diff options
Diffstat (limited to 'kernel')
| -rw-r--r-- | kernel/Makefile | 1 | ||||
| -rw-r--r-- | kernel/cpu_pm.c | 233 | ||||
| -rw-r--r-- | kernel/events/core.c | 71 | ||||
| -rw-r--r-- | kernel/irq/manage.c | 1 | ||||
| -rw-r--r-- | kernel/power/Kconfig | 4 | ||||
| -rw-r--r-- | kernel/printk.c | 2 | ||||
| -rw-r--r-- | kernel/sched.c | 43 | ||||
| -rw-r--r-- | kernel/sys.c | 38 | ||||
| -rw-r--r-- | kernel/sys_ni.c | 1 | ||||
| -rw-r--r-- | kernel/sysctl_binary.c | 2 | ||||
| -rw-r--r-- | kernel/sysctl_check.c | 2 | ||||
| -rw-r--r-- | kernel/time/alarmtimer.c | 18 |
12 files changed, 376 insertions, 40 deletions
diff --git a/kernel/Makefile b/kernel/Makefile index eca595e2fd5..988cb3da703 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -101,6 +101,7 @@ obj-$(CONFIG_RING_BUFFER) += trace/ obj-$(CONFIG_TRACEPOINTS) += trace/ obj-$(CONFIG_SMP) += sched_cpupri.o obj-$(CONFIG_IRQ_WORK) += irq_work.o +obj-$(CONFIG_CPU_PM) += cpu_pm.o obj-$(CONFIG_PERF_EVENTS) += events/ diff --git a/kernel/cpu_pm.c b/kernel/cpu_pm.c new file mode 100644 index 00000000000..249152e1530 --- /dev/null +++ b/kernel/cpu_pm.c @@ -0,0 +1,233 @@ +/* + * Copyright (C) 2011 Google, Inc. + * + * Author: + * Colin Cross <ccross@android.com> + * + * This software is licensed under the terms of the GNU General Public + * License version 2, as published by the Free Software Foundation, and + * may be copied, distributed, and modified under those terms. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + */ + +#include <linux/kernel.h> +#include <linux/cpu_pm.h> +#include <linux/module.h> +#include <linux/notifier.h> +#include <linux/spinlock.h> +#include <linux/syscore_ops.h> + +static DEFINE_RWLOCK(cpu_pm_notifier_lock); +static RAW_NOTIFIER_HEAD(cpu_pm_notifier_chain); + +static int cpu_pm_notify(enum cpu_pm_event event, int nr_to_call, int *nr_calls) +{ + int ret; + + ret = __raw_notifier_call_chain(&cpu_pm_notifier_chain, event, NULL, + nr_to_call, nr_calls); + + return notifier_to_errno(ret); +} + +/** + * cpu_pm_register_notifier - register a driver with cpu_pm + * @nb: notifier block to register + * + * Add a driver to a list of drivers that are notified about + * CPU and CPU cluster low power entry and exit. + * + * This function may sleep, and has the same return conditions as + * raw_notifier_chain_register. + */ +int cpu_pm_register_notifier(struct notifier_block *nb) +{ + unsigned long flags; + int ret; + + write_lock_irqsave(&cpu_pm_notifier_lock, flags); + ret = raw_notifier_chain_register(&cpu_pm_notifier_chain, nb); + write_unlock_irqrestore(&cpu_pm_notifier_lock, flags); + + return ret; +} +EXPORT_SYMBOL_GPL(cpu_pm_register_notifier); + +/** + * cpu_pm_unregister_notifier - unregister a driver with cpu_pm + * @nb: notifier block to be unregistered + * + * Remove a driver from the CPU PM notifier list. + * + * This function may sleep, and has the same return conditions as + * raw_notifier_chain_unregister. + */ +int cpu_pm_unregister_notifier(struct notifier_block *nb) +{ + unsigned long flags; + int ret; + + write_lock_irqsave(&cpu_pm_notifier_lock, flags); + ret = raw_notifier_chain_unregister(&cpu_pm_notifier_chain, nb); + write_unlock_irqrestore(&cpu_pm_notifier_lock, flags); + + return ret; +} +EXPORT_SYMBOL_GPL(cpu_pm_unregister_notifier); + +/** + * cpm_pm_enter - CPU low power entry