diff options
Diffstat (limited to 'kernel')
-rw-r--r-- | kernel/fork.c | 2 | ||||
-rw-r--r-- | kernel/hrtimer.c | 70 | ||||
-rw-r--r-- | kernel/itimer.c | 11 | ||||
-rw-r--r-- | kernel/posix-timers.c | 53 | ||||
-rw-r--r-- | kernel/power/console.c | 12 | ||||
-rw-r--r-- | kernel/power/disk.c | 6 | ||||
-rw-r--r-- | kernel/power/power.h | 9 | ||||
-rw-r--r-- | kernel/power/swsusp.c | 8 | ||||
-rw-r--r-- | kernel/rcutorture.c | 10 | ||||
-rw-r--r-- | kernel/sched.c | 8 | ||||
-rw-r--r-- | kernel/sysctl.c | 12 | ||||
-rw-r--r-- | kernel/time.c | 2 | ||||
-rw-r--r-- | kernel/user.c | 32 |
13 files changed, 123 insertions, 112 deletions
diff --git a/kernel/fork.c b/kernel/fork.c index 4ae8cfc1c89c..7f0ab5ee948c 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -802,7 +802,7 @@ static inline int copy_signal(unsigned long clone_flags, struct task_struct * ts init_sigpending(&sig->shared_pending); INIT_LIST_HEAD(&sig->posix_timers); - hrtimer_init(&sig->real_timer, CLOCK_MONOTONIC); + hrtimer_init(&sig->real_timer, CLOCK_MONOTONIC, HRTIMER_REL); sig->it_real_incr.tv64 = 0; sig->real_timer.function = it_real_fn; sig->real_timer.data = tsk; diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c index f1c4155b49ac..2b6e1757aedd 100644 --- a/kernel/hrtimer.c +++ b/kernel/hrtimer.c @@ -21,6 +21,12 @@ * Credits: * based on kernel/timer.c * + * Help, testing, suggestions, bugfixes, improvements were + * provided by: + * + * George Anzinger, Andrew Morton, Steven Rostedt, Roman Zippel + * et. al. + * * For licencing details see kernel-base/COPYING */ @@ -66,6 +72,12 @@ EXPORT_SYMBOL_GPL(ktime_get_real); /* * The timer bases: + * + * Note: If we want to add new timer bases, we have to skip the two + * clock ids captured by the cpu-timers. We do this by holding empty + * entries rather than doing math adjustment of the clock ids. + * This ensures that we capture erroneous accesses to these clock ids + * rather than moving them into the range of valid clock id's. */ #define MAX_HRTIMER_BASES 2 @@ -483,29 +495,25 @@ ktime_t hrtimer_get_remaining(const struct hrtimer *timer) } /** - * hrtimer_rebase - rebase an initialized hrtimer to a different base + * hrtimer_init - initialize a timer to the given clock * - * @timer: the timer to be rebased + * @timer: the timer to be initialized * @clock_id: the clock to be used + * @mode: timer mode abs/rel */ -void hrtimer_rebase(struct hrtimer *timer, const clockid_t clock_id) +void hrtimer_init(struct hrtimer *timer, clockid_t clock_id, + enum hrtimer_mode mode) { struct hrtimer_base *bases; + memset(timer, 0, sizeof(struct hrtimer)); + bases = per_cpu(hrtimer_bases, raw_smp_processor_id()); - timer->base = &bases[clock_id]; -} -/** - * hrtimer_init - initialize a timer to the given clock - * - * @timer: the timer to be initialized - * @clock_id: the clock to be used - */ -void hrtimer_init(struct hrtimer *timer, const clockid_t clock_id) -{ - memset(timer, 0, sizeof(struct hrtimer)); - hrtimer_rebase(timer, clock_id); + if (clock_id == CLOCK_REALTIME && mode != HRTIMER_ABS) + clock_id = CLOCK_MONOTONIC; + + timer->base = &bases[clock_id]; } /** @@ -550,6 +558,7 @@ static inline void run_hrtimer_queue(struct hrtimer_base *base) fn = timer->function; data = timer->data; set_curr_timer(base, timer); + timer->state = HRTIMER_RUNNING; __remove_hrtimer(timer, base); spin_unlock_irq(&base->lock); @@ -565,6 +574,10 @@ static inline void run_hrtimer_queue(struct hrtimer_base *base) spin_lock_irq(&base->lock); + /* Another CPU has added back the timer */ + if (timer->state != HRTIMER_RUNNING) + continue; + if (restart == HRTIMER_RESTART) enqueue_hrtimer(timer, base); else @@ -638,8 +651,7 @@ schedule_hrtimer_interruptible(struct hrtimer *timer, return schedule_hrtimer(timer, mode); } -static long __sched -nanosleep_restart(struct restart_block *restart, clockid_t clockid) +static long __sched nanosleep_restart(struct restart_block *restart) { struct timespec __user *rmtp; struct timespec tu; @@ -649,7 +661,7 @@ nanosleep_restart(struct restart_block *restart, clockid_t clockid) restart->fn = do_no_restart_syscall; - hrtimer_init(&timer, clockid); + hrtimer_init(&timer, (clockid_t) restart->arg3, HRTIMER_ABS); timer.expires.tv64 = ((u64)restart->arg1 << 32) | (u64) restart->arg0; @@ -669,16 +681,6 @@ nanosleep_restart(struct restart_block *restart, clockid_t clockid) return -ERESTART_RESTARTBLOCK; } -static long __sched nanosleep_restart_mono(struct restart_block *restart) -{ - return nanosleep_restart(restart, CLOCK_MONOTONIC); -} - -static long __sched nanosleep_restart_real(struct restart_block *restart) -{ - return nanosleep_restart(restart, CLOCK_REALTIME); -} - long hrtimer_nanosleep(struct timespec *rqtp, struct timespec __user *rmtp, const enum hrtimer_mode mode, const clockid_t clockid) { @@ -687,7 +689,7 @@ long hrtimer_nanosleep(struct timespec *rqtp, struct timespec __user *rmtp, struct timespec tu; ktime_t rem; - hrtimer_init(&timer, clockid); + hrtimer_init(&timer, clockid, mode); timer.expires = timespec_to_ktime(*rqtp); @@ -695,7 +697,7 @@ long hrtimer_nanosleep(struct timespec *rqtp, struct timespec __user *rmtp, if (rem.tv64 <= 0) return 0; - /* Absolute timers do not update the rmtp value: */ + /* Absolute timers do not update the rmtp value and restart: */ if (mode == HRTIMER_ABS) return -ERESTARTNOHAND; @@ -705,11 +707,11 @@ long hrtimer_nanosleep(struct timespec *rqtp, struct timespec __user *rmtp, return -EFAULT; restart = ¤t_thread_info()->restart_block; - restart->fn = (clockid == CLOCK_MONOTONIC) ? - nanosleep_restart_mono : nanosleep_restart_real; + restart->fn = nanosleep_restart; restart->arg0 = timer.expires.tv64 & 0xFFFFFFFF; restart->arg1 = timer.expires.tv64 >> 32; restart->arg2 = (unsigned long) rmtp; + restart->arg3 = (unsigned long) timer.base->index; return -ERESTART_RESTARTBLOCK; } @@ -736,10 +738,8 @@ static void __devinit init_hrtimers_cpu(int cpu) struct hrtimer_base *base = per_cpu(hrtimer_bases, cpu); int i; - for (i = 0; i < MAX_HRTIMER_BASES; i++) { + for (i = 0; i < MAX_HRTIMER_BASES; i++, base++) spin_lock_init(&base->lock); - base++; - } } #ifdef CONFIG_HOTPLUG_CPU diff --git a/kernel/itimer.c b/kernel/itimer.c index c2c05c4ff28d..379be2f8c84c 100644 --- a/kernel/itimer.c +++ b/kernel/itimer.c @@ -49,9 +49,11 @@ int do_getitimer(int which, struct itimerval *value) switch (which) { case ITIMER_REAL: + spin_lock_irq(&tsk->sighand->siglock); value->it_value = itimer_get_remtime(&tsk->signal->real_timer); value->it_interval = ktime_to_timeval(tsk->signal->it_real_incr); + spin_unlock_irq(&tsk->sighand->siglock); break; case ITIMER_VIRTUAL: read_lock(&tasklist_lock); @@ -150,18 +152,25 @@ int do_setitimer(int which, struct itimerval *value, struct itimerval *ovalue) switch (which) { case ITIMER_REAL: +again: + spin_lock_irq(&tsk->sighand->siglock); timer = &tsk->signal->real_timer; - hrtimer_cancel(timer); if (ovalue) { ovalue->it_value = itimer_get_remtime(timer); ovalue->it_interval = ktime_to_timeval(tsk->signal->it_real_incr); } + /* We are sharing ->siglock with it_real_fn() */ + if (hrtimer_try_to_cancel(timer) < 0) { + spin_unlock_irq(&tsk->sighand->siglock); + goto again; + } tsk->signal->it_real_incr = timeval_to_ktime(value->it_interval); expires = timeval_to_ktime(value->it_value); if (expires.tv64 != 0) hrtimer_start(timer, expires, HRTIMER_REL); + spin_unlock_irq(&tsk->sighand->siglock); break; case ITIMER_VIRTUAL: nval = timeval_to_cputime(&value->it_value); diff --git a/kernel/posix-timers.c b/kernel/posix-timers.c index 197208b3aa2a..216f574b5ffb 100644 --- a/kernel/posix-timers.c +++ b/kernel/posix-timers.c @@ -194,9 +194,7 @@ static inline int common_clock_set(const clockid_t which_clock, static int common_timer_create(struct k_itimer *new_timer) { - hrtimer_init(&new_timer->it.real.timer, new_timer->it_clock); - new_timer->it.real.timer.data = new_timer; - new_timer->it.real.timer.function = posix_timer_fn; + hrtimer_init(&new_timer->it.real.timer, new_timer->it_clock, 0); return 0; } @@ -290,7 +288,8 @@ void do_schedule_next_timer(struct siginfo *info) info->si_overrun = timr->it_overrun_last; } - unlock_timer(timr, flags); + if (timr) + unlock_timer(timr, flags); } int posix_timer_event(struct k_itimer *timr,int si_private) @@ -692,6 +691,7 @@ common_timer_set(struct k_itimer *timr, int flags, struct itimerspec *new_setting, struct itimerspec *old_setting) { struct hrtimer *timer = &timr->it.real.timer; + enum hrtimer_mode mode; if (old_setting) common_timer_get(timr, old_setting); @@ -713,14 +713,10 @@ common_timer_set(struct k_itimer *timr, int flags, if (!new_setting->it_value.tv_sec && !new_setting->it_value.tv_nsec) return 0; - /* Posix madness. Only absolute CLOCK_REALTIME timers - * are affected by clock sets. So we must reiniatilize - * the timer. - */ - if (timr->it_clock == CLOCK_REALTIME && (flags & TIMER_ABSTIME)) - hrtimer_rebase(timer, CLOCK_REALTIME); - else - hrtimer_rebase(timer, CLOCK_MONOTONIC); + mode = flags & TIMER_ABSTIME ? HRTIMER_ABS : HRTIMER_REL; + hrtimer_init(&timr->it.real.timer, timr->it_clock, mode); + timr->it.real.timer.data = timr; + timr->it.real.timer.function = posix_timer_fn; timer->expires = timespec_to_ktime(new_setting->it_value); @@ -728,11 +724,15 @@ common_timer_set(struct k_itimer *timr, int flags, timr->it.real.interval = timespec_to_ktime(new_setting->it_interval); /* SIGEV_NONE timers are not queued ! See common_timer_get */ - if (((timr->it_sigev_notify & ~SIGEV_THREAD_ID) == SIGEV_NONE)) + if (((timr->it_sigev_notify & ~SIGEV_THREAD_ID) == SIGEV_NONE)) { + /* Setup correct expiry time for relative timers */ + if (mode == HRTIMER_REL) + timer->expires = ktime_add(timer->expires, + timer->base->get_time()); return 0; + } - hrtimer_start(timer, timer->expires, (flags & TIMER_ABSTIME) ? - HRTIMER_ABS : HRTIMER_REL); + hrtimer_start(timer, timer->expires, mode); return 0; } @@ -875,12 +875,6 @@ int do_posix_clock_nosettime(const clockid_t clockid, struct timespec *tp) } EXPORT_SYMBOL_GPL(do_posix_clock_nosettime); -int do_posix_clock_notimer_create(struct k_itimer *timer) -{ - return -EINVAL; -} -EXPORT_SYMBOL_GPL(do_posix_clock_notimer_create); - int do_posix_clock_nonanosleep(const clockid_t clock, int flags, struct timespec *t, struct timespec __user *r) { @@ -947,21 +941,8 @@ sys_clock_getres(const clockid_t which_clock, struct timespec __user *tp) static int common_nsleep(const clockid_t which_clock, int flags, struct timespec *tsave, struct timespec __user *rmtp) { - int mode = flags & TIMER_ABSTIME ? HRTIMER_ABS : HRTIMER_REL; - int clockid = which_clock; - - switch (which_clock) { - case CLOCK_REALTIME: - /* Posix madness. Only absolute timers on clock realtime - are affected by clock set. */ - if (mode != HRTIMER_ABS) - clockid = CLOCK_MONOTONIC; - case CLOCK_MONOTONIC: - break; - default: - return -EINVAL; - } - return hrtimer_nanosleep(tsave, rmtp, mode, clockid); + return hrtimer_nanosleep(tsave, rmtp, flags & TIMER_ABSTIME ? + HRTIMER_ABS : HRTIMER_REL, which_clock); } asmlinkage long diff --git a/kernel/power/console.c b/kernel/power/console.c index 7ff375e7c95f..579d239d129f 100644 --- a/kernel/power/console.c +++ b/kernel/power/console.c @@ -9,18 +9,11 @@ #include <linux/console.h> #include "power.h" -static int new_loglevel = 10; -static int orig_loglevel; #ifdef SUSPEND_CONSOLE static int orig_fgconsole, orig_kmsg; -#endif int pm_prepare_console(void) { - orig_loglevel = console_loglevel; - console_loglevel = new_loglevel; - -#ifdef SUSPEND_CONSOLE acquire_console_sem(); orig_fgconsole = fg_console; @@ -41,18 +34,15 @@ int pm_prepare_console(void) } orig_kmsg = kmsg_redirect; kmsg_redirect = SUSPEND_CONSOLE; -#endif return 0; } void pm_restore_console(void) { - console_loglevel = orig_loglevel; -#ifdef SUSPEND_CONSOLE acquire_console_sem(); set_console(orig_fgconsole); release_console_sem(); kmsg_redirect = orig_kmsg; -#endif return; } +#endif diff --git a/kernel/power/disk.c b/kernel/power/disk.c index e03d85e55291..0b43847dc980 100644 --- a/kernel/power/disk.c +++ b/kernel/power/disk.c @@ -360,14 +360,14 @@ power_attr(resume); static ssize_t image_size_show(struct subsystem * subsys, char *buf) { - return sprintf(buf, "%u\n", image_size); + return sprintf(buf, "%lu\n", image_size); } static ssize_t image_size_store(struct subsystem * subsys, const char * buf, size_t n) { - unsigned int size; + unsigned long size; - if (sscanf(buf, "%u", &size) == 1) { + if (sscanf(buf, "%lu", &size) == 1) { image_size = size; return n; } diff --git a/kernel/power/power.h b/kernel/power/power.h index 7e8492fd1423..d8f0d1a76bae 100644 --- a/kernel/power/power.h +++ b/kernel/power/power.h @@ -42,8 +42,13 @@ static struct subsys_attribute _name##_attr = { \ extern struct subsystem power_subsys; +#ifdef SUSPEND_CONSOLE extern int pm_prepare_console(void); extern void pm_restore_console(void); +#else +static int pm_prepare_console(void) { return 0; } +static void pm_restore_console(void) {} +#endif /* References to section boundaries */ extern const void __nosave_begin, __nosave_end; @@ -51,8 +56,8 @@ extern const void __nosave_begin, __nosave_end; extern unsigned int nr_copy_pages; extern struct pbe *pagedir_nosave; -/* Preferred image size in MB (default 500) */ -extern unsigned int image_size; +/* Preferred image size in bytes (default 500 MB) */ +extern unsigned long image_size; extern asmlinkage int swsusp_arch_suspend(void); extern asmlinkage int swsusp_arch_resume(void); diff --git