27 files changed, 297 insertions, 112 deletions

diff --git a/kernel/fork.c b/kernel/fork.c
index a66fbde20715..4854c2c4a82e 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1179,10 +1179,6 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 #endif
         clear_all_latency_tracing(p);
 
-        /* Our parent execution domain becomes current domain
-           These must match for thread signalling to apply */
-        p->parent_exec_id = p->self_exec_id;
-
         /* ok, now we should be set up.. */
         p->exit_signal = (clone_flags & CLONE_THREAD) ? -1 : (clone_flags & CSIGNAL);
         p->pdeath_signal = 0;
@@ -1220,10 +1216,13 @@ static struct task_struct *copy_process(unsigned long clone_flags,
                 set_task_cpu(p, smp_processor_id());
 
         /* CLONE_PARENT re-uses the old parent */
-        if (clone_flags & (CLONE_PARENT|CLONE_THREAD))
+        if (clone_flags & (CLONE_PARENT|CLONE_THREAD)) {
                 p->real_parent = current->real_parent;
-        else
+                p->parent_exec_id = current->parent_exec_id;
+        } else {
                 p->real_parent = current;
+                p->parent_exec_id = current->self_exec_id;
+        }
 
         spin_lock(&current->sighand->siglock);
 
diff --git a/kernel/kexec.c b/kernel/kexec.c
index 8a6d7b08864e..483899578259 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -1465,6 +1465,11 @@ int kernel_kexec(void)
                 error = device_power_down(PMSG_FREEZE);
                 if (error)
                         goto Enable_irqs;
+
+                /* Suspend system devices */
+                error = sysdev_suspend(PMSG_FREEZE);
+                if (error)
+                        goto Power_up_devices;
         } else
 #endif
         {
@@ -1477,6 +1482,8 @@ int kernel_kexec(void)
 
 #ifdef CONFIG_KEXEC_JUMP
         if (kexec_image->preserve_context) {
+                sysdev_resume();
+ Power_up_devices:
                 device_power_up(PMSG_RESTORE);
  Enable_irqs:
                 local_irq_enable();
diff --git a/kernel/module.c b/kernel/module.c
index ba22484a987e..1196f5d11700 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -2015,14 +2015,6 @@ static noinline struct module *load_module(void __user *umod,
         if (err < 0)
                 goto free_mod;
 
-#if defined(CONFIG_MODULE_UNLOAD) && defined(CONFIG_SMP)
-        mod->refptr = percpu_modalloc(sizeof(local_t), __alignof__(local_t),
-                                      mod->name);
-        if (!mod->refptr) {
-                err = -ENOMEM;
-                goto free_mod;
-        }
-#endif
         if (pcpuindex) {
                 /* We have a special allocation for this section. */
                 percpu = percpu_modalloc(sechdrs[pcpuindex].sh_size,
@@ -2030,7 +2022,7 @@ static noinline struct module *load_module(void __user *umod,
                                          mod->name);
                 if (!percpu) {
                         err = -ENOMEM;
-                        goto free_percpu;
+                        goto free_mod;
                 }
                 sechdrs[pcpuindex].sh_flags &= ~(unsigned long)SHF_ALLOC;
                 mod->percpu = percpu;
@@ -2082,6 +2074,14 @@ static noinline struct module *load_module(void __user *umod,
         /* Module has been moved. */
         mod = (void *)sechdrs[modindex].sh_addr;
 
+#if defined(CONFIG_MODULE_UNLOAD) && defined(CONFIG_SMP)
+        mod->refptr = percpu_modalloc(sizeof(local_t), __alignof__(local_t),
+                                      mod->name);
+        if (!mod->refptr) {
+                err = -ENOMEM;
+                goto free_init;
+        }
+#endif
         /* Now we've moved module, initialize linked lists, etc. */
         module_unload_init(mod);
 
@@ -2288,15 +2288,17 @@ static noinline struct module *load_module(void __user *umod,
         ftrace_release(mod->module_core, mod->core_size);
  free_unload:
         module_unload_free(mod);
+ free_init:
+#if defined(CONFIG_MODULE_UNLOAD) && defined(CONFIG_SMP)
+        percpu_modfree(mod->refptr);
+#endif
         module_free(mod, mod->module_init);
  free_core:
         module_free(mod, mod->module_core);
+        /* mod will be freed with core. Don't access it beyond this line! */
  free_percpu:
         if (percpu)
                 percpu_modfree(percpu);
-#if defined(CONFIG_MODULE_UNLOAD) && defined(CONFIG_SMP)
-        percpu_modfree(mod->refptr);
-#endif
  free_mod:
         kfree(args);
  free_hdr:
diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c
index e976e505648d..8e5d9a68b022 100644
--- a/kernel/posix-cpu-timers.c
+++ b/kernel/posix-cpu-timers.c
@@ -1370,7 +1370,8 @@ static inline int fastpath_timer_check(struct task_struct *tsk)
                 if (task_cputime_expired(&group_sample, &sig->cputime_expires))
                         return 1;
         }
-        return 0;
+
+        return sig->rlim[RLIMIT_CPU].rlim_cur != RLIM_INFINITY;
 }
 
