124 files changed, 6229 insertions, 4860 deletions

diff --git a/kernel/Makefile b/kernel/Makefile
index bc010ee272b6..f2a8b6246ce9 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -18,11 +18,13 @@ CFLAGS_REMOVE_cgroup-debug.o = -pg
 CFLAGS_REMOVE_irq_work.o = -pg
 endif
 
+# cond_syscall is currently not LTO compatible
+CFLAGS_sys_ni.o = $(DISABLE_LTO)
+
 obj-y += sched/
 obj-y += locking/
 obj-y += power/
 obj-y += printk/
-obj-y += cpu/
 obj-y += irq/
 obj-y += rcu/
 
@@ -93,6 +95,7 @@ obj-$(CONFIG_PADATA) += padata.o
 obj-$(CONFIG_CRASH_DUMP) += crash_dump.o
 obj-$(CONFIG_JUMP_LABEL) += jump_label.o
 obj-$(CONFIG_CONTEXT_TRACKING) += context_tracking.o
+obj-$(CONFIG_TORTURE_TEST) += torture.o
 
 $(obj)/configs.o: $(obj)/config_data.h
 
diff --git a/kernel/audit.c b/kernel/audit.c
index 3392d3e0254a..95a20f3f52f1 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -608,9 +608,19 @@ static int audit_netlink_ok(struct sk_buff *skb, u16 msg_type)
         int err = 0;
 
         /* Only support the initial namespaces for now. */
+        /*
+         * We return ECONNREFUSED because it tricks userspace into thinking
+         * that audit was not configured into the kernel.  Lots of users
+         * configure their PAM stack (because that's what the distro does)
+         * to reject login if unable to send messages to audit.  If we return
+         * ECONNREFUSED the PAM stack thinks the kernel does not have audit
+         * configured in and will let login proceed.  If we return EPERM
+         * userspace will reject all logins.  This should be removed when we
+         * support non init namespaces!!
+         */
         if ((current_user_ns() != &init_user_ns) ||
             (task_active_pid_ns(current) != &init_pid_ns))
-                return -EPERM;
+                return -ECONNREFUSED;
 
         switch (msg_type) {
         case AUDIT_LIST:
diff --git a/kernel/capability.c b/kernel/capability.c
index 34019c57888d..a8d63df0c322 100644
--- a/kernel/capability.c
+++ b/kernel/capability.c
@@ -7,6 +7,8 @@
  * 30 May 2002: Cleanup, Robert M. Love <rml@tech9.net>
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/audit.h>
 #include <linux/capability.h>
 #include <linux/mm.h>
@@ -42,15 +44,10 @@ __setup("no_file_caps", file_caps_disable);
 
 static void warn_legacy_capability_use(void)
 {
-        static int warned;
-        if (!warned) {
-                char name[sizeof(current->comm)];
-
-                printk(KERN_INFO "warning: `%s' uses 32-bit capabilities"
-                       " (legacy support in use)\n",
-                       get_task_comm(name, current));
-                warned = 1;
-        }
+        char name[sizeof(current->comm)];
+
+        pr_info_once("warning: `%s' uses 32-bit capabilities (legacy support in use)\n",
+                     get_task_comm(name, current));
 }
 
 /*
@@ -71,16 +68,10 @@ static void warn_legacy_capability_use(void)
 
 static void warn_deprecated_v2(void)
 {
-        static int warned;
+        char name[sizeof(current->comm)];
 
-        if (!warned) {
-                char name[sizeof(current->comm)];
-
-                printk(KERN_INFO "warning: `%s' uses deprecated v2"
-                       " capabilities in a way that may be insecure.\n",
-                       get_task_comm(name, current));
-                warned = 1;
-        }
+        pr_info_once("warning: `%s' uses deprecated v2 capabilities in a way that may be insecure\n",
+                     get_task_comm(name, current));
 }
 
 /*
@@ -380,7 +371,7 @@ bool has_capability_noaudit(struct task_struct *t, int cap)
 bool ns_capable(struct user_namespace *ns, int cap)
 {
         if (unlikely(!cap_valid(cap))) {
-                printk(KERN_CRIT "capable() called with invalid cap=%u\n", cap);
+                pr_crit("capable() called with invalid cap=%u\n", cap);
                 BUG();
         }
 
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 105f273b6f86..fede3d3f28ff 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -40,23 +40,20 @@
 #include <linux/proc_fs.h>
 #include <linux/rcupdate.h>
 #include <linux/sched.h>
-#include <linux/backing-dev.h>
 #include <linux/slab.h>
-#include <linux/magic.h>
 #include <linux/spinlock.h>
+#include <linux/rwsem.h>
 #include <linux/string.h>
 #include <linux/sort.h>
 #include <linux/kmod.h>
-#include <linux/module.h>
 #include <linux/delayacct.h>
 #include <linux/cgroupstats.h>
 #include <linux/hashtable.h>
-#include <linux/namei.h>
 #include <linux/pid_namespace.h>
 #include <linux/idr.h>
 #include <linux/vmalloc.h> /* TODO: replace with more sophisticated array */
-#include <linux/flex_array.h> /* used in cgroup_attach_task */
 #include <linux/kthread.h>
+#include <linux/delay.h>
 
 #include <linux/atomic.h>
 
@@ -68,43 +65,49 @@
  */
 #define CGROUP_PIDLIST_DESTROY_DELAY    HZ
 
+#define CGROUP_FILE_NAME_MAX            (MAX_CGROUP_TYPE_NAMELEN +      \
+                                         MAX_CFTYPE_NAME + 2)
+
+/*
+ * cgroup_tree_mutex nests above cgroup_mutex and protects cftypes, file
+ * creation/removal and hierarchy changing operations including cgroup
+ * creation, removal, css association and controller rebinding.  This outer
+ * lock is needed mainly to resolve the circular dependency between kernfs
+ * active ref and cgroup_mutex.  cgroup_tree_mutex nests above both.
+ */
+static DEFINE_MUTEX(cgroup_tree_mutex);
+
 /*
  * cgroup_mutex is the master lock.  Any modification to cgroup or its
  * hierarchy must be performed while holding it.
  *
- * cgroup_root_mutex nests inside cgroup_mutex and should be held to modify
- * cgroupfs_root of any cgroup hierarchy - subsys list, flags,
- * release_agent_path and so on.  Modifying requires both cgroup_mutex and
- * cgroup_root_mutex.  Readers can acquire either of the two.  This is to
- * break the following locking order cycle.
- *
- *  A. cgroup_mutex -> cred_guard_mutex -> s_type->i_mutex_key -> namespace_sem
- *  B. namespace_sem -> cgroup_mutex
+ * css_set_rwsem protects task->cgroups pointer, the list of css_set
+ * objects, and the chain of tasks off each css_set.
  *
- * B happens only through cgroup_show_options() and using cgroup_root_mutex
- * breaks it.
+ * These locks are exported if CONFIG_PROVE_RCU so that accessors in
+ * cgroup.h can use them for lockdep annotations.
  */
 #ifdef CONFIG_PROVE_RCU
 DEFINE_MUTEX(cgroup_mutex);
-EXPORT_SYMBOL_GPL(cgroup_mutex);        /* only for lockdep */
+DECLARE_RWSEM(css_set_rwsem);
+EXPORT_SYMBOL_GPL(cgroup_mutex);
+EXPORT_SYMBOL_GPL(css_set_rwsem);
 #else
 static DEFINE_MUTEX(cgroup_mutex);
+static DECLARE_RWSEM(css_set_rwsem);
 #endif
 
-static DEFINE_MUTEX(cgroup_root_mutex);
+/*
+ * Protects cgroup_subsys->release_agent_path.  Modifying it also requires
+ * cgroup_mutex.  Reading requires either cgroup_mutex or this spinlock.
+ */
+static DEFINE_SPINLOCK(release_agent_path_lock);
 
-#define cgroup_assert_mutex_or_rcu_locked()                             \
+#define cgroup_assert_mutexes_or_rcu_locked()                           \
         rcu_lockdep_assert(rcu_read_lock_held() ||                      \
+                           lockdep_is_held(&cgroup_tree_mutex) ||       \
                            lockdep_is_held(&cgroup_mutex),              \
-                           "cgroup_mutex or RCU read lock required");
-
-#ifdef CONFIG_LOCKDEP
-#define cgroup_assert_mutex_or_root_locked()                            \
-        WARN_ON_ONCE(debug_locks && (!lockdep_is_held(&cgroup_mutex) && \
-                                     !lockdep_is_held(&cgroup_root_mutex)))
-#else
-#define cgroup_assert_mutex_or_root_locked()    do { } while (0)
-#endif
+                           "cgroup_[tree_]mutex or RCU read lock required");
 
 /*
  * cgroup destruction makes heavy use of work items and there can be a lot
@@ -120,42 +123,41 @@ static struct workqueue_struct *cgroup_destroy_wq;
  */
 static struct workqueue_struct *cgroup_pidlist_destroy_wq;
 
-/*
- * Generate an array of cgroup subsystem pointers. At boot time, this is
- * populated with the built in subsystems, and modular subsystems are
- * registered after that. The mutable section of this array is protected by
- * cgroup_mutex.
- */
-#define SUBSYS(_x) [_x ## _subsys_id] = &_x ## _subsys,
-#define IS_SUBSYS_ENABLED(option) IS_BUILTIN(option)
-static struct cgroup_subsys *cgroup_subsys[CGROUP_SUBSYS_COUNT] = {
+/* generate an array of cgroup subsystem pointers */
+#define SUBSYS(_x) [_x ## _cgrp_id] = &_x ## _cgrp_subsys,
+static struct cgroup_subsys *cgroup_subsys[] = {
+#include <linux/cgroup_subsys.h>
+};
+#undef SUBSYS
+
+/* array of cgroup subsystem names */
+#define SUBSYS(_x) [_x ## _cgrp_id] = #_x,
+static const char *cgroup_subsys_name[] = {
 #include <linux/cgroup_subsys.h>
 };
+#undef SUBSYS
 
 /*
- * The dummy hierarchy, reserved for the subsystems that are otherwise
+ * The default hierarchy, reserved for the subsystems that are otherwise
  * unattached - it never has more than a single cgroup, and all tasks are
  * part of that cgroup.
  */
-static struct cgroupfs_root cgroup_dummy_root;
+struct cgroup_root cgrp_dfl_root;
 
-/* dummy_top is a shorthand for the dummy hierarchy's top cgroup */
-static struct cgroup * const cgroup_dummy_top = &cgroup_dummy_root.top_cgroup;
+/*
+ * The default hierarchy always exists but is hidden until mounted for the
+ * first time.  This is for backward compatibility.
+ */
+static bool cgrp_dfl_root_visible;
 
 /* The list of hierarchy roots */
 
 static LIST_HEAD(cgroup_roots);
 static int cgroup_root_count;
 
-/*
- * Hierarchy ID allocation and mapping.  It follows the same exclusion
- * rules as other root ops - both cgroup_mutex and cgroup_root_mutex for
- * writes, either for reads.
- */
+/* hierarchy ID allocation and mapping, protected by cgroup_mutex */
 static DEFINE_IDR(cgroup_hierarchy_idr);
 
-static struct cgroup_name root_cgroup_name = { .name = "/" };
-
 /*
  * Assign a monotonically increasing serial number to cgroups.  It
  * guarantees cgroups with bigger numbers are newer than those with smaller
@@ -175,11 +177,13 @@ static int need_forkexit_callback __read_mostly;
 
 static struct cftype cgroup_base_files[];
 
+static void cgroup_put(struct cgroup *cgrp);
+static int rebind_subsystems(struct cgroup_root *dst_root,
+                             unsigned long ss_mask);
 static void cgroup_destroy_css_killed(struct cgroup *cgrp);
 static int cgroup_destroy_locked(struct cgroup *cgrp);
 static int cgroup_addrm_files(struct cgroup *cgrp, struct cftype cfts[],
                               bool is_add);
-static int cgroup_file_release(struct inode *inode, struct file *file);
 static void cgroup_pidlist_destroy_all(struct cgroup *cgrp);
 
 /**
@@ -197,8 +201,9 @@ static struct cgroup_subsys_state *cgroup_css(struct cgroup *cgrp,
                                               struct cgroup_subsys *ss)
 {
         if (ss)
-                return rcu_dereference_check(cgrp->subsys[ss->subsys_id],
-                                             lockdep_is_held(&cgroup_mutex));
+                return rcu_dereference_check(cgrp->subsys[ss->id],
+                                        lockdep_is_held(&cgroup_tree_mutex) ||
+                                        lockdep_is_held(&cgroup_mutex));
         else
                 return &cgrp->dummy_css;
 }
@@ -209,6 +214,27 @@ static inline bool cgroup_is_dead(const struct cgroup *cgrp)
         return test_bit(CGRP_DEAD, &cgrp->flags);
 }
 
+struct cgroup_subsys_state *seq_css(struct seq_file *seq)
+{
+        struct kernfs_open_file *of = seq->private;
+        struct cgroup *cgrp = of->kn->parent->priv;
+        struct cftype *cft = seq_cft(seq);
+
+        /*
+         * This is open and unprotected implementation of cgroup_css().
+         * seq_css() is only called from a kernfs file operation which has
+         * an active reference on the file.  Because all the subsystem
+         * files are drained before a css is disassociated with a cgroup,
+         * the matching css from the cgroup's subsys table is guaranteed to
+         * be and stay valid until the enclosing operation is complete.
+         */
+        if (cft->ss)
+                return rcu_dereference_raw(cgrp->subsys[cft->ss->id]);
+        else
+                return &cgrp->dummy_css;
+}
+EXPORT_SYMBOL_GPL(seq_css);
+
 /**
  * cgroup_is_descendant - test ancestry
  * @cgrp: the cgroup to be tested
@@ -227,7 +253,6 @@ bool cgroup_is_descendant(struct cgroup *cgrp, struct cgroup *ancestor)
         }
         return false;
 }
-EXPORT_SYMBOL_GPL(cgroup_is_descendant);
 
 static int cgroup_is_releasable(const struct cgroup *cgrp)
 {
@@ -254,54 +279,23 @@ static int notify_on_release(const struct cgroup *cgrp)
         for ((ssid) = 0; (ssid) < CGROUP_SUBSYS_COUNT; (ssid)++)        \
                 if (!((css) = rcu_dereference_check(                    \
                                 (cgrp)->subsys[(ssid)],                 \
+                                lockdep_is_held(&cgroup_tree_mutex) ||  \
                                 lockdep_is_held(&cgroup_mutex)))) { }   \
                 else
 
 /**
- * for_each_subsys - iterate all loaded cgroup subsystems
+ * for_each_subsys - iterate all enabled cgroup subsystems
  * @ss: the iteration cursor
  * @ssid: the index of @ss, CGROUP_SUBSYS_COUNT after reaching the end
- *
- * Iterates through all loaded subsystems.  Should be called under
- * cgroup_mutex or cgroup_root_mutex.
  */
 #define for_each_subsys(ss, ssid)                                       \
-        for (({ cgroup_assert_mutex_or_root_locked(); (ssid) = 0; });   \
-             (ssid) < CGROUP_SUBSYS_COUNT; (ssid)++)                    \
-                if (!((ss) = cgroup_subsys[(ssid)])) { }                \
-                else
+        for ((ssid) = 0; (ssid) < CGROUP_SUBSYS_COUNT &&                \
+             (((ss) = cgroup_subsys[ssid]) || true); (ssid)++)
 
-/**
- * for_each_builtin_subsys - iterate all built-in cgroup subsystems
- * @ss: the iteration cursor
- * @i: the index of @ss, CGROUP_BUILTIN_SUBSYS_COUNT after reaching the end
- *
- * Bulit-in subsystems are always present and iteration itself doesn't
- * require any synchronization.
- */
-#define for_each_builtin_subsys(ss, i)                                  \
-        for ((i) = 0; (i) < CGROUP_BUILTIN_SUBSYS_COUNT &&              \
-             (((ss) = cgroup_subsys[i]) || true); (i)++)
-
-/* iterate across the active hierarchies */
-#define for_each_active_root(root)                                      \
+/* iterate across the hierarchies */
+#define for_each_root(root)                                             \
         list_for_each_entry((root), &cgroup_roots, root_list)
 
-static inline struct cgroup *__d_cgrp(struct dentry *dentry)
-{
-        return dentry->d_fsdata;
-}
-
-static inline struct cfent *__d_cfe(struct dentry *dentry)
-{
-        return dentry->d_fsdata;
-}
-
-static inline struct cftype *__d_cft(struct dentry *dentry)
-{
-        return __d_cfe(dentry)->type;
-}
-
 /**
  * cgroup_lock_live_group - take cgroup_mutex and check that cgrp is alive.
  * @cgrp: the cgroup to be checked for liveness
@@ -347,23 +341,23 @@ struct cgrp_cset_link {
         struct list_head        cgrp_link;
 };
 
-/* The default css_set - used by init and its children prior to any
+/*
+ * The default css_set - used by init and its children prior to any
  * hierarchies being mounted. It contains a pointer to the root state
  * for each subsystem. Also used to anchor the list of css_sets. Not
  * reference-counted, to improve performance when child cgroups
  * haven't been created.
  */
+static struct css_set init_css_set = {
+        .refcount               = ATOMIC_INIT(1),
+        .cgrp_links             = LIST_HEAD_INIT(init_css_set.cgrp_links),
+        .tasks                  = LIST_HEAD_INIT(init_css_set.tasks),
+        .mg_tasks               = LIST_HEAD_INIT(init_css_set.mg_tasks),
+        .mg_preload_node        = LIST_HEAD_INIT(init_css_set.mg_preload_node),
+        .mg_node                = LIST_HEAD_INIT(init_css_set.mg_node),
+};
 
-static struct css_set init_css_set;
-static struct cgrp_cset_link init_cgrp_cset_link;
-
-/*
- * css_set_lock protects the list of css_set objects, and the chain of
- * tasks off each css_set.  Nests outside task->alloc_lock due to
- * css_task_iter_start().
- */
-static DEFINE_RWLOCK(css_set_lock);
-static int css_set_count;
+static int css_set_count        = 1;    /* 1 for init_css_set */
 
 /*
  * hash table for cgroup groups. This improves the performance to find
@@ -386,30 +380,14 @@ static unsigned long css_set_hash(struct cgroup_subsys_state *css[])
         return key;
 }
 
-/*
- * We don't maintain the lists running through each css_set to its task
- * until after the first call to css_task_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;
-
-static void __put_css_set(struct css_set *cset, int taskexit)
+static void put_css_set_locked(struct css_set *cset, bool taskexit)
 {
         struct cgrp_cset_link *link, *tmp_link;
 
-        /*
-         * Ensure that the refcount doesn't hit zero while any readers
-         * can see it. Similar to atomic_dec_and_lock(), but for an
-         * rwlock
-         */
-        if (atomic_add_unless(&cset->refcount, -1, 1))
-                return;
-        write_lock(&css_set_lock);
-        if (!atomic_dec_and_test(&cset->refcount)) {
-                write_unlock(&css_set_lock);
+        lockdep_assert_held(&css_set_rwsem);
+
+        if (!atomic_dec_and_test(&cset->refcount))
                 return;
-        }
 
         /* This css_set is dead. unlink it and release cgroup refcounts */
         hash_del(&cset->hlist);
@@ -421,7 +399,7 @@ static void __put_css_set(struct css_set *cset, int taskexit)
                 list_del(&link->cset_link);
                 list_del(&link->cgrp_link);
 
-                /* @cgrp can't go away while we're holding css_set_lock */
+                /* @cgrp can't go away while we're holding css_set_rwsem */
                 if (list_empty(&cgrp->cset_links) && notify_on_release(cgrp)) {
                         if (taskexit)
                                 set_bit(CGRP_RELEASABLE, &cgrp->flags);
@@ -431,10 +409,24 @@ static void __put_css_set(struct css_set *cset, int taskexit)
                 kfree(link);
         }
 
-        write_unlock(&css_set_lock);
         kfree_rcu(cset, rcu_head);
 }
 
+static void put_css_set(struct css_set *cset, bool taskexit)
+{
+        /*
+         * Ensure that the refcount doesn't hit zero while any readers
+         * can see it. Similar to atomic_dec_and_lock(), but for an
+         * rwlock
+         */
+        if (atomic_add_unless(&cset->refcount, -1, 1))
+                return;
+
+        down_write(&css_set_rwsem);
+        put_css_set_locked(cset, taskexit);
+        up_write(&css_set_rwsem);
+}
+
 /*
  * refcounted get/put for css_set objects
  */
@@ -443,16 +435,6 @@ static inline void get_css_set(struct css_set *cset)
         atomic_inc(&cset->refcount);
 }
 
-static inline void put_css_set(struct css_set *cset)
-{
-        __put_css_set(cset, 0);
-}
-
-static inline void put_css_set_taskexit(struct css_set *cset)
-{
-        __put_css_set(cset, 1);
-}
-
 /**
  * compare_css_sets - helper function for find_existing_css_set().
  * @cset: candidate css_set being tested
@@ -535,7 +517,7 @@ static struct css_set *find_existing_css_set(struct css_set *old_cset,
                                         struct cgroup *cgrp,
                                         struct cgroup_subsys_state *template[])
 {
-        struct cgroupfs_root *root = cgrp->root;
+        struct cgroup_root *root = cgrp->root;
         struct cgroup_subsys *ss;
         struct css_set *cset;
         unsigned long key;
@@ -547,7 +529,7 @@ static struct css_set *find_existing_css_set(struct css_set *old_cset,
          * won't change, so no need for locking.
          */
         for_each_subsys(ss, i) {
-                if (root->subsys_mask & (1UL << i)) {
+                if (root->cgrp.subsys_mask & (1UL << i)) {
                         /* Subsystem is in this hierarchy. So we want
                          * the subsystem state from the new
                          * cgroup */
@@ -652,11 +634,11 @@ static struct css_set *find_css_set(struct css_set *old_cset,
 
         /* First see if we already have a cgroup group that matches
          * the desired set */
-        read_lock(&css_set_lock);
+        down_read(&css_set_rwsem);
         cset = find_existing_css_set(old_cset, cgrp, template);
         if (cset)
                 get_css_set(cset);
-        read_unlock(&css_set_lock);
+        up_read(&css_set_rwsem);
 
         if (cset)
                 return cset;
@@ -674,13 +656,16 @@ static struct css_set *find_css_set(struct css_set *old_cset,
         atomic_set(&cset->refcount, 1);
         INIT_LIST_HEAD(&cset->cgrp_links);
         INIT_LIST_HEAD(&cset->tasks);
+        INIT_LIST_HEAD(&cset->mg_tasks);
+        INIT_LIST_HEAD(&cset->mg_preload_node);
+        INIT_LIST_HEAD(&cset->mg_node);
         INIT_HLIST_NODE(&cset->hlist);
 
         /* Copy the set of subsystem state objects generated in
          * find_existing_css_set() */
         memcpy(cset->subsys, template, sizeof(cset->subsys));
 
-        write_lock(&css_set_lock);
+        down_write(&css_set_rwsem);
         /* Add reference counts and links from the new css_set. */
         list_for_each_entry(link, &old_cset->cgrp_links, cgrp_link) {
                 struct cgroup *c = link->cgrp;
@@ -698,31 +683,105 @@ static struct css_set *find_css_set(struct css_set *old_cset,
         key = css_set_hash(cset->subsys);
         hash_add(css_set_table, &cset->hlist, key);
 
-        write_unlock(&css_set_lock);
+        up_write(&css_set_rwsem);
 
         return cset;
 }
 
-/*
- * 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)
+static struct cgroup_root *cgroup_root_from_kf(struct kernfs_root *kf_root)
 {
-        struct css_set *cset;
-        struct cgroup *res = NULL;
+        struct cgroup *root_cgrp = kf_root->kn->priv;
+
+        return root_cgrp->root;
+}
+
+static int cgroup_init_root_id(struct cgroup_root *root)
+{
+        int id;
+
+        lockdep_assert_held(&cgroup_mutex);
+
+        id = idr_alloc_cyclic(&cgroup_hierarchy_idr, root, 0, 0, GFP_KERNEL);
+        if (id < 0)
+                return id;
+
+        root->hierarchy_id = id;
+        return 0;
+}
+
+static void cgroup_exit_root_id(struct cgroup_root *root)
+{
+        lockdep_assert_held(&cgroup_mutex);
+
+        if (root->hierarchy_id) {
+                idr_remove(&cgroup_hierarchy_idr, root->hierarchy_id);
+                root->hierarchy_id = 0;
+        }
+}
+
+static void cgroup_free_root(struct cgroup_root *root)
+{
+        if (root) {
+                /* hierarhcy ID shoulid already have been released */
+                WARN_ON_ONCE(root->hierarchy_id);
+
+                idr_destroy(&root->cgroup_idr);
+                kfree(root);
+        }
+}
+
+static void cgroup_destroy_root(struct cgroup_root *root)
+{
+        struct cgroup *cgrp = &root->cgrp;
+        struct cgrp_cset_link *link, *tmp_link;
+
+        mutex_lock(&cgroup_tree_mutex);
+        mutex_lock(&cgroup_mutex);
+
+        BUG_ON(atomic_read(&root->nr_cgrps));
+        BUG_ON(!list_empty(&cgrp->children));
+
+        /* Rebind all subsystems back to the default hierarchy */
+        rebind_subsystems(&cgrp_dfl_root, cgrp->subsys_mask);
 
-        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.
+         * Release all the links from cset_links to this hierarchy's
+         * root cgroup
          */
-        cset = task_css_set(task);
+        down_write(&css_set_rwsem);
+
+        list_for_each_entry_safe(link, tmp_link, &cgrp->cset_links, cset_link) {
+                list_del(&link->cset_link);
+                list_del(&link->cgrp_link);
+                kfree(link);
+        }
+        up_write(&css_set_rwsem);
+
+        if (!list_empty(&root->root_list)) {
+                list_del(&root->root_list);
+                cgroup_root_count--;
+        }
+
+        cgroup_exit_root_id(root);
+
+        mutex_unlock(&cgroup_mutex);
+        mutex_unlock(&cgroup_tree_mutex);
+
+        kernfs_destroy_root(root->kf_root);
+        cgroup_free_root(root);
+}
+
+/* look up cgroup associated with given css_set on the specified hierarchy */
+static struct cgroup *cset_cgroup_from_root(struct css_set *cset,
+                                            struct cgroup_root *root)
+{
+        struct cgroup *res = NULL;
+
+        lockdep_assert_held(&cgroup_mutex);
+        lockdep_assert_held(&css_set_rwsem);
+
         if (cset == &init_css_set) {
-                res = &root->top_cgroup;
+                res = &root->cgrp;
         } else {
                 struct cgrp_cset_link *link;
 
@@ -735,16 +794,27 @@ static struct cgroup *task_cgroup_from_root(struct task_struct *task,
                         }
                 }
         }
-        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.
- *
+ * Return the cgroup for "task" from the given hierarchy. Must be
+ * called with cgroup_mutex and css_set_rwsem held.
+ */
+static struct cgroup *task_cgroup_from_root(struct task_struct *task,
+                                            struct cgroup_root *root)
+{
+        /*
+         * 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.
+         */
+        return cset_cgroup_from_root(task_css_set(task), root);
+}
+
+/*
  * A task must hold cgroup_mutex to modify cgroups.
  *
  * Any task can increment and decrement the count field without lock.
@@ -770,98 +840,79 @@ static struct cgroup *task_cgroup_from_root(struct task_struct *task,
  * A cgroup can only be deleted if both its 'count' of using tasks
  * is zero, and its list of 'children' cgroups is empty.  Since all
  * tasks in the system use _some_ cgroup, and since there is always at
- * least one task in the system (init, pid == 1), therefore, top_cgroup
+ * least one task in the system (init, pid == 1), therefore, root cgroup
  * always has either children cgroups and/or using tasks.  So we don't
- * need a special hack to ensure that top_cgroup cannot be deleted.
- *
- *      The task_lock() exception
- *
- * The need for this exception arises from the action of
- * cgroup_attach_task(), which overwrites one task's cgroup pointer with
- * another.  It does so using cgroup_mutex, however there are
- * several performance critical places that need to reference
- * task->cgroup without the expense of grabbing a system global
- * mutex.  Therefore except as noted below, when dereferencing or, as
- * in cgroup_attach_task(), modifying a task's cgroup pointer we use
- * task_lock(), which acts on a spinlock (task->alloc_lock) already in
- * the task_struct routinely used for such matters.
+ * need a special hack to ensure that root cgroup cannot be deleted.
  *
  * P.S.  One more locking exception.  RCU is used to guard the
  * update of a tasks cgroup pointer by cgroup_attach_task()
  */
 
-/*
- * A couple of forward declarations required, due to cyclic reference loop:
- * cgroup_mkdir -> cgroup_create -> cgroup_populate_dir ->
- * cgroup_add_file -> cgroup_create_file -> cgroup_dir_inode_operations
- * -> cgroup_mkdir.
- */
-
-static int cgroup_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode);
-static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry);
 static int cgroup_populate_dir(struct cgroup *cgrp, unsigned long subsys_mask);
-static const struct inode_operations cgroup_dir_inode_operations;
+static struct kernfs_syscall_ops cgroup_kf_syscall_ops;
 static const struct file_operations proc_cgroupstats_operations;
 
-static struct backing_dev_info cgroup_backing_dev_info = {
-        .name           = "cgroup",
-        .capabilities   = BDI_CAP_NO_ACCT_AND_WRITEBACK,
-};
-
-static struct inode *cgroup_new_inode(umode_t mode, struct super_block *sb)
+static char *cgroup_file_name(struct cgroup *cgrp, const struct cftype *cft,
+                              char *buf)
 {
-        struct inode *inode = new_inode(sb);
-
-        if (inode) {
-                inode->i_ino = get_next_ino();
-                inode->i_mode = mode;
-                inode->i_uid = current_fsuid();
-                inode->i_gid = current_fsgid();
-                inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
-                inode->i_mapping->backing_dev_info = &cgroup_backing_dev_info;
-        }
-        return inode;
+        if (cft->ss && !(cft->flags & CFTYPE_NO_PREFIX) &&
+            !(cgrp->root->flags & CGRP_ROOT_NOPREFIX))
+                snprintf(buf, CGROUP_FILE_NAME_MAX, "%s.%s",
+                         cft->ss->name, cft->name);
+        else
+                strncpy(buf, cft->name, CGROUP_FILE_NAME_MAX);
+        return buf;
 }
 
-static struct cgroup_name *cgroup_alloc_name(struct dentry *dentry)
+/**
+ * cgroup_file_mode - deduce file mode of a control file
+ * @cft: the control file in question
+ *
+ * returns cft->mode if ->mode is not 0
+ * returns S_IRUGO|S_IWUSR if it has both a read and a write handler
+ * returns S_IRUGO if it has only a read handler
+ * returns S_IWUSR if it has only a write hander
+ */
+static umode_t cgroup_file_mode(const struct cftype *cft)
 {
-        struct cgroup_name *name;
+        umode_t mode = 0;
 
-        name = kmalloc(sizeof(*name) + dentry->d_name.len + 1, GFP_KERNEL);
-        if (!name)
-                return NULL;
-        strcpy(name->name, dentry->d_name.name);
-        return name;
+        if (cft->mode)
+                return cft->mode;
+
+        if (cft->read_u64 || cft->read_s64 || cft->seq_show)
+                mode |= S_IRUGO;
+
+        if (cft->write_u64 || cft->write_s64 || cft->write_string ||
+            cft->trigger)
+                mode |= S_IWUSR;
+
+        return mode;
 }
 
 static void cgroup_free_fn(struct work_struct *work)
 {
         struct cgroup *cgrp = container_of(work, struct cgroup, destroy_work);
 
-        mutex_lock(&cgroup_mutex);
-        cgrp->root->number_of_cgroups--;
-        mutex_unlock(&cgroup_mutex);
-
-        /*
-         * We get a ref to the parent's dentry, and put the ref when
-         * this cgroup is being freed, so it's guaranteed that the
-         * parent won't be destroyed before its children.
-         */
-        dput(cgrp->parent->dentry);
-
-        /*
-         * Drop the active superblock reference that we took when we
-         * created the cgroup. This will free cgrp->root, if we are
-         * holding the last reference to @sb.
-         */
-        deactivate_super(cgrp->root->sb);
-
+        atomic_dec(&cgrp->root->nr_cgrps);
         cgroup_pidlist_destroy_all(cgrp);
 
-        simple_xattrs_free(&cgrp->xattrs);
-
-        kfree(rcu_dereference_raw(cgrp->name));
-        kfree(cgrp);
+        if (cgrp->parent) {
+                /*
+                 * We get a ref to the parent, and put the ref when this
+                 * cgroup is being freed, so it's guaranteed that the
+                 * parent won't be destroyed before its children.
+                 */
+                cgroup_put(cgrp->parent);
+                kernfs_put(cgrp->kn);
+                kfree(cgrp);
+        } else {
+                /*
+                 * This is root cgroup's refcnt reaching zero, which
+                 * indicates that the root should be released.
+                 */
+                cgroup_destroy_root(cgrp->root);
+        }
 }
 
 static void cgroup_free_rcu(struct rcu_head *head)
@@ -872,73 +923,40 @@ static void cgroup_free_rcu(struct rcu_head *head)
         queue_work(cgroup_destroy_wq, &cgrp->destroy_work);
 }
 
-static void cgroup_diput(struct dentry *dentry, struct inode *inode)
-{
-        /* is dentry a directory ? if so, kfree() associated cgroup */
-        if (S_ISDIR(inode->i_mode)) {
-                struct cgroup *cgrp = dentry->d_fsdata;
-
-                BUG_ON(!(cgroup_is_dead(cgrp)));
-
-                /*
-                 * XXX: cgrp->id is only used to look up css's.  As cgroup
-                 * and css's lifetimes will be decoupled, it should be made
-                 * per-subsystem and moved to css->id so that lookups are
-                 * successful until the target css is released.
-                 */
-                mutex_lock(&cgroup_mutex);
-                idr_remove(&cgrp->root->cgroup_idr, cgrp->id);
-                mutex_unlock(&cgroup_mutex);
-                cgrp->id = -1;
-
-                call_rcu(&cgrp->rcu_head, cgroup_free_rcu);
-        } else {
-                struct cfent *cfe = __d_cfe(dentry);
-                struct cgroup *cgrp = dentry->d_parent->d_fsdata;
-
-                WARN_ONCE(!list_empty(&cfe->node) &&
-                          cgrp != &cgrp->root->top_cgroup,
-                          "cfe still linked for %s\n", cfe->type->name);
-                simple_xattrs_free(&cfe->xattrs);
-                kfree(cfe);
-        }
-        iput(inode);
-}
-
-static void remove_dir(struct dentry *d)
+static void cgroup_get(struct cgroup *cgrp)
 {
-        struct dentry *parent = dget(d->d_parent);
-
-        d_delete(d);
-        simple_rmdir(parent->d_inode, d);
-        dput(parent);
+        WARN_ON_ONCE(cgroup_is_dead(cgrp));
+        WARN_ON_ONCE(atomic_read(&cgrp->refcnt) <= 0);
+        atomic_inc(&cgrp->refcnt);
 }
 
-static void cgroup_rm_file(struct cgroup *cgrp, const struct cftype *cft)
+static void cgroup_put(struct cgroup *cgrp)
 {
-        struct cfent *cfe;
-
-        lockdep_assert_held(&cgrp->dentry->d_inode->i_mutex);
-        lockdep_assert_held(&cgroup_mutex);
+        if (!atomic_dec_and_test(&cgrp->refcnt))
+                return;
+        if (WARN_ON_ONCE(cgrp->parent && !cgroup_is_dead(cgrp)))
+                return;
 
         /*
-         * If we're doing cleanup due to failure of cgroup_create(),
-         * the corresponding @cfe may not exist.
+         * XXX: cgrp->id is only used to look up css's.  As cgroup and
+         * css's lifetimes will be decoupled, it should be made
+         * per-subsystem and moved to css->id so that lookups are
+         * successful until the target css is released.
          */
-        list_for_each_entry(cfe, &cgrp->files, node) {
-                struct dentry *d = cfe->dentry;
+        mutex_lock(&cgroup_mutex);
+        idr_remove(&cgrp->root->cgroup_idr, cgrp->id);
+        mutex_unlock(&cgroup_mutex);
+        cgrp->id = -1;
 
-                if (cft && cfe->type != cft)
-                        continue;
+        call_rcu(&cgrp->rcu_head, cgroup_free_rcu);
+}
 
-                dget(d);
-                d_delete(d);
-                simple_unlink(cgrp->dentry->d_inode, d);
-                list_del_init(&cfe->node);
-                dput(d);
+static void cgroup_rm_file(struct cgroup *cgrp, const struct cftype *cft)
+{
+        char name[CGROUP_FILE_NAME_MAX];
 
-                break;
-        }
+        lockdep_assert_held(&cgroup_tree_mutex);
+        kernfs_remove_by_name(cgrp->kn, cgroup_file_name(cgrp, cft, name));
 }
 
 /**
@@ -952,144 +970,106 @@ static void cgroup_clear_dir(struct cgroup *cgrp, unsigned long subsys_mask)
         int i;
 
         for_each_subsys(ss, i) {
-                struct cftype_set *set;
+                struct cftype *cfts;
 
                 if (!test_bit(i, &subsys_mask))
                         continue;
-                list_for_each_entry(set, &ss->cftsets, node)
-                        cgroup_addrm_files(cgrp, set->cfts, false);
+                list_for_each_entry(cfts, &ss->cfts, node)
+                        cgroup_addrm_files(cgrp, cfts, false);
         }
 }
 
-/*
- * NOTE : the dentry must have been dget()'ed
- */
-static void cgroup_d_remove_dir(struct dentry *dentry)
-{
-        struct dentry *parent;
-
-        parent = dentry->d_parent;
-        spin_lock(&parent->d_lock);
-        spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED);
-        list_del_init(&dentry->d_u.d_child);
-        spin_unlock(&dentry->d_lock);
-        spin_unlock(&parent->d_lock);
-        remove_dir(dentry);
-}
-
-/*
- * Call with cgroup_mutex held. Drops reference counts on modules, including
- * any duplicate ones that parse_cgroupfs_options took. If this function
- * returns an error, no reference counts are touched.
- */
-static int rebind_subsystems(struct cgroupfs_root *root,
-                             unsigned long added_mask, unsigned removed_mask)
+static int rebind_subsystems(struct cgroup_root *dst_root,
+                             unsigned long ss_mask)
 {
-        struct cgroup *cgrp = &root->top_cgroup;
         struct cgroup_subsys *ss;
-        unsigned long pinned = 0;
-        int i, ret;
+        int ssid, ret;
 
-        BUG_ON(!mutex_is_locked(&cgroup_mutex));
-        BUG_ON(!mutex_is_locked(&cgroup_root_mutex));
+        lockdep_assert_held(&cgroup_tree_mutex);
+        lockdep_assert_held(&cgroup_mutex);
 
-        /* Check that any added subsystems are currently free */
-        for_each_subsys(ss, i) {
-                if (!(added_mask & (1 << i)))
+        for_each_subsys(ss, ssid) {
+                if (!(ss_mask & (1 << ssid)))
                         continue;
 
-                /* is the subsystem mounted elsewhere? */
-                if (ss->root != &cgroup_dummy_root) {
-                        ret = -EBUSY;
-                        goto out_put;
-                }
+                /* if @ss is on the dummy_root, we can always move it */
+                if (ss->root == &cgrp_dfl_root)
+                        continue;
 
-                /* pin the module */
-                if (!try_module_get(ss->module)) {
-                        ret = -ENOENT;
-                        goto out_put;
-                }
-                pinned |= 1 << i;
-        }
+                /* if @ss has non-root cgroups attached to it, can't move */
+                if (!list_empty(&ss->root->cgrp.children))
+                        return -EBUSY;
 
-        /* subsys could be missing if unloaded between parsing and here */
-        if (added_mask != pinned) {
-                ret = -ENOENT;
-                goto out_put;
+                /* can't move between two non-dummy roots either */
+                if (dst_root != &cgrp_dfl_root)
+                        return -EBUSY;
         }
 
-        ret = cgroup_populate_dir(cgrp, added_mask);
-        if (ret)
-                goto out_put;
+        ret = cgroup_populate_dir(&dst_root->cgrp, ss_mask);
+        if (ret) {
+                if (dst_root != &cgrp_dfl_root)
+                        return ret;
+
+                /*
+                 * Rebinding back to the default root is not allowed to
+                 * fail.  Using both default and non-default roots should
+                 * be rare.  Moving subsystems back and forth even more so.
+                 * Just warn about it and continue.
+                 */
+                if (cgrp_dfl_root_visible) {
+                        pr_warning("cgroup: failed to create files (%d) while rebinding 0x%lx to default root\n",
+                                   ret, ss_mask);
+                        pr_warning("cgroup: you may retry by moving them to a different hierarchy and unbinding\n");
+                }
+        }
 
         /*
          * Nothing can fail from this point on.  Remove files for the
          * removed subsystems and rebind each subsystem.
          */
-        cgroup_clear_dir(cgrp, removed_mask);
-
-        for_each_subsys(ss, i) {
-                unsigned long bit = 1UL << i;
-
-                if (bit & added_mask) {
-                        /* We're binding this subsystem to this hierarchy */
-                        BUG_ON(cgroup_css(cgrp, ss));
-                        BUG_ON(!cgroup_css(cgroup_dummy_top, ss));
-                        BUG_ON(cgroup_css(cgroup_dummy_top, ss)->cgroup != cgroup_dummy_top);
+        mutex_unlock(&cgroup_mutex);
+        for_each_subsys(ss, ssid)
+                if (ss_mask & (1 << ssid))
+                        cgroup_clear_dir(&ss->root->cgrp, 1 << ssid);
+        mutex_lock(&cgroup_mutex);
 
-                        rcu_assign_pointer(cgrp->subsys[i],
-                                           cgroup_css(cgroup_dummy_top, ss));
-                        cgroup_css(cgrp, ss)->cgroup = cgrp;
+        for_each_subsys(ss, ssid) {
+                struct cgroup_root *src_root;
+                struct cgroup_subsys_state *css;
 
-                        ss->root = root;
-                        if (ss->bind)
-                                ss->bind(cgroup_css(cgrp, ss));
+                if (!(ss_mask & (1 << ssid)))
+                        continue;
 
-                        /* refcount was already taken, and we're keeping it */
-                        root->subsys_mask |= bit;
-                } else if (bit & removed_mask) {
-                        /* We're removing this subsystem */
-                        BUG_ON(cgroup_css(cgrp, ss) != cgroup_css(cgroup_dummy_top, ss));
-                        BUG_ON(cgroup_css(cgrp, ss)->cgroup != cgrp);
+                src_root = ss->root;
+                css = cgroup_css(&src_root->cgrp, ss);
 
-                        if (ss->bind)
-                                ss->bind(cgroup_css(cgroup_dummy_top, ss));
+                WARN_ON(!css || cgroup_css(&dst_root->cgrp, ss));
 
-                        cgroup_css(cgroup_dummy_top, ss)->cgroup = cgroup_dummy_top;
-                        RCU_INIT_POINTER(cgrp->subsys[i], NULL);
+                RCU_INIT_POINTER(src_root->cgrp.subsys[ssid], NULL);
+                rcu_assign_pointer(dst_root->cgrp.subsys[ssid], css);
+                ss->root = dst_root;
+                css->cgroup = &dst_root->cgrp;
 
-                        cgroup_subsys[i]->root = &cgroup_dummy_root;
+                src_root->cgrp.subsys_mask &= ~(1 << ssid);
+                dst_root->cgrp.subsys_mask |= 1 << ssid;
 
-                        /* subsystem is now free - drop reference on module */
-                        module_put(ss->module);
-                        root->subsys_mask &= ~bit;
-                }
+                if (ss->bind)
+                        ss->bind(css);
         }
 
-        /*
-         * Mark @root has finished binding subsystems.  @root->subsys_mask
-         * now matches the bound subsystems.
-         */
-        root->flags |= CGRP_ROOT_SUBSYS_BOUND;
-
+        kernfs_activate(dst_root->cgrp.kn);
         return 0;
-
-out_put:
-        for_each_subsys(ss, i)
-                if (pinned & (1 << i))
-                        module_put(ss->module);
-        return ret;
 }
 
-static int cgroup_show_options(struct seq_file *seq, struct dentry *dentry)
+static int cgroup_show_options(struct seq_file *seq,
+                               struct kernfs_root *kf_root)
 {
-        struct cgroupfs_root *root = dentry->d_sb->s_fs_info;
+        struct cgroup_root *root = cgroup_root_from_kf(kf_root);
         struct cgroup_subsys *ss;
         int ssid;
 
-        mutex_lock(&cgroup_root_mutex);
         for_each_subsys(ss, ssid)
-                if (root->subsys_mask & (1 << ssid))
+                if (root->cgrp.subsys_mask & (1 << ssid))
                         seq_printf(seq, ",%s", ss->name);
         if (root->flags & CGRP_ROOT_SANE_BEHAVIOR)
                 seq_puts(seq, ",sane_behavior");
@@ -1097,13 +1077,16 @@ static int cgroup_show_options(struct seq_file *seq, struct dentry *dentry)
                 seq_puts(seq, ",noprefix");
         if (root->flags & CGRP_ROOT_XATTR)
                 seq_puts(seq, ",xattr");
+
+        spin_lock(&release_agent_path_lock);
         if (strlen(root->release_agent_path))
                 seq_printf(seq, ",release_agent=%s", root->release_agent_path);
-        if (test_bit(CGRP_CPUSET_CLONE_CHILDREN, &root->top_cgroup.flags))
+        spin_unlock(&release_agent_path_lock);
+
+        if (test_bit(CGRP_CPUSET_CLONE_CHILDREN, &root->cgrp.flags))
                 seq_puts(seq, ",clone_children");
         if (strlen(root->name))
                 seq_printf(seq, ",name=%s", root->name);
-        mutex_unlock(&cgroup_root_mutex);
         return 0;
 }
 
@@ -1115,9 +1098,6 @@ struct cgroup_sb_opts {
         char *name;
         /* User explicitly requested empty subsystem */
         bool none;
-
-        struct cgroupfs_root *new_root;
-
 };
 
 /*
@@ -1137,7 +1117,7 @@ static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts)
         BUG_ON(!mutex_is_locked(&cgroup_mutex));
 
 #ifdef CONFIG_CPUSETS
-        mask = ~(1UL << cpuset_subsys_id);
+        mask = ~(1UL << cpuset_cgrp_id);
 #endif
 
         memset(opts, 0, sizeof(*opts));
@@ -1227,30 +1207,34 @@ static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts)
                         return -ENOENT;
         }
 
-        /*
-         * If the 'all' option was specified select all the subsystems,
-         * otherwise if 'none', 'name=' and a subsystem name options
-         * were not specified, let's default to 'all'
-         */
-        if (all_ss || (!one_ss && !opts->none && !opts->name))
-                for_each_subsys(ss, i)
-                        if (!ss->disabled)
-                                set_bit(i, &opts->subsys_mask);
-
         /* Consistency checks */
 
         if (opts->flags & CGRP_ROOT_SANE_BEHAVIOR) {
                 pr_warning("cgroup: sane_behavior: this is still under development and its behaviors will change, proceed at your own risk\n");
 
-                if (opts->flags & CGRP_ROOT_NOPREFIX) {
-                        pr_err("cgroup: sane_behavior: noprefix is not allowed\n");
+                if ((opts->flags & (CGRP_ROOT_NOPREFIX | CGRP_ROOT_XATTR)) ||
+                    opts->cpuset_clone_children || opts->release_agent ||
+                    opts->name) {
+                        pr_err("cgroup: sane_behavior: noprefix, xattr, clone_children, release_agent and name are not allowed\n");
                         return -EINVAL;
                 }
+        } else {
+                /*
+                 * If the 'all' option was specified select all the
+                 * subsystems, otherwise if 'none', 'name=' and a subsystem
+                 * name options were not specified, let's default to 'all'
+                 */
+                if (all_ss || (!one_ss && !opts->none && !opts->name))
+                        for_each_subsys(ss, i)
+                                if (!ss->disabled)
+                                        set_bit(i, &opts->subsys_mask);
 
-                if (opts->cpuset_clone_children) {
-                        pr_err("cgroup: sane_behavior: clone_children is not allowed\n");
+                /*
+                 * We either have to specify by name or by subsystems. (So
+                 * all empty hierarchies must have a name).
+                 */
+                if (!opts->subsys_mask && !opts->name)
                         return -EINVAL;
-                }
         }
 
         /*
@@ -1266,21 +1250,13 @@ static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts)
         if (opts->subsys_mask && 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_mask && !opts->name)
-                return -EINVAL;
-
         return 0;
 }
 
-static int cgroup_remount(struct super_block *sb, int *flags, char *data)
+static int cgroup_remount(struct kernfs_root *kf_root, int *flags, char *data)
 {
         int ret = 0;
-        struct cgroupfs_root *root = sb->s_fs_info;
-        struct cgroup *cgrp = &root->top_cgroup;
+        struct cgroup_root *root = cgroup_root_from_kf(kf_root);
         struct cgroup_sb_opts opts;
         unsigned long added_mask, removed_mask;
 
@@ -1289,21 +1265,20 @@ static int cgroup_remount(struct super_block *sb, int *flags, char *data)
                 return -EINVAL;
         }
 
-        mutex_lock(&cgrp->dentry->d_inode->i_mutex);
+        mutex_lock(&cgroup_tree_mutex);
         mutex_lock(&cgroup_mutex);
-        mutex_lock(&cgroup_root_mutex);
 
         /* See what subsystems are wanted */
         ret = parse_cgroupfs_options(data, &opts);
         if (ret)
                 goto out_unlock;
 
-        if (opts.subsys_mask != root->subsys_mask || opts.release_agent)
+        if (opts.subsys_mask != root->cgrp.subsys_mask || opts.release_agent)
                 pr_warning("cgroup: option changes via remount are deprecated (pid=%d comm=%s)\n",
                            task_tgid_nr(current), current->comm);
 
-        added_mask = opts.subsys_mask & ~root->subsys_mask;
-        removed_mask = root->subsys_mask & ~opts.subsys_mask;
+        added_mask = opts.subsys_mask & ~root->cgrp.subsys_mask;
+        removed_mask = root->cgrp.subsys_mask & ~opts.subsys_mask;
 
         /* Don't allow flags or name to change at remount */
         if (((opts.flags ^ root->flags) & CGRP_ROOT_OPTION_MASK) ||
@@ -1316,422 +1291,331 @@ static int cgroup_remount(struct super_block *sb, int *flags, char *data)
         }
 
         /* remounting is not allowed for populated hierarchies */
-        if (root->number_of_cgroups > 1) {
+        if (!list_empty(&root->cgrp.children)) {
                 ret = -EBUSY;
                 goto out_unlock;
         }
 
-        ret = rebind_subsystems(root, added_mask, removed_mask);
+        ret = rebind_subsystems(root, added_mask);
         if (ret)
                 goto out_unlock;
 
-        if (opts.release_agent)
+        rebind_subsystems(&cgrp_dfl_root, removed_mask);
+
+        if (opts.release_agent) {
+                spin_lock(&release_agent_path_lock);
                 strcpy(root->release_agent_path, opts.release_agent);
+                spin_unlock(&release_agent_path_lock);
+        }
  out_unlock:
         kfree(opts.release_agent);
         kfree(opts.name);
-        mutex_unlock(&cgroup_root_mutex);
         mutex_unlock(&cgroup_mutex);
-        mutex_unlock(&cgrp->dentry->d_inode->i_mutex);
+        mutex_unlock(&cgroup_tree_mutex);
         return ret;
 }
 