notifier + * + * Notifies listeners that a single CPU is entering a low power state that may + * cause some blocks in the same power domain as the cpu to reset. + * + * Must be called on the affected CPU with interrupts disabled. Platform is + * responsible for ensuring that cpu_pm_enter is not called twice on the same + * CPU before cpu_pm_exit is called. Notified drivers can include VFP + * co-processor, interrupt controller and it's PM extensions, local CPU + * timers context save/restore which shouldn't be interrupted. Hence it + * must be called with interrupts disabled. + * + * Return conditions are same as __raw_notifier_call_chain. + */ +int cpu_pm_enter(void) +{ + int nr_calls; + int ret = 0; + + read_lock(&cpu_pm_notifier_lock); + ret = cpu_pm_notify(CPU_PM_ENTER, -1, &nr_calls); + if (ret) + /* + * Inform listeners (nr_calls - 1) about failure of CPU PM + * PM entry who are notified earlier to prepare for it. + */ + cpu_pm_notify(CPU_PM_ENTER_FAILED, nr_calls - 1, NULL); + read_unlock(&cpu_pm_notifier_lock); + + return ret; +} +EXPORT_SYMBOL_GPL(cpu_pm_enter); + +/** + * cpm_pm_exit - CPU low power exit notifier + * + * Notifies listeners that a single CPU is exiting a low power state that may + * have caused some blocks in the same power domain as the cpu to reset. + * + * Notified drivers can include VFP co-processor, interrupt controller + * and it's PM extensions, local CPU timers context save/restore which + * shouldn't be interrupted. Hence it must be called with interrupts disabled. + * + * Return conditions are same as __raw_notifier_call_chain. + */ +int cpu_pm_exit(void) +{ + int ret; + + read_lock(&cpu_pm_notifier_lock); + ret = cpu_pm_notify(CPU_PM_EXIT, -1, NULL); + read_unlock(&cpu_pm_notifier_lock); + + return ret; +} +EXPORT_SYMBOL_GPL(cpu_pm_exit); + +/** + * cpm_cluster_pm_enter - CPU cluster low power entry notifier + * + * Notifies listeners that all cpus in a power domain are entering a low power + * state that may cause some blocks in the same power domain to reset. + * + * Must be called after cpu_pm_enter has been called on all cpus in the power + * domain, and before cpu_pm_exit has been called on any cpu in the power + * domain. Notified drivers can include VFP co-processor, interrupt controller + * and it's PM extensions, local CPU timers context save/restore which + * shouldn't be interrupted. Hence it must be called with interrupts disabled. + * + * Must be called with interrupts disabled. + * + * Return conditions are same as __raw_notifier_call_chain. + */ +int cpu_cluster_pm_enter(void) +{ + int nr_calls; + int ret = 0; + + read_lock(&cpu_pm_notifier_lock); + ret = cpu_pm_notify(CPU_CLUSTER_PM_ENTER, -1, &nr_calls); + if (ret) + /* + * Inform listeners (nr_calls - 1) about failure of CPU cluster + * PM entry who are notified earlier to prepare for it. + */ + cpu_pm_notify(CPU_CLUSTER_PM_ENTER_FAILED, nr_calls - 1, NULL); + read_unlock(&cpu_pm_notifier_lock); + + return ret; +} +EXPORT_SYMBOL_GPL(cpu_cluster_pm_enter); + +/** + * cpm_cluster_pm_exit - CPU cluster low power exit notifier + * + * Notifies listeners that all cpus in a power domain are exiting form a + * low power state that may have caused some blocks in the same power domain + * to reset. + * + * Must be called after cpu_pm_exit has been called on all cpus in the power + * domain, and before cpu_pm_exit has been called on any cpu in the power + * domain. Notified drivers can include VFP co-processor, interrupt controller + * and it's PM extensions, local CPU timers context save/restore which + * shouldn't be interrupted. Hence it must be called with interrupts disabled. + * + * Return conditions are same as __raw_notifier_call_chain. + */ +int cpu_cluster_pm_exit(void) +{ + int ret; + + read_lock(&cpu_pm_notifier_lock); + ret = cpu_pm_notify(CPU_CLUSTER_PM_EXIT, -1, NULL); + read_unlock(&cpu_pm_notifier_lock); + + return ret; +} +EXPORT_SYMBOL_GPL(cpu_cluster_pm_exit); + +#ifdef CONFIG_PM +static int cpu_pm_suspend(void) +{ + int ret; + + ret = cpu_pm_enter(); + if (ret) + return ret; + + ret = cpu_cluster_pm_enter(); + return ret; +} + +static void cpu_pm_resume(void) +{ + cpu_cluster_pm_exit(); + cpu_pm_exit(); +} + +static struct syscore_ops cpu_pm_syscore_ops = { + .suspend = cpu_pm_suspend, + .resume = cpu_pm_resume, +}; + +static int cpu_pm_init(void) +{ + register_syscore_ops(&cpu_pm_syscore_ops); + return 0; +} +core_initcall(cpu_pm_init); +#endif diff --git a/kernel/events/core.c b/kernel/events/core.c index b8785e26ee1..fbe38f2e8ed 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -399,14 +399,54 @@ void perf_cgroup_switch(struct task_struct *task, int mode) local_irq_restore(flags); } -static inline void perf_cgroup_sched_out(struct task_struct *task) +static inline void perf_cgroup_sched_out(struct task_struct *task, + struct task_struct *next) { - perf_cgroup_switch(task, PERF_CGROUP_SWOUT); + struct perf_cgroup *cgrp1; + struct perf_cgroup *cgrp2 = NULL; + + /* + * we come here when we know perf_cgroup_events > 0 + */ + cgrp1 = perf_cgroup_from_task(task); + + /* + * next is NULL when called from perf_event_enable_on_exec() + * that will systematically cause a cgroup_switch() + */ + if (next) + cgrp2 = perf_cgroup_from_task(next); + + /* + * only schedule out current cgroup events if we know + * that we are switching to a different cgroup. Otherwise, + * do no touch the cgroup events. + */ + if (cgrp1 != cgrp2) + perf_cgroup_switch(task, PERF_CGROUP_SWOUT); } -static inline void perf_cgroup_sched_in(struct task_struct *task) +static inline void perf_cgroup_sched_in(struct task_struct *prev, + struct task_struct *task) { - perf_cgroup_switch(task, PERF_CGROUP_SWIN); + struct perf_cgroup *cgrp1; + struct perf_cgroup *cgrp2 = NULL; + + /* + * we come here when we know perf_cgroup_events > 0 + */ + cgrp1 = perf_cgroup_from_task(task); + + /* prev can never be NULL */ + cgrp2 = perf_cgroup_from_task(prev); + + /* + * only need to schedule in cgroup events if we are changing + * cgroup during ctxsw. Cgroup events were not scheduled + * out of ctxsw out if that was not the case. + */ + if (cgrp1 != cgrp2) + perf_cgroup_switch(task, PERF_CGROUP_SWIN); } static inline int perf_cgroup_connect(int fd, struct perf_event *event, @@ -518,11 +558,13 @@ static inline void update_cgrp_time_from_cpuctx(struct perf_cpu_context *cpuctx) { } -static inline void perf_cgroup_sched_out(struct task_struct *task) +static inline void perf_cgroup_sched_out(struct task_struct *task, + struct task_struct *next) { } -static inline void perf_cgroup_sched_in(struct task_struct *task) +static inline void perf_cgroup_sched_in(struct task_struct *prev, + struct