Merge remote-tracking branch 'common/android-3.0' into msm-3.0

* common/android-3.0: (570 commits)
  misc: remove kernel debugger core
  ARM: common: fiq_debugger: dump sysrq directly to console if enabled
  ARM: common: fiq_debugger: add irq context debug functions
  net: wireless: bcmdhd: Call init_ioctl() only if was started properly for WEXT
  net: wireless: bcmdhd: Call init_ioctl() only if was started properly
  net: wireless: bcmdhd: Fix possible memory leak in escan/iscan
  cpufreq: interactive governor: default 20ms timer
  cpufreq: interactive governor: go to intermediate hi speed before max
  cpufreq: interactive governor: scale to max only if at min speed
  cpufreq: interactive governor: apply intermediate load on current speed
  ARM: idle: update idle ticks before call idle end notifier
  input: gpio_input: don't print debounce message unless flag is set
  net: wireless: bcm4329: Skip dhd_bus_stop() if bus is already down
  net: wireless: bcmdhd: Skip dhd_bus_stop() if bus is already down
  net: wireless: bcmdhd: Improve suspend/resume processing
  net: wireless: bcmdhd: Check if FW is Ok for internal FW call
  tcp: Don't nuke connections for the wrong protocol
  ARM: common: fiq_debugger: make uart irq be no_suspend
  net: wireless: Skip connect warning for CONFIG_CFG80211_ALLOW_RECONNECT
  mm: avoid livelock on !__GFP_FS allocations
  ...

Conflicts:
	arch/arm/mm/cache-l2x0.c
	arch/arm/vfp/vfpmodule.c
	drivers/mmc/core/host.c
	kernel/power/wakelock.c
	net/bluetooth/hci_event.c

Signed-off-by: Bryan Huntsman <bryanh@codeaurora.org>
diff --git a/kernel/futex.c b/kernel/futex.c
index 0a30897..11cbe05 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -218,6 +218,8 @@
  * @uaddr:	virtual address of the futex
  * @fshared:	0 for a PROCESS_PRIVATE futex, 1 for PROCESS_SHARED
  * @key:	address where result is stored.
+ * @rw:		mapping needs to be read/write (values: VERIFY_READ,
+ *              VERIFY_WRITE)
  *
  * Returns a negative error code or 0
  * The key words are stored in *key on success.
@@ -229,12 +231,12 @@
  * lock_page() might sleep, the caller should not hold a spinlock.
  */
 static int
-get_futex_key(u32 __user *uaddr, int fshared, union futex_key *key)
+get_futex_key(u32 __user *uaddr, int fshared, union futex_key *key, int rw)
 {
 	unsigned long address = (unsigned long)uaddr;
 	struct mm_struct *mm = current->mm;
 	struct page *page, *page_head;
-	int err;
+	int err, ro = 0;
 
 	/*
 	 * The futex address must be "naturally" aligned.
@@ -262,8 +264,18 @@
 
 again:
 	err = get_user_pages_fast(address, 1, 1, &page);
+	/*
+	 * If write access is not required (eg. FUTEX_WAIT), try
+	 * and get read-only access.
+	 */
+	if (err == -EFAULT && rw == VERIFY_READ) {
+		err = get_user_pages_fast(address, 1, 0, &page);
+		ro = 1;
+	}
 	if (err < 0)
 		return err;
+	else
+		err = 0;
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 	page_head = page;
@@ -305,6 +317,13 @@
 	if (!page_head->mapping) {
 		unlock_page(page_head);
 		put_page(page_head);
+		/*
+		* ZERO_PAGE pages don't have a mapping. Avoid a busy loop
+		* trying to find one. RW mapping would have COW'd (and thus
+		* have a mapping) so this page is RO and won't ever change.
+		*/
+		if ((page_head == ZERO_PAGE(address)))
+			return -EFAULT;
 		goto again;
 	}
 
@@ -316,6 +335,15 @@
 	 * the object not the particular process.
 	 */
 	if (PageAnon(page_head)) {
+		/*
+		 * A RO anonymous page will never change and thus doesn't make
+		 * sense for futex operations.
+		 */
+		if (ro) {
+			err = -EFAULT;
+			goto out;
+		}
+
 		key->both.offset |= FUT_OFF_MMSHARED; /* ref taken on mm */
 		key->private.mm = mm;
 		key->private.address = address;
@@ -327,9 +355,10 @@
 
 	get_futex_key_refs(key);
 