-static const struct super_operations cgroup_ops = {
-        .statfs = simple_statfs,
-        .drop_inode = generic_delete_inode,
-        .show_options = cgroup_show_options,
-        .remount_fs = cgroup_remount,
-};
+/*
+ * To reduce the fork() overhead for systems that are not actually using
+ * their cgroups capability, we don't maintain the lists running through
+ * each css_set to its tasks until we see the list actually used - in other
+ * words after the first mount.
+ */
+static bool use_task_css_set_links __read_mostly;
+
+static void cgroup_enable_task_cg_lists(void)
+{
+        struct task_struct *p, *g;
+
+        down_write(&css_set_rwsem);
+
+        if (use_task_css_set_links)
+                goto out_unlock;
+
+        use_task_css_set_links = true;
+
+        /*
+         * We need tasklist_lock because RCU is not safe against
+         * while_each_thread(). Besides, a forking task that has passed
+         * cgroup_post_fork() without seeing use_task_css_set_links = 1
+         * is not guaranteed to have its child immediately visible in the
+         * tasklist if we walk through it with RCU.
+         */
+        read_lock(&tasklist_lock);
+        do_each_thread(g, p) {
+                WARN_ON_ONCE(!list_empty(&p->cg_list) ||
+                             task_css_set(p) != &init_css_set);
+
+                /*
+                 * We should check if the process is exiting, otherwise
+                 * it will race with cgroup_exit() in that the list
+                 * entry won't be deleted though the process has exited.
+                 * Do it while holding siglock so that we don't end up
+                 * racing against cgroup_exit().
+                 */
+                spin_lock_irq(&p->sighand->siglock);
+                if (!(p->flags & PF_EXITING)) {
+                        struct css_set *cset = task_css_set(p);
+
+                        list_add(&p->cg_list, &cset->tasks);
+                        get_css_set(cset);
+                }
+                spin_unlock_irq(&p->sighand->siglock);
+        } while_each_thread(g, p);
+        read_unlock(&tasklist_lock);
+out_unlock:
+        up_write(&css_set_rwsem);
+}
 
 static void init_cgroup_housekeeping(struct cgroup *cgrp)
 {
+        atomic_set(&cgrp->refcnt, 1);
         INIT_LIST_HEAD(&cgrp->sibling);
         INIT_LIST_HEAD(&cgrp->children);
-        INIT_LIST_HEAD(&cgrp->files);
         INIT_LIST_HEAD(&cgrp->cset_links);
         INIT_LIST_HEAD(&cgrp->release_list);
         INIT_LIST_HEAD(&cgrp->pidlists);
         mutex_init(&cgrp->pidlist_mutex);
         cgrp->dummy_css.cgroup = cgrp;
-        simple_xattrs_init(&cgrp->xattrs);
 }
 
-static void init_cgroup_root(struct cgroupfs_root *root)
+static void init_cgroup_root(struct cgroup_root *root,
+                             struct cgroup_sb_opts *opts)
 {
-        struct cgroup *cgrp = &root->top_cgroup;
+        struct cgroup *cgrp = &root->cgrp;
 
         INIT_LIST_HEAD(&root->root_list);
-        root->number_of_cgroups = 1;
+        atomic_set(&root->nr_cgrps, 1);
         cgrp->root = root;
-        RCU_INIT_POINTER(cgrp->name, &root_cgroup_name);
         init_cgroup_housekeeping(cgrp);
         idr_init(&root->cgroup_idr);
-}
-
-static int cgroup_init_root_id(struct cgroupfs_root *root, int start, int end)
-{
-        int id;
-
-        lockdep_assert_held(&cgroup_mutex);
-        lockdep_assert_held(&cgroup_root_mutex);
-
-        id = idr_alloc_cyclic(&cgroup_hierarchy_idr, root, start, end,
-                              GFP_KERNEL);
-        if (id < 0)
-                return id;
-
-        root->hierarchy_id = id;
-        return 0;
-}
-
-static void cgroup_exit_root_id(struct cgroupfs_root *root)
-{
-        lockdep_assert_held(&cgroup_mutex);
-        lockdep_assert_held(&cgroup_root_mutex);
-
-        if (root->hierarchy_id) {
-                idr_remove(&cgroup_hierarchy_idr, root->hierarchy_id);
-                root->hierarchy_id = 0;
-        }
-}
-
-static int cgroup_test_super(struct super_block *sb, void *data)
-{
-        struct cgroup_sb_opts *opts = data;
-        struct cgroupfs_root *root = sb->s_fs_info;
-
-        /* If we asked for a name then it must match */
-        if (opts->name && strcmp(opts->name, root->name))
-                return 0;
-
-        /*
-         * If we asked for subsystems (or explicitly for no
-         * subsystems) then they must match
-         */
-        if ((opts->subsys_mask || opts->none)
-            && (opts->subsys_mask != root->subsys_mask))
-                return 0;
-
-        return 1;
-}
-
-static struct cgroupfs_root *cgroup_root_from_opts(struct cgroup_sb_opts *opts)
-{
-        struct cgroupfs_root *root;
 
-        if (!opts->subsys_mask && !opts->none)
-                return NULL;
-
-        root = kzalloc(sizeof(*root), GFP_KERNEL);
-        if (!root)
-                return ERR_PTR(-ENOMEM);
-
-        init_cgroup_root(root);
-
-        /*
-         * We need to set @root->subsys_mask now so that @root can be
-         * matched by cgroup_test_super() before it finishes
-         * initialization; otherwise, competing mounts with the same
-         * options may try to bind the same subsystems instead of waiting
-         * for the first one leading to unexpected mount errors.
-         * SUBSYS_BOUND will be set once actual binding is complete.
-         */
-        root->subsys_mask = opts->subsys_mask;
         root->flags = opts->flags;
         if (opts->release_agent)
                 strcpy(root->release_agent_path, opts->release_agent);
         if (opts->name)
                 strcpy(root->name, opts->name);
         if (opts->cpuset_clone_children)
-                set_bit(CGRP_CPUSET_CLONE_CHILDREN, &root->top_cgroup.flags);
-        return root;
+                set_bit(CGRP_CPUSET_CLONE_CHILDREN, &root->cgrp.flags);
 }
 
-static void cgroup_free_root(struct cgroupfs_root *root)
+static int cgroup_setup_root(struct cgroup_root *root, unsigned long ss_mask)
 {
-        if (root) {
-                /* hierarhcy ID shoulid already have been released */
-                WARN_ON_ONCE(root->hierarchy_id);
-
-                idr_destroy(&root->cgroup_idr);
-                kfree(root);
-        }
-}
+        LIST_HEAD(tmp_links);
+        struct cgroup *root_cgrp = &root->cgrp;
+        struct css_set *cset;
+        int i, ret;
 
-static int cgroup_set_super(struct super_block *sb, void *data)
-{
-        int ret;
-        struct cgroup_sb_opts *opts = data;
+        lockdep_assert_held(&cgroup_tree_mutex);
+        lockdep_assert_held(&cgroup_mutex);
 
-        /* If we don't have a new root, we can't set up a new sb */
-        if (!opts->new_root)
-                return -EINVAL;
+        ret = idr_alloc(&root->cgroup_idr, root_cgrp, 0, 1, GFP_KERNEL);
+        if (ret < 0)
+                goto out;
+        root_cgrp->id = ret;
 
-        BUG_ON(!opts->subsys_mask && !opts->none);
+        /*
+         * We're accessing css_set_count without locking css_set_rwsem here,
+         * but that's OK - it can only be increased by someone holding
+         * cgroup_lock, and that's us. The worst that can happen is that we
+         * have some link structures left over
+         */
+        ret = allocate_cgrp_cset_links(css_set_count, &tmp_links);
+        if (ret)
+                goto out;
 
-        ret = set_anon_super(sb, NULL);
+        ret = cgroup_init_root_id(root);
         if (ret)
-                return ret;
+                goto out;
 
-        sb->s_fs_info = opts->new_root;
-        opts->new_root->sb = sb;
+        root->kf_root = kernfs_create_root(&cgroup_kf_syscall_ops,
+                                           KERNFS_ROOT_CREATE_DEACTIVATED,
+                                           root_cgrp);
+        if (IS_ERR(root->kf_root)) {
+                ret = PTR_ERR(root->kf_root);
+                goto exit_root_id;
+        }
+        root_cgrp->kn = root->kf_root->kn;
 
-        sb->s_blocksize = PAGE_CACHE_SIZE;
-        sb->s_blocksize_bits = PAGE_CACHE_SHIFT;
-        sb->s_magic = CGROUP_SUPER_MAGIC;
-        sb->s_op = &cgroup_ops;
+        ret = cgroup_addrm_files(root_cgrp, cgroup_base_files, true);
+        if (ret)
+                goto destroy_root;
 
-        return 0;
-}
+        ret = rebind_subsystems(root, ss_mask);
+        if (ret)
+                goto destroy_root;
 
-static int cgroup_get_rootdir(struct super_block *sb)
-{
-        static const struct dentry_operations cgroup_dops = {
-                .d_iput = cgroup_diput,
-                .d_delete = always_delete_dentry,
-        };
+        /*
+         * There must be no failure case after here, since rebinding takes
+         * care of subsystems' refcounts, which are explicitly dropped in
+         * the failure exit path.
+         */
+        list_add(&root->root_list, &cgroup_roots);
+        cgroup_root_count++;
 
-        struct inode *inode =
-                cgroup_new_inode(S_IFDIR | S_IRUGO | S_IXUGO | S_IWUSR, sb);
+        /*
+         * Link the root cgroup in this hierarchy into all the css_set
+         * objects.
+         */
+        down_write(&css_set_rwsem);
+        hash_for_each(css_set_table, i, cset, hlist)
+                link_css_set(&tmp_links, cset, root_cgrp);
+        up_write(&css_set_rwsem);
 
-        if (!inode)
-                return -ENOMEM;
+        BUG_ON(!list_empty(&root_cgrp->children));
+        BUG_ON(atomic_read(&root->nr_cgrps) != 1);
 
-        inode->i_fop = &simple_dir_operations;
-        inode->i_op = &cgroup_dir_inode_operations;
-        /* directories start off with i_nlink == 2 (for "." entry) */
-        inc_nlink(inode);
-        sb->s_root = d_make_root(inode);
-        if (!sb->s_root)
-                return -ENOMEM;
-        /* for everything else we want ->d_op set */
-        sb->s_d_op = &cgroup_dops;
-        return 0;
+        kernfs_activate(root_cgrp->kn);
+        ret = 0;
+        goto out;
+
+destroy_root:
+        kernfs_destroy_root(root->kf_root);
+        root->kf_root = NULL;
+exit_root_id:
+        cgroup_exit_root_id(root);
+out:
+        free_cgrp_cset_links(&tmp_links);
+        return ret;
 }
 
 static struct dentry *cgroup_mount(struct file_system_type *fs_type,
                          int flags, const char *unused_dev_name,
                          void *data)
 {
+        struct cgroup_root *root;
         struct cgroup_sb_opts opts;
-        struct cgroupfs_root *root;
-        int ret = 0;
-        struct super_block *sb;
-        struct cgroupfs_root *new_root;
-        struct list_head tmp_links;
-        struct inode *inode;
-        const struct cred *cred;
+        struct dentry *dentry;
+        int ret;
 
-        /* First find the desired set of subsystems */
+        /*
+         * The first time anyone tries to mount a cgroup, enable the list
+         * linking each css_set to its tasks and fix up all existing tasks.
+         */
+        if (!use_task_css_set_links)
+                cgroup_enable_task_cg_lists();
+retry:
+        mutex_lock(&cgroup_tree_mutex);
         mutex_lock(&cgroup_mutex);
+
+        /* First find the desired set of subsystems */
         ret = parse_cgroupfs_options(data, &opts);
-        mutex_unlock(&cgroup_mutex);
         if (ret)
-                goto out_err;
-
-        /*
-         * 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;
+                goto out_unlock;
 
-        /* Locate an existing or new sb for this hierarchy */
-        sb = sget(fs_type, cgroup_test_super, cgroup_set_super, 0, &opts);
-        if (IS_ERR(sb)) {
-                ret = PTR_ERR(sb);
-                cgroup_free_root(opts.new_root);
-                goto out_err;
+        /* look for a matching existing root */
+        if (!opts.subsys_mask && !opts.none && !opts.name) {
+                cgrp_dfl_root_visible = true;
+                root = &cgrp_dfl_root;
+                cgroup_get(&root->cgrp);
+                ret = 0;
+                goto out_unlock;
         }
 
-        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 cgroup *root_cgrp = &root->top_cgroup;
-                struct cgroupfs_root *existing_root;
-                int i;
-                struct css_set *cset;
-
-                BUG_ON(sb->s_root != NULL);
-
-                ret = cgroup_get_rootdir(sb);
-                if (ret)
-                        goto drop_new_super;
-                inode = sb->s_root->d_inode;
-
-                mutex_lock(&inode->i_mutex);
-                mutex_lock(&cgroup_mutex);
-                mutex_lock(&cgroup_root_mutex);
-
-                ret = idr_alloc(&root->cgroup_idr, root_cgrp, 0, 1, GFP_KERNEL);
-                if (ret < 0)
-                        goto unlock_drop;
-                root_cgrp->id = ret;
-
-                /* Check for name clashes with existing mounts */
-                ret = -EBUSY;
-                if (strlen(root->name))
-                        for_each_active_root(existing_root)
-                                if (!strcmp(existing_root->name, root->name))
-                                        goto unlock_drop;
-
-                /*
-                 * We're accessing css_set_count without locking
-                 * css_set_lock here, but that's OK - it can only be
-                 * increased by someone holding cgroup_lock, and
-                 * that's us. The worst that can happen is that we
-                 * have some link structures left over
-                 */
-                ret = allocate_cgrp_cset_links(css_set_count, &tmp_links);
-                if (ret)
-                        goto unlock_drop;
+        for_each_root(root) {
+                bool name_match = false;
 
-                /* ID 0 is reserved for dummy root, 1 for unified hierarchy */
-                ret = cgroup_init_root_id(root, 2, 0);
-                if (ret)
-                        goto unlock_drop;
-
-                sb->s_root->d_fsdata = root_cgrp;
-                root_cgrp->dentry = sb->s_root;
-
-                /*
-                 * We're inside get_sb() and will call lookup_one_len() to
-                 * create the root files, which doesn't work if SELinux is
-                 * in use.  The following cred dancing somehow works around
-                 * it.  See 2ce9738ba ("cgroupfs: use init_cred when
-                 * populating new cgroupfs mount") for more details.
-                 */
-                cred = override_creds(&init_cred);
-
-                ret = cgroup_addrm_files(root_cgrp, cgroup_base_files, true);
-                if (ret)
-                        goto rm_base_files;
-
-                ret = rebind_subsystems(root, root->subsys_mask, 0);
-                if (ret)
-                        goto rm_base_files;
-
-                revert_creds(cred);
+                if (root == &cgrp_dfl_root)
+                        continue;
 
                 /*
-                 * There must be no failure case after here, since rebinding
-                 * takes care of subsystems' refcounts, which are explicitly
-                 * dropped in the failure exit path.
+                 * If we asked for a name then it must match.  Also, if
+                 * name matches but sybsys_mask doesn't, we should fail.
+                 * Remember whether name matched.
                  */
+                if (opts.name) {
+                        if (strcmp(opts.name, root->name))
+                                continue;
+                        name_match = true;
+                }
 
-                list_add(&root->root_list, &cgroup_roots);
-                cgroup_root_count++;
-
-                /* Link the top cgroup in this hierarchy into all
-                 * the css_set objects */
-                write_lock(&css_set_lock);
-                hash_for_each(css_set_table, i, cset, hlist)
-                        link_css_set(&tmp_links, cset, root_cgrp);
-                write_unlock(&css_set_lock);
-
-                free_cgrp_cset_links(&tmp_links);
-
-                BUG_ON(!list_empty(&root_cgrp->children));
-                BUG_ON(root->number_of_cgroups != 1);
-
-                mutex_unlock(&cgroup_root_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
+                 * If we asked for subsystems (or explicitly for no
+                 * subsystems) then they must match.
                  */
-                cgroup_free_root(opts.new_root);
+                if ((opts.subsys_mask || opts.none) &&
+                    (opts.subsys_mask != root->cgrp.subsys_mask)) {
+                        if (!name_match)
+                                continue;
+                        ret = -EBUSY;
+                        goto out_unlock;
+                }
 
                 if ((root->flags ^ opts.flags) & CGRP_ROOT_OPTION_MASK) {
                         if ((root->flags | opts.flags) & CGRP_ROOT_SANE_BEHAVIOR) {
                                 pr_err("cgroup: sane_behavior: new mount options should match the existing superblock\n");
                                 ret = -EINVAL;
-                                goto drop_new_super;
+                                goto out_unlock;
                         } else {
                                 pr_warning("cgroup: new mount options do not match the existing superblock, will be ignored\n");
                         }
                 }
-        }
-
-        kfree(opts.release_agent);
-        kfree(opts.name);
-        return dget(sb->s_root);
-
- rm_base_files:
-        free_cgrp_cset_links(&tmp_links);
-        cgroup_addrm_files(&root->top_cgroup, cgroup_base_files, false);
-        revert_creds(cred);
- unlock_drop:
-        cgroup_exit_root_id(root);
-        mutex_unlock(&cgroup_root_mutex);
-        mutex_unlock(&cgroup_mutex);
-        mutex_unlock(&inode->i_mutex);
- drop_new_super:
-        deactivate_locked_super(sb);
- out_err:
-        kfree(opts.release_agent);
-        kfree(opts.name);
-        return ERR_PTR(ret);
-}
-
-static void cgroup_kill_sb(struct super_block *sb)
-{
-        struct cgroupfs_root *root = sb->s_fs_info;
-        struct cgroup *cgrp = &root->top_cgroup;
-        struct cgrp_cset_link *link, *tmp_link;
-        int ret;
-
-        BUG_ON(!root);
-
-        BUG_ON(root->number_of_cgroups != 1);
-        BUG_ON(!list_empty(&cgrp->children));
 
-        mutex_lock(&cgrp->dentry->d_inode->i_mutex);
-        mutex_lock(&cgroup_mutex);
-        mutex_lock(&cgroup_root_mutex);
+                /*
+                 * A root's lifetime is governed by its root cgroup.  Zero
+                 * ref indicate that the root is being destroyed.  Wait for
+                 * destruction to complete so that the subsystems are free.
+                 * We can use wait_queue for the wait but this path is
+                 * super cold.  Let's just sleep for a bit and retry.
+                 */
+                if (!atomic_inc_not_zero(&root->cgrp.refcnt)) {
+                        mutex_unlock(&cgroup_mutex);
+                        mutex_unlock(&cgroup_tree_mutex);
+                        kfree(opts.release_agent);
+                        kfree(opts.name);
+                        msleep(10);
+                        goto retry;
+                }
 
-        /* Rebind all subsystems back to the default hierarchy */
-        if (root->flags & CGRP_ROOT_SUBSYS_BOUND) {
-                ret = rebind_subsystems(root, 0, root->subsys_mask);
-                /* Shouldn't be able to fail ... */
-                BUG_ON(ret);
+                ret = 0;
+                goto out_unlock;
         }
 
         /*
-         * Release all the links from cset_links to this hierarchy's
-         * root cgroup
+         * No such thing, create a new one.  name= matching without subsys
+         * specification is allowed for already existing hierarchies but we
+         * can't create new one without subsys specification.
          */
-        write_lock(&css_set_lock);
-
-        list_for_each_entry_safe(link, tmp_link, &cgrp->cset_links, cset_link) {
-                list_del(&link->cset_link);
-                list_del(&link->cgrp_link);
-                kfree(link);
+        if (!opts.subsys_mask && !opts.none) {
+                ret = -EINVAL;
+                goto out_unlock;
         }
-        write_unlock(&css_set_lock);
 
-        if (!list_empty(&root->root_list)) {
-                list_del(&root->root_list);
-                cgroup_root_count--;
+        root = kzalloc(sizeof(*root), GFP_KERNEL);
+        if (!root) {
+                ret = -ENOMEM;
+                goto out_unlock;
         }
 
-        cgroup_exit_root_id(root);
+        init_cgroup_root(root, &opts);
 
-        mutex_unlock(&cgroup_root_mutex);
+        ret = cgroup_setup_root(root, opts.subsys_mask);
+        if (ret)
+                cgroup_free_root(root);
+
+out_unlock:
         mutex_unlock(&cgroup_mutex);
-        mutex_unlock(&cgrp->dentry->d_inode->i_mutex);
+        mutex_unlock(&cgroup_tree_mutex);
 
-        simple_xattrs_free(&cgrp->xattrs);
+        kfree(opts.release_agent);
+        kfree(opts.name);
 
-        kill_litter_super(sb);
-        cgroup_free_root(root);
+        if (ret)
+                return ERR_PTR(ret);
+
+        dentry = kernfs_mount(fs_type, flags, root->kf_root, NULL);
+        if (IS_ERR(dentry))
+                cgroup_put(&root->cgrp);
+        return dentry;
+}
+
+static void cgroup_kill_sb(struct super_block *sb)
+{
+        struct kernfs_root *kf_root = kernfs_root_from_sb(sb);
+        struct cgroup_root *root = cgroup_root_from_kf(kf_root);
+
+        cgroup_put(&root->cgrp);
+        kernfs_kill_sb(sb);
 }
 
 static struct file_system_type cgroup_fs_type = {
@@ -1743,57 +1627,6 @@ static struct file_system_type cgroup_fs_type = {
 static struct kobject *cgroup_kobj;
 
 /**
- * cgroup_path - generate the path of a cgroup
- * @cgrp: the cgroup in question
- * @buf: the buffer to write the path into
- * @buflen: the length of the buffer
- *
- * Writes path of cgroup into buf.  Returns 0 on success, -errno on error.
- *
- * We can't generate cgroup path using dentry->d_name, as accessing
- * dentry->name must be protected by irq-unsafe dentry->d_lock or parent
- * inode's i_mutex, while on the other hand cgroup_path() can be called
- * with some irq-safe spinlocks held.
- */
-int cgroup_path(const struct cgroup *cgrp, char *buf, int buflen)
-{
-        int ret = -ENAMETOOLONG;
-        char *start;
-
-        if (!cgrp->parent) {
-                if (strlcpy(buf, "/", buflen) >= buflen)
-                        return -ENAMETOOLONG;
-                return 0;
-        }
-
-        start = buf + buflen - 1;
-        *start = '\0';
-
-        rcu_read_lock();
-        do {
-                const char *name = cgroup_name(cgrp);
-                int len;
-
-                len = strlen(name);
-                if ((start -= len) < buf)
-                        goto out;
-                memcpy(start, name, len);
-
-                if (--start < buf)
-                        goto out;
-                *start = '/';
-
-                cgrp = cgrp->parent;
-        } while (cgrp->parent);
-        ret = 0;
-        memmove(buf, start, buf + buflen - start);
-out:
-        rcu_read_unlock();
-        return ret;
-}
-EXPORT_SYMBOL_GPL(cgroup_path);
-
-/**
  * task_cgroup_path - cgroup path of a task in the first cgroup hierarchy
  * @task: target task
  * @buf: the buffer to write the path into
@@ -1804,49 +1637,55 @@ EXPORT_SYMBOL_GPL(cgroup_path);
  * function grabs cgroup_mutex and shouldn't be used inside locks used by
  * cgroup controller callbacks.
  *
- * Returns 0 on success, fails with -%ENAMETOOLONG if @buflen is too short.
+ * Return value is the same as kernfs_path().
  */
-int task_cgroup_path(struct task_struct *task, char *buf, size_t buflen)
+char *task_cgroup_path(struct task_struct *task, char *buf, size_t buflen)
 {
-        struct cgroupfs_root *root;
+        struct cgroup_root *root;
         struct cgroup *cgrp;
-        int hierarchy_id = 1, ret = 0;
-
-        if (buflen < 2)
-                return -ENAMETOOLONG;
+        int hierarchy_id = 1;
+        char *path = NULL;
 
         mutex_lock(&cgroup_mutex);
+        down_read(&css_set_rwsem);
 
         root = idr_get_next(&cgroup_hierarchy_idr, &hierarchy_id);
 
         if (root) {
                 cgrp = task_cgroup_from_root(task, root);
-                ret = cgroup_path(cgrp, buf, buflen);
+                path = cgroup_path(cgrp, buf, buflen);
         } else {
                 /* if no hierarchy exists, everyone is in "/" */
-                memcpy(buf, "/", 2);
+                if (strlcpy(buf, "/", buflen) < buflen)
+                        path = buf;
         }
 
+        up_read(&css_set_rwsem);
         mutex_unlock(&cgroup_mutex);
-        return ret;
+        return path;
 }
 EXPORT_SYMBOL_GPL(task_cgroup_path);
 
-/*
- * Control Group taskset
- */
-struct task_and_cgroup {
-        struct task_struct      *task;
-        struct cgroup           *cgrp;
-        struct css_set          *cset;
-};
-
+/* used to track tasks and other necessary states during migration */
 struct cgroup_taskset {
-        struct task_and_cgroup  single;
-        struct flex_array       *tc_array;
-        int                     tc_array_len;
-        int                     idx;
-        struct cgroup           *cur_cgrp;
+        /* the src and dst cset list running through cset->mg_node */
+        struct list_head        src_csets;
+        struct list_head        dst_csets;
+
+        /*
+         * Fields for cgroup_taskset_*() iteration.
+         *
+         * Before migration is committed, the target migration tasks are on
+         * ->mg_tasks of the csets on ->src_csets.  After, on ->mg_tasks of
+         * the csets on ->dst_csets.  ->csets point to either ->src_csets
+         * or ->dst_csets depending on whether migration is committed.
+         *
+         * ->cur_csets and ->cur_task point to the current task position
+         * during iteration.
+         */
+        struct list_head        *csets;
+        struct css_set          *cur_cset;
+        struct task_struct      *cur_task;
 };
 
 /**
@@ -1857,15 +1696,11 @@ struct cgroup_taskset {
  */
 struct task_struct *cgroup_taskset_first(struct cgroup_taskset *tset)
 {
-        if (tset->tc_array) {
-                tset->idx = 0;
-                return cgroup_taskset_next(tset);
-        } else {
-                tset->cur_cgrp = tset->single.cgrp;
-                return tset->single.task;
-        }
+        tset->cur_cset = list_first_entry(tset->csets, struct css_set, mg_node);
+        tset->cur_task = NULL;
+
+        return cgroup_taskset_next(tset);
 }
-EXPORT_SYMBOL_GPL(cgroup_taskset_first);
 
 /**
  * cgroup_taskset_next - iterate to the next task in taskset
@@ -1876,48 +1711,36 @@ EXPORT_SYMBOL_GPL(cgroup_taskset_first);
  */
 struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset)
 {
-        struct task_and_cgroup *tc;
+        struct css_set *cset = tset->cur_cset;
+        struct task_struct *task = tset->cur_task;
 
-        if (!tset->tc_array || tset->idx >= tset->tc_array_len)
-                return NULL;
+        while (&cset->mg_node != tset->csets) {
+                if (!task)
+                        task = list_first_entry(&cset->mg_tasks,
+                                                struct task_struct, cg_list);
+                else
+                        task = list_next_entry(task, cg_list);
 
-        tc = flex_array_get(tset->tc_array, tset->idx++);
-        tset->cur_cgrp = tc->cgrp;
-        return tc->task;
-}
-EXPORT_SYMBOL_GPL(cgroup_taskset_next);
+                if (&task->cg_list != &cset->mg_tasks) {
+                        tset->cur_cset = cset;
+                        tset->cur_task = task;
+                        return task;
+                }
 
-/**
- * cgroup_taskset_cur_css - return the matching css for the current task
- * @tset: taskset of interest
- * @subsys_id: the ID of the target subsystem
- *
- * Return the css for the current (last returned) task of @tset for
- * subsystem specified by @subsys_id.  This function must be preceded by
- * either cgroup_taskset_first() or cgroup_taskset_next().
- */
-struct cgroup_subsys_state *cgroup_taskset_cur_css(struct cgroup_taskset *tset,
-                                                   int subsys_id)
-{
-        return cgroup_css(tset->cur_cgrp, cgroup_subsys[subsys_id]);
-}
-EXPORT_SYMBOL_GPL(cgroup_taskset_cur_css);
+                cset = list_next_entry(cset, mg_node);
+                task = NULL;
+        }
 
-/**
- * cgroup_taskset_size - return the number of tasks in taskset
- * @tset: taskset of interest
- */
-int cgroup_taskset_size(struct cgroup_taskset *tset)
-{
-        return tset->tc_array ? tset->tc_array_len : 1;
+        return NULL;
 }
-EXPORT_SYMBOL_GPL(cgroup_taskset_size);
 
-
-/*
+/**
  * cgroup_task_migrate - move a task from one cgroup to another.
+ * @old_cgrp; the cgroup @tsk is being migrated from
+ * @tsk: the task being migrated
+ * @new_cset: the new css_set @tsk is being attached to
  *
- * Must be called with cgroup_mutex and threadgroup locked.
+ * Must be called with cgroup_mutex, threadgroup and css_set_rwsem locked.
  */
 static void cgroup_task_migrate(struct cgroup *old_cgrp,
                                 struct task_struct *tsk,
@@ -1925,6 +1748,9 @@ static void cgroup_task_migrate(struct cgroup *old_cgrp,
 {
         struct css_set *old_cset;
 
+        lockdep_assert_held(&cgroup_mutex);
+        lockdep_assert_held(&css_set_rwsem);
+
         /*
          * We are synchronized through threadgroup_lock() against PF_EXITING
          * setting such that we can't race against cgroup_exit() changing the
@@ -1933,15 +1759,16 @@ static void cgroup_task_migrate(struct cgroup *old_cgrp,
         WARN_ON_ONCE(tsk->flags & PF_EXITING);
         old_cset = task_css_set(tsk);
 
-        task_lock(tsk);
+        get_css_set(new_cset);
         rcu_assign_pointer(tsk->cgroups, new_cset);
-        task_unlock(tsk);
 
-        /* Update the css_set linked lists if we're using them */
-        write_lock(&css_set_lock);
-        if (!list_empty(&tsk->cg_list))
-                list_move(&tsk->cg_list, &new_cset->tasks);
-        write_unlock(&css_set_lock);
+        /*
+         * Use move_tail so that cgroup_taskset_first() still returns the
+         * leader after migration.  This works because cgroup_migrate()
+         * ensures that the dst_cset of the leader is the first on the
+         * tset's dst_csets list.
+         */
+        list_move_tail(&tsk->cg_list, &new_cset->mg_tasks);
 
         /*
          * We just gained a reference on old_cset by taking it from the
@@ -1949,100 +1776,199 @@ static void cgroup_task_migrate(struct cgroup *old_cgrp,
          * we're safe to drop it here; it will be freed under RCU.
          */
         set_bit(CGRP_RELEASABLE, &old_cgrp->flags);
-        put_css_set(old_cset);
+        put_css_set_locked(old_cset, false);
 }
 
 /**
- * cgroup_attach_task - attach a task or a whole threadgroup to a cgroup
- * @cgrp: the cgroup to attach to
- * @tsk: the task or the leader of the threadgroup to be attached
- * @threadgroup: attach the whole threadgroup?
+ * cgroup_migrate_finish - cleanup after attach
+ * @preloaded_csets: list of preloaded css_sets
  *
- * Call holding cgroup_mutex and the group_rwsem of the leader. Will take
- * task_lock of @tsk or each thread in the threadgroup individually in turn.
+ * Undo cgroup_migrate_add_src() and cgroup_migrate_prepare_dst().  See
+ * those functions for details.
  */
-static int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk,
-                              bool threadgroup)
+static void cgroup_migrate_finish(struct list_head *preloaded_csets)
 {
-        int retval, i, group_size;
-        struct cgroupfs_root *root = cgrp->root;
-        struct cgroup_subsys_state *css, *failed_css = NULL;
-        /* threadgroup list cursor and array */
-        struct task_struct *leader = tsk;
-        struct task_and_cgroup *tc;
-        struct flex_array *group;
-        struct cgroup_taskset tset = { };
+        struct css_set *cset, *tmp_cset;
 
-        /*
-         * step 0: in order to do expensive, possibly blocking operations for
-         * every thread, we cannot iterate the thread group list, since it needs
-         * rcu or tasklist locked. instead, build an array of all threads in the
-         * group - group_rwsem prevents new threads from appearing, and if
-         * threads exit, this will just be an over-estimate.
-         */
-        if (threadgroup)
-                group_size = get_nr_threads(tsk);
-        else
-                group_size = 1;
-        /* flex_array supports very large thread-groups better than kmalloc. */
-        group = flex_array_alloc(sizeof(*tc), group_size, GFP_KERNEL);
-        if (!group)
-                return -ENOMEM;
-        /* pre-allocate to guarantee space while iterating in rcu read-side. */
-        retval = flex_array_prealloc(group, 0, group_size, GFP_KERNEL);
-        if (retval)
-                goto out_free_group_list;
+        lockdep_assert_held(&cgroup_mutex);
+
+        down_write(&css_set_rwsem);
+        list_for_each_entry_safe(cset, tmp_cset, preloaded_csets, mg_preload_node) {
+                cset->mg_src_cgrp = NULL;
+                cset->mg_dst_cset = NULL;
+                list_del_init(&cset->mg_preload_node);
+                put_css_set_locked(cset, false);
+        }
+        up_write(&css_set_rwsem);
+}
+
+/**
+ * cgroup_migrate_add_src - add a migration source css_set
+ * @src_cset: the source css_set to add
+ * @dst_cgrp: the destination cgroup
+ * @preloaded_csets: list of preloaded css_sets
+ *
+ * Tasks belonging to @src_cset are about to be migrated to @dst_cgrp.  Pin
+ * @src_cset and add it to @preloaded_csets, which should later be cleaned
+ * up by cgroup_migrate_finish().
+ *
+ * This function may be called without holding threadgroup_lock even if the
+ * target is a process.  Threads may be created and destroyed but as long
+ * as cgroup_mutex is not dropped, no new css_set can be put into play and
+ * the preloaded css_sets are guaranteed to cover all migrations.
+ */
+static void cgroup_migrate_add_src(struct css_set *src_cset,
+                                   struct cgroup *dst_cgrp,
+                                   struct list_head *preloaded_csets)
+{
+        struct cgroup *src_cgrp;
+
+        lockdep_assert_held(&cgroup_mutex);
+        lockdep_assert_held(&css_set_rwsem);
+
+        src_cgrp = cset_cgroup_from_root(src_cset, dst_cgrp->root);
+
+        /* nothing to do if this cset already belongs to the cgroup */
+        if (src_cgrp == dst_cgrp)
+                return;
+
+        if (!list_empty(&src_cset->mg_preload_node))
+                return;
+
+        WARN_ON(src_cset->mg_src_cgrp);
+        WARN_ON(!list_empty(&src_cset->mg_tasks));
+        WARN_ON(!list_empty(&src_cset->mg_node));
+
+        src_cset->mg_src_cgrp = src_cgrp;
+        get_css_set(src_cset);
+        list_add(&src_cset->mg_preload_node, preloaded_csets);
+}
+
+/**
+ * cgroup_migrate_prepare_dst - prepare destination css_sets for migration
+ * @dst_cgrp: the destination cgroup
+ * @preloaded_csets: list of preloaded source css_sets
+ *
+ * Tasks are about to be moved to @dst_cgrp and all the source css_sets
+ * have been preloaded to @preloaded_csets.  This function looks up and
+ * pins all destination css_sets, links each to its source, and put them on
+ * @preloaded_csets.
+ *
+ * This function must be called after cgroup_migrate_add_src() has been
+ * called on each migration source css_set.  After migration is performed
+ * using cgroup_migrate(), cgroup_migrate_finish() must be called on
+ * @preloaded_csets.
+ */
+static int cgroup_migrate_prepare_dst(struct cgroup *dst_cgrp,
+                                      struct list_head *preloaded_csets)
+{
+        LIST_HEAD(csets);
+        struct css_set *src_cset;
+
+        lockdep_assert_held(&cgroup_mutex);
+
+        /* look up the dst cset for each src cset and link it to src */
+        list_for_each_entry(src_cset, preloaded_csets, mg_preload_node) {
+                struct css_set *dst_cset;
+
+                dst_cset = find_css_set(src_cset, dst_cgrp);
+                if (!dst_cset)
+                        goto err;
+
+                WARN_ON_ONCE(src_cset->mg_dst_cset || dst_cset->mg_dst_cset);
+                src_cset->mg_dst_cset = dst_cset;
+
+                if (list_empty(&dst_cset->mg_preload_node))
+                        list_add(&dst_cset->mg_preload_node, &csets);
+                else
+                        put_css_set(dst_cset, false);
+        }
+
+        list_splice(&csets, preloaded_csets);
+        return 0;
+err:
+        cgroup_migrate_finish(&csets);
+        return -ENOMEM;
+}
+
+/**
+ * cgroup_migrate - migrate a process or task to a cgroup
+ * @cgrp: the destination cgroup
+ * @leader: the leader of the process or the task to migrate
+ * @threadgroup: whether @leader points to the whole process or a single task
+ *
+ * Migrate a process or task denoted by @leader to @cgrp.  If migrating a
+ * process, the caller must be holding threadgroup_lock of @leader.  The
+ * caller is also responsible for invoking cgroup_migrate_add_src() and
+ * cgroup_migrate_prepare_dst() on the targets before invoking this
+ * function and following up with cgroup_migrate_finish().
+ *
+ * As long as a controller's ->can_attach() doesn't fail, this function is
+ * guaranteed to succeed.  This means that, excluding ->can_attach()
+ * failure, when migrating multiple targets, the success or failure can be
+ * decided for all targets by invoking group_migrate_prepare_dst() before
+ * actually starting migrating.
+ */
+static int cgroup_migrate(struct cgroup *cgrp, struct task_struct *leader,
+                          bool threadgroup)
+{
+        struct cgroup_taskset tset = {
+                .src_csets      = LIST_HEAD_INIT(tset.src_csets),
+                .dst_csets      = LIST_HEAD_INIT(tset.dst_csets),
+                .csets          = &tset.src_csets,
+        };
+        struct cgroup_subsys_state *css, *failed_css = NULL;
+        struct css_set *cset, *tmp_cset;
+        struct task_struct *task, *tmp_task;
+        int i, ret;
 
-        i = 0;
         /*
          * Prevent freeing of tasks while we take a snapshot. Tasks that are
          * already PF_EXITING could be freed from underneath us unless we
          * take an rcu_read_lock.
          */
+        down_write(&css_set_rwsem);
         rcu_read_lock();
+        task = leader;
         do {
-                struct task_and_cgroup ent;
+                /* @task either already exited or can't exit until the end */
+                if (task->flags & PF_EXITING)
+                        goto next;
 
-                /* @tsk either already exited or can't exit until the end */
-                if (tsk->flags & PF_EXITING)
+                /* leave @task alone if post_fork() hasn't linked it yet */
+                if (list_empty(&task->cg_list))
                         goto next;
 
-                /* as per above, nr_threads may decrease, but not increase. */
-                BUG_ON(i >= group_size);
-                ent.task = tsk;
-                ent.cgrp = task_cgroup_from_root(tsk, root);
-                /* nothing to do if this task is already in the cgroup */
-                if (ent.cgrp == cgrp)
+                cset = task_css_set(task);
+                if (!cset->mg_src_cgrp)
                         goto next;
+
                 /*
-                 * saying GFP_ATOMIC has no effect here because we did prealloc
-                 * earlier, but it's good form to communicate our expectations.
+                 * cgroup_taskset_first() must always return the leader.
+                 * Take care to avoid disturbing the ordering.
                  */
-                retval = flex_array_put(group, i, &ent, GFP_ATOMIC);
-                BUG_ON(retval != 0);
-                i++;
+                list_move_tail(&task->cg_list, &cset->mg_tasks);
+                if (list_empty(&cset->mg_node))
+                        list_add_tail(&cset->mg_node, &tset.src_csets);
+                if (list_empty(&cset->mg_dst_cset->mg_node))
+                        list_move_tail(&cset->mg_dst_cset->mg_node,
+                                       &tset.dst_csets);
         next:
                 if (!threadgroup)
                         break;
-        } while_each_thread(leader, tsk);
+        } while_each_thread(leader, task);
         rcu_read_unlock();
-        /* remember the number of threads in the array for later. */
-        group_size = i;
-        tset.tc_array = group;
-        tset.tc_array_len = group_size;
+        up_write(&css_set_rwsem);
 
         /* methods shouldn't be called if no task is actually migrating */
-        retval = 0;
-        if (!group_size)
-                goto out_free_group_list;
+        if (list_empty(&tset.src_csets))
+                return 0;
 
-        /*
-         * step 1: check that we can legitimately attach to the cgroup.
-         */
+        /* check that we can legitimately attach to the cgroup */
         for_each_css(css, i, cgrp) {
                 if (css->ss->can_attach) {
-                        retval = css->ss->can_attach(css, &tset);
-                        if (retval) {
+                        ret = css->ss->can_attach(css, &tset);
+                        if (ret) {
                                 failed_css = css;
                                 goto out_cancel_attach;
                         }
@@ -2050,70 +1976,91 @@ static int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk,
         }
 
         /*
-         * step 2: make sure css_sets exist for all threads to be migrated.
-         * we use find_css_set, which allocates a new one if necessary.
+         * Now that we're guaranteed success, proceed to move all tasks to
+         * the new cgroup.  There are no failure cases after here, so this
+         * is the commit point.
          */
-        for (i = 0; i < group_size; i++) {
-                struct css_set *old_cset;
-
-                tc = flex_array_get(group, i);
-                old_cset = task_css_set(tc->task);
-                tc->cset = find_css_set(old_cset, cgrp);
-                if (!tc->cset) {
-                        retval = -ENOMEM;
-                        goto out_put_css_set_refs;
-                }
+        down_write(&css_set_rwsem);
+        list_for_each_entry(cset, &tset.src_csets, mg_node) {
+                list_for_each_entry_safe(task, tmp_task, &cset->mg_tasks, cg_list)
+                        cgroup_task_migrate(cset->mg_src_cgrp, task,
+                                            cset->mg_dst_cset);
         }
+        up_write(&css_set_rwsem);
 
         /*
-         * step 3: now that we're guaranteed success wrt the css_sets,
-         * proceed to move all tasks to the new cgroup.  There are no
-         * failure cases after here, so this is the commit point.
+         * Migration is committed, all target tasks are now on dst_csets.
+         * Nothing is sensitive to fork() after this point.  Notify
+         * controllers that migration is complete.
          */
-        for (i = 0; i < group_size; i++) {
-                tc = flex_array_get(group, i);
-                cgroup_task_migrate(tc->cgrp, tc->task, tc->cset);
-        }
-        /* nothing is sensitive to fork() after this point. */
+        tset.csets = &tset.dst_csets;
 
-        /*
-         * step 4: do subsystem attach callbacks.
-         */
         for_each_css(css, i, cgrp)
                 if (css->ss->attach)
                         css->ss->attach(css, &tset);
 
-        /*
-         * step 5: success! and cleanup
-         */
-        retval = 0;
-out_put_css_set_refs:
-        if (retval) {
-                for (i = 0; i < group_size; i++) {
-                        tc = flex_array_get(group, i);
-                        if (!tc->cset)
-                                break;
-                        put_css_set(tc->cset);
-                }
-        }
+        ret = 0;
+        goto out_release_tset;
+
 out_cancel_attach:
-        if (retval) {
-                for_each_css(css, i, cgrp) {
-                        if (css == failed_css)
-                                break;
-                        if (css->ss->cancel_attach)
-                                css->ss->cancel_attach(css, &tset);
-                }
+        for_each_css(css, i, cgrp) {
+                if (css == failed_css)
+                        break;
+                if (css->ss->cancel_attach)
+                        css->ss->cancel_attach(css, &tset);
         }
-out_free_group_list:
-        flex_array_free(group);
-        return retval;
+out_release_tset:
+        down_write(&css_set_rwsem);
+        list_splice_init(&tset.dst_csets, &tset.src_csets);
+        list_for_each_entry_safe(cset, tmp_cset, &tset.src_csets, mg_node) {
+                list_splice_tail_init(&cset->mg_tasks, &cset->tasks);
+                list_del_init(&cset->mg_node);
+        }
+        up_write(&css_set_rwsem);
+        return ret;
+}
+
+/**
+ * cgroup_attach_task - attach a task or a whole threadgroup to a cgroup
+ * @dst_cgrp: the cgroup to attach to
+ * @leader: the task or the leader of the threadgroup to be attached
+ * @threadgroup: attach the whole threadgroup?
+ *
+ * Call holding cgroup_mutex and threadgroup_lock of @leader.
+ */
+static int cgroup_attach_task(struct cgroup *dst_cgrp,
+                              struct task_struct *leader, bool threadgroup)
+{
+        LIST_HEAD(preloaded_csets);
+        struct task_struct *task;
+        int ret;
+
+        /* look up all src csets */
+        down_read(&css_set_rwsem);
+        rcu_read_lock();
+        task = leader;
+        do {
+                cgroup_migrate_add_src(task_css_set(task), dst_cgrp,
+                                       &preloaded_csets);
+                if (!threadgroup)
+                        break;
+        } while_each_thread(leader, task);
+        rcu_read_unlock();
+        up_read(&css_set_rwsem);
+
+        /* prepare dst csets and commit */
+        ret = cgroup_migrate_prepare_dst(dst_cgrp, &preloaded_csets);
+        if (!ret)
+                ret = cgroup_migrate(dst_cgrp, leader, threadgroup);
+
+        cgroup_migrate_finish(&preloaded_csets);
+        return ret;
 }
 
 /*
  * Find the task_struct of the task to attach by vpid and pass it along to the
  * function to attach either it or all tasks in its threadgroup. Will lock
- * cgroup_mutex and threadgroup; may take task_lock of task.
+ * cgroup_mutex and threadgroup.
  */
 static int attach_task_by_pid(struct cgroup *cgrp, u64 pid, bool threadgroup)
 {
@@ -2198,12 +2145,19 @@ out_unlock_cgroup:
  */
 int cgroup_attach_task_all(struct task_struct *from, struct task_struct *tsk)
 {
-        struct cgroupfs_root *root;
+        struct cgroup_root *root;
         int retval = 0;
 
         mutex_lock(&cgroup_mutex);
-        for_each_active_root(root) {
-                struct cgroup *from_cgrp = task_cgroup_from_root(from, root);
+        for_each_root(root) {
+                struct cgroup *from_cgrp;
+
+                if (root == &cgrp_dfl_root)
+                        continue;
+
+                down_read(&css_set_rwsem);
+                from_cgrp = task_cgroup_from_root(from, root);
+                up_read(&css_set_rwsem);
 
                 retval = cgroup_attach_task(from_cgrp, tsk, false);
                 if (retval)
@@ -2228,16 +2182,17 @@ static int cgroup_procs_write(struct cgroup_subsys_state *css,
 }
 
 static int cgroup_release_agent_write(struct cgroup_subsys_state *css,
-                                      struct cftype *cft, const char *buffer)
+                                      struct cftype *cft, char *buffer)
 {
-        BUILD_BUG_ON(sizeof(css->cgroup->root->release_agent_path) < PATH_MAX);
-        if (strlen(buffer) >= PATH_MAX)
-                return -EINVAL;
+        struct cgroup_root *root = css->cgroup->root;
+
+        BUILD_BUG_ON(sizeof(root->release_agent_path) < PATH_MAX);
         if (!cgroup_lock_live_group(css->cgroup))
                 return -ENODEV;
-        mutex_lock(&cgroup_root_mutex);
-        strcpy(css->cgroup->root->release_agent_path, buffer);
-        mutex_unlock(&cgroup_root_mutex);
+        spin_lock(&release_agent_path_lock);
+        strlcpy(root->release_agent_path, buffer,
+                sizeof(root->release_agent_path));
+        spin_unlock(&release_agent_path_lock);
         mutex_unlock(&cgroup_mutex);
         return 0;
 }
@@ -2262,32 +2217,23 @@ static int cgroup_sane_behavior_show(struct seq_file *seq, void *v)
         return 0;
 }
 
-/* A buffer size big enough for numbers or short strings */
-#define CGROUP_LOCAL_BUFFER_SIZE 64
-
-static ssize_t cgroup_file_write(struct file *file, const char __user *userbuf,
-                                 size_t nbytes, loff_t *ppos)
+static ssize_t cgroup_file_write(struct kernfs_open_file *of, char *buf,
+                                 size_t nbytes, loff_t off)
 {
-        struct cfent *cfe = __d_cfe(file->f_dentry);
-        struct cftype *cft = __d_cft(file->f_dentry);
-        struct cgroup_subsys_state *css = cfe->css;
-        size_t max_bytes = cft->max_write_len ?: CGROUP_LOCAL_BUFFER_SIZE - 1;
-        char *buf;
+        struct cgroup *cgrp = of->kn->parent->priv;
+        struct cftype *cft = of->kn->priv;
+        struct cgroup_subsys_state *css;
         int ret;
 
-        if (nbytes >= max_bytes)
-                return -E2BIG;
-
-        buf = kmalloc(nbytes + 1, GFP_KERNEL);
-        if (!buf)
-                return -ENOMEM;
-
-        if (copy_from_user(buf, userbuf, nbytes)) {
-                ret = -EFAULT;
-                goto out_free;
-        }
-
-        buf[nbytes] = '\0';
+        /*
+         * kernfs guarantees that a file isn't deleted with operations in
+         * flight, which means that the matching css is and stays alive and
+         * doesn't need to be pinned.  The RCU locking is not necessary
+         * either.  It's just for the convenience of using cgroup_css().
+         */
+        rcu_read_lock();
+        css = cgroup_css(cgrp, cft->ss);
+        rcu_read_unlock();
 
         if (cft->write_string) {
                 ret = cft->write_string(css, cft, strstrip(buf));
@@ -2306,53 +2252,23 @@ static ssize_t cgroup_file_write(struct file *file, const char __user *userbuf,
         } else {
                 ret = -EINVAL;
         }
-out_free:
-        kfree(buf);
+
         return ret ?: nbytes;
 }
 
-/*
- * seqfile ops/methods for returning structured data. Currently just
- * supports string->u64 maps, but can be extended in future.
- */
-
 static void *cgroup_seqfile_start(struct seq_file *seq, loff_t *ppos)
 {
-        struct cftype *cft = seq_cft(seq);
-
-        if (cft->seq_start) {
-                return cft->seq_start(seq, ppos);
-        } else {
-                /*
-                 * The same behavior and code as single_open().  Returns
-                 * !NULL if pos is at the beginning; otherwise, NULL.
-                 */
-                return NULL + !*ppos;
-        }
+        return seq_cft(seq)->seq_start(seq, ppos);
 }
 
 static void *cgroup_seqfile_next(struct seq_file *seq, void *v, loff_t *ppos)
 {
-        struct cftype *cft = seq_cft(seq);
-
-        if (cft->seq_next) {
-                return cft->seq_next(seq, v, ppos);
-        } else {
-                /*
-                 * The same behavior and code as single_open(), always
-                 * terminate after the initial read.
-                 */
-                ++*ppos;
-                return NULL;
-        }
+        return seq_cft(seq)->seq_next(seq, v, ppos);
 }
 
 static void cgroup_seqfile_stop(struct seq_file *seq, void *v)
 {
-        struct cftype *cft = seq_cft(seq);
-
-        if (cft->seq_stop)
-                cft->seq_stop(seq, v);
+        seq_cft(seq)->seq_stop(seq, v);
 }
 
 static int cgroup_seqfile_show(struct seq_file *m, void *arg)
@@ -2372,96 +2288,35 @@ static int cgroup_seqfile_show(struct seq_file *m, void *arg)
         return 0;
 }
 
-static struct seq_operations cgroup_seq_operations = {
-        .start          = cgroup_seqfile_start,
-        .next           = cgroup_seqfile_next,
-        .stop           = cgroup_seqfile_stop,
-        .show           = cgroup_seqfile_show,
+static struct kernfs_ops cgroup_kf_single_ops = {
+        .atomic_write_len       = PAGE_SIZE,
+        .write                  = cgroup_file_write,
+        .seq_show               = cgroup_seqfile_show,
 };
 