task_struct *task) { } @@ -1988,7 +2030,7 @@ void __perf_event_task_sched_out(struct task_struct *task, * cgroup event are system-wide mode only */ if (atomic_read(&__get_cpu_var(perf_cgroup_events))) - perf_cgroup_sched_out(task); + perf_cgroup_sched_out(task, next); } static void task_ctx_sched_out(struct perf_event_context *ctx) @@ -2153,7 +2195,8 @@ static void perf_event_context_sched_in(struct perf_event_context *ctx, * accessing the event control register. If a NMI hits, then it will * keep the event running. */ -void __perf_event_task_sched_in(struct task_struct *task) +void __perf_event_task_sched_in(struct task_struct *prev, + struct task_struct *task) { struct perf_event_context *ctx; int ctxn; @@ -2171,7 +2214,7 @@ void __perf_event_task_sched_in(struct task_struct *task) * cgroup event are system-wide mode only */ if (atomic_read(&__get_cpu_var(perf_cgroup_events))) - perf_cgroup_sched_in(task); + perf_cgroup_sched_in(prev, task); } static u64 perf_calculate_period(struct perf_event *event, u64 nsec, u64 count) @@ -2427,7 +2470,7 @@ static void perf_event_enable_on_exec(struct perf_event_context *ctx) * ctxswin cgroup events which are already scheduled * in. */ - perf_cgroup_sched_out(current); + perf_cgroup_sched_out(current, NULL); raw_spin_lock(&ctx->lock); task_ctx_sched_out(ctx); @@ -3353,8 +3396,8 @@ static int perf_event_index(struct perf_event *event) } static void calc_timer_values(struct perf_event *event, - u64 *running, - u64 *enabled) + u64 *enabled, + u64 *running) { u64 now, ctx_time; @@ -5715,6 +5758,7 @@ struct pmu *perf_init_event(struct perf_event *event) pmu = idr_find(&pmu_idr, event->attr.type); rcu_read_unlock(); if (pmu) { + event->pmu = pmu; ret = pmu->event_init(event); if (ret) pmu = ERR_PTR(ret); @@ -5722,6 +5766,7 @@ struct pmu *perf_init_event(struct perf_event *event) } list_for_each_entry_rcu(pmu, &pmus, entry) { + event->pmu = pmu; ret = pmu->event_init(event); if (!ret) goto unlock; @@ -5848,8 +5893,6 @@ done: return ERR_PTR(err); } - event->pmu = pmu; - if (!event->parent) { if (event->attach_state & PERF_ATTACH_TASK) jump_label_inc(&perf_sched_events); diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 2e9425889fa..9b956fa2030 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -1331,7 +1331,6 @@ int request_threaded_irq(unsigned int irq, irq_handler_t handler, if (!thread_fn) return -EINVAL; handler = irq_default_primary_handler; - irqflags |= IRQF_ONESHOT; } action = kzalloc(sizeof(struct irqaction), GFP_KERNEL); diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig index 3744c594b19..80a85971cf6 100644 --- a/kernel/power/Kconfig +++ b/kernel/power/Kconfig @@ -235,3 +235,7 @@ config PM_GENERIC_DOMAINS config PM_GENERIC_DOMAINS_RUNTIME def_bool y depends on PM_RUNTIME && PM_GENERIC_DOMAINS + +config CPU_PM + bool + depends on SUSPEND || CPU_IDLE diff --git a/kernel/printk.c b/kernel/printk.c index 836a2ae0ac3..28a40d8171b 100644 --- a/kernel/printk.c +++ b/kernel/printk.c @@ -1604,7 +1604,7 @@ static int __init printk_late_init(void) struct console *con; for_each_console(con) { - if (con->flags & CON_BOOT) { + if (!keep_bootcon && con->flags & CON_BOOT) { printk(KERN_INFO "turn off boot console %s%d\n", con->name, con->index); unregister_console(con); diff --git a/kernel/sched.c b/kernel/sched.c index ccacdbdecf4..ec5f472bc5b 