12 files changed, 180 insertions, 39 deletions

diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index c29831076e7a..5a54ff42874e 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -1115,8 +1115,10 @@ static void cgroup_kill_sb(struct super_block *sb) {
         }
         write_unlock(&css_set_lock);
 
-        list_del(&root->root_list);
-        root_count--;
+        if (!list_empty(&root->root_list)) {
+                list_del(&root->root_list);
+                root_count--;
+        }
 
         mutex_unlock(&cgroup_mutex);
 
@@ -2434,7 +2436,9 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
 
  err_remove:
 
+        cgroup_lock_hierarchy(root);
         list_del(&cgrp->sibling);
+        cgroup_unlock_hierarchy(root);
         root->number_of_cgroups--;
 
  err_destroy:
@@ -2507,7 +2511,7 @@ static int cgroup_clear_css_refs(struct cgroup *cgrp)
         for_each_subsys(cgrp->root, ss) {
                 struct cgroup_subsys_state *css = cgrp->subsys[ss->subsys_id];
                 int refcnt;
-                do {
+                while (1) {
                         /* We can only remove a CSS with a refcnt==1 */
                         refcnt = atomic_read(&css->refcnt);
                         if (refcnt > 1) {
@@ -2521,7 +2525,10 @@ static int cgroup_clear_css_refs(struct cgroup *cgrp)
                          * css_tryget() to spin until we set the
                          * CSS_REMOVED bits or abort
                          */
-                } while (atomic_cmpxchg(&css->refcnt, refcnt, 0) != refcnt);
+                        if (atomic_cmpxchg(&css->refcnt, refcnt, 0) == refcnt)
+                                break;
+                        cpu_relax();
+                }
         }
  done:
         for_each_subsys(cgrp->root, ss) {
@@ -2991,20 +2998,21 @@ int cgroup_clone(struct task_struct *tsk, struct cgroup_subsys *subsys,
                 mutex_unlock(&cgroup_mutex);
                 return 0;
         }
-        task_lock(tsk);
-        cg = tsk->cgroups;
-        parent = task_cgroup(tsk, subsys->subsys_id);
 
         /* Pin the hierarchy */
-        if (!atomic_inc_not_zero(&parent->root->sb->s_active)) {
+        if (!atomic_inc_not_zero(&root->sb->s_active)) {
                 /* We race with the final deactivate_super() */
                 mutex_unlock(&cgroup_mutex);
                 return 0;
         }
 
         /* Keep the cgroup alive */
+        task_lock(tsk);
+        parent = task_cgroup(tsk, subsys->subsys_id);
+        cg = tsk->cgroups;
         get_css_set(cg);
         task_unlock(tsk);
+
         mutex_unlock(&cgroup_mutex);
 
         /* Now do the VFS work to create a cgroup */
@@ -3043,7 +3051,7 @@ int cgroup_clone(struct task_struct *tsk, struct cgroup_subsys *subsys,
                 mutex_unlock(&inode->i_mutex);
                 put_css_set(cg);
 
-                deactivate_super(parent->root->sb);
+                deactivate_super(root->sb);
                 /* The cgroup is still accessible in the VFS, but
                  * we're not going to try to rmdir() it at this
                  * point. */
@@ -3069,7 +3077,7 @@ int cgroup_clone(struct task_struct *tsk, struct cgroup_subsys *subsys,
         mutex_lock(&cgroup_mutex);
         put_css_set(cg);
         mutex_unlock(&cgroup_mutex);
-        deactivate_super(parent->root->sb);
+        deactivate_super(root->sb);
         return ret;
 }
 
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index f33afb0407bc..f394d2a42ca3 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -501,6 +501,13 @@ static void hrtimer_force_reprogram(struct hrtimer_cpu_base *cpu_base)
                         continue;
                 timer = rb_entry(base->first, struct hrtimer, node);
                 expires = ktime_sub(hrtimer_get_expires(timer), base->offset);
+                /*
+                 * clock_was_set() has changed base->offset so the
+                 * result might be negative. Fix it up to prevent a
+                 * false positive in clockevents_program_event()
+                 */
+                if (expires.tv64 < 0)
+                        expires.tv64 = 0;
                 if (expires.tv64 < cpu_base->expires_next.tv64)
                         cpu_base->expires_next = expires;
         }
@@ -1158,6 +1165,29 @@ static void __run_hrtimer(struct hrtimer *timer)
 