 /*
diff --git a/kernel/power/console.c b/kernel/power/console.c
index b8628be2a465..a3961b205de7 100644
--- a/kernel/power/console.c
+++ b/kernel/power/console.c
@@ -78,6 +78,12 @@ void pm_restore_console(void)
         }
         set_console(orig_fgconsole);
         release_console_sem();
+
+        if (vt_waitactive(orig_fgconsole)) {
+                pr_debug("Resume: Can't switch VCs.");
+                return;
+        }
+
         kmsg_redirect = orig_kmsg;
 }
 #endif
diff --git a/kernel/power/disk.c b/kernel/power/disk.c
index 432ee575c9ee..4a4a206b1979 100644
--- a/kernel/power/disk.c
+++ b/kernel/power/disk.c
@@ -227,6 +227,12 @@ static int create_image(int platform_mode)
                         "aborting hibernation\n");
                 goto Enable_irqs;
         }
+        sysdev_suspend(PMSG_FREEZE);
+        if (error) {
+                printk(KERN_ERR "PM: Some devices failed to power down, "
+                        "aborting hibernation\n");
+                goto Power_up_devices;
+        }
 
         if (hibernation_test(TEST_CORE))
                 goto Power_up;
@@ -242,9 +248,11 @@ static int create_image(int platform_mode)
         if (!in_suspend)
                 platform_leave(platform_mode);
  Power_up:
+        sysdev_resume();
         /* NOTE:  device_power_up() is just a resume() for devices
          * that suspended with irqs off ... no overall powerup.
          */
+ Power_up_devices:
         device_power_up(in_suspend ?
                 (error ? PMSG_RECOVER : PMSG_THAW) : PMSG_RESTORE);
  Enable_irqs:
@@ -335,6 +343,7 @@ static int resume_target_kernel(void)
                         "aborting resume\n");
                 goto Enable_irqs;
         }
+        sysdev_suspend(PMSG_QUIESCE);
         /* We'll ignore saved state, but this gets preempt count (etc) right */
         save_processor_state();
         error = restore_highmem();
@@ -357,6 +366,7 @@ static int resume_target_kernel(void)
         swsusp_free();
         restore_processor_state();
         touch_softlockup_watchdog();
+        sysdev_resume();
         device_power_up(PMSG_RECOVER);
  Enable_irqs:
         local_irq_enable();
@@ -440,6 +450,7 @@ int hibernation_platform_enter(void)
         local_irq_disable();
         error = device_power_down(PMSG_HIBERNATE);
         if (!error) {
+                sysdev_suspend(PMSG_HIBERNATE);
                 hibernation_ops->enter();
                 /* We should never get here */
                 while (1);
@@ -595,6 +606,12 @@ static int software_resume(void)
         unsigned int flags;
 
         /*
+         * If the user said "noresume".. bail out early.
+         */
+        if (noresume)
+                return 0;
+
+        /*
          * name_to_dev_t() below takes a sysfs buffer mutex when sysfs
          * is configured into the kernel. Since the regular hibernate
          * trigger path is via sysfs which takes a buffer mutex before
@@ -610,6 +627,11 @@ static int software_resume(void)
                         mutex_unlock(&pm_mutex);
                         return -ENOENT;
                 }
+                /*
+                 * Some device discovery might still be in progress; we need
+                 * to wait for this to finish.
+                 */
+                wait_for_device_probe();
                 swsusp_resume_device = name_to_dev_t(resume_file);
                 pr_debug("PM: Resume from partition %s\n", resume_file);
         } else {
diff --git a/kernel/power/main.c b/kernel/power/main.c
index b4d219016b6c..c9632f841f64 100644
--- a/kernel/power/main.c
+++ b/kernel/power/main.c
@@ -298,8 +298,12 @@ static int suspend_enter(suspend_state_t state)
                 goto Done;
         }
 
-        if (!suspend_test(TEST_CORE))
-                error = suspend_ops->enter(state);
+        error = sysdev_suspend(PMSG_SUSPEND);
+        if (!error) {
+                if (!suspend_test(TEST_CORE))
+                        error = suspend_ops->enter(state);
+                sysdev_resume();
+        }
 
