6 files changed, 199 insertions, 113 deletions

diff --git a/kernel/params.c b/kernel/params.c
index 08107d181758..0da1411222b9 100644
--- a/kernel/params.c
+++ b/kernel/params.c
@@ -719,9 +719,7 @@ void destroy_params(const struct kernel_param *params, unsigned num)
                         params[i].ops->free(params[i].arg);
 }
 
-static void __init kernel_add_sysfs_param(const char *name,
-                                          struct kernel_param *kparam,
-                                          unsigned int name_skip)
+static struct module_kobject * __init locate_module_kobject(const char *name)
 {
         struct module_kobject *mk;
         struct kobject *kobj;
@@ -729,10 +727,7 @@ static void __init kernel_add_sysfs_param(const char *name,
 
         kobj = kset_find_obj(module_kset, name);
         if (kobj) {
-                /* We already have one.  Remove params so we can add more. */
                 mk = to_module_kobject(kobj);
-                /* We need to remove it before adding parameters. */
-                sysfs_remove_group(&mk->kobj, &mk->mp->grp);
         } else {
                 mk = kzalloc(sizeof(struct module_kobject), GFP_KERNEL);
                 BUG_ON(!mk);
@@ -743,15 +738,36 @@ static void __init kernel_add_sysfs_param(const char *name,
                                            "%s", name);
                 if (err) {
                         kobject_put(&mk->kobj);
-                        printk(KERN_ERR "Module '%s' failed add to sysfs, "
-                               "error number %d\n", name, err);
-                        printk(KERN_ERR "The system will be unstable now.\n");
-                        return;
+                        printk(KERN_ERR
+                                "Module '%s' failed add to sysfs, error number %d\n",
+                                name, err);
+                        printk(KERN_ERR
+                                "The system will be unstable now.\n");
+                        return NULL;
                 }
-                /* So that exit path is even. */
+
+                /* So that we hold reference in both cases. */
                 kobject_get(&mk->kobj);
         }
 
+        return mk;
+}
+
+static void __init kernel_add_sysfs_param(const char *name,
+                                          struct kernel_param *kparam,
+                                          unsigned int name_skip)
+{
+        struct module_kobject *mk;
+        int err;
+
+        mk = locate_module_kobject(name);
+        if (!mk)
+                return;
+
+        /* We need to remove old parameters before adding more. */
+        if (mk->mp)
+                sysfs_remove_group(&mk->kobj, &mk->mp->grp);
+
         /* These should not fail at boot. */
         err = add_sysfs_param(mk, kparam, kparam->name + name_skip);
         BUG_ON(err);
@@ -796,6 +812,32 @@ static void __init param_sysfs_builtin(void)
         }
 }
 
+ssize_t __modver_version_show(struct module_attribute *mattr,
+                              struct module *mod, char *buf)
+{
+        struct module_version_attribute *vattr =
+                container_of(mattr, struct module_version_attribute, mattr);
+
+        return sprintf(buf, "%s\n", vattr->version);
+}
+
+extern struct module_version_attribute __start___modver[], __stop___modver[];
+
+static void __init version_sysfs_builtin(void)
+{
+        const struct module_version_attribute *vattr;
+        struct module_kobject *mk;
+        int err;
+
+        for (vattr = __start___modver; vattr < __stop___modver; vattr++) {
+                mk = locate_module_kobject(vattr->module_name);
+                if (mk) {
+                        err = sysfs_create_file(&mk->kobj, &vattr->mattr.attr);
+                        kobject_uevent(&mk->kobj, KOBJ_ADD);
+                        kobject_put(&mk->kobj);
+                }
+        }
+}
 
 /* module-related sysfs stuff */
 
@@ -875,6 +917,7 @@ static int __init param_sysfs_init(void)
         }
         module_sysfs_initialized = 1;
 
+        version_sysfs_builtin();
         param_sysfs_builtin();
 
         return 0;
diff --git a/kernel/perf_event.c b/kernel/perf_event.c
index 84522c796987..126a302c481c 100644
--- a/kernel/perf_event.c
+++ b/kernel/perf_event.c
@@ -2201,13 +2201,6 @@ find_lively_task_by_vpid(pid_t vpid)
         if (!task)
                 return ERR_PTR(-ESRCH);
 
