Merge commit 'v2.6.30-rc1' into perfcounters/core

Conflicts:
	arch/powerpc/include/asm/systbl.h
	arch/powerpc/include/asm/unistd.h
	include/linux/init_task.h

Merge reason: the conflicts are non-trivial: PowerPC placement
              of sys_perf_counter_open has to be mixed with the
	      new preadv/pwrite syscalls.

Signed-off-by: Ingo Molnar <mingo@elte.hu>

18 files changed, 729 insertions, 221 deletions

diff --git a/kernel/Makefile b/kernel/Makefile
index 63c697529ca1..e914ca992d70 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -74,6 +74,7 @@ obj-$(CONFIG_AUDIT_TREE) += audit_tree.o
 obj-$(CONFIG_KPROBES) += kprobes.o
 obj-$(CONFIG_KGDB) += kgdb.o
 obj-$(CONFIG_DETECT_SOFTLOCKUP) += softlockup.o
+obj-$(CONFIG_DETECT_HUNG_TASK) += hung_task.o
 obj-$(CONFIG_GENERIC_HARDIRQS) += irq/
 obj-$(CONFIG_SECCOMP) += seccomp.o
 obj-$(CONFIG_RCU_TORTURE_TEST) += rcutorture.o
diff --git a/kernel/exit.c b/kernel/exit.c
index fbb5d94c8bbc..4741376c8dec 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -926,6 +926,8 @@ NORET_TYPE void do_exit(long code)
                 schedule();
         }
 
+        exit_irq_thread();
+
         exit_signals(tsk);  /* sets PF_EXITING */
         /*
          * tsk->flags are checked in the futex code to protect against
diff --git a/kernel/fork.c b/kernel/fork.c
index 381d7f9b70fb..89c1efb3ccf4 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -645,6 +645,9 @@ static int copy_mm(unsigned long clone_flags, struct task_struct * tsk)
 
         tsk->min_flt = tsk->maj_flt = 0;
         tsk->nvcsw = tsk->nivcsw = 0;
+#ifdef CONFIG_DETECT_HUNG_TASK
+        tsk->last_switch_count = tsk->nvcsw + tsk->nivcsw;
+#endif
 
         tsk->mm = NULL;
         tsk->active_mm = NULL;
@@ -1033,11 +1036,6 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 
         p->default_timer_slack_ns = current->timer_slack_ns;
 
-#ifdef CONFIG_DETECT_SOFTLOCKUP
-        p->last_switch_count = 0;
-        p->last_switch_timestamp = 0;
-#endif
-
         task_io_accounting_init(&p->ioac);
         acct_clear_integrals(p);
 
diff --git a/kernel/hung_task.c b/kernel/hung_task.c
new file mode 100644
index 000000000000..022a4927b785
--- /dev/null
+++ b/kernel/hung_task.c
@@ -0,0 +1,217 @@
+/*
+ * Detect Hung Task
+ *
+ * kernel/hung_task.c - kernel thread for detecting tasks stuck in D state
+ *
+ */
+
+#include <linux/mm.h>
+#include <linux/cpu.h>
+#include <linux/nmi.h>
+#include <linux/init.h>
+#include <linux/delay.h>
+#include <linux/freezer.h>
+#include <linux/kthread.h>
+#include <linux/lockdep.h>
+#include <linux/module.h>
+#include <linux/sysctl.h>
+
+/*
+ * The number of tasks checked:
+ */
+unsigned long __read_mostly sysctl_hung_task_check_count = PID_MAX_LIMIT;
+
+/*
+ * Limit number of tasks checked in a batch.
+ *
+ * This value controls the preemptibility of khungtaskd since preemption
+ * is disabled during the critical section. It also controls the size of
+ * the RCU grace period. So it needs to be upper-bound.
+ */
+#define HUNG_TASK_BATCHING 1024
+
+/*
+ * Zero means infinite timeout - no checking done:
+ */
+unsigned long __read_mostly sysctl_hung_task_timeout_secs = 120;
+
+unsigned long __read_mostly sysctl_hung_task_warnings = 10;
+
+static int __read_mostly did_panic;
+
+static struct task_struct *watchdog_task;
+
+/*
+ * Should we panic (and reboot, if panic_timeout= is set) when a
+ * hung task is detected:
+ */
+unsigned int __read_mostly sysctl_hung_task_panic =
+                                CONFIG_BOOTPARAM_HUNG_TASK_PANIC_VALUE;
+
+static int __init hung_task_panic_setup(char *str)
+{
+        sysctl_hung_task_panic = simple_strtoul(str, NULL, 0);
+
+        return 1;
+}
+__setup("hung_task_panic=", hung_task_panic_setup);
+
+static int
+hung_task_panic(struct notifier_block *this, unsigned long event, void *ptr)
+{
+        did_panic = 1;
+
+        return NOTIFY_DONE;
+}
+
+static struct notifier_block panic_block = {
+        .notifier_call = hung_task_panic,
+};
+
+static void check_hung_task(struct task_struct *t, unsigned long timeout)
+{
+        unsigned long switch_count = t->nvcsw + t->nivcsw;
+
+        /*
+         * Ensure the task is not frozen.
+         * Also, when a freshly created task is scheduled once, changes
+         * its state to TASK_UNINTERRUPTIBLE without having ever been
+         * switched out once, it musn't be checked.
+         */
+        if (unlikely(t->flags & PF_FROZEN || !switch_count))
+                return;
+
+        if (switch_count != t->last_switch_count) {
+                t->last_switch_count = switch_count;
+                return;
+        }
+        if (!sysctl_hung_task_warnings)
+                return;
+        sysctl_hung_task_warnings--;
+
+        /*
+         * Ok, the task did not get scheduled for more than 2 minutes,
+         * complain:
+         */
+        printk(KERN_ERR "INFO: task %s:%d blocked for more than "
+                        "%ld seconds.\n", t->comm, t->pid, timeout);
+        printk(KERN_ERR "\"echo 0 > /proc/sys/kernel/hung_task_timeout_secs\""
+                        " disables this message.\n");
+        sched_show_task(t);
+        __debug_show_held_locks(t);
+
+        touch_nmi_watchdog();
+
+        if (sysctl_hung_task_panic)
+                panic("hung_task: blocked tasks");
+}
+
+/*
+ * To avoid extending the RCU grace period for an unbounded amount of time,
+ * periodically exit the critical section and enter a new one.
+ *
+ * For preemptible RCU it is sufficient to call rcu_read_unlock in order
+ * exit the grace period. For classic RCU, a reschedule is required.
+ */
+static void rcu_lock_break(struct task_struct *g, struct task_struct *t)
+{
+        get_task_struct(g);
+        get_task_struct(t);
+        rcu_read_unlock();
+        cond_resched();
+        rcu_read_lock();
+        put_task_struct(t);
+        put_task_struct(g);
+}
+
+/*
+ * Check whether a TASK_UNINTERRUPTIBLE does not get woken up for
+ * a really long time (120 seconds). If that happens, print out
+ * a warning.
+ */
+static void check_hung_uninterruptible_tasks(unsigned long timeout)
+{
+        int max_count = sysctl_hung_task_check_count;
+        int batch_count = HUNG_TASK_BATCHING;
+        struct task_struct *g, *t;
+
+        /*
+         * If the system crashed already then all bets are off,
+         * do not report extra hung tasks:
+         */
+        if (test_taint(TAINT_DIE) || did_panic)
+                return;
+
+        rcu_read_lock();
+        do_each_thread(g, t) {
+                if (!--max_count)
+                        goto unlock;
+                if (!--batch_count) {
+                        batch_count = HUNG_TASK_BATCHING;
+                        rcu_lock_break(g, t);
+                        /* Exit if t or g was unhashed during refresh. */
+                        if (t->state == TASK_DEAD || g->state == TASK_DEAD)
+                                goto unlock;
+                }
+                /* use "==" to skip the TASK_KILLABLE tasks waiting on NFS */
+                if (t->state == TASK_UNINTERRUPTIBLE)
+                        check_hung_task(t, timeout);
+        } while_each_thread(g, t);
+ unlock:
+        rcu_read_unlock();
+}
+
+static unsigned long timeout_jiffies(unsigned long timeout)
+{
+        /* timeout of 0 will disable the watchdog */
+        return timeout ? timeout * HZ : MAX_SCHEDULE_TIMEOUT;
+}
+
+/*
+ * Process updating of timeout sysctl
+ */
+int proc_dohung_task_timeout_secs(struct ctl_table *table, int write,
+                                  struct file *filp, void __user *buffer,
+                                  size_t *lenp, loff_t *ppos)
+{
+        int ret;
+
+        ret = proc_doulongvec_minmax(table, write, filp, buffer, lenp, ppos);
+
+        if (ret || !write)
+                goto out;
+
+        wake_up_process(watchdog_task);
+
+ out:
+        return ret;
+}
+
+/*
+ * kthread which checks for tasks stuck in D state
+ */
+static int watchdog(void *dummy)
+{
+        set_user_nice(current, 0);
+
+        for ( ; ; ) {
+                unsigned long timeout = sysctl_hung_task_timeout_secs;
+
+                while (schedule_timeout_interruptible(timeout_jiffies(timeout)))
+                        timeout = sysctl_hung_task_timeout_secs;
+
+                check_hung_uninterruptible_tasks(timeout);
+        }
+
+        return 0;
+}
+
+static int __init hung_task_init(void)
+{
+        atomic_notifier_chain_register(&panic_notifier_list, &panic_block);
+        watchdog_task = kthread_run(watchdog, NULL, "khungtaskd");
+
+        return 0;
+}
+
+module_init(hung_task_init);
diff --git a/kernel/irq/devres.c b/kernel/irq/devres.c
index 38a25b8d8bff..d06df9c41cba 100644
--- a/kernel/irq/devres.c
+++ b/kernel/irq/devres.c
@@ -26,10 +26,12 @@ static int devm_irq_match(struct device *dev, void *res, void *data)
 }
 
