24 files changed, 1362 insertions, 668 deletions

diff --git a/kernel/Makefile b/kernel/Makefile
index 187c89b4783d..b8d4cd8ac0b9 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -58,7 +58,6 @@ obj-$(CONFIG_KEXEC) += kexec.o
 obj-$(CONFIG_BACKTRACE_SELF_TEST) += backtracetest.o
 obj-$(CONFIG_COMPAT) += compat.o
 obj-$(CONFIG_CGROUPS) += cgroup.o
-obj-$(CONFIG_CGROUP_DEBUG) += cgroup_debug.o
 obj-$(CONFIG_CGROUP_FREEZER) += cgroup_freezer.o
 obj-$(CONFIG_CPUSETS) += cpuset.o
 obj-$(CONFIG_CGROUP_NS) += ns_cgroup.o
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index cd83d9933b6b..7ccba4bc5e3b 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -23,6 +23,7 @@
  */
 
 #include <linux/cgroup.h>
+#include <linux/ctype.h>
 #include <linux/errno.h>
 #include <linux/fs.h>
 #include <linux/kernel.h>
@@ -48,6 +49,8 @@
 #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 */
 
 #include <asm/atomic.h>
 
@@ -60,6 +63,8 @@ static struct cgroup_subsys *subsys[] = {
 #include <linux/cgroup_subsys.h>
 };
 
+#define MAX_CGROUP_ROOT_NAMELEN 64
+
 /*
  * A cgroupfs_root represents the root of a cgroup hierarchy,
  * and may be associated with a superblock to form an active
@@ -74,6 +79,9 @@ struct cgroupfs_root {
          */
         unsigned long subsys_bits;
 
+        /* Unique id for this hierarchy. */
+        int hierarchy_id;
+
         /* The bitmask of subsystems currently attached to this hierarchy */
         unsigned long actual_subsys_bits;
 
@@ -94,6 +102,9 @@ struct cgroupfs_root {
 
         /* The path to use for release notifications. */
         char release_agent_path[PATH_MAX];
+
+        /* The name for this hierarchy - may be empty */
+        char name[MAX_CGROUP_ROOT_NAMELEN];
 };
 
 /*
@@ -141,6 +152,10 @@ struct css_id {
 static LIST_HEAD(roots);
 static int root_count;
 
+static DEFINE_IDA(hierarchy_ida);
+static int next_hierarchy_id;
+static DEFINE_SPINLOCK(hierarchy_id_lock);
+
 /* dummytop is a shorthand for the dummy hierarchy's top cgroup */
 #define dummytop (&rootnode.top_cgroup)
 
@@ -201,6 +216,7 @@ struct cg_cgroup_link {
          * cgroup, anchored on cgroup->css_sets
          */
         struct list_head cgrp_link_list;
+        struct cgroup *cgrp;
         /*
          * List running through cg_cgroup_links pointing at a
          * single css_set object, anchored on css_set->cg_links
@@ -227,8 +243,11 @@ static int cgroup_subsys_init_idr(struct cgroup_subsys *ss);
 static DEFINE_RWLOCK(css_set_lock);
 static int css_set_count;
 
-/* hash table for cgroup groups. This improves the performance to
- * find an existing css_set */
+/*
+ * hash table for cgroup groups. This improves the performance to find
+ * an existing css_set. This hash doesn't (currently) take into
+ * account cgroups in empty hierarchies.
+ */
 #define CSS_SET_HASH_BITS       7
 #define CSS_SET_TABLE_SIZE      (1 << CSS_SET_HASH_BITS)
 static struct hlist_head css_set_table[CSS_SET_TABLE_SIZE];
@@ -248,48 +267,22 @@ static struct hlist_head *css_set_hash(struct cgroup_subsys_state *css[])
         return &css_set_table[index];
 }
 
+static void free_css_set_rcu(struct rcu_head *obj)
+{
+        struct css_set *cg = container_of(obj, struct css_set, rcu_head);
+        kfree(cg);
+}
+
 /* We don't maintain the lists running through each css_set to its
  * task until after the first call to cgroup_iter_start(). This
  * reduces the fork()/exit() overhead for people who have cgroups
  * compiled into their kernel but not actually in use */
 static int use_task_css_set_links __read_mostly;
 
-/* When we create or destroy a css_set, the operation simply
- * takes/releases a reference count on all the cgroups referenced
- * by subsystems in this css_set. This can end up multiple-counting
- * some cgroups, but that's OK - the ref-count is just a
- * busy/not-busy indicator; ensuring that we only count each cgroup
- * once would require taking a global lock to ensure that no
- * subsystems moved between hierarchies while we were doing so.
- *
- * Possible TODO: decide at boot time based on the number of
- * registered subsystems and the number of CPUs or NUMA nodes whether
- * it's better for performance to ref-count every subsystem, or to
- * take a global lock and only add one ref count to each hierarchy.
- */
-
-/*
- * unlink a css_set from the list and free it
- */
-static void unlink_css_set(struct css_set *cg)
+static void __put_css_set(struct css_set *cg, int taskexit)
 {
         struct cg_cgroup_link *link;
         struct cg_cgroup_link *saved_link;
-
-        hlist_del(&cg->hlist);
-        css_set_count--;
-
-        list_for_each_entry_safe(link, saved_link, &cg->cg_links,
-                                 cg_link_list) {
-                list_del(&link->cg_link_list);
-                list_del(&link->cgrp_link_list);
-                kfree(link);
-        }
-}
-
-static void __put_css_set(struct css_set *cg, int taskexit)
-{
-        int i;
         /*
          * Ensure that the refcount doesn't hit zero while any readers
          * can see it. Similar to atomic_dec_and_lock(), but for an
@@ -302,21 +295,28 @@ static void __put_css_set(struct css_set *cg, int taskexit)
                 write_unlock(&css_set_lock);
                 return;
         }
-        unlink_css_set(cg);
-        write_unlock(&css_set_lock);
 
-        rcu_read_lock();
-        for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
-                struct cgroup *cgrp = rcu_dereference(cg->subsys[i]->cgroup);
+        /* This css_set is dead. unlink it and release cgroup refcounts */
+        hlist_del(&cg->hlist);
+        css_set_count--;
+
+        list_for_each_entry_safe(link, saved_link, &cg->cg_links,
+                                 cg_link_list) {
+                struct cgroup *cgrp = link->cgrp;
+                list_del(&link->cg_link_list);
+                list_del(&link->cgrp_link_list);
                 if (atomic_dec_and_test(&cgrp->count) &&
                     notify_on_release(cgrp)) {
                         if (taskexit)
                                 set_bit(CGRP_RELEASABLE, &cgrp->flags);
                         check_for_release(cgrp);
                 }
+
+                kfree(link);
         }
-        rcu_read_unlock();
-        kfree(cg);
+
+        write_unlock(&css_set_lock);
+        call_rcu(&cg->rcu_head, free_css_set_rcu);
 }
 
 /*
@@ -338,6 +338,78 @@ static inline void put_css_set_taskexit(struct css_set *cg)
 }
 
 /*
+ * compare_css_sets - helper function for find_existing_css_set().
+ * @cg: candidate css_set being tested
+ * @old_cg: existing css_set for a task
+ * @new_cgrp: cgroup that's being entered by the task
+ * @template: desired set of css pointers in css_set (pre-calculated)
+ *
+ * Returns true if "cg" matches "old_cg" except for the hierarchy
+ * which "new_cgrp" belongs to, for which it should match "new_cgrp".
+ */
+static bool compare_css_sets(struct css_set *cg,
+                             struct css_set *old_cg,
+                             struct cgroup *new_cgrp,
+                             struct cgroup_subsys_state *template[])
+{
+        struct list_head *l1, *l2;
+
+        if (memcmp(template, cg->subsys, sizeof(cg->subsys))) {
+                /* Not all subsystems matched */
+                return false;
+        }
+
+        /*
+         * Compare cgroup pointers in order to distinguish between
+         * different cgroups in heirarchies with no subsystems. We
+         * could get by with just this check alone (and skip the
+         * memcmp above) but on most setups the memcmp check will
+         * avoid the need for this more expensive check on almost all
+         * candidates.
+         */
+
+        l1 = &cg->cg_links;
+        l2 = &old_cg->cg_links;
+        while (1) {
+                struct cg_cgroup_link *cgl1, *cgl2;
+                struct cgroup *cg1, *cg2;
+
+                l1 = l1->next;
+                l2 = l2->next;
+                /* See if we reached the end - both lists are equal length. */
+                if (l1 == &cg->cg_links) {
+                        BUG_ON(l2 != &old_cg->cg_links);
+                        break;
+                } else {
+                        BUG_ON(l2 == &old_cg->cg_links);
+                }
+                /* Locate the cgroups associated with these links. */
+                cgl1 = list_entry(l1, struct cg_cgroup_link, cg_link_list);
+                cgl2 = list_entry(l2, struct cg_cgroup_link, cg_link_list);
+                cg1 = cgl1->cgrp;
+                cg2 = cgl2->cgrp;
+                /* Hierarchies should be linked in the same order. */
+                BUG_ON(cg1->root != cg2->root);
+
+                /*
+                 * If this hierarchy is the hierarchy of the cgroup
+                 * that's changing, then we need to check that this
+                 * css_set points to the new cgroup; if it's any other
+                 * hierarchy, then this css_set should point to the
+                 * same cgroup as the old css_set.
+                 */
+                if (cg1->root == new_cgrp->root) {
+                        if (cg1 != new_cgrp)
+                                return false;
+                } else {
+                        if (cg1 != cg2)
+                                return false;
+                }
+        }
+        return true;
+}
+
+/*
  * find_existing_css_set() is a helper for
  * find_css_set(), and checks to see whether an existing
  * css_set is suitable.
@@ -378,10 +450,11 @@ static struct css_set *find_existing_css_set(
 
         hhead = css_set_hash(template);
         hlist_for_each_entry(cg, node, hhead, hlist) {
-                if (!memcmp(template, cg->subsys, sizeof(cg->subsys))) {
-                        /* All subsystems matched */
-                        return cg;
-                }
+                if (!compare_css_sets(cg, oldcg, cgrp, template))
+                        continue;
+
+                /* This css_set matches what we need */
+                return cg;
         }
 
         /* No existing cgroup group matched */
@@ -435,8 +508,14 @@ static void link_css_set(struct list_head *tmp_cg_links,
         link = list_first_entry(tmp_cg_links, struct cg_cgroup_link,
                                 cgrp_link_list);
         link->cg = cg;
+        link->cgrp = cgrp;
+        atomic_inc(&cgrp->count);
         list_move(&link->cgrp_link_list, &cgrp->css_sets);
-        list_add(&link->cg_link_list, &cg->cg_links);
+        /*
+         * Always add links to the tail of the list so that the list
+         * is sorted by order of hierarchy creation
+         */
+        list_add_tail(&link->cg_link_list, &cg->cg_links);
 }
 
 /*
@@ -451,11 +530,11 @@ static struct css_set *find_css_set(
 {
         struct css_set *res;
         struct cgroup_subsys_state *template[CGROUP_SUBSYS_COUNT];
-        int i;
 
         struct list_head tmp_cg_links;
 
         struct hlist_head *hhead;
+        struct cg_cgroup_link *link;
 
         /* First see if we already have a cgroup group that matches
          * the desired set */
@@ -489,20 +568,12 @@ static struct css_set *find_css_set(
 
         write_lock(&css_set_lock);
         /* Add reference counts and links from the new css_set. */
-        for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
-                struct cgroup *cgrp = res->subsys[i]->cgroup;
-                struct cgroup_subsys *ss = subsys[i];
-                atomic_inc(&cgrp->count);
-                /*
-                 * We want to add a link once per cgroup, so we
-                 * only do it for the first subsystem in each
-                 * hierarchy
-                 */
-                if (ss->root->subsys_list.next == &ss->sibling)
-                        link_css_set(&tmp_cg_links, res, cgrp);
+        list_for_each_entry(link, &oldcg->cg_links, cg_link_list) {
+                struct cgroup *c = link->cgrp;
+                if (c->root == cgrp->root)
+                        c = cgrp;
+                link_css_set(&tmp_cg_links, res, c);
         }
-        if (list_empty(&rootnode.subsys_list))
-                link_css_set(&tmp_cg_links, res, dummytop);
 
         BUG_ON(!list_empty(&tmp_cg_links));
 
@@ -518,6 +589,41 @@ static struct css_set *find_css_set(
 }
 
 /*
+ * Return the cgroup for "task" from the given hierarchy. Must be
+ * called with cgroup_mutex held.
+ */
+static struct cgroup *task_cgroup_from_root(struct task_struct *task,
+                                            struct cgroupfs_root *root)
+{
+        struct css_set *css;
+        struct cgroup *res = NULL;
+
+        BUG_ON(!mutex_is_locked(&cgroup_mutex));
+        read_lock(&css_set_lock);
+        /*
+         * No need to lock the task - since we hold cgroup_mutex the
+         * task can't change groups, so the only thing that can happen
+         * is that it exits and its css is set back to init_css_set.
+         */
+        css = task->cgroups;
+        if (css == &init_css_set) {
+                res = &root->top_cgroup;
+        } else {
+                struct cg_cgroup_link *link;
+                list_for_each_entry(link, &css->cg_links, cg_link_list) {
+                        struct cgroup *c = link->cgrp;
+                        if (c->root == root) {
+                                res = c;
+                                break;
+                        }
+                }
+        }
+        read_unlock(&css_set_lock);
+        BUG_ON(!res);
+        return res;
+}
+
+/*
  * There is one global cgroup mutex. We also require taking
  * task_lock() when dereferencing a task's cgroup subsys pointers.
  * See "The task_lock() exception", at the end of this comment.
@@ -677,6 +783,12 @@ static void cgroup_diput(struct dentry *dentry, struct inode *inode)
                  */
                 deactivate_super(cgrp->root->sb);
 
+                /*
+                 * if we're getting rid of the cgroup, refcount should ensure
+                 * that there are no pidlists left.
+                 */
+                BUG_ON(!list_empty(&cgrp->pidlists));
+
                 call_rcu(&cgrp->rcu_head, free_cgroup_rcu);
         }
         iput(inode);
@@ -841,6 +953,8 @@ 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 (strlen(root->name))
+                seq_printf(seq, ",name=%s", root->name);
         mutex_unlock(&cgroup_mutex);
         return 0;
 }
@@ -849,6 +963,12 @@ struct cgroup_sb_opts {
         unsigned long subsys_bits;
         unsigned long flags;
         char *release_agent;
+        char *name;
+        /* User explicitly requested empty subsystem */
+        bool none;
+
+        struct cgroupfs_root *new_root;
+
 };
 
 /* Convert a hierarchy specifier into a bitmask of subsystems and
@@ -863,9 +983,7 @@ static int parse_cgroupfs_options(char *data,
         mask = ~(1UL << cpuset_subsys_id);
 #endif
 
-        opts->subsys_bits = 0;
-        opts->flags = 0;
-        opts->release_agent = NULL;
+        memset(opts, 0, sizeof(*opts));
 
         while ((token = strsep(&o, ",")) != NULL) {
                 if (!*token)
@@ -879,17 +997,42 @@ static int parse_cgroupfs_options(char *data,
                                 if (!ss->disabled)
                                         opts->subsys_bits |= 1ul << i;
                         }
+                } else if (!strcmp(token, "none")) {
+                        /* Explicitly have no subsystems */
+                        opts->none = true;
                 } else if (!strcmp(token, "noprefix")) {
                         set_bit(ROOT_NOPREFIX, &opts->flags);
                 } else if (!strncmp(token, "release_agent=", 14)) {
                         /* Specifying two release agents is forbidden */
                         if (opts->release_agent)
                                 return -EINVAL;
-                        opts->release_agent = kzalloc(PATH_MAX, GFP_KERNEL);
+                        opts->release_agent =
+                                kstrndup(token + 14, PATH_MAX, GFP_KERNEL);
                         if (!opts->release_agent)
                                 return -ENOMEM;
-                        strncpy(opts->release_agent, token + 14, PATH_MAX - 1);
-                        opts->release_agent[PATH_MAX - 1] = 0;
+                } else if (!strncmp(token, "name=", 5)) {
+                        int i;
+                        const char *name = token + 5;
+                        /* Can't specify an empty name */
+                        if (!strlen(name))
+                                return -EINVAL;
+                        /* Must match [\w.-]+ */
+                        for (i = 0; i < strlen(name); i++) {
+                                char c = name[i];
+                                if (isalnum(c))
+                                        continue;
+                                if ((c == '.') || (c == '-') || (c == '_'))
+                                        continue;
+                                return -EINVAL;
+                        }
+                        /* Specifying two names is forbidden */
+                        if (opts->name)
+                                return -EINVAL;
+                        opts->name = kstrndup(name,
+                                              MAX_CGROUP_ROOT_NAMELEN,
+                                              GFP_KERNEL);
+                        if (!opts->name)
+                                return -ENOMEM;
                 } else {
                         struct cgroup_subsys *ss;
                         int i;
@@ -906,6 +1049,8 @@ static int parse_cgroupfs_options(char *data,
                 }
         }
 