-        /*
-         * Can't attach events to a dying task.
-         */
-        err = -ESRCH;
-        if (task->flags & PF_EXITING)
-                goto errout;
-
         /* Reuse ptrace permission checks for now. */
         err = -EACCES;
         if (!ptrace_may_access(task, PTRACE_MODE_READ))
@@ -2268,14 +2261,27 @@ retry:
 
                 get_ctx(ctx);
 
-                if (cmpxchg(&task->perf_event_ctxp[ctxn], NULL, ctx)) {
-                        /*
-                         * We raced with some other task; use
-                         * the context they set.
-                         */
+                err = 0;
+                mutex_lock(&task->perf_event_mutex);
+                /*
+                 * If it has already passed perf_event_exit_task().
+                 * we must see PF_EXITING, it takes this mutex too.
+                 */
+                if (task->flags & PF_EXITING)
+                        err = -ESRCH;
+                else if (task->perf_event_ctxp[ctxn])
+                        err = -EAGAIN;
+                else
+                        rcu_assign_pointer(task->perf_event_ctxp[ctxn], ctx);
+                mutex_unlock(&task->perf_event_mutex);
+
+                if (unlikely(err)) {
                         put_task_struct(task);
                         kfree(ctx);
-                        goto retry;
+
+                        if (err == -EAGAIN)
+                                goto retry;
+                        goto errout;
                 }
         }
 
@@ -5374,6 +5380,8 @@ free_dev:
         goto out;
 }
 
+static struct lock_class_key cpuctx_mutex;
+
 int perf_pmu_register(struct pmu *pmu, char *name, int type)
 {
         int cpu, ret;
@@ -5422,6 +5430,7 @@ skip_type:
 
                 cpuctx = per_cpu_ptr(pmu->pmu_cpu_context, cpu);
                 __perf_event_init_context(&cpuctx->ctx);
+                lockdep_set_class(&cpuctx->ctx.mutex, &cpuctx_mutex);
                 cpuctx->ctx.type = cpu_context;
                 cpuctx->ctx.pmu = pmu;
                 cpuctx->jiffies_interval = 1;
@@ -6127,7 +6136,7 @@ static void perf_event_exit_task_context(struct task_struct *child, int ctxn)
          * scheduled, so we are now safe from rescheduling changing
          * our context.
          */
-        child_ctx = child->perf_event_ctxp[ctxn];
+        child_ctx = rcu_dereference_raw(child->perf_event_ctxp[ctxn]);
         task_ctx_sched_out(child_ctx, EVENT_ALL);
 
         /*
@@ -6440,11 +6449,6 @@ int perf_event_init_context(struct task_struct *child, int ctxn)
         unsigned long flags;
         int ret = 0;
 
-        child->perf_event_ctxp[ctxn] = NULL;
-
-        mutex_init(&child->perf_event_mutex);
-        INIT_LIST_HEAD(&child->perf_event_list);
-
         if (likely(!parent->perf_event_ctxp[ctxn]))
                 return 0;
 
@@ -6533,6 +6537,10 @@ int perf_event_init_task(struct task_struct *child)
 {
         int ctxn, ret;
 
+        memset(child->perf_event_ctxp, 0, sizeof(child->perf_event_ctxp));
+        mutex_init(&child->perf_event_mutex);
+        INIT_LIST_HEAD(&child->perf_event_list);
+
         for_each_task_context_nr(ctxn) {
                 ret = perf_event_init_context(child, ctxn);
                 if (ret)
diff --git a/kernel/printk.c b/kernel/printk.c
index 53d9a9ec88e6..2ddbdc73aade 100644
--- a/kernel/printk.c
+++ b/kernel/printk.c
@@ -97,7 +97,7 @@ static int console_locked, console_suspended;
 /*
  * logbuf_lock protects log_buf, log_start, log_end, con_start and logged_chars
  * It is also used in interesting ways to provide interlocking in
- * release_console_sem().
+ * console_unlock();.
  */
 static DEFINE_SPINLOCK(logbuf_lock);
 