-static int cgroup_file_open(struct inode *inode, struct file *file)
-{
-        struct cfent *cfe = __d_cfe(file->f_dentry);
-        struct cftype *cft = __d_cft(file->f_dentry);
-        struct cgroup *cgrp = __d_cgrp(cfe->dentry->d_parent);
-        struct cgroup_subsys_state *css;
-        struct cgroup_open_file *of;
-        int err;
-
-        err = generic_file_open(inode, file);
-        if (err)
-                return err;
-
-        /*
-         * If the file belongs to a subsystem, pin the css.  Will be
-         * unpinned either on open failure or release.  This ensures that
-         * @css stays alive for all file operations.
-         */
-        rcu_read_lock();
-        css = cgroup_css(cgrp, cft->ss);
-        if (cft->ss && !css_tryget(css))
-                css = NULL;
-        rcu_read_unlock();
-
-        if (!css)
-                return -ENODEV;
-
-        /*
-         * @cfe->css is used by read/write/close to determine the
-         * associated css.  @file->private_data would be a better place but
-         * that's already used by seqfile.  Multiple accessors may use it
-         * simultaneously which is okay as the association never changes.
-         */
-        WARN_ON_ONCE(cfe->css && cfe->css != css);
-        cfe->css = css;
-
-        of = __seq_open_private(file, &cgroup_seq_operations,
-                                sizeof(struct cgroup_open_file));
-        if (of) {
-                of->cfe = cfe;
-                return 0;
-        }
-
-        if (css->ss)
-                css_put(css);
-        return -ENOMEM;
-}
-
-static int cgroup_file_release(struct inode *inode, struct file *file)
-{
-        struct cfent *cfe = __d_cfe(file->f_dentry);
-        struct cgroup_subsys_state *css = cfe->css;
-
-        if (css->ss)
-                css_put(css);
-        return seq_release_private(inode, file);
-}
+static struct kernfs_ops cgroup_kf_ops = {
+        .atomic_write_len       = PAGE_SIZE,
+        .write                  = cgroup_file_write,
+        .seq_start              = cgroup_seqfile_start,
+        .seq_next               = cgroup_seqfile_next,
+        .seq_stop               = cgroup_seqfile_stop,
+        .seq_show               = cgroup_seqfile_show,
+};
 
 /*
  * cgroup_rename - Only allow simple rename of directories in place.
  */
-static int cgroup_rename(struct inode *old_dir, struct dentry *old_dentry,
-                            struct inode *new_dir, struct dentry *new_dentry)
+static int cgroup_rename(struct kernfs_node *kn, struct kernfs_node *new_parent,
+                         const char *new_name_str)
 {
+        struct cgroup *cgrp = kn->priv;
         int ret;
-        struct cgroup_name *name, *old_name;
-        struct cgroup *cgrp;
-
-        /*
-         * It's convinient to use parent dir's i_mutex to protected
-         * cgrp->name.
-         */
-        lockdep_assert_held(&old_dir->i_mutex);
 
-        if (!S_ISDIR(old_dentry->d_inode->i_mode))
+        if (kernfs_type(kn) != KERNFS_DIR)
                 return -ENOTDIR;
-        if (new_dentry->d_inode)
-                return -EEXIST;
-        if (old_dir != new_dir)
+        if (kn->parent != new_parent)
                 return -EIO;
 
-        cgrp = __d_cgrp(old_dentry);
-
         /*
          * This isn't a proper migration and its usefulness is very
          * limited.  Disallow if sane_behavior.
@@ -2469,218 +2324,40 @@ static int cgroup_rename(struct inode *old_dir, struct dentry *old_dentry,
         if (cgroup_sane_behavior(cgrp))
                 return -EPERM;
 
-        name = cgroup_alloc_name(new_dentry);
-        if (!name)
-                return -ENOMEM;
-
-        ret = simple_rename(old_dir, old_dentry, new_dir, new_dentry);
-        if (ret) {
-                kfree(name);
-                return ret;
-        }
-
-        old_name = rcu_dereference_protected(cgrp->name, true);
-        rcu_assign_pointer(cgrp->name, name);
-
-        kfree_rcu(old_name, rcu_head);
-        return 0;
-}
-
-static struct simple_xattrs *__d_xattrs(struct dentry *dentry)
-{
-        if (S_ISDIR(dentry->d_inode->i_mode))
-                return &__d_cgrp(dentry)->xattrs;
-        else
-                return &__d_cfe(dentry)->xattrs;
-}
-
-static inline int xattr_enabled(struct dentry *dentry)
-{
-        struct cgroupfs_root *root = dentry->d_sb->s_fs_info;
-        return root->flags & CGRP_ROOT_XATTR;
-}
-
-static bool is_valid_xattr(const char *name)
-{
-        if (!strncmp(name, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN) ||
-            !strncmp(name, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN))
-                return true;
-        return false;
-}
-
-static int cgroup_setxattr(struct dentry *dentry, const char *name,
-                           const void *val, size_t size, int flags)
-{
-        if (!xattr_enabled(dentry))
-                return -EOPNOTSUPP;
-        if (!is_valid_xattr(name))
-                return -EINVAL;
-        return simple_xattr_set(__d_xattrs(dentry), name, val, size, flags);
-}
-
-static int cgroup_removexattr(struct dentry *dentry, const char *name)
-{
-        if (!xattr_enabled(dentry))
-                return -EOPNOTSUPP;
-        if (!is_valid_xattr(name))
-                return -EINVAL;
-        return simple_xattr_remove(__d_xattrs(dentry), name);
-}
-
-static ssize_t cgroup_getxattr(struct dentry *dentry, const char *name,
-                               void *buf, size_t size)
-{
-        if (!xattr_enabled(dentry))
-                return -EOPNOTSUPP;
-        if (!is_valid_xattr(name))
-                return -EINVAL;
-        return simple_xattr_get(__d_xattrs(dentry), name, buf, size);
-}
-
-static ssize_t cgroup_listxattr(struct dentry *dentry, char *buf, size_t size)
-{
-        if (!xattr_enabled(dentry))
-                return -EOPNOTSUPP;
-        return simple_xattr_list(__d_xattrs(dentry), buf, size);
-}
-
-static const struct file_operations cgroup_file_operations = {
-        .read = seq_read,
-        .write = cgroup_file_write,
-        .llseek = generic_file_llseek,
-        .open = cgroup_file_open,
-        .release = cgroup_file_release,
-};
-
-static const struct inode_operations cgroup_file_inode_operations = {
-        .setxattr = cgroup_setxattr,
-        .getxattr = cgroup_getxattr,
-        .listxattr = cgroup_listxattr,
-        .removexattr = cgroup_removexattr,
-};
-
-static const struct inode_operations cgroup_dir_inode_operations = {
-        .lookup = simple_lookup,
-        .mkdir = cgroup_mkdir,
-        .rmdir = cgroup_rmdir,
-        .rename = cgroup_rename,
-        .setxattr = cgroup_setxattr,
-        .getxattr = cgroup_getxattr,
-        .listxattr = cgroup_listxattr,
-        .removexattr = cgroup_removexattr,
-};
-
-static int cgroup_create_file(struct dentry *dentry, umode_t mode,
-                                struct super_block *sb)
-{
-        struct inode *inode;
-
-        if (!dentry)
-                return -ENOENT;
-        if (dentry->d_inode)
-                return -EEXIST;
-
-        inode = cgroup_new_inode(mode, sb);
-        if (!inode)
-                return -ENOMEM;
-
-        if (S_ISDIR(mode)) {
-                inode->i_op = &cgroup_dir_inode_operations;
-                inode->i_fop = &simple_dir_operations;
-
-                /* start off with i_nlink == 2 (for "." entry) */
-                inc_nlink(inode);
-                inc_nlink(dentry->d_parent->d_inode);
-
-                /*
-                 * Control reaches here with cgroup_mutex held.
-                 * @inode->i_mutex should nest outside cgroup_mutex but we
-                 * want to populate it immediately without releasing
-                 * cgroup_mutex.  As @inode isn't visible to anyone else
-                 * yet, trylock will always succeed without affecting
-                 * lockdep checks.
-                 */
-                WARN_ON_ONCE(!mutex_trylock(&inode->i_mutex));
-        } else if (S_ISREG(mode)) {
-                inode->i_size = 0;
-                inode->i_fop = &cgroup_file_operations;
-                inode->i_op = &cgroup_file_inode_operations;
-        }
-        d_instantiate(dentry, inode);
-        dget(dentry);   /* Extra count - pin the dentry in core */
-        return 0;
-}
-
-/**
- * cgroup_file_mode - deduce file mode of a control file
- * @cft: the control file in question
- *
- * returns cft->mode if ->mode is not 0
- * returns S_IRUGO|S_IWUSR if it has both a read and a write handler
- * returns S_IRUGO if it has only a read handler
- * returns S_IWUSR if it has only a write hander
- */
-static umode_t cgroup_file_mode(const struct cftype *cft)
-{
-        umode_t mode = 0;
+        /*
+         * We're gonna grab cgroup_tree_mutex which nests outside kernfs
+         * active_ref.  kernfs_rename() doesn't require active_ref
+         * protection.  Break them before grabbing cgroup_tree_mutex.
+         */
+        kernfs_break_active_protection(new_parent);
+        kernfs_break_active_protection(kn);
 
-        if (cft->mode)
-                return cft->mode;
+        mutex_lock(&cgroup_tree_mutex);
+        mutex_lock(&cgroup_mutex);
 
-        if (cft->read_u64 || cft->read_s64 || cft->seq_show)
-                mode |= S_IRUGO;
+        ret = kernfs_rename(kn, new_parent, new_name_str);
 
-        if (cft->write_u64 || cft->write_s64 || cft->write_string ||
-            cft->trigger)
-                mode |= S_IWUSR;
+        mutex_unlock(&cgroup_mutex);
+        mutex_unlock(&cgroup_tree_mutex);
 
-        return mode;
+        kernfs_unbreak_active_protection(kn);
+        kernfs_unbreak_active_protection(new_parent);
+        return ret;
 }
 
 static int cgroup_add_file(struct cgroup *cgrp, struct cftype *cft)
 {
-        struct dentry *dir = cgrp->dentry;
-        struct cgroup *parent = __d_cgrp(dir);
-        struct dentry *dentry;
-        struct cfent *cfe;
-        int error;
-        umode_t mode;
-        char name[MAX_CGROUP_TYPE_NAMELEN + MAX_CFTYPE_NAME + 2] = { 0 };
-
-        if (cft->ss && !(cft->flags & CFTYPE_NO_PREFIX) &&
-            !(cgrp->root->flags & CGRP_ROOT_NOPREFIX)) {
-                strcpy(name, cft->ss->name);
-                strcat(name, ".");
-        }
-        strcat(name, cft->name);
-
-        BUG_ON(!mutex_is_locked(&dir->d_inode->i_mutex));
-
-        cfe = kzalloc(sizeof(*cfe), GFP_KERNEL);
-        if (!cfe)
-                return -ENOMEM;
+        char name[CGROUP_FILE_NAME_MAX];
+        struct kernfs_node *kn;
+        struct lock_class_key *key = NULL;
 
-        dentry = lookup_one_len(name, dir, strlen(name));
-        if (IS_ERR(dentry)) {
-                error = PTR_ERR(dentry);
-                goto out;
-        }
-
-        cfe->type = (void *)cft;
-        cfe->dentry = dentry;
-        dentry->d_fsdata = cfe;
-        simple_xattrs_init(&cfe->xattrs);
-
-        mode = cgroup_file_mode(cft);
-        error = cgroup_create_file(dentry, mode | S_IFREG, cgrp->root->sb);
-        if (!error) {
-                list_add_tail(&cfe->node, &parent->files);
-                cfe = NULL;
-        }
-        dput(dentry);
-out:
-        kfree(cfe);
-        return error;
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+        key = &cft->lockdep_key;
+#endif
+        kn = __kernfs_create_file(cgrp->kn, cgroup_file_name(cgrp, cft, name),
+                                  cgroup_file_mode(cft), 0, cft->kf_ops, cft,
+                                  NULL, false, key);
+        return PTR_ERR_OR_ZERO(kn);
 }
 
 /**
@@ -2700,11 +2377,12 @@ static int cgroup_addrm_files(struct cgroup *cgrp, struct cftype cfts[],
         struct cftype *cft;
         int ret;
 
-        lockdep_assert_held(&cgrp->dentry->d_inode->i_mutex);
-        lockdep_assert_held(&cgroup_mutex);
+        lockdep_assert_held(&cgroup_tree_mutex);
 
         for (cft = cfts; cft->name[0] != '\0'; cft++) {
                 /* does cft->flags tell us to skip this file on @cgrp? */
+                if ((cft->flags & CFTYPE_ONLY_ON_DFL) && !cgroup_on_dfl(cgrp))
+                        continue;
                 if ((cft->flags & CFTYPE_INSANE) && cgroup_sane_behavior(cgrp))
                         continue;
                 if ((cft->flags & CFTYPE_NOT_ON_ROOT) && !cgrp->parent)
@@ -2726,44 +2404,19 @@ static int cgroup_addrm_files(struct cgroup *cgrp, struct cftype cfts[],
         return 0;
 }
 
-static void cgroup_cfts_prepare(void)
-        __acquires(&cgroup_mutex)
-{
-        /*
-         * Thanks to the entanglement with vfs inode locking, we can't walk
-         * the existing cgroups under cgroup_mutex and create files.
-         * Instead, we use css_for_each_descendant_pre() and drop RCU read
-         * lock before calling cgroup_addrm_files().
-         */
-        mutex_lock(&cgroup_mutex);
-}
-
-static int cgroup_cfts_commit(struct cftype *cfts, bool is_add)
-        __releases(&cgroup_mutex)
+static int cgroup_apply_cftypes(struct cftype *cfts, bool is_add)
 {
         LIST_HEAD(pending);
         struct cgroup_subsys *ss = cfts[0].ss;
-        struct cgroup *root = &ss->root->top_cgroup;
-        struct super_block *sb = ss->root->sb;
-        struct dentry *prev = NULL;
-        struct inode *inode;
+        struct cgroup *root = &ss->root->cgrp;
         struct cgroup_subsys_state *css;
-        u64 update_before;
         int ret = 0;
 
-        /* %NULL @cfts indicates abort and don't bother if @ss isn't attached */
-        if (!cfts || ss->root == &cgroup_dummy_root ||
-            !atomic_inc_not_zero(&sb->s_active)) {
-                mutex_unlock(&cgroup_mutex);
-                return 0;
-        }
+        lockdep_assert_held(&cgroup_tree_mutex);
 
-        /*
-         * All cgroups which are created after we drop cgroup_mutex will
-         * have the updated set of files, so we only need to update the
-         * cgroups created before the current @cgroup_serial_nr_next.
-         */
-        update_before = cgroup_serial_nr_next;
+        /* don't bother if @ss isn't attached */
+        if (ss->root == &cgrp_dfl_root)
+                return 0;
 
         /* add/rm files for all cgroups created before */
         css_for_each_descendant_pre(css, cgroup_css(root, ss)) {
@@ -2772,62 +2425,75 @@ static int cgroup_cfts_commit(struct cftype *cfts, bool is_add)
                 if (cgroup_is_dead(cgrp))
                         continue;
 
-                inode = cgrp->dentry->d_inode;
-                dget(cgrp->dentry);
-                dput(prev);
-                prev = cgrp->dentry;
-
-                mutex_unlock(&cgroup_mutex);
-                mutex_lock(&inode->i_mutex);
-                mutex_lock(&cgroup_mutex);
-                if (cgrp->serial_nr < update_before && !cgroup_is_dead(cgrp))
-                        ret = cgroup_addrm_files(cgrp, cfts, is_add);
-                mutex_unlock(&inode->i_mutex);
+                ret = cgroup_addrm_files(cgrp, cfts, is_add);
                 if (ret)
                         break;
         }
-        mutex_unlock(&cgroup_mutex);
-        dput(prev);
-        deactivate_super(sb);
+
+        if (is_add && !ret)
+                kernfs_activate(root->kn);
         return ret;
 }
 
-/**
- * cgroup_add_cftypes - add an array of cftypes to a subsystem
- * @ss: target cgroup subsystem
- * @cfts: zero-length name terminated array of cftypes
- *
- * Register @cfts to @ss.  Files described by @cfts are created for all
- * existing cgroups to which @ss is attached and all future cgroups will
- * have them too.  This function can be called anytime whether @ss is
- * attached or not.
- *
- * Returns 0 on successful registration, -errno on failure.  Note that this
- * function currently returns 0 as long as @cfts registration is successful
- * even if some file creation attempts on existing cgroups fail.
- */
-int cgroup_add_cftypes(struct cgroup_subsys *ss, struct cftype *cfts)
+static void cgroup_exit_cftypes(struct cftype *cfts)
 {
-        struct cftype_set *set;
         struct cftype *cft;
-        int ret;
 
-        set = kzalloc(sizeof(*set), GFP_KERNEL);
-        if (!set)
-                return -ENOMEM;
+        for (cft = cfts; cft->name[0] != '\0'; cft++) {
+                /* free copy for custom atomic_write_len, see init_cftypes() */
+                if (cft->max_write_len && cft->max_write_len != PAGE_SIZE)
+                        kfree(cft->kf_ops);
+                cft->kf_ops = NULL;
+                cft->ss = NULL;
+        }
+}
 
-        for (cft = cfts; cft->name[0] != '\0'; cft++)
+static int cgroup_init_cftypes(struct cgroup_subsys *ss, struct cftype *cfts)
+{
+        struct cftype *cft;
+
+        for (cft = cfts; cft->name[0] != '\0'; cft++) {
+                struct kernfs_ops *kf_ops;
+
+                WARN_ON(cft->ss || cft->kf_ops);
+
+                if (cft->seq_start)
+                        kf_ops = &cgroup_kf_ops;
+                else
+                        kf_ops = &cgroup_kf_single_ops;
+
+                /*
+                 * Ugh... if @cft wants a custom max_write_len, we need to
+                 * make a copy of kf_ops to set its atomic_write_len.
+                 */
+                if (cft->max_write_len && cft->max_write_len != PAGE_SIZE) {
+                        kf_ops = kmemdup(kf_ops, sizeof(*kf_ops), GFP_KERNEL);
+                        if (!kf_ops) {
+                                cgroup_exit_cftypes(cfts);
+                                return -ENOMEM;
+                        }
+                        kf_ops->atomic_write_len = cft->max_write_len;
+                }
+
+                cft->kf_ops = kf_ops;
                 cft->ss = ss;
+        }
 
-        cgroup_cfts_prepare();
-        set->cfts = cfts;
-        list_add_tail(&set->node, &ss->cftsets);
-        ret = cgroup_cfts_commit(cfts, true);
-        if (ret)
-                cgroup_rm_cftypes(cfts);
-        return ret;
+        return 0;
+}
+
+static int cgroup_rm_cftypes_locked(struct cftype *cfts)
+{
+        lockdep_assert_held(&cgroup_tree_mutex);
+
+        if (!cfts || !cfts[0].ss)
+                return -ENOENT;
+
+        list_del(&cfts->node);
+        cgroup_apply_cftypes(cfts, false);
+        cgroup_exit_cftypes(cfts);
+        return 0;
 }
-EXPORT_SYMBOL_GPL(cgroup_add_cftypes);
 
 /**
  * cgroup_rm_cftypes - remove an array of cftypes from a subsystem
@@ -2842,24 +2508,48 @@ EXPORT_SYMBOL_GPL(cgroup_add_cftypes);
  */
 int cgroup_rm_cftypes(struct cftype *cfts)
 {
-        struct cftype_set *set;
+        int ret;
 
-        if (!cfts || !cfts[0].ss)
-                return -ENOENT;
+        mutex_lock(&cgroup_tree_mutex);
+        ret = cgroup_rm_cftypes_locked(cfts);
+        mutex_unlock(&cgroup_tree_mutex);
+        return ret;
+}
 
-        cgroup_cfts_prepare();
+/**
+ * cgroup_add_cftypes - add an array of cftypes to a subsystem
+ * @ss: target cgroup subsystem
+ * @cfts: zero-length name terminated array of cftypes
+ *
+ * Register @cfts to @ss.  Files described by @cfts are created for all
+ * existing cgroups to which @ss is attached and all future cgroups will
+ * have them too.  This function can be called anytime whether @ss is
+ * attached or not.
+ *
+ * Returns 0 on successful registration, -errno on failure.  Note that this
+ * function currently returns 0 as long as @cfts registration is successful
+ * even if some file creation attempts on existing cgroups fail.
+ */
+int cgroup_add_cftypes(struct cgroup_subsys *ss, struct cftype *cfts)
+{
+        int ret;
 
-        list_for_each_entry(set, &cfts[0].ss->cftsets, node) {
-                if (set->cfts == cfts) {
-                        list_del(&set->node);
-                        kfree(set);
-                        cgroup_cfts_commit(cfts, false);
-                        return 0;
-                }
-        }
+        if (!cfts || cfts[0].name[0] == '\0')
+                return 0;
+
+        ret = cgroup_init_cftypes(ss, cfts);
+        if (ret)
+                return ret;
+
+        mutex_lock(&cgroup_tree_mutex);
 
-        cgroup_cfts_commit(NULL, false);
-        return -ENOENT;
+        list_add_tail(&cfts->node, &ss->cfts);
+        ret = cgroup_apply_cftypes(cfts, true);
+        if (ret)
+                cgroup_rm_cftypes_locked(cfts);
+
+        mutex_unlock(&cgroup_tree_mutex);
+        return ret;
 }
 
 /**
@@ -2868,57 +2558,18 @@ int cgroup_rm_cftypes(struct cftype *cfts)
  *
  * Return the number of tasks in the cgroup.
  */
-int cgroup_task_count(const struct cgroup *cgrp)
+static int cgroup_task_count(const struct cgroup *cgrp)
 {
         int count = 0;
         struct cgrp_cset_link *link;
 
-        read_lock(&css_set_lock);
+        down_read(&css_set_rwsem);
         list_for_each_entry(link, &cgrp->cset_links, cset_link)
                 count += atomic_read(&link->cset->refcount);
-        read_unlock(&css_set_lock);
+        up_read(&css_set_rwsem);
         return count;
 }
 
-/*
- * To reduce the fork() overhead for systems that are not actually using
- * their cgroups capability, we don't maintain the lists running through
- * each css_set to its tasks until we see the list actually used - in other
- * words after the first call to css_task_iter_start().
- */
-static void cgroup_enable_task_cg_lists(void)
-{
-        struct task_struct *p, *g;
-        write_lock(&css_set_lock);
-        use_task_css_set_links = 1;
-        /*
-         * We need tasklist_lock because RCU is not safe against
-         * while_each_thread(). Besides, a forking task that has passed
-         * cgroup_post_fork() without seeing use_task_css_set_links = 1
-         * is not guaranteed to have its child immediately visible in the
-         * tasklist if we walk through it with RCU.
-         */
-        read_lock(&tasklist_lock);
-        do_each_thread(g, p) {
-                task_lock(p);
-                /*
-                 * We should check if the process is exiting, otherwise
-                 * it will race with cgroup_exit() in that the list
-                 * entry won't be deleted though the process has exited.
-                 * Do it while holding siglock so that we don't end up
-                 * racing against cgroup_exit().
-                 */
-                spin_lock_irq(&p->sighand->siglock);
-                if (!(p->flags & PF_EXITING) && list_empty(&p->cg_list))
-                        list_add(&p->cg_list, &task_css_set(p)->tasks);
-                spin_unlock_irq(&p->sighand->siglock);
-
-                task_unlock(p);
-        } while_each_thread(g, p);
-        read_unlock(&tasklist_lock);
-        write_unlock(&css_set_lock);
-}
-
 /**
  * css_next_child - find the next child of a given css
  * @pos_css: the current position (%NULL to initiate traversal)
@@ -2937,7 +2588,7 @@ css_next_child(struct cgroup_subsys_state *pos_css,
         struct cgroup *cgrp = parent_css->cgroup;
         struct cgroup *next;
 
-        cgroup_assert_mutex_or_rcu_locked();
+        cgroup_assert_mutexes_or_rcu_locked();
 
         /*
          * @pos could already have been removed.  Once a cgroup is removed,
@@ -2973,7 +2624,6 @@ css_next_child(struct cgroup_subsys_state *pos_css,
 
         return cgroup_css(next, parent_css->ss);
 }
-EXPORT_SYMBOL_GPL(css_next_child);
 
 /**
  * css_next_descendant_pre - find the next descendant for pre-order walk
@@ -2995,7 +2645,7 @@ css_next_descendant_pre(struct cgroup_subsys_state *pos,
 {
         struct cgroup_subsys_state *next;
 
-        cgroup_assert_mutex_or_rcu_locked();
+        cgroup_assert_mutexes_or_rcu_locked();
 
         /* if first iteration, visit @root */
         if (!pos)
@@ -3016,7 +2666,6 @@ css_next_descendant_pre(struct cgroup_subsys_state *pos,
 
         return NULL;
 }
-EXPORT_SYMBOL_GPL(css_next_descendant_pre);
 
 /**
  * css_rightmost_descendant - return the rightmost descendant of a css
@@ -3036,7 +2685,7 @@ css_rightmost_descendant(struct cgroup_subsys_state *pos)
 {
         struct cgroup_subsys_state *last, *tmp;
 
-        cgroup_assert_mutex_or_rcu_locked();
+        cgroup_assert_mutexes_or_rcu_locked();
 
         do {
                 last = pos;
@@ -3048,7 +2697,6 @@ css_rightmost_descendant(struct cgroup_subsys_state *pos)
 
         return last;
 }
-EXPORT_SYMBOL_GPL(css_rightmost_descendant);
 
 static struct cgroup_subsys_state *
 css_leftmost_descendant(struct cgroup_subsys_state *pos)
@@ -3084,7 +2732,7 @@ css_next_descendant_post(struct cgroup_subsys_state *pos,
 {
         struct cgroup_subsys_state *next;
 
-        cgroup_assert_mutex_or_rcu_locked();
+        cgroup_assert_mutexes_or_rcu_locked();
 
         /* if first iteration, visit leftmost descendant which may be @root */
         if (!pos)
@@ -3102,7 +2750,6 @@ css_next_descendant_post(struct cgroup_subsys_state *pos,
         /* no sibling left, visit parent */
         return css_parent(pos);
 }
-EXPORT_SYMBOL_GPL(css_next_descendant_post);
 
 /**
  * css_advance_task_iter - advance a task itererator to the next css_set
@@ -3125,9 +2772,14 @@ static void css_advance_task_iter(struct css_task_iter *it)
                 }
                 link = list_entry(l, struct cgrp_cset_link, cset_link);
                 cset = link->cset;
-        } while (list_empty(&cset->tasks));
+        } while (list_empty(&cset->tasks) && list_empty(&cset->mg_tasks));
+
         it->cset_link = l;
-        it->task = cset->tasks.next;
+
+        if (!list_empty(&cset->tasks))
+                it->task = cset->tasks.next;
+        else
+                it->task = cset->mg_tasks.next;
 }
 
 /**
@@ -3146,17 +2798,12 @@ static void css_advance_task_iter(struct css_task_iter *it)
  */
 void css_task_iter_start(struct cgroup_subsys_state *css,
                          struct css_task_iter *it)
-        __acquires(css_set_lock)
+        __acquires(css_set_rwsem)
 {
-        /*
-         * The first time anyone tries to iterate across a css, we need to
-         * enable the list linking each css_set to its tasks, and fix up
-         * all existing tasks.
-         */
-        if (!use_task_css_set_links)
-                cgroup_enable_task_cg_lists();
+        /* no one should try to iterate before mounting cgroups */
+        WARN_ON_ONCE(!use_task_css_set_links);
 
-        read_lock(&css_set_lock);
+        down_read(&css_set_rwsem);
 
         it->origin_css = css;
         it->cset_link = &css->cgroup->cset_links;
@@ -3176,24 +2823,29 @@ struct task_struct *css_task_iter_next(struct css_task_iter *it)
 {
         struct task_struct *res;
         struct list_head *l = it->task;
-        struct cgrp_cset_link *link;
+        struct cgrp_cset_link *link = list_entry(it->cset_link,
+                                        struct cgrp_cset_link, cset_link);
 
         /* If the iterator cg is NULL, we have no tasks */
         if (!it->cset_link)
                 return NULL;
         res = list_entry(l, struct task_struct, cg_list);
-        /* Advance iterator to find next entry */
+
+        /*
+         * Advance iterator to find next entry.  cset->tasks is consumed
+         * first and then ->mg_tasks.  After ->mg_tasks, we move onto the
+         * next cset.
+         */
         l = l->next;
-        link = list_entry(it->cset_link, struct cgrp_cset_link, cset_link);
-        if (l == &link->cset->tasks) {
-                /*
-                 * We reached the end of this task list - move on to the
-                 * next cgrp_cset_link.
-                 */
+
+        if (l == &link->cset->tasks)
+                l = link->cset->mg_tasks.next;
+
+        if (l == &link->cset->mg_tasks)
                 css_advance_task_iter(it);
-        } else {
+        else
                 it->task = l;
-        }
+
         return res;
 }
 
@@ -3204,191 +2856,62 @@ struct task_struct *css_task_iter_next(struct css_task_iter *it)
  * Finish task iteration started by css_task_iter_start().
  */
 void css_task_iter_end(struct css_task_iter *it)
-        __releases(css_set_lock)
-{
-        read_unlock(&css_set_lock);
-}
-
-static inline int started_after_time(struct task_struct *t1,
-                                     struct timespec *time,
-                                     struct task_struct *t2)
-{
-        int start_diff = timespec_compare(&t1->start_time, time);
-        if (start_diff > 0) {
-                return 1;
-        } else if (start_diff < 0) {
-                return 0;
-        } else {
-                /*
-                 * Arbitrarily, if two processes started at the same
-                 * time, we'll say that the lower pointer value
-                 * started first. Note that t2 may have exited by now
-                 * so this may not be a valid pointer any longer, but
-                 * that's fine - it still serves to distinguish
-                 * between two tasks started (effectively) simultaneously.
-                 */
-                return t1 > t2;
-        }
-}
-
-/*
- * This function is a callback from heap_insert() and is used to order
- * the heap.
- * In this case we order the heap in descending task start time.
- */
-static inline int started_after(void *p1, void *p2)
+        __releases(css_set_rwsem)
 {
-        struct task_struct *t1 = p1;
-        struct task_struct *t2 = p2;
-        return started_after_time(t1, &t2->start_time, t2);
+        up_read(&css_set_rwsem);
 }
 
 /**
- * css_scan_tasks - iterate though all the tasks in a css
- * @css: the css to iterate tasks of
- * @test: optional test callback
- * @process: process callback
- * @data: data passed to @test and @process
- * @heap: optional pre-allocated heap used for task iteration
- *
- * Iterate through all the tasks in @css, calling @test for each, and if it
- * returns %true, call @process for it also.
- *
- * @test may be NULL, meaning always true (select all tasks), which
- * effectively duplicates css_task_iter_{start,next,end}() but does not
- * lock css_set_lock for the call to @process.
- *
- * It is guaranteed that @process will act on every task that is a member
- * of @css for the duration of this call.  This function may or may not
- * call @process for tasks that exit or move to a different css during the
- * call, or are forked or move into the css during the call.
- *
- * Note that @test may be called with locks held, and may in some
- * situations be called multiple times for the same task, so it should be
- * cheap.
+ * cgroup_trasnsfer_tasks - move tasks from one cgroup to another
+ * @to: cgroup to which the tasks will be moved
+ * @from: cgroup in which the tasks currently reside
  *
- * If @heap is non-NULL, a heap has been pre-allocated and will be used for
- * heap operations (and its "gt" member will be overwritten), else a
- * temporary heap will be used (allocation of which may cause this function
- * to fail).
+ * Locking rules between cgroup_post_fork() and the migration path
+ * guarantee that, if a task is forking while being migrated, the new child
+ * is guaranteed to be either visible in the source cgroup after the
+ * parent's migration is complete or put into the target cgroup.  No task
+ * can slip out of migration through forking.
  */
-int css_scan_tasks(struct cgroup_subsys_state *css,
-                   bool (*test)(struct task_struct *, void *),
-                   void (*process)(struct task_struct *, void *),
-                   void *data, struct ptr_heap *heap)
+int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from)
 {
-        int retval, i;
+        LIST_HEAD(preloaded_csets);
+        struct cgrp_cset_link *link;
         struct css_task_iter it;
-        struct task_struct *p, *dropped;
-        /* Never dereference latest_task, since it's not refcounted */
-        struct task_struct *latest_task = NULL;
-        struct ptr_heap tmp_heap;
-        struct timespec latest_time = { 0, 0 };
-
-        if (heap) {
-                /* The caller supplied our heap and pre-allocated its memory */
-                heap->gt = &started_after;
-        } else {
-                /* We need to allocate our own heap memory */
-                heap = &tmp_heap;
-                retval = heap_init(heap, PAGE_SIZE, GFP_KERNEL, &started_after);
-                if (retval)
-                        /* cannot allocate the heap */
-                        return retval;
-        }
+        struct task_struct *task;
+        int ret;
 
- again:
-        /*
-         * Scan tasks in the css, using the @test callback to determine
-         * which are of interest, and invoking @process callback on the
-         * ones which need an update.  Since we don't want to hold any
-         * locks during the task updates, gather tasks to be processed in a
-         * heap structure.  The heap is sorted by descending task start
-         * time.  If the statically-sized heap fills up, we overflow tasks
-         * that started later, and in future iterations only consider tasks
-         * that started after the latest task in the previous pass. This
-         * guarantees forward progress and that we don't miss any tasks.
-         */
-        heap->size = 0;
-        css_task_iter_start(css, &it);
-        while ((p = css_task_iter_next(&it))) {
-                /*
-                 * Only affect tasks that qualify per the caller's callback,
-                 * if he provided one
-                 */
-                if (test && !test(p, data))
-                        continue;
-                /*
-                 * Only process tasks that started after the last task
-                 * we processed
-                 */
-                if (!started_after_time(p, &latest_time, latest_task))
-                        continue;
-                dropped = heap_insert(heap, p);
-                if (dropped == NULL) {
-                        /*
-                         * The new task was inserted; the heap wasn't
-                         * previously full
-                         */
-                        get_task_struct(p);
-                } else if (dropped != p) {
-                        /*
-                         * The new task was inserted, and pushed out a
-                         * different task
-                         */
-                        get_task_struct(p);
-                        put_task_struct(dropped);
-                }
-                /*
-                 * Else the new task was newer than anything already in
-                 * the heap and wasn't inserted
-                 */
-        }
-        css_task_iter_end(&it);
+        mutex_lock(&cgroup_mutex);
 
-        if (heap->size) {
-                for (i = 0; i < heap->size; i++) {
-                        struct task_struct *q = heap->ptrs[i];
-                        if (i == 0) {
-                                latest_time = q->start_time;
-                                latest_task = q;
-                        }
-                        /* Process the task per the caller's callback */
-                        process(q, data);
-                        put_task_struct(q);
-                }
-                /*
-                 * If we had to process any tasks at all, scan again
-                 * in case some of them were in the middle of forking
-                 * children that didn't get processed.
-                 * Not the most efficient way to do it, but it avoids
-                 * having to take callback_mutex in the fork path
-                 */
-                goto again;
-        }
-        if (heap == &tmp_heap)
-                heap_free(&tmp_heap);
-        return 0;
-}
+        /* all tasks in @from are being moved, all csets are source */
+        down_read(&css_set_rwsem);
+        list_for_each_entry(link, &from->cset_links, cset_link)
+                cgroup_migrate_add_src(link->cset, to, &preloaded_csets);
+        up_read(&css_set_rwsem);
 
-static void cgroup_transfer_one_task(struct task_struct *task, void *data)
-{
-        struct cgroup *new_cgroup = data;
+        ret = cgroup_migrate_prepare_dst(to, &preloaded_csets);
+        if (ret)
+                goto out_err;
 
-        mutex_lock(&cgroup_mutex);
-        cgroup_attach_task(new_cgroup, task, false);
+        /*
+         * Migrate tasks one-by-one until @form is empty.  This fails iff
+         * ->can_attach() fails.
+         */
+        do {
+                css_task_iter_start(&from->dummy_css, &it);
+                task = css_task_iter_next(&it);
+                if (task)
+                        get_task_struct(task);
+                css_task_iter_end(&it);
+
+                if (task) {
+                        ret = cgroup_migrate(to, task, false);
+                        put_task_struct(task);
+                }
+        } while (task && !ret);
+out_err:
+        cgroup_migrate_finish(&preloaded_csets);
         mutex_unlock(&cgroup_mutex);
-}
-
-/**
- * cgroup_trasnsfer_tasks - move tasks from one cgroup to another
- * @to: cgroup to which the tasks will be moved
- * @from: cgroup in which the tasks currently reside
- */
-int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from)
-{
-        return css_scan_tasks(&from->dummy_css, NULL, cgroup_transfer_one_task,
-                              to, NULL);
+        return ret;
 }
 
 /*
@@ -3687,21 +3210,31 @@ static int pidlist_array_load(struct cgroup *cgrp, enum cgroup_filetype type,
  */
 int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry)
 {
-        int ret = -EINVAL;
+        struct kernfs_node *kn = kernfs_node_from_dentry(dentry);
         struct cgroup *cgrp;
         struct css_task_iter it;
         struct task_struct *tsk;
 
+        /* it should be kernfs_node belonging to cgroupfs and is a directory */
+        if (dentry->d_sb->s_type != &cgroup_fs_type || !kn ||
+            kernfs_type(kn) != KERNFS_DIR)
+                return -EINVAL;
+
+        mutex_lock(&cgroup_mutex);
+
         /*
-         * Validate dentry by checking the superblock operations,
-         * and make sure it's a directory.
+         * We aren't being called from kernfs and there's no guarantee on
+         * @kn->priv's validity.  For this and css_tryget_from_dir(),
+         * @kn->priv is RCU safe.  Let's do the RCU dancing.
          */
-        if (dentry->d_sb->s_op != &cgroup_ops ||
-            !S_ISDIR(dentry->d_inode->i_mode))
-                 goto err;
-
-        ret = 0;
-        cgrp = dentry->d_fsdata;
+        rcu_read_lock();
+        cgrp = rcu_dereference(kn->priv);
+        if (!cgrp || cgroup_is_dead(cgrp)) {
+                rcu_read_unlock();
+                mutex_unlock(&cgroup_mutex);
+                return -ENOENT;
+        }
+        rcu_read_unlock();
 
         css_task_iter_start(&cgrp->dummy_css, &it);
         while ((tsk = css_task_iter_next(&it))) {
@@ -3726,8 +3259,8 @@ int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry)
         }
         css_task_iter_end(&it);
 
-err:
-        return ret;
+        mutex_unlock(&cgroup_mutex);
+        return 0;
 }
 
 
@@ -3745,7 +3278,7 @@ static void *cgroup_pidlist_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_open_file *of = s->private;
+        struct kernfs_open_file *of = s->private;
         struct cgroup *cgrp = seq_css(s)->cgroup;
         struct cgroup_pidlist *l;
         enum cgroup_filetype type = seq_cft(s)->private;
@@ -3800,7 +3333,7 @@ static void *cgroup_pidlist_start(struct seq_file *s, loff_t *pos)
 
 static void cgroup_pidlist_stop(struct seq_file *s, void *v)
 {
-        struct cgroup_open_file *of = s->private;
+        struct kernfs_open_file *of = s->private;
         struct cgroup_pidlist *l = of->priv;
 
         if (l)
@@ -3811,7 +3344,7 @@ static void cgroup_pidlist_stop(struct seq_file *s, void *v)
 
 static void *cgroup_pidlist_next(struct seq_file *s, void *v, loff_t *pos)
 {
-        struct cgroup_open_file *of = s->private;
+        struct kernfs_open_file *of = s->private;
         struct cgroup_pidlist *l = of->priv;
         pid_t *p = v;
         pid_t *end = l->list + l->length;
@@ -3861,23 +3394,6 @@ static int cgroup_write_notify_on_release(struct cgroup_subsys_state *css,
         return 0;
 }
 
-/*
- * When dput() is called asynchronously, if umount has been done and
- * then deactivate_super() in cgroup_free_fn() kills the superblock,
- * there's a small window that vfs will see the root dentry with non-zero
- * refcnt and trigger BUG().
- *
- * That's why we hold a reference before dput() and drop it right after.
- */
-static void cgroup_dput(struct cgroup *cgrp)
-{
-        struct super_block *sb = cgrp->root->sb;
-
-        atomic_inc(&sb->s_active);
-        dput(cgrp->dentry);
-        deactivate_super(sb);
-}
-
 static u64 cgroup_clone_children_read(struct cgroup_subsys_state *css,
                                       struct cftype *cft)
 {
@@ -3944,7 +3460,7 @@ static struct cftype cgroup_base_files[] = {
                 .flags = CFTYPE_INSANE | CFTYPE_ONLY_ON_ROOT,
                 .seq_show = cgroup_release_agent_show,
                 .write_string = cgroup_release_agent_write,
-                .max_write_len = PATH_MAX,
+                .max_write_len = PATH_MAX - 1,
         },
         { }     /* terminate */
 };
@@ -3963,13 +3479,13 @@ static int cgroup_populate_dir(struct cgroup *cgrp, unsigned long subsys_mask)
 
         /* process cftsets of each subsystem */
         for_each_subsys(ss, i) {
-                struct cftype_set *set;
+                struct cftype *cfts;
 
                 if (!test_bit(i, &subsys_mask))
                         continue;
 
-                list_for_each_entry(set, &ss->cftsets, node) {
-                        ret = cgroup_addrm_files(cgrp, set->cfts, true);
+                list_for_each_entry(cfts, &ss->cfts, node) {
+                        ret = cgroup_addrm_files(cgrp, cfts, true);
                         if (ret < 0)
                                 goto err;
                 }
@@ -4012,7 +3528,7 @@ static void css_free_work_fn(struct work_struct *work)
                 css_put(css->parent);
 
         css->ss->css_free(css);
-        cgroup_dput(cgrp);
+        cgroup_put(cgrp);
 }
 
 static void css_free_rcu_fn(struct rcu_head *rcu_head)
@@ -4020,10 +3536,6 @@ static void css_free_rcu_fn(struct rcu_head *rcu_head)
         struct cgroup_subsys_state *css =
                 container_of(rcu_head, struct cgroup_subsys_state, rcu_head);
 
-        /*
-         * css holds an extra ref to @cgrp->dentry which is put on the last
-         * css_put().  dput() requires process context which we don't have.
-         */
         INIT_WORK(&css->destroy_work, css_free_work_fn);
         queue_work(cgroup_destroy_wq, &css->destroy_work);
 }
@@ -4033,7 +3545,7 @@ static void css_release(struct percpu_ref *ref)
         struct cgroup_subsys_state *css =
                 container_of(ref, struct cgroup_subsys_state, refcnt);
 
-        rcu_assign_pointer(css->cgroup->subsys[css->ss->subsys_id], NULL);
+        RCU_INIT_POINTER(css->cgroup->subsys[css->ss->id], NULL);
         call_rcu(&css->rcu_head, css_free_rcu_fn);
 }
 
@@ -4058,6 +3570,7 @@ static int online_css(struct cgroup_subsys_state *css)
         struct cgroup_subsys *ss = css->ss;
         int ret = 0;
 
+        lockdep_assert_held(&cgroup_tree_mutex);
         lockdep_assert_held(&cgroup_mutex);
 
         if (ss->css_online)
@@ -4065,7 +3578,7 @@ static int online_css(struct cgroup_subsys_state *css)
         if (!ret) {
                 css->flags |= CSS_ONLINE;
                 css->cgroup->nr_css++;
-                rcu_assign_pointer(css->cgroup->subsys[ss->subsys_id], css);
+                rcu_assign_pointer(css->cgroup->subsys[ss->id], css);
         }
         return ret;
 }
@@ -4075,6 +3588,7 @@ static void offline_css(struct cgroup_subsys_state *css)
 {
         struct cgroup_subsys *ss = css->ss;
 
+        lockdep_assert_held(&cgroup_tree_mutex);
         lockdep_assert_held(&cgroup_mutex);
 
         if (!(css->flags & CSS_ONLINE))
@@ -4085,7 +3599,7 @@ static void offline_css(struct cgroup_subsys_state *css)
 
         css->flags &= ~CSS_ONLINE;
         css->cgroup->nr_css--;
-        RCU_INIT_POINTER(css->cgroup->subsys[ss->subsys_id], css);
+        RCU_INIT_POINTER(css->cgroup->subsys[ss->id], css);
 }
 
 /**
@@ -4103,7 +3617,6 @@ static int create_css(struct cgroup *cgrp, struct cgroup_subsys *ss)
         struct cgroup_subsys_state *css;
         int err;
 
-        lockdep_assert_held(&cgrp->dentry->d_inode->i_mutex);
         lockdep_assert_held(&cgroup_mutex);
 
         css = ss->css_alloc(cgroup_css(parent, ss));
@@ -4112,21 +3625,23 @@ static int create_css(struct cgroup *cgrp, struct cgroup_subsys *ss)
 
         err = percpu_ref_init(&css->refcnt, css_release);
         if (err)
-                goto err_free;
+                goto err_free_css;
 
         init_css(css, ss, cgrp);
 
-        err = cgroup_populate_dir(cgrp, 1 << ss->subsys_id);
+        err = cgroup_populate_dir(cgrp, 1 << ss->id);
         if (err)
-                goto err_free;
+                goto err_free_percpu_ref;
 
         err = online_css(css);
         if (err)
-                goto err_free;
+                goto err_clear_dir;
 
-        dget(cgrp->dentry);
+        cgroup_get(cgrp);
         css_get(css->parent);
 
+        cgrp->subsys_mask |= 1 << ss->id;
+
         if (ss->broken_hierarchy && !ss->warned_broken_hierarchy &&
             parent->parent) {
                 pr_warning("cgroup: %s (%d) created nested cgroup for controller \"%s\" which has incomplete hierarchy support. Nested cgroups may change behavior in the future.\n",
@@ -4138,41 +3653,43 @@ static int create_css(struct cgroup *cgrp, struct cgroup_subsys *ss)
 
         return 0;
 
-err_free:
+err_clear_dir:
+        cgroup_clear_dir(css->cgroup, 1 << css->ss->id);
+err_free_percpu_ref:
         percpu_ref_cancel_init(&css->refcnt);
+err_free_css:
         ss->css_free(css);
         return err;
 }
 
-/*
+/**
  * cgroup_create - create a cgroup
  * @parent: cgroup that will be parent of the new cgroup
- * @dentry: dentry of the new cgroup
- * @mode: mode to set on new inode
- *
- * Must be called with the mutex on the parent inode held
+ * @name: name of the new cgroup
+ * @mode: mode to set on new cgroup
  */
-static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
-                             umode_t mode)
+static long cgroup_create(struct cgroup *parent, const char *name,
+                          umode_t mode)
 {
         struct cgroup *cgrp;
-        struct cgroup_name *name;
-        struct cgroupfs_root *root = parent->root;
+        struct cgroup_root *root = parent->root;
         int ssid, err;
         struct cgroup_subsys *ss;
-        struct super_block *sb = root->sb;
+        struct kernfs_node *kn;
+
+        /*
+         * XXX: The default hierarchy isn't fully implemented yet.  Block
+         * !root cgroup creation on it for now.
+         */
+        if (root == &cgrp_dfl_root)
+                return -EINVAL;
 
         /* allocate the cgroup and its ID, 0 is reserved for the root */
         cgrp = kzalloc(sizeof(*cgrp), GFP_KERNEL);
         if (!cgrp)
                 return -ENOMEM;
 
-        name = cgroup_alloc_name(dentry);
-        if (!name) {
-                err = -ENOMEM;
-                goto err_free_cgrp;
-        }
-        rcu_assign_pointer(cgrp->name, name);
+        mutex_lock(&cgroup_tree_mutex);
 
         /*
          * Only live parents can have children.  Note that the liveliness
@@ -4183,7 +3700,7 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
          */
         if (!cgroup_lock_live_group(parent)) {
                 err = -ENODEV;
-                goto err_free_name;
+                goto err_unlock_tree;
         }
 
         /*
@@ -4196,18 +3713,8 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
                 goto err_unlock;
         }
 
-        /* Grab a reference on the superblock so the hierarchy doesn't
-         * get deleted on unmount if there are child cgroups.  This
-         * can be done outside cgroup_mutex, since the sb can't
-         * disappear while someone has an open control file on the
-         * fs */
-        atomic_inc(&sb->s_active);
-
         init_cgroup_housekeeping(cgrp);
 
-        dentry->d_fsdata = cgrp;
-        cgrp->dentry = dentry;
-
         cgrp->parent = parent;
         cgrp->dummy_css.parent = &parent->dummy_css;
         cgrp->root = parent->root;
@@ -4218,24 +3725,26 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
         if (test_bit(CGRP_CPUSET_CLONE_CHILDREN, &parent->flags))
                 set_bit(CGRP_CPUSET_CLONE_CHILDREN, &cgrp->flags);
 
+        /* create the directory */
+        kn = kernfs_create_dir(parent->kn, name, mode, cgrp);
+        if (IS_ERR(kn)) {
+                err = PTR_ERR(kn);
+                goto err_free_id;
+        }
+        cgrp->kn = kn;
+
         /*
-         * Create directory.  cgroup_create_file() returns with the new
-         * directory locked on success so that it can be populated without
-         * dropping cgroup_mutex.
+         * This extra ref will be put in cgroup_free_fn() and guarantees
+         * that @cgrp->kn is always accessible.
          */
-        err = cgroup_create_file(dentry, S_IFDIR | mode, sb);
-        if (err < 0)
-                goto err_free_id;
-        lockdep_assert_held(&dentry->d_inode->i_mutex);
+        kernfs_get(kn);
 
         cgrp->serial_nr = cgroup_serial_nr_next++;
 
         /* allocation complete, commit to creation */
         list_add_tail_rcu(&cgrp->sibling, &cgrp->parent->children);
-        root->number_of_cgroups++;
-
-        /* hold a ref to the parent's dentry */
-        dget(parent->dentry);
+        atomic_inc(&root->nr_cgrps);
+        cgroup_get(parent);
 
         /*
          * @cgrp is now fully operational.  If something fails after this
@@ -4249,43 +3758,56 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
 
         /* let's create and online css's */
         for_each_subsys(ss, ssid) {
-                if (root->subsys_mask & (1 << ssid)) {
+                if (root->cgrp.subsys_mask & (1 << ssid)) {
                         err = create_css(cgrp, ss);
                         if (err)
                                 goto err_destroy;
                 }
         }
 
+        kernfs_activate(kn);
+
         mutex_unlock(&cgroup_mutex);
-        mutex_unlock(&cgrp->dentry->d_inode->i_mutex);
+        mutex_unlock(&cgroup_tree_mutex);
 
         return 0;
 
 err_free_id:
         idr_remove(&root->cgroup_idr, cgrp->id);
-        /* Release the reference count that we took on the superblock */
-        deactivate_super(sb);
 err_unlock:
         mutex_unlock(&cgroup_mutex);
-err_free_name:
-        kfree(rcu_dereference_raw(cgrp->name));
-err_free_cgrp:
+err_unlock_tree:
+        mutex_unlock(&cgroup_tree_mutex);
         kfree(cgrp);
         return err;
 
 err_destroy:
         cgroup_destroy_locked(cgrp);
         mutex_unlock(&cgroup_mutex);
-        mutex_unlock(&dentry->d_inode->i_mutex);
+        mutex_unlock(&cgroup_tree_mutex);
         return err;
 }
 
-static int cgroup_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
+static int cgroup_mkdir(struct kernfs_node *parent_kn, const char *name,
+                        umode_t mode)
 {
-        struct cgroup *c_parent = dentry->d_parent->d_fsdata;
+        struct cgroup *parent = parent_kn->priv;
+        int ret;
+
+        /*
+         * cgroup_create() grabs cgroup_tree_mutex which nests outside
+         * kernfs active_ref and cgroup_create() already synchronizes
+         * properly against removal through cgroup_lock_live_group().
+         * Break it before calling cgroup_create().
+         */
+        cgroup_get(parent);
+        kernfs_break_active_protection(parent_kn);
+
+        ret = cgroup_create(parent, name, mode);
 
-        /* the vfs holds inode->i_mutex already */
-        return cgroup_create(c_parent, dentry, mode | S_IFDIR);
+        kernfs_unbreak_active_protection(parent_kn);
+        cgroup_put(parent);
+        return ret;
 }
 