+        /* Consistency checks */
+
         /*
          * Option noprefix was introduced just for backward compatibility
          * with the old cpuset, so we allow noprefix only if mounting just
@@ -915,8 +1060,16 @@ static int parse_cgroupfs_options(char *data,
             (opts->subsys_bits & mask))
                 return -EINVAL;
 
-        /* We can't have an empty hierarchy */
-        if (!opts->subsys_bits)
+
+        /* Can't specify "none" and some subsystems */
+        if (opts->subsys_bits && opts->none)
+                return -EINVAL;
+
+        /*
+         * We either have to specify by name or by subsystems. (So all
+         * empty hierarchies must have a name).
+         */
+        if (!opts->subsys_bits && !opts->name)
                 return -EINVAL;
 
         return 0;
@@ -944,6 +1097,12 @@ static int cgroup_remount(struct super_block *sb, int *flags, char *data)
                 goto out_unlock;
         }
 
+        /* Don't allow name to change at remount */
+        if (opts.name && strcmp(opts.name, root->name)) {
+                ret = -EINVAL;
+                goto out_unlock;
+        }
+
         ret = rebind_subsystems(root, opts.subsys_bits);
         if (ret)
                 goto out_unlock;
@@ -955,6 +1114,7 @@ static int cgroup_remount(struct super_block *sb, int *flags, char *data)
                 strcpy(root->release_agent_path, opts.release_agent);
  out_unlock:
         kfree(opts.release_agent);
+        kfree(opts.name);
         mutex_unlock(&cgroup_mutex);
         mutex_unlock(&cgrp->dentry->d_inode->i_mutex);
         unlock_kernel();
@@ -974,9 +1134,10 @@ static void init_cgroup_housekeeping(struct cgroup *cgrp)
         INIT_LIST_HEAD(&cgrp->children);
         INIT_LIST_HEAD(&cgrp->css_sets);
         INIT_LIST_HEAD(&cgrp->release_list);
-        INIT_LIST_HEAD(&cgrp->pids_list);
-        init_rwsem(&cgrp->pids_mutex);
+        INIT_LIST_HEAD(&cgrp->pidlists);
+        mutex_init(&cgrp->pidlist_mutex);
 }
+
 static void init_cgroup_root(struct cgroupfs_root *root)
 {
         struct cgroup *cgrp = &root->top_cgroup;
@@ -988,33 +1149,106 @@ static void init_cgroup_root(struct cgroupfs_root *root)
         init_cgroup_housekeeping(cgrp);
 }
 
+static bool init_root_id(struct cgroupfs_root *root)
+{
+        int ret = 0;
+
+        do {
+                if (!ida_pre_get(&hierarchy_ida, GFP_KERNEL))
+                        return false;
+                spin_lock(&hierarchy_id_lock);
+                /* Try to allocate the next unused ID */
+                ret = ida_get_new_above(&hierarchy_ida, next_hierarchy_id,
+                                        &root->hierarchy_id);
+                if (ret == -ENOSPC)
+                        /* Try again starting from 0 */
+                        ret = ida_get_new(&hierarchy_ida, &root->hierarchy_id);
+                if (!ret) {
+                        next_hierarchy_id = root->hierarchy_id + 1;
+                } else if (ret != -EAGAIN) {
+                        /* Can only get here if the 31-bit IDR is full ... */
+                        BUG_ON(ret);
+                }
+                spin_unlock(&hierarchy_id_lock);
+        } while (ret);
+        return true;
+}
+
 static int cgroup_test_super(struct super_block *sb, void *data)
 {
-        struct cgroupfs_root *new = data;
+        struct cgroup_sb_opts *opts = data;
         struct cgroupfs_root *root = sb->s_fs_info;
 
-        /* First check subsystems */
-        if (new->subsys_bits != root->subsys_bits)
-            return 0;
+        /* If we asked for a name then it must match */
+        if (opts->name && strcmp(opts->name, root->name))
+                return 0;
 
-        /* Next check flags */
-        if (new->flags != root->flags)
+        /*
+         * If we asked for subsystems (or explicitly for no
+         * subsystems) then they must match
+         */
+        if ((opts->subsys_bits || opts->none)
+            && (opts->subsys_bits != root->subsys_bits))
                 return 0;
 
         return 1;
 }
 
+static struct cgroupfs_root *cgroup_root_from_opts(struct cgroup_sb_opts *opts)
+{
+        struct cgroupfs_root *root;
+
+        if (!opts->subsys_bits && !opts->none)
+                return NULL;
+
+        root = kzalloc(sizeof(*root), GFP_KERNEL);
+        if (!root)
+                return ERR_PTR(-ENOMEM);
+
+        if (!init_root_id(root)) {
+                kfree(root);
+                return ERR_PTR(-ENOMEM);
+        }
+        init_cgroup_root(root);
+
+        root->subsys_bits = opts->subsys_bits;
+        root->flags = opts->flags;
+        if (opts->release_agent)
+                strcpy(root->release_agent_path, opts->release_agent);
+        if (opts->name)
+                strcpy(root->name, opts->name);
+        return root;
+}
+
+static void cgroup_drop_root(struct cgroupfs_root *root)
+{
+        if (!root)
+                return;
+
+        BUG_ON(!root->hierarchy_id);
+        spin_lock(&hierarchy_id_lock);
+        ida_remove(&hierarchy_ida, root->hierarchy_id);
+        spin_unlock(&hierarchy_id_lock);
+        kfree(root);
+}
+
 static int cgroup_set_super(struct super_block *sb, void *data)
 {
         int ret;
-        struct cgroupfs_root *root = data;
+        struct cgroup_sb_opts *opts = data;
+
+        /* If we don't have a new root, we can't set up a new sb */
+        if (!opts->new_root)
+                return -EINVAL;
+
+        BUG_ON(!opts->subsys_bits && !opts->none);
 
         ret = set_anon_super(sb, NULL);
         if (ret)
                 return ret;
 
-        sb->s_fs_info = root;
-        root->sb = sb;
+        sb->s_fs_info = opts->new_root;
+        opts->new_root->sb = sb;
 
         sb->s_blocksize = PAGE_CACHE_SIZE;
         sb->s_blocksize_bits = PAGE_CACHE_SHIFT;
@@ -1051,48 +1285,43 @@ static int cgroup_get_sb(struct file_system_type *fs_type,
                          void *data, struct vfsmount *mnt)
 {
         struct cgroup_sb_opts opts;
+        struct cgroupfs_root *root;
         int ret = 0;
         struct super_block *sb;
-        struct cgroupfs_root *root;
-        struct list_head tmp_cg_links;
+        struct cgroupfs_root *new_root;
 
         /* First find the desired set of subsystems */
         ret = parse_cgroupfs_options(data, &opts);
-        if (ret) {
-                kfree(opts.release_agent);
-                return ret;
-        }
-
-        root = kzalloc(sizeof(*root), GFP_KERNEL);
-        if (!root) {
-                kfree(opts.release_agent);
-                return -ENOMEM;
-        }
+        if (ret)
+                goto out_err;
 
-        init_cgroup_root(root);
-        root->subsys_bits = opts.subsys_bits;
-        root->flags = opts.flags;
-        if (opts.release_agent) {
-                strcpy(root->release_agent_path, opts.release_agent);
-                kfree(opts.release_agent);
+        /*
+         * Allocate a new cgroup root. We may not need it if we're
+         * reusing an existing hierarchy.
+         */
+        new_root = cgroup_root_from_opts(&opts);
+        if (IS_ERR(new_root)) {
+                ret = PTR_ERR(new_root);
+                goto out_err;
         }
+        opts.new_root = new_root;
 
-        sb = sget(fs_type, cgroup_test_super, cgroup_set_super, root);
-
+        /* Locate an existing or new sb for this hierarchy */
+        sb = sget(fs_type, cgroup_test_super, cgroup_set_super, &opts);
         if (IS_ERR(sb)) {
-                kfree(root);
-                return PTR_ERR(sb);
+                ret = PTR_ERR(sb);
+                cgroup_drop_root(opts.new_root);
+                goto out_err;
         }
 
-        if (sb->s_fs_info != root) {
-                /* Reusing an existing superblock */
-                BUG_ON(sb->s_root == NULL);
-                kfree(root);
-                root = NULL;
-        } else {
-                /* New superblock */
+        root = sb->s_fs_info;
+        BUG_ON(!root);
+        if (root == opts.new_root) {
+                /* We used the new root structure, so this is a new hierarchy */
+                struct list_head tmp_cg_links;
                 struct cgroup *root_cgrp = &root->top_cgroup;
                 struct inode *inode;
+                struct cgroupfs_root *existing_root;
                 int i;
 
                 BUG_ON(sb->s_root != NULL);
@@ -1105,6 +1334,18 @@ static int cgroup_get_sb(struct file_system_type *fs_type,
                 mutex_lock(&inode->i_mutex);
                 mutex_lock(&cgroup_mutex);
 
+                if (strlen(root->name)) {
+                        /* Check for name clashes with existing mounts */
+                        for_each_active_root(existing_root) {
+                                if (!strcmp(existing_root->name, root->name)) {
+                                        ret = -EBUSY;
+                                        mutex_unlock(&cgroup_mutex);
+                                        mutex_unlock(&inode->i_mutex);
+                                        goto drop_new_super;
+                                }
+                        }
+                }
+
                 /*
                  * We're accessing css_set_count without locking
                  * css_set_lock here, but that's OK - it can only be
@@ -1123,7 +1364,8 @@ static int cgroup_get_sb(struct file_system_type *fs_type,
                 if (ret == -EBUSY) {
                         mutex_unlock(&cgroup_mutex);
                         mutex_unlock(&inode->i_mutex);
-                        goto free_cg_links;
+                        free_cg_links(&tmp_cg_links);
+                        goto drop_new_super;
                 }
 
                 /* EBUSY should be the only error here */
@@ -1155,17 +1397,27 @@ static int cgroup_get_sb(struct file_system_type *fs_type,
                 BUG_ON(root->number_of_cgroups != 1);
 
                 cgroup_populate_dir(root_cgrp);
-                mutex_unlock(&inode->i_mutex);
                 mutex_unlock(&cgroup_mutex);
+                mutex_unlock(&inode->i_mutex);
+        } else {
+                /*
+                 * We re-used an existing hierarchy - the new root (if
+                 * any) is not needed
+                 */
+                cgroup_drop_root(opts.new_root);
         }
 
         simple_set_mnt(mnt, sb);
+        kfree(opts.release_agent);
+        kfree(opts.name);
         return 0;
 
- free_cg_links:
-        free_cg_links(&tmp_cg_links);
  drop_new_super:
         deactivate_locked_super(sb);
+ out_err:
+        kfree(opts.release_agent);
+        kfree(opts.name);
+
         return ret;
 }
 
@@ -1211,7 +1463,7 @@ static void cgroup_kill_sb(struct super_block *sb) {
         mutex_unlock(&cgroup_mutex);
 
         kill_litter_super(sb);
-        kfree(root);
+        cgroup_drop_root(root);
 }
 
 static struct file_system_type cgroup_fs_type = {
@@ -1276,27 +1528,6 @@ int cgroup_path(const struct cgroup *cgrp, char *buf, int buflen)
         return 0;
 }
 
-/*
- * Return the first subsystem attached to a cgroup's hierarchy, and
- * its subsystem id.
- */
-
-static void get_first_subsys(const struct cgroup *cgrp,
-                        struct cgroup_subsys_state **css, int *subsys_id)
-{
-        const struct cgroupfs_root *root = cgrp->root;
-        const struct cgroup_subsys *test_ss;
-        BUG_ON(list_empty(&root->subsys_list));
-        test_ss = list_entry(root->subsys_list.next,
-                             struct cgroup_subsys, sibling);
-        if (css) {
-                *css = cgrp->subsys[test_ss->subsys_id];
-                BUG_ON(!*css);
-        }
-        if (subsys_id)
-                *subsys_id = test_ss->subsys_id;
-}
-
 /**
  * cgroup_attach_task - attach task 'tsk' to cgroup 'cgrp'
  * @cgrp: the cgroup the task is attaching to
@@ -1313,18 +1544,15 @@ int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk)
         struct css_set *cg;
         struct css_set *newcg;
         struct cgroupfs_root *root = cgrp->root;
-        int subsys_id;
-
-        get_first_subsys(cgrp, NULL, &subsys_id);
 
         /* Nothing to do if the task is already in that cgroup */
-        oldcgrp = task_cgroup(tsk, subsys_id);
+        oldcgrp = task_cgroup_from_root(tsk, root);
         if (cgrp == oldcgrp)
                 return 0;
 
         for_each_subsys(root, ss) {
                 if (ss->can_attach) {
-                        retval = ss->can_attach(ss, cgrp, tsk);
+                        retval = ss->can_attach(ss, cgrp, tsk, false);
                         if (retval)
                                 return retval;
                 }
@@ -1362,7 +1590,7 @@ int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk)
 
         for_each_subsys(root, ss) {
                 if (ss->attach)
-                        ss->attach(ss, cgrp, oldcgrp, tsk);
+                        ss->attach(ss, cgrp, oldcgrp, tsk, false);
         }
         set_bit(CGRP_RELEASABLE, &oldcgrp->flags);
         synchronize_rcu();
@@ -1423,15 +1651,6 @@ static int cgroup_tasks_write(struct cgroup *cgrp, struct cftype *cft, u64 pid)
         return ret;
 }
 
-/* The various types of files and directories in a cgroup file system */
-enum cgroup_filetype {
-        FILE_ROOT,
-        FILE_DIR,
-        FILE_TASKLIST,
-        FILE_NOTIFY_ON_RELEASE,
-        FILE_RELEASE_AGENT,
-};
-
 /**
  * cgroup_lock_live_group - take cgroup_mutex and check that cgrp is alive.
  * @cgrp: the cgroup to be checked for liveness
@@ -1876,7 +2095,7 @@ int cgroup_task_count(const struct cgroup *cgrp)
  * the start of a css_set
  */
 static void cgroup_advance_iter(struct cgroup *cgrp,
-                                          struct cgroup_iter *it)
+                                struct cgroup_iter *it)
 {
         struct list_head *l = it->cg_link;
         struct cg_cgroup_link *link;
@@ -2129,7 +2348,7 @@ int cgroup_scan_tasks(struct cgroup_scanner *scan)
 }
 
 /*
- * Stuff for reading the 'tasks' file.
+ * Stuff for reading the 'tasks'/'procs' files.
  *
  * Reading this file can return large amounts of data if a cgroup has
  * *lots* of attached tasks. So it may need several calls to read(),
@@ -2139,27 +2358,196 @@ int cgroup_scan_tasks(struct cgroup_scanner *scan)
  */
 
