Merge branch 'linux-2.6'

12 files changed, 351 insertions, 227 deletions

diff --git a/kernel/acct.c b/kernel/acct.c
index 521dfa53cb99..91e1cfd734d2 100644
--- a/kernel/acct.c
+++ b/kernel/acct.c
@@ -58,6 +58,7 @@
 #include <asm/uaccess.h>
 #include <asm/div64.h>
 #include <linux/blkdev.h> /* sector_div */
+#include <linux/pid_namespace.h>
 
 /*
  * These constants control the amount of freespace that suspend and
@@ -74,7 +75,7 @@ int acct_parm[3] = {4, 2, 30};
 /*
  * External references and all of the globals.
  */
-static void do_acct_process(struct file *);
+static void do_acct_process(struct pid_namespace *ns, struct file *);
 
 /*
  * This structure is used so that all the data protected by lock
@@ -86,6 +87,7 @@ struct acct_glbs {
 	volatile int		active;
 	volatile int		needcheck;
 	struct file		*file;
+	struct pid_namespace	*ns;
 	struct timer_list	timer;
 };
 
@@ -175,9 +177,11 @@ out:
 static void acct_file_reopen(struct file *file)
 {
 	struct file *old_acct = NULL;
+	struct pid_namespace *old_ns = NULL;
 
 	if (acct_globals.file) {
 		old_acct = acct_globals.file;
+		old_ns = acct_globals.ns;
 		del_timer(&acct_globals.timer);
 		acct_globals.active = 0;
 		acct_globals.needcheck = 0;
@@ -185,6 +189,7 @@ static void acct_file_reopen(struct file *file)
 	}
 	if (file) {
 		acct_globals.file = file;
+		acct_globals.ns = get_pid_ns(task_active_pid_ns(current));
 		acct_globals.needcheck = 0;
 		acct_globals.active = 1;
 		/* It's been deleted if it was used before so this is safe */
@@ -196,8 +201,9 @@ static void acct_file_reopen(struct file *file)
 	if (old_acct) {
 		mnt_unpin(old_acct->f_path.mnt);
 		spin_unlock(&acct_globals.lock);
-		do_acct_process(old_acct);
+		do_acct_process(old_ns, old_acct);
 		filp_close(old_acct, NULL);
+		put_pid_ns(old_ns);
 		spin_lock(&acct_globals.lock);
 	}
 }
@@ -419,7 +425,7 @@ static u32 encode_float(u64 value)
 /*
  *  do_acct_process does all actual work. Caller holds the reference to file.
  */
-static void do_acct_process(struct file *file)
+static void do_acct_process(struct pid_namespace *ns, struct file *file)
 {
 	struct pacct_struct *pacct = &current->signal->pacct;
 	acct_t ac;
@@ -481,8 +487,10 @@ static void do_acct_process(struct file *file)
 	ac.ac_gid16 = current->gid;
 #endif
 #if ACCT_VERSION==3
-	ac.ac_pid = current->tgid;
-	ac.ac_ppid = current->real_parent->tgid;
+	ac.ac_pid = task_tgid_nr_ns(current, ns);
+	rcu_read_lock();
+	ac.ac_ppid = task_tgid_nr_ns(rcu_dereference(current->real_parent), ns);
+	rcu_read_unlock();
 #endif
 
 	spin_lock_irq(&current->sighand->siglock);
@@ -578,6 +586,7 @@ void acct_collect(long exitcode, int group_dead)
 void acct_process(void)
 {
 	struct file *file = NULL;
+	struct pid_namespace *ns;
 
 	/*
 	 * accelerate the common fastpath:
@@ -592,8 +601,10 @@ void acct_process(void)
 		return;
 	}
 	get_file(file);
+	ns = get_pid_ns(acct_globals.ns);
 	spin_unlock(&acct_globals.lock);
 
-	do_acct_process(file);
+	do_acct_process(ns, file);
 	fput(file);
+	put_pid_ns(ns);
 }
diff --git a/kernel/audit.c b/kernel/audit.c
index 10c4930c2bbf..be55cb503633 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -78,9 +78,13 @@ static int	audit_default;
 /* If auditing cannot proceed, audit_failure selects what happens. */
 static int	audit_failure = AUDIT_FAIL_PRINTK;
 
-/* If audit records are to be written to the netlink socket, audit_pid
- * contains the (non-zero) pid. */
+/*
+ * If audit records are to be written to the netlink socket, audit_pid
+ * contains the pid of the auditd process and audit_nlk_pid contains
+ * the pid to use to send netlink messages to that process.
+ */
 int		audit_pid;
+static int	audit_nlk_pid;
 
 /* If audit_rate_limit is non-zero, limit the rate of sending audit records
  * to that number per second.  This prevents DoS attacks, but results in
@@ -350,7 +354,7 @@ static int kauditd_thread(void *dummy)
 		wake_up(&audit_backlog_wait);
 		if (skb) {
 			if (audit_pid) {
-				int err = netlink_unicast(audit_sock, skb, audit_pid, 0);
+				int err = netlink_unicast(audit_sock, skb, audit_nlk_pid, 0);
 				if (err < 0) {
 					BUG_ON(err != -ECONNREFUSED); /* Shoudn't happen */
 					printk(KERN_ERR "audit: *NO* daemon at audit_pid=%d\n", audit_pid);
@@ -626,6 +630,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 							sid, 1);
 
 			audit_pid = new_pid;
+			audit_nlk_pid = NETLINK_CB(skb).pid;
 		}
 		if (status_get->mask & AUDIT_STATUS_RATE_LIMIT)
 			err = audit_set_rate_limit(status_get->rate_limit,
diff --git a/kernel/marker.c b/kernel/marker.c
index 48a4ea5afffd..041c33e3e95c 100644
--- a/kernel/marker.c
+++ b/kernel/marker.c
@@ -104,18 +104,18 @@ void marker_probe_cb(const struct marker *mdata, void *call_private,
 	char ptype;
 
