diff options
Diffstat (limited to 'kernel')
-rw-r--r-- | kernel/auditsc.c | 2 | ||||
-rw-r--r-- | kernel/exit.c | 7 | ||||
-rw-r--r-- | kernel/fork.c | 22 | ||||
-rw-r--r-- | kernel/hrtimer.c | 35 | ||||
-rw-r--r-- | kernel/ksysfs.c | 3 | ||||
-rw-r--r-- | kernel/module.c | 199 | ||||
-rw-r--r-- | kernel/params.c | 10 | ||||
-rw-r--r-- | kernel/posix-timers.c | 1 | ||||
-rw-r--r-- | kernel/rcupdate.c | 82 | ||||
-rw-r--r-- | kernel/sched.c | 16 | ||||
-rw-r--r-- | kernel/softirq.c | 20 | ||||
-rw-r--r-- | kernel/sysctl.c | 19 | ||||
-rw-r--r-- | kernel/timer.c | 26 | ||||
-rw-r--r-- | kernel/workqueue.c | 29 |
14 files changed, 331 insertions, 140 deletions
diff --git a/kernel/auditsc.c b/kernel/auditsc.c index d7e7e637b92a..c4394abcd5e6 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -958,7 +958,7 @@ void audit_syscall_entry(struct task_struct *tsk, int arch, int major, * * i386 no * x86_64 no - * ppc64 yes (see arch/ppc64/kernel/misc.S) + * ppc64 yes (see arch/powerpc/platforms/iseries/misc.S) * * This also happens with vm86 emulation in a non-nested manner * (entries without exits), so this case must be caught. diff --git a/kernel/exit.c b/kernel/exit.c index 531aadca5530..d1e8d500a7e1 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -807,8 +807,6 @@ fastcall NORET_TYPE void do_exit(long code) panic("Attempted to kill the idle task!"); if (unlikely(tsk->pid == 1)) panic("Attempted to kill init!"); - if (tsk->io_context) - exit_io_context(); if (unlikely(current->ptrace & PT_TRACE_EXIT)) { current->ptrace_message = code; @@ -822,6 +820,8 @@ fastcall NORET_TYPE void do_exit(long code) if (unlikely(tsk->flags & PF_EXITING)) { printk(KERN_ALERT "Fixing recursive fault but reboot is needed!\n"); + if (tsk->io_context) + exit_io_context(); set_current_state(TASK_UNINTERRUPTIBLE); schedule(); } @@ -881,6 +881,9 @@ fastcall NORET_TYPE void do_exit(long code) */ mutex_debug_check_no_locks_held(tsk); + if (tsk->io_context) + exit_io_context(); + /* PF_DEAD causes final put_task_struct after we schedule. */ preempt_disable(); BUG_ON(tsk->flags & PF_DEAD); diff --git a/kernel/fork.c b/kernel/fork.c index fbea12d7a943..9bd7b65ee418 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -108,8 +108,10 @@ void free_task(struct task_struct *tsk) } EXPORT_SYMBOL(free_task); -void __put_task_struct(struct task_struct *tsk) +void __put_task_struct_cb(struct rcu_head *rhp) { + struct task_struct *tsk = container_of(rhp, struct task_struct, rcu); + WARN_ON(!(tsk->exit_state & (EXIT_DEAD | EXIT_ZOMBIE))); WARN_ON(atomic_read(&tsk->usage)); WARN_ON(tsk == current); @@ -1060,6 +1062,12 @@ static task_t *copy_process(unsigned long clone_flags, p->clear_child_tid = (clone_flags & CLONE_CHILD_CLEARTID) ? child_tidptr: NULL; /* + * sigaltstack should be cleared when sharing the same VM + */ + if ((clone_flags & (CLONE_VM|CLONE_VFORK)) == CLONE_VM) + p->sas_ss_sp = p->sas_ss_size = 0; + + /* * Syscall tracing should be turned off in the child regardless * of CLONE_PTRACE. */ @@ -1470,9 +1478,7 @@ static int unshare_vm(unsigned long unshare_flags, struct mm_struct **new_mmp) if ((unshare_flags & CLONE_VM) && (mm && atomic_read(&mm->mm_users) > 1)) { - *new_mmp = dup_mm(current); - if (!