         device_power_up(PMSG_RESUME);
  Done:
diff --git a/kernel/power/user.c b/kernel/power/user.c
index 005b93d839ba..6c85359364f2 100644
--- a/kernel/power/user.c
+++ b/kernel/power/user.c
@@ -95,15 +95,15 @@ static int snapshot_open(struct inode *inode, struct file *filp)
                 data->swap = swsusp_resume_device ?
                         swap_type_of(swsusp_resume_device, 0, NULL) : -1;
                 data->mode = O_RDONLY;
-                error = pm_notifier_call_chain(PM_RESTORE_PREPARE);
+                error = pm_notifier_call_chain(PM_HIBERNATION_PREPARE);
                 if (error)
-                        pm_notifier_call_chain(PM_POST_RESTORE);
+                        pm_notifier_call_chain(PM_POST_HIBERNATION);
         } else {
                 data->swap = -1;
                 data->mode = O_WRONLY;
-                error = pm_notifier_call_chain(PM_HIBERNATION_PREPARE);
+                error = pm_notifier_call_chain(PM_RESTORE_PREPARE);
                 if (error)
-                        pm_notifier_call_chain(PM_POST_HIBERNATION);
+                        pm_notifier_call_chain(PM_POST_RESTORE);
         }
         if (error)
                 atomic_inc(&snapshot_device_available);
diff --git a/kernel/printk.c b/kernel/printk.c
index 69188f226a93..e3602d0755b0 100644
--- a/kernel/printk.c
+++ b/kernel/printk.c
@@ -73,7 +73,6 @@ EXPORT_SYMBOL(oops_in_progress);
  * driver system.
  */
 static DECLARE_MUTEX(console_sem);
-static DECLARE_MUTEX(secondary_console_sem);
 struct console *console_drivers;
 EXPORT_SYMBOL_GPL(console_drivers);
 
@@ -891,12 +890,14 @@ void suspend_console(void)
         printk("Suspending console(s) (use no_console_suspend to debug)\n");
         acquire_console_sem();
         console_suspended = 1;
+        up(&console_sem);
 }
 
 void resume_console(void)
 {
         if (!console_suspend_enabled)
                 return;
+        down(&console_sem);
         console_suspended = 0;
         release_console_sem();
 }
@@ -912,11 +913,9 @@ void resume_console(void)
 void acquire_console_sem(void)
 {
         BUG_ON(in_interrupt());
-        if (console_suspended) {
-                down(&secondary_console_sem);
-                return;
-        }
         down(&console_sem);
+        if (console_suspended)
+                return;
         console_locked = 1;
         console_may_schedule = 1;
 }
@@ -926,6 +925,10 @@ int try_acquire_console_sem(void)
 {
         if (down_trylock(&console_sem))
                 return -1;
+        if (console_suspended) {
+                up(&console_sem);
+                return -1;
+        }
         console_locked = 1;
         console_may_schedule = 0;
         return 0;
@@ -979,7 +982,7 @@ void release_console_sem(void)
         unsigned wake_klogd = 0;
 
         if (console_suspended) {
-                up(&secondary_console_sem);
+                up(&console_sem);
                 return;
         }
 
diff --git a/kernel/rcuclassic.c b/kernel/rcuclassic.c
index bd5a9003497c..654c640a6b9c 100644
--- a/kernel/rcuclassic.c
+++ b/kernel/rcuclassic.c
@@ -679,8 +679,8 @@ int rcu_needs_cpu(int cpu)
 void rcu_check_callbacks(int cpu, int user)
 {
         if (user ||
-            (idle_cpu(cpu) && !in_softirq() &&
-                                hardirq_count() <= (1 << HARDIRQ_SHIFT))) {
+            (idle_cpu(cpu) && rcu_scheduler_active &&
+             !in_softirq() && hardirq_count() <= (1 << HARDIRQ_SHIFT))) {
 
                 /*
                  * Get here if this CPU took its interrupt from user
diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c
index d92a76a881aa..cae8a059cf47 100644
--- a/kernel/rcupdate.c
+++ b/kernel/rcupdate.c
@@ -44,6 +44,7 @@
 #include <linux/cpu.h>
 #include <linux/mutex.h>
 #include <linux/module.h>
+#include <linux/kernel_stat.h>
 
 enum rcu_barrier {
         RCU_BARRIER_STD,
@@ -55,6 +56,7 @@ static DEFINE_PER_CPU(struct rcu_head, rcu_barrier_head) = {NULL};
 static atomic_t rcu_barrier_cpu_count;
 static DEFINE_MUTEX(rcu_barrier_mutex);
 static struct completion rcu_barrier_completion;
+int rcu_scheduler_active __read_mostly;
 
 /*
  * Awaken the corresponding synchronize_rcu() instance now that a
@@ -80,6 +82,10 @@ void wakeme_after_rcu(struct rcu_head  *head)
 void synchronize_rcu(void)
 {
         struct rcu_synchronize rcu;
+
+        if (rcu_blocking_is_gp())
+                return;
+
         init_completion(&rcu.completion);
         /* Will wake me after RCU finished. */
         call_rcu(&rcu.head, wakeme_after_rcu);
@@ -175,3 +181,9 @@ void __init rcu_init(void)
         __rcu_init();
 }
 