+out:
 	unlock_page(page_head);
 	put_page(page_head);
-	return 0;
+	return err;
 }
 
 static inline void put_futex_key(union futex_key *key)
@@ -940,7 +969,7 @@
 	if (!bitset)
 		return -EINVAL;
 
-	ret = get_futex_key(uaddr, flags & FLAGS_SHARED, &key);
+	ret = get_futex_key(uaddr, flags & FLAGS_SHARED, &key, VERIFY_READ);
 	if (unlikely(ret != 0))
 		goto out;
 
@@ -986,10 +1015,10 @@
 	int ret, op_ret;
 
 retry:
-	ret = get_futex_key(uaddr1, flags & FLAGS_SHARED, &key1);
+	ret = get_futex_key(uaddr1, flags & FLAGS_SHARED, &key1, VERIFY_READ);
 	if (unlikely(ret != 0))
 		goto out;
-	ret = get_futex_key(uaddr2, flags & FLAGS_SHARED, &key2);
+	ret = get_futex_key(uaddr2, flags & FLAGS_SHARED, &key2, VERIFY_WRITE);
 	if (unlikely(ret != 0))
 		goto out_put_key1;
 
@@ -1243,10 +1272,11 @@
 		pi_state = NULL;
 	}
 
-	ret = get_futex_key(uaddr1, flags & FLAGS_SHARED, &key1);
+	ret = get_futex_key(uaddr1, flags & FLAGS_SHARED, &key1, VERIFY_READ);
 	if (unlikely(ret != 0))
 		goto out;
-	ret = get_futex_key(uaddr2, flags & FLAGS_SHARED, &key2);
+	ret = get_futex_key(uaddr2, flags & FLAGS_SHARED, &key2,
+			    requeue_pi ? VERIFY_WRITE : VERIFY_READ);
 	if (unlikely(ret != 0))
 		goto out_put_key1;
 
@@ -1790,7 +1820,7 @@
 	 * while the syscall executes.
 	 */
 retry:
-	ret = get_futex_key(uaddr, flags & FLAGS_SHARED, &q->key);
+	ret = get_futex_key(uaddr, flags & FLAGS_SHARED, &q->key, VERIFY_READ);
 	if (unlikely(ret != 0))
 		return ret;
 
@@ -1941,7 +1971,7 @@
 	}
 
 retry:
-	ret = get_futex_key(uaddr, flags & FLAGS_SHARED, &q.key);
+	ret = get_futex_key(uaddr, flags & FLAGS_SHARED, &q.key, VERIFY_WRITE);
 	if (unlikely(ret != 0))
 		goto out;
 
@@ -2060,7 +2090,7 @@
 	if ((uval & FUTEX_TID_MASK) != vpid)
 		return -EPERM;
 
-	ret = get_futex_key(uaddr, flags & FLAGS_SHARED, &key);
+	ret = get_futex_key(uaddr, flags & FLAGS_SHARED, &key, VERIFY_WRITE);
 	if (unlikely(ret != 0))
 		goto out;
 
@@ -2249,7 +2279,7 @@
 	debug_rt_mutex_init_waiter(&rt_waiter);
 	rt_waiter.task = NULL;
 
-	ret = get_futex_key(uaddr2, flags & FLAGS_SHARED, &key2);
+	ret = get_futex_key(uaddr2, flags & FLAGS_SHARED, &key2, VERIFY_WRITE);
 	if (unlikely(ret != 0))
 		goto out;
 
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index 45e149c..2adc6b5 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -178,7 +178,7 @@
 	desc->depth = 1;
 	if (desc->irq_data.chip->irq_shutdown)
 		desc->irq_data.chip->irq_shutdown(&desc->irq_data);
-	if (desc->irq_data.chip->irq_disable)
+	else if (desc->irq_data.chip->irq_disable)
 		desc->irq_data.chip->irq_disable(&desc->irq_data);
 	else
 		desc->irq_data.chip->irq_mask(&desc->irq_data);
diff --git a/kernel/irq/generic-chip.c b/kernel/irq/generic-chip.c
index 3a2cab4..e38544d 100644
--- a/kernel/irq/generic-chip.c
+++ b/kernel/irq/generic-chip.c
@@ -246,7 +246,7 @@
 		gc->mask_cache = irq_reg_readl(gc->reg_base + ct->regs.mask);
 
 	for (i = gc->irq_base; msk; msk >>= 1, i++) {
-		if (!msk & 0x01)
+		if (!(msk & 0x01))
 			continue;
 
 		if (flags & IRQ_GC_INIT_NESTED_LOCK)
@@ -301,7 +301,7 @@
 	raw_spin_unlock(&gc_lock);
 
 	for (; msk; msk >>= 1, i++) {
-		if (!msk & 0x01)
+		if (!(msk & 0x01))
 			continue;
 