 /*
@@ -4298,6 +3820,7 @@ static void css_killed_work_fn(struct work_struct *work)
                 container_of(work, struct cgroup_subsys_state, destroy_work);
         struct cgroup *cgrp = css->cgroup;
 
+        mutex_lock(&cgroup_tree_mutex);
         mutex_lock(&cgroup_mutex);
 
         /*
@@ -4315,6 +3838,7 @@ static void css_killed_work_fn(struct work_struct *work)
                 cgroup_destroy_css_killed(cgrp);
 
         mutex_unlock(&cgroup_mutex);
+        mutex_unlock(&cgroup_tree_mutex);
 
         /*
          * Put the css refs from kill_css().  Each css holds an extra
@@ -4336,18 +3860,15 @@ static void css_killed_ref_fn(struct percpu_ref *ref)
         queue_work(cgroup_destroy_wq, &css->destroy_work);
 }
 
-/**
- * kill_css - destroy a css
- * @css: css to destroy
- *
- * This function initiates destruction of @css by removing cgroup interface
- * files and putting its base reference.  ->css_offline() will be invoked
- * asynchronously once css_tryget() is guaranteed to fail and when the
- * reference count reaches zero, @css will be released.
- */
-static void kill_css(struct cgroup_subsys_state *css)
+static void __kill_css(struct cgroup_subsys_state *css)
 {
-        cgroup_clear_dir(css->cgroup, 1 << css->ss->subsys_id);
+        lockdep_assert_held(&cgroup_tree_mutex);
+
+        /*
+         * This must happen before css is disassociated with its cgroup.
+         * See seq_css() for details.
+         */
+        cgroup_clear_dir(css->cgroup, 1 << css->ss->id);
 
         /*
          * Killing would put the base ref, but we need to keep it alive
@@ -4369,6 +3890,28 @@ static void kill_css(struct cgroup_subsys_state *css)
 }
 
 /**
+ * kill_css - destroy a css
+ * @css: css to destroy
+ *
+ * This function initiates destruction of @css by removing cgroup interface
+ * files and putting its base reference.  ->css_offline() will be invoked
+ * asynchronously once css_tryget() is guaranteed to fail and when the
+ * reference count reaches zero, @css will be released.
+ */
+static void kill_css(struct cgroup_subsys_state *css)
+{
+        struct cgroup *cgrp = css->cgroup;
+
+        lockdep_assert_held(&cgroup_tree_mutex);
+
+        /* if already killed, noop */
+        if (cgrp->subsys_mask & (1 << css->ss->id)) {
+                cgrp->subsys_mask &= ~(1 << css->ss->id);
+                __kill_css(css);
+        }
+}
+
+/**
  * cgroup_destroy_locked - the first stage of cgroup destruction
  * @cgrp: cgroup to be destroyed
  *
@@ -4395,22 +3938,21 @@ static void kill_css(struct cgroup_subsys_state *css)
 static int cgroup_destroy_locked(struct cgroup *cgrp)
         __releases(&cgroup_mutex) __acquires(&cgroup_mutex)
 {
-        struct dentry *d = cgrp->dentry;
-        struct cgroup_subsys_state *css;
         struct cgroup *child;
+        struct cgroup_subsys_state *css;
         bool empty;
         int ssid;
 
-        lockdep_assert_held(&d->d_inode->i_mutex);
+        lockdep_assert_held(&cgroup_tree_mutex);
         lockdep_assert_held(&cgroup_mutex);
 
         /*
-         * css_set_lock synchronizes access to ->cset_links and prevents
-         * @cgrp from being removed while __put_css_set() is in progress.
+         * css_set_rwsem synchronizes access to ->cset_links and prevents
+         * @cgrp from being removed while put_css_set() is in progress.
          */
-        read_lock(&css_set_lock);
+        down_read(&css_set_rwsem);
         empty = list_empty(&cgrp->cset_links);
-        read_unlock(&css_set_lock);
+        up_read(&css_set_rwsem);
         if (!empty)
                 return -EBUSY;
 
@@ -4431,14 +3973,6 @@ static int cgroup_destroy_locked(struct cgroup *cgrp)
                 return -EBUSY;
 
         /*
-         * Initiate massacre of all css's.  cgroup_destroy_css_killed()
-         * will be invoked to perform the rest of destruction once the
-         * percpu refs of all css's are confirmed to be killed.
-         */
-        for_each_css(css, ssid, cgrp)
-                kill_css(css);
-
-        /*
          * Mark @cgrp dead.  This prevents further task migration and child
          * creation by disabling cgroup_lock_live_group().  Note that
          * CGRP_DEAD assertion is depended upon by css_next_child() to
@@ -4447,6 +3981,17 @@ static int cgroup_destroy_locked(struct cgroup *cgrp)
          */
         set_bit(CGRP_DEAD, &cgrp->flags);
 
+        /*
+         * Initiate massacre of all css's.  cgroup_destroy_css_killed()
+         * will be invoked to perform the rest of destruction once the
+         * percpu refs of all css's are confirmed to be killed.  This
+         * involves removing the subsystem's files, drop cgroup_mutex.
+         */
+        mutex_unlock(&cgroup_mutex);
+        for_each_css(css, ssid, cgrp)
+                kill_css(css);
+        mutex_lock(&cgroup_mutex);
+
         /* CGRP_DEAD is set, remove from ->release_list for the last time */
         raw_spin_lock(&release_list_lock);
         if (!list_empty(&cgrp->release_list))
@@ -4462,14 +4007,20 @@ static int cgroup_destroy_locked(struct cgroup *cgrp)
         if (!cgrp->nr_css)
                 cgroup_destroy_css_killed(cgrp);
 
+        /* remove @cgrp directory along with the base files */
+        mutex_unlock(&cgroup_mutex);
+
         /*
-         * Clear the base files and remove @cgrp directory.  The removal
-         * puts the base ref but we aren't quite done with @cgrp yet, so
-         * hold onto it.
+         * There are two control paths which try to determine cgroup from
+         * dentry without going through kernfs - cgroupstats_build() and
+         * css_tryget_from_dir().  Those are supported by RCU protecting
+         * clearing of cgrp->kn->priv backpointer, which should happen
+         * after all files under it have been removed.
          */
-        cgroup_addrm_files(cgrp, cgroup_base_files, false);
-        dget(d);
-        cgroup_d_remove_dir(d);
+        kernfs_remove(cgrp->kn);        /* @cgrp has an extra ref on its kn */
+        RCU_INIT_POINTER(*(void __rcu __force **)&cgrp->kn->priv, NULL);
+
+        mutex_lock(&cgroup_mutex);
 
         return 0;
 };
@@ -4486,72 +4037,82 @@ static int cgroup_destroy_locked(struct cgroup *cgrp)
 static void cgroup_destroy_css_killed(struct cgroup *cgrp)
 {
         struct cgroup *parent = cgrp->parent;
-        struct dentry *d = cgrp->dentry;
 
+        lockdep_assert_held(&cgroup_tree_mutex);
         lockdep_assert_held(&cgroup_mutex);
 
         /* delete this cgroup from parent->children */
         list_del_rcu(&cgrp->sibling);
 
-        dput(d);
+        cgroup_put(cgrp);
 
         set_bit(CGRP_RELEASABLE, &parent->flags);
         check_for_release(parent);
 }
 
-static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry)
+static int cgroup_rmdir(struct kernfs_node *kn)
 {
-        int ret;
-
-        mutex_lock(&cgroup_mutex);
-        ret = cgroup_destroy_locked(dentry->d_fsdata);
-        mutex_unlock(&cgroup_mutex);
+        struct cgroup *cgrp = kn->priv;
+        int ret = 0;
 
-        return ret;
-}
+        /*
+         * This is self-destruction but @kn can't be removed while this
+         * callback is in progress.  Let's break active protection.  Once
+         * the protection is broken, @cgrp can be destroyed at any point.
+         * Pin it so that it stays accessible.
+         */
+        cgroup_get(cgrp);
+        kernfs_break_active_protection(kn);
 
-static void __init_or_module cgroup_init_cftsets(struct cgroup_subsys *ss)
-{
-        INIT_LIST_HEAD(&ss->cftsets);
+        mutex_lock(&cgroup_tree_mutex);
+        mutex_lock(&cgroup_mutex);
 
         /*
-         * base_cftset is embedded in subsys itself, no need to worry about
-         * deregistration.
+         * @cgrp might already have been destroyed while we're trying to
+         * grab the mutexes.
          */
-        if (ss->base_cftypes) {
-                struct cftype *cft;
+        if (!cgroup_is_dead(cgrp))
+                ret = cgroup_destroy_locked(cgrp);
 
-                for (cft = ss->base_cftypes; cft->name[0] != '\0'; cft++)
-                        cft->ss = ss;
+        mutex_unlock(&cgroup_mutex);
+        mutex_unlock(&cgroup_tree_mutex);
 
-                ss->base_cftset.cfts = ss->base_cftypes;
-                list_add_tail(&ss->base_cftset.node, &ss->cftsets);
-        }
+        kernfs_unbreak_active_protection(kn);
+        cgroup_put(cgrp);
+        return ret;
 }
 
+static struct kernfs_syscall_ops cgroup_kf_syscall_ops = {
+        .remount_fs             = cgroup_remount,
+        .show_options           = cgroup_show_options,
+        .mkdir                  = cgroup_mkdir,
+        .rmdir                  = cgroup_rmdir,
+        .rename                 = cgroup_rename,
+};
+
 static void __init cgroup_init_subsys(struct cgroup_subsys *ss)
 {
         struct cgroup_subsys_state *css;
 
         printk(KERN_INFO "Initializing cgroup subsys %s\n", ss->name);
 
+        mutex_lock(&cgroup_tree_mutex);
         mutex_lock(&cgroup_mutex);
 
-        /* init base cftset */
-        cgroup_init_cftsets(ss);
+        INIT_LIST_HEAD(&ss->cfts);
 
-        /* Create the top cgroup state for this subsystem */
-        ss->root = &cgroup_dummy_root;
-        css = ss->css_alloc(cgroup_css(cgroup_dummy_top, ss));
+        /* Create the root cgroup state for this subsystem */
+        ss->root = &cgrp_dfl_root;
+        css = ss->css_alloc(cgroup_css(&cgrp_dfl_root.cgrp, ss));
         /* We don't handle early failures gracefully */
         BUG_ON(IS_ERR(css));
-        init_css(css, ss, cgroup_dummy_top);
+        init_css(css, ss, &cgrp_dfl_root.cgrp);
 
         /* Update the init_css_set to contain a subsys
          * pointer to this state - since the subsystem is
          * newly registered, all tasks and hence the
-         * init_css_set is in the subsystem's top cgroup. */
-        init_css_set.subsys[ss->subsys_id] = css;
+         * init_css_set is in the subsystem's root cgroup. */
+        init_css_set.subsys[ss->id] = css;
 
         need_forkexit_callback |= ss->fork || ss->exit;
 
@@ -4562,185 +4123,11 @@ static void __init cgroup_init_subsys(struct cgroup_subsys *ss)
 
         BUG_ON(online_css(css));
 
-        mutex_unlock(&cgroup_mutex);
-
-        /* this function shouldn't be used with modular subsystems, since they
-         * need to register a subsys_id, among other things */
-        BUG_ON(ss->module);
-}
-
-/**
- * cgroup_load_subsys: load and register a modular subsystem at runtime
- * @ss: the subsystem to load
- *
- * This function should be called in a modular subsystem's initcall. If the
- * subsystem is built as a module, it will be assigned a new subsys_id and set
- * up for use. If the subsystem is built-in anyway, work is delegated to the
- * simpler cgroup_init_subsys.
- */
-int __init_or_module cgroup_load_subsys(struct cgroup_subsys *ss)
-{
-        struct cgroup_subsys_state *css;
-        int i, ret;
-        struct hlist_node *tmp;
-        struct css_set *cset;
-        unsigned long key;
-
-        /* check name and function validity */
-        if (ss->name == NULL || strlen(ss->name) > MAX_CGROUP_TYPE_NAMELEN ||
-            ss->css_alloc == NULL || ss->css_free == NULL)
-                return -EINVAL;
-
-        /*
-         * we don't support callbacks in modular subsystems. this check is
-         * before the ss->module check for consistency; a subsystem that could
-         * be a module should still have no callbacks even if the user isn't
-         * compiling it as one.
-         */
-        if (ss->fork || ss->exit)
-                return -EINVAL;
-
-        /*
-         * an optionally modular subsystem is built-in: we want to do nothing,
-         * since cgroup_init_subsys will have already taken care of it.
-         */
-        if (ss->module == NULL) {
-                /* a sanity check */
-                BUG_ON(cgroup_subsys[ss->subsys_id] != ss);
-                return 0;
-        }
-
-        /* init base cftset */
-        cgroup_init_cftsets(ss);
-
-        mutex_lock(&cgroup_mutex);
-        mutex_lock(&cgroup_root_mutex);
-        cgroup_subsys[ss->subsys_id] = ss;
-
-        /*
-         * no ss->css_alloc seems to need anything important in the ss
-         * struct, so this can happen first (i.e. before the dummy root
-         * attachment).
-         */
-        css = ss->css_alloc(cgroup_css(cgroup_dummy_top, ss));
-        if (IS_ERR(css)) {
-                /* failure case - need to deassign the cgroup_subsys[] slot. */
-                cgroup_subsys[ss->subsys_id] = NULL;
-                mutex_unlock(&cgroup_root_mutex);
-                mutex_unlock(&cgroup_mutex);
-                return PTR_ERR(css);
-        }
-
-        ss->root = &cgroup_dummy_root;
-
-        /* our new subsystem will be attached to the dummy hierarchy. */
-        init_css(css, ss, cgroup_dummy_top);
-
-        /*
-         * Now we need to entangle the css into the existing css_sets. unlike
-         * in cgroup_init_subsys, there are now multiple css_sets, so each one
-         * will need a new pointer to it; done by iterating the css_set_table.
-         * furthermore, modifying the existing css_sets will corrupt the hash
-         * table state, so each changed css_set will need its hash recomputed.
-         * this is all done under the css_set_lock.
-         */
-        write_lock(&css_set_lock);
-        hash_for_each_safe(css_set_table, i, tmp, cset, hlist) {
-                /* skip entries that we already rehashed */
-                if (cset->subsys[ss->subsys_id])
-                        continue;
-                /* remove existing entry */
-                hash_del(&cset->hlist);
-                /* set new value */
-                cset->subsys[ss->subsys_id] = css;
-                /* recompute hash and restore entry */
-                key = css_set_hash(cset->subsys);
-                hash_add(css_set_table, &cset->hlist, key);
-        }
-        write_unlock(&css_set_lock);
-
-        ret = online_css(css);
-        if (ret) {
-                ss->css_free(css);
-                goto err_unload;
-        }
-
-        /* success! */
-        mutex_unlock(&cgroup_root_mutex);
-        mutex_unlock(&cgroup_mutex);
-        return 0;
-
-err_unload:
-        mutex_unlock(&cgroup_root_mutex);
-        mutex_unlock(&cgroup_mutex);
-        /* @ss can't be mounted here as try_module_get() would fail */
-        cgroup_unload_subsys(ss);
-        return ret;
-}
-EXPORT_SYMBOL_GPL(cgroup_load_subsys);
-
-/**
- * cgroup_unload_subsys: unload a modular subsystem
- * @ss: the subsystem to unload
- *
- * This function should be called in a modular subsystem's exitcall. When this
- * function is invoked, the refcount on the subsystem's module will be 0, so
- * the subsystem will not be attached to any hierarchy.
- */
-void cgroup_unload_subsys(struct cgroup_subsys *ss)
-{
-        struct cgrp_cset_link *link;
-        struct cgroup_subsys_state *css;
-
-        BUG_ON(ss->module == NULL);
-
-        /*
-         * we shouldn't be called if the subsystem is in use, and the use of
-         * try_module_get() in rebind_subsystems() should ensure that it
-         * doesn't start being used while we're killing it off.
-         */
-        BUG_ON(ss->root != &cgroup_dummy_root);
-
-        mutex_lock(&cgroup_mutex);
-        mutex_lock(&cgroup_root_mutex);
-
-        css = cgroup_css(cgroup_dummy_top, ss);
-        if (css)
-                offline_css(css);
+        cgrp_dfl_root.cgrp.subsys_mask |= 1 << ss->id;
 
-        /* deassign the subsys_id */
-        cgroup_subsys[ss->subsys_id] = NULL;
-
-        /*
-         * disentangle the css from all css_sets attached to the dummy
-         * top. as in loading, we need to pay our respects to the hashtable
-         * gods.
-         */
-        write_lock(&css_set_lock);
-        list_for_each_entry(link, &cgroup_dummy_top->cset_links, cset_link) {
-                struct css_set *cset = link->cset;
-                unsigned long key;
-
-                hash_del(&cset->hlist);
-                cset->subsys[ss->subsys_id] = NULL;
-                key = css_set_hash(cset->subsys);
-                hash_add(css_set_table, &cset->hlist, key);
-        }
-        write_unlock(&css_set_lock);
-
-        /*
-         * remove subsystem's css from the cgroup_dummy_top and free it -
-         * need to free before marking as null because ss->css_free needs
-         * the cgrp->subsys pointer to find their state.
-         */
-        if (css)
-                ss->css_free(css);
-        RCU_INIT_POINTER(cgroup_dummy_top->subsys[ss->subsys_id], NULL);
-
-        mutex_unlock(&cgroup_root_mutex);
         mutex_unlock(&cgroup_mutex);
+        mutex_unlock(&cgroup_tree_mutex);
 }
-EXPORT_SYMBOL_GPL(cgroup_unload_subsys);
 
 /**
  * cgroup_init_early - cgroup initialization at system boot
@@ -4750,34 +4137,24 @@ EXPORT_SYMBOL_GPL(cgroup_unload_subsys);
  */
 int __init cgroup_init_early(void)
 {
+        static struct cgroup_sb_opts __initdata opts =
+                { .flags = CGRP_ROOT_SANE_BEHAVIOR };
         struct cgroup_subsys *ss;
         int i;
 
-        atomic_set(&init_css_set.refcount, 1);
-        INIT_LIST_HEAD(&init_css_set.cgrp_links);
-        INIT_LIST_HEAD(&init_css_set.tasks);
-        INIT_HLIST_NODE(&init_css_set.hlist);
-        css_set_count = 1;
-        init_cgroup_root(&cgroup_dummy_root);
-        cgroup_root_count = 1;
+        init_cgroup_root(&cgrp_dfl_root, &opts);
         RCU_INIT_POINTER(init_task.cgroups, &init_css_set);
 
-        init_cgrp_cset_link.cset = &init_css_set;
-        init_cgrp_cset_link.cgrp = cgroup_dummy_top;
-        list_add(&init_cgrp_cset_link.cset_link, &cgroup_dummy_top->cset_links);
-        list_add(&init_cgrp_cset_link.cgrp_link, &init_css_set.cgrp_links);
-
-        /* at bootup time, we don't worry about modular subsystems */
-        for_each_builtin_subsys(ss, i) {
-                BUG_ON(!ss->name);
-                BUG_ON(strlen(ss->name) > MAX_CGROUP_TYPE_NAMELEN);
-                BUG_ON(!ss->css_alloc);
-                BUG_ON(!ss->css_free);
-                if (ss->subsys_id != i) {
-                        printk(KERN_ERR "cgroup: Subsys %s id == %d\n",
-                               ss->name, ss->subsys_id);
-                        BUG();
-                }
+        for_each_subsys(ss, i) {
+                WARN(!ss->css_alloc || !ss->css_free || ss->name || ss->id,
+                     "invalid cgroup_subsys %d:%s css_alloc=%p css_free=%p name:id=%d:%s\n",
+                     i, cgroup_subsys_name[i], ss->css_alloc, ss->css_free,
+                     ss->id, ss->name);
+                WARN(strlen(cgroup_subsys_name[i]) > MAX_CGROUP_TYPE_NAMELEN,
+                     "cgroup_subsys_name %s too long\n", cgroup_subsys_name[i]);
+
+                ss->id = i;
+                ss->name = cgroup_subsys_name[i];
 
                 if (ss->early_init)
                         cgroup_init_subsys(ss);
@@ -4795,53 +4172,46 @@ int __init cgroup_init(void)
 {
         struct cgroup_subsys *ss;
         unsigned long key;
-        int i, err;
+        int ssid, err;
 
-        err = bdi_init(&cgroup_backing_dev_info);
-        if (err)
-                return err;
+        BUG_ON(cgroup_init_cftypes(NULL, cgroup_base_files));
 
-        for_each_builtin_subsys(ss, i) {
-                if (!ss->early_init)
-                        cgroup_init_subsys(ss);
-        }
-
-        /* allocate id for the dummy hierarchy */
+        mutex_lock(&cgroup_tree_mutex);
         mutex_lock(&cgroup_mutex);
-        mutex_lock(&cgroup_root_mutex);
 
         /* Add init_css_set to the hash table */
         key = css_set_hash(init_css_set.subsys);
         hash_add(css_set_table, &init_css_set.hlist, key);
 
-        BUG_ON(cgroup_init_root_id(&cgroup_dummy_root, 0, 1));
+        BUG_ON(cgroup_setup_root(&cgrp_dfl_root, 0));
 
-        err = idr_alloc(&cgroup_dummy_root.cgroup_idr, cgroup_dummy_top,
-                        0, 1, GFP_KERNEL);
-        BUG_ON(err < 0);
-
-        mutex_unlock(&cgroup_root_mutex);
         mutex_unlock(&cgroup_mutex);
+        mutex_unlock(&cgroup_tree_mutex);
 
-        cgroup_kobj = kobject_create_and_add("cgroup", fs_kobj);
-        if (!cgroup_kobj) {
-                err = -ENOMEM;
-                goto out;
+        for_each_subsys(ss, ssid) {
+                if (!ss->early_init)
+                        cgroup_init_subsys(ss);
+
+                /*
+                 * cftype registration needs kmalloc and can't be done
+                 * during early_init.  Register base cftypes separately.
+                 */
+                if (ss->base_cftypes)
+                        WARN_ON(cgroup_add_cftypes(ss, ss->base_cftypes));
         }
 
+        cgroup_kobj = kobject_create_and_add("cgroup", fs_kobj);
+        if (!cgroup_kobj)
+                return -ENOMEM;
+
         err = register_filesystem(&cgroup_fs_type);
         if (err < 0) {
                 kobject_put(cgroup_kobj);
-                goto out;
+                return err;
         }
 
         proc_create("cgroups", 0, NULL, &proc_cgroupstats_operations);
-
-out:
-        if (err)
-                bdi_destroy(&cgroup_backing_dev_info);
-
-        return err;
+        return 0;
 }
 
 static int __init cgroup_wq_init(void)
@@ -4873,12 +4243,6 @@ core_initcall(cgroup_wq_init);
  * proc_cgroup_show()
  *  - Print task's cgroup paths into seq_file, one line for each hierarchy
  *  - Used for /proc/<pid>/cgroup.
- *  - No need to task_lock(tsk) on this tsk->cgroup reference, as it
- *    doesn't really matter if tsk->cgroup changes after we read it,
- *    and we take cgroup_mutex, keeping cgroup_attach_task() from changing it
- *    anyway.  No need to check that tsk->cgroup != NULL, thanks to
- *    the_top_cgroup_hack in cgroup_exit(), which sets an exiting tasks
- *    cgroup to top_cgroup.
  */
 
 /* TODO: Use a proper seq_file iterator */
@@ -4886,12 +4250,12 @@ int proc_cgroup_show(struct seq_file *m, void *v)
 {
         struct pid *pid;
         struct task_struct *tsk;
-        char *buf;
+        char *buf, *path;
         int retval;
-        struct cgroupfs_root *root;
+        struct cgroup_root *root;
 
         retval = -ENOMEM;
-        buf = kmalloc(PAGE_SIZE, GFP_KERNEL);
+        buf = kmalloc(PATH_MAX, GFP_KERNEL);
         if (!buf)
                 goto out;
 
@@ -4904,29 +4268,36 @@ int proc_cgroup_show(struct seq_file *m, void *v)
         retval = 0;
 
         mutex_lock(&cgroup_mutex);
+        down_read(&css_set_rwsem);
 
-        for_each_active_root(root) {
+        for_each_root(root) {
                 struct cgroup_subsys *ss;
                 struct cgroup *cgrp;
                 int ssid, count = 0;
 
+                if (root == &cgrp_dfl_root && !cgrp_dfl_root_visible)
+                        continue;
+
                 seq_printf(m, "%d:", root->hierarchy_id);
                 for_each_subsys(ss, ssid)
-                        if (root->subsys_mask & (1 << ssid))
+                        if (root->cgrp.subsys_mask & (1 << ssid))
                                 seq_printf(m, "%s%s", count++ ? "," : "", ss->name);
                 if (strlen(root->name))
                         seq_printf(m, "%sname=%s", count ? "," : "",
                                    root->name);
                 seq_putc(m, ':');
                 cgrp = task_cgroup_from_root(tsk, root);
-                retval = cgroup_path(cgrp, buf, PAGE_SIZE);
-                if (retval < 0)
+                path = cgroup_path(cgrp, buf, PATH_MAX);
+                if (!path) {
+                        retval = -ENAMETOOLONG;
                         goto out_unlock;
-                seq_puts(m, buf);
+                }
+                seq_puts(m, path);
                 seq_putc(m, '\n');
         }
 
 out_unlock:
+        up_read(&css_set_rwsem);
         mutex_unlock(&cgroup_mutex);
         put_task_struct(tsk);
 out_free:
@@ -4952,7 +4323,7 @@ static int proc_cgroupstats_show(struct seq_file *m, void *v)
         for_each_subsys(ss, i)
                 seq_printf(m, "%s\t%d\t%d\t%d\n",
                            ss->name, ss->root->hierarchy_id,
-                           ss->root->number_of_cgroups, !ss->disabled);
+                           atomic_read(&ss->root->nr_cgrps), !ss->disabled);
 
         mutex_unlock(&cgroup_mutex);
         return 0;
@@ -4971,27 +4342,16 @@ static const struct file_operations proc_cgroupstats_operations = {
 };
 
 /**
- * cgroup_fork - attach newly forked task to its parents cgroup.
+ * cgroup_fork - initialize cgroup related fields during copy_process()
  * @child: pointer to task_struct of forking parent process.
  *
- * Description: A task inherits its parent's cgroup at fork().
- *
- * A pointer to the shared css_set was automatically copied in
- * fork.c by dup_task_struct().  However, we ignore that copy, since
- * it was not made under the protection of RCU or cgroup_mutex, so
- * might no longer be a valid cgroup pointer.  cgroup_attach_task() might
- * have already changed current->cgroups, allowing the previously
- * referenced cgroup group to be removed and freed.
- *
- * At the point that cgroup_fork() is called, 'current' is the parent
- * task, and the passed argument 'child' points to the child task.
+ * A task is associated with the init_css_set until cgroup_post_fork()
+ * attaches it to the parent's css_set.  Empty cg_list indicates that
+ * @child isn't holding reference to its css_set.
  */
 void cgroup_fork(struct task_struct *child)
 {
-        task_lock(current);
-        get_css_set(task_css_set(current));
-        child->cgroups = current->cgroups;
-        task_unlock(current);
+        RCU_INIT_POINTER(child->cgroups, &init_css_set);
         INIT_LIST_HEAD(&child->cg_list);
 }
 
@@ -5011,23 +4371,37 @@ void cgroup_post_fork(struct task_struct *child)
         int i;
 
         /*
-         * use_task_css_set_links is set to 1 before we walk the tasklist
-         * under the tasklist_lock and we read it here after we added the child
-         * to the tasklist under the tasklist_lock as well. If the child wasn't
-         * yet in the tasklist when we walked through it from
-         * cgroup_enable_task_cg_lists(), then use_task_css_set_links value
-         * should be visible now due to the paired locking and barriers implied
-         * by LOCK/UNLOCK: it is written before the tasklist_lock unlock
-         * in cgroup_enable_task_cg_lists() and read here after the tasklist_lock
-         * lock on fork.
+         * This may race against cgroup_enable_task_cg_links().  As that
+         * function sets use_task_css_set_links before grabbing
+         * tasklist_lock and we just went through tasklist_lock to add
+         * @child, it's guaranteed that either we see the set
+         * use_task_css_set_links or cgroup_enable_task_cg_lists() sees
+         * @child during its iteration.
+         *
+         * If we won the race, @child is associated with %current's
+         * css_set.  Grabbing css_set_rwsem guarantees both that the
+         * association is stable, and, on completion of the parent's
+         * migration, @child is visible in the source of migration or
+         * already in the destination cgroup.  This guarantee is necessary
+         * when implementing operations which need to migrate all tasks of
+         * a cgroup to another.
+         *
+         * Note that if we lose to cgroup_enable_task_cg_links(), @child
+         * will remain in init_css_set.  This is safe because all tasks are
+         * in the init_css_set before cg_links is enabled and there's no
+         * operation which transfers all tasks out of init_css_set.
          */
         if (use_task_css_set_links) {
-                write_lock(&css_set_lock);
-                task_lock(child);
-                if (list_empty(&child->cg_list))
-                        list_add(&child->cg_list, &task_css_set(child)->tasks);
-                task_unlock(child);
-                write_unlock(&css_set_lock);
+                struct css_set *cset;
+
+                down_write(&css_set_rwsem);
+                cset = task_css_set(current);
+                if (list_empty(&child->cg_list)) {
+                        rcu_assign_pointer(child->cgroups, cset);
+                        list_add(&child->cg_list, &cset->tasks);
+                        get_css_set(cset);
+                }
+                up_write(&css_set_rwsem);
         }
 
         /*
@@ -5036,15 +4410,7 @@ void cgroup_post_fork(struct task_struct *child)
          * and addition to css_set.
          */
         if (need_forkexit_callback) {
-                /*
-                 * fork/exit callbacks are supported only for builtin
-                 * subsystems, and the builtin section of the subsys
-                 * array is immutable, so we don't need to lock the
-                 * subsys array here. On the other hand, modular section
-                 * of the array can be freed at module unload, so we
-                 * can't touch that.
-                 */
-                for_each_builtin_subsys(ss, i)
+                for_each_subsys(ss, i)
                         if (ss->fork)
                                 ss->fork(child);
         }
@@ -5053,7 +4419,6 @@ void cgroup_post_fork(struct task_struct *child)
 /**
  * cgroup_exit - detach cgroup from exiting task
  * @tsk: pointer to task_struct of exiting process
- * @run_callback: run exit callbacks?
  *
  * Description: Detach cgroup from @tsk and release it.
  *
@@ -5063,57 +4428,38 @@ void cgroup_post_fork(struct task_struct *child)
  * use notify_on_release cgroups where very high task exit scaling
  * is required on large systems.
  *
- * the_top_cgroup_hack:
- *
- *    Set the exiting tasks cgroup to the root cgroup (top_cgroup).
- *
- *    We call cgroup_exit() while the task is still competent to
- *    handle notify_on_release(), then leave the task attached to the
- *    root cgroup in each hierarchy for the remainder of its exit.
- *
- *    To do this properly, we would increment the reference count on
- *    top_cgroup, and near the very end of the kernel/exit.c do_exit()
- *    code we would add a second cgroup function call, to drop that
- *    reference.  This would just create an unnecessary hot spot on
- *    the top_cgroup reference count, to no avail.
- *
- *    Normally, holding a reference to a cgroup without bumping its
- *    count is unsafe.   The cgroup could go away, or someone could
- *    attach us to a different cgroup, decrementing the count on
- *    the first cgroup that we never incremented.  But in this case,
- *    top_cgroup isn't going away, and either task has PF_EXITING set,
- *    which wards off any cgroup_attach_task() attempts, or task is a failed
- *    fork, never visible to cgroup_attach_task.
+ * We set the exiting tasks cgroup to the root cgroup (top_cgroup).  We
+ * call cgroup_exit() while the task is still competent to handle
+ * notify_on_release(), then leave the task attached to the root cgroup in
+ * each hierarchy for the remainder of its exit.  No need to bother with
+ * init_css_set refcnting.  init_css_set never goes away and we can't race
+ * with migration path - PF_EXITING is visible to migration path.
  */
-void cgroup_exit(struct task_struct *tsk, int run_callbacks)
+void cgroup_exit(struct task_struct *tsk)
 {
         struct cgroup_subsys *ss;
         struct css_set *cset;
+        bool put_cset = false;
         int i;
 
         /*
-         * Unlink from the css_set task list if necessary.
-         * Optimistically check cg_list before taking
-         * css_set_lock
+         * Unlink from @tsk from its css_set.  As migration path can't race
+         * with us, we can check cg_list without grabbing css_set_rwsem.
          */
         if (!list_empty(&tsk->cg_list)) {
-                write_lock(&css_set_lock);
-                if (!list_empty(&tsk->cg_list))
-                        list_del_init(&tsk->cg_list);
-                write_unlock(&css_set_lock);
+                down_write(&css_set_rwsem);
+                list_del_init(&tsk->cg_list);
+                up_write(&css_set_rwsem);
+                put_cset = true;
         }
 
         /* Reassign the task to the init_css_set. */
-        task_lock(tsk);
         cset = task_css_set(tsk);
         RCU_INIT_POINTER(tsk->cgroups, &init_css_set);
 
-        if (run_callbacks && need_forkexit_callback) {
-                /*
-                 * fork/exit callbacks are supported only for builtin
-                 * subsystems, see cgroup_post_fork() for details.
-                 */
-                for_each_builtin_subsys(ss, i) {
+        if (need_forkexit_callback) {
+                /* see cgroup_post_fork() for details */
+                for_each_subsys(ss, i) {
                         if (ss->exit) {
                                 struct cgroup_subsys_state *old_css = cset->subsys[i];
                                 struct cgroup_subsys_state *css = task_css(tsk, i);
@@ -5122,9 +4468,9 @@ void cgroup_exit(struct task_struct *tsk, int run_callbacks)
                         }
                 }
         }
-        task_unlock(tsk);
 
-        put_css_set_taskexit(cset);
+        if (put_cset)
+                put_css_set(cset, true);
 }
 
 static void check_for_release(struct cgroup *cgrp)
@@ -5181,16 +4527,17 @@ static void cgroup_release_agent(struct work_struct *work)
         while (!list_empty(&release_list)) {
                 char *argv[3], *envp[3];
                 int i;
-                char *pathbuf = NULL, *agentbuf = NULL;
+                char *pathbuf = NULL, *agentbuf = NULL, *path;
                 struct cgroup *cgrp = list_entry(release_list.next,
                                                     struct cgroup,
                                                     release_list);
                 list_del_init(&cgrp->release_list);
                 raw_spin_unlock(&release_list_lock);
-                pathbuf = kmalloc(PAGE_SIZE, GFP_KERNEL);
+                pathbuf = kmalloc(PATH_MAX, GFP_KERNEL);
                 if (!pathbuf)
                         goto continue_free;
-                if (cgroup_path(cgrp, pathbuf, PAGE_SIZE) < 0)
+                path = cgroup_path(cgrp, pathbuf, PATH_MAX);
+                if (!path)
                         goto continue_free;
                 agentbuf = kstrdup(cgrp->root->release_agent_path, GFP_KERNEL);
                 if (!agentbuf)
@@ -5198,7 +4545,7 @@ static void cgroup_release_agent(struct work_struct *work)
 
                 i = 0;
                 argv[i++] = agentbuf;
-                argv[i++] = pathbuf;
+                argv[i++] = path;
                 argv[i] = NULL;
 
                 i = 0;
@@ -5232,11 +4579,7 @@ static int __init cgroup_disable(char *str)
                 if (!*token)
                         continue;
 
-                /*
-                 * cgroup_disable, being at boot time, can't know about
-                 * module subsystems, so we don't worry about them.
-                 */
-                for_each_builtin_subsys(ss, i) {
+                for_each_subsys(ss, i) {
                         if (!strcmp(token, ss->name)) {
                                 ss->disabled = 1;
                                 printk(KERN_INFO "Disabling %s control group"
@@ -5250,28 +4593,42 @@ static int __init cgroup_disable(char *str)
 __setup("cgroup_disable=", cgroup_disable);
 
 /**
- * css_from_dir - get corresponding css from the dentry of a cgroup dir
+ * css_tryget_from_dir - get corresponding css from the dentry of a cgroup dir
  * @dentry: directory dentry of interest
  * @ss: subsystem of interest
  *
- * Must be called under cgroup_mutex or RCU read lock.  The caller is
- * responsible for pinning the returned css if it needs to be accessed
- * outside the critical section.
+ * If @dentry is a directory for a cgroup which has @ss enabled on it, try
+ * to get the corresponding css and return it.  If such css doesn't exist
+ * or can't be pinned, an ERR_PTR value is returned.
  */
-struct cgroup_subsys_state *css_from_dir(struct dentry *dentry,
-                                         struct cgroup_subsys *ss)
+struct cgroup_subsys_state *css_tryget_from_dir(struct dentry *dentry,
+                                                struct cgroup_subsys *ss)
 {
+        struct kernfs_node *kn = kernfs_node_from_dentry(dentry);
+        struct cgroup_subsys_state *css = NULL;
         struct cgroup *cgrp;
 
-        cgroup_assert_mutex_or_rcu_locked();
-
         /* is @dentry a cgroup dir? */
-        if (!dentry->d_inode ||
-            dentry->d_inode->i_op != &cgroup_dir_inode_operations)
+        if (dentry->d_sb->s_type != &cgroup_fs_type || !kn ||
+            kernfs_type(kn) != KERNFS_DIR)
                 return ERR_PTR(-EBADF);
 
-        cgrp = __d_cgrp(dentry);
-        return cgroup_css(cgrp, ss) ?: ERR_PTR(-ENOENT);
+        rcu_read_lock();
+
+        /*
+         * This path doesn't originate from kernfs and @kn could already
+         * have been or be removed at any point.  @kn->priv is RCU
+         * protected for this access.  See destroy_locked() for details.
+         */
+        cgrp = rcu_dereference(kn->priv);
+        if (cgrp)
+                css = cgroup_css(cgrp, ss);
+
+        if (!css || !css_tryget(css))
+                css = ERR_PTR(-ENOENT);
+
+        rcu_read_unlock();
+        return css;
 }
 
 /**
@@ -5286,7 +4643,7 @@ struct cgroup_subsys_state *css_from_id(int id, struct cgroup_subsys *ss)
 {
         struct cgroup *cgrp;
 
-        cgroup_assert_mutex_or_rcu_locked();
+        cgroup_assert_mutexes_or_rcu_locked();
 
         cgrp = idr_find(&ss->root->cgroup_idr, id);
         if (cgrp)
@@ -5338,23 +4695,25 @@ static int current_css_set_cg_links_read(struct seq_file *seq, void *v)
 {
         struct cgrp_cset_link *link;
         struct css_set *cset;
+        char *name_buf;
 
-        read_lock(&css_set_lock);
+        name_buf = kmalloc(NAME_MAX + 1, GFP_KERNEL);
+        if (!name_buf)
+                return -ENOMEM;
+
+        down_read(&css_set_rwsem);
         rcu_read_lock();
         cset = rcu_dereference(current->cgroups);
         list_for_each_entry(link, &cset->cgrp_links, cgrp_link) {
                 struct cgroup *c = link->cgrp;
-                const char *name;
 
-                if (c->dentry)
-                        name = c->dentry->d_name.name;
-                else
-                        name = "?";
+                cgroup_name(c, name_buf, NAME_MAX + 1);
                 seq_printf(seq, "Root %d group %s\n",
-                           c->root->hierarchy_id, name);
+                           c->root->hierarchy_id, name_buf);
         }
         rcu_read_unlock();
-        read_unlock(&css_set_lock);
+        up_read(&css_set_rwsem);
+        kfree(name_buf);
         return 0;
 }
 
@@ -5364,23 +4723,30 @@ static int cgroup_css_links_read(struct seq_file *seq, void *v)
         struct cgroup_subsys_state *css = seq_css(seq);
         struct cgrp_cset_link *link;
 
-        read_lock(&css_set_lock);
+        down_read(&css_set_rwsem);
         list_for_each_entry(link, &css->cgroup->cset_links, cset_link) {
                 struct css_set *cset = link->cset;
                 struct task_struct *task;
                 int count = 0;
+
                 seq_printf(seq, "css_set %p\n", cset);
+
                 list_for_each_entry(task, &cset->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));
-                        }
+                        if (count++ > MAX_TASKS_SHOWN_PER_CSS)
+                                goto overflow;
+                        seq_printf(seq, "  task %d\n", task_pid_vnr(task));
+                }
+
+                list_for_each_entry(task, &cset->mg_tasks, cg_list) {
+                        if (count++ > MAX_TASKS_SHOWN_PER_CSS)
+                                goto overflow;
+                        seq_printf(seq, "  task %d\n", task_pid_vnr(task));
                 }
+                continue;
+        overflow:
+                seq_puts(seq, "  ...\n");
         }
-        read_unlock(&css_set_lock);
+        up_read(&css_set_rwsem);
         return 0;
 }
 
@@ -5423,11 +4789,9 @@ static struct cftype debug_files[] =  {
         { }     /* terminate */
 };
 
-struct cgroup_subsys debug_subsys = {
-        .name = "debug",
+struct cgroup_subsys debug_cgrp_subsys = {
         .css_alloc = debug_css_alloc,
         .css_free = debug_css_free,
-        .subsys_id = debug_subsys_id,
         .base_cftypes = debug_files,
 };
 #endif /* CONFIG_CGROUP_DEBUG */
diff --git a/kernel/cgroup_freezer.c b/kernel/cgroup_freezer.c
index 6c3154e477f6..2bc4a2256444 100644
--- a/kernel/cgroup_freezer.c
+++ b/kernel/cgroup_freezer.c
@@ -52,7 +52,7 @@ static inline struct freezer *css_freezer(struct cgroup_subsys_state *css)
 
 static inline struct freezer *task_freezer(struct task_struct *task)
 {
-        return css_freezer(task_css(task, freezer_subsys_id));
+        return css_freezer(task_css(task, freezer_cgrp_id));
 }
 
 static struct freezer *parent_freezer(struct freezer *freezer)
@@ -84,8 +84,6 @@ static const char *freezer_state_strs(unsigned int state)
         return "THAWED";
 };
 
-struct cgroup_subsys freezer_subsys;
-
 static struct cgroup_subsys_state *
 freezer_css_alloc(struct cgroup_subsys_state *parent_css)
 {
@@ -189,7 +187,7 @@ static void freezer_attach(struct cgroup_subsys_state *new_css,
          * current state before executing the following - !frozen tasks may
          * be visible in a FROZEN cgroup and frozen tasks in a THAWED one.
          */
-        cgroup_taskset_for_each(task, new_css, tset) {
+        cgroup_taskset_for_each(task, tset) {
                 if (!(freezer->state & CGROUP_FREEZING)) {
                         __thaw_task(task);
                 } else {
@@ -216,6 +214,16 @@ static void freezer_attach(struct cgroup_subsys_state *new_css,
         }
 }
 
+/**
+ * freezer_fork - cgroup post fork callback
+ * @task: a task which has just been forked
+ *
+ * @task has just been created and should conform to the current state of
+ * the cgroup_freezer it belongs to.  This function may race against
+ * freezer_attach().  Losing to freezer_attach() means that we don't have
+ * to do anything as freezer_attach() will put @task into the appropriate
+ * state.
+ */
 static void freezer_fork(struct task_struct *task)
 {
         struct freezer *freezer;
@@ -224,14 +232,26 @@ static void freezer_fork(struct task_struct *task)
         freezer = task_freezer(task);
 
         /*
-         * The root cgroup is non-freezable, so we can skip the
-         * following check.
+         * The root cgroup is non-freezable, so we can skip locking the
+         * freezer.  This is safe regardless of race with task migration.
+         * If we didn't race or won, skipping is obviously the right thing
+         * to do.  If we lost and root is the new cgroup, noop is still the
+         * right thing to do.
          */
         if (!parent_freezer(freezer))
                 goto out;
 
+        /*
+         * Grab @freezer->lock and freeze @task after verifying @task still
+         * belongs to @freezer and it's freezing.  The former is for the
+         * case where we have raced against task migration and lost and
+         * @task is already in a different cgroup which may not be frozen.
+         * This isn't strictly necessary as freeze_task() is allowed to be
+         * called spuriously but let's do it anyway for, if nothing else,
+         * documentation.
+         */
         spin_lock_irq(&freezer->lock);
-        if (freezer->state & CGROUP_FREEZING)
+        if (freezer == task_freezer(task) && (freezer->state & CGROUP_FREEZING))
                 freeze_task(task);
         spin_unlock_irq(&freezer->lock);
 out:
@@ -422,7 +442,7 @@ static void freezer_change_state(struct freezer *freezer, bool freeze)
 }
 
 static int freezer_write(struct cgroup_subsys_state *css, struct cftype *cft,
-                         const char *buffer)
+                         char *buffer)
 {
         bool freeze;
 
@@ -473,13 +493,11 @@ static struct cftype files[] = {
         { }     /* terminate */
 };
 
-struct cgroup_subsys freezer_subsys = {
-        .name           = "freezer",
+struct cgroup_subsys freezer_cgrp_subsys = {
         .css_alloc      = freezer_css_alloc,
         .css_online     = freezer_css_online,
         .css_offline    = freezer_css_offline,
         .css_free       = freezer_css_free,
-        .subsys_id      = freezer_subsys_id,
         .attach         = freezer_attach,
         .fork           = freezer_fork,
         .base_cftypes   = files,
diff --git a/kernel/compat.c b/kernel/compat.c
index 0a09e481b70b..e40b0430b562 100644
--- a/kernel/compat.c
+++ b/kernel/compat.c
@@ -30,28 +30,6 @@
 
 #include <asm/uaccess.h>
 
-/*
- * Get/set struct timeval with struct timespec on the native side
- */
-static int compat_get_timeval_convert(struct timespec *o,
-                                      struct compat_timeval __user *i)
-{
-        long usec;
-
-        if (get_user(o->tv_sec, &i->tv_sec) ||
-            get_user(usec, &i->tv_usec))
-                return -EFAULT;
-        o->tv_nsec = usec * 1000;
-        return 0;
-}
-
-static int compat_put_timeval_convert(struct compat_timeval __user *o,
-                                      struct timeval *i)
-{
-        return (put_user(i->tv_sec, &o->tv_sec) ||
-                put_user(i->tv_usec, &o->tv_usec)) ? -EFAULT : 0;
-}
-
 static int compat_get_timex(struct timex *txc, struct compat_timex __user *utp)
 {
         memset(txc, 0, sizeof(struct timex));
@@ -110,13 +88,13 @@ static int compat_put_timex(struct compat_timex __user *utp, struct timex *txc)
         return 0;
 }
 
-asmlinkage long compat_sys_gettimeofday(struct compat_timeval __user *tv,
-                struct timezone __user *tz)
+COMPAT_SYSCALL_DEFINE2(gettimeofday, struct compat_timeval __user *, tv,
+                       struct timezone __user *, tz)
 {
         if (tv) {
                 struct timeval ktv;
                 do_gettimeofday(&ktv);
-                if (compat_put_timeval_convert(tv, &ktv))
+                if (compat_put_timeval(&ktv, tv))
                         return -EFAULT;
         }
         if (tz) {
@@ -127,62 +105,61 @@ asmlinkage long compat_sys_gettimeofday(struct compat_timeval __user *tv,
         return 0;
 }
 
-asmlinkage long compat_sys_settimeofday(struct compat_timeval __user *tv,
-                struct timezone __user *tz)
+COMPAT_SYSCALL_DEFINE2(settimeofday, struct compat_timeval __user *, tv,
+                       struct timezone __user *, tz)
 {
-        struct timespec kts;
-        struct timezone ktz;
+        struct timeval user_tv;
+        struct timespec new_ts;
+        struct timezone new_tz;
 
         if (tv) {
-                if (compat_get_timeval_convert(&kts, tv))
+                if (compat_get_timeval(&user_tv, tv))
                         return -EFAULT;
+                new_ts.tv_sec = user_tv.tv_sec;
+                new_ts.tv_nsec = user_tv.tv_usec * NSEC_PER_USEC;
         }
         if (tz) {
-                if (copy_from_user(&ktz, tz, sizeof(ktz)))
+                if (copy_from_user(&new_tz, tz, sizeof(*tz)))
                         return -EFAULT;
         }
 
-        return do_sys_settimeofday(tv ? &kts : NULL, tz ? &ktz : NULL);
+        return do_sys_settimeofday(tv ? &new_ts : NULL, tz ? &new_tz : NULL);
 }
 
-int get_compat_timeval(struct timeval *tv, const struct compat_timeval __user *ctv)
+static int __compat_get_timeval(struct timeval *tv, const struct compat_timeval __user *ctv)
 {
         return (!access_ok(VERIFY_READ, ctv, sizeof(*ctv)) ||
                         __get_user(tv->tv_sec, &ctv->tv_sec) ||
                         __get_user(tv->tv_usec, &ctv->tv_usec)) ? -EFAULT : 0;
 }
-EXPORT_SYMBOL_GPL(get_compat_timeval);
 
-int put_compat_timeval(const struct timeval *tv, struct compat_timeval __user *ctv)
+static int __compat_put_timeval(const struct timeval *tv, struct compat_timeval __user *ctv)
 {
         return (!access_ok(VERIFY_WRITE, ctv, sizeof(*ctv)) ||
                         __put_user(tv->tv_sec, &ctv->tv_sec) ||
                         __put_user(tv->tv_usec, &ctv->tv_usec)) ? -EFAULT : 0;
 }
-EXPORT_SYMBOL_GPL(put_compat_timeval);
 
-int get_compat_timespec(struct timespec *ts, const struct compat_timespec __user *cts)
+static int __compat_get_timespec(struct timespec *ts, const struct compat_timespec __user *cts)
 {
         return (!access_ok(VERIFY_READ, cts, sizeof(*cts)) ||
                         __get_user(ts->tv_sec, &cts->tv_sec) ||
                         __get_user(ts->tv_nsec, &cts->tv_nsec)) ? -EFAULT : 0;
 }
-EXPORT_SYMBOL_GPL(get_compat_timespec);
 
-int put_compat_timespec(const struct timespec *ts, struct compat_timespec __user *cts)
+static int __compat_put_timespec(const struct timespec *ts, struct compat_timespec __user *cts)
 {
         return (!access_ok(VERIFY_WRITE, cts, sizeof(*cts)) ||
                         __put_user(ts->tv_sec, &cts->tv_sec) ||
                         __put_user(ts->tv_nsec, &cts->tv_nsec)) ? -EFAULT : 0;
 }
-EXPORT_SYMBOL_GPL(put_compat_timespec);
 
 int compat_get_timeval(struct timeval *tv, const void __user *utv)
 {
         if (COMPAT_USE_64BIT_TIME)
                 return copy_from_user(tv, utv, sizeof *tv) ? -EFAULT : 0;
         else
-                return get_compat_timeval(tv, utv);
+                return __compat_get_timeval(tv, utv);
 }
 EXPORT_SYMBOL_GPL(compat_get_timeval);
 
@@ -191,7 +168,7 @@ int compat_put_timeval(const struct timeval *tv, void __user *utv)
         if (COMPAT_USE_64BIT_TIME)
                 return copy_to_user(utv, tv, sizeof *tv) ? -EFAULT : 0;
         else
-                return put_compat_timeval(tv, utv);
+                return __compat_put_timeval(tv, utv);
 }
 EXPORT_SYMBOL_GPL(compat_put_timeval);
 
@@ -200,7 +177,7 @@ int compat_get_timespec(struct timespec *ts, const void __user *uts)
         if (COMPAT_USE_64BIT_TIME)
                 return copy_from_user(ts, uts, sizeof *ts) ? -EFAULT : 0;
         else
-                return get_compat_timespec(ts, uts);
+                return __compat_get_timespec(ts, uts);
 }
 EXPORT_SYMBOL_GPL(compat_get_timespec);
 
@@ -209,10 +186,33 @@ int compat_put_timespec(const struct timespec *ts, void __user *uts)
         if (COMPAT_USE_64BIT_TIME)
                 return copy_to_user(uts, ts, sizeof *ts) ? -EFAULT : 0;
         else
-                return put_compat_timespec(ts, uts);
+                return __compat_put_timespec(ts, uts);
 }
 EXPORT_SYMBOL_GPL(compat_put_timespec);
 