@@ -501,7 +501,7 @@ static void _call_console_drivers(unsigned start,
 /*
  * Call the console drivers, asking them to write out
  * log_buf[start] to log_buf[end - 1].
- * The console_sem must be held.
+ * The console_lock must be held.
  */
 static void call_console_drivers(unsigned start, unsigned end)
 {
@@ -604,11 +604,11 @@ static int have_callable_console(void)
  *
  * This is printk().  It can be called from any context.  We want it to work.
  *
- * We try to grab the console_sem.  If we succeed, it's easy - we log the output and
+ * We try to grab the console_lock.  If we succeed, it's easy - we log the output and
  * call the console drivers.  If we fail to get the semaphore we place the output
  * into the log buffer and return.  The current holder of the console_sem will
- * notice the new output in release_console_sem() and will send it to the
- * consoles before releasing the semaphore.
+ * notice the new output in console_unlock(); and will send it to the
+ * consoles before releasing the lock.
  *
  * One effect of this deferred printing is that code which calls printk() and
  * then changes console_loglevel may break. This is because console_loglevel
@@ -659,19 +659,19 @@ static inline int can_use_console(unsigned int cpu)
 /*
  * Try to get console ownership to actually show the kernel
  * messages from a 'printk'. Return true (and with the
- * console_semaphore held, and 'console_locked' set) if it
+ * console_lock held, and 'console_locked' set) if it
  * is successful, false otherwise.
  *
  * This gets called with the 'logbuf_lock' spinlock held and
  * interrupts disabled. It should return with 'lockbuf_lock'
  * released but interrupts still disabled.
  */
-static int acquire_console_semaphore_for_printk(unsigned int cpu)
+static int console_trylock_for_printk(unsigned int cpu)
         __releases(&logbuf_lock)
 {
         int retval = 0;
 
-        if (!try_acquire_console_sem()) {
+        if (console_trylock()) {
                 retval = 1;
 
                 /*
@@ -827,12 +827,12 @@ asmlinkage int vprintk(const char *fmt, va_list args)
          * actual magic (print out buffers, wake up klogd,
          * etc). 
          *
-         * The acquire_console_semaphore_for_printk() function
+         * The console_trylock_for_printk() function
          * will release 'logbuf_lock' regardless of whether it
          * actually gets the semaphore or not.
          */
-        if (acquire_console_semaphore_for_printk(this_cpu))
-                release_console_sem();
+        if (console_trylock_for_printk(this_cpu))
+                console_unlock();
 
         lockdep_on();
 out_restore_irqs:
@@ -993,7 +993,7 @@ void suspend_console(void)
         if (!console_suspend_enabled)
                 return;
         printk("Suspending console(s) (use no_console_suspend to debug)\n");
-        acquire_console_sem();
+        console_lock();
         console_suspended = 1;
         up(&console_sem);
 }
@@ -1004,7 +1004,7 @@ void resume_console(void)
                 return;
         down(&console_sem);
         console_suspended = 0;
-        release_console_sem();
+        console_unlock();
 }
 
 /**
@@ -1027,21 +1027,21 @@ static int __cpuinit console_cpu_notify(struct notifier_block *self,
         case CPU_DYING:
         case CPU_DOWN_FAILED:
         case CPU_UP_CANCELED:
-                acquire_console_sem();
-                release_console_sem();
+                console_lock();
+                console_unlock();
         }
         return NOTIFY_OK;
 }
 
 /**
- * acquire_console_sem - lock the console system for exclusive use.
+ * console_lock - lock the console system for exclusive use.
  *
- * Acquires a semaphore which guarantees that the caller has
+ * Acquires a lock which guarantees that the caller has
  * exclusive access to the console system and the console_drivers list.
  *
  * Can sleep, returns nothing.
  */
-void acquire_console_sem(void)
+void console_lock(void)
 {
         BUG_ON(in_interrupt());
         down(&console_sem);
@@ -1050,21 +1050,29 @@ void acquire_console_sem(void)
         console_locked = 1;
         console_may_schedule = 1;
 }
-EXPORT_SYMBOL(acquire_console_sem);
+EXPORT_SYMBOL(console_lock);
 