 		/* Remove handler first. That will mask the irq line */
diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c
index 58f405b..640ded8 100644
--- a/kernel/posix-cpu-timers.c
+++ b/kernel/posix-cpu-timers.c
@@ -250,7 +250,7 @@
 	do {
 		times->utime = cputime_add(times->utime, t->utime);
 		times->stime = cputime_add(times->stime, t->stime);
-		times->sum_exec_runtime += t->se.sum_exec_runtime;
+		times->sum_exec_runtime += task_sched_runtime(t);
 	} while_each_thread(tsk, t);
 out:
 	rcu_read_unlock();
@@ -274,9 +274,7 @@
 	struct task_cputime sum;
 	unsigned long flags;
 
-	spin_lock_irqsave(&cputimer->lock, flags);
 	if (!cputimer->running) {
-		cputimer->running = 1;
 		/*
 		 * The POSIX timer interface allows for absolute time expiry
 		 * values through the TIMER_ABSTIME flag, therefore we have
@@ -284,8 +282,11 @@
 		 * it.
 		 */
 		thread_group_cputime(tsk, &sum);
+		spin_lock_irqsave(&cputimer->lock, flags);
+		cputimer->running = 1;
 		update_gt_cputime(&cputimer->cputime, &sum);
-	}
+	} else
+		spin_lock_irqsave(&cputimer->lock, flags);
 	*times = cputimer->cputime;
 	spin_unlock_irqrestore(&cputimer->lock, flags);
 }
@@ -312,7 +313,8 @@
 		cpu->cpu = cputime.utime;
 		break;
 	case CPUCLOCK_SCHED:
-		cpu->sched = thread_group_sched_runtime(p);
+		thread_group_cputime(p, &cputime);
+		cpu->sched = cputime.sum_exec_runtime;
 		break;
 	}
 	return 0;
diff --git a/kernel/power/earlysuspend.c b/kernel/power/earlysuspend.c
index b15f02e..5a6b2fa 100644
--- a/kernel/power/earlysuspend.c
+++ b/kernel/power/earlysuspend.c
@@ -17,7 +17,6 @@
 #include <linux/module.h>
 #include <linux/mutex.h>
 #include <linux/rtc.h>
-#include <linux/syscalls.h> /* sys_sync */
 #include <linux/wakelock.h>
 #include <linux/workqueue.h>
 
@@ -103,10 +102,7 @@
 	}
 	mutex_unlock(&early_suspend_lock);
 
-	if (debug_mask & DEBUG_SUSPEND)
-		pr_info("early_suspend: sync\n");
-
-	sys_sync();
+	suspend_sys_sync_queue();
 abort:
 	spin_lock_irqsave(&state_lock, irqflags);
 	if (state == SUSPEND_REQUESTED_AND_SUSPENDED)
diff --git a/kernel/power/power.h b/kernel/power/power.h
index b6b9006..2d57e79 100644
--- a/kernel/power/power.h
+++ b/kernel/power/power.h
@@ -251,6 +251,11 @@
 extern struct workqueue_struct *suspend_work_queue;
 extern struct wake_lock main_wake_lock;
 extern suspend_state_t requested_suspend_state;
+extern void suspend_sys_sync_queue(void);
+extern int suspend_sys_sync_wait(void);
+#else
+static inline void suspend_sys_sync_queue(void) {}
+static inline int suspend_sys_sync_wait(void) { return 0; }
 #endif
 
 #ifdef CONFIG_USER_WAKELOCK
diff --git a/kernel/power/process.c b/kernel/power/process.c
index 31338cd..6c8c925 100644
--- a/kernel/power/process.c
+++ b/kernel/power/process.c
@@ -17,6 +17,7 @@
 #include <linux/delay.h>
 #include <linux/workqueue.h>
 #include <linux/wakelock.h>
+#include "power.h"
 