*new_mmp) - return -ENOMEM; + return -EINVAL; } return 0; @@ -1528,6 +1534,12 @@ asmlinkage long sys_unshare(unsigned long unshare_flags) check_unshare_flags(&unshare_flags); + /* Return -EINVAL for all unsupported flags */ + err = -EINVAL; + if (unshare_flags & ~(CLONE_THREAD|CLONE_FS|CLONE_NEWNS|CLONE_SIGHAND| + CLONE_VM|CLONE_FILES|CLONE_SYSVSEM)) + goto bad_unshare_out; + if ((err = unshare_thread(unshare_flags))) goto bad_unshare_out; if ((err = unshare_fs(unshare_flags, &new_fs))) @@ -1561,7 +1573,7 @@ asmlinkage long sys_unshare(unsigned long unshare_flags) if (new_sigh) { sigh = current->sighand; - current->sighand = new_sigh; + rcu_assign_pointer(current->sighand, new_sigh); new_sigh = sigh; } diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c index 5ae51f1bc7c8..14bc9cfa6399 100644 --- a/kernel/hrtimer.c +++ b/kernel/hrtimer.c @@ -505,6 +505,41 @@ ktime_t hrtimer_get_remaining(const struct hrtimer *timer) return rem; } +#ifdef CONFIG_NO_IDLE_HZ +/** + * hrtimer_get_next_event - get the time until next expiry event + * + * Returns the delta to the next expiry event or KTIME_MAX if no timer + * is pending. + */ +ktime_t hrtimer_get_next_event(void) +{ + struct hrtimer_base *base = __get_cpu_var(hrtimer_bases); + ktime_t delta, mindelta = { .tv64 = KTIME_MAX }; + unsigned long flags; + int i; + + for (i = 0; i < MAX_HRTIMER_BASES; i++, base++) { + struct hrtimer *timer; + + spin_lock_irqsave(&base->lock, flags); + if (!base->first) { + spin_unlock_irqrestore(&base->lock, flags); + continue; + } + timer = rb_entry(base->first, struct hrtimer, node); + delta.tv64 = timer->expires.tv64; + spin_unlock_irqrestore(&base->lock, flags); + delta = ktime_sub(delta, base->get_time()); + if (delta.tv64 < mindelta.tv64) + mindelta.tv64 = delta.tv64; + } + if (mindelta.tv64 < 0) + mindelta.tv64 = 0; + return mindelta; +} +#endif + /** * hrtimer_init - initialize a timer to the given clock * diff --git a/kernel/ksysfs.c b/kernel/ksysfs.c index d5eeae0fa5bc..f2690ed74530 100644 --- a/kernel/ksysfs.c +++ b/kernel/ksysfs.c @@ -15,9 +15,6 @@ #include <linux/module.h> #include <linux/init.h> -u64 uevent_seqnum; -char uevent_helper[UEVENT_HELPER_PATH_LEN] = "/sbin/hotplug"; - #define KERNEL_ATTR_RO(_name) \ static struct subsys_attribute _name##_attr = __ATTR_RO(_name) diff --git a/kernel/module.c b/kernel/module.c index 5aad477ddc79..77764f22f021 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -126,8 +126,11 @@ extern const struct kernel_symbol __start___ksymtab[]; extern const struct kernel_symbol __stop___ksymtab[]; extern const struct kernel_symbol __start___ksymtab_gpl[]; extern const struct kernel_symbol __stop___ksymtab_gpl[]; +extern const struct kernel_symbol __start___ksymtab_gpl_future[]; +extern const struct kernel_symbol __stop___ksymtab_gpl_future[]; extern const unsigned long __start___kcrctab[]; extern const unsigned long __start___kcrctab_gpl[]; +extern const unsigned long __start___kcrctab_gpl_future[]; #ifndef CONFIG_MODVERSIONS #define symversion(base, idx) NULL @@ -135,6 +138,18 @@ extern const unsigned long __start___kcrctab_gpl[]; #define symversion(base, idx) ((base) ? ((base) + (idx)) : NULL) #endif +/* lookup symbol in given range of kernel_symbols */ +static const struct kernel_symbol *lookup_symbol(const char *name, + const struct kernel_symbol *start, + const struct kernel_symbol *stop) +{ + const struct kernel_symbol *ks = start; + for (; ks < stop; ks++) + if (strcmp(ks->name, name) == 0) + return ks; + return NULL; +} + /* Find a symbol, return value, crc and module which owns it */ static unsigned long __find_symbol(const char *name, struct module **owner, @@ -142,40 +157,75 @@ static unsigned long __find_symbol(const char *name, int gplok) { struct module *mod; - unsigned int i; + const struct kernel_symbol *ks; /* Core kernel first. */ *owner = NULL; - for (i = 0; __start___ksymtab+i < __stop___ksymtab; i++) { - if (strcmp(__start___ksymtab[i].name, name) == 0) { - *crc = symversion(__start___kcrctab, i); - return __start___ksymtab[i].value; - } + ks = lookup_symbol(name, __start___ksymtab, __stop___ksymtab); + if (ks) { + *crc = symversion(__start___kcrctab, (ks - __start___ksymtab)); + return ks->value; } if (gplok) { - for (i = 0; __start___ksymtab_gpl+i<__stop___ksymtab_gpl; i++) - if (strcmp(__start___ksymtab_gpl[i].name, name) == 0) { - *crc = symversion(__start___kcrctab_gpl, i); - return __start___ksymtab_gpl[i].value; - } + ks = lookup_symbol(name, __start___ksymtab_gpl, + __stop___ksymtab_gpl); + if (ks) { + *crc = symversion(__start___kcrctab_gpl, + (ks - __start___ksymtab_gpl)); + return ks->value; + } + } + ks = lookup_symbol(name, __start___ksymtab_gpl_future, + __stop___ksymtab_gpl_future); + if (ks) { + if (!gplok) { + printk(KERN_WARNING "Symbol %s is being used " + "by a non-GPL module, which will not " + "be allowed in the future\n", name); + printk(KERN_WARNING "Please see the file " + "Documentation/feature-removal-schedule.txt " + "in the kernel source tree for more " + "details.\n"); + } + *crc = symversion(__start___kcrctab_gpl_future, + (ks - __start___ksymtab_gpl_future)); + return ks->value; } /* Now try modules. */ list_for_each_entry(mod, &modules, list) { *owner = mod; - for (i = 0; i < mod->num_syms; i++) - if (strcmp(mod->syms[i].name, name) == 0) { - *crc = symversion(mod->crcs, i); - return mod->syms[i].value; - } + ks = lookup_symbol(name, mod->syms, mod->syms + mod->num_syms); + if (ks) { + *crc = symversion(mod->crcs, (ks - mod->syms)); + return ks->value; + } if (gplok) { - for (i = 0; i < mod->num_gpl_syms; i++) { - if (strcmp(mod->gpl_syms[i].name, name) == 0) { - *crc = symversion(mod->gpl_crcs, i); - return mod->gpl_syms[i].value; - } + ks = lookup_symbol(name, mod->gpl_syms, + mod->gpl_syms + mod->num_gpl_syms); + if (ks) { + *crc = symversion(mod->gpl_crcs, + (ks - mod->gpl_syms)); + return ks->value; + } + } + ks = lookup_symbol(name, mod->gpl_future_syms, + (mod->gpl_future_syms + + mod->num_gpl_future_syms)); + if (ks) { + if (!gplok) { + printk(KERN_WARNING "Symbol %s is being used " + "by a non-GPL module, which will not " + "be allowed in the future\n", name); + printk(KERN_WARNING "Please see the file " + "Documentation/feature-removal-schedule.txt " + "in the kernel source tree for more " + "details.\n"); } + *crc = symversion(mod->gpl_future_crcs, + (ks - mod->gpl_future_syms)); + return ks->value; } } DEBUGP("Failed to find symbol %s\n", name); @@ -379,7 +429,6 @@ static inline void percpu_modcopy(void *pcpudst, const void *src, } #endif /* CONFIG_SMP */ -#ifdef CONFIG_MODULE_UNLOAD #define MODINFO_ATTR(field) \ static void setup_modinfo_##field(struct module *mod, const char *s) \ { \ @@ -411,12 +460,7 @@ static struct module_attribute modinfo_##field = { \ MODINFO_ATTR(version); MODINFO_ATTR(srcversion); -static struct module_attribute *modinfo_attrs[] = { - &modinfo_version, - &modinfo_srcversion, - NULL, -}; - +#ifdef CONFIG_MODULE_UNLOAD /* Init the unload section of the module. */ static void module_unload_init(struct module *mod) { @@ -731,6 +775,15 @@ static inline void module_unload_init(struct module *mod) } #endif /* CONFIG_MODULE_UNLOAD */ +static struct module_attribute *modinfo_attrs[] = { + &modinfo_version, + &modinfo_srcversion, +#ifdef CONFIG_MODULE_UNLOAD + &refcnt, +#endif + NULL, +}; + #ifdef CONFIG_OBSOLETE_MODPARM /* Bounds checking done below */ static int obsparm_copy_string(const char *val, struct kernel_param *kp) @@ -1056,37 +1109,28 @@ static inline void remove_sect_attrs(struct module *mod) } #endif /* CONFIG_KALLSYMS */ - -#ifdef CONFIG_MODULE_UNLOAD -static inline int module_add_refcnt_attr(struct module *mod) -{ - return sysfs_create_file(&mod->mkobj.kobj, &refcnt.attr); -} -static void module_remove_refcnt_attr(struct module *mod) -{ - return sysfs_remove_file(&mod->mkobj.kobj, &refcnt.attr); -} -#else -static inline int module_add_refcnt_attr(struct module *mod) -{ - return 0; -} -static void module_remove_refcnt_attr(struct module *mod) -{ -} -#endif - -#ifdef CONFIG_MODULE_UNLOAD static int module_add_modinfo_attrs(struct module *mod) { struct module_attribute *attr; + struct module_attribute *temp_attr; int error = 0; int i; + mod->modinfo_attrs = kzalloc((sizeof(struct module_attribute) * + (ARRAY_SIZE(modinfo_attrs) + 1)), + GFP_KERNEL); + if (!mod->modinfo_attrs) + return -ENOMEM; + + temp_attr = mod->modinfo_attrs; for (i = 0; (attr = modinfo_attrs[i]) && !error; i++) { if (!attr->test || - (attr->test && attr->test(mod))) - error = sysfs_create_file(&mod->mkobj.kobj,&attr->attr); + (attr->test && attr->test(mod))) { + memcpy(temp_attr, attr, sizeof(*temp_attr)); + temp_attr->attr.owner = mod; + error = sysfs_create_file(&mod->mkobj.kobj,&temp_attr->attr); + ++temp_attr; + } } return error; } @@ -1096,12 +1140,16 @@ static void module_remove_modinfo_attrs(struct module *mod) struct module_attribute *attr; int i; - for (i = 0; (attr = modinfo_attrs[i]); i++) { + for (i = 0; (attr = &mod->modinfo_attrs[i]); i++) { + /* pick a field to test for end of list */ + if (!attr->attr.name) + break; sysfs_remove_file(&mod->mkobj.kobj,&attr->attr); - attr->free(mod); + if (attr->free) + attr->free(mod); } + kfree(mod->modinfo_attrs); } -#endif static int mod_sysfs_setup(struct module *mod, struct kernel_param *kparam, @@ -1119,19 +1167,13 @@ static int mod_sysfs_setup(struct module *mod, if (err) goto out; - err = module_add_refcnt_attr(mod); - if (err) - goto out_unreg; - err = module_param_sysfs_setup(mod, kparam, num_params); if (err) goto out_unreg; -#ifdef CONFIG_MODULE_UNLOAD err = module_add_modinfo_attrs(mod); if (err) goto out_unreg; -#endif return 0; @@ -1143,10 +1185,7 @@ out: static void mod_kobject_remove(struct module *mod) { -#ifdef CONFIG_MODULE_UNLOAD module_remove_modinfo_attrs(mod); -#endif - module_remove_refcnt_attr(mod); module_param_sysfs_remove(mod); kobject_unregister(&mod->mkobj.kobj); @@ -1424,7 +1463,6 @@ static char *get_modinfo(Elf_Shdr *sechdrs, return NULL; } -#ifdef CONFIG_MODULE_UNLOAD static void setup_modinfo(struct module *mod, Elf_Shdr *sechdrs, unsigned int infoindex) { @@ -1439,23 +1477,17 @@ static void setup_modinfo(struct module *mod, Elf_Shdr *sechdrs, attr->attr.name)); } } -#endif #ifdef CONFIG_KALLSYMS int is_exported(const char *name, const struct module *mod) { - unsigned int i; - - if (!mod) { - for (i = 0; __start___ksymtab+i < __stop___ksymtab; i++) - if (strcmp(__start___ksymtab[i].name, name) == 0) - return 1; - return 0; - } - for (i = 0; i < mod->num_syms; i++) - if (strcmp(mod->syms[i].name, name) == 0) + if (!mod && lookup_symbol(name, __start___ksymtab, __stop___ksymtab)) + return 1; + else + if (lookup_symbol(name, mod->syms, mod->syms + mod->num_syms)) return 1; - return 0; + else + return 0; } /* As per nm */ @@ -1537,7 +1569,8 @@ static struct module *load_module(void __user *umod, char *secstrings, *args, *modmagic, *strtab = NULL; unsigned int i, symindex = 0, strindex = 0, setupindex, exindex, exportindex, modindex, obsparmindex, infoindex, gplindex, - crcindex, gplcrcindex, versindex, pcpuindex; + crcindex, gplcrcindex, versindex, pcpuindex, gplfutureindex, + gplfuturecrcindex; long arglen; struct module *mod; long err = 0; @@ -1618,8 +1651,10 @@ static struct module *load_module(void __user *umod, /* Optional sections */ exportindex = find_sec(hdr, sechdrs, secstrings, "__ksymtab"); gplindex = find_sec(hdr, sechdrs, secstrings, "__ksymtab_gpl"); + gplfutureindex = find_sec(hdr, sechdrs, secstrings, "__ksymtab_gpl_future"); crcindex = find_sec(hdr, sechdrs, secstrings, "__kcrctab"); gplcrcindex = find_sec(hdr, sechdrs, secstrings, "__kcrctab_gpl"); + gplfuturecrcindex = find_sec(hdr, sechdrs, secstrings, "__kcrctab_gpl_future"); setupindex = find_sec(hdr, sechdrs, secstrings, "__param"); exindex = find_sec(hdr, sechdrs, secstrings, "__ex_table"); obsparmindex = find_sec(hdr, sechdrs, secstrings, "__obsparm"); @@ -1755,10 +1790,8 @@ static struct module *load_module(void __user *umod, if (strcmp(mod->name, "driverloader") == 0) add_taint(TAINT_PROPRIETARY_MODULE); -#ifdef CONFIG_MODULE_UNLOAD /* Set up MODINFO_ATTR fields */ setup_modinfo(mod, sechdrs, infoindex); -#endif /* Fix up syms, so that st_value is a pointer to location. */ err = simplify_symbols(sechdrs, symindex, strtab, versindex, pcpuindex, @@ -1775,10 +1808,16 @@ static struct module *load_module(void __user *umod, mod->gpl_syms = (void *)sechdrs[gplindex].sh_addr; if (gplcrcindex) mod->gpl_crcs = (void *)sechdrs[gplcrcindex].sh_addr; + mod->num_gpl_future_syms = sechdrs[gplfutureindex].sh_size / + sizeof(*mod->gpl_future_syms); + mod->gpl_future_syms = (void *)sechdrs[gplfutureindex].sh_addr; + if (gplfuturecrcindex) + mod->gpl_future_crcs = (void *)sechdrs[gplfuturecrcindex].sh_addr; #ifdef CONFIG_MODVERSIONS if ((mod->num_syms && !crcindex) || - (mod->num_gpl_syms && !gplcrcindex)) { + (mod->num_gpl_syms && !gplcrcindex) || + (mod->num_gpl_future_syms && !gplfuturecrcindex)) { printk(KERN_WARNING "%s: No versions for exported symbols." " Tainting kernel.\n", mod->name); add_taint(TAINT_FORCED_MODULE); diff --git a/kernel/params.c b/kernel/params.c index c76ad25e6a21..a29150582310 100644 --- a/kernel/params.c +++ b/kernel/params.c @@ -638,13 +638,8 @@ static ssize_t module_attr_show(struct kobject *kobj, if (!attribute->show) return -EIO; - if (!try_module_get(mk->mod)) - return -ENODEV; - ret = attribute->show(attribute, mk->mod, buf); - module_put(mk->mod); - return ret; } @@ -662,13 +657,8 @@ static ssize_t module_attr_store(struct kobject *kobj, if (!attribute->store) return -EIO; - if (!try_module_get(mk->mod)) - return -ENODEV; - ret = attribute->store(attribute, mk->mod, buf, len); - module_put(mk->mod); - return ret; } diff --git a/kernel/posix-timers.c b/kernel/posix-timers.c index 216f574b5ffb..fa895fc2ecf5 100644 --- a/kernel/posix-timers.c +++ b/kernel/posix-timers.c @@ -353,6 +353,7 @@ static int posix_timer_fn(void *data) hrtimer_forward(&timr->it.real.timer, timr->it.real.interval); ret = HRTIMER_RESTART; + ++timr->it_requeue_pending; } } diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c index 0cf8146bd585..fedf5e369755 