diff options
Diffstat (limited to 'kernel')
41 files changed, 683 insertions, 578 deletions
diff --git a/kernel/Kconfig.instrumentation b/kernel/Kconfig.instrumentation index f5f2c769d95e..468f47ad7503 100644 --- a/kernel/Kconfig.instrumentation +++ b/kernel/Kconfig.instrumentation @@ -20,8 +20,8 @@ config PROFILING config OPROFILE tristate "OProfile system profiling (EXPERIMENTAL)" - depends on PROFILING - depends on ALPHA || ARM || BLACKFIN || X86_32 || IA64 || M32R || MIPS || PARISC || PPC || S390 || SUPERH || SPARC || X86_64 + depends on PROFILING && !UML + depends on ARCH_SUPPORTS_OPROFILE || ALPHA || ARM || BLACKFIN || IA64 || M32R || PARISC || PPC || S390 || SUPERH || SPARC help OProfile is a profiling system capable of profiling the whole system, include the kernel, kernel modules, libraries, @@ -31,7 +31,7 @@ config OPROFILE config KPROBES bool "Kprobes" - depends on KALLSYMS && MODULES + depends on KALLSYMS && MODULES && !UML depends on X86_32 || IA64 || PPC || S390 || SPARC64 || X86_64 || AVR32 help Kprobes allows you to trap at almost any kernel address and diff --git a/kernel/acct.c b/kernel/acct.c index fce53d8df8a7..521dfa53cb99 100644 --- a/kernel/acct.c +++ b/kernel/acct.c @@ -413,7 +413,7 @@ static u32 encode_float(u64 value) * The acct_process() call is the workhorse of the process * accounting system. The struct acct is built here and then written * into the accounting file. This function should only be called from - * do_exit(). + * do_exit() or when switching to a different output file. */ /* @@ -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/exit.c b/kernel/exit.c index cd0f1d4137a7..549c0558ba68 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -1357,7 +1357,7 @@ static int wait_task_stopped(struct task_struct *p, int delayed_group_leader, int __user *stat_addr, struct rusage __user *ru) { int retval, exit_code; - struct pid_namespace *ns; + pid_t pid; if (!p->exit_code) return 0; @@ -1376,12 +1376,11 @@ static int wait_task_stopped(struct task_struct *p, int delayed_group_leader, * keep holding onto the tasklist_lock while we call getrusage and * possibly take page faults for user memory. */ - ns = current->nsproxy->pid_ns; + pid = task_pid_nr_ns(p, current->nsproxy->pid_ns); get_task_struct(p); read_unlock(&tasklist_lock); if (unlikely(noreap)) { - pid_t pid = task_pid_nr_ns(p, ns); uid_t uid = p->uid; int why = (p->ptrace & PT_PTRACED) ? CLD_TRAPPED : CLD_STOPPED; @@ -1389,7 +1388,7 @@ static int wait_task_stopped(struct task_struct *p, int delayed_group_leader, if (unlikely(!exit_code) || unlikely(p->exit_state)) goto bail_ref; return wait_noreap_copyout(p, pid, uid, - why, (exit_code << 8) | 0x7f, + why, exit_code, infop, ru); } @@ -1451,11 +1450,11 @@ bail_ref: if (!retval && infop) retval = put_user(exit_code, &infop->si_status); if (!retval && infop) - retval = put_user(task_pid_nr_ns(p, ns), &infop->si_pid); + retval = put_user(pid, &infop->si_pid); if (!retval && infop) retval = put_user(p->uid, &infop->si_uid); if (!retval) - retval = task_pid_nr_ns(p, ns); + retval = pid; put_task_struct(p); BUG_ON(!retval); diff --git a/kernel/fork.c b/kernel/fork.c index 8ca1a14cdc8c..8dd8ff281009 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1292,23 +1292,14 @@ static struct task_struct *copy_process(unsigned long clone_flags, __ptrace_link(p, current->parent); if (thread_group_leader(p)) { - if (clone_flags & CLONE_NEWPID) { + if (clone_flags & CLONE_NEWPID) p->nsproxy->pid_ns->child_reaper = p; - p->signal->tty = NULL; - set_task_pgrp(p, p->pid); - set_task_session(p, p->pid); - attach_pid(p, PIDTYPE_PGID, pid); - attach_pid(p, PIDTYPE_SID, pid); - } else { - p->signal->tty = current->signal->tty; - set_task_pgrp(p, task_pgrp_nr(current)); - set_task_session(p, task_session_nr(current)); - attach_pid(p, PIDTYPE_PGID, - task_pgrp(current)); - attach_pid(p, PIDTYPE_SID, - task_session(current)); - } + p->signal->tty = current->signal->tty; + set_task_pgrp(p, task_pgrp_nr(current)); + set_task_session(p, task_session_nr(current)); + attach_pid(p, PIDTYPE_PGID, task_pgrp(current)); + attach_pid(p, PIDTYPE_SID, task_session(current)); list_add_tail_rcu(&p->tasks, &init_task.tasks); __get_cpu_var(process_counts)++; } diff --git a/kernel/futex.c b/kernel/futex.c index 9dc591ab681a..db9824de8bf0 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -658,7 +658,7 @@ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_q *this) if (curval == -EFAULT) ret = -EFAULT; - if (curval != uval) + else if (curval != uval) ret = -EINVAL; if (ret) { spin_unlock(&pi_state->pi_mutex.wait_lock); @@ -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 @@ -1149,9 +1149,9 @@ static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q, /* * In case we must use restart_block to restart a futex_wait, - * we encode in the 'arg3' shared capability + * we encode in the 'flags' shared capability */ -#define ARG3_SHARED 1 +#define FLAGS_SHARED 1 static long futex_wait_restart(struct restart_block *restart); @@ -1290,12 +1290,13 @@ static int futex_wait(u32 __user *uaddr, struct rw_semaphore *fshared, struct restart_block *restart; restart = ¤t_thread_info()->restart_block; restart->fn = futex_wait_restart; - restart->arg0 = (unsigned long)uaddr; - restart->arg1 = (unsigned long)val; - restart->arg2 = (unsigned long)abs_time; - restart->arg3 = 0; + restart->futex.uaddr = (u32 *)uaddr; + restart->futex.val = val; + restart->futex.time = abs_time->tv64; + restart->futex.flags = 0; + if (fshared) - restart->arg3 |= ARG3_SHARED; + restart->futex.flags |= FLAGS_SHARED; return -ERESTART_RESTARTBLOCK; } @@ -1310,15 +1311,15 @@ static int futex_wait(u32 __user *uaddr, struct rw_semaphore *fshared, static long futex_wait_restart(struct restart_block *restart) { - u32 __user *uaddr = (u32 __user *)restart->arg0; - u32 val = (u32)restart->arg1; - ktime_t *abs_time = (ktime_t *)restart->arg2; + u32 __user *uaddr = (u32 __user *)restart->futex.uaddr; struct rw_semaphore *fshared = NULL; + ktime_t t; + t.tv64 = restart->futex.time; restart->fn = do_no_restart_syscall; - if (restart->arg3 & ARG3_SHARED) + if (restart->futex.flags & FLAGS_SHARED) fshared = ¤t->mm->mmap_sem; - return (long)futex_wait(uaddr, fshared, val, abs_time); + return (long)futex_wait(uaddr, fshared, restart->futex.val, &t); } @@ -1507,9 +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/hrtimer.c b/kernel/hrtimer.c index 22a25142e4cf..f994bb8065e6 100644 --- a/kernel/hrtimer.c +++ b/kernel/hrtimer.c @@ -850,6 +850,14 @@ hrtimer_start(struct hrtimer *timer, ktime_t tim, const enum hrtimer_mode mode) #ifdef CONFIG_TIME_LOW_RES tim = ktime_add(tim, base->resolution); #endif + /* + * Careful here: User space might have asked for a + * very long sleep, so the add above might result in a + * negative number, which enqueues the timer in front + * of the queue. + */ + if (tim.tv64 < 0) + tim.tv64 = KTIME_MAX; } timer->expires = tim; @@ -1370,7 +1378,7 @@ sys_nanosleep(struct timespec __user *rqtp, struct timespec __user *rmtp) /* * Functions related to boot-time initialization: */ -static void __devinit init_hrtimers_cpu(int cpu) +static void __cpuinit init_hrtimers_cpu(int cpu) { struct hrtimer_cpu_base *cpu_base = &per_cpu(hrtimer_bases, cpu); int i; diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index 9b5dff6b3f6a..44019ce30a14 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/kallsyms.c b/kernel/kallsyms.c index 474219a41929..2fc25810509e 100644 --- a/kernel/kallsyms.c +++ b/kernel/kallsyms.c @@ -32,9 +32,14 @@ /* These will be re-linked against their real values during the second link stage */ extern const unsigned long kallsyms_addresses[] __attribute__((weak)); -extern const unsigned long kallsyms_num_syms __attribute__((weak)); extern const u8 kallsyms_names[] __attribute__((weak)); +/* tell the compiler that the count isn't in the small data section if the arch + * has one (eg: FRV) + */ +extern const unsigned long kallsyms_num_syms +__attribute__((weak, section(".rodata"))); + extern const u8 kallsyms_token_table[] __attribute__((weak)); extern const u16 kallsyms_token_index[] __attribute__((weak)); diff --git a/kernel/kexec.c b/kernel/kexec.c index aa74a1ef2da8..9a26eec9eb04 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/kmod.c b/kernel/kmod.c index c6a4f8aebeba..bb7df2a28bd7 100644 --- a/kernel/kmod.c +++ b/kernel/kmod.c @@ -451,13 +451,11 @@ int call_usermodehelper_exec(struct subprocess_info *sub_info, enum umh_wait wait) { DECLARE_COMPLETION_ONSTACK(done); - int retval; + int retval = 0; helper_lock(); - if (sub_info->path[0] == '\0') { - retval = 0; + if (sub_info->path[0] == '\0') goto out; - } if (!khelper_wq || usermodehelper_disabled) { retval = -EBUSY; @@ -468,13 +466,14 @@ int call_usermodehelper_exec(struct subprocess_info *sub_info, sub_info->wait = wait; queue_work(khelper_wq, &sub_info->work); - if (wait == UMH_NO_WAIT) /* task has freed sub_info */ - return 0; + if (wait == UMH_NO_WAIT) /* task has freed sub_info */ + goto unlock; wait_for_completion(&done); retval = sub_info->retval; - out: +out: call_usermodehelper_freeinfo(sub_info); +unlock: helper_unlock(); return retval; } diff --git a/kernel/ksysfs.c b/kernel/ksysfs.c index 65daa5373ca6..e53bc30e9ba5 100644 --- a/kernel/ksysfs.c +++ b/kernel/ksysfs.c @@ -17,30 +17,34 @@ #include <linux/sched.h> #define KERNEL_ATTR_RO(_name) \ -static struct subsys_attribute _name##_attr = __ATTR_RO(_name) +static struct kobj_attribute _name##_attr = __ATTR_RO(_name) #define KERNEL_ATTR_RW(_name) \ -static struct subsys_attribute _name##_attr = \ +static struct kobj_attribute _name##_attr = \ __ATTR(_name, 0644, _name##_show, _name##_store) #if defined(CONFIG_HOTPLUG) && defined(CONFIG_NET) /* current uevent sequence number */ -static ssize_t uevent_seqnum_show(struct kset *kset, char *page) +static ssize_t uevent_seqnum_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) { - return sprintf(page, "%llu\n", (unsigned long long)uevent_seqnum); + return sprintf(buf, "%llu\n", (unsigned long