Merge branch 'linus' into sched/core

Merge reason: update to latest upstream

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

77 files changed, 2950 insertions, 789 deletions

diff --git a/kernel/Makefile b/kernel/Makefile
index 6aebdeb2aa3..a987aa1676b 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -10,7 +10,8 @@ obj-y     = sched.o fork.o exec_domain.o panic.o printk.o \
 	    kthread.o wait.o kfifo.o sys_ni.o posix-cpu-timers.o mutex.o \
 	    hrtimer.o rwsem.o nsproxy.o srcu.o semaphore.o \
 	    notifier.o ksysfs.o pm_qos_params.o sched_clock.o cred.o \
-	    async.o
+	    async.o range.o
+obj-$(CONFIG_HAVE_EARLY_RES) += early_res.o
 obj-y += groups.o
 
 ifdef CONFIG_FUNCTION_TRACER
@@ -90,6 +91,9 @@ obj-$(CONFIG_TASK_DELAY_ACCT) += delayacct.o
 obj-$(CONFIG_TASKSTATS) += taskstats.o tsacct.o
 obj-$(CONFIG_TRACEPOINTS) += tracepoint.o
 obj-$(CONFIG_LATENCYTOP) += latencytop.o
+obj-$(CONFIG_BINFMT_ELF) += elfcore.o
+obj-$(CONFIG_COMPAT_BINFMT_ELF) += elfcore.o
+obj-$(CONFIG_BINFMT_ELF_FDPIC) += elfcore.o
 obj-$(CONFIG_FUNCTION_TRACER) += trace/
 obj-$(CONFIG_TRACING) += trace/
 obj-$(CONFIG_X86_DS) += trace/
diff --git a/kernel/acct.c b/kernel/acct.c
index a6605ca921b..24f8c81fc48 100644
--- a/kernel/acct.c
+++ b/kernel/acct.c
@@ -588,16 +588,6 @@ out:
 }
 
 /**
- * acct_init_pacct - initialize a new pacct_struct
- * @pacct: per-process accounting info struct to initialize
- */
-void acct_init_pacct(struct pacct_struct *pacct)
-{
-	memset(pacct, 0, sizeof(struct pacct_struct));
-	pacct->ac_utime = pacct->ac_stime = cputime_zero;
-}
-
-/**
  * acct_collect - collect accounting information into pacct_struct
  * @exitcode: task exit code
  * @group_dead: not 0, if this thread is the last one in the process.
diff --git a/kernel/audit.c b/kernel/audit.c
index 5feed232be9..78f7f86aa23 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -398,7 +398,7 @@ static void kauditd_send_skb(struct sk_buff *skb)
 	skb_get(skb);
 	err = netlink_unicast(audit_sock, skb, audit_nlk_pid, 0);
 	if (err < 0) {
-		BUG_ON(err != -ECONNREFUSED); /* Shoudn't happen */
+		BUG_ON(err != -ECONNREFUSED); /* Shouldn't happen */
 		printk(KERN_ERR "audit: *NO* daemon at audit_pid=%d\n", audit_pid);
 		audit_log_lost("auditd dissapeared\n");
 		audit_pid = 0;
diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c
index 4b05bd9479d..028e85663f2 100644
--- a/kernel/audit_tree.c
+++ b/kernel/audit_tree.c
@@ -548,6 +548,11 @@ int audit_remove_tree_rule(struct audit_krule *rule)
 	return 0;
 }
 
+static int compare_root(struct vfsmount *mnt, void *arg)
+{
+	return mnt->mnt_root->d_inode == arg;
+}
+
 void audit_trim_trees(void)
 {
 	struct list_head cursor;
@@ -559,7 +564,6 @@ void audit_trim_trees(void)
 		struct path path;
 		struct vfsmount *root_mnt;
 		struct node *node;
-		struct list_head list;
 		int err;
 
 		tree = container_of(cursor.next, struct audit_tree, list);
@@ -577,24 +581,16 @@ void audit_trim_trees(void)
 		if (!root_mnt)
 			goto skip_it;
 
