Merge commit 'v2.6.26-rc9' into x86/cpu

kernel/audit.c

@@ -738,7 +738,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 		if (!audit_enabled && msg_type != AUDIT_USER_AVC)
 			return 0;
 
-		err = audit_filter_user(&NETLINK_CB(skb), msg_type);
+		err = audit_filter_user(&NETLINK_CB(skb));
 		if (err == 1) {
 			err = 0;
 			if (msg_type == AUDIT_USER_TTY) {
@@ -779,7 +779,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 		}
 		/* fallthrough */
 	case AUDIT_LIST:
-		err = audit_receive_filter(nlh->nlmsg_type, NETLINK_CB(skb).pid,
+		err = audit_receive_filter(msg_type, NETLINK_CB(skb).pid,
 					   uid, seq, data, nlmsg_len(nlh),
 					   loginuid, sessionid, sid);
 		break;
@@ -798,7 +798,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 		}
 		/* fallthrough */
 	case AUDIT_LIST_RULES:
-		err = audit_receive_filter(nlh->nlmsg_type, NETLINK_CB(skb).pid,
+		err = audit_receive_filter(msg_type, NETLINK_CB(skb).pid,
 					   uid, seq, data, nlmsg_len(nlh),
 					   loginuid, sessionid, sid);
 		break;

kernel/auditfilter.c

@@ -1544,6 +1544,7 @@ static void audit_log_rule_change(uid_t loginuid, u32 sessionid, u32 sid,
  * @data: payload data
  * @datasz: size of payload data
  * @loginuid: loginuid of sender
+ * @sessionid: sessionid for netlink audit message
  * @sid: SE Linux Security ID of sender
  */
 int audit_receive_filter(int type, int pid, int uid, int seq, void *data,
@@ -1720,7 +1721,7 @@ static int audit_filter_user_rules(struct netlink_skb_parms *cb,
 	return 1;
 }
 
-int audit_filter_user(struct netlink_skb_parms *cb, int type)
+int audit_filter_user(struct netlink_skb_parms *cb)
 {
 	enum audit_state state = AUDIT_DISABLED;
 	struct audit_entry *e;

kernel/capability.c

@@ -52,12 +52,96 @@ static void warn_legacy_capability_use(void)
 	}
 }
 
+/*
+ * Version 2 capabilities worked fine, but the linux/capability.h file
+ * that accompanied their introduction encouraged their use without
+ * the necessary user-space source code changes. As such, we have
+ * created a version 3 with equivalent functionality to version 2, but
+ * with a header change to protect legacy source code from using
+ * version 2 when it wanted to use version 1. If your system has code
+ * that trips the following warning, it is using version 2 specific
+ * capabilities and may be doing so insecurely.
+ *
+ * The remedy is to either upgrade your version of libcap (to 2.10+,
+ * if the application is linked against it), or recompile your
+ * application with modern kernel headers and this warning will go
+ * away.
+ */
+
+static void warn_deprecated_v2(void)
+{
+	static int warned;
+
+	if (!warned) {
+		char name[sizeof(current->comm)];
+
+		printk(KERN_INFO "warning: `%s' uses deprecated v2"
+		       " capabilities in a way that may be insecure.\n",
+		       get_task_comm(name, current));
+		warned = 1;
+	}
+}
+
+/*
+ * Version check. Return the number of u32s in each capability flag
+ * array, or a negative value on error.
+ */
+static int cap_validate_magic(cap_user_header_t header, unsigned *tocopy)
+{
+	__u32 version;
+
+	if (get_user(version, &header->version))
+		return -EFAULT;
+
+	switch (version) {
+	case _LINUX_CAPABILITY_VERSION_1:
+		warn_legacy_capability_use();
+		*tocopy = _LINUX_CAPABILITY_U32S_1;
+		break;
+	case _LINUX_CAPABILITY_VERSION_2:
+		warn_deprecated_v2();
+		/*
+		 * fall through - v3 is otherwise equivalent to v2.
+		 */
+	case _LINUX_CAPABILITY_VERSION_3:
+		*tocopy = _LINUX_CAPABILITY_U32S_3;
+		break;
+	default:
+		if (put_user((u32)_KERNEL_CAPABILITY_VERSION, &header->version))
+			return -EFAULT;
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 /*
  * For sys_getproccap() and sys_setproccap(), any of the three
  * capability set pointers may be NULL -- indicating that that set is
  * uninteresting and/or not to be changed.
  */
 