+int compat_convert_timespec(struct timespec __user **kts,
+                            const void __user *cts)
+{
+        struct timespec ts;
+        struct timespec __user *uts;
+
+        if (!cts || COMPAT_USE_64BIT_TIME) {
+                *kts = (struct timespec __user *)cts;
+                return 0;
+        }
+
+        uts = compat_alloc_user_space(sizeof(ts));
+        if (!uts)
+                return -EFAULT;
+        if (compat_get_timespec(&ts, cts))
+                return -EFAULT;
+        if (copy_to_user(uts, &ts, sizeof(ts)))
+                return -EFAULT;
+
+        *kts = uts;
+        return 0;
+}
+
 static long compat_nanosleep_restart(struct restart_block *restart)
 {
         struct compat_timespec __user *rmtp;
@@ -229,21 +229,21 @@ static long compat_nanosleep_restart(struct restart_block *restart)
         if (ret) {
                 rmtp = restart->nanosleep.compat_rmtp;
 
-                if (rmtp && put_compat_timespec(&rmt, rmtp))
+                if (rmtp && compat_put_timespec(&rmt, rmtp))
                         return -EFAULT;
         }
 
         return ret;
 }
 
-asmlinkage long compat_sys_nanosleep(struct compat_timespec __user *rqtp,
-                                     struct compat_timespec __user *rmtp)
+COMPAT_SYSCALL_DEFINE2(nanosleep, struct compat_timespec __user *, rqtp,
+                       struct compat_timespec __user *, rmtp)
 {
         struct timespec tu, rmt;
         mm_segment_t oldfs;
         long ret;
 
-        if (get_compat_timespec(&tu, rqtp))
+        if (compat_get_timespec(&tu, rqtp))
                 return -EFAULT;
 
         if (!timespec_valid(&tu))
@@ -263,7 +263,7 @@ asmlinkage long compat_sys_nanosleep(struct compat_timespec __user *rqtp,
                 restart->fn = compat_nanosleep_restart;
                 restart->nanosleep.compat_rmtp = rmtp;
 
-                if (rmtp && put_compat_timespec(&rmt, rmtp))
+                if (rmtp && compat_put_timespec(&rmt, rmtp))
                         return -EFAULT;
         }
 
@@ -328,7 +328,7 @@ static compat_clock_t clock_t_to_compat_clock_t(clock_t x)
         return compat_jiffies_to_clock_t(clock_t_to_jiffies(x));
 }
 
-asmlinkage long compat_sys_times(struct compat_tms __user *tbuf)
+COMPAT_SYSCALL_DEFINE1(times, struct compat_tms __user *, tbuf)
 {
         if (tbuf) {
                 struct tms tms;
@@ -354,7 +354,7 @@ asmlinkage long compat_sys_times(struct compat_tms __user *tbuf)
  * types that can be passed to put_user()/get_user().
  */
 
-asmlinkage long compat_sys_sigpending(compat_old_sigset_t __user *set)
+COMPAT_SYSCALL_DEFINE1(sigpending, compat_old_sigset_t __user *, set)
 {
         old_sigset_t s;
         long ret;
@@ -424,8 +424,8 @@ COMPAT_SYSCALL_DEFINE3(sigprocmask, int, how,
 
 #endif
 
-asmlinkage long compat_sys_setrlimit(unsigned int resource,
-                struct compat_rlimit __user *rlim)
+COMPAT_SYSCALL_DEFINE2(setrlimit, unsigned int, resource,
+                       struct compat_rlimit __user *, rlim)
 {
         struct rlimit r;
 
@@ -443,15 +443,15 @@ asmlinkage long compat_sys_setrlimit(unsigned int resource,
 
 #ifdef COMPAT_RLIM_OLD_INFINITY
 
-asmlinkage long compat_sys_old_getrlimit(unsigned int resource,
-                struct compat_rlimit __user *rlim)
+COMPAT_SYSCALL_DEFINE2(old_getrlimit, unsigned int, resource,
+                       struct compat_rlimit __user *, rlim)
 {
         struct rlimit r;
         int ret;
         mm_segment_t old_fs = get_fs();
 
         set_fs(KERNEL_DS);
-        ret = sys_old_getrlimit(resource, &r);
+        ret = sys_old_getrlimit(resource, (struct rlimit __user *)&r);
         set_fs(old_fs);
 
         if (!ret) {
@@ -470,8 +470,8 @@ asmlinkage long compat_sys_old_getrlimit(unsigned int resource,
 
 #endif
 
-asmlinkage long compat_sys_getrlimit(unsigned int resource,
-                struct compat_rlimit __user *rlim)
+COMPAT_SYSCALL_DEFINE2(getrlimit, unsigned int, resource,
+                       struct compat_rlimit __user *, rlim)
 {
         struct rlimit r;
         int ret;
@@ -596,9 +596,9 @@ static int compat_get_user_cpu_mask(compat_ulong_t __user *user_mask_ptr,
         return compat_get_bitmap(k, user_mask_ptr, len * 8);
 }
 
-asmlinkage long compat_sys_sched_setaffinity(compat_pid_t pid,
-                                             unsigned int len,
-                                             compat_ulong_t __user *user_mask_ptr)
+COMPAT_SYSCALL_DEFINE3(sched_setaffinity, compat_pid_t, pid,
+                       unsigned int, len,
+                       compat_ulong_t __user *, user_mask_ptr)
 {
         cpumask_var_t new_mask;
         int retval;
@@ -616,8 +616,8 @@ out:
         return retval;
 }
 
-asmlinkage long compat_sys_sched_getaffinity(compat_pid_t pid, unsigned int len,
-                                             compat_ulong_t __user *user_mask_ptr)
+COMPAT_SYSCALL_DEFINE3(sched_getaffinity, compat_pid_t,  pid, unsigned int, len,
+                       compat_ulong_t __user *, user_mask_ptr)
 {
         int ret;
         cpumask_var_t mask;
@@ -647,8 +647,8 @@ asmlinkage long compat_sys_sched_getaffinity(compat_pid_t pid, unsigned int len,
 int get_compat_itimerspec(struct itimerspec *dst,
                           const struct compat_itimerspec __user *src)
 {
-        if (get_compat_timespec(&dst->it_interval, &src->it_interval) ||
-            get_compat_timespec(&dst->it_value, &src->it_value))
+        if (__compat_get_timespec(&dst->it_interval, &src->it_interval) ||
+            __compat_get_timespec(&dst->it_value, &src->it_value))
                 return -EFAULT;
         return 0;
 }
@@ -656,15 +656,15 @@ int get_compat_itimerspec(struct itimerspec *dst,
 int put_compat_itimerspec(struct compat_itimerspec __user *dst,
                           const struct itimerspec *src)
 {
-        if (put_compat_timespec(&src->it_interval, &dst->it_interval) ||
-            put_compat_timespec(&src->it_value, &dst->it_value))
+        if (__compat_put_timespec(&src->it_interval, &dst->it_interval) ||
+            __compat_put_timespec(&src->it_value, &dst->it_value))
                 return -EFAULT;
         return 0;
 }
 
-long compat_sys_timer_create(clockid_t which_clock,
-                        struct compat_sigevent __user *timer_event_spec,
-                        timer_t __user *created_timer_id)
+COMPAT_SYSCALL_DEFINE3(timer_create, clockid_t, which_clock,
+                       struct compat_sigevent __user *, timer_event_spec,
+                       timer_t __user *, created_timer_id)
 {
         struct sigevent __user *event = NULL;
 
@@ -680,9 +680,9 @@ long compat_sys_timer_create(clockid_t which_clock,
         return sys_timer_create(which_clock, event, created_timer_id);
 }
 
-long compat_sys_timer_settime(timer_t timer_id, int flags,
-                          struct compat_itimerspec __user *new,
-                          struct compat_itimerspec __user *old)
+COMPAT_SYSCALL_DEFINE4(timer_settime, timer_t, timer_id, int, flags,
+                       struct compat_itimerspec __user *, new,
+                       struct compat_itimerspec __user *, old)
 {
         long err;
         mm_segment_t oldfs;
@@ -703,8 +703,8 @@ long compat_sys_timer_settime(timer_t timer_id, int flags,
         return err;
 }
 
-long compat_sys_timer_gettime(timer_t timer_id,
-                struct compat_itimerspec __user *setting)
+COMPAT_SYSCALL_DEFINE2(timer_gettime, timer_t, timer_id,
+                       struct compat_itimerspec __user *, setting)
 {
         long err;
         mm_segment_t oldfs;
@@ -720,14 +720,14 @@ long compat_sys_timer_gettime(timer_t timer_id,
         return err;
 }
 
-long compat_sys_clock_settime(clockid_t which_clock,
-                struct compat_timespec __user *tp)
+COMPAT_SYSCALL_DEFINE2(clock_settime, clockid_t, which_clock,
+                       struct compat_timespec __user *, tp)
 {
         long err;
         mm_segment_t oldfs;
         struct timespec ts;
 
-        if (get_compat_timespec(&ts, tp))
+        if (compat_get_timespec(&ts, tp))
                 return -EFAULT;
         oldfs = get_fs();
         set_fs(KERNEL_DS);
@@ -737,8 +737,8 @@ long compat_sys_clock_settime(clockid_t which_clock,
         return err;
 }
 
-long compat_sys_clock_gettime(clockid_t which_clock,
-                struct compat_timespec __user *tp)
+COMPAT_SYSCALL_DEFINE2(clock_gettime, clockid_t, which_clock,
+                       struct compat_timespec __user *, tp)
 {
         long err;
         mm_segment_t oldfs;
@@ -749,13 +749,13 @@ long compat_sys_clock_gettime(clockid_t which_clock,
         err = sys_clock_gettime(which_clock,
                                 (struct timespec __user *) &ts);
         set_fs(oldfs);
-        if (!err && put_compat_timespec(&ts, tp))
+        if (!err && compat_put_timespec(&ts, tp))
                 return -EFAULT;
         return err;
 }
 
-long compat_sys_clock_adjtime(clockid_t which_clock,
-                struct compat_timex __user *utp)
+COMPAT_SYSCALL_DEFINE2(clock_adjtime, clockid_t, which_clock,
+                       struct compat_timex __user *, utp)
 {
         struct timex txc;
         mm_segment_t oldfs;
@@ -777,8 +777,8 @@ long compat_sys_clock_adjtime(clockid_t which_clock,
         return ret;
 }
 
-long compat_sys_clock_getres(clockid_t which_clock,
-                struct compat_timespec __user *tp)
+COMPAT_SYSCALL_DEFINE2(clock_getres, clockid_t, which_clock,
+                       struct compat_timespec __user *, tp)
 {
         long err;
         mm_segment_t oldfs;
@@ -789,7 +789,7 @@ long compat_sys_clock_getres(clockid_t which_clock,
         err = sys_clock_getres(which_clock,
                                (struct timespec __user *) &ts);
         set_fs(oldfs);
-        if (!err && tp && put_compat_timespec(&ts, tp))
+        if (!err && tp && compat_put_timespec(&ts, tp))
                 return -EFAULT;
         return err;
 }
@@ -799,7 +799,7 @@ static long compat_clock_nanosleep_restart(struct restart_block *restart)
         long err;
         mm_segment_t oldfs;
         struct timespec tu;
-        struct compat_timespec *rmtp = restart->nanosleep.compat_rmtp;
+        struct compat_timespec __user *rmtp = restart->nanosleep.compat_rmtp;
 
         restart->nanosleep.rmtp = (struct timespec __user *) &tu;
         oldfs = get_fs();
@@ -808,7 +808,7 @@ static long compat_clock_nanosleep_restart(struct restart_block *restart)
         set_fs(oldfs);
 
         if ((err == -ERESTART_RESTARTBLOCK) && rmtp &&
-            put_compat_timespec(&tu, rmtp))
+            compat_put_timespec(&tu, rmtp))
                 return -EFAULT;
 
         if (err == -ERESTART_RESTARTBLOCK) {
@@ -818,16 +818,16 @@ static long compat_clock_nanosleep_restart(struct restart_block *restart)
         return err;
 }
 
-long compat_sys_clock_nanosleep(clockid_t which_clock, int flags,
-                            struct compat_timespec __user *rqtp,
-                            struct compat_timespec __user *rmtp)
+COMPAT_SYSCALL_DEFINE4(clock_nanosleep, clockid_t, which_clock, int, flags,
+                       struct compat_timespec __user *, rqtp,
+                       struct compat_timespec __user *, rmtp)
 {
         long err;
         mm_segment_t oldfs;
         struct timespec in, out;
         struct restart_block *restart;
 
-        if (get_compat_timespec(&in, rqtp))
+        if (compat_get_timespec(&in, rqtp))
                 return -EFAULT;
 
         oldfs = get_fs();
@@ -838,7 +838,7 @@ long compat_sys_clock_nanosleep(clockid_t which_clock, int flags,
         set_fs(oldfs);
 
         if ((err == -ERESTART_RESTARTBLOCK) && rmtp &&
-            put_compat_timespec(&out, rmtp))
+            compat_put_timespec(&out, rmtp))
                 return -EFAULT;
 
         if (err == -ERESTART_RESTARTBLOCK) {
@@ -1010,7 +1010,7 @@ COMPAT_SYSCALL_DEFINE4(rt_sigtimedwait, compat_sigset_t __user *, uthese,
 
 /* compat_time_t is a 32 bit "long" and needs to get converted. */
 
-asmlinkage long compat_sys_time(compat_time_t __user * tloc)
+COMPAT_SYSCALL_DEFINE1(time, compat_time_t __user *, tloc)
 {
         compat_time_t i;
         struct timeval tv;
@@ -1026,7 +1026,7 @@ asmlinkage long compat_sys_time(compat_time_t __user * tloc)
         return i;
 }
 
-asmlinkage long compat_sys_stime(compat_time_t __user *tptr)
+COMPAT_SYSCALL_DEFINE1(stime, compat_time_t __user *, tptr)
 {
         struct timespec tv;
         int err;
@@ -1046,7 +1046,7 @@ asmlinkage long compat_sys_stime(compat_time_t __user *tptr)
 
 #endif /* __ARCH_WANT_COMPAT_SYS_TIME */
 
-asmlinkage long compat_sys_adjtimex(struct compat_timex __user *utp)
+COMPAT_SYSCALL_DEFINE1(adjtimex, struct compat_timex __user *, utp)
 {
         struct timex txc;
         int err, ret;
@@ -1065,11 +1065,11 @@ asmlinkage long compat_sys_adjtimex(struct compat_timex __user *utp)
 }
 
 #ifdef CONFIG_NUMA
-asmlinkage long compat_sys_move_pages(pid_t pid, unsigned long nr_pages,
-                compat_uptr_t __user *pages32,
-                const int __user *nodes,
-                int __user *status,
-                int flags)
+COMPAT_SYSCALL_DEFINE6(move_pages, pid_t, pid, compat_ulong_t, nr_pages,
+                       compat_uptr_t __user *, pages32,
+                       const int __user *, nodes,
+                       int __user *, status,
+                       int, flags)
 {
         const void __user * __user *pages;
         int i;
@@ -1085,10 +1085,10 @@ asmlinkage long compat_sys_move_pages(pid_t pid, unsigned long nr_pages,
         return sys_move_pages(pid, nr_pages, pages, nodes, status, flags);
 }
 
-asmlinkage long compat_sys_migrate_pages(compat_pid_t pid,
-                        compat_ulong_t maxnode,
-                        const compat_ulong_t __user *old_nodes,
-                        const compat_ulong_t __user *new_nodes)
+COMPAT_SYSCALL_DEFINE4(migrate_pages, compat_pid_t, pid,
+                       compat_ulong_t, maxnode,
+                       const compat_ulong_t __user *, old_nodes,
+                       const compat_ulong_t __user *, new_nodes)
 {
         unsigned long __user *old = NULL;
         unsigned long __user *new = NULL;
@@ -1130,7 +1130,7 @@ COMPAT_SYSCALL_DEFINE2(sched_rr_get_interval,
         set_fs(KERNEL_DS);
         ret = sys_sched_rr_get_interval(pid, (struct timespec __user *)&t);
         set_fs(old_fs);
-        if (put_compat_timespec(&t, interval))
+        if (compat_put_timespec(&t, interval))
                 return -EFAULT;
         return ret;
 }
diff --git a/kernel/cpu/Makefile b/kernel/cpu/Makefile
deleted file mode 100644
index 59ab052ef7a0..000000000000
--- a/kernel/cpu/Makefile
+++ /dev/null
@@ -1 +0,0 @@
-obj-y   = idle.o
diff --git a/kernel/cpu/idle.c b/kernel/cpu/idle.c
deleted file mode 100644
index 277f494c2a9a..000000000000
--- a/kernel/cpu/idle.c
+++ /dev/null
@@ -1,144 +0,0 @@
-/*
- * Generic entry point for the idle threads
- */
-#include <linux/sched.h>
-#include <linux/cpu.h>
-#include <linux/tick.h>
-#include <linux/mm.h>
-#include <linux/stackprotector.h>
-
-#include <asm/tlb.h>
-
-#include <trace/events/power.h>
-
-static int __read_mostly cpu_idle_force_poll;
-
-void cpu_idle_poll_ctrl(bool enable)
-{
-        if (enable) {
-                cpu_idle_force_poll++;
-        } else {
-                cpu_idle_force_poll--;
-                WARN_ON_ONCE(cpu_idle_force_poll < 0);
-        }
-}
-
-#ifdef CONFIG_GENERIC_IDLE_POLL_SETUP
-static int __init cpu_idle_poll_setup(char *__unused)
-{
-        cpu_idle_force_poll = 1;
-        return 1;
-}
-__setup("nohlt", cpu_idle_poll_setup);
-
-static int __init cpu_idle_nopoll_setup(char *__unused)
-{
-        cpu_idle_force_poll = 0;
-        return 1;
-}
-__setup("hlt", cpu_idle_nopoll_setup);
-#endif
-
-static inline int cpu_idle_poll(void)
-{
-        rcu_idle_enter();
-        trace_cpu_idle_rcuidle(0, smp_processor_id());
-        local_irq_enable();
-        while (!tif_need_resched())
-                cpu_relax();
-        trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id());
-        rcu_idle_exit();
-        return 1;
-}
-
-/* Weak implementations for optional arch specific functions */
-void __weak arch_cpu_idle_prepare(void) { }
-void __weak arch_cpu_idle_enter(void) { }
-void __weak arch_cpu_idle_exit(void) { }
-void __weak arch_cpu_idle_dead(void) { }
-void __weak arch_cpu_idle(void)
-{
-        cpu_idle_force_poll = 1;
-        local_irq_enable();
-}
-
-/*
- * Generic idle loop implementation
- */
-static void cpu_idle_loop(void)
-{
-        while (1) {
-                tick_nohz_idle_enter();
-
-                while (!need_resched()) {
-                        check_pgt_cache();
-                        rmb();
-
-                        if (cpu_is_offline(smp_processor_id()))
-                                arch_cpu_idle_dead();
-
-                        local_irq_disable();
-                        arch_cpu_idle_enter();
-
-                        /*
-                         * In poll mode we reenable interrupts and spin.
-                         *
-                         * Also if we detected in the wakeup from idle
-                         * path that the tick broadcast device expired
-                         * for us, we don't want to go deep idle as we
-                         * know that the IPI is going to arrive right
-                         * away
-                         */
-                        if (cpu_idle_force_poll || tick_check_broadcast_expired()) {
-                                cpu_idle_poll();
-                        } else {
-                                if (!current_clr_polling_and_test()) {
-                                        stop_critical_timings();
-                                        rcu_idle_enter();
-                                        arch_cpu_idle();
-                                        WARN_ON_ONCE(irqs_disabled());
-                                        rcu_idle_exit();
-                                        start_critical_timings();
-                                } else {
-                                        local_irq_enable();
-                                }
-                                __current_set_polling();
-                        }
-                        arch_cpu_idle_exit();
-                }
-
-                /*
-                 * Since we fell out of the loop above, we know
-                 * TIF_NEED_RESCHED must be set, propagate it into
-                 * PREEMPT_NEED_RESCHED.
-                 *
-                 * This is required because for polling idle loops we will
-                 * not have had an IPI to fold the state for us.
-                 */
-                preempt_set_need_resched();
-                tick_nohz_idle_exit();
-                schedule_preempt_disabled();
-        }
-}
-
-void cpu_startup_entry(enum cpuhp_state state)
-{
-        /*
-         * This #ifdef needs to die, but it's too late in the cycle to
-         * make this generic (arm and sh have never invoked the canary
-         * init for the non boot cpus!). Will be fixed in 3.11
-         */
-#ifdef CONFIG_X86
-        /*
-         * If we're the non-boot CPU, nothing set the stack canary up
-         * for us. The boot CPU already has it initialized but no harm
-         * in doing it again. This is a good place for updating it, as
-         * we wont ever return from this function (so the invalid
-         * canaries already on the stack wont ever trigger).
-         */
-        boot_init_stack_canary();
-#endif
-        __current_set_polling();
-        arch_cpu_idle_prepare();
-        cpu_idle_loop();
-}
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index e6b1b66afe52..3d54c418bd06 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -119,7 +119,7 @@ static inline struct cpuset *css_cs(struct cgroup_subsys_state *css)
 /* Retrieve the cpuset for a task */
 static inline struct cpuset *task_cs(struct task_struct *task)
 {
-        return css_cs(task_css(task, cpuset_subsys_id));
+        return css_cs(task_css(task, cpuset_cgrp_id));
 }
 
 static inline struct cpuset *parent_cs(struct cpuset *cs)
@@ -467,7 +467,7 @@ static int validate_change(struct cpuset *cur, struct cpuset *trial)
          * be changed to have empty cpus_allowed or mems_allowed.
          */
         ret = -ENOSPC;
-        if ((cgroup_task_count(cur->css.cgroup) || cur->attach_in_progress)) {
+        if ((cgroup_has_tasks(cur->css.cgroup) || cur->attach_in_progress)) {
                 if (!cpumask_empty(cur->cpus_allowed) &&
                     cpumask_empty(trial->cpus_allowed))
                         goto out;
@@ -829,55 +829,36 @@ static struct cpuset *effective_nodemask_cpuset(struct cpuset *cs)
 }
 
 /**
- * cpuset_change_cpumask - make a task's cpus_allowed the same as its cpuset's
- * @tsk: task to test
- * @data: cpuset to @tsk belongs to
- *
- * Called by css_scan_tasks() for each task in a cgroup whose cpus_allowed
- * mask needs to be changed.
- *
- * We don't need to re-check for the cgroup/cpuset membership, since we're
- * holding cpuset_mutex at this point.
- */
-static void cpuset_change_cpumask(struct task_struct *tsk, void *data)
-{
-        struct cpuset *cs = data;
-        struct cpuset *cpus_cs = effective_cpumask_cpuset(cs);
-
-        set_cpus_allowed_ptr(tsk, cpus_cs->cpus_allowed);
-}
-
-/**
  * update_tasks_cpumask - Update the cpumasks of tasks in the cpuset.
  * @cs: the cpuset in which each task's cpus_allowed mask needs to be changed
- * @heap: if NULL, defer allocating heap memory to css_scan_tasks()
- *
- * Called with cpuset_mutex held
  *
- * The css_scan_tasks() function will scan all the tasks in a cgroup,
- * calling callback functions for each.
- *
- * No return value. It's guaranteed that css_scan_tasks() always returns 0
- * if @heap != NULL.
+ * Iterate through each task of @cs updating its cpus_allowed to the
+ * effective cpuset's.  As this function is called with cpuset_mutex held,
+ * cpuset membership stays stable.
  */
-static void update_tasks_cpumask(struct cpuset *cs, struct ptr_heap *heap)
+static void update_tasks_cpumask(struct cpuset *cs)
 {
-        css_scan_tasks(&cs->css, NULL, cpuset_change_cpumask, cs, heap);
+        struct cpuset *cpus_cs = effective_cpumask_cpuset(cs);
+        struct css_task_iter it;
+        struct task_struct *task;
+
+        css_task_iter_start(&cs->css, &it);
+        while ((task = css_task_iter_next(&it)))
+                set_cpus_allowed_ptr(task, cpus_cs->cpus_allowed);
+        css_task_iter_end(&it);
 }
 
 /*
  * update_tasks_cpumask_hier - Update the cpumasks of tasks in the hierarchy.
  * @root_cs: the root cpuset of the hierarchy
  * @update_root: update root cpuset or not?
- * @heap: the heap used by css_scan_tasks()
  *
  * This will update cpumasks of tasks in @root_cs and all other empty cpusets
  * which take on cpumask of @root_cs.
  *
  * Called with cpuset_mutex held
  */
-static void update_tasks_cpumask_hier(struct cpuset *root_cs,
-                                      bool update_root, struct ptr_heap *heap)
+static void update_tasks_cpumask_hier(struct cpuset *root_cs, bool update_root)
 {
         struct cpuset *cp;
         struct cgroup_subsys_state *pos_css;
@@ -898,7 +879,7 @@ static void update_tasks_cpumask_hier(struct cpuset *root_cs,
                         continue;
                 rcu_read_unlock();
 
-                update_tasks_cpumask(cp, heap);
+                update_tasks_cpumask(cp);
 
                 rcu_read_lock();
                 css_put(&cp->css);
@@ -914,7 +895,6 @@ static void update_tasks_cpumask_hier(struct cpuset *root_cs,
 static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs,
                           const char *buf)
 {
-        struct ptr_heap heap;
         int retval;
         int is_load_balanced;
 
@@ -947,19 +927,13 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs,
         if (retval < 0)
                 return retval;
 
-        retval = heap_init(&heap, PAGE_SIZE, GFP_KERNEL, NULL);
-        if (retval)
-                return retval;
-
         is_load_balanced = is_sched_load_balance(trialcs);
 
         mutex_lock(&callback_mutex);
         cpumask_copy(cs->cpus_allowed, trialcs->cpus_allowed);
         mutex_unlock(&callback_mutex);
 
-        update_tasks_cpumask_hier(cs, true, &heap);
-
-        heap_free(&heap);
+        update_tasks_cpumask_hier(cs, true);
 
         if (is_load_balanced)
                 rebuild_sched_domains_locked();
@@ -1022,7 +996,7 @@ static void cpuset_change_task_nodemask(struct task_struct *tsk,
         task_lock(tsk);
         /*
          * Determine if a loop is necessary if another thread is doing
-         * get_mems_allowed().  If at least one node remains unchanged and
+         * read_mems_allowed_begin().  If at least one node remains unchanged and
          * tsk does not have a mempolicy, then an empty nodemask will not be
          * possible when mems_allowed is larger than a word.
          */
@@ -1048,53 +1022,22 @@ static void cpuset_change_task_nodemask(struct task_struct *tsk,
         task_unlock(tsk);
 }
 
-struct cpuset_change_nodemask_arg {
-        struct cpuset           *cs;
-        nodemask_t              *newmems;
-};
-
-/*
- * Update task's mems_allowed and rebind its mempolicy and vmas' mempolicy
- * of it to cpuset's new mems_allowed, and migrate pages to new nodes if
- * memory_migrate flag is set. Called with cpuset_mutex held.
- */
-static void cpuset_change_nodemask(struct task_struct *p, void *data)
-{
-        struct cpuset_change_nodemask_arg *arg = data;
-        struct cpuset *cs = arg->cs;
-        struct mm_struct *mm;
-        int migrate;
-
-        cpuset_change_task_nodemask(p, arg->newmems);
-
-        mm = get_task_mm(p);
-        if (!mm)
-                return;
-
-        migrate = is_memory_migrate(cs);
-
-        mpol_rebind_mm(mm, &cs->mems_allowed);
-        if (migrate)
-                cpuset_migrate_mm(mm, &cs->old_mems_allowed, arg->newmems);
-        mmput(mm);
-}
-
 static void *cpuset_being_rebound;
 
 /**
  * update_tasks_nodemask - Update the nodemasks of tasks in the cpuset.
  * @cs: the cpuset in which each task's mems_allowed mask needs to be changed
- * @heap: if NULL, defer allocating heap memory to css_scan_tasks()
  *
- * Called with cpuset_mutex held.  No return value. It's guaranteed that
- * css_scan_tasks() always returns 0 if @heap != NULL.
+ * Iterate through each task of @cs updating its mems_allowed to the
+ * effective cpuset's.  As this function is called with cpuset_mutex held,
+ * cpuset membership stays stable.
  */
-static void update_tasks_nodemask(struct cpuset *cs, struct ptr_heap *heap)
+static void update_tasks_nodemask(struct cpuset *cs)
 {
         static nodemask_t newmems;      /* protected by cpuset_mutex */
         struct cpuset *mems_cs = effective_nodemask_cpuset(cs);
-        struct cpuset_change_nodemask_arg arg = { .cs = cs,
-                                                  .newmems = &newmems };
+        struct css_task_iter it;
+        struct task_struct *task;
 
         cpuset_being_rebound = cs;              /* causes mpol_dup() rebind */
 
@@ -1110,7 +1053,25 @@ static void update_tasks_nodemask(struct cpuset *cs, struct ptr_heap *heap)
          * It's ok if we rebind the same mm twice; mpol_rebind_mm()
          * is idempotent.  Also migrate pages in each mm to new nodes.
          */
-        css_scan_tasks(&cs->css, NULL, cpuset_change_nodemask, &arg, heap);
+        css_task_iter_start(&cs->css, &it);
+        while ((task = css_task_iter_next(&it))) {
+                struct mm_struct *mm;
+                bool migrate;
+
+                cpuset_change_task_nodemask(task, &newmems);
+
+                mm = get_task_mm(task);
+                if (!mm)
+                        continue;
+
+                migrate = is_memory_migrate(cs);
+
+                mpol_rebind_mm(mm, &cs->mems_allowed);
+                if (migrate)
+                        cpuset_migrate_mm(mm, &cs->old_mems_allowed, &newmems);
+                mmput(mm);
+        }
+        css_task_iter_end(&it);
 
         /*
          * All the tasks' nodemasks have been updated, update
@@ -1126,15 +1087,13 @@ static void update_tasks_nodemask(struct cpuset *cs, struct ptr_heap *heap)
  * update_tasks_nodemask_hier - Update the nodemasks of tasks in the hierarchy.
  * @cs: the root cpuset of the hierarchy
  * @update_root: update the root cpuset or not?
- * @heap: the heap used by css_scan_tasks()
  *
  * This will update nodemasks of tasks in @root_cs and all other empty cpusets
  * which take on nodemask of @root_cs.
  *
  * Called with cpuset_mutex held
  */
-static void update_tasks_nodemask_hier(struct cpuset *root_cs,
-                                       bool update_root, struct ptr_heap *heap)
+static void update_tasks_nodemask_hier(struct cpuset *root_cs, bool update_root)
 {
         struct cpuset *cp;
         struct cgroup_subsys_state *pos_css;
@@ -1155,7 +1114,7 @@ static void update_tasks_nodemask_hier(struct cpuset *root_cs,
                         continue;
                 rcu_read_unlock();
 
-                update_tasks_nodemask(cp, heap);
+                update_tasks_nodemask(cp);
 
                 rcu_read_lock();
                 css_put(&cp->css);
@@ -1180,7 +1139,6 @@ static int update_nodemask(struct cpuset *cs, struct cpuset *trialcs,
                            const char *buf)
 {
         int retval;
-        struct ptr_heap heap;
 
         /*
          * top_cpuset.mems_allowed tracks node_stats[N_MEMORY];
@@ -1219,17 +1177,11 @@ static int update_nodemask(struct cpuset *cs, struct cpuset *trialcs,
         if (retval < 0)
                 goto done;
 
-        retval = heap_init(&heap, PAGE_SIZE, GFP_KERNEL, NULL);
-        if (retval < 0)
-                goto done;
-
         mutex_lock(&callback_mutex);
         cs->mems_allowed = trialcs->mems_allowed;
         mutex_unlock(&callback_mutex);
 
-        update_tasks_nodemask_hier(cs, true, &heap);
-
-        heap_free(&heap);
+        update_tasks_nodemask_hier(cs, true);
 done:
         return retval;
 }
@@ -1257,38 +1209,22 @@ static int update_relax_domain_level(struct cpuset *cs, s64 val)
 }
 
 /**
- * cpuset_change_flag - make a task's spread flags the same as its cpuset's
- * @tsk: task to be updated
- * @data: cpuset to @tsk belongs to
- *
- * Called by css_scan_tasks() for each task in a cgroup.
- *
- * We don't need to re-check for the cgroup/cpuset membership, since we're
- * holding cpuset_mutex at this point.
- */
-static void cpuset_change_flag(struct task_struct *tsk, void *data)
-{
-        struct cpuset *cs = data;
-
-        cpuset_update_task_spread_flag(cs, tsk);
-}
-
-/**
  * update_tasks_flags - update the spread flags of tasks in the cpuset.
  * @cs: the cpuset in which each task's spread flags needs to be changed
- * @heap: if NULL, defer allocating heap memory to css_scan_tasks()
- *
- * Called with cpuset_mutex held
  *
- * The css_scan_tasks() function will scan all the tasks in a cgroup,
- * calling callback functions for each.
- *
- * No return value. It's guaranteed that css_scan_tasks() always returns 0
- * if @heap != NULL.
+ * Iterate through each task of @cs updating its spread flags.  As this
+ * function is called with cpuset_mutex held, cpuset membership stays
+ * stable.
  */
-static void update_tasks_flags(struct cpuset *cs, struct ptr_heap *heap)
+static void update_tasks_flags(struct cpuset *cs)
 {
-        css_scan_tasks(&cs->css, NULL, cpuset_change_flag, cs, heap);
+        struct css_task_iter it;
+        struct task_struct *task;
+
+        css_task_iter_start(&cs->css, &it);
+        while ((task = css_task_iter_next(&it)))
+                cpuset_update_task_spread_flag(cs, task);
+        css_task_iter_end(&it);
 }
 
 /*
@@ -1306,7 +1242,6 @@ static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs,
         struct cpuset *trialcs;
         int balance_flag_changed;
         int spread_flag_changed;
-        struct ptr_heap heap;
         int err;
 
         trialcs = alloc_trial_cpuset(cs);
@@ -1322,10 +1257,6 @@ static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs,
         if (err < 0)
                 goto out;
 
-        err = heap_init(&heap, PAGE_SIZE, GFP_KERNEL, NULL);
-        if (err < 0)
-                goto out;
-
         balance_flag_changed = (is_sched_load_balance(cs) !=
                                 is_sched_load_balance(trialcs));
 
@@ -1340,8 +1271,7 @@ static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs,
                 rebuild_sched_domains_locked();
 
         if (spread_flag_changed)
-                update_tasks_flags(cs, &heap);
-        heap_free(&heap);
+                update_tasks_flags(cs);
 out:
         free_trial_cpuset(trialcs);
         return err;
@@ -1445,6 +1375,8 @@ static int fmeter_getrate(struct fmeter *fmp)
         return val;
 }
 
+static struct cpuset *cpuset_attach_old_cs;
+
 /* Called by cgroups to determine if a cpuset is usable; cpuset_mutex held */
 static int cpuset_can_attach(struct cgroup_subsys_state *css,
                              struct cgroup_taskset *tset)
@@ -1453,6 +1385,9 @@ static int cpuset_can_attach(struct cgroup_subsys_state *css,
         struct task_struct *task;
         int ret;
 
+        /* used later by cpuset_attach() */
+        cpuset_attach_old_cs = task_cs(cgroup_taskset_first(tset));
+
         mutex_lock(&cpuset_mutex);
 
         /*
@@ -1464,7 +1399,7 @@ static int cpuset_can_attach(struct cgroup_subsys_state *css,
             (cpumask_empty(cs->cpus_allowed) || nodes_empty(cs->mems_allowed)))
                 goto out_unlock;
 
-        cgroup_taskset_for_each(task, css, tset) {
+        cgroup_taskset_for_each(task, tset) {
                 /*
                  * Kthreads which disallow setaffinity shouldn't be moved
                  * to a new cpuset; we don't want to change their cpu
@@ -1516,10 +1451,8 @@ static void cpuset_attach(struct cgroup_subsys_state *css,
         struct mm_struct *mm;
         struct task_struct *task;
         struct task_struct *leader = cgroup_taskset_first(tset);
-        struct cgroup_subsys_state *oldcss = cgroup_taskset_cur_css(tset,
-                                                        cpuset_subsys_id);
         struct cpuset *cs = css_cs(css);
-        struct cpuset *oldcs = css_cs(oldcss);
+        struct cpuset *oldcs = cpuset_attach_old_cs;
         struct cpuset *cpus_cs = effective_cpumask_cpuset(cs);
         struct cpuset *mems_cs = effective_nodemask_cpuset(cs);
 
@@ -1533,7 +1466,7 @@ static void cpuset_attach(struct cgroup_subsys_state *css,
 
         guarantee_online_mems(mems_cs, &cpuset_attach_nodemask_to);
 
-        cgroup_taskset_for_each(task, css, tset) {
+        cgroup_taskset_for_each(task, tset) {
                 /*
                  * can_attach beforehand should guarantee that this doesn't
                  * fail.  TODO: have a better way to handle failure here
@@ -1673,7 +1606,7 @@ out_unlock:
  * Common handling for a write to a "cpus" or "mems" file.
  */
 static int cpuset_write_resmask(struct cgroup_subsys_state *css,
-                                struct cftype *cft, const char *buf)
+                                struct cftype *cft, char *buf)
 {
         struct cpuset *cs = css_cs(css);
         struct cpuset *trialcs;
@@ -2020,8 +1953,7 @@ static void cpuset_css_free(struct cgroup_subsys_state *css)
         kfree(cs);
 }
 
-struct cgroup_subsys cpuset_subsys = {
-        .name = "cpuset",
+struct cgroup_subsys cpuset_cgrp_subsys = {
         .css_alloc = cpuset_css_alloc,
         .css_online = cpuset_css_online,
         .css_offline = cpuset_css_offline,
@@ -2029,7 +1961,6 @@ struct cgroup_subsys cpuset_subsys = {
         .can_attach = cpuset_can_attach,
         .cancel_attach = cpuset_cancel_attach,
         .attach = cpuset_attach,
-        .subsys_id = cpuset_subsys_id,
         .base_cftypes = files,
         .early_init = 1,
 };
@@ -2086,10 +2017,9 @@ static void remove_tasks_in_empty_cpuset(struct cpuset *cs)
                 parent = parent_cs(parent);
 
         if (cgroup_transfer_tasks(parent->css.cgroup, cs->css.cgroup)) {
-                rcu_read_lock();
-                printk(KERN_ERR "cpuset: failed to transfer tasks out of empty cpuset %s\n",
-                       cgroup_name(cs->css.cgroup));
-                rcu_read_unlock();
+                printk(KERN_ERR "cpuset: failed to transfer tasks out of empty cpuset ");
+                pr_cont_cgroup_name(cs->css.cgroup);
+                pr_cont("\n");
         }
 }
 
@@ -2137,7 +2067,7 @@ retry:
          */
         if ((sane && cpumask_empty(cs->cpus_allowed)) ||
             (!cpumask_empty(&off_cpus) && !cpumask_empty(cs->cpus_allowed)))
-                update_tasks_cpumask(cs, NULL);
+                update_tasks_cpumask(cs);
 
         mutex_lock(&callback_mutex);
         nodes_andnot(cs->mems_allowed, cs->mems_allowed, off_mems);
@@ -2151,7 +2081,7 @@ retry:
          */
         if ((sane && nodes_empty(cs->mems_allowed)) ||
             (!nodes_empty(off_mems) && !nodes_empty(cs->mems_allowed)))
-                update_tasks_nodemask(cs, NULL);
+                update_tasks_nodemask(cs);
 
         is_empty = cpumask_empty(cs->cpus_allowed) ||
                 nodes_empty(cs->mems_allowed);
@@ -2213,7 +2143,7 @@ static void cpuset_hotplug_workfn(struct work_struct *work)
                 mutex_lock(&callback_mutex);
                 top_cpuset.mems_allowed = new_mems;
                 mutex_unlock(&callback_mutex);
-                update_tasks_nodemask(&top_cpuset, NULL);
+                update_tasks_nodemask(&top_cpuset);
         }
 
         mutex_unlock(&cpuset_mutex);
@@ -2305,10 +2235,10 @@ void cpuset_cpus_allowed(struct task_struct *tsk, struct cpumask *pmask)
         struct cpuset *cpus_cs;
 
         mutex_lock(&callback_mutex);
-        task_lock(tsk);
+        rcu_read_lock();
         cpus_cs = effective_cpumask_cpuset(task_cs(tsk));
         guarantee_online_cpus(cpus_cs, pmask);
-        task_unlock(tsk);
+        rcu_read_unlock();
         mutex_unlock(&callback_mutex);
 }
 
@@ -2361,10 +2291,10 @@ nodemask_t cpuset_mems_allowed(struct task_struct *tsk)
         nodemask_t mask;
 
         mutex_lock(&callback_mutex);
-        task_lock(tsk);
+        rcu_read_lock();
         mems_cs = effective_nodemask_cpuset(task_cs(tsk));
         guarantee_online_mems(mems_cs, &mask);
-        task_unlock(tsk);
+        rcu_read_unlock();
         mutex_unlock(&callback_mutex);
 
         return mask;
@@ -2480,10 +2410,10 @@ int __cpuset_node_allowed_softwall(int node, gfp_t gfp_mask)
         /* Not hardwall and node outside mems_allowed: scan up cpusets */
         mutex_lock(&callback_mutex);
 
-        task_lock(current);
+        rcu_read_lock();
         cs = nearest_hardwall_ancestor(task_cs(current));
         allowed = node_isset(node, cs->mems_allowed);
-        task_unlock(current);
+        rcu_read_unlock();
 
         mutex_unlock(&callback_mutex);
         return allowed;
@@ -2609,27 +2539,27 @@ int cpuset_mems_allowed_intersects(const struct task_struct *tsk1,
  * @task: pointer to task_struct of some task.
  *
  * Description: Prints @task's name, cpuset name, and cached copy of its
- * mems_allowed to the kernel log.  Must hold task_lock(task) to allow
- * dereferencing task_cs(task).
+ * mems_allowed to the kernel log.
  */
 void cpuset_print_task_mems_allowed(struct task_struct *tsk)
 {
          /* Statically allocated to prevent using excess stack. */
         static char cpuset_nodelist[CPUSET_NODELIST_LEN];
         static DEFINE_SPINLOCK(cpuset_buffer_lock);
+        struct cgroup *cgrp;
 
-        struct cgroup *cgrp = task_cs(tsk)->css.cgroup;
-
-        rcu_read_lock();
         spin_lock(&cpuset_buffer_lock);
+        rcu_read_lock();
 
+        cgrp = task_cs(tsk)->css.cgroup;
         nodelist_scnprintf(cpuset_nodelist, CPUSET_NODELIST_LEN,
                            tsk->mems_allowed);
-        printk(KERN_INFO "%s cpuset=%s mems_allowed=%s\n",
-               tsk->comm, cgroup_name(cgrp), cpuset_nodelist);
+        printk(KERN_INFO "%s cpuset=", tsk->comm);
+        pr_cont_cgroup_name(cgrp);
+        pr_cont(" mems_allowed=%s\n", cpuset_nodelist);
 
-        spin_unlock(&cpuset_buffer_lock);
         rcu_read_unlock();
+        spin_unlock(&cpuset_buffer_lock);
 }
 
 /*
@@ -2660,9 +2590,9 @@ int cpuset_memory_pressure_enabled __read_mostly;
 
 void __cpuset_memory_pressure_bump(void)
 {
-        task_lock(current);
+        rcu_read_lock();
         fmeter_markevent(&task_cs(current)->fmeter);
-        task_unlock(current);
+        rcu_read_unlock();
 }
 
 #ifdef CONFIG_PROC_PID_CPUSET
@@ -2679,12 +2609,12 @@ int proc_cpuset_show(struct seq_file *m, void *unused_v)
 {
         struct pid *pid;
         struct task_struct *tsk;
-        char *buf;
+        char *buf, *p;
         struct cgroup_subsys_state *css;
         int retval;
 
         retval = -ENOMEM;
-        buf = kmalloc(PAGE_SIZE, GFP_KERNEL);
+        buf = kmalloc(PATH_MAX, GFP_KERNEL);
         if (!buf)
                 goto out;
 
@@ -2694,14 +2624,16 @@ int proc_cpuset_show(struct seq_file *m, void *unused_v)
         if (!tsk)
                 goto out_free;
 
+        retval = -ENAMETOOLONG;
         rcu_read_lock();
-        css = task_css(tsk, cpuset_subsys_id);
-        retval = cgroup_path(css->cgroup, buf, PAGE_SIZE);
+        css = task_css(tsk, cpuset_cgrp_id);
+        p = cgroup_path(css->cgroup, buf, PATH_MAX);
         rcu_read_unlock();
-        if (retval < 0)
+        if (!p)
                 goto out_put_task;
-        seq_puts(m, buf);
+        seq_puts(m, p);
         seq_putc(m, '\n');
+        retval = 0;
 out_put_task:
         put_task_struct(tsk);
 out_free:
diff --git a/kernel/debug/debug_core.c b/kernel/debug/debug_core.c
index 334b3980ffc1..99982a70ddad 100644
--- a/kernel/debug/debug_core.c
+++ b/kernel/debug/debug_core.c
@@ -1035,7 +1035,7 @@ int dbg_io_get_char(void)
  * otherwise as a quick means to stop program execution and "break" into
  * the debugger.
  */
-void kgdb_breakpoint(void)
+noinline void kgdb_breakpoint(void)
 {
         atomic_inc(&kgdb_setting_breakpoint);
         wmb(); /* Sync point before breakpoint */
diff --git a/kernel/events/core.c b/kernel/events/core.c
index fa0b2d4ad83c..f83a71a3e46d 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -231,11 +231,29 @@ int perf_cpu_time_max_percent_handler(struct ctl_table *table, int write,
 #define NR_ACCUMULATED_SAMPLES 128
 static DEFINE_PER_CPU(u64, running_sample_length);
 
-void perf_sample_event_took(u64 sample_len_ns)
+static void perf_duration_warn(struct irq_work *w)
 {
+        u64 allowed_ns = ACCESS_ONCE(perf_sample_allowed_ns);
         u64 avg_local_sample_len;
         u64 local_samples_len;
+
+        local_samples_len = __get_cpu_var(running_sample_length);
+        avg_local_sample_len = local_samples_len/NR_ACCUMULATED_SAMPLES;
+
+        printk_ratelimited(KERN_WARNING
+                        "perf interrupt took too long (%lld > %lld), lowering "
+                        "kernel.perf_event_max_sample_rate to %d\n",
+                        avg_local_sample_len, allowed_ns >> 1,
+                        sysctl_perf_event_sample_rate);
+}
+
+static DEFINE_IRQ_WORK(perf_duration_work, perf_duration_warn);
+
+void perf_sample_event_took(u64 sample_len_ns)
+{
         u64 allowed_ns = ACCESS_ONCE(perf_sample_allowed_ns);
+        u64 avg_local_sample_len;
+        u64 local_samples_len;
 
         if (allowed_ns == 0)
                 return;
@@ -263,13 +281,14 @@ void perf_sample_event_took(u64 sample_len_ns)
         sysctl_perf_event_sample_rate = max_samples_per_tick * HZ;
         perf_sample_period_ns = NSEC_PER_SEC / sysctl_perf_event_sample_rate;
 
-        printk_ratelimited(KERN_WARNING
-                        "perf samples too long (%lld > %lld), lowering "
-                        "kernel.perf_event_max_sample_rate to %d\n",
-                        avg_local_sample_len, allowed_ns,
-                        sysctl_perf_event_sample_rate);
-
         update_perf_cpu_limits();
+
+        if (!irq_work_queue(&perf_duration_work)) {
+                early_printk("perf interrupt took too long (%lld > %lld), lowering "
+                             "kernel.perf_event_max_sample_rate to %d\n",
+                             avg_local_sample_len, allowed_ns >> 1,
+                             sysctl_perf_event_sample_rate);
+        }
 }
 
 static atomic64_t perf_event_id;
@@ -342,7 +361,7 @@ struct perf_cgroup {
 static inline struct perf_cgroup *
 perf_cgroup_from_task(struct task_struct *task)
 {
-        return container_of(task_css(task, perf_subsys_id),
+        return container_of(task_css(task, perf_event_cgrp_id),
                             struct perf_cgroup, css);
 }
 
@@ -370,11 +389,6 @@ perf_cgroup_match(struct perf_event *event)
                                     event->cgrp->css.cgroup);
 }
 
-static inline bool perf_tryget_cgroup(struct perf_event *event)
-{
-        return css_tryget(&event->cgrp->css);
-}
-
 static inline void perf_put_cgroup(struct perf_event *event)
 {
         css_put(&event->cgrp->css);
@@ -593,9 +607,7 @@ static inline int perf_cgroup_connect(int fd, struct perf_event *event,
         if (!f.file)
                 return -EBADF;
 
-        rcu_read_lock();
-
-        css = css_from_dir(f.file->f_dentry, &perf_subsys);
+        css = css_tryget_from_dir(f.file->f_dentry, &perf_event_cgrp_subsys);
         if (IS_ERR(css)) {
                 ret = PTR_ERR(css);
                 goto out;
@@ -604,13 +616,6 @@ static inline int perf_cgroup_connect(int fd, struct perf_event *event,
         cgrp = container_of(css, struct perf_cgroup, css);
         event->cgrp = cgrp;
 
-        /* must be done before we fput() the file */
-        if (!perf_tryget_cgroup(event)) {
-                event->cgrp = NULL;
-                ret = -ENOENT;
-                goto out;
-        }
-
         /*
          * all events in a group must monitor
          * the same cgroup because a task belongs
@@ -621,7 +626,6 @@ static inline int perf_cgroup_connect(int fd, struct perf_event *event,
                 ret = -EINVAL;
         }
 out:
-        rcu_read_unlock();
         fdput(f);
         return ret;
 }
@@ -1714,7 +1718,7 @@ group_sched_in(struct perf_event *group_event,
                struct perf_event_context *ctx)
 {
         struct perf_event *event, *partial_group = NULL;
-        struct pmu *pmu = group_event->pmu;
+        struct pmu *pmu = ctx->pmu;
         u64 now = ctx->time;
         bool simulate = false;
 
@@ -2563,8 +2567,6 @@ static void perf_branch_stack_sched_in(struct task_struct *prev,
                 if (cpuctx->ctx.nr_branch_stack > 0
                     && pmu->flush_branch_stack) {
 
-                        pmu = cpuctx->ctx.pmu;
-
                         perf_ctx_lock(cpuctx, cpuctx->task_ctx);
 
                         perf_pmu_disable(pmu);
@@ -6294,7 +6296,7 @@ static int perf_event_idx_default(struct perf_event *event)
  * Ensures all contexts with the same task_ctx_nr have the same
  * pmu_cpu_context too.
  */
-static void *find_pmu_context(int ctxn)
+static struct perf_cpu_context __percpu *find_pmu_context(int ctxn)
 {
         struct pmu *pmu;
 
@@ -8036,7 +8038,7 @@ static void perf_cgroup_attach(struct cgroup_subsys_state *css,
 {
         struct task_struct *task;
 
-        cgroup_taskset_for_each(task, css, tset)
+        cgroup_taskset_for_each(task, tset)
                 task_function_call(task, __perf_cgroup_move, task);
 }
 
@@ -8055,9 +8057,7 @@ static void perf_cgroup_exit(struct cgroup_subsys_state *css,
         task_function_call(task, __perf_cgroup_move, task);
 }
 
-struct cgroup_subsys perf_subsys = {
-        .name           = "perf_event",
-        .subsys_id      = perf_subsys_id,
+struct cgroup_subsys perf_event_cgrp_subsys = {
         .css_alloc      = perf_cgroup_css_alloc,
         .css_free       = perf_cgroup_css_free,
         .exit           = perf_cgroup_exit,
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 307d87c0991a..04709b66369d 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -1804,6 +1804,11 @@ static bool handle_trampoline(struct pt_regs *regs)
         return true;
 }
 