long)uevent_seqnum); } KERNEL_ATTR_RO(uevent_seqnum); /* uevent helper program, used during early boo */ -static ssize_t uevent_helper_show(struct kset *kset, char *page) +static ssize_t uevent_helper_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) { - return sprintf(page, "%s\n", uevent_helper); + return sprintf(buf, "%s\n", uevent_helper); } -static ssize_t uevent_helper_store(struct kset *kset, const char *page, size_t count) +static ssize_t uevent_helper_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t count) { if (count+1 > UEVENT_HELPER_PATH_LEN) return -ENOENT; - memcpy(uevent_helper, page, count); + memcpy(uevent_helper, buf, count); uevent_helper[count] = '\0'; if (count && uevent_helper[count-1] == '\n') uevent_helper[count-1] = '\0'; @@ -50,21 +54,24 @@ KERNEL_ATTR_RW(uevent_helper); #endif #ifdef CONFIG_KEXEC -static ssize_t kexec_loaded_show(struct kset *kset, char *page) +static ssize_t kexec_loaded_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) { - return sprintf(page, "%d\n", !!kexec_image); + return sprintf(buf, "%d\n", !!kexec_image); } KERNEL_ATTR_RO(kexec_loaded); -static ssize_t kexec_crash_loaded_show(struct kset *kset, char *page) +static ssize_t kexec_crash_loaded_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) { - return sprintf(page, "%d\n", !!kexec_crash_image); + return sprintf(buf, "%d\n", !!kexec_crash_image); } KERNEL_ATTR_RO(kexec_crash_loaded); -static ssize_t vmcoreinfo_show(struct kset *kset, char *page) +static ssize_t vmcoreinfo_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) { - return sprintf(page, "%lx %x\n", + return sprintf(buf, "%lx %x\n", paddr_vmcoreinfo_note(), (unsigned int)vmcoreinfo_max_size); } @@ -94,8 +101,8 @@ static struct bin_attribute notes_attr = { .read = ¬es_read, }; -decl_subsys(kernel, NULL, NULL); -EXPORT_SYMBOL_GPL(kernel_subsys); +struct kobject *kernel_kobj; +EXPORT_SYMBOL_GPL(kernel_kobj); static struct attribute * kernel_attrs[] = { #if defined(CONFIG_HOTPLUG) && defined(CONFIG_NET) @@ -116,24 +123,39 @@ static struct attribute_group kernel_attr_group = { static int __init ksysfs_init(void) { - int error = subsystem_register(&kernel_subsys); - if (!error) - error = sysfs_create_group(&kernel_subsys.kobj, - &kernel_attr_group); + int error; - if (!error && notes_size > 0) { - notes_attr.size = notes_size; - error = sysfs_create_bin_file(&kernel_subsys.kobj, - ¬es_attr); + kernel_kobj = kobject_create_and_add("kernel", NULL); + if (!kernel_kobj) { + error = -ENOMEM; + goto exit; } + error = sysfs_create_group(kernel_kobj, &kernel_attr_group); + if (error) + goto kset_exit; - /* - * Create "/sys/kernel/uids" directory and corresponding root user's - * directory under it. - */ - if (!error) - error = uids_kobject_init(); + if (notes_size > 0) { + notes_attr.size = notes_size; + error = sysfs_create_bin_file(kernel_kobj, ¬es_attr); + if (error) + goto group_exit; + } + /* create the /sys/kernel/uids/ directory */ + error = uids_sysfs_init(); + if (error) + goto notes_exit; + + return 0; + +notes_exit: + if (notes_size > 0) + sysfs_remove_bin_file(kernel_kobj, ¬es_attr); +group_exit: + sysfs_remove_group(kernel_kobj, &kernel_attr_group); +kset_exit: + kobject_put(kernel_kobj); +exit: return error; } diff --git a/kernel/lockdep.c b/kernel/lockdep.c index ed38bbfc48a3..e2c07ece367d 100644 --- a/kernel/lockdep.c +++ b/kernel/lockdep.c @@ -2654,10 +2654,15 @@ static void check_flags(unsigned long flags) if (!debug_locks) return; - if (irqs_disabled_flags(flags)) - DEBUG_LOCKS_WARN_ON(current->hardirqs_enabled); - else - DEBUG_LOCKS_WARN_ON(!current->hardirqs_enabled); + if (irqs_disabled_flags(flags)) { + if (DEBUG_LOCKS_WARN_ON(current->hardirqs_enabled)) { + printk("possible reason: unannotated irqs-off.\n"); + } + } else { + if (DEBUG_LOCKS_WARN_ON(!current->hardirqs_enabled)) { + printk("possible reason: unannotated irqs-on.\n"); + } + } /* * We dont accurately track softirq state in e.g. @@ -2927,7 +2932,7 @@ static void zap_class(struct lock_class *class) } -static inline int within(void *addr, void *start, unsigned long size) +static inline int within(const void *addr, void *start, unsigned long size) { return addr >= start && addr < start + size; } @@ -2938,9 +2943,10 @@ void lockdep_free_key_range(void *start, unsigned long size) struct list_head *head; unsigned long flags; int i; + int locked; raw_local_irq_save(flags); - graph_lock(); + locked = graph_lock(); /* * Unhash all classes that were created by this module: @@ -2949,12 +2955,16 @@ void lockdep_free_key_range(void *start, unsigned long size) head = classhash_table + i; if (list_empty(head)) continue; - list_for_each_entry_safe(class, next, head, hash_entry) + list_for_each_entry_safe(class, next, head, hash_entry) { if (within(class->key, start, size)) zap_class(class); + else if (within(class->name, start, size)) + zap_class(class); + } } - graph_unlock(); + if (locked) + graph_unlock(); raw_local_irq_restore(flags); } @@ -2964,6 +2974,7 @@ void lockdep_reset_lock(struct lockdep_map *lock) struct list_head *head; unsigned long flags; int i, j; + int locked; raw_local_irq_save(flags); @@ -2982,7 +2993,7 @@ void lockdep_reset_lock(struct lockdep_map *lock) * Debug check: in the end all mapped classes should * be gone. */ - graph_lock(); + locked = graph_lock(); for (i = 0; i < CLASSHASH_SIZE; i++) { head = classhash_table + i; if (list_empty(head)) @@ -2995,7 +3006,8 @@ void lockdep_reset_lock(struct lockdep_map *lock) } } } - graph_unlock(); + if (locked) + graph_unlock(); out_restore: raw_local_irq_restore(flags); @@ -3054,11 +3066,6 @@ void __init lockdep_info(void) #endif } -static inline int in_range(const void *start, const void *addr, const void *end) -{ - return addr >= start && addr <= end; -} - static void print_freed_lock_bug(struct task_struct *curr, const void *mem_from, const void *mem_to, struct held_lock *hlock) @@ -3080,6 +3087,13 @@ print_freed_lock_bug(struct task_struct *curr, const void *mem_from, dump_stack(); } +static inline int not_in_range(const void* mem_from, unsigned long mem_len, + const void* lock_from, unsigned long lock_len) +{ + return lock_from + lock_len <= mem_from || + mem_from + mem_len <= lock_from; +} + /* * Called when kernel memory is freed (or unmapped), or if a lock * is destroyed or reinitialized - this code checks whether there is @@ -3087,7 +3101,6 @@ print_freed_lock_bug(struct task_struct *curr, const void *mem_from, */ void debug_check_no_locks_freed(const void *mem_from, unsigned long mem_len) { - const void *mem_to = mem_from + mem_len, *lock_from, *lock_to; struct task_struct *curr = current; struct held_lock *hlock; unsigned long flags; @@ -3100,14 +3113,11 @@ void debug_check_no_locks_freed(const void *mem_from, unsigned long mem_len) for (i = 0; i < curr->lockdep_depth; i++) { hlock = curr->held_locks + i; - lock_from = (void *)hlock->instance; - lock_to = (void *)(hlock->instance + 1); - - if (!in_range(mem_from, lock_from, mem_to) && - !in_range(mem_from, lock_to, mem_to)) + if (not_in_range(mem_from, mem_len, hlock->instance, + sizeof(*hlock->instance))) continue; - print_freed_lock_bug(curr, mem_from, mem_to, hlock); + print_freed_lock_bug(curr, mem_from, mem_from + mem_len, hlock); break; } local_irq_restore(flags); @@ -3173,6 +3183,13 @@ retry: printk(" locked it.\n"); do_each_thread(g, p) { + /* + * It's not reliable to print a task's held locks + * if it's not sleeping (or if it's not the current + * task): + */ + if (p->state == TASK_RUNNING && p != current) + continue; if (p->lockdep_depth) lockdep_print_held_locks(p); if (!unlock) diff --git a/kernel/module.c b/kernel/module.c index 3202c9950073..dcb8a2cbf75e 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -47,8 +47,6 @@ #include <asm/cacheflush.h> #include <linux/license.h> -extern int module_sysfs_initialized; - #if 0 #define DEBUGP printk #else @@ -81,7 +79,8 @@ int unregister_module_notifier(struct notifier_block * nb) } EXPORT_SYMBOL(unregister_module_notifier); -/* We require a truly strong try_module_get() */ +/* We require a truly strong try_module_get(): 0 means failure due to + ongoing or failed initialization etc. */ static inline int strong_try_module_get(struct module *mod) { if (mod && mod->state == MODULE_STATE_COMING) @@ -952,7 +951,8 @@ static unsigned long resolve_symbol(Elf_Shdr *sechdrs, ret = __find_symbol(name, &owner, &crc, !(mod->taints & TAINT_PROPRIETARY_MODULE)); if (ret) { - /* use_module can fail due to OOM, or module unloading */ + /* use_module can fail due to OOM, + or module initialization or unloading */ if (!check_version(sechdrs, versindex, name, mod, crc) || !use_module(mod, owner)) ret = 0; @@ -1120,7 +1120,7 @@ static void add_notes_attrs(struct module *mod, unsigned int nsect, ++loaded; } - notes_attrs->dir = kobject_add_dir(&mod->mkobj.kobj, "notes"); + notes_attrs->dir = kobject_create_and_add("notes", &mod->mkobj.kobj); if (!notes_attrs->dir) goto out; @@ -1217,15 +1217,16 @@ int mod_sysfs_init(struct module *mod) err = -EINVAL; goto out; } - memset(&mod->mkobj.kobj, 0, sizeof(mod->mkobj.kobj)); - err = kobject_set_name(&mod->mkobj.kobj, "%s", mod->name); - if (err) - goto out; - kobj_set_kset_s(&mod->mkobj, module_subsys); mod->mkobj.mod = mod; - kobject_init(&mod->mkobj.kobj); + memset(&mod->mkobj.kobj, 0, sizeof(mod->mkobj.kobj)); + mod->mkobj.kobj.kset = module_kset; + err = kobject_init_and_add(&mod->mkobj.kobj, &module_ktype, NULL, + "%s", mod->name); + if (err) + kobject_put(&mod->mkobj.kobj); + /* delay uevent until full sysfs population */ out: return err; } @@ -1236,12 +1237,7 @@ int mod_sysfs_setup(struct module *mod, { int err; - /* delay uevent until full sysfs population */ - err = kobject_add(&mod->mkobj.kobj); - if (err) - goto out; - - mod->holders_dir = kobject_add_dir(&mod->mkobj.kobj, "holders"); + mod->holders_dir = kobject_create_and_add("holders", &mod->mkobj.kobj); if (!mod->holders_dir) { err = -ENOMEM; goto out_unreg; @@ -1261,11 +1257,9 @@ int mod_sysfs_setup(struct module *mod, out_unreg_param: module_param_sysfs_remove(mod); out_unreg_holders: - kobject_unregister(mod->holders_dir); + kobject_put(mod->holders_dir); out_unreg: - kobject_del(&mod->mkobj.kobj); kobject_put(&mod->mkobj.kobj); -out: return err; } #endif @@ -1274,9 +1268,9 @@ static void mod_kobject_remove(struct module *mod) { module_remove_modinfo_attrs(mod); module_param_sysfs_remove(mod); - kobject_unregister(mod->mkobj.drivers_dir); - kobject_unregister(mod->holders_dir); - kobject_unregister(&mod->mkobj.kobj); + kobject_put(mod->mkobj.drivers_dir); + kobject_put(mod->holders_dir); + kobject_put(&mod->mkobj.kobj); } /* @@ -1369,7 +1363,7 @@ dup: return ret; } -/* Change all symbols so that sh_value encodes the pointer directly. */ +/* Change all symbols so that st_value encodes the pointer directly. */ static int simplify_symbols(Elf_Shdr *sechdrs, unsigned int symindex, const char *strtab, @@ -1882,10 +1876,10 @@ static struct module *load_module(void __user *umod, /* Now we've moved module, initialize linked lists, etc. */ module_unload_init(mod); - /* Initialize kobject, so we can reference it. */ + /* add kobject, so we can reference it. */ err = mod_sysfs_init(mod); if (err) - goto cleanup; + goto free_unload; /* Set up license info based on the info section */ set_license(mod, get_modinfo(sechdrs, infoindex, "license")); @@ -2055,6 +2049,9 @@ static struct module *load_module(void __user *umod, arch_cleanup: module_arch_cleanup(mod); cleanup: + kobject_del(&mod->mkobj.kobj); + kobject_put(&mod->mkobj.kobj); + free_unload: module_unload_free(mod); module_free(mod, mod->module_init); free_core: @@ -2212,29 +2209,34 @@ static const char *get_ksymbol(struct module *mod, /* For kallsyms to ask for address resolution. NULL means not found. We don't lock, as this is used for oops resolution and races are a lesser concern. */ +/* FIXME: Risky: returns a pointer into a module w/o lock */ const char *module_address_lookup(unsigned long addr, unsigned long *size, unsigned long *offset, char **modname) { struct module *mod; + const char *ret = NULL; + preempt_disable(); list_for_each_entry(mod, &modules, list) { if (within(addr, mod->module_init, mod->init_size) || within(addr, mod->module_core, mod->core_size)) { if (modname) *modname = mod->name; - return get_ksymbol(mod, addr, size, offset); + ret = get_ksymbol(mod, addr, size, offset); + break; } } - return NULL; + preempt_enable(); + return ret; } int lookup_module_symbol_name(unsigned long addr, char *symname) { struct module *mod; - mutex_lock(&module_mutex); + preempt_disable(); list_for_each_entry(mod, &modules, list) { if (within(addr, mod->module_init, mod->init_size) || within(addr, mod->module_core, mod->core_size)) { @@ -2244,12 +2246,12 @@ int lookup_module_symbol_name(unsigned long addr, char *symname) if (!sym) goto out; strlcpy(symname, sym, KSYM_NAME_LEN); - mutex_unlock(&module_mutex); + preempt_enable(); return 0; } } out: - mutex_unlock(&module_mutex); + preempt_enable(); return -ERANGE; } @@ -2258,7 +2260,7 @@ int lookup_module_symbol_attrs(unsigned long addr, unsigned long *size, { struct module *mod; - mutex_lock(&module_mutex); + preempt_disable(); list_for_each_entry(mod, &modules, list) { if (within(addr, mod->module_init, mod->init_size) || within(addr, mod->module_core, mod->core_size)) { @@ -2271,12 +2273,12 @@ int lookup_module_symbol_attrs(unsigned long addr, unsigned long *size, strlcpy(modname, mod->name, MODULE_NAME_LEN); if (name) strlcpy(name, sym, KSYM_NAME_LEN); - mutex_unlock(&module_mutex); + preempt_enable(); return 0; } } out: - mutex_unlock(&module_mutex); + preempt_enable(); return -ERANGE; } @@ -2285,7 +2287,7 @@ int module_get_kallsym(unsigned int symnum, unsigned long *value, char *type, { struct module *mod; - mutex_lock(&module_mutex); + preempt_disable(); list_for_each_entry(mod, &modules, list) { if (symnum < mod->num_symtab) { *value = mod->symtab[symnum].st_value; @@ -2294,12 +2296,12 @@ int module_get_kallsym(unsigned int symnum, unsigned long *value, char *type, KSYM_NAME_LEN); strlcpy(module_name, mod->name, MODULE_NAME_LEN); *exported = is_exported(name, mod); - mutex_unlock(&module_mutex); + preempt_enable(); return 0; } symnum -= mod->num_symtab; } - mutex_unlock(&module_mutex); + preempt_enable(); return -ERANGE; } @@ -2322,6 +2324,7 @@ unsigned long module_kallsyms_lookup_name(const char *name) unsigned long ret = 0; /* Don't lock: we're in enough trouble already. */ + preempt_disable(); if ((colon = strchr(name, ':')) != NULL) { *colon = '\0'; if ((mod = find_module(name)) != NULL) @@ -2332,6 +2335,7 @@ unsigned long module_kallsyms_lookup_name(const char *name) if ((ret = mod_find_symname(mod, name)) != 0) break; } + preempt_enable(); return ret; } #endif /* CONFIG_KALLSYMS */ @@ -2493,93 +2497,6 @@ void print_modules(void) printk("\n"); } -#ifdef CONFIG_SYSFS -static char *make_driver_name(struct device_driver *drv) -{ - char *driver_name; - - driver_name = kmalloc(strlen(drv->name) + strlen(drv->bus->name) + 2, - GFP_KERNEL); - if (!driver_name) - return NULL; - - sprintf(driver_name, "%s:%s", drv->bus->name, drv->name); - return driver_name; -} - -static void module_create_drivers_dir(struct module_kobject *mk) -{ - if (!mk || mk->drivers_dir) - return; - - mk->drivers_dir = kobject_add_dir(&mk->kobj, "drivers"); -} - -void module_add_driver(struct module *mod, struct device_driver *drv) -{ - char *driver_name; - int no_warn; - struct module_kobject *mk = NULL; - - if (!drv) - return; - - if (mod) - mk = &mod->mkobj; - else if (drv->mod_name) { - struct kobject *mkobj; - - /* Lookup built-in module entry in /sys/modules */ - mkobj = kset_find_obj(&module_subsys, drv->mod_name); - if (mkobj) { - mk = container_of(mkobj, struct module_kobject, kobj); - /* remember our module structure */ - drv->mkobj = mk; - /* kset_find_obj took a reference */ - kobject_put(mkobj); - } - } - - if (!mk) - return; - - /* Don't check return codes; these calls are idempotent */ - no_warn = sysfs_create_link(&drv->kobj, &mk->kobj, "module"); - driver_name = make_driver_name(drv); - if (driver_name) { - module_create_drivers_dir(mk); - no_warn = sysfs_create_link(mk->drivers_dir, &drv->kobj, - driver_name); - kfree(driver_name); - } -} -EXPORT_SYMBOL(module_add_driver); - -void module_remove_driver(struct device_driver *drv) -{ - struct module_kobject *mk = NULL; - char *driver_name; - - if (!drv) - return; - - sysfs_remove_link(&drv->kobj, "module"); - - if (drv->owner) - mk = &drv->owner->mkobj; - else if (drv->mkobj) - mk = drv->mkobj; - if (mk && mk->drivers_dir) { - driver_name = make_driver_name(drv); - if (driver_name) { - sysfs_remove_link(mk->drivers_dir, driver_name); - kfree(driver_name); - } - } -} -EXPORT_SYMBOL(module_remove_driver); -#endif - #ifdef CONFIG_MODVERSIONS /* Generate the signature for struct module here, too, for modversions. */ void struct_module(struct module *mod) { return; } diff --git a/kernel/panic.c b/kernel/panic.c index 6f6e03e91595..da4d6bac270e 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 2a4c51487e72..b4da9505f4d2 100644 --- a/kernel/params.c +++ b/kernel/params.c @@ -560,11 +560,10 @@ static void __init kernel_param_sysfs_setup(const char *name, BUG_ON(!mk); mk->mod = THIS_MODULE; - kobj_set_kset_s(mk, module_subsys); - kobject_set_name(&mk->kobj, name); - kobject_init(&mk->kobj); - ret = kobject_add(&mk->kobj); + mk->kobj.kset = module_kset; + ret = kobject_init_and_add(&mk->kobj, &module_ktype, NULL, "%s", name); if (ret) { + kobject_put(&mk->kobj); printk(KERN_ERR "Module '%s' failed to be added to sysfs, " "error number %d\n", name, ret); printk(KERN_ERR "The system will be unstable now.\n"); @@ -679,8 +678,6 @@ static struct sysfs_ops module_sysfs_ops = { .store = module_attr_store, }; -static struct kobj_type module_ktype; - static int uevent_filter(struct kset *kset, struct kobject *kobj) { struct kobj_type *ktype = get_ktype(kobj); @@ -694,10 +691,10 @@ static struct kset_uevent_ops module_uevent_ops = { .filter = uevent_filter, }; -decl_subsys(module, &module_ktype, &module_uevent_ops); +struct kset *module_kset; int module_sysfs_initialized; -static struct kobj_type module_ktype = { +struct kobj_type module_ktype = { .sysfs_ops = &module_sysfs_ops, }; @@ -706,13 +703,11 @@ static struct kobj_type module_ktype = { */ static int __init param_sysfs_init(void) { - int ret; - - ret = subsystem_register(&module_subsys); - if (ret < 0) { - printk(KERN_WARNING "%s (%d): subsystem_register error: %d\n", - __FILE__, __LINE__, ret); - return ret; + module_kset = kset_create_and_add("module", &module_uevent_ops, NULL); + if (!module_kset) { + printk(KERN_WARNING "%s (%d): error creating kset\n", + __FILE__, __LINE__); + return -ENOMEM; } module_sysfs_initialized = 1; @@ -722,14 +717,7 @@ static int __init param_sysfs_init(void) } subsys_initcall(param_sysfs_init); -#else -#if 0 -static struct sysfs_ops module_sysfs_ops = { - .show = NULL, - .store = NULL, -}; -#endif -#endif +#endif /* CONFIG_SYSFS */ EXPORT_SYMBOL(param_set_byte); EXPORT_SYMBOL(param_get_byte); diff --git a/kernel/power/disk.c b/kernel/power/disk.c index 05b64790fe83..b138b431e271 100644 --- a/kernel/power/disk.c +++ b/kernel/power/disk.c @@ -567,7 +567,8 @@ static const char * const hibernation_modes[] = { * supports it (as determined by having hibernation_ops). */ -static ssize_t disk_show(struct kset *kset, char *buf) +static ssize_t disk_show(struct kobject *kobj, struct kobj_attribute *attr, + char *buf) { int i; char *start = buf; @@ -597,7 +598,8 @@ static ssize_t disk_show(struct kset *kset, char *buf) } -static ssize_t disk_store(struct kset *kset, const char *buf, size_t n) +static ssize_t disk_store(struct kobject *kobj, struct kobj_attribute *attr, + const char *buf, size_t n) { int error = 0; int i; @@ -642,13 +644,15 @@ static ssize_t disk_store(struct kset *kset, const char *buf, size_t n) power_attr(disk); -static ssize_t resume_show(struct kset *kset, char *buf) +static ssize_t resume_show(struct kobject *kobj, struct kobj_attribute *attr, + char *buf) { return sprintf(buf,"%d:%d\n", MAJOR(swsusp_resume_device), MINOR(swsusp_resume_device)); } -static ssize_t resume_store(struct kset *kset, const char *buf, size_t n) +static ssize_t resume_store(struct kobject *kobj, struct kobj_attribute *attr, + const char *buf, size_t n) { unsigned int maj, min; dev_t res; @@ -674,12 +678,14 @@ static ssize_t resume_store(struct kset *kset, const char *buf, size_t n) power_attr(resume); -static ssize_t image_size_show(struct kset *kset, char *buf) +static ssize_t image_size_show(struct kobject *kobj, struct kobj_attribute *attr, + char *buf) { return sprintf(buf, "%lu\n", image_size); } -static ssize_t image_size_store(struct kset *kset, const char *buf, size_t n) +static ssize_t image_size_store(struct kobject *kobj, struct kobj_attribute *attr, + const char *buf, size_t n) { unsigned long size; @@ -708,7 +714,7 @@ static struct attribute_group attr_group = { static int __init pm_disk_init(void) { - return sysfs_create_group(&power_subsys.kobj, &attr_group); + return sysfs_create_group(power_kobj, &attr_group); } core_initcall(pm_disk_init); diff --git a/kernel/power/main.c b/kernel/power/main.c index 3cdf95b1dc92..efc08360e627 100644 --- a/kernel/power/main.c +++ b/kernel/power/main.c @@ -28,6 +28,9 @@ BLOCKING_NOTIFIER_HEAD(pm_chain_head); DEFINE_MUTEX(pm_mutex); +unsigned int pm_flags; +EXPORT_SYMBOL(pm_flags); + #ifdef CONFIG_SUSPEND /* This is just an arbitrary number */ @@ -273,8 +276,7 @@ EXPORT_SYMBOL(pm_suspend); #endif /* CONFIG_SUSPEND */ -decl_subsys(power,NULL,NULL); - +struct kobject *power_kobj; /** * state - control system power state. @@ -287,7 +289,8 @@ decl_subsys(power,NULL,NULL); * proper enumerated value, and initiates a suspend transition. */ -static ssize_t state_show(struct kset *kset, char *buf) +static ssize_t state_show(struct kobject *kobj, struct kobj_attribute *attr, + char *buf) { char *s = buf; #ifdef CONFIG_SUSPEND @@ -308,7 +311,8 @@ static ssize_t state_show(struct kset *kset, char *buf) return (s - buf); } -static ssize_t state_store(struct kset *kset, const char *buf, size_t n) +static ssize_t state_store(struct kobject *kobj, struct kobj_attribute *attr, + const char *buf, size_t n) { #ifdef CONFIG_SUSPEND suspend_state_t state = PM_SUSPEND_STANDBY; @@ -345,13 +349,15 @@ power_attr(state); #ifdef CONFIG_PM_TRACE int pm_trace_enabled; -static ssize_t pm_trace_show(struct kset *kset, char *buf) +static ssize_t pm_trace_show(struct kobject *kobj, struct kobj_attribute *attr, + char *buf) { return sprintf(buf, "%d\n", pm_trace_enabled); } static ssize_t -pm_trace_store(struct kset *kset, const char *buf, size_t n) +pm_trace_store(struct kobject *kobj, struct kobj_attribute *attr, + const char *buf, size_t n) { int val; @@ -383,10 +389,10 @@ static struct attribute_group attr_group = { static int __init pm_init(void) { - int error = subsystem_register(&power_subsys); - if (!error) - error = sysfs_create_group(&power_subsys.kobj,&attr_group); - return error; + power_kobj = kobject_create_and_add("power", NULL); + if (!power_kobj) + return -ENOMEM; + return sysfs_create_group(power_kobj, &attr_group); } core_initcall(pm_init); diff --git a/kernel/power/pm.c b/kernel/power/pm.c index c50d15266c10..60c73fa670d5 100644 --- a/kernel/power/pm.c +++ b/kernel/power/pm.c @@ -27,8 +27,6 @@ #include <linux/interrupt.h> #include <linux/mutex.h> -int pm_active; - /* * Locking notes: * pm_devs_lock can be a semaphore providing pm ops are not called @@ -204,6 +202,4 @@ int pm_send_all(pm_request_t rqst, void *data) EXPORT_SYMBOL(pm_register); EXPORT_SYMBOL(pm_send_all); -EXPORT_SYMBOL(pm_active); - diff --git a/kernel/power/power.h b/kernel/power/power.h index 195dc4611764..2093c3a9a994 100644 --- a/kernel/power/power.h +++ b/kernel/power/power.h @@ -54,7 +54,7 @@ extern int pfn_is_nosave(unsigned long); extern struct mutex pm_mutex; #define power_attr(_name) \ -static struct subsys_attribute _name##_attr = { \ +static struct kobj_attribute _name##_attr = { \ .attr = { \ .name = __stringify(_name), \ .mode = 0644, \ @@ -63,8 +63,6 @@ static struct subsys_attribute _name##_attr = { \ .store = _name##_store, \ } -extern struct kset power_subsys; - /* Preferred image size in bytes (default 500 MB) */ extern unsigned long image_size; extern int in_suspend; diff --git a/kernel/printk.c b/kernel/printk.c index a30fe33de395..89011bf8c106 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 7c76f2ffaeaa..c25db863081d 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/rcupdate.c b/kernel/rcupdate.c index a66d4d1615f7..f2c1a04e9b18 100644 --- a/kernel/rcupdate.c +++ b/kernel/rcupdate.c @@ -549,7 +549,7 @@ static void rcu_init_percpu_data(int cpu, struct rcu_ctrlblk *rcp, rdp->blimit = blimit; } -static void __devinit rcu_online_cpu(int cpu) +static void __cpuinit rcu_online_cpu(int cpu) { struct rcu_data *rdp = &per_cpu(rcu_data, cpu); struct rcu_data *bh_rdp = &per_cpu(rcu_bh_data, cpu); diff --git a/kernel/rtmutex-tester.c b/kernel/rtmutex-tester.c index e3055ba69159..092e4c620af9 100644 --- a/kernel/rtmutex-tester.c +++ b/kernel/rtmutex-tester.c @@ -394,7 +394,7 @@ static SYSDEV_ATTR(status, 0600, sysfs_test_status, NULL); static SYSDEV_ATTR(command, 0600, NULL, sysfs_test_command); static struct sysdev_class rttest_sysclass = { - set_kset_name("rttest"), + .name = "rttest", }; static int init_test_thread(int id) diff --git a/kernel/rwsem.c b/kernel/rwsem.c index 1ec620c03064..cae050b05f5e 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 38933cafea8a..e76b11ca6df3 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -209,9 +209,8 @@ static inline struct task_group *task_group(struct task_struct *p) tg = container_of(task_subsys_state(p, cpu_cgroup_subsys_id), struct task_group, css); #else - tg = &init_task_group; + tg = &init_task_group; #endif - return tg; } @@ -249,15 +248,16 @@ struct cfs_rq { #ifdef CONFIG_FAIR_GROUP_SCHED struct rq *rq; /* cpu runqueue to which this cfs_rq is attached */ - /* leaf cfs_rqs are those that hold tasks (lowest schedulable entity in + /* + * leaf cfs_rqs are those that hold tasks (lowest schedulable entity in * a hierarchy). Non-leaf lrqs hold other higher schedulable entities * (like users, containers etc.) * * leaf_cfs_rq_list ties together list of leaf cfs_rq's in a cpu. This * list is used during load balance. */ - struct list_head leaf_cfs_rq_list; /* Better name : task_cfs_rq_list? */ - struct task_group *tg; /* group that "owns" this runqueue */ + struct list_head leaf_cfs_rq_list; + struct task_group *tg; /* group that "owns" this runqueue */ #endif }; @@ -300,7 +300,7 @@ struct rq { /* list of leaf cfs_rq on this cpu: */ struct list_head leaf_cfs_rq_list; #endif - struct rt_rq rt; + struct rt_rq rt; /* * This is part of a global counter where only the total sum @@ -457,8 +457,8 @@ enum { SCHED_FEAT_NEW_FAIR_SLEEPERS = 1, SCHED_FEAT_WAKEUP_PREEMPT = 2, SCHED_FEAT_START_DEBIT = 4, - SCHED_FEAT_TREE_AVG = 8, - SCHED_FEAT_APPROX_AVG = 16, + SCHED_FEAT_TREE_AVG = 8, + SCHED_FEAT_APPROX_AVG = 16, }; const_debug unsigned int sysctl_sched_features = @@ -488,7 +488,12 @@ unsigned long long cpu_clock(int cpu) local_irq_save(flags); rq = cpu_rq(cpu); - update_rq_clock(rq); + /* + * Only call sched_clock() if the scheduler has already been + * initialized (some code might call cpu_clock() very early): + */ + if (rq->idle) + update_rq_clock(rq); now = rq->clock; local_irq_restore(flags); @@ -503,10 +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) @@ -535,7 +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 } @@ -591,7 +601,7 @@ static inline struct rq *__task_rq_lock(struct task_struct *p) /* * task_rq_lock - lock the runqueue a given task resides on and disable - * interrupts. Note the ordering: we can safely lookup the task_rq without + * interrupts. Note the ordering: we can safely lookup the task_rq without * explicitly disabling preemption. */ static struct rq *task_rq_lock(struct task_struct *p, unsigned long *flags) @@ -658,6 +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 @@ -779,7 +790,7 @@ static inline void update_load_sub(struct load_weight *lw, unsigned long dec) * To aid in avoiding the subversion of "niceness" due to uneven distribution * of tasks with abnormal "nice" values across CPUs the contribution that * each task makes to its run queue's load is weighted according to its - * scheduling class and "nice" value. For SCHED_NORMAL tasks this is just a + * scheduling class and "nice" value. For SCHED_NORMAL tasks this is just a * scaled version of the new time slice allocation that they receive on time * slice expiry etc. */ @@ -854,6 +865,12 @@ iter_move_one_task(struct rq *this_rq, int this_cpu, struct rq *busiest, struct rq_iterator *iterator); #endif +#ifdef CONFIG_CGROUP_CPUACCT +static void cpuacct_charge(struct task_struct *tsk, u64 cputime); +#else +static inline void cpuacct_charge(struct task_struct *tsk, u64 cputime) {} +#endif + #include "sched_stats.h" #include "sched_idletask.c" #include "sched_fair.c" @@ -1848,7 +1865,7 @@ prepare_task_switch(struct rq *rq, struct task_struct *prev, * and do any other architecture-specific cleanup actions. * * Note that we may have delayed dropping an mm in context_switch(). If - * so, we finish that here outside of the runqueue lock. (Doing it + * so, we finish that here outside of the runqueue lock. (Doing it * with the lock held can cause deadlocks; see schedule() for * details.) */ @@ -2130,7 +2147,7 @@ static void double_lock_balance(struct rq *this_rq, struct rq *busiest) /* * If dest_cpu is allowed for this process, migrate the task to it. * This is accomplished by forcing the cpu_allowed mask to only - * allow dest_cpu, which will force the cpu onto dest_cpu. Then + * allow dest_cpu, which will force the cpu onto dest_cpu. Then * the cpu_allowed mask is restored. */ static void sched_migrate_task(struct task_struct *p, int dest_cpu) @@ -2575,7 +2592,7 @@ group_next: * tasks around. Thus we look for the minimum possible imbalance. * Negative