+/*
+ * Atomically modify the effective capabilities returning the original
+ * value. No permission check is performed here - it is assumed that the
+ * caller is permitted to set the desired effective capabilities.
+ */
+kernel_cap_t cap_set_effective(const kernel_cap_t pE_new)
+{
+	kernel_cap_t pE_old;
+
+	spin_lock(&task_capability_lock);
+
+	pE_old = current->cap_effective;
+	current->cap_effective = pE_new;
+
+	spin_unlock(&task_capability_lock);
+
+	return pE_old;
+}
+
+EXPORT_SYMBOL(cap_set_effective);
+
 /**
  * sys_capget - get the capabilities of a given process.
  * @header: pointer to struct that contains capability version and
@@ -71,27 +155,13 @@ asmlinkage long sys_capget(cap_user_header_t header, cap_user_data_t dataptr)
 {
 	int ret = 0;
 	pid_t pid;
-	__u32 version;
 	struct task_struct *target;
 	unsigned tocopy;
 	kernel_cap_t pE, pI, pP;
 
-	if (get_user(version, &header->version))
-		return -EFAULT;
-
-	switch (version) {
-	case _LINUX_CAPABILITY_VERSION_1:
-		warn_legacy_capability_use();
-		tocopy = _LINUX_CAPABILITY_U32S_1;
-		break;
-	case _LINUX_CAPABILITY_VERSION_2:
-		tocopy = _LINUX_CAPABILITY_U32S_2;
-		break;
-	default:
-		if (put_user(_LINUX_CAPABILITY_VERSION, &header->version))
-			return -EFAULT;
-		return -EINVAL;
-	}
+	ret = cap_validate_magic(header, &tocopy);
+	if (ret != 0)
+		return ret;
 
 	if (get_user(pid, &header->pid))
 		return -EFAULT;
@@ -118,7 +188,7 @@ out:
 	spin_unlock(&task_capability_lock);
 
 	if (!ret) {
-		struct __user_cap_data_struct kdata[_LINUX_CAPABILITY_U32S];
+		struct __user_cap_data_struct kdata[_KERNEL_CAPABILITY_U32S];
 		unsigned i;
 
 		for (i = 0; i < tocopy; i++) {
@@ -128,7 +198,7 @@ out:
 		}
 
 		/*
-		 * Note, in the case, tocopy < _LINUX_CAPABILITY_U32S,
+		 * Note, in the case, tocopy < _KERNEL_CAPABILITY_U32S,
 		 * we silently drop the upper capabilities here. This
 		 * has the effect of making older libcap
 		 * implementations implicitly drop upper capability
@@ -240,30 +310,16 @@ static inline int cap_set_all(kernel_cap_t *effective,
  */
 asmlinkage long sys_capset(cap_user_header_t header, const cap_user_data_t data)
 {
-	struct __user_cap_data_struct kdata[_LINUX_CAPABILITY_U32S];
+	struct __user_cap_data_struct kdata[_KERNEL_CAPABILITY_U32S];
 	unsigned i, tocopy;
 	kernel_cap_t inheritable, permitted, effective;
-	__u32 version;
 	struct task_struct *target;
 	int ret;
 	pid_t pid;
 
-	if (get_user(version, &header->version))
-		return -EFAULT;
-
-	switch (version) {
-	case _LINUX_CAPABILITY_VERSION_1:
-		warn_legacy_capability_use();
-		tocopy = _LINUX_CAPABILITY_U32S_1;
-		break;
-	case _LINUX_CAPABILITY_VERSION_2:
-		tocopy = _LINUX_CAPABILITY_U32S_2;
-		break;
-	default:
-		if (put_user(_LINUX_CAPABILITY_VERSION, &header->version))
-			return -EFAULT;
-		return -EINVAL;
-	}
+	ret = cap_validate_magic(header, &tocopy);
+	if (ret != 0)
+		return ret;
 
 	if (get_user(pid, &header->pid))
 		return -EFAULT;
@@ -281,7 +337,7 @@ asmlinkage long sys_capset(cap_user_header_t header, const cap_user_data_t data)
 		permitted.cap[i] = kdata[i].permitted;
 		inheritable.cap[i] = kdata[i].inheritable;
 	}
-	while (i < _LINUX_CAPABILITY_U32S) {
+	while (i < _KERNEL_CAPABILITY_U32S) {
 		effective.cap[i] = 0;
 		permitted.cap[i] = 0;
 		inheritable.cap[i] = 0;

kernel/cpuset.c

@@ -797,8 +797,10 @@ static int update_cpumask(struct cpuset *cs, char *buf)
 		retval = cpulist_parse(buf, trialcs.cpus_allowed);
 		if (retval < 0)
 			return retval;
+
+		if (!cpus_subset(trialcs.cpus_allowed, cpu_online_map))
+			return -EINVAL;
 	}
-	cpus_and(trialcs.cpus_allowed, trialcs.cpus_allowed, cpu_online_map);
 	retval = validate_change(cs, &trialcs);
 	if (retval < 0)
 		return retval;
@@ -932,9 +934,11 @@ static int update_nodemask(struct cpuset *cs, char *buf)
 		retval = nodelist_parse(buf, trialcs.mems_allowed);
 		if (retval < 0)
 			goto done;
+
+		if (!nodes_subset(trialcs.mems_allowed,
+				node_states[N_HIGH_MEMORY]))
+			return -EINVAL;
 	}
-	nodes_and(trialcs.mems_allowed, trialcs.mems_allowed,
-						node_states[N_HIGH_MEMORY]);
 	oldmem = cs->mems_allowed;
 	if (nodes_equal(oldmem, trialcs.mems_allowed)) {
 		retval = 0;		/* Too easy - nothing to do */
@@ -1033,8 +1037,8 @@ int current_cpuset_is_being_rebound(void)
 