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -3065,7 +3065,7 @@ static void finish_task_switch(struct rq *rq, struct task_struct *prev) #ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW local_irq_disable(); #endif /* __ARCH_WANT_INTERRUPTS_ON_CTXSW */ - perf_event_task_sched_in(current); + perf_event_task_sched_in(prev, current); #ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW local_irq_enable(); #endif /* __ARCH_WANT_INTERRUPTS_ON_CTXSW */ @@ -4279,9 +4279,9 @@ pick_next_task(struct rq *rq) } /* - * schedule() is the main scheduler function. + * __schedule() is the main scheduler function. */ -asmlinkage void __sched schedule(void) +static void __sched __schedule(void) { struct task_struct *prev, *next; unsigned long *switch_count; @@ -4322,16 +4322,6 @@ need_resched: if (to_wakeup) try_to_wake_up_local(to_wakeup); } - - /* - * If we are going to sleep and we have plugged IO - * queued, make sure to submit it to avoid deadlocks. - */ - if (blk_needs_flush_plug(prev)) { - raw_spin_unlock(&rq->lock); - blk_schedule_flush_plug(prev); - raw_spin_lock(&rq->lock); - } } switch_count = &prev->nvcsw; } @@ -4369,6 +4359,26 @@ need_resched: if (need_resched()) goto need_resched; } + +static inline void sched_submit_work(struct task_struct *tsk) +{ + if (!tsk->state) + return; + /* + * If we are going to sleep and we have plugged IO queued, + * make sure to submit it to avoid deadlocks. + */ + if (blk_needs_flush_plug(tsk)) + blk_schedule_flush_plug(tsk); +} + +asmlinkage void schedule(void) +{ + struct task_struct *tsk = current; + + sched_submit_work(tsk); + __schedule(); +} EXPORT_SYMBOL(schedule); #ifdef CONFIG_MUTEX_SPIN_ON_OWNER @@ -4435,7 +4445,7 @@ asmlinkage void __sched notrace preempt_schedule(void) do { add_preempt_count_notrace(PREEMPT_ACTIVE); - schedule(); + __schedule(); sub_preempt_count_notrace(PREEMPT_ACTIVE); /* @@ -4463,7 +4473,7 @@ asmlinkage void __sched preempt_schedule_irq(void) do { add_preempt_count(PREEMPT_ACTIVE); local_irq_enable(); - schedule(); + __schedule(); local_irq_disable(); sub_preempt_count(PREEMPT_ACTIVE); @@ -5588,7 +5598,7 @@ static inline int should_resched(void) static void __cond_resched(void) { add_preempt_count(PREEMPT_ACTIVE); - schedule(); + __schedule(); sub_preempt_count(PREEMPT_ACTIVE); } @@ -7443,6 +7453,7 @@ static void __sdt_free(const struct cpumask *cpu_map) struct sched_domain *sd = *per_cpu_ptr(sdd->sd, j); if (sd && (sd->flags & SD_OVERLAP)) free_sched_groups(sd->groups, 0); + kfree(*per_cpu_ptr(sdd->sd, j)); kfree(*per_cpu_ptr(sdd->sg, j)); kfree(*per_cpu_ptr(sdd->sgp, j)); } diff --git a/kernel/sys.c b/kernel/sys.c index dd948a1fca4..18ee1d2f647 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -37,6 +37,8 @@ #include <linux/fs_struct.h> #include <linux/gfp.h> #include <linux/syscore_ops.h> +#include <linux/version.h> +#include <linux/ctype.h> #include <linux/compat.h> #include <linux/syscalls.h> @@ -44,6 +46,8 @@ #include <linux/user_namespace.h> #include <linux/kmsg_dump.h> +/* Move somewhere else to avoid recompiling? */ +#include <generated/utsrelease.h> #include <asm/uaccess.h> #include <asm/io.h> @@ -1161,6 +1165,34 @@ DECLARE_RWSEM(uts_sem); #define override_architecture(name) 0 #endif +/* + * Work around broken programs that cannot handle "Linux 3.0". + * Instead we map 3.x to 2.6.40+x, so e.g. 3.0 would be 2.6.40 + */ +static int override_release(char __user *release, int len) +{ + int ret = 0; + char buf[len]; + + if (current->personality & UNAME26) { + char *rest = UTS_RELEASE; + int ndots = 0; + unsigned v; + + while (*rest) { + if (*rest == '.' && ++ndots >= 3) + break; + if (!isdigit(*rest) && *rest != '.') + break; + rest++; + } + v = ((LINUX_VERSION_CODE >> 8) & 0xff) + 40; + snprintf(buf, len, "2.6.