diff options
Diffstat (limited to 'kernel')
-rw-r--r-- | kernel/cpu.c | 37 | ||||
-rw-r--r-- | kernel/exit.c | 17 | ||||
-rw-r--r-- | kernel/fork.c | 6 | ||||
-rw-r--r-- | kernel/irq/chip.c | 2 | ||||
-rw-r--r-- | kernel/irq/internals.h | 4 | ||||
-rw-r--r-- | kernel/irq/irqdesc.c | 1 | ||||
-rw-r--r-- | kernel/irq/irqdomain.c | 19 | ||||
-rw-r--r-- | kernel/irq/manage.c | 62 | ||||
-rw-r--r-- | kernel/kprobes.c | 42 | ||||
-rw-r--r-- | kernel/locking/qspinlock.c | 1 | ||||
-rw-r--r-- | kernel/locking/rwsem-spinlock.c | 4 | ||||
-rw-r--r-- | kernel/sched/cputime.c | 180 | ||||
-rw-r--r-- | kernel/sched/fair.c | 32 | ||||
-rw-r--r-- | kernel/trace/trace_kprobe.c | 2 |
14 files changed, 255 insertions, 154 deletions
diff --git a/kernel/cpu.c b/kernel/cpu.c index b03a32595cfe..ab860453841d 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -271,11 +271,25 @@ void cpu_hotplug_enable(void) EXPORT_SYMBOL_GPL(cpu_hotplug_enable); #endif /* CONFIG_HOTPLUG_CPU */ +static void __cpuhp_kick_ap_work(struct cpuhp_cpu_state *st); + static int bringup_wait_for_ap(unsigned int cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); + /* Wait for the CPU to reach CPUHP_AP_ONLINE_IDLE */ wait_for_completion(&st->done); + BUG_ON(!cpu_online(cpu)); + + /* Unpark the stopper thread and the hotplug thread of the target cpu */ + stop_machine_unpark(cpu); + kthread_unpark(st->thread); + + /* Should we go further up ? */ + if (st->target > CPUHP_AP_ONLINE_IDLE) { + __cpuhp_kick_ap_work(st); + wait_for_completion(&st->done); + } return st->result; } @@ -296,9 +310,7 @@ static int bringup_cpu(unsigned int cpu) irq_unlock_sparse(); if (ret) return ret; - ret = bringup_wait_for_ap(cpu); - BUG_ON(!cpu_online(cpu)); - return ret; + return bringup_wait_for_ap(cpu); } /* @@ -767,31 +779,20 @@ void notify_cpu_starting(unsigned int cpu) } /* - * Called from the idle task. We need to set active here, so we can kick off - * the stopper thread and unpark the smpboot threads. If the target state is - * beyond CPUHP_AP_ONLINE_IDLE we kick cpuhp thread and let it bring up the - * cpu further. + * Called from the idle task. Wake up the controlling task which brings the + * stopper and the hotplug thread of the upcoming CPU up and then delegates + * the rest of the online bringup to the hotplug thread. */ void cpuhp_online_idle(enum cpuhp_state state) { struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state); - unsigned int cpu = smp_processor_id(); /* Happens for the boot cpu */ if (state != CPUHP_AP_ONLINE_IDLE) return; st->state = CPUHP_AP_ONLINE_IDLE; - - /* Unpark the stopper thread and the hotplug thread of this cpu */ - stop_machine_unpark(cpu); - kthread_unpark(st->thread); - - /* Should we go further up ? */ - if (st->target > CPUHP_AP_ONLINE_IDLE) - __cpuhp_kick_ap_work(st); - else - complete(&st->done); + complete(&st->done); } /* Requires cpu_add_remove_lock to be held */ diff --git a/kernel/exit.c b/kernel/exit.c index 2bbc23273e2f..608c9775a37b 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -1590,9 +1590,6 @@ static long kernel_waitid(int which, pid_t upid, struct waitid_info *infop, wo.wo_rusage = ru; ret = do_wait(&wo); - if (ret > 0) - ret = 0; - put_pid(pid); return ret; } @@ -1603,6 +1600,11 @@ SYSCALL_DEFINE5(waitid, int, which, pid_t, upid, struct siginfo __user *, struct rusage r; struct waitid_info info = {.status = 0}; long err = kernel_waitid(which, upid, &info, options, ru ? &r : NULL); + int signo = 0; + if (err > 0) { + signo = SIGCHLD; + err = 0; + } if (!err) { if (ru && copy_to_user(ru, &r, sizeof(struct rusage))) @@ -1612,7 +1614,7 @@ SYSCALL_DEFINE5(waitid, int, which, pid_t, upid, struct siginfo __user *, return err; user_access_begin(); - unsafe_put_user(err ? 