 static int update_relax_domain_level(struct cpuset *cs, s64 val)
 {
-	if ((int)val < 0)
-		val = -1;
+	if (val < -1 || val >= SD_LV_MAX)
+		return -EINVAL;
 
 	if (val != cs->relax_domain_level) {
 		cs->relax_domain_level = val;
@@ -1886,6 +1890,12 @@ static void common_cpu_mem_hotplug_unplug(void)
 	top_cpuset.mems_allowed = node_states[N_HIGH_MEMORY];
 	scan_for_empty_cpusets(&top_cpuset);
 
+	/*
+	 * Scheduler destroys domains on hotplug events.
+	 * Rebuild them based on the current settings.
+	 */
+	rebuild_sched_domains();
+
 	cgroup_unlock();
 }
 

kernel/futex.c

@@ -1096,21 +1096,64 @@ static void unqueue_me_pi(struct futex_q *q)
  * private futexes.
  */
 static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q,
-				struct task_struct *newowner)
+				struct task_struct *newowner,
+				struct rw_semaphore *fshared)
 {
 	u32 newtid = task_pid_vnr(newowner) | FUTEX_WAITERS;
 	struct futex_pi_state *pi_state = q->pi_state;
+	struct task_struct *oldowner = pi_state->owner;
 	u32 uval, curval, newval;
-	int ret;
+	int ret, attempt = 0;
 
 	/* Owner died? */
+	if (!pi_state->owner)
+		newtid |= FUTEX_OWNER_DIED;
+
+	/*
+	 * We are here either because we stole the rtmutex from the
+	 * pending owner or we are the pending owner which failed to
+	 * get the rtmutex. We have to replace the pending owner TID
+	 * in the user space variable. This must be atomic as we have
+	 * to preserve the owner died bit here.
+	 *
+	 * Note: We write the user space value _before_ changing the
+	 * pi_state because we can fault here. Imagine swapped out
+	 * pages or a fork, which was running right before we acquired
+	 * mmap_sem, that marked all the anonymous memory readonly for
+	 * cow.
+	 *
+	 * Modifying pi_state _before_ the user space value would
+	 * leave the pi_state in an inconsistent state when we fault
+	 * here, because we need to drop the hash bucket lock to
+	 * handle the fault. This might be observed in the PID check
+	 * in lookup_pi_state.
+	 */
+retry:
+	if (get_futex_value_locked(&uval, uaddr))
+		goto handle_fault;
+
+	while (1) {
+		newval = (uval & FUTEX_OWNER_DIED) | newtid;
+
+		curval = cmpxchg_futex_value_locked(uaddr, uval, newval);
+
+		if (curval == -EFAULT)
+			goto handle_fault;
+		if (curval == uval)
+			break;
+		uval = curval;
+	}
+
+	/*
+	 * We fixed up user space. Now we need to fix the pi_state
+	 * itself.
+	 */
 	if (pi_state->owner != NULL) {
 		spin_lock_irq(&pi_state->owner->pi_lock);
 		WARN_ON(list_empty(&pi_state->list));
 		list_del_init(&pi_state->list);
 		spin_unlock_irq(&pi_state->owner->pi_lock);
-	} else
-		newtid |= FUTEX_OWNER_DIED;
+	}
 
 	pi_state->owner = newowner;
 
@@ -1118,26 +1161,35 @@ static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q,
 	WARN_ON(!list_empty(&pi_state->list));
 	list_add(&pi_state->list, &newowner->pi_state_list);
 	spin_unlock_irq(&newowner->pi_lock);
+	return 0;
 
 	/*
-	 * We own it, so we have to replace the pending owner
-	 * TID. This must be atomic as we have preserve the
-	 * owner died bit here.
+	 * To handle the page fault we need to drop the hash bucket
+	 * lock here. That gives the other task (either the pending
+	 * owner itself or the task which stole the rtmutex) the
+	 * chance to try the fixup of the pi_state. So once we are
+	 * back from handling the fault we need to check the pi_state
+	 * after reacquiring the hash bucket lock and before trying to
+	 * do another fixup. When the fixup has been done already we
+	 * simply return.
 	 */
-	ret = get_futex_value_locked(&uval, uaddr);
+handle_fault:
+	spin_unlock(q->lock_ptr);
 