 #ifdef CONFIG_HIGH_RES_TIMERS
 
+static int force_clock_reprogram;
+
+/*
+ * After 5 iteration's attempts, we consider that hrtimer_interrupt()
+ * is hanging, which could happen with something that slows the interrupt
+ * such as the tracing. Then we force the clock reprogramming for each future
+ * hrtimer interrupts to avoid infinite loops and use the min_delta_ns
+ * threshold that we will overwrite.
+ * The next tick event will be scheduled to 3 times we currently spend on
+ * hrtimer_interrupt(). This gives a good compromise, the cpus will spend
+ * 1/4 of their time to process the hrtimer interrupts. This is enough to
+ * let it running without serious starvation.
+ */
+
+static inline void
+hrtimer_interrupt_hanging(struct clock_event_device *dev,
+                        ktime_t try_time)
+{
+        force_clock_reprogram = 1;
+        dev->min_delta_ns = (unsigned long)try_time.tv64 * 3;
+        printk(KERN_WARNING "hrtimer: interrupt too slow, "
+                "forcing clock min delta to %lu ns\n", dev->min_delta_ns);
+}
 /*
  * High resolution timer interrupt
  * Called with interrupts disabled
@@ -1167,6 +1197,7 @@ void hrtimer_interrupt(struct clock_event_device *dev)
         struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases);
         struct hrtimer_clock_base *base;
         ktime_t expires_next, now;
+        int nr_retries = 0;
         int i;
 
         BUG_ON(!cpu_base->hres_active);
@@ -1174,6 +1205,10 @@ void hrtimer_interrupt(struct clock_event_device *dev)
         dev->next_event.tv64 = KTIME_MAX;
 
  retry:
+        /* 5 retries is enough to notice a hang */
+        if (!(++nr_retries % 5))
+                hrtimer_interrupt_hanging(dev, ktime_sub(ktime_get(), now));
+
         now = ktime_get();
 
         expires_next.tv64 = KTIME_MAX;
@@ -1226,7 +1261,7 @@ void hrtimer_interrupt(struct clock_event_device *dev)
 
         /* Reprogramming necessary ? */
         if (expires_next.tv64 != KTIME_MAX) {
-                if (tick_program_event(expires_next, 0))
+                if (tick_program_event(expires_next, force_clock_reprogram))
                         goto retry;
         }
 }
@@ -1580,6 +1615,10 @@ static int __cpuinit hrtimer_cpu_notify(struct notifier_block *self,
                 break;
 
 #ifdef CONFIG_HOTPLUG_CPU
+        case CPU_DYING:
+        case CPU_DYING_FROZEN:
+                clockevents_notify(CLOCK_EVT_NOTIFY_CPU_DYING, &scpu);
+                break;
         case CPU_DEAD:
         case CPU_DEAD_FROZEN:
         {
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index f63c706d25e1..7de11bd64dfe 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -383,6 +383,7 @@ handle_level_irq(unsigned int irq, struct irq_desc *desc)
 out_unlock:
         spin_unlock(&desc->lock);
 }
+EXPORT_SYMBOL_GPL(handle_level_irq);
 
 /**
  *      handle_fasteoi_irq - irq handler for transparent controllers
@@ -593,6 +594,7 @@ __set_irq_handler(unsigned int irq, irq_flow_handler_t handle, int is_chained,
         }
         spin_unlock_irqrestore(&desc->lock, flags);
 }
+EXPORT_SYMBOL_GPL(__set_irq_handler);
 
 void
 set_irq_chip_and_handler(unsigned int irq, struct irq_chip *chip,
diff --git a/kernel/module.c b/kernel/module.c
index e8b51d41dd72..ba22484a987e 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -573,13 +573,13 @@ static char last_unloaded_module[MODULE_NAME_LEN+1];
 /* Init the unload section of the module. */
 static void module_unload_init(struct module *mod)
 {
-        unsigned int i;
+        int cpu;
 
         INIT_LIST_HEAD(&mod->modules_which_use_me);
-        for (i = 0; i < NR_CPUS; i++)
-                local_set(&mod->ref[i].count, 0);
+        for_each_possible_cpu(cpu)
+                local_set(__module_ref_addr(mod, cpu), 0);
         /* Hold reference count during initialization. */
-        local_set(&mod->ref[raw_smp_processor_id()].count, 1);
+        local_set(__module_ref_addr(mod, raw_smp_processor_id()), 1);
         /* Backwards compatibility macros put refcount during init. */
         mod->waiter = current;
 }
@@ -717,10 +717,11 @@ static int try_stop_module(struct module *mod, int flags, int *forced)
 
 unsigned int module_refcount(struct module *mod)
 {
-        unsigned int i, total = 0;
+        unsigned int total = 0;
+        int cpu;
 