0 : SIGCHLD, &infop->si_signo, Efault); + unsafe_put_user(signo, &infop->si_signo, Efault); unsafe_put_user(0, &infop->si_errno, Efault); unsafe_put_user((short)info.cause, &infop->si_code, Efault); unsafe_put_user(info.pid, &infop->si_pid, Efault); @@ -1714,6 +1716,11 @@ COMPAT_SYSCALL_DEFINE5(waitid, struct rusage ru; struct waitid_info info = {.status = 0}; long err = kernel_waitid(which, pid, &info, options, uru ? &ru : NULL); + int signo = 0; + if (err > 0) { + signo = SIGCHLD; + err = 0; + } if (!err && uru) { /* kernel_waitid() overwrites everything in ru */ @@ -1729,7 +1736,7 @@ COMPAT_SYSCALL_DEFINE5(waitid, return err; user_access_begin(); - unsafe_put_user(err ? 0 : SIGCHLD, &infop->si_signo, Efault); + unsafe_put_user(signo, &infop->si_signo, Efault); unsafe_put_user(0, &infop->si_errno, Efault); unsafe_put_user((short)info.cause, &infop->si_code, Efault); unsafe_put_user(info.pid, &infop->si_pid, Efault); diff --git a/kernel/fork.c b/kernel/fork.c index aa01b810c0bd..0f69a3e5281e 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1637,9 +1637,9 @@ static __latent_entropy struct task_struct *copy_process( prev_cputime_init(&p->prev_cputime); #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN - seqcount_init(&p->vtime_seqcount); - p->vtime_snap = 0; - p->vtime_snap_whence = VTIME_INACTIVE; + seqcount_init(&p->vtime.seqcount); + p->vtime.starttime = 0; + p->vtime.state = VTIME_INACTIVE; #endif #if defined(SPLIT_RSS_COUNTING) diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index ad43468e89f0..d171bc57e1e0 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -234,7 +234,7 @@ __irq_startup_managed(struct irq_desc *desc, struct cpumask *aff, bool force) return IRQ_STARTUP_MANAGED; } #else -static int +static __always_inline int __irq_startup_managed(struct irq_desc *desc, struct cpumask *aff, bool force) { return IRQ_STARTUP_NORMAL; diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h index 9da14d125df4..dbfba9933ed2 100644 --- a/kernel/irq/internals.h +++ b/kernel/irq/internals.h @@ -437,7 +437,9 @@ static inline void irq_remove_debugfs_entry(struct irq_desc *desc) # ifdef CONFIG_IRQ_DOMAIN void irq_domain_debugfs_init(struct dentry *root); # else -static inline void irq_domain_debugfs_init(struct dentry *root); +static inline void irq_domain_debugfs_init(struct dentry *root) +{ +} # endif #else /* CONFIG_GENERIC_IRQ_DEBUGFS */ static inline void irq_add_debugfs_entry(unsigned int irq, struct irq_desc *d) diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c index 8bbd06405e60..73be2b3909bd 100644 --- a/kernel/irq/irqdesc.c +++ b/kernel/irq/irqdesc.c @@ -373,6 +373,7 @@ static struct irq_desc *alloc_desc(int irq, int node, unsigned int flags, raw_spin_lock_init(&desc->lock); lockdep_set_class(&desc->lock, &irq_desc_lock_class); + mutex_init(&desc->request_mutex); init_rcu_head(&desc->rcu); desc_set_defaults(irq, desc, node, affinity, owner); diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c index 14fe862aa2e3..f1f251479aa6 100644 --- a/kernel/irq/irqdomain.c +++ b/kernel/irq/irqdomain.c @@ -1,5 +1,6 @@ #define pr_fmt(fmt) "irq: " fmt +#include <linux/acpi.h> #include <linux/debugfs.h> #include <linux/hardirq.h> #include <linux/interrupt.h> @@ -155,6 +156,21 @@ struct irq_domain *__irq_domain_add(struct fwnode_handle *fwnode, int size, domain->name = fwid->name; break; } +#ifdef CONFIG_ACPI + } else if (is_acpi_device_node(fwnode)) { + struct acpi_buffer buf = { + .length = ACPI_ALLOCATE_BUFFER, + }; + acpi_handle handle; + + handle = acpi_device_handle(to_acpi_device_node(fwnode)); + if (acpi_get_name(handle, ACPI_FULL_PATHNAME, &buf) == AE_OK) { + domain->name = buf.pointer; + domain->flags |= IRQ_DOMAIN_NAME_ALLOCATED; + } + + domain->fwnode = fwnode; +#endif } else if (of_node) { char *name; @@ -1667,8 +1683,7 @@ static void debugfs_add_domain_dir(struct irq_domain *d) static void debugfs_remove_domain_dir(struct irq_domain *d) { - if (d->debugfs_file) - debugfs_remove(d->debugfs_file); + debugfs_remove(d->debugfs_file); } void __init irq_domain_debugfs_init(struct dentry *root) diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 5c11c1730ba5..5624b2dd6b58 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -1167,6 +1167,18 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) if (desc->irq_data.chip->flags & IRQCHIP_ONESHOT_SAFE) new->flags &= ~IRQF_ONESHOT; + mutex_lock(&desc->request_mutex); + if (!desc->action) { + ret = irq_request_resources(desc); + if (ret) { + pr_err("Failed to request resources for %s (irq %d) on irqchip %s\n", + new->name, irq, desc->irq_data.chip->name); + goto out_mutex; + } + } + + chip_bus_lock(desc); + /* * The following block of code has to be executed atomically */ @@ -1267,13 +1279,6 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) } if (!shared) { - ret = irq_request_resources(desc); - if (ret) { - pr_err("Failed to request resources for %s (irq %d) on irqchip %s\n", - new->name, irq, desc->irq_data.chip->name); - goto out_unlock; - } - init_waitqueue_head(&desc->wait_for_threads); /* Setup the type (level, edge polarity) if configured: */ @@ -1347,6 +1352,8 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) } raw_spin_unlock_irqrestore(&desc->lock, flags); + chip_bus_sync_unlock(desc); + mutex_unlock(&desc->request_mutex); irq_setup_timings(desc, new); @@ -1378,6 +1385,14 @@ mismatch: out_unlock: raw_spin_unlock_irqrestore(&desc->lock, flags); + chip_bus_sync_unlock(desc); + + if (!desc->action) + irq_release_resources(desc); + +out_mutex: + mutex_unlock(&desc->request_mutex); + out_thread: if (new->thread) { struct task_struct *t = new->thread; @@ -1417,9 +1432,7 @@ int setup_irq(unsigned int irq, struct irqaction *act) if (retval < 0) return retval; - chip_bus_lock(desc); retval = __setup_irq(irq, desc, act); - chip_bus_sync_unlock(desc); if (retval) irq_chip_pm_put(&desc->irq_data); @@ -1443,6 +1456,7 @@ static struct irqaction *__free_irq(unsigned int irq, void *dev_id) if (!desc) return NULL; + mutex_lock(&desc->request_mutex); chip_bus_lock(desc); raw_spin_lock_irqsave(&desc->lock, flags); @@ -1475,8 +1489,6 @@ static struct irqaction *__free_irq(unsigned int irq, void *dev_id) if (!desc->action) { irq_settings_clr_disable_unlazy(desc); irq_shutdown(desc); - irq_release_resources(desc); - irq_remove_timings(desc); } #ifdef CONFIG_SMP @@ -1518,6 +1530,13 @@ static struct irqaction *__free_irq(unsigned int irq, void *dev_id) } } + if (!desc->action) { + irq_release_resources(desc); + irq_remove_timings(desc); + } + + mutex_unlock(&desc->request_mutex); + irq_chip_pm_put(&desc->irq_data); module_put(desc->owner); kfree(action->secondary); @@ -1674,9 +1693,7 @@ int request_threaded_irq(unsigned