imbalances (*we* are more loaded than anyone else) will * be counted as no imbalance for these purposes -- we can't fix that - * by pulling tasks to us. Be careful of negative numbers as they'll + * by pulling tasks to us. Be careful of negative numbers as they'll * appear as very large values with unsigned longs. */ if (max_load <= busiest_load_per_task) @@ -3010,7 +3027,7 @@ static void active_load_balance(struct rq *busiest_rq, int busiest_cpu) /* * This condition is "impossible", if it occurs - * we need to fix it. Originally reported by + * we need to fix it. Originally reported by * Bjorn Helgaas on a 128-cpu setup. */ BUG_ON(busiest_rq == target_rq); @@ -3042,7 +3059,7 @@ static void active_load_balance(struct rq *busiest_rq, int busiest_cpu) #ifdef CONFIG_NO_HZ static struct { atomic_t load_balancer; - cpumask_t cpu_mask; + cpumask_t cpu_mask; } nohz ____cacheline_aligned = { .load_balancer = ATOMIC_INIT(-1), .cpu_mask = CPU_MASK_NONE, @@ -3323,7 +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) @@ -3546,7 +3563,7 @@ static noinline void __schedule_bug(struct task_struct *prev) static inline void schedule_debug(struct task_struct *prev) { /* - * Test if we are atomic. Since do_exit() needs to call into + * Test if we are atomic. Since do_exit() needs to call into * schedule() atomically, we ignore that path for now. * Otherwise, whine if we are scheduling when we should not be. */ @@ -3668,7 +3685,7 @@ EXPORT_SYMBOL(schedule); #ifdef CONFIG_PREEMPT /* * this is the entry point to schedule() from in-kernel preemption - * off of preempt_enable. Kernel preemptions off return from interrupt + * off of preempt_enable. Kernel preemptions off return from interrupt * occur there and call schedule directly. */ asmlinkage void __sched preempt_schedule(void) @@ -3680,7 +3697,7 @@ asmlinkage void __sched preempt_schedule(void) #endif /* * If there is a non-zero preempt_count or interrupts are disabled, - * we do not want to preempt the current task. Just return.. + * we do not want to preempt the current task. Just return.. */ if (likely(ti->preempt_count || irqs_disabled())) return; @@ -3766,12 +3783,12 @@ int default_wake_function(wait_queue_t *curr, unsigned mode, int sync, EXPORT_SYMBOL(default_wake_function); /* - * The core wakeup function. Non-exclusive wakeups (nr_exclusive == 0) just - * wake everything up. If it's an exclusive wakeup (nr_exclusive == small +ve + * The core wakeup function. Non-exclusive wakeups (nr_exclusive == 0) just + * wake everything up. If it's an exclusive wakeup (nr_exclusive == small +ve * number) then we wake all the non-exclusive tasks and one exclusive task. * * There are circumstances in which we can try to wake a task which has already - * started to run but is not in state TASK_RUNNING. try_to_wake_up() returns + * started to run but is not in state TASK_RUNNING. try_to_wake_up() returns * zero in this (rare) case, and we handle it by continuing to scan the queue. */ static void __wake_up_common(wait_queue_head_t *q, unsigned int mode, @@ -4010,7 +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) @@ -4321,7 +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) @@ -4384,8 +4401,8 @@ do_sched_setscheduler(pid_t pid, int policy, struct sched_param __user *param) * @policy: new policy. * @param: structure containing the new RT priority. */ -asmlinkage long sys_sched_setscheduler(pid_t pid, int policy, - struct sched_param __user *param) +asmlinkage long +sys_sched_setscheduler(pid_t pid, int policy, struct sched_param __user *param) { /* negative values for policy are not valid */ if (policy < 0) @@ -4485,7 +4502,7 @@ long sched_setaffinity(pid_t pid, cpumask_t new_mask) /* * It is not safe to call set_cpus_allowed with the - * tasklist_lock held. We will bump the task_struct's + * tasklist_lock held. We will bump the task_struct's * usage count and then drop tasklist_lock. */ get_task_struct(p); @@ -4681,7 +4698,7 @@ EXPORT_SYMBOL(cond_resched); * cond_resched_lock() - if a reschedule is pending, drop the given lock, * call schedule, and on return reacquire the lock. * - * This works OK both with and without CONFIG_PREEMPT. We do strange low-level + * This works OK both with and without CONFIG_PREEMPT. We do strange low-level * operations here to prevent schedule() from being called twice (once via * spin_unlock(), once by hand). */ @@ -4735,7 +4752,7 @@ void __sched yield(void) EXPORT_SYMBOL(yield); /* - * This task is about to go to sleep on IO. Increment rq->nr_iowait so + * This task is about to go to sleep on IO. Increment rq->nr_iowait so * that process accounting knows that this is a task in IO wait state. * * But don't do that if it is a deliberate, throttling IO wait (this task @@ -4844,17 +4861,21 @@ long sys_sched_rr_get_interval(pid_t pid, struct timespec __user *interval) if (retval) goto out_unlock; - if (p->policy == SCHED_FIFO) - time_slice = 0; - else if (p->policy == SCHED_RR) + /* + * Time slice is 0 for SCHED_FIFO tasks and for SCHED_OTHER + * tasks that are on an otherwise idle runqueue: + */ + time_slice = 0; + if (p->policy == SCHED_RR) { time_slice = DEF_TIMESLICE; - else { + } else { struct sched_entity *se = &p->se; unsigned long flags; struct rq *rq; rq = task_rq_lock(p, &flags); - time_slice = NS_TO_JIFFIES(sched_slice(cfs_rq_of(se), se)); + if (rq->cfs.load.weight) + time_slice = NS_TO_JIFFIES(sched_slice(&rq->cfs, se)); task_rq_unlock(rq, &flags); } read_unlock(&tasklist_lock); @@ -4897,7 +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); @@ -5040,7 +5061,7 @@ static inline void sched_init_granularity(void) * is removed from the allowed bitmask. * * NOTE: the caller must have a valid reference to the task, the - * task must not exit() & deallocate itself prematurely. The + * task must not exit() & deallocate itself prematurely. The * call is not atomic; no spinlocks may be held. */ int set_cpus_allowed(struct task_struct *p, cpumask_t new_mask) @@ -5077,7 +5098,7 @@ out: EXPORT_SYMBOL_GPL(set_cpus_allowed); /* - * Move (not current) task off this cpu, onto dest cpu. We're doing + * Move (not current) task off this cpu, onto dest cpu. We're doing * this because either it can't run here any more (set_cpus_allowed() * away from this CPU, or CPU going down), or because we're * attempting to rebalance this task on exec (sched_exec). @@ -5222,7 +5243,7 @@ static void move_task_off_dead_cpu(int dead_cpu, struct task_struct *p) * Try to stay on the same cpuset, where the * current cpuset may be a subset of all cpus. * The cpuset_cpus_allowed_locked() variant of - * cpuset_cpus_allowed() will not block. It must be + * cpuset_cpus_allowed() will not block. It must be * called within calls to cpuset_lock/cpuset_unlock. */ rq = task_rq_lock(p, &flags); @@ -5235,10 +5256,11 @@ static void move_task_off_dead_cpu(int dead_cpu, struct task_struct *p) * kernel threads (both mm NULL), since they never * leave kernel. */ - if (p->mm && printk_ratelimit()) + if (p->mm && printk_ratelimit()) { printk(KERN_INFO "process %d (%s) no " "longer affine to cpu%d\n", - task_pid_nr(p), p->comm, dead_cpu); + task_pid_nr(p), p->comm, dead_cpu); + } } } while (!__migrate_task_irq(p, dead_cpu, dest_cpu)); } @@ -5340,7 +5362,7 @@ static void migrate_dead(unsigned int dead_cpu, struct task_struct *p) /* * Drop lock around migration; if someone else moves it, - * that's OK. No task can be added to this CPU, so iteration is + * that's OK. No task can be added to this CPU, so iteration is * fine. */ spin_unlock_irq(&rq->lock); @@ -5404,7 +5426,7 @@ static void sd_free_ctl_entry(struct ctl_table **tablep) /* * In the intermediate directories, both the child directory and * procname are dynamically allocated and could fail but the mode - * will always be set. In the lowest directory the names are + * will always be set. In the lowest directory the names are * static strings and all have proc handlers. */ for (entry = *tablep; entry->mode; entry++) { @@ -5466,7 +5488,7 @@ sd_alloc_ctl_domain_table(struct sched_domain *sd) return table; } -static ctl_table * sd_alloc_ctl_cpu_table(int cpu) +static ctl_table *sd_alloc_ctl_cpu_table(int cpu) { struct ctl_table *entry, *table; struct sched_domain *sd; @@ -5575,7 +5597,7 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu) case CPU_UP_CANCELED_FROZEN: if (!cpu_rq(cpu)->migration_thread) break; - /* Unbind it from offline cpu so it can run. Fall thru. */ + /* Unbind it from offline cpu so it can run. Fall thru. */ kthread_bind(cpu_rq(cpu)->migration_thread, any_online_cpu(cpu_online_map)); kthread_stop(cpu_rq(cpu)->migration_thread); @@ -5602,9 +5624,11 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu) migrate_nr_uninterruptible(rq); BUG_ON(rq->nr_running != 0); - /* No need to migrate the tasks: it was best-effort if - * they didn't take sched_hotcpu_mutex. Just wake up - * the requestors. */ + /* + * No need to migrate the tasks: it was best-effort if + * they didn't take sched_hotcpu_mutex. Just wake up + * the requestors. + */ spin_lock_irq(&rq->lock); while (!list_empty(&rq->migration_queue)) { struct migration_req *req; @@ -5912,7 +5936,7 @@ init_sched_build_groups(cpumask_t span, const cpumask_t *cpu_map, * @node: node whose sched_domain we're building * @used_nodes: nodes already in the sched_domain * - * Find the next node to include in a given scheduling domain. Simply + * Find the next node to include in a given scheduling domain. Simply * finds the closest node not already in the @used_nodes map. * * Should use nodemask_t. @@ -5952,7 +5976,7 @@ static int find_next_best_node(int node, unsigned long *used_nodes) * @node: node whose cpumask we're constructing * @size: number of nodes to include in this span * - * Given a node, construct a good cpumask for its sched_domain to span. It + * Given a node, construct a good cpumask for its sched_domain to span. It * should be one that prevents unnecessary balancing, but also spreads tasks * out optimally. */ @@ -5989,8 +6013,8 @@ int sched_smt_power_savings = 0, sched_mc_power_savings = 0; static DEFINE_PER_CPU(struct sched_domain, cpu_domains); static DEFINE_PER_CPU(struct sched_group, sched_group_cpus); -static int cpu_to_cpu_group(int cpu, const cpumask_t *cpu_map, - struct sched_group **sg) +static int +cpu_to_cpu_group(int cpu, const cpumask_t *cpu_map, struct sched_group **sg) { if (sg) *sg = &per_cpu(sched_group_cpus, cpu); @@ -6007,8 +6031,8 @@ static DEFINE_PER_CPU(struct sched_group, sched_group_core); #endif #if defined(CONFIG_SCHED_MC) && defined(CONFIG_SCHED_SMT) -static int cpu_to_core_group(int cpu, const cpumask_t *cpu_map, - struct sched_group **sg) +static int +cpu_to_core_group(int cpu, const cpumask_t *cpu_map, struct sched_group **sg) { int group; cpumask_t mask = per_cpu(cpu_sibling_map, cpu); @@ -6019,8 +6043,8 @@ static int cpu_to_core_group(int cpu, const cpumask_t *cpu_map, return group; } #elif defined(CONFIG_SCHED_MC) -static int cpu_to_core_group(int cpu, const cpumask_t *cpu_map, - struct sched_group **sg) +static int +cpu_to_core_group(int cpu, const cpumask_t *cpu_map, struct sched_group **sg) { if (sg) *sg = &per_cpu(sched_group_core, cpu); @@ -6031,8 +6055,8 @@ static int cpu_to_core_group(int cpu, const cpumask_t *cpu_map, static DEFINE_PER_CPU(struct sched_domain, phys_domains); static DEFINE_PER_CPU(struct sched_group, sched_group_phys); -static int cpu_to_phys_group(int cpu, const cpumask_t *cpu_map, - struct sched_group **sg) +static int +cpu_to_phys_group(int cpu, const cpumask_t *cpu_map, struct sched_group **sg) { int group; #ifdef CONFIG_SCHED_MC @@ -6212,7 +6236,7 @@ static int build_sched_domains(const cpumask_t *cpu_map) * Allocate the per-node list of sched groups */ sched_group_nodes = kcalloc(MAX_NUMNODES, sizeof(struct sched_group *), - GFP_KERNEL); + GFP_KERNEL); if (!sched_group_nodes) { printk(KERN_WARNING "Can not alloc sched group node list\n"); return -ENOMEM; @@ -6459,7 +6483,7 @@ static int ndoms_cur; /* number of sched domains in 'doms_cur' */ static cpumask_t fallback_doms; /* - * Set up scheduler domains and groups. Callers must hold the hotplug lock. + * Set up scheduler domains and groups. Callers must hold the hotplug lock. * For now this just excludes isolated cpus, but could be used to * exclude other special cases in the future. */ @@ -6501,19 +6525,19 @@ static void detach_destroy_domains(const cpumask_t *cpu_map) /* * Partition sched domains as specified by the 'ndoms_new' - * cpumasks in the array doms_new[] of cpumasks. This compares + * cpumasks in the array doms_new[] of cpumasks. This compares * doms_new[] to the current sched domain partitioning, doms_cur[]. * It destroys each deleted domain and builds each new domain. * * 'doms_new' is an array of cpumask_t's of length 'ndoms_new'. - * The masks don't intersect (don't overlap.) We should setup one - * sched domain for each mask. CPUs not in any of the cpumasks will - * not be load balanced. If the same cpumask appears both in the + * The masks don't intersect (don't overlap.) We should setup one + * sched domain for each mask. CPUs not in any of the cpumasks will + * not be load balanced. If the same cpumask appears both in the * current 'doms_cur' domains and in the new 'doms_new', we can leave * it as it is. * - * The passed in 'doms_new' should be kmalloc'd. This routine takes - * ownership of it and will kfree it when done with it. If the caller + * The passed in 'doms_new' should be kmalloc'd. This routine takes + * ownership of it and will kfree it when done with it. If the caller * failed the kmalloc call, then it can pass in doms_new == NULL, * and partition_sched_domains() will fallback to the single partition * 'fallback_doms'. @@ -6643,7 +6667,7 @@ int sched_create_sysfs_power_savings_entries(struct sysdev_class *cls) #endif /* - * Force a reinitialization of the sched domains hierarchy. The domains + * Force a reinitialization of the sched domains hierarchy. The domains * and groups cannot be updated in place without racing with the balancing * code, so we temporarily attach all running cpus to the NULL domain * which will prevent rebalancing while the sched domains are recalculated. @@ -6708,9 +6732,6 @@ void __init sched_init_smp(void) int in_sched_functions(unsigned long addr) { - /* Linker adds these: start and end of __sched functions */ - extern char __sched_text_start[], __sched_text_end[]; - return in_lock_functions(addr) || (addr >= (unsigned long)__sched_text_start && addr < (unsigned long)__sched_text_end); @@ -6936,8 +6957,8 @@ struct task_struct *curr_task(int cpu) * @p: the task pointer to set. * * Description: This function must only be used when non-maskable interrupts - * are serviced on a separate stack. It allows the architecture to switch the - * notion of the current task on a cpu in a non-blocking manner. This function + * are serviced on a separate stack. It allows the architecture to switch the + * notion of the current task on a cpu in a non-blocking manner. This function * must be called with all CPU's synchronized, and interrupts disabled, the * and caller must save the original value of the current task (see * curr_task() above) and restore that value before reenabling interrupts and @@ -7086,7 +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) { @@ -7132,6 +7153,14 @@ int sched_group_set_shares(struct task_group *tg, unsigned long shares) { int i; + /* + * A weight of 0 or 1 can cause arithmetics problems. + * (The default weight is 1024 - so there's no practical + * limitation from this.) + */ + if (shares < 2) + shares = 2; + spin_lock(&tg->lock); if (tg->shares == shares) goto done; @@ -7186,16 +7215,17 @@ cpu_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cgrp) return &tg->css; } -static void cpu_cgroup_destroy(struct cgroup_subsys *ss, - struct cgroup *cgrp) +static void +cpu_cgroup_destroy(struct cgroup_subsys *ss, struct cgroup *cgrp) { struct task_group *tg = cgroup_tg(cgrp); sched_destroy_group(tg); } -static int cpu_cgroup_can_attach(struct cgroup_subsys *ss, - struct cgroup *cgrp, struct task_struct *tsk) +static int +cpu_cgroup_can_attach(struct cgroup_subsys *ss, struct cgroup *cgrp, + struct task_struct *tsk) { /* We don't support RT-tasks being in separate groups */ if (tsk->sched_class != &fair_sched_class) @@ -7224,38 +7254,12 @@ static u64 cpu_shares_read_uint(struct cgroup *cgrp, struct cftype *cft) return (u64) tg->shares; } -static u64 cpu_usage_read(struct cgroup *cgrp, struct cftype *cft) -{ - struct task_group *tg = cgroup_tg(cgrp); - unsigned long flags; - u64 res = 0; - int i; - - for_each_possible_cpu(i) { - /* - * Lock to prevent races with updating 64-bit counters - * on 32-bit arches. - */ - spin_lock_irqsave(&cpu_rq(i)->lock, flags); - res += tg->se[i]->sum_exec_runtime; - spin_unlock_irqrestore(&cpu_rq(i)->lock, flags); - } - /* Convert from ns to ms */ - do_div(res, NSEC_PER_MSEC); - - return res; -} - static struct cftype cpu_files[] = { { .name = "shares", .read_uint = cpu_shares_read_uint, .write_uint = cpu_shares_write_uint, }, - { - .name = "usage", - .read_uint = cpu_usage_read, - }, }; static int cpu_cgroup_populate(struct cgroup_subsys *ss, struct cgroup *cont) @@ -7275,3 +7279,126 @@ struct cgroup_subsys cpu_cgroup_subsys = { }; #endif /* CONFIG_FAIR_CGROUP_SCHED */ + +#ifdef CONFIG_CGROUP_CPUACCT + +/* + * CPU accounting code for task groups. + * + * Based on the work by Paul Menage (menage@google.com) and Balbir Singh + * (balbir@in.ibm.com). + */ + +/* track cpu usage of a group of tasks */ +struct cpuacct { + struct cgroup_subsys_state css; + /* cpuusage holds pointer to a u64-type object on every cpu */ + u64 *cpuusage; +}; + +struct cgroup_subsys cpuacct_subsys; + +/* return cpu accounting group corresponding to this container */ +static inline struct cpuacct *cgroup_ca(struct cgroup *cont) +{ + return container_of(cgroup_subsys_state(cont, cpuacct_subsys_id), + struct cpuacct, css); +} + +/* return cpu accounting group to which this task belongs */ +static inline struct cpuacct *task_ca(struct task_struct *tsk) +{ + return container_of(task_subsys_state(tsk, cpuacct_subsys_id), + struct cpuacct, css); +} + +/* create a new cpu accounting group */ +static struct cgroup_subsys_state *cpuacct_create( + struct cgroup_subsys *ss, struct cgroup *cont) +{ + struct cpuacct *ca = kzalloc(sizeof(*ca), GFP_KERNEL); + + if (!ca) + return ERR_PTR(-ENOMEM); + + ca->cpuusage = alloc_percpu(u64); + if (!ca->cpuusage) { + kfree(ca); + return ERR_PTR(-ENOMEM); + } + + return &ca->css; +} + +/* destroy an existing cpu accounting group */ +static void +cpuacct_destroy(struct cgroup_subsys *ss, struct cgroup *cont) +{ + struct cpuacct *ca = cgroup_ca(cont); + + free_percpu(ca->cpuusage); + kfree(ca); +} + +/* return total cpu usage (in nanoseconds) of a group */ +static u64 cpuusage_read(struct cgroup *cont, struct cftype *cft) +{ + struct cpuacct *ca = cgroup_ca(cont); + u64 totalcpuusage = 0; + int i; + + for_each_possible_cpu(i) { + u64 *cpuusage = percpu_ptr(ca->cpuusage, i); + + /* + * Take rq->lock to make 64-bit addition safe on 32-bit + * platforms. + */ + spin_lock_irq(&cpu_rq(i)->lock); + totalcpuusage += *cpuusage; + spin_unlock_irq(&cpu_rq(i)->lock); + } + + return totalcpuusage; +} + +static struct cftype files[] = { + { + .name = "usage", + .read_uint = cpuusage_read, + }, +}; + +static int cpuacct_populate(struct cgroup_subsys *ss, struct cgroup *cont) +{ + return cgroup_add_files(cont, ss, files, ARRAY_SIZE(files)); +} + +/* + * charge this task's execution time to its accounting group. + * + * called with rq->lock held. + */ +static void cpuacct_charge(struct task_struct *tsk, u64 cputime) +{ + struct cpuacct *ca; + + if (!cpuacct_subsys.active) + return; + + ca = task_ca(tsk); + if (ca) { + u64 *cpuusage = percpu_ptr(ca->cpuusage, task_cpu(tsk)); + + *cpuusage += cputime; + } +} + +struct cgroup_subsys cpuacct_subsys = { + .name = "cpuacct", + .create = cpuacct_create, + .destroy = cpuacct_destroy, + .populate = cpuacct_populate, + .subsys_id = cpuacct_subsys_id, +}; +#endif /* CONFIG_CGROUP_CPUACCT */ diff --git a/kernel/sched_debug.c b/kernel/sched_debug.c index ca198a797bfa..80fbbfc04290 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); @@ -199,7 +199,7 @@ static int sched_debug_show(struct seq_file *m, void *v) u64 now = ktime_to_ns(ktime_get()); int cpu; - SEQ_printf(m, "Sched Debug Version: v0.06-v22, %s %.