_ON(nr >= nr_list_entries); /* Out-of-bounds, input fail */ return lock->class->dep_gen_id == lockdep_dependency_gen_id; } @@ -1129,10 +1145,11 @@ print_circular_bug_header(struct lock_list *entry, unsigned int depth, if (debug_locks_silent) return 0; - printk("\n=======================================================\n"); - printk( "[ INFO: possible circular locking dependency detected ]\n"); + printk("\n"); + printk("======================================================\n"); + printk("[ INFO: possible circular locking dependency detected ]\n"); print_kernel_version(); - printk( "-------------------------------------------------------\n"); + printk("-------------------------------------------------------\n"); printk("%s/%d is trying to acquire lock:\n", curr->comm, task_pid_nr(curr)); print_lock(check_src); @@ -1196,6 +1213,9 @@ static noinline int print_bfs_bug(int ret) if (!debug_locks_off_graph_unlock()) return 0; + /* + * Breadth-first-search failed, graph got corrupted? + */ WARN(1, "lockdep bfs error:%d\n", ret); return 0; @@ -1463,11 +1483,12 @@ print_bad_irq_dependency(struct task_struct *curr, if (!debug_locks_off_graph_unlock() || debug_locks_silent) return 0; - printk("\n======================================================\n"); - printk( "[ INFO: %s-safe -> %s-unsafe lock order detected ]\n", + printk("\n"); + printk("======================================================\n"); + printk("[ INFO: %s-safe -> %s-unsafe lock order detected ]\n", irqclass, irqclass); print_kernel_version(); - printk( "------------------------------------------------------\n"); + printk("------------------------------------------------------\n"); printk("%s/%d [HC%u[%lu]:SC%u[%lu]:HE%u:SE%u] is trying to acquire:\n", curr->comm, task_pid_nr(curr), curr->hardirq_context, hardirq_count() >> HARDIRQ_SHIFT, @@ -1692,10 +1713,11 @@ print_deadlock_bug(struct task_struct *curr, struct held_lock *prev, if (!debug_locks_off_graph_unlock() || debug_locks_silent) return 0; - printk("\n=============================================\n"); - printk( "[ INFO: possible recursive locking detected ]\n"); + printk("\n"); + printk("=============================================\n"); + printk("[ INFO: possible recursive locking detected ]\n"); print_kernel_version(); - printk( "---------------------------------------------\n"); + printk("---------------------------------------------\n"); printk("%s/%d is trying to acquire lock:\n", curr->comm, task_pid_nr(curr)); print_lock(next); @@ -1944,6 +1966,11 @@ out_bug: if (!debug_locks_off_graph_unlock()) return 0; + /* + * Clearly we all shouldn't be here, but since we made it we + * can reliable say we messed up our state. See the above two + * gotos for reasons why we could possibly end up here. + */ WARN_ON(1); return 0; @@ -1975,6 +2002,11 @@ static inline int lookup_chain_cache(struct task_struct *curr, struct held_lock *hlock_curr, *hlock_next; int i, j; + /* + * We might need to take the graph lock, ensure we've got IRQs + * disabled to make this an IRQ-safe lock.. for recursion reasons + * lockdep won't complain about its own locking errors. + */ if (DEBUG_LOCKS_WARN_ON(!irqs_disabled())) return 0; /* @@ -2126,6 +2158,10 @@ static void check_chain_key(struct task_struct *curr) hlock = curr->held_locks + i; if (chain_key != hlock->prev_chain_key) { debug_locks_off(); + /* + * We got mighty confused, our chain keys don't match + * with what we expect, someone trample on our task state? + */ WARN(1, "hm#1, depth: %u [%u], %016Lx != %016Lx\n", curr->lockdep_depth, i, (unsigned long long)chain_key, @@ -2133,6 +2169,9 @@ static void check_chain_key(struct task_struct *curr) return; } id = hlock->class_idx - 1; + /* + * Whoops ran out of static storage again? + */ if (DEBUG_LOCKS_WARN_ON(id >= MAX_LOCKDEP_KEYS)) return; @@ -2144,6 +2183,10 @@ static void check_chain_key(struct task_struct *curr) } if (chain_key != curr->curr_chain_key) { debug_locks_off(); + /* + * More smoking hash instead of calculating it, damn see these + * numbers float.. I bet that a pink elephant stepped on my memory. + */ WARN(1, "hm#2, depth: %u [%u], %016Lx != %016Lx\n", curr->lockdep_depth, i, (unsigned long long)chain_key, @@ -2177,10 +2220,11 @@ print_usage_bug(struct task_struct *curr, struct held_lock *this, if (!debug_locks_off_graph_unlock() || debug_locks_silent) return 0; - printk("\n=================================\n"); - printk( "[ INFO: inconsistent lock state ]\n"); + printk("\n"); + printk("=================================\n"); + printk("[ INFO: inconsistent lock state ]\n"); print_kernel_version(); - printk( "---------------------------------\n"); + printk("---------------------------------\n"); printk("inconsistent {%s} -> {%s} usage.\n", usage_str[prev_bit], usage_str[new_bit]); @@ -2241,10 +2285,11 @@ print_irq_inversion_bug(struct task_struct *curr, if (!debug_locks_off_graph_unlock() || debug_locks_silent) return 0; - printk("\n=========================================================\n"); - printk( "[ INFO: possible irq lock inversion dependency detected ]\n"); + printk("\n"); + printk("=========================================================\n"); + printk("[ INFO: possible irq lock inversion dependency detected ]\n"); print_kernel_version(); - printk( "---------------------------------------------------------\n"); + printk("---------------------------------------------------------\n"); printk("%s/%d just changed the state of lock:\n", curr->comm, task_pid_nr(curr)); print_lock(this); @@ -2525,12 +2570,24 @@ void trace_hardirqs_on_caller(unsigned long ip) return; } + /* + * We're enabling irqs and according to our state above irqs weren't + * already enabled, yet we find the hardware thinks they are in fact + * enabled.. someone messed up their IRQ state tracing. + */ if (DEBUG_LOCKS_WARN_ON(!irqs_disabled())) return; + /* + * See the fine text that goes along with this variable definition. + */ if (DEBUG_LOCKS_WARN_ON(unlikely(early_boot_irqs_disabled))) return; + /* + * Can't allow enabling interrupts while in an interrupt handler, + * that's general bad form and such. Recursion, limited stack etc.. + */ if (DEBUG_LOCKS_WARN_ON(current->hardirq_context)) return; @@ -2558,6 +2615,10 @@ void trace_hardirqs_off_caller(unsigned long ip) if (unlikely(!debug_locks || current->lockdep_recursion)) return; + /* + * So we're supposed to get called after you mask local IRQs, but for + * some reason the hardware doesn't quite think you did a proper job. + */ if (DEBUG_LOCKS_WARN_ON(!irqs_disabled())) return; @@ -2590,6 +2651,10 @@ void trace_softirqs_on(unsigned long ip) if (unlikely(!debug_locks || current->lockdep_recursion)) return; + /* + * We fancy IRQs being disabled here, see softirq.c, avoids + * funny state and nesting things. + */ if (DEBUG_LOCKS_WARN_ON(!irqs_disabled())) return; @@ -2626,6 +2691,9 @@ void trace_softirqs_off(unsigned long ip) if (unlikely(!debug_locks || current->lockdep_recursion)) return; + /* + * We fancy IRQs being disabled here, see softirq.c + */ if (DEBUG_LOCKS_WARN_ON(!irqs_disabled())) return; @@ -2637,6 +2705,9 @@ void trace_softirqs_off(unsigned long ip) curr->softirq_disable_ip = ip; curr->softirq_disable_event = ++curr->irq_events; debug_atomic_inc(softirqs_off_events); + /* + * Whoops, we wanted softirqs off, so why aren't they? + */ DEBUG_LOCKS_WARN_ON(!softirq_count()); } else debug_atomic_inc(redundant_softirqs_off); @@ -2661,6 +2732,9 @@ static void __lockdep_trace_alloc(gfp_t gfp_mask, unsigned long flags) if (!(gfp_mask & __GFP_FS)) return; + /* + * Oi! Can't be having __GFP_FS allocations with IRQs disabled. + */ if (DEBUG_LOCKS_WARN_ON(irqs_disabled_flags(flags))) return; @@ -2773,13 +2847,13 @@ static int separate_irq_context(struct task_struct *curr, return 0; } -#else +#else /* defined(CONFIG_TRACE_IRQFLAGS) && defined(CONFIG_PROVE_LOCKING) */ static inline int mark_lock_irq(struct task_struct *curr, struct held_lock *this, enum lock_usage_bit new_bit) { - WARN_ON(1); + WARN_ON(1); /* Impossible innit? when we don't have TRACE_IRQFLAG */ return 1; } @@ -2799,7 +2873,7 @@ void lockdep_trace_alloc(gfp_t gfp_mask) { } -#endif +#endif /* defined(CONFIG_TRACE_IRQFLAGS) && defined(CONFIG_PROVE_LOCKING) */ /* * Mark a lock with a usage bit, and validate the state transition: @@ -2880,6 +2954,9 @@ void lockdep_init_map(struct lockdep_map *lock, const char *name, lock->cpu = raw_smp_processor_id(); #endif + /* + * Can't be having no nameless bastards around this place! + */ if (DEBUG_LOCKS_WARN_ON(!name)) { lock->name = "NULL"; return; @@ -2887,6 +2964,9 @@ void lockdep_init_map(struct lockdep_map *lock, const char *name, lock->name = name; + /* + * No key, no joy, we need to hash something. + */ if (DEBUG_LOCKS_WARN_ON(!key)) return; /* @@ -2894,6 +2974,9 @@ void lockdep_init_map(struct lockdep_map *lock, const char *name, */ if (!static_obj(key)) { printk("BUG: key %p not in .data!\n", key); + /* + * What it says above ^^^^^, I suggest you read it. + */ DEBUG_LOCKS_WARN_ON(1); return; } @@ -2932,6 +3015,11 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass, if (unlikely(!debug_locks)) return 0; + /* + * Lockdep should run with IRQs disabled, otherwise we could + * get an interrupt which would want to take locks, which would + * end up in lockdep and have you got a head-ache already? + */ if (DEBUG_LOCKS_WARN_ON(!irqs_disabled())) return 0; @@ -2963,6 +3051,9 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass, * dependency checks are done) */ depth = curr->lockdep_depth; + /* + * Ran out of static storage for our per-task lock stack again have we? + */ if (DEBUG_LOCKS_WARN_ON(depth >= MAX_LOCK_DEPTH)) return 0; @@ -2981,6 +3072,10 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass, } hlock = curr->held_locks + depth; + /* + * Plain impossible, we just registered it and checked it weren't no + * NULL like.. I bet this mushroom I ate was good! + */ if (DEBUG_LOCKS_WARN_ON(!class)) return 0; hlock->class_idx = class_idx; @@ -3015,11 +3110,17 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass, * the hash, not class->key. */ id = class - lock_classes; + /* + * Whoops, we did it again.. ran straight out of our static allocation. + */ if (DEBUG_LOCKS_WARN_ON(id >= MAX_LOCKDEP_KEYS)) return 0; chain_key = curr->curr_chain_key; if (!depth) { + /* + * How can we have a chain hash when we ain't got no keys?! + */ if (DEBUG_LOCKS_WARN_ON(chain_key != 0)) return 0; chain_head = 1; @@ -3065,9 +3166,10 @@ print_unlock_inbalance_bug(struct task_struct *curr, struct lockdep_map *lock, if (debug_locks_silent) return 0; - printk("\n=====================================\n"); - printk( "[ BUG: bad unlock balance detected! ]\n"); - printk( "-------------------------------------\n"); + printk("\n"); + printk("=====================================\n"); + printk("[ BUG: bad unlock balance detected! ]\n"); + printk("-------------------------------------\n"); printk("%s/%d is trying to release lock (", curr->comm, task_pid_nr(curr)); print_lockdep_cache(lock); @@ -3091,6 +3193,9 @@ static int check_unlock(struct task_struct *curr, struct lockdep_map *lock, { if (unlikely(!debug_locks)) return 0; + /* + * Lockdep should run with IRQs disabled, recursion, head-ache, etc.. + */ if (DEBUG_LOCKS_WARN_ON(!irqs_disabled())) return 0; @@ -3120,6 +3225,11 @@ static int match_held_lock(struct held_lock *hlock, struct lockdep_map *lock) if (!class) return 0; + /* + * References, but not a lock we're actually ref-counting? + * State got messed up, follow the sites that change ->references + * and try to make sense of it. + */ if (DEBUG_LOCKS_WARN_ON(!hlock->nest_lock)) return 0; @@ -3142,6 +3252,10 @@ __lock_set_class(struct lockdep_map *lock, const char *name, int i; depth = curr->lockdep_depth; + /* + * This function is about (re)setting the class of a held lock, + * yet we're not actually holding any locks. Naughty user! + */ if (DEBUG_LOCKS_WARN_ON(!depth)) return 0; @@ -3177,6 +3291,10 @@ found_it: return 0; } + /* + * I took it apart and put it back together again, except now I have + * these 'spare' parts.. where shall I put them. + */ if (DEBUG_LOCKS_WARN_ON(curr->lockdep_depth != depth)) return 0; return 1; @@ -3201,6 +3319,10 @@ lock_release_non_nested(struct task_struct *curr, * of held locks: */ depth = curr->lockdep_depth; + /* + * So we're all set to release this lock.. wait what lock? We don't + * own any locks, you've been drinking again? + */ if (DEBUG_LOCKS_WARN_ON(!depth)) return 0; @@ -3253,6 +3375,10 @@ found_it: return 0; } + /* + * We had N bottles of beer on the wall, we drank one, but now + * there's not N-1 bottles of beer left on the wall... + */ if (DEBUG_LOCKS_WARN_ON(curr->lockdep_depth != depth - 1)) return 0; return 1; @@ -3283,6 +3409,9 @@ static int lock_release_nested(struct task_struct *curr, return lock_release_non_nested(curr, lock, ip); curr->lockdep_depth--; + /* + * No more locks, but somehow we've got hash left over, who left it? + */ if (DEBUG_LOCKS_WARN_ON(!depth && (hlock->prev_chain_key != 0))) return 0; @@ -3365,10 +3494,13 @@ static void check_flags(unsigned long flags) * check if not in hardirq contexts: */ if (!hardirq_count()) { - if (softirq_count()) + if (softirq_count()) { + /* like the above, but with softirqs */ DEBUG_LOCKS_WARN_ON(current->softirqs_enabled); - else + } else { + /* lick the above, does it taste good? */ DEBUG_LOCKS_WARN_ON(!current->softirqs_enabled); + } } if (!debug_locks) @@ -3478,9 +3610,10 @@ print_lock_contention_bug(struct task_struct *curr, struct lockdep_map *lock, if (debug_locks_silent) return 0; - printk("\n=================================\n"); - printk( "[ BUG: bad contention detected! ]\n"); - printk( "---------------------------------\n"); + printk("\n"); + printk("=================================\n"); + printk("[ BUG: bad contention detected! ]\n"); + printk("---------------------------------\n"); printk("%s/%d is trying to contend lock (", curr->comm, task_pid_nr(curr)); print_lockdep_cache(lock); @@ -3506,6 +3639,10 @@ __lock_contended(struct lockdep_map *lock, unsigned long ip) int i, contention_point, contending_point; depth = curr->lockdep_depth; + /* + * Whee, we contended on this lock, except it seems we're not + * actually trying to acquire anything much at all.. + */ if (DEBUG_LOCKS_WARN_ON(!depth)) return; @@ -3555,6 +3692,10 @@ __lock_acquired(struct lockdep_map *lock, unsigned long ip) int i, cpu; depth = curr->lockdep_depth; + /* + * Yay, we acquired ownership of this lock we didn't try to + * acquire, how the heck did that happen? + */ if (DEBUG_LOCKS_WARN_ON(!depth)) return; @@ -3759,8 +3900,12 @@ void lockdep_reset_lock(struct lockdep_map *lock) match |= class == lock->class_cache[j]; if (unlikely(match)) { - if (debug_locks_off_graph_unlock()) + if (debug_locks_off_graph_unlock()) { + /* + * We all just reset everything, how did it match? + */ WARN_ON(1); + } goto out_restore; } } @@ -3839,9 +3984,10 @@ print_freed_lock_bug(struct task_struct *curr, const void *mem_from, if (debug_locks_silent) return; - printk("\n=========================\n"); - printk( "[ BUG: held lock freed! ]\n"); - printk( "-------------------------\n"); + printk("\n"); + printk("=========================\n"); + printk("[ BUG: held lock freed! ]\n"); + printk("-------------------------\n"); printk("%s/%d is freeing memory %p-%p, with a lock still held there!\n", curr->comm, task_pid_nr(curr), mem_from, mem_to-1); print_lock(hlock); @@ -3895,9 +4041,10 @@ static void print_held_locks_bug(struct task_struct *curr) if (debug_locks_silent) return; - printk("\n=====================================\n"); - printk( "[ BUG: lock held at task exit time! ]\n"); - printk( "-------------------------------------\n"); + printk("\n"); + printk("=====================================\n"); + printk("[ BUG: lock held at task exit time! ]\n"); + printk("-------------------------------------\n"); printk("%s/%d is exiting with locks still held!\n", curr->comm, task_pid_nr(curr)); lockdep_print_held_locks(curr); @@ -3991,16 +4138,17 @@ void lockdep_sys_exit(void) if (unlikely(curr->lockdep_depth)) { if (!debug_locks_off()) return; - printk("\n================================================\n"); - printk( "[ BUG: lock held when returning to user space! ]\n"); - printk( "------------------------------------------------\n"); + printk("\n"); + printk("================================================\n"); + printk("[ BUG: lock held when returning to user space! ]\n"); + printk("------------------------------------------------\n"); printk("%s/%d is leaving the kernel with locks still held!\n", curr->comm, curr->pid); lockdep_print_held_locks(curr); } } -void lockdep_rcu_dereference(const char *file, const int line) +void lockdep_rcu_suspicious(const char *file, const int line, const char *s) { struct task_struct *curr = current; @@ -4009,15 +4157,15 @@ void lockdep_rcu_dereference(const char *file, const int line) return; #endif /* #ifdef CONFIG_PROVE_RCU_REPEATEDLY */ /* Note: the following can be executed concurrently, so be careful. */ - printk("\n===================================================\n"); - printk( "[ INFO: suspicious rcu_dereference_check() usage. ]\n"); - printk( "---------------------------------------------------\n"); - printk("%s:%d invoked rcu_dereference_check() without protection!\n", - file, line); + printk("\n"); + printk("===============================\n"); + printk("[ INFO: suspicious RCU usage. ]\n"); + printk("-------------------------------\n"); + printk("%s:%d %s!\n", file, line, s); printk("\nother info that might help us debug this:\n\n"); printk("\nrcu_scheduler_active = %d, debug_locks = %d\n", rcu_scheduler_active, debug_locks); lockdep_print_held_locks(curr); printk("\nstack backtrace:\n"); dump_stack(); } -EXPORT_SYMBOL_GPL(lockdep_rcu_dereference); +EXPORT_SYMBOL_GPL(lockdep_rcu_suspicious); diff --git a/kernel/module.c b/kernel/module.c index 04379f92..93342d9 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -3487,50 +3487,3 @@ void module_layout(struct module *mod, } EXPORT_SYMBOL(module_layout); #endif - -#ifdef CONFIG_TRACEPOINTS -void module_update_tracepoints(void) -{ - struct module *mod; - - mutex_lock(&module_mutex); - list_for_each_entry(mod, &modules, list) - if (!mod->taints) - tracepoint_update_probe_range(mod->tracepoints_ptrs, - mod->tracepoints_ptrs + mod->num_tracepoints); - mutex_unlock(&module_mutex); -} - -/* - * Returns 0 if current not found. - * Returns 1 if current found. - */ -int module_get_iter_tracepoints(struct tracepoint_iter *iter) -{ - struct module *iter_mod; - int found = 0; - - mutex_lock(&module_mutex); - list_for_each_entry(iter_mod, &modules, list) { - if (!iter_mod->taints) { - /* - * Sorted module list - */ - if (iter_mod < iter->module) - continue; - else if (iter_mod > iter->module) - iter->tracepoint = NULL; - found = tracepoint_get_iter_range(&iter->tracepoint, - iter_mod->tracepoints_ptrs, - iter_mod->tracepoints_ptrs - + iter_mod->num_tracepoints); - if (found) { - iter->module = iter_mod; - break; - } - } - } - mutex_unlock(&module_mutex); - return found; -} -#endif diff --git a/kernel/params.c b/kernel/params.c index 22df3e0..8217889 100644 --- a/kernel/params.c +++ b/kernel/params.c @@ -67,20 +67,27 @@ static void maybe_kfree_parameter(void *param) } } -static inline char dash2underscore(char c) +static char dash2underscore(char c) { if (c == '-') return '_'; return c; } -static inline int parameq(const char *input, const char *paramname) +bool parameqn(const char *a, const char *b, size_t n) { - unsigned int i; - for (i = 0; dash2underscore(input[i]) == paramname[i]; i++) - if (input[i] == '\0') - return 1; - return 0; + size_t i; + + for (i = 0; i < n; i++) { + if (dash2underscore(a[i]) != dash2underscore(b[i])) + return false; + } + return true; +} + +bool parameq(const char *a, const char *b) +{ + return parameqn(a, b, strlen(a)+1); } static int parse_one(char *param, diff --git a/kernel/pid.c b/kernel/pid.c index e432057..8cafe7e 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -418,7 +418,9 @@ EXPORT_SYMBOL(pid_task); */ struct task_struct *find_task_by_pid_ns(pid_t nr, struct pid_namespace *ns) { - rcu_lockdep_assert(rcu_read_lock_held()); + rcu_lockdep_assert(rcu_read_lock_held(), + "find_task_by_pid_ns() needs rcu_read_lock()" + " protection"); return pid_task(find_pid_ns(nr, ns), PIDTYPE_PID); } diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c index 640ded8..e7cb76d 100644 --- a/kernel/posix-cpu-timers.c +++ b/kernel/posix-cpu-timers.c @@ -282,13 +282,13 @@ void thread_group_cputimer(struct task_struct *tsk, struct task_cputime *times) * it. */ thread_group_cputime(tsk, &sum); - spin_lock_irqsave(&cputimer->lock, flags); + raw_spin_lock_irqsave(&cputimer->lock, flags); cputimer->running = 1; update_gt_cputime(&cputimer->cputime, &sum); } else - spin_lock_irqsave(&cputimer->lock, flags); + raw_spin_lock_irqsave(&cputimer->lock, flags); *times = cputimer->cputime; - spin_unlock_irqrestore(&cputimer->lock, flags); + raw_spin_unlock_irqrestore(&cputimer->lock, flags); } /* @@ -999,9 +999,9 @@ static void stop_process_timers(struct signal_struct *sig) struct thread_group_cputimer *cputimer = &sig->cputimer; unsigned long flags; - spin_lock_irqsave(&cputimer->lock, flags); + raw_spin_lock_irqsave(&cputimer->lock, flags); cputimer->running = 0; - spin_unlock_irqrestore(&cputimer->lock, flags); + raw_spin_unlock_irqrestore(&cputimer->lock, flags); } static u32 onecputick; @@ -1291,9 +1291,9 @@ static inline int fastpath_timer_check(struct task_struct *tsk) if (sig->cputimer.running) { struct task_cputime group_sample; - spin_lock(&sig->cputimer.lock); + raw_spin_lock(&sig->cputimer.lock); group_sample = sig->cputimer.cputime; - spin_unlock(&sig->cputimer.lock); + raw_spin_unlock(&sig->cputimer.lock); if (task_cputime_expired(&group_sample, &sig->cputime_expires)) return 1; diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig index 80a8597..deb5461 100644 --- a/kernel/power/Kconfig +++ b/kernel/power/Kconfig @@ -27,6 +27,7 @@ config HIBERNATION select HIBERNATE_CALLBACKS select LZO_COMPRESS select LZO_DECOMPRESS + select CRC32 ---help--- Enable the suspend to disk (STD) functionality, which is usually called "hibernation" in user interfaces. STD checkpoints the @@ -65,6 +66,9 @@ config HIBERNATION For more information take a look at <file:Documentation/power/swsusp.txt>. +config ARCH_SAVE_PAGE_KEYS + bool + config PM_STD_PARTITION string "Default resume partition" depends on HIBERNATION diff --git a/kernel/power/Makefile b/kernel/power/Makefile index c5ebc6a..07e0e28 100644 --- a/kernel/power/Makefile +++ b/kernel/power/Makefile @@ -1,8 +1,8 @@ ccflags-$(CONFIG_PM_DEBUG) := -DDEBUG -obj-$(CONFIG_PM) += main.o -obj-$(CONFIG_PM_SLEEP) += console.o +obj-$(CONFIG_PM) += main.o qos.o +obj-$(CONFIG_VT_CONSOLE_SLEEP) += console.o obj-$(CONFIG_FREEZER) += process.o obj-$(CONFIG_SUSPEND) += suspend.o obj-$(CONFIG_PM_TEST_SUSPEND) += suspend_test.o diff --git a/kernel/power/console.c b/kernel/power/console.c index 218e5af..b1dc456 100644 --- a/kernel/power/console.c +++ b/kernel/power/console.c @@ -1,5 +1,5 @@ /* - * drivers/power/process.c - Functions for saving/restoring console. + * Functions for saving/restoring console. * * Originally from swsusp. */ @@ -10,7 +10,6 @@ #include <linux/module.h> #include "power.h" -#if defined(CONFIG_VT) && defined(CONFIG_VT_CONSOLE) #define SUSPEND_CONSOLE (MAX_NR_CONSOLES-1) static int orig_fgconsole, orig_kmsg; @@ -32,4 +31,3 @@ void pm_restore_console(void) vt_kmsg_redirect(orig_kmsg); } } -#endif diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c index 8f7b1db..1c53f7f 100644 --- a/kernel/power/hibernate.c +++ b/kernel/power/hibernate.c @@ -14,6 +14,7 @@ #include <linux/reboot.h> #include <linux/string.h> #include <linux/device.h> +#include <linux/async.h> #include <linux/kmod.h> #include <linux/delay.h> #include <linux/fs.h> @@ -29,12 +30,14 @@ #include "power.h" -static int nocompress = 0; -static int noresume = 0; +static int nocompress; +static int noresume; +static int resume_wait; +static int resume_delay; static char resume_file[256] = CONFIG_PM_STD_PARTITION; dev_t swsusp_resume_device; sector_t swsusp_resume_block; -int in_suspend __nosavedata = 0; +int in_suspend __nosavedata; enum { HIBERNATION_INVALID, @@ -334,13 +337,17 @@ int hibernation_snapshot(int platform_mode) if (error) goto Close; - error = dpm_prepare(PMSG_FREEZE); - if (error) - goto Complete_devices; - /* Preallocate image memory before shutting down devices. */ error = hibernate_preallocate_memory(); if (error) + goto Close; + + error = freeze_kernel_threads(); + if (error) + goto Close; + + error = dpm_prepare(PMSG_FREEZE); + if (error) goto Complete_devices; suspend_console(); @@ -463,7 +470,7 @@ static int resume_target_kernel(bool platform_mode) * @platform_mode: If set, use platform driver to prepare for the transition. * * This routine must be called with pm_mutex held. If it is successful, control - * reappears in the restored target kernel in hibernation_snaphot(). + * reappears in the restored target kernel in hibernation_snapshot(). */ int hibernation_restore(int platform_mode) { @@ -650,6 +657,9 @@ int hibernate(void) flags |= SF_PLATFORM_MODE; if (nocompress) flags |= SF_NOCOMPRESS_MODE; + else + flags |= SF_CRC32_MODE; + pr_debug("PM: writing image.\n"); error = swsusp_write(flags); swsusp_free(); @@ -724,6 +734,12 @@ static int software_resume(void) pr_debug("PM: Checking hibernation image partition %s\n", resume_file); + if (resume_delay) { + printk(KERN_INFO "Waiting %dsec before reading resume device...\n", + resume_delay); + ssleep(resume_delay); + } + /* Check if the device is there */ swsusp_resume_device = name_to_dev_t(resume_file); if (!swsusp_resume_device) { @@ -732,6 +748,13 @@ static int software_resume(void) * to wait for this to finish. */ wait_for_device_probe(); + + if (resume_wait) { + while ((swsusp_resume_device = name_to_dev_t(resume_file)) == 0) + msleep(10); + async_synchronize_full(); + } + /* * We can't depend on SCSI devices being available after loading * one of their modules until scsi_complete_async_scans() is @@ -1060,7 +1083,21 @@ static int __init noresume_setup(char *str) return 1; } +static int __init resumewait_setup(char *str) +{ + resume_wait = 1; + return 1; +} + +static int __init resumedelay_setup(char *str) +{ + resume_delay = simple_strtoul(str, NULL, 0); + return 1; +} + __setup("noresume", noresume_setup); __setup("resume_offset=", resume_offset_setup); __setup("resume=", resume_setup); __setup("hibernate=", hibernate_setup); +__setup("resumewait", resumewait_setup); +__setup("resumedelay=", resumedelay_setup); diff --git a/kernel/power/main.c b/kernel/power/main.c index 6c601f8..a52e884 100644 --- a/kernel/power/main.c +++ b/kernel/power/main.c @@ -12,6 +12,8 @@ #include <linux/string.h> #include <linux/resume-trace.h> #include <linux/workqueue.h> +#include <linux/debugfs.h> +#include <linux/seq_file.h> #include "power.h" @@ -131,6 +133,101 @@ static ssize_t pm_test_store(struct kobject *kobj, struct kobj_attribute *attr, power_attr(pm_test); #endif /* CONFIG_PM_DEBUG */ +#ifdef CONFIG_DEBUG_FS +static char *suspend_step_name(enum suspend_stat_step step) +{ + switch (step) { + case SUSPEND_FREEZE: + return "freeze"; + case SUSPEND_PREPARE: + return "prepare"; + case SUSPEND_SUSPEND: + return "suspend"; + case SUSPEND_SUSPEND_NOIRQ: + return "suspend_noirq"; + case SUSPEND_RESUME_NOIRQ: + return "resume_noirq"; + case SUSPEND_RESUME: + return "resume"; + default: + return ""; + } +} + +static int suspend_stats_show(struct seq_file *s, void *unused) +{ + int i, index, last_dev, last_errno, last_step; + + last_dev = suspend_stats.last_failed_dev + REC_FAILED_NUM - 1; + last_dev %= REC_FAILED_NUM; + last_errno = suspend_stats.last_failed_errno + REC_FAILED_NUM - 1; + last_errno %= REC_FAILED_NUM; + last_step = suspend_stats.last_failed_step + REC_FAILED_NUM - 1; + last_step %= REC_FAILED_NUM; + seq_printf(s, "%s: %d\n%s: %d\n%s: %d\n%s: %d\n" + "%s: %d\n%s: %d\n%s: %d\n%s: %d\n", + "success", suspend_stats.success, + "fail", suspend_stats.fail, + "failed_freeze", suspend_stats.failed_freeze, + "failed_prepare", suspend_stats.failed_prepare, + "failed_suspend", suspend_stats.failed_suspend, + "failed_suspend_noirq", + suspend_stats.failed_suspend_noirq, + "failed_resume", suspend_stats.failed_resume, + "failed_resume_noirq", + suspend_stats.failed_resume_noirq); + seq_printf(s, "failures:\n last_failed_dev:\t%-s\n", + suspend_stats.failed_devs[last_dev]); + for (i = 1; i < REC_FAILED_NUM; i++) { + index = last_dev + REC_FAILED_NUM - i; + index %= REC_FAILED_NUM; + seq_printf(s, "\t\t\t%-s\n", + suspend_stats.failed_devs[index]); + } + seq_printf(s, " last_failed_errno:\t%-d\n", + suspend_stats.errno[last_errno]); + for (i = 1; i < REC_FAILED_NUM; i++) { + index = last_errno + REC_FAILED_NUM - i; + index %= REC_FAILED_NUM; + seq_printf(s, "\t\t\t%-d\n", + suspend_stats.errno[index]); + } + seq_printf(s, " last_failed_step:\t%-s\n", + suspend_step_name( + suspend_stats.failed_steps[last_step])); + for (i = 1; i < REC_FAILED_NUM; i++) { + index = last_step + REC_FAILED_NUM - i; + index %= REC_FAILED_NUM; + seq_printf(s, "\t\t\t%-s\n", + suspend_step_name( + suspend_stats.failed_steps[index])); + } + + return 0; +} + +static int suspend_stats_open(struct inode *inode, struct file *file) +{ + return single_open(file, suspend_stats_show, NULL); +} + +static const struct file_operations suspend_stats_operations = { + .open = suspend_stats_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static int __init pm_debugfs_init(void) +{ + debugfs_create_file("suspend_stats", S_IFREG | S_IRUGO, + NULL, NULL, &suspend_stats_operations); + return 0; +} + +late_initcall(pm_debugfs_init); +#endif /* CONFIG_DEBUG_FS */ + #endif /* CONFIG_PM_SLEEP */ struct kobject *power_kobj; @@ -194,6 +291,11 @@ static ssize_t state_store(struct kobject *kobj, struct kobj_attribute *attr, } if (state < PM_SUSPEND_MAX && *s) error = enter_state(state); + if (error) { + suspend_stats.fail++; + dpm_save_failed_errno(error); + } else + suspend_stats.success++; #endif Exit: diff --git a/kernel/power/power.h b/kernel/power/power.h index 9a00a0a..23a2db1 100644 --- a/kernel/power/power.h +++ b/kernel/power/power.h @@ -146,6 +146,7 @@ extern int swsusp_swap_in_use(void); */ #define SF_PLATFORM_MODE 1 #define SF_NOCOMPRESS_MODE 2 +#define SF_CRC32_MODE 4 /* kernel/power/hibernate.c */ extern int swsusp_check(void); @@ -228,7 +229,8 @@ extern int pm_test_level; #ifdef CONFIG_SUSPEND_FREEZER static inline int suspend_freeze_processes(void) { - return freeze_processes(); + int error = freeze_processes(); + return error ? : freeze_kernel_threads(); } static inline void suspend_thaw_processes(void) diff --git a/kernel/power/process.c b/kernel/power/process.c index 0cf3a27..addbbe5 100644 --- a/kernel/power/process.c +++ b/kernel/power/process.c @@ -135,7 +135,7 @@ static int try_to_freeze_tasks(bool sig_only) } /** - * freeze_processes - tell processes to enter the refrigerator + * freeze_processes - Signal user space processes to enter the refrigerator. */ int freeze_processes(void) { @@ -143,20 +143,30 @@ int freeze_processes(void) printk("Freezing user space processes ... "); error = try_to_freeze_tasks(true); - if (error) - goto Exit; - printk("done.\n"); + if (!error) { + printk("done."); + oom_killer_disable(); + } + printk("\n"); + BUG_ON(in_atomic()); + + return error; +} + +/** + * freeze_kernel_threads - Make freezable kernel threads go to the refrigerator. + */ +int freeze_kernel_threads(void) +{ + int error; printk("Freezing remaining freezable tasks ... "); error = try_to_freeze_tasks(false); - if (error) - goto Exit; - printk("done."); + if (!error) + printk("done."); - oom_killer_disable(); - Exit: - BUG_ON(in_atomic()); printk("\n"); + BUG_ON(in_atomic()); return error; } diff --git a/kernel/pm_qos_params.c b/kernel/power/qos.c index 37f05d0..1c1797d 100644 --- a/kernel/pm_qos_params.c +++ b/kernel/power/qos.c @@ -29,7 +29,7 @@ /*#define DEBUG*/ -#include <linux/pm_qos_params.h> +#include <linux/pm_qos.h> #include <linux/sched.h> #include <linux/spinlock.h> #include <linux/slab.h> @@ -45,62 +45,57 @@ #include <linux/uaccess.h> /* - * locking rule: all changes to requests or notifiers lists + * locking rule: all changes to constraints or notifiers lists * or pm_qos_object list and pm_qos_objects need to happen with pm_qos_lock * held, taken with _irqsave. One lock to rule them all */ -enum pm_qos_type { - PM_QOS_MAX, /* return the largest value */ - PM_QOS_MIN /* return the smallest value */ -}; - -/* - * Note: The lockless read path depends on the CPU accessing - * target_value atomically. Atomic access is only guaranteed on all CPU - * types linux supports for 32 bit quantites - */ struct pm_qos_object { - struct plist_head requests; - struct blocking_notifier_head *notifiers; + struct pm_qos_constraints *constraints; struct miscdevice pm_qos_power_miscdev; char *name; - s32 target_value; /* Do not change to 64 bit */ - s32 default_value; - enum pm_qos_type type; }; static DEFINE_SPINLOCK(pm_qos_lock); static struct pm_qos_object null_pm_qos; + static BLOCKING_NOTIFIER_HEAD(cpu_dma_lat_notifier); -static struct pm_qos_object cpu_dma_pm_qos = { - .requests = PLIST_HEAD_INIT(cpu_dma_pm_qos.requests), - .notifiers = &cpu_dma_lat_notifier, - .name = "cpu_dma_latency", +static struct pm_qos_constraints cpu_dma_constraints = { + .list = PLIST_HEAD_INIT(cpu_dma_constraints.list), .target_value = PM_QOS_CPU_DMA_LAT_DEFAULT_VALUE, .default_value = PM_QOS_CPU_DMA_LAT_DEFAULT_VALUE, .type = PM_QOS_MIN, + .notifiers = &cpu_dma_lat_notifier, +}; +static struct pm_qos_object cpu_dma_pm_qos = { + .constraints = &cpu_dma_constraints, }; static BLOCKING_NOTIFIER_HEAD(network_lat_notifier); -static struct pm_qos_object network_lat_pm_qos = { - .requests = PLIST_HEAD_INIT(network_lat_pm_qos.requests), - .notifiers = &network_lat_notifier, - .name = "network_latency", +static struct pm_qos_constraints network_lat_constraints = { + .list = PLIST_HEAD_INIT(network_lat_constraints.list), .target_value = PM_QOS_NETWORK_LAT_DEFAULT_VALUE, .default_value = PM_QOS_NETWORK_LAT_DEFAULT_VALUE, - .type = PM_QOS_MIN + .type = PM_QOS_MIN, + .notifiers = &network_lat_notifier, +}; +static struct pm_qos_object network_lat_pm_qos = { + .constraints = &network_lat_constraints, + .name = "network_latency", }; static BLOCKING_NOTIFIER_HEAD(network_throughput_notifier); -static struct pm_qos_object network_throughput_pm_qos = { - .requests = PLIST_HEAD_INIT(network_throughput_pm_qos.requests), - .notifiers = &network_throughput_notifier, - .name = "network_throughput", +static struct pm_qos_constraints network_tput_constraints = { + .list = PLIST_HEAD_INIT(network_tput_constraints.list), .target_value = PM_QOS_NETWORK_THROUGHPUT_DEFAULT_VALUE, .default_value = PM_QOS_NETWORK_THROUGHPUT_DEFAULT_VALUE, .type = PM_QOS_MAX, + .notifiers = &network_throughput_notifier, +}; +static struct pm_qos_object network_throughput_pm_qos = { + .constraints = &network_tput_constraints, + .name = "network_throughput", }; @@ -127,17 +122,17 @@ static const struct file_operations pm_qos_power_fops = { }; /* unlocked internal variant */ -static inline int pm_qos_get_value(struct pm_qos_object *o) +static inline int pm_qos_get_value(struct pm_qos_constraints *c) { - if (plist_head_empty(&o->requests)) - return o->default_value; + if (plist_head_empty(&c->list)) + return c->default_value; - switch (o->type) { + switch (c->type) { case PM_QOS_MIN: - return plist_first(&o->requests)->prio; + return plist_first(&c->list)->prio; case PM_QOS_MAX: - return plist_last(&o->requests)->prio; + return plist_last(&c->list)->prio; default: /* runtime check for not using enum */ @@ -145,69 +140,73 @@ static inline int pm_qos_get_value(struct pm_qos_object *o) } } -static inline s32 pm_qos_read_value(struct pm_qos_object *o) +s32 pm_qos_read_value(struct pm_qos_constraints *c) { - return o->target_value; + return c->target_value; } -static inline void pm_qos_set_value(struct pm_qos_object *o, s32 value) +static inline void pm_qos_set_value(struct pm_qos_constraints *c, s32 value) { - o->target_value = value; + c->target_value = value; } -static void update_target(struct pm_qos_object *o, struct plist_node *node, - int del, int value) +/** + * pm_qos_update_target - manages the constraints list and calls the notifiers + * if needed + * @c: constraints data struct + * @node: request to add to the list, to update or to remove + * @action: action to take on the constraints list + * @value: value of the request to add or update + * + * This function returns 1 if the aggregated constraint value has changed, 0 + * otherwise. + */ +int pm_qos_update_target(struct pm_qos_constraints *c, struct plist_node *node, + enum pm_qos_req_action action, int value) { unsigned long flags; - int prev_value, curr_value; + int prev_value, curr_value, new_value; spin_lock_irqsave(&pm_qos_lock, flags); - prev_value = pm_qos_get_value(o); - /* PM_QOS_DEFAULT_VALUE is a signal that the value is unchanged */ - if (value != PM_QOS_DEFAULT_VALUE) { + prev_value = pm_qos_get_value(c); + if (value == PM_QOS_DEFAULT_VALUE) + new_value = c->default_value; + else + new_value = value; + + switch (action) { + case PM_QOS_REMOVE_REQ: + plist_del(node, &c->list); + break; + case PM_QOS_UPDATE_REQ: /* * to change the list, we atomically remove, reinit * with new value and add, then see if the extremal * changed */ - plist_del(node, &o->requests); - plist_node_init(node, value); - plist_add(node, &o->requests); - } else if (del) { - plist_del(node, &o->requests); - } else { - plist_add(node, &o->requests); + plist_del(node, &c->list); + case PM_QOS_ADD_REQ: + plist_node_init(node, new_value); + plist_add(node, &c->list); + break; + default: + /* no action */ + ; } - curr_value = pm_qos_get_value(o); - pm_qos_set_value(o, curr_value); + + curr_value = pm_qos_get_value(c); + pm_qos_set_value(c, curr_value); + spin_unlock_irqrestore(&pm_qos_lock, flags); - if (prev_value != curr_value) - blocking_notifier_call_chain(o->notifiers, + if (prev_value != curr_value) { + blocking_notifier_call_chain(c->notifiers, (unsigned long)curr_value, NULL); -} - -static int register_pm_qos_misc(struct pm_qos_object *qos) -{ - qos->pm_qos_power_miscdev.minor = MISC_DYNAMIC_MINOR; - qos->pm_qos_power_miscdev.name = qos->name; - qos->pm_qos_power_miscdev.fops = &pm_qos_power_fops; - - return misc_register(&qos->pm_qos_power_miscdev); -} - -static int find_pm_qos_object_by_minor(int minor) -{ - int pm_qos_class; - - for (pm_qos_class = 0; - pm_qos_class < PM_QOS_NUM_CLASSES; pm_qos_class++) { - if (minor == - pm_qos_array[pm_qos_class]->pm_qos_power_miscdev.minor) - return pm_qos_class; + return 1; + } else { + return 0; } - return -1; } /** @@ -218,11 +217,11 @@ static int find_pm_qos_object_by_minor(int minor) */ int pm_qos_request(int pm_qos_class) { - return pm_qos_read_value(pm_qos_array[pm_qos_class]); + return pm_qos_read_value(pm_qos_array[pm_qos_class]->constraints); } EXPORT_SYMBOL_GPL(pm_qos_request); -int pm_qos_request_active(struct pm_qos_request_list *req) +int pm_qos_request_active(struct pm_qos_request *req) { return req->pm_qos_class != 0; } @@ -230,40 +229,36 @@ EXPORT_SYMBOL_GPL(pm_qos_request_active); /** * pm_qos_add_request - inserts new qos request into the list - * @dep: pointer to a preallocated handle + * @req: pointer to a preallocated handle * @pm_qos_class: identifies which list of qos request to use * @value: defines the qos request * * This function inserts a new entry in the pm_qos_class list of requested qos * performance characteristics. It recomputes the aggregate QoS expectations - * for the pm_qos_class of parameters and initializes the pm_qos_request_list + * for the pm_qos_class of parameters and initializes the pm_qos_request * handle. Caller needs to save this handle for later use in updates and * removal. */ -void pm_qos_add_request(struct pm_qos_request_list *dep, +void pm_qos_add_request(struct pm_qos_request *req, int pm_qos_class, s32 value) { - struct pm_qos_object *o = pm_qos_array[pm_qos_class]; - int new_value; + if (!req) /*guard against callers passing in null */ + return; - if (pm_qos_request_active(dep)) { + if (pm_qos_request_active(req)) { WARN(1, KERN_ERR "pm_qos_add_request() called for already added request\n"); return; } - if (value == PM_QOS_DEFAULT_VALUE) - new_value = o->default_value; - else - new_value = value; - plist_node_init(&dep->list, new_value); - dep->pm_qos_class = pm_qos_class; - update_target(o, &dep->list, 0, PM_QOS_DEFAULT_VALUE); + req->pm_qos_class = pm_qos_class; + pm_qos_update_target(pm_qos_array[pm_qos_class]->constraints, + &req->node, PM_QOS_ADD_REQ, value); } EXPORT_SYMBOL_GPL(pm_qos_add_request); /** * pm_qos_update_request - modifies an existing qos request - * @pm_qos_req : handle to list element holding a pm_qos request to use + * @req : handle to list element holding a pm_qos request to use * @value: defines the qos request * * Updates an existing qos request for the pm_qos_class of parameters along @@ -271,56 +266,47 @@ EXPORT_SYMBOL_GPL(pm_qos_add_request); * * Attempts are made to make this code callable on hot code paths. */ -void pm_qos_update_request(struct pm_qos_request_list *pm_qos_req, +void pm_qos_update_request(struct pm_qos_request *req, s32 new_value) { - s32 temp; - struct pm_qos_object *o; - - if (!pm_qos_req) /*guard against callers passing in null */ + if (!req) /*guard against callers passing in null */ return; - if (!pm_qos_request_active(pm_qos_req)) { + if (!pm_qos_request_active(req)) { WARN(1, KERN_ERR "pm_qos_update_request() called for unknown object\n"); return; } - o = pm_qos_array[pm_qos_req->pm_qos_class]; - - if (new_value == PM_QOS_DEFAULT_VALUE) - temp = o->default_value; - else - temp = new_value; - - if (temp != pm_qos_req->list.prio) - update_target(o, &pm_qos_req->list, 0, temp); + if (new_value != req->node.prio) + pm_qos_update_target( + pm_qos_array[req->pm_qos_class]->constraints, + &req->node, PM_QOS_UPDATE_REQ, new_value); } EXPORT_SYMBOL_GPL(pm_qos_update_request); /** * pm_qos_remove_request - modifies an existing qos request - * @pm_qos_req: handle to request list element + * @req: handle to request list element * - * Will remove pm qos request from the list of requests and + * Will remove pm qos request from the list of constraints and * recompute the current target value for the pm_qos_class. Call this * on slow code paths. */ -void pm_qos_remove_request(struct pm_qos_request_list *pm_qos_req) +void pm_qos_remove_request(struct pm_qos_request *req) { - struct pm_qos_object *o; - - if (pm_qos_req == NULL) + if (!req) /*guard against callers passing in null */ return; /* silent return to keep pcm code cleaner */ - if (!pm_qos_request_active(pm_qos_req)) { + if (!pm_qos_request_active(req)) { WARN(1, KERN_ERR "pm_qos_remove_request() called for unknown object\n"); return; } - o = pm_qos_array[pm_qos_req->pm_qos_class]; - update_target(o, &pm_qos_req->list, 1, PM_QOS_DEFAULT_VALUE); - memset(pm_qos_req, 0, sizeof(*pm_qos_req)); + pm_qos_update_target(pm_qos_array[req->pm_qos_class]->constraints, + &req->node, PM_QOS_REMOVE_REQ, + PM_QOS_DEFAULT_VALUE); + memset(req, 0, sizeof(*req)); } EXPORT_SYMBOL_GPL(pm_qos_remove_request); @@ -337,7 +323,8 @@ int pm_qos_add_notifier(int pm_qos_class, struct notifier_block *notifier) int retval; retval = blocking_notifier_chain_register( - pm_qos_array[pm_qos_class]->notifiers, notifier); + pm_qos_array[pm_qos_class]->constraints->notifiers, + notifier); return retval; } @@ -356,19 +343,43 @@ int pm_qos_remove_notifier(int pm_qos_class, struct notifier_block *notifier) int retval; retval = blocking_notifier_chain_unregister( - pm_qos_array[pm_qos_class]->notifiers, notifier); + pm_qos_array[pm_qos_class]->constraints->notifiers, + notifier); return retval; } EXPORT_SYMBOL_GPL(pm_qos_remove_notifier); +/* User space interface to PM QoS classes via misc devices */ +static int register_pm_qos_misc(struct pm_qos_object *qos) +{ + qos->pm_qos_power_miscdev.minor = MISC_DYNAMIC_MINOR; + qos->pm_qos_power_miscdev.name = qos->name; + qos->pm_qos_power_miscdev.fops = &pm_qos_power_fops; + + return misc_register(&qos->pm_qos_power_miscdev); +} + +static int find_pm_qos_object_by_minor(int minor) +{ + int pm_qos_class; + + for (pm_qos_class = 0; + pm_qos_class < PM_QOS_NUM_CLASSES; pm_qos_class++) { + if (minor == + pm_qos_array[pm_qos_class]->pm_qos_power_miscdev.minor) + return pm_qos_class; + } + return -1; +} + static int pm_qos_power_open(struct inode *inode, struct file *filp) { long pm_qos_class; pm_qos_class = find_pm_qos_object_by_minor(iminor(inode)); if (pm_qos_class >= 0) { - struct pm_qos_request_list *req = kzalloc(sizeof(*req), GFP_KERNEL); + struct pm_qos_request *req = kzalloc(sizeof(*req), GFP_KERNEL); if (!req) return -ENOMEM; @@ -383,7 +394,7 @@ static int pm_qos_power_open(struct inode *inode, struct file *filp) static int pm_qos_power_release(struct inode *inode, struct file *filp) { - struct pm_qos_request_list *req; + struct pm_qos_request *req; req = filp->private_data; pm_qos_remove_request(req); @@ -398,17 +409,15 @@ static ssize_t pm_qos_power_read(struct file *filp, char __user *buf, { s32 value; unsigned long flags; - struct pm_qos_object *o; - struct pm_qos_request_list *pm_qos_req = filp->private_data; + struct pm_qos_request *req = filp->private_data; - if (!pm_qos_req) + if (!req) return -EINVAL; - if (!pm_qos_request_active(pm_qos_req)) + if (!pm_qos_request_active(req)) return -EINVAL; - o = pm_qos_array[pm_qos_req->pm_qos_class]; spin_lock_irqsave(&pm_qos_lock, flags); - value = pm_qos_get_value(o); + value = pm_qos_get_value(pm_qos_array[req->pm_qos_class]->constraints); spin_unlock_irqrestore(&pm_qos_lock, flags); return simple_read_from_buffer(buf, count, f_pos, &value, sizeof(s32)); @@ -418,7 +427,7 @@ static ssize_t pm_qos_power_write(struct file *filp, const char __user *buf, size_t count, loff_t *f_pos) { s32 value; - struct pm_qos_request_list *pm_qos_req; + struct pm_qos_request *req; if (count == sizeof(s32)) { if (copy_from_user(&value, buf, sizeof(s32))) @@ -449,8 +458,8 @@ static ssize_t pm_qos_power_write(struct file *filp, const char __user *buf, return -EINVAL; } - pm_qos_req = filp->private_data; - pm_qos_update_request(pm_qos_req, value); + req = filp->private_data; + pm_qos_update_request(req, value); return count; } diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c index 06efa54..cbe2c14 100644 --- a/kernel/power/snapshot.c +++ b/kernel/power/snapshot.c @@ -1339,6 +1339,9 @@ int hibernate_preallocate_memory(void) count += highmem; count -= totalreserve_pages; + /* Add number of pages required for page keys (s390 only). */ + size += page_key_additional_pages(saveable); + /* Compute the maximum number of saveable pages to leave in memory. */ max_size = (count - (size + PAGES_FOR_IO)) / 2 - 2 * DIV_ROUND_UP(reserved_size, PAGE_SIZE); @@ -1662,6 +1665,8 @@ pack_pfns(unsigned long *buf, struct memory_bitmap *bm) buf[j] = memory_bm_next_pfn(bm); if (unlikely(buf[j] == BM_END_OF_MAP)) break; + /* Save page key for data page (s390 only). */ + page_key_read(buf + j); } } @@ -1821,6 +1826,9 @@ static int unpack_orig_pfns(unsigned long *buf, struct memory_bitmap *bm) if (unlikely(buf[j] == BM_END_OF_MAP)) break; + /* Extract and buffer page key for data page (s390 only). */ + page_key_memorize(buf + j); + if (memory_bm_pfn_present(bm, buf[j])) memory_bm_set_bit(bm, buf[j]); else @@ -2223,6 +2231,11 @@ int snapshot_write_next(struct snapshot_handle *handle) if (error) return error; + /* Allocate buffer for page keys. */ + error = page_key_alloc(nr_copy_pages); + if (error) + return error; + } else if (handle->cur <= nr_meta_pages + 1) { error = unpack_orig_pfns(buffer, ©_bm); if (error) @@ -2243,6 +2256,8 @@ int snapshot_write_next(struct snapshot_handle *handle) } } else { copy_last_highmem_page(); + /* Restore page key for data page (s390 only). */ + page_key_write(handle->buffer); handle->buffer = get_buffer(&orig_bm, &ca); if (IS_ERR(handle->buffer)) return PTR_ERR(handle->buffer); @@ -2264,6 +2279,9 @@ int snapshot_write_next(struct snapshot_handle *handle) void snapshot_write_finalize(struct snapshot_handle *handle) { copy_last_highmem_page(); + /* Restore page key for data page (s390 only). */ + page_key_write(handle->buffer); + page_key_free(); /* Free only if we have loaded the image entirely */ if (handle->cur > 1 && handle->cur > nr_meta_pages + nr_copy_pages) { memory_bm_free(&orig_bm, PG_UNSAFE_CLEAR); diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c index b6b71ad..fdd4263 100644 --- a/kernel/power/suspend.c +++ b/kernel/power/suspend.c @@ -104,7 +104,10 @@ static int suspend_prepare(void) goto Finish; error = suspend_freeze_processes(); - if (!error) + if (error) { + suspend_stats.failed_freeze++; + dpm_save_failed_step(SUSPEND_FREEZE); + } else return 0; suspend_thaw_processes(); @@ -315,8 +318,16 @@ int enter_state(suspend_state_t state) */ int pm_suspend(suspend_state_t state) { - if (state > PM_SUSPEND_ON && state <= PM_SUSPEND_MAX) - return enter_state(state); + int ret; + if (state > PM_SUSPEND_ON && state < PM_SUSPEND_MAX) { + ret = enter_state(state); + if (ret) { + suspend_stats.fail++; + dpm_save_failed_errno(ret); + } else + suspend_stats.success++; + return ret; + } return -EINVAL; } EXPORT_SYMBOL(pm_suspend); diff --git a/kernel/power/swap.c b/kernel/power/swap.c index 7c97c3a..11a594c 100644 --- a/kernel/power/swap.c +++ b/kernel/power/swap.c @@ -27,6 +27,10 @@ #include <linux/slab.h> #include <linux/lzo.h> #include <linux/vmalloc.h> +#include <linux/cpumask.h> +#include <linux/atomic.h> +#include <linux/kthread.h> +#include <linux/crc32.h> #include "power.h" @@ -43,8 +47,7 @@ * allocated and populated one at a time, so we only need one memory * page to set up the entire structure. * - * During resume we also only need to use one swap_map_page structure - * at a time. + * During resume we pick up all swap_map_page structures into a list. */ #define MAP_PAGE_ENTRIES (PAGE_SIZE / sizeof(sector_t) - 1) @@ -54,6 +57,11 @@ struct swap_map_page { sector_t next_swap; }; +struct swap_map_page_list { + struct swap_map_page *map; + struct swap_map_page_list *next; +}; + /** * The swap_map_handle structure is used for handling swap in * a file-alike way @@ -61,13 +69,18 @@ struct swap_map_page { struct swap_map_handle { struct swap_map_page *cur; + struct swap_map_page_list *maps; sector_t cur_swap; sector_t first_sector; unsigned int k; + unsigned long nr_free_pages, written; + u32 crc32; }; struct swsusp_header { - char reserved[PAGE_SIZE - 20 - sizeof(sector_t) - sizeof(int)]; + char reserved[PAGE_SIZE - 20 - sizeof(sector_t) - sizeof(int) - + sizeof(u32)]; + u32 crc32; sector_t image; unsigned int flags; /* Flags to pass to the "boot" kernel */ char orig_sig[10]; @@ -199,6 +212,8 @@ static int mark_swapfiles(struct swap_map_handle *handle, unsigned int flags) memcpy(swsusp_header->sig, HIBERNATE_SIG, 10); swsusp_header->image = handle->first_sector; swsusp_header->flags = flags; + if (flags & SF_CRC32_MODE) + swsusp_header->crc32 = handle->crc32; error = hib_bio_write_page(swsusp_resume_block, swsusp_header, NULL); } else { @@ -245,6 +260,7 @@ static int swsusp_swap_check(void) static int write_page(void *buf, sector_t offset, struct bio **bio_chain) { void *src; + int ret; if (!offset) return -ENOSPC; @@ -254,9 +270,17 @@ static int write_page(void *buf, sector_t offset, struct bio **bio_chain) if (src) { copy_page(src, buf); } else { - WARN_ON_ONCE(1); - bio_chain = NULL; /* Go synchronous */ - src = buf; + ret = hib_wait_on_bio_chain(bio_chain); /* Free pages */ + if (ret) + return ret; + src = (void *)__get_free_page(__GFP_WAIT | __GFP_HIGH); + if (src) { + copy_page(src, buf); + } else { + WARN_ON_ONCE(1); + bio_chain = NULL; /* Go synchronous */ + src = buf; + } } } else { src = buf; @@ -293,6 +317,8 @@ static int get_swap_writer(struct swap_map_handle *handle) goto err_rel; } handle->k = 0; + handle->nr_free_pages = nr_free_pages() >> 1; + handle->written = 0; handle->first_sector = handle->cur_swap; return 0; err_rel: @@ -316,20 +342,23 @@ static int swap_write_page(struct swap_map_handle *handle, void *buf, return error; handle->cur->entries[handle->k++] = offset; if (handle->k >= MAP_PAGE_ENTRIES) { - error = hib_wait_on_bio_chain(bio_chain); - if (error) - goto out; offset = alloc_swapdev_block(root_swap); if (!offset) return -ENOSPC; handle->cur->next_swap = offset; - error = write_page(handle->cur, handle->cur_swap, NULL); + error = write_page(handle->cur, handle->cur_swap, bio_chain); if (error) goto out; clear_page(handle->cur); handle->cur_swap = offset; handle->k = 0; } + if (bio_chain && ++handle->written > handle->nr_free_pages) { + error = hib_wait_on_bio_chain(bio_chain); + if (error) + goto out; + handle->written = 0; + } out: return error; } @@ -372,6 +401,13 @@ static int swap_writer_finish(struct swap_map_handle *handle, LZO_HEADER, PAGE_SIZE) #define LZO_CMP_SIZE (LZO_CMP_PAGES * PAGE_SIZE) +/* Maximum number of threads for compression/decompression. */ +#define LZO_THREADS 3 + +/* Maximum number of pages for read buffering. */ +#define LZO_READ_PAGES (MAP_PAGE_ENTRIES * 8) + + /** * save_image - save the suspend image data */ @@ -419,6 +455,92 @@ static int save_image(struct swap_map_handle *handle, return ret; } +/** + * Structure used for CRC32. + */ +struct crc_data { + struct task_struct *thr; /* thread */ + atomic_t ready; /* ready to start flag */ + atomic_t stop; /* ready to stop flag */ + unsigned run_threads; /* nr current threads */ + wait_queue_head_t go; /* start crc update */ + wait_queue_head_t done; /* crc update done */ + u32 *crc32; /* points to handle's crc32 */ + size_t *unc_len[LZO_THREADS]; /* uncompressed lengths */ + unsigned char *unc[LZO_THREADS]; /* uncompressed data */ +}; + +/** + * CRC32 update function that runs in its own thread. + */ +static int crc32_threadfn(void *data) +{ + struct crc_data *d = data; + unsigned i; + + while (1) { + wait_event(d->go, atomic_read(&d->ready) || + kthread_should_stop()); + if (kthread_should_stop()) { + d->thr = NULL; + atomic_set(&d->stop, 1); + wake_up(&d->done); + break; + } + atomic_set(&d->ready, 0); + + for (i = 0; i < d->run_threads; i++) + *d->crc32 = crc32_le(*d->crc32, + d->unc[i], *d->unc_len[i]); + atomic_set(&d->stop, 1); + wake_up(&d->done); + } + return 0; +} +/** + * Structure used for LZO data compression. + */ +struct cmp_data { + struct task_struct *thr; /* thread */ + atomic_t ready; /* ready to start flag */ + atomic_t stop; /* ready to stop flag */ + int ret; /* return code */ + wait_queue_head_t go; /* start compression */ + wait_queue_head_t done; /* compression done */ + size_t unc_len; /* uncompressed length */ + size_t cmp_len; /* compressed length */ + unsigned char unc[LZO_UNC_SIZE]; /* uncompressed buffer */ + unsigned char cmp[LZO_CMP_SIZE]; /* compressed buffer */ + unsigned char wrk[LZO1X_1_MEM_COMPRESS]; /* compression workspace */ +}; + +/** + * Compression function that runs in its own thread. + */ +static int lzo_compress_threadfn(void *data) +{ + struct cmp_data *d = data; + + while (1) { + wait_event(d->go, atomic_read(&d->ready) || + kthread_should_stop()); + if (kthread_should_stop()) { + d->thr = NULL; + d->ret = -1; + atomic_set(&d->stop, 1); + wake_up(&d->done); + break; + } + atomic_set(&d->ready, 0); + + d->ret = lzo1x_1_compress(d->unc, d->unc_len, + d->cmp + LZO_HEADER, &d->cmp_len, + d->wrk); + atomic_set(&d->stop, 1); + wake_up(&d->done); + } + return 0; +} /** * save_image_lzo - Save the suspend image data compressed with LZO. @@ -437,42 +559,93 @@ static int save_image_lzo(struct swap_map_handle *handle, struct bio *bio; struct timeval start; struct timeval stop; - size_t off, unc_len, cmp_len; - unsigned char *unc, *cmp, *wrk, *page; + size_t off; + unsigned thr, run_threads, nr_threads; + unsigned char *page = NULL; + struct cmp_data *data = NULL; + struct crc_data *crc = NULL; + + /* + * We'll limit the number of threads for compression to limit memory + * footprint. + */ + nr_threads = num_online_cpus() - 1; + nr_threads = clamp_val(nr_threads, 1, LZO_THREADS); page = (void *)__get_free_page(__GFP_WAIT | __GFP_HIGH); if (!page) { printk(KERN_ERR "PM: Failed to allocate LZO page\n"); - return -ENOMEM; + ret = -ENOMEM; + goto out_clean; } - wrk = vmalloc(LZO1X_1_MEM_COMPRESS); - if (!wrk) { - printk(KERN_ERR "PM: Failed to allocate LZO workspace\n"); - free_page((unsigned long)page); - return -ENOMEM; + data = vmalloc(sizeof(*data) * nr_threads); + if (!data) { + printk(KERN_ERR "PM: Failed to allocate LZO data\n"); + ret = -ENOMEM; + goto out_clean; } + for (thr = 0; thr < nr_threads; thr++) + memset(&data[thr], 0, offsetof(struct cmp_data, go)); - unc = vmalloc(LZO_UNC_SIZE); - if (!unc) { - printk(KERN_ERR "PM: Failed to allocate LZO uncompressed\n"); - vfree(wrk); - free_page((unsigned long)page); - return -ENOMEM; + crc = kmalloc(sizeof(*crc), GFP_KERNEL); + if (!crc) { + printk(KERN_ERR "PM: Failed to allocate crc\n"); + ret = -ENOMEM; + goto out_clean; + } + memset(crc, 0, offsetof(struct crc_data, go)); + + /* + * Start the compression threads. + */ + for (thr = 0; thr < nr_threads; thr++) { + init_waitqueue_head(&data[thr].go); + init_waitqueue_head(&data[thr].done); + + data[thr].thr = kthread_run(lzo_compress_threadfn, + &data[thr], + "image_compress/%u", thr); + if (IS_ERR(data[thr].thr)) { + data[thr].thr = NULL; + printk(KERN_ERR + "PM: Cannot start compression threads\n"); + ret = -ENOMEM; + goto out_clean; + } } - cmp = vmalloc(LZO_CMP_SIZE); - if (!cmp) { - printk(KERN_ERR "PM: Failed to allocate LZO compressed\n"); - vfree(unc); - vfree(wrk); - free_page((unsigned long)page); - return -ENOMEM; + /* + * Adjust number of free pages after all allocations have been done. + * We don't want to run out of pages when writing. + */ + handle->nr_free_pages = nr_free_pages() >> 1; + + /* + * Start the CRC32 thread. + */ + init_waitqueue_head(&crc->go); + init_waitqueue_head(&crc->done); + + handle->crc32 = 0; + crc->crc32 = &handle->crc32; + for (thr = 0; thr < nr_threads; thr++) { + crc->unc[thr] = data[thr].unc; + crc->unc_len[thr] = &data[thr].unc_len; + } + + crc->thr = kthread_run(crc32_threadfn, crc, "image_crc32"); + if (IS_ERR(crc->thr)) { + crc->thr = NULL; + printk(KERN_ERR "PM: Cannot start CRC32 thread\n"); + ret = -ENOMEM; + goto out_clean; } printk(KERN_INFO + "PM: Using %u thread(s) for compression.\n" "PM: Compressing and saving image data (%u pages) ... ", - nr_to_write); + nr_threads, nr_to_write); m = nr_to_write / 100; if (!m) m = 1; @@ -480,55 +653,83 @@ static int save_image_lzo(struct swap_map_handle *handle, bio = NULL; do_gettimeofday(&start); for (;;) { - for (off = 0; off < LZO_UNC_SIZE; off += PAGE_SIZE) { - ret = snapshot_read_next(snapshot); - if (ret < 0) - goto out_finish; - - if (!ret) + for (thr = 0; thr < nr_threads; thr++) { + for (off = 0; off < LZO_UNC_SIZE; off += PAGE_SIZE) { + ret = snapshot_read_next(snapshot); + if (ret < 0) + goto out_finish; + + if (!ret) + break; + + memcpy(data[thr].unc + off, + data_of(*snapshot), PAGE_SIZE); + + if (!(nr_pages % m)) + printk(KERN_CONT "\b\b\b\b%3d%%", + nr_pages / m); + nr_pages++; + } + if (!off) break; - memcpy(unc + off, data_of(*snapshot), PAGE_SIZE); + data[thr].unc_len = off; - if (!(nr_pages % m)) - printk(KERN_CONT "\b\b\b\b%3d%%", nr_pages / m); - nr_pages++; + atomic_set(&data[thr].ready, 1); + wake_up(&data[thr].go); } - if (!off) + if (!thr) break; - unc_len = off; - ret = lzo1x_1_compress(unc, unc_len, - cmp + LZO_HEADER, &cmp_len, wrk); - if (ret < 0) { - printk(KERN_ERR "PM: LZO compression failed\n"); - break; - } + crc->run_threads = thr; + atomic_set(&crc->ready, 1); + wake_up(&crc->go); - if (unlikely(!cmp_len || - cmp_len > lzo1x_worst_compress(unc_len))) { - printk(KERN_ERR "PM: Invalid LZO compressed length\n"); - ret = -1; - break; - } + for (run_threads = thr, thr = 0; thr < run_threads; thr++) { + wait_event(data[thr].done, + atomic_read(&data[thr].stop)); + atomic_set(&data[thr].stop, 0); - *(size_t *)cmp = cmp_len; + ret = data[thr].ret; - /* - * Given we are writing one page at a time to disk, we copy - * that much from the buffer, although the last bit will likely - * be smaller than full page. This is OK - we saved the length - * of the compressed data, so any garbage at the end will be - * discarded when we read it. - */ - for (off = 0; off < LZO_HEADER + cmp_len; off += PAGE_SIZE) { - memcpy(page, cmp + off, PAGE_SIZE); + if (ret < 0) { + printk(KERN_ERR "PM: LZO compression failed\n"); + goto out_finish; + } - ret = swap_write_page(handle, page, &bio); - if (ret) + if (unlikely(!data[thr].cmp_len || + data[thr].cmp_len > + lzo1x_worst_compress(data[thr].unc_len))) { + printk(KERN_ERR + "PM: Invalid LZO compressed length\n"); + ret = -1; goto out_finish; + } + + *(size_t *)data[thr].cmp = data[thr].cmp_len; + + /* + * Given we are writing one page at a time to disk, we + * copy that much from the buffer, although the last + * bit will likely be smaller than full page. This is + * OK - we saved the length of the compressed data, so + * any garbage at the end will be discarded when we + * read it. + */ + for (off = 0; + off < LZO_HEADER + data[thr].cmp_len; + off += PAGE_SIZE) { + memcpy(page, data[thr].cmp + off, PAGE_SIZE); + + ret = swap_write_page(handle, page, &bio); + if (ret) + goto out_finish; + } } + + wait_event(crc->done, atomic_read(&crc->stop)); + atomic_set(&crc->stop, 0); } out_finish: @@ -536,16 +737,25 @@ out_finish: do_gettimeofday(&stop); if (!ret) ret = err2; - if (!ret) + if (!ret) { printk(KERN_CONT "\b\b\b\bdone\n"); - else + } else { printk(KERN_CONT "\n"); + } swsusp_show_speed(&start, &stop, nr_to_write, "Wrote"); - - vfree(cmp); - vfree(unc); - vfree(wrk); - free_page((unsigned long)page); +out_clean: + if (crc) { + if (crc->thr) + kthread_stop(crc->thr); + kfree(crc); + } + if (data) { + for (thr = 0; thr < nr_threads; thr++) + if (data[thr].thr) + kthread_stop(data[thr].thr); + vfree(data); + } + if (page) free_page((unsigned long)page); return ret; } @@ -625,8 +835,15 @@ out_finish: static void release_swap_reader(struct swap_map_handle *handle) { - if (handle->cur) - free_page((unsigned long)handle->cur); + struct swap_map_page_list *tmp; + + while (handle->maps) { + if (handle->maps->map) + free_page((unsigned long)handle->maps->map); + tmp = handle->maps; + handle->maps = handle->maps->next; + kfree(tmp); + } handle->cur = NULL; } @@ -634,22 +851,46 @@ static int get_swap_reader(struct swap_map_handle *handle, unsigned int *flags_p) { int error; + struct swap_map_page_list *tmp, *last; + sector_t offset; *flags_p = swsusp_header->flags; if (!swsusp_header->image) /* how can this happen? */ return -EINVAL; - handle->cur = (struct swap_map_page *)get_zeroed_page(__GFP_WAIT | __GFP_HIGH); - if (!handle->cur) - return -ENOMEM; + handle->cur = NULL; + last = handle->maps = NULL; + offset = swsusp_header->image; + while (offset) { + tmp = kmalloc(sizeof(*handle->maps), GFP_KERNEL); + if (!tmp) { + release_swap_reader(handle); + return -ENOMEM; + } + memset(tmp, 0, sizeof(*tmp)); + if (!handle->maps) + handle->maps = tmp; + if (last) + last->next = tmp; + last = tmp; + + tmp->map = (struct swap_map_page *) + __get_free_page(__GFP_WAIT | __GFP_HIGH); + if (!tmp->map) { + release_swap_reader(handle); + return -ENOMEM; + } - error = hib_bio_read_page(swsusp_header->image, handle->cur, NULL); - if (error) { - release_swap_reader(handle); - return error; + error = hib_bio_read_page(offset, tmp->map, NULL); + if (error) { + release_swap_reader(handle); + return error; + } + offset = tmp->map->next_swap; } handle->k = 0; + handle->cur = handle->maps->map; return 0; } @@ -658,6 +899,7 @@ static int swap_read_page(struct swap_map_handle *handle, void *buf, { sector_t offset; int error; + struct swap_map_page_list *tmp; if (!handle->cur) return -EINVAL; @@ -668,13 +910,15 @@ static int swap_read_page(struct swap_map_handle *handle, void *buf, if (error) return error; if (++handle->k >= MAP_PAGE_ENTRIES) { - error = hib_wait_on_bio_chain(bio_chain); handle->k = 0; - offset = handle->cur->next_swap; - if (!offset) + free_page((unsigned long)handle->maps->map); + tmp = handle->maps; + handle->maps = handle->maps->next; + kfree(tmp); + if (!handle->maps) release_swap_reader(handle); - else if (!error) - error = hib_bio_read_page(offset, handle->cur, NULL); + else + handle->cur = handle->maps->map; } return error; } @@ -697,7 +941,7 @@ static int load_image(struct swap_map_handle *handle, unsigned int nr_to_read) { unsigned int m; - int error = 0; + int ret = 0; struct timeval start; struct timeval stop; struct bio *bio; @@ -713,15 +957,15 @@ static int load_image(struct swap_map_handle *handle, bio = NULL; do_gettimeofday(&start); for ( ; ; ) { - error = snapshot_write_next(snapshot); - if (error <= 0) + ret = snapshot_write_next(snapshot); + if (ret <= 0) break; - error = swap_read_page(handle, data_of(*snapshot), &bio); - if (error) + ret = swap_read_page(handle, data_of(*snapshot), &bio); + if (ret) break; if (snapshot->sync_read) - error = hib_wait_on_bio_chain(&bio); - if (error) + ret = hib_wait_on_bio_chain(&bio); + if (ret) break; if (!(nr_pages % m)) printk("\b\b\b\b%3d%%", nr_pages / m); @@ -729,17 +973,61 @@ static int load_image(struct swap_map_handle *handle, } err2 = hib_wait_on_bio_chain(&bio); do_gettimeofday(&stop); - if (!error) - error = err2; - if (!error) { + if (!ret) + ret = err2; + if (!ret) { printk("\b\b\b\bdone\n"); snapshot_write_finalize(snapshot); if (!snapshot_image_loaded(snapshot)) - error = -ENODATA; + ret = -ENODATA; } else printk("\n"); swsusp_show_speed(&start, &stop, nr_to_read, "Read"); - return error; + return ret; +} + +/** + * Structure used for LZO data decompression. + */ +struct dec_data { + struct task_struct *thr; /* thread */ + atomic_t ready; /* ready to start flag */ + atomic_t stop; /* ready to stop flag */ + int ret; /* return code */ + wait_queue_head_t go; /* start decompression */ + wait_queue_head_t done; /* decompression done */ + size_t unc_len; /* uncompressed length */ + size_t cmp_len; /* compressed length */ + unsigned char unc[LZO_UNC_SIZE]; /* uncompressed buffer */ + unsigned char cmp[LZO_CMP_SIZE]; /* compressed buffer */ +}; + +/** + * Deompression function that runs in its own thread. + */ +static int lzo_decompress_threadfn(void *data) +{ + struct dec_data *d = data; + + while (1) { + wait_event(d->go, atomic_read(&d->ready) || + kthread_should_stop()); + if (kthread_should_stop()) { + d->thr = NULL; + d->ret = -1; + atomic_set(&d->stop, 1); + wake_up(&d->done); + break; + } + atomic_set(&d->ready, 0); + + d->unc_len = LZO_UNC_SIZE; + d->ret = lzo1x_decompress_safe(d->cmp + LZO_HEADER, d->cmp_len, + d->unc, &d->unc_len); + atomic_set(&d->stop, 1); + wake_up(&d->done); + } + return 0; } /** @@ -753,50 +1041,120 @@ static int load_image_lzo(struct swap_map_handle *handle, unsigned int nr_to_read) { unsigned int m; - int error = 0; + int ret = 0; + int eof = 0; struct bio *bio; struct timeval start; struct timeval stop; unsigned nr_pages; - size_t i, off, unc_len, cmp_len; - unsigned char *unc, *cmp, *page[LZO_CMP_PAGES]; - - for (i = 0; i < LZO_CMP_PAGES; i++) { - page[i] = (void *)__get_free_page(__GFP_WAIT | __GFP_HIGH); - if (!page[i]) { - printk(KERN_ERR "PM: Failed to allocate LZO page\n"); + size_t off; + unsigned i, thr, run_threads, nr_threads; + unsigned ring = 0, pg = 0, ring_size = 0, + have = 0, want, need, asked = 0; + unsigned long read_pages; + unsigned char **page = NULL; + struct dec_data *data = NULL; + struct crc_data *crc = NULL; + + /* + * We'll limit the number of threads for decompression to limit memory + * footprint. + */ + nr_threads = num_online_cpus() - 1; + nr_threads = clamp_val(nr_threads, 1, LZO_THREADS); + + page = vmalloc(sizeof(*page) * LZO_READ_PAGES); + if (!page) { + printk(KERN_ERR "PM: Failed to allocate LZO page\n"); + ret = -ENOMEM; + goto out_clean; + } - while (i) - free_page((unsigned long)page[--i]); + data = vmalloc(sizeof(*data) * nr_threads); + if (!data) { + printk(KERN_ERR "PM: Failed to allocate LZO data\n"); + ret = -ENOMEM; + goto out_clean; + } + for (thr = 0; thr < nr_threads; thr++) + memset(&data[thr], 0, offsetof(struct dec_data, go)); - return -ENOMEM; + crc = kmalloc(sizeof(*crc), GFP_KERNEL); + if (!crc) { + printk(KERN_ERR "PM: Failed to allocate crc\n"); + ret = -ENOMEM; + goto out_clean; + } + memset(crc, 0, offsetof(struct crc_data, go)); + + /* + * Start the decompression threads. + */ + for (thr = 0; thr < nr_threads; thr++) { + init_waitqueue_head(&data[thr].go); + init_waitqueue_head(&data[thr].done); + + data[thr].thr = kthread_run(lzo_decompress_threadfn, + &data[thr], + "image_decompress/%u", thr); + if (IS_ERR(data[thr].thr)) { + data[thr].thr = NULL; + printk(KERN_ERR + "PM: Cannot start decompression threads\n"); + ret = -ENOMEM; + goto out_clean; } } - unc = vmalloc(LZO_UNC_SIZE); - if (!unc) { - printk(KERN_ERR "PM: Failed to allocate LZO uncompressed\n"); - - for (i = 0; i < LZO_CMP_PAGES; i++) - free_page((unsigned long)page[i]); - - return -ENOMEM; + /* + * Start the CRC32 thread. + */ + init_waitqueue_head(&crc->go); + init_waitqueue_head(&crc->done); + + handle->crc32 = 0; + crc->crc32 = &handle->crc32; + for (thr = 0; thr < nr_threads; thr++) { + crc->unc[thr] = data[thr].unc; + crc->unc_len[thr] = &data[thr].unc_len; } - cmp = vmalloc(LZO_CMP_SIZE); - if (!cmp) { - printk(KERN_ERR "PM: Failed to allocate LZO compressed\n"); + crc->thr = kthread_run(crc32_threadfn, crc, "image_crc32"); + if (IS_ERR(crc->thr)) { + crc->thr = NULL; + printk(KERN_ERR "PM: Cannot start CRC32 thread\n"); + ret = -ENOMEM; + goto out_clean; + } - vfree(unc); - for (i = 0; i < LZO_CMP_PAGES; i++) - free_page((unsigned long)page[i]); + /* + * Adjust number of pages for read buffering, in case we are short. + */ + read_pages = (nr_free_pages() - snapshot_get_image_size()) >> 1; + read_pages = clamp_val(read_pages, LZO_CMP_PAGES, LZO_READ_PAGES); - return -ENOMEM; + for (i = 0; i < read_pages; i++) { + page[i] = (void *)__get_free_page(i < LZO_CMP_PAGES ? + __GFP_WAIT | __GFP_HIGH : + __GFP_WAIT); + if (!page[i]) { + if (i < LZO_CMP_PAGES) { + ring_size = i; + printk(KERN_ERR + "PM: Failed to allocate LZO pages\n"); + ret = -ENOMEM; + goto out_clean; + } else { + break; + } + } } + want = ring_size = i; printk(KERN_INFO + "PM: Using %u thread(s) for decompression.\n" "PM: Loading and decompressing image data (%u pages) ... ", - nr_to_read); + nr_threads, nr_to_read); m = nr_to_read / 100; if (!m) m = 1; @@ -804,85 +1162,189 @@ static int load_image_lzo(struct swap_map_handle *handle, bio = NULL; do_gettimeofday(&start); - error = snapshot_write_next(snapshot); - if (error <= 0) + ret = snapshot_write_next(snapshot); + if (ret <= 0) goto out_finish; - for (;;) { - error = swap_read_page(handle, page[0], NULL); /* sync */ - if (error) - break; - - cmp_len = *(size_t *)page[0]; - if (unlikely(!cmp_len || - cmp_len > lzo1x_worst_compress(LZO_UNC_SIZE))) { - printk(KERN_ERR "PM: Invalid LZO compressed length\n"); - error = -1; - break; + for(;;) { + for (i = 0; !eof && i < want; i++) { + ret = swap_read_page(handle, page[ring], &bio); + if (ret) { + /* + * On real read error, finish. On end of data, + * set EOF flag and just exit the read loop. + */ + if (handle->cur && + handle->cur->entries[handle->k]) { + goto out_finish; + } else { + eof = 1; + break; + } + } + if (++ring >= ring_size) + ring = 0; } + asked += i; + want -= i; - for (off = PAGE_SIZE, i = 1; - off < LZO_HEADER + cmp_len; off += PAGE_SIZE, i++) { - error = swap_read_page(handle, page[i], &bio); - if (error) + /* + * We are out of data, wait for some more. + */ + if (!have) { + if (!asked) + break; + + ret = hib_wait_on_bio_chain(&bio); + if (ret) goto out_finish; + have += asked; + asked = 0; + if (eof) + eof = 2; } - error = hib_wait_on_bio_chain(&bio); /* need all data now */ - if (error) - goto out_finish; - - for (off = 0, i = 0; - off < LZO_HEADER + cmp_len; off += PAGE_SIZE, i++) { - memcpy(cmp + off, page[i], PAGE_SIZE); + if (crc->run_threads) { + wait_event(crc->done, atomic_read(&crc->stop)); + atomic_set(&crc->stop, 0); + crc->run_threads = 0; } - unc_len = LZO_UNC_SIZE; - error = lzo1x_decompress_safe(cmp + LZO_HEADER, cmp_len, - unc, &unc_len); - if (error < 0) { - printk(KERN_ERR "PM: LZO decompression failed\n"); - break; + for (thr = 0; have && thr < nr_threads; thr++) { + data[thr].cmp_len = *(size_t *)page[pg]; + if (unlikely(!data[thr].cmp_len || + data[thr].cmp_len > + lzo1x_worst_compress(LZO_UNC_SIZE))) { + printk(KERN_ERR + "PM: Invalid LZO compressed length\n"); + ret = -1; + goto out_finish; + } + + need = DIV_ROUND_UP(data[thr].cmp_len + LZO_HEADER, + PAGE_SIZE); + if (need > have) { + if (eof > 1) { + ret = -1; + goto out_finish; + } + break; + } + + for (off = 0; + off < LZO_HEADER + data[thr].cmp_len; + off += PAGE_SIZE) { + memcpy(data[thr].cmp + off, + page[pg], PAGE_SIZE); + have--; + want++; + if (++pg >= ring_size) + pg = 0; + } + + atomic_set(&data[thr].ready, 1); + wake_up(&data[thr].go); } - if (unlikely(!unc_len || - unc_len > LZO_UNC_SIZE || - unc_len & (PAGE_SIZE - 1))) { - printk(KERN_ERR "PM: Invalid LZO uncompressed length\n"); - error = -1; - break; + /* + * Wait for more data while we are decompressing. + */ + if (have < LZO_CMP_PAGES && asked) { + ret = hib_wait_on_bio_chain(&bio); + if (ret) + goto out_finish; + have += asked; + asked = 0; + if (eof) + eof = 2; } - for (off = 0; off < unc_len; off += PAGE_SIZE) { - memcpy(data_of(*snapshot), unc + off, PAGE_SIZE); + for (run_threads = thr, thr = 0; thr < run_threads; thr++) { + wait_event(data[thr].done, + atomic_read(&data[thr].stop)); + atomic_set(&data[thr].stop, 0); + + ret = data[thr].ret; - if (!(nr_pages % m)) - printk("\b\b\b\b%3d%%", nr_pages / m); - nr_pages++; + if (ret < 0) { + printk(KERN_ERR + "PM: LZO decompression failed\n"); + goto out_finish; + } - error = snapshot_write_next(snapshot); - if (error <= 0) + if (unlikely(!data[thr].unc_len || + data[thr].unc_len > LZO_UNC_SIZE || + data[thr].unc_len & (PAGE_SIZE - 1))) { + printk(KERN_ERR + "PM: Invalid LZO uncompressed length\n"); + ret = -1; goto out_finish; + } + + for (off = 0; + off < data[thr].unc_len; off += PAGE_SIZE) { + memcpy(data_of(*snapshot), + data[thr].unc + off, PAGE_SIZE); + + if (!(nr_pages % m)) + printk("\b\b\b\b%3d%%", nr_pages / m); + nr_pages++; + + ret = snapshot_write_next(snapshot); + if (ret <= 0) { + crc->run_threads = thr + 1; + atomic_set(&crc->ready, 1); + wake_up(&crc->go); + goto out_finish; + } + } } + + crc->run_threads = thr; + atomic_set(&crc->ready, 1); + wake_up(&crc->go); } out_finish: + if (crc->run_threads) { + wait_event(crc->done, atomic_read(&crc->stop)); + atomic_set(&crc->stop, 0); + } do_gettimeofday(&stop); - if (!error) { + if (!ret) { printk("\b\b\b\bdone\n"); snapshot_write_finalize(snapshot); if (!snapshot_image_loaded(snapshot)) - error = -ENODATA; + ret = -ENODATA; + if (!ret) { + if (swsusp_header->flags & SF_CRC32_MODE) { + if(handle->crc32 != swsusp_header->crc32) { + printk(KERN_ERR + "PM: Invalid image CRC32!\n"); + ret = -ENODATA; + } + } + } } else printk("\n"); swsusp_show_speed(&start, &stop, nr_to_read, "Read"); - - vfree(cmp); - vfree(unc); - for (i = 0; i < LZO_CMP_PAGES; i++) +out_clean: + for (i = 0; i < ring_size; i++) free_page((unsigned long)page[i]); + if (crc) { + if (crc->thr) + kthread_stop(crc->thr); + kfree(crc); + } + if (data) { + for (thr = 0; thr < nr_threads; thr++) + if (data[thr].thr) + kthread_stop(data[thr].thr); + vfree(data); + } + if (page) vfree(page); - return error; + return ret; } /** diff --git a/kernel/printk.c b/kernel/printk.c index 28a40d8..1455a0d 100644 --- a/kernel/printk.c +++ b/kernel/printk.c @@ -100,7 +100,7 @@ static int console_locked, console_suspended; * It is also used in interesting ways to provide interlocking in * console_unlock();. */ -static DEFINE_SPINLOCK(logbuf_lock); +static DEFINE_RAW_SPINLOCK(logbuf_lock); #define LOG_BUF_MASK (log_buf_len-1) #define LOG_BUF(idx) (log_buf[(idx) & LOG_BUF_MASK]) @@ -212,7 +212,7 @@ void __init setup_log_buf(int early) return; } - spin_lock_irqsave(&logbuf_lock, flags); + raw_spin_lock_irqsave(&logbuf_lock, flags); log_buf_len = new_log_buf_len; log_buf = new_log_buf; new_log_buf_len = 0; @@ -230,7 +230,7 @@ void __init setup_log_buf(int early) log_start -= offset; con_start -= offset; log_end -= offset; - spin_unlock_irqrestore(&logbuf_lock, flags); + raw_spin_unlock_irqrestore(&logbuf_lock, flags); pr_info("log_buf_len: %d\n", log_buf_len); pr_info("early log buf free: %d(%d%%)\n", @@ -365,18 +365,18 @@ int do_syslog(int type, char __user *buf, int len, bool from_file) if (error) goto out; i = 0; - spin_lock_irq(&logbuf_lock); + raw_spin_lock_irq(&logbuf_lock); while (!error && (log_start != log_end) && i < len) { c = LOG_BUF(log_start); log_start++; - spin_unlock_irq(&logbuf_lock); + raw_spin_unlock_irq(&logbuf_lock); error = __put_user(c,buf); buf++; i++; cond_resched(); - spin_lock_irq(&logbuf_lock); + raw_spin_lock_irq(&logbuf_lock); } - spin_unlock_irq(&logbuf_lock); + raw_spin_unlock_irq(&logbuf_lock); if (!error) error = i; break; @@ -399,7 +399,7 @@ int do_syslog(int type, char __user *buf, int len, bool from_file) count = len; if (count > log_buf_len) count = log_buf_len; - spin_lock_irq(&logbuf_lock); + raw_spin_lock_irq(&logbuf_lock); if (count > logged_chars) count = logged_chars; if (do_clear) @@ -416,12 +416,12 @@ int do_syslog(int type, char __user *buf, int len, bool from_file) if (j + log_buf_len < log_end) break; c = LOG_BUF(j); - spin_unlock_irq(&logbuf_lock); + raw_spin_unlock_irq(&logbuf_lock); error = __put_user(c,&buf[count-1-i]); cond_resched(); - spin_lock_irq(&logbuf_lock); + raw_spin_lock_irq(&logbuf_lock); } - spin_unlock_irq(&logbuf_lock); + raw_spin_unlock_irq(&logbuf_lock); if (error) break; error = i; @@ -532,6 +532,9 @@ static int __init ignore_loglevel_setup(char *str) } early_param("ignore_loglevel", ignore_loglevel_setup); +module_param_named(ignore_loglevel, ignore_loglevel, bool, S_IRUGO | S_IWUSR); +MODULE_PARM_DESC(ignore_loglevel, "ignore loglevel setting, to" + "print all kernel messages to the console."); /* * Write out chars from start to end - 1 inclusive @@ -592,9 +595,6 @@ static size_t log_prefix(const char *p, unsigned int *level, char *special) /* multi digit including the level and facility number */ char *endp = NULL; - if (p[1] < '0' && p[1] > '9') - return 0; - lev = (simple_strtoul(&p[1], &endp, 10) & 7); if (endp == NULL || endp[0] != '>') return 0; @@ -689,7 +689,7 @@ static void zap_locks(void) oops_timestamp = jiffies; /* If a crash is occurring, make sure we can't deadlock */ - spin_lock_init(&logbuf_lock); + raw_spin_lock_init(&logbuf_lock); /* And make sure that we print immediately */ sema_init(&console_sem, 1); } @@ -802,9 +802,9 @@ static int console_trylock_for_printk(unsigned int cpu) } } printk_cpu = UINT_MAX; - spin_unlock(&logbuf_lock); if (wake) up(&console_sem); + raw_spin_unlock(&logbuf_lock); return retval; } static const char recursion_bug_msg [] = @@ -864,7 +864,7 @@ asmlinkage int vprintk(const char *fmt, va_list args) } lockdep_off(); - spin_lock(&logbuf_lock); + raw_spin_lock(&logbuf_lock); printk_cpu = this_cpu; if (recursion_bug) { @@ -1108,6 +1108,10 @@ static int __init console_suspend_disable(char *str) return 1; } __setup("no_console_suspend", console_suspend_disable); +module_param_named(console_suspend, console_suspend_enabled, + bool, S_IRUGO | S_IWUSR); +MODULE_PARM_DESC(console_suspend, "suspend console during suspend" + " and hibernate operations"); /** * suspend_console - suspend the console subsystem @@ -1257,14 +1261,14 @@ void console_unlock(void) again: for ( ; ; ) { - spin_lock_irqsave(&logbuf_lock, flags); + raw_spin_lock_irqsave(&logbuf_lock, flags); wake_klogd |= log_start - log_end; if (con_start == log_end) break; /* Nothing to print */ _con_start = con_start; _log_end = log_end; con_start = log_end; /* Flush */ - spin_unlock(&logbuf_lock); + raw_spin_unlock(&logbuf_lock); stop_critical_timings(); /* don't trace print latency */ call_console_drivers(_con_start, _log_end); start_critical_timings(); @@ -1276,7 +1280,7 @@ again: if (unlikely(exclusive_console)) exclusive_console = NULL; - spin_unlock(&logbuf_lock); + raw_spin_unlock(&logbuf_lock); up(&console_sem); @@ -1286,13 +1290,13 @@ again: * there's a new owner and the console_unlock() from them will do the * flush, no worries. */ - spin_lock(&logbuf_lock); + raw_spin_lock(&logbuf_lock); if (con_start != log_end) retry = 1; - spin_unlock_irqrestore(&logbuf_lock, flags); if (retry && console_trylock()) goto again; + raw_spin_unlock_irqrestore(&logbuf_lock, flags); if (wake_klogd) wake_up_klogd(); } @@ -1522,9 +1526,9 @@ void register_console(struct console *newcon) * console_unlock(); will print out the buffered messages * for us. */ - spin_lock_irqsave(&logbuf_lock, flags); + raw_spin_lock_irqsave(&logbuf_lock, flags); con_start = log_start; - spin_unlock_irqrestore(&logbuf_lock, flags); + raw_spin_unlock_irqrestore(&logbuf_lock, flags); /* * We're about to replay the log buffer. Only do this to the * just-registered console to avoid excessive message spam to @@ -1731,10 +1735,10 @@ void kmsg_dump(enum kmsg_dump_reason reason) /* Theoretically, the log could move on after we do this, but there's not a lot we can do about that. The new messages will overwrite the start of what we dump. */ - spin_lock_irqsave(&logbuf_lock, flags); + raw_spin_lock_irqsave(&logbuf_lock, flags); end = log_end & LOG_BUF_MASK; chars = logged_chars; - spin_unlock_irqrestore(&logbuf_lock, flags); + raw_spin_unlock_irqrestore(&logbuf_lock, flags); if (chars > end) { s1 = log_buf + log_buf_len - chars + end; diff --git a/kernel/rcu.h b/kernel/rcu.h new file mode 100644 index 0000000..f600868 --- /dev/null +++ b/kernel/rcu.h @@ -0,0 +1,85 @@ +/* + * Read-Copy Update definitions shared among RCU implementations. + * + * 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. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * + * Copyright IBM Corporation, 2011 + * + * Author: Paul E. McKenney <paulmck@linux.vnet.ibm.com> + */ + +#ifndef __LINUX_RCU_H +#define __LINUX_RCU_H + +#ifdef CONFIG_RCU_TRACE +#define RCU_TRACE(stmt) stmt +#else /* #ifdef CONFIG_RCU_TRACE */ +#define RCU_TRACE(stmt) +#endif /* #else #ifdef CONFIG_RCU_TRACE */ + +/* + * debug_rcu_head_queue()/debug_rcu_head_unqueue() are used internally + * by call_rcu() and rcu callback execution, and are therefore not part of the + * RCU API. Leaving in rcupdate.h because they are used by all RCU flavors. + */ + +#ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD +# define STATE_RCU_HEAD_READY 0 +# define STATE_RCU_HEAD_QUEUED 1 + +extern struct debug_obj_descr rcuhead_debug_descr; + +static inline void debug_rcu_head_queue(struct rcu_head *head) +{ + WARN_ON_ONCE((unsigned long)head & 0x3); + debug_object_activate(head, &rcuhead_debug_descr); + debug_object_active_state(head, &rcuhead_debug_descr, + STATE_RCU_HEAD_READY, + STATE_RCU_HEAD_QUEUED); +} + +static inline void debug_rcu_head_unqueue(struct rcu_head *head) +{ + debug_object_active_state(head, &rcuhead_debug_descr, + STATE_RCU_HEAD_QUEUED, + STATE_RCU_HEAD_READY); + debug_object_deactivate(head, &rcuhead_debug_descr); +} +#else /* !CONFIG_DEBUG_OBJECTS_RCU_HEAD */ +static inline void debug_rcu_head_queue(struct rcu_head *head) +{ +} + +static inline void debug_rcu_head_unqueue(struct rcu_head *head) +{ +} +#endif /* #else !CONFIG_DEBUG_OBJECTS_RCU_HEAD */ + +extern void kfree(const void *); + +static inline void __rcu_reclaim(char *rn, struct rcu_head *head) +{ + unsigned long offset = (unsigned long)head->func; + + if (__is_kfree_rcu_offset(offset)) { + RCU_TRACE(trace_rcu_invoke_kfree_callback(rn, head, offset)); + kfree((void *)head - offset); + } else { + RCU_TRACE(trace_rcu_invoke_callback(rn, head)); + head->func(head); + } +} + +#endif /* __LINUX_RCU_H */ diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c index ddddb32..ca0d23b 100644 --- a/kernel/rcupdate.c +++ b/kernel/rcupdate.c @@ -46,6 +46,11 @@ #include <linux/module.h> #include <linux/hardirq.h> +#define CREATE_TRACE_POINTS +#include <trace/events/rcu.h> + +#include "rcu.h" + #ifdef CONFIG_DEBUG_LOCK_ALLOC static struct lock_class_key rcu_lock_key; struct lockdep_map rcu_lock_map = @@ -94,11 +99,16 @@ EXPORT_SYMBOL_GPL(rcu_read_lock_bh_held); #endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ +struct rcu_synchronize { + struct rcu_head head; + struct completion completion; +}; + /* * Awaken the corresponding synchronize_rcu() instance now that a * grace period has elapsed. */ -void wakeme_after_rcu(struct rcu_head *head) +static void wakeme_after_rcu(struct rcu_head *head) { struct rcu_synchronize *rcu; @@ -106,6 +116,20 @@ void wakeme_after_rcu(struct rcu_head *head) complete(&rcu->completion); } +void wait_rcu_gp(call_rcu_func_t crf) +{ + struct rcu_synchronize rcu; + + init_rcu_head_on_stack(&rcu.head); + init_completion(&rcu.completion); + /* Will wake me after RCU finished. */ + crf(&rcu.head, wakeme_after_rcu); + /* Wait for it. */ + wait_for_completion(&rcu.completion); + destroy_rcu_head_on_stack(&rcu.head); +} +EXPORT_SYMBOL_GPL(wait_rcu_gp); + #ifdef CONFIG_PROVE_RCU /* * wrapper function to avoid #include problems. diff --git a/kernel/rcutiny.c b/kernel/rcutiny.c index 7bbac7d..da775c8 100644 --- a/kernel/rcutiny.c +++ b/kernel/rcutiny.c @@ -37,16 +37,17 @@ #include <linux/cpu.h> #include <linux/prefetch.h> -/* Controls for rcu_kthread() kthread, replacing RCU_SOFTIRQ used previously. */ -static struct task_struct *rcu_kthread_task; -static DECLARE_WAIT_QUEUE_HEAD(rcu_kthread_wq); -static unsigned long have_rcu_kthread_work; +#ifdef CONFIG_RCU_TRACE +#include <trace/events/rcu.h> +#endif /* #else #ifdef CONFIG_RCU_TRACE */ + +#include "rcu.h" /* Forward declarations for rcutiny_plugin.h. */ struct rcu_ctrlblk; -static void invoke_rcu_kthread(void); -static void rcu_process_callbacks(struct rcu_ctrlblk *rcp); -static int rcu_kthread(void *arg); +static void invoke_rcu_callbacks(void); +static void __rcu_process_callbacks(struct rcu_ctrlblk *rcp); +static void rcu_process_callbacks(struct softirq_action *unused); static void __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu), struct rcu_ctrlblk *rcp); @@ -96,16 +97,6 @@ static int rcu_qsctr_help(struct rcu_ctrlblk *rcp) } /* - * Wake up rcu_kthread() to process callbacks now eligible for invocation - * or to boost readers. - */ -static void invoke_rcu_kthread(void) -{ - have_rcu_kthread_work = 1; - wake_up(&rcu_kthread_wq); -} - -/* * Record an rcu quiescent state. And an rcu_bh quiescent state while we * are at it, given that any rcu quiescent state is also an rcu_bh * quiescent state. Use "+" instead of "||" to defeat short circuiting. @@ -117,7 +108,7 @@ void rcu_sched_qs(int cpu) local_irq_save(flags); if (rcu_qsctr_help(&rcu_sched_ctrlblk) + rcu_qsctr_help(&rcu_bh_ctrlblk)) - invoke_rcu_kthread(); + invoke_rcu_callbacks(); local_irq_restore(flags); } @@ -130,7 +121,7 @@ void rcu_bh_qs(int cpu) local_irq_save(flags); if (rcu_qsctr_help(&rcu_bh_ctrlblk)) - invoke_rcu_kthread(); + invoke_rcu_callbacks(); local_irq_restore(flags); } @@ -154,18 +145,23 @@ void rcu_check_callbacks(int cpu, int user) * Invoke the RCU callbacks on the specified rcu_ctrlkblk structure * whose grace period has elapsed. */ -static void rcu_process_callbacks(struct rcu_ctrlblk *rcp) +static void __rcu_process_callbacks(struct rcu_ctrlblk *rcp) { + char *rn = NULL; struct rcu_head *next, *list; unsigned long flags; RCU_TRACE(int cb_count = 0); /* If no RCU callbacks ready to invoke, just return. */ - if (&rcp->rcucblist == rcp->donetail) + if (&rcp->rcucblist == rcp->donetail) { + RCU_TRACE(trace_rcu_batch_start(rcp->name, 0, -1)); + RCU_TRACE(trace_rcu_batch_end(rcp->name, 0)); return; + } /* Move the ready-to-invoke callbacks to a local list. */ local_irq_save(flags); + RCU_TRACE(trace_rcu_batch_start(rcp->name, 0, -1)); list = rcp->rcucblist; rcp->rcucblist = *rcp->donetail; *rcp->donetail = NULL; @@ -176,49 +172,26 @@ static void rcu_process_callbacks(struct rcu_ctrlblk *rcp) local_irq_restore(flags); /* Invoke the callbacks on the local list. */ + RCU_TRACE(rn = rcp->name); while (list) { next = list->next; prefetch(next); debug_rcu_head_unqueue(list); local_bh_disable(); - __rcu_reclaim(list); + __rcu_reclaim(rn, list); local_bh_enable(); list = next; RCU_TRACE(cb_count++); } RCU_TRACE(rcu_trace_sub_qlen(rcp, cb_count)); + RCU_TRACE(trace_rcu_batch_end(rcp->name, cb_count)); } -/* - * This kthread invokes RCU callbacks whose grace periods have - * elapsed. It is awakened as needed, and takes the place of the - * RCU_SOFTIRQ that was used previously for this purpose. - * This is a kthread, but it is never stopped, at least not until - * the system goes down. - */ -static int rcu_kthread(void *arg) +static void rcu_process_callbacks(struct softirq_action *unused) { - unsigned long work; - unsigned long morework; - unsigned long flags; - - for (;;) { - wait_event_interruptible(rcu_kthread_wq, - have_rcu_kthread_work != 0); - morework = rcu_boost(); - local_irq_save(flags); - work = have_rcu_kthread_work; - have_rcu_kthread_work = morework; - local_irq_restore(flags); - if (work) { - rcu_process_callbacks(&rcu_sched_ctrlblk); - rcu_process_callbacks(&rcu_bh_ctrlblk); - rcu_preempt_process_callbacks(); - } - schedule_timeout_interruptible(1); /* Leave CPU for others. */ - } - - return 0; /* Not reached, but needed to shut gcc up. */ + __rcu_process_callbacks(&rcu_sched_ctrlblk); + __rcu_process_callbacks(&rcu_bh_ctrlblk); + rcu_preempt_process_callbacks(); } /* @@ -280,45 +253,3 @@ void call_rcu_bh(struct rcu_head *head, void (*func)(struct rcu_head *rcu)) __call_rcu(head, func, &rcu_bh_ctrlblk); } EXPORT_SYMBOL_GPL(call_rcu_bh); - -void rcu_barrier_bh(void) -{ - struct rcu_synchronize rcu; - - init_rcu_head_on_stack(&rcu.head); - init_completion(&rcu.completion); - /* Will wake me after RCU finished. */ - call_rcu_bh(&rcu.head, wakeme_after_rcu); - /* Wait for it. */ - wait_for_completion(&rcu.completion); - destroy_rcu_head_on_stack(&rcu.head); -} -EXPORT_SYMBOL_GPL(rcu_barrier_bh); - -void rcu_barrier_sched(void) -{ - struct rcu_synchronize rcu; - - init_rcu_head_on_stack(&rcu.head); - init_completion(&rcu.completion); - /* Will wake me after RCU finished. */ - call_rcu_sched(&rcu.head, wakeme_after_rcu); - /* Wait for it. */ - wait_for_completion(&rcu.completion); - destroy_rcu_head_on_stack(&rcu.head); -} -EXPORT_SYMBOL_GPL(rcu_barrier_sched); - -/* - * Spawn the kthread that invokes RCU callbacks. - */ -static int __init rcu_spawn_kthreads(void) -{ - struct sched_param sp; - - rcu_kthread_task = kthread_run(rcu_kthread, NULL, "rcu_kthread"); - sp.sched_priority = RCU_BOOST_PRIO; - sched_setscheduler_nocheck(rcu_kthread_task, SCHED_FIFO, &sp); - return 0; -} -early_initcall(rcu_spawn_kthreads); diff --git a/kernel/rcutiny_plugin.h b/kernel/rcutiny_plugin.h index f259c67..02aa713 100644 --- a/kernel/rcutiny_plugin.h +++ b/kernel/rcutiny_plugin.h @@ -26,29 +26,26 @@ #include <linux/debugfs.h> #include <linux/seq_file.h> -#ifdef CONFIG_RCU_TRACE -#define RCU_TRACE(stmt) stmt -#else /* #ifdef CONFIG_RCU_TRACE */ -#define RCU_TRACE(stmt) -#endif /* #else #ifdef CONFIG_RCU_TRACE */ - /* Global control variables for rcupdate callback mechanism. */ struct rcu_ctrlblk { struct rcu_head *rcucblist; /* List of pending callbacks (CBs). */ struct rcu_head **donetail; /* ->next pointer of last "done" CB. */ struct rcu_head **curtail; /* ->next pointer of last CB. */ RCU_TRACE(long qlen); /* Number of pending CBs. */ + RCU_TRACE(char *name); /* Name of RCU type. */ }; /* Definition for rcupdate control block. */ static struct rcu_ctrlblk rcu_sched_ctrlblk = { .donetail = &rcu_sched_ctrlblk.rcucblist, .curtail = &rcu_sched_ctrlblk.rcucblist, + RCU_TRACE(.name = "rcu_sched") }; static struct rcu_ctrlblk rcu_bh_ctrlblk = { .donetail = &rcu_bh_ctrlblk.rcucblist, .curtail = &rcu_bh_ctrlblk.rcucblist, + RCU_TRACE(.name = "rcu_bh") }; #ifdef CONFIG_DEBUG_LOCK_ALLOC @@ -131,6 +128,7 @@ static struct rcu_preempt_ctrlblk rcu_preempt_ctrlblk = { .rcb.curtail = &rcu_preempt_ctrlblk.rcb.rcucblist, .nexttail = &rcu_preempt_ctrlblk.rcb.rcucblist, .blkd_tasks = LIST_HEAD_INIT(rcu_preempt_ctrlblk.blkd_tasks), + RCU_TRACE(.rcb.name = "rcu_preempt") }; static int rcu_preempted_readers_exp(void); @@ -247,6 +245,13 @@ static void show_tiny_preempt_stats(struct seq_file *m) #include "rtmutex_common.h" +#define RCU_BOOST_PRIO CONFIG_RCU_BOOST_PRIO + +/* Controls for rcu_kthread() kthread. */ +static struct task_struct *rcu_kthread_task; +static DECLARE_WAIT_QUEUE_HEAD(rcu_kthread_wq); +static unsigned long have_rcu_kthread_work; + /* * Carry out RCU priority boosting on the task indicated by ->boost_tasks, * and advance ->boost_tasks to the next task in the ->blkd_tasks list. @@ -334,7 +339,7 @@ static int rcu_initiate_boost(void) if (rcu_preempt_ctrlblk.exp_tasks == NULL) rcu_preempt_ctrlblk.boost_tasks = rcu_preempt_ctrlblk.gp_tasks; - invoke_rcu_kthread(); + invoke_rcu_callbacks(); } else RCU_TRACE(rcu_initiate_boost_trace()); return 1; @@ -353,14 +358,6 @@ static void rcu_preempt_boost_start_gp(void) #else /* #ifdef CONFIG_RCU_BOOST */ /* - * If there is no RCU priority boosting, we don't boost. - */ -static int rcu_boost(void) -{ - return 0; -} - -/* * If there is no RCU priority boosting, we don't initiate boosting, * but we do indicate whether there are blocked readers blocking the * current grace period. @@ -427,7 +424,7 @@ static void rcu_preempt_cpu_qs(void) /* If there are done callbacks, cause them to be invoked. */ if (*rcu_preempt_ctrlblk.rcb.donetail != NULL) - invoke_rcu_kthread(); + invoke_rcu_callbacks(); } /* @@ -648,7 +645,7 @@ static void rcu_preempt_check_callbacks(void) rcu_preempt_cpu_qs(); if (&rcu_preempt_ctrlblk.rcb.rcucblist != rcu_preempt_ctrlblk.rcb.donetail) - invoke_rcu_kthread(); + invoke_rcu_callbacks(); if (rcu_preempt_gp_in_progress() && rcu_cpu_blocking_cur_gp() && rcu_preempt_running_reader()) @@ -674,7 +671,7 @@ static void rcu_preempt_remove_callbacks(struct rcu_ctrlblk *rcp) */ static void rcu_preempt_process_callbacks(void) { - rcu_process_callbacks(&rcu_preempt_ctrlblk.rcb); + __rcu_process_callbacks(&rcu_preempt_ctrlblk.rcb); } /* @@ -697,20 +694,6 @@ void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu)) } EXPORT_SYMBOL_GPL(call_rcu); -void rcu_barrier(void) -{ - struct rcu_synchronize rcu; - - init_rcu_head_on_stack(&rcu.head); - init_completion(&rcu.completion); - /* Will wake me after RCU finished. */ - call_rcu(&rcu.head, wakeme_after_rcu); - /* Wait for it. */ - wait_for_completion(&rcu.completion); - destroy_rcu_head_on_stack(&rcu.head); -} -EXPORT_SYMBOL_GPL(rcu_barrier); - /* * synchronize_rcu - wait until a grace period has elapsed. * @@ -864,15 +847,6 @@ static void show_tiny_preempt_stats(struct seq_file *m) #endif /* #ifdef CONFIG_RCU_TRACE */ /* - * Because preemptible RCU does not exist, it is never necessary to - * boost preempted RCU readers. - */ -static int rcu_boost(void) -{ - return 0; -} - -/* * Because preemptible RCU does not exist, it never has any callbacks * to check. */ @@ -898,6 +872,78 @@ static void rcu_preempt_process_callbacks(void) #endif /* #else #ifdef CONFIG_TINY_PREEMPT_RCU */ +#ifdef CONFIG_RCU_BOOST + +/* + * Wake up rcu_kthread() to process callbacks now eligible for invocation + * or to boost readers. + */ +static void invoke_rcu_callbacks(void) +{ + have_rcu_kthread_work = 1; + wake_up(&rcu_kthread_wq); +} + +/* + * This kthread invokes RCU callbacks whose grace periods have + * elapsed. It is awakened as needed, and takes the place of the + * RCU_SOFTIRQ that is used for this purpose when boosting is disabled. + * This is a kthread, but it is never stopped, at least not until + * the system goes down. + */ +static int rcu_kthread(void *arg) +{ + unsigned long work; + unsigned long morework; + unsigned long flags; + + for (;;) { + wait_event_interruptible(rcu_kthread_wq, + have_rcu_kthread_work != 0); + morework = rcu_boost(); + local_irq_save(flags); + work = have_rcu_kthread_work; + have_rcu_kthread_work = morework; + local_irq_restore(flags); + if (work) + rcu_process_callbacks(NULL); + schedule_timeout_interruptible(1); /* Leave CPU for others. */ + } + + return 0; /* Not reached, but needed to shut gcc up. */ +} + +/* + * Spawn the kthread that invokes RCU callbacks. + */ +static int __init rcu_spawn_kthreads(void) +{ + struct sched_param sp; + + rcu_kthread_task = kthread_run(rcu_kthread, NULL, "rcu_kthread"); + sp.sched_priority = RCU_BOOST_PRIO; + sched_setscheduler_nocheck(rcu_kthread_task, SCHED_FIFO, &sp); + return 0; +} +early_initcall(rcu_spawn_kthreads); + +#else /* #ifdef CONFIG_RCU_BOOST */ + +/* + * Start up softirq processing of callbacks. + */ +void invoke_rcu_callbacks(void) +{ + raise_softirq(RCU_SOFTIRQ); +} + +void rcu_init(void) +{ + open_softirq(RCU_SOFTIRQ, rcu_process_callbacks); +} + +#endif /* #else #ifdef CONFIG_RCU_BOOST */ + #ifdef CONFIG_DEBUG_LOCK_ALLOC #include <linux/kernel_stat.h> @@ -913,12 +959,6 @@ void __init rcu_scheduler_starting(void) #endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ -#ifdef CONFIG_RCU_BOOST -#define RCU_BOOST_PRIO CONFIG_RCU_BOOST_PRIO -#else /* #ifdef CONFIG_RCU_BOOST */ -#define RCU_BOOST_PRIO 1 -#endif /* #else #ifdef CONFIG_RCU_BOOST */ - #ifdef CONFIG_RCU_TRACE #ifdef CONFIG_RCU_BOOST diff --git a/kernel/rcutorture.c b/kernel/rcutorture.c index 98f51b1..764825c2 100644 --- a/kernel/rcutorture.c +++ b/kernel/rcutorture.c @@ -73,7 +73,7 @@ module_param(nreaders, int, 0444); MODULE_PARM_DESC(nreaders, "Number of RCU reader threads"); module_param(nfakewriters, int, 0444); MODULE_PARM_DESC(nfakewriters, "Number of RCU fake writer threads"); -module_param(stat_interval, int, 0444); +module_param(stat_interval, int, 0644); MODULE_PARM_DESC(stat_interval, "Number of seconds between stats printk()s"); module_param(verbose, bool, 0444); MODULE_PARM_DESC(verbose, "Enable verbose debugging printk()s"); @@ -480,30 +480,6 @@ static void rcu_bh_torture_deferred_free(struct rcu_torture *p) call_rcu_bh(&p->rtort_rcu, rcu_torture_cb); } -struct rcu_bh_torture_synchronize { - struct rcu_head head; - struct completion completion; -}; - -static void rcu_bh_torture_wakeme_after_cb(struct rcu_head *head) -{ - struct rcu_bh_torture_synchronize *rcu; - - rcu = container_of(head, struct rcu_bh_torture_synchronize, head); - complete(&rcu->completion); -} - -static void rcu_bh_torture_synchronize(void) -{ - struct rcu_bh_torture_synchronize rcu; - - init_rcu_head_on_stack(&rcu.head); - init_completion(&rcu.completion); - call_rcu_bh(&rcu.head, rcu_bh_torture_wakeme_after_cb); - wait_for_completion(&rcu.completion); - destroy_rcu_head_on_stack(&rcu.head); -} - static struct rcu_torture_ops rcu_bh_ops = { .init = NULL, .cleanup = NULL, @@ -512,7 +488,7 @@ static struct rcu_torture_ops rcu_bh_ops = { .readunlock = rcu_bh_torture_read_unlock, .completed = rcu_bh_torture_completed, .deferred_free = rcu_bh_torture_deferred_free, - .sync = rcu_bh_torture_synchronize, + .sync = synchronize_rcu_bh, .cb_barrier = rcu_barrier_bh, .fqs = rcu_bh_force_quiescent_state, .stats = NULL, @@ -528,7 +504,7 @@ static struct rcu_torture_ops rcu_bh_sync_ops = { .readunlock = rcu_bh_torture_read_unlock, .completed = rcu_bh_torture_completed, .deferred_free = rcu_sync_torture_deferred_free, - .sync = rcu_bh_torture_synchronize, + .sync = synchronize_rcu_bh, .cb_barrier = NULL, .fqs = rcu_bh_force_quiescent_state, .stats = NULL, @@ -536,6 +512,22 @@ static struct rcu_torture_ops rcu_bh_sync_ops = { .name = "rcu_bh_sync" }; +static struct rcu_torture_ops rcu_bh_expedited_ops = { + .init = rcu_sync_torture_init, + .cleanup = NULL, + .readlock = rcu_bh_torture_read_lock, + .read_delay = rcu_read_delay, /* just reuse rcu's version. */ + .readunlock = rcu_bh_torture_read_unlock, + .completed = rcu_bh_torture_completed, + .deferred_free = rcu_sync_torture_deferred_free, + .sync = synchronize_rcu_bh_expedited, + .cb_barrier = NULL, + .fqs = rcu_bh_force_quiescent_state, + .stats = NULL, + .irq_capable = 1, + .name = "rcu_bh_expedited" +}; + /* * Definitions for srcu torture testing. */ @@ -659,11 +651,6 @@ static void rcu_sched_torture_deferred_free(struct rcu_torture *p) call_rcu_sched(&p->rtort_rcu, rcu_torture_cb); } -static void sched_torture_synchronize(void) -{ - synchronize_sched(); -} - static struct rcu_torture_ops sched_ops = { .init = rcu_sync_torture_init, .cleanup = NULL, @@ -672,7 +659,7 @@ static struct rcu_torture_ops sched_ops = { .readunlock = sched_torture_read_unlock, .completed = rcu_no_completed, .deferred_free = rcu_sched_torture_deferred_free, - .sync = sched_torture_synchronize, + .sync = synchronize_sched, .cb_barrier = rcu_barrier_sched, .fqs = rcu_sched_force_quiescent_state, .stats = NULL, @@ -688,7 +675,7 @@ static struct rcu_torture_ops sched_sync_ops = { .readunlock = sched_torture_read_unlock, .completed = rcu_no_completed, .deferred_free = rcu_sync_torture_deferred_free, - .sync = sched_torture_synchronize, + .sync = synchronize_sched, .cb_barrier = NULL, .fqs = rcu_sched_force_quiescent_state, .stats = NULL, @@ -754,7 +741,7 @@ static int rcu_torture_boost(void *arg) do { /* Wait for the next test interval. */ oldstarttime = boost_starttime; - while (jiffies - oldstarttime > ULONG_MAX / 2) { + while (ULONG_CMP_LT(jiffies, oldstarttime)) { schedule_timeout_uninterruptible(1); rcu_stutter_wait("rcu_torture_boost"); if (kthread_should_stop() || @@ -765,7 +752,7 @@ static int rcu_torture_boost(void *arg) /* Do one boost-test interval. */ endtime = oldstarttime + test_boost_duration * HZ; call_rcu_time = jiffies; - while (jiffies - endtime > ULONG_MAX / 2) { + while (ULONG_CMP_LT(jiffies, endtime)) { /* If we don't have a callback in flight, post one. */ if (!rbi.inflight) { smp_mb(); /* RCU core before ->inflight = 1. */ @@ -792,7 +779,8 @@ static int rcu_torture_boost(void *arg) * interval. Besides, we are running at RT priority, * so delays should be relatively rare. */ - while (oldstarttime == boost_starttime) { + while (oldstarttime == boost_starttime && + !kthread_should_stop()) { if (mutex_trylock(&boost_mutex)) { boost_starttime = jiffies + test_boost_interval * HZ; @@ -809,11 +797,11 @@ checkwait: rcu_stutter_wait("rcu_torture_boost"); /* Clean up and exit. */ VERBOSE_PRINTK_STRING("rcu_torture_boost task stopping"); - destroy_rcu_head_on_stack(&rbi.rcu); rcutorture_shutdown_absorb("rcu_torture_boost"); while (!kthread_should_stop() || rbi.inflight) schedule_timeout_uninterruptible(1); smp_mb(); /* order accesses to ->inflight before stack-frame death. */ + destroy_rcu_head_on_stack(&rbi.rcu); return 0; } @@ -831,11 +819,13 @@ rcu_torture_fqs(void *arg) VERBOSE_PRINTK_STRING("rcu_torture_fqs task started"); do { fqs_resume_time = jiffies + fqs_stutter * HZ; - while (jiffies - fqs_resume_time > LONG_MAX) { + while (ULONG_CMP_LT(jiffies, fqs_resume_time) && + !kthread_should_stop()) { schedule_timeout_interruptible(1); } fqs_burst_remaining = fqs_duration; - while (fqs_burst_remaining > 0) { + while (fqs_burst_remaining > 0 && + !kthread_should_stop()) { cur_ops->fqs(); udelay(fqs_holdoff); fqs_burst_remaining -= fqs_holdoff; @@ -1280,8 +1270,9 @@ static int rcutorture_booster_init(int cpu) /* Don't allow time recalculation while creating a new task. */ mutex_lock(&boost_mutex); VERBOSE_PRINTK_STRING("Creating rcu_torture_boost task"); - boost_tasks[cpu] = kthread_create(rcu_torture_boost, NULL, - "rcu_torture_boost"); + boost_tasks[cpu] = kthread_create_on_node(rcu_torture_boost, NULL, + cpu_to_node(cpu), + "rcu_torture_boost"); if (IS_ERR(boost_tasks[cpu])) { retval = PTR_ERR(boost_tasks[cpu]); VERBOSE_PRINTK_STRING("rcu_torture_boost task create failed"); @@ -1424,7 +1415,7 @@ rcu_torture_init(void) int firsterr = 0; static struct rcu_torture_ops *torture_ops[] = { &rcu_ops, &rcu_sync_ops, &rcu_expedited_ops, - &rcu_bh_ops, &rcu_bh_sync_ops, + &rcu_bh_ops, &rcu_bh_sync_ops, &rcu_bh_expedited_ops, &srcu_ops, &srcu_expedited_ops, &sched_ops, &sched_sync_ops, &sched_expedited_ops, }; diff --git a/kernel/rcutree.c b/kernel/rcutree.c index ba06207..e234eb9 100644 --- a/kernel/rcutree.c +++ b/kernel/rcutree.c @@ -52,13 +52,16 @@ #include <linux/prefetch.h> #include "rcutree.h" +#include <trace/events/rcu.h> + +#include "rcu.h" /* Data structures. */ static struct lock_class_key rcu_node_class[NUM_RCU_LVLS]; #define RCU_STATE_INITIALIZER(structname) { \ - .level = { &structname.node[0] }, \ + .level = { &structname##_state.node[0] }, \ .levelcnt = { \ NUM_RCU_LVL_0, /* root of hierarchy. */ \ NUM_RCU_LVL_1, \ @@ -69,17 +72,17 @@ static struct lock_class_key rcu_node_class[NUM_RCU_LVLS]; .signaled = RCU_GP_IDLE, \ .gpnum = -300, \ .completed = -300, \ - .onofflock = __RAW_SPIN_LOCK_UNLOCKED(&structname.onofflock), \ - .fqslock = __RAW_SPIN_LOCK_UNLOCKED(&structname.fqslock), \ + .onofflock = __RAW_SPIN_LOCK_UNLOCKED(&structname##_state.onofflock), \ + .fqslock = __RAW_SPIN_LOCK_UNLOCKED(&structname##_state.fqslock), \ .n_force_qs = 0, \ .n_force_qs_ngp = 0, \ .name = #structname, \ } -struct rcu_state rcu_sched_state = RCU_STATE_INITIALIZER(rcu_sched_state); +struct rcu_state rcu_sched_state = RCU_STATE_INITIALIZER(rcu_sched); DEFINE_PER_CPU(struct rcu_data, rcu_sched_data); -struct rcu_state rcu_bh_state = RCU_STATE_INITIALIZER(rcu_bh_state); +struct rcu_state rcu_bh_state = RCU_STATE_INITIALIZER(rcu_bh); DEFINE_PER_CPU(struct rcu_data, rcu_bh_data); static struct rcu_state *rcu_state; @@ -128,8 +131,6 @@ static void rcu_node_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu); static void invoke_rcu_core(void); static void invoke_rcu_callbacks(struct rcu_state *rsp, struct rcu_data *rdp); -#define RCU_KTHREAD_PRIO 1 /* RT priority for per-CPU kthreads. */ - /* * Track the rcutorture test sequence number and the update version * number within a given test. The rcutorture_testseq is incremented @@ -156,33 +157,41 @@ static int rcu_gp_in_progress(struct rcu_state *rsp) * Note a quiescent state. Because we do not need to know * how many quiescent states passed, just if there was at least * one since the start of the grace period, this just sets a flag. + * The caller must have disabled preemption. */ void rcu_sched_qs(int cpu) { struct rcu_data *rdp = &per_cpu(rcu_sched_data, cpu); - rdp->passed_quiesc_completed = rdp->gpnum - 1; + rdp->passed_quiesce_gpnum = rdp->gpnum; barrier(); - rdp->passed_quiesc = 1; + if (rdp->passed_quiesce == 0) + trace_rcu_grace_period("rcu_sched", rdp->gpnum, "cpuqs"); + rdp->passed_quiesce = 1; } void rcu_bh_qs(int cpu) { struct rcu_data *rdp = &per_cpu(rcu_bh_data, cpu); - rdp->passed_quiesc_completed = rdp->gpnum - 1; + rdp->passed_quiesce_gpnum = rdp->gpnum; barrier(); - rdp->passed_quiesc = 1; + if (rdp->passed_quiesce == 0) + trace_rcu_grace_period("rcu_bh", rdp->gpnum, "cpuqs"); + rdp->passed_quiesce = 1; } /* * Note a context switch. This is a quiescent state for RCU-sched, * and requires special handling for preemptible RCU. + * The caller must have disabled preemption. */ void rcu_note_context_switch(int cpu) { + trace_rcu_utilization("Start context switch"); rcu_sched_qs(cpu); rcu_preempt_note_context_switch(cpu); + trace_rcu_utilization("End context switch"); } EXPORT_SYMBOL_GPL(rcu_note_context_switch); @@ -193,7 +202,7 @@ DEFINE_PER_CPU(struct rcu_dynticks, rcu_dynticks) = { }; #endif /* #ifdef CONFIG_NO_HZ */ -static int blimit = 10; /* Maximum callbacks per softirq. */ +static int blimit = 10; /* Maximum callbacks per rcu_do_batch. */ static int qhimark = 10000; /* If this many pending, ignore blimit. */ static int qlowmark = 100; /* Once only this many pending, use blimit. */ @@ -314,6 +323,7 @@ static int rcu_implicit_offline_qs(struct rcu_data *rdp) * trust its state not to change because interrupts are disabled. */ if (cpu_is_offline(rdp->cpu)) { + trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, "ofl"); rdp->offline_fqs++; return 1; } @@ -354,19 +364,13 @@ void rcu_enter_nohz(void) local_irq_restore(flags); return; } + trace_rcu_dyntick("Start"); /* CPUs seeing atomic_inc() must see prior RCU read-side crit sects */ smp_mb__before_atomic_inc(); /* See above. */ atomic_inc(&rdtp->dynticks); smp_mb__after_atomic_inc(); /* Force ordering with next sojourn. */ WARN_ON_ONCE(atomic_read(&rdtp->dynticks) & 0x1); local_irq_restore(flags); - - /* If the interrupt queued a callback, get out of dyntick mode. */ - if (in_irq() && - (__get_cpu_var(rcu_sched_data).nxtlist || - __get_cpu_var(rcu_bh_data).nxtlist || - rcu_preempt_needs_cpu(smp_processor_id()))) - set_need_resched(); } /* @@ -391,6 +395,7 @@ void rcu_exit_nohz(void) /* CPUs seeing atomic_inc() must see later RCU read-side crit sects */ smp_mb__after_atomic_inc(); /* See above. */ WARN_ON_ONCE(!(atomic_read(&rdtp->dynticks) & 0x1)); + trace_rcu_dyntick("End"); local_irq_restore(flags); } @@ -481,11 +486,11 @@ static int dyntick_save_progress_counter(struct rcu_data *rdp) */ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp) { - unsigned long curr; - unsigned long snap; + unsigned int curr; + unsigned int snap; - curr = (unsigned long)atomic_add_return(0, &rdp->dynticks->dynticks); - snap = (unsigned long)rdp->dynticks_snap; + curr = (unsigned int)atomic_add_return(0, &rdp->dynticks->dynticks); + snap = (unsigned int)rdp->dynticks_snap; /* * If the CPU passed through or entered a dynticks idle phase with @@ -495,7 +500,8 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp) * read-side critical section that started before the beginning * of the current RCU grace period. */ - if ((curr & 0x1) == 0 || ULONG_CMP_GE(curr, snap + 2)) { + if ((curr & 0x1) == 0 || UINT_CMP_GE(curr, snap + 2)) { + trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, "dti"); rdp->dynticks_fqs++; return 1; } @@ -537,6 +543,7 @@ static void print_other_cpu_stall(struct rcu_state *rsp) int cpu; long delta; unsigned long flags; + int ndetected; struct rcu_node *rnp = rcu_get_root(rsp); /* Only let one CPU complain about others per time interval. */ @@ -553,7 +560,7 @@ static void print_other_cpu_stall(struct rcu_state *rsp) * Now rat on any tasks that got kicked up to the root rcu_node * due to CPU offlining. */ - rcu_print_task_stall(rnp); + ndetected = rcu_print_task_stall(rnp); raw_spin_unlock_irqrestore(&rnp->lock, flags); /* @@ -565,17 +572,22 @@ static void print_other_cpu_stall(struct rcu_state *rsp) rsp->name); rcu_for_each_leaf_node(rsp, rnp) { raw_spin_lock_irqsave(&rnp->lock, flags); - rcu_print_task_stall(rnp); + ndetected += rcu_print_task_stall(rnp); raw_spin_unlock_irqrestore(&rnp->lock, flags); if (rnp->qsmask == 0) continue; for (cpu = 0; cpu <= rnp->grphi - rnp->grplo; cpu++) - if (rnp->qsmask & (1UL << cpu)) + if (rnp->qsmask & (1UL << cpu)) { printk(" %d", rnp->grplo + cpu); + ndetected++; + } } printk("} (detected by %d, t=%ld jiffies)\n", smp_processor_id(), (long)(jiffies - rsp->gp_start)); - trigger_all_cpu_backtrace(); + if (ndetected == 0) + printk(KERN_ERR "INFO: Stall ended before state dump start\n"); + else if (!trigger_all_cpu_backtrace()) + dump_stack(); /* If so configured, complain about tasks blocking the grace period. */ @@ -596,7 +608,8 @@ static void print_cpu_stall(struct rcu_state *rsp) */ printk(KERN_ERR "INFO: %s detected stall on CPU %d (t=%lu jiffies)\n", rsp->name, smp_processor_id(), jiffies - rsp->gp_start); - trigger_all_cpu_backtrace(); + if (!trigger_all_cpu_backtrace()) + dump_stack(); raw_spin_lock_irqsave(&rnp->lock, flags); if (ULONG_CMP_GE(jiffies, rsp->jiffies_stall)) @@ -678,9 +691,10 @@ static void __note_new_gpnum(struct rcu_state *rsp, struct rcu_node *rnp, struct * go looking for one. */ rdp->gpnum = rnp->gpnum; + trace_rcu_grace_period(rsp->name, rdp->gpnum, "cpustart"); if (rnp->qsmask & rdp->grpmask) { rdp->qs_pending = 1; - rdp->passed_quiesc = 0; + rdp->passed_quiesce = 0; } else rdp->qs_pending = 0; } @@ -741,6 +755,7 @@ __rcu_process_gp_end(struct rcu_state *rsp, struct rcu_node *rnp, struct rcu_dat /* Remember that we saw this grace-period completion. */ rdp->completed = rnp->completed; + trace_rcu_grace_period(rsp->name, rdp->gpnum, "cpuend"); /* * If we were in an extended quiescent state, we may have @@ -826,31 +841,31 @@ rcu_start_gp(struct rcu_state *rsp, unsigned long flags) struct rcu_data *rdp = this_cpu_ptr(rsp->rda); struct rcu_node *rnp = rcu_get_root(rsp); - if (!cpu_needs_another_gp(rsp, rdp) || rsp->fqs_active) { - if (cpu_needs_another_gp(rsp, rdp)) - rsp->fqs_need_gp = 1; - if (rnp->completed == rsp->completed) { - raw_spin_unlock_irqrestore(&rnp->lock, flags); - return; - } - raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */ + if (!rcu_scheduler_fully_active || + !cpu_needs_another_gp(rsp, rdp)) { + /* + * Either the scheduler hasn't yet spawned the first + * non-idle task or this CPU does not need another + * grace period. Either way, don't start a new grace + * period. + */ + raw_spin_unlock_irqrestore(&rnp->lock, flags); + return; + } + if (rsp->fqs_active) { /* - * Propagate new ->completed value to rcu_node structures - * so that other CPUs don't have to wait until the start - * of the next grace period to process their callbacks. + * This CPU needs a grace period, but force_quiescent_state() + * is running. Tell it to start one on this CPU's behalf. */ - rcu_for_each_node_breadth_first(rsp, rnp) { - raw_spin_lock(&rnp->lock); /* irqs already disabled. */ - rnp->completed = rsp->completed; - raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */ - } - local_irq_restore(flags); + rsp->fqs_need_gp = 1; + raw_spin_unlock_irqrestore(&rnp->lock, flags); return; } /* Advance to a new grace period and initialize state. */ rsp->gpnum++; + trace_rcu_grace_period(rsp->name, rsp->gpnum, "start"); WARN_ON_ONCE(rsp->signaled == RCU_GP_INIT); rsp->signaled = RCU_GP_INIT; /* Hold off force_quiescent_state. */ rsp->jiffies_force_qs = jiffies + RCU_JIFFIES_TILL_FORCE_QS; @@ -865,6 +880,9 @@ rcu_start_gp(struct rcu_state *rsp, unsigned long flags) rsp->signaled = RCU_SIGNAL_INIT; /* force_quiescent_state OK. */ rcu_start_gp_per_cpu(rsp, rnp, rdp); rcu_preempt_boost_start_gp(rnp); + trace_rcu_grace_period_init(rsp->name, rnp->gpnum, + rnp->level, rnp->grplo, + rnp->grphi, rnp->qsmask); raw_spin_unlock_irqrestore(&rnp->lock, flags); return; } @@ -901,6 +919,9 @@ rcu_start_gp(struct rcu_state *rsp, unsigned long flags) if (rnp == rdp->mynode) rcu_start_gp_per_cpu(rsp, rnp, rdp); rcu_preempt_boost_start_gp(rnp); + trace_rcu_grace_period_init(rsp->name, rnp->gpnum, + rnp->level, rnp->grplo, + rnp->grphi, rnp->qsmask); raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */ } @@ -922,6 +943,8 @@ static void rcu_report_qs_rsp(struct rcu_state *rsp, unsigned long flags) __releases(rcu_get_root(rsp)->lock) { unsigned long gp_duration; + struct rcu_node *rnp = rcu_get_root(rsp); + struct rcu_data *rdp = this_cpu_ptr(rsp->rda); WARN_ON_ONCE(!rcu_gp_in_progress(rsp)); @@ -933,7 +956,41 @@ static void rcu_report_qs_rsp(struct rcu_state *rsp, unsigned long flags) gp_duration = jiffies - rsp->gp_start; if (gp_duration > rsp->gp_max) rsp->gp_max = gp_duration; - rsp->completed = rsp->gpnum; + + /* + * We know the grace period is complete, but to everyone else + * it appears to still be ongoing. But it is also the case + * that to everyone else it looks like there is nothing that + * they can do to advance the grace period. It is therefore + * safe for us to drop the lock in order to mark the grace + * period as completed in all of the rcu_node structures. + * + * But if this CPU needs another grace period, it will take + * care of this while initializing the next grace period. + * We use RCU_WAIT_TAIL instead of the usual RCU_DONE_TAIL + * because the callbacks have not yet been advanced: Those + * callbacks are waiting on the grace period that just now + * completed. + */ + if (*rdp->nxttail[RCU_WAIT_TAIL] == NULL) { + raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */ + + /* + * Propagate new ->completed value to rcu_node structures + * so that other CPUs don't have to wait until the start + * of the next grace period to process their callbacks. + */ + rcu_for_each_node_breadth_first(rsp, rnp) { + raw_spin_lock(&rnp->lock); /* irqs already disabled. */ + rnp->completed = rsp->gpnum; + raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */ + } + rnp = rcu_get_root(rsp); + raw_spin_lock(&rnp->lock); /* irqs already disabled. */ + } + + rsp->completed = rsp->gpnum; /* Declare the grace period complete. */ + trace_rcu_grace_period(rsp->name, rsp->completed, "end"); rsp->signaled = RCU_GP_IDLE; rcu_start_gp(rsp, flags); /* releases root node's rnp->lock. */ } @@ -962,6 +1019,10 @@ rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp, return; } rnp->qsmask &= ~mask; + trace_rcu_quiescent_state_report(rsp->name, rnp->gpnum, + mask, rnp->qsmask, rnp->level, + rnp->grplo, rnp->grphi, + !!rnp->gp_tasks); if (rnp->qsmask != 0 || rcu_preempt_blocked_readers_cgp(rnp)) { /* Other bits still set at this level, so done. */ @@ -1000,7 +1061,7 @@ rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp, * based on quiescent states detected in an earlier grace period! */ static void -rcu_report_qs_rdp(int cpu, struct rcu_state *rsp, struct rcu_data *rdp, long lastcomp) +rcu_report_qs_rdp(int cpu, struct rcu_state *rsp, struct rcu_data *rdp, long lastgp) { unsigned long flags; unsigned long mask; @@ -1008,17 +1069,15 @@ rcu_report_qs_rdp(int cpu, struct rcu_state *rsp, struct rcu_data *rdp, long las rnp = rdp->mynode; raw_spin_lock_irqsave(&rnp->lock, flags); - if (lastcomp != rnp->completed) { + if (lastgp != rnp->gpnum || rnp->completed == rnp->gpnum) { /* - * Someone beat us to it for this grace period, so leave. - * The race with GP start is resolved by the fact that we - * hold the leaf rcu_node lock, so that the per-CPU bits - * cannot yet be initialized -- so we would simply find our - * CPU's bit already cleared in rcu_report_qs_rnp() if this - * race occurred. + * The grace period in which this quiescent state was + * recorded has ended, so don't report it upwards. + * We will instead need a new quiescent state that lies + * within the current grace period. */ - rdp->passed_quiesc = 0; /* try again later! */ + rdp->passed_quiesce = 0; /* need qs for new gp. */ raw_spin_unlock_irqrestore(&rnp->lock, flags); return; } @@ -1062,14 +1121,14 @@ rcu_check_quiescent_state(struct rcu_state *rsp, struct rcu_data *rdp) * Was there a quiescent state since the beginning of the grace * period? If no, then exit and wait for the next call. */ - if (!rdp->passed_quiesc) + if (!rdp->passed_quiesce) return; /* * Tell RCU we are done (but rcu_report_qs_rdp() will be the * judge of that). */ - rcu_report_qs_rdp(rdp->cpu, rsp, rdp, rdp->passed_quiesc_completed); + rcu_report_qs_rdp(rdp->cpu, rsp, rdp, rdp->passed_quiesce_gpnum); } #ifdef CONFIG_HOTPLUG_CPU @@ -1130,11 +1189,20 @@ static void __rcu_offline_cpu(int cpu, struct rcu_state *rsp) if (rnp->qsmaskinit != 0) { if (rnp != rdp->mynode) raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */ + else + trace_rcu_grace_period(rsp->name, + rnp->gpnum + 1 - + !!(rnp->qsmask & mask), + "cpuofl"); break; } - if (rnp == rdp->mynode) + if (rnp == rdp->mynode) { + trace_rcu_grace_period(rsp->name, + rnp->gpnum + 1 - + !!(rnp->qsmask & mask), + "cpuofl"); need_report = rcu_preempt_offline_tasks(rsp, rnp, rdp); - else + } else raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */ mask = rnp->grpmask; rnp = rnp->parent; @@ -1190,17 +1258,22 @@ static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp) { unsigned long flags; struct rcu_head *next, *list, **tail; - int count; + int bl, count; /* If no callbacks are ready, just return.