-int try_acquire_console_sem(void)
+/**
+ * console_trylock - try to lock the console system for exclusive use.
+ *
+ * Tried to acquire a lock which guarantees that the caller has
+ * exclusive access to the console system and the console_drivers list.
+ *
+ * returns 1 on success, and 0 on failure to acquire the lock.
+ */
+int console_trylock(void)
 {
         if (down_trylock(&console_sem))
-                return -1;
+                return 0;
         if (console_suspended) {
                 up(&console_sem);
-                return -1;
+                return 0;
         }
         console_locked = 1;
         console_may_schedule = 0;
-        return 0;
+        return 1;
 }
-EXPORT_SYMBOL(try_acquire_console_sem);
+EXPORT_SYMBOL(console_trylock);
 
 int is_console_locked(void)
 {
@@ -1095,20 +1103,20 @@ void wake_up_klogd(void)
 }
 
 /**
- * release_console_sem - unlock the console system
+ * console_unlock - unlock the console system
  *
- * Releases the semaphore which the caller holds on the console system
+ * Releases the console_lock which the caller holds on the console system
  * and the console driver list.
  *
- * While the semaphore was held, console output may have been buffered
- * by printk().  If this is the case, release_console_sem() emits
- * the output prior to releasing the semaphore.
+ * While the console_lock was held, console output may have been buffered
+ * by printk().  If this is the case, console_unlock(); emits
+ * the output prior to releasing the lock.
  *
  * If there is output waiting for klogd, we wake it up.
  *
- * release_console_sem() may be called from any context.
+ * console_unlock(); may be called from any context.
  */
-void release_console_sem(void)
+void console_unlock(void)
 {
         unsigned long flags;
         unsigned _con_start, _log_end;
@@ -1141,7 +1149,7 @@ void release_console_sem(void)
         if (wake_klogd)
                 wake_up_klogd();
 }
-EXPORT_SYMBOL(release_console_sem);
+EXPORT_SYMBOL(console_unlock);
 
 /**
  * console_conditional_schedule - yield the CPU if required
@@ -1150,7 +1158,7 @@ EXPORT_SYMBOL(release_console_sem);
  * if this CPU should yield the CPU to another task, do
  * so here.
  *
- * Must be called within acquire_console_sem().
+ * Must be called within console_lock();.
  */
 void __sched console_conditional_schedule(void)
 {
@@ -1171,14 +1179,14 @@ void console_unblank(void)
                 if (down_trylock(&console_sem) != 0)
                         return;
         } else
-                acquire_console_sem();
+                console_lock();
 
         console_locked = 1;
         console_may_schedule = 0;
         for_each_console(c)
                 if ((c->flags & CON_ENABLED) && c->unblank)
                         c->unblank();
-        release_console_sem();
+        console_unlock();
 }
 
 /*
@@ -1189,7 +1197,7 @@ struct tty_driver *console_device(int *index)
         struct console *c;
         struct tty_driver *driver = NULL;
 
-        acquire_console_sem();
+        console_lock();
         for_each_console(c) {
                 if (!c->device)
                         continue;
@@ -1197,7 +1205,7 @@ struct tty_driver *console_device(int *index)
                 if (driver)
                         break;
         }
-        release_console_sem();
+        console_unlock();
         return driver;
 }
 
@@ -1208,17 +1216,17 @@ struct tty_driver *console_device(int *index)
  */
 void console_stop(struct console *console)
 {
-        acquire_console_sem();
+        console_lock();
         console->flags &= ~CON_ENABLED;
-        release_console_sem();
+        console_unlock();
 }
 EXPORT_SYMBOL(console_stop);
 
 void console_start(struct console *console)
 {
-        acquire_console_sem();
+        console_lock();
         console->flags |= CON_ENABLED;
-        release_console_sem();
+        console_unlock();
 }
 EXPORT_SYMBOL(console_start);
 