 /* 
  * Timeout for stopping processes
@@ -158,6 +159,10 @@
 		goto Exit;
 	printk("done.\n");
 
+	error = suspend_sys_sync_wait();
+	if (error)
+		goto Exit;
+
 	printk("Freezing remaining freezable tasks ... ");
 	error = try_to_freeze_tasks(false);
 	if (error)
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index 6799c42..9046443 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -276,7 +276,7 @@
 	if (!mutex_trylock(&pm_mutex))
 		return -EBUSY;
 
-	sys_sync();
+	suspend_sys_sync_queue();
 
 	pr_debug("PM: Preparing system for %s sleep\n", pm_states[state]);
 	error = suspend_prepare();
diff --git a/kernel/power/wakelock.c b/kernel/power/wakelock.c
index 892e3ec..23dfc40 100644
--- a/kernel/power/wakelock.c
+++ b/kernel/power/wakelock.c
@@ -52,6 +52,14 @@
 struct wake_lock main_wake_lock;
 suspend_state_t requested_suspend_state = PM_SUSPEND_MEM;
 static struct wake_lock unknown_wakeup;
+/* flag to warn/bug if wakelocks are taken after suspend_noirq */
+static int msm_suspend_check_done;
+static struct wake_lock suspend_backoff_lock;
+
+#define SUSPEND_BACKOFF_THRESHOLD	10
+#define SUSPEND_BACKOFF_INTERVAL	10000
+
+static unsigned suspend_short_count;
 
 #ifdef CONFIG_WAKELOCK_STAT
 static struct wake_lock deleted_wake_locks;
@@ -323,10 +331,18 @@
 	return 0;
 }
 
+static void suspend_backoff(void)
+{
+	pr_info("suspend: too many immediate wakeups, back off\n");
+	wake_lock_timeout(&suspend_backoff_lock,
+			  msecs_to_jiffies(SUSPEND_BACKOFF_INTERVAL));
+}
+
 static void suspend(struct work_struct *work)
 {
 	int ret;
 	int entry_event_num;
+	struct timespec ts_entry, ts_exit;
 
 	if (has_wake_lock(WAKE_LOCK_SUSPEND)) {
 		if (debug_mask & DEBUG_SUSPEND)
@@ -335,20 +351,33 @@
 	}
 
 	entry_event_num = current_event_num;
-	sys_sync();
+	suspend_sys_sync_queue();
 	if (debug_mask & DEBUG_SUSPEND)
 		pr_info("suspend: enter suspend\n");
+	getnstimeofday(&ts_entry);
 	ret = pm_suspend(requested_suspend_state);
+	getnstimeofday(&ts_exit);
+
 	if (debug_mask & DEBUG_EXIT_SUSPEND) {
-		struct timespec ts;
 		struct rtc_time tm;
-		getnstimeofday(&ts);
-		rtc_time_to_tm(ts.tv_sec, &tm);
+		rtc_time_to_tm(ts_exit.tv_sec, &tm);
 		pr_info("suspend: exit suspend, ret = %d "
 			"(%d-%02d-%02d %02d:%02d:%02d.%09lu UTC)\n", ret,
 			tm.tm_year + 1900, tm.tm_mon + 1, tm.tm_mday,
-			tm.tm_hour, tm.tm_min, tm.tm_sec, ts.tv_nsec);
+			tm.tm_hour, tm.tm_min, tm.tm_sec, ts_exit.tv_nsec);
 	}
+
+	if (ts_exit.tv_sec - ts_entry.tv_sec <= 1) {
+		++suspend_short_count;
+
+		if (suspend_short_count == SUSPEND_BACKOFF_THRESHOLD) {
+			suspend_backoff();
+			suspend_short_count = 0;
+		}
+	} else {
+		suspend_short_count = 0;
+	}
+
 	if (current_event_num == entry_event_num) {
 		if (debug_mask & DEBUG_SUSPEND)
 			pr_info("suspend: pm_suspend returned with no event\n");
@@ -383,11 +412,21 @@
 #endif
 	if (debug_mask & DEBUG_SUSPEND)
 		pr_info("power_suspend_late return %d\n", ret);
+
+	if (ret == 0)
+		msm_suspend_check_done = 1;
 	return ret;
 }
 