 	/*
-	 * disabling preemption to make sure the teardown of the callbacks can
-	 * be done correctly when they are in modules and they insure RCU read
-	 * coherency.
+	 * preempt_disable does two things : disabling preemption to make sure
+	 * the teardown of the callbacks can be done correctly when they are in
+	 * modules and they insure RCU read coherency.
 	 */
 	preempt_disable();
-	ptype = ACCESS_ONCE(mdata->ptype);
+	ptype = mdata->ptype;
 	if (likely(!ptype)) {
 		marker_probe_func *func;
 		/* Must read the ptype before ptr. They are not data dependant,
 		 * so we put an explicit smp_rmb() here. */
 		smp_rmb();
-		func = ACCESS_ONCE(mdata->single.func);
+		func = mdata->single.func;
 		/* Must read the ptr before private data. They are not data
 		 * dependant, so we put an explicit smp_rmb() here. */
 		smp_rmb();
@@ -133,7 +133,7 @@ void marker_probe_cb(const struct marker *mdata, void *call_private,
 		 * in the fast path, so put the explicit barrier here.
 		 */
 		smp_read_barrier_depends();
-		multi = ACCESS_ONCE(mdata->multi);
+		multi = mdata->multi;
 		for (i = 0; multi[i].func; i++) {
 			va_start(args, fmt);
 			multi[i].func(multi[i].probe_private, call_private, fmt,
@@ -161,13 +161,13 @@ void marker_probe_cb_noarg(const struct marker *mdata,
 	char ptype;
 
 	preempt_disable();
-	ptype = ACCESS_ONCE(mdata->ptype);
+	ptype = mdata->ptype;
 	if (likely(!ptype)) {
 		marker_probe_func *func;
 		/* Must read the ptype before ptr. They are not data dependant,
 		 * so we put an explicit smp_rmb() here. */
 		smp_rmb();
-		func = ACCESS_ONCE(mdata->single.func);
+		func = mdata->single.func;
 		/* Must read the ptr before private data. They are not data
 		 * dependant, so we put an explicit smp_rmb() here. */
 		smp_rmb();
@@ -183,7 +183,7 @@ void marker_probe_cb_noarg(const struct marker *mdata,
 		 * in the fast path, so put the explicit barrier here.
 		 */
 		smp_read_barrier_depends();
-		multi = ACCESS_ONCE(mdata->multi);
+		multi = mdata->multi;
 		for (i = 0; multi[i].func; i++)
 			multi[i].func(multi[i].probe_private, call_private, fmt,
 				&args);
@@ -551,9 +551,9 @@ static int set_marker(struct marker_entry **entry, struct marker *elem,
 
 /*
  * Disable a marker and its probe callback.
- * Note: only after a synchronize_sched() issued after setting elem->call to the
- * empty function insures that the original callback is not used anymore. This
- * insured by preemption disabling around the call site.
+ * Note: only waiting an RCU period after setting elem->call to the empty
+ * function insures that the original callback is not used anymore. This insured
+ * by preempt_disable around the call site.
  */
 static void disable_marker(struct marker *elem)
 {
@@ -565,8 +565,8 @@ static void disable_marker(struct marker *elem)
 	elem->ptype = 0;	/* single probe */
 	/*
 	 * Leave the private data and id there, because removal is racy and
-	 * should be done only after a synchronize_sched(). These are never used
-	 * until the next initialization anyway.
+	 * should be done only after an RCU period. These are never used until
+	 * the next initialization anyway.
 	 */
 }
 
@@ -601,9 +601,6 @@ void marker_update_probe_range(struct marker *begin,
 
 /*
  * Update probes, removing the faulty probes.
- * Issues a synchronize_sched() when no reference to the module passed
- * as parameter is found in the probes so the probe module can be
- * safely unloaded from now on.
  *
  * Internal callback only changed before the first probe is connected to it.
  * Single probe private data can only be changed on 0 -> 1 and 2 -> 1
diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig
index 79833170bb9c..6233f3b4ae66 100644
--- a/kernel/power/Kconfig
+++ b/kernel/power/Kconfig
@@ -190,7 +190,7 @@ config APM_EMULATION
 	  notification of APM "events" (e.g. battery status change).
 
 	  In order to use APM, you will need supporting software. For location
-	  and more information, read <file:Documentation/pm.txt> and the
+	  and more information, read <file:Documentation/power/pm.txt> and the
 	  Battery Powered Linux mini-HOWTO, available from
 	  <http://www.tldp.org/docs.html#howto>.
 