 /**
- *      devm_request_irq - allocate an interrupt line for a managed device
+ *      devm_request_threaded_irq - allocate an interrupt line for a managed device
  *      @dev: device to request interrupt for
  *      @irq: Interrupt line to allocate
  *      @handler: Function to be called when the IRQ occurs
+ *      @thread_fn: function to be called in a threaded interrupt context. NULL
+ *                  for devices which handle everything in @handler
  *      @irqflags: Interrupt type flags
  *      @devname: An ascii name for the claiming device
  *      @dev_id: A cookie passed back to the handler function
@@ -42,9 +44,10 @@ static int devm_irq_match(struct device *dev, void *res, void *data)
  *      If an IRQ allocated with this function needs to be freed
  *      separately, dev_free_irq() must be used.
  */
-int devm_request_irq(struct device *dev, unsigned int irq,
-                     irq_handler_t handler, unsigned long irqflags,
-                     const char *devname, void *dev_id)
+int devm_request_threaded_irq(struct device *dev, unsigned int irq,
+                              irq_handler_t handler, irq_handler_t thread_fn,
+                              unsigned long irqflags, const char *devname,
+                              void *dev_id)
 {
         struct irq_devres *dr;
         int rc;
@@ -54,7 +57,8 @@ int devm_request_irq(struct device *dev, unsigned int irq,
         if (!dr)
                 return -ENOMEM;
 
-        rc = request_irq(irq, handler, irqflags, devname, dev_id);
+        rc = request_threaded_irq(irq, handler, thread_fn, irqflags, devname,
+                                  dev_id);
         if (rc) {
                 devres_free(dr);
                 return rc;
@@ -66,7 +70,7 @@ int devm_request_irq(struct device *dev, unsigned int irq,
 
         return 0;
 }
-EXPORT_SYMBOL(devm_request_irq);
+EXPORT_SYMBOL(devm_request_threaded_irq);
 
 /**
  *      devm_free_irq - free an interrupt
diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c
index 343acecae629..d82142be8dd2 100644
--- a/kernel/irq/handle.c
+++ b/kernel/irq/handle.c
@@ -339,6 +339,15 @@ irqreturn_t no_action(int cpl, void *dev_id)
         return IRQ_NONE;
 }
 
+static void warn_no_thread(unsigned int irq, struct irqaction *action)
+{
+        if (test_and_set_bit(IRQTF_WARNED, &action->thread_flags))
+                return;
+
+        printk(KERN_WARNING "IRQ %d device %s returned IRQ_WAKE_THREAD "
+               "but no thread function available.", irq, action->name);
+}
+
 DEFINE_TRACE(irq_handler_entry);
 DEFINE_TRACE(irq_handler_exit);
 
@@ -363,8 +372,47 @@ irqreturn_t handle_IRQ_event(unsigned int irq, struct irqaction *action)
                 trace_irq_handler_entry(irq, action);
                 ret = action->handler(irq, action->dev_id);
                 trace_irq_handler_exit(irq, action, ret);
-                if (ret == IRQ_HANDLED)
+
+                switch (ret) {
+                case IRQ_WAKE_THREAD:
+                        /*
+                         * Set result to handled so the spurious check
+                         * does not trigger.
+                         */
+                        ret = IRQ_HANDLED;
+
+                        /*
+                         * Catch drivers which return WAKE_THREAD but
+                         * did not set up a thread function
+                         */
+                        if (unlikely(!action->thread_fn)) {
+                                warn_no_thread(irq, action);
+                                break;
+                        }
+
+                        /*
+                         * Wake up the handler thread for this
+                         * action. In case the thread crashed and was
+                         * killed we just pretend that we handled the
+                         * interrupt. The hardirq handler above has
+                         * disabled the device interrupt, so no irq
+                         * storm is lurking.
+                         */
+                        if (likely(!test_bit(IRQTF_DIED,
+                                             &action->thread_flags))) {
+                                set_bit(IRQTF_RUNTHREAD, &action->thread_flags);
+                                wake_up_process(action->thread);
+                        }
+
+                        /* Fall through to add to randomness */
+                case IRQ_HANDLED:
                         status |= action->flags;
+                        break;
+
+                default:
+                        break;
+                }
+
                 retval |= ret;
                 action = action->next;
         } while (action);
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 1516ab77355c..7e2e7dd4cd2f 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -8,16 +8,15 @@
  */
 
 #include <linux/irq.h>
+#include <linux/kthread.h>
 #include <linux/module.h>
 #include <linux/random.h>
 #include <linux/interrupt.h>
 #include <linux/slab.h>
+#include <linux/sched.h>
 
 #include "internals.h"
 
-#if defined(CONFIG_SMP) && defined(CONFIG_GENERIC_HARDIRQS)
-cpumask_var_t irq_default_affinity;
-
 /**
  *      synchronize_irq - wait for pending IRQ handlers (on other CPUs)
  *      @irq: interrupt number to wait for
@@ -53,9 +52,18 @@ void synchronize_irq(unsigned int irq)
 
                 /* Oops, that failed? */
         } while (status & IRQ_INPROGRESS);
+
+        /*
+         * We made sure that no hardirq handler is running. Now verify
+         * that no threaded handlers are active.
+         */
+        wait_event(desc->wait_for_threads, !atomic_read(&desc->threads_active));
 }
 EXPORT_SYMBOL(synchronize_irq);
 
+#ifdef CONFIG_SMP
+cpumask_var_t irq_default_affinity;
+
 /**
  *      irq_can_set_affinity - Check if the affinity of a given irq can be set
  *      @irq:           Interrupt to check
@@ -72,6 +80,18 @@ int irq_can_set_affinity(unsigned int irq)
         return 1;
 }
 