-		list_add_tail(&list, &root_mnt->mnt_list);
 		spin_lock(&hash_lock);
 		list_for_each_entry(node, &tree->chunks, list) {
-			struct audit_chunk *chunk = find_chunk(node);
-			struct inode *inode = chunk->watch.inode;
-			struct vfsmount *mnt;
+			struct inode *inode = find_chunk(node)->watch.inode;
 			node->index |= 1U<<31;
-			list_for_each_entry(mnt, &list, mnt_list) {
-				if (mnt->mnt_root->d_inode == inode) {
-					node->index &= ~(1U<<31);
-					break;
-				}
-			}
+			if (iterate_mounts(compare_root, inode, root_mnt))
+				node->index &= ~(1U<<31);
 		}
 		spin_unlock(&hash_lock);
 		trim_marked(tree);
 		put_tree(tree);
-		list_del_init(&list);
 		drop_collected_mounts(root_mnt);
 skip_it:
 		mutex_lock(&audit_filter_mutex);
@@ -603,22 +599,6 @@ skip_it:
 	mutex_unlock(&audit_filter_mutex);
 }
 
-static int is_under(struct vfsmount *mnt, struct dentry *dentry,
-		    struct path *path)
-{
-	if (mnt != path->mnt) {
-		for (;;) {
-			if (mnt->mnt_parent == mnt)
-				return 0;
-			if (mnt->mnt_parent == path->mnt)
-					break;
-			mnt = mnt->mnt_parent;
-		}
-		dentry = mnt->mnt_mountpoint;
-	}
-	return is_subdir(dentry, path->dentry);
-}
-
 int audit_make_tree(struct audit_krule *rule, char *pathname, u32 op)
 {
 
@@ -638,13 +618,17 @@ void audit_put_tree(struct audit_tree *tree)
 	put_tree(tree);
 }
 
+static int tag_mount(struct vfsmount *mnt, void *arg)
+{
+	return tag_chunk(mnt->mnt_root->d_inode, arg);
+}
+
 /* called with audit_filter_mutex */
 int audit_add_tree_rule(struct audit_krule *rule)
 {
 	struct audit_tree *seed = rule->tree, *tree;
 	struct path path;
-	struct vfsmount *mnt, *p;
-	struct list_head list;
+	struct vfsmount *mnt;
 	int err;
 
 	list_for_each_entry(tree, &tree_list, list) {
@@ -670,16 +654,9 @@ int audit_add_tree_rule(struct audit_krule *rule)
 		err = -ENOMEM;
 		goto Err;
 	}
-	list_add_tail(&list, &mnt->mnt_list);
 
 	get_tree(tree);
-	list_for_each_entry(p, &list, mnt_list) {
-		err = tag_chunk(p->mnt_root->d_inode, tree);
-		if (err)
-			break;
-	}
-
-	list_del(&list);
+	err = iterate_mounts(tag_mount, tree, mnt);
 	drop_collected_mounts(mnt);
 
 	if (!err) {
@@ -714,31 +691,23 @@ int audit_tag_tree(char *old, char *new)
 {
 	struct list_head cursor, barrier;
 	int failed = 0;
-	struct path path;
+	struct path path1, path2;
 	struct vfsmount *tagged;
-	struct list_head list;
-	struct vfsmount *mnt;
-	struct dentry *dentry;
 	int err;
 
-	err = kern_path(new, 0, &path);
+	err = kern_path(new, 0, &path2);
 	if (err)
 		return err;
-	tagged = collect_mounts(&path);
-	path_put(&path);
+	tagged = collect_mounts(&path2);
+	path_put(&path2);
 	if (!tagged)
 		return -ENOMEM;
 