*/ - if (!cpu_has_callbacks_ready_to_invoke(rdp)) + if (!cpu_has_callbacks_ready_to_invoke(rdp)) { + trace_rcu_batch_start(rsp->name, 0, 0); + trace_rcu_batch_end(rsp->name, 0); return; + } /* * Extract the list of ready callbacks, disabling to prevent * races with call_rcu() from interrupt handlers. */ local_irq_save(flags); + bl = rdp->blimit; + trace_rcu_batch_start(rsp->name, rdp->qlen, bl); list = rdp->nxtlist; rdp->nxtlist = *rdp->nxttail[RCU_DONE_TAIL]; *rdp->nxttail[RCU_DONE_TAIL] = NULL; @@ -1216,13 +1289,14 @@ static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp) next = list->next; prefetch(next); debug_rcu_head_unqueue(list); - __rcu_reclaim(list); + __rcu_reclaim(rsp->name, list); list = next; - if (++count >= rdp->blimit) + if (++count >= bl) break; } local_irq_save(flags); + trace_rcu_batch_end(rsp->name, count); /* Update count, and requeue any remaining callbacks. */ rdp->qlen -= count; @@ -1250,7 +1324,7 @@ static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp) local_irq_restore(flags); - /* Re-raise the RCU softirq if there are callbacks remaining. */ + /* Re-invoke RCU core processing if there are callbacks remaining. */ if (cpu_has_callbacks_ready_to_invoke(rdp)) invoke_rcu_core(); } @@ -1258,7 +1332,7 @@ static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp) /* * Check to see if this CPU is in a non-context-switch quiescent state * (user mode or idle loop for rcu, non-softirq execution for rcu_bh). - * Also schedule the RCU softirq handler. + * Also schedule RCU core processing. * * This function must be called with hardirqs disabled. It is normally * invoked from the scheduling-clock interrupt. If rcu_pending returns @@ -1266,6 +1340,7 @@ static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp) */ void rcu_check_callbacks(int cpu, int user) { + trace_rcu_utilization("Start scheduler-tick"); if (user || (idle_cpu(cpu) && rcu_scheduler_active && !in_softirq() && hardirq_count() <= (1 << HARDIRQ_SHIFT))) { @@ -1299,6 +1374,7 @@ void rcu_check_callbacks(int cpu, int user) rcu_preempt_check_callbacks(cpu); if (rcu_pending(cpu)) invoke_rcu_core(); + trace_rcu_utilization("End scheduler-tick"); } #ifdef CONFIG_SMP @@ -1360,10 +1436,14 @@ static void force_quiescent_state(struct rcu_state *rsp, int relaxed) unsigned long flags; struct rcu_node *rnp = rcu_get_root(rsp); - if (!rcu_gp_in_progress(rsp)) + trace_rcu_utilization("Start fqs"); + if (!rcu_gp_in_progress(rsp)) { + trace_rcu_utilization("End fqs"); return; /* No grace period in progress, nothing to force. */ + } if (!raw_spin_trylock_irqsave(&rsp->fqslock, flags)) { rsp->n_force_qs_lh++; /* Inexact, can lose counts. Tough! */ + trace_rcu_utilization("End fqs"); return; /* Someone else is already on the job. */ } if (relaxed && ULONG_CMP_GE(rsp->jiffies_force_qs, jiffies)) @@ -1412,11 +1492,13 @@ static void force_quiescent_state(struct rcu_state *rsp, int relaxed) raw_spin_unlock(&rsp->fqslock); /* irqs remain disabled */ rsp->fqs_need_gp = 0; rcu_start_gp(rsp, flags); /* releases rnp->lock */ + trace_rcu_utilization("End fqs"); return; } raw_spin_unlock(&rnp->lock); /* irqs remain disabled */ unlock_fqs_ret: raw_spin_unlock_irqrestore(&rsp->fqslock, flags); + trace_rcu_utilization("End fqs"); } #else /* #ifdef CONFIG_SMP */ @@ -1429,9 +1511,9 @@ static void force_quiescent_state(struct rcu_state *rsp, int relaxed) #endif /* #else #ifdef CONFIG_SMP */ /* - * This does the RCU processing work from softirq context for the - * specified rcu_state and rcu_data structures. This may be called - * only from the CPU to whom the rdp belongs. + * This does the RCU core processing work for the specified rcu_state + * and rcu_data structures. This may be called only from the CPU to + * whom the rdp belongs. */ static void __rcu_process_callbacks(struct rcu_state *rsp, struct rcu_data *rdp) @@ -1468,24 +1550,24 @@ __rcu_process_callbacks(struct rcu_state *rsp, struct rcu_data *rdp) } /* - * Do softirq processing for the current CPU. + * Do RCU core processing for the current CPU. */ static void rcu_process_callbacks(struct softirq_action *unused) { + trace_rcu_utilization("Start RCU core"); __rcu_process_callbacks(&rcu_sched_state, &__get_cpu_var(rcu_sched_data)); __rcu_process_callbacks(&rcu_bh_state, &__get_cpu_var(rcu_bh_data)); rcu_preempt_process_callbacks(); - - /* If we are last CPU on way to dyntick-idle mode, accelerate it. */ - rcu_needs_cpu_flush(); + trace_rcu_utilization("End RCU core"); } /* - * Wake up the current CPU's kthread. This replaces raise_softirq() - * in earlier versions of RCU. Note that because we are running on - * the current CPU with interrupts disabled, the rcu_cpu_kthread_task - * cannot disappear out from under us. + * Schedule RCU callback invocation. If the specified type of RCU + * does not support RCU priority boosting, just do a direct call, + * otherwise wake up the per-CPU kernel kthread. Note that because we + * are running on the current CPU with interrupts disabled, the + * rcu_cpu_kthread_task cannot disappear out from under us. */ static void invoke_rcu_callbacks(struct rcu_state *rsp, struct rcu_data *rdp) { @@ -1530,6 +1612,12 @@ __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu), rdp->nxttail[RCU_NEXT_TAIL] = &head->next; rdp->qlen++; + if (__is_kfree_rcu_offset((unsigned long)func)) + trace_rcu_kfree_callback(rsp->name, head, (unsigned long)func, + rdp->qlen); + else + trace_rcu_callback(rsp->name, head, rdp->qlen); + /* If interrupts were disabled, don't dive into RCU core. */ if (irqs_disabled_flags(flags)) { local_irq_restore(flags); @@ -1613,18 +1701,9 @@ EXPORT_SYMBOL_GPL(call_rcu_bh); */ void synchronize_sched(void) { - struct rcu_synchronize rcu; - if (rcu_blocking_is_gp()) return; - - init_rcu_head_on_stack(&rcu.head); - init_completion(&rcu.completion); - /* Will wake me after RCU finished. */ - call_rcu_sched(&rcu.head, wakeme_after_rcu); - /* Wait for it. */ - wait_for_completion(&rcu.completion); - destroy_rcu_head_on_stack(&rcu.head); + wait_rcu_gp(call_rcu_sched); } EXPORT_SYMBOL_GPL(synchronize_sched); @@ -1639,18 +1718,9 @@ EXPORT_SYMBOL_GPL(synchronize_sched); */ void synchronize_rcu_bh(void) { - struct rcu_synchronize rcu; - if (rcu_blocking_is_gp()) return; - - init_rcu_head_on_stack(&rcu.head); - init_completion(&rcu.completion); - /* Will wake me after RCU finished. */ - call_rcu_bh(&rcu.head, wakeme_after_rcu); - /* Wait for it. */ - wait_for_completion(&rcu.completion); - destroy_rcu_head_on_stack(&rcu.head); + wait_rcu_gp(call_rcu_bh); } EXPORT_SYMBOL_GPL(synchronize_rcu_bh); @@ -1671,7 +1741,8 @@ static int __rcu_pending(struct rcu_state *rsp, struct rcu_data *rdp) check_cpu_stall(rsp, rdp); /* Is the RCU core waiting for a quiescent state from this CPU? */ - if (rdp->qs_pending && !rdp->passed_quiesc) { + if (rcu_scheduler_fully_active && + rdp->qs_pending && !rdp->passed_quiesce) { /* * If force_quiescent_state() coming soon and this CPU @@ -1683,7 +1754,7 @@ static int __rcu_pending(struct rcu_state *rsp, struct rcu_data *rdp) ULONG_CMP_LT(ACCESS_ONCE(rsp->jiffies_force_qs) - 1, jiffies)) set_need_resched(); - } else if (rdp->qs_pending && rdp->passed_quiesc) { + } else if (rdp->qs_pending && rdp->passed_quiesce) { rdp->n_rp_report_qs++; return 1; } @@ -1846,6 +1917,7 @@ rcu_boot_init_percpu_data(int cpu, struct rcu_state *rsp) rdp->dynticks = &per_cpu(rcu_dynticks, cpu); #endif /* #ifdef CONFIG_NO_HZ */ rdp->cpu = cpu; + rdp->rsp = rsp; raw_spin_unlock_irqrestore(&rnp->lock, flags); } @@ -1865,8 +1937,6 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp, int preemptible) /* Set up local state, ensuring consistent view of global state. */ raw_spin_lock_irqsave(&rnp->lock, flags); - rdp->passed_quiesc = 0; /* We could be racing with new GP, */ - rdp->qs_pending = 1; /* so set up to respond to current GP. */ rdp->beenonline = 1; /* We have now been online. */ rdp->preemptible = preemptible; rdp->qlen_last_fqs_check = 0; @@ -1891,9 +1961,17 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp, int preemptible) rnp->qsmaskinit |= mask; mask = rnp->grpmask; if (rnp == rdp->mynode) { - rdp->gpnum = rnp->completed; /* if GP in progress... */ + /* + * If there is a grace period in progress, we will + * set up to wait for it next time we run the + * RCU core code. + */ + rdp->gpnum = rnp->completed; rdp->completed = rnp->completed; - rdp->passed_quiesc_completed = rnp->completed - 1; + rdp->passed_quiesce = 0; + rdp->qs_pending = 0; + rdp->passed_quiesce_gpnum = rnp->gpnum - 1; + trace_rcu_grace_period(rsp->name, rdp->gpnum, "cpuonl"); } raw_spin_unlock(&rnp->lock); /* irqs already disabled. */ rnp = rnp->parent; @@ -1919,6 +1997,7 @@ static int __cpuinit rcu_cpu_notify(struct notifier_block *self, struct rcu_data *rdp = per_cpu_ptr(rcu_state->rda, cpu); struct rcu_node *rnp = rdp->mynode; + trace_rcu_utilization("Start CPU hotplug"); switch (action) { case CPU_UP_PREPARE: case CPU_UP_PREPARE_FROZEN: @@ -1954,6 +2033,7 @@ static int __cpuinit rcu_cpu_notify(struct notifier_block *self, default: break; } + trace_rcu_utilization("End CPU hotplug"); return NOTIFY_OK; } diff --git a/kernel/rcutree.h b/kernel/rcutree.h index 01b2ccd..849ce9e 100644 --- a/kernel/rcutree.h +++ b/kernel/rcutree.h @@ -230,9 +230,9 @@ struct rcu_data { /* in order to detect GP end. */ unsigned long gpnum; /* Highest gp number that this CPU */ /* is aware of having started. */ - unsigned long passed_quiesc_completed; - /* Value of completed at time of qs. */ - bool passed_quiesc; /* User-mode/idle loop etc. */ + unsigned long passed_quiesce_gpnum; + /* gpnum at time of quiescent state. */ + bool passed_quiesce; /* User-mode/idle loop etc. */ bool qs_pending; /* Core waits for quiesc state. */ bool beenonline; /* CPU online at least once. */ bool preemptible; /* Preemptible RCU? */ @@ -299,6 +299,7 @@ struct rcu_data { unsigned long n_rp_need_nothing; int cpu; + struct rcu_state *rsp; }; /* Values for signaled field in struct rcu_state. */ @@ -417,6 +418,13 @@ extern struct rcu_state rcu_preempt_state; DECLARE_PER_CPU(struct rcu_data, rcu_preempt_data); #endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */ +#ifdef CONFIG_RCU_BOOST +DECLARE_PER_CPU(unsigned int, rcu_cpu_kthread_status); +DECLARE_PER_CPU(int, rcu_cpu_kthread_cpu); +DECLARE_PER_CPU(unsigned int, rcu_cpu_kthread_loops); +DECLARE_PER_CPU(char, rcu_cpu_has_work); +#endif /* #ifdef CONFIG_RCU_BOOST */ + #ifndef RCU_TREE_NONCORE /* Forward declarations for rcutree_plugin.h */ @@ -430,7 +438,7 @@ static void rcu_report_unblock_qs_rnp(struct rcu_node *rnp, static void rcu_stop_cpu_kthread(int cpu); #endif /* #ifdef CONFIG_HOTPLUG_CPU */ static void rcu_print_detail_task_stall(struct rcu_state *rsp); -static void rcu_print_task_stall(struct rcu_node *rnp); +static int rcu_print_task_stall(struct rcu_node *rnp); static void rcu_preempt_stall_reset(void); static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp); #ifdef CONFIG_HOTPLUG_CPU @@ -450,7 +458,6 @@ static int rcu_preempt_needs_cpu(int cpu); static void __cpuinit rcu_preempt_init_percpu_data(int cpu); static void rcu_preempt_send_cbs_to_online(void); static void __init __rcu_init_preempt(void); -static void rcu_needs_cpu_flush(void); static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags); static void rcu_preempt_boost_start_gp(struct rcu_node *rnp); static void invoke_rcu_callbacks_kthread(void); diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h index 8aafbb8..4b9b9f8 100644 --- a/kernel/rcutree_plugin.h +++ b/kernel/rcutree_plugin.h @@ -27,6 +27,14 @@ #include <linux/delay.h> #include <linux/stop_machine.h> +#define RCU_KTHREAD_PRIO 1 + +#ifdef CONFIG_RCU_BOOST +#define RCU_BOOST_PRIO CONFIG_RCU_BOOST_PRIO +#else +#define RCU_BOOST_PRIO RCU_KTHREAD_PRIO +#endif + /* * Check the RCU kernel configuration parameters and print informative * messages about anything out of the ordinary. If you like #ifdef, you @@ -64,7 +72,7 @@ static void __init rcu_bootup_announce_oddness(void) #ifdef CONFIG_TREE_PREEMPT_RCU -struct rcu_state rcu_preempt_state = RCU_STATE_INITIALIZER(rcu_preempt_state); +struct rcu_state rcu_preempt_state = RCU_STATE_INITIALIZER(rcu_preempt); DEFINE_PER_CPU(struct rcu_data, rcu_preempt_data); static struct rcu_state *rcu_state = &rcu_preempt_state; @@ -122,9 +130,11 @@ static void rcu_preempt_qs(int cpu) { struct rcu_data *rdp = &per_cpu(rcu_preempt_data, cpu); - rdp->passed_quiesc_completed = rdp->gpnum - 1; + rdp->passed_quiesce_gpnum = rdp->gpnum; barrier(); - rdp->passed_quiesc = 1; + if (rdp->passed_quiesce == 0) + trace_rcu_grace_period("rcu_preempt", rdp->gpnum, "cpuqs"); + rdp->passed_quiesce = 1; current->rcu_read_unlock_special &= ~RCU_READ_UNLOCK_NEED_QS; } @@ -190,6 +200,11 @@ static void rcu_preempt_note_context_switch(int cpu) if (rnp->qsmask & rdp->grpmask) rnp->gp_tasks = &t->rcu_node_entry; } + trace_rcu_preempt_task(rdp->rsp->name, + t->pid, + (rnp->qsmask & rdp->grpmask) + ? rnp->gpnum + : rnp->gpnum + 1); raw_spin_unlock_irqrestore(&rnp->lock, flags); } else if (t->rcu_read_lock_nesting < 0 && t->rcu_read_unlock_special) { @@ -299,6 +314,9 @@ static noinline void rcu_read_unlock_special(struct task_struct *t) int empty_exp; unsigned long flags; struct list_head *np; +#ifdef CONFIG_RCU_BOOST + struct rt_mutex *rbmp = NULL; +#endif /* #ifdef CONFIG_RCU_BOOST */ struct rcu_node *rnp; int special; @@ -344,6 +362,9 @@ static noinline void rcu_read_unlock_special(struct task_struct *t) smp_mb(); /* ensure expedited fastpath sees end of RCU c-s. */ np = rcu_next_node_entry(t, rnp); list_del_init(&t->rcu_node_entry); + t->rcu_blocked_node = NULL; + trace_rcu_unlock_preempted_task("rcu_preempt", + rnp->gpnum, t->pid); if (&t->rcu_node_entry == rnp->gp_tasks) rnp->gp_tasks = np; if (&t->rcu_node_entry == rnp->exp_tasks) @@ -351,30 +372,34 @@ static noinline void rcu_read_unlock_special(struct task_struct *t) #ifdef CONFIG_RCU_BOOST if (&t->rcu_node_entry == rnp->boost_tasks) rnp->boost_tasks = np; - /* Snapshot and clear ->rcu_boosted with rcu_node lock held. */ - if (t->rcu_boosted) { - special |= RCU_READ_UNLOCK_BOOSTED; - t->rcu_boosted = 0; + /* Snapshot/clear ->rcu_boost_mutex with rcu_node lock held. */ + if (t->rcu_boost_mutex) { + rbmp = t->rcu_boost_mutex; + t->rcu_boost_mutex = NULL; } #endif /* #ifdef CONFIG_RCU_BOOST */ - t->rcu_blocked_node = NULL; /* * If this was the last task on the current list, and if * we aren't waiting on any CPUs, report the quiescent state. * Note that rcu_report_unblock_qs_rnp() releases rnp->lock. */ - if (empty) - raw_spin_unlock_irqrestore(&rnp->lock, flags); - else + if (!empty && !rcu_preempt_blocked_readers_cgp(rnp)) { + trace_rcu_quiescent_state_report("preempt_rcu", + rnp->gpnum, + 0, rnp->qsmask, + rnp->level, + rnp->grplo, + rnp->grphi, + !!rnp->gp_tasks); rcu_report_unblock_qs_rnp(rnp, flags); + } else + raw_spin_unlock_irqrestore(&rnp->lock, flags); #ifdef CONFIG_RCU_BOOST /* Unboost if we were boosted. */ - if (special & RCU_READ_UNLOCK_BOOSTED) { - rt_mutex_unlock(t->rcu_boost_mutex); - t->rcu_boost_mutex = NULL; - } + if (rbmp) + rt_mutex_unlock(rbmp); #endif /* #ifdef CONFIG_RCU_BOOST */ /* @@ -399,10 +424,10 @@ void __rcu_read_unlock(void) { struct task_struct *t = current; - barrier(); /* needed if we ever invoke rcu_read_unlock in rcutree.c */ if (t->rcu_read_lock_nesting != 1) --t->rcu_read_lock_nesting; else { + barrier(); /* critical section before exit code. */ t->rcu_read_lock_nesting = INT_MIN; barrier(); /* assign before ->rcu_read_unlock_special load */ if (unlikely(ACCESS_ONCE(t->rcu_read_unlock_special))) @@ -466,16 +491,20 @@ static void rcu_print_detail_task_stall(struct rcu_state *rsp) * Scan the current list of tasks blocked within RCU read-side critical * sections, printing out the tid of each. */ -static void rcu_print_task_stall(struct rcu_node *rnp) +static int rcu_print_task_stall(struct rcu_node *rnp) { struct task_struct *t; + int ndetected = 0; if (!rcu_preempt_blocked_readers_cgp(rnp)) - return; + return 0; t = list_entry(rnp->gp_tasks, struct task_struct, rcu_node_entry); - list_for_each_entry_continue(t, &rnp->blkd_tasks, rcu_node_entry) + list_for_each_entry_continue(t, &rnp->blkd_tasks, rcu_node_entry) { printk(" P%d", t->pid); + ndetected++; + } + return ndetected; } /* @@ -656,18 +685,9 @@ EXPORT_SYMBOL_GPL(call_rcu); */ void synchronize_rcu(void) { - struct rcu_synchronize rcu; - if (!rcu_scheduler_active) return; - - init_rcu_head_on_stack(&rcu.head); - init_completion(&rcu.completion); - /* Will wake me after RCU finished. */ - call_rcu(&rcu.head, wakeme_after_rcu); - /* Wait for it. */ - wait_for_completion(&rcu.completion); - destroy_rcu_head_on_stack(&rcu.head); + wait_rcu_gp(call_rcu); } EXPORT_SYMBOL_GPL(synchronize_rcu); @@ -968,8 +988,9 @@ static void rcu_print_detail_task_stall(struct rcu_state *rsp) * Because preemptible RCU does not exist, we never have to check for * tasks blocked within RCU read-side critical sections. */ -static void rcu_print_task_stall(struct rcu_node *rnp) +static int rcu_print_task_stall(struct rcu_node *rnp) { + return 0; } /* @@ -1136,6 +1157,8 @@ static void rcu_initiate_boost_trace(struct rcu_node *rnp) #endif /* #else #ifdef CONFIG_RCU_TRACE */ +static struct lock_class_key rcu_boost_class; + /* * Carry out RCU priority boosting on the task indicated by ->exp_tasks * or ->boost_tasks, advancing the pointer to the next task in the @@ -1198,8 +1221,10 @@ static int rcu_boost(struct rcu_node *rnp) */ t = container_of(tb, struct task_struct, rcu_node_entry); rt_mutex_init_proxy_locked(&mtx, t); + /* Avoid lockdep false positives. This rt_mutex is its own thing. */ + lockdep_set_class_and_name(&mtx.wait_lock, &rcu_boost_class, + "rcu_boost_mutex"); t->rcu_boost_mutex = &mtx; - t->rcu_boosted = 1; raw_spin_unlock_irqrestore(&rnp->lock, flags); rt_mutex_lock(&mtx); /* Side effect: boosts task t's priority. */ rt_mutex_unlock(&mtx); /* Keep lockdep happy. */ @@ -1228,9 +1253,12 @@ static int rcu_boost_kthread(void *arg) int spincnt = 0; int more2boost; + trace_rcu_utilization("Start boost kthread@init"); for (;;) { rnp->boost_kthread_status = RCU_KTHREAD_WAITING; + trace_rcu_utilization("End boost kthread@rcu_wait"); rcu_wait(rnp->boost_tasks || rnp->exp_tasks); + trace_rcu_utilization("Start boost kthread@rcu_wait"); rnp->boost_kthread_status = RCU_KTHREAD_RUNNING; more2boost = rcu_boost(rnp); if (more2boost) @@ -1238,11 +1266,14 @@ static int rcu_boost_kthread(void *arg) else spincnt = 0; if (spincnt > 10) { + trace_rcu_utilization("End boost kthread@rcu_yield"); rcu_yield(rcu_boost_kthread_timer, (unsigned long)rnp); + trace_rcu_utilization("Start boost kthread@rcu_yield"); spincnt = 0; } } /* NOTREACHED */ + trace_rcu_utilization("End boost kthread@notreached"); return 0; } @@ -1291,11 +1322,9 @@ static void invoke_rcu_callbacks_kthread(void) local_irq_save(flags); __this_cpu_write(rcu_cpu_has_work, 1); - if (__this_cpu_read(rcu_cpu_kthread_task) == NULL) { - local_irq_restore(flags); - return; - } - wake_up_process(__this_cpu_read(rcu_cpu_kthread_task)); + if (__this_cpu_read(rcu_cpu_kthread_task) != NULL && + current != __this_cpu_read(rcu_cpu_kthread_task)) + wake_up_process(__this_cpu_read(rcu_cpu_kthread_task)); local_irq_restore(flags); } @@ -1343,13 +1372,13 @@ static int __cpuinit rcu_spawn_one_boost_kthread(struct rcu_state *rsp, if (rnp->boost_kthread_task != NULL) return 0; t = kthread_create(rcu_boost_kthread, (void *)rnp, - "rcub%d", rnp_index); + "rcub/%d", rnp_index); if (IS_ERR(t)) return PTR_ERR(t); raw_spin_lock_irqsave(&rnp->lock, flags); rnp->boost_kthread_task = t; raw_spin_unlock_irqrestore(&rnp->lock, flags); - sp.sched_priority = RCU_KTHREAD_PRIO; + sp.sched_priority = RCU_BOOST_PRIO; sched_setscheduler_nocheck(t, SCHED_FIFO, &sp); wake_up_process(t); /* get to TASK_INTERRUPTIBLE quickly. */ return 0; @@ -1444,6 +1473,7 @@ static void rcu_yield(void (*f)(unsigned long), unsigned long arg) { struct sched_param sp; struct timer_list yield_timer; + int prio = current->rt_priority; setup_timer_on_stack(&yield_timer, f, arg); mod_timer(&yield_timer, jiffies + 2); @@ -1451,7 +1481,8 @@ static void rcu_yield(void (*f)(unsigned long), unsigned long arg) sched_setscheduler_nocheck(current, SCHED_NORMAL, &sp); set_user_nice(current, 19); schedule(); - sp.sched_priority = RCU_KTHREAD_PRIO; + set_user_nice(current, 0); + sp.sched_priority = prio; sched_setscheduler_nocheck(current, SCHED_FIFO, &sp); del_timer(&yield_timer); } @@ -1489,7 +1520,8 @@ static int rcu_cpu_kthread_should_stop(int cpu) /* * Per-CPU kernel thread that invokes RCU callbacks. This replaces the - * earlier RCU softirq. + * RCU softirq used in flavors and configurations of RCU that do not + * support RCU priority boosting. */ static int rcu_cpu_kthread(void *arg) { @@ -1500,9 +1532,12 @@ static int rcu_cpu_kthread(void *arg) char work; char *workp = &per_cpu(rcu_cpu_has_work, cpu); + trace_rcu_utilization("Start CPU kthread@init"); for (;;) { *statusp = RCU_KTHREAD_WAITING; + trace_rcu_utilization("End CPU kthread@rcu_wait"); rcu_wait(*workp != 0 || kthread_should_stop()); + trace_rcu_utilization("Start CPU kthread@rcu_wait"); local_bh_disable(); if (rcu_cpu_kthread_should_stop(cpu)) { local_bh_enable(); @@ -1523,11 +1558,14 @@ static int rcu_cpu_kthread(void *arg) spincnt = 0; if (spincnt > 10) { *statusp = RCU_KTHREAD_YIELDING; + trace_rcu_utilization("End CPU kthread@rcu_yield"); rcu_yield(rcu_cpu_kthread_timer, (unsigned long)cpu); + trace_rcu_utilization("Start CPU kthread@rcu_yield"); spincnt = 0; } } *statusp = RCU_KTHREAD_STOPPED; + trace_rcu_utilization("End CPU kthread@term"); return 0; } @@ -1560,7 +1598,10 @@ static int __cpuinit rcu_spawn_one_cpu_kthread(int cpu) if (!rcu_scheduler_fully_active || per_cpu(rcu_cpu_kthread_task, cpu) != NULL) return 0; - t = kthread_create(rcu_cpu_kthread, (void *)(long)cpu, "rcuc%d", cpu); + t = kthread_create_on_node(rcu_cpu_kthread, + (void *)(long)cpu, + cpu_to_node(cpu), + "rcuc/%d", cpu); if (IS_ERR(t)) return PTR_ERR(t); if (cpu_online(cpu)) @@ -1669,7 +1710,7 @@ static int __cpuinit rcu_spawn_one_node_kthread(struct rcu_state *rsp, return 0; if (rnp->node_kthread_task == NULL) { t = kthread_create(rcu_node_kthread, (void *)rnp, - "rcun%d", rnp_index); + "rcun/%d", rnp_index); if (IS_ERR(t)) return PTR_ERR(t); raw_spin_lock_irqsave(&rnp->lock, flags); @@ -1907,15 +1948,6 @@ int rcu_needs_cpu(int cpu) return rcu_needs_cpu_quick_check(cpu); } -/* - * Check to see if we need to continue a callback-flush operations to - * allow the last CPU to enter dyntick-idle mode. But fast dyntick-idle - * entry is not configured, so we never do need to. - */ -static void rcu_needs_cpu_flush(void) -{ -} - #else /* #if !defined(CONFIG_RCU_FAST_NO_HZ) */ #define RCU_NEEDS_CPU_FLUSHES 5 @@ -1991,20 +2023,4 @@ int rcu_needs_cpu(int cpu) return c; } -/* - * Check to see if we need to continue a callback-flush operations to - * allow the last CPU to enter dyntick-idle mode. - */ -static void rcu_needs_cpu_flush(void) -{ - int cpu = smp_processor_id(); - unsigned long flags; - - if (per_cpu(rcu_dyntick_drain, cpu) <= 0) - return; - local_irq_save(flags); - (void)rcu_needs_cpu(cpu); - local_irq_restore(flags); -} - #endif /* #else #if !defined(CONFIG_RCU_FAST_NO_HZ) */ diff --git a/kernel/rcutree_trace.c b/kernel/rcutree_trace.c index 3b0c098..9feffa4 100644 --- a/kernel/rcutree_trace.c +++ b/kernel/rcutree_trace.c @@ -48,11 +48,6 @@ #ifdef CONFIG_RCU_BOOST -DECLARE_PER_CPU(unsigned int, rcu_cpu_kthread_status); -DECLARE_PER_CPU(unsigned int, rcu_cpu_kthread_cpu); -DECLARE_PER_CPU(unsigned int, rcu_cpu_kthread_loops); -DECLARE_PER_CPU(char, rcu_cpu_has_work); - static char convert_kthread_status(unsigned int kthread_status) { if (kthread_status > RCU_KTHREAD_MAX) @@ -66,11 +61,11 @@ static void print_one_rcu_data(struct seq_file *m, struct rcu_data *rdp) { if (!rdp->beenonline) return; - seq_printf(m, "%3d%cc=%lu g=%lu pq=%d pqc=%lu qp=%d", + seq_printf(m, "%3d%cc=%lu g=%lu pq=%d pgp=%lu qp=%d", rdp->cpu, cpu_is_offline(rdp->cpu) ? '!' : ' ', rdp->completed, rdp->gpnum, - rdp->passed_quiesc, rdp->passed_quiesc_completed, + rdp->passed_quiesce, rdp->passed_quiesce_gpnum, rdp->qs_pending); #ifdef CONFIG_NO_HZ seq_printf(m, " dt=%d/%d/%d df=%lu", @@ -144,7 +139,7 @@ static void print_one_rcu_data_csv(struct seq_file *m, struct rcu_data *rdp) rdp->cpu, cpu_is_offline(rdp->cpu) ? "\"N\"" : "\"Y\"", rdp->completed, rdp->gpnum, - rdp->passed_quiesc, rdp->passed_quiesc_completed, + rdp->passed_quiesce, rdp->passed_quiesce_gpnum, rdp->qs_pending); #ifdef CONFIG_NO_HZ seq_printf(m, ",%d,%d,%d,%lu", @@ -175,7 +170,7 @@ static void print_one_rcu_data_csv(struct seq_file *m, struct rcu_data *rdp) static int show_rcudata_csv(struct seq_file *m, void *unused) { - seq_puts(m, "\"CPU\",\"Online?\",\"c\",\"g\",\"pq\",\"pqc\",\"pq\","); + seq_puts(m, "\"CPU\",\"Online?\",\"c\",\"g\",\"pq\",\"pgp\",\"pq\","); #ifdef CONFIG_NO_HZ seq_puts(m, "\"dt\",\"dt nesting\",\"dt NMI nesting\",\"df\","); #endif /* #ifdef CONFIG_NO_HZ */ diff --git a/kernel/rtmutex-debug.c b/kernel/rtmutex-debug.c index 3c7cbc2..a2e7e72 100644 --- a/kernel/rtmutex-debug.c +++ b/kernel/rtmutex-debug.c @@ -29,61 +29,6 @@ #include "rtmutex_common.h" -# define TRACE_WARN_ON(x) WARN_ON(x) -# define TRACE_BUG_ON(x) BUG_ON(x) - -# define TRACE_OFF() \ -do { \ - if (rt_trace_on) { \ - rt_trace_on = 0; \ - console_verbose(); \ - if (raw_spin_is_locked(¤t->pi_lock)) \ - raw_spin_unlock(¤t->pi_lock); \ - } \ -} while (0) - -# define TRACE_OFF_NOLOCK() \ -do { \ - if (rt_trace_on) { \ - rt_trace_on = 0; \ - console_verbose(); \ - } \ -} while (0) - -# define TRACE_BUG_LOCKED() \ -do { \ - TRACE_OFF(); \ - BUG(); \ -} while (0) - -# define TRACE_WARN_ON_LOCKED(c) \ -do { \ - if (unlikely(c)) { \ - TRACE_OFF(); \ - WARN_ON(1); \ - } \ -} while (0) - -# define TRACE_BUG_ON_LOCKED(c) \ -do { \ - if (unlikely(c)) \ - TRACE_BUG_LOCKED(); \ -} while (0) - -#ifdef CONFIG_SMP -# define SMP_TRACE_BUG_ON_LOCKED(c) TRACE_BUG_ON_LOCKED(c) -#else -# define SMP_TRACE_BUG_ON_LOCKED(c) do { } while (0) -#endif - -/* - * deadlock detection flag. We turn it off when we detect - * the first problem because we dont want to recurse back - * into the tracing code when doing error printk or - * executing a BUG(): - */ -static int rt_trace_on = 1; - static void printk_task(struct task_struct *p) { if (p) @@ -111,8 +56,8 @@ static void printk_lock(struct rt_mutex *lock, int print_owner) void rt_mutex_debug_task_free(struct task_struct *task) { - WARN_ON(!plist_head_empty(&task->pi_waiters)); - WARN_ON(task->pi_blocked_on); + DEBUG_LOCKS_WARN_ON(!plist_head_empty(&task->pi_waiters)); + DEBUG_LOCKS_WARN_ON(task->pi_blocked_on); } /* @@ -125,7 +70,7 @@ void debug_rt_mutex_deadlock(int detect, struct rt_mutex_waiter *act_waiter, { struct task_struct *task; - if (!rt_trace_on || detect || !act_waiter) + if (!debug_locks || detect || !act_waiter) return; task = rt_mutex_owner(act_waiter->lock); @@ -139,7 +84,7 @@ void debug_rt_mutex_print_deadlock(struct rt_mutex_waiter *waiter) { struct task_struct *task; - if (!waiter->deadlock_lock || !rt_trace_on) + if (!waiter->deadlock_lock || !debug_locks) return; rcu_read_lock(); @@ -149,7 +94,10 @@ void debug_rt_mutex_print_deadlock(struct rt_mutex_waiter *waiter) return; } - TRACE_OFF_NOLOCK(); + if (!debug_locks_off()) { + rcu_read_unlock(); + return; + } printk("\n============================================\n"); printk( "[ BUG: circular locking deadlock detected! ]\n"); @@ -180,7 +128,6 @@ void debug_rt_mutex_print_deadlock(struct rt_mutex_waiter *waiter) printk("[ turning off deadlock detection." "Please report this trace. ]\n\n"); - local_irq_disable(); } void debug_rt_mutex_lock(struct rt_mutex *lock) @@ -189,7 +136,7 @@ void debug_rt_mutex_lock(struct rt_mutex *lock) void debug_rt_mutex_unlock(struct rt_mutex *lock) { - TRACE_WARN_ON_LOCKED(rt_mutex_owner(lock) != current); + DEBUG_LOCKS_WARN_ON(rt_mutex_owner(lock) != current); } void @@ -199,7 +146,7 @@ debug_rt_mutex_proxy_lock(struct rt_mutex *lock, struct task_struct *powner) void debug_rt_mutex_proxy_unlock(struct rt_mutex *lock) { - TRACE_WARN_ON_LOCKED(!rt_mutex_owner(lock)); + DEBUG_LOCKS_WARN_ON(!rt_mutex_owner(lock)); } void debug_rt_mutex_init_waiter(struct rt_mutex_waiter *waiter) @@ -213,8 +160,8 @@ void debug_rt_mutex_init_waiter(struct rt_mutex_waiter *waiter) void debug_rt_mutex_free_waiter(struct rt_mutex_waiter *waiter) { put_pid(waiter->deadlock_task_pid); - TRACE_WARN_ON(!plist_node_empty(&waiter->list_entry)); - TRACE_WARN_ON(!plist_node_empty(&waiter->pi_list_entry)); + DEBUG_LOCKS_WARN_ON(!plist_node_empty(&waiter->list_entry)); + DEBUG_LOCKS_WARN_ON(!plist_node_empty(&waiter->pi_list_entry)); memset(waiter, 0x22, sizeof(*waiter)); } diff --git a/kernel/rtmutex.c b/kernel/rtmutex.c index 255e166..5e8d9cc 100644 --- a/kernel/rtmutex.c +++ b/kernel/rtmutex.c @@ -579,6 +579,7 @@ __rt_mutex_slowlock(struct rt_mutex *lock, int state, struct rt_mutex_waiter *waiter) { int ret = 0; + int was_disabled; for (;;) { /* Try to acquire the lock: */ @@ -601,10 +602,17 @@ __rt_mutex_slowlock(struct rt_mutex *lock, int state, raw_spin_unlock(&lock->wait_lock); + was_disabled = irqs_disabled(); + if (was_disabled) + local_irq_enable(); + debug_rt_mutex_print_deadlock(waiter); schedule_rt_mutex(lock); + if (was_disabled) + local_irq_disable(); + raw_spin_lock(&lock->wait_lock); set_current_state(state); } diff --git a/kernel/sched.c b/kernel/sched.c index b50b0f0..d87c6e5 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -196,10 +196,28 @@ static inline int rt_bandwidth_enabled(void) return sysctl_sched_rt_runtime >= 0; } -static void start_rt_bandwidth(struct rt_bandwidth *rt_b) +static void start_bandwidth_timer(struct hrtimer *period_timer, ktime_t period) { - ktime_t now; + unsigned long delta; + ktime_t soft, hard, now; + + for (;;) { + if (hrtimer_active(period_timer)) + break; + + now = hrtimer_cb_get_time(period_timer); + hrtimer_forward(period_timer, now, period); + soft = hrtimer_get_softexpires(period_timer); + hard = hrtimer_get_expires(period_timer); + delta = ktime_to_ns(ktime_sub(hard, soft)); + __hrtimer_start_range_ns(period_timer, soft, delta, + HRTIMER_MODE_ABS_PINNED, 0); + } +} + +static void start_rt_bandwidth(struct rt_bandwidth *rt_b) +{ if (!rt_bandwidth_enabled() || rt_b->rt_runtime == RUNTIME_INF) return; @@ -207,22 +225,7 @@ static void start_rt_bandwidth(struct rt_bandwidth *rt_b) return; raw_spin_lock(&rt_b->rt_runtime_lock); - for (;;) { - unsigned long delta; - ktime_t soft, hard; - - if (hrtimer_active(&rt_b->rt_period_timer)) - break; - - now = hrtimer_cb_get_time(&rt_b->rt_period_timer); - hrtimer_forward(&rt_b->rt_period_timer, now, rt_b->rt_period); - - soft = hrtimer_get_softexpires(&rt_b->rt_period_timer); - hard = hrtimer_get_expires(&rt_b->rt_period_timer); - delta = ktime_to_ns(ktime_sub(hard, soft)); - __hrtimer_start_range_ns(&rt_b->rt_period_timer, soft, delta, - HRTIMER_MODE_ABS_PINNED, 0); - } + start_bandwidth_timer(&rt_b->rt_period_timer, rt_b->rt_period); raw_spin_unlock(&rt_b->rt_runtime_lock); } @@ -247,6 +250,24 @@ struct cfs_rq; static LIST_HEAD(task_groups); +struct cfs_bandwidth { +#ifdef CONFIG_CFS_BANDWIDTH + raw_spinlock_t lock; + ktime_t period; + u64 quota, runtime; + s64 hierarchal_quota; + u64 runtime_expires; + + int idle, timer_active; + struct hrtimer period_timer, slack_timer; + struct list_head throttled_cfs_rq; + + /* statistics */ + int nr_periods, nr_throttled; + u64 throttled_time; +#endif +}; + /* task group related information */ struct task_group { struct cgroup_subsys_state css; @@ -278,6 +299,8 @@ struct task_group { #ifdef CONFIG_SCHED_AUTOGROUP struct autogroup *autogroup; #endif + + struct cfs_bandwidth cfs_bandwidth; }; /* task_group_lock serializes the addition/removal of task groups */ @@ -311,7 +334,7 @@ struct task_group root_task_group; /* CFS-related fields in a runqueue */ struct cfs_rq { struct load_weight load; - unsigned long nr_running; + unsigned long nr_running, h_nr_running; u64 exec_clock; u64 min_vruntime; @@ -377,9 +400,120 @@ struct cfs_rq { unsigned long load_contribution; #endif +#ifdef CONFIG_CFS_BANDWIDTH + int runtime_enabled; + u64 runtime_expires; + s64 runtime_remaining; + + u64 throttled_timestamp; + int throttled, throttle_count; + struct list_head throttled_list; +#endif #endif }; +#ifdef CONFIG_FAIR_GROUP_SCHED +#ifdef CONFIG_CFS_BANDWIDTH +static inline struct cfs_bandwidth *tg_cfs_bandwidth(struct task_group *tg) +{ + return &tg->cfs_bandwidth; +} + +static inline u64 default_cfs_period(void); +static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun); +static void do_sched_cfs_slack_timer(struct cfs_bandwidth *cfs_b); + +static enum hrtimer_restart sched_cfs_slack_timer(struct hrtimer *timer) +{ + struct cfs_bandwidth *cfs_b = + container_of(timer, struct cfs_bandwidth, slack_timer); + do_sched_cfs_slack_timer(cfs_b); + + return HRTIMER_NORESTART; +} + +static enum hrtimer_restart sched_cfs_period_timer(struct hrtimer *timer) +{ + struct cfs_bandwidth *cfs_b = + container_of(timer, struct cfs_bandwidth, period_timer); + ktime_t now; + int overrun; + int idle = 0; + + for (;;) { + now = hrtimer_cb_get_time(timer); + overrun = hrtimer_forward(timer, now, cfs_b->period); + + if (!overrun) + break; + + idle = do_sched_cfs_period_timer(cfs_b, overrun); + } + + return idle ? HRTIMER_NORESTART : HRTIMER_RESTART; +} + +static void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b) +{ + raw_spin_lock_init(&cfs_b->lock); + cfs_b->runtime = 0; + cfs_b->quota = RUNTIME_INF; + cfs_b->period = ns_to_ktime(default_cfs_period()); + + INIT_LIST_HEAD(&cfs_b->throttled_cfs_rq); + hrtimer_init(&cfs_b->period_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + cfs_b->period_timer.function = sched_cfs_period_timer; + hrtimer_init(&cfs_b->slack_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + cfs_b->slack_timer.function = sched_cfs_slack_timer; +} + +static void init_cfs_rq_runtime(struct cfs_rq *cfs_rq) +{ + cfs_rq->runtime_enabled = 0; + INIT_LIST_HEAD(&cfs_rq->throttled_list); +} + +/* requires cfs_b->lock, may release to reprogram timer */ +static void __start_cfs_bandwidth(struct cfs_bandwidth *cfs_b) +{ + /* + * The timer may be active because we're trying to set a new bandwidth + * period or because we're racing with the tear-down path + * (timer_active==0 becomes visible before the hrtimer call-back + * terminates). In either case we ensure that it's re-programmed + */ + while (unlikely(hrtimer_active(&cfs_b->period_timer))) { + raw_spin_unlock(&cfs_b->lock); + /* ensure cfs_b->lock is available while we wait */ + hrtimer_cancel(&cfs_b->period_timer); + + raw_spin_lock(&cfs_b->lock); + /* if someone else restarted the timer then we're done */ + if (cfs_b->timer_active) + return; + } + + cfs_b->timer_active = 1; + start_bandwidth_timer(&cfs_b->period_timer, cfs_b->period); +} + +static void destroy_cfs_bandwidth(struct cfs_bandwidth *cfs_b) +{ + hrtimer_cancel(&cfs_b->period_timer); + hrtimer_cancel(&cfs_b->slack_timer); +} +#else +static void init_cfs_rq_runtime(struct cfs_rq *cfs_rq) {} +static void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b) {} +static void destroy_cfs_bandwidth(struct cfs_bandwidth *cfs_b) {} + +static inline struct cfs_bandwidth *tg_cfs_bandwidth(struct task_group *tg) +{ + return NULL; +} +#endif /* CONFIG_CFS_BANDWIDTH */ +#endif /* CONFIG_FAIR_GROUP_SCHED */ + /* Real-Time classes' related field in a runqueue: */ struct rt_rq { struct rt_prio_array active; @@ -510,7 +644,7 @@ struct rq { unsigned long cpu_power; - unsigned char idle_at_tick; + unsigned char idle_balance; /* For active balancing */ int post_schedule; int active_balance; @@ -520,8 +654,6 @@ struct rq { int cpu; int online; - unsigned long avg_load_per_task; - u64 rt_avg; u64 age_stamp; u64 idle_stamp; @@ -570,7 +702,7 @@ struct rq { #endif #ifdef CONFIG_SMP - struct task_struct *wake_list; + struct llist_head wake_list; #endif }; @@ -1272,6 +1404,18 @@ void wake_up_idle_cpu(int cpu) smp_send_reschedule(cpu); } +static inline bool got_nohz_idle_kick(void) +{ + return idle_cpu(smp_processor_id()) && this_rq()->nohz_balance_kick; +} + +#else /* CONFIG_NO_HZ */ + +static inline bool got_nohz_idle_kick(void) +{ + return false; +} + #endif /* CONFIG_NO_HZ */ static u64 sched_avg_period(void) @@ -1471,24 +1615,28 @@ static inline void dec_cpu_load(struct rq *rq, unsigned long load) update_load_sub(&rq->load, load); } -#if (defined(CONFIG_SMP) && defined(CONFIG_FAIR_GROUP_SCHED)) || defined(CONFIG_RT_GROUP_SCHED) +#if defined(CONFIG_RT_GROUP_SCHED) || (defined(CONFIG_FAIR_GROUP_SCHED) && \ + (defined(CONFIG_SMP) || defined(CONFIG_CFS_BANDWIDTH))) typedef int (*tg_visitor)(struct task_group *, void *); /* - * Iterate the full tree, calling @down when first entering a node and @up when - * leaving it for the final time. + * Iterate task_group tree rooted at *from, calling @down when first entering a + * node and @up when leaving it for the final time. + * + * Caller must hold rcu_lock or sufficient equivalent. */ -static int walk_tg_tree(tg_visitor down, tg_visitor up, void *data) +static int walk_tg_tree_from(struct task_group *from, + tg_visitor down, tg_visitor up, void *data) { struct task_group *parent, *child; int ret; - rcu_read_lock(); - parent = &root_task_group; + parent = from; + down: ret = (*down)(parent, data); if (ret) - goto out_unlock; + goto out; list_for_each_entry_rcu(child, &parent->children, siblings) { parent = child; goto down; @@ -1497,19 +1645,29 @@ up: continue; } ret = (*up)(parent, data); - if (ret) - goto out_unlock; + if (ret || parent == from) + goto out; child = parent; parent = parent->parent; if (parent) goto up; -out_unlock: - rcu_read_unlock(); - +out: return ret; } +/* + * Iterate the full tree, calling @down when first entering a node and @up when + * leaving it for the final time. + * + * Caller must hold rcu_lock or sufficient equivalent. + */ + +static inline int walk_tg_tree(tg_visitor down, tg_visitor up, void *data) +{ + return walk_tg_tree_from(&root_task_group, down, up, data); +} + static int tg_nop(struct task_group *tg, void *data) { return 0; @@ -1569,11 +1727,9 @@ static unsigned long cpu_avg_load_per_task(int cpu) unsigned long nr_running = ACCESS_ONCE(rq->nr_running); if (nr_running) - rq->avg_load_per_task = rq->load.weight / nr_running; - else - rq->avg_load_per_task = 0; + return rq->load.weight / nr_running; - return rq->avg_load_per_task; + return 0; } #ifdef CONFIG_PREEMPT @@ -1739,7 +1895,7 @@ static inline void __set_task_cpu(struct task_struct *p, unsigned int cpu) #ifdef CONFIG_SMP /* * After ->cpu is set up to a new value, task_rq_lock(p, ...) can be - * successfuly executed on another CPU. We must ensure that updates of + * successfully executed on another CPU. We must ensure that updates of * per-task data have been completed by this moment. */ smp_wmb(); @@ -1806,7 +1962,6 @@ static void activate_task(struct rq *rq, struct task_struct *p, int flags) rq->nr_uninterruptible--; enqueue_task(rq, p, flags); - inc_nr_running(rq); } /* @@ -1818,7 +1973,6 @@ static void deactivate_task(struct rq *rq, struct task_struct *p, int flags) rq->nr_uninterruptible++; dequeue_task(rq, p, flags); - dec_nr_running(rq); } #ifdef CONFIG_IRQ_TIME_ACCOUNTING @@ -2390,11 +2544,11 @@ static int select_fallback_rq(int cpu, struct task_struct *p) /* Look for allowed, online CPU in same node. */ for_each_cpu_and(dest_cpu, nodemask, cpu_active_mask) - if (cpumask_test_cpu(dest_cpu, &p->cpus_allowed)) + if (cpumask_test_cpu(dest_cpu, tsk_cpus_allowed(p))) return dest_cpu; /* Any allowed, online CPU? */ - dest_cpu = cpumask_any_and(&p->cpus_allowed, cpu_active_mask); + dest_cpu = cpumask_any_and(tsk_cpus_allowed(p), cpu_active_mask); if (dest_cpu < nr_cpu_ids) return dest_cpu; @@ -2431,7 +2585,7 @@ int select_task_rq(struct task_struct *p, int sd_flags, int wake_flags) * [ this allows ->select_task() to simply return task_cpu(p) and * not worry about this generic constraint ] */ - if (unlikely(!cpumask_test_cpu(cpu, &p->cpus_allowed) || + if (unlikely(!cpumask_test_cpu(cpu, tsk_cpus_allowed(p)) || !cpu_online(cpu))) cpu = select_fallback_rq(task_cpu(p), p); @@ -2556,42 +2710,26 @@ static int ttwu_remote(struct task_struct *p, int wake_flags) } #ifdef CONFIG_SMP -static void sched_ttwu_do_pending(struct task_struct *list) +static void sched_ttwu_pending(void) { struct rq *rq = this_rq(); + struct llist_node *llist = llist_del_all(&rq->wake_list); + struct task_struct *p; raw_spin_lock(&rq->lock); - while (list) { - struct task_struct *p = list; - list = list->wake_entry; + while (llist) { + p = llist_entry(llist, struct task_struct, wake_entry); + llist = llist_next(llist); ttwu_do_activate(rq, p, 0); } raw_spin_unlock(&rq->lock); } -#ifdef CONFIG_HOTPLUG_CPU - -static void sched_ttwu_pending(void) -{ - struct rq *rq = this_rq(); - struct task_struct *list = xchg(&rq->wake_list, NULL); - - if (!list) - return; - - sched_ttwu_do_pending(list); -} - -#endif /* CONFIG_HOTPLUG_CPU */ - void scheduler_ipi(void) { - struct rq *rq = this_rq(); - struct task_struct *list = xchg(&rq->wake_list, NULL); - - if (!list) + if (llist_empty(&this_rq()->wake_list) && !got_nohz_idle_kick()) return; /* @@ -2608,25 +2746,21 @@ void scheduler_ipi(void) * somewhat pessimize the simple resched case. */ irq_enter(); - sched_ttwu_do_pending(list); + sched_ttwu_pending(); + + /* + * Check if someone kicked us for doing the nohz idle load balance. + */ + if (unlikely(got_nohz_idle_kick() && !need_resched())) { + this_rq()->idle_balance = 1; + raise_softirq_irqoff(SCHED_SOFTIRQ); + } irq_exit(); } static void ttwu_queue_remote(struct task_struct *p, int cpu) { - struct rq *rq = cpu_rq(cpu); - struct task_struct *next = rq->wake_list; - - for (;;) { - struct task_struct *old = next; - - p->wake_entry = next; - next = cmpxchg(&rq->wake_list, old, p); - if (next == old) - break; - } - - if (!next) + if (llist_add(&p->wake_entry, &cpu_rq(cpu)->wake_list)) smp_send_reschedule(cpu); } @@ -2848,19 +2982,23 @@ void sched_fork(struct task_struct *p) p->state = TASK_RUNNING; /* + * Make sure we do not leak PI boosting priority to the child. + */ + p->prio = current->normal_prio; + + /* * Revert to default priority/policy on fork if requested. */ if (unlikely(p->sched_reset_on_fork)) { - if (p->policy == SCHED_FIFO || p->policy == SCHED_RR) { + if (task_has_rt_policy(p)) { p->policy = SCHED_NORMAL; - p->normal_prio = p->static_prio; - } - - if (PRIO_TO_NICE(p->static_prio) < 0) { p->static_prio = NICE_TO_PRIO(0); - p->normal_prio = p->static_prio; - set_load_weight(p); - } + p->rt_priority = 0; + } else if (PRIO_TO_NICE(p->static_prio) < 0) + p->static_prio = NICE_TO_PRIO(0); + + p->prio = p->normal_prio = __normal_prio(p); + set_load_weight(p); /* * We don't need the reset flag anymore after the fork. It has @@ -2869,11 +3007,6 @@ void sched_fork(struct task_struct *p) p->sched_reset_on_fork = 0; } - /* - * Make sure we do not leak PI boosting priority to the child. - */ - p->prio = current->normal_prio; - if (!rt_prio(p->prio)) p->sched_class = &fair_sched_class; @@ -4116,7 +4249,7 @@ void scheduler_tick(void) perf_event_task_tick(); #ifdef CONFIG_SMP - rq->idle_at_tick = idle_cpu(cpu); + rq->idle_balance = idle_cpu(cpu); trigger_load_balance(rq, cpu); #endif } @@ -4213,6 +4346,7 @@ static inline void schedule_debug(struct task_struct *prev) */ if (unlikely(in_atomic_preempt_off() && !prev->exit_state)) __schedule_bug(prev); + rcu_sleep_check(); profile_hit(SCHED_PROFILING, __builtin_return_address(0)); @@ -4239,7 +4373,7 @@ pick_next_task(struct rq *rq) * Optimization: we know that if all tasks are in * the fair class we can call that function directly: */ - if (likely(rq->nr_running == rq->cfs.nr_running)) { + if (likely(rq->nr_running == rq->cfs.h_nr_running)) { p = fair_sched_class.pick_next_task(rq); if (likely(p)) return p; @@ -5025,7 +5159,20 @@ EXPORT_SYMBOL(task_nice); */ int idle_cpu(int cpu) { - return cpu_curr(cpu) == cpu_rq(cpu)->idle; + struct rq *rq = cpu_rq(cpu); + + if (rq->curr != rq->idle) + return 0; + + if (rq->nr_running) + return 0; + +#ifdef CONFIG_SMP + if (!llist_empty(&rq->wake_list)) + return 0; +#endif + + return 1; } /** @@ -5875,7 +6022,7 @@ void show_state_filter(unsigned long state_filter) printk(KERN_INFO " task PC stack pid father\n"); #endif - read_lock(&tasklist_lock); + rcu_read_lock(); do_each_thread(g, p) { /* * reset the NMI-timeout, listing all files on a slow @@ -5891,7 +6038,7 @@ void show_state_filter(unsigned long state_filter) #ifdef CONFIG_SCHED_DEBUG sysrq_sched_debug_show(); #endif - read_unlock(&tasklist_lock); + rcu_read_unlock(); /* * Only show locks if all tasks are dumped: */ @@ -5955,15 +6102,6 @@ void __cpuinit init_idle(struct task_struct *idle, int cpu) } /* - * In a system that switches off the HZ timer nohz_cpu_mask - * indicates which cpus entered this state. This is used - * in the rcu update to wait only for active cpus. For system - * which do not switch off the HZ timer nohz_cpu_mask should - * always be CPU_BITS_NONE. - */ -cpumask_var_t nohz_cpu_mask; - -/* * Increase the granularity value when there are more CPUs, * because with more CPUs the 'effective latency' as visible * to users decreases. But the relationship is not linear, @@ -6015,10 +6153,9 @@ void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask) { if (p->sched_class && p->sched_class->set_cpus_allowed) p->sched_class->set_cpus_allowed(p, new_mask); - else { - cpumask_copy(&p->cpus_allowed, new_mask); - p->rt.nr_cpus_allowed = cpumask_weight(new_mask); - } + + cpumask_copy(&p->cpus_allowed, new_mask); + p->rt.nr_cpus_allowed = cpumask_weight(new_mask); } /* @@ -6116,7 +6253,7 @@ static int __migrate_task(struct task_struct *p, int src_cpu, int dest_cpu) if (task_cpu(p) != src_cpu) goto done; /* Affinity changed (again). */ - if (!cpumask_test_cpu(dest_cpu, &p->cpus_allowed)) + if (!cpumask_test_cpu(dest_cpu, tsk_cpus_allowed(p))) goto fail; /* @@ -6197,6 +6334,30 @@ static void calc_global_load_remove(struct rq *rq) rq->calc_load_active = 0; } +#ifdef CONFIG_CFS_BANDWIDTH +static void unthrottle_offline_cfs_rqs(struct rq *rq) +{ + struct cfs_rq *cfs_rq; + + for_each_leaf_cfs_rq(rq, cfs_rq) { + struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg); + + if (!cfs_rq->runtime_enabled) + continue; + + /* + * clock_task is not advancing so we just need to make sure + * there's some valid quota amount + */ + cfs_rq->runtime_remaining = cfs_b->quota; + if (cfs_rq_throttled(cfs_rq)) + unthrottle_cfs_rq(cfs_rq); + } +} +#else +static void unthrottle_offline_cfs_rqs(struct rq *rq) {} +#endif + /* * Migrate all tasks from the rq, sleeping tasks will be migrated by * try_to_wake_up()->select_task_rq(). @@ -6222,6 +6383,9 @@ static void migrate_tasks(unsigned int dead_cpu) */ rq->stop = NULL; + /* Ensure any throttled groups are reachable by pick_next_task */ + unthrottle_offline_cfs_rqs(rq); + for ( ; ; ) { /* * There's this thread running, bail when that's the only @@ -7965,6 +8129,7 @@ static void init_tg_cfs_entry(struct task_group *tg, struct cfs_rq *cfs_rq, /* allow initial update_cfs_load() to truncate */ cfs_rq->load_stamp = 1; #endif + init_cfs_rq_runtime(cfs_rq); tg->cfs_rq[cpu] = cfs_rq; tg->se[cpu] = se; @@ -8104,6 +8269,7 @@ void __init sched_init(void) * We achieve this by letting root_task_group's tasks sit * directly in rq->cfs (i.e root_task_group->se[] = NULL). */ + init_cfs_bandwidth(&root_task_group.cfs_bandwidth); init_tg_cfs_entry(&root_task_group, &rq->cfs, NULL, i, NULL); #endif /* CONFIG_FAIR_GROUP_SCHED */ @@ -8133,7 +8299,6 @@ void __init sched_init(void) rq_attach_root(rq, &def_root_domain); #ifdef CONFIG_NO_HZ rq->nohz_balance_kick = 0; - init_sched_softirq_csd(&per_cpu(remote_sched_softirq_cb, i)); #endif #endif init_rq_hrtick(rq); @@ -8175,8 +8340,6 @@ void __init sched_init(void) */ current->sched_class = &fair_sched_class; - /* Allocate the nohz_cpu_mask if CONFIG_CPUMASK_OFFSTACK */ - zalloc_cpumask_var(&nohz_cpu_mask, GFP_NOWAIT); #ifdef CONFIG_SMP zalloc_cpumask_var(&sched_domains_tmpmask, GFP_NOWAIT); #ifdef CONFIG_NO_HZ @@ -8206,6 +8369,7 @@ void __might_sleep(const char *file, int line, int preempt_offset) { static unsigned long prev_jiffy; /* ratelimiting */ + rcu_sleep_check(); /* WARN_ON_ONCE() by default, no rate limit reqd. */ if ((preempt_count_equals(preempt_offset) && !irqs_disabled()) || system_state != SYSTEM_RUNNING || oops_in_progress) return; @@ -8345,6 +8509,8 @@ static void free_fair_sched_group(struct task_group *tg) { int i; + destroy_cfs_bandwidth(tg_cfs_bandwidth(tg)); + for_each_possible_cpu(i) { if (tg->cfs_rq) kfree(tg->cfs_rq[i]); @@ -8372,6 +8538,8 @@ int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent) tg->shares = NICE_0_LOAD; + init_cfs_bandwidth(tg_cfs_bandwidth(tg)); + for_each_possible_cpu(i) { cfs_rq = kzalloc_node(sizeof(struct cfs_rq), GFP_KERNEL, cpu_to_node(i)); @@ -8647,12 +8815,7 @@ unsigned long sched_group_shares(struct task_group *tg) } #endif -#ifdef CONFIG_RT_GROUP_SCHED -/* - * Ensure that the real time constraints are schedulable. - */ -static DEFINE_MUTEX(rt_constraints_mutex); - +#if defined(CONFIG_RT_GROUP_SCHED) || defined(CONFIG_CFS_BANDWIDTH) static unsigned long to_ratio(u64 period, u64 runtime) { if (runtime == RUNTIME_INF) @@ -8660,6 +8823,13 @@ static unsigned long to_ratio(u64 period, u64 runtime) return div64_u64(runtime << 20, period); } +#endif + +#ifdef CONFIG_RT_GROUP_SCHED +/* + * Ensure that the real time constraints are schedulable. + */ +static DEFINE_MUTEX(rt_constraints_mutex); /* Must be called with tasklist_lock held */ static inline int tg_has_rt_tasks(struct task_group *tg) @@ -8680,7 +8850,7 @@ struct rt_schedulable_data { u64 rt_runtime; }; -static int tg_schedulable(struct task_group *tg, void *data) +static int tg_rt_schedulable(struct task_group *tg, void *data) { struct rt_schedulable_data *d = data; struct task_group *child; @@ -8738,16 +8908,22 @@ static int tg_schedulable(struct task_group *tg, void *data) static int __rt_schedulable(struct task_group *tg, u64 period, u64 runtime) { + int ret; + struct rt_schedulable_data data = { .tg = tg, .rt_period = period, .rt_runtime = runtime, }; - return walk_tg_tree(tg_schedulable, tg_nop, &data); + rcu_read_lock(); + ret = walk_tg_tree(tg_rt_schedulable, tg_nop, &data); + rcu_read_unlock(); + + return ret; } -static int tg_set_bandwidth(struct task_group *tg, +static int tg_set_rt_bandwidth(struct task_group *tg, u64 rt_period, u64 rt_runtime) { int i, err = 0; @@ -8786,7 +8962,7 @@ int sched_group_set_rt_runtime(struct task_group *tg, long rt_runtime_us) if (rt_runtime_us < 0) rt_runtime = RUNTIME_INF; - return tg_set_bandwidth(tg, rt_period, rt_runtime); + return tg_set_rt_bandwidth(tg, rt_period, rt_runtime); } long sched_group_rt_runtime(struct task_group *tg) @@ -8811,7 +8987,7 @@ int sched_group_set_rt_period(struct task_group *tg, long rt_period_us) if (rt_period == 0) return -EINVAL; - return tg_set_bandwidth(tg, rt_period, rt_runtime); + return tg_set_rt_bandwidth(tg, rt_period, rt_runtime); } long sched_group_rt_period(struct task_group *tg) @@ -9001,6 +9177,238 @@ static u64 cpu_shares_read_u64(struct cgroup *cgrp, struct cftype *cft) return (u64) scale_load_down(tg->shares); } + +#ifdef CONFIG_CFS_BANDWIDTH +static DEFINE_MUTEX(cfs_constraints_mutex); + +const u64 max_cfs_quota_period = 1 * NSEC_PER_SEC; /* 1s */ +const u64 min_cfs_quota_period = 1 * NSEC_PER_MSEC; /* 1ms */ + +static int __cfs_schedulable(struct task_group *tg, u64 period, u64 runtime); + +static int tg_set_cfs_bandwidth(struct task_group *tg, u64 period, u64 quota) +{ + int i, ret = 0, runtime_enabled; + struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(tg); + + if (tg == &root_task_group) + return -EINVAL; + + /* + * Ensure we have at some amount of bandwidth every period. This is + * to prevent reaching a state of large arrears when throttled via + * entity_tick() resulting in prolonged exit starvation. + */ + if (quota < min_cfs_quota_period || period < min_cfs_quota_period) + return -EINVAL; + + /* + * Likewise, bound things on the otherside by preventing insane quota + * periods. This also allows us to normalize in computing quota + * feasibility. + */ + if (period > max_cfs_quota_period) + return -EINVAL; + + mutex_lock(&cfs_constraints_mutex); + ret = __cfs_schedulable(tg, period, quota); + if (ret) + goto out_unlock; + + runtime_enabled = quota != RUNTIME_INF; + raw_spin_lock_irq(&cfs_b->lock); + cfs_b->period = ns_to_ktime(period); + cfs_b->quota = quota; + + __refill_cfs_bandwidth_runtime(cfs_b); + /* restart the period timer (if active) to handle new period expiry */ + if (runtime_enabled && cfs_b->timer_active) { + /* force a reprogram */ + cfs_b->timer_active = 0; + __start_cfs_bandwidth(cfs_b); + } + raw_spin_unlock_irq(&cfs_b->lock); + + for_each_possible_cpu(i) { + struct cfs_rq *cfs_rq = tg->cfs_rq[i]; + struct rq *rq = rq_of(cfs_rq); + + raw_spin_lock_irq(&rq->lock); + cfs_rq->runtime_enabled = runtime_enabled; + cfs_rq->runtime_remaining = 0; + + if (cfs_rq_throttled(cfs_rq)) + unthrottle_cfs_rq(cfs_rq); + raw_spin_unlock_irq(&rq->lock); + } +out_unlock: + mutex_unlock(&cfs_constraints_mutex); + + return ret; +} + +int tg_set_cfs_quota(struct task_group *tg, long cfs_quota_us) +{ + u64 quota, period; + + period = ktime_to_ns(tg_cfs_bandwidth(tg)->period); + if (cfs_quota_us < 0) + quota = RUNTIME_INF; + else + quota = (u64)cfs_quota_us * NSEC_PER_USEC; + + return tg_set_cfs_bandwidth(tg, period, quota); +} + +long tg_get_cfs_quota(struct task_group *tg) +{ + u64 quota_us; + + if (tg_cfs_bandwidth(tg)->quota == RUNTIME_INF) + return -1; + + quota_us = tg_cfs_bandwidth(tg)->quota; + do_div(quota_us, NSEC_PER_USEC); + + return quota_us; +} + +int tg_set_cfs_period(struct task_group *tg, long cfs_period_us) +{ + u64 quota, period; + + period = (u64)cfs_period_us * NSEC_PER_USEC; + quota = tg_cfs_bandwidth(tg)->quota; + + if (period <= 0) + return -EINVAL; + + return tg_set_cfs_bandwidth(tg, period, quota); +} + +long tg_get_cfs_period(struct task_group *tg) +{ + u64 cfs_period_us; + + cfs_period_us = ktime_to_ns(tg_cfs_bandwidth(tg)->period); + do_div(cfs_period_us, NSEC_PER_USEC); + + return cfs_period_us; +} + +static s64 cpu_cfs_quota_read_s64(struct cgroup *cgrp, struct cftype *cft) +{ + return tg_get_cfs_quota(cgroup_tg(cgrp)); +} + +static int cpu_cfs_quota_write_s64(struct cgroup *cgrp, struct cftype *cftype, + s64 cfs_quota_us) +{ + return tg_set_cfs_quota(cgroup_tg(cgrp), cfs_quota_us); +} + +static u64 cpu_cfs_period_read_u64(struct cgroup *cgrp, struct cftype *cft) +{ + return tg_get_cfs_period(cgroup_tg(cgrp)); +} + +static int cpu_cfs_period_write_u64(struct cgroup *cgrp, struct cftype *cftype, + u64 cfs_period_us) +{ + return tg_set_cfs_period(cgroup_tg(cgrp), cfs_period_us); +} + +struct cfs_schedulable_data { + struct task_group *tg; + u64 period, quota; +}; + +/* + * normalize group quota/period to be quota/max_period + * note: units are usecs + */ +static u64 normalize_cfs_quota(struct task_group *tg, + struct cfs_schedulable_data *d) +{ + u64 quota, period; + + if (tg == d->tg) { + period = d->period; + quota = d->quota; + } else { + period = tg_get_cfs_period(tg); + quota = tg_get_cfs_quota(tg); + } + + /* note: these should typically be equivalent */ + if (quota == RUNTIME_INF || quota == -1) + return RUNTIME_INF; + + return to_ratio(period, quota); +} + +static int tg_cfs_schedulable_down(struct task_group *tg, void *data) +{ + struct cfs_schedulable_data *d = data; + struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(tg); + s64 quota = 0, parent_quota = -1; + + if (!tg->parent) { + quota = RUNTIME_INF; + } else { + struct cfs_bandwidth *parent_b = tg_cfs_bandwidth(tg->parent); + + quota = normalize_cfs_quota(tg, d); + parent_quota = parent_b->hierarchal_quota; + + /* + * ensure max(child_quota) <= parent_quota, inherit when no + * limit is set + */ + if (quota == RUNTIME_INF) + quota = parent_quota; + else if (parent_quota != RUNTIME_INF && quota > parent_quota) + return -EINVAL; + } + cfs_b->hierarchal_quota = quota; + + return 0; +} + +static int __cfs_schedulable(struct task_group *tg, u64 period, u64 quota) +{ + int ret; + struct cfs_schedulable_data data = { + .tg = tg, + .period = period, + .quota = quota, + }; + + if (quota != RUNTIME_INF) { + do_div(data.period, NSEC_PER_USEC); + do_div(data.quota, NSEC_PER_USEC); + } + + rcu_read_lock(); + ret = walk_tg_tree(tg_cfs_schedulable_down, tg_nop, &data); + rcu_read_unlock(); + + return ret; +} + +static int cpu_stats_show(struct cgroup *cgrp, struct cftype *cft, + struct cgroup_map_cb *cb) +{ + struct task_group *tg = cgroup_tg(cgrp); + struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(tg); + + cb->fill(cb, "nr_periods", cfs_b->nr_periods); + cb->fill(cb, "nr_throttled", cfs_b->nr_throttled); + cb->fill(cb, "throttled_time", cfs_b->throttled_time); + + return 0; +} +#endif /* CONFIG_CFS_BANDWIDTH */ #endif /* CONFIG_FAIR_GROUP_SCHED */ #ifdef CONFIG_RT_GROUP_SCHED @@ -9035,6 +9443,22 @@ static struct cftype cpu_files[] = { .write_u64 = cpu_shares_write_u64, }, #endif +#ifdef CONFIG_CFS_BANDWIDTH + { + .name = "cfs_quota_us", + .read_s64 = cpu_cfs_quota_read_s64, + .write_s64 = cpu_cfs_quota_write_s64, + }, + { + .name = "cfs_period_us", + .read_u64 = cpu_cfs_period_read_u64, + .write_u64 = cpu_cfs_period_write_u64, + }, + { + .name = "stat", + .read_map = cpu_stats_show, + }, +#endif #ifdef CONFIG_RT_GROUP_SCHED { .name = "rt_runtime_us", @@ -9344,4 +9768,3 @@ struct cgroup_subsys cpuacct_subsys = { .subsys_id = cpuacct_subsys_id, }; #endif /* CONFIG_CGROUP_CPUACCT */ - diff --git a/kernel/sched_cpupri.c b/kernel/sched_cpupri.c index 2722dc1..a86cf9d 100644 --- a/kernel/sched_cpupri.c +++ b/kernel/sched_cpupri.c @@ -47,9 +47,6 @@ static int convert_prio(int prio) return cpupri; } -#define for_each_cpupri_active(array, idx) \ - for_each_set_bit(idx, array, CPUPRI_NR_PRIORITIES) - /** * cpupri_find - find the best (lowest-pri) CPU in the system * @cp: The cpupri context @@ -71,11 +68,38 @@ int cpupri_find(struct cpupri *cp, struct task_struct *p, int idx = 0; int task_pri = convert_prio(p->prio); - for_each_cpupri_active(cp->pri_active, idx) { - struct cpupri_vec *vec = &cp->pri_to_cpu[idx]; + if (task_pri >= MAX_RT_PRIO) + return 0; - if (idx >= task_pri) - break; + for (idx = 0; idx < task_pri; idx++) { + struct cpupri_vec *vec = &cp->pri_to_cpu[idx]; + int skip = 0; + + if (!atomic_read(&(vec)->count)) + skip = 1; + /* + * When looking at the vector, we need to read the counter, + * do a memory barrier, then read the mask. + * + * Note: This is still all racey, but we can deal with it. + * Ideally, we only want to look at masks that are set. + * + * If a mask is not set, then the only thing wrong is that we + * did a little more work than necessary. + * + * If we read a zero count but the mask is set, because of the + * memory barriers, that can only happen when the highest prio + * task for a run queue has left the run queue, in which case, + * it will be followed by a pull. If the task we are processing + * fails to find a proper place to go, that pull request will + * pull this task if the run queue is running at a lower + * priority. + */ + smp_rmb(); + + /* Need to do the rmb for every iteration */ + if (skip) + continue; if (cpumask_any_and(&p->cpus_allowed, vec->mask) >= nr_cpu_ids) continue; @@ -115,7 +139,7 @@ void cpupri_set(struct cpupri *cp, int cpu, int newpri) { int *currpri = &cp->cpu_to_pri[cpu]; int oldpri = *currpri; - unsigned long flags; + int do_mb = 0; newpri = convert_prio(newpri); @@ -128,32 +152,46 @@ void cpupri_set(struct cpupri *cp, int cpu, int newpri) * If the cpu was currently mapped to a different value, we * need to map it to the new value then remove the old value. * Note, we must add the new value first, otherwise we risk the - * cpu being cleared from pri_active, and this cpu could be - * missed for a push or pull. + * cpu being missed by the priority loop in cpupri_find. */ if (likely(newpri != CPUPRI_INVALID)) { struct cpupri_vec *vec = &cp->pri_to_cpu[newpri]; - raw_spin_lock_irqsave(&vec->lock, flags); - cpumask_set_cpu(cpu, vec->mask); - vec->count++; - if (vec->count == 1) - set_bit(newpri, cp->pri_active); - - raw_spin_unlock_irqrestore(&vec->lock, flags); + /* + * When adding a new vector, we update the mask first, + * do a write memory barrier, and then update the count, to + * make sure the vector is visible when count is set. + */ + smp_mb__before_atomic_inc(); + atomic_inc(&(vec)->count); + do_mb = 1; } if (likely(oldpri != CPUPRI_INVALID)) { struct cpupri_vec *vec = &cp->pri_to_cpu[oldpri]; - raw_spin_lock_irqsave(&vec->lock, flags); - - vec->count--; - if (!vec->count) - clear_bit(oldpri, cp->pri_active); + /* + * Because the order of modification of the vec->count + * is important, we must make sure that the update + * of the new prio is seen before we decrement the + * old prio. This makes sure that the loop sees + * one or the other when we raise the priority of + * the run queue. We don't care about when we lower the + * priority, as that will trigger an rt pull anyway. + * + * We only need to do a memory barrier if we updated + * the new priority vec. + */ + if (do_mb) + smp_mb__after_atomic_inc(); + + /* + * When removing from the vector, we decrement the counter first + * do a memory barrier and then clear the mask. + */ + atomic_dec(&(vec)->count); + smp_mb__after_atomic_inc(); cpumask_clear_cpu(cpu, vec->mask); - - raw_spin_unlock_irqrestore(&vec->lock, flags); } *currpri = newpri; @@ -175,8 +213,7 @@ int cpupri_init(struct cpupri *cp) for (i = 0; i < CPUPRI_NR_PRIORITIES; i++) { struct cpupri_vec *vec = &cp->pri_to_cpu[i]; - raw_spin_lock_init(&vec->lock); - vec->count = 0; + atomic_set(&vec->count, 0); if (!zalloc_cpumask_var(&vec->mask, GFP_KERNEL)) goto cleanup; } diff --git a/kernel/sched_cpupri.h b/kernel/sched_cpupri.h index 9fc7d38..f6d7561 100644 --- a/kernel/sched_cpupri.h +++ b/kernel/sched_cpupri.h @@ -4,7 +4,6 @@ #include <linux/sched.h> #define CPUPRI_NR_PRIORITIES (MAX_RT_PRIO + 2) -#define CPUPRI_NR_PRI_WORDS BITS_TO_LONGS(CPUPRI_NR_PRIORITIES) #define CPUPRI_INVALID -1 #define CPUPRI_IDLE 0 @@ -12,14 +11,12 @@ /* values 2-101 are RT priorities 0-99 */ struct cpupri_vec { - raw_spinlock_t lock; - int count; - cpumask_var_t mask; + atomic_t count; + cpumask_var_t mask; }; struct cpupri { struct cpupri_vec pri_to_cpu[CPUPRI_NR_PRIORITIES]; - long pri_active[CPUPRI_NR_PRI_WORDS]; int cpu_to_pri[NR_CPUS]; }; diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c index bc8ee99..5c9e679 100644 --- a/kernel/sched_fair.c +++ b/kernel/sched_fair.c @@ -89,6 +89,20 @@ const_debug unsigned int sysctl_sched_migration_cost = 500000UL; */ unsigned int __read_mostly sysctl_sched_shares_window = 10000000UL; +#ifdef CONFIG_CFS_BANDWIDTH +/* + * Amount of runtime to allocate from global (tg) to local (per-cfs_rq) pool + * each time a cfs_rq requests quota. + * + * Note: in the case that the slice exceeds the runtime remaining (either due + * to consumption or the quota being specified to be smaller than the slice) + * we will always only issue the remaining available time. + * + * default: 5 msec, units: microseconds + */ +unsigned int sysctl_sched_cfs_bandwidth_slice = 5000UL; +#endif + static const struct sched_class fair_sched_class; /************************************************************** @@ -292,6 +306,8 @@ find_matching_se(struct sched_entity **se, struct sched_entity **pse) #endif /* CONFIG_FAIR_GROUP_SCHED */ +static void account_cfs_rq_runtime(struct cfs_rq *cfs_rq, + unsigned long delta_exec); /************************************************************** * Scheduling class tree data structure manipulation methods: @@ -583,6 +599,8 @@ static void update_curr(struct cfs_rq *cfs_rq) cpuacct_charge(curtask, delta_exec); account_group_exec_runtime(curtask, delta_exec); } + + account_cfs_rq_runtime(cfs_rq, delta_exec); } static inline void @@ -688,6 +706,8 @@ account_entity_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se) } #ifdef CONFIG_FAIR_GROUP_SCHED +/* we need this in update_cfs_load and load-balance functions below */ +static inline int throttled_hierarchy(struct cfs_rq *cfs_rq); # ifdef CONFIG_SMP static void update_cfs_rq_load_contribution(struct cfs_rq *cfs_rq, int global_update) @@ -710,7 +730,7 @@ static void update_cfs_load(struct cfs_rq *cfs_rq, int global_update) u64 now, delta; unsigned long load = cfs_rq->load.weight; - if (cfs_rq->tg == &root_task_group) + if (cfs_rq->tg == &root_task_group || throttled_hierarchy(cfs_rq)) return; now = rq_of(cfs_rq)->clock_task; @@ -819,7 +839,7 @@ static void update_cfs_shares(struct cfs_rq *cfs_rq) tg = cfs_rq->tg; se = tg->se[cpu_of(rq_of(cfs_rq))]; - if (!se) + if (!se || throttled_hierarchy(cfs_rq)) return; #ifndef CONFIG_SMP if (likely(se->load.weight == tg->shares)) @@ -950,6 +970,8 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial) se->vruntime = vruntime; } +static void check_enqueue_throttle(struct cfs_rq *cfs_rq); + static void enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) { @@ -979,8 +1001,10 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) __enqueue_entity(cfs_rq, se); se->on_rq = 1; - if (cfs_rq->nr_running == 1) + if (cfs_rq->nr_running == 1) { list_add_leaf_cfs_rq(cfs_rq); + check_enqueue_throttle(cfs_rq); + } } static void __clear_buddies_last(struct sched_entity *se) @@ -1028,6 +1052,8 @@ static void clear_buddies(struct cfs_rq *cfs_rq, struct sched_entity *se) __clear_buddies_skip(se); } +static void return_cfs_rq_runtime(struct cfs_rq *cfs_rq); + static void dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) { @@ -1066,6 +1092,9 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) if (!(flags & DEQUEUE_SLEEP)) se->vruntime -= cfs_rq->min_vruntime; + /* return excess runtime on last dequeue */ + return_cfs_rq_runtime(cfs_rq); + update_min_vruntime(cfs_rq); update_cfs_shares(cfs_rq); } @@ -1077,6 +1106,8 @@ static void check_preempt_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr) { unsigned long ideal_runtime, delta_exec; + struct sched_entity *se; + s64 delta; ideal_runtime = sched_slice(cfs_rq, curr); delta_exec = curr->sum_exec_runtime - curr->prev_sum_exec_runtime; @@ -1095,22 +1126,17 @@ check_preempt_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr) * narrow margin doesn't have to wait for a full slice. * This also mitigates buddy induced latencies under load. */ - if (!sched_feat(WAKEUP_PREEMPT)) - return; - if (delta_exec < sysctl_sched_min_granularity) return; - if (cfs_rq->nr_running > 1) { - struct sched_entity *se = __pick_first_entity(cfs_rq); - s64 delta = curr->vruntime - se->vruntime; + se = __pick_first_entity(cfs_rq); + delta = curr->vruntime - se->vruntime; - if (delta < 0) - return; + if (delta < 0) + return; - if (delta > ideal_runtime) - resched_task(rq_of(cfs_rq)->curr); - } + if (delta > ideal_runtime) + resched_task(rq_of(cfs_rq)->curr); } static void @@ -1185,6 +1211,8 @@ static struct sched_entity *pick_next_entity(struct cfs_rq *cfs_rq) return se; } +static void check_cfs_rq_runtime(struct cfs_rq *cfs_rq); + static void put_prev_entity(struct cfs_rq *cfs_rq, struct sched_entity *prev) { /* @@ -1194,6 +1222,9 @@ static void put_prev_entity(struct cfs_rq *cfs_rq, struct sched_entity *prev) if (prev->on_rq) update_curr(cfs_rq); + /* throttle cfs_rqs exceeding runtime */ + check_cfs_rq_runtime(cfs_rq); + check_spread(cfs_rq, prev); if (prev->on_rq) { update_stats_wait_start(cfs_rq, prev); @@ -1233,10 +1264,583 @@ entity_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr, int queued) return; #endif - if (cfs_rq->nr_running > 1 || !sched_feat(WAKEUP_PREEMPT)) + if (cfs_rq->nr_running > 1) check_preempt_tick(cfs_rq, curr); } + +/************************************************** + * CFS bandwidth control machinery + */ + +#ifdef CONFIG_CFS_BANDWIDTH +/* + * default period for cfs group bandwidth. + * default: 0.1s, units: nanoseconds + */ +static inline u64 default_cfs_period(void) +{ + return 100000000ULL; +} + +static inline u64 sched_cfs_bandwidth_slice(void) +{ + return (u64)sysctl_sched_cfs_bandwidth_slice * NSEC_PER_USEC; +} + +/* + * Replenish runtime according to assigned quota and update expiration time. + * We use sched_clock_cpu directly instead of rq->clock to avoid adding + * additional synchronization around rq->lock. + * + * requires cfs_b->lock + */ +static void __refill_cfs_bandwidth_runtime(struct cfs_bandwidth *cfs_b) +{ + u64 now; + + if (cfs_b->quota == RUNTIME_INF) + return; + + now = sched_clock_cpu(smp_processor_id()); + cfs_b->runtime = cfs_b->quota; + cfs_b->runtime_expires = now + ktime_to_ns(cfs_b->period); +} + +/* returns 0 on failure to allocate runtime */ +static int assign_cfs_rq_runtime(struct cfs_rq *cfs_rq) +{ + struct task_group *tg = cfs_rq->tg; + struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(tg); + u64 amount = 0, min_amount, expires; + + /* note: this is a positive sum as runtime_remaining <= 0 */ + min_amount = sched_cfs_bandwidth_slice() - cfs_rq->runtime_remaining; + + raw_spin_lock(&cfs_b->lock); + if (cfs_b->quota == RUNTIME_INF) + amount = min_amount; + else { + /* + * If the bandwidth pool has become inactive, then at least one + * period must have elapsed since the last consumption. + * Refresh the global state and ensure bandwidth timer becomes + * active. + */ + if (!cfs_b->timer_active) { + __refill_cfs_bandwidth_runtime(cfs_b); + __start_cfs_bandwidth(cfs_b); + } + + if (cfs_b->runtime > 0) { + amount = min(cfs_b->runtime, min_amount); + cfs_b->runtime -= amount; + cfs_b->idle = 0; + } + } + expires = cfs_b->runtime_expires; + raw_spin_unlock(&cfs_b->lock); + + cfs_rq->runtime_remaining += amount; + /* + * we may have advanced our local expiration to account for allowed + * spread between our sched_clock and the one on which runtime was + * issued. + */ + if ((s64)(expires - cfs_rq->runtime_expires) > 0) + cfs_rq->runtime_expires = expires; + + return cfs_rq->runtime_remaining > 0; +} + +/* + * Note: This depends on the synchronization provided by sched_clock and the + * fact that rq->clock snapshots this value. + */ +static void expire_cfs_rq_runtime(struct cfs_rq *cfs_rq) +{ + struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg); + struct rq *rq = rq_of(cfs_rq); + + /* if the deadline is ahead of our clock, nothing to do */ + if (likely((s64)(rq->clock - cfs_rq->runtime_expires) < 0)) + return; + + if (cfs_rq->runtime_remaining < 0) + return; + + /* + * If the local deadline has passed we have to consider the + * possibility that our sched_clock is 'fast' and the global deadline + * has not truly expired. + * + * Fortunately we can check determine whether this the case by checking + * whether the global deadline has advanced. + */ + + if ((s64)(cfs_rq->runtime_expires - cfs_b->runtime_expires) >= 0) { + /* extend local deadline, drift is bounded above by 2 ticks */ + cfs_rq->runtime_expires += TICK_NSEC; + } else { + /* global deadline is ahead, expiration has passed */ + cfs_rq->runtime_remaining = 0; + } +} + +static void __account_cfs_rq_runtime(struct cfs_rq *cfs_rq, + unsigned long delta_exec) +{ + /* dock delta_exec before expiring quota (as it could span periods) */ + cfs_rq->runtime_remaining -= delta_exec; + expire_cfs_rq_runtime(cfs_rq); + + if (likely(cfs_rq->runtime_remaining > 0)) + return; + + /* + * if we're unable to extend our runtime we resched so that the active + * hierarchy can be throttled + */ + if (!assign_cfs_rq_runtime(cfs_rq) && likely(cfs_rq->curr)) + resched_task(rq_of(cfs_rq)->curr); +} + +static __always_inline void account_cfs_rq_runtime(struct cfs_rq *cfs_rq, + unsigned long delta_exec) +{ + if (!cfs_rq->runtime_enabled) + return; + + __account_cfs_rq_runtime(cfs_rq, delta_exec); +} + +static inline int cfs_rq_throttled(struct cfs_rq *cfs_rq) +{ + return cfs_rq->throttled; +} + +/* check whether cfs_rq, or any parent, is throttled */ +static inline int throttled_hierarchy(struct cfs_rq *cfs_rq) +{ + return cfs_rq->throttle_count; +} + +/* + * Ensure that neither of the group entities corresponding to src_cpu or + * dest_cpu are members of a throttled hierarchy when performing group + * load-balance operations. + */ +static inline int throttled_lb_pair(struct task_group *tg, + int src_cpu, int dest_cpu) +{ + struct cfs_rq *src_cfs_rq, *dest_cfs_rq; + + src_cfs_rq = tg->cfs_rq[src_cpu]; + dest_cfs_rq = tg->cfs_rq[dest_cpu]; + + return throttled_hierarchy(src_cfs_rq) || + throttled_hierarchy(dest_cfs_rq); +} + +/* updated child weight may affect parent so we have to do this bottom up */ +static int tg_unthrottle_up(struct task_group *tg, void *data) +{ + struct rq *rq = data; + struct cfs_rq *cfs_rq = tg->cfs_rq[cpu_of(rq)]; + + cfs_rq->throttle_count--; +#ifdef CONFIG_SMP + if (!cfs_rq->throttle_count) { + u64 delta = rq->clock_task - cfs_rq->load_stamp; + + /* leaving throttled state, advance shares averaging windows */ + cfs_rq->load_stamp += delta; + cfs_rq->load_last += delta; + + /* update entity weight now that we are on_rq again */ + update_cfs_shares(cfs_rq); + } +#endif + + return 0; +} + +static int tg_throttle_down(struct task_group *tg, void *data) +{ + struct rq *rq = data; + struct cfs_rq *cfs_rq = tg->cfs_rq[cpu_of(rq)]; + + /* group is entering throttled state, record last load */ + if (!cfs_rq->throttle_count) + update_cfs_load(cfs_rq, 0); + cfs_rq->throttle_count++; + + return 0; +} + +static void throttle_cfs_rq(struct cfs_rq *cfs_rq) +{ + struct rq *rq = rq_of(cfs_rq); + struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg); + struct sched_entity *se; + long task_delta, dequeue = 1; + + se = cfs_rq->tg->se[cpu_of(rq_of(cfs_rq))]; + + /* account load preceding throttle */ + rcu_read_lock(); + walk_tg_tree_from(cfs_rq->tg, tg_throttle_down, tg_nop, (void *)rq); + rcu_read_unlock(); + + task_delta = cfs_rq->h_nr_running; + for_each_sched_entity(se) { + struct cfs_rq *qcfs_rq = cfs_rq_of(se); + /* throttled entity or throttle-on-deactivate */ + if (!se->on_rq) + break; + + if (dequeue) + dequeue_entity(qcfs_rq, se, DEQUEUE_SLEEP); + qcfs_rq->h_nr_running -= task_delta; + + if (qcfs_rq->load.weight) + dequeue = 0; + } + + if (!se) + rq->nr_running -= task_delta; + + cfs_rq->throttled = 1; + cfs_rq->throttled_timestamp = rq->clock; + raw_spin_lock(&cfs_b->lock); + list_add_tail_rcu(&cfs_rq->throttled_list, &cfs_b->throttled_cfs_rq); + raw_spin_unlock(&cfs_b->lock); +} + +static void unthrottle_cfs_rq(struct cfs_rq *cfs_rq) +{ + struct rq *rq = rq_of(cfs_rq); + struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg); + struct sched_entity *se; + int enqueue = 1; + long task_delta; + + se = cfs_rq->tg->se[cpu_of(rq_of(cfs_rq))]; + + cfs_rq->throttled = 0; + raw_spin_lock(&cfs_b->lock); + cfs_b->throttled_time += rq->clock - cfs_rq->throttled_timestamp; + list_del_rcu(&cfs_rq->throttled_list); + raw_spin_unlock(&cfs_b->lock); + cfs_rq->throttled_timestamp = 0; + + update_rq_clock(rq); + /* update hierarchical throttle state */ + walk_tg_tree_from(cfs_rq->tg, tg_nop, tg_unthrottle_up, (void *)rq); + + if (!cfs_rq->load.weight) + return; + + task_delta = cfs_rq->h_nr_running; + for_each_sched_entity(se) { + if (se->on_rq) + enqueue = 0; + + cfs_rq = cfs_rq_of(se); + if (enqueue) + enqueue_entity(cfs_rq, se, ENQUEUE_WAKEUP); + cfs_rq->h_nr_running += task_delta; + + if (cfs_rq_throttled(cfs_rq)) + break; + } + + if (!se) + rq->nr_running += task_delta; + + /* determine whether we need to wake up potentially idle cpu */ + if (rq->curr == rq->idle && rq->cfs.nr_running) + resched_task(rq->curr); +} + +static u64 distribute_cfs_runtime(struct cfs_bandwidth *cfs_b, + u64 remaining, u64 expires) +{ + struct cfs_rq *cfs_rq; + u64 runtime = remaining; + + rcu_read_lock(); + list_for_each_entry_rcu(cfs_rq, &cfs_b->throttled_cfs_rq, + throttled_list) { + struct rq *rq = rq_of(cfs_rq); + + raw_spin_lock(&rq->lock); + if (!cfs_rq_throttled(cfs_rq)) + goto next; + + runtime = -cfs_rq->runtime_remaining + 1; + if (runtime > remaining) + runtime = remaining; + remaining -= runtime; + + cfs_rq->runtime_remaining += runtime; + cfs_rq->runtime_expires = expires; + + /* we check whether we're throttled above */ + if (cfs_rq->runtime_remaining > 0) + unthrottle_cfs_rq(cfs_rq); + +next: + raw_spin_unlock(&rq->lock); + + if (!remaining) + break; + } + rcu_read_unlock(); + + return remaining; +} + +/* + * Responsible for refilling a task_group's bandwidth and unthrottling its + * cfs_rqs as appropriate. If there has been no activity within the last + * period the timer is deactivated until scheduling resumes; cfs_b->idle is + * used to track this state. + */ +static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun) +{ + u64 runtime, runtime_expires; + int idle = 1, throttled; + + raw_spin_lock(&cfs_b->lock); + /* no need to continue the timer with no bandwidth constraint */ + if (cfs_b->quota == RUNTIME_INF) + goto out_unlock; + + throttled = !list_empty(&cfs_b->throttled_cfs_rq); + /* idle depends on !throttled (for the case of a large deficit) */ + idle = cfs_b->idle && !throttled; + cfs_b->nr_periods += overrun; + + /* if we're going inactive then everything else can be deferred */ + if (idle) + goto out_unlock; + + __refill_cfs_bandwidth_runtime(cfs_b); + + if (!throttled) { + /* mark as potentially idle for the upcoming period */ + cfs_b->idle = 1; + goto out_unlock; + } + + /* account preceding periods in which throttling occurred */ + cfs_b->nr_throttled += overrun; + + /* + * There are throttled entities so we must first use the new bandwidth + * to unthrottle them before making it generally available. This + * ensures that all existing debts will be paid before a new cfs_rq is + * allowed to run. + */ + runtime = cfs_b->runtime; + runtime_expires = cfs_b->runtime_expires; + cfs_b->runtime = 0; + + /* + * This check is repeated as we are holding onto the new bandwidth + * while we unthrottle. This can potentially race with an unthrottled + * group trying to acquire new bandwidth from the global pool. + */ + while (throttled && runtime > 0) { + raw_spin_unlock(&cfs_b->lock); + /* we can't nest cfs_b->lock while distributing bandwidth */ + runtime = distribute_cfs_runtime(cfs_b, runtime, + runtime_expires); + raw_spin_lock(&cfs_b->lock); + + throttled = !list_empty(&cfs_b->throttled_cfs_rq); + } + + /* return (any) remaining runtime */ + cfs_b->runtime = runtime; + /* + * While we are ensured activity in the period following an + * unthrottle, this also covers the case in which the new bandwidth is + * insufficient to cover the existing bandwidth deficit. (Forcing the + * timer to remain active while there are any throttled entities.) + */ + cfs_b->idle = 0; +out_unlock: + if (idle) + cfs_b->timer_active = 0; + raw_spin_unlock(&cfs_b->lock); + + return idle; +} + +/* a cfs_rq won't donate quota below this amount */ +static const u64 min_cfs_rq_runtime = 1 * NSEC_PER_MSEC; +/* minimum remaining period time to redistribute slack quota */ +static const u64 min_bandwidth_expiration = 2 * NSEC_PER_MSEC; +/* how long we wait to gather additional slack before distributing */ +static const u64 cfs_bandwidth_slack_period = 5 * NSEC_PER_MSEC; + +/* are we near the end of the current quota period? */ +static int runtime_refresh_within(struct cfs_bandwidth *cfs_b, u64 min_expire) +{ + struct hrtimer *refresh_timer = &cfs_b->period_timer; + u64 remaining; + + /* if the call-back is running a quota refresh is already occurring */ + if (hrtimer_callback_running(refresh_timer)) + return 1; + + /* is a quota refresh about to occur? */ + remaining = ktime_to_ns(hrtimer_expires_remaining(refresh_timer)); + if (remaining < min_expire) + return 1; + + return 0; +} + +static void start_cfs_slack_bandwidth(struct cfs_bandwidth *cfs_b) +{ + u64 min_left = cfs_bandwidth_slack_period + min_bandwidth_expiration; + + /* if there's a quota refresh soon don't bother with slack */ + if (runtime_refresh_within(cfs_b, min_left)) + return; + + start_bandwidth_timer(&cfs_b->slack_timer, + ns_to_ktime(cfs_bandwidth_slack_period)); +} + +/* we know any runtime found here is valid as update_curr() precedes return */ +static void __return_cfs_rq_runtime(struct cfs_rq *cfs_rq) +{ + struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg); + s64 slack_runtime = cfs_rq->runtime_remaining - min_cfs_rq_runtime; + + if (slack_runtime <= 0) + return; + + raw_spin_lock(&cfs_b->lock); + if (cfs_b->quota != RUNTIME_INF && + cfs_rq->runtime_expires == cfs_b->runtime_expires) { + cfs_b->runtime += slack_runtime; + + /* we are under rq->lock, defer unthrottling using a timer */ + if (cfs_b->runtime > sched_cfs_bandwidth_slice() && + !list_empty(&cfs_b->throttled_cfs_rq)) + start_cfs_slack_bandwidth(cfs_b); + } + raw_spin_unlock(&cfs_b->lock); + + /* even if it's not valid for return we don't want to try again */ + cfs_rq->runtime_remaining -= slack_runtime; +} + +static __always_inline void return_cfs_rq_runtime(struct cfs_rq *cfs_rq) +{ + if (!cfs_rq->runtime_enabled || !cfs_rq->nr_running) + return; + + __return_cfs_rq_runtime(cfs_rq); +} + +/* + * This is done with a timer (instead of inline with bandwidth return) since + * it's necessary to juggle rq->locks to unthrottle their respective cfs_rqs. + */ +static void do_sched_cfs_slack_timer(struct cfs_bandwidth *cfs_b) +{ + u64 runtime = 0, slice = sched_cfs_bandwidth_slice(); + u64 expires; + + /* confirm we're still not at a refresh boundary */ + if (runtime_refresh_within(cfs_b, min_bandwidth_expiration)) + return; + + raw_spin_lock(&cfs_b->lock); + if (cfs_b->quota != RUNTIME_INF && cfs_b->runtime > slice) { + runtime = cfs_b->runtime; + cfs_b->runtime = 0; + } + expires = cfs_b->runtime_expires; + raw_spin_unlock(&cfs_b->lock); + + if (!runtime) + return; + + runtime = distribute_cfs_runtime(cfs_b, runtime, expires); + + raw_spin_lock(&cfs_b->lock); + if (expires == cfs_b->runtime_expires) + cfs_b->runtime = runtime; + raw_spin_unlock(&cfs_b->lock); +} + +/* + * When a group wakes up we want to make sure that its quota is not already + * expired/exceeded, otherwise it may be allowed to steal additional ticks of + * runtime as update_curr() throttling can not not trigger until it's on-rq. + */ +static void check_enqueue_throttle(struct cfs_rq *cfs_rq) +{ + /* an active group must be handled by the update_curr()->put() path */ + if (!cfs_rq->runtime_enabled || cfs_rq->curr) + return; + + /* ensure the group is not already throttled */ + if (cfs_rq_throttled(cfs_rq)) + return; + + /* update runtime allocation */ + account_cfs_rq_runtime(cfs_rq, 0); + if (cfs_rq->runtime_remaining <= 0) + throttle_cfs_rq(cfs_rq); +} + +/* conditionally throttle active cfs_rq's from put_prev_entity() */ +static void check_cfs_rq_runtime(struct cfs_rq *cfs_rq) +{ + if (likely(!cfs_rq->runtime_enabled || cfs_rq->runtime_remaining > 0)) + return; + + /* + * it's possible for a throttled entity to be forced into a running + * state (e.g. set_curr_task), in this case we're finished. + */ + if (cfs_rq_throttled(cfs_rq)) + return; + + throttle_cfs_rq(cfs_rq); +} +#else +static void account_cfs_rq_runtime(struct cfs_rq *cfs_rq, + unsigned long delta_exec) {} +static void check_cfs_rq_runtime(struct cfs_rq *cfs_rq) {} +static void check_enqueue_throttle(struct cfs_rq *cfs_rq) {} +static void return_cfs_rq_runtime(struct cfs_rq *cfs_rq) {} + +static inline int cfs_rq_throttled(struct cfs_rq *cfs_rq) +{ + return 0; +} + +static inline int throttled_hierarchy(struct cfs_rq *cfs_rq) +{ + return 0; +} + +static inline int throttled_lb_pair(struct task_group *tg, + int src_cpu, int dest_cpu) +{ + return 0; +} +#endif + /************************************************** * CFS operations on tasks: */ @@ -1313,16 +1917,33 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags) break; cfs_rq = cfs_rq_of(se); enqueue_entity(cfs_rq, se, flags); + + /* + * end evaluation on encountering a throttled cfs_rq + * + * note: in the case of encountering a throttled cfs_rq we will + * post the final h_nr_running increment below. + */ + if (cfs_rq_throttled(cfs_rq)) + break; + cfs_rq->h_nr_running++; + flags = ENQUEUE_WAKEUP; } for_each_sched_entity(se) { cfs_rq = cfs_rq_of(se); + cfs_rq->h_nr_running++; + + if (cfs_rq_throttled(cfs_rq)) + break; update_cfs_load(cfs_rq, 0); update_cfs_shares(cfs_rq); } + if (!se) + inc_nr_running(rq); hrtick_update(rq); } @@ -1343,6 +1964,16 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags) cfs_rq = cfs_rq_of(se); dequeue_entity(cfs_rq, se, flags); + /* + * end evaluation on encountering a throttled cfs_rq + * + * note: in the case of encountering a throttled cfs_rq we will + * post the final h_nr_running decrement below. + */ + if (cfs_rq_throttled(cfs_rq)) + break; + cfs_rq->h_nr_running--; + /* Don't dequeue parent if it has other entities besides us */ if (cfs_rq->load.weight) { /* @@ -1361,11 +1992,17 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags) for_each_sched_entity(se) { cfs_rq = cfs_rq_of(se); + cfs_rq->h_nr_running--; + + if (cfs_rq_throttled(cfs_rq)) + break; update_cfs_load(cfs_rq, 0); update_cfs_shares(cfs_rq); } + if (!se) + dec_nr_running(rq); hrtick_update(rq); } @@ -1434,7 +2071,6 @@ static long effective_load(struct task_group *tg, int cpu, long wl, long wg) return wl; } - #else static inline unsigned long effective_load(struct task_group *tg, int cpu, @@ -1547,7 +2183,7 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p, /* Skip over this group if it has no CPUs allowed */ if (!cpumask_intersects(sched_group_cpus(group), - &p->cpus_allowed)) + tsk_cpus_allowed(p))) continue; local_group = cpumask_test_cpu(this_cpu, @@ -1593,7 +2229,7 @@ find_idlest_cpu(struct sched_group *group, struct task_struct *p, int this_cpu) int i; /* Traverse only the allowed CPUs */ - for_each_cpu_and(i, sched_group_cpus(group), &p->cpus_allowed) { + for_each_cpu_and(i, sched_group_cpus(group), tsk_cpus_allowed(p)) { load = weighted_cpuload(i); if (load < min_load || (load == min_load && i == this_cpu)) { @@ -1637,7 +2273,7 @@ static int select_idle_sibling(struct task_struct *p, int target) if (!