-	while (!ret) {
-		newval = (uval & FUTEX_OWNER_DIED) | newtid;
+	ret = futex_handle_fault((unsigned long)uaddr, fshared, attempt++);
 
-		curval = cmpxchg_futex_value_locked(uaddr, uval, newval);
+	spin_lock(q->lock_ptr);
 
-		if (curval == -EFAULT)
-			ret = -EFAULT;
-		if (curval == uval)
-			break;
-		uval = curval;
-	}
-	return ret;
+	/*
+	 * Check if someone else fixed it for us:
+	 */
+	if (pi_state->owner != oldowner)
+		return 0;
+
+	if (ret)
+		return ret;
+
+	goto retry;
 }
 
 /*
@@ -1507,7 +1559,7 @@ static int futex_lock_pi(u32 __user *uaddr, struct rw_semaphore *fshared,
 		 * that case:
 		 */
 		if (q.pi_state->owner != curr)
-			ret = fixup_pi_state_owner(uaddr, &q, curr);
+			ret = fixup_pi_state_owner(uaddr, &q, curr, fshared);
 	} else {
 		/*
 		 * Catch the rare case, where the lock was released
@@ -1539,7 +1591,8 @@ static int futex_lock_pi(u32 __user *uaddr, struct rw_semaphore *fshared,
 				int res;
 
 				owner = rt_mutex_owner(&q.pi_state->pi_mutex);
-				res = fixup_pi_state_owner(uaddr, &q, owner);
+				res = fixup_pi_state_owner(uaddr, &q, owner,
+							   fshared);
 
 				/* propagate -EFAULT, if the fixup failed */
 				if (res)

kernel/hrtimer.c

@@ -1003,10 +1003,18 @@ hrtimer_start(struct hrtimer *timer, ktime_t tim, const enum hrtimer_mode mode)
 	 */
 	raise = timer->state == HRTIMER_STATE_PENDING;
 
+	/*
+	 * We use preempt_disable to prevent this task from migrating after
+	 * setting up the softirq and raising it. Otherwise, if me migrate
+	 * we will raise the softirq on the wrong CPU.
+	 */
+	preempt_disable();
+
 	unlock_hrtimer_base(timer, &flags);
 
 	if (raise)
 		hrtimer_raise_softirq();
+	preempt_enable();
 
 	return ret;
 }

kernel/kgdb.c

@@ -52,6 +52,7 @@
 #include <asm/byteorder.h>
 #include <asm/atomic.h>
 #include <asm/system.h>
+#include <asm/unaligned.h>
 
 static int kgdb_break_asap;
 
@@ -227,8 +228,6 @@ void __weak kgdb_disable_hw_debug(struct pt_regs *regs)
  * GDB remote protocol parser:
  */
 
-static const char	hexchars[] = "0123456789abcdef";
-
 static int hex(char ch)
 {
 	if ((ch >= 'a') && (ch <= 'f'))
@@ -316,8 +315,8 @@ static void put_packet(char *buffer)
 		}
 
 		kgdb_io_ops->write_char('#');
-		kgdb_io_ops->write_char(hexchars[checksum >> 4]);
-		kgdb_io_ops->write_char(hexchars[checksum & 0xf]);
+		kgdb_io_ops->write_char(hex_asc_hi(checksum));
+		kgdb_io_ops->write_char(hex_asc_lo(checksum));
 		if (kgdb_io_ops->flush)
 			kgdb_io_ops->flush();
 
@@ -478,8 +477,8 @@ static void error_packet(char *pkt, int error)
 {
 	error = -error;
 	pkt[0] = 'E';
-	pkt[1] = hexchars[(error / 10)];
-	pkt[2] = hexchars[(error % 10)];
+	pkt[1] = hex_asc[(error / 10)];
+	pkt[2] = hex_asc[(error % 10)];
 	pkt[3] = '\0';
 }
 
@@ -510,10 +509,7 @@ static void int_to_threadref(unsigned char *id, int value)
 	scan = (unsigned char *)id;
 	while (i--)
 		*scan++ = 0;
-	*scan++ = (value >> 24) & 0xff;
-	*scan++ = (value >> 16) & 0xff;
-	*scan++ = (value >> 8) & 0xff;
-	*scan++ = (value & 0xff);
+	put_unaligned_be32(value, scan);
 }
 
 static struct task_struct *getthread(struct pt_regs *regs, int tid)
@@ -1503,7 +1499,8 @@ int kgdb_nmicallback(int cpu, void *regs)
 	return 1;
 }
 