+bool __weak arch_uprobe_ignore(struct arch_uprobe *aup, struct pt_regs *regs)
+{
+        return false;
+}
+
 /*
  * Run handler and ask thread to singlestep.
  * Ensure all non-fatal signals cannot interrupt thread while it singlesteps.
@@ -1858,7 +1863,11 @@ static void handle_swbp(struct pt_regs *regs)
         if (!get_utask())
                 goto out;
 
+        if (arch_uprobe_ignore(&uprobe->arch, regs))
+                goto out;
+
         handler_chain(uprobe, regs);
+
         if (can_skip_sstep(uprobe, regs))
                 goto out;
 
diff --git a/kernel/exit.c b/kernel/exit.c
index 1e77fc645317..6480d1c85d7a 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -797,7 +797,7 @@ void do_exit(long code)
          */
         perf_event_exit_task(tsk);
 
-        cgroup_exit(tsk, 1);
+        cgroup_exit(tsk);
 
         if (group_dead)
                 disassociate_ctty(1);
diff --git a/kernel/extable.c b/kernel/extable.c
index 763faf037ec1..d8a6446adbcb 100644
--- a/kernel/extable.c
+++ b/kernel/extable.c
@@ -36,7 +36,7 @@ extern struct exception_table_entry __start___ex_table[];
 extern struct exception_table_entry __stop___ex_table[];
 
 /* Cleared by build time tools if the table is already sorted. */
-u32 __initdata main_extable_sort_needed = 1;
+u32 __initdata __visible main_extable_sort_needed = 1;
 
 /* Sort the kernel's built-in exception table */
 void __init sort_main_extable(void)
diff --git a/kernel/fork.c b/kernel/fork.c
index a17621c6cd42..abc45890f0a5 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -237,6 +237,7 @@ void __put_task_struct(struct task_struct *tsk)
         WARN_ON(atomic_read(&tsk->usage));
         WARN_ON(tsk == current);
 
+        task_numa_free(tsk);
         security_task_free(tsk);
         exit_creds(tsk);
         delayacct_tsk_free(tsk);
@@ -1271,7 +1272,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
         if (IS_ERR(p->mempolicy)) {
                 retval = PTR_ERR(p->mempolicy);
                 p->mempolicy = NULL;
-                goto bad_fork_cleanup_cgroup;
+                goto bad_fork_cleanup_threadgroup_lock;
         }
         mpol_fix_fork_child_flag(p);
 #endif
@@ -1524,11 +1525,10 @@ bad_fork_cleanup_policy:
         perf_event_free_task(p);
 #ifdef CONFIG_NUMA
         mpol_put(p->mempolicy);
-bad_fork_cleanup_cgroup:
+bad_fork_cleanup_threadgroup_lock:
 #endif
         if (clone_flags & CLONE_THREAD)
                 threadgroup_change_end(current);
-        cgroup_exit(p, 0);
         delayacct_tsk_free(p);
         module_put(task_thread_info(p)->exec_domain->module);
 bad_fork_cleanup_count:
diff --git a/kernel/futex.c b/kernel/futex.c
index 44a1261cb9ff..67dacaf93e56 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -157,7 +157,9 @@
  * enqueue.
  */
 
+#ifndef CONFIG_HAVE_FUTEX_CMPXCHG
 int __read_mostly futex_cmpxchg_enabled;
+#endif
 
 /*
  * Futex flags used to encode options to functions and preserve them across
@@ -234,6 +236,7 @@ static const struct futex_q futex_q_init = {
  * waiting on a futex.
  */
 struct futex_hash_bucket {
+        atomic_t waiters;
         spinlock_t lock;
         struct plist_head chain;
 } ____cacheline_aligned_in_smp;
@@ -253,22 +256,37 @@ static inline void futex_get_mm(union futex_key *key)
         smp_mb__after_atomic_inc();
 }
 
-static inline bool hb_waiters_pending(struct futex_hash_bucket *hb)
+/*
+ * Reflects a new waiter being added to the waitqueue.
+ */
+static inline void hb_waiters_inc(struct futex_hash_bucket *hb)
 {
 #ifdef CONFIG_SMP
+        atomic_inc(&hb->waiters);
         /*
-         * Tasks trying to enter the critical region are most likely
-         * potential waiters that will be added to the plist. Ensure
-         * that wakers won't miss to-be-slept tasks in the window between
-         * the wait call and the actual plist_add.
+         * Full barrier (A), see the ordering comment above.
          */
-        if (spin_is_locked(&hb->lock))
-                return true;
-        smp_rmb(); /* Make sure we check the lock state first */
+        smp_mb__after_atomic_inc();
+#endif
+}
+
+/*
+ * Reflects a waiter being removed from the waitqueue by wakeup
+ * paths.
+ */
+static inline void hb_waiters_dec(struct futex_hash_bucket *hb)
+{
+#ifdef CONFIG_SMP
+        atomic_dec(&hb->waiters);
+#endif
+}
 
-        return !plist_head_empty(&hb->chain);
+static inline int hb_waiters_pending(struct futex_hash_bucket *hb)
+{
+#ifdef CONFIG_SMP
+        return atomic_read(&hb->waiters);
 #else
-        return true;
+        return 1;
 #endif
 }
 
@@ -954,6 +972,7 @@ static void __unqueue_futex(struct futex_q *q)
 
         hb = container_of(q->lock_ptr, struct futex_hash_bucket, lock);
         plist_del(&q->list, &hb->chain);
+        hb_waiters_dec(hb);
 }
 
 /*
@@ -1257,7 +1276,9 @@ void requeue_futex(struct futex_q *q, struct futex_hash_bucket *hb1,
          */
         if (likely(&hb1->chain != &hb2->chain)) {
                 plist_del(&q->list, &hb1->chain);
+                hb_waiters_dec(hb1);
                 plist_add(&q->list, &hb2->chain);
+                hb_waiters_inc(hb2);
                 q->lock_ptr = &hb2->lock;
         }
         get_futex_key_refs(key2);
@@ -1600,6 +1621,17 @@ static inline struct futex_hash_bucket *queue_lock(struct futex_q *q)
         struct futex_hash_bucket *hb;
 
         hb = hash_futex(&q->key);
+
+        /*
+         * Increment the counter before taking the lock so that
+         * a potential waker won't miss a to-be-slept task that is
+         * waiting for the spinlock. This is safe as all queue_lock()
+         * users end up calling queue_me(). Similarly, for housekeeping,
+         * decrement the counter at queue_unlock() when some error has
+         * occurred and we don't end up adding the task to the list.
+         */
+        hb_waiters_inc(hb);
+
         q->lock_ptr = &hb->lock;
 
         spin_lock(&hb->lock); /* implies MB (A) */
@@ -1611,6 +1643,7 @@ queue_unlock(struct futex_hash_bucket *hb)
         __releases(&hb->lock)
 {
         spin_unlock(&hb->lock);
+        hb_waiters_dec(hb);
 }
 
 /**
@@ -2342,6 +2375,7 @@ int handle_early_requeue_pi_wakeup(struct futex_hash_bucket *hb,
                  * Unqueue the futex_q and determine which it was.
                  */
                 plist_del(&q->list, &hb->chain);
+                hb_waiters_dec(hb);
 
                 /* Handle spurious wakeups gracefully */
                 ret = -EWOULDBLOCK;
@@ -2843,9 +2877,28 @@ SYSCALL_DEFINE6(futex, u32 __user *, uaddr, int, op, u32, val,
         return do_futex(uaddr, op, val, tp, uaddr2, val2, val3);
 }
 
-static int __init futex_init(void)
+static void __init futex_detect_cmpxchg(void)
 {
+#ifndef CONFIG_HAVE_FUTEX_CMPXCHG
         u32 curval;
+
+        /*
+         * This will fail and we want it. Some arch implementations do
+         * runtime detection of the futex_atomic_cmpxchg_inatomic()
+         * functionality. We want to know that before we call in any
+         * of the complex code paths. Also we want to prevent
+         * registration of robust lists in that case. NULL is
+         * guaranteed to fault and we get -EFAULT on functional
+         * implementation, the non-functional ones will return
+         * -ENOSYS.
+         */
+        if (cmpxchg_futex_value_locked(&curval, NULL, 0, 0) == -EFAULT)
+                futex_cmpxchg_enabled = 1;
+#endif
+}
+
+static int __init futex_init(void)
+{
         unsigned int futex_shift;
         unsigned long i;
 
@@ -2861,20 +2914,11 @@ static int __init futex_init(void)
                                                &futex_shift, NULL,
                                                futex_hashsize, futex_hashsize);
         futex_hashsize = 1UL << futex_shift;
-        /*
-         * This will fail and we want it. Some arch implementations do
-         * runtime detection of the futex_atomic_cmpxchg_inatomic()
-         * functionality. We want to know that before we call in any
-         * of the complex code paths. Also we want to prevent
-         * registration of robust lists in that case. NULL is
-         * guaranteed to fault and we get -EFAULT on functional
-         * implementation, the non-functional ones will return
-         * -ENOSYS.
-         */
-        if (cmpxchg_futex_value_locked(&curval, NULL, 0, 0) == -EFAULT)
-                futex_cmpxchg_enabled = 1;
+
+        futex_detect_cmpxchg();
 
         for (i = 0; i < futex_hashsize; i++) {
+                atomic_set(&futex_queues[i].waiters, 0);
                 plist_head_init(&futex_queues[i].chain);
                 spin_lock_init(&futex_queues[i].lock);
         }
diff --git a/kernel/futex_compat.c b/kernel/futex_compat.c
index f9f44fd4d34d..55c8c9349cfe 100644
--- a/kernel/futex_compat.c
+++ b/kernel/futex_compat.c
@@ -183,7 +183,7 @@ COMPAT_SYSCALL_DEFINE6(futex, u32 __user *, uaddr, int, op, u32, val,
         if (utime && (cmd == FUTEX_WAIT || cmd == FUTEX_LOCK_PI ||
                       cmd == FUTEX_WAIT_BITSET ||
                       cmd == FUTEX_WAIT_REQUEUE_PI)) {
-                if (get_compat_timespec(&ts, utime))
+                if (compat_get_timespec(&ts, utime))
                         return -EFAULT;
                 if (!timespec_valid(&ts))
                         return -EINVAL;
diff --git a/kernel/groups.c b/kernel/groups.c
index 90cf1c38c8ea..451698f86cfa 100644
--- a/kernel/groups.c
+++ b/kernel/groups.c
@@ -157,17 +157,13 @@ int groups_search(const struct group_info *group_info, kgid_t grp)
  * set_groups - Change a group subscription in a set of credentials
  * @new: The newly prepared set of credentials to alter
  * @group_info: The group list to install
- *
- * Validate a group subscription and, if valid, insert it into a set
- * of credentials.
  */
-int set_groups(struct cred *new, struct group_info *group_info)
+void set_groups(struct cred *new, struct group_info *group_info)
 {
         put_group_info(new->group_info);
         groups_sort(group_info);
         get_group_info(group_info);
         new->group_info = group_info;
-        return 0;
 }
 
 EXPORT_SYMBOL(set_groups);
@@ -182,18 +178,12 @@ EXPORT_SYMBOL(set_groups);
 int set_current_groups(struct group_info *group_info)
 {
         struct cred *new;
-        int ret;
 
         new = prepare_creds();
         if (!new)
                 return -ENOMEM;
 
-        ret = set_groups(new, group_info);
-        if (ret < 0) {
-                abort_creds(new);
-                return ret;
-        }
-
+        set_groups(new, group_info);
         return commit_creds(new);
 }
 
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index 09094361dce5..d55092ceee29 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -168,19 +168,6 @@ struct hrtimer_clock_base *lock_hrtimer_base(const struct hrtimer *timer,
         }
 }
 
-
-/*
- * Get the preferred target CPU for NOHZ
- */
-static int hrtimer_get_target(int this_cpu, int pinned)
-{
-#ifdef CONFIG_NO_HZ_COMMON
-        if (!pinned && get_sysctl_timer_migration() && idle_cpu(this_cpu))
-                return get_nohz_timer_target();
-#endif
-        return this_cpu;
-}
-
 /*
  * With HIGHRES=y we do not migrate the timer when it is expiring
  * before the next event on the target cpu because we cannot reprogram
@@ -214,7 +201,7 @@ switch_hrtimer_base(struct hrtimer *timer, struct hrtimer_clock_base *base,
         struct hrtimer_clock_base *new_base;
         struct hrtimer_cpu_base *new_cpu_base;
         int this_cpu = smp_processor_id();
-        int cpu = hrtimer_get_target(this_cpu, pinned);
+        int cpu = get_nohz_timer_target(pinned);
         int basenum = base->index;
 
 again:
diff --git a/kernel/hung_task.c b/kernel/hung_task.c
index 0b9c169d577f..06bb1417b063 100644
--- a/kernel/hung_task.c
+++ b/kernel/hung_task.c
@@ -246,5 +246,4 @@ static int __init hung_task_init(void)
 
         return 0;
 }
-
-module_init(hung_task_init);
+subsys_initcall(hung_task_init);
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index dc04c166c54d..6397df2d6945 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -281,6 +281,19 @@ void unmask_irq(struct irq_desc *desc)
         }
 }
 
+void unmask_threaded_irq(struct irq_desc *desc)
+{
+        struct irq_chip *chip = desc->irq_data.chip;
+
+        if (chip->flags & IRQCHIP_EOI_THREADED)
+                chip->irq_eoi(&desc->irq_data);
+
+        if (chip->irq_unmask) {
+                chip->irq_unmask(&desc->irq_data);
+                irq_state_clr_masked(desc);
+        }
+}
+
 /*
  *      handle_nested_irq - Handle a nested irq from a irq thread
  *      @irq:   the interrupt number
@@ -435,6 +448,27 @@ static inline void preflow_handler(struct irq_desc *desc)
 static inline void preflow_handler(struct irq_desc *desc) { }
 #endif
 
+static void cond_unmask_eoi_irq(struct irq_desc *desc, struct irq_chip *chip)
+{
+        if (!(desc->istate & IRQS_ONESHOT)) {
+                chip->irq_eoi(&desc->irq_data);
+                return;
+        }
+        /*
+         * We need to unmask in the following cases:
+         * - Oneshot irq which did not wake the thread (caused by a
+         *   spurious interrupt or a primary handler handling it
+         *   completely).
+         */
+        if (!irqd_irq_disabled(&desc->irq_data) &&
+            irqd_irq_masked(&desc->irq_data) && !desc->threads_oneshot) {
+                chip->irq_eoi(&desc->irq_data);
+                unmask_irq(desc);
+        } else if (!(chip->flags & IRQCHIP_EOI_THREADED)) {
+                chip->irq_eoi(&desc->irq_data);
+        }
+}
+
 /**
  *      handle_fasteoi_irq - irq handler for transparent controllers
  *      @irq:   the interrupt number
@@ -448,6 +482,8 @@ static inline void preflow_handler(struct irq_desc *desc) { }
 void
 handle_fasteoi_irq(unsigned int irq, struct irq_desc *desc)
 {
+        struct irq_chip *chip = desc->irq_data.chip;
+
         raw_spin_lock(&desc->lock);
 
         if (unlikely(irqd_irq_inprogress(&desc->irq_data)))
@@ -473,18 +509,14 @@ handle_fasteoi_irq(unsigned int irq, struct irq_desc *desc)
         preflow_handler(desc);
         handle_irq_event(desc);
 
-        if (desc->istate & IRQS_ONESHOT)
-                cond_unmask_irq(desc);
+        cond_unmask_eoi_irq(desc, chip);
 
-out_eoi:
-        desc->irq_data.chip->irq_eoi(&desc->irq_data);
-out_unlock:
         raw_spin_unlock(&desc->lock);
         return;
 out:
-        if (!(desc->irq_data.chip->flags & IRQCHIP_EOI_IF_HANDLED))
-                goto out_eoi;
-        goto out_unlock;
+        if (!(chip->flags & IRQCHIP_EOI_IF_HANDLED))
+                chip->irq_eoi(&desc->irq_data);
+        raw_spin_unlock(&desc->lock);
 }
 
 /**
diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c
index 131ca176b497..635480270858 100644
--- a/kernel/irq/handle.c
+++ b/kernel/irq/handle.c
@@ -41,6 +41,7 @@ irqreturn_t no_action(int cpl, void *dev_id)
 {
         return IRQ_NONE;
 }
+EXPORT_SYMBOL_GPL(no_action);
 
 static void warn_no_thread(unsigned int irq, struct irqaction *action)
 {
@@ -51,7 +52,7 @@ static void warn_no_thread(unsigned int irq, struct irqaction *action)
                "but no thread function available.", irq, action->name);
 }
 
-static void irq_wake_thread(struct irq_desc *desc, struct irqaction *action)
+void __irq_wake_thread(struct irq_desc *desc, struct irqaction *action)
 {
         /*
          * In case the thread crashed and was killed we just pretend that
@@ -157,7 +158,7 @@ handle_irq_event_percpu(struct irq_desc *desc, struct irqaction *action)
                                 break;
                         }
 
-                        irq_wake_thread(desc, action);
+                        __irq_wake_thread(desc, action);
 
                         /* Fall through to add to randomness */
                 case IRQ_HANDLED:
diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h
index 001fa5bab490..ddf1ffeb79f1 100644
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -6,6 +6,7 @@
  * of this file for your non core code.
  */
 #include <linux/irqdesc.h>
+#include <linux/kernel_stat.h>
 
 #ifdef CONFIG_SPARSE_IRQ
 # define IRQ_BITMAP_BITS        (NR_IRQS + 8196)
@@ -73,6 +74,7 @@ extern void irq_percpu_enable(struct irq_desc *desc, unsigned int cpu);
 extern void irq_percpu_disable(struct irq_desc *desc, unsigned int cpu);
 extern void mask_irq(struct irq_desc *desc);
 extern void unmask_irq(struct irq_desc *desc);
+extern void unmask_threaded_irq(struct irq_desc *desc);
 
 extern void init_kstat_irqs(struct irq_desc *desc, int node, int nr);
 
@@ -82,6 +84,7 @@ irqreturn_t handle_irq_event(struct irq_desc *desc);
 /* Resending of interrupts :*/
 void check_irq_resend(struct irq_desc *desc, unsigned int irq);
 bool irq_wait_for_poll(struct irq_desc *desc);
+void __irq_wake_thread(struct irq_desc *desc, struct irqaction *action);
 
 #ifdef CONFIG_PROC_FS
 extern void register_irq_proc(unsigned int irq, struct irq_desc *desc);
@@ -179,3 +182,9 @@ static inline bool irqd_has_set(struct irq_data *d, unsigned int mask)
 {
         return d->state_use_accessors & mask;
 }
+
+static inline void kstat_incr_irqs_this_cpu(unsigned int irq, struct irq_desc *desc)
+{
+        __this_cpu_inc(*desc->kstat_irqs);
+        __this_cpu_inc(kstat.irqs_sum);
+}
diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c
index 8ab8e9390297..a7174617616b 100644
--- a/kernel/irq/irqdesc.c
+++ b/kernel/irq/irqdesc.c
@@ -489,6 +489,11 @@ void dynamic_irq_cleanup(unsigned int irq)
         raw_spin_unlock_irqrestore(&desc->lock, flags);
 }
 
+void kstat_incr_irq_this_cpu(unsigned int irq)
+{
+        kstat_incr_irqs_this_cpu(irq, irq_to_desc(irq));
+}
+
 unsigned int kstat_irqs_cpu(unsigned int irq, int cpu)
 {
         struct irq_desc *desc = irq_to_desc(irq);
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index d3bf660cb57f..2486a4c1a710 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -32,24 +32,10 @@ static int __init setup_forced_irqthreads(char *arg)
 early_param("threadirqs", setup_forced_irqthreads);
 #endif
 
-/**
- *      synchronize_irq - wait for pending IRQ handlers (on other CPUs)
- *      @irq: interrupt number to wait for
- *
- *      This function waits for any pending IRQ handlers for this interrupt
- *      to complete before returning. If you use this function while
- *      holding a resource the IRQ handler may need you will deadlock.
- *
- *      This function may be called - with care - from IRQ context.
- */
-void synchronize_irq(unsigned int irq)
+static void __synchronize_hardirq(struct irq_desc *desc)
 {
-        struct irq_desc *desc = irq_to_desc(irq);
         bool inprogress;
 
-        if (!desc)
-                return;
-
         do {
                 unsigned long flags;
 
@@ -67,12 +53,56 @@ void synchronize_irq(unsigned int irq)
 
                 /* Oops, that failed? */
         } while (inprogress);
+}
 
-        /*
-         * We made sure that no hardirq handler is running. Now verify
-         * that no threaded handlers are active.
-         */
-        wait_event(desc->wait_for_threads, !atomic_read(&desc->threads_active));
+/**
+ *      synchronize_hardirq - wait for pending hard IRQ handlers (on other CPUs)
+ *      @irq: interrupt number to wait for
+ *
+ *      This function waits for any pending hard IRQ handlers for this
+ *      interrupt to complete before returning. If you use this
+ *      function while holding a resource the IRQ handler may need you
+ *      will deadlock. It does not take associated threaded handlers
+ *      into account.
+ *
+ *      Do not use this for shutdown scenarios where you must be sure
+ *      that all parts (hardirq and threaded handler) have completed.
+ *
+ *      This function may be called - with care - from IRQ context.
+ */
+void synchronize_hardirq(unsigned int irq)
+{
+        struct irq_desc *desc = irq_to_desc(irq);
+
+        if (desc)
+                __synchronize_hardirq(desc);
+}
+EXPORT_SYMBOL(synchronize_hardirq);
+
+/**
+ *      synchronize_irq - wait for pending IRQ handlers (on other CPUs)
+ *      @irq: interrupt number to wait for
+ *
+ *      This function waits for any pending IRQ handlers for this interrupt
+ *      to complete before returning. If you use this function while
+ *      holding a resource the IRQ handler may need you will deadlock.
+ *
+ *      This function may be called - with care - from IRQ context.
+ */
+void synchronize_irq(unsigned int irq)
+{
+        struct irq_desc *desc = irq_to_desc(irq);
+
+        if (desc) {
+                __synchronize_hardirq(desc);
+                /*
+                 * We made sure that no hardirq handler is
+                 * running. Now verify that no threaded handlers are
+                 * active.
+                 */
+                wait_event(desc->wait_for_threads,
+                           !atomic_read(&desc->threads_active));
+        }
 }
 EXPORT_SYMBOL(synchronize_irq);
 
@@ -718,7 +748,7 @@ again:
 
         if (!desc->threads_oneshot && !irqd_irq_disabled(&desc->irq_data) &&
             irqd_irq_masked(&desc->irq_data))
-                unmask_irq(desc);
+                unmask_threaded_irq(desc);
 
 out_unlock:
         raw_spin_unlock_irq(&desc->lock);
@@ -727,7 +757,7 @@ out_unlock:
 
 #ifdef CONFIG_SMP
 /*
- * Check whether we need to chasnge the affinity of the interrupt thread.
+ * Check whether we need to change the affinity of the interrupt thread.
  */
 static void
 irq_thread_check_affinity(struct irq_desc *desc, struct irqaction *action)
@@ -880,6 +910,33 @@ static int irq_thread(void *data)
         return 0;
 }
 
+/**
+ *      irq_wake_thread - wake the irq thread for the action identified by dev_id
+ *      @irq:           Interrupt line
+ *      @dev_id:        Device identity for which the thread should be woken
+ *
+ */
+void irq_wake_thread(unsigned int irq, void *dev_id)
+{
+        struct irq_desc *desc = irq_to_desc(irq);
+        struct irqaction *action;
+        unsigned long flags;
+
+        if (!desc || WARN_ON(irq_settings_is_per_cpu_devid(desc)))
+                return;
+
+        raw_spin_lock_irqsave(&desc->lock, flags);
+        for (action = desc->action; action; action = action->next) {
+                if (action->dev_id == dev_id) {
+                        if (action->thread)
+                                __irq_wake_thread(desc, action);
+                        break;
+                }
+        }
+        raw_spin_unlock_irqrestore(&desc->lock, flags);
+}
+EXPORT_SYMBOL_GPL(irq_wake_thread);
+
 static void irq_setup_forced_threading(struct irqaction *new)
 {
         if (!force_irqthreads)
@@ -896,6 +953,23 @@ static void irq_setup_forced_threading(struct irqaction *new)
         }
 }
 
+static int irq_request_resources(struct irq_desc *desc)
+{
+        struct irq_data *d = &desc->irq_data;
+        struct irq_chip *c = d->chip;
+
+        return c->irq_request_resources ? c->irq_request_resources(d) : 0;
+}
+
+static void irq_release_resources(struct irq_desc *desc)
+{
+        struct irq_data *d = &desc->irq_data;
+        struct irq_chip *c = d->chip;
+
+        if (c->irq_release_resources)
+                c->irq_release_resources(d);
+}
+
 /*
  * Internal function to register an irqaction - typically used to
  * allocate special interrupts that are part of the architecture.
@@ -1091,6 +1165,13 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
         }
 
         if (!shared) {
+                ret = irq_request_resources(desc);
+                if (ret) {
+                        pr_err("Failed to request resources for %s (irq %d) on irqchip %s\n",
+                               new->name, irq, desc->irq_data.chip->name);
+                        goto out_mask;
+                }
+
                 init_waitqueue_head(&desc->wait_for_threads);
 
                 /* Setup the type (level, edge polarity) if configured: */
@@ -1261,8 +1342,10 @@ static struct irqaction *__free_irq(unsigned int irq, void *dev_id)
         *action_ptr = action->next;
 
         /* If this was the last handler, shut down the IRQ line: */
-        if (!desc->action)
+        if (!desc->action) {
                 irq_shutdown(desc);
+                irq_release_resources(desc);
+        }
 
 #ifdef CONFIG_SMP
         /* make sure affinity_hint is cleaned up */
diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c
index 36f6ee181b0c..ac1ba2f11032 100644
--- a/kernel/irq/proc.c
+++ b/kernel/irq/proc.c
@@ -324,15 +324,15 @@ void register_irq_proc(unsigned int irq, struct irq_desc *desc)
 
 #ifdef CONFIG_SMP
         /* create /proc/irq/<irq>/smp_affinity */
-        proc_create_data("smp_affinity", 0600, desc->dir,
+        proc_create_data("smp_affinity", 0644, desc->dir,
                          &irq_affinity_proc_fops, (void *)(long)irq);
 
         /* create /proc/irq/<irq>/affinity_hint */
-        proc_create_data("affinity_hint", 0400, desc->dir,
+        proc_create_data("affinity_hint", 0444, desc->dir,
                          &irq_affinity_hint_proc_fops, (void *)(long)irq);
 
         /* create /proc/irq/<irq>/smp_affinity_list */
-        proc_create_data("smp_affinity_list", 0600, desc->dir,
+        proc_create_data("smp_affinity_list", 0644, desc->dir,
                          &irq_affinity_list_proc_fops, (void *)(long)irq);
 
         proc_create_data("node", 0444, desc->dir,
@@ -372,7 +372,7 @@ void unregister_handler_proc(unsigned int irq, struct irqaction *action)
 static void register_default_affinity_proc(void)
 {
 #ifdef CONFIG_SMP
-        proc_create("irq/default_smp_affinity", 0600, NULL,
+        proc_create("irq/default_smp_affinity", 0644, NULL,
                     &default_affinity_proc_fops);
 #endif
 }
diff --git a/kernel/irq_work.c b/kernel/irq_work.c
index 55fcce6065cf..a82170e2fa78 100644
--- a/kernel/irq_work.c
+++ b/kernel/irq_work.c
@@ -61,11 +61,11 @@ void __weak arch_irq_work_raise(void)
  *
  * Can be re-enqueued while the callback is still in progress.
  */
-void irq_work_queue(struct irq_work *work)
+bool irq_work_queue(struct irq_work *work)
 {
         /* Only queue if not already pending */
         if (!irq_work_claim(work))
-                return;
+                return false;
 
         /* Queue the entry and raise the IPI if needed. */
         preempt_disable();
@@ -83,6 +83,8 @@ void irq_work_queue(struct irq_work *work)
         }
 
         preempt_enable();
+
+        return true;
 }
 EXPORT_SYMBOL_GPL(irq_work_queue);
 
diff --git a/kernel/kexec.c b/kernel/kexec.c
index 60bafbed06ab..c0d261c7db7b 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -1039,10 +1039,10 @@ void __weak crash_unmap_reserved_pages(void)
 {}
 
 #ifdef CONFIG_COMPAT
-asmlinkage long compat_sys_kexec_load(unsigned long entry,
-                                unsigned long nr_segments,
-                                struct compat_kexec_segment __user *segments,
-                                unsigned long flags)
+COMPAT_SYSCALL_DEFINE4(kexec_load, compat_ulong_t, entry,
+                       compat_ulong_t, nr_segments,
+                       struct compat_kexec_segment __user *, segments,
+                       compat_ulong_t, flags)
 {
         struct compat_kexec_segment in;
         struct kexec_segment out, __user *ksegments;
@@ -1235,7 +1235,7 @@ static int __init crash_notes_memory_init(void)
         }
         return 0;
 }
-module_init(crash_notes_memory_init)
+subsys_initcall(crash_notes_memory_init);
 
 
 /*
@@ -1629,7 +1629,7 @@ static int __init crash_save_vmcoreinfo_init(void)
         return 0;
 }
 
-module_init(crash_save_vmcoreinfo_init)
+subsys_initcall(crash_save_vmcoreinfo_init);
 
 /*
  * Move into place and start executing a preloaded standalone
diff --git a/kernel/ksysfs.c b/kernel/ksysfs.c
index d945a949760f..e660964086e2 100644
--- a/kernel/ksysfs.c
+++ b/kernel/ksysfs.c
@@ -19,6 +19,8 @@
 #include <linux/sched.h>
 #include <linux/capability.h>
 
+#include <linux/rcupdate.h>     /* rcu_expedited */
+
 #define KERNEL_ATTR_RO(_name) \
 static struct kobj_attribute _name##_attr = __ATTR_RO(_name)
 
diff --git a/kernel/kthread.c b/kernel/kthread.c
index b5ae3ee860a9..9a130ec06f7a 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -217,7 +217,7 @@ int tsk_fork_get_node(struct task_struct *tsk)
         if (tsk == kthreadd_task)
                 return tsk->pref_node_fork;
 #endif
-        return numa_node_id();
+        return NUMA_NO_NODE;
 }
 
 static void create_kthread(struct kthread_create_info *create)
@@ -369,7 +369,7 @@ struct task_struct *kthread_create_on_cpu(int (*threadfn)(void *data),
 {
         struct task_struct *p;
 
-        p = kthread_create_on_node(threadfn, data, cpu_to_node(cpu), namefmt,
+        p = kthread_create_on_node(threadfn, data, cpu_to_mem(cpu), namefmt,
                                    cpu);
         if (IS_ERR(p))
                 return p;
diff --git a/kernel/locking/Makefile b/kernel/locking/Makefile
index baab8e5e7f66..306a76b51e0f 100644
--- a/kernel/locking/Makefile
+++ b/kernel/locking/Makefile
@@ -1,5 +1,5 @@
 
-obj-y += mutex.o semaphore.o rwsem.o lglock.o
+obj-y += mutex.o semaphore.o rwsem.o lglock.o mcs_spinlock.o
 
 ifdef CONFIG_FUNCTION_TRACER
 CFLAGS_REMOVE_lockdep.o = -pg
@@ -23,3 +23,4 @@ obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock_debug.o
 obj-$(CONFIG_RWSEM_GENERIC_SPINLOCK) += rwsem-spinlock.o
 obj-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem-xadd.o
 obj-$(CONFIG_PERCPU_RWSEM) += percpu-rwsem.o
+obj-$(CONFIG_LOCK_TORTURE_TEST) += locktorture.o
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index eb8a54783fa0..b0e9467922e1 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -1936,12 +1936,12 @@ check_prevs_add(struct task_struct *curr, struct held_lock *next)
 
         for (;;) {
                 int distance = curr->lockdep_depth - depth + 1;
-                hlock = curr->held_locks + depth-1;
+                hlock = curr->held_locks + depth - 1;
                 /*
                  * Only non-recursive-read entries get new dependencies
                  * added:
                  */
-                if (hlock->read != 2) {
+                if (hlock->read != 2 && hlock->check) {
                         if (!check_prev_add(curr, hlock, next,
                                                 distance, trylock_loop))
                                 return 0;
@@ -2098,7 +2098,7 @@ static int validate_chain(struct task_struct *curr, struct lockdep_map *lock,
          * (If lookup_chain_cache() returns with 1 it acquires
          * graph_lock for us)
          */
-        if (!hlock->trylock && (hlock->check == 2) &&
+        if (!hlock->trylock && hlock->check &&
             lookup_chain_cache(curr, hlock, chain_key)) {
                 /*
                  * Check whether last held lock:
@@ -2517,7 +2517,7 @@ mark_held_locks(struct task_struct *curr, enum mark_type mark)
 
                 BUG_ON(usage_bit >= LOCK_USAGE_STATES);
 
-                if (hlock_class(hlock)->key == __lockdep_no_validate__.subkeys)
+                if (!hlock->check)
                         continue;
 
                 if (!mark_lock(curr, hlock, usage_bit))
@@ -2557,7 +2557,7 @@ static void __trace_hardirqs_on_caller(unsigned long ip)
         debug_atomic_inc(hardirqs_on_events);
 }
 
-void trace_hardirqs_on_caller(unsigned long ip)
+__visible void trace_hardirqs_on_caller(unsigned long ip)
 {
         time_hardirqs_on(CALLER_ADDR0, ip);
 
@@ -2610,7 +2610,7 @@ EXPORT_SYMBOL(trace_hardirqs_on);
 /*
  * Hardirqs were disabled:
  */
-void trace_hardirqs_off_caller(unsigned long ip)
+__visible void trace_hardirqs_off_caller(unsigned long ip)
 {
         struct task_struct *curr = current;
 
@@ -3055,9 +3055,6 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass,
         int class_idx;
         u64 chain_key;
 
-        if (!prove_locking)
-                check = 1;
-
         if (unlikely(!debug_locks))
                 return 0;
 
@@ -3069,8 +3066,8 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass,
         if (DEBUG_LOCKS_WARN_ON(!irqs_disabled()))
                 return 0;
 
-        if (lock->key == &__lockdep_no_validate__)
-                check = 1;
+        if (!prove_locking || lock->key == &__lockdep_no_validate__)
+                check = 0;
 
         if (subclass < NR_LOCKDEP_CACHING_CLASSES)
                 class = lock->class_cache[subclass];
@@ -3138,7 +3135,7 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass,
         hlock->holdtime_stamp = lockstat_clock();
 #endif
 
-        if (check == 2 && !mark_irqflags(curr, hlock))
+        if (check && !mark_irqflags(curr, hlock))
                 return 0;
 
         /* mark it as used: */
@@ -4191,7 +4188,7 @@ void debug_show_held_locks(struct task_struct *task)
 }
 EXPORT_SYMBOL_GPL(debug_show_held_locks);
 
-void lockdep_sys_exit(void)
+asmlinkage void lockdep_sys_exit(void)
 {
         struct task_struct *curr = current;
 
diff --git a/kernel/locking/locktorture.c b/kernel/locking/locktorture.c
new file mode 100644
index 000000000000..f26b1a18e34e
--- /dev/null
+++ b/kernel/locking/locktorture.c
@@ -0,0 +1,452 @@
+/*
+ * Module-based torture test facility for locking
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program 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 General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, you can access it online at
+ * http://www.gnu.org/licenses/gpl-2.0.html.
+ *
+ * Copyright (C) IBM Corporation, 2014
+ *
+ * Author: Paul E. McKenney <paulmck@us.ibm.com>
+ *      Based on kernel/rcu/torture.c.
+ */
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/kthread.h>
+#include <linux/err.h>
+#include <linux/spinlock.h>
+#include <linux/smp.h>
+#include <linux/interrupt.h>
+#include <linux/sched.h>
+#include <linux/atomic.h>
+#include <linux/bitops.h>
+#include <linux/completion.h>
+#include <linux/moduleparam.h>
+#include <linux/percpu.h>
+#include <linux/notifier.h>
+#include <linux/reboot.h>
+#include <linux/freezer.h>
+#include <linux/cpu.h>
+#include <linux/delay.h>
+#include <linux/stat.h>
+#include <linux/slab.h>
+#include <linux/trace_clock.h>
+#include <asm/byteorder.h>
+#include <linux/torture.h>
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Paul E. McKenney <paulmck@us.ibm.com>");
+
+torture_param(int, nwriters_stress, -1,
+             "Number of write-locking stress-test threads");
+torture_param(int, onoff_holdoff, 0, "Time after boot before CPU hotplugs (s)");
+torture_param(int, onoff_interval, 0,
+             "Time between CPU hotplugs (s), 0=disable");
+torture_param(int, shuffle_interval, 3,
+             "Number of jiffies between shuffles, 0=disable");
+torture_param(int, shutdown_secs, 0, "Shutdown time (j), <= zero to disable.");
+torture_param(int, stat_interval, 60,
+             "Number of seconds between stats printk()s");
+torture_param(int, stutter, 5, "Number of jiffies to run/halt test, 0=disable");
+torture_param(bool, verbose, true,
+             "Enable verbose debugging printk()s");
+
+static char *torture_type = "spin_lock";
+module_param(torture_type, charp, 0444);
+MODULE_PARM_DESC(torture_type,
+                 "Type of lock to torture (spin_lock, spin_lock_irq, ...)");
+
+static atomic_t n_lock_torture_errors;
+
+static struct task_struct *stats_task;
+static struct task_struct **writer_tasks;
+
+static int nrealwriters_stress;
+static bool lock_is_write_held;
+
+struct lock_writer_stress_stats {
+        long n_write_lock_fail;
+        long n_write_lock_acquired;
+};
+static struct lock_writer_stress_stats *lwsa;
+
+#if defined(MODULE) || defined(CONFIG_LOCK_TORTURE_TEST_RUNNABLE)
+#define LOCKTORTURE_RUNNABLE_INIT 1
+#else
+#define LOCKTORTURE_RUNNABLE_INIT 0
+#endif
+int locktorture_runnable = LOCKTORTURE_RUNNABLE_INIT;
+module_param(locktorture_runnable, int, 0444);
+MODULE_PARM_DESC(locktorture_runnable, "Start locktorture at boot");
+
+/* Forward reference. */
+static void lock_torture_cleanup(void);
+
+/*
+ * Operations vector for selecting different types of tests.
+ */
+struct lock_torture_ops {
+        void (*init)(void);
+        int (*writelock)(void);
+        void (*write_delay)(struct torture_random_state *trsp);
+        void (*writeunlock)(void);
+        unsigned long flags;
+        const char *name;
+};
+
+static struct lock_torture_ops *cur_ops;
+
+/*
+ * Definitions for lock torture testing.
+ */
+
+static int torture_lock_busted_write_lock(void)
+{
+        return 0;  /* BUGGY, do not use in real life!!! */
+}
+
+static void torture_lock_busted_write_delay(struct torture_random_state *trsp)
+{
+        const unsigned long longdelay_us = 100;
+
+        /* We want a long delay occasionally to force massive contention.  */
+        if (!(torture_random(trsp) %
+              (nrealwriters_stress * 2000 * longdelay_us)))
+                mdelay(longdelay_us);
+#ifdef CONFIG_PREEMPT
+        if (!(torture_random(trsp) % (nrealwriters_stress * 20000)))
+                preempt_schedule();  /* Allow test to be preempted. */
+#endif
+}
+
+static void torture_lock_busted_write_unlock(void)
+{
+          /* BUGGY, do not use in real life!!! */
+}
+
+static struct lock_torture_ops lock_busted_ops = {
+        .writelock      = torture_lock_busted_write_lock,
+        .write_delay    = torture_lock_busted_write_delay,
+        .writeunlock    = torture_lock_busted_write_unlock,
+        .name           = "lock_busted"
+};
+
+static DEFINE_SPINLOCK(torture_spinlock);
+
+static int torture_spin_lock_write_lock(void) __acquires(torture_spinlock)
+{
+        spin_lock(&torture_spinlock);
+        return 0;
+}
+
+static void torture_spin_lock_write_delay(struct torture_random_state *trsp)
+{
+        const unsigned long shortdelay_us = 2;
+        const unsigned long longdelay_us = 100;
+
+        /* We want a short delay mostly to emulate likely code, and
+         * we want a long delay occasionally to force massive contention.
+         */
+        if (!(torture_random(trsp) %
+              (nrealwriters_stress * 2000 * longdelay_us)))
+                mdelay(longdelay_us);
+        if (!(torture_random(trsp) %
+              (nrealwriters_stress * 2 * shortdelay_us)))
+                udelay(shortdelay_us);
+#ifdef CONFIG_PREEMPT
+        if (!(torture_random(trsp) % (nrealwriters_stress * 20000)))
+                preempt_schedule();  /* Allow test to be preempted. */
+#endif
+}
+
+static void torture_spin_lock_write_unlock(void) __releases(torture_spinlock)
+{
+        spin_unlock(&torture_spinlock);
+}
+
+static struct lock_torture_ops spin_lock_ops = {
+        .writelock      = torture_spin_lock_write_lock,
+        .write_delay    = torture_spin_lock_write_delay,
+        .writeunlock    = torture_spin_lock_write_unlock,
+        .name           = "spin_lock"
+};
+
+static int torture_spin_lock_write_lock_irq(void)
+__acquires(torture_spinlock_irq)
+{
+        unsigned long flags;
+
+        spin_lock_irqsave(&torture_spinlock, flags);
+        cur_ops->flags = flags;
+        return 0;
+}
+
+static void torture_lock_spin_write_unlock_irq(void)
+__releases(torture_spinlock)
+{
+        spin_unlock_irqrestore(&torture_spinlock, cur_ops->flags);
+}
+
+static struct lock_torture_ops spin_lock_irq_ops = {
+        .writelock      = torture_spin_lock_write_lock_irq,
+        .write_delay    = torture_spin_lock_write_delay,
+        .writeunlock    = torture_lock_spin_write_unlock_irq,
+        .name           = "spin_lock_irq"
+};
+
+/*
+ * Lock torture writer kthread.  Repeatedly acquires and releases
+ * the lock, checking for duplicate acquisitions.
+ */
+static int lock_torture_writer(void *arg)
+{
+        struct lock_writer_stress_stats *lwsp = arg;
+        static DEFINE_TORTURE_RANDOM(rand);
+
+        VERBOSE_TOROUT_STRING("lock_torture_writer task started");
+        set_user_nice(current, 19);
+
+        do {
+                schedule_timeout_uninterruptible(1);
+                cur_ops->writelock();
+                if (WARN_ON_ONCE(lock_is_write_held))
+                        lwsp->n_write_lock_fail++;
+                lock_is_write_held = 1;
+                lwsp->n_write_lock_acquired++;
+                cur_ops->write_delay(&rand);
+                lock_is_write_held = 0;
+                cur_ops->writeunlock();
+                stutter_wait("lock_torture_writer");
+        } while (!torture_must_stop());
+        torture_kthread_stopping("lock_torture_writer");
+        return 0;
+}
+
+/*
+ * Create an lock-torture-statistics message in the specified buffer.
+ */
+static void lock_torture_printk(char *page)
+{
+        bool fail = 0;
+        int i;
+        long max = 0;
+        long min = lwsa[0].n_write_lock_acquired;
+        long long sum = 0;
+
+        for (i = 0; i < nrealwriters_stress; i++) {
+                if (lwsa[i].n_write_lock_fail)
+                        fail = true;
+                sum += lwsa[i].n_write_lock_acquired;
+                if (max < lwsa[i].n_write_lock_fail)
+                        max = lwsa[i].n_write_lock_fail;
+                if (min > lwsa[i].n_write_lock_fail)
+                        min = lwsa[i].n_write_lock_fail;
+        }
+        page += sprintf(page, "%s%s ", torture_type, TORTURE_FLAG);
+        page += sprintf(page,
+                        "Writes:  Total: %lld  Max/Min: %ld/%ld %s  Fail: %d %s\n",
+                        sum, max, min, max / 2 > min ? "???" : "",
+                        fail, fail ? "!!!" : "");
+        if (fail)
+                atomic_inc(&n_lock_torture_errors);
+}
+
+/*
+ * Print torture statistics.  Caller must ensure that there is only one
+ * call to this function at a given time!!!  This is normally accomplished
+ * by relying on the module system to only have one copy of the module
+ * loaded, and then by giving the lock_torture_stats kthread full control
+ * (or the init/cleanup functions when lock_torture_stats thread is not
+ * running).
+ */
+static void lock_torture_stats_print(void)
+{
+        int size = nrealwriters_stress * 200 + 8192;
+        char *buf;
+
+        buf = kmalloc(size, GFP_KERNEL);
+        if (!buf) {
+                pr_err("lock_torture_stats_print: Out of memory, need: %d",
+                       size);
+                return;
+        }
+        lock_torture_printk(buf);
+        pr_alert("%s", buf);
+        kfree(buf);
+}
+
+/*
+ * Periodically prints torture statistics, if periodic statistics printing
+ * was specified via the stat_interval module parameter.
+ *
+ * No need to worry about fullstop here, since this one doesn't reference
+ * volatile state or register callbacks.
+ */
+static int lock_torture_stats(void *arg)
+{
+        VERBOSE_TOROUT_STRING("lock_torture_stats task started");
+        do {
+                schedule_timeout_interruptible(stat_interval * HZ);
+                lock_torture_stats_print();
+                torture_shutdown_absorb("lock_torture_stats");
+        } while (!torture_must_stop());
+        torture_kthread_stopping("lock_torture_stats");
+        return 0;
+}
+
+static inline void
+lock_torture_print_module_parms(struct lock_torture_ops *cur_ops,
+                                const char *tag)
+{
+        pr_alert("%s" TORTURE_FLAG
+                 "--- %s: nwriters_stress=%d stat_interval=%d verbose=%d shuffle_interval=%d stutter=%d shutdown_secs=%d onoff_interval=%d onoff_holdoff=%d\n",
+                 torture_type, tag, nrealwriters_stress, stat_interval, verbose,
+                 shuffle_interval, stutter, shutdown_secs,
+                 onoff_interval, onoff_holdoff);
+}
+
+static void lock_torture_cleanup(void)
+{
+        int i;
+
+        if (torture_cleanup())
+                return;
+
+        if (writer_tasks) {
+                for (i = 0; i < nrealwriters_stress; i++)
+                        torture_stop_kthread(lock_torture_writer,
+                                             writer_tasks[i]);
+                kfree(writer_tasks);
+                writer_tasks = NULL;
+        }
+
+        torture_stop_kthread(lock_torture_stats, stats_task);
+        lock_torture_stats_print();  /* -After- the stats thread is stopped! */
+
+        if (atomic_read(&n_lock_torture_errors))
+                lock_torture_print_module_parms(cur_ops,
+                                                "End of test: FAILURE");
+        else if (torture_onoff_failures())
+                lock_torture_print_module_parms(cur_ops,
+                                                "End of test: LOCK_HOTPLUG");
+        else
+                lock_torture_print_module_parms(cur_ops,
+                                                "End of test: SUCCESS");
+}
+
+static int __init lock_torture_init(void)
+{
+        int i;
+        int firsterr = 0;
+        static struct lock_torture_ops *torture_ops[] = {
+                &lock_busted_ops, &spin_lock_ops, &spin_lock_irq_ops,
+        };
+
+        torture_init_begin(torture_type, verbose, &locktorture_runnable);
+
+        /* Process args and tell the world that the torturer is on the job. */
+        for (i = 0; i < ARRAY_SIZE(torture_ops); i++) {
+                cur_ops = torture_ops[i];
+                if (strcmp(torture_type, cur_ops->name) == 0)
+                        break;
+        }
+        if (i == ARRAY_SIZE(torture_ops)) {
+                pr_alert("lock-torture: invalid torture type: \"%s\"\n",
+                         torture_type);
+                pr_alert("lock-torture types:");
+                for (i = 0; i < ARRAY_SIZE(torture_ops); i++)
+                        pr_alert(" %s", torture_ops[i]->name);
+                pr_alert("\n");
+                torture_init_end();
+                return -EINVAL;
+        }
+        if (cur_ops->init)
+                cur_ops->init(); /* no "goto unwind" prior to this point!!! */
+
+        if (nwriters_stress >= 0)
+                nrealwriters_stress = nwriters_stress;
+        else
+                nrealwriters_stress = 2 * num_online_cpus();
+        lock_torture_print_module_parms(cur_ops, "Start of test");
+
+        /* Initialize the statistics so that each run gets its own numbers. */
+
+        lock_is_write_held = 0;
+        lwsa = kmalloc(sizeof(*lwsa) * nrealwriters_stress, GFP_KERNEL);
+        if (lwsa == NULL) {
+                VERBOSE_TOROUT_STRING("lwsa: Out of memory");
+                firsterr = -ENOMEM;
+                goto unwind;
+        }
+        for (i = 0; i < nrealwriters_stress; i++) {
+                lwsa[i].n_write_lock_fail = 0;
+                lwsa[i].n_write_lock_acquired = 0;
+        }
+
+        /* Start up the kthreads. */
+
+        if (onoff_interval > 0) {
+                firsterr = torture_onoff_init(onoff_holdoff * HZ,
+                                              onoff_interval * HZ);
+                if (firsterr)
+                        goto unwind;
+        }
+        if (shuffle_interval > 0) {
+                firsterr = torture_shuffle_init(shuffle_interval);
+                if (firsterr)
+                        goto unwind;
+        }
+        if (shutdown_secs > 0) {
+                firsterr = torture_shutdown_init(shutdown_secs,
+                                                 lock_torture_cleanup);
+                if (firsterr)
+                        goto unwind;
+        }
+        if (stutter > 0) {
+                firsterr = torture_stutter_init(stutter);
+                if (firsterr)
+                        goto unwind;
+        }
+
+        writer_tasks = kzalloc(nrealwriters_stress * sizeof(writer_tasks[0]),
+                               GFP_KERNEL);
+        if (writer_tasks == NULL) {
+                VERBOSE_TOROUT_ERRSTRING("writer_tasks: Out of memory");
+                firsterr = -ENOMEM;
+                goto unwind;
+        }
+        for (i = 0; i < nrealwriters_stress; i++) {
+                firsterr = torture_create_kthread(lock_torture_writer, &lwsa[i],
+                                                  writer_tasks[i]);
+                if (firsterr)
+                        goto unwind;
+        }
+        if (stat_interval > 0) {
+                firsterr = torture_create_kthread(lock_torture_stats, NULL,
+                                                  stats_task);
+                if (firsterr)
+                        goto unwind;
+        }
+        torture_init_end();
+        return 0;
+
+unwind:
+        torture_init_end();
+        lock_torture_cleanup();
+        return firsterr;
+}
+
+module_init(lock_torture_init);
+module_exit(lock_torture_cleanup);
diff --git a/kernel/locking/mcs_spinlock.c b/kernel/locking/mcs_spinlock.c
new file mode 100644
index 000000000000..838dc9e00669
--- /dev/null
+++ b/kernel/locking/mcs_spinlock.c
@@ -0,0 +1,178 @@
+
+#include <linux/percpu.h>
+#include <linux/mutex.h>
+#include <linux/sched.h>
+#include "mcs_spinlock.h"
+
+#ifdef CONFIG_SMP
+
+/*
+ * An MCS like lock especially tailored for optimistic spinning for sleeping
+ * lock implementations (mutex, rwsem, etc).
+ *
+ * Using a single mcs node per CPU is safe because sleeping locks should not be
+ * called from interrupt context and we have preemption disabled while
+ * spinning.
+ */
+static DEFINE_PER_CPU_SHARED_ALIGNED(struct optimistic_spin_queue, osq_node);
+
+/*
+ * Get a stable @node->next pointer, either for unlock() or unqueue() purposes.
+ * Can return NULL in case we were the last queued and we updated @lock instead.
+ */
+static inline struct optimistic_spin_queue *
+osq_wait_next(struct optimistic_spin_queue **lock,
+              struct optimistic_spin_queue *node,
+              struct optimistic_spin_queue *prev)
+{
+        struct optimistic_spin_queue *next = NULL;
+
+        for (;;) {
+                if (*lock == node && cmpxchg(lock, node, prev) == node) {
+                        /*
+                         * We were the last queued, we moved @lock back. @prev
+                         * will now observe @lock and will complete its
+                         * unlock()/unqueue().
+                         */
+                        break;
+                }
+
+                /*
+                 * We must xchg() the @node->next value, because if we were to
+                 * leave it in, a concurrent unlock()/unqueue() from
+                 * @node->next might complete Step-A and think its @prev is
+                 * still valid.
+                 *
+                 * If the concurrent unlock()/unqueue() wins the race, we'll
+                 * wait for either @lock to point to us, through its Step-B, or
+                 * wait for a new @node->next from its Step-C.
+                 */
+                if (node->next) {
+                        next = xchg(&node->next, NULL);
+                        if (next)
+                                break;
+                }
+
+                arch_mutex_cpu_relax();
+        }
+
+        return next;
+}
+
+bool osq_lock(struct optimistic_spin_queue **lock)
+{
+        struct optimistic_spin_queue *node = this_cpu_ptr(&osq_node);
+        struct optimistic_spin_queue *prev, *next;
+
+        node->locked = 0;
+        node->next = NULL;
+
+        node->prev = prev = xchg(lock, node);
+        if (likely(prev == NULL))
+                return true;
+
+        ACCESS_ONCE(prev->next) = node;
+
+        /*
+         * Normally @prev is untouchable after the above store; because at that
+         * moment unlock can proceed and wipe the node element from stack.
+         *
+         * However, since our nodes are static per-cpu storage, we're
+         * guaranteed their existence -- this allows us to apply
+         * cmpxchg in an attempt to undo our queueing.
+         */
+
+        while (!smp_load_acquire(&node->locked)) {
+                /*
+                 * If we need to reschedule bail... so we can block.
+                 */
+                if (need_resched())
+                        goto unqueue;
+
+                arch_mutex_cpu_relax();
+        }
+        return true;
+
+unqueue:
+        /*
+         * Step - A  -- stabilize @prev
+         *
+         * Undo our @prev->next assignment; this will make @prev's
+         * unlock()/unqueue() wait for a next pointer since @lock points to us
+         * (or later).
+         */
+
+        for (;;) {
+                if (prev->next == node &&
+                    cmpxchg(&prev->next, node, NULL) == node)
+                        break;
+
+                /*
+                 * We can only fail the cmpxchg() racing against an unlock(),
+                 * in which case we should observe @node->locked becomming
+                 * true.
+                 */
+                if (smp_load_acquire(&node->locked))
+                        return true;
+
+                arch_mutex_cpu_relax();
+
+                /*
+                 * Or we race against a concurrent unqueue()'s step-B, in which
+                 * case its step-C will write us a new @node->prev pointer.
+                 */
+                prev = ACCESS_ONCE(node->prev);
+        }
+
+        /*
+         * Step - B -- stabilize @next
+         *
+         * Similar to unlock(), wait for @node->next or move @lock from @node
+         * back to @prev.
+         */
+
+        next = osq_wait_next(lock, node, prev);
+        if (!next)
+                return false;
+
+        /*
+         * Step - C -- unlink
+         *
+         * @prev is stable because its still waiting for a new @prev->next
+         * pointer, @next is stable because our @node->next pointer is NULL and
+         * it will wait in Step-A.
+         */
+
+        ACCESS_ONCE(next->prev) = prev;
+        ACCESS_ONCE(prev->next) = next;
+
+        return false;
+}
+
+void osq_unlock(struct optimistic_spin_queue **lock)
+{
+        struct optimistic_spin_queue *node = this_cpu_ptr(&osq_node);
+        struct optimistic_spin_queue *next;
+
+        /*
+         * Fast path for the uncontended case.
+         */
+        if (likely(cmpxchg(lock, node, NULL) == node))
+                return;
+
+        /*
+         * Second most likely case.
+         */
+        next = xchg(&node->next, NULL);
+        if (next) {
+                ACCESS_ONCE(next->locked) = 1;
+                return;
+        }
+
+        next = osq_wait_next(lock, node, NULL);
+        if (next)
+                ACCESS_ONCE(next->locked) = 1;
+}
+
+#endif
+
diff --git a/kernel/locking/mcs_spinlock.h b/kernel/locking/mcs_spinlock.h
new file mode 100644
index 000000000000..a2dbac4aca6b
--- /dev/null
+++ b/kernel/locking/mcs_spinlock.h
@@ -0,0 +1,129 @@
+/*
+ * MCS lock defines
+ *
+ * This file contains the main data structure and API definitions of MCS lock.
+ *
+ * The MCS lock (proposed by Mellor-Crummey and Scott) is a simple spin-lock
+ * with the desirable properties of being fair, and with each cpu trying
+ * to acquire the lock spinning on a local variable.
+ * It avoids expensive cache bouncings that common test-and-set spin-lock
+ * implementations incur.
+ */
+#ifndef __LINUX_MCS_SPINLOCK_H
+#define __LINUX_MCS_SPINLOCK_H
+
+#include <asm/mcs_spinlock.h>
+
+struct mcs_spinlock {
+        struct mcs_spinlock *next;
+        int locked; /* 1 if lock acquired */
+};
+
+#ifndef arch_mcs_spin_lock_contended
+/*
+ * Using smp_load_acquire() provides a memory barrier that ensures
+ * subsequent operations happen after the lock is acquired.
+ */
+#define arch_mcs_spin_lock_contended(l)                                 \
+do {                                                                    \
+        while (!(smp_load_acquire(l)))                                  \
+                arch_mutex_cpu_relax();                                 \
+} while (0)
+#endif
+
+#ifndef arch_mcs_spin_unlock_contended
+/*
+ * smp_store_release() provides a memory barrier to ensure all
+ * operations in the critical section has been completed before
+ * unlocking.
+ */
+#define arch_mcs_spin_unlock_contended(l)                               \
+        smp_store_release((l), 1)
+#endif
+
+/*
+ * Note: the smp_load_acquire/smp_store_release pair is not
+ * sufficient to form a full memory barrier across
+ * cpus for many architectures (except x86) for mcs_unlock and mcs_lock.
+ * For applications that need a full barrier across multiple cpus
+ * with mcs_unlock and mcs_lock pair, smp_mb__after_unlock_lock() should be
+ * used after mcs_lock.
+ */
+
+/*
+ * In order to acquire the lock, the caller should declare a local node and
+ * pass a reference of the node to this function in addition to the lock.
+ * If the lock has already been acquired, then this will proceed to spin
+ * on this node->locked until the previous lock holder sets the node->locked
+ * in mcs_spin_unlock().
+ *
+ * We don't inline mcs_spin_lock() so that perf can correctly account for the
+ * time spent in this lock function.
+ */
+static inline
+void mcs_spin_lock(struct mcs_spinlock **lock, struct mcs_spinlock *node)
+{
+        struct mcs_spinlock *prev;
+
+        /* Init node */
+        node->locked = 0;
+        node->next   = NULL;
+
+        prev = xchg(lock, node);
+        if (likely(prev == NULL)) {
+                /*
+                 * Lock acquired, don't need to set node->locked to 1. Threads
+                 * only spin on its own node->locked value for lock acquisition.
+                 * However, since this thread can immediately acquire the lock
+                 * and does not proceed to spin on its own node->locked, this
+                 * value won't be used. If a debug mode is needed to
+                 * audit lock status, then set node->locked value here.
+                 */
+                return;
+        }
+        ACCESS_ONCE(prev->next) = node;
+
+        /* Wait until the lock holder passes the lock down. */
+        arch_mcs_spin_lock_contended(&node->locked);
+}
+
+/*
+ * Releases the lock. The caller should pass in the corresponding node that
+ * was used to acquire the lock.
+ */
+static inline
+void mcs_spin_unlock(struct mcs_spinlock **lock, struct mcs_spinlock *node)
+{
+        struct mcs_spinlock *next = ACCESS_ONCE(node->next);
+
+        if (likely(!next)) {
+                /*
+                 * Release the lock by setting it to NULL
+                 */
+                if (likely(cmpxchg(lock, node, NULL) == node))
+                        return;
+                /* Wait until the next pointer is set */
+                while (!(next = ACCESS_ONCE(node->next)))
+                        arch_mutex_cpu_relax();
+        }
+
+        /* Pass lock to next waiter. */
+        arch_mcs_spin_unlock_contended(&next->locked);
+}
+
+/*
+ * Cancellable version of the MCS lock above.
+ *
+ * Intended for adaptive spinning of sleeping locks:
+ * mutex_lock()/rwsem_down_{read,write}() etc.
+ */
+
+struct optimistic_spin_queue {
+        struct optimistic_spin_queue *next, *prev;
+        int locked; /* 1 if lock acquired */
+};
+
+extern bool osq_lock(struct optimistic_spin_queue **lock);
+extern void osq_unlock(struct optimistic_spin_queue **lock);
+
+#endif /* __LINUX_MCS_SPINLOCK_H */
diff --git a/kernel/locking/mutex-debug.c b/kernel/locking/mutex-debug.c
index faf6f5b53e77..e1191c996c59 100644
--- a/kernel/locking/mutex-debug.c
+++ b/kernel/locking/mutex-debug.c
@@ -83,6 +83,12 @@ void debug_mutex_unlock(struct mutex *lock)
 