 /*
- * Load into 'pidarray' up to 'npids' of the tasks using cgroup
- * 'cgrp'.  Return actual number of pids loaded.  No need to
- * task_lock(p) when reading out p->cgroup, since we're in an RCU
- * read section, so the css_set can't go away, and is
- * immutable after creation.
+ * The following two functions "fix" the issue where there are more pids
+ * than kmalloc will give memory for; in such cases, we use vmalloc/vfree.
+ * TODO: replace with a kernel-wide solution to this problem
+ */
+#define PIDLIST_TOO_LARGE(c) ((c) * sizeof(pid_t) > (PAGE_SIZE * 2))
+static void *pidlist_allocate(int count)
+{
+        if (PIDLIST_TOO_LARGE(count))
+                return vmalloc(count * sizeof(pid_t));
+        else
+                return kmalloc(count * sizeof(pid_t), GFP_KERNEL);
+}
+static void pidlist_free(void *p)
+{
+        if (is_vmalloc_addr(p))
+                vfree(p);
+        else
+                kfree(p);
+}
+static void *pidlist_resize(void *p, int newcount)
+{
+        void *newlist;
+        /* note: if new alloc fails, old p will still be valid either way */
+        if (is_vmalloc_addr(p)) {
+                newlist = vmalloc(newcount * sizeof(pid_t));
+                if (!newlist)
+                        return NULL;
+                memcpy(newlist, p, newcount * sizeof(pid_t));
+                vfree(p);
+        } else {
+                newlist = krealloc(p, newcount * sizeof(pid_t), GFP_KERNEL);
+        }
+        return newlist;
+}
+
+/*
+ * pidlist_uniq - given a kmalloc()ed list, strip out all duplicate entries
+ * If the new stripped list is sufficiently smaller and there's enough memory
+ * to allocate a new buffer, will let go of the unneeded memory. Returns the
+ * number of unique elements.
+ */
+/* is the size difference enough that we should re-allocate the array? */
+#define PIDLIST_REALLOC_DIFFERENCE(old, new) ((old) - PAGE_SIZE >= (new))
+static int pidlist_uniq(pid_t **p, int length)
+{
+        int src, dest = 1;
+        pid_t *list = *p;
+        pid_t *newlist;
+
+        /*
+         * we presume the 0th element is unique, so i starts at 1. trivial
+         * edge cases first; no work needs to be done for either
+         */
+        if (length == 0 || length == 1)
+                return length;
+        /* src and dest walk down the list; dest counts unique elements */
+        for (src = 1; src < length; src++) {
+                /* find next unique element */
+                while (list[src] == list[src-1]) {
+                        src++;
+                        if (src == length)
+                                goto after;
+                }
+                /* dest always points to where the next unique element goes */
+                list[dest] = list[src];
+                dest++;
+        }
+after:
+        /*
+         * if the length difference is large enough, we want to allocate a
+         * smaller buffer to save memory. if this fails due to out of memory,
+         * we'll just stay with what we've got.
+         */
+        if (PIDLIST_REALLOC_DIFFERENCE(length, dest)) {
+                newlist = pidlist_resize(list, dest);
+                if (newlist)
+                        *p = newlist;
+        }
+        return dest;
+}
+
+static int cmppid(const void *a, const void *b)
+{
+        return *(pid_t *)a - *(pid_t *)b;
+}
+
+/*
+ * find the appropriate pidlist for our purpose (given procs vs tasks)
+ * returns with the lock on that pidlist already held, and takes care
+ * of the use count, or returns NULL with no locks held if we're out of
+ * memory.
  */
-static int pid_array_load(pid_t *pidarray, int npids, struct cgroup *cgrp)
+static struct cgroup_pidlist *cgroup_pidlist_find(struct cgroup *cgrp,
+                                                  enum cgroup_filetype type)
 {
-        int n = 0, pid;
+        struct cgroup_pidlist *l;
+        /* don't need task_nsproxy() if we're looking at ourself */
+        struct pid_namespace *ns = get_pid_ns(current->nsproxy->pid_ns);
+        /*
+         * We can't drop the pidlist_mutex before taking the l->mutex in case
+         * the last ref-holder is trying to remove l from the list at the same
+         * time. Holding the pidlist_mutex precludes somebody taking whichever
+         * list we find out from under us - compare release_pid_array().
+         */
+        mutex_lock(&cgrp->pidlist_mutex);
+        list_for_each_entry(l, &cgrp->pidlists, links) {
+                if (l->key.type == type && l->key.ns == ns) {
+                        /* found a matching list - drop the extra refcount */
+                        put_pid_ns(ns);
+                        /* make sure l doesn't vanish out from under us */
+                        down_write(&l->mutex);
+                        mutex_unlock(&cgrp->pidlist_mutex);
+                        l->use_count++;
+                        return l;
+                }
+        }
+        /* entry not found; create a new one */
+        l = kmalloc(sizeof(struct cgroup_pidlist), GFP_KERNEL);
+        if (!l) {
+                mutex_unlock(&cgrp->pidlist_mutex);
+                put_pid_ns(ns);
+                return l;
+        }
+        init_rwsem(&l->mutex);
+        down_write(&l->mutex);
+        l->key.type = type;
+        l->key.ns = ns;
+        l->use_count = 0; /* don't increment here */
+        l->list = NULL;
+        l->owner = cgrp;
+        list_add(&l->links, &cgrp->pidlists);
+        mutex_unlock(&cgrp->pidlist_mutex);
+        return l;
+}
+
+/*
+ * Load a cgroup's pidarray with either procs' tgids or tasks' pids
+ */
+static int pidlist_array_load(struct cgroup *cgrp, enum cgroup_filetype type,
+                              struct cgroup_pidlist **lp)
+{
+        pid_t *array;
+        int length;
+        int pid, n = 0; /* used for populating the array */
         struct cgroup_iter it;
         struct task_struct *tsk;
+        struct cgroup_pidlist *l;
+
+        /*
+         * If cgroup gets more users after we read count, we won't have
+         * enough space - tough.  This race is indistinguishable to the
+         * caller from the case that the additional cgroup users didn't
+         * show up until sometime later on.
+         */
+        length = cgroup_task_count(cgrp);
+        array = pidlist_allocate(length);
+        if (!array)
+                return -ENOMEM;
+        /* now, populate the array */
         cgroup_iter_start(cgrp, &it);
         while ((tsk = cgroup_iter_next(cgrp, &it))) {
-                if (unlikely(n == npids))
+                if (unlikely(n == length))
                         break;
-                pid = task_pid_vnr(tsk);
-                if (pid > 0)
-                        pidarray[n++] = pid;
+                /* get tgid or pid for procs or tasks file respectively */
+                if (type == CGROUP_FILE_PROCS)
+                        pid = task_tgid_vnr(tsk);
+                else
+                        pid = task_pid_vnr(tsk);
+                if (pid > 0) /* make sure to only use valid results */
+                        array[n++] = pid;
         }
         cgroup_iter_end(cgrp, &it);
-        return n;
+        length = n;
+        /* now sort & (if procs) strip out duplicates */
+        sort(array, length, sizeof(pid_t), cmppid, NULL);
+        if (type == CGROUP_FILE_PROCS)
+                length = pidlist_uniq(&array, length);
+        l = cgroup_pidlist_find(cgrp, type);
+        if (!l) {
+                pidlist_free(array);
+                return -ENOMEM;
+        }
+        /* store array, freeing old if necessary - lock already held */
+        pidlist_free(l->list);
+        l->list = array;
+        l->length = length;
+        l->use_count++;
+        up_write(&l->mutex);
+        *lp = l;
+        return 0;
 }
 
 /**
@@ -2216,37 +2604,14 @@ err:
         return ret;
 }
 
-/*
- * Cache pids for all threads in the same pid namespace that are
- * opening the same "tasks" file.
- */
-struct cgroup_pids {
-        /* The node in cgrp->pids_list */
-        struct list_head list;
-        /* The cgroup those pids belong to */
-        struct cgroup *cgrp;
-        /* The namepsace those pids belong to */
-        struct pid_namespace *ns;
-        /* Array of process ids in the cgroup */
-        pid_t *tasks_pids;
-        /* How many files are using the this tasks_pids array */
-        int use_count;
-        /* Length of the current tasks_pids array */
-        int length;
-};
-
-static int cmppid(const void *a, const void *b)
-{
-        return *(pid_t *)a - *(pid_t *)b;
-}
 
 /*
- * seq_file methods for the "tasks" file. The seq_file position is the
+ * seq_file methods for the tasks/procs files. The seq_file position is the
  * next pid to display; the seq_file iterator is a pointer to the pid
- * in the cgroup->tasks_pids array.
+ * in the cgroup->l->list array.
  */
 
-static void *cgroup_tasks_start(struct seq_file *s, loff_t *pos)
+static void *cgroup_pidlist_start(struct seq_file *s, loff_t *pos)
 {
         /*
          * Initially we receive a position value that corresponds to
@@ -2254,48 +2619,45 @@ static void *cgroup_tasks_start(struct seq_file *s, loff_t *pos)
          * after a seek to the start). Use a binary-search to find the
          * next pid to display, if any
          */
-        struct cgroup_pids *cp = s->private;
-        struct cgroup *cgrp = cp->cgrp;
+        struct cgroup_pidlist *l = s->private;
         int index = 0, pid = *pos;
         int *iter;
 
-        down_read(&cgrp->pids_mutex);
+        down_read(&l->mutex);
         if (pid) {
-                int end = cp->length;
+                int end = l->length;
 
                 while (index < end) {
                         int mid = (index + end) / 2;
-                        if (cp->tasks_pids[mid] == pid) {
+                        if (l->list[mid] == pid) {
                                 index = mid;
                                 break;
-                        } else if (cp->tasks_pids[mid] <= pid)
+                        } else if (l->list[mid] <= pid)
                                 index = mid + 1;
                         else
                                 end = mid;
                 }
         }
         /* If we're off the end of the array, we're done */
-        if (index >= cp->length)
+        if (index >= l->length)
                 return NULL;
         /* Update the abstract position to be the actual pid that we found */
-        iter = cp->tasks_pids + index;
+        iter = l->list + index;
         *pos = *iter;
         return iter;
 }
 
-static void cgroup_tasks_stop(struct seq_file *s, void *v)
+static void cgroup_pidlist_stop(struct seq_file *s, void *v)
 {
-        struct cgroup_pids *cp = s->private;
-        struct cgroup *cgrp = cp->cgrp;
-        up_read(&cgrp->pids_mutex);
+        struct cgroup_pidlist *l = s->private;
+        up_read(&l->mutex);
 }
 
-static void *cgroup_tasks_next(struct seq_file *s, void *v, loff_t *pos)
+static void *cgroup_pidlist_next(struct seq_file *s, void *v, loff_t *pos)
 {
-        struct cgroup_pids *cp = s->private;
-        int *p = v;
-        int *end = cp->tasks_pids + cp->length;
-
+        struct cgroup_pidlist *l = s->private;
+        pid_t *p = v;
+        pid_t *end = l->list + l->length;
         /*
          * Advance to the next pid in the array. If this goes off the
          * end, we're done
@@ -2309,124 +2671,107 @@ static void *cgroup_tasks_next(struct seq_file *s, void *v, loff_t *pos)
         }
 }
 
-static int cgroup_tasks_show(struct seq_file *s, void *v)
+static int cgroup_pidlist_show(struct seq_file *s, void *v)
 {
         return seq_printf(s, "%d\n", *(int *)v);
 }
 
-static const struct seq_operations cgroup_tasks_seq_operations = {
-        .start = cgroup_tasks_start,
-        .stop = cgroup_tasks_stop,
-        .next = cgroup_tasks_next,
-        .show = cgroup_tasks_show,
+/*
+ * seq_operations functions for iterating on pidlists through seq_file -
+ * independent of whether it's tasks or procs
+ */
+static const struct seq_operations cgroup_pidlist_seq_operations = {
+        .start = cgroup_pidlist_start,
+        .stop = cgroup_pidlist_stop,
+        .next = cgroup_pidlist_next,
+        .show = cgroup_pidlist_show,
 };
 
-static void release_cgroup_pid_array(struct cgroup_pids *cp)
+static void cgroup_release_pid_array(struct cgroup_pidlist *l)
 {
-        struct cgroup *cgrp = cp->cgrp;
-
-        down_write(&cgrp->pids_mutex);
-        BUG_ON(!cp->use_count);
-        if (!--cp->use_count) {
-                list_del(&cp->list);
-                put_pid_ns(cp->ns);
-                kfree(cp->tasks_pids);
-                kfree(cp);
+        /*
+         * the case where we're the last user of this particular pidlist will
+         * have us remove it from the cgroup's list, which entails taking the
+         * mutex. since in pidlist_find the pidlist->lock depends on cgroup->
+         * pidlist_mutex, we have to take pidlist_mutex first.
+         */
+        mutex_lock(&l->owner->pidlist_mutex);
+        down_write(&l->mutex);
+        BUG_ON(!l->use_count);
+        if (!--l->use_count) {
+                /* we're the last user if refcount is 0; remove and free */
+                list_del(&l->links);
+                mutex_unlock(&l->owner->pidlist_mutex);
+                pidlist_free(l->list);
+                put_pid_ns(l->key.ns);
+                up_write(&l->mutex);
+                kfree(l);
+                return;
         }
-        up_write(&cgrp->pids_mutex);
+        mutex_unlock(&l->owner->pidlist_mutex);
+        up_write(&l->mutex);
 }
 
-static int cgroup_tasks_release(struct inode *inode, struct file *file)
+static int cgroup_pidlist_release(struct inode *inode, struct file *file)
 {
-        struct seq_file *seq;
-        struct cgroup_pids *cp;
-
+        struct cgroup_pidlist *l;
         if (!(file->f_mode & FMODE_READ))
                 return 0;
-
-        seq = file->private_data;
-        cp = seq->private;
-
-        release_cgroup_pid_array(cp);
+        /*
+         * the seq_file will only be initialized if the file was opened for
+         * reading; hence we check if it's not null only in that case.
+         */
+        l = ((struct seq_file *)file->private_data)->private;
+        cgroup_release_pid_array(l);
         return seq_release(inode, file);
 }
 
-static struct file_operations cgroup_tasks_operations = {
+static const struct file_operations cgroup_pidlist_operations = {
         .read = seq_read,
         .llseek = seq_lseek,
         .write = cgroup_file_write,
-        .release = cgroup_tasks_release,
+        .release = cgroup_pidlist_release,
 };
 
 /*
- * Handle an open on 'tasks' file.  Prepare an array containing the
- * process id's of tasks currently attached to the cgroup being opened.
+ * The following functions handle opens on a file that displays a pidlist
+ * (tasks or procs). Prepare an array of the process/thread IDs of whoever's
+ * in the cgroup.
  */
-
-static int cgroup_tasks_open(struct inode *unused, struct file *file)
+/* helper function for the two below it */
+static int cgroup_pidlist_open(struct file *file, enum cgroup_filetype type)
 {
         struct cgroup *cgrp = __d_cgrp(file->f_dentry->d_parent);
-        struct pid_namespace *ns = current->nsproxy->pid_ns;
-        struct cgroup_pids *cp;
-        pid_t *pidarray;
-        int npids;
+        struct cgroup_pidlist *l;
         int retval;
 
         /* Nothing to do for write-only files */
         if (!(file->f_mode & FMODE_READ))
                 return 0;
 
-        /*
-         * If cgroup gets more users after we read count, we won't have
-         * enough space - tough.  This race is indistinguishable to the
-         * caller from the case that the additional cgroup users didn't
-         * show up until sometime later on.
-         */
-        npids = cgroup_task_count(cgrp);
-        pidarray = kmalloc(npids * sizeof(pid_t), GFP_KERNEL);
-        if (!pidarray)
-                return -ENOMEM;
-        npids = pid_array_load(pidarray, npids, cgrp);
-        sort(pidarray, npids, sizeof(pid_t), cmppid, NULL);
-
-        /*
-         * Store the array in the cgroup, freeing the old
-         * array if necessary
-         */
-        down_write(&cgrp->pids_mutex);
-
-        list_for_each_entry(cp, &cgrp->pids_list, list) {
-                if (ns == cp->ns)
-                        goto found;
-        }
-
-        cp = kzalloc(sizeof(*cp), GFP_KERNEL);
-        if (!cp) {
-                up_write(&cgrp->pids_mutex);
-                kfree(pidarray);
-                return -ENOMEM;
-        }
-        cp->cgrp = cgrp;
-        cp->ns = ns;
-        get_pid_ns(ns);
-        list_add(&cp->list, &cgrp->pids_list);
-found:
-        kfree(cp->tasks_pids);
-        cp->tasks_pids = pidarray;
-        cp->length = npids;
-        cp->use_count++;
-        up_write(&cgrp->pids_mutex);
-
-        file->f_op = &cgroup_tasks_operations;
+        /* have the array populated */
+        retval = pidlist_array_load(cgrp, type, &l);
+        if (retval)
+                return retval;
+        /* configure file information */
+        file->f_op = &cgroup_pidlist_operations;
 