+void rcu_scheduler_starting(void)
+{
+        WARN_ON(num_online_cpus() != 1);
+        WARN_ON(nr_context_switches() > 0);
+        rcu_scheduler_active = 1;
+}
diff --git a/kernel/rcupreempt.c b/kernel/rcupreempt.c
index 33cfc50781f9..5d59e850fb71 100644
--- a/kernel/rcupreempt.c
+++ b/kernel/rcupreempt.c
@@ -1181,6 +1181,9 @@ void __synchronize_sched(void)
 {
         struct rcu_synchronize rcu;
 
+        if (num_online_cpus() == 1)
+                return;  /* blocking is gp if only one CPU! */
+
         init_completion(&rcu.completion);
         /* Will wake me after RCU finished. */
         call_rcu_sched(&rcu.head, wakeme_after_rcu);
diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index b2fd602a6f6f..97ce31579ec0 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -948,8 +948,8 @@ static void rcu_do_batch(struct rcu_data *rdp)
 void rcu_check_callbacks(int cpu, int user)
 {
         if (user ||
-            (idle_cpu(cpu) && !in_softirq() &&
-                                hardirq_count() <= (1 << HARDIRQ_SHIFT))) {
+            (idle_cpu(cpu) && rcu_scheduler_active &&
+             !in_softirq() && hardirq_count() <= (1 << HARDIRQ_SHIFT))) {
 
                 /*
                  * Get here if this CPU took its interrupt from user
diff --git a/kernel/relay.c b/kernel/relay.c
index 9d79b7854fa6..8f2179c8056f 100644
--- a/kernel/relay.c
+++ b/kernel/relay.c
@@ -750,7 +750,7 @@ size_t relay_switch_subbuf(struct rchan_buf *buf, size_t length)
                          * from the scheduler (trying to re-grab
                          * rq->lock), so defer it.
                          */
-                        __mod_timer(&buf->timer, jiffies + 1);
+                        mod_timer(&buf->timer, jiffies + 1);
         }
 
         old = buf->data;
diff --git a/kernel/sched.c b/kernel/sched.c
index 410eec404133..8e2558c2ba67 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -223,7 +223,7 @@ static void start_rt_bandwidth(struct rt_bandwidth *rt_b)
 {
         ktime_t now;
 
-        if (rt_bandwidth_enabled() && rt_b->rt_runtime == RUNTIME_INF)
+        if (!rt_bandwidth_enabled() || rt_b->rt_runtime == RUNTIME_INF)
                 return;
 
         if (hrtimer_active(&rt_b->rt_period_timer))
@@ -9224,6 +9224,16 @@ static int sched_rt_global_constraints(void)
 
         return ret;
 }
+
+int sched_rt_can_attach(struct task_group *tg, struct task_struct *tsk)
+{
+        /* Don't accept realtime tasks when there is no way for them to run */
+        if (rt_task(tsk) && tg->rt_bandwidth.rt_runtime == 0)
+                return 0;
+
+        return 1;
+}
+
 #else /* !CONFIG_RT_GROUP_SCHED */
 static int sched_rt_global_constraints(void)
 {
@@ -9317,8 +9327,7 @@ cpu_cgroup_can_attach(struct cgroup_subsys *ss, struct cgroup *cgrp,
                       struct task_struct *tsk)
 {
 #ifdef CONFIG_RT_GROUP_SCHED
-        /* Don't accept realtime tasks when there is no way for them to run */
-        if (rt_task(tsk) && cgroup_tg(cgrp)->rt_bandwidth.rt_runtime == 0)
+        if (!sched_rt_can_attach(cgroup_tg(cgrp), tsk))
                 return -EINVAL;
 #else
         /* We don't support RT-tasks being in separate groups */
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index ad64fcb731f2..57d4b13b631d 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -8,6 +8,7 @@
 
 #include <linux/seccomp.h>
 #include <linux/sched.h>
+#include <linux/compat.h>
 
 /* #define SECCOMP_DEBUG 1 */
 #define NR_SECCOMP_MODES 1
@@ -22,7 +23,7 @@ static int mode1_syscalls[] = {
         0, /* null terminated */
 };
 