-void kgdb_console_write(struct console *co, const char *s, unsigned count)
+static void kgdb_console_write(struct console *co, const char *s,
+   unsigned count)
 {
 	unsigned long flags;
 

kernel/kprobes.c

@@ -699,8 +699,9 @@ static int __register_kprobes(struct kprobe **kps, int num,
 		return -EINVAL;
 	for (i = 0; i < num; i++) {
 		ret = __register_kprobe(kps[i], called_from);
-		if (ret < 0 && i > 0) {
-			unregister_kprobes(kps, i);
+		if (ret < 0) {
+			if (i > 0)
+				unregister_kprobes(kps, i);
 			break;
 		}
 	}
@@ -776,8 +777,9 @@ static int __register_jprobes(struct jprobe **jps, int num,
 			jp->kp.break_handler = longjmp_break_handler;
 			ret = __register_kprobe(&jp->kp, called_from);
 		}
-		if (ret < 0 && i > 0) {
-			unregister_jprobes(jps, i);
+		if (ret < 0) {
+			if (i > 0)
+				unregister_jprobes(jps, i);
 			break;
 		}
 	}
@@ -920,8 +922,9 @@ static int __register_kretprobes(struct kretprobe **rps, int num,
 		return -EINVAL;
 	for (i = 0; i < num; i++) {
 		ret = __register_kretprobe(rps[i], called_from);
-		if (ret < 0 && i > 0) {
-			unregister_kretprobes(rps, i);
+		if (ret < 0) {
+			if (i > 0)
+				unregister_kretprobes(rps, i);
 			break;
 		}
 	}

kernel/rcuclassic.c

@@ -89,8 +89,22 @@ static void force_quiescent_state(struct rcu_data *rdp,
 		/*
 		 * Don't send IPI to itself. With irqs disabled,
 		 * rdp->cpu is the current cpu.
+		 *
+		 * cpu_online_map is updated by the _cpu_down()
+		 * using stop_machine_run(). Since we're in irqs disabled
+		 * section, stop_machine_run() is not exectuting, hence
+		 * the cpu_online_map is stable.
+		 *
+		 * However,  a cpu might have been offlined _just_ before
+		 * we disabled irqs while entering here.
+		 * And rcu subsystem might not yet have handled the CPU_DEAD
+		 * notification, leading to the offlined cpu's bit
+		 * being set in the rcp->cpumask.
+		 *
+		 * Hence cpumask = (rcp->cpumask & cpu_online_map) to prevent
+		 * sending smp_reschedule() to an offlined CPU.
 		 */
-		cpumask = rcp->cpumask;
+		cpus_and(cpumask, rcp->cpumask, cpu_online_map);
 		cpu_clear(rdp->cpu, cpumask);
 		for_each_cpu_mask(cpu, cpumask)
 			smp_send_reschedule(cpu);

kernel/rcupreempt.c

@@ -217,8 +217,6 @@ long rcu_batches_completed(void)
 }
 EXPORT_SYMBOL_GPL(rcu_batches_completed);
 
-EXPORT_SYMBOL_GPL(rcu_batches_completed_bh);
-
 void __rcu_read_lock(void)
 {
 	int idx;

kernel/sched.c

@@ -312,12 +312,15 @@ static DEFINE_SPINLOCK(task_group_lock);
 #endif
 
 /*
- * A weight of 0, 1 or ULONG_MAX can cause arithmetics problems.
+ * A weight of 0 or 1 can cause arithmetics problems.
+ * A weight of a cfs_rq is the sum of weights of which entities
+ * are queued on this cfs_rq, so a weight of a entity should not be
+ * too large, so as the shares value of a task group.
  * (The default weight is 1024 - so there's no practical
  *  limitation from this.)
  */
 #define MIN_SHARES	2
-#define MAX_SHARES	(ULONG_MAX - 1)
+#define MAX_SHARES	(1UL << 18)
 
 static int init_task_group_load = INIT_TASK_GROUP_LOAD;
 #endif
@@ -1124,6 +1127,7 @@ static enum hrtimer_restart hrtick(struct hrtimer *timer)
 	return HRTIMER_NORESTART;
 }
 
+#ifdef CONFIG_SMP
 static void hotplug_hrtick_disable(int cpu)
 {
 	struct rq *rq = cpu_rq(cpu);
@@ -1179,6 +1183,7 @@ static void init_hrtick(void)
 {
 	hotcpu_notifier(hotplug_hrtick, 0);
 }
+#endif /* CONFIG_SMP */
 
 static void init_rq_hrtick(struct rq *rq)
 {
@@ -1337,8 +1342,13 @@ calc_delta_mine(unsigned long delta_exec, unsigned long weight,
 {
 	u64 tmp;
 