-        for (i = 0; i < NR_CPUS; i++)
-                total += local_read(&mod->ref[i].count);
+        for_each_possible_cpu(cpu)
+                total += local_read(__module_ref_addr(mod, cpu));
         return total;
 }
 EXPORT_SYMBOL(module_refcount);
@@ -894,7 +895,7 @@ void module_put(struct module *module)
 {
         if (module) {
                 unsigned int cpu = get_cpu();
-                local_dec(&module->ref[cpu].count);
+                local_dec(__module_ref_addr(module, cpu));
                 /* Maybe they're waiting for us to drop reference? */
                 if (unlikely(!module_is_live(module)))
                         wake_up_process(module->waiter);
@@ -1464,7 +1465,10 @@ static void free_module(struct module *mod)
         kfree(mod->args);
         if (mod->percpu)
                 percpu_modfree(mod->percpu);
-
+#if defined(CONFIG_MODULE_UNLOAD) && defined(CONFIG_SMP)
+        if (mod->refptr)
+                percpu_modfree(mod->refptr);
+#endif
         /* Free lock-classes: */
         lockdep_free_key_range(mod->module_core, mod->core_size);
 
@@ -2011,6 +2015,14 @@ 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,
@@ -2018,7 +2030,7 @@ static noinline struct module *load_module(void __user *umod,
                                          mod->name);
                 if (!percpu) {
                         err = -ENOMEM;
-                        goto free_mod;
+                        goto free_percpu;
                 }
                 sechdrs[pcpuindex].sh_flags &= ~(unsigned long)SHF_ALLOC;
                 mod->percpu = percpu;
@@ -2282,6 +2294,9 @@ static noinline struct module *load_module(void __user *umod,
  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/signal.c b/kernel/signal.c
index e73759783dc8..b6b36768b758 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -909,7 +909,9 @@ static void print_fatal_signal(struct pt_regs *regs, int signr)
         }
 #endif
         printk("\n");
+        preempt_disable();
         show_regs(regs);
+        preempt_enable();
 }
 
 static int __init setup_print_fatal_signals(char *str)
diff --git a/kernel/smp.c b/kernel/smp.c
index 5cfa0e5e3e88..bbedbb7efe32 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -18,6 +18,7 @@ __cacheline_aligned_in_smp DEFINE_SPINLOCK(call_function_lock);
 enum {
         CSD_FLAG_WAIT           = 0x01,
         CSD_FLAG_ALLOC          = 0x02,
+        CSD_FLAG_LOCK           = 0x04,
 };
 
 struct call_function_data {
@@ -186,6 +187,9 @@ void generic_smp_call_function_single_interrupt(void)
                         if (data_flags & CSD_FLAG_WAIT) {
                                 smp_wmb();
                                 data->flags &= ~CSD_FLAG_WAIT;
+                        } else if (data_flags & CSD_FLAG_LOCK) {
+                                smp_wmb();
+                                data->flags &= ~CSD_FLAG_LOCK;
                         } else if (data_flags & CSD_FLAG_ALLOC)
                                 kfree(data);
                 }
@@ -196,6 +200,8 @@ void generic_smp_call_function_single_interrupt(void)
         }
 }
 
+static DEFINE_PER_CPU(struct call_single_data, csd_data);
+
 /*
  * smp_call_function_single - Run a function on a specific CPU
  * @func: The function to run. This must be fast and non-blocking.
@@ -224,14 +230,38 @@ int smp_call_function_single(int cpu, void (*func) (void *info), void *info,
                 func(info);
                 local_irq_restore(flags);
         } else if ((unsigned)cpu < nr_cpu_ids && cpu_online(cpu)) {
-                struct call_single_data *data = NULL;
+                struct call_single_data *data;
 