(sd->flags & SD_SHARE_PKG_RESOURCES)) break; - for_each_cpu_and(i, sched_domain_span(sd), &p->cpus_allowed) { + for_each_cpu_and(i, sched_domain_span(sd), tsk_cpus_allowed(p)) { if (idle_cpu(i)) { target = i; break; @@ -1680,7 +2316,7 @@ select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flags) int sync = wake_flags & WF_SYNC; if (sd_flag & SD_BALANCE_WAKE) { - if (cpumask_test_cpu(cpu, &p->cpus_allowed)) + if (cpumask_test_cpu(cpu, tsk_cpus_allowed(p))) want_affine = 1; new_cpu = prev_cpu; } @@ -1875,6 +2511,15 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_ if (unlikely(se == pse)) return; + /* + * This is possible from callers such as pull_task(), in which we + * unconditionally check_prempt_curr() after an enqueue (which may have + * lead to a throttle). This both saves work and prevents false + * next-buddy nomination below. + */ + if (unlikely(throttled_hierarchy(cfs_rq_of(pse)))) + return; + if (sched_feat(NEXT_BUDDY) && scale && !(wake_flags & WF_FORK)) { set_next_buddy(pse); next_buddy_marked = 1; @@ -1883,6 +2528,12 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_ /* * We can come here with TIF_NEED_RESCHED already set from new task * wake up path. + * + * Note: this also catches the edge-case of curr being in a throttled + * group (e.g. via set_curr_task), since update_curr() (in the + * enqueue of curr) will have resulted in resched being set. This + * prevents us from potentially nominating it as a false LAST_BUDDY + * below. */ if (test_tsk_need_resched(curr)) return; @@ -1899,10 +2550,6 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_ if (unlikely(p->policy != SCHED_NORMAL)) return; - - if (!sched_feat(WAKEUP_PREEMPT)) - return; - find_matching_se(&se, &pse); update_curr(cfs_rq_of(se)); BUG_ON(!pse); @@ -2005,7 +2652,8 @@ static bool yield_to_task_fair(struct rq *rq, struct task_struct *p, bool preemp { struct sched_entity *se = &p->se; - if (!se->on_rq) + /* throttled hierarchies are not runnable */ + if (!se->on_rq || throttled_hierarchy(cfs_rq_of(se))) return false; /* Tell the scheduler that we'd really like pse to run next. */ @@ -2049,7 +2697,7 @@ int can_migrate_task(struct task_struct *p, struct rq *rq, int this_cpu, * 2) cannot be migrated to this CPU due to cpus_allowed, or * 3) are cache-hot on their current CPU. */ - if (!cpumask_test_cpu(this_cpu, &p->cpus_allowed)) { + if (!cpumask_test_cpu(this_cpu, tsk_cpus_allowed(p))) { schedstat_inc(p, se.statistics.nr_failed_migrations_affine); return 0; } @@ -2102,6 +2750,9 @@ move_one_task(struct rq *this_rq, int this_cpu, struct rq *busiest, for_each_leaf_cfs_rq(busiest, cfs_rq) { list_for_each_entry_safe(p, n, &cfs_rq->tasks, se.group_node) { + if (throttled_lb_pair(task_group(p), + busiest->cpu, this_cpu)) + break; if (!can_migrate_task(p, busiest, this_cpu, sd, idle, &pinned)) @@ -2217,8 +2868,13 @@ static void update_shares(int cpu) * Iterates the task_group tree in a bottom up fashion, see * list_add_leaf_cfs_rq() for details. */ - for_each_leaf_cfs_rq(rq, cfs_rq) + for_each_leaf_cfs_rq(rq, cfs_rq) { + /* throttled entities do not contribute to load */ + if (throttled_hierarchy(cfs_rq)) + continue; + update_shares_cpu(cfs_rq->tg, cpu); + } rcu_read_unlock(); } @@ -2268,9 +2924,10 @@ load_balance_fair(struct rq *this_rq, int this_cpu, struct rq *busiest, u64 rem_load, moved_load; /* - * empty group + * empty group or part of a throttled hierarchy */ - if (!busiest_cfs_rq->task_weight) + if (!busiest_cfs_rq->task_weight || + throttled_lb_pair(busiest_cfs_rq->tg, cpu_of(busiest), this_cpu)) continue; rem_load = (u64)rem_load_move * busiest_weight; @@ -3430,7 +4087,7 @@ redo: * moved to this_cpu */ if (!cpumask_test_cpu(this_cpu, - &busiest->curr->cpus_allowed)) { + tsk_cpus_allowed(busiest->curr))) { raw_spin_unlock_irqrestore(&busiest->lock, flags); all_pinned = 1; @@ -3612,22 +4269,6 @@ out_unlock: } #ifdef CONFIG_NO_HZ - -static DEFINE_PER_CPU(struct call_single_data, remote_sched_softirq_cb); - -static void trigger_sched_softirq(void *data) -{ - raise_softirq_irqoff(SCHED_SOFTIRQ); -} - -static inline void init_sched_softirq_csd(struct call_single_data *csd) -{ - csd->func = trigger_sched_softirq; - csd->info = NULL; - csd->flags = 0; - csd->priv = 0; -} - /* * idle load balancing details * - One of the idle CPUs nominates itself as idle load_balancer, while @@ -3667,7 +4308,7 @@ static inline struct sched_domain *lowest_flag_domain(int cpu, int flag) struct sched_domain *sd; for_each_domain(cpu, sd) - if (sd && (sd->flags & flag)) + if (sd->flags & flag) break; return sd; @@ -3793,11 +4434,16 @@ static void nohz_balancer_kick(int cpu) } if (!cpu_rq(ilb_cpu)->nohz_balance_kick) { - struct call_single_data *cp; - cpu_rq(ilb_cpu)->nohz_balance_kick = 1; - cp = &per_cpu(remote_sched_softirq_cb, cpu); - __smp_call_function_single(ilb_cpu, cp, 0); + + smp_mb(); + /* + * Use smp_send_reschedule() instead of resched_cpu(). + * This way we generate a sched IPI on the target cpu which + * is idle. And the softirq performing nohz idle load balance + * will be run before returning from the IPI. + */ + smp_send_reschedule(ilb_cpu); } return; } @@ -4030,7 +4676,7 @@ static inline int nohz_kick_needed(struct rq *rq, int cpu) if (time_before(now, nohz.next_balance)) return 0; - if (rq->idle_at_tick) + if (idle_cpu(cpu)) return 0; first_pick_cpu = atomic_read(&nohz.first_pick_cpu); @@ -4066,7 +4712,7 @@ static void run_rebalance_domains(struct softirq_action *h) { int this_cpu = smp_processor_id(); struct rq *this_rq = cpu_rq(this_cpu); - enum cpu_idle_type idle = this_rq->idle_at_tick ? + enum cpu_idle_type idle = this_rq->idle_balance ? CPU_IDLE : CPU_NOT_IDLE; rebalance_domains(this_cpu, idle); @@ -4251,8 +4897,13 @@ static void set_curr_task_fair(struct rq *rq) { struct sched_entity *se = &rq->curr->se; - for_each_sched_entity(se) - set_next_entity(cfs_rq_of(se), se); + for_each_sched_entity(se) { + struct cfs_rq *cfs_rq = cfs_rq_of(se); + + set_next_entity(cfs_rq, se); + /* ensure bandwidth has been allocated on our new cfs_rq */ + account_cfs_rq_runtime(cfs_rq, 0); + } } #ifdef CONFIG_FAIR_GROUP_SCHED diff --git a/kernel/sched_features.h b/kernel/sched_features.h index 2e74677..efa0a7b 100644 --- a/kernel/sched_features.h +++ b/kernel/sched_features.h @@ -12,11 +12,6 @@ SCHED_FEAT(GENTLE_FAIR_SLEEPERS, 1) SCHED_FEAT(START_DEBIT, 1) /* - * Should wakeups try to preempt running tasks. - */ -SCHED_FEAT(WAKEUP_PREEMPT, 1) - -/* * Based on load and program behaviour, see if it makes sense to place * a newly woken task on the same cpu as the task that woke it -- * improve cache locality. Typically used with SYNC wakeups as diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c index af11778..056cbd2 100644 --- a/kernel/sched_rt.c +++ b/kernel/sched_rt.c @@ -124,21 +124,33 @@ static void dec_rt_migration(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq) update_rt_migration(rt_rq); } +static inline int has_pushable_tasks(struct rq *rq) +{ + return !plist_head_empty(&rq->rt.pushable_tasks); +} + static void enqueue_pushable_task(struct rq *rq, struct task_struct *p) { plist_del(&p->pushable_tasks, &rq->rt.pushable_tasks); plist_node_init(&p->pushable_tasks, p->prio); plist_add(&p->pushable_tasks, &rq->rt.pushable_tasks); + + /* Update the highest prio pushable task */ + if (p->prio < rq->rt.highest_prio.next) + rq->rt.highest_prio.next = p->prio; } static void dequeue_pushable_task(struct rq *rq, struct task_struct *p) { plist_del(&p->pushable_tasks, &rq->rt.pushable_tasks); -} -static inline int has_pushable_tasks(struct rq *rq) -{ - return !plist_head_empty(&rq->rt.pushable_tasks); + /* Update the new highest prio pushable task */ + if (has_pushable_tasks(rq)) { + p = plist_first_entry(&rq->rt.pushable_tasks, + struct task_struct, pushable_tasks); + rq->rt.highest_prio.next = p->prio; + } else + rq->rt.highest_prio.next = MAX_RT_PRIO; } #else @@ -643,6 +655,7 @@ static int sched_rt_runtime_exceeded(struct rt_rq *rt_rq) if (rt_rq->rt_time > runtime) { rt_rq->rt_throttled = 1; + printk_once(KERN_WARNING "sched: RT throttling activated\n"); if (rt_rq_throttled(rt_rq)) { sched_rt_rq_dequeue(rt_rq); return 1; @@ -698,47 +711,13 @@ static void update_curr_rt(struct rq *rq) #if defined CONFIG_SMP -static struct task_struct *pick_next_highest_task_rt(struct rq *rq, int cpu); - -static inline int next_prio(struct rq *rq) -{ - struct task_struct *next = pick_next_highest_task_rt(rq, rq->cpu); - - if (next && rt_prio(next->prio)) - return next->prio; - else - return MAX_RT_PRIO; -} - static void inc_rt_prio_smp(struct rt_rq *rt_rq, int prio, int prev_prio) { struct rq *rq = rq_of_rt_rq(rt_rq); - if (prio < prev_prio) { - - /* - * If the new task is higher in priority than anything on the - * run-queue, we know that the previous high becomes our - * next-highest. - */ - rt_rq->highest_prio.next = prev_prio; - - if (rq->online) - cpupri_set(&rq->rd->cpupri, rq->cpu, prio); - - } else if (prio == rt_rq->highest_prio.curr) - /* - * If the next task is equal in priority to the highest on - * the run-queue, then we implicitly know that the next highest - * task cannot be any lower than current - */ - rt_rq->highest_prio.next = prio; - else if (prio < rt_rq->highest_prio.next) - /* - * Otherwise, we need to recompute next-highest - */ - rt_rq->highest_prio.next = next_prio(rq); + if (rq->online && prio < prev_prio) + cpupri_set(&rq->rd->cpupri, rq->cpu, prio); } static void @@ -746,9 +725,6 @@ dec_rt_prio_smp(struct rt_rq *rt_rq, int prio, int prev_prio) { struct rq *rq = rq_of_rt_rq(rt_rq); - if (rt_rq->rt_nr_running && (prio <= rt_rq->highest_prio.next)) - rt_rq->highest_prio.next = next_prio(rq); - if (rq->online && rt_rq->highest_prio.curr != prev_prio) cpupri_set(&rq->rd->cpupri, rq->cpu, rt_rq->highest_prio.curr); } @@ -961,6 +937,8 @@ enqueue_task_rt(struct rq *rq, struct task_struct *p, int flags) if (!task_current(rq, p) && p->rt.nr_cpus_allowed > 1) enqueue_pushable_task(rq, p); + + inc_nr_running(rq); } static void dequeue_task_rt(struct rq *rq, struct task_struct *p, int flags) @@ -971,6 +949,8 @@ static void dequeue_task_rt(struct rq *rq, struct task_struct *p, int flags) dequeue_rt_entity(rt_se); dequeue_pushable_task(rq, p); + + dec_nr_running(rq); } /* @@ -1017,10 +997,12 @@ select_task_rq_rt(struct task_struct *p, int sd_flag, int flags) struct rq *rq; int cpu; - if (sd_flag != SD_BALANCE_WAKE) - return smp_processor_id(); - cpu = task_cpu(p); + + /* For anything but wake ups, just return the task_cpu */ + if (sd_flag != SD_BALANCE_WAKE && sd_flag != SD_BALANCE_FORK) + goto out; + rq = cpu_rq(cpu); rcu_read_lock(); @@ -1059,6 +1041,7 @@ select_task_rq_rt(struct task_struct *p, int sd_flag, int flags) } rcu_read_unlock(); +out: return cpu; } @@ -1178,7 +1161,6 @@ static struct task_struct *pick_next_task_rt(struct rq *rq) static void put_prev_task_rt(struct rq *rq, struct task_struct *p) { update_curr_rt(rq); - p->se.exec_start = 0; /* * The previous task needs to be made eligible for pushing @@ -1198,7 +1180,7 @@ static void deactivate_task(struct rq *rq, struct task_struct *p, int sleep); static int pick_rt_task(struct rq *rq, struct task_struct *p, int cpu) { if (!task_running(rq, p) && - (cpu < 0 || cpumask_test_cpu(cpu, &p->cpus_allowed)) && + (cpu < 0 || cpumask_test_cpu(cpu, tsk_cpus_allowed(p))) && (p->rt.nr_cpus_allowed > 1)) return 1; return 0; @@ -1343,7 +1325,7 @@ static struct rq *find_lock_lowest_rq(struct task_struct *task, struct rq *rq) */ if (unlikely(task_rq(task) != rq || !cpumask_test_cpu(lowest_rq->cpu, - &task->cpus_allowed) || + tsk_cpus_allowed(task)) || task_running(rq, task) || !task->on_rq)) { @@ -1394,6 +1376,7 @@ static int push_rt_task(struct rq *rq) { struct task_struct *next_task; struct rq *lowest_rq; + int ret = 0; if (!rq->rt.overloaded) return 0; @@ -1426,7 +1409,7 @@ retry: if (!lowest_rq) { struct task_struct *task; /* - * find lock_lowest_rq releases rq->lock + * find_lock_lowest_rq releases rq->lock * so it is possible that next_task has migrated. * * We need to make sure that the task is still on the same @@ -1436,12 +1419,11 @@ retry: task = pick_next_pushable_task(rq); if (task_cpu(next_task) == rq->cpu && task == next_task) { /* - * If we get here, the task hasn't moved at all, but - * it has failed to push. We will not try again, - * since the other cpus will pull from us when they - * are ready. + * The task hasn't migrated, and is still the next + * eligible task, but we failed to find a run-queue + * to push it to. Do not retry in this case, since + * other cpus will pull from us when ready. */ - dequeue_pushable_task(rq, next_task); goto out; } @@ -1460,6 +1442,7 @@ retry: deactivate_task(rq, next_task, 0); set_task_cpu(next_task, lowest_rq->cpu); activate_task(lowest_rq, next_task, 0); + ret = 1; resched_task(lowest_rq->curr); @@ -1468,7 +1451,7 @@ retry: out: put_task_struct(next_task); - return 1; + return ret; } static void push_rt_tasks(struct rq *rq) @@ -1626,9 +1609,6 @@ static void set_cpus_allowed_rt(struct task_struct *p, update_rt_migration(&rq->rt); } - - cpumask_copy(&p->cpus_allowed, new_mask); - p->rt.nr_cpus_allowed = weight; } /* Assumes rq->lock is held */ @@ -1863,4 +1843,3 @@ static void print_rt_stats(struct seq_file *m, int cpu) rcu_read_unlock(); } #endif /* CONFIG_SCHED_DEBUG */ - diff --git a/kernel/sched_stats.h b/kernel/sched_stats.h index 331e01b..87f9e36 100644 --- a/kernel/sched_stats.h +++ b/kernel/sched_stats.h @@ -282,10 +282,10 @@ static inline void account_group_user_time(struct task_struct *tsk, if (!cputimer->running) return; - spin_lock(&cputimer->lock); + raw_spin_lock(&cputimer->lock); cputimer->cputime.utime = cputime_add(cputimer->cputime.utime, cputime); - spin_unlock(&cputimer->lock); + raw_spin_unlock(&cputimer->lock); } /** @@ -306,10 +306,10 @@ static inline void account_group_system_time(struct task_struct *tsk, if (!cputimer->running) return; - spin_lock(&cputimer->lock); + raw_spin_lock(&cputimer->lock); cputimer->cputime.stime = cputime_add(cputimer->cputime.stime, cputime); - spin_unlock(&cputimer->lock); + raw_spin_unlock(&cputimer->lock); } /** @@ -330,7 +330,7 @@ static inline void account_group_exec_runtime(struct task_struct *tsk, if (!cputimer->running) return; - spin_lock(&cputimer->lock); + raw_spin_lock(&cputimer->lock); cputimer->cputime.sum_exec_runtime += ns; - spin_unlock(&cputimer->lock); + raw_spin_unlock(&cputimer->lock); } diff --git a/kernel/sched_stoptask.c b/kernel/sched_stoptask.c index 6f43763..8b44e7f 100644 --- a/kernel/sched_stoptask.c +++ b/kernel/sched_stoptask.c @@ -34,11 +34,13 @@ static struct task_struct *pick_next_task_stop(struct rq *rq) static void enqueue_task_stop(struct rq *rq, struct task_struct *p, int flags) { + inc_nr_running(rq); } static void dequeue_task_stop(struct rq *rq, struct task_struct *p, int flags) { + dec_nr_running(rq); } static void yield_task_stop(struct rq *rq) diff --git a/kernel/semaphore.c b/kernel/semaphore.c index 94a62c0..d831841 100644 --- a/kernel/semaphore.c +++ b/kernel/semaphore.c @@ -54,12 +54,12 @@ void down(struct semaphore *sem) { unsigned long flags; - spin_lock_irqsave(&sem->lock, flags); + raw_spin_lock_irqsave(&sem->lock, flags); if (likely(sem->count > 0)) sem->count--; else __down(sem); - spin_unlock_irqrestore(&sem->lock, flags); + raw_spin_unlock_irqrestore(&sem->lock, flags); } EXPORT_SYMBOL(down); @@ -77,12 +77,12 @@ int down_interruptible(struct semaphore *sem) unsigned long flags; int result = 0; - spin_lock_irqsave(&sem->lock, flags); + raw_spin_lock_irqsave(&sem->lock, flags); if (likely(sem->count > 0)) sem->count--; else result = __down_interruptible(sem); - spin_unlock_irqrestore(&sem->lock, flags); + raw_spin_unlock_irqrestore(&sem->lock, flags); return result; } @@ -103,12 +103,12 @@ int down_killable(struct semaphore *sem) unsigned long flags; int result = 0; - spin_lock_irqsave(&sem->lock, flags); + raw_spin_lock_irqsave(&sem->lock, flags); if (likely(sem->count > 0)) sem->count--; else result = __down_killable(sem); - spin_unlock_irqrestore(&sem->lock, flags); + raw_spin_unlock_irqrestore(&sem->lock, flags); return result; } @@ -132,11 +132,11 @@ int down_trylock(struct semaphore *sem) unsigned long flags; int count; - spin_lock_irqsave(&sem->lock, flags); + raw_spin_lock_irqsave(&sem->lock, flags); count = sem->count - 1; if (likely(count >= 0)) sem->count = count; - spin_unlock_irqrestore(&sem->lock, flags); + raw_spin_unlock_irqrestore(&sem->lock, flags); return (count < 0); } @@ -157,12 +157,12 @@ int down_timeout(struct semaphore *sem, long jiffies) unsigned long flags; int result = 0; - spin_lock_irqsave(&sem->lock, flags); + raw_spin_lock_irqsave(&sem->lock, flags); if (likely(sem->count > 0)) sem->count--; else result = __down_timeout(sem, jiffies); - spin_unlock_irqrestore(&sem->lock, flags); + raw_spin_unlock_irqrestore(&sem->lock, flags); return result; } @@ -179,12 +179,12 @@ void up(struct semaphore *sem) { unsigned long flags; - spin_lock_irqsave(&sem->lock, flags); + raw_spin_lock_irqsave(&sem->lock, flags); if (likely(list_empty(&sem->wait_list))) sem->count++; else __up(sem); - spin_unlock_irqrestore(&sem->lock, flags); + raw_spin_unlock_irqrestore(&sem->lock, flags); } EXPORT_SYMBOL(up); @@ -217,9 +217,9 @@ static inline int __sched __down_common(struct semaphore *sem, long state, if (timeout <= 0) goto timed_out; __set_task_state(task, state); - spin_unlock_irq(&sem->lock); + raw_spin_unlock_irq(&sem->lock); timeout = schedule_timeout(timeout); - spin_lock_irq(&sem->lock); + raw_spin_lock_irq(&sem->lock); if (waiter.up) return 0; } diff --git a/kernel/signal.c b/kernel/signal.c index 291c970..d252be2 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -1344,13 +1344,24 @@ int kill_proc_info(int sig, struct siginfo *info, pid_t pid) return error; } +static int kill_as_cred_perm(const struct cred *cred, + struct task_struct *target) +{ + const struct cred *pcred = __task_cred(target); + if (cred->user_ns != pcred->user_ns) + return 0; + if (cred->euid != pcred->suid && cred->euid != pcred->uid && + cred->uid != pcred->suid && cred->uid != pcred->uid) + return 0; + return 1; +} + /* like kill_pid_info(), but doesn't use uid/euid of "current" */ -int kill_pid_info_as_uid(int sig, struct siginfo *info, struct pid *pid, - uid_t uid, uid_t euid, u32 secid) +int kill_pid_info_as_cred(int sig, struct siginfo *info, struct pid *pid, + const struct cred *cred, u32 secid) { int ret = -EINVAL; struct task_struct *p; - const struct cred *pcred; unsigned long flags; if (!valid_signal(sig)) @@ -1362,10 +1373,7 @@ int kill_pid_info_as_uid(int sig, struct siginfo *info, struct pid *pid, ret = -ESRCH; goto out_unlock; } - pcred = __task_cred(p); - if (si_fromuser(info) && - euid != pcred->suid && euid != pcred->uid && - uid != pcred->suid && uid != pcred->uid) { + if (si_fromuser(info) && !kill_as_cred_perm(cred, p)) { ret = -EPERM; goto out_unlock; } @@ -1384,7 +1392,7 @@ out_unlock: rcu_read_unlock(); return ret; } -EXPORT_SYMBOL_GPL(kill_pid_info_as_uid); +EXPORT_SYMBOL_GPL(kill_pid_info_as_cred); /* * kill_something_info() interprets pid in interesting ways just like kill(2). diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c index ba5070c..5b0951aa0 100644 --- a/kernel/stop_machine.c +++ b/kernel/stop_machine.c @@ -41,6 +41,7 @@ struct cpu_stopper { }; static DEFINE_PER_CPU(struct cpu_stopper, cpu_stopper); +static bool stop_machine_initialized = false; static void cpu_stop_init_done(struct cpu_stop_done *done, unsigned int nr_todo) { @@ -386,6 +387,8 @@ static int __init cpu_stop_init(void) cpu_stop_cpu_callback(&cpu_stop_cpu_notifier, CPU_ONLINE, bcpu); register_cpu_notifier(&cpu_stop_cpu_notifier); + stop_machine_initialized = true; + return 0; } early_initcall(cpu_stop_init); @@ -485,6 +488,25 @@ int __stop_machine(int (*fn)(void *), void *data, const struct cpumask *cpus) .num_threads = num_online_cpus(), .active_cpus = cpus }; + if (!stop_machine_initialized) { + /* + * Handle the case where stop_machine() is called + * early in boot before stop_machine() has been + * initialized. + */ + unsigned long flags; + int ret; + + WARN_ON_ONCE(smdata.num_threads != 1); + + local_irq_save(flags); + hard_irq_disable(); + ret = (*fn)(data); + local_irq_restore(flags); + + return ret; + } + /* Set the initial state and stop all online cpus. */ set_state(&smdata, STOPMACHINE_PREPARE); return stop_cpus(cpu_online_mask, stop_machine_cpu_stop, &smdata); diff --git a/kernel/sys.c b/kernel/sys.c index 1dbbe69..5845950 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -1759,6 +1759,7 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, sizeof(me->comm) - 1) < 0) return -EFAULT; set_task_comm(me, comm); + proc_comm_connector(me); return 0; case PR_GET_NAME: get_task_comm(comm, me); diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c index a9a5de0..47bfa16 100644 --- a/kernel/sys_ni.c +++ b/kernel/sys_ni.c @@ -145,6 +145,10 @@ cond_syscall(sys_io_submit); cond_syscall(sys_io_cancel); cond_syscall(sys_io_getevents); cond_syscall(sys_syslog); +cond_syscall(sys_process_vm_readv); +cond_syscall(sys_process_vm_writev); +cond_syscall(compat_sys_process_vm_readv); +cond_syscall(compat_sys_process_vm_writev); /* arch-specific weak syscall entries */ cond_syscall(sys_pciconfig_read); diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 11d65b5..ae27196 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -57,6 +57,7 @@ #include <linux/pipe_fs_i.h> #include <linux/oom.h> #include <linux/kmod.h> +#include <linux/capability.h> #include <asm/uaccess.h> #include <asm/processor.h> @@ -134,6 +135,7 @@ static int minolduid; static int min_percpu_pagelist_fract = 8; static int ngroups_max = NGROUPS_MAX; +static const int cap_last_cap = CAP_LAST_CAP; #ifdef CONFIG_INOTIFY_USER #include <linux/inotify.h> @@ -151,14 +153,6 @@ extern int pwrsw_enabled; extern int unaligned_enabled; #endif -#ifdef CONFIG_S390 -#ifdef CONFIG_MATHEMU -extern int sysctl_ieee_emulation_warnings; -#endif -extern int sysctl_userprocess_debug; -extern int spin_retry; -#endif - #ifdef CONFIG_IA64 extern int no_unaligned_warning; extern int unaligned_dump_stack; @@ -379,6 +373,16 @@ static struct ctl_table kern_table[] = { .extra2 = &one, }, #endif +#ifdef CONFIG_CFS_BANDWIDTH + { + .procname = "sched_cfs_bandwidth_slice_us", + .data = &sysctl_sched_cfs_bandwidth_slice, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &one, + }, +#endif #ifdef CONFIG_PROVE_LOCKING { .procname = "prove_locking", @@ -730,6 +734,13 @@ static struct ctl_table kern_table[] = { .mode = 0444, .proc_handler = proc_dointvec, }, + { + .procname = "cap_last_cap", + .data = (void *)&cap_last_cap, + .maxlen = sizeof(int), + .mode = 0444, + .proc_handler = proc_dointvec, + }, #if defined(CONFIG_LOCKUP_DETECTOR) { .procname = "watchdog", diff --git a/kernel/sysctl_binary.c b/kernel/sysctl_binary.c index e8bffbe..6318b51 100644 --- a/kernel/sysctl_binary.c +++ b/kernel/sysctl_binary.c @@ -214,7 +214,7 @@ static const struct bin_table bin_net_ipv4_route_table[] = { { CTL_INT, NET_IPV4_ROUTE_GC_MIN_INTERVAL, "gc_min_interval" }, { CTL_INT, NET_IPV4_ROUTE_GC_MIN_INTERVAL_MS, "gc_min_interval_ms" }, { CTL_INT, NET_IPV4_ROUTE_GC_TIMEOUT, "gc_timeout" }, - { CTL_INT, NET_IPV4_ROUTE_GC_INTERVAL, "gc_interval" }, + /* NET_IPV4_ROUTE_GC_INTERVAL "gc_interval" no longer used */ { CTL_INT, NET_IPV4_ROUTE_REDIRECT_LOAD, "redirect_load" }, { CTL_INT, NET_IPV4_ROUTE_REDIRECT_NUMBER, "redirect_number" }, { CTL_INT, NET_IPV4_ROUTE_REDIRECT_SILENCE, "redirect_silence" }, diff --git a/kernel/time.c b/kernel/time.c index 8e8dc6d..d776062 100644 --- a/kernel/time.c +++ b/kernel/time.c @@ -575,7 +575,7 @@ EXPORT_SYMBOL(jiffies_to_timeval); /* * Convert jiffies/jiffies_64 to clock_t and back. */ -clock_t jiffies_to_clock_t(long x) +clock_t jiffies_to_clock_t(unsigned long x) { #if (TICK_NSEC % (NSEC_PER_SEC / USER_HZ)) == 0 # if HZ < USER_HZ diff --git a/kernel/time/Kconfig b/kernel/time/Kconfig index f06a8a3..b26c2228 100644 --- a/kernel/time/Kconfig +++ b/kernel/time/Kconfig @@ -27,3 +27,5 @@ config GENERIC_CLOCKEVENTS_BUILD default y depends on GENERIC_CLOCKEVENTS || GENERIC_CLOCKEVENTS_MIGR +config GENERIC_CLOCKEVENTS_MIN_ADJUST + bool diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c index ea5e1a9..c436e79 100644 --- a/kernel/time/alarmtimer.c +++ b/kernel/time/alarmtimer.c @@ -53,27 +53,6 @@ static struct rtc_device *rtcdev; static DEFINE_SPINLOCK(rtcdev_lock); /** - * has_wakealarm - check rtc device has wakealarm ability - * @dev: current device - * @name_ptr: name to be returned - * - * This helper function checks to see if the rtc device can wake - * from suspend. - */ -static int has_wakealarm(struct device *dev, void *name_ptr) -{ - struct rtc_device *candidate = to_rtc_device(dev); - - if (!candidate->ops->set_alarm) - return 0; - if (!device_may_wakeup(candidate->dev.parent)) - return 0; - - *(const char **)name_ptr = dev_name(dev); - return 1; -} - -/** * alarmtimer_get_rtcdev - Return selected rtcdevice * * This function returns the rtc device to use for wakealarms. @@ -82,37 +61,64 @@ static int has_wakealarm(struct device *dev, void *name_ptr) */ static struct rtc_device *alarmtimer_get_rtcdev(void) { - struct device *dev; - char *str; unsigned long flags; struct rtc_device *ret; spin_lock_irqsave(&rtcdev_lock, flags); - if (!rtcdev) { - /* Find an rtc device and init the rtc_timer */ - dev = class_find_device(rtc_class, NULL, &str, has_wakealarm); - /* If we have a device then str is valid. See has_wakealarm() */ - if (dev) { - rtcdev = rtc_class_open(str); - /* - * Drop the reference we got in class_find_device, - * rtc_open takes its own. - */ - put_device(dev); - rtc_timer_init(&rtctimer, NULL, NULL); - } - } ret = rtcdev; spin_unlock_irqrestore(&rtcdev_lock, flags); return ret; } + + +static int alarmtimer_rtc_add_device(struct device *dev, + struct class_interface *class_intf) +{ + unsigned long flags; + struct rtc_device *rtc = to_rtc_device(dev); + + if (rtcdev) + return -EBUSY; + + if (!rtc->ops->set_alarm) + return -1; + if (!device_may_wakeup(rtc->dev.parent)) + return -1; + + spin_lock_irqsave(&rtcdev_lock, flags); + if (!rtcdev) { + rtcdev = rtc; + /* hold a reference so it doesn't go away */ + get_device(dev); + } + spin_unlock_irqrestore(&rtcdev_lock, flags); + return 0; +} + +static struct class_interface alarmtimer_rtc_interface = { + .add_dev = &alarmtimer_rtc_add_device, +}; + +static int alarmtimer_rtc_interface_setup(void) +{ + alarmtimer_rtc_interface.class = rtc_class; + return class_interface_register(&alarmtimer_rtc_interface); +} +static void alarmtimer_rtc_interface_remove(void) +{ + class_interface_unregister(&alarmtimer_rtc_interface); +} #else -#define alarmtimer_get_rtcdev() (0) -#define rtcdev (0) +static inline struct rtc_device *alarmtimer_get_rtcdev(void) +{ + return NULL; +} +#define rtcdev (NULL) +static inline int alarmtimer_rtc_interface_setup(void) { return 0; } +static inline void alarmtimer_rtc_interface_remove(void) { } #endif - /** * alarmtimer_enqueue - Adds an alarm timer to an alarm_base timerqueue * @base: pointer to the base where the timer is being run @@ -126,6 +132,8 @@ static struct rtc_device *alarmtimer_get_rtcdev(void) static void alarmtimer_enqueue(struct alarm_base *base, struct alarm *alarm) { timerqueue_add(&base->timerqueue, &alarm->node); + alarm->state |= ALARMTIMER_STATE_ENQUEUED; + if (&alarm->node == timerqueue_getnext(&base->timerqueue)) { hrtimer_try_to_cancel(&base->timer); hrtimer_start(&base->timer, alarm->node.expires, @@ -147,7 +155,12 @@ static void alarmtimer_remove(struct alarm_base *base, struct alarm *alarm) { struct timerqueue_node *next = timerqueue_getnext(&base->timerqueue); + if (!(alarm->state & ALARMTIMER_STATE_ENQUEUED)) + return; + timerqueue_del(&base->timerqueue, &alarm->node); + alarm->state &= ~ALARMTIMER_STATE_ENQUEUED; + if (next == &alarm->node) { hrtimer_try_to_cancel(&base->timer); next = timerqueue_getnext(&base->timerqueue); @@ -174,6 +187,7 @@ static enum hrtimer_restart alarmtimer_fired(struct hrtimer *timer) unsigned long flags; ktime_t now; int ret = HRTIMER_NORESTART; + int restart = ALARMTIMER_NORESTART; spin_lock_irqsave(&base->lock, flags); now = base->gettime(); @@ -187,17 +201,19 @@ static enum hrtimer_restart alarmtimer_fired(struct hrtimer *timer) alarm = container_of(next, struct alarm, node); timerqueue_del(&base->timerqueue, &alarm->node); - alarm->enabled = 0; - /* Re-add periodic timers */ - if (alarm->period.tv64) { - alarm->node.expires = ktime_add(expired, alarm->period); - timerqueue_add(&base->timerqueue, &alarm->node); - alarm->enabled = 1; - } + alarm->state &= ~ALARMTIMER_STATE_ENQUEUED; + + alarm->state |= ALARMTIMER_STATE_CALLBACK; spin_unlock_irqrestore(&base->lock, flags); if (alarm->function) - alarm->function(alarm); + restart = alarm->function(alarm, now); spin_lock_irqsave(&base->lock, flags); + alarm->state &= ~ALARMTIMER_STATE_CALLBACK; + + if (restart != ALARMTIMER_NORESTART) { + timerqueue_add(&base->timerqueue, &alarm->node); + alarm->state |= ALARMTIMER_STATE_ENQUEUED; + } } if (next) { @@ -234,7 +250,7 @@ static int alarmtimer_suspend(struct device *dev) freezer_delta = ktime_set(0, 0); spin_unlock_irqrestore(&freezer_delta_lock, flags); - rtc = rtcdev; + rtc = alarmtimer_get_rtcdev(); /* If we have no rtcdev, just return */ if (!rtc) return 0; @@ -299,53 +315,111 @@ static void alarmtimer_freezerset(ktime_t absexp, enum alarmtimer_type type) * @function: callback that is run when the alarm fires */ void alarm_init(struct alarm *alarm, enum alarmtimer_type type, - void (*function)(struct alarm *)) + enum alarmtimer_restart (*function)(struct alarm *, ktime_t)) { timerqueue_init(&alarm->node); - alarm->period = ktime_set(0, 0); alarm->function = function; alarm->type = type; - alarm->enabled = 0; + alarm->state = ALARMTIMER_STATE_INACTIVE; } /** * alarm_start - Sets an alarm to fire * @alarm: ptr to alarm to set * @start: time to run the alarm - * @period: period at which the alarm will recur */ -void alarm_start(struct alarm *alarm, ktime_t start, ktime_t period) +void alarm_start(struct alarm *alarm, ktime_t start) { struct alarm_base *base = &alarm_bases[alarm->type]; unsigned long flags; spin_lock_irqsave(&base->lock, flags); - if (alarm->enabled) + if (alarmtimer_active(alarm)) alarmtimer_remove(base, alarm); alarm->node.expires = start; - alarm->period = period; alarmtimer_enqueue(base, alarm); - alarm->enabled = 1; spin_unlock_irqrestore(&base->lock, flags); } /** - * alarm_cancel - Tries to cancel an alarm timer + * alarm_try_to_cancel - Tries to cancel an alarm timer * @alarm: ptr to alarm to be canceled + * + * Returns 1 if the timer was canceled, 0 if it was not running, + * and -1 if the callback was running */ -void alarm_cancel(struct alarm *alarm) +int alarm_try_to_cancel(struct alarm *alarm) { struct alarm_base *base = &alarm_bases[alarm->type]; unsigned long flags; - + int ret = -1; spin_lock_irqsave(&base->lock, flags); - if (alarm->enabled) + + if (alarmtimer_callback_running(alarm)) + goto out; + + if (alarmtimer_is_queued(alarm)) { alarmtimer_remove(base, alarm); - alarm->enabled = 0; + ret = 1; + } else + ret = 0; +out: spin_unlock_irqrestore(&base->lock, flags); + return ret; +} + + +/** + * alarm_cancel - Spins trying to cancel an alarm timer until it is done + * @alarm: ptr to alarm to be canceled + * + * Returns 1 if the timer was canceled, 0 if it was not active. + */ +int alarm_cancel(struct alarm *alarm) +{ + for (;;) { + int ret = alarm_try_to_cancel(alarm); + if (ret >= 0) + return ret; + cpu_relax(); + } +} + + +u64 alarm_forward(struct alarm *alarm, ktime_t now, ktime_t interval) +{ + u64 overrun = 1; + ktime_t delta; + + delta = ktime_sub(now, alarm->node.expires); + + if (delta.tv64 < 0) + return 0; + + if (unlikely(delta.tv64 >= interval.tv64)) { + s64 incr = ktime_to_ns(interval); + + overrun = ktime_divns(delta, incr); + + alarm->node.expires = ktime_add_ns(alarm->node.expires, + incr*overrun); + + if (alarm->node.expires.tv64 > now.tv64) + return overrun; + /* + * This (and the ktime_add() below) is the + * correction for exact: + */ + overrun++; + } + + alarm->node.expires = ktime_add(alarm->node.expires, interval); + return overrun; } + + /** * clock2alarm - helper that converts from clockid to alarmtypes * @clockid: clockid. @@ -365,12 +439,21 @@ static enum alarmtimer_type clock2alarm(clockid_t clockid) * * Posix timer callback for expired alarm timers. */ -static void alarm_handle_timer(struct alarm *alarm) +static enum alarmtimer_restart alarm_handle_timer(struct alarm *alarm, + ktime_t now) { struct k_itimer *ptr = container_of(alarm, struct k_itimer, - it.alarmtimer); + it.alarm.alarmtimer); if (posix_timer_event(ptr, 0) != 0) ptr->it_overrun++; + + /* Re-add periodic timers */ + if (ptr->it.alarm.interval.tv64) { + ptr->it_overrun += alarm_forward(alarm, now, + ptr->it.alarm.interval); + return ALARMTIMER_RESTART; + } + return ALARMTIMER_NORESTART; } /** @@ -427,7 +510,7 @@ static int alarm_timer_create(struct k_itimer *new_timer) type = clock2alarm(new_timer->it_clock); base = &alarm_bases[type]; - alarm_init(&new_timer->it.alarmtimer, type, alarm_handle_timer); + alarm_init(&new_timer->it.alarm.alarmtimer, type, alarm_handle_timer); return 0; } @@ -444,9 +527,9 @@ static void alarm_timer_get(struct k_itimer *timr, memset(cur_setting, 0, sizeof(struct itimerspec)); cur_setting->it_interval = - ktime_to_timespec(timr->it.alarmtimer.period); + ktime_to_timespec(timr->it.alarm.interval); cur_setting->it_value = - ktime_to_timespec(timr->it.alarmtimer.node.expires); + ktime_to_timespec(timr->it.alarm.alarmtimer.node.expires); return; } @@ -461,7 +544,9 @@ static int alarm_timer_del(struct k_itimer *timr) if (!rtcdev) return -ENOTSUPP; - alarm_cancel(&timr->it.alarmtimer); + if (alarm_try_to_cancel(&timr->it.alarm.alarmtimer) < 0) + return TIMER_RETRY; + return 0; } @@ -481,25 +566,17 @@ static int alarm_timer_set(struct k_itimer *timr, int flags, if (!rtcdev) return -ENOTSUPP; - /* - * XXX HACK! Currently we can DOS a system if the interval - * period on alarmtimers is too small. Cap the interval here - * to 100us and solve this properly in a future patch! -jstultz - */ - if ((new_setting->it_interval.tv_sec == 0) && - (new_setting->it_interval.tv_nsec < 100000)) - new_setting->it_interval.tv_nsec = 100000; - if (old_setting) alarm_timer_get(timr, old_setting); /* If the timer was already set, cancel it */ - alarm_cancel(&timr->it.alarmtimer); + if (alarm_try_to_cancel(&timr->it.alarm.alarmtimer) < 0) + return TIMER_RETRY; /* start the timer */ - alarm_start(&timr->it.alarmtimer, - timespec_to_ktime(new_setting->it_value), - timespec_to_ktime(new_setting->it_interval)); + timr->it.alarm.interval = timespec_to_ktime(new_setting->it_interval); + alarm_start(&timr->it.alarm.alarmtimer, + timespec_to_ktime(new_setting->it_value)); return 0; } @@ -509,13 +586,15 @@ static int alarm_timer_set(struct k_itimer *timr, int flags, * * Wakes up the task that set the alarmtimer */ -static void alarmtimer_nsleep_wakeup(struct alarm *alarm) +static enum alarmtimer_restart alarmtimer_nsleep_wakeup(struct alarm *alarm, + ktime_t now) { struct task_struct *task = (struct task_struct *)alarm->data; alarm->data = NULL; if (task) wake_up_process(task); + return ALARMTIMER_NORESTART; } /** @@ -530,7 +609,7 @@ static int alarmtimer_do_nsleep(struct alarm *alarm, ktime_t absexp) alarm->data = (void *)current; do { set_current_state(TASK_INTERRUPTIBLE); - alarm_start(alarm, absexp, ktime_set(0, 0)); + alarm_start(alarm, absexp); if (likely(alarm->data)) schedule(); @@ -691,6 +770,7 @@ static struct platform_driver alarmtimer_driver = { */ static int __init alarmtimer_init(void) { + struct platform_device *pdev; int error = 0; int i; struct k_clock alarm_clock = { @@ -719,10 +799,26 @@ static int __init alarmtimer_init(void) HRTIMER_MODE_ABS); alarm_bases[i].timer.function = alarmtimer_fired; } + + error = alarmtimer_rtc_interface_setup(); + if (error) + return error; + error = platform_driver_register(&alarmtimer_driver); - platform_device_register_simple("alarmtimer", -1, NULL, 0); + if (error) + goto out_if; + pdev = platform_device_register_simple("alarmtimer", -1, NULL, 0); + if (IS_ERR(pdev)) { + error = PTR_ERR(pdev); + goto out_drv; + } + return 0; + +out_drv: + platform_driver_unregister(&alarmtimer_driver); +out_if: + alarmtimer_rtc_interface_remove(); return error; } device_initcall(alarmtimer_init); - diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c index e4c699d..1ecd6ba 100644 --- a/kernel/time/clockevents.c +++ b/kernel/time/clockevents.c @@ -94,42 +94,143 @@ void clockevents_shutdown(struct clock_event_device *dev) dev->next_event.tv64 = KTIME_MAX; } +#ifdef CONFIG_GENERIC_CLOCKEVENTS_MIN_ADJUST + +/* Limit min_delta to a jiffie */ +#define MIN_DELTA_LIMIT (NSEC_PER_SEC / HZ) + +/** + * clockevents_increase_min_delta - raise minimum delta of a clock event device + * @dev: device to increase the minimum delta + * + * Returns 0 on success, -ETIME when the minimum delta reached the limit. + */ +static int clockevents_increase_min_delta(struct clock_event_device *dev) +{ + /* Nothing to do if we already reached the limit */ + if (dev->min_delta_ns >= MIN_DELTA_LIMIT) { + printk(KERN_WARNING "CE: Reprogramming failure. Giving up\n"); + dev->next_event.tv64 = KTIME_MAX; + return -ETIME; + } + + if (dev->min_delta_ns < 5000) + dev->min_delta_ns = 5000; + else + dev->min_delta_ns += dev->min_delta_ns >> 1; + + if (dev->min_delta_ns > MIN_DELTA_LIMIT) + dev->min_delta_ns = MIN_DELTA_LIMIT; + + printk(KERN_WARNING "CE: %s increased min_delta_ns to %llu nsec\n", + dev->name ? dev->name : "?", + (unsigned long long) dev->min_delta_ns); + return 0; +} + +/** + * clockevents_program_min_delta - Set clock event device to the minimum delay. + * @dev: device to program + * + * Returns 0 on success, -ETIME when the retry loop failed. + */ +static int clockevents_program_min_delta(struct clock_event_device *dev) +{ + unsigned long long clc; + int64_t delta; + int i; + + for (i = 0;;) { + delta = dev->min_delta_ns; + dev->next_event = ktime_add_ns(ktime_get(), delta); + + if (dev->mode == CLOCK_EVT_MODE_SHUTDOWN) + return 0; + + dev->retries++; + clc = ((unsigned long long) delta * dev->mult) >> dev->shift; + if (dev->set_next_event((unsigned long) clc, dev) == 0) + return 0; + + if (++i > 2) { + /* + * We tried 3 times to program the device with the + * given min_delta_ns. Try to increase the minimum + * delta, if that fails as well get out of here. + */ + if (clockevents_increase_min_delta(dev)) + return -ETIME; + i = 0; + } + } +} + +#else /* CONFIG_GENERIC_CLOCKEVENTS_MIN_ADJUST */ + +/** + * clockevents_program_min_delta - Set clock event device to the minimum delay. + * @dev: device to program + * + * Returns 0 on success, -ETIME when the retry loop failed. + */ +static int clockevents_program_min_delta(struct clock_event_device *dev) +{ + unsigned long long clc; + int64_t delta; + + delta = dev->min_delta_ns; + dev->next_event = ktime_add_ns(ktime_get(), delta); + + if (dev->mode == CLOCK_EVT_MODE_SHUTDOWN) + return 0; + + dev->retries++; + clc = ((unsigned long long) delta * dev->mult) >> dev->shift; + return dev->set_next_event((unsigned long) clc, dev); +} + +#endif /* CONFIG_GENERIC_CLOCKEVENTS_MIN_ADJUST */ + /** * clockevents_program_event - Reprogram the clock event device. + * @dev: device to program * @expires: absolute expiry time (monotonic clock) + * @force: program minimum delay if expires can not be set * * Returns 0 on success, -ETIME when the event is in the past. */ int clockevents_program_event(struct clock_event_device *dev, ktime_t expires, - ktime_t now) + bool force) { unsigned long long clc; int64_t delta; + int rc; if (unlikely(expires.tv64 < 0)) { WARN_ON_ONCE(1); return -ETIME; } - delta = ktime_to_ns(ktime_sub(expires, now)); - - if (delta <= 0) - return -ETIME; - dev->next_event = expires; if (dev->mode == CLOCK_EVT_MODE_SHUTDOWN) return 0; - if (delta > dev->max_delta_ns) - delta = dev->max_delta_ns; - if (delta < dev->min_delta_ns) - delta = dev->min_delta_ns; + /* Shortcut for clockevent devices that can deal with ktime. */ + if (dev->features & CLOCK_EVT_FEAT_KTIME) + return dev->set_next_ktime(expires, dev); + + delta = ktime_to_ns(ktime_sub(expires, ktime_get())); + if (delta <= 0) + return force ? clockevents_program_min_delta(dev) : -ETIME; - clc = delta * dev->mult; - clc >>= dev->shift; + delta = min(delta, (int64_t) dev->max_delta_ns); + delta = max(delta, (int64_t) dev->min_delta_ns); - return dev->set_next_event((unsigned long) clc, dev); + clc = ((unsigned long long) delta * dev->mult) >> dev->shift; + rc = dev->set_next_event((unsigned long) clc, dev); + + return (rc && force) ? clockevents_program_min_delta(dev) : rc; } /** @@ -258,7 +359,7 @@ int clockevents_update_freq(struct clock_event_device *dev, u32 freq) if (dev->mode != CLOCK_EVT_MODE_ONESHOT) return 0; - return clockevents_program_event(dev, dev->next_event, ktime_get()); + return clockevents_program_event(dev, dev->next_event, false); } /* diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index e0980f0..cf52fda 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -186,6 +186,7 @@ static struct timer_list watchdog_timer; static DECLARE_WORK(watchdog_work, clocksource_watchdog_work); static DEFINE_SPINLOCK(watchdog_lock); static int watchdog_running; +static atomic_t watchdog_reset_pending; static int clocksource_watchdog_kthread(void *data); static void __clocksource_change_rating(struct clocksource *cs, int rating); @@ -247,12 +248,14 @@ static void clocksource_watchdog(unsigned long data) struct clocksource *cs; cycle_t csnow, wdnow; int64_t wd_nsec, cs_nsec; - int next_cpu; + int next_cpu, reset_pending; spin_lock(&watchdog_lock); if (!watchdog_running) goto out; + reset_pending = atomic_read(&watchdog_reset_pending); + list_for_each_entry(cs, &watchdog_list, wd_list) { /* Clocksource already marked unstable? */ @@ -268,7 +271,8 @@ static void clocksource_watchdog(unsigned long data) local_irq_enable(); /* Clocksource initialized ? */ - if (!