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index 72a020cabb4c..5f91a07c4eac 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -447,7 +447,7 @@ static void memory_bm_free(struct memory_bitmap *bm, int clear_nosave_free)
  *	of @bm->cur_zone_bm are updated.
  */
 
-static void memory_bm_find_bit(struct memory_bitmap *bm, unsigned long pfn,
+static int memory_bm_find_bit(struct memory_bitmap *bm, unsigned long pfn,
 				void **addr, unsigned int *bit_nr)
 {
 	struct zone_bitmap *zone_bm;
@@ -461,7 +461,8 @@ static void memory_bm_find_bit(struct memory_bitmap *bm, unsigned long pfn,
 		while (pfn < zone_bm->start_pfn || pfn >= zone_bm->end_pfn) {
 			zone_bm = zone_bm->next;
 
-			BUG_ON(!zone_bm);
+			if (!zone_bm)
+				return -EFAULT;
 		}
 		bm->cur.zone_bm = zone_bm;
 	}
@@ -479,23 +480,40 @@ static void memory_bm_find_bit(struct memory_bitmap *bm, unsigned long pfn,
 	pfn -= bb->start_pfn;
 	*bit_nr = pfn % BM_BITS_PER_CHUNK;
 	*addr = bb->data + pfn / BM_BITS_PER_CHUNK;
+	return 0;
 }
 
 static void memory_bm_set_bit(struct memory_bitmap *bm, unsigned long pfn)
 {
 	void *addr;
 	unsigned int bit;
+	int error;
 
-	memory_bm_find_bit(bm, pfn, &addr, &bit);
+	error = memory_bm_find_bit(bm, pfn, &addr, &bit);
+	BUG_ON(error);
 	set_bit(bit, addr);
 }
 
+static int mem_bm_set_bit_check(struct memory_bitmap *bm, unsigned long pfn)
+{
+	void *addr;
+	unsigned int bit;
+	int error;
+
+	error = memory_bm_find_bit(bm, pfn, &addr, &bit);
+	if (!error)
+		set_bit(bit, addr);
+	return error;
+}
+
 static void memory_bm_clear_bit(struct memory_bitmap *bm, unsigned long pfn)
 {
 	void *addr;
 	unsigned int bit;
+	int error;
 
-	memory_bm_find_bit(bm, pfn, &addr, &bit);
+	error = memory_bm_find_bit(bm, pfn, &addr, &bit);
+	BUG_ON(error);
 	clear_bit(bit, addr);
 }
 
@@ -503,8 +521,10 @@ static int memory_bm_test_bit(struct memory_bitmap *bm, unsigned long pfn)
 {
 	void *addr;
 	unsigned int bit;
+	int error;
 
-	memory_bm_find_bit(bm, pfn, &addr, &bit);
+	error = memory_bm_find_bit(bm, pfn, &addr, &bit);
+	BUG_ON(error);
 	return test_bit(bit, addr);
 }
 
@@ -709,8 +729,15 @@ static void mark_nosave_pages(struct memory_bitmap *bm)
 				region->end_pfn << PAGE_SHIFT);
 
 		for (pfn = region->start_pfn; pfn < region->end_pfn; pfn++)
-			if (pfn_valid(pfn))
-				memory_bm_set_bit(bm, pfn);
+			if (pfn_valid(pfn)) {
+				/*
+				 * It is safe to ignore the result of
+				 * mem_bm_set_bit_check() here, since we won't
+				 * touch the PFNs for which the error is
+				 * returned anyway.
+				 */
+				mem_bm_set_bit_check(bm, pfn);
+			}
 	}
 }
 
diff --git a/kernel/printk.c b/kernel/printk.c
index 9adc2a473e6e..c46a20a19a15 100644
--- a/kernel/printk.c
+++ b/kernel/printk.c
@@ -616,6 +616,40 @@ asmlinkage int printk(const char *fmt, ...)
 /* cpu currently holding logbuf_lock */
 static volatile unsigned int printk_cpu = UINT_MAX;
 
+/*
+ * Can we actually use the console at this time on this cpu?
+ *
+ * Console drivers may assume that per-cpu resources have
+ * been allocated. So unless they're explicitly marked as
+ * being able to cope (CON_ANYTIME) don't call them until
+ * this CPU is officially up.
+ */
+static inline int can_use_console(unsigned int cpu)
+{
+	return cpu_online(cpu) || have_callable_console();
+}
+
+/*
+ * Try to get console ownership to actually show the kernel
+ * messages from a 'printk'. Return true (and with the
+ * console_semaphore held, and 'console_locked' set) if it
+ * is successful, false otherwise.
+ *
+ * This gets called with the 'logbuf_lock' spinlock held and
+ * interrupts disabled. It should return with 'lockbuf_lock'
+ * released but interrupts still disabled.
+ */
+static int acquire_console_semaphore_for_printk(unsigned int cpu)
+{
+	int retval = 0;
+
+	if (can_use_console(cpu))
+		retval = !try_acquire_console_sem();
+	printk_cpu = UINT_MAX;
+	spin_unlock(&logbuf_lock);
+	return retval;
+}
+
 const char printk_recursion_bug_msg [] =
 			KERN_CRIT "BUG: recent printk recursion!\n";
 static int printk_recursion_bug;
@@ -725,43 +759,22 @@ asmlinkage int vprintk(const char *fmt, va_list args)
 			log_level_unknown = 1;
 	}
 
-	if (!down_trylock(&console_sem)) {
-		/*
-		 * We own the drivers.  We can drop the spinlock and
-		 * let release_console_sem() print the text, maybe ...
-		 */
-		console_locked = 1;
-		printk_cpu = UINT_MAX;
-		spin_unlock(&logbuf_lock);
+	/*
+	 * Try to acquire and then immediately release the
+	 * console semaphore. The release will do all the
+	 * actual magic (print out buffers, wake up klogd,
+	 * etc). 
+	 *
+	 * The acquire_console_semaphore_for_printk() function
+	 * will release 'logbuf_lock' regardless of whether it
+	 * actually gets the semaphore or not.
+	 */
+	if (acquire_console_semaphore_for_printk(this_cpu))
+		release_console_sem();
 