                 if (!wait) {
+                        /*
+                         * We are calling a function on a single CPU
+                         * and we are not going to wait for it to finish.
+                         * We first try to allocate the data, but if we
+                         * fail, we fall back to use a per cpu data to pass
+                         * the information to that CPU. Since all callers
+                         * of this code will use the same data, we must
+                         * synchronize the callers to prevent a new caller
+                         * from corrupting the data before the callee
+                         * can access it.
+                         *
+                         * The CSD_FLAG_LOCK is used to let us know when
+                         * the IPI handler is done with the data.
+                         * The first caller will set it, and the callee
+                         * will clear it. The next caller must wait for
+                         * it to clear before we set it again. This
+                         * will make sure the callee is done with the
+                         * data before a new caller will use it.
+                         */
                         data = kmalloc(sizeof(*data), GFP_ATOMIC);
                         if (data)
                                 data->flags = CSD_FLAG_ALLOC;
-                }
-                if (!data) {
+                        else {
+                                data = &per_cpu(csd_data, me);
+                                while (data->flags & CSD_FLAG_LOCK)
+                                        cpu_relax();
+                                data->flags = CSD_FLAG_LOCK;
+                        }
+                } else {
                         data = &d;
                         data->flags = CSD_FLAG_WAIT;
                 }
diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c
index 63e05d423a09..21a5ca849514 100644
--- a/kernel/time/tick-common.c
+++ b/kernel/time/tick-common.c
@@ -274,6 +274,21 @@ out_bc:
 }
 
 /*
+ * Transfer the do_timer job away from a dying cpu.
+ *
+ * Called with interrupts disabled.
+ */
+static void tick_handover_do_timer(int *cpup)
+{
+        if (*cpup == tick_do_timer_cpu) {
+                int cpu = cpumask_first(cpu_online_mask);
+
+                tick_do_timer_cpu = (cpu < nr_cpu_ids) ? cpu :
+                        TICK_DO_TIMER_NONE;
+        }
+}
+
+/*
  * Shutdown an event device on a given cpu:
  *
  * This is called on a life CPU, when a CPU is dead. So we cannot
@@ -297,13 +312,6 @@ static void tick_shutdown(unsigned int *cpup)
                 clockevents_exchange_device(dev, NULL);
                 td->evtdev = NULL;
         }
-        /* Transfer the do_timer job away from this cpu */
-        if (*cpup == tick_do_timer_cpu) {
-                int cpu = cpumask_first(cpu_online_mask);
-
-                tick_do_timer_cpu = (cpu < nr_cpu_ids) ? cpu :
-                        TICK_DO_TIMER_NONE;
-        }
         spin_unlock_irqrestore(&tick_device_lock, flags);
 }
 
@@ -357,6 +365,10 @@ static int tick_notify(struct notifier_block *nb, unsigned long reason,
                 tick_broadcast_oneshot_control(reason);
                 break;
 
+        case CLOCK_EVT_NOTIFY_CPU_DYING:
+                tick_handover_do_timer(dev);
+                break;
+
         case CLOCK_EVT_NOTIFY_CPU_DEAD:
                 tick_shutdown_broadcast_oneshot(dev);
                 tick_shutdown_broadcast(dev);
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 2f32969c09df..7dcf6e9f2b04 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -17,6 +17,7 @@
 #include <linux/clocksource.h>
 #include <linux/kallsyms.h>
 #include <linux/seq_file.h>
+#include <linux/suspend.h>
 #include <linux/debugfs.h>
 #include <linux/hardirq.h>
 #include <linux/kthread.h>
@@ -1965,6 +1966,7 @@ ftrace_enable_sysctl(struct ctl_table *table, int write,
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 
 static atomic_t ftrace_graph_active;
+static struct notifier_block ftrace_suspend_notifier;
 
 int ftrace_graph_entry_stub(struct ftrace_graph_ent *trace)
 {
@@ -2043,6 +2045,27 @@ static int start_graph_tracing(void)
         return ret;
 }
 
+/*
+ * Hibernation protection.
+ * The state of the current task is too much unstable during
+ * suspend/restore to disk. We want to protect against that.
+ */
+static int
+ftrace_suspend_notifier_call(struct notifier_block *bl, unsigned long state,
+                                                        void *unused)
+{
+        switch (state) {
+        case PM_HIBERNATION_PREPARE:
+                pause_graph_tracing();
+                break;
+
+        case PM_POST_HIBERNATION:
+                unpause_graph_tracing();
+                break;
+        }
+        return NOTIFY_DONE;
+}
+
 int register_ftrace_graph(trace_func_graph_ret_t retfunc,
                         trace_func_graph_ent_t entryfunc)
 {
@@ -2050,6 +2073,9 @@ int register_ftrace_graph(trace_func_graph_ret_t retfunc,
 
         mutex_lock(&ftrace_sysctl_lock);
 