*s\n", + SEQ_printf(m, "Sched Debug Version: v0.07, %s %.*s\n", init_utsname()->release, (int)strcspn(init_utsname()->version, " "), init_utsname()->version); @@ -327,10 +327,12 @@ void proc_sched_show_task(struct task_struct *p, struct seq_file *m) avg_atom = -1LL; avg_per_cpu = p->se.sum_exec_runtime; - if (p->se.nr_migrations) - avg_per_cpu = div64_64(avg_per_cpu, p->se.nr_migrations); - else + if (p->se.nr_migrations) { + avg_per_cpu = div64_64(avg_per_cpu, + p->se.nr_migrations); + } else { avg_per_cpu = -1LL; + } __PN(avg_atom); __PN(avg_per_cpu); diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c index ee00da284b12..da7c061e7206 100644 --- a/kernel/sched_fair.c +++ b/kernel/sched_fair.c @@ -22,7 +22,7 @@ /* * Targeted preemption latency for CPU-bound tasks: - * (default: 20ms * ilog(ncpus), units: nanoseconds) + * (default: 20ms * (1 + ilog(ncpus)), units: nanoseconds) * * NOTE: this latency value is not the same as the concept of * 'timeslice length' - timeslices in CFS are of variable length @@ -36,14 +36,14 @@ unsigned int sysctl_sched_latency = 20000000ULL; /* * Minimal preemption granularity for CPU-bound tasks: - * (default: 1 msec * ilog(ncpus), units: nanoseconds) + * (default: 4 msec * (1 + ilog(ncpus)), units: nanoseconds) */ -unsigned int sysctl_sched_min_granularity = 1000000ULL; +unsigned int sysctl_sched_min_granularity = 4000000ULL; /* * is kept at sysctl_sched_latency / sysctl_sched_min_granularity */ -static unsigned int sched_nr_latency = 20; +static unsigned int sched_nr_latency = 5; /* * After fork, child runs first. (default) If set to 0 then @@ -61,7 +61,7 @@ unsigned int __read_mostly sysctl_sched_compat_yield; /* * SCHED_BATCH wake-up granularity. - * (default: 10 msec * ilog(ncpus), units: nanoseconds) + * (default: 10 msec * (1 + ilog(ncpus)), units: nanoseconds) * * This option delays the preemption effects of decoupled workloads * and reduces their over-scheduling. Synchronous workloads will still @@ -71,7 +71,7 @@ unsigned int sysctl_sched_batch_wakeup_granularity = 10000000UL; /* * SCHED_OTHER wake-up granularity. - * (default: 10 msec * ilog(ncpus), units: nanoseconds) + * (default: 10 msec * (1 + ilog(ncpus)), units: nanoseconds) * * This option delays the preemption effects of decoupled workloads * and reduces their over-scheduling. Synchronous workloads will still @@ -351,6 +351,12 @@ static void update_curr(struct cfs_rq *cfs_rq) __update_curr(cfs_rq, curr, delta_exec); curr->exec_start = now; + + if (entity_is_task(curr)) { + struct task_struct *curtask = task_of(curr); + + cpuacct_charge(curtask, delta_exec); + } } static inline void @@ -505,8 +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. */ @@ -793,8 +798,9 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int sleep) */ static void yield_task_fair(struct rq *rq) { - struct cfs_rq *cfs_rq = task_cfs_rq(rq->curr); - struct sched_entity *rightmost, *se = &rq->curr->se; + struct task_struct *curr = rq->curr; + struct cfs_rq *cfs_rq = task_cfs_rq(curr); + struct sched_entity *rightmost, *se = &curr->se; /* * Are we the only task in the tree? @@ -802,7 +808,7 @@ static void yield_task_fair(struct rq *rq) if (unlikely(cfs_rq->nr_running == 1)) return; - if (likely(!sysctl_sched_compat_yield)) { + if (likely(!sysctl_sched_compat_yield) && curr->policy != SCHED_BATCH) { __update_rq_clock(rq); /* * Update run-time statistics of the 'current'. diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c index 8abd752a0ebd..9ba3daa03475 100644 --- a/kernel/sched_rt.c +++ b/kernel/sched_rt.c @@ -23,6 +23,7 @@ static void update_curr_rt(struct rq *rq) curr->se.sum_exec_runtime += delta_exec; curr->se.exec_start = rq->clock; + cpuacct_charge(curr, delta_exec); } static void enqueue_task_rt(struct rq *rq, struct task_struct *p, int wakeup) @@ -207,6 +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/sched_stats.h b/kernel/sched_stats.h index 630178e53bb6..5b32433e7ee5 100644 --- a/kernel/sched_stats.h +++ b/kernel/sched_stats.h @@ -52,7 +52,8 @@ static int show_schedstat(struct seq_file *seq, void *v) sd->lb_nobusyq[itype], sd->lb_nobusyg[itype]); } - seq_printf(seq, " %u %u %u %u %u %u %u %u %u %u %u %u\n", + seq_printf(seq, + " %u %u %u %u %u %u %u %u %u %u %u %u\n", sd->alb_count, sd->alb_failed, sd->alb_pushed, sd->sbe_count, sd->sbe_balanced, sd->sbe_pushed, sd->sbf_count, sd->sbf_balanced, sd->sbf_pushed, diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 0deed82a6156..c68f68dcc605 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 { @@ -1588,6 +1588,10 @@ struct ctl_table_header *register_sysctl_table(struct ctl_table * table) void unregister_sysctl_table(struct ctl_table_header * header) { might_sleep(); + + if (header == NULL) + return; + spin_lock(&sysctl_lock); start_unregistering(header); spin_unlock(&sysctl_lock); diff --git a/kernel/sysctl_check.c b/kernel/sysctl_check.c index 4abc6d2306f4..a68425a5cc1d 100644 --- a/kernel/sysctl_check.c +++ b/kernel/sysctl_check.c @@ -96,7 +96,7 @@ static struct trans_ctl_table trans_kern_table[] = { { KERN_PTY, "pty", trans_pty_table }, { KERN_NGROUPS_MAX, "ngroups_max" }, - { KERN_SPARC_SCONS_PWROFF, "scons_poweroff" }, + { KERN_SPARC_SCONS_PWROFF, "scons-poweroff" }, { KERN_HZ_TIMER, "hz_timer" }, { KERN_UNKNOWN_NMI_PANIC, "unknown_nmi_panic" }, { KERN_BOOTLOADER_TYPE, "bootloader_type" }, @@ -140,9 +140,6 @@ static struct trans_ctl_table trans_vm_table[] = { { VM_PANIC_ON_OOM, "panic_on_oom" }, { VM_VDSO_ENABLED, "vdso_enabled" }, { VM_MIN_SLAB, "min_slab_ratio" }, - { VM_CMM_PAGES, "cmm_pages" }, - { VM_CMM_TIMED_PAGES, "cmm_timed_pages" }, - { VM_CMM_TIMEOUT, "cmm_timeout" }, {} }; @@ -237,36 +234,6 @@ static struct trans_ctl_table trans_net_ipv4_conf_table[] = { {} }; - -static struct trans_ctl_table trans_net_ipv4_vs_table[] = { - { NET_IPV4_VS_AMEMTHRESH, "amemthresh" }, - { NET_IPV4_VS_DEBUG_LEVEL, "debug_level" }, - { NET_IPV4_VS_AMDROPRATE, "am_droprate" }, - { NET_IPV4_VS_DROP_ENTRY, "drop_entry" }, - { NET_IPV4_VS_DROP_PACKET, "drop_packet" }, - { NET_IPV4_VS_SECURE_TCP, "secure_tcp" }, - { NET_IPV4_VS_TO_ES, "timeout_established" }, - { NET_IPV4_VS_TO_SS, "timeout_synsent" }, - { NET_IPV4_VS_TO_SR, "timeout_synrecv" }, - { NET_IPV4_VS_TO_FW, "timeout_finwait" }, - { NET_IPV4_VS_TO_TW, "timeout_timewait" }, - { NET_IPV4_VS_TO_CL, "timeout_close" }, - { NET_IPV4_VS_TO_CW, "timeout_closewait" }, - { NET_IPV4_VS_TO_LA, "timeout_lastack" }, - { NET_IPV4_VS_TO_LI, "timeout_listen" }, - { NET_IPV4_VS_TO_SA, "timeout_synack" }, - { NET_IPV4_VS_TO_UDP, "timeout_udp" }, - { NET_IPV4_VS_TO_ICMP, "timeout_icmp" }, - { NET_IPV4_VS_CACHE_BYPASS, "cache_bypass" }, - { NET_IPV4_VS_EXPIRE_NODEST_CONN, "expire_nodest_conn" }, - { NET_IPV4_VS_EXPIRE_QUIESCENT_TEMPLATE, "expire_quiescent_template" }, - { NET_IPV4_VS_SYNC_THRESHOLD, "sync_threshold" }, - { NET_IPV4_VS_NAT_ICMP_SEND, "nat_icmp_send" }, - { NET_IPV4_VS_LBLC_EXPIRE, "lblc_expiration" }, - { NET_IPV4_VS_LBLCR_EXPIRE, "lblcr_expiration" }, - {} -}; - static struct trans_ctl_table trans_net_neigh_vars_table[] = { { NET_NEIGH_MCAST_SOLICIT, "mcast_solicit" }, { NET_NEIGH_UCAST_SOLICIT, "ucast_solicit" }, @@ -341,7 +308,6 @@ static struct trans_ctl_table trans_net_ipv4_table[] = { { NET_IPV4_ROUTE, "route", trans_net_ipv4_route_table }, /* NET_IPV4_FIB_HASH unused */ { NET_IPV4_NETFILTER, "netfilter", trans_net_ipv4_netfilter_table }, - { NET_IPV4_VS, "vs", trans_net_ipv4_vs_table }, { NET_IPV4_TCP_TIMESTAMPS, "tcp_timestamps" }, { NET_IPV4_TCP_WINDOW_SCALING, "tcp_window_scaling" }, @@ -462,7 +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" }, @@ -480,6 +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" }, @@ -1219,16 +1190,6 @@ static struct trans_ctl_table trans_arlan_table[] = { {} }; -static struct trans_ctl_table trans_appldata_table[] = { - { CTL_APPLDATA_TIMER, "timer" }, - { CTL_APPLDATA_INTERVAL, "interval" }, - { CTL_APPLDATA_OS, "os" }, - { CTL_APPLDATA_NET_SUM, "net_sum" }, - { CTL_APPLDATA_MEM, "mem" }, - {} - -}; - static struct trans_ctl_table trans_s390dbf_table[] = { { 5678 /* CTL_S390DBF_STOPPABLE */, "debug_stoppable" }, { 5679 /* CTL_S390DBF_ACTIVE */, "debug_active" }, @@ -1273,7 +1234,6 @@ static struct trans_ctl_table trans_root_table[] = { { CTL_ABI, "abi" }, /* CTL_CPU not used */ { CTL_ARLAN, "arlan", trans_arlan_table }, - { CTL_APPLDATA, "appldata", trans_appldata_table }, { CTL_S390DBF, "s390dbf", trans_s390dbf_table }, { CTL_SUNRPC, "sunrpc", trans_sunrpc_table }, { CTL_PM, "pm", trans_pm_table }, diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c index 822beebe664a..5fb139fef9fa 100644 --- a/kernel/time/clockevents.c +++ b/kernel/time/clockevents.c @@ -78,6 +78,11 @@ int clockevents_program_event(struct clock_event_device *dev, ktime_t expires, unsigned long long clc; int64_t delta; + if (unlikely(expires.tv64 < 0)) { + WARN_ON_ONCE(1); + return -ETIME; + } + delta = ktime_to_ns(ktime_sub(expires, now)); if (delta <= 0) diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index c8a9d13874df..8d6125ad2cf0 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -441,7 +441,7 @@ static SYSDEV_ATTR(available_clocksource, 0600, sysfs_show_available_clocksources, NULL); static struct sysdev_class clocksource_sysclass = { - set_kset_name("clocksource"), + .name = "clocksource", }; static struct sys_device device_clocksource = { diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c index 14a2ecf2b318..e64efaf957e8 100644 --- a/kernel/time/ntp.c +++ b/kernel/time/ntp.c @@ -249,10 +249,12 @@ int do_adjtimex(struct timex *txc) /* Now we validate the data before disabling interrupts */ - if ((txc->modes & ADJ_OFFSET_SINGLESHOT) == ADJ_OFFSET_SINGLESHOT) + if ((txc->modes & ADJ_OFFSET_SINGLESHOT) == ADJ_OFFSET_SINGLESHOT) { /* singleshot must not be used with any other mode bits */ - if (txc->modes != ADJ_OFFSET_SINGLESHOT) + if (txc->modes != ADJ_OFFSET_SINGLESHOT && + txc->modes != ADJ_OFFSET_SS_READ) return -EINVAL; + } if (txc->modes != ADJ_OFFSET_SINGLESHOT && (txc->modes & ADJ_OFFSET)) /* adjustment Offset limited to +- .512 seconds */ @@ -372,7 +374,8 @@ int do_adjtimex(struct timex *txc) leave: if ((time_status & (STA_UNSYNC|STA_CLOCKERR)) != 0) result = TIME_ERROR; - if ((txc->modes & ADJ_OFFSET_SINGLESHOT) == ADJ_OFFSET_SINGLESHOT) + if ((txc->modes == ADJ_OFFSET_SINGLESHOT) || + (txc->modes == ADJ_OFFSET_SS_READ)) txc->offset = save_adjust; else txc->offset = ((long)shift_right(time_offset, SHIFT_UPDATE)) * diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c index aa82d7bf478a..5b86698faa0b 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/time/tick-sched.c b/kernel/time/tick-sched.c index 27a2338deb4a..cb89fa8db110 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -133,6 +133,8 @@ void tick_nohz_update_jiffies(void) if (!ts->tick_stopped) return; + touch_softlockup_watchdog(); + cpu_clear(cpu, nohz_cpu_mask); now = ktime_get(); diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index e5e466b27598..ab46ae8c062b 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -335,9 +335,9 @@ static int timekeeping_suspend(struct sys_device *dev, pm_message_t state) /* sysfs resume/suspend bits for timekeeping */ static struct sysdev_class timekeeping_sysclass = { + .name = "timekeeping", .resume = timekeeping_resume, .suspend = timekeeping_suspend, - set_kset_name("timekeeping"), }; static struct sys_device device_timer = { diff --git a/kernel/timer.c b/kernel/timer.c index a05817c021d6..2a00c22203f3 100644 --- a/kernel/timer.c +++ b/kernel/timer.c @@ -978,7 +978,7 @@ asmlinkage long sys_getppid(void) int pid; rcu_read_lock(); - pid = task_ppid_nr_ns(current, current->nsproxy->pid_ns); + pid = task_tgid_nr_ns(current->real_parent, current->nsproxy->pid_ns); rcu_read_unlock(); return pid; @@ -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; @@ -1289,7 +1289,7 @@ static void migrate_timer_list(tvec_base_t *new_base, struct list_head *head) } } -static void __devinit migrate_timers(int cpu) +static void __cpuinit migrate_timers(int cpu) { tvec_base_t *old_base; tvec_base_t *new_base; diff --git a/kernel/user.c b/kernel/user.c index 0f3aa0234107..ab4fd706993b 100644 --- a/kernel/user.c +++ b/kernel/user.c @@ -115,7 +115,7 @@ static void sched_switch_user(struct task_struct *p) { } #if defined(CONFIG_FAIR_USER_SCHED) && defined(CONFIG_SYSFS) -static struct kobject uids_kobject; /* represents /sys/kernel/uids directory */ +static struct kset *uids_kset; /* represents the /sys/kernel/uids/ directory */ static DEFINE_MUTEX(uids_mutex); static inline void uids_mutex_lock(void) @@ -128,86 +128,83 @@ static inline void uids_mutex_unlock(void) mutex_unlock(&uids_mutex); } -/* return cpu shares held by the user */ -static ssize_t cpu_shares_show(struct kset *kset, char *buffer) +/* uid directory attributes */ +static ssize_t cpu_shares_show(struct kobject *kobj, + struct kobj_attribute *attr, + char *buf) { - struct user_struct *up = container_of(kset, struct user_struct, kset); + struct user_struct *up = container_of(kobj, struct user_struct, kobj); - return sprintf(buffer, "%lu\n", sched_group_shares(up->tg)); + return sprintf(buf, "%lu\n", sched_group_shares(up->tg)); } -/* modify cpu shares held by the user */ -static ssize_t cpu_shares_store(struct kset *kset, const char *buffer, - size_t size) +static ssize_t cpu_shares_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t size) { - struct user_struct *up = container_of(kset, struct user_struct, kset); + struct user_struct *up = container_of(kobj, struct user_struct, kobj); unsigned long shares; int rc; - sscanf(buffer, "%lu", &shares); + sscanf(buf, "%lu", &shares); rc = sched_group_set_shares(up->tg, shares); return (rc ? rc : size); } -static void user_attr_init(struct subsys_attribute *sa, char *name, int mode) +static struct kobj_attribute cpu_share_attr = + __ATTR(cpu_share, 0644, cpu_shares_show, cpu_shares_store); + +/* default attributes per uid directory */ +static struct attribute *uids_attributes[] = { + &cpu_share_attr.attr, + NULL +}; + +/* the lifetime of user_struct is not managed by the core (now) */ +static void uids_release(struct kobject *kobj) { - sa->attr.name = name; - sa->attr.mode = mode; - sa->show = cpu_shares_show; - sa->store = cpu_shares_store; + return; } -/* Create "/sys/kernel/uids/<uid>" directory and - * "/sys/kernel/uids/<uid>/cpu_share" file for this user. - */ -static int user_kobject_create(struct user_struct *up) +static struct kobj_type uids_ktype = { + .sysfs_ops = &kobj_sysfs_ops, + .default_attrs = uids_attributes, + .release = uids_release, +}; + +/* create /sys/kernel/uids/<uid>/cpu_share file for this user */ +static int uids_user_create(struct user_struct *up) { - struct kset *kset = &up->kset; - struct kobject *kobj = &kset->kobj; + struct kobject *kobj = &up->kobj; int error; - memset(kset, 0, sizeof(struct kset)); - kobj->parent = &uids_kobject; /* create under /sys/kernel/uids dir */ - kobject_set_name(kobj, "%d", up->uid); - kset_init(kset); - user_attr_init(&up->user_attr, "cpu_share", 0644); - - error = kobject_add(kobj); - if (error) + memset(kobj, 0, sizeof(struct kobject)); + kobj->kset = uids_kset; + error = kobject_init_and_add(kobj, &uids_ktype, NULL, "%d", up->uid); + if (error) { + kobject_put(kobj); goto done; - - error = sysfs_create_file(kobj, &up->user_attr.attr); - if (error) - kobject_del(kobj); + } kobject_uevent(kobj, KOBJ_ADD); - done: return error; } -/* create these in sysfs filesystem: +/* create these entries in sysfs: * "/sys/kernel/uids" directory * "/sys/kernel/uids/0" directory (for root user) * "/sys/kernel/uids/0/cpu_share" file (for root user) */ -int __init uids_kobject_init(void) +int __init uids_sysfs_init(void) { - int error; - - /* create under /sys/kernel dir */ - uids_kobject.parent = &kernel_subsys.kobj; - uids_kobject.kset = &kernel_subsys; - kobject_set_name(&uids_kobject, "uids"); - kobject_init(&uids_kobject); - - error = kobject_add(&uids_kobject); - if (!error) - error = user_kobject_create(&root_user); + uids_kset = kset_create_and_add("uids", NULL, kernel_kobj); + if (!uids_kset) + return -ENOMEM; - return error; + return uids_user_create(&root_user); } /* work function to remove sysfs directory for a user and free up @@ -216,7 +213,6 @@ int __init uids_kobject_init(void) static void remove_user_sysfs_dir(struct work_struct *w) { struct user_struct *up = container_of(w, struct user_struct, work); - struct kobject *kobj = &up->kset.kobj; unsigned long flags; int remove_user = 0; @@ -238,9 +234,9 @@ static void remove_user_sysfs_dir(struct work_struct *w) if (!remove_user) goto done; - sysfs_remove_file(kobj, &up->user_attr.attr); - kobject_uevent(kobj, KOBJ_REMOVE); - kobject_del(kobj); + kobject_uevent(&up->kobj, KOBJ_REMOVE); + kobject_del(&up->kobj); + kobject_put(&up->kobj); sched_destroy_user(up); key_put(up->uid_keyring); @@ -267,7 +263,8 @@ static inline void free_user(struct user_struct *up, unsigned long flags) #else /* CONFIG_FAIR_USER_SCHED && CONFIG_SYSFS */ -static inline int user_kobject_create(struct user_struct *up) { return 0; } +int uids_sysfs_init(void) { return 0; } +static inline int uids_user_create(struct user_struct *up) { return 0; } static inline void uids_mutex_lock(void) { } static inline void uids_mutex_unlock(void) { } @@ -324,7 +321,7 @@ struct user_struct * alloc_uid(struct user_namespace *ns, uid_t uid) struct hlist_head *hashent = uidhashentry(ns, uid); struct user_struct *up; - /* Make uid_hash_find() + user_kobject_create() + uid_hash_insert() + /* Make uid_hash_find() + uids_user_create() + uid_hash_insert() * atomic. */ uids_mutex_lock(); @@ -337,8 +334,11 @@ struct user_struct * alloc_uid(struct user_namespace *ns, uid_t uid) struct user_struct *new; new = kmem_cache_alloc(uid_cachep, GFP_KERNEL); - if (!new) + if (!new) { + uids_mutex_unlock(); return NULL; + } + new->uid = uid; atomic_set(&new->__count, 1); atomic_set(&new->processes, 0); @@ -355,6 +355,7 @@ struct user_struct * alloc_uid(struct user_namespace *ns, uid_t uid) if (alloc_uid_keyring(new, current) < 0) { kmem_cache_free(uid_cachep, new); + uids_mutex_unlock(); return NULL; } @@ -362,10 +363,11 @@ struct user_struct * alloc_uid(struct user_namespace *ns, uid_t uid) key_put(new->uid_keyring); key_put(new->session_keyring); kmem_cache_free(uid_cachep, new); + uids_mutex_unlock(); return NULL; } - if (user_kobject_create(new)) { + if (uids_user_create(new)) { sched_destroy_user(new); key_put(new->uid_keyring); key_put(new->session_keyring); diff --git a/kernel/utsname_sysctl.c b/kernel/utsname_sysctl.c index c76c06466bfd..fe3a56c2256d 100644 --- a/kernel/utsname_sysctl.c +++ b/kernel/utsname_sysctl.c @@ -18,6 +18,10 @@ static void *get_uts(ctl_table *table, int write) { char *which = table->data; + struct uts_namespace *uts_ns; + + uts_ns = current->nsproxy->uts_ns; + which = (which - (char *)&init_uts_ns) + (char *)uts_ns; if (!write) down_read(&uts_sem); diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 52d5e7c9a8e6..8db0b597509e 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -722,7 +722,8 @@ static void start_workqueue_thread(struct cpu_workqueue_struct *cwq, int cpu) struct workqueue_struct *__create_workqueue_key(const char *name, int singlethread, int freezeable, - struct lock_class_key *key) + struct lock_class_key *key, + const char *lock_name) { struct workqueue_struct *wq; struct cpu_workqueue_struct *cwq; @@ -739,7 +740,7 @@ struct workqueue_struct *__create_workqueue_key(const char *name, } wq->name = name; - lockdep_init_map(&wq->lockdep_map, name, key, 0); + lockdep_init_map(&wq->lockdep_map, lock_name, key, 0); wq->singlethread = singlethread; wq->freezeable = freezeable; INIT_LIST_HEAD(&wq->list); |