+static int power_resume_early(struct device *dev)
+{
+	msm_suspend_check_done = 0;
+	return 0;
+}
+
 static struct dev_pm_ops power_driver_pm_ops = {
 	.suspend_noirq = power_suspend_late,
+	.resume_noirq = power_resume_early,
 };
 
 static struct platform_driver power_driver = {
@@ -530,12 +569,24 @@
 
 void wake_lock(struct wake_lock *lock)
 {
+	/*
+	 * if wake lock is being called too late in the suspend sequence,
+	 * call bug so we get to analyze the callstack
+	 */
+	BUG_ON(msm_suspend_check_done);
+
 	wake_lock_internal(lock, 0, 0);
 }
 EXPORT_SYMBOL(wake_lock);
 
 void wake_lock_timeout(struct wake_lock *lock, long timeout)
 {
+	/*
+	 * if wake lock is being called too late in the suspend sequence,
+	 * call bug so we get to analyze the callstack
+	 */
+	BUG_ON(msm_suspend_check_done);
+
 	wake_lock_internal(lock, timeout, 1);
 }
 EXPORT_SYMBOL(wake_lock_timeout);
@@ -615,6 +666,8 @@
 	wake_lock_init(&main_wake_lock, WAKE_LOCK_SUSPEND, "main");
 	wake_lock(&main_wake_lock);
 	wake_lock_init(&unknown_wakeup, WAKE_LOCK_SUSPEND, "unknown_wakeups");
+	wake_lock_init(&suspend_backoff_lock, WAKE_LOCK_SUSPEND,
+		       "suspend_backoff");
 
 	ret = platform_device_register(&power_device);
 	if (ret) {
@@ -627,6 +680,14 @@
 		goto err_platform_driver_register;
 	}
 
+	INIT_COMPLETION(suspend_sys_sync_comp);
+	suspend_sys_sync_work_queue =
+		create_singlethread_workqueue("suspend_sys_sync");
+	if (suspend_sys_sync_work_queue == NULL) {
+		ret = -ENOMEM;
+		goto err_suspend_sys_sync_work_queue;
+	}
+
 	suspend_work_queue = create_singlethread_workqueue("suspend");
 	if (suspend_work_queue == NULL) {
 		ret = -ENOMEM;
@@ -640,10 +701,12 @@
 	return 0;
 
 err_suspend_work_queue:
+err_suspend_sys_sync_work_queue:
 	platform_driver_unregister(&power_driver);
 err_platform_driver_register:
 	platform_device_unregister(&power_device);
 err_platform_device_register:
+	wake_lock_destroy(&suspend_backoff_lock);
 	wake_lock_destroy(&unknown_wakeup);
 	wake_lock_destroy(&main_wake_lock);
 #ifdef CONFIG_WAKELOCK_STAT
@@ -658,8 +721,10 @@
 	remove_proc_entry("wakelocks", NULL);
 #endif
 	destroy_workqueue(suspend_work_queue);
+	destroy_workqueue(suspend_sys_sync_work_queue);
 	platform_driver_unregister(&power_driver);
 	platform_device_unregister(&power_device);
+	wake_lock_destroy(&suspend_backoff_lock);
 	wake_lock_destroy(&unknown_wakeup);
 	wake_lock_destroy(&main_wake_lock);
 #ifdef CONFIG_WAKELOCK_STAT
diff --git a/kernel/printk.c b/kernel/printk.c
index bddd32b..b790764 100644
--- a/kernel/printk.c
+++ b/kernel/printk.c
@@ -1653,7 +1653,7 @@
 	struct console *con;
 
 	for_each_console(con) {
-		if (con->flags & CON_BOOT) {
+		if (!keep_bootcon && con->flags & CON_BOOT) {
 			printk(KERN_INFO "turn off boot console %s%d\n",
 				con->name, con->index);
 			unregister_console(con);
diff --git a/kernel/sched.c b/kernel/sched.c
index 8388f03..232c1c0 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -3714,30 +3714,6 @@
 }
 
 /*
- * Return sum_exec_runtime for the thread group.
- * In case the task is currently running, return the sum plus current's
- * pending runtime that have not been accounted yet.
- *
- * Note that the thread group might have other running tasks as well,
- * so the return value not includes other pending runtime that other
- * running tasks might have.
- */
-unsigned long long thread_group_sched_runtime(struct task_struct *p)
-{
-	struct task_cputime totals;
-	unsigned long flags;
-	struct rq *rq;
-	u64 ns;
-
-	rq = task_rq_lock(p, &flags);
-	thread_group_cputime(p, &totals);
-	ns = totals.sum_exec_runtime + do_task_delta_exec(p, rq);
-	task_rq_unlock(rq, p, &flags);
-
-	return ns;
-}
-
-/*
  * Account user cpu time to a process.
  * @p: the process that the cpu time gets accounted to
  * @cputime: the cpu time spent in user space since the last update
@@ -4243,9 +4219,9 @@
 }
 
