Merge branch 'master' of /home/davem/src/GIT/linux-2.6/

89 files changed, 2910 insertions, 2134 deletions

diff --git a/kernel/acct.c b/kernel/acct.c
index 9a4715a2f6bf..a6605ca921b6 100644
--- a/kernel/acct.c
+++ b/kernel/acct.c
@@ -536,7 +536,8 @@ static void do_acct_process(struct bsd_acct_struct *acct,
 	do_div(elapsed, AHZ);
 	ac.ac_btime = get_seconds() - elapsed;
 	/* we really need to bite the bullet and change layout */
-	current_uid_gid(&ac.ac_uid, &ac.ac_gid);
+	ac.ac_uid = orig_cred->uid;
+	ac.ac_gid = orig_cred->gid;
 #if ACCT_VERSION==2
 	ac.ac_ahz = AHZ;
 #endif
diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c
index 2451dc6f3282..4b05bd9479db 100644
--- a/kernel/audit_tree.c
+++ b/kernel/audit_tree.c
@@ -277,7 +277,7 @@ static void untag_chunk(struct node *p)
 		owner->root = NULL;
 	}
 
-	for (i = j = 0; i < size; i++, j++) {
+	for (i = j = 0; j <= size; i++, j++) {
 		struct audit_tree *s;
 		if (&chunk->owners[j] == p) {
 			list_del_init(&p->list);
@@ -290,7 +290,7 @@ static void untag_chunk(struct node *p)
 		if (!s) /* result of earlier fallback */
 			continue;
 		get_tree(s);
-		list_replace_init(&chunk->owners[i].list, &new->owners[j].list);
+		list_replace_init(&chunk->owners[j].list, &new->owners[i].list);
 	}
 
 	list_replace_rcu(&chunk->hash, &new->hash);
@@ -373,15 +373,17 @@ static int tag_chunk(struct inode *inode, struct audit_tree *tree)
 	for (n = 0; n < old->count; n++) {
 		if (old->owners[n].owner == tree) {
 			spin_unlock(&hash_lock);
-			put_inotify_watch(watch);
+			put_inotify_watch(&old->watch);
 			return 0;
 		}
 	}
 	spin_unlock(&hash_lock);
 
 	chunk = alloc_chunk(old->count + 1);
-	if (!chunk)
+	if (!chunk) {
+		put_inotify_watch(&old->watch);
 		return -ENOMEM;
+	}
 
 	mutex_lock(&inode->inotify_mutex);
 	if (inotify_clone_watch(&old->watch, &chunk->watch) < 0) {
@@ -425,7 +427,8 @@ static int tag_chunk(struct inode *inode, struct audit_tree *tree)
 	spin_unlock(&hash_lock);
 	inotify_evict_watch(&old->watch);
 	mutex_unlock(&inode->inotify_mutex);
-	put_inotify_watch(&old->watch);
+	put_inotify_watch(&old->watch); /* pair to inotify_find_watch */
+	put_inotify_watch(&old->watch); /* and kill it */
 	return 0;
 }
 
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index 267e484f0198..fc0f928167e7 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -250,7 +250,6 @@ struct audit_context {
 #endif
 };
 
-#define ACC_MODE(x) ("\004\002\006\006"[(x)&O_ACCMODE])
 static inline int open_arg(int flags, int mask)
 {
 	int n = ACC_MODE(flags);
diff --git a/kernel/bounds.c b/kernel/bounds.c
index 3c5301381837..98a51f26c136 100644
--- a/kernel/bounds.c
+++ b/kernel/bounds.c
@@ -12,7 +12,7 @@
 
 void foo(void)
 {
-	/* The enum constants to put into include/linux/bounds.h */
+	/* The enum constants to put into include/generated/bounds.h */
 	DEFINE(NR_PAGEFLAGS, __NR_PAGEFLAGS);
 	DEFINE(MAX_NR_ZONES, __MAX_NR_ZONES);
 	/* End of constants */
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 7c4e2713df0a..1c8ddd6ee940 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -209,9 +209,12 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen)
 		return -ENOMEM;
 