-	err = kern_path(old, 0, &path);
+	err = kern_path(old, 0, &path1);
 	if (err) {
 		drop_collected_mounts(tagged);
 		return err;
 	}
-	mnt = mntget(path.mnt);
-	dentry = dget(path.dentry);
-	path_put(&path);
-
-	list_add_tail(&list, &tagged->mnt_list);
 
 	mutex_lock(&audit_filter_mutex);
 	list_add(&barrier, &tree_list);
@@ -746,7 +715,7 @@ int audit_tag_tree(char *old, char *new)
 
 	while (cursor.next != &tree_list) {
 		struct audit_tree *tree;
-		struct vfsmount *p;
+		int good_one = 0;
 
 		tree = container_of(cursor.next, struct audit_tree, list);
 		get_tree(tree);
@@ -754,30 +723,19 @@ int audit_tag_tree(char *old, char *new)
 		list_add(&cursor, &tree->list);
 		mutex_unlock(&audit_filter_mutex);
 
-		err = kern_path(tree->pathname, 0, &path);
-		if (err) {
-			put_tree(tree);
-			mutex_lock(&audit_filter_mutex);
-			continue;
+		err = kern_path(tree->pathname, 0, &path2);
+		if (!err) {
+			good_one = path_is_under(&path1, &path2);
+			path_put(&path2);
 		}
 
-		spin_lock(&vfsmount_lock);
-		if (!is_under(mnt, dentry, &path)) {
-			spin_unlock(&vfsmount_lock);
-			path_put(&path);
+		if (!good_one) {
 			put_tree(tree);
 			mutex_lock(&audit_filter_mutex);
 			continue;
 		}
-		spin_unlock(&vfsmount_lock);
-		path_put(&path);
-
-		list_for_each_entry(p, &list, mnt_list) {
-			failed = tag_chunk(p->mnt_root->d_inode, tree);
-			if (failed)
-				break;
-		}
 
+		failed = iterate_mounts(tag_mount, tree, tagged);
 		if (failed) {
 			put_tree(tree);
 			mutex_lock(&audit_filter_mutex);
@@ -818,10 +776,8 @@ int audit_tag_tree(char *old, char *new)
 	}
 	list_del(&barrier);
 	list_del(&cursor);
-	list_del(&list);
 	mutex_unlock(&audit_filter_mutex);
-	dput(dentry);
-	mntput(mnt);
+	path_put(&path1);
 	drop_collected_mounts(tagged);
 	return failed;
 }
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index fc0f928167e..f3a461c0970 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -1988,7 +1988,6 @@ void __audit_inode(const char *name, const struct dentry *dentry)
 
 /**
  * audit_inode_child - collect inode info for created/removed objects
- * @dname: inode's dentry name
  * @dentry: dentry being audited
  * @parent: inode of dentry parent
  *
@@ -2000,13 +1999,14 @@ void __audit_inode(const char *name, const struct dentry *dentry)
  * must be hooked prior, in order to capture the target inode during
  * unsuccessful attempts.
  */
-void __audit_inode_child(const char *dname, const struct dentry *dentry,
+void __audit_inode_child(const struct dentry *dentry,
 			 const struct inode *parent)
 {
 	int idx;
 	struct audit_context *context = current->audit_context;
 	const char *found_parent = NULL, *found_child = NULL;
 	const struct inode *inode = dentry->d_inode;
+	const char *dname = dentry->d_name.name;
 	int dirlen = 0;
 
 	if (!context->in_syscall)
@@ -2014,9 +2014,6 @@ void __audit_inode_child(const char *dname, const struct dentry *dentry,
 
 	if (inode)
 		handle_one(inode);
-	/* determine matching parent */
-	if (!dname)
-		goto add_names;
 