 /*
- * schedule() is the main scheduler function.
+ * __schedule() is the main scheduler function.
  */
-asmlinkage void __sched schedule(void)
+static void __sched __schedule(void)
 {
 	struct task_struct *prev, *next;
 	unsigned long *switch_count;
@@ -4286,16 +4262,6 @@
 				if (to_wakeup)
 					try_to_wake_up_local(to_wakeup);
 			}
-
-			/*
-			 * If we are going to sleep and we have plugged IO
-			 * queued, make sure to submit it to avoid deadlocks.
-			 */
-			if (blk_needs_flush_plug(prev)) {
-				raw_spin_unlock(&rq->lock);
-				blk_schedule_flush_plug(prev);
-				raw_spin_lock(&rq->lock);
-			}
 		}
 		switch_count = &prev->nvcsw;
 	}
@@ -4333,6 +4299,26 @@
 	if (need_resched())
 		goto need_resched;
 }
+
+static inline void sched_submit_work(struct task_struct *tsk)
+{
+	if (!tsk->state)
+		return;
+	/*
+	 * If we are going to sleep and we have plugged IO queued,
+	 * make sure to submit it to avoid deadlocks.
+	 */
+	if (blk_needs_flush_plug(tsk))
+		blk_schedule_flush_plug(tsk);
+}
+
+asmlinkage void __sched schedule(void)
+{
+	struct task_struct *tsk = current;
+
+	sched_submit_work(tsk);
+	__schedule();
+}
 EXPORT_SYMBOL(schedule);
 
 #ifdef CONFIG_MUTEX_SPIN_ON_OWNER
@@ -4406,7 +4392,7 @@
 
 	do {
 		add_preempt_count_notrace(PREEMPT_ACTIVE);
-		schedule();
+		__schedule();
 		sub_preempt_count_notrace(PREEMPT_ACTIVE);
 
 		/*
@@ -4434,7 +4420,7 @@
 	do {
 		add_preempt_count(PREEMPT_ACTIVE);
 		local_irq_enable();
-		schedule();
+		__schedule();
 		local_irq_disable();
 		sub_preempt_count(PREEMPT_ACTIVE);
 
@@ -5576,7 +5562,7 @@
 static void __cond_resched(void)
 {
 	add_preempt_count(PREEMPT_ACTIVE);
-	schedule();
+	__schedule();
 	sub_preempt_count(PREEMPT_ACTIVE);
 }
 
@@ -7432,6 +7418,7 @@
 			struct sched_domain *sd = *per_cpu_ptr(sdd->sd, j);
 			if (sd && (sd->flags & SD_OVERLAP))
 				free_sched_groups(sd->groups, 0);
+			kfree(*per_cpu_ptr(sdd->sd, j));
 			kfree(*per_cpu_ptr(sdd->sg, j));
 			kfree(*per_cpu_ptr(sdd->sgp, j));
 		}
diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c
index 10d0182..17f2319 100644
--- a/kernel/sched_rt.c
+++ b/kernel/sched_rt.c
@@ -1038,7 +1038,7 @@
 	 */
 	if (curr && unlikely(rt_task(curr)) &&
 	    (curr->rt.nr_cpus_allowed < 2 ||
-	     curr->prio < p->prio) &&
+	     curr->prio <= p->prio) &&
 	    (p->rt.nr_cpus_allowed > 1)) {
 		int target = find_lowest_rq(p);
 
@@ -1569,7 +1569,7 @@
 	    p->rt.nr_cpus_allowed > 1 &&
 	    rt_task(rq->curr) &&
 	    (rq->curr->rt.nr_cpus_allowed < 2 ||
-	     rq->curr->prio < p->prio))
+	     rq->curr->prio <= p->prio))
 		push_rt_tasks(rq);
 }
 
diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c
index e3516b2..0cae1cc 100644
--- a/kernel/stop_machine.c
+++ b/kernel/stop_machine.c
@@ -132,8 +132,8 @@
 	cpu_stop_queue_work(&per_cpu(cpu_stopper, cpu), work_buf);
 }
 