-#ifdef TIF_32BIT
+#ifdef CONFIG_COMPAT
 static int mode1_syscalls_32[] = {
         __NR_seccomp_read_32, __NR_seccomp_write_32, __NR_seccomp_exit_32, __NR_seccomp_sigreturn_32,
         0, /* null terminated */
@@ -37,8 +38,8 @@ void __secure_computing(int this_syscall)
         switch (mode) {
         case 1:
                 syscall = mode1_syscalls;
-#ifdef TIF_32BIT
-                if (test_thread_flag(TIF_32BIT))
+#ifdef CONFIG_COMPAT
+                if (is_compat_task())
                         syscall = mode1_syscalls_32;
 #endif
                 do {
diff --git a/kernel/signal.c b/kernel/signal.c
index 2a74fe87c0dd..1c8814481a11 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -1575,7 +1575,15 @@ static void ptrace_stop(int exit_code, int clear_code, siginfo_t *info)
         read_lock(&tasklist_lock);
         if (may_ptrace_stop()) {
                 do_notify_parent_cldstop(current, CLD_TRAPPED);
+                /*
+                 * Don't want to allow preemption here, because
+                 * sys_ptrace() needs this task to be inactive.
+                 *
+                 * XXX: implement read_unlock_no_resched().
+                 */
+                preempt_disable();
                 read_unlock(&tasklist_lock);
+                preempt_enable_no_resched();
                 schedule();
         } else {
                 /*
diff --git a/kernel/softirq.c b/kernel/softirq.c
index bdbe9de9cd8d..9041ea7948fe 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -626,6 +626,7 @@ static int ksoftirqd(void * __bind_cpu)
                         preempt_enable_no_resched();
                         cond_resched();
                         preempt_disable();
+                        rcu_qsctr_inc((long)__bind_cpu);
                 }
                 preempt_enable();
                 set_current_state(TASK_INTERRUPTIBLE);
diff --git a/kernel/sys.c b/kernel/sys.c
index f145c415bc16..37f458e6882a 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -559,7 +559,7 @@ error:
         abort_creds(new);
         return retval;
 }
-  
+
 /*
  * change the user struct in a credentials set to match the new UID
  */
@@ -571,6 +571,11 @@ static int set_user(struct cred *new)
         if (!new_user)
                 return -EAGAIN;
 
+        if (!task_can_switch_user(new_user, current)) {
+                free_uid(new_user);
+                return -EINVAL;
+        }
+
         if (atomic_read(&new_user->processes) >=
                                 current->signal->rlim[RLIMIT_NPROC].rlim_cur &&
                         new_user != INIT_USER) {
@@ -631,10 +636,11 @@ SYSCALL_DEFINE2(setreuid, uid_t, ruid, uid_t, euid)
                         goto error;
         }
 
-        retval = -EAGAIN;
-        if (new->uid != old->uid && set_user(new) < 0)
-                goto error;
-
+        if (new->uid != old->uid) {
+                retval = set_user(new);
+                if (retval < 0)
+                        goto error;
+        }
         if (ruid != (uid_t) -1 ||
             (euid != (uid_t) -1 && euid != old->uid))
                 new->suid = new->euid;
@@ -680,9 +686,10 @@ SYSCALL_DEFINE1(setuid, uid_t, uid)
         retval = -EPERM;
         if (capable(CAP_SETUID)) {
                 new->suid = new->uid = uid;
-                if (uid != old->uid && set_user(new) < 0) {
-                        retval = -EAGAIN;
-                        goto error;
+                if (uid != old->uid) {
+                        retval = set_user(new);
+                        if (retval < 0)
+                                goto error;
                 }
         } else if (uid != old->uid && uid != new->suid) {
                 goto error;
@@ -734,11 +741,13 @@ SYSCALL_DEFINE3(setresuid, uid_t, ruid, uid_t, euid, uid_t, suid)
                         goto error;
         }
 
-        retval = -EAGAIN;
         if (ruid != (uid_t) -1) {
                 new->uid = ruid;
-                if (ruid != old->uid && set_user(new) < 0)
-                        goto error;
+                if (ruid != old->uid) {
+                        retval = set_user(new);
+                        if (retval < 0)
+                                goto error;
+                }
         }
         if (euid != (uid_t) -1)
                 new->euid = euid;
diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c
index ea2f48af83cf..d13be216a790 100644
--- a/kernel/time/clockevents.c
+++ b/kernel/time/clockevents.c
@@ -68,6 +68,17 @@ void clockevents_set_mode(struct clock_event_device *dev,
         if (dev->mode != mode) {
                 dev->set_mode(mode, dev);
                 dev->mode = mode;
+
+                /*
+                 * A nsec2cyc multiplicator of 0 is invalid and we'd crash
+                 * on it, so fix it up and emit a warning:
+                 */
+                if (mode == CLOCK_EVT_MODE_ONESHOT) {
+                        if (unlikely(!dev->mult)) {
+                                dev->mult = 1;
+                                WARN_ON(1);
+                        }
+                }
         }
 }
 
@@ -168,15 +179,6 @@ void clockevents_register_device(struct clock_event_device *dev)
         BUG_ON(dev->mode != CLOCK_EVT_MODE_UNUSED);
         BUG_ON(!dev->cpumask);
 
-        /*
-         * A nsec2cyc multiplicator of 0 is invalid and we'd crash
-         * on it, so fix it up and emit a warning:
-         */
-        if (unlikely(!dev->mult)) {
-                dev->mult = 1;
-                WARN_ON(1);
-        }
-
         spin_lock(&clockevents_lock);
 
         list_add(&dev->list, &clockevent_devices);
diff --git a/kernel/timer.c b/kernel/timer.c
index 13dd64fe143d..9b77fc9a9ac8 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -589,11 +589,14 @@ static struct tvec_base *lock_timer_base(struct timer_list *timer,
         }
 }
 