(cs->flags & CLOCK_SOURCE_WATCHDOG)) { + if (!(cs->flags & CLOCK_SOURCE_WATCHDOG) || + atomic_read(&watchdog_reset_pending)) { cs->flags |= CLOCK_SOURCE_WATCHDOG; cs->wd_last = wdnow; cs->cs_last = csnow; @@ -283,8 +287,11 @@ static void clocksource_watchdog(unsigned long data) cs->cs_last = csnow; cs->wd_last = wdnow; + if (atomic_read(&watchdog_reset_pending)) + continue; + /* Check the deviation from the watchdog clocksource. */ - if (abs(cs_nsec - wd_nsec) > WATCHDOG_THRESHOLD) { + if ((abs(cs_nsec - wd_nsec) > WATCHDOG_THRESHOLD)) { clocksource_unstable(cs, cs_nsec - wd_nsec); continue; } @@ -303,6 +310,13 @@ static void clocksource_watchdog(unsigned long data) } /* + * We only clear the watchdog_reset_pending, when we did a + * full cycle through all clocksources. + */ + if (reset_pending) + atomic_dec(&watchdog_reset_pending); + + /* * Cycle through CPUs to check if the CPUs stay synchronized * to each other. */ @@ -344,23 +358,7 @@ static inline void clocksource_reset_watchdog(void) static void clocksource_resume_watchdog(void) { - unsigned long flags; - - /* - * We use trylock here to avoid a potential dead lock when - * kgdb calls this code after the kernel has been stopped with - * watchdog_lock held. When watchdog_lock is held we just - * return and accept, that the watchdog might trigger and mark - * the monitored clock source (usually TSC) unstable. - * - * This does not affect the other caller clocksource_resume() - * because at this point the kernel is UP, interrupts are - * disabled and nothing can hold watchdog_lock. - */ - if (!spin_trylock_irqsave(&watchdog_lock, flags)) - return; - clocksource_reset_watchdog(); - spin_unlock_irqrestore(&watchdog_lock, flags); + atomic_inc(&watchdog_reset_pending); } static void clocksource_enqueue_watchdog(struct clocksource *cs) diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c index c7218d1..f954282 100644 --- a/kernel/time/tick-broadcast.c +++ b/kernel/time/tick-broadcast.c @@ -194,7 +194,7 @@ static void tick_handle_periodic_broadcast(struct clock_event_device *dev) for (next = dev->next_event; ;) { next = ktime_add(next, tick_period); - if (!clockevents_program_event(dev, next, ktime_get())) + if (!clockevents_program_event(dev, next, false)) return; tick_do_periodic_broadcast(); } @@ -373,7 +373,7 @@ static int tick_broadcast_set_event(ktime_t expires, int force) { struct clock_event_device *bc = tick_broadcast_device.evtdev; - return tick_dev_program_event(bc, expires, force); + return clockevents_program_event(bc, expires, force); } int tick_resume_broadcast_oneshot(struct clock_event_device *bc) diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c index 119528d..da6c9ec 100644 --- a/kernel/time/tick-common.c +++ b/kernel/time/tick-common.c @@ -94,7 +94,7 @@ void tick_handle_periodic(struct clock_event_device *dev) */ next = ktime_add(dev->next_event, tick_period); for (;;) { - if (!clockevents_program_event(dev, next, ktime_get())) + if (!clockevents_program_event(dev, next, false)) return; /* * Have to be careful here. If we're in oneshot mode, @@ -137,7 +137,7 @@ void tick_setup_periodic(struct clock_event_device *dev, int broadcast) clockevents_set_mode(dev, CLOCK_EVT_MODE_ONESHOT); for (;;) { - if (!clockevents_program_event(dev, next, ktime_get())) + if (!clockevents_program_event(dev, next, false)) return; next = ktime_add(next, tick_period); } diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h index 1009b06..4e265b90 100644 --- a/kernel/time/tick-internal.h +++ b/kernel/time/tick-internal.h @@ -26,8 +26,6 @@ extern void clockevents_shutdown(struct clock_event_device *dev); extern void tick_setup_oneshot(struct clock_event_device *newdev, void (*handler)(struct clock_event_device *), ktime_t nextevt); -extern int tick_dev_program_event(struct clock_event_device *dev, - ktime_t expires, int force); extern int tick_program_event(ktime_t expires, int force); extern void tick_oneshot_notify(void); extern int tick_switch_to_oneshot(void (*handler)(struct clock_event_device *)); diff --git a/kernel/time/tick-oneshot.c b/kernel/time/tick-oneshot.c index 2d04411..8241090 100644 --- a/kernel/time/tick-oneshot.c +++ b/kernel/time/tick-oneshot.c @@ -21,74 +21,6 @@ #include "tick-internal.h" -/* Limit min_delta to a jiffie */ -#define MIN_DELTA_LIMIT (NSEC_PER_SEC / HZ) - -static int tick_increase_min_delta(struct clock_event_device *dev) -{ - /* Nothing to do if we already reached the limit */ - if (dev->min_delta_ns >= MIN_DELTA_LIMIT) - return -ETIME; - - if (dev->min_delta_ns < 5000) - dev->min_delta_ns = 5000; - else - dev->min_delta_ns += dev->min_delta_ns >> 1; - - if (dev->min_delta_ns > MIN_DELTA_LIMIT) - dev->min_delta_ns = MIN_DELTA_LIMIT; - - printk(KERN_WARNING "CE: %s increased min_delta_ns to %llu nsec\n", - dev->name ? dev->name : "?", - (unsigned long long) dev->min_delta_ns); - return 0; -} - -/** - * tick_program_event internal worker function - */ -int tick_dev_program_event(struct clock_event_device *dev, ktime_t expires, - int force) -{ - ktime_t now = ktime_get(); - int i; - - for (i = 0;;) { - int ret = clockevents_program_event(dev, expires, now); - - if (!ret || !force) - return ret; - - dev->retries++; - /* - * We tried 3 times to program the device with the given - * min_delta_ns. If that's not working then we increase it - * and emit a warning. - */ - if (++i > 2) { - /* Increase the min. delta and try again */ - if (tick_increase_min_delta(dev)) { - /* - * Get out of the loop if min_delta_ns - * hit the limit already. That's - * better than staying here forever. - * - * We clear next_event so we have a - * chance that the box survives. - */ - printk(KERN_WARNING - "CE: Reprogramming failure. Giving up\n"); - dev->next_event.tv64 = KTIME_MAX; - return -ETIME; - } - i = 0; - } - - now = ktime_get(); - expires = ktime_add_ns(now, dev->min_delta_ns); - } -} - /** * tick_program_event */ @@ -96,7 +28,7 @@ int tick_program_event(ktime_t expires, int force) { struct clock_event_device *dev = __this_cpu_read(tick_cpu_device.evtdev); - return tick_dev_program_event(dev, expires, force); + return clockevents_program_event(dev, expires, force); } /** @@ -104,11 +36,10 @@ int tick_program_event(ktime_t expires, int force) */ void tick_resume_oneshot(void) { - struct tick_device *td = &__get_cpu_var(tick_cpu_device); - struct clock_event_device *dev = td->evtdev; + struct clock_event_device *dev = __this_cpu_read(tick_cpu_device.evtdev); clockevents_set_mode(dev, CLOCK_EVT_MODE_ONESHOT); - tick_program_event(ktime_get(), 1); + clockevents_program_event(dev, ktime_get(), true); } /** @@ -120,7 +51,7 @@ void tick_setup_oneshot(struct clock_event_device *newdev, { newdev->event_handler = handler; clockevents_set_mode(newdev, CLOCK_EVT_MODE_ONESHOT); - tick_dev_program_event(newdev, next_event, 1); + clockevents_program_event(newdev, next_event, true); } /** diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index d5097c4..4042064 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -139,7 +139,6 @@ static void tick_nohz_update_jiffies(ktime_t now) struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu); unsigned long flags; - cpumask_clear_cpu(cpu, nohz_cpu_mask); ts->idle_waketime = now; local_irq_save(flags); @@ -159,9 +158,10 @@ update_ts_time_stats(int cpu, struct tick_sched *ts, ktime_t now, u64 *last_upda if (ts->idle_active) { delta = ktime_sub(now, ts->idle_entrytime); - ts->idle_sleeptime = ktime_add(ts->idle_sleeptime, delta); if (nr_iowait_cpu(cpu) > 0) ts->iowait_sleeptime = ktime_add(ts->iowait_sleeptime, delta); + else + ts->idle_sleeptime = ktime_add(ts->idle_sleeptime, delta); ts->idle_entrytime = now; } @@ -197,11 +197,11 @@ static ktime_t tick_nohz_start_idle(int cpu, struct tick_sched *ts) /** * get_cpu_idle_time_us - get the total idle time of a cpu * @cpu: CPU number to query - * @last_update_time: variable to store update time in + * @last_update_time: variable to store update time in. Do not update + * counters if NULL. * * Return the cummulative idle time (since boot) for a given - * CPU, in microseconds. The idle time returned includes - * the iowait time (unlike what "top" and co report). + * CPU, in microseconds. * * This time is measured via accounting rather than sampling, * and is as accurate as ktime_get() is. @@ -211,20 +211,35 @@ static ktime_t tick_nohz_start_idle(int cpu, struct tick_sched *ts) u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time) { struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu); + ktime_t now, idle; if (!tick_nohz_enabled) return -1; - update_ts_time_stats(cpu, ts, ktime_get(), last_update_time); + now = ktime_get(); + if (last_update_time) { + update_ts_time_stats(cpu, ts, now, last_update_time); + idle = ts->idle_sleeptime; + } else { + if (ts->idle_active && !nr_iowait_cpu(cpu)) { + ktime_t delta = ktime_sub(now, ts->idle_entrytime); + + idle = ktime_add(ts->idle_sleeptime, delta); + } else { + idle = ts->idle_sleeptime; + } + } + + return ktime_to_us(idle); - return ktime_to_us(ts->idle_sleeptime); } EXPORT_SYMBOL_GPL(get_cpu_idle_time_us); -/* +/** * get_cpu_iowait_time_us - get the total iowait time of a cpu * @cpu: CPU number to query - * @last_update_time: variable to store update time in + * @last_update_time: variable to store update time in. Do not update + * counters if NULL. * * Return the cummulative iowait time (since boot) for a given * CPU, in microseconds. @@ -237,13 +252,26 @@ EXPORT_SYMBOL_GPL(get_cpu_idle_time_us); u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time) { struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu); + ktime_t now, iowait; if (!tick_nohz_enabled) return -1; - update_ts_time_stats(cpu, ts, ktime_get(), last_update_time); + now = ktime_get(); + if (last_update_time) { + update_ts_time_stats(cpu, ts, now, last_update_time); + iowait = ts->iowait_sleeptime; + } else { + if (ts->idle_active && nr_iowait_cpu(cpu) > 0) { + ktime_t delta = ktime_sub(now, ts->idle_entrytime); + + iowait = ktime_add(ts->iowait_sleeptime, delta); + } else { + iowait = ts->iowait_sleeptime; + } + } - return ktime_to_us(ts->iowait_sleeptime); + return ktime_to_us(iowait); } EXPORT_SYMBOL_GPL(get_cpu_iowait_time_us); @@ -389,9 +417,6 @@ void tick_nohz_stop_sched_tick(int inidle) else expires.tv64 = KTIME_MAX; - if (delta_jiffies > 1) - cpumask_set_cpu(cpu, nohz_cpu_mask); - /* Skip reprogram of event if its not changed */ if (ts->tick_stopped && ktime_equal(expires, dev->next_event)) goto out; @@ -441,7 +466,6 @@ void tick_nohz_stop_sched_tick(int inidle) * softirq. */ tick_do_update_jiffies64(ktime_get()); - cpumask_clear_cpu(cpu, nohz_cpu_mask); } raise_softirq_irqoff(TIMER_SOFTIRQ); out: @@ -524,7 +548,6 @@ void tick_nohz_restart_sched_tick(void) /* Update jiffies first */ select_nohz_load_balancer(0); tick_do_update_jiffies64(now); - cpumask_clear_cpu(cpu, nohz_cpu_mask); #ifndef CONFIG_VIRT_CPU_ACCOUNTING /* @@ -640,8 +663,6 @@ static void tick_nohz_switch_to_nohz(void) next = ktime_add(next, tick_period); } local_irq_enable(); - - printk(KERN_INFO "Switched to NOHz mode on CPU #%d\n", smp_processor_id()); } /* @@ -793,10 +814,8 @@ void tick_setup_sched_timer(void) } #ifdef CONFIG_NO_HZ - if (tick_nohz_enabled) { + if (tick_nohz_enabled) ts->nohz_mode = NOHZ_MODE_HIGHRES; - printk(KERN_INFO "Switched to NOHz mode on CPU #%d\n", smp_processor_id()); - } #endif } #endif /* HIGH_RES_TIMERS */ diff --git a/kernel/time/timer_stats.c b/kernel/time/timer_stats.c index a5d0a3a..0b537f2 100644 --- a/kernel/time/timer_stats.c +++ b/kernel/time/timer_stats.c @@ -81,7 +81,7 @@ struct entry { /* * Spinlock protecting the tables - not taken during lookup: */ -static DEFINE_SPINLOCK(table_lock); +static DEFINE_RAW_SPINLOCK(table_lock); /* * Per-CPU lookup locks for fast hash lookup: @@ -188,7 +188,7 @@ static struct entry *tstat_lookup(struct entry *entry, char *comm) prev = NULL; curr = *head; - spin_lock(&table_lock); + raw_spin_lock(&table_lock); /* * Make sure we have not raced with another CPU: */ @@ -215,7 +215,7 @@ static struct entry *tstat_lookup(struct entry *entry, char *comm) *head = curr; } out_unlock: - spin_unlock(&table_lock); + raw_spin_unlock(&table_lock); return curr; } diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile index 761c510..5f39a07 100644 --- a/kernel/trace/Makefile +++ b/kernel/trace/Makefile @@ -15,6 +15,8 @@ ifdef CONFIG_TRACING_BRANCHES KBUILD_CFLAGS += -DDISABLE_BRANCH_PROFILING endif +CFLAGS_trace_events_filter.o := -I$(src) + # # Make the trace clocks available generally: it's infrastructure # relied on by ptrace for example: @@ -53,6 +55,9 @@ endif obj-$(CONFIG_EVENT_TRACING) += trace_events_filter.o obj-$(CONFIG_KPROBE_EVENT) += trace_kprobe.o obj-$(CONFIG_TRACEPOINTS) += power-traces.o +ifeq ($(CONFIG_PM_RUNTIME),y) +obj-$(CONFIG_TRACEPOINTS) += rpm-traces.o +endif ifeq ($(CONFIG_TRACING),y) obj-$(CONFIG_KGDB_KDB) += trace_kdb.o endif diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index c3e4575..077d853 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -3863,6 +3863,14 @@ void ftrace_kill(void) } /** + * Test if ftrace is dead or not. + */ +int ftrace_is_dead(void) +{ + return ftrace_disabled; +} + +/** * register_ftrace_function - register a function for profiling * @ops - ops structure that holds the function for profiling. * diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 731201b..f5b7b5c 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -478,7 +478,7 @@ struct ring_buffer_per_cpu { int cpu; atomic_t record_disabled; struct ring_buffer *buffer; - spinlock_t reader_lock; /* serialize readers */ + raw_spinlock_t reader_lock; /* serialize readers */ arch_spinlock_t lock; struct lock_class_key lock_key; struct list_head *pages; @@ -488,12 +488,14 @@ struct ring_buffer_per_cpu { struct buffer_page *reader_page; unsigned long lost_events; unsigned long last_overrun; + local_t entries_bytes; local_t commit_overrun; local_t overrun; local_t entries; local_t committing; local_t commits; unsigned long read; + unsigned long read_bytes; u64 write_stamp; u64 read_stamp; }; @@ -1062,7 +1064,7 @@ rb_allocate_cpu_buffer(struct ring_buffer *buffer, int cpu) cpu_buffer->cpu = cpu; cpu_buffer->buffer = buffer; - spin_lock_init(&cpu_buffer->reader_lock); + raw_spin_lock_init(&cpu_buffer->reader_lock); lockdep_set_class(&cpu_buffer->reader_lock, buffer->reader_lock_key); cpu_buffer->lock = (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED; @@ -1259,7 +1261,7 @@ rb_remove_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned nr_pages) struct list_head *p; unsigned i; - spin_lock_irq(&cpu_buffer->reader_lock); + raw_spin_lock_irq(&cpu_buffer->reader_lock); rb_head_page_deactivate(cpu_buffer); for (i = 0; i < nr_pages; i++) { @@ -1277,7 +1279,7 @@ rb_remove_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned nr_pages) rb_check_pages(cpu_buffer); out: - spin_unlock_irq(&cpu_buffer->reader_lock); + raw_spin_unlock_irq(&cpu_buffer->reader_lock); } static void @@ -1288,7 +1290,7 @@ rb_insert_pages(struct ring_buffer_per_cpu *cpu_buffer, struct list_head *p; unsigned i; - spin_lock_irq(&cpu_buffer->reader_lock); + raw_spin_lock_irq(&cpu_buffer->reader_lock); rb_head_page_deactivate(cpu_buffer); for (i = 0; i < nr_pages; i++) { @@ -1303,7 +1305,7 @@ rb_insert_pages(struct ring_buffer_per_cpu *cpu_buffer, rb_check_pages(cpu_buffer); out: - spin_unlock_irq(&cpu_buffer->reader_lock); + raw_spin_unlock_irq(&cpu_buffer->reader_lock); } /** @@ -1708,6 +1710,7 @@ rb_handle_head_page(struct ring_buffer_per_cpu *cpu_buffer, * the counters. */ local_add(entries, &cpu_buffer->overrun); + local_sub(BUF_PAGE_SIZE, &cpu_buffer->entries_bytes); /* * The entries will be zeroed out when we move the @@ -1863,6 +1866,9 @@ rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer, event = __rb_page_index(tail_page, tail); kmemcheck_annotate_bitfield(event, bitfield); + /* account for padding bytes */ + local_add(BUF_PAGE_SIZE - tail, &cpu_buffer->entries_bytes); + /* * Save the original length to the meta data. * This will be used by the reader to add lost event @@ -2054,6 +2060,9 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer, if (!tail) tail_page->page->time_stamp = ts; + /* account for these added bytes */ + local_add(length, &cpu_buffer->entries_bytes); + return event; } @@ -2076,6 +2085,7 @@ rb_try_to_discard(struct ring_buffer_per_cpu *cpu_buffer, if (bpage->page == (void *)addr && rb_page_write(bpage) == old_index) { unsigned long write_mask = local_read(&bpage->write) & ~RB_WRITE_MASK; + unsigned long event_length = rb_event_length(event); /* * This is on the tail page. It is possible that * a write could come in and move the tail page @@ -2085,8 +2095,11 @@ rb_try_to_discard(struct ring_buffer_per_cpu *cpu_buffer, old_index += write_mask; new_index += write_mask; index = local_cmpxchg(&bpage->write, old_index, new_index); - if (index == old_index) + if (index == old_index) { + /* update counters */ + local_sub(event_length, &cpu_buffer->entries_bytes); return 1; + } } /* could not discard */ @@ -2661,6 +2674,58 @@ rb_num_of_entries(struct ring_buffer_per_cpu *cpu_buffer) } /** + * ring_buffer_oldest_event_ts - get the oldest event timestamp from the buffer + * @buffer: The ring buffer + * @cpu: The per CPU buffer to read from. + */ +unsigned long ring_buffer_oldest_event_ts(struct ring_buffer *buffer, int cpu) +{ + unsigned long flags; + struct ring_buffer_per_cpu *cpu_buffer; + struct buffer_page *bpage; + unsigned long ret; + + if (!cpumask_test_cpu(cpu, buffer->cpumask)) + return 0; + + cpu_buffer = buffer->buffers[cpu]; + raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags); + /* + * if the tail is on reader_page, oldest time stamp is on the reader + * page + */ + if (cpu_buffer->tail_page == cpu_buffer->reader_page) + bpage = cpu_buffer->reader_page; + else + bpage = rb_set_head_page(cpu_buffer); + ret = bpage->page->time_stamp; + raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); + + return ret; +} +EXPORT_SYMBOL_GPL(ring_buffer_oldest_event_ts); + +/** + * ring_buffer_bytes_cpu - get the number of bytes consumed in a cpu buffer + * @buffer: The ring buffer + * @cpu: The per CPU buffer to read from. + */ +unsigned long ring_buffer_bytes_cpu(struct ring_buffer *buffer, int cpu) +{ + struct ring_buffer_per_cpu *cpu_buffer; + unsigned long ret; + + if (!cpumask_test_cpu(cpu, buffer->cpumask)) + return 0; + + cpu_buffer = buffer->buffers[cpu]; + ret = local_read(&cpu_buffer->entries_bytes) - cpu_buffer->read_bytes; + + return ret; +} +EXPORT_SYMBOL_GPL(ring_buffer_bytes_cpu); + +/** * ring_buffer_entries_cpu - get the number of entries in a cpu buffer * @buffer: The ring buffer * @cpu: The per CPU buffer to get the entries from. @@ -2804,9 +2869,9 @@ void ring_buffer_iter_reset(struct ring_buffer_iter *iter) cpu_buffer = iter->cpu_buffer; - spin_lock_irqsave(&cpu_buffer->reader_lock, flags); + raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags); rb_iter_reset(iter); - spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); + raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); } EXPORT_SYMBOL_GPL(ring_buffer_iter_reset); @@ -3265,12 +3330,12 @@ ring_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts, again: local_irq_save(flags); if (dolock) - spin_lock(&cpu_buffer->reader_lock); + raw_spin_lock(&cpu_buffer->reader_lock); event = rb_buffer_peek(cpu_buffer, ts, lost_events); if (event && event->type_len == RINGBUF_TYPE_PADDING) rb_advance_reader(cpu_buffer); if (dolock) - spin_unlock(&cpu_buffer->reader_lock); + raw_spin_unlock(&cpu_buffer->reader_lock); local_irq_restore(flags); if (event && event->type_len == RINGBUF_TYPE_PADDING) @@ -3295,9 +3360,9 @@ ring_buffer_iter_peek(struct ring_buffer_iter *iter, u64 *ts) unsigned long flags; again: - spin_lock_irqsave(&cpu_buffer->reader_lock, flags); + raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags); event = rb_iter_peek(iter, ts); - spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); + raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); if (event && event->type_len == RINGBUF_TYPE_PADDING) goto again; @@ -3337,7 +3402,7 @@ ring_buffer_consume(struct ring_buffer *buffer, int cpu, u64 *ts, cpu_buffer = buffer->buffers[cpu]; local_irq_save(flags); if (dolock) - spin_lock(&cpu_buffer->reader_lock); + raw_spin_lock(&cpu_buffer->reader_lock); event = rb_buffer_peek(cpu_buffer, ts, lost_events); if (event) { @@ -3346,7 +3411,7 @@ ring_buffer_consume(struct ring_buffer *buffer, int cpu, u64 *ts, } if (dolock) - spin_unlock(&cpu_buffer->reader_lock); + raw_spin_unlock(&cpu_buffer->reader_lock); local_irq_restore(flags); out: @@ -3438,11 +3503,11 @@ ring_buffer_read_start(struct ring_buffer_iter *iter) cpu_buffer = iter->cpu_buffer; - spin_lock_irqsave(&cpu_buffer->reader_lock, flags); + raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags); arch_spin_lock(&cpu_buffer->lock); rb_iter_reset(iter); arch_spin_unlock(&cpu_buffer->lock); - spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); + raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); } EXPORT_SYMBOL_GPL(ring_buffer_read_start); @@ -3477,7 +3542,7 @@ ring_buffer_read(struct ring_buffer_iter *iter, u64 *ts) struct ring_buffer_per_cpu *cpu_buffer = iter->cpu_buffer; unsigned long flags; - spin_lock_irqsave(&cpu_buffer->reader_lock, flags); + raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags); again: event = rb_iter_peek(iter, ts); if (!event) @@ -3488,7 +3553,7 @@ ring_buffer_read(struct ring_buffer_iter *iter, u64 *ts) rb_advance_iter(iter); out: - spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); + raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); return event; } @@ -3527,11 +3592,13 @@ rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer) cpu_buffer->reader_page->read = 0; local_set(&cpu_buffer->commit_overrun, 0); + local_set(&cpu_buffer->entries_bytes, 0); local_set(&cpu_buffer->overrun, 0); local_set(&cpu_buffer->entries, 0); local_set(&cpu_buffer->committing, 0); local_set(&cpu_buffer->commits, 0); cpu_buffer->read = 0; + cpu_buffer->read_bytes = 0; cpu_buffer->write_stamp = 0; cpu_buffer->read_stamp = 0; @@ -3557,7 +3624,7 @@ void ring_buffer_reset_cpu(struct ring_buffer *buffer, int cpu) atomic_inc(&cpu_buffer->record_disabled); - spin_lock_irqsave(&cpu_buffer->reader_lock, flags); + raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags); if (RB_WARN_ON(cpu_buffer, local_read(&cpu_buffer->committing))) goto out; @@ -3569,7 +3636,7 @@ void ring_buffer_reset_cpu(struct ring_buffer *buffer, int cpu) arch_spin_unlock(&cpu_buffer->lock); out: - spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); + raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); atomic_dec(&cpu_buffer->record_disabled); } @@ -3607,10 +3674,10 @@ int ring_buffer_empty(struct ring_buffer *buffer) cpu_buffer = buffer->buffers[cpu]; local_irq_save(flags); if (dolock) - spin_lock(&cpu_buffer->reader_lock); + raw_spin_lock(&cpu_buffer->reader_lock); ret = rb_per_cpu_empty(cpu_buffer); if (dolock) - spin_unlock(&cpu_buffer->reader_lock); + raw_spin_unlock(&cpu_buffer->reader_lock); local_irq_restore(flags); if (!ret) @@ -3641,10 +3708,10 @@ int ring_buffer_empty_cpu(struct ring_buffer *buffer, int cpu) cpu_buffer = buffer->buffers[cpu]; local_irq_save(flags); if (dolock) - spin_lock(&cpu_buffer->reader_lock); + raw_spin_lock(&cpu_buffer->reader_lock); ret = rb_per_cpu_empty(cpu_buffer); if (dolock) - spin_unlock(&cpu_buffer->reader_lock); + raw_spin_unlock(&cpu_buffer->reader_lock); local_irq_restore(flags); return ret; @@ -3841,7 +3908,7 @@ int ring_buffer_read_page(struct ring_buffer *buffer, if (!bpage) goto out; - spin_lock_irqsave(&cpu_buffer->reader_lock, flags); + raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags); reader = rb_get_reader_page(cpu_buffer); if (!reader) @@ -3918,6 +3985,7 @@ int ring_buffer_read_page(struct ring_buffer *buffer, } else { /* update the entry counter */ cpu_buffer->read += rb_page_entries(reader); + cpu_buffer->read_bytes += BUF_PAGE_SIZE; /* swap the pages */ rb_init_page(bpage); @@ -3964,7 +4032,7 @@ int ring_buffer_read_page(struct ring_buffer *buffer, memset(&bpage->data[commit], 0, BUF_PAGE_SIZE - commit); out_unlock: - spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); + raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); out: return ret; diff --git a/kernel/trace/rpm-traces.c b/kernel/trace/rpm-traces.c new file mode 100644 index 0000000..4b3b5ea --- /dev/null +++ b/kernel/trace/rpm-traces.c @@ -0,0 +1,20 @@ +/* + * Power trace points + * + * Copyright (C) 2009 Ming Lei <ming.lei@canonical.com> + */ + +#include <linux/string.h> +#include <linux/types.h> +#include <linux/workqueue.h> +#include <linux/sched.h> +#include <linux/module.h> +#include <linux/usb.h> + +#define CREATE_TRACE_POINTS +#include <trace/events/rpm.h> + +EXPORT_TRACEPOINT_SYMBOL_GPL(rpm_return_int); +EXPORT_TRACEPOINT_SYMBOL_GPL(rpm_idle); +EXPORT_TRACEPOINT_SYMBOL_GPL(rpm_suspend); +EXPORT_TRACEPOINT_SYMBOL_GPL(rpm_resume); diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index e5df02c..f2bd275 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -341,7 +341,7 @@ unsigned long trace_flags = TRACE_ITER_PRINT_PARENT | TRACE_ITER_PRINTK | TRACE_ITER_GRAPH_TIME | TRACE_ITER_RECORD_CMD | TRACE_ITER_OVERWRITE; static int trace_stop_count; -static DEFINE_SPINLOCK(tracing_start_lock); +static DEFINE_RAW_SPINLOCK(tracing_start_lock); static void wakeup_work_handler(struct work_struct *work) { @@ -435,6 +435,7 @@ static struct { } trace_clocks[] = { { trace_clock_local, "local" }, { trace_clock_global, "global" }, + { trace_clock_counter, "counter" }, }; int trace_clock_id; @@ -960,7 +961,7 @@ void tracing_start(void) if (tracing_disabled) return; - spin_lock_irqsave(&tracing_start_lock, flags); + raw_spin_lock_irqsave(&tracing_start_lock, flags); if (--trace_stop_count) { if (trace_stop_count < 0) { /* Someone screwed up their debugging */ @@ -985,7 +986,7 @@ void tracing_start(void) ftrace_start(); out: - spin_unlock_irqrestore(&tracing_start_lock, flags); + raw_spin_unlock_irqrestore(&tracing_start_lock, flags); } /** @@ -1000,7 +1001,7 @@ void tracing_stop(void) unsigned long flags; ftrace_stop(); - spin_lock_irqsave(&tracing_start_lock, flags); + raw_spin_lock_irqsave(&tracing_start_lock, flags); if (trace_stop_count++) goto out; @@ -1018,7 +1019,7 @@ void tracing_stop(void) arch_spin_unlock(&ftrace_max_lock); out: - spin_unlock_irqrestore(&tracing_start_lock, flags); + raw_spin_unlock_irqrestore(&tracing_start_lock, flags); } void trace_stop_cmdline_recording(void); @@ -2159,6 +2160,14 @@ void trace_default_header(struct seq_file *m) } } +static void test_ftrace_alive(struct seq_file *m) +{ + if (!ftrace_is_dead()) + return; + seq_printf(m, "# WARNING: FUNCTION TRACING IS CORRUPTED\n"); + seq_printf(m, "# MAY BE MISSING FUNCTION EVENTS\n"); +} + static int s_show(struct seq_file *m, void *v) { struct trace_iterator *iter = v; @@ -2168,6 +2177,7 @@ static int s_show(struct seq_file *m, void *v) if (iter->tr) { seq_printf(m, "# tracer: %s\n", iter->trace->name); seq_puts(m, "#\n"); + test_ftrace_alive(m); } if (iter->trace && iter->trace->print_header) iter->trace->print_header(m); @@ -2710,9 +2720,9 @@ static const char readme_msg[] = "# cat /sys/kernel/debug/tracing/trace_options\n" "noprint-parent nosym-offset nosym-addr noverbose\n" "# echo print-parent > /sys/kernel/debug/tracing/trace_options\n" - "# echo 1 > /sys/kernel/debug/tracing/tracing_enabled\n" + "# echo 1 > /sys/kernel/debug/tracing/tracing_on\n" "# cat /sys/kernel/debug/tracing/trace > /tmp/trace.txt\n" - "# echo 0 > /sys/kernel/debug/tracing/tracing_enabled\n" + "# echo 0 > /sys/kernel/debug/tracing/tracing_on\n" ; static ssize_t @@ -3569,6 +3579,30 @@ tracing_entries_write(struct file *filp, const char __user *ubuf, } static ssize_t +tracing_total_entries_read(struct file *filp, char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + struct trace_array *tr = filp->private_data; + char buf[64]; + int r, cpu; + unsigned long size = 0, expanded_size = 0; + + mutex_lock(&trace_types_lock); + for_each_tracing_cpu(cpu) { + size += tr->entries >> 10; + if (!ring_buffer_expanded) + expanded_size += trace_buf_size >> 10; + } + if (ring_buffer_expanded) + r = sprintf(buf, "%lu\n", size); + else + r = sprintf(buf, "%lu (expanded: %lu)\n", size, expanded_size); + mutex_unlock(&trace_types_lock); + + return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); +} + +static ssize_t tracing_free_buffer_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *ppos) { @@ -3594,22 +3628,24 @@ tracing_free_buffer_release(struct inode *inode, struct file *filp) return 0; } -static int mark_printk(const char *fmt, ...) -{ - int ret; - va_list args; - va_start(args, fmt); - ret = trace_vprintk(0, fmt, args); - va_end(args); - return ret; -} - static ssize_t tracing_mark_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *fpos) { - char *buf; - size_t written; + unsigned long addr = (unsigned long)ubuf; + struct ring_buffer_event *event; + struct ring_buffer *buffer; + struct print_entry *entry; + unsigned long irq_flags; + struct page *pages[2]; + int nr_pages = 1; + ssize_t written; + void *page1; + void *page2; + int offset; + int size; + int len; + int ret; if (tracing_disabled) return -EINVAL; @@ -3617,28 +3653,81 @@ tracing_mark_write(struct file *filp, const char __user *ubuf, if (cnt > TRACE_BUF_SIZE) cnt = TRACE_BUF_SIZE; - buf = kmalloc(cnt + 2, GFP_KERNEL); - if (buf == NULL) - return -ENOMEM; + /* + * Userspace is injecting traces into the kernel trace buffer. + * We want to be as non intrusive as possible. + * To do so, we do not want to allocate any special buffers + * or take any locks, but instead write the userspace data + * straight into the ring buffer. + * + * First we need to pin the userspace buffer into memory, + * which, most likely it is, because it just referenced it. + * But there's no guarantee that it is. By using get_user_pages_fast() + * and kmap_atomic/kunmap_atomic() we can get access to the + * pages directly. We then write the data directly into the + * ring buffer. + */ + BUILD_BUG_ON(TRACE_BUF_SIZE >= PAGE_SIZE); - if (copy_from_user(buf, ubuf, cnt)) { - kfree(buf); - return -EFAULT; + /* check if we cross pages */ + if ((addr & PAGE_MASK) != ((addr + cnt) & PAGE_MASK)) + nr_pages = 2; + + offset = addr & (PAGE_SIZE - 1); + addr &= PAGE_MASK; + + ret = get_user_pages_fast(addr, nr_pages, 0, pages); + if (ret < nr_pages) { + while (--ret >= 0) + put_page(pages[ret]); + written = -EFAULT; + goto out; + } + + page1 = kmap_atomic(pages[0]); + if (nr_pages == 2) + page2 = kmap_atomic(pages[1]); + + local_save_flags(irq_flags); + size = sizeof(*entry) + cnt + 2; /* possible \n added */ + buffer = global_trace.buffer; + event = trace_buffer_lock_reserve(buffer, TRACE_PRINT, size, + irq_flags, preempt_count()); + if (!event) { + /* Ring buffer disabled, return as if not open for write */ + written = -EBADF; + goto out_unlock; } - if (buf[cnt-1] != '\n') { - buf[cnt] = '\n'; - buf[cnt+1] = '\0'; + + entry = ring_buffer_event_data(event); + entry->ip = _THIS_IP_; + + if (nr_pages == 2) { + len = PAGE_SIZE - offset; + memcpy(&entry->buf, page1 + offset, len); + memcpy(&entry->buf[len], page2, cnt - len); } else - buf[cnt] = '\0'; + memcpy(&entry->buf, page1 + offset, cnt); - written = mark_printk("%s", buf); - kfree(buf); - *fpos += written; + if (entry->buf[cnt - 1] != '\n') { + entry->buf[cnt] = '\n'; + entry->buf[cnt + 1] = '\0'; + } else + entry->buf[cnt] = '\0'; + + ring_buffer_unlock_commit(buffer, event); - /* don't tell userspace we wrote more - it might confuse them */ - if (written > cnt) - written = cnt; + written = cnt; + *fpos += written; + + out_unlock: + if (nr_pages == 2) + kunmap_atomic(page2); + kunmap_atomic(page1); + while (nr_pages > 0) + put_page(pages[--nr_pages]); + out: return written; } @@ -3739,6 +3828,12 @@ static const struct file_operations tracing_entries_fops = { .llseek = generic_file_llseek, }; +static const struct file_operations tracing_total_entries_fops = { + .open = tracing_open_generic, + .read = tracing_total_entries_read, + .llseek = generic_file_llseek, +}; + static const struct file_operations tracing_free_buffer_fops = { .write = tracing_free_buffer_write, .release = tracing_free_buffer_release, @@ -3808,8 +3903,6 @@ tracing_buffers_read(struct file *filp, char __user *ubuf, if (info->read < PAGE_SIZE) goto read; - info->read = 0; - trace_access_lock(info->cpu); ret = ring_buffer_read_page(info->tr->buffer, &info->spare, @@ -3819,6 +3912,8 @@ tracing_buffers_read(struct file *filp, char __user *ubuf, if (ret < 0) return 0; + info->read = 0; + read: size = PAGE_SIZE - info->read; if (size > count) @@ -4026,6 +4121,8 @@ tracing_stats_read(struct file *filp, char __user *ubuf, struct trace_array *tr = &global_trace; struct trace_seq *s; unsigned long cnt; + unsigned long long t; + unsigned long usec_rem; s = kmalloc(sizeof(*s), GFP_KERNEL); if (!s) @@ -4042,6 +4139,17 @@ tracing_stats_read(struct file *filp, char __user *ubuf, cnt = ring_buffer_commit_overrun_cpu(tr->buffer, cpu); trace_seq_printf(s, "commit overrun: %ld\n", cnt); + cnt = ring_buffer_bytes_cpu(tr->buffer, cpu); + trace_seq_printf(s, "bytes: %ld\n", cnt); + + t = ns2usecs(ring_buffer_oldest_event_ts(tr->buffer, cpu)); + usec_rem = do_div(t, USEC_PER_SEC); + trace_seq_printf(s, "oldest event ts: %5llu.%06lu\n", t, usec_rem); + + t = ns2usecs(ring_buffer_time_stamp(tr->buffer, cpu)); + usec_rem = do_div(t, USEC_PER_SEC); + trace_seq_printf(s, "now ts: %5llu.