-        retval = seq_open(file, &cgroup_tasks_seq_operations);
+        retval = seq_open(file, &cgroup_pidlist_seq_operations);
         if (retval) {
-                release_cgroup_pid_array(cp);
+                cgroup_release_pid_array(l);
                 return retval;
         }
-        ((struct seq_file *)file->private_data)->private = cp;
+        ((struct seq_file *)file->private_data)->private = l;
         return 0;
 }
+static int cgroup_tasks_open(struct inode *unused, struct file *file)
+{
+        return cgroup_pidlist_open(file, CGROUP_FILE_TASKS);
+}
+static int cgroup_procs_open(struct inode *unused, struct file *file)
+{
+        return cgroup_pidlist_open(file, CGROUP_FILE_PROCS);
+}
 
 static u64 cgroup_read_notify_on_release(struct cgroup *cgrp,
                                             struct cftype *cft)
@@ -2449,21 +2794,27 @@ static int cgroup_write_notify_on_release(struct cgroup *cgrp,
 /*
  * for the common functions, 'private' gives the type of file
  */
+/* for hysterical raisins, we can't put this on the older files */
+#define CGROUP_FILE_GENERIC_PREFIX "cgroup."
 static struct cftype files[] = {
         {
                 .name = "tasks",
                 .open = cgroup_tasks_open,
                 .write_u64 = cgroup_tasks_write,
-                .release = cgroup_tasks_release,
-                .private = FILE_TASKLIST,
+                .release = cgroup_pidlist_release,
                 .mode = S_IRUGO | S_IWUSR,
         },
-
+        {
+                .name = CGROUP_FILE_GENERIC_PREFIX "procs",
+                .open = cgroup_procs_open,
+                /* .write_u64 = cgroup_procs_write, TODO */
+                .release = cgroup_pidlist_release,
+                .mode = S_IRUGO,
+        },
         {
                 .name = "notify_on_release",
                 .read_u64 = cgroup_read_notify_on_release,
                 .write_u64 = cgroup_write_notify_on_release,
-                .private = FILE_NOTIFY_ON_RELEASE,
         },
 };
 
@@ -2472,7 +2823,6 @@ static struct cftype cft_release_agent = {
         .read_seq_string = cgroup_release_agent_show,
         .write_string = cgroup_release_agent_write,
         .max_write_len = PATH_MAX,
-        .private = FILE_RELEASE_AGENT,
 };
 
 static int cgroup_populate_dir(struct cgroup *cgrp)
@@ -2879,6 +3229,7 @@ int __init cgroup_init_early(void)
         init_task.cgroups = &init_css_set;
 
         init_css_set_link.cg = &init_css_set;
+        init_css_set_link.cgrp = dummytop;
         list_add(&init_css_set_link.cgrp_link_list,
                  &rootnode.top_cgroup.css_sets);
         list_add(&init_css_set_link.cg_link_list,
@@ -2933,7 +3284,7 @@ int __init cgroup_init(void)
         /* Add init_css_set to the hash table */
         hhead = css_set_hash(init_css_set.subsys);
         hlist_add_head(&init_css_set.hlist, hhead);
-
+        BUG_ON(!init_root_id(&rootnode));
         err = register_filesystem(&cgroup_fs_type);
         if (err < 0)
                 goto out;
@@ -2986,15 +3337,16 @@ static int proc_cgroup_show(struct seq_file *m, void *v)
         for_each_active_root(root) {
                 struct cgroup_subsys *ss;
                 struct cgroup *cgrp;
-                int subsys_id;
                 int count = 0;
 
-                seq_printf(m, "%lu:", root->subsys_bits);
+                seq_printf(m, "%d:", root->hierarchy_id);
                 for_each_subsys(root, ss)
                         seq_printf(m, "%s%s", count++ ? "," : "", ss->name);
+                if (strlen(root->name))
+                        seq_printf(m, "%sname=%s", count ? "," : "",
+                                   root->name);
                 seq_putc(m, ':');
-                get_first_subsys(&root->top_cgroup, NULL, &subsys_id);
-                cgrp = task_cgroup(tsk, subsys_id);
+                cgrp = task_cgroup_from_root(tsk, root);
                 retval = cgroup_path(cgrp, buf, PAGE_SIZE);
                 if (retval < 0)
                         goto out_unlock;
@@ -3033,8 +3385,8 @@ static int proc_cgroupstats_show(struct seq_file *m, void *v)
         mutex_lock(&cgroup_mutex);
         for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
                 struct cgroup_subsys *ss = subsys[i];
-                seq_printf(m, "%s\t%lu\t%d\t%d\n",
-                           ss->name, ss->root->subsys_bits,
+                seq_printf(m, "%s\t%d\t%d\t%d\n",
+                           ss->name, ss->root->hierarchy_id,
                            ss->root->number_of_cgroups, !ss->disabled);
         }
         mutex_unlock(&cgroup_mutex);
@@ -3320,13 +3672,11 @@ int cgroup_is_descendant(const struct cgroup *cgrp, struct task_struct *task)
 {
         int ret;
         struct cgroup *target;
-        int subsys_id;
 
         if (cgrp == dummytop)
                 return 1;
 
-        get_first_subsys(cgrp, NULL, &subsys_id);
-        target = task_cgroup(task, subsys_id);
+        target = task_cgroup_from_root(task, cgrp->root);
         while (cgrp != target && cgrp!= cgrp->top_cgroup)
                 cgrp = cgrp->parent;
         ret = (cgrp == target);
@@ -3693,3 +4043,154 @@ css_get_next(struct cgroup_subsys *ss, int id,
         return ret;
 }
 
+#ifdef CONFIG_CGROUP_DEBUG
+static struct cgroup_subsys_state *debug_create(struct cgroup_subsys *ss,
+                                                   struct cgroup *cont)
+{
+        struct cgroup_subsys_state *css = kzalloc(sizeof(*css), GFP_KERNEL);
+
+        if (!css)
+                return ERR_PTR(-ENOMEM);
+
+        return css;
+}
+
+static void debug_destroy(struct cgroup_subsys *ss, struct cgroup *cont)
+{
+        kfree(cont->subsys[debug_subsys_id]);
+}
+
+static u64 cgroup_refcount_read(struct cgroup *cont, struct cftype *cft)
+{
+        return atomic_read(&cont->count);
+}
+
+static u64 debug_taskcount_read(struct cgroup *cont, struct cftype *cft)
+{
+        return cgroup_task_count(cont);
+}
+
+static u64 current_css_set_read(struct cgroup *cont, struct cftype *cft)
+{
+        return (u64)(unsigned long)current->cgroups;
+}
+
+static u64 current_css_set_refcount_read(struct cgroup *cont,
+                                           struct cftype *cft)
+{
+        u64 count;
+
+        rcu_read_lock();
+        count = atomic_read(&current->cgroups->refcount);
+        rcu_read_unlock();
+        return count;
+}
+
+static int current_css_set_cg_links_read(struct cgroup *cont,
+                                         struct cftype *cft,
+                                         struct seq_file *seq)
+{
+        struct cg_cgroup_link *link;
+        struct css_set *cg;
+
+        read_lock(&css_set_lock);
+        rcu_read_lock();
+        cg = rcu_dereference(current->cgroups);
+        list_for_each_entry(link, &cg->cg_links, cg_link_list) {
+                struct cgroup *c = link->cgrp;
+                const char *name;
+
+                if (c->dentry)
+                        name = c->dentry->d_name.name;
+                else
+                        name = "?";
+                seq_printf(seq, "Root %d group %s\n",
+                           c->root->hierarchy_id, name);
+        }
+        rcu_read_unlock();
+        read_unlock(&css_set_lock);
+        return 0;
+}
+
+#define MAX_TASKS_SHOWN_PER_CSS 25
+static int cgroup_css_links_read(struct cgroup *cont,
+                                 struct cftype *cft,
+                                 struct seq_file *seq)
+{
+        struct cg_cgroup_link *link;
+
+        read_lock(&css_set_lock);
+        list_for_each_entry(link, &cont->css_sets, cgrp_link_list) {
+                struct css_set *cg = link->cg;
+                struct task_struct *task;
+                int count = 0;
+                seq_printf(seq, "css_set %p\n", cg);
+                list_for_each_entry(task, &cg->tasks, cg_list) {
+                        if (count++ > MAX_TASKS_SHOWN_PER_CSS) {
+                                seq_puts(seq, "  ...\n");
+                                break;
+                        } else {
+                                seq_printf(seq, "  task %d\n",
+                                           task_pid_vnr(task));
+                        }
+                }
+        }
+        read_unlock(&css_set_lock);
+        return 0;
+}
+
+static u64 releasable_read(struct cgroup *cgrp, struct cftype *cft)
+{
+        return test_bit(CGRP_RELEASABLE, &cgrp->flags);
+}
+
+static struct cftype debug_files[] =  {
+        {
+                .name = "cgroup_refcount",
+                .read_u64 = cgroup_refcount_read,
+        },
+        {
+                .name = "taskcount",
+                .read_u64 = debug_taskcount_read,
+        },
+
+        {
+                .name = "current_css_set",
+                .read_u64 = current_css_set_read,
+        },
+
+        {
+                .name = "current_css_set_refcount",
+                .read_u64 = current_css_set_refcount_read,
+        },
+
+        {
+                .name = "current_css_set_cg_links",
+                .read_seq_string = current_css_set_cg_links_read,
+        },
+
+        {
+                .name = "cgroup_css_links",
+                .read_seq_string = cgroup_css_links_read,
+        },
+
+        {
+                .name = "releasable",
+                .read_u64 = releasable_read,
+        },
+};
+
+static int debug_populate(struct cgroup_subsys *ss, struct cgroup *cont)
+{
+        return cgroup_add_files(cont, ss, debug_files,
+                                ARRAY_SIZE(debug_files));
+}
+
+struct cgroup_subsys debug_subsys = {
+        .name = "debug",
+        .create = debug_create,
+        .destroy = debug_destroy,
+        .populate = debug_populate,
+        .subsys_id = debug_subsys_id,
+};
+#endif /* CONFIG_CGROUP_DEBUG */
diff --git a/kernel/cgroup_debug.c b/kernel/cgroup_debug.c
deleted file mode 100644
index 0c92d797baa6..000000000000
--- a/kernel/cgroup_debug.c
+++ /dev/null
@@ -1,105 +0,0 @@
-/*
- * kernel/cgroup_debug.c - Example cgroup subsystem that
- * exposes debug info
- *
- * Copyright (C) Google Inc, 2007
- *
- * Developed by Paul Menage (menage@google.com)
- *
- */
-
-#include <linux/cgroup.h>
-#include <linux/fs.h>
-#include <linux/slab.h>
-#include <linux/rcupdate.h>
-
-#include <asm/atomic.h>
-
-static struct cgroup_subsys_state *debug_create(struct cgroup_subsys *ss,
-                                                   struct cgroup *cont)
-{
-        struct cgroup_subsys_state *css = kzalloc(sizeof(*css), GFP_KERNEL);
-
-        if (!css)
-                return ERR_PTR(-ENOMEM);
-
-        return css;
-}
-
-static void debug_destroy(struct cgroup_subsys *ss, struct cgroup *cont)
-{
-        kfree(cont->subsys[debug_subsys_id]);
-}
-
-static u64 cgroup_refcount_read(struct cgroup *cont, struct cftype *cft)
-{
-        return atomic_read(&cont->count);
-}
-
-static u64 taskcount_read(struct cgroup *cont, struct cftype *cft)
-{
-        u64 count;
-
-        count = cgroup_task_count(cont);
-        return count;
-}
-
-static u64 current_css_set_read(struct cgroup *cont, struct cftype *cft)
-{
-        return (u64)(long)current->cgroups;
-}
-
-static u64 current_css_set_refcount_read(struct cgroup *cont,
-                                           struct cftype *cft)
-{
-        u64 count;
-
-        rcu_read_lock();
-        count = atomic_read(&current->cgroups->refcount);
-        rcu_read_unlock();
-        return count;
-}
-
-static u64 releasable_read(struct cgroup *cgrp, struct cftype *cft)
-{
-        return test_bit(CGRP_RELEASABLE, &cgrp->flags);
-}
-
-static struct cftype files[] =  {
-        {
-                .name = "cgroup_refcount",
-                .read_u64 = cgroup_refcount_read,
-        },
-        {
-                .name = "taskcount",
-                .read_u64 = taskcount_read,
-        },
-
-        {
-                .name = "current_css_set",
-                .read_u64 = current_css_set_read,
-        },
-
-        {
-                .name = "current_css_set_refcount",
-                .read_u64 = current_css_set_refcount_read,
-        },
-
-        {
-                .name = "releasable",
-                .read_u64 = releasable_read,
-        },
-};
-
-static int debug_populate(struct cgroup_subsys *ss, struct cgroup *cont)
-{
-        return cgroup_add_files(cont, ss, files, ARRAY_SIZE(files));
-}
-
-struct cgroup_subsys debug_subsys = {
-        .name = "debug",
-        .create = debug_create,
-        .destroy = debug_destroy,
-        .populate = debug_populate,
-        .subsys_id = debug_subsys_id,
-};
diff --git a/kernel/cgroup_freezer.c b/kernel/cgroup_freezer.c
index fb249e2bcada..59e9ef6aab40 100644
--- a/kernel/cgroup_freezer.c
+++ b/kernel/cgroup_freezer.c
@@ -159,7 +159,7 @@ static bool is_task_frozen_enough(struct task_struct *task)
  */
 static int freezer_can_attach(struct cgroup_subsys *ss,
                               struct cgroup *new_cgroup,
-                              struct task_struct *task)
+                              struct task_struct *task, bool threadgroup)
 {
         struct freezer *freezer;
 
@@ -177,6 +177,19 @@ static int freezer_can_attach(struct cgroup_subsys *ss,
         if (freezer->state == CGROUP_FROZEN)
                 return -EBUSY;
 
+        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)) {
+                                rcu_read_unlock();
+                                return -EBUSY;
+                        }
+                }
+                rcu_read_unlock();
+        }
+
         return 0;
 }
 
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 7e75a41bd508..b5cb469d2545 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -1324,9 +1324,10 @@ static int fmeter_getrate(struct fmeter *fmp)
 static cpumask_var_t cpus_attach;
 
 /* Called by cgroups to determine if a cpuset is usable; cgroup_mutex held */
-static int cpuset_can_attach(struct cgroup_subsys *ss,
-                             struct cgroup *cont, struct task_struct *tsk)
+static int cpuset_can_attach(struct cgroup_subsys *ss, struct cgroup *cont,
+                             struct task_struct *tsk, bool threadgroup)
 {
+        int ret;
         struct cpuset *cs = cgroup_cs(cont);
 
         if (cpumask_empty(cs->cpus_allowed) || nodes_empty(cs->mems_allowed))
@@ -1343,18 +1344,51 @@ static int cpuset_can_attach(struct cgroup_subsys *ss,
         if (tsk->flags & PF_THREAD_BOUND)
                 return -EINVAL;
 