@@ -1340,7 +1348,7 @@ void register_console(struct console *newcon)
          *      Put this console in the list - keep the
          *      preferred driver at the head of the list.
          */
-        acquire_console_sem();
+        console_lock();
         if ((newcon->flags & CON_CONSDEV) || console_drivers == NULL) {
                 newcon->next = console_drivers;
                 console_drivers = newcon;
@@ -1352,14 +1360,14 @@ void register_console(struct console *newcon)
         }
         if (newcon->flags & CON_PRINTBUFFER) {
                 /*
-                 * release_console_sem() will print out the buffered messages
+                 * console_unlock(); will print out the buffered messages
                  * for us.
                  */
                 spin_lock_irqsave(&logbuf_lock, flags);
                 con_start = log_start;
                 spin_unlock_irqrestore(&logbuf_lock, flags);
         }
-        release_console_sem();
+        console_unlock();
         console_sysfs_notify();
 
         /*
@@ -1396,7 +1404,7 @@ int unregister_console(struct console *console)
                 return braille_unregister_console(console);
 #endif
 
-        acquire_console_sem();
+        console_lock();
         if (console_drivers == console) {
                 console_drivers=console->next;
                 res = 0;
@@ -1418,7 +1426,7 @@ int unregister_console(struct console *console)
         if (console_drivers != NULL && console->flags & CON_CONSDEV)
                 console_drivers->flags |= CON_CONSDEV;
 
-        release_console_sem();
+        console_unlock();
         console_sysfs_notify();
         return res;
 }
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 77e9166d7bbf..0c26e2df450e 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -699,7 +699,8 @@ account_entity_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se)
         cfs_rq->nr_running--;
 }
 
-#if defined CONFIG_SMP && defined CONFIG_FAIR_GROUP_SCHED
+#ifdef CONFIG_FAIR_GROUP_SCHED
+# ifdef CONFIG_SMP
 static void update_cfs_rq_load_contribution(struct cfs_rq *cfs_rq,
                                             int global_update)
 {
@@ -721,10 +722,10 @@ static void update_cfs_load(struct cfs_rq *cfs_rq, int global_update)
         u64 now, delta;
         unsigned long load = cfs_rq->load.weight;
 
-        if (!cfs_rq)
+        if (cfs_rq->tg == &root_task_group)
                 return;
 
-        now = rq_of(cfs_rq)->clock;
+        now = rq_of(cfs_rq)->clock_task;
         delta = now - cfs_rq->load_stamp;
 
         /* truncate load history at 4 idle periods */
@@ -762,6 +763,51 @@ static void update_cfs_load(struct cfs_rq *cfs_rq, int global_update)
                 list_del_leaf_cfs_rq(cfs_rq);
 }
 
+static long calc_cfs_shares(struct cfs_rq *cfs_rq, struct task_group *tg,
+                                long weight_delta)
+{
+        long load_weight, load, shares;
+
+        load = cfs_rq->load.weight + weight_delta;
+
+        load_weight = atomic_read(&tg->load_weight);
+        load_weight -= cfs_rq->load_contribution;
+        load_weight += load;
+
+        shares = (tg->shares * load);
+        if (load_weight)
+                shares /= load_weight;
+
+        if (shares < MIN_SHARES)
+                shares = MIN_SHARES;
+        if (shares > tg->shares)
+                shares = tg->shares;
+
+        return shares;
+}
+
+static void update_entity_shares_tick(struct cfs_rq *cfs_rq)
+{
+        if (cfs_rq->load_unacc_exec_time > sysctl_sched_shares_window) {
+                update_cfs_load(cfs_rq, 0);
+                update_cfs_shares(cfs_rq, 0);
+        }
+}
+# else /* CONFIG_SMP */
+static void update_cfs_load(struct cfs_rq *cfs_rq, int global_update)
+{
+}
+
+static inline long calc_cfs_shares(struct cfs_rq *cfs_rq, struct task_group *tg,
+                                long weight_delta)
+{
+        return tg->shares;
+}
+
+static inline void update_entity_shares_tick(struct cfs_rq *cfs_rq)
+{
+}
+# endif /* CONFIG_SMP */
 static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se,
                             unsigned long weight)
 {
@@ -782,41 +828,20 @@ static void update_cfs_shares(struct cfs_rq *cfs_rq, long weight_delta)
 {
         struct task_group *tg;
         struct sched_entity *se;
-        long load_weight, load, shares;
-
-        if (!cfs_rq)
-                return;
+        long shares;
 