a/kernel/power/swsusp.c b/kernel/power/swsusp.c index 55a18d26abed..59c91c148e82 100644 --- a/kernel/power/swsusp.c +++ b/kernel/power/swsusp.c @@ -70,12 +70,12 @@ #include "power.h" /* - * Preferred image size in MB (tunable via /sys/power/image_size). + * Preferred image size in bytes (tunable via /sys/power/image_size). * When it is set to N, swsusp will do its best to ensure the image - * size will not exceed N MB, but if that is impossible, it will + * size will not exceed N bytes, but if that is impossible, it will * try to create the smallest image possible. */ -unsigned int image_size = 500; +unsigned long image_size = 500 * 1024 * 1024; #ifdef CONFIG_HIGHMEM unsigned int count_highmem_pages(void); @@ -590,7 +590,7 @@ int swsusp_shrink_memory(void) if (!tmp) return -ENOMEM; pages += tmp; - } else if (size > (image_size * 1024 * 1024) / PAGE_SIZE) { + } else if (size > image_size / PAGE_SIZE) { tmp = shrink_all_memory(SHRINK_BITE); pages += tmp; } diff --git a/kernel/rcutorture.c b/kernel/rcutorture.c index 773219907dd8..7712912dbc84 100644 --- a/kernel/rcutorture.c +++ b/kernel/rcutorture.c @@ -114,16 +114,16 @@ rcu_torture_alloc(void) { struct list_head *p; - spin_lock(&rcu_torture_lock); + spin_lock_bh(&rcu_torture_lock); if (list_empty(&rcu_torture_freelist)) { atomic_inc(&n_rcu_torture_alloc_fail); - spin_unlock(&rcu_torture_lock); + spin_unlock_bh(&rcu_torture_lock); return NULL; } atomic_inc(&n_rcu_torture_alloc); p = rcu_torture_freelist.next; list_del_init(p); - spin_unlock(&rcu_torture_lock); + spin_unlock_bh(&rcu_torture_lock); return container_of(p, struct rcu_torture, rtort_free); } @@ -134,9 +134,9 @@ static void rcu_torture_free(struct rcu_torture *p) { atomic_inc(&n_rcu_torture_free); - spin_lock(&rcu_torture_lock); + spin_lock_bh(&rcu_torture_lock); list_add_tail(&p->rtort_free, &rcu_torture_freelist); - spin_unlock(&rcu_torture_lock); + spin_unlock_bh(&rcu_torture_lock); } static void diff --git a/kernel/sched.c b/kernel/sched.c index 3ee2ae45125f..f77f23f8f479 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -4031,7 +4031,7 @@ long sched_getaffinity(pid_t pid, cpumask_t *mask) goto out_unlock; retval = 0; - cpus_and(*mask, p->cpus_allowed, cpu_possible_map); + cpus_and(*mask, p->cpus_allowed, cpu_online_map); out_unlock: read_unlock(&tasklist_lock); @@ -5141,7 +5141,7 @@ static void init_sched_build_groups(struct sched_group groups[], cpumask_t span, #define SEARCH_SCOPE 2 #define MIN_CACHE_SIZE (64*1024U) #define DEFAULT_CACHE_SIZE (5*1024*1024U) -#define ITERATIONS 2 +#define ITERATIONS 1 #define SIZE_THRESH 130 #define COST_THRESH 130 @@ -5480,9 +5480,9 @@ static unsigned long long measure_migration_cost(int cpu1, int cpu2) break; } /* - * Increase the cachesize in 5% steps: + * Increase the cachesize in 10% steps: */ - size = size * 20 / 19; + size = size * 10 / 9; } if (migration_debug) diff --git a/kernel/sysctl.c b/kernel/sysctl.c index cb99a42f8b37..71dd6f62efec 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -878,7 +878,17 @@ static ctl_table vm_table[] = { .maxlen = sizeof(zone_reclaim_mode), .mode = 0644, .proc_handler = &proc_dointvec, - .strategy = &zero, + .strategy = &sysctl_intvec, + .extra1 = &zero, + }, + { + .ctl_name = VM_ZONE_RECLAIM_INTERVAL, + .procname = "zone_reclaim_interval", + .data = &zone_reclaim_interval, + .maxlen = sizeof(zone_reclaim_interval), + .mode = 0644, + .proc_handler = &proc_dointvec_jiffies, + .strategy = &sysctl_jiffies, }, #endif { .ctl_name = 0 } diff --git a/kernel/time.c b/kernel/time.c index 7477b1d2079e..1f23e683d6aa 100644 --- a/kernel/time.c +++ b/kernel/time.c @@ -155,7 +155,7 @@ int do_sys_settimeofday(struct timespec *tv, struct timezone *tz) static int firsttime = 1; int error = 0; - if (!timespec_valid(tv)) + if (tv && !timespec_valid(tv)) return -EINVAL; error = security_settime(tv, tz); diff --git a/kernel/user.c b/kernel/user.c index 89e562feb1b1..d9deae43a9ab 100644 --- a/kernel/user.c +++ b/kernel/user.c @@ -13,6 +13,7 @@ #include <linux/slab.h> #include <linux/bitops.h> #include <linux/key.h> +#include <linux/interrupt.h> /* * UID task count cache, to get fast user lookup in "alloc_uid" @@ -27,6 +28,16 @@ static kmem_cache_t *uid_cachep; static struct list_head uidhash_table[UIDHASH_SZ]; + +/* + * The uidhash_lock is mostly taken from process context, but it is + * occasionally also taken from softirq/tasklet context, when + * task-structs get RCU-freed. Hence all locking must be softirq-safe. + * But free_uid() is also called with local interrupts disabled, and running + * local_bh_enable() with local interrupts disabled is an error - we'll run + * softirq callbacks, and they can unconditionally enable interrupts, and + * the caller of free_uid() didn't expect that.. + */ static DEFINE_SPINLOCK(uidhash_lock); struct user_struct root_user = { @@ -82,15 +93,19 @@ static inline struct user_struct *uid_hash_find(uid_t uid, struct list_head *has struct user_struct *find_user(uid_t uid) { struct user_struct *ret; + unsigned long flags; - spin_lock(&uidhash_lock); + spin_lock_irqsave(&uidhash_lock, flags); ret = uid_hash_find(uid, uidhashentry(uid)); - spin_unlock(&uidhash_lock); + spin_unlock_irqrestore(&uidhash_lock, flags); return ret; } void free_uid(struct user_struct *up) { + unsigned long flags; + + local_irq_save(flags); if (up && atomic_dec_and_lock(&up->__count, &uidhash_lock)) { uid_hash_remove(up); key_put(up->uid_keyring); @@ -98,6 +113,7 @@ void free_uid(struct user_struct *up) kmem_cache_free(uid_cachep, up); spin_unlock(&uidhash_lock); } + local_irq_restore(flags); } struct user_struct * alloc_uid(uid_t uid) @@ -105,9 +121,9 @@ struct user_struct * alloc_uid(uid_t uid) struct list_head *hashent = uidhashentry(uid); struct user_struct *up; - spin_lock(&uidhash_lock); + spin_lock_irq(&uidhash_lock); up = uid_hash_find(uid, hashent); - spin_unlock(&uidhash_lock); + spin_unlock_irq(&uidhash_lock); if (!up) { struct user_struct *new; @@ -137,7 +153,7 @@ struct user_struct * alloc_uid(uid_t uid) * Before adding this, check whether we raced * on adding the same user already.. */ - spin_lock(&uidhash_lock); + spin_lock_irq(&uidhash_lock); up = uid_hash_find(uid, hashent); if (up) { key_put(new->uid_keyring); @@ -147,7 +163,7 @@ struct user_struct * alloc_uid(uid_t uid) uid_hash_insert(new, hashent); up = new; } - spin_unlock(&uidhash_lock); + spin_unlock_irq(&uidhash_lock); } return up; @@ -183,9 +199,9 @@ static int __init uid_cache_init(void) INIT_LIST_HEAD(uidhash_table + n); /* Insert the root user immediately (init already runs as root) */ - spin_lock(&uidhash_lock); + spin_lock_irq(&uidhash_lock); uid_hash_insert(&root_user, uidhashentry(0)); - spin_unlock(&uidhash_lock); + spin_unlock_irq(&uidhash_lock); return 0; } |