-	if (!lw->inv_weight)
-		lw->inv_weight = 1 + (WMULT_CONST-lw->weight/2)/(lw->weight+1);
+	if (!lw->inv_weight) {
+		if (BITS_PER_LONG > 32 && unlikely(lw->weight >= WMULT_CONST))
+			lw->inv_weight = 1;
+		else
+			lw->inv_weight = 1 + (WMULT_CONST-lw->weight/2)
+				/ (lw->weight+1);
+	}
 
 	tmp = (u64)delta_exec * weight;
 	/*
@@ -4159,12 +4169,10 @@ need_resched_nonpreemptible:
 	clear_tsk_need_resched(prev);
 
 	if (prev->state && !(preempt_count() & PREEMPT_ACTIVE)) {
-		if (unlikely((prev->state & TASK_INTERRUPTIBLE) &&
-				signal_pending(prev))) {
+		if (unlikely(signal_pending_state(prev->state, prev)))
 			prev->state = TASK_RUNNING;
-		} else {
+		else
 			deactivate_task(rq, prev, 1);
-		}
 		switch_count = &prev->nvcsw;
 	}
 
@@ -4390,22 +4398,20 @@ do_wait_for_common(struct completion *x, long timeout, int state)
 			     signal_pending(current)) ||
 			    (state == TASK_KILLABLE &&
 			     fatal_signal_pending(current))) {
-				__remove_wait_queue(&x->wait, &wait);
-				return -ERESTARTSYS;
+				timeout = -ERESTARTSYS;
+				break;
 			}
 			__set_current_state(state);
 			spin_unlock_irq(&x->wait.lock);
 			timeout = schedule_timeout(timeout);
 			spin_lock_irq(&x->wait.lock);
-			if (!timeout) {
-				__remove_wait_queue(&x->wait, &wait);
-				return timeout;
-			}
-		} while (!x->done);
+		} while (!x->done && timeout);
 		__remove_wait_queue(&x->wait, &wait);
+		if (!x->done)
+			return timeout;
 	}
 	x->done--;
-	return timeout;
+	return timeout ?: 1;
 }
 
 static long __sched
@@ -5881,6 +5887,7 @@ static void migrate_dead_tasks(unsigned int dead_cpu)
 		next = pick_next_task(rq, rq->curr);
 		if (!next)
 			break;
+		next->sched_class->put_prev_task(rq, next);
 		migrate_dead(dead_cpu, next);
 
 	}
@@ -6871,7 +6878,12 @@ static int default_relax_domain_level = -1;
 
 static int __init setup_relax_domain_level(char *str)
 {
-	default_relax_domain_level = simple_strtoul(str, NULL, 0);
+	unsigned long val;
+
+	val = simple_strtoul(str, NULL, 0);
+	if (val < SD_LV_MAX)
+		default_relax_domain_level = val;
+
 	return 1;
 }
 __setup("relax_domain_level=", setup_relax_domain_level);
@@ -7229,6 +7241,18 @@ void __attribute__((weak)) arch_update_cpu_topology(void)
 {
 }
 
+/*
+ * Free current domain masks.
+ * Called after all cpus are attached to NULL domain.
+ */
+static void free_sched_domains(void)
+{
+	ndoms_cur = 0;
+	if (doms_cur != &fallback_doms)
+		kfree(doms_cur);
+	doms_cur = &fallback_doms;
+}
+
 /*
  * Set up scheduler domains and groups. Callers must hold the hotplug lock.
  * For now this just excludes isolated cpus, but could be used to
@@ -7376,6 +7400,7 @@ int arch_reinit_sched_domains(void)
 	get_online_cpus();
 	mutex_lock(&sched_domains_mutex);
 	detach_destroy_domains(&cpu_online_map);
+	free_sched_domains();
 	err = arch_init_sched_domains(&cpu_online_map);
 	mutex_unlock(&sched_domains_mutex);
 	put_online_cpus();
@@ -7461,6 +7486,7 @@ static int update_sched_domains(struct notifier_block *nfb,
 	case CPU_DOWN_PREPARE:
 	case CPU_DOWN_PREPARE_FROZEN:
 		detach_destroy_domains(&cpu_online_map);
+		free_sched_domains();
 		return NOTIFY_OK;
 
 	case CPU_UP_CANCELED:
@@ -7479,8 +7505,16 @@ static int update_sched_domains(struct notifier_block *nfb,
 		return NOTIFY_DONE;
 	}
 
+#ifndef CONFIG_CPUSETS
+	/*
+	 * Create default domain partitioning if cpusets are disabled.
+	 * Otherwise we let cpusets rebuild the domains based on the
+	 * current setup.
+	 */
+
 	/* The hotplug lock is already held by cpu_up/cpu_down */
 	arch_init_sched_domains(&cpu_online_map);
+#endif
 
 	return NOTIFY_OK;
 }
@@ -7620,7 +7654,6 @@ static void init_tg_rt_entry(struct task_group *tg, struct rt_rq *rt_rq,
 	else
 		rt_se->rt_rq = parent->my_q;
 