 	cpu_hotplug_begin();
+	set_cpu_active(cpu, false);
 	err = __raw_notifier_call_chain(&cpu_chain, CPU_DOWN_PREPARE | mod,
 					hcpu, -1, &nr_calls);
 	if (err == NOTIFY_BAD) {
+		set_cpu_active(cpu, true);
+
 		nr_calls--;
 		__raw_notifier_call_chain(&cpu_chain, CPU_DOWN_FAILED | mod,
 					  hcpu, nr_calls, NULL);
@@ -223,11 +226,11 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen)
 
 	/* Ensure that we are not runnable on dying cpu */
 	cpumask_copy(old_allowed, &current->cpus_allowed);
-	set_cpus_allowed_ptr(current,
-			     cpumask_of(cpumask_any_but(cpu_online_mask, cpu)));
+	set_cpus_allowed_ptr(current, cpu_active_mask);
 
 	err = __stop_machine(take_cpu_down, &tcd_param, cpumask_of(cpu));
 	if (err) {
+		set_cpu_active(cpu, true);
 		/* CPU didn't die: tell everyone.  Can't complain. */
 		if (raw_notifier_call_chain(&cpu_chain, CPU_DOWN_FAILED | mod,
 					    hcpu) == NOTIFY_BAD)
@@ -278,23 +281,8 @@ int __ref cpu_down(unsigned int cpu)
 		goto out;
 	}
 
-	set_cpu_active(cpu, false);
-
-	/*
-	 * Make sure the all cpus did the reschedule and are not
-	 * using stale version of the cpu_active_mask.
-	 * This is not strictly necessary becuase stop_machine()
-	 * that we run down the line already provides the required
-	 * synchronization. But it's really a side effect and we do not
-	 * want to depend on the innards of the stop_machine here.
-	 */
-	synchronize_sched();
-
 	err = _cpu_down(cpu, 0);
 
-	if (cpu_online(cpu))
-		set_cpu_active(cpu, true);
-
 out:
 	cpu_maps_update_done();
 	stop_machine_destroy();
@@ -383,10 +371,12 @@ int disable_nonboot_cpus(void)
 		return error;
 	cpu_maps_update_begin();
 	first_cpu = cpumask_first(cpu_online_mask);
-	/* We take down all of the non-boot CPUs in one shot to avoid races
+	/*
+	 * We take down all of the non-boot CPUs in one shot to avoid races
 	 * with the userspace trying to use the CPU hotplug at the same time
 	 */
 	cpumask_clear(frozen_cpus);
+
 	printk("Disabling non-boot CPUs ...\n");
 	for_each_online_cpu(cpu) {
 		if (cpu == first_cpu)
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 3cf2183b472d..ba401fab459f 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -737,7 +737,7 @@ static void do_rebuild_sched_domains(struct work_struct *unused)
 {
 }
 
-static int generate_sched_domains(struct cpumask **domains,
+static int generate_sched_domains(cpumask_var_t **domains,
 			struct sched_domain_attr **attributes)
 {
 	*domains = NULL;
@@ -872,7 +872,7 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs,
 		if (retval < 0)
 			return retval;
 
-		if (!cpumask_subset(trialcs->cpus_allowed, cpu_online_mask))
+		if (!cpumask_subset(trialcs->cpus_allowed, cpu_active_mask))
 			return -EINVAL;
 	}
 	retval = validate_change(cs, trialcs);
@@ -2010,7 +2010,7 @@ static void scan_for_empty_cpusets(struct cpuset *root)
 		}
 