+static void
+irq_set_thread_affinity(struct irq_desc *desc, const struct cpumask *cpumask)
+{
+        struct irqaction *action = desc->action;
+
+        while (action) {
+                if (action->thread)
+                        set_cpus_allowed_ptr(action->thread, cpumask);
+                action = action->next;
+        }
+}
+
 /**
  *      irq_set_affinity - Set the irq affinity of a given irq
  *      @irq:           Interrupt to set affinity
@@ -100,6 +120,7 @@ int irq_set_affinity(unsigned int irq, const struct cpumask *cpumask)
         cpumask_copy(desc->affinity, cpumask);
         desc->chip->set_affinity(irq, cpumask);
 #endif
+        irq_set_thread_affinity(desc, cpumask);
         desc->status |= IRQ_AFFINITY_SET;
         spin_unlock_irqrestore(&desc->lock, flags);
         return 0;
@@ -150,6 +171,8 @@ int irq_select_affinity_usr(unsigned int irq)
 
         spin_lock_irqsave(&desc->lock, flags);
         ret = setup_affinity(irq, desc);
+        if (!ret)
+                irq_set_thread_affinity(desc, desc->affinity);
         spin_unlock_irqrestore(&desc->lock, flags);
 
         return ret;
@@ -401,6 +424,90 @@ int __irq_set_trigger(struct irq_desc *desc, unsigned int irq,
         return ret;
 }
 
+static int irq_wait_for_interrupt(struct irqaction *action)
+{
+        while (!kthread_should_stop()) {
+                set_current_state(TASK_INTERRUPTIBLE);
+
+                if (test_and_clear_bit(IRQTF_RUNTHREAD,
+                                       &action->thread_flags)) {
+                        __set_current_state(TASK_RUNNING);
+                        return 0;
+                }
+                schedule();
+        }
+        return -1;
+}
+
+/*
+ * Interrupt handler thread
+ */
+static int irq_thread(void *data)
+{
+        struct sched_param param = { .sched_priority = MAX_USER_RT_PRIO/2, };
+        struct irqaction *action = data;
+        struct irq_desc *desc = irq_to_desc(action->irq);
+        int wake;
+
+        sched_setscheduler(current, SCHED_FIFO, &param);
+        current->irqaction = action;
+
+        while (!irq_wait_for_interrupt(action)) {
+
+                atomic_inc(&desc->threads_active);
+
+                spin_lock_irq(&desc->lock);
+                if (unlikely(desc->status & IRQ_DISABLED)) {
+                        /*
+                         * CHECKME: We might need a dedicated
+                         * IRQ_THREAD_PENDING flag here, which
+                         * retriggers the thread in check_irq_resend()
+                         * but AFAICT IRQ_PENDING should be fine as it
+                         * retriggers the interrupt itself --- tglx
+                         */
+                        desc->status |= IRQ_PENDING;
+                        spin_unlock_irq(&desc->lock);
+                } else {
+                        spin_unlock_irq(&desc->lock);
+
+                        action->thread_fn(action->irq, action->dev_id);
+                }
+
+                wake = atomic_dec_and_test(&desc->threads_active);
+
+                if (wake && waitqueue_active(&desc->wait_for_threads))
+                        wake_up(&desc->wait_for_threads);
+        }
+
+        /*
+         * Clear irqaction. Otherwise exit_irq_thread() would make
+         * fuzz about an active irq thread going into nirvana.
+         */
+        current->irqaction = NULL;
+        return 0;
+}
+
+/*
+ * Called from do_exit()
+ */
+void exit_irq_thread(void)
+{
+        struct task_struct *tsk = current;
+
+        if (!tsk->irqaction)
+                return;
+
+        printk(KERN_ERR
+               "exiting task \"%s\" (%d) is an active IRQ thread (irq %d)\n",
+               tsk->comm ? tsk->comm : "", tsk->pid, tsk->irqaction->irq);
+
+        /*
+         * Set the THREAD DIED flag to prevent further wakeups of the
+         * soon to be gone threaded handler.
+         */
+        set_bit(IRQTF_DIED, &tsk->irqaction->flags);
+}
+
 /*
  * Internal function to register an irqaction - typically used to
  * allocate special interrupts that are part of the architecture.
@@ -437,6 +544,26 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
         }
 
         /*
+         * Threaded handler ?
+         */
+        if (new->thread_fn) {
+                struct task_struct *t;
+
+                t = kthread_create(irq_thread, new, "irq/%d-%s", irq,
+                                   new->name);
+                if (IS_ERR(t))
+                        return PTR_ERR(t);
+                /*
+                 * We keep the reference to the task struct even if
+                 * the thread dies to avoid that the interrupt code
+                 * references an already freed task_struct.
+                 */
+                get_task_struct(t);
+                new->thread = t;
+                wake_up_process(t);
+        }
+
+        /*
          * The following block of code has to be executed atomically
          */
         spin_lock_irqsave(&desc->lock, flags);
@@ -473,15 +600,15 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
         if (!shared) {
                 irq_chip_set_defaults(desc->chip);
 
+                init_waitqueue_head(&desc->wait_for_threads);
+
                 /* Setup the type (level, edge polarity) if configured: */
                 if (new->flags & IRQF_TRIGGER_MASK) {
                         ret = __irq_set_trigger(desc, irq,
                                         new->flags & IRQF_TRIGGER_MASK);
 
-                        if (ret) {
-                                spin_unlock_irqrestore(&desc->lock, flags);
-                                return ret;
-                        }
+                        if (ret)
+                                goto out_thread;
                 } else
                         compat_irq_chip_set_default_handler(desc);
 #if defined(CONFIG_IRQ_PER_CPU)
@@ -549,8 +676,19 @@ mismatch:
                 dump_stack();
         }
 #endif
+        ret = -EBUSY;
+
+out_thread:
         spin_unlock_irqrestore(&desc->lock, flags);
-        return -EBUSY;
+        if (new->thread) {
+                struct task_struct *t = new->thread;
+
+                new->thread = NULL;
+                if (likely(!test_bit(IRQTF_DIED, &new->thread_flags)))
+                        kthread_stop(t);
+                put_task_struct(t);
+        }
+        return ret;
 }
 
 /**
@@ -576,6 +714,7 @@ static struct irqaction *__free_irq(unsigned int irq, void *dev_id)
 {
         struct irq_desc *desc = irq_to_desc(irq);
         struct irqaction *action, **action_ptr;
+        struct task_struct *irqthread;
         unsigned long flags;
 
         WARN(in_interrupt(), "Trying to free IRQ %d from IRQ context!\n", irq);
@@ -622,6 +761,10 @@ static struct irqaction *__free_irq(unsigned int irq, void *dev_id)
                 else
                         desc->chip->disable(irq);
         }
+
+        irqthread = action->thread;
+        action->thread = NULL;
+
         spin_unlock_irqrestore(&desc->lock, flags);
 
         unregister_handler_proc(irq, action);
@@ -629,6 +772,12 @@ static struct irqaction *__free_irq(unsigned int irq, void *dev_id)
         /* Make sure it's not being used on another CPU: */
         synchronize_irq(irq);
 
+        if (irqthread) {
+                if (!test_bit(IRQTF_DIED, &action->thread_flags))
+                        kthread_stop(irqthread);
+                put_task_struct(irqthread);
+        }
+
 #ifdef CONFIG_DEBUG_SHIRQ
         /*
          * It's a shared IRQ -- the driver ought to be prepared for an IRQ
@@ -681,9 +830,12 @@ void free_irq(unsigned int irq, void *dev_id)
 EXPORT_SYMBOL(free_irq);
 