-        return security_task_setscheduler(tsk, 0, NULL);
+        ret = security_task_setscheduler(tsk, 0, NULL);
+        if (ret)
+                return ret;
+        if (threadgroup) {
+                struct task_struct *c;
+
+                rcu_read_lock();
+                list_for_each_entry_rcu(c, &tsk->thread_group, thread_group) {
+                        ret = security_task_setscheduler(c, 0, NULL);
+                        if (ret) {
+                                rcu_read_unlock();
+                                return ret;
+                        }
+                }
+                rcu_read_unlock();
+        }
+        return 0;
+}
+
+static void cpuset_attach_task(struct task_struct *tsk, nodemask_t *to,
+                               struct cpuset *cs)
+{
+        int err;
+        /*
+         * can_attach beforehand should guarantee that this doesn't fail.
+         * TODO: have a better way to handle failure here
+         */
+        err = set_cpus_allowed_ptr(tsk, cpus_attach);
+        WARN_ON_ONCE(err);
+
+        task_lock(tsk);
+        cpuset_change_task_nodemask(tsk, to);
+        task_unlock(tsk);
+        cpuset_update_task_spread_flag(cs, tsk);
+
 }
 
-static void cpuset_attach(struct cgroup_subsys *ss,
-                          struct cgroup *cont, struct cgroup *oldcont,
-                          struct task_struct *tsk)
+static void cpuset_attach(struct cgroup_subsys *ss, struct cgroup *cont,
+                          struct cgroup *oldcont, struct task_struct *tsk,
+                          bool threadgroup)
 {
         nodemask_t from, to;
         struct mm_struct *mm;
         struct cpuset *cs = cgroup_cs(cont);
         struct cpuset *oldcs = cgroup_cs(oldcont);
-        int err;
 
         if (cs == &top_cpuset) {
                 cpumask_copy(cpus_attach, cpu_possible_mask);
@@ -1363,15 +1397,19 @@ static void cpuset_attach(struct cgroup_subsys *ss,
                 guarantee_online_cpus(cs, cpus_attach);
                 guarantee_online_mems(cs, &to);
         }
-        err = set_cpus_allowed_ptr(tsk, cpus_attach);
-        if (err)
-                return;
 
-        task_lock(tsk);
-        cpuset_change_task_nodemask(tsk, &to);
-        task_unlock(tsk);
-        cpuset_update_task_spread_flag(cs, tsk);
+        /* do per-task migration stuff possibly for each in the threadgroup */
+        cpuset_attach_task(tsk, &to, cs);
+        if (threadgroup) {
+                struct task_struct *c;
+                rcu_read_lock();
+                list_for_each_entry_rcu(c, &tsk->thread_group, thread_group) {
+                        cpuset_attach_task(c, &to, cs);
+                }
+                rcu_read_unlock();
+        }
 
+        /* change mm; only needs to be done once even if threadgroup */
         from = oldcs->mems_allowed;
         to = cs->mems_allowed;
         mm = get_task_mm(tsk);
diff --git a/kernel/exit.c b/kernel/exit.c
index 60d6fdcc9265..5859f598c951 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -976,8 +976,6 @@ NORET_TYPE void do_exit(long code)
                 disassociate_ctty(1);
 
         module_put(task_thread_info(tsk)->exec_domain->module);
-        if (tsk->binfmt)
-                module_put(tsk->binfmt->module);
 
         proc_exit_connector(tsk);
 
@@ -1097,28 +1095,28 @@ struct wait_opts {
         int __user              *wo_stat;
         struct rusage __user    *wo_rusage;
 
+        wait_queue_t            child_wait;
         int                     notask_error;
 };
 
-static struct pid *task_pid_type(struct task_struct *task, enum pid_type type)
+static inline
+struct pid *task_pid_type(struct task_struct *task, enum pid_type type)
 {
-        struct pid *pid = NULL;
-        if (type == PIDTYPE_PID)
-                pid = task->pids[type].pid;
-        else if (type < PIDTYPE_MAX)
-                pid = task->group_leader->pids[type].pid;
-        return pid;
+        if (type != PIDTYPE_PID)
+                task = task->group_leader;
+        return task->pids[type].pid;
 }
 
-static int eligible_child(struct wait_opts *wo, struct task_struct *p)
+static int eligible_pid(struct wait_opts *wo, struct task_struct *p)
 {
-        int err;
-
-        if (wo->wo_type < PIDTYPE_MAX) {
-                if (task_pid_type(p, wo->wo_type) != wo->wo_pid)
-                        return 0;
-        }
+        return  wo->wo_type == PIDTYPE_MAX ||
+                task_pid_type(p, wo->wo_type) == wo->wo_pid;
+}
 
+static int eligible_child(struct wait_opts *wo, struct task_struct *p)
+{
+        if (!eligible_pid(wo, p))
+                return 0;
         /* Wait for all children (clone and not) if __WALL is set;
          * otherwise, wait for clone children *only* if __WCLONE is
          * set; otherwise, wait for non-clone children *only*.  (Note:
@@ -1128,10 +1126,6 @@ static int eligible_child(struct wait_opts *wo, struct task_struct *p)
             && !(wo->wo_flags & __WALL))
                 return 0;
 
-        err = security_task_wait(p);
-        if (err)
-                return err;
-
         return 1;
 }
 
@@ -1144,18 +1138,20 @@ static int wait_noreap_copyout(struct wait_opts *wo, struct task_struct *p,
 
         put_task_struct(p);
         infop = wo->wo_info;
-        if (!retval)
-                retval = put_user(SIGCHLD, &infop->si_signo);
-        if (!retval)
-                retval = put_user(0, &infop->si_errno);
-        if (!retval)
-                retval = put_user((short)why, &infop->si_code);
-        if (!retval)
-                retval = put_user(pid, &infop->si_pid);
-        if (!retval)
-                retval = put_user(uid, &infop->si_uid);
-        if (!retval)
-                retval = put_user(status, &infop->si_status);
+        if (infop) {
+                if (!retval)
+                        retval = put_user(SIGCHLD, &infop->si_signo);
+                if (!retval)
+                        retval = put_user(0, &infop->si_errno);
+                if (!retval)
+                        retval = put_user((short)why, &infop->si_code);
+                if (!retval)
+                        retval = put_user(pid, &infop->si_pid);
+                if (!retval)
+                        retval = put_user(uid, &infop->si_uid);
+                if (!retval)
+                        retval = put_user(status, &infop->si_status);
+        }
         if (!retval)
                 retval = pid;
         return retval;
@@ -1485,13 +1481,14 @@ static int wait_task_continued(struct wait_opts *wo, struct task_struct *p)
  * then ->notask_error is 0 if @p is an eligible child,
  * or another error from security_task_wait(), or still -ECHILD.
  */
-static int wait_consider_task(struct wait_opts *wo, struct task_struct *parent,
-                                int ptrace, struct task_struct *p)
+static int wait_consider_task(struct wait_opts *wo, int ptrace,
+                                struct task_struct *p)
 {
         int ret = eligible_child(wo, p);
         if (!ret)
                 return ret;
 
+        ret = security_task_wait(p);
         if (unlikely(ret < 0)) {
                 /*
                  * If we have not yet seen any eligible child,
@@ -1553,7 +1550,7 @@ static int do_wait_thread(struct wait_opts *wo, struct task_struct *tsk)
                  * Do not consider detached threads.
                  */
                 if (!task_detached(p)) {
-                        int ret = wait_consider_task(wo, tsk, 0, p);
+                        int ret = wait_consider_task(wo, 0, p);
                         if (ret)
                                 return ret;
                 }
@@ -1567,7 +1564,7 @@ static int ptrace_do_wait(struct wait_opts *wo, struct task_struct *tsk)
         struct task_struct *p;
 
         list_for_each_entry(p, &tsk->ptraced, ptrace_entry) {
-                int ret = wait_consider_task(wo, tsk, 1, p);
+                int ret = wait_consider_task(wo, 1, p);
                 if (ret)
                         return ret;
         }
@@ -1575,15 +1572,38 @@ static int ptrace_do_wait(struct wait_opts *wo, struct task_struct *tsk)
         return 0;
 }
 
+static int child_wait_callback(wait_queue_t *wait, unsigned mode,
+                                int sync, void *key)
+{
+        struct wait_opts *wo = container_of(wait, struct wait_opts,
+                                                child_wait);
+        struct task_struct *p = key;
+
+        if (!eligible_pid(wo, p))
+                return 0;
+
+        if ((wo->wo_flags & __WNOTHREAD) && wait->private != p->parent)
+                return 0;
+
+        return default_wake_function(wait, mode, sync, key);
+}
+
+void __wake_up_parent(struct task_struct *p, struct task_struct *parent)
+{
+        __wake_up_sync_key(&parent->signal->wait_chldexit,
+                                TASK_INTERRUPTIBLE, 1, p);
+}
+
 static long do_wait(struct wait_opts *wo)
 {
-        DECLARE_WAITQUEUE(wait, current);
         struct task_struct *tsk;
         int retval;
 
         trace_sched_process_wait(wo->wo_pid);
 
-        add_wait_queue(&current->signal->wait_chldexit,&wait);
+        init_waitqueue_func_entry(&wo->child_wait, child_wait_callback);
+        wo->child_wait.private = current;
+        add_wait_queue(&current->signal->wait_chldexit, &wo->child_wait);
 repeat:
         /*
          * If there is nothing that can match our critiera just get out.
@@ -1624,32 +1644,7 @@ notask:
         }
 end:
         __set_current_state(TASK_RUNNING);
-        remove_wait_queue(&current->signal->wait_chldexit,&wait);
-        if (wo->wo_info) {
-                struct siginfo __user *infop = wo->wo_info;
-
-                if (retval > 0)
-                        retval = 0;
-                else {
-                        /*
-                         * For a WNOHANG return, clear out all the fields
-                         * we would set so the user can easily tell the
-                         * difference.
-                         */
-                        if (!retval)
-                                retval = put_user(0, &infop->si_signo);
-                        if (!retval)
-                                retval = put_user(0, &infop->si_errno);
-                        if (!retval)
-                                retval = put_user(0, &infop->si_code);
-                        if (!retval)
-                                retval = put_user(0, &infop->si_pid);
-                        if (!retval)
-                                retval = put_user(0, &infop->si_uid);
-                        if (!retval)
-                                retval = put_user(0, &infop->si_status);
-                }
-        }
+        remove_wait_queue(&current->signal->wait_chldexit, &wo->child_wait);
         return retval;
 }
 
@@ -1694,6 +1689,29 @@ SYSCALL_DEFINE5(waitid, int, which, pid_t, upid, struct siginfo __user *,
         wo.wo_stat      = NULL;
         wo.wo_rusage    = ru;
         ret = do_wait(&wo);
+
+        if (ret > 0) {
+                ret = 0;
+        } else if (infop) {
+                /*
+                 * For a WNOHANG return, clear out all the fields
+                 * we would set so the user can easily tell the
+                 * difference.
+                 */
+                if (!ret)
+                        ret = put_user(0, &infop->si_signo);
+                if (!ret)
+                        ret = put_user(0, &infop->si_errno);
+                if (!ret)
+                        ret = put_user(0, &infop->si_code);
+                if (!ret)
+                        ret = put_user(0, &infop->si_pid);
+                if (!ret)
+                        ret = put_user(0, &infop->si_uid);
+                if (!ret)
+                        ret = put_user(0, &infop->si_status);
+        }
+
         put_pid(pid);
 
         /* avoid REGPARM breakage on x86: */
diff --git a/kernel/fork.c b/kernel/fork.c
index 51ad0b0b7266..266c6af6ef1b 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -434,6 +434,14 @@ __setup("coredump_filter=", coredump_filter_setup);
 
 #include <linux/init_task.h>
 
+static void mm_init_aio(struct mm_struct *mm)
+{
+#ifdef CONFIG_AIO
+        spin_lock_init(&mm->ioctx_lock);
+        INIT_HLIST_HEAD(&mm->ioctx_list);
+#endif
+}
+
 static struct mm_struct * mm_init(struct mm_struct * mm, struct task_struct *p)
 {
         atomic_set(&mm->mm_users, 1);
@@ -447,10 +455,9 @@ static struct mm_struct * mm_init(struct mm_struct * mm, struct task_struct *p)
         set_mm_counter(mm, file_rss, 0);
         set_mm_counter(mm, anon_rss, 0);
         spin_lock_init(&mm->page_table_lock);
-        spin_lock_init(&mm->ioctx_lock);
-        INIT_HLIST_HEAD(&mm->ioctx_list);
         mm->free_area_cache = TASK_UNMAPPED_BASE;
         mm->cached_hole_size = ~0UL;
+        mm_init_aio(mm);
         mm_init_owner(mm, p);
 
         if (likely(!mm_alloc_pgd(mm))) {
@@ -511,6 +518,8 @@ void mmput(struct mm_struct *mm)
                         spin_unlock(&mmlist_lock);
                 }
                 put_swap_token(mm);
+                if (mm->binfmt)
+                        module_put(mm->binfmt->module);
                 mmdrop(mm);
         }
 }
@@ -636,9 +645,14 @@ struct mm_struct *dup_mm(struct task_struct *tsk)
         mm->hiwater_rss = get_mm_rss(mm);
         mm->hiwater_vm = mm->total_vm;
 
+        if (mm->binfmt && !try_module_get(mm->binfmt->module))
+                goto free_pt;
+
         return mm;
 
 free_pt:
+        /* don't put binfmt in mmput, we haven't got module yet */
+        mm->binfmt = NULL;
         mmput(mm);
 
 fail_nomem:
@@ -979,6 +993,16 @@ static struct task_struct *copy_process(unsigned long clone_flags,
         if ((clone_flags & CLONE_SIGHAND) && !(clone_flags & CLONE_VM))
                 return ERR_PTR(-EINVAL);
 
+        /*
+         * Siblings of global init remain as zombies on exit since they are
+         * not reaped by their parent (swapper). To solve this and to avoid
+         * multi-rooted process trees, prevent global and container-inits
+         * from creating siblings.
+         */
+        if ((clone_flags & CLONE_PARENT) &&
+                                current->signal->flags & SIGNAL_UNKILLABLE)
+                return ERR_PTR(-EINVAL);
+
         retval = security_task_create(clone_flags);
         if (retval)
                 goto fork_out;
@@ -1020,9 +1044,6 @@ static struct task_struct *copy_process(unsigned long clone_flags,
         if (!try_module_get(task_thread_info(p)->exec_domain->module))
                 goto bad_fork_cleanup_count;
 
-        if (p->binfmt && !try_module_get(p->binfmt->module))
-                goto bad_fork_cleanup_put_domain;
-
         p->did_exec = 0;
         delayacct_tsk_init(p);  /* Must remain after dup_task_struct() */
         copy_flags(clone_flags, p);
@@ -1310,9 +1331,6 @@ bad_fork_cleanup_cgroup:
 #endif
         cgroup_exit(p, cgroup_callbacks_done);
         delayacct_tsk_free(p);
-        if (p->binfmt)
-                module_put(p->binfmt->module);
-bad_fork_cleanup_put_domain:
         module_put(task_thread_info(p)->exec_domain->module);
 bad_fork_cleanup_count:
         atomic_dec(&p->cred->user->processes);
diff --git a/kernel/hung_task.c b/kernel/hung_task.c
index 022a4927b785..d4e841747400 100644
--- a/kernel/hung_task.c
+++ b/kernel/hung_task.c
@@ -171,12 +171,12 @@ static unsigned long timeout_jiffies(unsigned long timeout)
  * Process updating of timeout sysctl
  */
 int proc_dohung_task_timeout_secs(struct ctl_table *table, int write,
-                                  struct file *filp, void __user *buffer,
+                                  void __user *buffer,
                                   size_t *lenp, loff_t *ppos)
 {
         int ret;
 
-        ret = proc_doulongvec_minmax(table, write, filp, buffer, lenp, ppos);
+        ret = proc_doulongvec_minmax(table, write, buffer, lenp, ppos);
 
         if (ret || !write)
                 goto out;
diff --git a/kernel/ns_cgroup.c b/kernel/ns_cgroup.c
index 5aa854f9e5ae..2a5dfec8efe0 100644
--- a/kernel/ns_cgroup.c
+++ b/kernel/ns_cgroup.c
@@ -42,8 +42,8 @@ int ns_cgroup_clone(struct task_struct *task, struct pid *pid)
  *       (hence either you are in the same cgroup as task, or in an
  *        ancestor cgroup thereof)
  */
-static int ns_can_attach(struct cgroup_subsys *ss,
-                struct cgroup *new_cgroup, struct task_struct *task)
+static int ns_can_attach(struct cgroup_subsys *ss, struct cgroup *new_cgroup,
+                         struct task_struct *task, bool threadgroup)
 {
         if (current != task) {
                 if (!capable(CAP_SYS_ADMIN))
@@ -56,6 +56,18 @@ static int ns_can_attach(struct cgroup_subsys *ss,
         if (!cgroup_is_descendant(new_cgroup, task))
                 return -EPERM;
 