-		/*
-		 * Console drivers may assume that per-cpu resources have
-		 * been allocated. So unless they're explicitly marked as
-		 * being able to cope (CON_ANYTIME) don't call them until
-		 * this CPU is officially up.
-		 */
-		if (cpu_online(smp_processor_id()) || have_callable_console()) {
-			console_may_schedule = 0;
-			release_console_sem();
-		} else {
-			/* Release by hand to avoid flushing the buffer. */
-			console_locked = 0;
-			up(&console_sem);
-		}
-		lockdep_on();
-		raw_local_irq_restore(flags);
-	} else {
-		/*
-		 * Someone else owns the drivers.  We drop the spinlock, which
-		 * allows the semaphore holder to proceed and to call the
-		 * console drivers with the output which we just produced.
-		 */
-		printk_cpu = UINT_MAX;
-		spin_unlock(&logbuf_lock);
-		lockdep_on();
+	lockdep_on();
 out_restore_irqs:
-		raw_local_irq_restore(flags);
-	}
+	raw_local_irq_restore(flags);
 
 	preempt_enable();
 	return printed_len;
diff --git a/kernel/relay.c b/kernel/relay.c
index d080b9d161a7..4c035a8a248c 100644
--- a/kernel/relay.c
+++ b/kernel/relay.c
@@ -1066,7 +1066,7 @@ static int subbuf_splice_actor(struct file *in,
 			       unsigned int flags,
 			       int *nonpad_ret)
 {
-	unsigned int pidx, poff, total_len, subbuf_pages, ret;
+	unsigned int pidx, poff, total_len, subbuf_pages, nr_pages, ret;
 	struct rchan_buf *rbuf = in->private_data;
 	unsigned int subbuf_size = rbuf->chan->subbuf_size;
 	uint64_t pos = (uint64_t) *ppos;
@@ -1097,8 +1097,9 @@ static int subbuf_splice_actor(struct file *in,
 	subbuf_pages = rbuf->chan->alloc_size >> PAGE_SHIFT;
 	pidx = (read_start / PAGE_SIZE) % subbuf_pages;
 	poff = read_start & ~PAGE_MASK;
+	nr_pages = min_t(unsigned int, subbuf_pages, PIPE_BUFFERS);
 
-	for (total_len = 0; spd.nr_pages < subbuf_pages; spd.nr_pages++) {
+	for (total_len = 0; spd.nr_pages < nr_pages; spd.nr_pages++) {
 		unsigned int this_len, this_end, private;
 		unsigned int cur_pos = read_start + total_len;
 
diff --git a/kernel/sched.c b/kernel/sched.c
index 1cb53fb1fe3d..28c73f07efb2 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -301,7 +301,7 @@ struct cfs_rq {
 	/* 'curr' points to currently running entity on this cfs_rq.
 	 * It is set to NULL otherwise (i.e when none are currently running).
 	 */
-	struct sched_entity *curr;
+	struct sched_entity *curr, *next;
 
 	unsigned long nr_spread_over;
 
@@ -594,18 +594,14 @@ enum {
 	SCHED_FEAT_NEW_FAIR_SLEEPERS	= 1,
 	SCHED_FEAT_WAKEUP_PREEMPT	= 2,
 	SCHED_FEAT_START_DEBIT		= 4,
-	SCHED_FEAT_TREE_AVG		= 8,
-	SCHED_FEAT_APPROX_AVG		= 16,
-	SCHED_FEAT_HRTICK		= 32,
-	SCHED_FEAT_DOUBLE_TICK		= 64,
+	SCHED_FEAT_HRTICK		= 8,
+	SCHED_FEAT_DOUBLE_TICK		= 16,
 };
 
 const_debug unsigned int sysctl_sched_features =
 		SCHED_FEAT_NEW_FAIR_SLEEPERS	* 1 |
 		SCHED_FEAT_WAKEUP_PREEMPT	* 1 |
 		SCHED_FEAT_START_DEBIT		* 1 |
-		SCHED_FEAT_TREE_AVG		* 0 |
-		SCHED_FEAT_APPROX_AVG		* 0 |
 		SCHED_FEAT_HRTICK		* 1 |
 		SCHED_FEAT_DOUBLE_TICK		* 0;
 
@@ -1084,7 +1080,7 @@ calc_delta_mine(unsigned long delta_exec, unsigned long weight,
 	u64 tmp;
 
 	if (unlikely(!lw->inv_weight))
-		lw->inv_weight = (WMULT_CONST - lw->weight/2) / lw->weight + 1;
+		lw->inv_weight = (WMULT_CONST-lw->weight/2) / (lw->weight+1);
 
 	tmp = (u64)delta_exec * weight;
 	/*
@@ -1108,11 +1104,13 @@ calc_delta_fair(unsigned long delta_exec, struct load_weight *lw)
 static inline void update_load_add(struct load_weight *lw, unsigned long inc)
 {
 	lw->weight += inc;
+	lw->inv_weight = 0;
 }
 
 static inline void update_load_sub(struct load_weight *lw, unsigned long dec)
 {
 	lw->weight -= dec;
+	lw->inv_weight = 0;
 }
 
 /*
@@ -1394,6 +1392,12 @@ task_hot(struct task_struct *p, u64 now, struct sched_domain *sd)
 {
 	s64 delta;
 
+	/*
+	 * Buddy candidates are cache hot:
+	 */
+	if (&p->se == cfs_rq_of(&p->se)->next)
+		return 1;
+
 	if (p->sched_class != &fair_sched_class)
 		return 0;
 