 /**
- *      request_irq - allocate an interrupt line
+ *      request_threaded_irq - allocate an interrupt line
  *      @irq: Interrupt line to allocate
- *      @handler: Function to be called when the IRQ occurs
+ *      @handler: Function to be called when the IRQ occurs.
+ *                Primary handler for threaded interrupts
+ *      @thread_fn: Function called from the irq handler thread
+ *                  If NULL, no irq thread is created
  *      @irqflags: Interrupt type flags
  *      @devname: An ascii name for the claiming device
  *      @dev_id: A cookie passed back to the handler function
@@ -695,6 +847,15 @@ EXPORT_SYMBOL(free_irq);
  *      raises, you must take care both to initialise your hardware
  *      and to set up the interrupt handler in the right order.
  *
+ *      If you want to set up a threaded irq handler for your device
+ *      then you need to supply @handler and @thread_fn. @handler ist
+ *      still called in hard interrupt context and has to check
+ *      whether the interrupt originates from the device. If yes it
+ *      needs to disable the interrupt on the device and return
+ *      IRQ_THREAD_WAKE which will wake up the handler thread and run
+ *      @thread_fn. This split handler design is necessary to support
+ *      shared interrupts.
+ *
  *      Dev_id must be globally unique. Normally the address of the
  *      device data structure is used as the cookie. Since the handler
  *      receives this value it makes sense to use it.
@@ -710,8 +871,9 @@ EXPORT_SYMBOL(free_irq);
  *      IRQF_TRIGGER_*          Specify active edge(s) or level
  *
  */
-int request_irq(unsigned int irq, irq_handler_t handler,
-                unsigned long irqflags, const char *devname, void *dev_id)
+int request_threaded_irq(unsigned int irq, irq_handler_t handler,
+                         irq_handler_t thread_fn, unsigned long irqflags,
+                         const char *devname, void *dev_id)
 {
         struct irqaction *action;
         struct irq_desc *desc;
@@ -759,6 +921,7 @@ int request_irq(unsigned int irq, irq_handler_t handler,
                 return -ENOMEM;
 
         action->handler = handler;
+        action->thread_fn = thread_fn;
         action->flags = irqflags;
         action->name = devname;
         action->dev_id = dev_id;
@@ -788,4 +951,4 @@ int request_irq(unsigned int irq, irq_handler_t handler,
 #endif
         return retval;
 }
-EXPORT_SYMBOL(request_irq);
+EXPORT_SYMBOL(request_threaded_irq);
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 5016bfb682b9..a5e74ddee0e2 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -68,7 +68,7 @@ static struct hlist_head kprobe_table[KPROBE_TABLE_SIZE];
 static struct hlist_head kretprobe_inst_table[KPROBE_TABLE_SIZE];
 
 /* NOTE: change this value only with kprobe_mutex held */
-static bool kprobe_enabled;
+static bool kprobes_all_disarmed;
 
 static DEFINE_MUTEX(kprobe_mutex);      /* Protects kprobe_table */
 static DEFINE_PER_CPU(struct kprobe *, kprobe_instance) = NULL;
@@ -328,7 +328,7 @@ static int __kprobes aggr_pre_handler(struct kprobe *p, struct pt_regs *regs)
         struct kprobe *kp;
 
         list_for_each_entry_rcu(kp, &p->list, list) {
-                if (kp->pre_handler && !kprobe_gone(kp)) {
+                if (kp->pre_handler && likely(!kprobe_disabled(kp))) {
                         set_kprobe_instance(kp);
                         if (kp->pre_handler(kp, regs))
                                 return 1;
@@ -344,7 +344,7 @@ static void __kprobes aggr_post_handler(struct kprobe *p, struct pt_regs *regs,
         struct kprobe *kp;
 
         list_for_each_entry_rcu(kp, &p->list, list) {
-                if (kp->post_handler && !kprobe_gone(kp)) {
+                if (kp->post_handler && likely(!kprobe_disabled(kp))) {
                         set_kprobe_instance(kp);
                         kp->post_handler(kp, regs, flags);
                         reset_kprobe_instance();
@@ -518,20 +518,28 @@ static inline void copy_kprobe(struct kprobe *old_p, struct kprobe *p)
 }
 
 /*
-* Add the new probe to old_p->list. Fail if this is the
+* Add the new probe to ap->list. Fail if this is the
 * second jprobe at the address - two jprobes can't coexist
 */
-static int __kprobes add_new_kprobe(struct kprobe *old_p, struct kprobe *p)
+static int __kprobes add_new_kprobe(struct kprobe *ap, struct kprobe *p)
 {
+        BUG_ON(kprobe_gone(ap) || kprobe_gone(p));
         if (p->break_handler) {
-                if (old_p->break_handler)
+                if (ap->break_handler)
                         return -EEXIST;
-                list_add_tail_rcu(&p->list, &old_p->list);
-                old_p->break_handler = aggr_break_handler;
+                list_add_tail_rcu(&p->list, &ap->list);
+                ap->break_handler = aggr_break_handler;
         } else
-                list_add_rcu(&p->list, &old_p->list);
-        if (p->post_handler && !old_p->post_handler)
-                old_p->post_handler = aggr_post_handler;
+                list_add_rcu(&p->list, &ap->list);
+        if (p->post_handler && !ap->post_handler)
+                ap->post_handler = aggr_post_handler;
+
+        if (kprobe_disabled(ap) && !kprobe_disabled(p)) {
+                ap->flags &= ~KPROBE_FLAG_DISABLED;
+                if (!kprobes_all_disarmed)
+                        /* Arm the breakpoint again. */
+                        arch_arm_kprobe(ap);
+        }
         return 0;
 }
 
@@ -544,6 +552,7 @@ static inline void add_aggr_kprobe(struct kprobe *ap, struct kprobe *p)
         copy_kprobe(p, ap);
         flush_insn_slot(ap);
         ap->addr = p->addr;
+        ap->flags = p->flags;
         ap->pre_handler = aggr_pre_handler;
         ap->fault_handler = aggr_fault_handler;
         /* We don't care the kprobe which has gone. */
@@ -566,44 +575,59 @@ static int __kprobes register_aggr_kprobe(struct kprobe *old_p,
                                           struct kprobe *p)
 {
         int ret = 0;
-        struct kprobe *ap;
+        struct kprobe *ap = old_p;
 
-        if (kprobe_gone(old_p)) {
+        if (old_p->pre_handler != aggr_pre_handler) {
+                /* If old_p is not an aggr_probe, create new aggr_kprobe. */
+                ap = kzalloc(sizeof(struct kprobe), GFP_KERNEL);
+                if (!ap)
+                        return -ENOMEM;
+                add_aggr_kprobe(ap, old_p);
+        }
+
+        if (kprobe_gone(ap)) {
                 /*
                  * Attempting to insert new probe at the same location that
                  * had a probe in the module vaddr area which already
                  * freed. So, the instruction slot has already been
                  * released. We need a new slot for the new probe.
                  */
-                ret = arch_prepare_kprobe(old_p);
+                ret = arch_prepare_kprobe(ap);
                 if (ret)
+                        /*
+                         * Even if fail to allocate new slot, don't need to
+                         * free aggr_probe. It will be used next time, or
+                         * freed by unregister_kprobe.
+                         */
                         return ret;
-        }
-        if (old_p->pre_handler == aggr_pre_handler) {
-                copy_kprobe(old_p, p);
-                ret = add_new_kprobe(old_p, p);
-                ap = old_p;
-        } else {
-                ap = kzalloc(sizeof(struct kprobe), GFP_KERNEL);
-                if (!ap) {
-                        if (kprobe_gone(old_p))
-                                arch_remove_kprobe(old_p);
-                        return -ENOMEM;
-                }
-                add_aggr_kprobe(ap, old_p);
-                copy_kprobe(ap, p);
-                ret = add_new_kprobe(ap, p);
-        }
-        if (kprobe_gone(old_p)) {
+
                 /*
-                 * If the old_p has gone, its breakpoint has been disarmed.
-                 * We have to arm it again after preparing real kprobes.
+                 * Clear gone flag to prevent allocating new slot again, and
+                 * set disabled flag because it is not armed yet.
                  */
-                ap->flags &= ~KPROBE_FLAG_GONE;
-                if (kprobe_enabled)
-                        arch_arm_kprobe(ap);
+                ap->flags = (ap->flags & ~KPROBE_FLAG_GONE)
+                            | KPROBE_FLAG_DISABLED;
         }
-        return ret;
+
+        copy_kprobe(ap, p);
+        return add_new_kprobe(ap, p);
+}
+
+/* Try to disable aggr_kprobe, and return 1 if succeeded.*/
+static int __kprobes try_to_disable_aggr_kprobe(struct kprobe *p)
+{
+        struct kprobe *kp;
+
+        list_for_each_entry_rcu(kp, &p->list, list) {
+                if (!kprobe_disabled(kp))
+                        /*
+                         * There is an active probe on the list.
+                         * We can't disable aggr_kprobe.
+                         */
+                        return 0;
+        }
+        p->flags |= KPROBE_FLAG_DISABLED;
+        return 1;
 }
 
 static int __kprobes in_kprobes_functions(unsigned long addr)
@@ -664,7 +688,9 @@ int __kprobes register_kprobe(struct kprobe *p)
                 return -EINVAL;
         }
 