int irq, irq_handler_t handler, return retval; } - chip_bus_lock(desc); retval = __setup_irq(irq, desc, action); - chip_bus_sync_unlock(desc); if (retval) { irq_chip_pm_put(&desc->irq_data); @@ -1924,9 +1941,7 @@ int setup_percpu_irq(unsigned int irq, struct irqaction *act) if (retval < 0) return retval; - chip_bus_lock(desc); retval = __setup_irq(irq, desc, act); - chip_bus_sync_unlock(desc); if (retval) irq_chip_pm_put(&desc->irq_data); @@ -1935,9 +1950,10 @@ int setup_percpu_irq(unsigned int irq, struct irqaction *act) } /** - * request_percpu_irq - allocate a percpu interrupt line + * __request_percpu_irq - allocate a percpu interrupt line * @irq: Interrupt line to allocate * @handler: Function to be called when the IRQ occurs. + * @flags: Interrupt type flags (IRQF_TIMER only) * @devname: An ascii name for the claiming device * @dev_id: A percpu cookie passed back to the handler function * @@ -1950,8 +1966,9 @@ int setup_percpu_irq(unsigned int irq, struct irqaction *act) * the handler gets called with the interrupted CPU's instance of * that variable. */ -int request_percpu_irq(unsigned int irq, irq_handler_t handler, - const char *devname, void __percpu *dev_id) +int __request_percpu_irq(unsigned int irq, irq_handler_t handler, + unsigned long flags, const char *devname, + void __percpu *dev_id) { struct irqaction *action; struct irq_desc *desc; @@ -1965,12 +1982,15 @@ int request_percpu_irq(unsigned int irq, irq_handler_t handler, !irq_settings_is_per_cpu_devid(desc)) return -EINVAL; + if (flags && flags != IRQF_TIMER) + return -EINVAL; + action = kzalloc(sizeof(struct irqaction), GFP_KERNEL); if (!action) return -ENOMEM; action->handler = handler; - action->flags = IRQF_PERCPU | IRQF_NO_SUSPEND; + action->flags = flags | IRQF_PERCPU | IRQF_NO_SUSPEND; action->name = devname; action->percpu_dev_id = dev_id; @@ -1980,9 +2000,7 @@ int request_percpu_irq(unsigned int irq, irq_handler_t handler, return retval; } - chip_bus_lock(desc); retval = __setup_irq(irq, desc, action); - chip_bus_sync_unlock(desc); if (retval) { irq_chip_pm_put(&desc->irq_data); @@ -1991,7 +2009,7 @@ int request_percpu_irq(unsigned int irq, irq_handler_t handler, return retval; } -EXPORT_SYMBOL_GPL(request_percpu_irq); +EXPORT_SYMBOL_GPL(__request_percpu_irq); /** * irq_get_irqchip_state - returns the irqchip state of a interrupt. diff --git a/kernel/kprobes.c b/kernel/kprobes.c index 6756d750b31b..a1606a4224e1 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -1771,24 +1771,13 @@ unsigned long __weak arch_deref_entry_point(void *entry) int register_jprobes(struct jprobe **jps, int num) { - struct jprobe *jp; int ret = 0, i; if (num <= 0) return -EINVAL; + for (i = 0; i < num; i++) { - unsigned long addr, offset; - jp = jps[i]; - addr = arch_deref_entry_point(jp->entry); - - /* Verify probepoint is a function entry point */ - if (kallsyms_lookup_size_offset(addr, NULL, &offset) && - offset == 0) { - jp->kp.pre_handler = setjmp_pre_handler; - jp->kp.break_handler = longjmp_break_handler; - ret = register_kprobe(&jp->kp); - } else - ret = -EINVAL; + ret = register_jprobe(jps[i]); if (ret < 0) { if (i > 0) @@ -1796,13 +1785,30 @@ int register_jprobes(struct jprobe **jps, int num) break; } } + return ret; } EXPORT_SYMBOL_GPL(register_jprobes); int register_jprobe(struct jprobe *jp) { - return register_jprobes(&jp, 1); + unsigned long addr, offset; + struct kprobe *kp = &jp->kp; + + /* + * Verify probepoint as well as the jprobe handler