-int __mod_timer(struct timer_list *timer, unsigned long expires)
+static inline int
+__mod_timer(struct timer_list *timer, unsigned long expires, bool pending_only)
 {
         struct tvec_base *base, *new_base;
         unsigned long flags;
-        int ret = 0;
+        int ret;
+
+        ret = 0;
 
         timer_stats_timer_set_start_info(timer);
         BUG_ON(!timer->function);
@@ -603,6 +606,9 @@ int __mod_timer(struct timer_list *timer, unsigned long expires)
         if (timer_pending(timer)) {
                 detach_timer(timer, 0);
                 ret = 1;
+        } else {
+                if (pending_only)
+                        goto out_unlock;
         }
 
         debug_timer_activate(timer);
@@ -629,42 +635,28 @@ int __mod_timer(struct timer_list *timer, unsigned long expires)
 
         timer->expires = expires;
         internal_add_timer(base, timer);
+
+out_unlock:
         spin_unlock_irqrestore(&base->lock, flags);
 
         return ret;
 }
 
-EXPORT_SYMBOL(__mod_timer);
-
 /**
- * add_timer_on - start a timer on a particular CPU
- * @timer: the timer to be added
- * @cpu: the CPU to start it on
+ * mod_timer_pending - modify a pending timer's timeout
+ * @timer: the pending timer to be modified
+ * @expires: new timeout in jiffies
  *
- * This is not very scalable on SMP. Double adds are not possible.
+ * mod_timer_pending() is the same for pending timers as mod_timer(),
+ * but will not re-activate and modify already deleted timers.
+ *
+ * It is useful for unserialized use of timers.
  */
-void add_timer_on(struct timer_list *timer, int cpu)
+int mod_timer_pending(struct timer_list *timer, unsigned long expires)
 {
-        struct tvec_base *base = per_cpu(tvec_bases, cpu);
-        unsigned long flags;
-
-        timer_stats_timer_set_start_info(timer);
-        BUG_ON(timer_pending(timer) || !timer->function);
-        spin_lock_irqsave(&base->lock, flags);
-        timer_set_base(timer, base);
-        debug_timer_activate(timer);
-        internal_add_timer(base, timer);
-        /*
-         * Check whether the other CPU is idle and needs to be
-         * triggered to reevaluate the timer wheel when nohz is
-         * active. We are protected against the other CPU fiddling
-         * with the timer by holding the timer base lock. This also
-         * makes sure that a CPU on the way to idle can not evaluate
-         * the timer wheel.
-         */
-        wake_up_idle_cpu(cpu);
-        spin_unlock_irqrestore(&base->lock, flags);
+        return __mod_timer(timer, expires, true);
 }
+EXPORT_SYMBOL(mod_timer_pending);
 
 /**
  * mod_timer - modify a timer's timeout
@@ -688,9 +680,6 @@ void add_timer_on(struct timer_list *timer, int cpu)
  */
 int mod_timer(struct timer_list *timer, unsigned long expires)
 {
-        BUG_ON(!timer->function);
-
-        timer_stats_timer_set_start_info(timer);
         /*
          * This is a common optimization triggered by the
          * networking code - if the timer is re-modified
@@ -699,12 +688,62 @@ int mod_timer(struct timer_list *timer, unsigned long expires)
         if (timer->expires == expires && timer_pending(timer))
                 return 1;
 
-        return __mod_timer(timer, expires);
+        return __mod_timer(timer, expires, false);
 }
-
 EXPORT_SYMBOL(mod_timer);
 
 /**
+ * add_timer - start a timer
+ * @timer: the timer to be added
+ *
+ * The kernel will do a ->function(->data) callback from the
+ * timer interrupt at the ->expires point in the future. The
+ * current time is 'jiffies'.
+ *
+ * The timer's ->expires, ->function (and if the handler uses it, ->data)
+ * fields must be set prior calling this function.
+ *
+ * Timers with an ->expires field in the past will be executed in the next
+ * timer tick.
+ */
+void add_timer(struct timer_list *timer)
+{
+        BUG_ON(timer_pending(timer));
+        mod_timer(timer, timer->expires);
+}
+EXPORT_SYMBOL(add_timer);
+
+/**
+ * add_timer_on - start a timer on a particular CPU
+ * @timer: the timer to be added
+ * @cpu: the CPU to start it on
+ *
+ * This is not very scalable on SMP. Double adds are not possible.
+ */
+void add_timer_on(struct timer_list *timer, int cpu)
+{
+        struct tvec_base *base = per_cpu(tvec_bases, cpu);
+        unsigned long flags;
+
+        timer_stats_timer_set_start_info(timer);
+        BUG_ON(timer_pending(timer) || !timer->function);
+        spin_lock_irqsave(&base->lock, flags);
+        timer_set_base(timer, base);
+        debug_timer_activate(timer);
+        internal_add_timer(base, timer);
+        /*
+         * Check whether the other CPU is idle and needs to be
+         * triggered to reevaluate the timer wheel when nohz is
+         * active. We are protected against the other CPU fiddling
+         * with the timer by holding the timer base lock. This also
+         * makes sure that a CPU on the way to idle can not evaluate
+         * the timer wheel.
+         */
+        wake_up_idle_cpu(cpu);
+        spin_unlock_irqrestore(&base->lock, flags);
+}
+
+/**
  * del_timer - deactive a timer.
  * @timer: the timer to be deactivated
  *
@@ -733,7 +772,6 @@ int del_timer(struct timer_list *timer)
 