-        p->flags = 0;
+        /* User can pass only KPROBE_FLAG_DISABLED to register_kprobe */
+        p->flags &= KPROBE_FLAG_DISABLED;
+
         /*
          * Check if are we probing a module.
          */
@@ -709,7 +735,7 @@ int __kprobes register_kprobe(struct kprobe *p)
         hlist_add_head_rcu(&p->hlist,
                        &kprobe_table[hash_ptr(p->addr, KPROBE_HASH_BITS)]);
 
-        if (kprobe_enabled)
+        if (!kprobes_all_disarmed && !kprobe_disabled(p))
                 arch_arm_kprobe(p);
 
 out_unlock_text:
@@ -722,26 +748,39 @@ out:
 
         return ret;
 }
+EXPORT_SYMBOL_GPL(register_kprobe);
 
-/*
- * Unregister a kprobe without a scheduler synchronization.
- */
-static int __kprobes __unregister_kprobe_top(struct kprobe *p)
+/* Check passed kprobe is valid and return kprobe in kprobe_table. */
+static struct kprobe * __kprobes __get_valid_kprobe(struct kprobe *p)
 {
         struct kprobe *old_p, *list_p;
 
         old_p = get_kprobe(p->addr);
         if (unlikely(!old_p))
-                return -EINVAL;
+                return NULL;
 
         if (p != old_p) {
                 list_for_each_entry_rcu(list_p, &old_p->list, list)
                         if (list_p == p)
                         /* kprobe p is a valid probe */
-                                goto valid_p;
-                return -EINVAL;
+                                goto valid;
+                return NULL;
         }
-valid_p:
+valid:
+        return old_p;
+}
+
+/*
+ * Unregister a kprobe without a scheduler synchronization.
+ */
+static int __kprobes __unregister_kprobe_top(struct kprobe *p)
+{
+        struct kprobe *old_p, *list_p;
+
+        old_p = __get_valid_kprobe(p);
+        if (old_p == NULL)
+                return -EINVAL;
+
         if (old_p == p ||
             (old_p->pre_handler == aggr_pre_handler &&
              list_is_singular(&old_p->list))) {
@@ -750,7 +789,7 @@ valid_p:
                  * enabled and not gone - otherwise, the breakpoint would
                  * already have been removed. We save on flushing icache.
                  */
-                if (kprobe_enabled && !kprobe_gone(old_p)) {
+                if (!kprobes_all_disarmed && !kprobe_disabled(old_p)) {
                         mutex_lock(&text_mutex);
                         arch_disarm_kprobe(p);
                         mutex_unlock(&text_mutex);
@@ -768,6 +807,11 @@ valid_p:
                 }
 noclean:
                 list_del_rcu(&p->list);
+                if (!kprobe_disabled(old_p)) {
+                        try_to_disable_aggr_kprobe(old_p);
+                        if (!kprobes_all_disarmed && kprobe_disabled(old_p))
+                                arch_disarm_kprobe(old_p);
+                }
         }
         return 0;
 }
@@ -803,11 +847,13 @@ int __kprobes register_kprobes(struct kprobe **kps, int num)
         }
         return ret;
 }
+EXPORT_SYMBOL_GPL(register_kprobes);
 
 void __kprobes unregister_kprobe(struct kprobe *p)
 {
         unregister_kprobes(&p, 1);
 }
+EXPORT_SYMBOL_GPL(unregister_kprobe);
 
 void __kprobes unregister_kprobes(struct kprobe **kps, int num)
 {
@@ -826,6 +872,7 @@ void __kprobes unregister_kprobes(struct kprobe **kps, int num)
                 if (kps[i]->addr)
                         __unregister_kprobe_bottom(kps[i]);
 }
+EXPORT_SYMBOL_GPL(unregister_kprobes);
 
 static struct notifier_block kprobe_exceptions_nb = {
         .notifier_call = kprobe_exceptions_notify,
@@ -865,16 +912,19 @@ int __kprobes register_jprobes(struct jprobe **jps, int num)
         }
         return ret;
 }
+EXPORT_SYMBOL_GPL(register_jprobes);
 
 int __kprobes register_jprobe(struct jprobe *jp)
 {
         return register_jprobes(&jp, 1);
 }
+EXPORT_SYMBOL_GPL(register_jprobe);
 
 void __kprobes unregister_jprobe(struct jprobe *jp)
 {
         unregister_jprobes(&jp, 1);
 }
+EXPORT_SYMBOL_GPL(unregister_jprobe);
 
 void __kprobes unregister_jprobes(struct jprobe **jps, int num)
 {
@@ -894,6 +944,7 @@ void __kprobes unregister_jprobes(struct jprobe **jps, int num)
                         __unregister_kprobe_bottom(&jps[i]->kp);
         }
 }
+EXPORT_SYMBOL_GPL(unregister_jprobes);
 
 #ifdef CONFIG_KRETPROBES
 /*
@@ -987,6 +1038,7 @@ int __kprobes register_kretprobe(struct kretprobe *rp)
                 free_rp_inst(rp);
         return ret;
 }
+EXPORT_SYMBOL_GPL(register_kretprobe);
 
 int __kprobes register_kretprobes(struct kretprobe **rps, int num)
 {
@@ -1004,11 +1056,13 @@ int __kprobes register_kretprobes(struct kretprobe **rps, int num)
         }
         return ret;
 }
+EXPORT_SYMBOL_GPL(register_kretprobes);
 
 void __kprobes unregister_kretprobe(struct kretprobe *rp)
 {
         unregister_kretprobes(&rp, 1);
 }
+EXPORT_SYMBOL_GPL(unregister_kretprobe);
 
 void __kprobes unregister_kretprobes(struct kretprobe **rps, int num)
 {
@@ -1030,24 +1084,30 @@ void __kprobes unregister_kretprobes(struct kretprobe **rps, int num)
                 }
         }
 }
+EXPORT_SYMBOL_GPL(unregister_kretprobes);
 
 #else /* CONFIG_KRETPROBES */
 int __kprobes register_kretprobe(struct kretprobe *rp)
 {
         return -ENOSYS;
 }
+EXPORT_SYMBOL_GPL(register_kretprobe);
 
 int __kprobes register_kretprobes(struct kretprobe **rps, int num)
 {
         return -ENOSYS;
 }
+EXPORT_SYMBOL_GPL(register_kretprobes);
+
 void __kprobes unregister_kretprobe(struct kretprobe *rp)
 {
 }
+EXPORT_SYMBOL_GPL(unregister_kretprobe);
 
 void __kprobes unregister_kretprobes(struct kretprobe **rps, int num)
 {
 }
+EXPORT_SYMBOL_GPL(unregister_kretprobes);
 
 static int __kprobes pre_handler_kretprobe(struct kprobe *p,
                                            struct pt_regs *regs)
@@ -1061,6 +1121,7 @@ static int __kprobes pre_handler_kretprobe(struct kprobe *p,
 static void __kprobes kill_kprobe(struct kprobe *p)
 {
         struct kprobe *kp;
+
         p->flags |= KPROBE_FLAG_GONE;
         if (p->pre_handler == aggr_pre_handler) {
                 /*
@@ -1173,8 +1234,8 @@ static int __init init_kprobes(void)
                 }
         }
 