@@ -1853,10 +1857,11 @@ out_activate:
 		schedstat_inc(p, se.nr_wakeups_remote);
 	update_rq_clock(rq);
 	activate_task(rq, p, 1);
-	check_preempt_curr(rq, p);
 	success = 1;
 
 out_running:
+	check_preempt_curr(rq, p);
+
 	p->state = TASK_RUNNING;
 #ifdef CONFIG_SMP
 	if (p->sched_class->task_wake_up)
@@ -1890,6 +1895,8 @@ static void __sched_fork(struct task_struct *p)
 	p->se.exec_start		= 0;
 	p->se.sum_exec_runtime		= 0;
 	p->se.prev_sum_exec_runtime	= 0;
+	p->se.last_wakeup		= 0;
+	p->se.avg_overlap		= 0;
 
 #ifdef CONFIG_SCHEDSTATS
 	p->se.wait_start		= 0;
@@ -3875,7 +3882,7 @@ need_resched_nonpreemptible:
 
 	if (prev->state && !(preempt_count() & PREEMPT_ACTIVE)) {
 		if (unlikely((prev->state & TASK_INTERRUPTIBLE) &&
-				unlikely(signal_pending(prev)))) {
+				signal_pending(prev))) {
 			prev->state = TASK_RUNNING;
 		} else {
 			deactivate_task(rq, prev, 1);
@@ -4268,11 +4275,10 @@ void rt_mutex_setprio(struct task_struct *p, int prio)
 	oldprio = p->prio;
 	on_rq = p->se.on_rq;
 	running = task_current(rq, p);
-	if (on_rq) {
+	if (on_rq)
 		dequeue_task(rq, p, 0);
-		if (running)
-			p->sched_class->put_prev_task(rq, p);
-	}
+	if (running)
+		p->sched_class->put_prev_task(rq, p);
 
 	if (rt_prio(prio))
 		p->sched_class = &rt_sched_class;
@@ -4281,10 +4287,9 @@ void rt_mutex_setprio(struct task_struct *p, int prio)
 
 	p->prio = prio;
 
+	if (running)
+		p->sched_class->set_curr_task(rq);
 	if (on_rq) {
-		if (running)
-			p->sched_class->set_curr_task(rq);
-
 		enqueue_task(rq, p, 0);
 
 		check_class_changed(rq, p, prev_class, oldprio, running);
@@ -4581,19 +4586,17 @@ recheck:
 	update_rq_clock(rq);
 	on_rq = p->se.on_rq;
 	running = task_current(rq, p);
-	if (on_rq) {
+	if (on_rq)
 		deactivate_task(rq, p, 0);
-		if (running)
-			p->sched_class->put_prev_task(rq, p);
-	}
+	if (running)
+		p->sched_class->put_prev_task(rq, p);
 
 	oldprio = p->prio;
 	__setscheduler(rq, p, policy, param->sched_priority);
 
+	if (running)
+		p->sched_class->set_curr_task(rq);
 	if (on_rq) {
-		if (running)
-			p->sched_class->set_curr_task(rq);
-
 		activate_task(rq, p, 0);
 
 		check_class_changed(rq, p, prev_class, oldprio, running);
@@ -6804,6 +6807,10 @@ static int ndoms_cur;		/* number of sched domains in 'doms_cur' */
  */
 static cpumask_t fallback_doms;
 
+void __attribute__((weak)) arch_update_cpu_topology(void)
+{
+}
+
 /*
  * Set up scheduler domains and groups. Callers must hold the hotplug lock.
  * For now this just excludes isolated cpus, but could be used to
@@ -6813,6 +6820,7 @@ static int arch_init_sched_domains(const cpumask_t *cpu_map)
 {
 	int err;
 
+	arch_update_cpu_topology();
 	ndoms_cur = 1;
 	doms_cur = kmalloc(sizeof(cpumask_t), GFP_KERNEL);
 	if (!doms_cur)
@@ -6917,7 +6925,7 @@ match2:
 }
 
 #if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT)
-static int arch_reinit_sched_domains(void)
+int arch_reinit_sched_domains(void)
 {
 	int err;
 
@@ -7618,11 +7626,10 @@ void sched_move_task(struct task_struct *tsk)
 	running = task_current(rq, tsk);
 	on_rq = tsk->se.on_rq;
 
-	if (on_rq) {
+	if (on_rq)
 		dequeue_task(rq, tsk, 0);
-		if (unlikely(running))
-			tsk->sched_class->put_prev_task(rq, tsk);
-	}
+	if (unlikely(running))
+		tsk->sched_class->put_prev_task(rq, tsk);
 
 	set_task_rq(tsk, task_cpu(tsk));
 
@@ -7631,11 +7638,10 @@ void sched_move_task(struct task_struct *tsk)
 		tsk->sched_class->moved_group(tsk);
 #endif
 
-	if (on_rq) {
-		if (unlikely(running))
-			tsk->sched_class->set_curr_task(rq);
+	if (unlikely(running))
+		tsk->sched_class->set_curr_task(rq);
+	if (on_rq)
 		enqueue_task(rq, tsk, 0);
-	}
 
 	task_rq_unlock(rq, &flags);
 }
diff --git a/kernel/sched_debug.c b/kernel/sched_debug.c
index 4b5e24cf2f4a..ef358ba07683 100644
--- a/kernel/sched_debug.c
+++ b/kernel/sched_debug.c
@@ -288,6 +288,7 @@ void proc_sched_show_task(struct task_struct *p, struct seq_file *m)
 	PN(se.exec_start);
 	PN(se.vruntime);
 	PN(se.sum_exec_runtime);
+	PN(se.avg_overlap);
 
 	nr_switches = p->nvcsw + p->nivcsw;
 
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index e2a530515619..86a93376282c 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -73,13 +73,13 @@ unsigned int sysctl_sched_batch_wakeup_granularity = 10000000UL;
 