 		/* Continue past cpusets with all cpus, mems online */
-		if (cpumask_subset(cp->cpus_allowed, cpu_online_mask) &&
+		if (cpumask_subset(cp->cpus_allowed, cpu_active_mask) &&
 		    nodes_subset(cp->mems_allowed, node_states[N_HIGH_MEMORY]))
 			continue;
 
@@ -2019,7 +2019,7 @@ static void scan_for_empty_cpusets(struct cpuset *root)
 		/* Remove offline cpus and mems from this cpuset. */
 		mutex_lock(&callback_mutex);
 		cpumask_and(cp->cpus_allowed, cp->cpus_allowed,
-			    cpu_online_mask);
+			    cpu_active_mask);
 		nodes_and(cp->mems_allowed, cp->mems_allowed,
 						node_states[N_HIGH_MEMORY]);
 		mutex_unlock(&callback_mutex);
@@ -2057,8 +2057,10 @@ static int cpuset_track_online_cpus(struct notifier_block *unused_nb,
 	switch (phase) {
 	case CPU_ONLINE:
 	case CPU_ONLINE_FROZEN:
-	case CPU_DEAD:
-	case CPU_DEAD_FROZEN:
+	case CPU_DOWN_PREPARE:
+	case CPU_DOWN_PREPARE_FROZEN:
+	case CPU_DOWN_FAILED:
+	case CPU_DOWN_FAILED_FROZEN:
 		break;
 
 	default:
@@ -2067,7 +2069,7 @@ static int cpuset_track_online_cpus(struct notifier_block *unused_nb,
 
 	cgroup_lock();
 	mutex_lock(&callback_mutex);
-	cpumask_copy(top_cpuset.cpus_allowed, cpu_online_mask);
+	cpumask_copy(top_cpuset.cpus_allowed, cpu_active_mask);
 	mutex_unlock(&callback_mutex);
 	scan_for_empty_cpusets(&top_cpuset);
 	ndoms = generate_sched_domains(&doms, &attr);
@@ -2114,7 +2116,7 @@ static int cpuset_track_online_nodes(struct notifier_block *self,
 
 void __init cpuset_init_smp(void)
 {
-	cpumask_copy(top_cpuset.cpus_allowed, cpu_online_mask);
+	cpumask_copy(top_cpuset.cpus_allowed, cpu_active_mask);
 	top_cpuset.mems_allowed = node_states[N_HIGH_MEMORY];
 
 	hotcpu_notifier(cpuset_track_online_cpus, 0);
diff --git a/kernel/exit.c b/kernel/exit.c
index 1143012951e9..546774a31a66 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -68,10 +68,10 @@ static void __unhash_process(struct task_struct *p)
 		detach_pid(p, PIDTYPE_SID);
 
 		list_del_rcu(&p->tasks);
+		list_del_init(&p->sibling);
 		__get_cpu_var(process_counts)--;
 	}
 	list_del_rcu(&p->thread_group);
-	list_del_init(&p->sibling);
 }
 
 /*
@@ -736,12 +736,9 @@ static struct task_struct *find_new_reaper(struct task_struct *father)
 /*
 * Any that need to be release_task'd are put on the @dead list.
  */
-static void reparent_thread(struct task_struct *father, struct task_struct *p,
+static void reparent_leader(struct task_struct *father, struct task_struct *p,
 				struct list_head *dead)
 {
-	if (p->pdeath_signal)
-		group_send_sig_info(p->pdeath_signal, SEND_SIG_NOINFO, p);
-
 	list_move_tail(&p->sibling, &p->real_parent->children);
 
 	if (task_detached(p))
@@ -780,12 +777,18 @@ static void forget_original_parent(struct task_struct *father)
 	reaper = find_new_reaper(father);
 
 	list_for_each_entry_safe(p, n, &father->children, sibling) {
-		p->real_parent = reaper;
-		if (p->parent == father) {
-			BUG_ON(task_ptrace(p));
-			p->parent = p->real_parent;
-		}
-		reparent_thread(father, p, &dead_children);
+		struct task_struct *t = p;
+		do {
+			t->real_parent = reaper;
+			if (t->parent == father) {
+				BUG_ON(task_ptrace(t));
+				t->parent = t->real_parent;
+			}
+			if (t->pdeath_signal)
+				group_send_sig_info(t->pdeath_signal,
+						    SEND_SIG_NOINFO, t);
+		} while_each_thread(p, t);
+		reparent_leader(father, p, &dead_children);
 	}
 	write_unlock_irq(&tasklist_lock);
 
@@ -933,7 +936,7 @@ NORET_TYPE void do_exit(long code)
 	 * an exiting task cleaning up the robust pi futexes.
 	 */
 	smp_mb();
-	spin_unlock_wait(&tsk->pi_lock);
+	raw_spin_unlock_wait(&tsk->pi_lock);
 
 	if (unlikely(in_atomic()))
 		printk(KERN_INFO "note: %s[%d] exited with preempt_count %d\n",
@@ -971,7 +974,7 @@ NORET_TYPE void do_exit(long code)
 	exit_thread();
 	cgroup_exit(tsk, 1);
 
-	if (group_dead && tsk->signal->leader)
+	if (group_dead)
 		disassociate_ctty(1);
 
 	module_put(task_thread_info(tsk)->exec_domain->module);
@@ -1551,14 +1554,9 @@ static int do_wait_thread(struct wait_opts *wo, struct task_struct *tsk)
 	struct task_struct *p;
 
 	list_for_each_entry(p, &tsk->children, sibling) {
-		/*
-		 * Do not consider detached threads.
-		 */
-		if (!task_detached(p)) {
-			int ret = wait_consider_task(wo, 0, p);
-			if (ret)
-				return ret;
-		}
+		int ret = wait_consider_task(wo, 0, p);
+		if (ret)
+			return ret;
 	}
 
 	return 0;
diff --git a/kernel/fork.c b/kernel/fork.c
index 1415dc4598ae..5b2959b3ffc2 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -939,9 +939,9 @@ SYSCALL_DEFINE1(set_tid_address, int __user *, tidptr)
 
 static void rt_mutex_init_task(struct task_struct *p)
 {
-	spin_lock_init(&p->pi_lock);
+	raw_spin_lock_init(&p->pi_lock);
 #ifdef CONFIG_RT_MUTEXES
-	plist_head_init(&p->pi_waiters, &p->pi_lock);
+	plist_head_init_raw(&p->pi_waiters, &p->pi_lock);
 	p->pi_blocked_on = NULL;
 #endif
 }
@@ -1127,6 +1127,10 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 #ifdef CONFIG_DEBUG_MUTEXES
 	p->blocked_on = NULL; /* not blocked yet */
 #endif
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR
+	p->memcg_batch.do_batch = 0;
+	p->memcg_batch.memcg = NULL;
+#endif
 
 	p->bts = NULL;
 
@@ -1206,9 +1210,10 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 		p->sas_ss_sp = p->sas_ss_size = 0;
 
 	/*
-	 * Syscall tracing should be turned off in the child regardless
-	 * of CLONE_PTRACE.
+	 * Syscall tracing and stepping should be turned off in the
+	 * child regardless of CLONE_PTRACE.
 	 */
+	user_disable_single_step(p);
 	clear_tsk_thread_flag(p, TIF_SYSCALL_TRACE);
 #ifdef TIF_SYSCALL_EMU
 	clear_tsk_thread_flag(p, TIF_SYSCALL_EMU);
@@ -1286,7 +1291,6 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	}
 
 	if (likely(p->pid)) {
-		list_add_tail(&p->sibling, &p->real_parent->children);
 		tracehook_finish_clone(p, clone_flags, trace);
 
 		if (thread_group_leader(p)) {
@@ -1298,6 +1302,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 			p->signal->tty = tty_kref_get(current->signal->