         DEBUG_LOCKS_WARN_ON(!lock->wait_list.prev && !lock->wait_list.next);
         mutex_clear_owner(lock);
+
+        /*
+         * __mutex_slowpath_needs_to_unlock() is explicitly 0 for debug
+         * mutexes so that we can do it here after we've verified state.
+         */
+        atomic_set(&lock->count, 1);
 }
 
 void debug_mutex_init(struct mutex *lock, const char *name,
diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c
index 4dd6e4c219de..bc73d33c6760 100644
--- a/kernel/locking/mutex.c
+++ b/kernel/locking/mutex.c
@@ -25,6 +25,7 @@
 #include <linux/spinlock.h>
 #include <linux/interrupt.h>
 #include <linux/debug_locks.h>
+#include "mcs_spinlock.h"
 
 /*
  * In the DEBUG case we are using the "NULL fastpath" for mutexes,
@@ -33,6 +34,13 @@
 #ifdef CONFIG_DEBUG_MUTEXES
 # include "mutex-debug.h"
 # include <asm-generic/mutex-null.h>
+/*
+ * Must be 0 for the debug case so we do not do the unlock outside of the
+ * wait_lock region. debug_mutex_unlock() will do the actual unlock in this
+ * case.
+ */
+# undef __mutex_slowpath_needs_to_unlock
+# define  __mutex_slowpath_needs_to_unlock()    0
 #else
 # include "mutex.h"
 # include <asm/mutex.h>
@@ -52,7 +60,7 @@ __mutex_init(struct mutex *lock, const char *name, struct lock_class_key *key)
         INIT_LIST_HEAD(&lock->wait_list);
         mutex_clear_owner(lock);
 #ifdef CONFIG_MUTEX_SPIN_ON_OWNER
-        lock->spin_mlock = NULL;
+        lock->osq = NULL;
 #endif
 
         debug_mutex_init(lock, name, key);
@@ -67,8 +75,7 @@ EXPORT_SYMBOL(__mutex_init);
  * We also put the fastpath first in the kernel image, to make sure the
  * branch is predicted by the CPU as default-untaken.
  */
-static __used noinline void __sched
-__mutex_lock_slowpath(atomic_t *lock_count);
+__visible void __sched __mutex_lock_slowpath(atomic_t *lock_count);
 
 /**
  * mutex_lock - acquire the mutex
@@ -111,54 +118,7 @@ EXPORT_SYMBOL(mutex_lock);
  * more or less simultaneously, the spinners need to acquire a MCS lock
  * first before spinning on the owner field.
  *
- * We don't inline mspin_lock() so that perf can correctly account for the
- * time spent in this lock function.
  */
-struct mspin_node {
-        struct mspin_node *next ;
-        int               locked;       /* 1 if lock acquired */
-};
-#define MLOCK(mutex)    ((struct mspin_node **)&((mutex)->spin_mlock))
-
-static noinline
-void mspin_lock(struct mspin_node **lock, struct mspin_node *node)
-{
-        struct mspin_node *prev;
-
-        /* Init node */
-        node->locked = 0;
-        node->next   = NULL;
-
-        prev = xchg(lock, node);
-        if (likely(prev == NULL)) {
-                /* Lock acquired */
-                node->locked = 1;
-                return;
-        }
-        ACCESS_ONCE(prev->next) = node;
-        smp_wmb();
-        /* Wait until the lock holder passes the lock down */
-        while (!ACCESS_ONCE(node->locked))
-                arch_mutex_cpu_relax();
-}
-
-static void mspin_unlock(struct mspin_node **lock, struct mspin_node *node)
-{
-        struct mspin_node *next = ACCESS_ONCE(node->next);
-
-        if (likely(!next)) {
-                /*
-                 * Release the lock by setting it to NULL
-                 */
-                if (cmpxchg(lock, node, NULL) == node)
-                        return;
-                /* Wait until the next pointer is set */
-                while (!(next = ACCESS_ONCE(node->next)))
-                        arch_mutex_cpu_relax();
-        }
-        ACCESS_ONCE(next->locked) = 1;
-        smp_wmb();
-}
 
 /*
  * Mutex spinning code migrated from kernel/sched/core.c
@@ -212,6 +172,9 @@ static inline int mutex_can_spin_on_owner(struct mutex *lock)
         struct task_struct *owner;
         int retval = 1;
 
+        if (need_resched())
+                return 0;
+
         rcu_read_lock();
         owner = ACCESS_ONCE(lock->owner);
         if (owner)
@@ -225,7 +188,8 @@ static inline int mutex_can_spin_on_owner(struct mutex *lock)
 }
 #endif
 
-static __used noinline void __sched __mutex_unlock_slowpath(atomic_t *lock_count);
+__visible __used noinline
+void __sched __mutex_unlock_slowpath(atomic_t *lock_count);
 
 /**
  * mutex_unlock - release the mutex
@@ -446,9 +410,11 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
         if (!mutex_can_spin_on_owner(lock))
                 goto slowpath;
 
+        if (!osq_lock(&lock->osq))
+                goto slowpath;
+
         for (;;) {
                 struct task_struct *owner;
-                struct mspin_node  node;
 
                 if (use_ww_ctx && ww_ctx->acquired > 0) {
                         struct ww_mutex *ww;
@@ -463,19 +429,16 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
                          * performed the optimistic spinning cannot be done.
                          */
                         if (ACCESS_ONCE(ww->ctx))
-                                goto slowpath;
+                                break;
                 }
 
                 /*
                  * If there's an owner, wait for it to either
                  * release the lock or go to sleep.
                  */
-                mspin_lock(MLOCK(lock), &node);
                 owner = ACCESS_ONCE(lock->owner);
-                if (owner && !mutex_spin_on_owner(lock, owner)) {
-                        mspin_unlock(MLOCK(lock), &node);
-                        goto slowpath;
-                }
+                if (owner && !mutex_spin_on_owner(lock, owner))
+                        break;
 
                 if ((atomic_read(&lock->count) == 1) &&
                     (atomic_cmpxchg(&lock->count, 1, 0) == 1)) {
@@ -488,11 +451,10 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
                         }
 
                         mutex_set_owner(lock);
-                        mspin_unlock(MLOCK(lock), &node);
+                        osq_unlock(&lock->osq);
                         preempt_enable();
                         return 0;
                 }
-                mspin_unlock(MLOCK(lock), &node);
 
                 /*
                  * When there's no owner, we might have preempted between the
@@ -501,7 +463,7 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
                  * the owner complete.
                  */
                 if (!owner && (need_resched() || rt_task(task)))
-                        goto slowpath;
+                        break;
 
                 /*
                  * The cpu_relax() call is a compiler barrier which forces
@@ -511,7 +473,15 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
                  */
                 arch_mutex_cpu_relax();
         }
+        osq_unlock(&lock->osq);
 slowpath:
+        /*
+         * If we fell out of the spin path because of need_resched(),
+         * reschedule now, before we try-lock the mutex. This avoids getting
+         * scheduled out right after we obtained the mutex.
+         */
+        if (need_resched())
+                schedule_preempt_disabled();
 #endif
         spin_lock_mutex(&lock->wait_lock, flags);
 
@@ -717,10 +687,6 @@ __mutex_unlock_common_slowpath(atomic_t *lock_count, int nested)
         struct mutex *lock = container_of(lock_count, struct mutex, count);
         unsigned long flags;
 
-        spin_lock_mutex(&lock->wait_lock, flags);
-        mutex_release(&lock->dep_map, nested, _RET_IP_);
-        debug_mutex_unlock(lock);
-
         /*
          * some architectures leave the lock unlocked in the fastpath failure
          * case, others need to leave it locked. In the later case we have to
@@ -729,6 +695,10 @@ __mutex_unlock_common_slowpath(atomic_t *lock_count, int nested)
         if (__mutex_slowpath_needs_to_unlock())
                 atomic_set(&lock->count, 1);
 
+        spin_lock_mutex(&lock->wait_lock, flags);
+        mutex_release(&lock->dep_map, nested, _RET_IP_);
+        debug_mutex_unlock(lock);
+
         if (!list_empty(&lock->wait_list)) {
                 /* get the first entry from the wait-list: */
                 struct mutex_waiter *waiter =
@@ -746,7 +716,7 @@ __mutex_unlock_common_slowpath(atomic_t *lock_count, int nested)
 /*
  * Release the lock, slowpath:
  */
-static __used noinline void
+__visible void
 __mutex_unlock_slowpath(atomic_t *lock_count)
 {
         __mutex_unlock_common_slowpath(lock_count, 1);
@@ -803,7 +773,7 @@ int __sched mutex_lock_killable(struct mutex *lock)
 }
 EXPORT_SYMBOL(mutex_lock_killable);
 
-static __used noinline void __sched
+__visible void __sched
 __mutex_lock_slowpath(atomic_t *lock_count)
 {
         struct mutex *lock = container_of(lock_count, struct mutex, count);
diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
index 2e960a2bab81..aa4dff04b594 100644
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -213,6 +213,18 @@ struct task_struct *rt_mutex_get_top_task(struct task_struct *task)
 }
 
 /*
+ * Called by sched_setscheduler() to check whether the priority change
+ * is overruled by a possible priority boosting.
+ */
+int rt_mutex_check_prio(struct task_struct *task, int newprio)
+{
+        if (!task_has_pi_waiters(task))
+                return 0;
+
+        return task_top_pi_waiter(task)->task->prio <= newprio;
+}
+
+/*
  * Adjust the priority of a task, after its pi_waiters got modified.
  *
  * This can be both boosting and unboosting. task->pi_lock must be held.
diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c
index 19c5fa95e0b4..1d66e08e897d 100644
--- a/kernel/locking/rwsem-xadd.c
+++ b/kernel/locking/rwsem-xadd.c
@@ -143,6 +143,7 @@ __rwsem_do_wake(struct rw_semaphore *sem, enum rwsem_wake_type wake_type)
 /*
  * wait for the read lock to be granted
  */
+__visible
 struct rw_semaphore __sched *rwsem_down_read_failed(struct rw_semaphore *sem)
 {
         long count, adjustment = -RWSEM_ACTIVE_READ_BIAS;
@@ -190,6 +191,7 @@ struct rw_semaphore __sched *rwsem_down_read_failed(struct rw_semaphore *sem)
 /*
  * wait until we successfully acquire the write lock
  */
+__visible
 struct rw_semaphore __sched *rwsem_down_write_failed(struct rw_semaphore *sem)
 {
         long count, adjustment = -RWSEM_ACTIVE_WRITE_BIAS;
@@ -252,6 +254,7 @@ struct rw_semaphore __sched *rwsem_down_write_failed(struct rw_semaphore *sem)
  * handle waking up a waiter on the semaphore
  * - up_read/up_write has decremented the active part of count if we come here
  */
+__visible
 struct rw_semaphore *rwsem_wake(struct rw_semaphore *sem)
 {
         unsigned long flags;
@@ -272,6 +275,7 @@ struct rw_semaphore *rwsem_wake(struct rw_semaphore *sem)
  * - caller incremented waiting part of count and discovered it still negative
  * - just wake up any readers at the front of the queue
  */
+__visible
 struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem)
 {
         unsigned long flags;
diff --git a/kernel/module.c b/kernel/module.c
index d24fcf29cb64..29f7790eaa14 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -1013,9 +1013,11 @@ static size_t module_flags_taint(struct module *mod, char *buf)
                 buf[l++] = 'F';
         if (mod->taints & (1 << TAINT_CRAP))
                 buf[l++] = 'C';
+        if (mod->taints & (1 << TAINT_UNSIGNED_MODULE))
+                buf[l++] = 'E';
         /*
          * TAINT_FORCED_RMMOD: could be added.
-         * TAINT_UNSAFE_SMP, TAINT_MACHINE_CHECK, TAINT_BAD_PAGE don't
+         * TAINT_CPU_OUT_OF_SPEC, TAINT_MACHINE_CHECK, TAINT_BAD_PAGE don't
          * apply to modules.
          */
         return l;
@@ -1948,6 +1950,10 @@ static int simplify_symbols(struct module *mod, const struct load_info *info)
 
                 switch (sym[i].st_shndx) {
                 case SHN_COMMON:
+                        /* Ignore common symbols */
+                        if (!strncmp(name, "__gnu_lto", 9))
+                                break;
+
                         /* We compiled with -fno-common.  These are not
                            supposed to happen.  */
                         pr_debug("Common symbol: %s\n", name);
@@ -3214,7 +3220,7 @@ static int load_module(struct load_info *info, const char __user *uargs,
                 pr_notice_once("%s: module verification failed: signature "
                                "and/or  required key missing - tainting "
                                "kernel\n", mod->name);
-                add_taint_module(mod, TAINT_FORCED_MODULE, LOCKDEP_STILL_OK);
+                add_taint_module(mod, TAINT_UNSIGNED_MODULE, LOCKDEP_STILL_OK);
         }
 #endif
 
@@ -3809,12 +3815,12 @@ void print_modules(void)
         list_for_each_entry_rcu(mod, &modules, list) {
                 if (mod->state == MODULE_STATE_UNFORMED)
                         continue;
-                printk(" %s%s", mod->name, module_flags(mod, buf));
+                pr_cont(" %s%s", mod->name, module_flags(mod, buf));
         }
         preempt_enable();
         if (last_unloaded_module[0])
-                printk(" [last unloaded: %s]", last_unloaded_module);
-        printk("\n");
+                pr_cont(" [last unloaded: %s]", last_unloaded_module);
+        pr_cont("\n");
 }
 
 #ifdef CONFIG_MODVERSIONS
diff --git a/kernel/notifier.c b/kernel/notifier.c
index 2d5cc4ccff7f..db4c8b08a50c 100644
--- a/kernel/notifier.c
+++ b/kernel/notifier.c
@@ -309,7 +309,7 @@ int __blocking_notifier_call_chain(struct blocking_notifier_head *nh,
          * racy then it does not matter what the result of the test
          * is, we re-check the list after having taken the lock anyway:
          */
-        if (rcu_dereference_raw(nh->head)) {
+        if (rcu_access_pointer(nh->head)) {
                 down_read(&nh->rwsem);
                 ret = notifier_call_chain(&nh->head, val, v, nr_to_call,
                                         nr_calls);
diff --git a/kernel/panic.c b/kernel/panic.c
index 6d6300375090..79fd820bb5e8 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -199,7 +199,7 @@ struct tnt {
 static const struct tnt tnts[] = {
         { TAINT_PROPRIETARY_MODULE,     'P', 'G' },
         { TAINT_FORCED_MODULE,          'F', ' ' },
-        { TAINT_UNSAFE_SMP,             'S', ' ' },
+        { TAINT_CPU_OUT_OF_SPEC,        'S', ' ' },
         { TAINT_FORCED_RMMOD,           'R', ' ' },
         { TAINT_MACHINE_CHECK,          'M', ' ' },
         { TAINT_BAD_PAGE,               'B', ' ' },
@@ -210,6 +210,7 @@ static const struct tnt tnts[] = {
         { TAINT_CRAP,                   'C', ' ' },
         { TAINT_FIRMWARE_WORKAROUND,    'I', ' ' },
         { TAINT_OOT_MODULE,             'O', ' ' },
+        { TAINT_UNSIGNED_MODULE,        'E', ' ' },
 };
 
 /**
@@ -228,6 +229,7 @@ static const struct tnt tnts[] = {
  *  'C' - modules from drivers/staging are loaded.
  *  'I' - Working around severe firmware bug.
  *  'O' - Out-of-tree module has been loaded.
+ *  'E' - Unsigned module has been loaded.
  *
  *      The string is overwritten by the next call to print_tainted().
  */
@@ -459,7 +461,7 @@ EXPORT_SYMBOL(warn_slowpath_null);
  * Called when gcc's -fstack-protector feature is used, and
  * gcc detects corruption of the on-stack canary value
  */
-void __stack_chk_fail(void)
+__visible void __stack_chk_fail(void)
 {
         panic("stack-protector: Kernel stack is corrupted in: %p\n",
                 __builtin_return_address(0));
diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c
index 06c62de9c711..db95d8eb761b 100644
--- a/kernel/pid_namespace.c
+++ b/kernel/pid_namespace.c
@@ -318,7 +318,9 @@ static void *pidns_get(struct task_struct *task)
         struct pid_namespace *ns;
 
         rcu_read_lock();
-        ns = get_pid_ns(task_active_pid_ns(task));
+        ns = task_active_pid_ns(task);
+        if (ns)
+                get_pid_ns(ns);
         rcu_read_unlock();
 
         return ns;
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index 37170d4dd9a6..f4f2073711d3 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -973,16 +973,20 @@ static ssize_t resume_show(struct kobject *kobj, struct kobj_attribute *attr,
 static ssize_t resume_store(struct kobject *kobj, struct kobj_attribute *attr,
                             const char *buf, size_t n)
 {
-        unsigned int maj, min;
         dev_t res;
-        int ret = -EINVAL;
+        int len = n;
+        char *name;
 
-        if (sscanf(buf, "%u:%u", &maj, &min) != 2)
-                goto out;
+        if (len && buf[len-1] == '\n')
+                len--;
+        name = kstrndup(buf, len, GFP_KERNEL);
+        if (!name)
+                return -ENOMEM;
 
-        res = MKDEV(maj,min);
-        if (maj != MAJOR(res) || min != MINOR(res))
-                goto out;
+        res = name_to_dev_t(name);
+        kfree(name);
+        if (!res)
+                return -EINVAL;
 
         lock_system_sleep();
         swsusp_resume_device = res;
@@ -990,9 +994,7 @@ static ssize_t resume_store(struct kobject *kobj, struct kobj_attribute *attr,
         printk(KERN_INFO "PM: Starting manual resume from disk\n");
         noresume = 0;
         software_resume();
-        ret = n;
- out:
-        return ret;
+        return n;
 }
 
 power_attr(resume);
diff --git a/kernel/power/main.c b/kernel/power/main.c
index 1d1bf630e6e9..6271bc4073ef 100644
--- a/kernel/power/main.c
+++ b/kernel/power/main.c
@@ -282,8 +282,8 @@ struct kobject *power_kobj;
  *      state - control system power state.
  *
  *      show() returns what states are supported, which is hard-coded to
- *      'standby' (Power-On Suspend), 'mem' (Suspend-to-RAM), and
- *      'disk' (Suspend-to-Disk).
+ *      'freeze' (Low-Power Idle), 'standby' (Power-On Suspend),
+ *      'mem' (Suspend-to-RAM), and 'disk' (Suspend-to-Disk).
  *
  *      store() accepts one of those strings, translates it into the
  *      proper enumerated value, and initiates a suspend transition.
diff --git a/kernel/power/power.h b/kernel/power/power.h
index 7d4b7ffb3c1d..1ca753106557 100644
--- a/kernel/power/power.h
+++ b/kernel/power/power.h
@@ -49,6 +49,8 @@ static inline char *check_image_kernel(struct swsusp_info *info)
  */
 #define SPARE_PAGES     ((1024 * 1024) >> PAGE_SHIFT)
 
+asmlinkage int swsusp_save(void);
+
 /* kernel/power/hibernate.c */
 extern bool freezer_test_done;
 
diff --git a/kernel/power/qos.c b/kernel/power/qos.c
index 8dff9b48075a..884b77058864 100644
--- a/kernel/power/qos.c
+++ b/kernel/power/qos.c
@@ -66,6 +66,7 @@ static struct pm_qos_constraints cpu_dma_constraints = {
         .list = PLIST_HEAD_INIT(cpu_dma_constraints.list),
         .target_value = PM_QOS_CPU_DMA_LAT_DEFAULT_VALUE,
         .default_value = PM_QOS_CPU_DMA_LAT_DEFAULT_VALUE,
+        .no_constraint_value = PM_QOS_CPU_DMA_LAT_DEFAULT_VALUE,
         .type = PM_QOS_MIN,
         .notifiers = &cpu_dma_lat_notifier,
 };
@@ -79,6 +80,7 @@ static struct pm_qos_constraints network_lat_constraints = {
         .list = PLIST_HEAD_INIT(network_lat_constraints.list),
         .target_value = PM_QOS_NETWORK_LAT_DEFAULT_VALUE,
         .default_value = PM_QOS_NETWORK_LAT_DEFAULT_VALUE,
+        .no_constraint_value = PM_QOS_NETWORK_LAT_DEFAULT_VALUE,
         .type = PM_QOS_MIN,
         .notifiers = &network_lat_notifier,
 };
@@ -93,6 +95,7 @@ static struct pm_qos_constraints network_tput_constraints = {
         .list = PLIST_HEAD_INIT(network_tput_constraints.list),
         .target_value = PM_QOS_NETWORK_THROUGHPUT_DEFAULT_VALUE,
         .default_value = PM_QOS_NETWORK_THROUGHPUT_DEFAULT_VALUE,
+        .no_constraint_value = PM_QOS_NETWORK_THROUGHPUT_DEFAULT_VALUE,
         .type = PM_QOS_MAX,
         .notifiers = &network_throughput_notifier,
 };
@@ -128,7 +131,7 @@ static const struct file_operations pm_qos_power_fops = {
 static inline int pm_qos_get_value(struct pm_qos_constraints *c)
 {
         if (plist_head_empty(&c->list))
-                return c->default_value;
+                return c->no_constraint_value;
 
         switch (c->type) {
         case PM_QOS_MIN:
@@ -170,6 +173,7 @@ int pm_qos_update_target(struct pm_qos_constraints *c, struct plist_node *node,
 {
         unsigned long flags;
         int prev_value, curr_value, new_value;
+        int ret;
 
         spin_lock_irqsave(&pm_qos_lock, flags);
         prev_value = pm_qos_get_value(c);
@@ -205,13 +209,15 @@ int pm_qos_update_target(struct pm_qos_constraints *c, struct plist_node *node,
 
         trace_pm_qos_update_target(action, prev_value, curr_value);
         if (prev_value != curr_value) {
-                blocking_notifier_call_chain(c->notifiers,
-                                             (unsigned long)curr_value,
-                                             NULL);
-                return 1;
+                ret = 1;
+                if (c->notifiers)
+                        blocking_notifier_call_chain(c->notifiers,
+                                                     (unsigned long)curr_value,
+                                                     NULL);
         } else {
-                return 0;
+                ret = 0;
         }
+        return ret;
 }
 
 /**
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index d9f61a145802..149e745eaa52 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -1268,7 +1268,7 @@ static void free_unnecessary_pages(void)
  * [number of saveable pages] - [number of pages that can be freed in theory]
  *
  * where the second term is the sum of (1) reclaimable slab pages, (2) active
- * and (3) inactive anonymouns pages, (4) active and (5) inactive file pages,
+ * and (3) inactive anonymous pages, (4) active and (5) inactive file pages,
  * minus mapped file pages.
  */
 static unsigned long minimum_image_size(unsigned long saveable)
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index 62ee437b5c7e..90b3d9366d1a 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -39,7 +39,7 @@ static const struct platform_suspend_ops *suspend_ops;
 
 static bool need_suspend_ops(suspend_state_t state)
 {
-        return !!(state > PM_SUSPEND_FREEZE);
+        return state > PM_SUSPEND_FREEZE;
 }
 
 static DECLARE_WAIT_QUEUE_HEAD(suspend_freeze_wait_head);
diff --git a/kernel/power/wakelock.c b/kernel/power/wakelock.c
index 8f50de394d22..019069c84ff6 100644
--- a/kernel/power/wakelock.c
+++ b/kernel/power/wakelock.c
@@ -18,6 +18,8 @@
 #include <linux/rbtree.h>
 #include <linux/slab.h>
 
+#include "power.h"
+
 static DEFINE_MUTEX(wakelocks_lock);
 
 struct wakelock {
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index 4dae9cbe9259..a45b50962295 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -319,7 +319,7 @@ static void log_store(int facility, int level,
                 else
                         free = log_first_idx - log_next_idx;
 
-                if (free > size + sizeof(struct printk_log))
+                if (free >= size + sizeof(struct printk_log))
                         break;
 
                 /* drop old messages until we have enough contiuous space */
@@ -327,7 +327,7 @@ static void log_store(int facility, int level,
                 log_first_seq++;
         }
 
-        if (log_next_idx + size + sizeof(struct printk_log) >= log_buf_len) {
+        if (log_next_idx + size + sizeof(struct printk_log) > log_buf_len) {
                 /*
                  * This message + an additional empty header does not fit
                  * at the end of the buffer. Add an empty header with len == 0
@@ -351,7 +351,7 @@ static void log_store(int facility, int level,
         else
                 msg->ts_nsec = local_clock();
         memset(log_dict(msg) + dict_len, 0, pad_len);
-        msg->len = sizeof(struct printk_log) + text_len + dict_len + pad_len;
+        msg->len = size;
 
         /* insert message */
         log_next_idx += msg->len;
@@ -1560,9 +1560,12 @@ asmlinkage int vprintk_emit(int facility, int level,
                                         level = kern_level - '0';
                         case 'd':       /* KERN_DEFAULT */
                                 lflags |= LOG_PREFIX;
-                        case 'c':       /* KERN_CONT */
-                                break;
                         }
+                        /*
+                         * No need to check length here because vscnprintf
+                         * put '\0' at the end of the string. Only valid and
+                         * newly printed level is detected.
+                         */
                         text_len -= end_of_header - text;
                         text = (char *)end_of_header;
                 }
@@ -1880,6 +1883,7 @@ void suspend_console(void)
         console_lock();
         console_suspended = 1;
         up(&console_sem);
+        mutex_release(&console_lock_dep_map, 1, _RET_IP_);
 }
 
 void resume_console(void)
@@ -1887,6 +1891,7 @@ void resume_console(void)
         if (!console_suspend_enabled)
                 return;
         down(&console_sem);
+        mutex_acquire(&console_lock_dep_map, 0, 0, _RET_IP_);
         console_suspended = 0;
         console_unlock();
 }
diff --git a/kernel/profile.c b/kernel/profile.c
index 93b2a3fe0a64..cb980f0c731b 100644
--- a/kernel/profile.c
+++ b/kernel/profile.c
@@ -614,5 +614,5 @@ out:
         cpu_notifier_register_done();
         return err;
 }
-module_init(create_proc_profile);
+subsys_initcall(create_proc_profile);
 #endif /* CONFIG_PROC_FS */
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 1f4bcb3cc21c..adf98622cb32 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -1180,8 +1180,8 @@ int compat_ptrace_request(struct task_struct *child, compat_long_t request,
         return ret;
 }
 
-asmlinkage long compat_sys_ptrace(compat_long_t request, compat_long_t pid,
-                                  compat_long_t addr, compat_long_t data)
+COMPAT_SYSCALL_DEFINE4(ptrace, compat_long_t, request, compat_long_t, pid,
+                       compat_long_t, addr, compat_long_t, data)
 {
         struct task_struct *child;
         long ret;
diff --git a/kernel/rcu/Makefile b/kernel/rcu/Makefile
index 01e9ec37a3e3..807ccfbf69b3 100644
--- a/kernel/rcu/Makefile
+++ b/kernel/rcu/Makefile
@@ -1,5 +1,5 @@
 obj-y += update.o srcu.o
-obj-$(CONFIG_RCU_TORTURE_TEST) += torture.o
+obj-$(CONFIG_RCU_TORTURE_TEST) += rcutorture.o
 obj-$(CONFIG_TREE_RCU) += tree.o
 obj-$(CONFIG_TREE_PREEMPT_RCU) += tree.o
 obj-$(CONFIG_TREE_RCU_TRACE) += tree_trace.o
diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h
index 79c3877e9c5b..bfda2726ca45 100644
--- a/kernel/rcu/rcu.h
+++ b/kernel/rcu/rcu.h
@@ -12,8 +12,8 @@
  * GNU General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ * along with this program; if not, you can access it online at
+ * http://www.gnu.org/licenses/gpl-2.0.html.
  *
  * Copyright IBM Corporation, 2011
  *
@@ -23,6 +23,7 @@
 #ifndef __LINUX_RCU_H
 #define __LINUX_RCU_H
 
+#include <trace/events/rcu.h>
 #ifdef CONFIG_RCU_TRACE
 #define RCU_TRACE(stmt) stmt
 #else /* #ifdef CONFIG_RCU_TRACE */
@@ -116,8 +117,6 @@ static inline bool __rcu_reclaim(const char *rn, struct rcu_head *head)
         }
 }
 
-extern int rcu_expedited;
-
 #ifdef CONFIG_RCU_STALL_COMMON
 
 extern int rcu_cpu_stall_suppress;
diff --git a/kernel/rcu/torture.c b/kernel/rcu/rcutorture.c
index 732f8ae3086a..bd30bc61bc05 100644
--- a/kernel/rcu/torture.c
+++ b/kernel/rcu/rcutorture.c
@@ -12,8 +12,8 @@
  * GNU General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ * along with this program; if not, you can access it online at
+ * http://www.gnu.org/licenses/gpl-2.0.html.
  *
  * Copyright (C) IBM Corporation, 2005, 2006
  *
@@ -48,110 +48,58 @@
 #include <linux/slab.h>
 #include <linux/trace_clock.h>
 #include <asm/byteorder.h>
+#include <linux/torture.h>
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Paul E. McKenney <paulmck@us.ibm.com> and Josh Triplett <josh@freedesktop.org>");
 
-MODULE_ALIAS("rcutorture");
-#ifdef MODULE_PARAM_PREFIX
-#undef MODULE_PARAM_PREFIX
-#endif
-#define MODULE_PARAM_PREFIX "rcutorture."
-
-static int fqs_duration;
-module_param(fqs_duration, int, 0444);
-MODULE_PARM_DESC(fqs_duration, "Duration of fqs bursts (us), 0 to disable");
-static int fqs_holdoff;
-module_param(fqs_holdoff, int, 0444);
-MODULE_PARM_DESC(fqs_holdoff, "Holdoff time within fqs bursts (us)");
-static int fqs_stutter = 3;
-module_param(fqs_stutter, int, 0444);
-MODULE_PARM_DESC(fqs_stutter, "Wait time between fqs bursts (s)");
-static bool gp_exp;
-module_param(gp_exp, bool, 0444);
-MODULE_PARM_DESC(gp_exp, "Use expedited GP wait primitives");
-static bool gp_normal;
-module_param(gp_normal, bool, 0444);
-MODULE_PARM_DESC(gp_normal, "Use normal (non-expedited) GP wait primitives");
-static int irqreader = 1;
-module_param(irqreader, int, 0444);
-MODULE_PARM_DESC(irqreader, "Allow RCU readers from irq handlers");
-static int n_barrier_cbs;
-module_param(n_barrier_cbs, int, 0444);
-MODULE_PARM_DESC(n_barrier_cbs, "# of callbacks/kthreads for barrier testing");
-static int nfakewriters = 4;
-module_param(nfakewriters, int, 0444);
-MODULE_PARM_DESC(nfakewriters, "Number of RCU fake writer threads");
-static int nreaders = -1;
-module_param(nreaders, int, 0444);
-MODULE_PARM_DESC(nreaders, "Number of RCU reader threads");
-static int object_debug;
-module_param(object_debug, int, 0444);
-MODULE_PARM_DESC(object_debug, "Enable debug-object double call_rcu() testing");
-static int onoff_holdoff;
-module_param(onoff_holdoff, int, 0444);
-MODULE_PARM_DESC(onoff_holdoff, "Time after boot before CPU hotplugs (s)");
-static int onoff_interval;
-module_param(onoff_interval, int, 0444);
-MODULE_PARM_DESC(onoff_interval, "Time between CPU hotplugs (s), 0=disable");
-static int shuffle_interval = 3;
-module_param(shuffle_interval, int, 0444);
-MODULE_PARM_DESC(shuffle_interval, "Number of seconds between shuffles");
-static int shutdown_secs;
-module_param(shutdown_secs, int, 0444);
-MODULE_PARM_DESC(shutdown_secs, "Shutdown time (s), <= zero to disable.");
-static int stall_cpu;
-module_param(stall_cpu, int, 0444);
-MODULE_PARM_DESC(stall_cpu, "Stall duration (s), zero to disable.");
-static int stall_cpu_holdoff = 10;
-module_param(stall_cpu_holdoff, int, 0444);
-MODULE_PARM_DESC(stall_cpu_holdoff, "Time to wait before starting stall (s).");
-static int stat_interval = 60;
-module_param(stat_interval, int, 0644);
-MODULE_PARM_DESC(stat_interval, "Number of seconds between stats printk()s");
-static int stutter = 5;
-module_param(stutter, int, 0444);
-MODULE_PARM_DESC(stutter, "Number of seconds to run/halt test");
-static int test_boost = 1;
-module_param(test_boost, int, 0444);
-MODULE_PARM_DESC(test_boost, "Test RCU prio boost: 0=no, 1=maybe, 2=yes.");
-static int test_boost_duration = 4;
-module_param(test_boost_duration, int, 0444);
-MODULE_PARM_DESC(test_boost_duration, "Duration of each boost test, seconds.");
-static int test_boost_interval = 7;
-module_param(test_boost_interval, int, 0444);
-MODULE_PARM_DESC(test_boost_interval, "Interval between boost tests, seconds.");
-static bool test_no_idle_hz = true;
-module_param(test_no_idle_hz, bool, 0444);
-MODULE_PARM_DESC(test_no_idle_hz, "Test support for tickless idle CPUs");
+
+torture_param(int, fqs_duration, 0,
+              "Duration of fqs bursts (us), 0 to disable");
+torture_param(int, fqs_holdoff, 0, "Holdoff time within fqs bursts (us)");
+torture_param(int, fqs_stutter, 3, "Wait time between fqs bursts (s)");
+torture_param(bool, gp_exp, false, "Use expedited GP wait primitives");
+torture_param(bool, gp_normal, false,
+             "Use normal (non-expedited) GP wait primitives");
+torture_param(int, irqreader, 1, "Allow RCU readers from irq handlers");
+torture_param(int, n_barrier_cbs, 0,
+             "# of callbacks/kthreads for barrier testing");
+torture_param(int, nfakewriters, 4, "Number of RCU fake writer threads");
+torture_param(int, nreaders, -1, "Number of RCU reader threads");
+torture_param(int, object_debug, 0,
+             "Enable debug-object double call_rcu() testing");
+torture_param(int, onoff_holdoff, 0, "Time after boot before CPU hotplugs (s)");
+torture_param(int, onoff_interval, 0,
+             "Time between CPU hotplugs (s), 0=disable");
+torture_param(int, shuffle_interval, 3, "Number of seconds between shuffles");
+torture_param(int, shutdown_secs, 0, "Shutdown time (s), <= zero to disable.");
+torture_param(int, stall_cpu, 0, "Stall duration (s), zero to disable.");
+torture_param(int, stall_cpu_holdoff, 10,
+             "Time to wait before starting stall (s).");
+torture_param(int, stat_interval, 60,
+             "Number of seconds between stats printk()s");
+torture_param(int, stutter, 5, "Number of seconds to run/halt test");
+torture_param(int, test_boost, 1, "Test RCU prio boost: 0=no, 1=maybe, 2=yes.");
+torture_param(int, test_boost_duration, 4,
+             "Duration of each boost test, seconds.");
+torture_param(int, test_boost_interval, 7,
+             "Interval between boost tests, seconds.");
+torture_param(bool, test_no_idle_hz, true,
+             "Test support for tickless idle CPUs");
+torture_param(bool, verbose, true,
+             "Enable verbose debugging printk()s");
+
 static char *torture_type = "rcu";
 module_param(torture_type, charp, 0444);
 MODULE_PARM_DESC(torture_type, "Type of RCU to torture (rcu, rcu_bh, ...)");
-static bool verbose;
-module_param(verbose, bool, 0444);
-MODULE_PARM_DESC(verbose, "Enable verbose debugging printk()s");
-
-#define TORTURE_FLAG "-torture:"
-#define PRINTK_STRING(s) \
-        do { pr_alert("%s" TORTURE_FLAG s "\n", torture_type); } while (0)
-#define VERBOSE_PRINTK_STRING(s) \
-        do { if (verbose) pr_alert("%s" TORTURE_FLAG s "\n", torture_type); } while (0)
-#define VERBOSE_PRINTK_ERRSTRING(s) \
-        do { if (verbose) pr_alert("%s" TORTURE_FLAG "!!! " s "\n", torture_type); } while (0)
 
 static int nrealreaders;
 static struct task_struct *writer_task;
 static struct task_struct **fakewriter_tasks;
 static struct task_struct **reader_tasks;
 static struct task_struct *stats_task;
-static struct task_struct *shuffler_task;
-static struct task_struct *stutter_task;
 static struct task_struct *fqs_task;
 static struct task_struct *boost_tasks[NR_CPUS];
-static struct task_struct *shutdown_task;
-#ifdef CONFIG_HOTPLUG_CPU
-static struct task_struct *onoff_task;
-#endif /* #ifdef CONFIG_HOTPLUG_CPU */
 static struct task_struct *stall_task;
 static struct task_struct **barrier_cbs_tasks;
 static struct task_struct *barrier_task;
@@ -170,10 +118,10 @@ static struct rcu_torture __rcu *rcu_torture_current;
 static unsigned long rcu_torture_current_version;
 static struct rcu_torture rcu_tortures[10 * RCU_TORTURE_PIPE_LEN];
 static DEFINE_SPINLOCK(rcu_torture_lock);
-static DEFINE_PER_CPU(long [RCU_TORTURE_PIPE_LEN + 1], rcu_torture_count) =
-        { 0 };
-static DEFINE_PER_CPU(long [RCU_TORTURE_PIPE_LEN + 1], rcu_torture_batch) =
-        { 0 };
+static DEFINE_PER_CPU(long [RCU_TORTURE_PIPE_LEN + 1],
+                      rcu_torture_count) = { 0 };
+static DEFINE_PER_CPU(long [RCU_TORTURE_PIPE_LEN + 1],
+                      rcu_torture_batch) = { 0 };
 static atomic_t rcu_torture_wcount[RCU_TORTURE_PIPE_LEN + 1];
 static atomic_t n_rcu_torture_alloc;
 static atomic_t n_rcu_torture_alloc_fail;
@@ -186,22 +134,9 @@ static long n_rcu_torture_boost_rterror;
 static long n_rcu_torture_boost_failure;
 static long n_rcu_torture_boosts;
 static long n_rcu_torture_timers;
-static long n_offline_attempts;
-static long n_offline_successes;
-static unsigned long sum_offline;
-static int min_offline = -1;
-static int max_offline;
-static long n_online_attempts;
-static long n_online_successes;
-static unsigned long sum_online;
-static int min_online = -1;
-static int max_online;
 static long n_barrier_attempts;
 static long n_barrier_successes;
 static struct list_head rcu_torture_removed;
-static cpumask_var_t shuffle_tmp_mask;
-
-static int stutter_pause_test;
 
 #if defined(MODULE) || defined(CONFIG_RCU_TORTURE_TEST_RUNNABLE)
 #define RCUTORTURE_RUNNABLE_INIT 1
@@ -232,7 +167,6 @@ static u64 notrace rcu_trace_clock_local(void)
 }
 #endif /* #else #ifdef CONFIG_RCU_TRACE */
 
-static unsigned long shutdown_time;     /* jiffies to system shutdown. */
 static unsigned long boost_starttime;   /* jiffies of next boost test start. */
 DEFINE_MUTEX(boost_mutex);              /* protect setting boost_starttime */
                                         /*  and boost task create/destroy. */
@@ -242,51 +176,6 @@ static atomic_t barrier_cbs_invoked;	/* Barrier callbacks invoked. */
 static wait_queue_head_t *barrier_cbs_wq; /* Coordinate barrier testing. */
 static DECLARE_WAIT_QUEUE_HEAD(barrier_wq);
 
-/* Mediate rmmod and system shutdown.  Concurrent rmmod & shutdown illegal! */
-
-#define FULLSTOP_DONTSTOP 0     /* Normal operation. */
-#define FULLSTOP_SHUTDOWN 1     /* System shutdown with rcutorture running. */
-#define FULLSTOP_RMMOD    2     /* Normal rmmod of rcutorture. */
-static int fullstop = FULLSTOP_RMMOD;
-/*
- * Protect fullstop transitions and spawning of kthreads.
- */
-static DEFINE_MUTEX(fullstop_mutex);
-
-/* Forward reference. */
-static void rcu_torture_cleanup(void);
-
-/*
- * Detect and respond to a system shutdown.
- */
-static int
-rcutorture_shutdown_notify(struct notifier_block *unused1,
-                           unsigned long unused2, void *unused3)
-{
-        mutex_lock(&fullstop_mutex);
-        if (fullstop == FULLSTOP_DONTSTOP)
-                fullstop = FULLSTOP_SHUTDOWN;
-        else
-                pr_warn(/* but going down anyway, so... */
-                       "Concurrent 'rmmod rcutorture' and shutdown illegal!\n");
-        mutex_unlock(&fullstop_mutex);
-        return NOTIFY_DONE;
-}
-
-/*
- * Absorb kthreads into a kernel function that won't return, so that
- * they won't ever access module text or data again.
- */
-static void rcutorture_shutdown_absorb(const char *title)
-{
-        if (ACCESS_ONCE(fullstop) == FULLSTOP_SHUTDOWN) {
-                pr_notice(
-                       "rcutorture thread %s parking due to system shutdown\n",
-                       title);
-                schedule_timeout_uninterruptible(MAX_SCHEDULE_TIMEOUT);
-        }
-}
-
 /*
  * Allocate an element from the rcu_tortures pool.
  */
@@ -320,44 +209,6 @@ rcu_torture_free(struct rcu_torture *p)
         spin_unlock_bh(&rcu_torture_lock);
 }
 
-struct rcu_random_state {
-        unsigned long rrs_state;
-        long rrs_count;
-};
-
-#define RCU_RANDOM_MULT 39916801  /* prime */
-#define RCU_RANDOM_ADD  479001701 /* prime */
-#define RCU_RANDOM_REFRESH 10000
-
-#define DEFINE_RCU_RANDOM(name) struct rcu_random_state name = { 0, 0 }
-
-/*
- * Crude but fast random-number generator.  Uses a linear congruential
- * generator, with occasional help from cpu_clock().
- */
-static unsigned long
-rcu_random(struct rcu_random_state *rrsp)
-{
-        if (--rrsp->rrs_count < 0) {
-                rrsp->rrs_state += (unsigned long)local_clock();
-                rrsp->rrs_count = RCU_RANDOM_REFRESH;
-        }
-        rrsp->rrs_state = rrsp->rrs_state * RCU_RANDOM_MULT + RCU_RANDOM_ADD;
-        return swahw32(rrsp->rrs_state);
-}
-
-static void
-rcu_stutter_wait(const char *title)
-{
-        while (stutter_pause_test || !rcutorture_runnable) {
-                if (rcutorture_runnable)
-                        schedule_timeout_interruptible(1);
-                else
-                        schedule_timeout_interruptible(round_jiffies_relative(HZ));
-                rcutorture_shutdown_absorb(title);
-        }
-}
-
 /*
  * Operations vector for selecting different types of tests.
  */
@@ -365,7 +216,7 @@ rcu_stutter_wait(const char *title)
 struct rcu_torture_ops {
         void (*init)(void);
         int (*readlock)(void);
-        void (*read_delay)(struct rcu_random_state *rrsp);
+        void (*read_delay)(struct torture_random_state *rrsp);
         void (*readunlock)(int idx);
         int (*completed)(void);
         void (*deferred_free)(struct rcu_torture *p);
@@ -392,7 +243,7 @@ static int rcu_torture_read_lock(void) __acquires(RCU)
         return 0;
 }
 