-        /* By default, kprobes are enabled */
-        kprobe_enabled = true;
+        /* By default, kprobes are armed */
+        kprobes_all_disarmed = false;
 
         err = arch_init_kprobes();
         if (!err)
@@ -1202,12 +1263,18 @@ static void __kprobes report_probe(struct seq_file *pi, struct kprobe *p,
         else
                 kprobe_type = "k";
         if (sym)
-                seq_printf(pi, "%p  %s  %s+0x%x  %s %s\n", p->addr, kprobe_type,
-                        sym, offset, (modname ? modname : " "),
-                        (kprobe_gone(p) ? "[GONE]" : ""));
+                seq_printf(pi, "%p  %s  %s+0x%x  %s %s%s\n",
+                        p->addr, kprobe_type, sym, offset,
+                        (modname ? modname : " "),
+                        (kprobe_gone(p) ? "[GONE]" : ""),
+                        ((kprobe_disabled(p) && !kprobe_gone(p)) ?
+                         "[DISABLED]" : ""));
         else
-                seq_printf(pi, "%p  %s  %p %s\n", p->addr, kprobe_type, p->addr,
-                        (kprobe_gone(p) ? "[GONE]" : ""));
+                seq_printf(pi, "%p  %s  %p %s%s\n",
+                        p->addr, kprobe_type, p->addr,
+                        (kprobe_gone(p) ? "[GONE]" : ""),
+                        ((kprobe_disabled(p) && !kprobe_gone(p)) ?
+                         "[DISABLED]" : ""));
 }
 
 static void __kprobes *kprobe_seq_start(struct seq_file *f, loff_t *pos)
@@ -1272,7 +1339,72 @@ static struct file_operations debugfs_kprobes_operations = {
         .release        = seq_release,
 };
 
-static void __kprobes enable_all_kprobes(void)
+/* Disable one kprobe */
+int __kprobes disable_kprobe(struct kprobe *kp)
+{
+        int ret = 0;
+        struct kprobe *p;
+
+        mutex_lock(&kprobe_mutex);
+
+        /* Check whether specified probe is valid. */
+        p = __get_valid_kprobe(kp);
+        if (unlikely(p == NULL)) {
+                ret = -EINVAL;
+                goto out;
+        }
+
+        /* If the probe is already disabled (or gone), just return */
+        if (kprobe_disabled(kp))
+                goto out;
+
+        kp->flags |= KPROBE_FLAG_DISABLED;
+        if (p != kp)
+                /* When kp != p, p is always enabled. */
+                try_to_disable_aggr_kprobe(p);
+
+        if (!kprobes_all_disarmed && kprobe_disabled(p))
+                arch_disarm_kprobe(p);
+out:
+        mutex_unlock(&kprobe_mutex);
+        return ret;
+}
+EXPORT_SYMBOL_GPL(disable_kprobe);
+
+/* Enable one kprobe */
+int __kprobes enable_kprobe(struct kprobe *kp)
+{
+        int ret = 0;
+        struct kprobe *p;
+
+        mutex_lock(&kprobe_mutex);
+
+        /* Check whether specified probe is valid. */
+        p = __get_valid_kprobe(kp);
+        if (unlikely(p == NULL)) {
+                ret = -EINVAL;
+                goto out;
+        }
+
+        if (kprobe_gone(kp)) {
+                /* This kprobe has gone, we couldn't enable it. */
+                ret = -EINVAL;
+                goto out;
+        }
+
+        if (!kprobes_all_disarmed && kprobe_disabled(p))
+                arch_arm_kprobe(p);
+
+        p->flags &= ~KPROBE_FLAG_DISABLED;
+        if (p != kp)
+                kp->flags &= ~KPROBE_FLAG_DISABLED;
+out:
+        mutex_unlock(&kprobe_mutex);
+        return ret;
+}
+EXPORT_SYMBOL_GPL(enable_kprobe);
+
+static void __kprobes arm_all_kprobes(void)
 {
         struct hlist_head *head;
         struct hlist_node *node;
@@ -1281,20 +1413,20 @@ static void __kprobes enable_all_kprobes(void)
 
         mutex_lock(&kprobe_mutex);
 
-        /* If kprobes are already enabled, just return */
-        if (kprobe_enabled)
+        /* If kprobes are armed, just return */
+        if (!kprobes_all_disarmed)
                 goto already_enabled;
 
         mutex_lock(&text_mutex);
         for (i = 0; i < KPROBE_TABLE_SIZE; i++) {
                 head = &kprobe_table[i];
                 hlist_for_each_entry_rcu(p, node, head, hlist)
-                        if (!kprobe_gone(p))
+                        if (!kprobe_disabled(p))
                                 arch_arm_kprobe(p);
         }
         mutex_unlock(&text_mutex);
 
-        kprobe_enabled = true;
+        kprobes_all_disarmed = false;
         printk(KERN_INFO "Kprobes globally enabled\n");
 
 already_enabled:
@@ -1302,7 +1434,7 @@ already_enabled:
         return;
 }
 
-static void __kprobes disable_all_kprobes(void)
+static void __kprobes disarm_all_kprobes(void)
 {
         struct hlist_head *head;
         struct hlist_node *node;
@@ -1311,17 +1443,17 @@ static void __kprobes disable_all_kprobes(void)
 
         mutex_lock(&kprobe_mutex);
 
-        /* If kprobes are already disabled, just return */
-        if (!kprobe_enabled)
+        /* If kprobes are already disarmed, just return */
+        if (kprobes_all_disarmed)
                 goto already_disabled;
 
-        kprobe_enabled = false;
+        kprobes_all_disarmed = true;
         printk(KERN_INFO "Kprobes globally disabled\n");
         mutex_lock(&text_mutex);
         for (i = 0; i < KPROBE_TABLE_SIZE; i++) {
                 head = &kprobe_table[i];
                 hlist_for_each_entry_rcu(p, node, head, hlist) {
-                        if (!arch_trampoline_kprobe(p) && !kprobe_gone(p))
+                        if (!arch_trampoline_kprobe(p) && !kprobe_disabled(p))
                                 arch_disarm_kprobe(p);
                 }
         }
@@ -1347,7 +1479,7 @@ static ssize_t read_enabled_file_bool(struct file *file,
 {
         char buf[3];
 
-        if (kprobe_enabled)
+        if (!kprobes_all_disarmed)
                 buf[0] = '1';
         else
                 buf[0] = '0';
@@ -1370,12 +1502,12 @@ static ssize_t write_enabled_file_bool(struct file *file,
         case 'y':
         case 'Y':
         case '1':
-                enable_all_kprobes();
+                arm_all_kprobes();
                 break;
         case 'n':
         case 'N':
         case '0':
-                disable_all_kprobes();
+                disarm_all_kprobes();
                 break;
         }
 
@@ -1418,16 +1550,5 @@ late_initcall(debugfs_kprobe_init);
 
 module_init(init_kprobes);
 
-EXPORT_SYMBOL_GPL(register_kprobe);
-EXPORT_SYMBOL_GPL(unregister_kprobe);
-EXPORT_SYMBOL_GPL(register_kprobes);
-EXPORT_SYMBOL_GPL(unregister_kprobes);
-EXPORT_SYMBOL_GPL(register_jprobe);
-EXPORT_SYMBOL_GPL(unregister_jprobe);
-EXPORT_SYMBOL_GPL(register_jprobes);
-EXPORT_SYMBOL_GPL(unregister_jprobes);
+/* defined in arch/.../kernel/kprobes.c */
 EXPORT_SYMBOL_GPL(jprobe_return);
-EXPORT_SYMBOL_GPL(register_kretprobe);
-EXPORT_SYMBOL_GPL(unregister_kretprobe);
-EXPORT_SYMBOL_GPL(register_kretprobes);
-EXPORT_SYMBOL_GPL(unregister_kretprobes);
diff --git a/kernel/module.c b/kernel/module.c
index c268a771595c..05f014efa32c 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -1952,9 +1952,6 @@ static noinline struct module *load_module(void __user *umod,
                 if (strstarts(secstrings+sechdrs[i].sh_name, ".exit"))
                         sechdrs[i].sh_flags &= ~(unsigned long)SHF_ALLOC;
 #endif
-                /* Don't keep __versions around; it's just for loading. */
-                if (strcmp(secstrings + sechdrs[i].sh_name, "__versions") == 0)
-                        sechdrs[i].sh_flags &= ~(unsigned long)SHF_ALLOC;
         }
 
         modindex = find_sec(hdr, sechdrs, secstrings,
diff --git a/kernel/softlockup.c b/kernel/softlockup.c
index 85d5a2455103..88796c330838 100644
--- a/kernel/softlockup.c
+++ b/kernel/softlockup.c
@@ -166,97 +166,11 @@ void softlockup_tick(void)
 }
 