%u%s", v, rest); + ret = copy_to_user(release, buf, len); + } + return ret; +} + SYSCALL_DEFINE1(newuname, struct new_utsname __user *, name) { int errno = 0; @@ -1170,6 +1202,8 @@ SYSCALL_DEFINE1(newuname, struct new_utsname __user *, name) errno = -EFAULT; up_read(&uts_sem); + if (!errno && override_release(name->release, sizeof(name->release))) + errno = -EFAULT; if (!errno && override_architecture(name)) errno = -EFAULT; return errno; @@ -1191,6 +1225,8 @@ SYSCALL_DEFINE1(uname, struct old_utsname __user *, name) error = -EFAULT; up_read(&uts_sem); + if (!error && override_release(name->release, sizeof(name->release))) + error = -EFAULT; if (!error && override_architecture(name)) error = -EFAULT; return error; @@ -1225,6 +1261,8 @@ SYSCALL_DEFINE1(olduname, struct oldold_utsname __user *, name) if (!error && override_architecture(name)) error = -EFAULT; + if (!error && override_release(name->release, sizeof(name->release))) + error = -EFAULT; return error ? -EFAULT : 0; } #endif diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c index 62cbc8877fe..a9a5de07c4f 100644 --- a/kernel/sys_ni.c +++ b/kernel/sys_ni.c @@ -16,7 +16,6 @@ asmlinkage long sys_ni_syscall(void) return -ENOSYS; } -cond_syscall(sys_nfsservctl); cond_syscall(sys_quotactl); cond_syscall(sys32_quotactl); cond_syscall(sys_acct); diff --git a/kernel/sysctl_binary.c b/kernel/sysctl_binary.c index 3b8e028b960..e8bffbe2ba4 100644 --- a/kernel/sysctl_binary.c +++ b/kernel/sysctl_binary.c @@ -1,6 +1,6 @@ #include <linux/stat.h> #include <linux/sysctl.h> -#include "../fs/xfs/linux-2.6/xfs_sysctl.h" +#include "../fs/xfs/xfs_sysctl.h" #include <linux/sunrpc/debug.h> #include <linux/string.h> #include <net/ip_vs.h> diff --git a/kernel/sysctl_check.c b/kernel/sysctl_check.c index 4e4932a7b36..362da653813 100644 --- a/kernel/sysctl_check.c +++ b/kernel/sysctl_check.c @@ -1,6 +1,6 @@ #include <linux/stat.h> #include <linux/sysctl.h> -#include "../fs/xfs/linux-2.6/xfs_sysctl.h" +#include "../fs/xfs/xfs_sysctl.h" #include <linux/sunrpc/debug.h> #include <linux/string.h> #include <net/ip_vs.h> diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c index 59f369f98a0..ea5e1a928d5 100644 --- a/kernel/time/alarmtimer.c +++ b/kernel/time/alarmtimer.c @@ -441,6 +441,8 @@ static int alarm_timer_create(struct k_itimer *new_timer) static void alarm_timer_get(struct k_itimer *timr, struct itimerspec *cur_setting) { + memset(cur_setting, 0, sizeof(struct itimerspec)); + cur_setting->it_interval = ktime_to_timespec(timr->it.alarmtimer.period); cur_setting->it_value = @@ -479,11 +481,17 @@ static int alarm_timer_set(struct k_itimer *timr, int flags, if (!rtcdev) return -ENOTSUPP; - /* Save old values */ - old_setting->it_interval = - ktime_to_timespec(timr->it.alarmtimer.period); - old_setting->it_value = - ktime_to_timespec(timr->it.alarmtimer.node.expires); + /* + * 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); |