+DEFINE_MUTEX(stop_cpus_mutex);
 /* static data for stop_cpus */
-static DEFINE_MUTEX(stop_cpus_mutex);
 static DEFINE_PER_CPU(struct cpu_stop_work, stop_cpus_work);
 
 int __stop_cpus(const struct cpumask *cpumask, cpu_stop_fn_t fn, void *arg)
diff --git a/kernel/sys.c b/kernel/sys.c
index e4128b2..f88dadc 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -38,6 +38,8 @@
 #include <linux/fs_struct.h>
 #include <linux/gfp.h>
 #include <linux/syscore_ops.h>
+#include <linux/version.h>
+#include <linux/ctype.h>
 
 #include <linux/compat.h>
 #include <linux/syscalls.h>
@@ -45,6 +47,8 @@
 #include <linux/user_namespace.h>
 
 #include <linux/kmsg_dump.h>
+/* Move somewhere else to avoid recompiling? */
+#include <generated/utsrelease.h>
 
 #include <asm/uaccess.h>
 #include <asm/io.h>
@@ -1124,6 +1128,34 @@
 #define override_architecture(name)	0
 #endif
 
+/*
+ * Work around broken programs that cannot handle "Linux 3.0".
+ * Instead we map 3.x to 2.6.40+x, so e.g. 3.0 would be 2.6.40
+ */
+static int override_release(char __user *release, int len)
+{
+	int ret = 0;
+	char buf[65];
+
+	if (current->personality & UNAME26) {
+		char *rest = UTS_RELEASE;
+		int ndots = 0;
+		unsigned v;
+
+		while (*rest) {
+			if (*rest == '.' && ++ndots >= 3)
+				break;
+			if (!isdigit(*rest) && *rest != '.')
+				break;
+			rest++;
+		}
+		v = ((LINUX_VERSION_CODE >> 8) & 0xff) + 40;
+		snprintf(buf, len, "2.6.%u%s", v, rest);
+		ret = copy_to_user(release, buf, len);
+	}
+	return ret;
+}
+
 SYSCALL_DEFINE1(newuname, struct new_utsname __user *, name)
 {
 	int errno = 0;
@@ -1133,6 +1165,8 @@
 		errno = -EFAULT;
 	up_read(&uts_sem);
 
+	if (!errno && override_release(name->release, sizeof(name->release)))
+		errno = -EFAULT;
 	if (!errno && override_architecture(name))
 		errno = -EFAULT;
 	return errno;
@@ -1154,6 +1188,8 @@
 		error = -EFAULT;
 	up_read(&uts_sem);
 
+	if (!error && override_release(name->release, sizeof(name->release)))
+		error = -EFAULT;
 	if (!error && override_architecture(name))
 		error = -EFAULT;
 	return error;
@@ -1188,6 +1224,8 @@
 
 	if (!error && override_architecture(name))
 		error = -EFAULT;
+	if (!error && override_release(name->release, sizeof(name->release)))
+		error = -EFAULT;
 	return error ? -EFAULT : 0;
 }
 #endif
diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c
index 59f369f..ea5e1a9 100644
--- a/kernel/time/alarmtimer.c
+++ b/kernel/time/alarmtimer.c
@@ -441,6 +441,8 @@
 static void alarm_timer_get(struct k_itimer *timr,
 				struct itimerspec *cur_setting)
 {
+	memset(cur_setting, 0, sizeof(struct itimerspec));
+
 	cur_setting->it_interval =
 			ktime_to_timespec(timr->it.alarmtimer.period);
 	cur_setting->it_value =
@@ -479,11 +481,17 @@
 	if (!rtcdev)
 		return -ENOTSUPP;
 
-	/* Save old values */
-	old_setting->it_interval =
-			ktime_to_timespec(timr->it.alarmtimer.period);
-	old_setting->it_value =
-			ktime_to_timespec(timr->it.alarmtimer.node.expires);
+	/*
+	 * XXX HACK! Currently we can DOS a system if the interval
+	 * period on alarmtimers is too small. Cap the interval here
+	 * to 100us and solve this properly in a future patch! -jstultz
+	 */
+	if ((new_setting->it_interval.tv_sec == 0) &&
+			(new_setting->it_interval.tv_nsec < 100000))
+		new_setting->it_interval.tv_nsec = 100000;
+
+	if (old_setting)
+		alarm_timer_get(timr, old_setting);
 