 	/* parent is more likely, look for it first */
 	for (idx = 0; idx < context->name_count; idx++) {
diff --git a/kernel/capability.c b/kernel/capability.c
index 7f876e60521..9e4697e9b27 100644
--- a/kernel/capability.c
+++ b/kernel/capability.c
@@ -135,7 +135,7 @@ static inline int cap_get_target_pid(pid_t pid, kernel_cap_t *pEp,
 	if (pid && (pid != task_pid_vnr(current))) {
 		struct task_struct *target;
 
-		read_lock(&tasklist_lock);
+		rcu_read_lock();
 
 		target = find_task_by_vpid(pid);
 		if (!target)
@@ -143,7 +143,7 @@ static inline int cap_get_target_pid(pid_t pid, kernel_cap_t *pEp,
 		else
 			ret = security_capget(target, pEp, pIp, pPp);
 
-		read_unlock(&tasklist_lock);
+		rcu_read_unlock();
 	} else
 		ret = security_capget(current, pEp, pIp, pPp);
 
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 4fd90e12977..e2769e13980 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -4,6 +4,10 @@
  *  Based originally on the cpuset system, extracted by Paul Menage
  *  Copyright (C) 2006 Google, Inc
  *
+ *  Notifications support
+ *  Copyright (C) 2009 Nokia Corporation
+ *  Author: Kirill A. Shutemov
+ *
  *  Copyright notices from the original cpuset code:
  *  --------------------------------------------------
  *  Copyright (C) 2003 BULL SA.
@@ -23,7 +27,6 @@
  */
 
 #include <linux/cgroup.h>
-#include <linux/module.h>
 #include <linux/ctype.h>
 #include <linux/errno.h>
 #include <linux/fs.h>
@@ -44,6 +47,7 @@
 #include <linux/string.h>
 #include <linux/sort.h>
 #include <linux/kmod.h>
+#include <linux/module.h>
 #include <linux/delayacct.h>
 #include <linux/cgroupstats.h>
 #include <linux/hash.h>
@@ -52,15 +56,21 @@
 #include <linux/pid_namespace.h>
 #include <linux/idr.h>
 #include <linux/vmalloc.h> /* TODO: replace with more sophisticated array */
+#include <linux/eventfd.h>
+#include <linux/poll.h>
 
 #include <asm/atomic.h>
 
 static DEFINE_MUTEX(cgroup_mutex);
 
-/* Generate an array of cgroup subsystem pointers */
+/*
+ * Generate an array of cgroup subsystem pointers. At boot time, this is
+ * populated up to CGROUP_BUILTIN_SUBSYS_COUNT, and modular subsystems are
+ * registered after that. The mutable section of this array is protected by
+ * cgroup_mutex.
+ */
 #define SUBSYS(_x) &_x ## _subsys,
-
-static struct cgroup_subsys *subsys[] = {
+static struct cgroup_subsys *subsys[CGROUP_SUBSYS_COUNT] = {
 #include <linux/cgroup_subsys.h>
 };
 
@@ -147,6 +157,35 @@ struct css_id {
 	unsigned short stack[0]; /* Array of Length (depth+1) */
 };
 
+/*
+ * cgroup_event represents events which userspace want to recieve.
+ */
+struct cgroup_event {
+	/*
+	 * Cgroup which the event belongs to.
+	 */
+	struct cgroup *cgrp;
+	/*
+	 * Control file which the event associated.
+	 */
+	struct cftype *cft;
+	/*
+	 * eventfd to signal userspace about the event.
+	 */
+	struct eventfd_ctx *eventfd;
+	/*
+	 * Each of these stored in a list by the cgroup.
+	 */
+	struct list_head list;
+	/*
+	 * All fields below needed to unregister event when
+	 * userspace closes eventfd.
+	 */
+	poll_table pt;
+	wait_queue_head_t *wqh;
+	wait_queue_t wait;
+	struct work_struct remove;
+};
 
 /* The list of hierarchy roots */
 
@@ -250,7 +289,8 @@ struct cg_cgroup_link {
 static struct css_set init_css_set;
 static struct cg_cgroup_link init_css_set_link;
 