 /*
- * Have a reasonable limit on the number of tasks checked:
- */
-unsigned long __read_mostly sysctl_hung_task_check_count = 1024;
-
-/*
- * Zero means infinite timeout - no checking done:
- */
-unsigned long __read_mostly sysctl_hung_task_timeout_secs = 480;
-
-unsigned long __read_mostly sysctl_hung_task_warnings = 10;
-
-/*
- * Only do the hung-tasks check on one CPU:
- */
-static int check_cpu __read_mostly = -1;
-
-static void check_hung_task(struct task_struct *t, unsigned long now)
-{
-        unsigned long switch_count = t->nvcsw + t->nivcsw;
-
-        if (t->flags & PF_FROZEN)
-                return;
-
-        if (switch_count != t->last_switch_count || !t->last_switch_timestamp) {
-                t->last_switch_count = switch_count;
-                t->last_switch_timestamp = now;
-                return;
-        }
-        if ((long)(now - t->last_switch_timestamp) <
-                                        sysctl_hung_task_timeout_secs)
-                return;
-        if (!sysctl_hung_task_warnings)
-                return;
-        sysctl_hung_task_warnings--;
-
-        /*
-         * Ok, the task did not get scheduled for more than 2 minutes,
-         * complain:
-         */
-        printk(KERN_ERR "INFO: task %s:%d blocked for more than "
-                        "%ld seconds.\n", t->comm, t->pid,
-                        sysctl_hung_task_timeout_secs);
-        printk(KERN_ERR "\"echo 0 > /proc/sys/kernel/hung_task_timeout_secs\""
-                        " disables this message.\n");
-        sched_show_task(t);
-        __debug_show_held_locks(t);
-
-        t->last_switch_timestamp = now;
-        touch_nmi_watchdog();
-
-        if (softlockup_panic)
-                panic("softlockup: blocked tasks");
-}
-
-/*
- * Check whether a TASK_UNINTERRUPTIBLE does not get woken up for
- * a really long time (120 seconds). If that happens, print out
- * a warning.
- */
-static void check_hung_uninterruptible_tasks(int this_cpu)
-{
-        int max_count = sysctl_hung_task_check_count;
-        unsigned long now = get_timestamp(this_cpu);
-        struct task_struct *g, *t;
-
-        /*
-         * If the system crashed already then all bets are off,
-         * do not report extra hung tasks:
-         */
-        if (test_taint(TAINT_DIE) || did_panic)
-                return;
-
-        read_lock(&tasklist_lock);
-        do_each_thread(g, t) {
-                if (!--max_count)
-                        goto unlock;
-                /* use "==" to skip the TASK_KILLABLE tasks waiting on NFS */
-                if (t->state == TASK_UNINTERRUPTIBLE)
-                        check_hung_task(t, now);
-        } while_each_thread(g, t);
- unlock:
-        read_unlock(&tasklist_lock);
-}
-
-/*
  * The watchdog thread - runs every second and touches the timestamp.
  */
 static int watchdog(void *__bind_cpu)
 {
         struct sched_param param = { .sched_priority = MAX_RT_PRIO-1 };
-        int this_cpu = (long)__bind_cpu;
 
         sched_setscheduler(current, SCHED_FIFO, &param);
 
@@ -276,11 +190,6 @@ static int watchdog(void *__bind_cpu)
                 if (kthread_should_stop())
                         break;
 
-                if (this_cpu == check_cpu) {
-                        if (sysctl_hung_task_timeout_secs)
-                                check_hung_uninterruptible_tasks(this_cpu);
-                }
-
                 set_current_state(TASK_INTERRUPTIBLE);
         }
         __set_current_state(TASK_RUNNING);
@@ -312,18 +221,9 @@ cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu)
                 break;
         case CPU_ONLINE:
         case CPU_ONLINE_FROZEN:
-                check_cpu = cpumask_any(cpu_online_mask);
                 wake_up_process(per_cpu(watchdog_task, hotcpu));
                 break;
 #ifdef CONFIG_HOTPLUG_CPU
-        case CPU_DOWN_PREPARE:
-        case CPU_DOWN_PREPARE_FROZEN:
-                if (hotcpu == check_cpu) {
-                        /* Pick any other online cpu. */
-                        check_cpu = cpumask_any_but(cpu_online_mask, hotcpu);
-                }
-                break;
-
         case CPU_UP_CANCELED:
         case CPU_UP_CANCELED_FROZEN:
                 if (!per_cpu(watchdog_task, hotcpu))
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index b125e3387568..4286b62b34a0 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -101,6 +101,7 @@ static int __maybe_unused one = 1;
 static int __maybe_unused two = 2;
 static unsigned long one_ul = 1;
 static int one_hundred = 100;
+static int one_thousand = 1000;
 
 /* this is needed for the proc_dointvec_minmax for [fs_]overflow UID and GID */
 static int maxolduid = 65535;
@@ -813,6 +814,19 @@ static struct ctl_table kern_table[] = {
                 .extra1         = &neg_one,
                 .extra2         = &sixty,
         },
+#endif
+#ifdef CONFIG_DETECT_HUNG_TASK
+        {
+                .ctl_name       = CTL_UNNUMBERED,
+                .procname       = "hung_task_panic",
+                .data           = &sysctl_hung_task_panic,
+                .maxlen         = sizeof(int),
+                .mode           = 0644,
+                .proc_handler   = &proc_dointvec_minmax,
+                .strategy       = &sysctl_intvec,
+                .extra1         = &zero,
+                .extra2         = &one,
+        },
         {
                 .ctl_name       = CTL_UNNUMBERED,
                 .procname       = "hung_task_check_count",
@@ -828,7 +842,7 @@ static struct ctl_table kern_table[] = {
                 .data           = &sysctl_hung_task_timeout_secs,
                 .maxlen         = sizeof(unsigned long),
                 .mode           = 0644,
-                .proc_handler   = &proc_doulongvec_minmax,
+                .proc_handler   = &proc_dohung_task_timeout_secs,
                 .strategy       = &sysctl_intvec,
         },
         {
@@ -1027,6 +1041,28 @@ static struct ctl_table vm_table[] = {
                 .proc_handler   = &proc_dointvec,
         },
         {
+                .ctl_name       = CTL_UNNUMBERED,
+                .procname       = "nr_pdflush_threads_min",
+                .data           = &nr_pdflush_threads_min,
+                .maxlen         = sizeof nr_pdflush_threads_min,
+                .mode           = 0644 /* read-write */,
+                .proc_handler   = &proc_dointvec_minmax,
+                .strategy       = &sysctl_intvec,
+                .extra1         = &one,
+                .extra2         = &nr_pdflush_threads_max,
+        },
+        {
+                .ctl_name       = CTL_UNNUMBERED,
+                .procname       = "nr_pdflush_threads_max",
+                .data           = &nr_pdflush_threads_max,
+                .maxlen         = sizeof nr_pdflush_threads_max,
+                .mode           = 0644 /* read-write */,
+                .proc_handler   = &proc_dointvec_minmax,
+                .strategy       = &sysctl_intvec,
+                .extra1         = &nr_pdflush_threads_min,
+                .extra2         = &one_thousand,
+        },
+        {
                 .ctl_name       = VM_SWAPPINESS,
                 .procname       = "swappiness",
                 .data           = &vm_swappiness,
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index 947c5b3f90c4..b32ff446c3fb 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -327,10 +327,10 @@ static ssize_t blk_msg_write(struct file *filp, const char __user *buffer,
         char *msg;
         struct blk_trace *bt;
 