-	rt_se->rt_rq = &rq->rt;
 	rt_se->my_q = rt_rq;
 	rt_se->parent = parent;
 	INIT_LIST_HEAD(&rt_se->run_list);
@@ -8342,7 +8375,7 @@ static unsigned long to_ratio(u64 period, u64 runtime)
 #ifdef CONFIG_CGROUP_SCHED
 static int __rt_schedulable(struct task_group *tg, u64 period, u64 runtime)
 {
-	struct task_group *tgi, *parent = tg->parent;
+	struct task_group *tgi, *parent = tg ? tg->parent : NULL;
 	unsigned long total = 0;
 
 	if (!parent) {
@@ -8469,6 +8502,9 @@ int sched_group_set_rt_period(struct task_group *tg, long rt_period_us)
 	rt_period = (u64)rt_period_us * NSEC_PER_USEC;
 	rt_runtime = tg->rt_bandwidth.rt_runtime;
 
+	if (rt_period == 0)
+		return -EINVAL;
+
 	return tg_set_bandwidth(tg, rt_period, rt_runtime);
 }
 

kernel/sched_rt.c

@@ -250,7 +250,8 @@ static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun)
 			if (rt_rq->rt_time || rt_rq->rt_nr_running)
 				idle = 0;
 			spin_unlock(&rt_rq->rt_runtime_lock);
-		}
+		} else if (rt_rq->rt_nr_running)
+			idle = 0;
 
 		if (enqueue)
 			sched_rt_rq_enqueue(rt_rq);
@@ -449,13 +450,19 @@ void dec_rt_tasks(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
 #endif
 }
 
-static void enqueue_rt_entity(struct sched_rt_entity *rt_se)
+static void __enqueue_rt_entity(struct sched_rt_entity *rt_se)
 {
 	struct rt_rq *rt_rq = rt_rq_of_se(rt_se);
 	struct rt_prio_array *array = &rt_rq->active;
 	struct rt_rq *group_rq = group_rt_rq(rt_se);
 
-	if (group_rq && rt_rq_throttled(group_rq))
+	/*
+	 * Don't enqueue the group if its throttled, or when empty.
+	 * The latter is a consequence of the former when a child group
+	 * get throttled and the current group doesn't have any other
+	 * active members.
+	 */
+	if (group_rq && (rt_rq_throttled(group_rq) || !group_rq->rt_nr_running))
 		return;
 
 	list_add_tail(&rt_se->run_list, array->queue + rt_se_prio(rt_se));
@@ -464,7 +471,7 @@ static void enqueue_rt_entity(struct sched_rt_entity *rt_se)
 	inc_rt_tasks(rt_se, rt_rq);
 }
 
-static void dequeue_rt_entity(struct sched_rt_entity *rt_se)
+static void __dequeue_rt_entity(struct sched_rt_entity *rt_se)
 {
 	struct rt_rq *rt_rq = rt_rq_of_se(rt_se);
 	struct rt_prio_array *array = &rt_rq->active;
@@ -480,11 +487,10 @@ static void dequeue_rt_entity(struct sched_rt_entity *rt_se)
  * Because the prio of an upper entry depends on the lower
  * entries, we must remove entries top - down.
  */
-static void dequeue_rt_stack(struct task_struct *p)
+static void dequeue_rt_stack(struct sched_rt_entity *rt_se)
 {
-	struct sched_rt_entity *rt_se, *back = NULL;
+	struct sched_rt_entity *back = NULL;
 
-	rt_se = &p->rt;
 	for_each_sched_rt_entity(rt_se) {
 		rt_se->back = back;
 		back = rt_se;
@@ -492,7 +498,26 @@ static void dequeue_rt_stack(struct task_struct *p)
 
 	for (rt_se = back; rt_se; rt_se = rt_se->back) {
 		if (on_rt_rq(rt_se))
-			dequeue_rt_entity(rt_se);
+			__dequeue_rt_entity(rt_se);
+	}
+}
+
+static void enqueue_rt_entity(struct sched_rt_entity *rt_se)
+{
+	dequeue_rt_stack(rt_se);
+	for_each_sched_rt_entity(rt_se)
+		__enqueue_rt_entity(rt_se);
+}
+
+static void dequeue_rt_entity(struct sched_rt_entity *rt_se)
+{
+	dequeue_rt_stack(rt_se);
+
+	for_each_sched_rt_entity(rt_se) {
+		struct rt_rq *rt_rq = group_rt_rq(rt_se);
+
+		if (rt_rq && rt_rq->rt_nr_running)
+			__enqueue_rt_entity(rt_se);
 	}
 }
 
@@ -506,32 +531,15 @@ static void enqueue_task_rt(struct rq *rq, struct task_struct *p, int wakeup)
 	if (wakeup)
 		rt_se->timeout = 0;
 