are + * valid function entry points. + */ + addr = arch_deref_entry_point(jp->entry); + + if (kallsyms_lookup_size_offset(addr, NULL, &offset) && offset == 0 && + kprobe_on_func_entry(kp->addr, kp->symbol_name, kp->offset)) { + kp->pre_handler = setjmp_pre_handler; + kp->break_handler = longjmp_break_handler; + return register_kprobe(kp); + } + + return -EINVAL; } EXPORT_SYMBOL_GPL(register_jprobe); @@ -1888,12 +1894,12 @@ static int pre_handler_kretprobe(struct kprobe *p, struct pt_regs *regs) } NOKPROBE_SYMBOL(pre_handler_kretprobe); -bool __weak arch_function_offset_within_entry(unsigned long offset) +bool __weak arch_kprobe_on_func_entry(unsigned long offset) { return !offset; } -bool function_offset_within_entry(kprobe_opcode_t *addr, const char *sym, unsigned long offset) +bool kprobe_on_func_entry(kprobe_opcode_t *addr, const char *sym, unsigned long offset) { kprobe_opcode_t *kp_addr = _kprobe_addr(addr, sym, offset); @@ -1901,7 +1907,7 @@ bool function_offset_within_entry(kprobe_opcode_t *addr, const char *sym, unsign return false; if (!kallsyms_lookup_size_offset((unsigned long)kp_addr, NULL, &offset) || - !arch_function_offset_within_entry(offset)) + !arch_kprobe_on_func_entry(offset)) return false; return true; @@ -1914,7 +1920,7 @@ int register_kretprobe(struct kretprobe *rp) int i; void *addr; - if (!function_offset_within_entry(rp->kp.addr, rp->kp.symbol_name, rp->kp.offset)) + if (!kprobe_on_func_entry(rp->kp.addr, rp->kp.symbol_name, rp->kp.offset)) return -EINVAL; if (kretprobe_blacklist_size) { diff --git a/kernel/locking/qspinlock.c b/kernel/locking/qspinlock.c index b2caec7315af..fd24153e8a48 100644 --- a/kernel/locking/qspinlock.c +++ b/kernel/locking/qspinlock.c @@ -28,6 +28,7 @@ #include <linux/percpu.h> #include <linux/hardirq.h> #include <linux/mutex.h> +#include <linux/prefetch.h> #include <asm/byteorder.h> #include <asm/qspinlock.h> diff --git a/kernel/locking/rwsem-spinlock.c b/kernel/locking/rwsem-spinlock.c index c65f7989f850..20819df98125 100644 --- a/kernel/locking/rwsem-spinlock.c +++ b/kernel/locking/rwsem-spinlock.c @@ -231,8 +231,8 @@ int __sched __down_write_common(struct rw_semaphore *sem, int state) out_nolock: list_del(&waiter.list); - if (!list_empty(&sem->wait_list)) - __rwsem_do_wake(sem, 1); + if (!list_empty(&sem->wait_list) && sem->count >= 0) + __rwsem_do_wake(sem, 0); raw_spin_unlock_irqrestore(&sem->wait_lock, flags); return -EINTR; diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index 67c70e287647..6e3ea4ac1bda 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -611,17 +611,23 @@ static void cputime_adjust(struct task_cputime *curr, utime = curr->utime; /* - * If either stime or both stime and utime are 0, assume all runtime is - * userspace. Once a task gets some ticks, the monotonicy code at - * 'update' will ensure things converge to the observed ratio. + * If either stime or utime are 0, assume all runtime is userspace. + * Once a task gets some ticks, the monotonicy code at 'update:' + * will ensure things converge to the observed ratio. */ - if (stime != 0) { - if (utime == 0) - stime = rtime; - else - stime = scale_stime(stime, rtime, stime + utime); + if (stime == 0) { + utime = rtime; + goto update; } + if (utime == 0) { + stime = rtime; + goto update; + } + + stime = scale_stime(stime, rtime, stime + utime); + +update: /* * Make sure stime doesn't go backwards; this preserves monotonicity * for utime because rtime is monotonic. @@ -673,20 +679,21 @@ void thread_group_cputime_adjusted(struct task_struct *p, u64 *ut, u64 *st) #endif /* !CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */ #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN -static u64 vtime_delta(struct task_struct *tsk) +static u64 vtime_delta(struct vtime *vtime) { - unsigned long now = READ_ONCE(jiffies); + unsigned long long clock; - if (time_before(now, (unsigned long)tsk->vtime_snap)) + clock = sched_clock_cpu(smp_processor_id()); + if (clock < vtime->starttime) return 0; - return jiffies_to_nsecs(now - tsk->vtime_snap); + return clock - vtime->starttime; } -static u64 get_vtime_delta(struct task_struct *tsk) +static u64 get_vtime_delta(struct vtime *vtime) { - unsigned long now = READ_ONCE(jiffies); - u64 delta, other; + u64 delta = vtime_delta(vtime); + u64 other; /* * Unlike tick based timing, vtime based timing never has lost @@ -695,104 +702,138 @@ static u64 get_vtime_delta(struct task_struct *tsk) * elapsed time. Limit account_other_time to prevent rounding * errors from causing elapsed vtime to go negative. */ - delta = jiffies_to_nsecs(now - tsk->vtime_snap); other = account_other_time(delta); - WARN_ON_ONCE(tsk->vtime_snap_whence == VTIME_INACTIVE); - tsk->vtime_snap = now; + WARN_ON_ONCE(vtime->state == VTIME_INACTIVE); + vtime->starttime += delta; return delta - other; } -static void __vtime_account_system(struct task_struct *tsk) +static void __vtime_account_system(struct task_struct *tsk, + struct vtime *vtime) +{ + vtime->stime += get_vtime_delta(vtime); + if (vtime->stime >= TICK_NSEC) { + account_system_time(tsk, irq_count(), vtime->stime); + vtime->stime = 0; + } +} + +static void vtime_account_guest(struct task_struct *tsk, + struct vtime *vtime) { - account_system_time(tsk, irq_count(), get_vtime_delta(tsk)); + vtime->gtime += get_vtime_delta(vtime); + if (vtime->gtime >= TICK_NSEC) { + account_guest_time(tsk, vtime->gtime); + vtime->gtime = 0; + } } void vtime_account_system(struct task_struct *tsk) { - if (!vtime_delta(tsk)) + struct vtime *vtime = &tsk->vtime; + + if (!vtime_delta(vtime)) return; - write_seqcount_begin(&tsk->vtime_seqcount); - __vtime_account_system(tsk); - write_seqcount_end(&tsk->vtime_seqcount); + write_seqcount_begin(&vtime->seqcount); + /* We might have scheduled out from guest path */ + if (current->flags & PF_VCPU) + vtime_account_guest(tsk, vtime); + else + __vtime_account_system(tsk, vtime); + write_seqcount_end(&vtime->seqcount); } -void vtime_account_user(struct task_struct *tsk) +void vtime_user_enter(struct task_struct *tsk) { - write_seqcount_begin(&tsk->vtime_seqcount); - tsk->vtime_snap_whence = VTIME_SYS; - if (vtime_delta(tsk)) - account_user_time(tsk, get_vtime_delta(tsk)); - write_seqcount_end(&tsk->vtime_seqcount); + struct vtime *vtime = &tsk->vtime; + + write_seqcount_begin(&vtime->seqcount); + __vtime_account_system(tsk, vtime); + vtime->state = VTIME_USER; + write_seqcount_end(&vtime->seqcount); } -void vtime_user_enter(struct task_struct *tsk) +void vtime_user_exit(struct task_struct *tsk) { - write_seqcount_begin(&tsk->vtime_seqcount); - if (vtime_delta(tsk)) - __vtime_account_system(tsk); - tsk->vtime_snap_whence = VTIME_USER; - write_seqcount_end(&tsk->vtime_seqcount); + struct vtime *vtime = &tsk->vtime; + + write_seqcount_begin(&vtime->seqcount); + vtime->utime += get_vtime_delta(vtime); + if (vtime->utime >= TICK_NSEC) { + account_user_time(tsk, vtime->utime); + vtime->utime = 0; + } + vtime->state = VTIME_SYS; + write_seqcount_end(&vtime->seqcount); } void vtime_guest_enter(struct task_struct *tsk) { + struct vtime *vtime = &tsk->vtime; /* * The flags must be updated under the lock with - * the vtime_snap flush and update. + * the vtime_starttime flush and update. * That enforces a right ordering and update sequence * synchronization against the reader (task_gtime()) * that can thus safely catch up with a tickless delta. */ - write_seqcount_begin(&tsk->vtime_seqcount); - if (vtime_delta(tsk)) - __vtime_account_system(tsk); + write_seqcount_begin(&vtime->seqcount); + __vtime_account_system(tsk, vtime); current->flags |= PF_VCPU; - write_seqcount_end(&tsk->vtime_seqcount); + write_seqcount_end(&vtime->seqcount); } EXPORT_SYMBOL_GPL(vtime_guest_enter); void vtime_guest_exit(struct task_struct *tsk) { - write_seqcount_begin(&tsk->vtime_seqcount); - __vtime_account_system(tsk); + struct vtime *vtime = &tsk->vtime; + + write_seqcount_begin(&vtime->seqcount); + vtime_account_guest(tsk, vtime); current->flags &= ~PF_VCPU; - write_seqcount_end(&tsk->vtime_seqcount); + write_seqcount_end(&vtime->seqcount); } EXPORT_SYMBOL_GPL(vtime_guest_exit); void vtime_account_idle(struct task_struct *tsk) { - account_idle_time(get_vtime_delta(tsk)); + account_idle_time(get_vtime_delta(&tsk->vtime)); } void arch_vtime_task_switch(struct task_struct *prev) { - write_seqcount_begin(&prev->vtime_seqcount); - prev->vtime_snap_whence = VTIME_INACTIVE; - write_seqcount_end(&prev->vtime_seqcount); + struct vtime *vtime = &prev->vtime; + + write_seqcount_begin(&vtime->seqcount); + vtime->state = VTIME_INACTIVE; + write_seqcount_end(&vtime->seqcount); + + vtime = ¤t->vtime; - write_seqcount_begin(¤t->vtime_seqcount); - current->vtime_snap_whence = VTIME_SYS; - current->vtime_snap = jiffies; - write_seqcount_end(¤t->vtime_seqcount); + write_seqcount_begin(&vtime->seqcount); + vtime->state = VTIME_SYS; + vtime->starttime = sched_clock_cpu(smp_processor_id()); + write_seqcount_end(&vtime->seqcount); } void vtime_init_idle(struct task_struct *t, int cpu) { + struct vtime *vtime = &t->vtime; unsigned long flags; local_irq_save(flags); - write_seqcount_begin(&t->vtime_seqcount); - t->vtime_snap_whence = VTIME_SYS; - t->vtime_snap = jiffies; - write_seqcount_end(&t->vtime_seqcount); + write_seqcount_begin(&vtime->seqcount); + vtime->state = VTIME_SYS; + vtime->starttime = sched_clock_cpu(cpu); + write_seqcount_end(&vtime->seqcount); local_irq_restore(flags); } u64 task_gtime(struct task_struct *t) { + struct vtime *vtime = &t->vtime; unsigned int seq; u64 gtime; @@ -800,13 +841,13 @@ u64 task_gtime(struct task_struct *t) return t->gtime; do { - seq = read_seqcount_begin(&t->vtime_seqcount); + seq = read_seqcount_begin(&vtime->seqcount); gtime = t->gtime; - if (t->vtime_snap_whence == VTIME_SYS && t->flags & PF_VCPU) - gtime += vtime_delta(t); + if (vtime->state == VTIME_SYS && t->flags & PF_VCPU) + gtime += vtime->gtime + vtime_delta(vtime); - } while (read_seqcount_retry(&t->vtime_seqcount, seq)); + } while (read_seqcount_retry(&vtime->seqcount, seq)); return gtime; } @@ -818,8 +859,9 @@ u64 task_gtime(struct task_struct *t) */ void task_cputime(struct task_struct *t, u64 *utime, u64 *stime) { - u64 delta; + struct vtime *vtime = &t->vtime; unsigned int seq; + u64 delta; if (!vtime_accounting_enabled()) { *utime = t->utime; @@ -828,25 +870,25 @@ void task_cputime(struct task_struct *t, u64 *utime, u64 *stime) } do { - seq = read_seqcount_begin(&t->vtime_seqcount); + seq = read_seqcount_begin(&vtime->seqcount); *utime = t->utime; *stime = t->stime; /* Task is sleeping, nothing to add */ - if (t->vtime_snap_whence == VTIME_INACTIVE || is_idle_task(t)) + if (vtime->state == VTIME_INACTIVE || is_idle_task(t)) continue; - delta = vtime_delta(t); + delta = vtime_delta(vtime); /* * Task runs either in user or kernel space, add pending nohz time to * the right place. */ - if (t->vtime_snap_whence == VTIME_USER || t->flags & PF_VCPU) - *utime += delta; - else if (t->vtime_snap_whence == VTIME_SYS) - *stime += delta; - } while (read_seqcount_retry(&t->vtime_seqcount, seq)); + if (vtime->state == VTIME_USER || t->flags & PF_VCPU) + *utime += vtime->utime + delta; + else if (vtime->state == VTIME_SYS) + *stime += vtime->stime + delta; + } while (read_seqcount_retry(&vtime->seqcount, seq)); } #endif /* CONFIG_VIRT_CPU_ACCOUNTING_GEN */ diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 008c514dc241..c95880e216f6 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -6646,10 +6646,10 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env) * our sched_group. We may want to revisit it if we couldn't * meet load balance goals by pulling other tasks on src_cpu. * - * Also avoid computing new_dst_cpu if we have already computed - * one in current iteration. + * Avoid computing new_dst_cpu for NEWLY_IDLE or if we have + * already computed one in current iteration. */ - if (!env->dst_grpmask || (env->flags & LBF_DST_PINNED)) + if (env->idle == CPU_NEWLY_IDLE || (env->flags & LBF_DST_PINNED)) return 0; /* Prevent to re-select dst_cpu via env's cpus */ @@ -8022,14 +8022,7 @@ static int load_balance(int this_cpu, struct rq *this_rq, .tasks = LIST_HEAD_INIT(env.tasks), }; - /* - * For NEWLY_IDLE load_balancing, we don't need to consider - * other cpus in our group - */ - if (idle == CPU_NEWLY_IDLE) - env.dst_grpmask = NULL; - - cpumask_copy(cpus, cpu_active_mask); + cpumask_and(cpus, sched_domain_span(sd), cpu_active_mask); schedstat_inc(sd->lb_count[idle]); @@ -8151,7 +8144,15 @@ more_balance: /* All tasks on this runqueue were pinned by CPU affinity */ if (unlikely(env.flags & LBF_ALL_PINNED)) { cpumask_clear_cpu(cpu_of(busiest), cpus); - if (!cpumask_empty(cpus)) { + /* + * Attempting to continue load balancing at the current + * sched_domain level only makes sense if there are + * active CPUs remaining as possible busiest CPUs to + * pull load from which are not contained within the + * destination group that is receiving any migrated + * load. + */ + if (!cpumask_subset(cpus, env.dst_grpmask)) { env.loop = 0; env.loop_break = sched_nr_migrate_break; goto redo; @@ -8447,6 +8448,13 @@ static int active_load_balance_cpu_stop(void *data) .src_cpu = busiest_rq->cpu, .src_rq = busiest_rq, .idle = CPU_IDLE, + /* + * can_migrate_task() doesn't need to compute new_dst_cpu + * for active balancing. Since we have CPU_IDLE, but no + * @dst_grpmask we need to make that test go away with lying + * about DST_PINNED. + */ + .flags = LBF_DST_PINNED, }; schedstat_inc(sd->alb_count); diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index b53c8d369163..2c5221819be5 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -720,7 +720,7 @@ static int create_trace_kprobe(int argc, char **argv) return ret; } if (offset && is_return && - !function_offset_within_entry(NULL, symbol, offset)) { + !kprobe_on_func_entry(NULL, symbol, offset)) { pr_info("Given offset is not valid for return probe.\n"); return -EINVAL; } |