+        if (threadgroup) {
+                struct task_struct *c;
+                rcu_read_lock();
+                list_for_each_entry_rcu(c, &task->thread_group, thread_group) {
+                        if (!cgroup_is_descendant(new_cgroup, c)) {
+                                rcu_read_unlock();
+                                return -EPERM;
+                        }
+                }
+                rcu_read_unlock();
+        }
+
         return 0;
 }
 
diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c
index 821722ae58a7..86b3796b0436 100644
--- a/kernel/pid_namespace.c
+++ b/kernel/pid_namespace.c
@@ -118,7 +118,7 @@ struct pid_namespace *copy_pid_ns(unsigned long flags, struct pid_namespace *old
 {
         if (!(flags & CLONE_NEWPID))
                 return get_pid_ns(old_ns);
-        if (flags & CLONE_THREAD)
+        if (flags & (CLONE_THREAD|CLONE_PARENT))
                 return ERR_PTR(-EINVAL);
         return create_pid_namespace(old_ns);
 }
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 307c285af59e..23bd09cd042e 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -266,9 +266,10 @@ static int ignoring_children(struct sighand_struct *sigh)
  * or self-reaping.  Do notification now if it would have happened earlier.
  * If it should reap itself, return true.
  *
- * If it's our own child, there is no notification to do.
- * But if our normal children self-reap, then this child
- * was prevented by ptrace and we must reap it now.
+ * If it's our own child, there is no notification to do. But if our normal
+ * children self-reap, then this child was prevented by ptrace and we must
+ * reap it now, in that case we must also wake up sub-threads sleeping in
+ * do_wait().
  */
 static bool __ptrace_detach(struct task_struct *tracer, struct task_struct *p)
 {
@@ -278,8 +279,10 @@ static bool __ptrace_detach(struct task_struct *tracer, struct task_struct *p)
                 if (!task_detached(p) && thread_group_empty(p)) {
                         if (!same_thread_group(p->real_parent, tracer))
                                 do_notify_parent(p, p->exit_signal);
-                        else if (ignoring_children(tracer->sighand))
+                        else if (ignoring_children(tracer->sighand)) {
+                                __wake_up_parent(p, tracer);
                                 p->exit_signal = -1;
+                        }
                 }
                 if (task_detached(p)) {
                         /* Mark it as in the process of being reaped. */
diff --git a/kernel/res_counter.c b/kernel/res_counter.c
index e1338f074314..88faec23e833 100644
--- a/kernel/res_counter.c
+++ b/kernel/res_counter.c
@@ -19,6 +19,7 @@ void res_counter_init(struct res_counter *counter, struct res_counter *parent)
 {
         spin_lock_init(&counter->lock);
         counter->limit = RESOURCE_MAX;
+        counter->soft_limit = RESOURCE_MAX;
         counter->parent = parent;
 }
 
@@ -36,17 +37,27 @@ int res_counter_charge_locked(struct res_counter *counter, unsigned long val)
 }
 
 int res_counter_charge(struct res_counter *counter, unsigned long val,
-                        struct res_counter **limit_fail_at)
+                        struct res_counter **limit_fail_at,
+                        struct res_counter **soft_limit_fail_at)
 {
         int ret;
         unsigned long flags;
         struct res_counter *c, *u;
 
         *limit_fail_at = NULL;
+        if (soft_limit_fail_at)
+                *soft_limit_fail_at = NULL;
         local_irq_save(flags);
         for (c = counter; c != NULL; c = c->parent) {
                 spin_lock(&c->lock);
                 ret = res_counter_charge_locked(c, val);
+                /*
+                 * With soft limits, we return the highest ancestor
+                 * that exceeds its soft limit
+                 */
+                if (soft_limit_fail_at &&
+                        !res_counter_soft_limit_check_locked(c))
+                        *soft_limit_fail_at = c;
                 spin_unlock(&c->lock);
                 if (ret < 0) {
                         *limit_fail_at = c;
@@ -74,7 +85,8 @@ void res_counter_uncharge_locked(struct res_counter *counter, unsigned long val)
         counter->usage -= val;
 }
 
-void res_counter_uncharge(struct res_counter *counter, unsigned long val)
+void res_counter_uncharge(struct res_counter *counter, unsigned long val,
+                                bool *was_soft_limit_excess)
 {
         unsigned long flags;
         struct res_counter *c;
@@ -82,6 +94,9 @@ void res_counter_uncharge(struct res_counter *counter, unsigned long val)
         local_irq_save(flags);
         for (c = counter; c != NULL; c = c->parent) {
                 spin_lock(&c->lock);
+                if (was_soft_limit_excess)
+                        *was_soft_limit_excess =
+                                !res_counter_soft_limit_check_locked(c);
                 res_counter_uncharge_locked(c, val);
                 spin_unlock(&c->lock);
         }
@@ -101,6 +116,8 @@ res_counter_member(struct res_counter *counter, int member)
                 return &counter->limit;
         case RES_FAILCNT:
                 return &counter->failcnt;
+        case RES_SOFT_LIMIT:
+                return &counter->soft_limit;
         };
 
         BUG();
diff --git a/kernel/sched.c b/kernel/sched.c
index 2f76e06bea58..ee61f454a98b 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -10312,7 +10312,7 @@ static int sched_rt_global_constraints(void)
 #endif /* CONFIG_RT_GROUP_SCHED */
 
 int sched_rt_handler(struct ctl_table *table, int write,
-                struct file *filp, void __user *buffer, size_t *lenp,
+                void __user *buffer, size_t *lenp,
                 loff_t *ppos)
 {
         int ret;
@@ -10323,7 +10323,7 @@ int sched_rt_handler(struct ctl_table *table, int write,
         old_period = sysctl_sched_rt_period;
         old_runtime = sysctl_sched_rt_runtime;
 
-        ret = proc_dointvec(table, write, filp, buffer, lenp, ppos);
+        ret = proc_dointvec(table, write, buffer, lenp, ppos);
 
         if (!ret && write) {
                 ret = sched_rt_global_constraints();
@@ -10377,8 +10377,7 @@ cpu_cgroup_destroy(struct cgroup_subsys *ss, struct cgroup *cgrp)
 }
 
 static int
-cpu_cgroup_can_attach(struct cgroup_subsys *ss, struct cgroup *cgrp,
-                      struct task_struct *tsk)
+cpu_cgroup_can_attach_task(struct cgroup *cgrp, struct task_struct *tsk)
 {
 #ifdef CONFIG_RT_GROUP_SCHED
         if (!sched_rt_can_attach(cgroup_tg(cgrp), tsk))
@@ -10388,15 +10387,45 @@ cpu_cgroup_can_attach(struct cgroup_subsys *ss, struct cgroup *cgrp,
         if (tsk->sched_class != &fair_sched_class)
                 return -EINVAL;
 #endif
+        return 0;
+}
 
+static int
+cpu_cgroup_can_attach(struct cgroup_subsys *ss, struct cgroup *cgrp,
+                      struct task_struct *tsk, bool threadgroup)
+{
+        int retval = cpu_cgroup_can_attach_task(cgrp, tsk);
+        if (retval)
+                return retval;
+        if (threadgroup) {
+                struct task_struct *c;
+                rcu_read_lock();
+                list_for_each_entry_rcu(c, &tsk->thread_group, thread_group) {
+                        retval = cpu_cgroup_can_attach_task(cgrp, c);
+                        if (retval) {
+                                rcu_read_unlock();
+                                return retval;
+                        }
+                }
+                rcu_read_unlock();
+        }
         return 0;
 }
 
 static void
 cpu_cgroup_attach(struct cgroup_subsys *ss, struct cgroup *cgrp,
-                        struct cgroup *old_cont, struct task_struct *tsk)
+                  struct cgroup *old_cont, struct task_struct *tsk,
+                  bool threadgroup)
 {
         sched_move_task(tsk);
+        if (threadgroup) {
+                struct task_struct *c;
+                rcu_read_lock();
+                list_for_each_entry_rcu(c, &tsk->thread_group, thread_group) {
+                        sched_move_task(c);
+                }
+                rcu_read_unlock();
+        }
 }
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index ecc637a0d591..4e777b47eeda 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -384,10 +384,10 @@ static struct sched_entity *__pick_last_entity(struct cfs_rq *cfs_rq)
 
 #ifdef CONFIG_SCHED_DEBUG
 int sched_nr_latency_handler(struct ctl_table *table, int write,
-                struct file *filp, void __user *buffer, size_t *lenp,
+                void __user *buffer, size_t *lenp,
                 loff_t *ppos)
 {
-        int ret = proc_dointvec_minmax(table, write, filp, buffer, lenp, ppos);
+        int ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
 
         if (ret || !write)
                 return ret;
diff --git a/kernel/signal.c b/kernel/signal.c
index 64c5deeaca5d..6705320784fd 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -705,7 +705,7 @@ static int prepare_signal(int sig, struct task_struct *p, int from_ancestor_ns)
 
                 if (why) {
                         /*
-                         * The first thread which returns from finish_stop()
+                         * The first thread which returns from do_signal_stop()
                          * will take ->siglock, notice SIGNAL_CLD_MASK, and
                          * notify its parent. See get_signal_to_deliver().
                          */
@@ -971,6 +971,20 @@ specific_send_sig_info(int sig, struct siginfo *info, struct task_struct *t)
         return send_signal(sig, info, t, 0);
 }
 
+int do_send_sig_info(int sig, struct siginfo *info, struct task_struct *p,
+                        bool group)
+{
+        unsigned long flags;
+        int ret = -ESRCH;
+
+        if (lock_task_sighand(p, &flags)) {
+                ret = send_signal(sig, info, p, group);
+                unlock_task_sighand(p, &flags);
+        }
+
+        return ret;
+}
+
 /*
  * Force a signal that the process can't ignore: if necessary
  * we unblock the signal and change any SIG_IGN to SIG_DFL.
@@ -1036,12 +1050,6 @@ void zap_other_threads(struct task_struct *p)
         }
 }
 
-int __fatal_signal_pending(struct task_struct *tsk)
-{
-        return sigismember(&tsk->pending.signal, SIGKILL);
-}
-EXPORT_SYMBOL(__fatal_signal_pending);
-
 struct sighand_struct *lock_task_sighand(struct task_struct *tsk, unsigned long *flags)
 {
         struct sighand_struct *sighand;
@@ -1068,18 +1076,10 @@ struct sighand_struct *lock_task_sighand(struct task_struct *tsk, unsigned long
  */
 int group_send_sig_info(int sig, struct siginfo *info, struct task_struct *p)
 {
-        unsigned long flags;
-        int ret;
+        int ret = check_kill_permission(sig, info, p);
 
-        ret = check_kill_permission(sig, info, p);
-
-        if (!ret && sig) {
-                ret = -ESRCH;
-                if (lock_task_sighand(p, &flags)) {
-                        ret = __group_send_sig_info(sig, info, p);
-                        unlock_task_sighand(p, &flags);
-                }
-        }
+        if (!ret && sig)
+                ret = do_send_sig_info(sig, info, p, true);
 
         return ret;
 }
@@ -1224,15 +1224,9 @@ static int kill_something_info(int sig, struct siginfo *info, pid_t pid)
  * These are for backward compatibility with the rest of the kernel source.
  */
 
-/*
- * The caller must ensure the task can't exit.
- */
 int
 send_sig_info(int sig, struct siginfo *info, struct task_struct *p)
 {
-        int ret;
-        unsigned long flags;
-
         /*
          * Make sure legacy kernel users don't send in bad values
          * (normal paths check this in check_kill_permission).
@@ -1240,10 +1234,7 @@ send_sig_info(int sig, struct siginfo *info, struct task_struct *p)
         if (!valid_signal(sig))
                 return -EINVAL;
 
-        spin_lock_irqsave(&p->sighand->siglock, flags);
-        ret = specific_send_sig_info(sig, info, p);
-        spin_unlock_irqrestore(&p->sighand->siglock, flags);
-        return ret;
+        return do_send_sig_info(sig, info, p, false);
 }
 
 #define __si_special(priv) \
@@ -1383,15 +1374,6 @@ ret:
 }
 
 /*
- * Wake up any threads in the parent blocked in wait* syscalls.
- */
-static inline void __wake_up_parent(struct task_struct *p,
-                                    struct task_struct *parent)
-{
-        wake_up_interruptible_sync(&parent->signal->wait_chldexit);
-}
-
-/*
  * Let a parent know about the death of a child.
  * For a stopped/continued status change, use do_notify_parent_cldstop instead.
  *
@@ -1673,29 +1655,6 @@ void ptrace_notify(int exit_code)
         spin_unlock_irq(&current->sighand->siglock);
 }
 
-static void
-finish_stop(int stop_count)
-{
-        /*
-         * If there are no other threads in the group, or if there is
-         * a group stop in progress and we are the last to stop,
-         * report to the parent.  When ptraced, every thread reports itself.
-         */
-        if (tracehook_notify_jctl(stop_count == 0, CLD_STOPPED)) {
-                read_lock(&tasklist_lock);
-                do_notify_parent_cldstop(current, CLD_STOPPED);
-                read_unlock(&tasklist_lock);
-        }
-
-        do {
-                schedule();
-        } while (try_to_freeze());
-        /*
-         * Now we don't run again until continued.
-         */
-        current->exit_code = 0;
-}
-
 /*
  * This performs the stopping for SIGSTOP and other stop signals.
  * We have to stop all threads in the thread group.
@@ -1705,15 +1664,9 @@ finish_stop(int stop_count)
 static int do_signal_stop(int signr)
 {
         struct signal_struct *sig = current->signal;
-        int stop_count;
+        int notify;
 
-        if (sig->group_stop_count > 0) {
-                /*
-                 * There is a group stop in progress.  We don't need to
-                 * start another one.
-                 */
-                stop_count = --sig->group_stop_count;
-        } else {
+        if (!sig->group_stop_count) {
                 struct task_struct *t;
 
                 if (!likely(sig->flags & SIGNAL_STOP_DEQUEUED) ||
@@ -1725,7 +1678,7 @@ static int do_signal_stop(int signr)
                  */
                 sig->group_exit_code = signr;
 
-                stop_count = 0;
+                sig->group_stop_count = 1;
                 for (t = next_thread(current); t != current; t = next_thread(t))
                         /*
                          * Setting state to TASK_STOPPED for a group
@@ -1734,19 +1687,44 @@ static int do_signal_stop(int signr)
                          */
                         if (!(t->flags & PF_EXITING) &&
                             !task_is_stopped_or_traced(t)) {
-                                stop_count++;
+                                sig->group_stop_count++;
                                 signal_wake_up(t, 0);
                         }
-                sig->group_stop_count = stop_count;
         }
+        /*
+         * If there are no other threads in the group, or if there is
+         * a group stop in progress and we are the last to stop, report
+         * to the parent.  When ptraced, every thread reports itself.
+         */
+        notify = sig->group_stop_count == 1 ? CLD_STOPPED : 0;
+        notify = tracehook_notify_jctl(notify, CLD_STOPPED);
+        /*
+         * tracehook_notify_jctl() can drop and reacquire siglock, so
+         * we keep ->group_stop_count != 0 before the call. If SIGCONT
+         * or SIGKILL comes in between ->group_stop_count == 0.
+         */
+        if (sig->group_stop_count) {
+                if (!--sig->group_stop_count)
+                        sig->flags = SIGNAL_STOP_STOPPED;
+                current->exit_code = sig->group_exit_code;
+                __set_current_state(TASK_STOPPED);
+        }
+        spin_unlock_irq(&current->sighand->siglock);
 