         return ret;
 }
-
 EXPORT_SYMBOL(del_timer);
 
 #ifdef CONFIG_SMP
@@ -767,7 +805,6 @@ out:
 
         return ret;
 }
-
 EXPORT_SYMBOL(try_to_del_timer_sync);
 
 /**
@@ -796,7 +833,6 @@ int del_timer_sync(struct timer_list *timer)
                 cpu_relax();
         }
 }
-
 EXPORT_SYMBOL(del_timer_sync);
 #endif
 
@@ -1268,7 +1304,7 @@ signed long __sched schedule_timeout(signed long timeout)
         expire = timeout + jiffies;
 
         setup_timer_on_stack(&timer, process_timeout, (unsigned long)current);
-        __mod_timer(&timer, expire);
+        __mod_timer(&timer, expire, false);
         schedule();
         del_singleshot_timer_sync(&timer);
 
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 58a93fbd68aa..34e707e5ab87 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -52,6 +52,7 @@ config FUNCTION_TRACER
         depends on HAVE_FUNCTION_TRACER
         depends on DEBUG_KERNEL
         select FRAME_POINTER
+        select KALLSYMS
         select TRACING
         select CONTEXT_SWITCH_TRACER
         help
@@ -238,6 +239,7 @@ config STACK_TRACER
         depends on DEBUG_KERNEL
         select FUNCTION_TRACER
         select STACKTRACE
+        select KALLSYMS
         help
           This special tracer records the maximum stack footprint of the
           kernel and displays it in debugfs/tracing/stack_trace.
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 9a236ffe2aa4..fdf913dfc7e8 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -2033,7 +2033,7 @@ free:
 static int start_graph_tracing(void)
 {
         struct ftrace_ret_stack **ret_stack_list;
-        int ret;
+        int ret, cpu;
 
         ret_stack_list = kmalloc(FTRACE_RETSTACK_ALLOC_SIZE *
                                 sizeof(struct ftrace_ret_stack *),
@@ -2042,6 +2042,10 @@ static int start_graph_tracing(void)
         if (!ret_stack_list)
                 return -ENOMEM;
 
+        /* The cpu_boot init_task->ret_stack will never be freed */
+        for_each_online_cpu(cpu)
+                ftrace_graph_init_task(idle_task(cpu));
+
         do {
                 ret = alloc_retstack_tasklist(ret_stack_list);
         } while (ret == -EAGAIN);
diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c
index 88c8eb70f54a..bc8e80a86bca 100644
--- a/kernel/trace/trace_selftest.c
+++ b/kernel/trace/trace_selftest.c
@@ -23,10 +23,20 @@ static int trace_test_buffer_cpu(struct trace_array *tr, int cpu)
 {
         struct ring_buffer_event *event;
         struct trace_entry *entry;
+        unsigned int loops = 0;
 
         while ((event = ring_buffer_consume(tr->buffer, cpu, NULL))) {
                 entry = ring_buffer_event_data(event);
 
+                /*
+                 * The ring buffer is a size of trace_buf_size, if
+                 * we loop more than the size, there's something wrong
+                 * with the ring buffer.
+                 */
+                if (loops++ > trace_buf_size) {
+                        printk(KERN_CONT ".. bad ring buffer ");
+                        goto failed;
+                }
                 if (!trace_valid_entry(entry)) {
                         printk(KERN_CONT ".. invalid entry %d ",
                                 entry->type);
@@ -57,11 +67,20 @@ static int trace_test_buffer(struct trace_array *tr, unsigned long *count)
 
         cnt = ring_buffer_entries(tr->buffer);
 
+        /*
+         * The trace_test_buffer_cpu runs a while loop to consume all data.
+         * If the calling tracer is broken, and is constantly filling
+         * the buffer, this will run forever, and hard lock the box.
+         * We disable the ring buffer while we do this test to prevent
+         * a hard lock up.
+         */
+        tracing_off();
         for_each_possible_cpu(cpu) {
                 ret = trace_test_buffer_cpu(tr, cpu);
                 if (ret)
                         break;
         }
+        tracing_on();
         __raw_spin_unlock(&ftrace_max_lock);
         local_irq_restore(flags);
 
diff --git a/kernel/tsacct.c b/kernel/tsacct.c
index 43f891b05a4b..00d59d048edf 100644
--- a/kernel/tsacct.c
+++ b/kernel/tsacct.c
@@ -122,8 +122,10 @@ void acct_update_integrals(struct task_struct *tsk)
         if (likely(tsk->mm)) {
                 cputime_t time, dtime;
                 struct timeval value;
+                unsigned long flags;
                 u64 delta;
 