 	/* If the timer was already set, cancel it */
 	alarm_cancel(&timr->it.alarmtimer);
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 908038f..ef9271b 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -1744,10 +1744,36 @@
 static unsigned long	ftrace_update_cnt;
 unsigned long		ftrace_update_tot_cnt;
 
+static int ops_traces_mod(struct ftrace_ops *ops)
+{
+	struct ftrace_hash *hash;
+
+	hash = ops->filter_hash;
+	return !!(!hash || !hash->count);
+}
+
 static int ftrace_update_code(struct module *mod)
 {
 	struct dyn_ftrace *p;
 	cycle_t start, stop;
+	unsigned long ref = 0;
+
+	/*
+	 * When adding a module, we need to check if tracers are
+	 * currently enabled and if they are set to trace all functions.
+	 * If they are, we need to enable the module functions as well
+	 * as update the reference counts for those function records.
+	 */
+	if (mod) {
+		struct ftrace_ops *ops;
+
+		for (ops = ftrace_ops_list;
+		     ops != &ftrace_list_end; ops = ops->next) {
+			if (ops->flags & FTRACE_OPS_FL_ENABLED &&
+			    ops_traces_mod(ops))
+				ref++;
+		}
+	}
 
 	start = ftrace_now(raw_smp_processor_id());
 	ftrace_update_cnt = 0;
@@ -1760,7 +1786,7 @@
 
 		p = ftrace_new_addrs;
 		ftrace_new_addrs = p->newlist;
-		p->flags = 0L;
+		p->flags = ref;
 
 		/*
 		 * Do the initial record conversion from mcount jump
@@ -1783,7 +1809,7 @@
 		 * conversion puts the module to the correct state, thus
 		 * passing the ftrace_make_call check.
 		 */
-		if (ftrace_start_up) {
+		if (ftrace_start_up && ref) {
 			int failed = __ftrace_replace_code(p, 1);
 			if (failed) {
 				ftrace_bug(failed, p->ip);
@@ -2407,10 +2433,9 @@
  */
 
 static int
-ftrace_mod_callback(char *func, char *cmd, char *param, int enable)
+ftrace_mod_callback(struct ftrace_hash *hash,
+		    char *func, char *cmd, char *param, int enable)
 {
-	struct ftrace_ops *ops = &global_ops;
-	struct ftrace_hash *hash;
 	char *mod;
 	int ret = -EINVAL;
 
@@ -2430,11 +2455,6 @@
 	if (!strlen(mod))
 		return ret;
 
-	if (enable)
-		hash = ops->filter_hash;
-	else
-		hash = ops->notrace_hash;
-
 	ret = ftrace_match_module_records(hash, func, mod);
 	if (!ret)
 		ret = -EINVAL;
@@ -2760,7 +2780,7 @@
 	mutex_lock(&ftrace_cmd_mutex);
 	list_for_each_entry(p, &ftrace_commands, list) {
 		if (strcmp(p->name, command) == 0) {
-			ret = p->func(func, command, next, enable);
+			ret = p->func(hash, func, command, next, enable);
 			goto out_unlock;
 		}
 	}
diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c
index 8d0e1cc..c7b0c6a 100644
--- a/kernel/trace/trace_functions.c
+++ b/kernel/trace/trace_functions.c
@@ -324,7 +324,8 @@
 }
 
 static int
-ftrace_trace_onoff_callback(char *glob, char *cmd, char *param, int enable)
+ftrace_trace_onoff_callback(struct ftrace_hash *hash,
+			    char *glob, char *cmd, char *param, int enable)
 {
 	struct ftrace_probe_ops *ops;
 	void *count = (void *)-1;
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 0400553..aec02b6 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -3026,8 +3026,13 @@
 
 	for_each_cwq_cpu(cpu, wq) {
 		struct cpu_workqueue_struct *cwq = get_cwq(cpu, wq);
+		bool drained;
 
-		if (!cwq->nr_active && list_empty(&cwq->delayed_works))
+		spin_lock_irq(&cwq->gcwq->lock);
+		drained = !cwq->nr_active && list_empty(&cwq->delayed_works);
+		spin_unlock_irq(&cwq->gcwq->lock);
+
+		if (drained)
 			continue;
 
 		if (++flush_cnt == 10 ||