100644 --- a/kernel/rcupdate.c +++ b/kernel/rcupdate.c @@ -67,7 +67,43 @@ DEFINE_PER_CPU(struct rcu_data, rcu_bh_data) = { 0L }; /* Fake initialization required by compiler */ static DEFINE_PER_CPU(struct tasklet_struct, rcu_tasklet) = {NULL}; -static int maxbatch = 10000; +static int blimit = 10; +static int qhimark = 10000; +static int qlowmark = 100; +#ifdef CONFIG_SMP +static int rsinterval = 1000; +#endif + +static atomic_t rcu_barrier_cpu_count; +static struct semaphore rcu_barrier_sema; +static struct completion rcu_barrier_completion; + +#ifdef CONFIG_SMP +static void force_quiescent_state(struct rcu_data *rdp, + struct rcu_ctrlblk *rcp) +{ + int cpu; + cpumask_t cpumask; + set_need_resched(); + if (unlikely(rdp->qlen - rdp->last_rs_qlen > rsinterval)) { + rdp->last_rs_qlen = rdp->qlen; + /* + * Don't send IPI to itself. With irqs disabled, + * rdp->cpu is the current cpu. + */ + cpumask = rcp->cpumask; + cpu_clear(rdp->cpu, cpumask); + for_each_cpu_mask(cpu, cpumask) + smp_send_reschedule(cpu); + } +} +#else +static inline void force_quiescent_state(struct rcu_data *rdp, + struct rcu_ctrlblk *rcp) +{ + set_need_resched(); +} +#endif /** * call_rcu - Queue an RCU callback for invocation after a grace period. @@ -92,17 +128,13 @@ void fastcall call_rcu(struct rcu_head *head, rdp = &__get_cpu_var(rcu_data); *rdp->nxttail = head; rdp->nxttail = &head->next; - - if (unlikely(++rdp->count > 10000)) - set_need_resched(); - + if (unlikely(++rdp->qlen > qhimark)) { + rdp->blimit = INT_MAX; + force_quiescent_state(rdp, &rcu_ctrlblk); + } local_irq_restore(flags); } -static atomic_t rcu_barrier_cpu_count; -static struct semaphore rcu_barrier_sema; -static struct completion rcu_barrier_completion; - /** * call_rcu_bh - Queue an RCU for invocation after a quicker grace period. * @head: structure to be used for queueing the RCU updates. @@ -131,12 +163,12 @@ void fastcall call_rcu_bh(struct rcu_head *head, rdp = &__get_cpu_var(rcu_bh_data); *rdp->nxttail = head; rdp->nxttail = &head->next; - rdp->count++; -/* - * Should we directly call rcu_do_batch() here ? - * if (unlikely(rdp->count > 10000)) - * rcu_do_batch(rdp); - */ + + if (unlikely(++rdp->qlen > qhimark)) { + rdp->blimit = INT_MAX; + force_quiescent_state(rdp, &rcu_bh_ctrlblk); + } + local_irq_restore(flags); } @@ -199,10 +231,12 @@ static void rcu_do_batch(struct rcu_data *rdp) next = rdp->donelist = list->next; list->func(list); list = next; - rdp->count--; - if (++count >= maxbatch) + rdp->qlen--; + if (++count >= rdp->blimit) break; } + if (rdp->blimit == INT_MAX && rdp->qlen <= qlowmark) + rdp->blimit = blimit; if (!rdp->donelist) rdp->donetail = &rdp->donelist; else @@ -473,6 +507,7 @@ static void rcu_init_percpu_data(int cpu, struct rcu_ctrlblk *rcp, rdp->quiescbatch = rcp->completed; rdp->qs_pending = 0; rdp->cpu = cpu; + rdp->blimit = blimit; } static void __devinit rcu_online_cpu(int cpu) @@ -567,9 +602,14 @@ void synchronize_kernel(void) synchronize_rcu(); } -module_param(maxbatch, int, 0); +module_param(blimit, int, 0); +module_param(qhimark, int, 0); +module_param(qlowmark, int, 0); +#ifdef CONFIG_SMP +module_param(rsinterval, int, 0); +#endif EXPORT_SYMBOL_GPL(rcu_batches_completed); -EXPORT_SYMBOL(call_rcu); /* WARNING: GPL-only in April 2006. */ -EXPORT_SYMBOL(call_rcu_bh); /* WARNING: GPL-only in April 2006. */ +EXPORT_SYMBOL_GPL_FUTURE(call_rcu); /* WARNING: GPL-only in April 2006. */ +EXPORT_SYMBOL_GPL_FUTURE(call_rcu_bh); /* WARNING: GPL-only in April 2006. */ EXPORT_SYMBOL_GPL(synchronize_rcu); -EXPORT_SYMBOL(synchronize_kernel); /* WARNING: GPL-only in April 2006. */ +EXPORT_SYMBOL_GPL_FUTURE(synchronize_kernel); /* WARNING: GPL-only in April 2006. */ diff --git a/kernel/sched.c b/kernel/sched.c index 12d291bf3379..6b6e0d70eb30 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -178,13 +178,6 @@ static unsigned int task_timeslice(task_t *p) #define task_hot(p, now, sd) ((long long) ((now) - (p)->last_ran) \ < (long long) (sd)->cache_hot_time) -void __put_task_struct_cb(struct rcu_head *rhp) -{ - __put_task_struct(container_of(rhp, struct task_struct, rcu)); -} - -EXPORT_SYMBOL_GPL(__put_task_struct_cb); - /* * These are the runqueue data structures: */ @@ -714,12 +707,6 @@ static int recalc_task_prio(task_t *p, unsigned long long now) DEF_TIMESLICE); } else { /* - * The lower the sleep avg a task has the more - * rapidly it will rise with sleep time. - */ - sleep_time *= (MAX_BONUS - CURRENT_BONUS(p)) ? : 1; - - /* * Tasks waking from uninterruptible sleep are * limited in their sleep_avg rise as they * are likely to be waiting on I/O @@ -4028,6 +4015,8 @@ static inline void __cond_resched(void) */ if (unlikely(preempt_count())) return; + if (unlikely(system_state != SYSTEM_RUNNING)) + return; do { add_preempt_count(PREEMPT_ACTIVE); schedule(); @@ -4333,6 +4322,7 @@ void __devinit init_idle(task_t *idle, int cpu) runqueue_t *rq = cpu_rq(cpu); unsigned long flags; + idle->timestamp = sched_clock(); idle->sleep_avg = 0; idle->array = NULL; idle->prio = MAX_PRIO; diff --git a/kernel/softirq.c b/kernel/softirq.c index ad3295cdded5..ec8fed42a86f 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -16,6 +16,7 @@ #include <linux/cpu.h> #include <linux/kthread.h> #include <linux/rcupdate.h> +#include <linux/smp.h> #include <asm/irq.h> /* @@ -495,3 +496,22 @@ __init int spawn_ksoftirqd(void) register_cpu_notifier(&cpu_nfb); return 0; } + +#ifdef CONFIG_SMP +/* + * Call a function on all processors + */ +int on_each_cpu(void (*func) (void *info), void *info, int retry, int wait) +{ + int ret = 0; + + preempt_disable(); + ret = smp_call_function(func, info, retry, wait); + local_irq_disable(); + func(info); + local_irq_enable(); + preempt_enable(); + return ret; +} +EXPORT_SYMBOL(on_each_cpu); +#endif diff --git a/kernel/sysctl.c b/kernel/sysctl.c index c05a2b7125e1..32b48e8ee36e 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -50,6 +50,9 @@ #include <asm/uaccess.h> #include <asm/processor.h> +extern int proc_nr_files(ctl_table *table, int write, struct file *filp, + void __user *buffer, size_t *lenp, loff_t *ppos); + #if defined(CONFIG_SYSCTL) /* External variables not in a header file. */ @@ -124,6 +127,10 @@ extern int sysctl_hz_timer; extern int acct_parm[]; #endif +#ifdef CONFIG_IA64 +extern int no_unaligned_warning; +#endif + static int parse_table(int __user *, int, void __user *, size_t __user *, void __user *, size_t, ctl_table *, void **); static int proc_doutsstring(ctl_table *table, int write, struct file *filp, @@ -663,6 +670,16 @@ static ctl_table kern_table[] = { .data = &acpi_video_flags, .maxlen = sizeof (unsigned long), .mode = 0644, + .proc_handler = &proc_doulongvec_minmax, + }, +#endif +#ifdef CONFIG_IA64 + { + .ctl_name = KERN_IA64_UNALIGNED, + .procname = "ignore-unaligned-usertrap", + .data = &no_unaligned_warning, + .maxlen = sizeof (int), + .mode = 0644, .proc_handler = &proc_dointvec, }, #endif @@ -929,7 +946,7 @@ static ctl_table fs_table[] = { .data = &files_stat, .maxlen = 3*sizeof(int), .mode = 0444, - .proc_handler = &proc_dointvec, + .proc_handler = &proc_nr_files, }, { .ctl_name = FS_MAXFILE, diff --git a/kernel/timer.c b/kernel/timer.c index fe3a9a9f8328..2410c18dbeb1 100644 --- a/kernel/timer.c +++ b/kernel/timer.c @@ -489,9 +489,21 @@ unsigned long next_timer_interrupt(void) struct list_head *list; struct timer_list *nte; unsigned long expires; + unsigned long hr_expires = MAX_JIFFY_OFFSET; + ktime_t hr_delta; tvec_t *varray[4]; int i, j; + hr_delta = hrtimer_get_next_event(); + if (hr_delta.tv64 != KTIME_MAX) { + struct timespec tsdelta; + tsdelta = ktime_to_timespec(hr_delta); + hr_expires = timespec_to_jiffies(&tsdelta); + if (hr_expires < 3) + return hr_expires + jiffies; + } + hr_expires += jiffies; + base = &__get_cpu_var(tvec_bases); spin_lock(&base->t_base.lock); expires = base->timer_jiffies + (LONG_MAX >> 1); @@ -542,6 +554,10 @@ found: } } spin_unlock(&base->t_base.lock); + + if (time_before(hr_expires, expires)) + return hr_expires; + return expires; } #endif @@ -925,6 +941,8 @@ static inline void update_times(void) void do_timer(struct pt_regs *regs) { jiffies_64++; + /* prevent loading jiffies before storing new jiffies_64 value. */ + barrier(); update_times(); softlockup_tick(regs); } @@ -1336,8 +1354,8 @@ void __init init_timers(void) #ifdef CONFIG_TIME_INTERPOLATION -struct time_interpolator *time_interpolator; -static struct time_interpolator *time_interpolator_list; +struct time_interpolator *time_interpolator __read_mostly; +static struct time_interpolator *time_interpolator_list __read_mostly; static DEFINE_SPINLOCK(time_interpolator_lock); static inline u64 time_interpolator_get_cycles(unsigned int src) @@ -1351,10 +1369,10 @@ static inline u64 time_interpolator_get_cycles(unsigned int src) return x(); case TIME_SOURCE_MMIO64 : - return readq((void __iomem *) time_interpolator->addr); + return readq_relaxed((void __iomem *)time_interpolator->addr); case TIME_SOURCE_MMIO32 : - return readl((void __iomem *) time_interpolator->addr); + return readl_relaxed((void __iomem *)time_interpolator->addr); default: return get_cycles(); } diff --git a/kernel/workqueue.c b/kernel/workqueue.c index b052e2c4c710..e9e464a90376 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -27,6 +27,7 @@ #include <linux/cpu.h> #include <linux/notifier.h> #include <linux/kthread.h> +#include <linux/hardirq.h> /* * The per-CPU workqueue (if single thread, we always use the first @@ -476,6 +477,34 @@ void cancel_rearming_delayed_work(struct work_struct *work) } EXPORT_SYMBOL(cancel_rearming_delayed_work); +/** + * execute_in_process_context - reliably execute the routine with user context + * @fn: the function to execute + * @data: data to pass to the function + * @ew: guaranteed storage for the execute work structure (must + * be available when the work executes) + * + * Executes the function immediately if process context is available, + * otherwise schedules the function for delayed execution. + * + * Returns: 0 - function was executed + * 1 - function was scheduled for execution + */ +int execute_in_process_context(void (*fn)(void *data), void *data, + struct execute_work *ew) +{ + if (!in_interrupt()) { + fn(data); + return 0; + } + + INIT_WORK(&ew->work, fn, data); + schedule_work(&ew->work); + + return 1; +} +EXPORT_SYMBOL_GPL(execute_in_process_context); + int keventd_up(void) { return keventd_wq != NULL; |