 /*
  * SCHED_OTHER wake-up granularity.
- * (default: 10 msec * (1 + ilog(ncpus)), units: nanoseconds)
+ * (default: 5 msec * (1 + ilog(ncpus)), units: nanoseconds)
  *
  * This option delays the preemption effects of decoupled workloads
  * and reduces their over-scheduling. Synchronous workloads will still
  * have immediate wakeup/sleep latencies.
  */
-unsigned int sysctl_sched_wakeup_granularity = 10000000UL;
+unsigned int sysctl_sched_wakeup_granularity = 5000000UL;
 
 const_debug unsigned int sysctl_sched_migration_cost = 500000UL;
 
@@ -175,8 +175,15 @@ static void __enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
 	 * Maintain a cache of leftmost tree entries (it is frequently
 	 * used):
 	 */
-	if (leftmost)
+	if (leftmost) {
 		cfs_rq->rb_leftmost = &se->run_node;
+		/*
+		 * maintain cfs_rq->min_vruntime to be a monotonic increasing
+		 * value tracking the leftmost vruntime in the tree.
+		 */
+		cfs_rq->min_vruntime =
+			max_vruntime(cfs_rq->min_vruntime, se->vruntime);
+	}
 
 	rb_link_node(&se->run_node, parent, link);
 	rb_insert_color(&se->run_node, &cfs_rq->tasks_timeline);
@@ -184,8 +191,24 @@ static void __enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
 
 static void __dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
-	if (cfs_rq->rb_leftmost == &se->run_node)
-		cfs_rq->rb_leftmost = rb_next(&se->run_node);
+	if (cfs_rq->rb_leftmost == &se->run_node) {
+		struct rb_node *next_node;
+		struct sched_entity *next;
+
+		next_node = rb_next(&se->run_node);
+		cfs_rq->rb_leftmost = next_node;
+
+		if (next_node) {
+			next = rb_entry(next_node,
+					struct sched_entity, run_node);
+			cfs_rq->min_vruntime =
+				max_vruntime(cfs_rq->min_vruntime,
+					     next->vruntime);
+		}
+	}
+
+	if (cfs_rq->next == se)
+		cfs_rq->next = NULL;
 
 	rb_erase(&se->run_node, &cfs_rq->tasks_timeline);
 }
@@ -260,12 +283,8 @@ static u64 __sched_period(unsigned long nr_running)
  */
 static u64 sched_slice(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
-	u64 slice = __sched_period(cfs_rq->nr_running);
-
-	slice *= se->load.weight;
-	do_div(slice, cfs_rq->load.weight);
-
-	return slice;
+	return calc_delta_mine(__sched_period(cfs_rq->nr_running),
+			       se->load.weight, &cfs_rq->load);
 }
 
 /*
@@ -283,11 +302,6 @@ static u64 __sched_vslice(unsigned long rq_weight, unsigned long nr_running)
 	return vslice;
 }
 
-static u64 sched_vslice(struct cfs_rq *cfs_rq)
-{
-	return __sched_vslice(cfs_rq->load.weight, cfs_rq->nr_running);
-}
-
 static u64 sched_vslice_add(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
 	return __sched_vslice(cfs_rq->load.weight + se->load.weight,
@@ -303,7 +317,6 @@ __update_curr(struct cfs_rq *cfs_rq, struct sched_entity *curr,
 	      unsigned long delta_exec)
 {
 	unsigned long delta_exec_weighted;
-	u64 vruntime;
 
 	schedstat_set(curr->exec_max, max((u64)delta_exec, curr->exec_max));
 
@@ -315,19 +328,6 @@ __update_curr(struct cfs_rq *cfs_rq, struct sched_entity *curr,
 							&curr->load);
 	}
 	curr->vruntime += delta_exec_weighted;
-
-	/*
-	 * maintain cfs_rq->min_vruntime to be a monotonic increasing
-	 * value tracking the leftmost vruntime in the tree.
-	 */
-	if (first_fair(cfs_rq)) {
-		vruntime = min_vruntime(curr->vruntime,
-				__pick_next_entity(cfs_rq)->vruntime);
-	} else
-		vruntime = curr->vruntime;
-
-	cfs_rq->min_vruntime =
-		max_vruntime(cfs_rq->min_vruntime, vruntime);
 }
 
 static void update_curr(struct cfs_rq *cfs_rq)
@@ -493,16 +493,11 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial)
 {
 	u64 vruntime;
 
-	vruntime = cfs_rq->min_vruntime;
-
-	if (sched_feat(TREE_AVG)) {
-		struct sched_entity *last = __pick_last_entity(cfs_rq);
-		if (last) {
-			vruntime += last->vruntime;
-			vruntime >>= 1;
-		}
-	} else if (sched_feat(APPROX_AVG) && cfs_rq->nr_running)
-		vruntime += sched_vslice(cfs_rq)/2;
+	if (first_fair(cfs_rq)) {
+		vruntime = min_vruntime(cfs_rq->min_vruntime,
+				__pick_next_entity(cfs_rq)->vruntime);
+	} else
+		vruntime = cfs_rq->min_vruntime;
 
 	/*
 	 * The 'current' period is already promised to the current tasks,
@@ -515,8 +510,10 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial)
 
 	if (!initial) {
 		/* sleeps upto a single latency don't count. */
-		if (sched_feat(NEW_FAIR_SLEEPERS))
-			vruntime -= sysctl_sched_latency;
+		if (sched_feat(NEW_FAIR_SLEEPERS)) {
+			vruntime -= calc_delta_fair(sysctl_sched_latency,
+						    &cfs_rq->load);
+		}
 
 		/* ensure we never gain time by being placed backwards. */
 		vruntime = max_vruntime(se->vruntime, vruntime);
@@ -545,6 +542,21 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int wakeup)
 	account_entity_enqueue(cfs_rq, se);
 }
 