-	dequeue_rt_stack(p);
-
-	/*
-	 * enqueue everybody, bottom - up.
-	 */
-	for_each_sched_rt_entity(rt_se)
-		enqueue_rt_entity(rt_se);
+	enqueue_rt_entity(rt_se);
 }
 
 static void dequeue_task_rt(struct rq *rq, struct task_struct *p, int sleep)
 {
 	struct sched_rt_entity *rt_se = &p->rt;
-	struct rt_rq *rt_rq;
 
 	update_curr_rt(rq);
-
-	dequeue_rt_stack(p);
-
-	/*
-	 * re-enqueue all non-empty rt_rq entities.
-	 */
-	for_each_sched_rt_entity(rt_se) {
-		rt_rq = group_rt_rq(rt_se);
-		if (rt_rq && rt_rq->rt_nr_running)
-			enqueue_rt_entity(rt_se);
-	}
+	dequeue_rt_entity(rt_se);
 }
 
 /*
@@ -542,8 +550,10 @@ static
 void requeue_rt_entity(struct rt_rq *rt_rq, struct sched_rt_entity *rt_se)
 {
 	struct rt_prio_array *array = &rt_rq->active;
+	struct list_head *queue = array->queue + rt_se_prio(rt_se);
 
-	list_move_tail(&rt_se->run_list, array->queue + rt_se_prio(rt_se));
+	if (on_rt_rq(rt_se))
+		list_move_tail(&rt_se->run_list, queue);
 }
 
 static void requeue_task_rt(struct rq *rq, struct task_struct *p)

kernel/sched_stats.h

@@ -198,6 +198,9 @@ static inline void sched_info_queued(struct task_struct *t)
 /*
  * Called when a process ceases being the active-running process, either
  * voluntarily or involuntarily.  Now we can calculate how long we ran.
+ * Also, if the process is still in the TASK_RUNNING state, call
+ * sched_info_queued() to mark that it has now again started waiting on
+ * the runqueue.
  */
 static inline void sched_info_depart(struct task_struct *t)
 {
@@ -206,6 +209,9 @@ static inline void sched_info_depart(struct task_struct *t)
 
 	t->sched_info.cpu_time += delta;
 	rq_sched_info_depart(task_rq(t), delta);
+
+	if (t->state == TASK_RUNNING)
+		sched_info_queued(t);
 }
 
 /*

kernel/softlockup.c

@@ -49,12 +49,17 @@ static unsigned long get_timestamp(int this_cpu)
 	return cpu_clock(this_cpu) >> 30LL;  /* 2^30 ~= 10^9 */
 }
 
-void touch_softlockup_watchdog(void)
+static void __touch_softlockup_watchdog(void)
 {
 	int this_cpu = raw_smp_processor_id();
 
 	__raw_get_cpu_var(touch_timestamp) = get_timestamp(this_cpu);
 }
+
+void touch_softlockup_watchdog(void)
+{
+	__raw_get_cpu_var(touch_timestamp) = 0;
+}
 EXPORT_SYMBOL(touch_softlockup_watchdog);
 
 void touch_all_softlockup_watchdogs(void)
@@ -80,7 +85,7 @@ void softlockup_tick(void)
 	unsigned long now;
 
 	if (touch_timestamp == 0) {
-		touch_softlockup_watchdog();
+		__touch_softlockup_watchdog();
 		return;
 	}
 
@@ -95,7 +100,7 @@ void softlockup_tick(void)
 
 	/* do not print during early bootup: */
 	if (unlikely(system_state != SYSTEM_RUNNING)) {
-		touch_softlockup_watchdog();
+		__touch_softlockup_watchdog();
 		return;
 	}
 
@@ -115,6 +120,7 @@ void softlockup_tick(void)
 	printk(KERN_ERR "BUG: soft lockup - CPU#%d stuck for %lus! [%s:%d]\n",
 			this_cpu, now - touch_timestamp,
 			current->comm, task_pid_nr(current));
+	print_modules();
 	if (regs)
 		show_regs(regs);
 	else
@@ -214,7 +220,7 @@ static int watchdog(void *__bind_cpu)
 	sched_setscheduler(current, SCHED_FIFO, &param);
 
 	/* initialize timestamp */
-	touch_softlockup_watchdog();
+	__touch_softlockup_watchdog();
 
 	set_current_state(TASK_INTERRUPTIBLE);
 	/*
@@ -223,7 +229,7 @@ static int watchdog(void *__bind_cpu)
 	 * debug-printout triggers in softlockup_tick().
 	 */
 	while (!kthread_should_stop()) {
-		touch_softlockup_watchdog();
+		__touch_softlockup_watchdog();
 		schedule();
 
 		if (kthread_should_stop())

kernel/workqueue.c

@@ -13,7 +13,7 @@
  *   Kai Petzke <wpp@marie.physik.tu-berlin.de>
  *   Theodore Ts'o <tytso@mit.edu>
  *
- * Made to use alloc_percpu by Christoph Lameter <clameter@sgi.com>.
+ * Made to use alloc_percpu by Christoph Lameter.
  */
 
 #include <linux/module.h>