-        if (stop_count == 0)
-                sig->flags = SIGNAL_STOP_STOPPED;
-        current->exit_code = sig->group_exit_code;
-        __set_current_state(TASK_STOPPED);
+        if (notify) {
+                read_lock(&tasklist_lock);
+                do_notify_parent_cldstop(current, notify);
+                read_unlock(&tasklist_lock);
+        }
+
+        /* Now we don't run again until woken by SIGCONT or SIGKILL */
+        do {
+                schedule();
+        } while (try_to_freeze());
+
+        tracehook_finish_jctl();
+        current->exit_code = 0;
 
-        spin_unlock_irq(&current->sighand->siglock);
-        finish_stop(stop_count);
         return 1;
 }
 
@@ -1815,14 +1793,15 @@ relock:
                 int why = (signal->flags & SIGNAL_STOP_CONTINUED)
                                 ? CLD_CONTINUED : CLD_STOPPED;
                 signal->flags &= ~SIGNAL_CLD_MASK;
-                spin_unlock_irq(&sighand->siglock);
 
-                if (unlikely(!tracehook_notify_jctl(1, why)))
-                        goto relock;
+                why = tracehook_notify_jctl(why, CLD_CONTINUED);
+                spin_unlock_irq(&sighand->siglock);
 
-                read_lock(&tasklist_lock);
-                do_notify_parent_cldstop(current->group_leader, why);
-                read_unlock(&tasklist_lock);
+                if (why) {
+                        read_lock(&tasklist_lock);
+                        do_notify_parent_cldstop(current->group_leader, why);
+                        read_unlock(&tasklist_lock);
+                }
                 goto relock;
         }
 
@@ -1987,14 +1966,14 @@ void exit_signals(struct task_struct *tsk)
         if (unlikely(tsk->signal->group_stop_count) &&
                         !--tsk->signal->group_stop_count) {
                 tsk->signal->flags = SIGNAL_STOP_STOPPED;
-                group_stop = 1;
+                group_stop = tracehook_notify_jctl(CLD_STOPPED, CLD_STOPPED);
         }
 out:
         spin_unlock_irq(&tsk->sighand->siglock);
 
-        if (unlikely(group_stop) && tracehook_notify_jctl(1, CLD_STOPPED)) {
+        if (unlikely(group_stop)) {
                 read_lock(&tasklist_lock);
-                do_notify_parent_cldstop(tsk, CLD_STOPPED);
+                do_notify_parent_cldstop(tsk, group_stop);
                 read_unlock(&tasklist_lock);
         }
 }
@@ -2290,7 +2269,6 @@ static int
 do_send_specific(pid_t tgid, pid_t pid, int sig, struct siginfo *info)
 {
         struct task_struct *p;
-        unsigned long flags;
         int error = -ESRCH;
 
         rcu_read_lock();
@@ -2300,14 +2278,16 @@ do_send_specific(pid_t tgid, pid_t pid, int sig, struct siginfo *info)
                 /*
                  * The null signal is a permissions and process existence
                  * probe.  No signal is actually delivered.
-                 *
-                 * If lock_task_sighand() fails we pretend the task dies
-                 * after receiving the signal. The window is tiny, and the
-                 * signal is private anyway.
                  */
-                if (!error && sig && lock_task_sighand(p, &flags)) {
-                        error = specific_send_sig_info(sig, info, p);
-                        unlock_task_sighand(p, &flags);
+                if (!error && sig) {
+                        error = do_send_sig_info(sig, info, p, false);
+                        /*
+                         * If lock_task_sighand() failed we pretend the task
+                         * dies after receiving the signal. The window is tiny,
+                         * and the signal is private anyway.
+                         */
+                        if (unlikely(error == -ESRCH))
+                                error = 0;
                 }
         }
         rcu_read_unlock();
diff --git a/kernel/slow-work.c b/kernel/slow-work.c
index 09d7519557d3..0d31135efbf4 100644
--- a/kernel/slow-work.c
+++ b/kernel/slow-work.c
@@ -26,10 +26,10 @@ static void slow_work_cull_timeout(unsigned long);
 static void slow_work_oom_timeout(unsigned long);
 
 #ifdef CONFIG_SYSCTL
-static int slow_work_min_threads_sysctl(struct ctl_table *, int, struct file *,
+static int slow_work_min_threads_sysctl(struct ctl_table *, int,
                                         void __user *, size_t *, loff_t *);
 
-static int slow_work_max_threads_sysctl(struct ctl_table *, int , struct file *,
+static int slow_work_max_threads_sysctl(struct ctl_table *, int ,
                                         void __user *, size_t *, loff_t *);
 #endif
 
@@ -493,10 +493,10 @@ static void slow_work_oom_timeout(unsigned long data)
  * Handle adjustment of the minimum number of threads
  */
 static int slow_work_min_threads_sysctl(struct ctl_table *table, int write,
-                                        struct file *filp, void __user *buffer,
+                                        void __user *buffer,
                                         size_t *lenp, loff_t *ppos)
 {
-        int ret = proc_dointvec_minmax(table, write, filp, buffer, lenp, ppos);
+        int ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
         int n;
 
         if (ret == 0) {
@@ -521,10 +521,10 @@ static int slow_work_min_threads_sysctl(struct ctl_table *table, int write,
  * Handle adjustment of the maximum number of threads
  */
 static int slow_work_max_threads_sysctl(struct ctl_table *table, int write,
-                                        struct file *filp, void __user *buffer,
+                                        void __user *buffer,
                                         size_t *lenp, loff_t *ppos)
 {
-        int ret = proc_dointvec_minmax(table, write, filp, buffer, lenp, ppos);
+        int ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
         int n;
 
         if (ret == 0) {
diff --git a/kernel/softlockup.c b/kernel/softlockup.c
index 88796c330838..81324d12eb35 100644
--- a/kernel/softlockup.c
+++ b/kernel/softlockup.c
@@ -90,11 +90,11 @@ void touch_all_softlockup_watchdogs(void)
 EXPORT_SYMBOL(touch_all_softlockup_watchdogs);
 
 int proc_dosoftlockup_thresh(struct ctl_table *table, int write,
-                             struct file *filp, void __user *buffer,
+                             void __user *buffer,
                              size_t *lenp, loff_t *ppos)
 {
         touch_all_softlockup_watchdogs();
-        return proc_dointvec_minmax(table, write, filp, buffer, lenp, ppos);
+        return proc_dointvec_minmax(table, write, buffer, lenp, ppos);
 }
 
 /*
diff --git a/kernel/sys.c b/kernel/sys.c
index ebcb15611728..255475d163e0 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -1542,6 +1542,28 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
                                 current->timer_slack_ns = arg2;
                         error = 0;
                         break;
+                case PR_MCE_KILL:
+                        if (arg4 | arg5)
+                                return -EINVAL;
+                        switch (arg2) {
+                        case 0:
+                                if (arg3 != 0)
+                                        return -EINVAL;
+                                current->flags &= ~PF_MCE_PROCESS;
+                                break;
+                        case 1:
+                                current->flags |= PF_MCE_PROCESS;
+                                if (arg3 != 0)
+                                        current->flags |= PF_MCE_EARLY;
+                                else
+                                        current->flags &= ~PF_MCE_EARLY;
+                                break;
+                        default:
+                                return -EINVAL;
+                        }
+                        error = 0;
+                        break;
+
                 default:
                         error = -EINVAL;
                         break;
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 7f4f57bea4ce..0d949c517412 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -76,6 +76,7 @@ extern int max_threads;
 extern int core_uses_pid;
 extern int suid_dumpable;
 extern char core_pattern[];
+extern unsigned int core_pipe_limit;
 extern int pid_max;
 extern int min_free_kbytes;
 extern int pid_max_min, pid_max_max;
@@ -162,9 +163,9 @@ extern int max_lock_depth;
 #endif
 
 #ifdef CONFIG_PROC_SYSCTL
-static int proc_do_cad_pid(struct ctl_table *table, int write, struct file *filp,
+static int proc_do_cad_pid(struct ctl_table *table, int write,
                   void __user *buffer, size_t *lenp, loff_t *ppos);
-static int proc_taint(struct ctl_table *table, int write, struct file *filp,
+static int proc_taint(struct ctl_table *table, int write,
                                void __user *buffer, size_t *lenp, loff_t *ppos);
 #endif
 
@@ -423,6 +424,14 @@ static struct ctl_table kern_table[] = {
                 .proc_handler   = &proc_dostring,
                 .strategy       = &sysctl_string,
         },
+        {
+                .ctl_name       = CTL_UNNUMBERED,
+                .procname       = "core_pipe_limit",
+                .data           = &core_pipe_limit,
+                .maxlen         = sizeof(unsigned int),
+                .mode           = 0644,
+                .proc_handler   = &proc_dointvec,
+        },
 #ifdef CONFIG_PROC_SYSCTL
         {
                 .procname       = "tainted",
@@ -1389,6 +1398,31 @@ static struct ctl_table vm_table[] = {
                 .mode           = 0644,
                 .proc_handler   = &scan_unevictable_handler,
         },
+#ifdef CONFIG_MEMORY_FAILURE
+        {
+                .ctl_name       = CTL_UNNUMBERED,
+                .procname       = "memory_failure_early_kill",
+                .data           = &sysctl_memory_failure_early_kill,
+                .maxlen         = sizeof(sysctl_memory_failure_early_kill),
+                .mode           = 0644,
+                .proc_handler   = &proc_dointvec_minmax,
+                .strategy       = &sysctl_intvec,
+                .extra1         = &zero,
+                .extra2         = &one,
+        },
+        {
+                .ctl_name       = CTL_UNNUMBERED,
+                .procname       = "memory_failure_recovery",
+                .data           = &sysctl_memory_failure_recovery,
+                .maxlen         = sizeof(sysctl_memory_failure_recovery),
+                .mode           = 0644,
+                .proc_handler   = &proc_dointvec_minmax,
+                .strategy       = &sysctl_intvec,
+                .extra1         = &zero,
+                .extra2         = &one,
+        },
+#endif
+
 /*
  * NOTE: do not add new entries to this table unless you have read
  * Documentation/sysctl/ctl_unnumbered.txt
@@ -2217,7 +2251,7 @@ void sysctl_head_put(struct ctl_table_header *head)
 #ifdef CONFIG_PROC_SYSCTL
 
 static int _proc_do_string(void* data, int maxlen, int write,
-                           struct file *filp, void __user *buffer,
+                           void __user *buffer,
                            size_t *lenp, loff_t *ppos)
 {
         size_t len;
@@ -2278,7 +2312,6 @@ static int _proc_do_string(void* data, int maxlen, int write,
  * proc_dostring - read a string sysctl
  * @table: the sysctl table
  * @write: %TRUE if this is a write to the sysctl file
- * @filp: the file structure
  * @buffer: the user buffer
  * @lenp: the size of the user buffer
  * @ppos: file position
@@ -2292,10 +2325,10 @@ static int _proc_do_string(void* data, int maxlen, int write,
  *
  * Returns 0 on success.
  */
-int proc_dostring(struct ctl_table *table, int write, struct file *filp,
+int proc_dostring(struct ctl_table *table, int write,
                   void __user *buffer, size_t *lenp, loff_t *ppos)
 {
-        return _proc_do_string(table->data, table->maxlen, write, filp,
+        return _proc_do_string(table->data, table->maxlen, write,
                                buffer, lenp, ppos);
 }
 
@@ -2320,7 +2353,7 @@ static int do_proc_dointvec_conv(int *negp, unsigned long *lvalp,
 }
 
 static int __do_proc_dointvec(void *tbl_data, struct ctl_table *table,
-                  int write, struct file *filp, void __user *buffer,
+                  int write, void __user *buffer,
                   size_t *lenp, loff_t *ppos,
                   int (*conv)(int *negp, unsigned long *lvalp, int *valp,
                               int write, void *data),
@@ -2427,13 +2460,13 @@ static int __do_proc_dointvec(void *tbl_data, struct ctl_table *table,
 #undef TMPBUFLEN
 }
 
-static int do_proc_dointvec(struct ctl_table *table, int write, struct file *filp,
+static int do_proc_dointvec(struct ctl_table *table, int write,
                   void __user *buffer, size_t *lenp, loff_t *ppos,
                   int (*conv)(int *negp, unsigned long *lvalp, int *valp,
                               int write, void *data),
                   void *data)
 {
-        return __do_proc_dointvec(table->data, table, write, filp,
+        return __do_proc_dointvec(table->data, table, write,
                         buffer, lenp, ppos, conv, data);
 }
 
@@ -2441,7 +2474,6 @@ static int do_proc_dointvec(struct ctl_table *table, int write, struct file *fil
  * proc_dointvec - read a vector of integers
  * @table: the sysctl table
  * @write: %TRUE if this is a write to the sysctl file
- * @filp: the file structure
  * @buffer: the user buffer
  * @lenp: the size of the user buffer
  * @ppos: file position
@@ -2451,10 +2483,10 @@ static int do_proc_dointvec(struct ctl_table *table, int write, struct file *fil
  *
  * Returns 0 on success.
  */
-int proc_dointvec(struct ctl_table *table, int write, struct file *filp,
+int proc_dointvec(struct ctl_table *table, int write,
                      void __user *buffer, size_t *lenp, loff_t *ppos)
 {
-    return do_proc_dointvec(table,write,filp,buffer,lenp,ppos,
+    return do_proc_dointvec(table,write,buffer,lenp,ppos,
                             NULL,NULL);
 }
 
@@ -2462,7 +2494,7 @@ int proc_dointvec(struct ctl_table *table, int write, struct file *filp,
  * Taint values can only be increased
  * This means we can safely use a temporary.
  */
-static int proc_taint(struct ctl_table *table, int write, struct file *filp,
+static int proc_taint(struct ctl_table *table, int write,
                                void __user *buffer, size_t *lenp, loff_t *ppos)
 {
         struct ctl_table t;
@@ -2474,7 +2506,7 @@ static int proc_taint(struct ctl_table *table, int write, struct file *filp,
 
         t = *table;
         t.data = &tmptaint;
-        err = proc_doulongvec_minmax(&t, write, filp, buffer, lenp, ppos);
+        err = proc_doulongvec_minmax(&t, write, buffer, lenp, ppos);
         if (err < 0)
                 return err;
 
@@ -2526,7 +2558,6 @@ static int do_proc_dointvec_minmax_conv(int *negp, unsigned long *lvalp,
  * proc_dointvec_minmax - read a vector of integers with min/max values
  * @table: the sysctl table
  * @write: %TRUE if this is a write to the sysctl file
- * @filp: the file structure
  * @buffer: the user buffer
  * @lenp: the size of the user buffer
  * @ppos: file position
@@ -2539,19 +2570,18 @@ static int do_proc_dointvec_minmax_conv(int *negp, unsigned long *lvalp,
  *
  * Returns 0 on success.
  */
-int proc_dointvec_minmax(struct ctl_table *table, int write, struct file *filp,
+int proc_dointvec_minmax(struct ctl_table *table, int write,
                   void __user *buffer, size_t *lenp, loff_t *ppos)
 {
         struct do_proc_dointvec_minmax_conv_param param = {
                 .min = (int *) table->extra1,
                 .max = (int *) table->extra2,
         };
-        return do_proc_dointvec(table, write, filp, buffer, lenp, ppos,
+        return do_proc_dointvec(table, write, buffer, lenp, ppos,
                                 do_proc_dointvec_minmax_conv, &param);
 }
 
 static int __do_proc_doulongvec_minmax(void *data, struct ctl_table *table, int write,
-                                     struct file *filp,
                                      void __user *buffer,
                                      size_t *lenp, loff_t *ppos,
                                      unsigned long convmul,
@@ -2656,21 +2686,19 @@ static int __do_proc_doulongvec_minmax(void *data, struct ctl_table *table, int
 }
 
 static int do_proc_doulongvec_minmax(struct ctl_table *table, int write,
-                                     struct file *filp,
                                      void __user *buffer,
                                      size_t *lenp, loff_t *ppos,
                                      unsigned long convmul,
                                      unsigned long convdiv)
 {
         return __do_proc_doulongvec_minmax(table->data, table, write,
-                        filp, buffer, lenp, ppos, convmul, convdiv);
+                        buffer, lenp, ppos, convmul, convdiv);
 }
 
