diff options
Diffstat (limited to 'kernel')
-rw-r--r-- | kernel/acct.c | 2 | ||||
-rw-r--r-- | kernel/futex.c | 51 | ||||
-rw-r--r-- | kernel/irq/chip.c | 9 | ||||
-rw-r--r-- | kernel/kexec.c | 1 | ||||
-rw-r--r-- | kernel/panic.c | 18 | ||||
-rw-r--r-- | kernel/params.c | 10 | ||||
-rw-r--r-- | kernel/printk.c | 2 | ||||
-rw-r--r-- | kernel/ptrace.c | 6 | ||||
-rw-r--r-- | kernel/rwsem.c | 5 | ||||
-rw-r--r-- | kernel/sched.c | 20 | ||||
-rw-r--r-- | kernel/sched_debug.c | 8 | ||||
-rw-r--r-- | kernel/sched_fair.c | 3 | ||||
-rw-r--r-- | kernel/sched_rt.c | 2 | ||||
-rw-r--r-- | kernel/sysctl.c | 16 | ||||
-rw-r--r-- | kernel/sysctl_check.c | 7 | ||||
-rw-r--r-- | kernel/time/tick-broadcast.c | 56 | ||||
-rw-r--r-- | kernel/timer.c | 4 |
17 files changed, 137 insertions, 83 deletions
diff --git a/kernel/acct.c b/kernel/acct.c index cf19547cc9e..521dfa53cb9 100644 --- a/kernel/acct.c +++ b/kernel/acct.c @@ -482,7 +482,7 @@ static void do_acct_process(struct file *file) #endif #if ACCT_VERSION==3 ac.ac_pid = current->tgid; - ac.ac_ppid = current->parent->tgid; + ac.ac_ppid = current->real_parent->tgid; #endif spin_lock_irq(¤t->sighand->siglock); diff --git a/kernel/futex.c b/kernel/futex.c index 172a1aeeafd..db9824de8bf 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -1097,15 +1097,15 @@ static void unqueue_me_pi(struct futex_q *q) } /* - * Fixup the pi_state owner with current. + * Fixup the pi_state owner with the new owner. * * Must be called with hash bucket lock held and mm->sem held for non * private futexes. */ static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q, - struct task_struct *curr) + struct task_struct *newowner) { - u32 newtid = task_pid_vnr(curr) | FUTEX_WAITERS; + u32 newtid = task_pid_vnr(newowner) | FUTEX_WAITERS; struct futex_pi_state *pi_state = q->pi_state; u32 uval, curval, newval; int ret; @@ -1119,12 +1119,12 @@ static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q, } else newtid |= FUTEX_OWNER_DIED; - pi_state->owner = curr; + pi_state->owner = newowner; - spin_lock_irq(&curr->pi_lock); + spin_lock_irq(&newowner->pi_lock); WARN_ON(!list_empty(&pi_state->list)); - list_add(&pi_state->list, &curr->pi_state_list); - spin_unlock_irq(&curr->pi_lock); + list_add(&pi_state->list, &newowner->pi_state_list); + spin_unlock_irq(&newowner->pi_lock); /* * We own it, so we have to replace the pending owner @@ -1508,9 +1508,40 @@ static int futex_lock_pi(u32 __user *uaddr, struct rw_semaphore *fshared, * when we were on the way back before we locked the * hash bucket. */ - if (q.pi_state->owner == curr && - rt_mutex_trylock(&q.pi_state->pi_mutex)) { - ret = 0; + if (q.pi_state->owner == curr) { + /* + * Try to get the rt_mutex now. This might + * fail as some other task acquired the + * rt_mutex after we removed ourself from the + * rt_mutex waiters list. + */ + if (rt_mutex_trylock(&q.pi_state->pi_mutex)) + ret = 0; + else { + /* + * pi_state is incorrect, some other + * task did a lock steal and we + * returned due to timeout or signal + * without taking the rt_mutex. Too + * late. We can access the + * rt_mutex_owner without locking, as + * the other task is now blocked on + * the hash bucket lock. Fix the state + * up. + */ + struct task_struct *owner; + int res; + + owner = rt_mutex_owner(&q.pi_state->pi_mutex); + res = fixup_pi_state_owner(uaddr, &q, owner); + + WARN_ON(rt_mutex_owner(&q.pi_state->pi_mutex) != + owner); + + /* propagate -EFAULT, if the fixup failed */ + if (res) + ret = res; + } } else { /* * Paranoia check. If we did not take the lock diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index 9b5dff6b3f6..44019ce30a1 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -297,18 +297,13 @@ handle_simple_irq(unsigned int irq, struct irq_desc *desc) if (unlikely(desc->status & IRQ_INPROGRESS)) goto out_unlock; + desc->status &= ~(IRQ_REPLAY | IRQ_WAITING); kstat_cpu(cpu).irqs[irq]++; action = desc->action; - if (unlikely(!action || (desc->status & IRQ_DISABLED))) { - if (desc->chip->mask) - desc->chip->mask(irq); - desc->status &= ~(IRQ_REPLAY | IRQ_WAITING); - desc->status |= IRQ_PENDING; + if (unlikely(!action || (desc->status & IRQ_DISABLED))) goto out_unlock; - } - desc->status &= ~(IRQ_REPLAY | IRQ_WAITING | IRQ_PENDING); desc->status |= IRQ_INPROGRESS; spin_unlock(&desc->lock); diff --git a/kernel/kexec.c b/kernel/kexec.c index aa74a1ef2da..9a26eec9eb0 100644 --- a/kernel/kexec.c +++ b/kernel/kexec.c @@ -1404,6 +1404,7 @@ static int __init crash_save_vmcoreinfo_init(void) VMCOREINFO_OFFSET(list_head, next); VMCOREINFO_OFFSET(list_head, prev); VMCOREINFO_LENGTH(zone.free_area, MAX_ORDER); + VMCOREINFO_LENGTH(free_area.free_list, MIGRATE_TYPES); VMCOREINFO_NUMBER(NR_FREE_PAGES); arch_crash_save_vmcoreinfo(); diff --git a/kernel/panic.c b/kernel/panic.c index 6f6e03e9159..da4d6bac270 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -19,6 +19,7 @@ #include <linux/nmi.h> #include <linux/kexec.h> #include <linux/debug_locks.h> +#include <linux/random.h> int panic_on_oops; int tainted; @@ -266,12 +267,29 @@ void oops_enter(void) } /* + * 64-bit random ID for oopses: + */ +static u64 oops_id; + +static int init_oops_id(void) +{ + if (!oops_id) + get_random_bytes(&oops_id, sizeof(oops_id)); + + return 0; +} +late_initcall(init_oops_id); + +/* * Called when the architecture exits its oops handler, after printing * everything. */ void oops_exit(void) { do_oops_enter_exit(); + init_oops_id(); + printk(KERN_WARNING "---[ end trace %016llx ]---\n", + (unsigned long long)oops_id); } #ifdef CONFIG_CC_STACKPROTECTOR diff --git a/kernel/params.c b/kernel/params.c index 2a4c51487e7..7686417ee00 100644 --- a/kernel/params.c +++ b/kernel/params.c @@ -697,8 +697,18 @@ static struct kset_uevent_ops module_uevent_ops = { decl_subsys(module, &module_ktype, &module_uevent_ops); int module_sysfs_initialized; +static void module_release(struct kobject *kobj) +{ + /* + * Stupid empty release function to allow the memory for the kobject to + * be properly cleaned up. This will not need to be present for 2.6.25 + * with the upcoming kobject core rework. + */ +} + static struct kobj_type module_ktype = { .sysfs_ops = &module_sysfs_ops, + .release = module_release, }; /* diff --git a/kernel/printk.c b/kernel/printk.c index a30fe33de39..89011bf8c10 100644 --- a/kernel/printk.c +++ b/kernel/printk.c @@ -817,7 +817,7 @@ __setup("console=", console_setup); * commonly to provide a default console (ie from PROM variables) when * the user has not supplied one. */ -int __init add_preferred_console(char *name, int idx, char *options) +int add_preferred_console(char *name, int idx, char *options) { struct console_cmdline *c; int i; diff --git a/kernel/ptrace.c b/kernel/ptrace.c index 7c76f2ffaea..c25db863081 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -120,7 +120,7 @@ int