-        if (count > BLK_TN_MAX_MSG)
+        if (count >= BLK_TN_MAX_MSG)
                 return -EINVAL;
 
-        msg = kmalloc(count, GFP_KERNEL);
+        msg = kmalloc(count + 1, GFP_KERNEL);
         if (msg == NULL)
                 return -ENOMEM;
 
@@ -339,6 +339,7 @@ static ssize_t blk_msg_write(struct file *filp, const char __user *buffer,
                 return -EFAULT;
         }
 
+        msg[count] = '\0';
         bt = filp->private_data;
         __trace_note_message(bt, "%s", msg);
         kfree(msg);
@@ -642,7 +643,7 @@ static void blk_add_trace_rq(struct request_queue *q, struct request *rq,
         if (blk_pc_request(rq)) {
                 what |= BLK_TC_ACT(BLK_TC_PC);
                 __blk_add_trace(bt, 0, rq->data_len, rw, what, rq->errors,
-                                sizeof(rq->cmd), rq->cmd);
+                                rq->cmd_len, rq->cmd);
         } else  {
                 what |= BLK_TC_ACT(BLK_TC_FS);
                 __blk_add_trace(bt, rq->hard_sector, rq->hard_nr_sectors << 9,
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index a0174a40c563..9d28476a9851 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -30,6 +30,7 @@
 #include <linux/percpu.h>
 #include <linux/splice.h>
 #include <linux/kdebug.h>
+#include <linux/string.h>
 #include <linux/ctype.h>
 #include <linux/init.h>
 #include <linux/poll.h>
@@ -147,8 +148,7 @@ static int __init set_ftrace_dump_on_oops(char *str)
 }
 __setup("ftrace_dump_on_oops", set_ftrace_dump_on_oops);
 
-long
-ns2usecs(cycle_t nsec)
+unsigned long long ns2usecs(cycle_t nsec)
 {
         nsec += 500;
         do_div(nsec, 1000);
@@ -1632,7 +1632,11 @@ static void test_cpu_buff_start(struct trace_iterator *iter)
                 return;
 
         cpumask_set_cpu(iter->cpu, iter->started);
-        trace_seq_printf(s, "##### CPU %u buffer started ####\n", iter->cpu);
+
+        /* Don't print started cpu buffer for the first entry of the trace */
+        if (iter->idx > 1)
+                trace_seq_printf(s, "##### CPU %u buffer started ####\n",
+                                iter->cpu);
 }
 
 static enum print_line_t print_trace_fmt(struct trace_iterator *iter)
@@ -1867,6 +1871,11 @@ __tracing_open(struct inode *inode, struct file *file)
         if (current_trace)
                 *iter->trace = *current_trace;
 
+        if (!alloc_cpumask_var(&iter->started, GFP_KERNEL))
+                goto fail;
+
+        cpumask_clear(iter->started);
+
         if (current_trace && current_trace->print_max)
                 iter->tr = &max_tr;
         else
@@ -1917,6 +1926,7 @@ __tracing_open(struct inode *inode, struct file *file)
                 if (iter->buffer_iter[cpu])
                         ring_buffer_read_finish(iter->buffer_iter[cpu]);
         }
+        free_cpumask_var(iter->started);
  fail:
         mutex_unlock(&trace_types_lock);
         kfree(iter->trace);
@@ -1960,6 +1970,7 @@ static int tracing_release(struct inode *inode, struct file *file)
 
         seq_release(inode, file);
         mutex_destroy(&iter->mutex);
+        free_cpumask_var(iter->started);
         kfree(iter->trace);
         kfree(iter);
         return 0;
@@ -2358,9 +2369,9 @@ static const char readme_msg[] =
         "# mkdir /debug\n"
         "# mount -t debugfs nodev /debug\n\n"
         "# cat /debug/tracing/available_tracers\n"
-        "wakeup preemptirqsoff preemptoff irqsoff ftrace sched_switch none\n\n"
+        "wakeup preemptirqsoff preemptoff irqsoff function sched_switch nop\n\n"
         "# cat /debug/tracing/current_tracer\n"
-        "none\n"
+        "nop\n"
         "# echo sched_switch > /debug/tracing/current_tracer\n"
         "# cat /debug/tracing/current_tracer\n"
         "sched_switch\n"
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index cbc168f1e43d..e685ac2b2ba1 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -602,7 +602,7 @@ extern int trace_selftest_startup_branch(struct tracer *trace,
 #endif /* CONFIG_FTRACE_STARTUP_TEST */
 
 extern void *head_page(struct trace_array_cpu *data);
-extern long ns2usecs(cycle_t nsec);
+extern unsigned long long ns2usecs(cycle_t nsec);
 extern int
 trace_vbprintk(unsigned long ip, const char *fmt, va_list args);
 extern int
diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c
index 4d9952d3df50..07a22c33ebf3 100644
--- a/kernel/trace/trace_export.c
+++ b/kernel/trace/trace_export.c
@@ -40,7 +40,7 @@
 
 #undef TRACE_FIELD_ZERO_CHAR
 #define TRACE_FIELD_ZERO_CHAR(item)                                     \
-        ret = trace_seq_printf(s, "\tfield: char " #item ";\t"          \
+        ret = trace_seq_printf(s, "\tfield:char " #item ";\t"           \
                                "offset:%u;\tsize:0;\n",                 \
                                (unsigned int)offsetof(typeof(field), item)); \
         if (!ret)                                                       \
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index d72b9a63b247..64b54a59c55b 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -423,7 +423,7 @@ int trace_print_lat_context(struct trace_iterator *iter)
 
                 trace_find_cmdline(entry->pid, comm);
 
-                ret = trace_seq_printf(s, "%16s %5d %3d %d %08x %08lx [%08lx]"
+                ret = trace_seq_printf(s, "%16s %5d %3d %d %08x %08lx [%08llx]"
                                        " %ld.%03ldms (+%ld.%03ldms): ", comm,
                                        entry->pid, iter->cpu, entry->flags,
                                        entry->preempt_count, iter->idx,
diff --git a/kernel/trace/trace_sched_switch.c b/kernel/trace/trace_sched_switch.c
index de35f200abd3..9117cea6f1ae 100644
--- a/kernel/trace/trace_sched_switch.c
+++ b/kernel/trace/trace_sched_switch.c
@@ -62,6 +62,9 @@ probe_sched_wakeup(struct rq *__rq, struct task_struct *wakee, int success)
         pc = preempt_count();
         tracing_record_cmdline(current);
 
+        if (sched_stopped)
+                return;
+
         local_irq_save(flags);
         cpu = raw_smp_processor_id();
         data = ctx_trace->data[cpu];
diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c
index 3c5ad6b2ec84..5bc00e8f153e 100644
--- a/kernel/trace/trace_sched_wakeup.c
+++ b/kernel/trace/trace_sched_wakeup.c
@@ -154,7 +154,7 @@ probe_wakeup_sched_switch(struct rq *rq, struct task_struct *prev,
         if (unlikely(!tracer_enabled || next != wakeup_task))
                 goto out_unlock;
 
-        trace_function(wakeup_trace, CALLER_ADDR1, CALLER_ADDR2, flags, pc);
+        trace_function(wakeup_trace, CALLER_ADDR0, CALLER_ADDR1, flags, pc);
         tracing_sched_switch_trace(wakeup_trace, prev, next, flags, pc);
 
         /*
@@ -257,6 +257,12 @@ probe_wakeup(struct rq *rq, struct task_struct *p, int success)
         data = wakeup_trace->data[wakeup_cpu];
         data->preempt_timestamp = ftrace_now(cpu);
         tracing_sched_wakeup_trace(wakeup_trace, p, current, flags, pc);
+
+        /*
+         * We must be careful in using CALLER_ADDR2. But since wake_up
+         * is not called by an assembly function  (where as schedule is)
+         * it should be safe to use it here.
+         */
         trace_function(wakeup_trace, CALLER_ADDR1, CALLER_ADDR2, flags, pc);
 
 out_locked: