Merge commit 'v2.6.37-rc2' into sched/core

Merge reason: Move to a .37-rc base.

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

62 files changed, 1301 insertions, 911 deletions

diff --git a/kernel/audit.c b/kernel/audit.c
index d96045789b54..77770a034d59 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -467,23 +467,16 @@ static int audit_prepare_user_tty(pid_t pid, uid_t loginuid, u32 sessionid)
 	struct task_struct *tsk;
 	int err;
 
-	read_lock(&tasklist_lock);
+	rcu_read_lock();
 	tsk = find_task_by_vpid(pid);
-	err = -ESRCH;
-	if (!tsk)
-		goto out;
-	err = 0;
-
-	spin_lock_irq(&tsk->sighand->siglock);
-	if (!tsk->signal->audit_tty)
-		err = -EPERM;
-	spin_unlock_irq(&tsk->sighand->siglock);
-	if (err)
-		goto out;
-
-	tty_audit_push_task(tsk, loginuid, sessionid);
-out:
-	read_unlock(&tasklist_lock);
+	if (!tsk) {
+		rcu_read_unlock();
+		return -ESRCH;
+	}
+	get_task_struct(tsk);
+	rcu_read_unlock();
+	err = tty_audit_push_task(tsk, loginuid, sessionid);
+	put_task_struct(tsk);
 	return err;
 }
 
@@ -506,7 +499,7 @@ int audit_send_list(void *_dest)
 }
 
 struct sk_buff *audit_make_reply(int pid, int seq, int type, int done,
-				 int multi, void *payload, int size)
+				 int multi, const void *payload, int size)
 {
 	struct sk_buff	*skb;
 	struct nlmsghdr	*nlh;
@@ -555,8 +548,8 @@ static int audit_send_reply_thread(void *arg)
  * Allocates an skb, builds the netlink message, and sends it to the pid.
  * No failure notifications.
  */
-void audit_send_reply(int pid, int seq, int type, int done, int multi,
-		      void *payload, int size)
+static void audit_send_reply(int pid, int seq, int type, int done, int multi,
+			     const void *payload, int size)
 {
 	struct sk_buff *skb;
 	struct task_struct *tsk;
@@ -880,40 +873,40 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 	case AUDIT_TTY_GET: {
 		struct audit_tty_status s;
 		struct task_struct *tsk;
+		unsigned long flags;
 
-		read_lock(&tasklist_lock);
+		rcu_read_lock();
 		tsk = find_task_by_vpid(pid);
-		if (!tsk)
-			err = -ESRCH;
-		else {
-			spin_lock_irq(&tsk->sighand->siglock);
+		if (tsk && lock_task_sighand(tsk, &flags)) {
 			s.enabled = tsk->signal->audit_tty != 0;
-			spin_unlock_irq(&tsk->sighand->siglock);
-		}
-		read_unlock(&tasklist_lock);
-		audit_send_reply(NETLINK_CB(skb).pid, seq, AUDIT_TTY_GET, 0, 0,
-				 &s, sizeof(s));
+			unlock_task_sighand(tsk, &flags);
+		} else
+			err = -ESRCH;
+		rcu_read_unlock();
+
+		if (!err)
+			audit_send_reply(NETLINK_CB(skb).pid, seq,
+					 AUDIT_TTY_GET, 0, 0, &s, sizeof(s));
 		break;
 	}
 	case AUDIT_TTY_SET: {
 		struct audit_tty_status *s;
 		struct task_struct *tsk;
+		unsigned long flags;
 
 		if (nlh->nlmsg_len < sizeof(struct audit_tty_status))
 			return -EINVAL;
 		s = data;
 		if (s->enabled != 0 && s->enabled != 1)
 			return -EINVAL;
-		read_lock(&tasklist_lock);
+		rcu_read_lock();
 		tsk = find_task_by_vpid(pid);
-		if (!tsk)
-			err = -ESRCH;
-		else {
-			spin_lock_irq(&tsk->sighand->siglock);
+		if (tsk && lock_task_sighand(tsk, &flags)) {
 			tsk->signal->audit_tty = s->enabled != 0;
-			spin_unlock_irq(&tsk->sighand->siglock);
-		}
-		read_unlock(&tasklist_lock);
+			unlock_task_sighand(tsk, &flags);
+		} else
+			err = -ESRCH;
+		rcu_read_unlock();
 		break;
 	}
 	default:
diff --git a/kernel/audit.h b/kernel/audit.h
index f7206db4e13d..91e7071c4d2c 100644
--- a/kernel/audit.h
+++ b/kernel/audit.h
@@ -84,10 +84,7 @@ extern int audit_compare_dname_path(const char *dname, const char *path,
 				    int *dirlen);
 extern struct sk_buff *	    audit_make_reply(int pid, int seq, int type,
 					     int done, int multi,
-					     void *payload, int size);
-extern void		    audit_send_reply(int pid, int seq, int type,
-					     int done, int multi,
-					     void *payload, int size);
+					     const void *payload, int size);
 extern void		    audit_panic(const char *message);
 
 struct audit_netlink_list {
diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c
index 7f18d3a4527e..37b2bea170c8 100644
--- a/kernel/audit_tree.c
+++ b/kernel/audit_tree.c
@@ -223,7 +223,7 @@ static void untag_chunk(struct node *p)
 {
 	struct audit_chunk *chunk = find_chunk(p);
 	struct fsnotify_mark *entry = &chunk->mark;
-	struct audit_chunk *new;
+	struct audit_chunk *new = NULL;
 	struct audit_tree *owner;
 	int size = chunk->count - 1;
 	int i, j;
@@ -232,9 +232,14 @@ static void untag_chunk(struct node *p)
 
 	spin_unlock(&hash_lock);
 
+	if (size)
+		new = alloc_chunk(size);
+
 	spin_lock(&entry->lock);
 	if (chunk->dead || !entry->i.inode) {
 		spin_unlock(&entry->lock);
+		if (new)
+			free_chunk(new);
 		goto out;
 	}
 
@@ -255,9 +260,9 @@ static void untag_chunk(struct node *p)
 		goto out;
 	}
 
-	new = alloc_chunk(size);
 	if (!new)
 		goto Fallback;
+
 	fsnotify_duplicate_mark(&new->mark, entry);
 	if (fsnotify_add_mark(&new->mark, new->mark.group, new->mark.i.inode, NULL, 1)) {
 		free_chunk(new);
diff --git a/kernel/audit_watch.c b/kernel/audit_watch.c
index f0c9b2e7542d..d2e3c7866460 100644
--- a/kernel/audit_watch.c
+++ b/kernel/audit_watch.c
@@ -60,7 +60,7 @@ struct audit_parent {
 };
 
 /* fsnotify handle. */
-struct fsnotify_group *audit_watch_group;
+static struct fsnotify_group *audit_watch_group;
 
 /* fsnotify events we care about. */
 #define AUDIT_FS_WATCH (FS_MOVE | FS_CREATE | FS_DELETE | FS_DELETE_SELF |\
@@ -123,7 +123,7 @@ void audit_put_watch(struct audit_watch *watch)
 	}
 }
 
-void audit_remove_watch(struct audit_watch *watch)
+static void audit_remove_watch(struct audit_watch *watch)
 {
 	list_del(&watch->wlist);
 	audit_put_parent(watch->parent);
diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c
index eb7675499fb5..add2819af71b 100644
--- a/kernel/auditfilter.c
+++ b/kernel/auditfilter.c
@@ -1252,6 +1252,18 @@ static int audit_filter_user_rules(struct netlink_skb_parms *cb,
 		case AUDIT_LOGINUID:
 			result = audit_comparator(cb->loginuid, f->op, f->val);
 			break;
+		case AUDIT_SUBJ_USER:
+		case AUDIT_SUBJ_ROLE:
+		case AUDIT_SUBJ_TYPE:
+		case AUDIT_SUBJ_SEN:
+		case AUDIT_SUBJ_CLR:
+			if (f->lsm_rule)
+				result = security_audit_rule_match(cb->sid,
+								   f->type,
+								   f->op,
+								   f->lsm_rule,
+								   NULL);
+			break;
 		}
 
 		if (!result)
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index 1b31c130d034..f49a0318c2ed 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -241,6 +241,10 @@ struct audit_context {
 			pid_t			pid;
 			struct audit_cap_data	cap;
 		} capset;
+		struct {
+			int			fd;
+			int			flags;
+		} mmap;
 	};
 	int fds[2];
 
@@ -1305,6 +1309,10 @@ static void show_special(struct audit_context *context, int *call_panic)
 		audit_log_cap(ab, "cap_pp", &context->capset.cap.permitted);
 		audit_log_cap(ab, "cap_pe", &context->capset.cap.effective);
 		break; }
+	case AUDIT_MMAP: {
+		audit_log_format(ab, "fd=%d flags=0x%x", context->mmap.fd,
+				 context->mmap.flags);
+		break; }
 	}
 	audit_log_end(ab);
 }
@@ -2476,6 +2484,14 @@ void __audit_log_capset(pid_t pid,
 	context->type = AUDIT_CAPSET;
 }
 
+void __audit_mmap_fd(int fd, int flags)
+{
+	struct audit_context *context = current->audit_context;
+	context->mmap.fd = fd;
+	context->mmap.flags = flags;
+	context->type = AUDIT_MMAP;
+}
+
 /**
  * audit_core_dumps - record information about processes that end abnormally
  * @signr: signal value
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 291ba3d04bea..66a416b42c18 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -52,7 +52,6 @@
 #include <linux/cgroupstats.h>
 #include <linux/hash.h>
 #include <linux/namei.h>
-#include <linux/smp_lock.h>
 #include <linux/pid_namespace.h>
 #include <linux/idr.h>
 #include <linux/vmalloc.h> /* TODO: replace with more sophisticated array */
@@ -244,6 +243,11 @@ static int notify_on_release(const struct cgroup *cgrp)
 	return test_bit(CGRP_NOTIFY_ON_RELEASE, &cgrp->flags);
 }
 
+static int clone_children(const struct cgroup *cgrp)
+{
+	return test_bit(CGRP_CLONE_CHILDREN, &cgrp->flags);
+}
+
 /*
  * for_each_subsys() allows you to iterate on each subsystem attached to
  * an active hierarchy
@@ -778,6 +782,7 @@ static struct inode *cgroup_new_inode(mode_t mode, struct super_block *sb)
 	struct inode *inode = new_inode(sb);
 
 	if (inode) {
+		inode->i_ino = get_next_ino();
 		inode->i_mode = mode;
 		inode->i_uid = current_fsuid();
 		inode->i_gid = current_fsgid();
@@ -1040,6 +1045,8 @@ static int cgroup_show_options(struct seq_file *seq, struct vfsmount *vfs)
 		seq_puts(seq, ",noprefix");
 	if (strlen(root->release_agent_path))
 		seq_printf(seq, ",release_agent=%s", root->release_agent_path);
+	if (clone_children(&root->top_cgroup))
+		seq_puts(seq, ",clone_children");
 	if (strlen(root->name))
 		seq_printf(seq, ",name=%s", root->name);
 	mutex_unlock(&cgroup_mutex);
@@ -1050,6 +1057,7 @@ struct cgroup_sb_opts {
 	unsigned long subsys_bits;
 	unsigned long flags;
 	char *release_agent;
+	bool clone_children;
 	char *name;
 	/* User explicitly requested empty subsystem */
 	bool none;
@@ -1066,7 +1074,8 @@ struct cgroup_sb_opts {
  */
 static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts)
 {
-	char *token, *o = data ?: "all";
+	char *token, *o = data;
+	bool all_ss = false, one_ss = false;
 	unsigned long mask = (unsigned long)-1;
 	int i;
 	bool module_pin_failed = false;
@@ -1082,22 +1091,27 @@ static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts)
 	while ((token = strsep(&o, ",")) != NULL) {
 		if (!*token)
 			return -EINVAL;
-		if (!strcmp(token, "all")) {
-			/* Add all non-disabled subsystems */
-			opts->subsys_bits = 0;
-			for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
-				struct cgroup_subsys *ss = subsys[i];
-				if (ss == NULL)
-					continue;
-				if (!ss->disabled)
-					opts->subsys_bits |= 1ul << i;
-			}
-		} else if (!strcmp(token, "none")) {
+		if (!strcmp(token, "none")) {
 			/* Explicitly have no subsystems */
 			opts->none = true;
-		} else if (!strcmp(token, "noprefix")) {
+			continue;
+		}
+		if (!strcmp(token, "all")) {
+			/* Mutually exclusive option 'all' + subsystem name */
+			if (one_ss)
+				return -EINVAL;
+			all_ss = true;
+			continue;
+		}
+		if (!strcmp(token, "noprefix")) {
 			set_bit(ROOT_NOPREFIX, &opts->flags);
-		} else if (!strncmp(token, "release_agent=", 14)) {
+			continue;
+		}
+		if (!strcmp(token, "clone_children")) {
+			opts->clone_children = true;
+			continue;
+		}
+		if (!strncmp(token, "release_agent=", 14)) {
 			/* Specifying two release agents is forbidden */
 			if (opts->release_agent)
 				return -EINVAL;
@@ -1105,7 +1119,9 @@ static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts)
 				kstrndup(token + 14, PATH_MAX - 1, GFP_KERNEL);
 			if (!opts->release_agent)
 				return -ENOMEM;
-		} else if (!strncmp(token, "name=", 5)) {
+			continue;
+		}
+		if (!strncmp(token, "name=", 5)) {
 			const char *name = token + 5;
 			/* Can't specify an empty name */
 			if (!strlen(name))
@@ -1127,20 +1143,44 @@ static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts)
 					      GFP_KERNEL);
 			if (!opts->name)
 				return -ENOMEM;
-		} else {
-			struct cgroup_subsys *ss;
-			for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
-				ss = subsys[i];
-				if (ss == NULL)
-					continue;
-				if (!strcmp(token, ss->name)) {
-					if (!ss->disabled)
-						set_bit(i, &opts->subsys_bits);
-					break;
-				}
-			}
-			if (i == CGROUP_SUBSYS_COUNT)
-				return -ENOENT;
+
+			continue;
+		}
+
+		for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
+			struct cgroup_subsys *ss = subsys[i];
+			if (ss == NULL)
+				continue;
+			if (strcmp(token, ss->name))
+				continue;
+			if (ss->disabled)
+				continue;
+
+			/* Mutually exclusive option 'all' + subsystem name */
+			if (all_ss)
+				return -EINVAL;
+			set_bit(i, &opts->subsys_bits);
+			one_ss = true;
+
+			break;
+		}
+		if (i == CGROUP_SUBSYS_COUNT)
+			return -ENOENT;
+	}
+
+	/*
+	 * If the 'all' option was specified select all the subsystems,
+	 * otherwise 'all, 'none' and a subsystem name options were not
+	 * specified, let's default to 'all'
+	 */
+	if (all_ss || (!all_ss && !one_ss && !opts->none)) {
+		for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
+			struct cgroup_subsys *ss = subsys[i];
+			if (ss == NULL)
+				continue;
+			if (ss->disabled)
+				continue;
+			set_bit(i, &opts->subsys_bits);
 		}
 	}
 
@@ -1222,7 +1262,6 @@ static int cgroup_remount(struct super_block *sb, int *flags, char *data)
 	struct cgroup *cgrp = &root->top_cgroup;
 	struct cgroup_sb_opts opts;
 
-	lock_kernel();
 	mutex_lock(&cgrp->dentry->d_inode->i_mutex);
 	mutex_lock(&cgroup_mutex);
 
@@ -1255,7 +1294,6 @@ static int cgroup_remount(struct super_block *sb, int *flags, char *data)
 	kfree(opts.name);
 	mutex_unlock(&cgroup_mutex);
 	mutex_unlock(&cgrp->dentry->d_inode->i_mutex);
-	unlock_kernel();
 	return ret;
 }
 
@@ -1357,6 +1395,8 @@ static struct cgroupfs_root *cgroup_root_from_opts(struct cgroup_sb_opts *opts)
 		strcpy(root->release_agent_path, opts->release_agent);
 	if (opts->name)
 		strcpy(root->name, opts->name);
+	if (opts->clone_children)
+		set_bit(CGRP_CLONE_CHILDREN, &root->top_cgroup.flags);
 	return root;
 }
 
@@ -1420,9 +1460,9 @@ static int cgroup_get_rootdir(struct super_block *sb)
 	return 0;
 }
 
-static int cgroup_get_sb(struct file_system_type *fs_type,
+static struct dentry *cgroup_mount(struct file_system_type *fs_type,
 			 int flags, const char *unused_dev_name,
-			 void *data, struct vfsmount *mnt)
+			 void *data)
 {
 	struct cgroup_sb_opts opts;
 	struct cgroupfs_root *root;
@@ -1556,10 +1596,9 @@ static int cgroup_get_sb(struct file_system_type *fs_type,
 		drop_parsed_module_refcounts(opts.subsys_bits);
 	}
 
-	simple_set_mnt(mnt, sb);
 	kfree(opts.release_agent);
 	kfree(opts.name);
-	return 0;
+	return dget(sb->s_root);
 
  drop_new_super:
 	deactivate_locked_super(sb);
@@ -1568,8 +1607,7 @@ static int cgroup_get_sb(struct file_system_type *fs_type,
  out_err:
 	kfree(opts.release_agent);
 	kfree(opts.name);
-
-	return ret;
+	return ERR_PTR(ret);
 }
 
 static void cgroup_kill_sb(struct super_block *sb) {
@@ -1619,7 +1657,7 @@ static void cgroup_kill_sb(struct super_block *sb) {
 
 static struct file_system_type cgroup_fs_type = {
 	.name = "cgroup",
-	.get_sb = cgroup_get_sb,
+	.mount = cgroup_mount,
 	.kill_sb = cgroup_kill_sb,
 };
 
@@ -1883,6 +1921,8 @@ static int cgroup_release_agent_write(struct cgroup *cgrp, struct cftype *cft,
 				      const char *buffer)
 {
 	BUILD_BUG_ON(sizeof(cgrp->root->release_agent_path) < PATH_MAX);
+	if (strlen(buffer) >= PATH_MAX)
+		return -EINVAL;
 	if (!cgroup_lock_live_group(cgrp))
 		return -ENODEV;
 	strcpy(cgrp->root->release_agent_path, buffer);
@@ -3176,6 +3216,23 @@ fail:
 	return ret;
 }
 
+static u64 cgroup_clone_children_read(struct cgroup *cgrp,
+				    struct cftype *cft)
+{
+	return clone_children(cgrp);
+}
+
+static int cgroup_clone_children_write(struct cgroup *cgrp,
+				     struct cftype *cft,
+				     u64 val)
+{
+	if (val)
+		set_bit(CGRP_CLONE_CHILDREN, &cgrp->flags);
+	else
+		clear_bit(CGRP_CLONE_CHILDREN, &cgrp->flags);
+	return 0;
+}
+
 /*
  * for the common functions, 'private' gives the type of file
  */
@@ -3206,6 +3263,11 @@ static struct cftype files[] = {
 		.write_string = cgroup_write_event_control,
 		.mode = S_IWUGO,
 	},
+	{
+		.name = "cgroup.clone_children",
+		.read_u64 = cgroup_clone_children_read,
+		.write_u64 = cgroup_clone_children_write,
+	},
 };
 
 static struct cftype cft_release_agent = {
@@ -3335,6 +3397,9 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
 	if (notify_on_release(parent))
 		set_bit(CGRP_NOTIFY_ON_RELEASE, &cgrp->flags);
 
+	if (clone_children(parent))
+		set_bit(CGRP_CLONE_CHILDREN, &cgrp->flags);
+
 	for_each_subsys(root, ss) {
 		struct cgroup_subsys_state *css = ss->create(ss, cgrp);
 
@@ -3349,6 +3414,8 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
 				goto err_destroy;
 		}
 		/* At error, ->destroy() callback has to free assigned ID. */
+		if (clone_children(parent) && ss->post_clone)
+			ss->post_clone(ss, cgrp);
 	}
 
 	cgroup_lock_hierarchy(root);
diff --git a/kernel/cgroup_freezer.c b/kernel/cgroup_freezer.c
index ce71ed53e88f..e7bebb7c6c38 100644
--- a/kernel/cgroup_freezer.c
+++ b/kernel/cgroup_freezer.c
@@ -48,20 +48,19 @@ static inline struct freezer *task_freezer(struct task_struct *task)
 			    struct freezer, css);
 }
 
-int cgroup_freezing_or_frozen(struct task_struct *task)
+static inline int __cgroup_freezing_or_frozen(struct task_struct *task)
 {
-	struct freezer *freezer;
-	enum freezer_state state;
+	enum freezer_state state = task_freezer(task)->state;
+	return (state == CGROUP_FREEZING) || (state == CGROUP_FROZEN);
+}
 
+int cgroup_freezing_or_frozen(struct task_struct *task)
+{
+	int result;
 	task_lock(task);
-	freezer = task_freezer(task);
-	if (!freezer->css.cgroup->parent)
-		state = CGROUP_THAWED; /* root cgroup can't be frozen */
-	else
-		state = freezer->state;
+	result = __cgroup_freezing_or_frozen(task);
 	task_unlock(task);
-
-	return (state == CGROUP_FREEZING) || (state == CGROUP_FROZEN);
+	return result;
 }
 
 /*
@@ -154,13 +153,6 @@ static void freezer_destroy(struct cgroup_subsys *ss,
 	kfree(cgroup_freezer(cgroup));
 }
 
-/* Task is frozen or will freeze immediately when next it gets woken */
-static bool is_task_frozen_enough(struct task_struct *task)
-{
-	return frozen(task) ||
-		(task_is_stopped_or_traced(task) && freezing(task));
-}
-
 /*
  * The call to cgroup_lock() in the freezer.state write method prevents
  * a write to that file racing against an attach, and hence the
@@ -174,24 +166,25 @@ static int freezer_can_attach(struct cgroup_subsys *ss,
 
 	/*
 	 * Anything frozen can't move or be moved to/from.
-	 *
-	 * Since orig_freezer->state == FROZEN means that @task has been
-	 * frozen, so it's sufficient to check the latter condition.
 	 */
 
-	if (is_task_frozen_enough(task))
+	freezer = cgroup_freezer(new_cgroup);
+	if (freezer->state != CGROUP_THAWED)
 		return -EBUSY;
 
-	freezer = cgroup_freezer(new_cgroup);
-	if (freezer->state == CGROUP_FROZEN)
+	rcu_read_lock();
+	if (__cgroup_freezing_or_frozen(task)) {
+		rcu_read_unlock();
 		return -EBUSY;
+	}
+	rcu_read_unlock();
 
 	if (threadgroup) {
 		struct task_struct *c;
 
 		rcu_read_lock();
 		list_for_each_entry_rcu(c, &task->thread_group, thread_group) {
-			if (is_task_frozen_enough(c)) {
+			if (__cgroup_freezing_or_frozen(c)) {
 				rcu_read_unlock();
 				return -EBUSY;
 			}
@@ -236,31 +229,30 @@ static void freezer_fork(struct cgroup_subsys *ss, struct task_struct *task)
 /*
  * caller must hold freezer->lock
  */
-static void update_freezer_state(struct cgroup *cgroup,
+static void update_if_frozen(struct cgroup *cgroup,
 				 struct freezer *freezer)
 {
 	struct cgroup_iter it;
 	struct task_struct *task;
 	unsigned int nfrozen = 0, ntotal = 0;
+	enum freezer_state old_state = freezer->state;