+                local_irq_save(flags);
                 time = tsk->stime + tsk->utime;
                 dtime = cputime_sub(time, tsk->acct_timexpd);
                 jiffies_to_timeval(cputime_to_jiffies(dtime), &value);
@@ -131,10 +133,12 @@ void acct_update_integrals(struct task_struct *tsk)
                 delta = delta * USEC_PER_SEC + value.tv_usec;
 
                 if (delta == 0)
-                        return;
+                        goto out;
                 tsk->acct_timexpd = time;
                 tsk->acct_rss_mem1 += delta * get_mm_rss(tsk->mm);
                 tsk->acct_vm_mem1 += delta * tsk->mm->total_vm;
+        out:
+                local_irq_restore(flags);
         }
 }
 
diff --git a/kernel/user.c b/kernel/user.c
index 3551ac742395..fbb300e6191f 100644
--- a/kernel/user.c
+++ b/kernel/user.c
@@ -286,14 +286,12 @@ int __init uids_sysfs_init(void)
 /* work function to remove sysfs directory for a user and free up
  * corresponding structures.
  */
-static void remove_user_sysfs_dir(struct work_struct *w)
+static void cleanup_user_struct(struct work_struct *w)
 {
         struct user_struct *up = container_of(w, struct user_struct, work);
         unsigned long flags;
         int remove_user = 0;
 
-        if (up->user_ns != &init_user_ns)
-                return;
         /* Make uid_hash_remove() + sysfs_remove_file() + kobject_del()
          * atomic.
          */
@@ -312,9 +310,11 @@ static void remove_user_sysfs_dir(struct work_struct *w)
         if (!remove_user)
                 goto done;
 
-        kobject_uevent(&up->kobj, KOBJ_REMOVE);
-        kobject_del(&up->kobj);
-        kobject_put(&up->kobj);
+        if (up->user_ns == &init_user_ns) {
+                kobject_uevent(&up->kobj, KOBJ_REMOVE);
+                kobject_del(&up->kobj);
+                kobject_put(&up->kobj);
+        }
 
         sched_destroy_user(up);
         key_put(up->uid_keyring);
@@ -335,7 +335,7 @@ static void free_user(struct user_struct *up, unsigned long flags)
         atomic_inc(&up->__count);
         spin_unlock_irqrestore(&uidhash_lock, flags);
 
-        INIT_WORK(&up->work, remove_user_sysfs_dir);
+        INIT_WORK(&up->work, cleanup_user_struct);
         schedule_work(&up->work);
 }
 
@@ -362,6 +362,24 @@ static void free_user(struct user_struct *up, unsigned long flags)
 
 #endif
 
+#if defined(CONFIG_RT_GROUP_SCHED) && defined(CONFIG_USER_SCHED)
+/*
+ * We need to check if a setuid can take place. This function should be called
+ * before successfully completing the setuid.
+ */
+int task_can_switch_user(struct user_struct *up, struct task_struct *tsk)
+{
+
+        return sched_rt_can_attach(up->tg, tsk);
+
+}
+#else
+int task_can_switch_user(struct user_struct *up, struct task_struct *tsk)
+{
+        return 1;
+}
+#endif
+
 /*
  * Locate the user_struct for the passed UID.  If found, take a ref on it.  The
  * caller must undo that ref with free_uid().
diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c
index 79084311ee57..076c7c8215b0 100644
--- a/kernel/user_namespace.c
+++ b/kernel/user_namespace.c
@@ -60,12 +60,25 @@ int create_user_ns(struct cred *new)
         return 0;
 }
 
-void free_user_ns(struct kref *kref)
+/*
+ * Deferred destructor for a user namespace.  This is required because
+ * free_user_ns() may be called with uidhash_lock held, but we need to call
+ * back to free_uid() which will want to take the lock again.
+ */
+static void free_user_ns_work(struct work_struct *work)
 {
-        struct user_namespace *ns;
-
-        ns = container_of(kref, struct user_namespace, kref);
+        struct user_namespace *ns =
+                container_of(work, struct user_namespace, destroyer);
         free_uid(ns->creator);
         kfree(ns);
 }
+
+void free_user_ns(struct kref *kref)
+{
+        struct user_namespace *ns =
+                container_of(kref, struct user_namespace, kref);
+
+        INIT_WORK(&ns->destroyer, free_user_ns_work);
+        schedule_work(&ns->destroyer);
+}
 EXPORT_SYMBOL(free_user_ns);