+        ftrace_suspend_notifier.notifier_call = ftrace_suspend_notifier_call;
+        register_pm_notifier(&ftrace_suspend_notifier);
+
         atomic_inc(&ftrace_graph_active);
         ret = start_graph_tracing();
         if (ret) {
@@ -2075,6 +2101,7 @@ void unregister_ftrace_graph(void)
         ftrace_graph_return = (trace_func_graph_ret_t)ftrace_stub;
         ftrace_graph_entry = ftrace_graph_entry_stub;
         ftrace_shutdown(FTRACE_STOP_FUNC_RET);
+        unregister_pm_notifier(&ftrace_suspend_notifier);
 
         mutex_unlock(&ftrace_sysctl_lock);
 }
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 8b0daf0662ef..bd38c5cfd8ad 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -246,7 +246,7 @@ static inline int test_time_stamp(u64 delta)
         return 0;
 }
 
-#define BUF_PAGE_SIZE (PAGE_SIZE - sizeof(struct buffer_data_page))
+#define BUF_PAGE_SIZE (PAGE_SIZE - offsetof(struct buffer_data_page, data))
 
 /*
  * head_page == tail_page && head == tail then buffer is empty.
@@ -1025,12 +1025,8 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
                 }
 
                 if (next_page == head_page) {
-                        if (!(buffer->flags & RB_FL_OVERWRITE)) {
-                                /* reset write */
-                                if (tail <= BUF_PAGE_SIZE)
-                                        local_set(&tail_page->write, tail);
+                        if (!(buffer->flags & RB_FL_OVERWRITE))
                                 goto out_unlock;
-                        }
 
                         /* tail_page has not moved yet? */
                         if (tail_page == cpu_buffer->tail_page) {
@@ -1105,6 +1101,10 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
         return event;
 
  out_unlock:
+        /* reset write */
+        if (tail <= BUF_PAGE_SIZE)
+                local_set(&tail_page->write, tail);
+
         __raw_spin_unlock(&cpu_buffer->lock);
         local_irq_restore(flags);
         return NULL;
@@ -2174,6 +2174,9 @@ rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer)
 
         cpu_buffer->overrun = 0;
         cpu_buffer->entries = 0;
+
+        cpu_buffer->write_stamp = 0;
+        cpu_buffer->read_stamp = 0;
 }
 
 /**
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index c580233add95..17bb88d86ac2 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -40,7 +40,7 @@
 
 #define TRACE_BUFFER_FLAGS      (RB_FL_OVERWRITE)
 
-unsigned long __read_mostly     tracing_max_latency = (cycle_t)ULONG_MAX;
+unsigned long __read_mostly     tracing_max_latency;
 unsigned long __read_mostly     tracing_thresh;
 
 /*
@@ -3736,7 +3736,7 @@ static struct notifier_block trace_die_notifier = {
  * it if we decide to change what log level the ftrace dump
  * should be at.
  */
-#define KERN_TRACE              KERN_INFO
+#define KERN_TRACE              KERN_EMERG
 
 static void
 trace_printk_seq(struct trace_seq *s)
@@ -3770,6 +3770,7 @@ void ftrace_dump(void)
         dump_ran = 1;
 
         /* No turning back! */
+        tracing_off();
         ftrace_kill();
 
         for_each_tracing_cpu(cpu) {
diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c
index 7c2e326bbc8b..62a78d943534 100644
--- a/kernel/trace/trace_irqsoff.c
+++ b/kernel/trace/trace_irqsoff.c
@@ -380,6 +380,7 @@ static void stop_irqsoff_tracer(struct trace_array *tr)
 
 static void __irqsoff_tracer_init(struct trace_array *tr)
 {
+        tracing_max_latency = 0;
         irqsoff_trace = tr;
         /* make sure that the tracer is visible */
         smp_wmb();
diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c
index 43586b689e31..42ae1e77b6b3 100644
--- a/kernel/trace/trace_sched_wakeup.c
+++ b/kernel/trace/trace_sched_wakeup.c
@@ -333,6 +333,7 @@ static void stop_wakeup_tracer(struct trace_array *tr)
 
 static int wakeup_tracer_init(struct trace_array *tr)
 {
+        tracing_max_latency = 0;
         wakeup_trace = tr;
         start_wakeup_tracer(tr);
         return 0;