%06lu\n", t, usec_rem); + count = simple_read_from_buffer(ubuf, count, ppos, s->buffer, s->len); kfree(s); @@ -4450,6 +4558,9 @@ static __init int tracer_init_debugfs(void) trace_create_file("buffer_size_kb", 0644, d_tracer, &global_trace, &tracing_entries_fops); + trace_create_file("buffer_total_size_kb", 0444, d_tracer, + &global_trace, &tracing_total_entries_fops); + trace_create_file("free_buffer", 0644, d_tracer, &global_trace, &tracing_free_buffer_fops); @@ -4566,6 +4677,12 @@ __ftrace_dump(bool disable_tracing, enum ftrace_dump_mode oops_dump_mode) tracing_off(); + /* Did function tracer already get disabled? */ + if (ftrace_is_dead()) { + printk("# WARNING: FUNCTION TRACING IS CORRUPTED\n"); + printk("# MAY BE MISSING FUNCTION EVENTS\n"); + } + if (disable_tracing) ftrace_kill(); diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 616846b..092e1f8 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -579,11 +579,13 @@ static inline int ftrace_trace_task(struct task_struct *task) return test_tsk_trace_trace(task); } +extern int ftrace_is_dead(void); #else static inline int ftrace_trace_task(struct task_struct *task) { return 1; } +static inline int ftrace_is_dead(void) { return 0; } #endif /* @@ -761,16 +763,10 @@ struct filter_pred { filter_pred_fn_t fn; u64 val; struct regex regex; - /* - * Leaf nodes use field_name, ops is used by AND and OR - * nodes. The field_name is always freed when freeing a pred. - * We can overload field_name for ops and have it freed - * as well. - */ - union { - char *field_name; - unsigned short *ops; - }; + unsigned short *ops; +#ifdef CONFIG_FTRACE_STARTUP_TEST + struct ftrace_event_field *field; +#endif int offset; int not; int op; diff --git a/kernel/trace/trace_clock.c b/kernel/trace/trace_clock.c index 6302747..3947835 100644 --- a/kernel/trace/trace_clock.c +++ b/kernel/trace/trace_clock.c @@ -113,3 +113,15 @@ u64 notrace trace_clock_global(void) return now; } + +static atomic64_t trace_counter; + +/* + * trace_clock_counter(): simply an atomic counter. + * Use the trace_counter "counter" for cases where you do not care + * about timings, but are interested in strict ordering. + */ +u64 notrace trace_clock_counter(void) +{ + return atomic64_add_return(1, &trace_counter); +} diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index 256764ec..816d3d0 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -381,6 +381,63 @@ get_pred_parent(struct filter_pred *pred, struct filter_pred *preds, return pred; } +enum walk_return { + WALK_PRED_ABORT, + WALK_PRED_PARENT, + WALK_PRED_DEFAULT, +}; + +typedef int (*filter_pred_walkcb_t) (enum move_type move, + struct filter_pred *pred, + int *err, void *data); + +static int walk_pred_tree(struct filter_pred *preds, + struct filter_pred *root, + filter_pred_walkcb_t cb, void *data) +{ + struct filter_pred *pred = root; + enum move_type move = MOVE_DOWN; + int done = 0; + + if (!preds) + return -EINVAL; + + do { + int err = 0, ret; + + ret = cb(move, pred, &err, data); + if (ret == WALK_PRED_ABORT) + return err; + if (ret == WALK_PRED_PARENT) + goto get_parent; + + switch (move) { + case MOVE_DOWN: + if (pred->left != FILTER_PRED_INVALID) { + pred = &preds[pred->left]; + continue; + } + goto get_parent; + case MOVE_UP_FROM_LEFT: + pred = &preds[pred->right]; + move = MOVE_DOWN; + continue; + case MOVE_UP_FROM_RIGHT: + get_parent: + if (pred == root) + break; + pred = get_pred_parent(pred, preds, + pred->parent, + &move); + continue; + } + done = 1; + } while (!done); + + /* We are fine. */ + return 0; +} + /* * A series of AND or ORs where found together. Instead of * climbing up and down the tree branches, an array of the @@ -410,99 +467,91 @@ static int process_ops(struct filter_pred *preds, for (i = 0; i < op->val; i++) { pred = &preds[op->ops[i]]; - match = pred->fn(pred, rec); + if (!WARN_ON_ONCE(!pred->fn)) + match = pred->fn(pred, rec); if (!!match == type) return match; } return match; } +struct filter_match_preds_data { + struct filter_pred *preds; + int match; + void *rec; +}; + +static int filter_match_preds_cb(enum move_type move, struct filter_pred *pred, + int *err, void *data) +{ + struct filter_match_preds_data *d = data; + + *err = 0; + switch (move) { + case MOVE_DOWN: + /* only AND and OR have children */ + if (pred->left != FILTER_PRED_INVALID) { + /* If ops is set, then it was folded. */ + if (!pred->ops) + return WALK_PRED_DEFAULT; + /* We can treat folded ops as a leaf node */ + d->match = process_ops(d->preds, pred, d->rec); + } else { + if (!WARN_ON_ONCE(!pred->fn)) + d->match = pred->fn(pred, d->rec); + } + + return WALK_PRED_PARENT; + case MOVE_UP_FROM_LEFT: + /* + * Check for short circuits. + * + * Optimization: !!match == (pred->op == OP_OR) + * is the same as: + * if ((match && pred->op == OP_OR) || + * (!match && pred->op == OP_AND)) + */ + if (!!d->match == (pred->op == OP_OR)) + return WALK_PRED_PARENT; + break; + case MOVE_UP_FROM_RIGHT: + break; + } + + return WALK_PRED_DEFAULT; +} + /* return 1 if event matches, 0 otherwise (discard) */ int filter_match_preds(struct event_filter *filter, void *rec) { - int match = -1; - enum move_type move = MOVE_DOWN; struct filter_pred *preds; - struct filter_pred *pred; struct filter_pred *root; - int n_preds; - int done = 0; + struct filter_match_preds_data data = { + /* match is currently meaningless */ + .match = -1, + .rec = rec, + }; + int n_preds, ret; /* no filter is considered a match */ if (!filter) return 1; n_preds = filter->n_preds; - if (!n_preds) return 1; /* * n_preds, root and filter->preds are protect with preemption disabled. */ - preds = rcu_dereference_sched(filter->preds); root = rcu_dereference_sched(filter->root); if (!root) return 1; - pred = root; - - /* match is currently meaningless */ - match = -1; - - do { - switch (move) { - case MOVE_DOWN: - /* only AND and OR have children */ - if (pred->left != FILTER_PRED_INVALID) { - /* If ops is set, then it was folded. */ - if (!pred->ops) { - /* keep going to down the left side */ - pred = &preds[pred->left]; - continue; - } - /* We can treat folded ops as a leaf node */ - match = process_ops(preds, pred, rec); - } else - match = pred->fn(pred, rec); - /* If this pred is the only pred */ - if (pred == root) - break; - pred = get_pred_parent(pred, preds, - pred->parent, &move); - continue; - case MOVE_UP_FROM_LEFT: - /* - * Check for short circuits. - * - * Optimization: !!match == (pred->op == OP_OR) - * is the same as: - * if ((match && pred->op == OP_OR) || - * (!match && pred->op == OP_AND)) - */ - if (!!match == (pred->op == OP_OR)) { - if (pred == root) - break; - pred = get_pred_parent(pred, preds, - pred->parent, &move); - continue; - } - /* now go down the right side of the tree. */ - pred = &preds[pred->right]; - move = MOVE_DOWN; - continue; - case MOVE_UP_FROM_RIGHT: - /* We finished this equation. */ - if (pred == root) - break; - pred = get_pred_parent(pred, preds, - pred->parent, &move); - continue; - } - done = 1; - } while (!done); - - return match; + data.preds = preds = rcu_dereference_sched(filter->preds); + ret = walk_pred_tree(preds, root, filter_match_preds_cb, &data); + WARN_ON(ret); + return data.match; } EXPORT_SYMBOL_GPL(filter_match_preds); @@ -628,22 +677,6 @@ find_event_field(struct ftrace_event_call *call, char *name) return __find_event_field(head, name); } -static void filter_free_pred(struct filter_pred *pred) -{ - if (!pred) - return; - - kfree(pred->field_name); - kfree(pred); -} - -static void filter_clear_pred(struct filter_pred *pred) -{ - kfree(pred->field_name); - pred->field_name = NULL; - pred->regex.len = 0; -} - static int __alloc_pred_stack(struct pred_stack *stack, int n_preds) { stack->preds = kzalloc(sizeof(*stack->preds)*(n_preds + 1), GFP_KERNEL); @@ -689,20 +722,13 @@ __pop_pred_stack(struct pred_stack *stack) static int filter_set_pred(struct event_filter *filter, int idx, struct pred_stack *stack, - struct filter_pred *src, - filter_pred_fn_t fn) + struct filter_pred *src) { struct filter_pred *dest = &filter->preds[idx]; struct filter_pred *left; struct filter_pred *right; *dest = *src; - if (src->field_name) { - dest->field_name = kstrdup(src->field_name, GFP_KERNEL); - if (!dest->field_name) - return -ENOMEM; - } - dest->fn = fn; dest->index = idx; if (dest->op == OP_OR || dest->op == OP_AND) { @@ -743,11 +769,7 @@ static int filter_set_pred(struct event_filter *filter, static void __free_preds(struct event_filter *filter) { - int i; - if (filter->preds) { - for (i = 0; i < filter->a_preds; i++) - kfree(filter->preds[i].field_name); kfree(filter->preds); filter->preds = NULL; } @@ -840,23 +862,19 @@ static void filter_free_subsystem_filters(struct event_subsystem *system) } } -static int filter_add_pred_fn(struct filter_parse_state *ps, - struct ftrace_event_call *call, - struct event_filter *filter, - struct filter_pred *pred, - struct pred_stack *stack, - filter_pred_fn_t fn) +static int filter_add_pred(struct filter_parse_state *ps, + struct event_filter *filter, + struct filter_pred *pred, + struct pred_stack *stack) { - int idx, err; + int err; if (WARN_ON(filter->n_preds == filter->a_preds)) { parse_error(ps, FILT_ERR_TOO_MANY_PREDS, 0); return -ENOSPC; } - idx = filter->n_preds; - filter_clear_pred(&filter->preds[idx]); - err = filter_set_pred(filter, idx, stack, pred, fn); + err = filter_set_pred(filter, filter->n_preds, stack, pred); if (err) return err; @@ -937,31 +955,15 @@ static filter_pred_fn_t select_comparison_fn(int op, int field_size, return fn; } -static int filter_add_pred(struct filter_parse_state *ps, - struct ftrace_event_call *call, - struct event_filter *filter, - struct filter_pred *pred, - struct pred_stack *stack, - bool dry_run) +static int init_pred(struct filter_parse_state *ps, + struct ftrace_event_field *field, + struct filter_pred *pred) + { - struct ftrace_event_field *field; - filter_pred_fn_t fn; + filter_pred_fn_t fn = filter_pred_none; unsigned long long val; int ret; - fn = pred->fn = filter_pred_none; - - if (pred->op == OP_AND) - goto add_pred_fn; - else if (pred->op == OP_OR) - goto add_pred_fn; - - field = find_event_field(call, pred->field_name); - if (!field) { - parse_error(ps, FILT_ERR_FIELD_NOT_FOUND, 0); - return -EINVAL; - } - pred->offset = field->offset; if (!is_legal_op(field, pred->op)) { @@ -1001,9 +1003,7 @@ static int filter_add_pred(struct filter_parse_state *ps, if (pred->op == OP_NE) pred->not = 1; -add_pred_fn: - if (!dry_run) - return filter_add_pred_fn(ps, call, filter, pred, stack, fn); + pred->fn = fn; return 0; } @@ -1302,39 +1302,37 @@ parse_operand: return 0; } -static struct filter_pred *create_pred(int op, char *operand1, char *operand2) +static struct filter_pred *create_pred(struct filter_parse_state *ps, + struct ftrace_event_call *call, + int op, char *operand1, char *operand2) { - struct filter_pred *pred; + struct ftrace_event_field *field; + static struct filter_pred pred; - pred = kzalloc(sizeof(*pred), GFP_KERNEL); - if (!pred) - return NULL; + memset(&pred, 0, sizeof(pred)); + pred.op = op; - pred->field_name = kstrdup(operand1, GFP_KERNEL); - if (!pred->field_name) { - kfree(pred); + if (op == OP_AND || op == OP_OR) + return &pred; + + if (!operand1 || !operand2) { + parse_error(ps, FILT_ERR_MISSING_FIELD, 0); return NULL; } - strcpy(pred->regex.pattern, operand2); - pred->regex.len = strlen(pred->regex.pattern); - - pred->op = op; - - return pred; -} - -static struct filter_pred *create_logical_pred(int op) -{ - struct filter_pred *pred; - - pred = kzalloc(sizeof(*pred), GFP_KERNEL); - if (!pred) + field = find_event_field(call, operand1); + if (!field) { + parse_error(ps, FILT_ERR_FIELD_NOT_FOUND, 0); return NULL; + } - pred->op = op; + strcpy(pred.regex.pattern, operand2); + pred.regex.len = strlen(pred.regex.pattern); - return pred; +#ifdef CONFIG_FTRACE_STARTUP_TEST + pred.field = field; +#endif + return init_pred(ps, field, &pred) ? NULL : &pred; } static int check_preds(struct filter_parse_state *ps) @@ -1375,6 +1373,23 @@ static int count_preds(struct filter_parse_state *ps) return n_preds; } +struct check_pred_data { + int count; + int max; +}; + +static int check_pred_tree_cb(enum move_type move, struct filter_pred *pred, + int *err, void *data) +{ + struct check_pred_data *d = data; + + if (WARN_ON(d->count++ > d->max)) { + *err = -EINVAL; + return WALK_PRED_ABORT; + } + return WALK_PRED_DEFAULT; +} + /* * The tree is walked at filtering of an event. If the tree is not correctly * built, it may cause an infinite loop. Check here that the tree does @@ -1383,107 +1398,76 @@ static int count_preds(struct filter_parse_state *ps) static int check_pred_tree(struct event_filter *filter, struct filter_pred *root) { - struct filter_pred *preds; - struct filter_pred *pred; - enum move_type move = MOVE_DOWN; - int count = 0; - int done = 0; - int max; - - /* - * The max that we can hit a node is three times. - * Once going down, once coming up from left, and - * once coming up from right. This is more than enough - * since leafs are only hit a single time. - */ - max = 3 * filter->n_preds; + struct check_pred_data data = { + /* + * The max that we can hit a node is three times. + * Once going down, once coming up from left, and + * once coming up from right. This is more than enough + * since leafs are only hit a single time. + */ + .max = 3 * filter->n_preds, + .count = 0, + }; - preds = filter->preds; - if (!preds) - return -EINVAL; - pred = root; + return walk_pred_tree(filter->preds, root, + check_pred_tree_cb, &data); +} - do { - if (WARN_ON(count++ > max)) - return -EINVAL; +static int count_leafs_cb(enum move_type move, struct filter_pred *pred, + int *err, void *data) +{ + int *count = data; - switch (move) { - case MOVE_DOWN: - if (pred->left != FILTER_PRED_INVALID) { - pred = &preds[pred->left]; - continue; - } - /* A leaf at the root is just a leaf in the tree */ - if (pred == root) - break; - pred = get_pred_parent(pred, preds, - pred->parent, &move); - continue; - case MOVE_UP_FROM_LEFT: - pred = &preds[pred->right]; - move = MOVE_DOWN; - continue; - case MOVE_UP_FROM_RIGHT: - if (pred == root) - break; - pred = get_pred_parent(pred, preds, - pred->parent, &move); - continue; - } - done = 1; - } while (!done); + if ((move == MOVE_DOWN) && + (pred->left == FILTER_PRED_INVALID)) + (*count)++; - /* We are fine. */ - return 0; + return WALK_PRED_DEFAULT; } static int count_leafs(struct filter_pred *preds, struct filter_pred *root) { - struct filter_pred *pred; - enum move_type move = MOVE_DOWN; - int count = 0; - int done = 0; + int count = 0, ret; - pred = root; + ret = walk_pred_tree(preds, root, count_leafs_cb, &count); + WARN_ON(ret); + return count; +} - do { - switch (move) { - case MOVE_DOWN: - if (pred->left != FILTER_PRED_INVALID) { - pred = &preds[pred->left]; - continue; - } - /* A leaf at the root is just a leaf in the tree */ - if (pred == root) - return 1; - count++; - pred = get_pred_parent(pred, preds, - pred->parent, &move); - continue; - case MOVE_UP_FROM_LEFT: - pred = &preds[pred->right]; - move = MOVE_DOWN; - continue; - case MOVE_UP_FROM_RIGHT: - if (pred == root) - break; - pred = get_pred_parent(pred, preds, - pred->parent, &move); - continue; - } - done = 1; - } while (!done); +struct fold_pred_data { + struct filter_pred *root; + int count; + int children; +}; - return count; +static int fold_pred_cb(enum move_type move, struct filter_pred *pred, + int *err, void *data) +{ + struct fold_pred_data *d = data; + struct filter_pred *root = d->root; + + if (move != MOVE_DOWN) + return WALK_PRED_DEFAULT; + if (pred->left != FILTER_PRED_INVALID) + return WALK_PRED_DEFAULT; + + if (WARN_ON(d->count == d->children)) { + *err = -EINVAL; + return WALK_PRED_ABORT; + } + + pred->index &= ~FILTER_PRED_FOLD; + root->ops[d->count++] = pred->index; + return WALK_PRED_DEFAULT; } static int fold_pred(struct filter_pred *preds, struct filter_pred *root) { - struct filter_pred *pred; - enum move_type move = MOVE_DOWN; - int count = 0; + struct fold_pred_data data = { + .root = root, + .count = 0, + }; int children; - int done = 0; /* No need to keep the fold flag */ root->index &= ~FILTER_PRED_FOLD; @@ -1501,37 +1485,26 @@ static int fold_pred(struct filter_pred *preds, struct filter_pred *root) return -ENOMEM; root->val = children; + data.children = children; + return walk_pred_tree(preds, root, fold_pred_cb, &data); +} - pred = root; - do { - switch (move) { - case MOVE_DOWN: - if (pred->left != FILTER_PRED_INVALID) { - pred = &preds[pred->left]; - continue; - } - if (WARN_ON(count == children)) - return -EINVAL; - pred->index &= ~FILTER_PRED_FOLD; - root->ops[count++] = pred->index; - pred = get_pred_parent(pred, preds, - pred->parent, &move); - continue; - case MOVE_UP_FROM_LEFT: - pred = &preds[pred->right]; - move = MOVE_DOWN; - continue; - case MOVE_UP_FROM_RIGHT: - if (pred == root) - break; - pred = get_pred_parent(pred, preds, - pred->parent, &move); - continue; - } - done = 1; - } while (!done); +static int fold_pred_tree_cb(enum move_type move, struct filter_pred *pred, + int *err, void *data) +{ + struct filter_pred *preds = data; - return 0; + if (move != MOVE_DOWN) + return WALK_PRED_DEFAULT; + if (!(pred->index & FILTER_PRED_FOLD)) + return WALK_PRED_DEFAULT; + + *err = fold_pred(preds, pred); + if (*err) + return WALK_PRED_ABORT; + + /* eveyrhing below is folded, continue with parent */ + return WALK_PRED_PARENT; } /* @@ -1542,51 +1515,8 @@ static int fold_pred(struct filter_pred *preds, struct filter_pred *root) static int fold_pred_tree(struct event_filter *filter, struct filter_pred *root) { - struct filter_pred *preds; - struct filter_pred *pred; - enum move_type move = MOVE_DOWN; - int done = 0; - int err; - - preds = filter->preds; - if (!preds) - return -EINVAL; - pred = root; - - do { - switch (move) { - case MOVE_DOWN: - if (pred->index & FILTER_PRED_FOLD) { - err = fold_pred(preds, pred); - if (err) - return err; - /* Folded nodes are like leafs */ - } else if (pred->left != FILTER_PRED_INVALID) { - pred = &preds[pred->left]; - continue; - } - - /* A leaf at the root is just a leaf in the tree */ - if (pred == root) - break; - pred = get_pred_parent(pred, preds, - pred->parent, &move); - continue; - case MOVE_UP_FROM_LEFT: - pred = &preds[pred->right]; - move = MOVE_DOWN; - continue; - case MOVE_UP_FROM_RIGHT: - if (pred == root) - break; - pred = get_pred_parent(pred, preds, - pred->parent, &move); - continue; - } - done = 1; - } while (!done); - - return 0; + return walk_pred_tree(filter->preds, root, fold_pred_tree_cb, + filter->preds); } static int replace_preds(struct ftrace_event_call *call, @@ -1643,27 +1573,17 @@ static int replace_preds(struct ftrace_event_call *call, goto fail; } - if (elt->op == OP_AND || elt->op == OP_OR) { - pred = create_logical_pred(elt->op); - goto add_pred; - } - - if (!operand1 || !operand2) { - parse_error(ps, FILT_ERR_MISSING_FIELD, 0); + pred = create_pred(ps, call, elt->op, operand1, operand2); + if (!pred) { err = -EINVAL; goto fail; } - pred = create_pred(elt->op, operand1, operand2); -add_pred: - if (!pred) { - err = -ENOMEM; - goto fail; + if (!dry_run) { + err = filter_add_pred(ps, filter, pred, &stack); + if (err) + goto fail; } - err = filter_add_pred(ps, call, filter, pred, &stack, dry_run); - filter_free_pred(pred); - if (err) - goto fail; operand1 = operand2 = NULL; } @@ -1958,17 +1878,14 @@ int ftrace_profile_set_filter(struct perf_event *event, int event_id, int err; struct event_filter *filter; struct filter_parse_state *ps; - struct ftrace_event_call *call = NULL; + struct ftrace_event_call *call; mutex_lock(&event_mutex); - list_for_each_entry(call, &ftrace_events, list) { - if (call->event.type == event_id) - break; - } + call = event->tp_event; err = -EINVAL; - if (&call->list == &ftrace_events) + if (!call) goto out_unlock; err = -EEXIST; @@ -2012,3 +1929,215 @@ out_unlock: #endif /* CONFIG_PERF_EVENTS */ +#ifdef CONFIG_FTRACE_STARTUP_TEST + +#include <linux/types.h> +#include <linux/tracepoint.h> + +#define CREATE_TRACE_POINTS +#include "trace_events_filter_test.h" + +static int test_get_filter(char *filter_str, struct ftrace_event_call *call, + struct event_filter **pfilter) +{ + struct event_filter *filter; + struct filter_parse_state *ps; + int err = -ENOMEM; + + filter = __alloc_filter(); + if (!filter) + goto out; + + ps = kzalloc(sizeof(*ps), GFP_KERNEL); + if (!ps) + goto free_filter; + + parse_init(ps, filter_ops, filter_str); + err = filter_parse(ps); + if (err) + goto free_ps; + + err = replace_preds(call, filter, ps, filter_str, false); + if (!err) + *pfilter = filter; + + free_ps: + filter_opstack_clear(ps); + postfix_clear(ps); + kfree(ps); + + free_filter: + if (err) + __free_filter(filter); + + out: + return err; +} + +#define DATA_REC(m, va, vb, vc, vd, ve, vf, vg, vh, nvisit) \ +{ \ + .filter = FILTER, \ + .rec = { .a = va, .b = vb, .c = vc, .d = vd, \ + .e = ve, .f = vf, .g = vg, .h = vh }, \ + .match = m, \ + .not_visited = nvisit, \ +} +#define YES 1 +#define NO 0 + +static struct test_filter_data_t { + char *filter; + struct ftrace_raw_ftrace_test_filter rec; + int match; + char *not_visited; +} test_filter_data[] = { +#define FILTER "a == 1 && b == 1 && c == 1 && d == 1 && " \ + "e == 1 && f == 1 && g == 1 && h == 1" + DATA_REC(YES, 1, 1, 1, 1, 1, 1, 1, 1, ""), + DATA_REC(NO, 0, 1, 1, 1, 1, 1, 1, 1, "bcdefgh"), + DATA_REC(NO, 1, 1, 1, 1, 1, 1, 1, 0, ""), +#undef FILTER +#define FILTER "a == 1 || b == 1 || c == 1 || d == 1 || " \ + "e == 1 || f == 1 || g == 1 || h == 1" + DATA_REC(NO, 0, 0, 0, 0, 0, 0, 0, 0, ""), + DATA_REC(YES, 0, 0, 0, 0, 0, 0, 0, 1, ""), + DATA_REC(YES, 1, 0, 0, 0, 0, 0, 0, 0, "bcdefgh"), +#undef FILTER +#define FILTER "(a == 1 || b == 1) && (c == 1 || d == 1) && " \ + "(e == 1 || f == 1) && (g == 1 || h == 1)" + DATA_REC(NO, 0, 0, 1, 1, 1, 1, 1, 1, "dfh"), + DATA_REC(YES, 0, 1, 0, 1, 0, 1, 0, 1, ""), + DATA_REC(YES, 1, 0, 1, 0, 0, 1, 0, 1, "bd"), + DATA_REC(NO, 1, 0, 1, 0, 0, 1, 0, 0, "bd"), +#undef FILTER +#define FILTER "(a == 1 && b == 1) || (c == 1 && d == 1) || " \ + "(e == 1 && f == 1) || (g == 1 && h == 1)" + DATA_REC(YES, 1, 0, 1, 1, 1, 1, 1, 1, "efgh"), + DATA_REC(YES, 0, 0, 0, 0, 0, 0, 1, 1, ""), + DATA_REC(NO, 0, 0, 0, 0, 0, 0, 0, 1, ""), +#undef FILTER +#define FILTER "(a == 1 && b == 1) && (c == 1 && d == 1) && " \ + "(e == 1 && f == 1) || (g == 1 && h == 1)" + DATA_REC(YES, 1, 1, 1, 1, 1, 1, 0, 0, "gh"), + DATA_REC(NO, 0, 0, 0, 0, 0, 0, 0, 1, ""), + DATA_REC(YES, 1, 1, 1, 1, 1, 0, 1, 1, ""), +#undef FILTER +#define FILTER "((a == 1 || b == 1) || (c == 1 || d == 1) || " \ + "(e == 1 || f == 1)) && (g == 1 || h == 1)" + DATA_REC(YES, 1, 1, 1, 1, 1, 1, 0, 1, "bcdef"), + DATA_REC(NO, 0, 0, 0, 0, 0, 0, 0, 0, ""), + DATA_REC(YES, 1, 1, 1, 1, 1, 0, 1, 1, "h"), +#undef FILTER +#define FILTER "((((((((a == 1) && (b == 1)) || (c == 1)) && (d == 1)) || " \ + "(e == 1)) && (f == 1)) || (g == 1)) && (h == 1))" + DATA_REC(YES, 1, 1, 1, 1, 1, 1, 1, 1, "ceg"), + DATA_REC(NO, 0, 1, 0, 1, 0, 1, 0, 1, ""), + DATA_REC(NO, 1, 0, 1, 0, 1, 0, 1, 0, ""), +#undef FILTER +#define FILTER "((((((((a == 1) || (b == 1)) && (c == 1)) || (d == 1)) && " \ + "(e == 1)) || (f == 1)) && (g == 1)) || (h == 1))" + DATA_REC(YES, 1, 1, 1, 1, 1, 1, 1, 1, "bdfh"), + DATA_REC(YES, 0, 1, 0, 1, 0, 1, 0, 1, ""), + DATA_REC(YES, 1, 0, 1, 0, 1, 0, 1, 0, "bdfh"), +}; + +#undef DATA_REC +#undef FILTER +#undef YES +#undef NO + +#define DATA_CNT (sizeof(test_filter_data)/sizeof(struct test_filter_data_t)) + +static int test_pred_visited; + +static int test_pred_visited_fn(struct filter_pred *pred, void *event) +{ + struct ftrace_event_field *field = pred->field; + + test_pred_visited = 1; + printk(KERN_INFO "\npred visited %s\n", field->name); + return 1; +} + +static int test_walk_pred_cb(enum move_type move, struct filter_pred *pred, + int *err, void *data) +{ + char *fields = data; + + if ((move == MOVE_DOWN) && + (pred->left == FILTER_PRED_INVALID)) { + struct ftrace_event_field *field = pred->field; + + if (!field) { + WARN(1, "all leafs should have field defined"); + return WALK_PRED_DEFAULT; + } + if (!strchr(fields, *field->name)) + return WALK_PRED_DEFAULT; + + WARN_ON(!pred->fn); + pred->fn = test_pred_visited_fn; + } + return WALK_PRED_DEFAULT; +} + +static __init int ftrace_test_event_filter(void) +{ + int i; + + printk(KERN_INFO "Testing ftrace filter: "); + + for (i = 0; i < DATA_CNT; i++) { + struct event_filter *filter = NULL; + struct test_filter_data_t *d = &test_filter_data[i]; + int err; + + err = test_get_filter(d->filter, &event_ftrace_test_filter, + &filter); + if (err) { + printk(KERN_INFO + "Failed to get filter for '%s', err %d\n", + d->filter, err); + break; + } + + /* + * The preemption disabling is not really needed for self + * tests, but the rcu dereference will complain without it. + */ + preempt_disable(); + if (*d->not_visited) + walk_pred_tree(filter->preds, filter->root, + test_walk_pred_cb, + d->not_visited); + + test_pred_visited = 0; + err = filter_match_preds(filter, &d->rec); + preempt_enable(); + + __free_filter(filter); + + if (test_pred_visited) { + printk(KERN_INFO + "Failed, unwanted pred visited for filter %s\n", + d->filter); + break; + } + + if (err != d->match) { + printk(KERN_INFO + "Failed to match filter '%s', expected %d\n", + d->filter, d->match); + break; + } + } + + if (i == DATA_CNT) + printk(KERN_CONT "OK\n"); + + return 0; +} + +late_initcall(ftrace_test_event_filter); + +#endif /* CONFIG_FTRACE_STARTUP_TEST */ diff --git a/kernel/trace/trace_events_filter_test.h b/kernel/trace/trace_events_filter_test.h new file mode 100644 index 0000000..bfd4dba --- /dev/null +++ b/kernel/trace/trace_events_filter_test.h @@ -0,0 +1,50 @@ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM test + +#if !defined(_TRACE_TEST_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_TEST_H + +#include <linux/tracepoint.h> + +TRACE_EVENT(ftrace_test_filter, + + TP_PROTO(int a, int b, int c, int d, int e, int f, int g, int h), + + TP_ARGS(a, b, c, d, e, f, g, h), + + TP_STRUCT__entry( + __field(int, a) + __field(int, b) + __field(int, c) + __field(int, d) + __field(int, e) + __field(int, f) + __field(int, g) + __field(int, h) + ), + + TP_fast_assign( + __entry->a = a; + __entry->b = b; + __entry->c = c; + __entry->d = d; + __entry->e = e; + __entry->f = f; + __entry->g = g; + __entry->h = h; + ), + + TP_printk("a %d, b %d, c %d, d %d, e %d, f %d, g %d, h %d", + __entry->a, __entry->b, __entry->c, __entry->d, + __entry->e, __entry->f, __entry->g, __entry->h) +); + +#endif /* _TRACE_TEST_H || TRACE_HEADER_MULTI_READ */ + +#undef TRACE_INCLUDE_PATH +#undef TRACE_INCLUDE_FILE +#define TRACE_INCLUDE_PATH . +#define TRACE_INCLUDE_FILE trace_events_filter_test + +/* This part must be outside protection */ +#include <trace/define_trace.h> diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c index 667aa8c..20dad0d 100644 --- a/kernel/trace/trace_irqsoff.c +++ b/kernel/trace/trace_irqsoff.c @@ -23,7 +23,7 @@ static int tracer_enabled __read_mostly; static DEFINE_PER_CPU(int, tracing_cpu); -static DEFINE_SPINLOCK(max_trace_lock); +static DEFINE_RAW_SPINLOCK(max_trace_lock); enum { TRACER_IRQS_OFF = (1 << 1), @@ -321,7 +321,7 @@ check_critical_timing(struct trace_array *tr, if (!report_latency(delta)) goto out; - spin_lock_irqsave(&max_trace_lock, flags); + raw_spin_lock_irqsave(&max_trace_lock, flags); /* check if we are still the max latency */ if (!report_latency(delta)) @@ -344,7 +344,7 @@ check_critical_timing(struct trace_array *tr, max_sequence++; out_unlock: - spin_unlock_irqrestore(&max_trace_lock, flags); + raw_spin_unlock_irqrestore(&max_trace_lock, flags); out: data->critical_sequence = max_sequence; @@ -505,13 +505,13 @@ EXPORT_SYMBOL(trace_hardirqs_off_caller); #ifdef CONFIG_PREEMPT_TRACER void trace_preempt_on(unsigned long a0, unsigned long a1) { - if (preempt_trace()) + if (preempt_trace() && !irq_trace()) stop_critical_timing(a0, a1); } void trace_preempt_off(unsigned long a0, unsigned long a1) { - if (preempt_trace()) + if (preempt_trace() && !irq_trace()) start_critical_timing(a0, a1); } #endif /* CONFIG_PREEMPT_TRACER */ diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 5fb3697..00d527c 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -836,11 +836,17 @@ static void __unregister_trace_probe(struct trace_probe *tp) } /* Unregister a trace_probe and probe_event: call with locking probe_lock */ -static void unregister_trace_probe(struct trace_probe *tp) +static int unregister_trace_probe(struct trace_probe *tp) { + /* Enabled event can not be unregistered */ + if (trace_probe_is_enabled(tp)) + return -EBUSY; + __unregister_trace_probe(tp); list_del(&tp->list); unregister_probe_event(tp); + + return 0; } /* Register a trace_probe and probe_event */ @@ -854,7 +860,9 @@ static int register_trace_probe(struct trace_probe *tp) /* Delete old (same name) event if exist */ old_tp = find_trace_probe(tp->call.name, tp->call.class->system); if (old_tp) { - unregister_trace_probe(old_tp); + ret = unregister_trace_probe(old_tp); + if (ret < 0) + goto end; free_trace_probe(old_tp); } @@ -892,6 +900,7 @@ static int trace_probe_module_callback(struct notifier_block *nb, mutex_lock(&probe_lock); list_for_each_entry(tp, &probe_list, list) { if (trace_probe_within_module(tp, mod)) { + /* Don't need to check busy - this should have gone. */ __unregister_trace_probe(tp); ret = __register_trace_probe(tp); if (ret) @@ -1205,10 +1214,11 @@ static int create_trace_probe(int argc, char **argv) return -ENOENT; } /* delete an event */ - unregister_trace_probe(tp); - free_trace_probe(tp); + ret = unregister_trace_probe(tp); + if (ret == 0) + free_trace_probe(tp); mutex_unlock(&probe_lock); - return 0; + return ret; } if (argc < 2) { @@ -1317,18 +1327,29 @@ error: return ret; } -static void release_all_trace_probes(void) +static int release_all_trace_probes(void) { struct trace_probe *tp; + int ret = 0; mutex_lock(&probe_lock); + /* Ensure no probe is in use. */ + list_for_each_entry(tp, &probe_list, list) + if (trace_probe_is_enabled(tp)) { + ret = -EBUSY; + goto end; + } /* TODO: Use batch unregistration */ while (!list_empty(&probe_list)) { tp = list_entry(probe_list.next, struct trace_probe, list); unregister_trace_probe(tp); free_trace_probe(tp); } + +end: mutex_unlock(&probe_lock); + + return ret; } /* Probes listing interfaces */ @@ -1380,9 +1401,13 @@ 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)) - release_all_trace_probes(); + int ret; + + if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) { + ret = release_all_trace_probes(); + if (ret < 0) + return ret; + } return seq_open(file, &probes_seq_op); } @@ -2055,6 +2080,21 @@ static __init int kprobe_trace_self_tests_init(void) ret = target(1, 2, 3, 4, 5, 6); + /* Disable trace points before removing it */ + tp = find_trace_probe("testprobe", KPROBE_EVENT_SYSTEM); + if (WARN_ON_ONCE(tp == NULL)) { + pr_warning("error on getting test probe.\n"); + warn++; + } else + disable_trace_probe(tp, TP_FLAG_TRACE); + + tp = find_trace_probe("testprobe2", KPROBE_EVENT_SYSTEM); + if (WARN_ON_ONCE(tp == NULL)) { + pr_warning("error on getting 2nd test probe.\n"); + warn++; + } else + disable_trace_probe(tp, TP_FLAG_TRACE); + ret = command_trace_probe("-:testprobe"); if (WARN_ON_ONCE(ret)) { pr_warning("error on deleting a probe.\n"); diff --git a/kernel/trace/trace_printk.c b/kernel/trace/trace_printk.c index 1f06468..6fd4ffd 100644 --- a/kernel/trace/trace_printk.c +++ b/kernel/trace/trace_printk.c @@ -59,18 +59,19 @@ void hold_module_trace_bprintk_format(const char **start, const char **end) continue; } + fmt = NULL; tb_fmt = kmalloc(sizeof(*tb_fmt), GFP_KERNEL); - if (tb_fmt) + if (tb_fmt) { fmt = kmalloc(strlen(*iter) + 1, GFP_KERNEL); - if (tb_fmt && fmt) { - list_add_tail(&tb_fmt->list, &trace_bprintk_fmt_list); - strcpy(fmt, *iter); - tb_fmt->fmt = fmt; - *iter = tb_fmt->fmt; - } else { - kfree(tb_fmt); - *iter = NULL; + if (fmt) { + list_add_tail(&tb_fmt->list, &trace_bprintk_fmt_list); + strcpy(fmt, *iter); + tb_fmt->fmt = fmt; + } else + kfree(tb_fmt); } + *iter = fmt; + } mutex_unlock(&btrace_mutex); } diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c index b219f14..db110b8 100644 --- a/kernel/tracepoint.c +++ b/kernel/tracepoint.c @@ -34,11 +34,16 @@ extern struct tracepoint * const __stop___tracepoints_ptrs[]; static const int tracepoint_debug; /* - * tracepoints_mutex nests inside module_mutex. Tracepoints mutex protects the - * builtin and module tracepoints and the hash table. + * Tracepoints mutex protects the builtin and module tracepoints and the hash + * table, as well as the local module list. */ static DEFINE_MUTEX(tracepoints_mutex); +#ifdef CONFIG_MODULES +/* Local list of struct module */ +static LIST_HEAD(tracepoint_module_list); +#endif /* CONFIG_MODULES */ + /* * Tracepoint hash table, containing the active tracepoints. * Protected by tracepoints_mutex. @@ -292,9 +297,10 @@ static void disable_tracepoint(struct tracepoint *elem) * @end: end of the range * * Updates the probe callback corresponding to a range of tracepoints. + * Called with tracepoints_mutex held. */ -void tracepoint_update_probe_range(struct tracepoint * const *begin, - struct tracepoint * const *end) +static void tracepoint_update_probe_range(struct tracepoint * const *begin, + struct tracepoint * const *end) { struct tracepoint * const *iter; struct tracepoint_entry *mark_entry; @@ -302,7 +308,6 @@ void tracepoint_update_probe_range(struct tracepoint * const *begin, if (!begin) return; - mutex_lock(&tracepoints_mutex); for (iter = begin; iter < end; iter++) { mark_entry = get_tracepoint((*iter)->name); if (mark_entry) { @@ -312,11 +317,27 @@ void tracepoint_update_probe_range(struct tracepoint * const *begin, disable_tracepoint(*iter); } } - mutex_unlock(&tracepoints_mutex); } +#ifdef CONFIG_MODULES +void module_update_tracepoints(void) +{ + struct tp_module *tp_mod; + + list_for_each_entry(tp_mod, &tracepoint_module_list, list) + tracepoint_update_probe_range(tp_mod->tracepoints_ptrs, + tp_mod->tracepoints_ptrs + tp_mod->num_tracepoints); +} +#else /* CONFIG_MODULES */ +void module_update_tracepoints(void) +{ +} +#endif /* CONFIG_MODULES */ + + /* * Update probes, removing the faulty probes. + * Called with tracepoints_mutex held. */ static void tracepoint_update_probes(void) { @@ -359,11 +380,12 @@ int tracepoint_probe_register(const char *name, void *probe, void *data) mutex_lock(&tracepoints_mutex); old = tracepoint_add_probe(name, probe, data); - mutex_unlock(&tracepoints_mutex); - if (IS_ERR(old)) + if (IS_ERR(old)) { + mutex_unlock(&tracepoints_mutex); return PTR_ERR(old); - + } tracepoint_update_probes(); /* may update entry */ + mutex_unlock(&tracepoints_mutex); release_probes(old); return 0; } @@ -402,11 +424,12 @@ int tracepoint_probe_unregister(const char *name, void *probe, void *data) mutex_lock(&tracepoints_mutex); old = tracepoint_remove_probe(name, probe, data); - mutex_unlock(&tracepoints_mutex); - if (IS_ERR(old)) + if (IS_ERR(old)) { + mutex_unlock(&tracepoints_mutex); return PTR_ERR(old); - + } tracepoint_update_probes(); /* may update entry */ + mutex_unlock(&tracepoints_mutex); release_probes(old); return 0; } @@ -489,9 +512,8 @@ void tracepoint_probe_update_all(void) if (!list_empty(&old_probes)) list_replace_init(&old_probes, &release_probes); need_update = 0; - mutex_unlock(&tracepoints_mutex); - tracepoint_update_probes(); + mutex_unlock(&tracepoints_mutex); list_for_each_entry_safe(pos, next, &release_probes, u.list) { list_del(&pos->u.list); call_rcu_sched(&pos->u.rcu, rcu_free_old_probes); @@ -509,7 +531,7 @@ EXPORT_SYMBOL_GPL(tracepoint_probe_update_all); * Will return the first tracepoint in the range if the input tracepoint is * NULL. */ -int tracepoint_get_iter_range(struct tracepoint * const **tracepoint, +static int tracepoint_get_iter_range(struct tracepoint * const **tracepoint, struct tracepoint * const *begin, struct tracepoint * const *end) { if (!*tracepoint && begin != end) { @@ -520,11 +542,12 @@ int tracepoint_get_iter_range(struct tracepoint * const **tracepoint, return 1; return 0; } -EXPORT_SYMBOL_GPL(tracepoint_get_iter_range); +#ifdef CONFIG_MODULES static void tracepoint_get_iter(struct tracepoint_iter *iter) { int found = 0; + struct tp_module *iter_mod; /* Core kernel tracepoints */ if (!iter->module) { @@ -534,12 +557,43 @@ static void tracepoint_get_iter(struct tracepoint_iter *iter) if (found) goto end; } - /* tracepoints in modules. */ - found = module_get_iter_tracepoints(iter); + /* Tracepoints in modules */ + mutex_lock(&tracepoints_mutex); + list_for_each_entry(iter_mod, &tracepoint_module_list, list) { + /* + * Sorted module list + */ + if (iter_mod < iter->module) + continue; + else if (iter_mod > iter->module) + iter->tracepoint = NULL; + found = tracepoint_get_iter_range(&iter->tracepoint, + iter_mod->tracepoints_ptrs, + iter_mod->tracepoints_ptrs + + iter_mod->num_tracepoints); + if (found) { + iter->module = iter_mod; + break; + } + } + mutex_unlock(&tracepoints_mutex); end: if (!found) tracepoint_iter_reset(iter); } +#else /* CONFIG_MODULES */ +static void tracepoint_get_iter(struct tracepoint_iter *iter) +{ + int found = 0; + + /* Core kernel tracepoints */ + found = tracepoint_get_iter_range(&iter->tracepoint, + __start___tracepoints_ptrs, + __stop___tracepoints_ptrs); + if (!found) + tracepoint_iter_reset(iter); +} +#endif /* CONFIG_MODULES */ void tracepoint_iter_start(struct tracepoint_iter *iter) { @@ -566,26 +620,98 @@ EXPORT_SYMBOL_GPL(tracepoint_iter_stop); void tracepoint_iter_reset(struct tracepoint_iter *iter) { +#ifdef CONFIG_MODULES iter->module = NULL; +#endif /* CONFIG_MODULES */ iter->tracepoint = NULL; } EXPORT_SYMBOL_GPL(tracepoint_iter_reset); #ifdef CONFIG_MODULES +static int tracepoint_module_coming(struct module *mod) +{ + struct tp_module *tp_mod, *iter; + int ret = 0; + + /* + * We skip modules that tain the kernel, especially those with different + * module header (for forced load), to make sure we don't cause a crash. + */ + if (mod->taints) + return 0; + mutex_lock(&tracepoints_mutex); + tp_mod = kmalloc(sizeof(struct tp_module), GFP_KERNEL); + if (!tp_mod) { + ret = -ENOMEM; + goto end; + } + tp_mod->num_tracepoints = mod->num_tracepoints; + tp_mod->tracepoints_ptrs = mod->tracepoints_ptrs; + + /* + * tracepoint_module_list is kept sorted by struct module pointer + * address for iteration on tracepoints from a seq_file that can release + * the mutex between calls. + */ + list_for_each_entry_reverse(iter, &tracepoint_module_list, list) { + BUG_ON(iter == tp_mod); /* Should never be in the list twice */ + if (iter < tp_mod) { + /* We belong to the location right after iter. */ + list_add(&tp_mod->list, &iter->list); + goto module_added; + } + } + /* We belong to the beginning of the list */ + list_add(&tp_mod->list, &tracepoint_module_list); +module_added: + tracepoint_update_probe_range(mod->tracepoints_ptrs, + mod->tracepoints_ptrs + mod->num_tracepoints); +end: + mutex_unlock(&tracepoints_mutex); + return ret; +} + +static int tracepoint_module_going(struct module *mod) +{ + struct tp_module *pos; + + mutex_lock(&tracepoints_mutex); + tracepoint_update_probe_range(mod->tracepoints_ptrs, + mod->tracepoints_ptrs + mod->num_tracepoints); + list_for_each_entry(pos, &tracepoint_module_list, list) { + if (pos->tracepoints_ptrs == mod->tracepoints_ptrs) { + list_del(&pos->list); + kfree(pos); + break; + } + } + /* + * In the case of modules that were tainted at "coming", we'll simply + * walk through the list without finding it. We cannot use the "tainted" + * flag on "going", in case a module taints the kernel only after being + * loaded. + */ + mutex_unlock(&tracepoints_mutex); + return 0; +} int tracepoint_module_notify(struct notifier_block *self, unsigned long val, void *data) { struct module *mod = data; + int ret = 0; switch (val) { case MODULE_STATE_COMING: + ret = tracepoint_module_coming(mod); + break; + case MODULE_STATE_LIVE: + break; case MODULE_STATE_GOING: - tracepoint_update_probe_range(mod->tracepoints_ptrs, - mod->tracepoints_ptrs + mod->num_tracepoints); + ret = tracepoint_module_going(mod); break; } - return 0; + return ret; } struct notifier_block tracepoint_module_nb = { @@ -598,7 +724,6 @@ static int init_tracepoints(void) return register_module_notifier(&tracepoint_module_nb); } __initcall(init_tracepoints); - #endif /* CONFIG_MODULES */ #ifdef CONFIG_HAVE_SYSCALL_TRACEPOINTS diff --git a/kernel/watchdog.c b/kernel/watchdog.c index 36491cd..1d7bca7 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -321,7 +321,7 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) */ static int watchdog(void *unused) { - static struct sched_param param = { .sched_priority = MAX_RT_PRIO-1 }; + struct sched_param param = { .sched_priority = MAX_RT_PRIO-1 }; struct hrtimer *hrtimer = &__raw_get_cpu_var(watchdog_hrtimer); sched_setscheduler(current, SCHED_FIFO, ¶m); @@ -350,7 +350,8 @@ static int watchdog(void *unused) set_current_state(TASK_INTERRUPTIBLE); } __set_current_state(TASK_RUNNING); - + param.sched_priority = 0; + sched_setscheduler(current, SCHED_NORMAL, ¶m); return 0; } @@ -438,7 +439,7 @@ static int watchdog_enable(int cpu) /* create the watchdog thread */ if (!p) { - p = kthread_create(watchdog, (void *)(unsigned long)cpu, "watchdog/%d", cpu); + p = kthread_create_on_node(watchdog, NULL, cpu_to_node(cpu), "watchdog/%d", cpu); if (IS_ERR(p)) { printk(KERN_ERR "softlockup watchdog for %i failed\n", cpu); if (!err) { @@ -480,6 +481,8 @@ static void watchdog_disable(int cpu) } } +/* sysctl functions */ +#ifdef CONFIG_SYSCTL static void watchdog_enable_all_cpus(void) { int cpu; @@ -509,8 +512,6 @@ static void watchdog_disable_all_cpus(void) } -/* sysctl functions */ -#ifdef CONFIG_SYSCTL /* * proc handler for /proc/sys/kernel/nmi_watchdog,watchdog_thresh */ |