-static int cgroup_subsys_init_idr(struct cgroup_subsys *ss);
+static int cgroup_init_idr(struct cgroup_subsys *ss,
+			   struct cgroup_subsys_state *css);
 
 /* css_set_lock protects the list of css_set objects, and the
  * chain of tasks off each css_set.  Nests outside task->alloc_lock
@@ -448,8 +488,11 @@ static struct css_set *find_existing_css_set(
 	struct hlist_node *node;
 	struct css_set *cg;
 
-	/* Built the set of subsystem state objects that we want to
-	 * see in the new css_set */
+	/*
+	 * Build the set of subsystem state objects that we want to see in the
+	 * new css_set. while subsystems can change globally, the entries here
+	 * won't change, so no need for locking.
+	 */
 	for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
 		if (root->subsys_bits & (1UL << i)) {
 			/* Subsystem is in this hierarchy. So we want
@@ -696,6 +739,7 @@ void cgroup_lock(void)
 {
 	mutex_lock(&cgroup_mutex);
 }
+EXPORT_SYMBOL_GPL(cgroup_lock);
 
 /**
  * cgroup_unlock - release lock on cgroup changes
@@ -706,6 +750,7 @@ void cgroup_unlock(void)
 {
 	mutex_unlock(&cgroup_mutex);
 }
+EXPORT_SYMBOL_GPL(cgroup_unlock);
 
 /*
  * A couple of forward declarations required, due to cyclic reference loop:
@@ -757,6 +802,7 @@ static int cgroup_call_pre_destroy(struct cgroup *cgrp)
 			if (ret)
 				break;
 		}
+
 	return ret;
 }
 
@@ -884,7 +930,11 @@ void cgroup_release_and_wakeup_rmdir(struct cgroup_subsys_state *css)
 	css_put(css);
 }
 
-
+/*
+ * Call with cgroup_mutex held. Drops reference counts on modules, including
+ * any duplicate ones that parse_cgroupfs_options took. If this function
+ * returns an error, no reference counts are touched.
+ */
 static int rebind_subsystems(struct cgroupfs_root *root,
 			      unsigned long final_bits)
 {
@@ -892,6 +942,8 @@ static int rebind_subsystems(struct cgroupfs_root *root,
 	struct cgroup *cgrp = &root->top_cgroup;
 	int i;
 
+	BUG_ON(!mutex_is_locked(&cgroup_mutex));
+
 	removed_bits = root->actual_subsys_bits & ~final_bits;
 	added_bits = final_bits & ~root->actual_subsys_bits;
 	/* Check that any added subsystems are currently free */
@@ -900,6 +952,12 @@ static int rebind_subsystems(struct cgroupfs_root *root,
 		struct cgroup_subsys *ss = subsys[i];
 		if (!(bit & added_bits))
 			continue;
+		/*
+		 * Nobody should tell us to do a subsys that doesn't exist:
+		 * parse_cgroupfs_options should catch that case and refcounts
+		 * ensure that subsystems won't disappear once selected.
+		 */
+		BUG_ON(ss == NULL);
 		if (ss->root != &rootnode) {
 			/* Subsystem isn't free */
 			return -EBUSY;
@@ -919,6 +977,7 @@ static int rebind_subsystems(struct cgroupfs_root *root,
 		unsigned long bit = 1UL << i;
 		if (bit & added_bits) {
 			/* We're binding this subsystem to this hierarchy */
+			BUG_ON(ss == NULL);
 			BUG_ON(cgrp->subsys[i]);
 			BUG_ON(!dummytop->subsys[i]);
 			BUG_ON(dummytop->subsys[i]->cgroup != dummytop);
@@ -930,8 +989,10 @@ static int rebind_subsystems(struct cgroupfs_root *root,
 			if (ss->bind)
 				ss->bind(ss, cgrp);
 			mutex_unlock(&ss->hierarchy_mutex);
+			/* refcount was already take