ptrace_check_attach(struct task_struct *child, int kill) return ret; } -static int may_attach(struct task_struct *task) +int __ptrace_may_attach(struct task_struct *task) { /* May we inspect the given task? * This check is used both for attaching with ptrace @@ -154,7 +154,7 @@ int ptrace_may_attach(struct task_struct *task) { int err; task_lock(task); - err = may_attach(task); + err = __ptrace_may_attach(task); task_unlock(task); return !err; } @@ -196,7 +196,7 @@ repeat: /* the same process cannot be attached many times */ if (task->ptrace & PT_PTRACED) goto bad; - retval = may_attach(task); + retval = __ptrace_may_attach(task); if (retval) goto bad; diff --git a/kernel/rwsem.c b/kernel/rwsem.c index 1ec620c0306..cae050b05f5 100644 --- a/kernel/rwsem.c +++ b/kernel/rwsem.c @@ -6,6 +6,7 @@ #include <linux/types.h> #include <linux/kernel.h> +#include <linux/sched.h> #include <linux/module.h> #include <linux/rwsem.h> @@ -15,7 +16,7 @@ /* * lock for reading */ -void down_read(struct rw_semaphore *sem) +void __sched down_read(struct rw_semaphore *sem) { might_sleep(); rwsem_acquire_read(&sem->dep_map, 0, 0, _RET_IP_); @@ -42,7 +43,7 @@ EXPORT_SYMBOL(down_read_trylock); /* * lock for writing */ -void down_write(struct rw_semaphore *sem) +void __sched down_write(struct rw_semaphore *sem) { might_sleep(); rwsem_acquire(&sem->dep_map, 0, 0, _RET_IP_); diff --git a/kernel/sched.c b/kernel/sched.c index c6e551de795..37cf07aa416 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -508,10 +508,15 @@ EXPORT_SYMBOL_GPL(cpu_clock); # define finish_arch_switch(prev) do { } while (0) #endif +static inline int task_current(struct rq *rq, struct task_struct *p) +{ + return rq->curr == p; +} + #ifndef __ARCH_WANT_UNLOCKED_CTXSW static inline int task_running(struct rq *rq, struct task_struct *p) { - return rq->curr == p; + return task_current(rq, p); } static inline void prepare_lock_switch(struct rq *rq, struct task_struct *next) @@ -540,7 +545,7 @@ static inline int task_running(struct rq *rq, struct task_struct *p) #ifdef CONFIG_SMP return p->oncpu; #else - return rq->curr == p; + return task_current(rq, p); #endif } @@ -663,6 +668,7 @@ void sched_clock_idle_wakeup_event(u64 delta_ns) struct rq *rq = cpu_rq(smp_processor_id()); u64 now = sched_clock(); + touch_softlockup_watchdog(); rq->idle_clock += delta_ns; /* * Override the previous timestamp and ignore all @@ -3334,7 +3340,7 @@ unsigned long long task_sched_runtime(struct task_struct *p) rq = task_rq_lock(p, &flags); ns = p->se.sum_exec_runtime; - if (rq->curr == p) { + if (task_current(rq, p)) { update_rq_clock(rq); delta_exec = rq->clock - p->se.exec_start; if ((s64)delta_exec > 0) @@ -4021,7 +4027,7 @@ void rt_mutex_setprio(struct task_struct *p, int prio) oldprio = p->prio; on_rq = p->se.on_rq; - running = task_running(rq, p); + running = task_current(rq, p); if (on_rq) { dequeue_task(rq, p, 0); if (running) @@ -4332,7 +4338,7 @@ recheck: } update_rq_clock(rq); on_rq = p->se.on_rq; - running = task_running(rq, p); + running = task_current(rq, p); if (on_rq) { deactivate_task(rq, p, 0); if (running) @@ -4912,7 +4918,7 @@ static void show_task(struct task_struct *p) } #endif printk(KERN_CONT "%5lu %5d %6d\n", free, - task_pid_nr(p), task_pid_nr(p->parent)); + task_pid_nr(p), task_pid_nr(p->real_parent)); if (state != TASK_RUNNING) show_stack(p, NULL); @@ -7101,7 +7107,7 @@ void sched_move_task(struct task_struct *tsk) update_rq_clock(rq); - running = task_running(rq, tsk); + running = task_current(rq, tsk); on_rq = tsk->se.on_rq; if (on_rq) { diff --git a/kernel/sched_debug.c b/kernel/sched_debug.c index d30467b47dd..80fbbfc0429 100644 --- a/kernel/sched_debug.c +++ b/kernel/sched_debug.c @@ -31,9 +31,9 @@ /* * Ease the printing of nsec fields: */ -static long long nsec_high(long long nsec) +static long long nsec_high(unsigned long long nsec) { - if (nsec < 0) { + if ((long long)nsec < 0) { nsec = -nsec; do_div(nsec, 1000000); return -nsec; @@ -43,9 +43,9 @@ static long long nsec_high(long long nsec) return nsec; } -static unsigned long nsec_low(long long nsec) +static unsigned long nsec_low(unsigned long long nsec) { - if (nsec < 0) + if ((long long)nsec < 0) nsec = -nsec; return do_div(nsec, 1000000); diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c index c33f0ceb3de..da7c061e720 100644 --- a/kernel/sched_fair.c +++ b/kernel/sched_fair.c @@ -511,8 +511,7 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial) if (!initial) { /* sleeps upto a single latency don't count. */ - if (sched_feat(NEW_FAIR_SLEEPERS) && entity_is_task(se) && - task_of(se)->policy != SCHED_BATCH) + if (sched_feat(NEW_FAIR_SLEEPERS) && entity_is_task(se)) vruntime -= sysctl_sched_latency; /* ensure we never gain time by being placed backwards. */ diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c index ee9c8b6529e..9ba3daa0347 100644 --- a/kernel/sched_rt.c +++ b/kernel/sched_rt.c @@ -208,6 +208,8 @@ move_one_task_rt(struct rq *this_rq, int this_cpu, struct rq *busiest, static void task_tick_rt(struct rq *rq, struct task_struct *p) { + update_curr_rt(rq); + /* * RR tasks need a special form of timeslice management. * FIFO tasks have no timeslices. diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 8ac51714b08..c68f68dcc60 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -225,10 +225,10 @@ static struct ctl_table root_table[] = { }; #ifdef CONFIG_SCHED_DEBUG -static unsigned long min_sched_granularity_ns = 100000; /* 100 usecs */ -static unsigned long max_sched_granularity_ns = NSEC_PER_SEC; /* 1 second */ -static unsigned long min_wakeup_granularity_ns; /* 0 usecs */ -static unsigned long max_wakeup_granularity_ns = NSEC_PER_SEC; /* 1 second */ +static int min_sched_granularity_ns = 100000; /* 100 usecs */ +static int max_sched_granularity_ns = NSEC_PER_SEC; /* 1 second */ +static int min_wakeup_granularity_ns; /* 0 usecs */ +static int max_wakeup_granularity_ns = NSEC_PER_SEC; /* 1 second */ #endif static struct ctl_table kern_table[] = { @@ -906,11 +906,11 @@ static struct ctl_table vm_table[] = { }, { .ctl_name = CTL_UNNUMBERED, - .procname = "hugetlb_dynamic_pool", - .data = &hugetlb_dynamic_pool, - .maxlen = sizeof(hugetlb_dynamic_pool), + .procname = "nr_overcommit_hugepages", + .data = &nr_overcommit_huge_pages, + .maxlen = sizeof(nr_overcommit_huge_pages), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = &proc_doulongvec_minmax, }, #endif { diff --git a/kernel/sysctl_check.c b/kernel/sysctl_check.c index bed939f82c3..a68425a5cc1 100644 --- a/kernel/sysctl_check.c +++ b/kernel/sysctl_check.c @@ -428,7 +428,7 @@ static struct trans_ctl_table trans_net_netrom_table[] = { {} }; -static struct trans_ctl_table trans_net_ax25_table[] = { +static struct trans_ctl_table trans_net_ax25_param_table[] = { { NET_AX25_IP_DEFAULT_MODE, "ip_default_mode" }, { NET_AX25_DEFAULT_MODE, "ax25_default_mode" }, { NET_AX25_BACKOFF_TYPE, "backoff_type" }, @@ -446,6 +446,11 @@ static struct trans_ctl_table trans_net_ax25_table[] = { {} }; +static struct trans_ctl_table trans_net_ax25_table[] = { + { 0, NULL, trans_net_ax25_param_table }, + {} +}; + static struct trans_ctl_table trans_net_bridge_table[] = { { NET_BRIDGE_NF_CALL_ARPTABLES, "bridge-nf-call-arptables" }, { NET_BRIDGE_NF_CALL_IPTABLES, "bridge-nf-call-iptables" }, diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c index aa82d7bf478..5b86698faa0 100644 --- a/kernel/time/tick-broadcast.c +++ b/kernel/time/tick-broadcast.c @@ -384,45 +384,19 @@ int tick_resume_broadcast_oneshot(struct clock_event_device *bc) } /* - * Reprogram the broadcast device: - * - * Called with tick_broadcast_lock held and interrupts disabled. - */ -static int tick_broadcast_reprogram(void) -{ - ktime_t expires = { .tv64 = KTIME_MAX }; - struct tick_device *td; - int cpu; - - /* - * Find the event which expires next: - */ - for (cpu = first_cpu(tick_broadcast_oneshot_mask); cpu != NR_CPUS; - cpu = next_cpu(cpu, tick_broadcast_oneshot_mask)) { - td = &per_cpu(tick_cpu_device, cpu); - if (td->evtdev->next_event.tv64 < expires.tv64) - expires = td->evtdev->next_event; - } - - if (expires.tv64 == KTIME_MAX) - return 0; - - return tick_broadcast_set_event(expires, 0); -} - -/* * Handle oneshot mode broadcasting */ static void tick_handle_oneshot_broadcast(struct clock_event_device *dev) { struct tick_device *td; cpumask_t mask; - ktime_t now; + ktime_t now, next_event; int cpu; spin_lock(&tick_broadcast_lock); again: dev->next_event.tv64 = KTIME_MAX; + next_event.tv64 = KTIME_MAX; mask = CPU_MASK_NONE; now = ktime_get(); /* Find all expired events */ @@ -431,19 +405,31 @@ again: td = &per_cpu(tick_cpu_device, cpu); if (td->evtdev->next_event.tv64 <= now.tv64) cpu_set(cpu, mask); + else if (td->evtdev->next_event.tv64 < next_event.tv64) + next_event.tv64 = td->evtdev->next_event.tv64; } /* - * Wakeup the cpus which have an expired event. The broadcast - * device is reprogrammed in the return from idle code. + * Wakeup the cpus which have an expired event. + */ + tick_do_broadcast(mask); + + /* + * Two reasons for reprogram: + * + * - The global event did not expire any CPU local + * events. This happens in dyntick mode, as the maximum PIT + * delta is quite small. + * + * - There are pending events on sleeping CPUs which were not + * in the event mask */ - if (!tick_do_broadcast(mask)) { + if (next_event.tv64 != KTIME_MAX) { /* - * The global event did not expire any CPU local - * events. This happens in dyntick mode, as the - * maximum PIT delta is quite small. + * Rearm the broadcast device. If event expired, + * repeat the above */ - if (tick_broadcast_reprogram()) + if (tick_broadcast_set_event(next_event, 0)) goto again; } spin_unlock(&tick_broadcast_lock); diff --git a/kernel/timer.c b/kernel/timer.c index a05817c021d..d4527dcef1a 100644 --- a/kernel/timer.c +++ b/kernel/timer.c @@ -1219,11 +1219,11 @@ asmlinkage long sys_sysinfo(struct sysinfo __user *info) */ static struct lock_class_key base_lock_keys[NR_CPUS]; -static int __devinit init_timers_cpu(int cpu) +static int __cpuinit init_timers_cpu(int cpu) { int j; tvec_base_t *base; - static char __devinitdata tvec_base_done[NR_CPUS]; + static char __cpuinitdata tvec_base_done[NR_CPUS]; if (!tvec_base_done[cpu]) { static char boot_done; |