 /**
  * proc_doulongvec_minmax - read a vector of long integers with min/max values
  * @table: the sysctl table
  * @write: %TRUE if this is a write to the sysctl file
- * @filp: the file structure
  * @buffer: the user buffer
  * @lenp: the size of the user buffer
  * @ppos: file position
@@ -2683,17 +2711,16 @@ static int do_proc_doulongvec_minmax(struct ctl_table *table, int write,
  *
  * Returns 0 on success.
  */
-int proc_doulongvec_minmax(struct ctl_table *table, int write, struct file *filp,
+int proc_doulongvec_minmax(struct ctl_table *table, int write,
                            void __user *buffer, size_t *lenp, loff_t *ppos)
 {
-    return do_proc_doulongvec_minmax(table, write, filp, buffer, lenp, ppos, 1l, 1l);
+    return do_proc_doulongvec_minmax(table, write, buffer, lenp, ppos, 1l, 1l);
 }
 
 /**
  * proc_doulongvec_ms_jiffies_minmax - read a vector of millisecond values with min/max values
  * @table: the sysctl table
  * @write: %TRUE if this is a write to the sysctl file
- * @filp: the file structure
  * @buffer: the user buffer
  * @lenp: the size of the user buffer
  * @ppos: file position
@@ -2708,11 +2735,10 @@ int proc_doulongvec_minmax(struct ctl_table *table, int write, struct file *filp
  * Returns 0 on success.
  */
 int proc_doulongvec_ms_jiffies_minmax(struct ctl_table *table, int write,
-                                      struct file *filp,
                                       void __user *buffer,
                                       size_t *lenp, loff_t *ppos)
 {
-    return do_proc_doulongvec_minmax(table, write, filp, buffer,
+    return do_proc_doulongvec_minmax(table, write, buffer,
                                      lenp, ppos, HZ, 1000l);
 }
 
@@ -2788,7 +2814,6 @@ static int do_proc_dointvec_ms_jiffies_conv(int *negp, unsigned long *lvalp,
  * proc_dointvec_jiffies - read a vector of integers as seconds
  * @table: the sysctl table
  * @write: %TRUE if this is a write to the sysctl file
- * @filp: the file structure
  * @buffer: the user buffer
  * @lenp: the size of the user buffer
  * @ppos: file position
@@ -2800,10 +2825,10 @@ static int do_proc_dointvec_ms_jiffies_conv(int *negp, unsigned long *lvalp,
  *
  * Returns 0 on success.
  */
-int proc_dointvec_jiffies(struct ctl_table *table, int write, struct file *filp,
+int proc_dointvec_jiffies(struct ctl_table *table, int write,
                           void __user *buffer, size_t *lenp, loff_t *ppos)
 {
-    return do_proc_dointvec(table,write,filp,buffer,lenp,ppos,
+    return do_proc_dointvec(table,write,buffer,lenp,ppos,
                             do_proc_dointvec_jiffies_conv,NULL);
 }
 
@@ -2811,7 +2836,6 @@ int proc_dointvec_jiffies(struct ctl_table *table, int write, struct file *filp,
  * proc_dointvec_userhz_jiffies - read a vector of integers as 1/USER_HZ seconds
  * @table: the sysctl table
  * @write: %TRUE if this is a write to the sysctl file
- * @filp: the file structure
  * @buffer: the user buffer
  * @lenp: the size of the user buffer
  * @ppos: pointer to the file position
@@ -2823,10 +2847,10 @@ int proc_dointvec_jiffies(struct ctl_table *table, int write, struct file *filp,
  *
  * Returns 0 on success.
  */
-int proc_dointvec_userhz_jiffies(struct ctl_table *table, int write, struct file *filp,
+int proc_dointvec_userhz_jiffies(struct ctl_table *table, int write,
                                  void __user *buffer, size_t *lenp, loff_t *ppos)
 {
-    return do_proc_dointvec(table,write,filp,buffer,lenp,ppos,
+    return do_proc_dointvec(table,write,buffer,lenp,ppos,
                             do_proc_dointvec_userhz_jiffies_conv,NULL);
 }
 
@@ -2834,7 +2858,6 @@ int proc_dointvec_userhz_jiffies(struct ctl_table *table, int write, struct file
  * proc_dointvec_ms_jiffies - read a vector of integers as 1 milliseconds
  * @table: the sysctl table
  * @write: %TRUE if this is a write to the sysctl file
- * @filp: the file structure
  * @buffer: the user buffer
  * @lenp: the size of the user buffer
  * @ppos: file position
@@ -2847,14 +2870,14 @@ int proc_dointvec_userhz_jiffies(struct ctl_table *table, int write, struct file
  *
  * Returns 0 on success.
  */
-int proc_dointvec_ms_jiffies(struct ctl_table *table, int write, struct file *filp,
+int proc_dointvec_ms_jiffies(struct ctl_table *table, int write,
                              void __user *buffer, size_t *lenp, loff_t *ppos)
 {
-        return do_proc_dointvec(table, write, filp, buffer, lenp, ppos,
+        return do_proc_dointvec(table, write, buffer, lenp, ppos,
                                 do_proc_dointvec_ms_jiffies_conv, NULL);
 }
 
-static int proc_do_cad_pid(struct ctl_table *table, int write, struct file *filp,
+static int proc_do_cad_pid(struct ctl_table *table, int write,
                            void __user *buffer, size_t *lenp, loff_t *ppos)
 {
         struct pid *new_pid;
@@ -2863,7 +2886,7 @@ static int proc_do_cad_pid(struct ctl_table *table, int write, struct file *filp
 
         tmp = pid_vnr(cad_pid);
 
-        r = __do_proc_dointvec(&tmp, table, write, filp, buffer,
+        r = __do_proc_dointvec(&tmp, table, write, buffer,
                                lenp, ppos, NULL, NULL);
         if (r || !write)
                 return r;
@@ -2878,50 +2901,49 @@ static int proc_do_cad_pid(struct ctl_table *table, int write, struct file *filp
 
 #else /* CONFIG_PROC_FS */
 
-int proc_dostring(struct ctl_table *table, int write, struct file *filp,
+int proc_dostring(struct ctl_table *table, int write,
                   void __user *buffer, size_t *lenp, loff_t *ppos)
 {
         return -ENOSYS;
 }
 
-int proc_dointvec(struct ctl_table *table, int write, struct file *filp,
+int proc_dointvec(struct ctl_table *table, int write,
                   void __user *buffer, size_t *lenp, loff_t *ppos)
 {
         return -ENOSYS;
 }
 
-int proc_dointvec_minmax(struct ctl_table *table, int write, struct file *filp,
+int proc_dointvec_minmax(struct ctl_table *table, int write,
                     void __user *buffer, size_t *lenp, loff_t *ppos)
 {
         return -ENOSYS;
 }
 
-int proc_dointvec_jiffies(struct ctl_table *table, int write, struct file *filp,
+int proc_dointvec_jiffies(struct ctl_table *table, int write,
                     void __user *buffer, size_t *lenp, loff_t *ppos)
 {
         return -ENOSYS;
 }
 
-int proc_dointvec_userhz_jiffies(struct ctl_table *table, int write, struct file *filp,
+int proc_dointvec_userhz_jiffies(struct ctl_table *table, int write,
                     void __user *buffer, size_t *lenp, loff_t *ppos)
 {
         return -ENOSYS;
 }
 
-int proc_dointvec_ms_jiffies(struct ctl_table *table, int write, struct file *filp,
+int proc_dointvec_ms_jiffies(struct ctl_table *table, int write,
                              void __user *buffer, size_t *lenp, loff_t *ppos)
 {
         return -ENOSYS;
 }
 
-int proc_doulongvec_minmax(struct ctl_table *table, int write, struct file *filp,
+int proc_doulongvec_minmax(struct ctl_table *table, int write,
                     void __user *buffer, size_t *lenp, loff_t *ppos)
 {
         return -ENOSYS;
 }
 
 int proc_doulongvec_ms_jiffies_minmax(struct ctl_table *table, int write,
-                                      struct file *filp,
                                       void __user *buffer,
                                       size_t *lenp, loff_t *ppos)
 {
diff --git a/kernel/time/Makefile b/kernel/time/Makefile
index 0b0a6366c9d4..ee266620b06c 100644
--- a/kernel/time/Makefile
+++ b/kernel/time/Makefile
@@ -1,4 +1,4 @@
-obj-y += timekeeping.o ntp.o clocksource.o jiffies.o timer_list.o timecompare.o
+obj-y += timekeeping.o ntp.o clocksource.o jiffies.o timer_list.o timecompare.o timeconv.o
 
 obj-$(CONFIG_GENERIC_CLOCKEVENTS_BUILD)         += clockevents.o
 obj-$(CONFIG_GENERIC_CLOCKEVENTS)               += tick-common.o
diff --git a/kernel/time/timeconv.c b/kernel/time/timeconv.c
new file mode 100644
index 000000000000..86628e755f38
--- /dev/null
+++ b/kernel/time/timeconv.c
@@ -0,0 +1,127 @@
+/*
+ * Copyright (C) 1993, 1994, 1995, 1996, 1997 Free Software Foundation, Inc.
+ * This file is part of the GNU C Library.
+ * Contributed by Paul Eggert (eggert@twinsun.com).
+ *
+ * The GNU C Library is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU Library General Public License as
+ * published by the Free Software Foundation; either version 2 of the
+ * License, or (at your option) any later version.
+ *
+ * The GNU C Library is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * Library General Public License for more details.
+ *
+ * You should have received a copy of the GNU Library General Public
+ * License along with the GNU C Library; see the file COPYING.LIB.  If not,
+ * write to the Free Software Foundation, Inc., 59 Temple Place - Suite 330,
+ * Boston, MA 02111-1307, USA.
+ */
+
+/*
+ * Converts the calendar time to broken-down time representation
+ * Based on code from glibc-2.6
+ *
+ * 2009-7-14:
+ *   Moved from glibc-2.6 to kernel by Zhaolei<zhaolei@cn.fujitsu.com>
+ */
+
+#include <linux/time.h>
+#include <linux/module.h>
+
+/*
+ * Nonzero if YEAR is a leap year (every 4 years,
+ * except every 100th isn't, and every 400th is).
+ */
+static int __isleap(long year)
+{
+        return (year) % 4 == 0 && ((year) % 100 != 0 || (year) % 400 == 0);
+}
+
+/* do a mathdiv for long type */
+static long math_div(long a, long b)
+{
+        return a / b - (a % b < 0);
+}
+
+/* How many leap years between y1 and y2, y1 must less or equal to y2 */
+static long leaps_between(long y1, long y2)
+{
+        long leaps1 = math_div(y1 - 1, 4) - math_div(y1 - 1, 100)
+                + math_div(y1 - 1, 400);
+        long leaps2 = math_div(y2 - 1, 4) - math_div(y2 - 1, 100)
+                + math_div(y2 - 1, 400);
+        return leaps2 - leaps1;
+}
+
+/* How many days come before each month (0-12). */
+static const unsigned short __mon_yday[2][13] = {
+        /* Normal years. */
+        {0, 31, 59, 90, 120, 151, 181, 212, 243, 273, 304, 334, 365},
+        /* Leap years. */
+        {0, 31, 60, 91, 121, 152, 182, 213, 244, 274, 305, 335, 366}
+};
+
+#define SECS_PER_HOUR   (60 * 60)
+#define SECS_PER_DAY    (SECS_PER_HOUR * 24)
+
+/**
+ * time_to_tm - converts the calendar time to local broken-down time
+ *
+ * @totalsecs   the number of seconds elapsed since 00:00:00 on January 1, 1970,
+ *              Coordinated Universal Time (UTC).
+ * @offset      offset seconds adding to totalsecs.
+ * @result      pointer to struct tm variable to receive broken-down time
+ */
+void time_to_tm(time_t totalsecs, int offset, struct tm *result)
+{
+        long days, rem, y;
+        const unsigned short *ip;
+
+        days = totalsecs / SECS_PER_DAY;
+        rem = totalsecs % SECS_PER_DAY;
+        rem += offset;
+        while (rem < 0) {
+                rem += SECS_PER_DAY;
+                --days;
+        }
+        while (rem >= SECS_PER_DAY) {
+                rem -= SECS_PER_DAY;
+                ++days;
+        }
+
+        result->tm_hour = rem / SECS_PER_HOUR;
+        rem %= SECS_PER_HOUR;
+        result->tm_min = rem / 60;
+        result->tm_sec = rem % 60;
+
+        /* January 1, 1970 was a Thursday. */
+        result->tm_wday = (4 + days) % 7;
+        if (result->tm_wday < 0)
+                result->tm_wday += 7;
+
+        y = 1970;
+
+        while (days < 0 || days >= (__isleap(y) ? 366 : 365)) {
+                /* Guess a corrected year, assuming 365 days per year. */
+                long yg = y + math_div(days, 365);
+
+                /* Adjust DAYS and Y to match the guessed year. */
+                days -= (yg - y) * 365 + leaps_between(y, yg);
+                y = yg;
+        }
+
+        result->tm_year = y - 1900;
+
+        result->tm_yday = days;
+
+        ip = __mon_yday[__isleap(y)];
+        for (y = 11; days < ip[y]; y--)
+                continue;
+        days -= ip[y];
+
+        result->tm_mon = y;
+        result->tm_mday = days + 1;
+}
+EXPORT_SYMBOL(time_to_tm);
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 23df7771c937..a142579765bf 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -3015,7 +3015,7 @@ int unregister_ftrace_function(struct ftrace_ops *ops)
 
 int
 ftrace_enable_sysctl(struct ctl_table *table, int write,
-                     struct file *file, void __user *buffer, size_t *lenp,
+                     void __user *buffer, size_t *lenp,
                      loff_t *ppos)
 {
         int ret;
@@ -3025,7 +3025,7 @@ ftrace_enable_sysctl(struct ctl_table *table, int write,
 
         mutex_lock(&ftrace_lock);
 
-        ret  = proc_dointvec(table, write, file, buffer, lenp, ppos);
+        ret  = proc_dointvec(table, write, buffer, lenp, ppos);
 
         if (ret || !write || (last_ftrace_enabled == !!ftrace_enabled))
                 goto out;
diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index 0f6facb050a1..8504ac71e4e8 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -296,14 +296,14 @@ static const struct file_operations stack_trace_fops = {
 
 int
 stack_trace_sysctl(struct ctl_table *table, int write,
-                   struct file *file, void __user *buffer, size_t *lenp,
+                   void __user *buffer, size_t *lenp,
                    loff_t *ppos)
 {
         int ret;
 
         mutex_lock(&stack_sysctl_mutex);
 
-        ret = proc_dointvec(table, write, file, buffer, lenp, ppos);
+        ret = proc_dointvec(table, write, buffer, lenp, ppos);
 
         if (ret || !write ||
             (last_stack_tracer_enabled == !!stack_tracer_enabled))
diff --git a/kernel/utsname_sysctl.c b/kernel/utsname_sysctl.c
index 92359cc747a7..69eae358a726 100644
--- a/kernel/utsname_sysctl.c
+++ b/kernel/utsname_sysctl.c
@@ -42,14 +42,14 @@ static void put_uts(ctl_table *table, int write, void *which)
  *      Special case of dostring for the UTS structure. This has locks
  *      to observe. Should this be in kernel/sys.c ????
  */
-static int proc_do_uts_string(ctl_table *table, int write, struct file *filp,
+static int proc_do_uts_string(ctl_table *table, int write,
                   void __user *buffer, size_t *lenp, loff_t *ppos)
 {
         struct ctl_table uts_table;
         int r;
         memcpy(&uts_table, table, sizeof(uts_table));
         uts_table.data = get_uts(table, write);
-        r = proc_dostring(&uts_table,write,filp,buffer,lenp, ppos);
+        r = proc_dostring(&uts_table,write,buffer,lenp, ppos);
         put_uts(table, write, uts_table.data);
         return r;
 }