         tg = cfs_rq->tg;
         se = tg->se[cpu_of(rq_of(cfs_rq))];
         if (!se)
                 return;
-
-        load = cfs_rq->load.weight + weight_delta;
-
-        load_weight = atomic_read(&tg->load_weight);
-        load_weight -= cfs_rq->load_contribution;
-        load_weight += load;
-
-        shares = (tg->shares * load);
-        if (load_weight)
-                shares /= load_weight;
-
-        if (shares < MIN_SHARES)
-                shares = MIN_SHARES;
-        if (shares > tg->shares)
-                shares = tg->shares;
+#ifndef CONFIG_SMP
+        if (likely(se->load.weight == tg->shares))
+                return;
+#endif
+        shares = calc_cfs_shares(cfs_rq, tg, weight_delta);
 
         reweight_entity(cfs_rq_of(se), se, shares);
 }
-
-static void update_entity_shares_tick(struct cfs_rq *cfs_rq)
-{
-        if (cfs_rq->load_unacc_exec_time > sysctl_sched_shares_window) {
-                update_cfs_load(cfs_rq, 0);
-                update_cfs_shares(cfs_rq, 0);
-        }
-}
 #else /* CONFIG_FAIR_GROUP_SCHED */
 static void update_cfs_load(struct cfs_rq *cfs_rq, int global_update)
 {
@@ -1404,7 +1429,7 @@ static inline unsigned long effective_load(struct task_group *tg, int cpu,
 
 static int wake_affine(struct sched_domain *sd, struct task_struct *p, int sync)
 {
-        unsigned long this_load, load;
+        s64 this_load, load;
         int idx, this_cpu, prev_cpu;
         unsigned long tl_per_task;
         struct task_group *tg;
@@ -1443,8 +1468,8 @@ static int wake_affine(struct sched_domain *sd, struct task_struct *p, int sync)
          * Otherwise check if either cpus are near enough in load to allow this
          * task to be woken on this_cpu.
          */
-        if (this_load) {
-                unsigned long this_eff_load, prev_eff_load;
+        if (this_load > 0) {
+                s64 this_eff_load, prev_eff_load;
 
                 this_eff_load = 100;
                 this_eff_load *= power_of(prev_cpu);
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index bc86bb32e126..0f1bd83db985 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -170,7 +170,8 @@ static int proc_taint(struct ctl_table *table, int write,
 #endif
 
 #ifdef CONFIG_MAGIC_SYSRQ
-static int __sysrq_enabled; /* Note: sysrq code ises it's own private copy */
+/* Note: sysrq code uses it's own private copy */
+static int __sysrq_enabled = SYSRQ_DEFAULT_ENABLE;
 
 static int sysrq_sysctl_handler(ctl_table *table, int write,
                                 void __user *buffer, size_t *lenp,
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 3e216e01bbd1..c55ea2433471 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -642,8 +642,7 @@ static void tick_nohz_switch_to_nohz(void)
         }
         local_irq_enable();
 
-        printk(KERN_INFO "Switched to NOHz mode on CPU #%d\n",
-               smp_processor_id());
+        printk(KERN_INFO "Switched to NOHz mode on CPU #%d\n", smp_processor_id());
 }
 
 /*
@@ -795,8 +794,10 @@ void tick_setup_sched_timer(void)
         }
 
 #ifdef CONFIG_NO_HZ
-        if (tick_nohz_enabled)
+        if (tick_nohz_enabled) {
                 ts->nohz_mode = NOHZ_MODE_HIGHRES;
+                printk(KERN_INFO "Switched to NOHz mode on CPU #%d\n", smp_processor_id());
+        }
 #endif
 }
 #endif /* HIGH_RES_TIMERS */