+static void update_avg(u64 *avg, u64 sample)
+{
+	s64 diff = sample - *avg;
+	*avg += diff >> 3;
+}
+
+static void update_avg_stats(struct cfs_rq *cfs_rq, struct sched_entity *se)
+{
+	if (!se->last_wakeup)
+		return;
+
+	update_avg(&se->avg_overlap, se->sum_exec_runtime - se->last_wakeup);
+	se->last_wakeup = 0;
+}
+
 static void
 dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int sleep)
 {
@@ -555,6 +567,7 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int sleep)
 
 	update_stats_dequeue(cfs_rq, se);
 	if (sleep) {
+		update_avg_stats(cfs_rq, se);
 #ifdef CONFIG_SCHEDSTATS
 		if (entity_is_task(se)) {
 			struct task_struct *tsk = task_of(se);
@@ -616,12 +629,32 @@ set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
 	se->prev_sum_exec_runtime = se->sum_exec_runtime;
 }
 
+static struct sched_entity *
+pick_next(struct cfs_rq *cfs_rq, struct sched_entity *se)
+{
+	s64 diff, gran;
+
+	if (!cfs_rq->next)
+		return se;
+
+	diff = cfs_rq->next->vruntime - se->vruntime;
+	if (diff < 0)
+		return se;
+
+	gran = calc_delta_fair(sysctl_sched_wakeup_granularity, &cfs_rq->load);
+	if (diff > gran)
+		return se;
+
+	return cfs_rq->next;
+}
+
 static struct sched_entity *pick_next_entity(struct cfs_rq *cfs_rq)
 {
 	struct sched_entity *se = NULL;
 
 	if (first_fair(cfs_rq)) {
 		se = __pick_next_entity(cfs_rq);
+		se = pick_next(cfs_rq, se);
 		set_next_entity(cfs_rq, se);
 	}
 
@@ -949,96 +982,121 @@ static inline int wake_idle(int cpu, struct task_struct *p)
 #endif
 
 #ifdef CONFIG_SMP
-static int select_task_rq_fair(struct task_struct *p, int sync)
+
+static const struct sched_class fair_sched_class;
+
+static int
+wake_affine(struct rq *rq, struct sched_domain *this_sd, struct rq *this_rq,
+	    struct task_struct *p, int prev_cpu, int this_cpu, int sync,
+	    int idx, unsigned long load, unsigned long this_load,
+	    unsigned int imbalance)
 {
-	int cpu, this_cpu;
-	struct rq *rq;
-	struct sched_domain *sd, *this_sd = NULL;
-	int new_cpu;
+	struct task_struct *curr = this_rq->curr;
+	unsigned long tl = this_load;
+	unsigned long tl_per_task;
+
+	if (!(this_sd->flags & SD_WAKE_AFFINE))
+		return 0;
+
+	/*
+	 * If the currently running task will sleep within
+	 * a reasonable amount of time then attract this newly
+	 * woken task:
+	 */
+	if (sync && curr->sched_class == &fair_sched_class) {
+		if (curr->se.avg_overlap < sysctl_sched_migration_cost &&
+				p->se.avg_overlap < sysctl_sched_migration_cost)
+			return 1;
+	}
+
+	schedstat_inc(p, se.nr_wakeups_affine_attempts);
+	tl_per_task = cpu_avg_load_per_task(this_cpu);
 
-	cpu      = task_cpu(p);
-	rq       = task_rq(p);
-	this_cpu = smp_processor_id();
-	new_cpu  = cpu;
+	/*
+	 * If sync wakeup then subtract the (maximum possible)
+	 * effect of the currently running task from the load
+	 * of the current CPU:
+	 */
+	if (sync)
+		tl -= current->se.load.weight;
+
+	if ((tl <= load && tl + target_load(prev_cpu, idx) <= tl_per_task) ||
+			100*(tl + p->se.load.weight) <= imbalance*load) {
+		/*
+		 * This domain has SD_WAKE_AFFINE and
+		 * p is cache cold in this domain, and
+		 * there is no bad imbalance.
+		 */
+		schedstat_inc(this_sd, ttwu_move_affine);
+		schedstat_inc(p, se.nr_wakeups_affine);
+
+		return 1;
+	}
+	return 0;
+}
 
-	if (cpu == this_cpu)
-		goto out_set_cpu;
+static int select_task_rq_fair(struct task_struct *p, int sync)
+{
+	struct sched_domain *sd, *this_sd = NULL;
+	int prev_cpu, this_cpu, new_cpu;
+	unsigned long load, this_load;
+	struct rq *rq, *this_rq;
+	unsigned int imbalance;
+	int idx;
+
+	prev_cpu	= task_cpu(p);
+	rq		= task_rq(p);
+	this_cpu	= smp_processor_id();
+	this_rq		= cpu_rq(this_cpu);
+	new_cpu		= prev_cpu;
 
+	/*
+	 * 'this_sd' is the first domain that both
+	 * this_cpu and prev_cpu are present in:
+	 */
 	for_each_domain(this_cpu, sd) {
-		if (cpu_isset(cpu, sd->span)) {
+		if (cpu_isset(prev_cpu, sd->span)) {
 			this_sd = sd;
 			break;
 		}
 	}
 
 	if (unlikely(!cpu_isset(this_cpu, p->cpus_allowed)))
-		goto out_set_cpu;
+		goto out;
 
 	/*
 	 * Check for affine wakeup and passive balancing possibilities.
 	 */
-	if (this_sd) {
-		int idx = this_sd->wake_idx;
-		unsigned int imbalance;
-		unsigned long load, this_load;
-
-		imbalance = 100 + (this_sd->imbalance_pct - 100) / 2;
-
-		load = source_load(cpu, idx);
-		this_load = target_load(this_cpu, idx);
-
-		new_cpu = this_cpu; /* Wake to this CPU if we can */
-
-		if (this_sd->flags & SD_WAKE_AFFINE) {
-			unsigned long tl = this_load;
-			unsigned long tl_per_task;
-
-			/*
-			 * Attract cache-cold tasks on sync wakeups:
-			 */
-			if (sync && !task_hot(p, rq->clock, this_sd))
-				goto out_set_cpu;
-
-			schedstat_inc(p, se.nr_wakeups_affine_attempts);
-			tl_per_task = cpu_avg_load_per_task(this_cpu);
-
-			/*
-			 * If sync wakeup then subtract the (maximum possible)
-			 * effect of the currently running task from the load
-			 * of the current CPU:
-			 */
-			if (sync)
-				tl -= current->se.load.weight;
-
-			if ((tl <= load &&
-				tl + target_load(cpu, idx) <= tl_per_task) ||
-			       100*(tl + p->se.load.weight) <= imbalance*load) {
-				/*
-				 * This domain has SD_WAKE_AFFINE and
-				 * p is cache cold in this domain, and
-				 * there is no bad imbalance.
-				 */
-				schedstat_inc(this_sd, ttwu_move_affine);
-				schedstat_inc(p, se.nr_wakeups_affine);
-				goto out_set_cpu;
-			}
-		}
+	if (!this_sd)
+		goto out;
 
-		/*
-		 * Start passive balancing when half the imbalance_pct
-		 * limit is reached.
-		 */
-		if (this_sd->flags & SD_WAKE_BALANCE) {
-			if (imbalance*this_load <= 100*load) {
-				schedstat_inc(this_sd, ttwu_move_balance);
-				schedstat_inc(p, se.nr_wakeups_passive);
-				goto out_set_cpu;
-			}
+	idx = this_sd->wake_idx;
+
+	imbalance = 100 + (this_sd->imbalance_pct - 100) / 2;
+
+	load = source_load(prev_cpu, idx);
+	this_load = target_load(this_cpu, idx);
+
+	if (wake_affine(rq, this_sd, this_rq, p, prev_cpu, this_cpu, sync, idx,
+				     load, this_load, imbalance))
+		return this_cpu;
+
+	if (prev_cpu == this_cpu)
+		goto out;
+
+	/*
+	 * Start passive balancing when half the imbalance_pct
+	 * limit is reached.
+	 */
+	if (this_sd->flags & SD_WAKE_BALANCE) {
+		if (imbalance*this_load <= 100*load) {
+			schedstat_inc(this_sd, ttwu_move_balance);
+			schedstat_inc(p, se.nr_wakeups_passive);
+			return this_cpu;
 		}
 	}
 
-	new_cpu = cpu; /* Could not wake to this_cpu. Wake to cpu instead */
-out_set_cpu:
+out:
 	return wake_idle(new_cpu, p);
 }
 #endif /* CONFIG_SMP */
@@ -1060,6 +1118,13 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p)
 		resched_task(curr);
 		return;
 	}
+
+	se->last_wakeup = se->sum_exec_runtime;
+	if (unlikely(se == pse))
+		return;
+
+	cfs_rq_of(pse)->next = pse;
+
 	/*
 	 * Batch tasks do not preempt (their preemption is driven by
 	 * the tick):
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index 548c436a776b..278534bbca95 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -141,13 +141,8 @@ static void clocksource_watchdog(unsigned long data)
 	}
 
 	if (!list_empty(&watchdog_list)) {
-		/* Cycle through CPUs to check if the CPUs stay synchronized to
-		 * each other. */
-		int next_cpu = next_cpu(raw_smp_processor_id(), cpu_online_map);
-		if (next_cpu >= NR_CPUS)
-			next_cpu = first_cpu(cpu_online_map);
-		watchdog_timer.expires += WATCHDOG_INTERVAL;
-		add_timer_on(&watchdog_timer, next_cpu);
+		__mod_timer(&watchdog_timer,
+			    watchdog_timer.expires + WATCHDOG_INTERVAL);
 	}
 	spin_unlock(&watchdog_lock);
 }
@@ -169,7 +164,7 @@ static void clocksource_check_watchdog(struct clocksource *cs)
 		if (!started && watchdog) {
 			watchdog_last = watchdog->read();
 			watchdog_timer.expires = jiffies + WATCHDOG_INTERVAL;
-			add_timer_on(&watchdog_timer, first_cpu(cpu_online_map));
+			add_timer(&watchdog_timer);
 		}
 	} else {
 		if (cs->flags & CLOCK_SOURCE_IS_CONTINUOUS)
@@ -190,8 +185,7 @@ static void clocksource_check_watchdog(struct clocksource *cs)
 				watchdog_last = watchdog->read();
 				watchdog_timer.expires =
 					jiffies + WATCHDOG_INTERVAL;
-				add_timer_on(&watchdog_timer,
-						first_cpu(cpu_online_map));
+				add_timer(&watchdog_timer);
 			}
 		}
 	}
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 671af612b768..a3fa587c350c 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -191,8 +191,12 @@ static void change_clocksource(void)
 
 	tick_clock_notify();
 
+	/*
+	 * We're holding xtime lock and waking up klogd would deadlock
+	 * us on enqueue.  So no printing!
 	printk(KERN_INFO "Time: %s clocksource has been installed.\n",
 	       clock->name);
+	 */
 }
 #else
 static inline void change_clocksource(void) { }