-static void rcu_read_delay(struct rcu_random_state *rrsp)
+static void rcu_read_delay(struct torture_random_state *rrsp)
 {
         const unsigned long shortdelay_us = 200;
         const unsigned long longdelay_ms = 50;
@@ -401,12 +252,13 @@ static void rcu_read_delay(struct rcu_random_state *rrsp)
          * period, and we want a long delay occasionally to trigger
          * force_quiescent_state. */
 
-        if (!(rcu_random(rrsp) % (nrealreaders * 2000 * longdelay_ms)))
+        if (!(torture_random(rrsp) % (nrealreaders * 2000 * longdelay_ms)))
                 mdelay(longdelay_ms);
-        if (!(rcu_random(rrsp) % (nrealreaders * 2 * shortdelay_us)))
+        if (!(torture_random(rrsp) % (nrealreaders * 2 * shortdelay_us)))
                 udelay(shortdelay_us);
 #ifdef CONFIG_PREEMPT
-        if (!preempt_count() && !(rcu_random(rrsp) % (nrealreaders * 20000)))
+        if (!preempt_count() &&
+            !(torture_random(rrsp) % (nrealreaders * 20000)))
                 preempt_schedule();  /* No QS if preempt_disable() in effect */
 #endif
 }
@@ -427,7 +279,7 @@ rcu_torture_cb(struct rcu_head *p)
         int i;
         struct rcu_torture *rp = container_of(p, struct rcu_torture, rtort_rcu);
 
-        if (fullstop != FULLSTOP_DONTSTOP) {
+        if (torture_must_stop_irq()) {
                 /* Test is ending, just drop callbacks on the floor. */
                 /* The next initialization will pick up the pieces. */
                 return;
@@ -520,6 +372,48 @@ static struct rcu_torture_ops rcu_bh_ops = {
 };
 
 /*
+ * Don't even think about trying any of these in real life!!!
+ * The names includes "busted", and they really means it!
+ * The only purpose of these functions is to provide a buggy RCU
+ * implementation to make sure that rcutorture correctly emits
+ * buggy-RCU error messages.
+ */
+static void rcu_busted_torture_deferred_free(struct rcu_torture *p)
+{
+        /* This is a deliberate bug for testing purposes only! */
+        rcu_torture_cb(&p->rtort_rcu);
+}
+
+static void synchronize_rcu_busted(void)
+{
+        /* This is a deliberate bug for testing purposes only! */
+}
+
+static void
+call_rcu_busted(struct rcu_head *head, void (*func)(struct rcu_head *rcu))
+{
+        /* This is a deliberate bug for testing purposes only! */
+        func(head);
+}
+
+static struct rcu_torture_ops rcu_busted_ops = {
+        .init           = rcu_sync_torture_init,
+        .readlock       = rcu_torture_read_lock,
+        .read_delay     = rcu_read_delay,  /* just reuse rcu's version. */
+        .readunlock     = rcu_torture_read_unlock,
+        .completed      = rcu_no_completed,
+        .deferred_free  = rcu_busted_torture_deferred_free,
+        .sync           = synchronize_rcu_busted,
+        .exp_sync       = synchronize_rcu_busted,
+        .call           = call_rcu_busted,
+        .cb_barrier     = NULL,
+        .fqs            = NULL,
+        .stats          = NULL,
+        .irq_capable    = 1,
+        .name           = "rcu_busted"
+};
+
+/*
  * Definitions for srcu torture testing.
  */
 
@@ -530,7 +424,7 @@ static int srcu_torture_read_lock(void) __acquires(&srcu_ctl)
         return srcu_read_lock(&srcu_ctl);
 }
 
-static void srcu_read_delay(struct rcu_random_state *rrsp)
+static void srcu_read_delay(struct torture_random_state *rrsp)
 {
         long delay;
         const long uspertick = 1000000 / HZ;
@@ -538,7 +432,8 @@ static void srcu_read_delay(struct rcu_random_state *rrsp)
 
         /* We want there to be long-running readers, but not all the time. */
 
-        delay = rcu_random(rrsp) % (nrealreaders * 2 * longdelay * uspertick);
+        delay = torture_random(rrsp) %
+                (nrealreaders * 2 * longdelay * uspertick);
         if (!delay)
                 schedule_timeout_interruptible(longdelay);
         else
@@ -677,12 +572,12 @@ static int rcu_torture_boost(void *arg)
         struct rcu_boost_inflight rbi = { .inflight = 0 };
         struct sched_param sp;
 
-        VERBOSE_PRINTK_STRING("rcu_torture_boost started");
+        VERBOSE_TOROUT_STRING("rcu_torture_boost started");
 
         /* Set real-time priority. */
         sp.sched_priority = 1;
         if (sched_setscheduler(current, SCHED_FIFO, &sp) < 0) {
-                VERBOSE_PRINTK_STRING("rcu_torture_boost RT prio failed!");
+                VERBOSE_TOROUT_STRING("rcu_torture_boost RT prio failed!");
                 n_rcu_torture_boost_rterror++;
         }
 
@@ -693,9 +588,8 @@ static int rcu_torture_boost(void *arg)
                 oldstarttime = boost_starttime;
                 while (ULONG_CMP_LT(jiffies, oldstarttime)) {
                         schedule_timeout_interruptible(oldstarttime - jiffies);
-                        rcu_stutter_wait("rcu_torture_boost");
-                        if (kthread_should_stop() ||
-                            fullstop != FULLSTOP_DONTSTOP)
+                        stutter_wait("rcu_torture_boost");
+                        if (torture_must_stop())
                                 goto checkwait;
                 }
 
@@ -710,15 +604,14 @@ static int rcu_torture_boost(void *arg)
                                 call_rcu(&rbi.rcu, rcu_torture_boost_cb);
                                 if (jiffies - call_rcu_time >
                                          test_boost_duration * HZ - HZ / 2) {
-                                        VERBOSE_PRINTK_STRING("rcu_torture_boost boosting failed");
+                                        VERBOSE_TOROUT_STRING("rcu_torture_boost boosting failed");
                                         n_rcu_torture_boost_failure++;
                                 }
                                 call_rcu_time = jiffies;
                         }
                         cond_resched();
-                        rcu_stutter_wait("rcu_torture_boost");
-                        if (kthread_should_stop() ||
-                            fullstop != FULLSTOP_DONTSTOP)
+                        stutter_wait("rcu_torture_boost");
+                        if (torture_must_stop())
                                 goto checkwait;
                 }
 
@@ -742,16 +635,17 @@ static int rcu_torture_boost(void *arg)
                 }
 
                 /* Go do the stutter. */
-checkwait:      rcu_stutter_wait("rcu_torture_boost");
-        } while (!kthread_should_stop() && fullstop  == FULLSTOP_DONTSTOP);
+checkwait:      stutter_wait("rcu_torture_boost");
+        } while (!torture_must_stop());
 
         /* Clean up and exit. */
-        VERBOSE_PRINTK_STRING("rcu_torture_boost task stopping");
-        rcutorture_shutdown_absorb("rcu_torture_boost");
-        while (!kthread_should_stop() || rbi.inflight)
+        while (!kthread_should_stop() || rbi.inflight) {
+                torture_shutdown_absorb("rcu_torture_boost");
                 schedule_timeout_uninterruptible(1);
+        }
         smp_mb(); /* order accesses to ->inflight before stack-frame death. */
         destroy_rcu_head_on_stack(&rbi.rcu);
+        torture_kthread_stopping("rcu_torture_boost");
         return 0;
 }
 
@@ -766,7 +660,7 @@ rcu_torture_fqs(void *arg)
         unsigned long fqs_resume_time;
         int fqs_burst_remaining;
 
-        VERBOSE_PRINTK_STRING("rcu_torture_fqs task started");
+        VERBOSE_TOROUT_STRING("rcu_torture_fqs task started");
         do {
                 fqs_resume_time = jiffies + fqs_stutter * HZ;
                 while (ULONG_CMP_LT(jiffies, fqs_resume_time) &&
@@ -780,12 +674,9 @@ rcu_torture_fqs(void *arg)
                         udelay(fqs_holdoff);
                         fqs_burst_remaining -= fqs_holdoff;
                 }
-                rcu_stutter_wait("rcu_torture_fqs");
-        } while (!kthread_should_stop() && fullstop == FULLSTOP_DONTSTOP);
-        VERBOSE_PRINTK_STRING("rcu_torture_fqs task stopping");
-        rcutorture_shutdown_absorb("rcu_torture_fqs");
-        while (!kthread_should_stop())
-                schedule_timeout_uninterruptible(1);
+                stutter_wait("rcu_torture_fqs");
+        } while (!torture_must_stop());
+        torture_kthread_stopping("rcu_torture_fqs");
         return 0;
 }
 
@@ -802,10 +693,10 @@ rcu_torture_writer(void *arg)
         struct rcu_torture *rp;
         struct rcu_torture *rp1;
         struct rcu_torture *old_rp;
-        static DEFINE_RCU_RANDOM(rand);
+        static DEFINE_TORTURE_RANDOM(rand);
 
-        VERBOSE_PRINTK_STRING("rcu_torture_writer task started");
-        set_user_nice(current, 19);
+        VERBOSE_TOROUT_STRING("rcu_torture_writer task started");
+        set_user_nice(current, MAX_NICE);
 
         do {
                 schedule_timeout_uninterruptible(1);
@@ -813,7 +704,7 @@ rcu_torture_writer(void *arg)
                 if (rp == NULL)
                         continue;
                 rp->rtort_pipe_count = 0;
-                udelay(rcu_random(&rand) & 0x3ff);
+                udelay(torture_random(&rand) & 0x3ff);
                 old_rp = rcu_dereference_check(rcu_torture_current,
                                                current == writer_task);
                 rp->rtort_mbtest = 1;
@@ -826,7 +717,7 @@ rcu_torture_writer(void *arg)
                         atomic_inc(&rcu_torture_wcount[i]);
                         old_rp->rtort_pipe_count++;
                         if (gp_normal == gp_exp)
-                                exp = !!(rcu_random(&rand) & 0x80);
+                                exp = !!(torture_random(&rand) & 0x80);
                         else
                                 exp = gp_exp;
                         if (!exp) {
@@ -852,12 +743,9 @@ rcu_torture_writer(void *arg)
                         }
                 }
                 rcutorture_record_progress(++rcu_torture_current_version);
-                rcu_stutter_wait("rcu_torture_writer");
-        } while (!kthread_should_stop() && fullstop == FULLSTOP_DONTSTOP);
-        VERBOSE_PRINTK_STRING("rcu_torture_writer task stopping");
-        rcutorture_shutdown_absorb("rcu_torture_writer");
-        while (!kthread_should_stop())
-                schedule_timeout_uninterruptible(1);
+                stutter_wait("rcu_torture_writer");
+        } while (!torture_must_stop());
+        torture_kthread_stopping("rcu_torture_writer");
         return 0;
 }
 
@@ -868,19 +756,19 @@ rcu_torture_writer(void *arg)
 static int
 rcu_torture_fakewriter(void *arg)
 {
-        DEFINE_RCU_RANDOM(rand);
+        DEFINE_TORTURE_RANDOM(rand);
 
-        VERBOSE_PRINTK_STRING("rcu_torture_fakewriter task started");
-        set_user_nice(current, 19);
+        VERBOSE_TOROUT_STRING("rcu_torture_fakewriter task started");
+        set_user_nice(current, MAX_NICE);
 
         do {
-                schedule_timeout_uninterruptible(1 + rcu_random(&rand)%10);
-                udelay(rcu_random(&rand) & 0x3ff);
+                schedule_timeout_uninterruptible(1 + torture_random(&rand)%10);
+                udelay(torture_random(&rand) & 0x3ff);
                 if (cur_ops->cb_barrier != NULL &&
-                    rcu_random(&rand) % (nfakewriters * 8) == 0) {
+                    torture_random(&rand) % (nfakewriters * 8) == 0) {
                         cur_ops->cb_barrier();
                 } else if (gp_normal == gp_exp) {
-                        if (rcu_random(&rand) & 0x80)
+                        if (torture_random(&rand) & 0x80)
                                 cur_ops->sync();
                         else
                                 cur_ops->exp_sync();
@@ -889,13 +777,10 @@ rcu_torture_fakewriter(void *arg)
                 } else {
                         cur_ops->exp_sync();
                 }
-                rcu_stutter_wait("rcu_torture_fakewriter");
-        } while (!kthread_should_stop() && fullstop == FULLSTOP_DONTSTOP);
+                stutter_wait("rcu_torture_fakewriter");
+        } while (!torture_must_stop());
 
-        VERBOSE_PRINTK_STRING("rcu_torture_fakewriter task stopping");
-        rcutorture_shutdown_absorb("rcu_torture_fakewriter");
-        while (!kthread_should_stop())
-                schedule_timeout_uninterruptible(1);
+        torture_kthread_stopping("rcu_torture_fakewriter");
         return 0;
 }
 
@@ -921,7 +806,7 @@ static void rcu_torture_timer(unsigned long unused)
         int idx;
         int completed;
         int completed_end;
-        static DEFINE_RCU_RANDOM(rand);
+        static DEFINE_TORTURE_RANDOM(rand);
         static DEFINE_SPINLOCK(rand_lock);
         struct rcu_torture *p;
         int pipe_count;
@@ -980,14 +865,14 @@ rcu_torture_reader(void *arg)
         int completed;
         int completed_end;
         int idx;
-        DEFINE_RCU_RANDOM(rand);
+        DEFINE_TORTURE_RANDOM(rand);
         struct rcu_torture *p;
         int pipe_count;
         struct timer_list t;
         unsigned long long ts;
 
-        VERBOSE_PRINTK_STRING("rcu_torture_reader task started");
-        set_user_nice(current, 19);
+        VERBOSE_TOROUT_STRING("rcu_torture_reader task started");
+        set_user_nice(current, MAX_NICE);
         if (irqreader && cur_ops->irq_capable)
                 setup_timer_on_stack(&t, rcu_torture_timer, 0);
 
@@ -1034,14 +919,11 @@ rcu_torture_reader(void *arg)
                 preempt_enable();
                 cur_ops->readunlock(idx);
                 schedule();
-                rcu_stutter_wait("rcu_torture_reader");
-        } while (!kthread_should_stop() && fullstop == FULLSTOP_DONTSTOP);
-        VERBOSE_PRINTK_STRING("rcu_torture_reader task stopping");
-        rcutorture_shutdown_absorb("rcu_torture_reader");
+                stutter_wait("rcu_torture_reader");
+        } while (!torture_must_stop());
         if (irqreader && cur_ops->irq_capable)
                 del_timer_sync(&t);
-        while (!kthread_should_stop())
-                schedule_timeout_uninterruptible(1);
+        torture_kthread_stopping("rcu_torture_reader");
         return 0;
 }
 
@@ -1083,13 +965,7 @@ rcu_torture_printk(char *page)
                        n_rcu_torture_boost_failure,
                        n_rcu_torture_boosts,
                        n_rcu_torture_timers);
-        page += sprintf(page,
-                       "onoff: %ld/%ld:%ld/%ld %d,%d:%d,%d %lu:%lu (HZ=%d) ",
-                       n_online_successes, n_online_attempts,
-                       n_offline_successes, n_offline_attempts,
-                       min_online, max_online,
-                       min_offline, max_offline,
-                       sum_online, sum_offline, HZ);
+        page = torture_onoff_stats(page);
         page += sprintf(page, "barrier: %ld/%ld:%ld",
                        n_barrier_successes,
                        n_barrier_attempts,
@@ -1150,123 +1026,17 @@ rcu_torture_stats_print(void)
 /*
  * Periodically prints torture statistics, if periodic statistics printing
  * was specified via the stat_interval module parameter.
- *
- * No need to worry about fullstop here, since this one doesn't reference
- * volatile state or register callbacks.
  */
 static int
 rcu_torture_stats(void *arg)
 {
-        VERBOSE_PRINTK_STRING("rcu_torture_stats task started");
+        VERBOSE_TOROUT_STRING("rcu_torture_stats task started");
         do {
                 schedule_timeout_interruptible(stat_interval * HZ);
                 rcu_torture_stats_print();
-                rcutorture_shutdown_absorb("rcu_torture_stats");
-        } while (!kthread_should_stop());
-        VERBOSE_PRINTK_STRING("rcu_torture_stats task stopping");
-        return 0;
-}
-
-static int rcu_idle_cpu;        /* Force all torture tasks off this CPU */
-
-/* Shuffle tasks such that we allow @rcu_idle_cpu to become idle. A special case
- * is when @rcu_idle_cpu = -1, when we allow the tasks to run on all CPUs.
- */
-static void rcu_torture_shuffle_tasks(void)
-{
-        int i;
-
-        cpumask_setall(shuffle_tmp_mask);
-        get_online_cpus();
-
-        /* No point in shuffling if there is only one online CPU (ex: UP) */
-        if (num_online_cpus() == 1) {
-                put_online_cpus();
-                return;
-        }
-
-        if (rcu_idle_cpu != -1)
-                cpumask_clear_cpu(rcu_idle_cpu, shuffle_tmp_mask);
-
-        set_cpus_allowed_ptr(current, shuffle_tmp_mask);
-
-        if (reader_tasks) {
-                for (i = 0; i < nrealreaders; i++)
-                        if (reader_tasks[i])
-                                set_cpus_allowed_ptr(reader_tasks[i],
-                                                     shuffle_tmp_mask);
-        }
-        if (fakewriter_tasks) {
-                for (i = 0; i < nfakewriters; i++)
-                        if (fakewriter_tasks[i])
-                                set_cpus_allowed_ptr(fakewriter_tasks[i],
-                                                     shuffle_tmp_mask);
-        }
-        if (writer_task)
-                set_cpus_allowed_ptr(writer_task, shuffle_tmp_mask);
-        if (stats_task)
-                set_cpus_allowed_ptr(stats_task, shuffle_tmp_mask);
-        if (stutter_task)
-                set_cpus_allowed_ptr(stutter_task, shuffle_tmp_mask);
-        if (fqs_task)
-                set_cpus_allowed_ptr(fqs_task, shuffle_tmp_mask);
-        if (shutdown_task)
-                set_cpus_allowed_ptr(shutdown_task, shuffle_tmp_mask);
-#ifdef CONFIG_HOTPLUG_CPU
-        if (onoff_task)
-                set_cpus_allowed_ptr(onoff_task, shuffle_tmp_mask);
-#endif /* #ifdef CONFIG_HOTPLUG_CPU */
-        if (stall_task)
-                set_cpus_allowed_ptr(stall_task, shuffle_tmp_mask);
-        if (barrier_cbs_tasks)
-                for (i = 0; i < n_barrier_cbs; i++)
-                        if (barrier_cbs_tasks[i])
-                                set_cpus_allowed_ptr(barrier_cbs_tasks[i],
-                                                     shuffle_tmp_mask);
-        if (barrier_task)
-                set_cpus_allowed_ptr(barrier_task, shuffle_tmp_mask);
-
-        if (rcu_idle_cpu == -1)
-                rcu_idle_cpu = num_online_cpus() - 1;
-        else
-                rcu_idle_cpu--;
-
-        put_online_cpus();
-}
-
-/* Shuffle tasks across CPUs, with the intent of allowing each CPU in the
- * system to become idle at a time and cut off its timer ticks. This is meant
- * to test the support for such tickless idle CPU in RCU.
- */
-static int
-rcu_torture_shuffle(void *arg)
-{
-        VERBOSE_PRINTK_STRING("rcu_torture_shuffle task started");
-        do {
-                schedule_timeout_interruptible(shuffle_interval * HZ);
-                rcu_torture_shuffle_tasks();
-                rcutorture_shutdown_absorb("rcu_torture_shuffle");
-        } while (!kthread_should_stop());
-        VERBOSE_PRINTK_STRING("rcu_torture_shuffle task stopping");
-        return 0;
-}
-
-/* Cause the rcutorture test to "stutter", starting and stopping all
- * threads periodically.
- */
-static int
-rcu_torture_stutter(void *arg)
-{
-        VERBOSE_PRINTK_STRING("rcu_torture_stutter task started");
-        do {
-                schedule_timeout_interruptible(stutter * HZ);
-                stutter_pause_test = 1;
-                if (!kthread_should_stop())
-                        schedule_timeout_interruptible(stutter * HZ);
-                stutter_pause_test = 0;
-                rcutorture_shutdown_absorb("rcu_torture_stutter");
-        } while (!kthread_should_stop());
-        VERBOSE_PRINTK_STRING("rcu_torture_stutter task stopping");
+                torture_shutdown_absorb("rcu_torture_stats");
+        } while (!torture_must_stop());
+        torture_kthread_stopping("rcu_torture_stats");
         return 0;
 }
 
@@ -1293,10 +1063,6 @@ rcu_torture_print_module_parms(struct rcu_torture_ops *cur_ops, const char *tag)
                  onoff_interval, onoff_holdoff);
 }
 
-static struct notifier_block rcutorture_shutdown_nb = {
-        .notifier_call = rcutorture_shutdown_notify,
-};
-
 static void rcutorture_booster_cleanup(int cpu)
 {
         struct task_struct *t;
@@ -1304,14 +1070,12 @@ static void rcutorture_booster_cleanup(int cpu)
         if (boost_tasks[cpu] == NULL)
                 return;
         mutex_lock(&boost_mutex);
-        VERBOSE_PRINTK_STRING("Stopping rcu_torture_boost task");
         t = boost_tasks[cpu];
         boost_tasks[cpu] = NULL;
         mutex_unlock(&boost_mutex);
 
         /* This must be outside of the mutex, otherwise deadlock! */
-        kthread_stop(t);
-        boost_tasks[cpu] = NULL;
+        torture_stop_kthread(rcu_torture_boost, t);
 }
 
 static int rcutorture_booster_init(int cpu)
@@ -1323,13 +1087,13 @@ static int rcutorture_booster_init(int cpu)
 
         /* Don't allow time recalculation while creating a new task. */
         mutex_lock(&boost_mutex);
-        VERBOSE_PRINTK_STRING("Creating rcu_torture_boost task");
+        VERBOSE_TOROUT_STRING("Creating rcu_torture_boost task");
         boost_tasks[cpu] = kthread_create_on_node(rcu_torture_boost, NULL,
                                                   cpu_to_node(cpu),
                                                   "rcu_torture_boost");
         if (IS_ERR(boost_tasks[cpu])) {
                 retval = PTR_ERR(boost_tasks[cpu]);
-                VERBOSE_PRINTK_STRING("rcu_torture_boost task create failed");
+                VERBOSE_TOROUT_STRING("rcu_torture_boost task create failed");
                 n_rcu_torture_boost_ktrerror++;
                 boost_tasks[cpu] = NULL;
                 mutex_unlock(&boost_mutex);
@@ -1342,175 +1106,6 @@ static int rcutorture_booster_init(int cpu)
 }
 
 /*
- * Cause the rcutorture test to shutdown the system after the test has
- * run for the time specified by the shutdown_secs module parameter.
- */
-static int
-rcu_torture_shutdown(void *arg)
-{
-        long delta;
-        unsigned long jiffies_snap;
-
-        VERBOSE_PRINTK_STRING("rcu_torture_shutdown task started");
-        jiffies_snap = ACCESS_ONCE(jiffies);
-        while (ULONG_CMP_LT(jiffies_snap, shutdown_time) &&
-               !kthread_should_stop()) {
-                delta = shutdown_time - jiffies_snap;
-                if (verbose)
-                        pr_alert("%s" TORTURE_FLAG
-                                 "rcu_torture_shutdown task: %lu jiffies remaining\n",
-                                 torture_type, delta);
-                schedule_timeout_interruptible(delta);
-                jiffies_snap = ACCESS_ONCE(jiffies);
-        }
-        if (kthread_should_stop()) {
-                VERBOSE_PRINTK_STRING("rcu_torture_shutdown task stopping");
-                return 0;
-        }
-
-        /* OK, shut down the system. */
-
-        VERBOSE_PRINTK_STRING("rcu_torture_shutdown task shutting down system");
-        shutdown_task = NULL;   /* Avoid self-kill deadlock. */
-        rcu_torture_cleanup();  /* Get the success/failure message. */
-        kernel_power_off();     /* Shut down the system. */
-        return 0;
-}
-
-#ifdef CONFIG_HOTPLUG_CPU
-
-/*
- * Execute random CPU-hotplug operations at the interval specified
- * by the onoff_interval.
- */
-static int
-rcu_torture_onoff(void *arg)
-{
-        int cpu;
-        unsigned long delta;
-        int maxcpu = -1;
-        DEFINE_RCU_RANDOM(rand);
-        int ret;
-        unsigned long starttime;
-
-        VERBOSE_PRINTK_STRING("rcu_torture_onoff task started");
-        for_each_online_cpu(cpu)
-                maxcpu = cpu;
-        WARN_ON(maxcpu < 0);
-        if (onoff_holdoff > 0) {
-                VERBOSE_PRINTK_STRING("rcu_torture_onoff begin holdoff");
-                schedule_timeout_interruptible(onoff_holdoff * HZ);
-                VERBOSE_PRINTK_STRING("rcu_torture_onoff end holdoff");
-        }
-        while (!kthread_should_stop()) {
-                cpu = (rcu_random(&rand) >> 4) % (maxcpu + 1);
-                if (cpu_online(cpu) && cpu_is_hotpluggable(cpu)) {
-                        if (verbose)
-                                pr_alert("%s" TORTURE_FLAG
-                                         "rcu_torture_onoff task: offlining %d\n",
-                                         torture_type, cpu);
-                        starttime = jiffies;
-                        n_offline_attempts++;
-                        ret = cpu_down(cpu);
-                        if (ret) {
-                                if (verbose)
-                                        pr_alert("%s" TORTURE_FLAG
-                                                 "rcu_torture_onoff task: offline %d failed: errno %d\n",
-                                                 torture_type, cpu, ret);
-                        } else {
-                                if (verbose)
-                                        pr_alert("%s" TORTURE_FLAG
-                                                 "rcu_torture_onoff task: offlined %d\n",
-                                                 torture_type, cpu);
-                                n_offline_successes++;
-                                delta = jiffies - starttime;
-                                sum_offline += delta;
-                                if (min_offline < 0) {
-                                        min_offline = delta;
-                                        max_offline = delta;
-                                }
-                                if (min_offline > delta)
-                                        min_offline = delta;
-                                if (max_offline < delta)
-                                        max_offline = delta;
-                        }
-                } else if (cpu_is_hotpluggable(cpu)) {
-                        if (verbose)
-                                pr_alert("%s" TORTURE_FLAG
-                                         "rcu_torture_onoff task: onlining %d\n",
-                                         torture_type, cpu);
-                        starttime = jiffies;
-                        n_online_attempts++;
-                        ret = cpu_up(cpu);
-                        if (ret) {
-                                if (verbose)
-                                        pr_alert("%s" TORTURE_FLAG
-                                                 "rcu_torture_onoff task: online %d failed: errno %d\n",
-                                                 torture_type, cpu, ret);
-                        } else {
-                                if (verbose)
-                                        pr_alert("%s" TORTURE_FLAG
-                                                 "rcu_torture_onoff task: onlined %d\n",
-                                                 torture_type, cpu);
-                                n_online_successes++;
-                                delta = jiffies - starttime;
-                                sum_online += delta;
-                                if (min_online < 0) {
-                                        min_online = delta;
-                                        max_online = delta;
-                                }
-                                if (min_online > delta)
-                                        min_online = delta;
-                                if (max_online < delta)
-                                        max_online = delta;
-                        }
-                }
-                schedule_timeout_interruptible(onoff_interval * HZ);
-        }
-        VERBOSE_PRINTK_STRING("rcu_torture_onoff task stopping");
-        return 0;
-}
-
-static int
-rcu_torture_onoff_init(void)
-{
-        int ret;
-
-        if (onoff_interval <= 0)
-                return 0;
-        onoff_task = kthread_run(rcu_torture_onoff, NULL, "rcu_torture_onoff");
-        if (IS_ERR(onoff_task)) {
-                ret = PTR_ERR(onoff_task);
-                onoff_task = NULL;
-                return ret;
-        }
-        return 0;
-}
-
-static void rcu_torture_onoff_cleanup(void)
-{
-        if (onoff_task == NULL)
-                return;
-        VERBOSE_PRINTK_STRING("Stopping rcu_torture_onoff task");
-        kthread_stop(onoff_task);
-        onoff_task = NULL;
-}
-
-#else /* #ifdef CONFIG_HOTPLUG_CPU */
-
-static int
-rcu_torture_onoff_init(void)
-{
-        return 0;
-}
-
-static void rcu_torture_onoff_cleanup(void)
-{
-}
-
-#endif /* #else #ifdef CONFIG_HOTPLUG_CPU */
-
-/*
  * CPU-stall kthread.  It waits as specified by stall_cpu_holdoff, then
  * induces a CPU stall for the time specified by stall_cpu.
  */
@@ -1518,11 +1113,11 @@ static int rcu_torture_stall(void *args)
 {
         unsigned long stop_at;
 
-        VERBOSE_PRINTK_STRING("rcu_torture_stall task started");
+        VERBOSE_TOROUT_STRING("rcu_torture_stall task started");
         if (stall_cpu_holdoff > 0) {
-                VERBOSE_PRINTK_STRING("rcu_torture_stall begin holdoff");
+                VERBOSE_TOROUT_STRING("rcu_torture_stall begin holdoff");
                 schedule_timeout_interruptible(stall_cpu_holdoff * HZ);
-                VERBOSE_PRINTK_STRING("rcu_torture_stall end holdoff");
+                VERBOSE_TOROUT_STRING("rcu_torture_stall end holdoff");
         }
         if (!kthread_should_stop()) {
                 stop_at = get_seconds() + stall_cpu;
@@ -1536,7 +1131,7 @@ static int rcu_torture_stall(void *args)
                 rcu_read_unlock();
                 pr_alert("rcu_torture_stall end.\n");
         }
-        rcutorture_shutdown_absorb("rcu_torture_stall");
+        torture_shutdown_absorb("rcu_torture_stall");
         while (!kthread_should_stop())
                 schedule_timeout_interruptible(10 * HZ);
         return 0;
@@ -1545,27 +1140,9 @@ static int rcu_torture_stall(void *args)
 /* Spawn CPU-stall kthread, if stall_cpu specified. */
 static int __init rcu_torture_stall_init(void)
 {
-        int ret;
-
         if (stall_cpu <= 0)
                 return 0;
-        stall_task = kthread_run(rcu_torture_stall, NULL, "rcu_torture_stall");
-        if (IS_ERR(stall_task)) {
-                ret = PTR_ERR(stall_task);
-                stall_task = NULL;
-                return ret;
-        }
-        return 0;
-}
-
-/* Clean up after the CPU-stall kthread, if one was spawned. */
-static void rcu_torture_stall_cleanup(void)
-{
-        if (stall_task == NULL)
-                return;
-        VERBOSE_PRINTK_STRING("Stopping rcu_torture_stall_task.");
-        kthread_stop(stall_task);
-        stall_task = NULL;
+        return torture_create_kthread(rcu_torture_stall, NULL, stall_task);
 }
 
 /* Callback function for RCU barrier testing. */
@@ -1583,28 +1160,24 @@ static int rcu_torture_barrier_cbs(void *arg)
         struct rcu_head rcu;
 
         init_rcu_head_on_stack(&rcu);
-        VERBOSE_PRINTK_STRING("rcu_torture_barrier_cbs task started");
-        set_user_nice(current, 19);
+        VERBOSE_TOROUT_STRING("rcu_torture_barrier_cbs task started");
+        set_user_nice(current, MAX_NICE);
         do {
                 wait_event(barrier_cbs_wq[myid],
                            (newphase =
                             ACCESS_ONCE(barrier_phase)) != lastphase ||
-                           kthread_should_stop() ||
-                           fullstop != FULLSTOP_DONTSTOP);
+                           torture_must_stop());
                 lastphase = newphase;
                 smp_mb(); /* ensure barrier_phase load before ->call(). */
-                if (kthread_should_stop() || fullstop != FULLSTOP_DONTSTOP)
+                if (torture_must_stop())
                         break;
                 cur_ops->call(&rcu, rcu_torture_barrier_cbf);
                 if (atomic_dec_and_test(&barrier_cbs_count))
                         wake_up(&barrier_wq);
-        } while (!kthread_should_stop() && fullstop == FULLSTOP_DONTSTOP);
-        VERBOSE_PRINTK_STRING("rcu_torture_barrier_cbs task stopping");
-        rcutorture_shutdown_absorb("rcu_torture_barrier_cbs");
-        while (!kthread_should_stop())
-                schedule_timeout_interruptible(1);
+        } while (!torture_must_stop());
         cur_ops->cb_barrier();
         destroy_rcu_head_on_stack(&rcu);
+        torture_kthread_stopping("rcu_torture_barrier_cbs");
         return 0;
 }
 
@@ -1613,7 +1186,7 @@ static int rcu_torture_barrier(void *arg)
 {
         int i;
 
-        VERBOSE_PRINTK_STRING("rcu_torture_barrier task starting");
+        VERBOSE_TOROUT_STRING("rcu_torture_barrier task starting");
         do {
                 atomic_set(&barrier_cbs_invoked, 0);
                 atomic_set(&barrier_cbs_count, n_barrier_cbs);
@@ -1623,9 +1196,8 @@ static int rcu_torture_barrier(void *arg)
                         wake_up(&barrier_cbs_wq[i]);
                 wait_event(barrier_wq,
                            atomic_read(&barrier_cbs_count) == 0 ||
-                           kthread_should_stop() ||
-                           fullstop != FULLSTOP_DONTSTOP);
-                if (kthread_should_stop() || fullstop != FULLSTOP_DONTSTOP)
+                           torture_must_stop());
+                if (torture_must_stop())
                         break;
                 n_barrier_attempts++;
                 cur_ops->cb_barrier(); /* Implies smp_mb() for wait_event(). */
@@ -1635,11 +1207,8 @@ static int rcu_torture_barrier(void *arg)
                 }
                 n_barrier_successes++;
                 schedule_timeout_interruptible(HZ / 10);
-        } while (!kthread_should_stop() && fullstop == FULLSTOP_DONTSTOP);
-        VERBOSE_PRINTK_STRING("rcu_torture_barrier task stopping");
-        rcutorture_shutdown_absorb("rcu_torture_barrier");
-        while (!kthread_should_stop())
-                schedule_timeout_interruptible(1);
+        } while (!torture_must_stop());
+        torture_kthread_stopping("rcu_torture_barrier");
         return 0;
 }
 
@@ -1672,24 +1241,13 @@ static int rcu_torture_barrier_init(void)
                 return -ENOMEM;
         for (i = 0; i < n_barrier_cbs; i++) {
                 init_waitqueue_head(&barrier_cbs_wq[i]);
-                barrier_cbs_tasks[i] = kthread_run(rcu_torture_barrier_cbs,
-                                                   (void *)(long)i,
-                                                   "rcu_torture_barrier_cbs");
-                if (IS_ERR(barrier_cbs_tasks[i])) {
-                        ret = PTR_ERR(barrier_cbs_tasks[i]);
-                        VERBOSE_PRINTK_ERRSTRING("Failed to create rcu_torture_barrier_cbs");
-                        barrier_cbs_tasks[i] = NULL;
+                ret = torture_create_kthread(rcu_torture_barrier_cbs,
+                                             (void *)(long)i,
+                                             barrier_cbs_tasks[i]);
+                if (ret)
                         return ret;
-                }
         }
-        barrier_task = kthread_run(rcu_torture_barrier, NULL,
-                                   "rcu_torture_barrier");
-        if (IS_ERR(barrier_task)) {
-                ret = PTR_ERR(barrier_task);
-                VERBOSE_PRINTK_ERRSTRING("Failed to create rcu_torture_barrier");
-                barrier_task = NULL;
-        }
-        return 0;
+        return torture_create_kthread(rcu_torture_barrier, NULL, barrier_task);
 }
 
 /* Clean up after RCU barrier testing. */
@@ -1697,19 +1255,11 @@ static void rcu_torture_barrier_cleanup(void)
 {
         int i;
 
-        if (barrier_task != NULL) {
-                VERBOSE_PRINTK_STRING("Stopping rcu_torture_barrier task");
-                kthread_stop(barrier_task);
-                barrier_task = NULL;
-        }
+        torture_stop_kthread(rcu_torture_barrier, barrier_task);
         if (barrier_cbs_tasks != NULL) {
-                for (i = 0; i < n_barrier_cbs; i++) {
-                        if (barrier_cbs_tasks[i] != NULL) {
-                                VERBOSE_PRINTK_STRING("Stopping rcu_torture_barrier_cbs task");
-                                kthread_stop(barrier_cbs_tasks[i]);
-                                barrier_cbs_tasks[i] = NULL;
-                        }
-                }
+                for (i = 0; i < n_barrier_cbs; i++)
+                        torture_stop_kthread(rcu_torture_barrier_cbs,
+                                             barrier_cbs_tasks[i]);
                 kfree(barrier_cbs_tasks);
                 barrier_cbs_tasks = NULL;
         }
@@ -1747,90 +1297,42 @@ rcu_torture_cleanup(void)
 {
         int i;
 
-        mutex_lock(&fullstop_mutex);
         rcutorture_record_test_transition();
-        if (fullstop == FULLSTOP_SHUTDOWN) {
-                pr_warn(/* but going down anyway, so... */
-                       "Concurrent 'rmmod rcutorture' and shutdown illegal!\n");
-                mutex_unlock(&fullstop_mutex);
-                schedule_timeout_uninterruptible(10);
+        if (torture_cleanup()) {
                 if (cur_ops->cb_barrier != NULL)
                         cur_ops->cb_barrier();
                 return;
         }
-        fullstop = FULLSTOP_RMMOD;
-        mutex_unlock(&fullstop_mutex);
-        unregister_reboot_notifier(&rcutorture_shutdown_nb);
-        rcu_torture_barrier_cleanup();
-        rcu_torture_stall_cleanup();
-        if (stutter_task) {
-                VERBOSE_PRINTK_STRING("Stopping rcu_torture_stutter task");
-                kthread_stop(stutter_task);
-        }
-        stutter_task = NULL;
-        if (shuffler_task) {
-                VERBOSE_PRINTK_STRING("Stopping rcu_torture_shuffle task");
-                kthread_stop(shuffler_task);
-                free_cpumask_var(shuffle_tmp_mask);
-        }
-        shuffler_task = NULL;
 
-        if (writer_task) {
-                VERBOSE_PRINTK_STRING("Stopping rcu_torture_writer task");
-                kthread_stop(writer_task);
-        }
-        writer_task = NULL;
+        rcu_torture_barrier_cleanup();
+        torture_stop_kthread(rcu_torture_stall, stall_task);
+        torture_stop_kthread(rcu_torture_writer, writer_task);
 
         if (reader_tasks) {
-                for (i = 0; i < nrealreaders; i++) {
-                        if (reader_tasks[i]) {
-                                VERBOSE_PRINTK_STRING(
-                                        "Stopping rcu_torture_reader task");
-                                kthread_stop(reader_tasks[i]);
-                        }
-                        reader_tasks[i] = NULL;
-                }
+                for (i = 0; i < nrealreaders; i++)
+                        torture_stop_kthread(rcu_torture_reader,
+                                             reader_tasks[i]);
                 kfree(reader_tasks);
-                reader_tasks = NULL;
         }
         rcu_torture_current = NULL;
 
         if (fakewriter_tasks) {
                 for (i = 0; i < nfakewriters; i++) {
-                        if (fakewriter_tasks[i]) {
-                                VERBOSE_PRINTK_STRING(
-                                        "Stopping rcu_torture_fakewriter task");
-                                kthread_stop(fakewriter_tasks[i]);
-                        }
-                        fakewriter_tasks[i] = NULL;
+                        torture_stop_kthread(rcu_torture_fakewriter,
+                                             fakewriter_tasks[i]);
                 }
                 kfree(fakewriter_tasks);
                 fakewriter_tasks = NULL;
         }
 
-        if (stats_task) {
-                VERBOSE_PRINTK_STRING("Stopping rcu_torture_stats task");
-                kthread_stop(stats_task);
-        }
-        stats_task = NULL;
-
-        if (fqs_task) {
-                VERBOSE_PRINTK_STRING("Stopping rcu_torture_fqs task");
-                kthread_stop(fqs_task);
-        }
-        fqs_task = NULL;
+        torture_stop_kthread(rcu_torture_stats, stats_task);
+        torture_stop_kthread(rcu_torture_fqs, fqs_task);
         if ((test_boost == 1 && cur_ops->can_boost) ||
             test_boost == 2) {
                 unregister_cpu_notifier(&rcutorture_cpu_nb);
                 for_each_possible_cpu(i)
                         rcutorture_booster_cleanup(i);
         }
-        if (shutdown_task != NULL) {
-                VERBOSE_PRINTK_STRING("Stopping rcu_torture_shutdown task");
-                kthread_stop(shutdown_task);
-        }
-        shutdown_task = NULL;
-        rcu_torture_onoff_cleanup();
 
         /* Wait for all RCU callbacks to fire.  */
 
@@ -1841,8 +1343,7 @@ rcu_torture_cleanup(void)
 
         if (atomic_read(&n_rcu_torture_error) || n_rcu_torture_barrier_error)
                 rcu_torture_print_module_parms(cur_ops, "End of test: FAILURE");
-        else if (n_online_successes != n_online_attempts ||
-                 n_offline_successes != n_offline_attempts)
+        else if (torture_onoff_failures())
                 rcu_torture_print_module_parms(cur_ops,
                                                "End of test: RCU_HOTPLUG");
         else
@@ -1911,12 +1412,11 @@ rcu_torture_init(void)
         int i;
         int cpu;
         int firsterr = 0;
-        int retval;
         static struct rcu_torture_ops *torture_ops[] = {
-                &rcu_ops, &rcu_bh_ops, &srcu_ops, &sched_ops,
+                &rcu_ops, &rcu_bh_ops, &rcu_busted_ops, &srcu_ops, &sched_ops,
         };
 
-        mutex_lock(&fullstop_mutex);
+        torture_init_begin(torture_type, verbose, &rcutorture_runnable);
 
         /* Process args and tell the world that the torturer is on the job. */
         for (i = 0; i < ARRAY_SIZE(torture_ops); i++) {
@@ -1931,7 +1431,7 @@ rcu_torture_init(void)
                 for (i = 0; i < ARRAY_SIZE(torture_ops); i++)
                         pr_alert(" %s", torture_ops[i]->name);
                 pr_alert("\n");
-                mutex_unlock(&fullstop_mutex);
+                torture_init_end();
                 return -EINVAL;
         }
         if (cur_ops->fqs == NULL && fqs_duration != 0) {
@@ -1946,7 +1446,6 @@ rcu_torture_init(void)
         else
                 nrealreaders = 2 * num_online_cpus();
         rcu_torture_print_module_parms(cur_ops, "Start of test");
-        fullstop = FULLSTOP_DONTSTOP;
 
         /* Set up the freelist. */
 
@@ -1982,108 +1481,61 @@ rcu_torture_init(void)
 
         /* Start up the kthreads. */
 
-        VERBOSE_PRINTK_STRING("Creating rcu_torture_writer task");
-        writer_task = kthread_create(rcu_torture_writer, NULL,
-                                     "rcu_torture_writer");
-        if (IS_ERR(writer_task)) {
-                firsterr = PTR_ERR(writer_task);
-                VERBOSE_PRINTK_ERRSTRING("Failed to create writer");
-                writer_task = NULL;
+        firsterr = torture_create_kthread(rcu_torture_writer, NULL,
+                                          writer_task);
+        if (firsterr)
                 goto unwind;
-        }
-        wake_up_process(writer_task);
         fakewriter_tasks = kzalloc(nfakewriters * sizeof(fakewriter_tasks[0]),
                                    GFP_KERNEL);
         if (fakewriter_tasks == NULL) {
-                VERBOSE_PRINTK_ERRSTRING("out of memory");
+                VERBOSE_TOROUT_ERRSTRING("out of memory");
                 firsterr = -ENOMEM;
                 goto unwind;
         }
         for (i = 0; i < nfakewriters; i++) {
-                VERBOSE_PRINTK_STRING("Creating rcu_torture_fakewriter task");
-                fakewriter_tasks[i] = kthread_run(rcu_torture_fakewriter, NULL,
-                                                  "rcu_torture_fakewriter");
-                if (IS_ERR(fakewriter_tasks[i])) {
-                        firsterr = PTR_ERR(fakewriter_tasks[i]);
-                        VERBOSE_PRINTK_ERRSTRING("Failed to create fakewriter");
-                        fakewriter_tasks[i] = NULL;
+                firsterr = torture_create_kthread(rcu_torture_fakewriter,
+                                                  NULL, fakewriter_tasks[i]);
+                if (firsterr)
                         goto unwind;
-                }
         }
         reader_tasks = kzalloc(nrealreaders * sizeof(reader_tasks[0]),
                                GFP_KERNEL);
         if (reader_tasks == NULL) {
-                VERBOSE_PRINTK_ERRSTRING("out of memory");
+                VERBOSE_TOROUT_ERRSTRING("out of memory");
                 firsterr = -ENOMEM;
                 goto unwind;
         }
         for (i = 0; i < nrealreaders; i++) {
-                VERBOSE_PRINTK_STRING("Creating rcu_torture_reader task");
-                reader_tasks[i] = kthread_run(rcu_torture_reader, NULL,
-                                              "rcu_torture_reader");
-                if (IS_ERR(reader_tasks[i])) {
-                        firsterr = PTR_ERR(reader_tasks[i]);
-                        VERBOSE_PRINTK_ERRSTRING("Failed to create reader");
-                        reader_tasks[i] = NULL;
+                firsterr = torture_create_kthread(rcu_torture_reader, NULL,
+                                                  reader_tasks[i]);
+                if (firsterr)
                         goto unwind;
-                }
         }
         if (stat_interval > 0) {
-                VERBOSE_PRINTK_STRING("Creating rcu_torture_stats task");
-                stats_task = kthread_run(rcu_torture_stats, NULL,
-                                        "rcu_torture_stats");
-                if (IS_ERR(stats_task)) {
-                        firsterr = PTR_ERR(stats_task);
-                        VERBOSE_PRINTK_ERRSTRING("Failed to create stats");
-                        stats_task = NULL;
+                firsterr = torture_create_kthread(rcu_torture_stats, NULL,
+                                                  stats_task);
+                if (firsterr)
                         goto unwind;
-                }
         }
         if (test_no_idle_hz) {
-                rcu_idle_cpu = num_online_cpus() - 1;
-
-                if (!alloc_cpumask_var(&shuffle_tmp_mask, GFP_KERNEL)) {
-                        firsterr = -ENOMEM;
-                        VERBOSE_PRINTK_ERRSTRING("Failed to alloc mask");
-                        goto unwind;
-                }
-
-                /* Create the shuffler thread */
-                shuffler_task = kthread_run(rcu_torture_shuffle, NULL,
-                                          "rcu_torture_shuffle");
-                if (IS_ERR(shuffler_task)) {
-                        free_cpumask_var(shuffle_tmp_mask);
-                        firsterr = PTR_ERR(shuffler_task);
-                        VERBOSE_PRINTK_ERRSTRING("Failed to create shuffler");
-                        shuffler_task = NULL;
+                firsterr = torture_shuffle_init(shuffle_interval * HZ);
+                if (firsterr)
                         goto unwind;
-                }
         }
         if (stutter < 0)
                 stutter = 0;
         if (stutter) {
-                /* Create the stutter thread */
-                stutter_task = kthread_run(rcu_torture_stutter, NULL,
-                                          "rcu_torture_stutter");
-                if (IS_ERR(stutter_task)) {
-                        firsterr = PTR_ERR(stutter_task);
-                        VERBOSE_PRINTK_ERRSTRING("Failed to create stutter");
-                        stutter_task = NULL;
+                firsterr = torture_stutter_init(stutter * HZ);
+                if (firsterr)
                         goto unwind;
-                }
         }
         if (fqs_duration < 0)
                 fqs_duration = 0;
         if (fqs_duration) {
-                /* Create the stutter thread */
-                fqs_task = kthread_run(rcu_torture_fqs, NULL,
-                                       "rcu_torture_fqs");
-                if (IS_ERR(fqs_task)) {
-                        firsterr = PTR_ERR(fqs_task);
-                        VERBOSE_PRINTK_ERRSTRING("Failed to create fqs");
-                        fqs_task = NULL;
+                /* Create the fqs thread */
+                torture_create_kthread(rcu_torture_fqs, NULL, fqs_task);
+                if (firsterr)
                         goto unwind;
-                }
         }
         if (test_boost_interval < 1)
                 test_boost_interval = 1;
@@ -2097,49 +1549,31 @@ rcu_torture_init(void)
                 for_each_possible_cpu(i) {
                         if (cpu_is_offline(i))
                                 continue;  /* Heuristic: CPU can go offline. */
-                        retval = rcutorture_booster_init(i);
-                        if (retval < 0) {
-                                firsterr = retval;
+                        firsterr = rcutorture_booster_init(i);
+                        if (firsterr)
                                 goto unwind;
-                        }
                 }
         }
-        if (shutdown_secs > 0) {
-                shutdown_time = jiffies + shutdown_secs * HZ;
-                shutdown_task = kthread_create(rcu_torture_shutdown, NULL,
-                                               "rcu_torture_shutdown");
-                if (IS_ERR(shutdown_task)) {
-                        firsterr = PTR_ERR(shutdown_task);
-                        VERBOSE_PRINTK_ERRSTRING("Failed to create shutdown");
-                        shutdown_task = NULL;
-                        goto unwind;
-                }
-                wake_up_process(shutdown_task);
-        }
-        i = rcu_torture_onoff_init();
-        if (i != 0) {
-                firsterr = i;
+        firsterr = torture_shutdown_init(shutdown_secs, rcu_torture_cleanup);
+        if (firsterr)
                 goto unwind;
-        }
-        register_reboot_notifier(&rcutorture_shutdown_nb);
-        i = rcu_torture_stall_init();
-        if (i != 0) {
-                firsterr = i;
+        firsterr = torture_onoff_init(onoff_holdoff * HZ, onoff_interval * HZ);
+        if (firsterr)
                 goto unwind;
-        }
-        retval = rcu_torture_barrier_init();
-        if (retval != 0) {
-                firsterr = retval;
+        firsterr = rcu_torture_stall_init();
+        if (firsterr)
+                goto unwind;
+        firsterr = rcu_torture_barrier_init();
+        if (firsterr)
                 goto unwind;
-        }
         if (object_debug)
                 rcu_test_debug_objects();
         rcutorture_record_test_transition();
-        mutex_unlock(&fullstop_mutex);
+        torture_init_end();
         return 0;
 
 unwind:
-        mutex_unlock(&fullstop_mutex);
+        torture_init_end();
         rcu_torture_cleanup();
         return firsterr;
 }
diff --git a/kernel/rcu/srcu.c b/kernel/rcu/srcu.c
index 3318d8284384..c639556f3fa0 100644
--- a/kernel/rcu/srcu.c
+++ b/kernel/rcu/srcu.c
@@ -12,8 +12,8 @@
  * GNU General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ * along with this program; if not, you can access it online at
+ * http://www.gnu.org/licenses/gpl-2.0.html.
  *
  * Copyright (C) IBM Corporation, 2006
  * Copyright (C) Fujitsu, 2012
@@ -36,8 +36,6 @@
 #include <linux/delay.h>
 #include <linux/srcu.h>
 
-#include <trace/events/rcu.h>
-
 #include "rcu.h"
 
 /*
@@ -398,7 +396,7 @@ void call_srcu(struct srcu_struct *sp, struct rcu_head *head,
         rcu_batch_queue(&sp->batch_queue, head);
         if (!sp->running) {
                 sp->running = true;
-                schedule_delayed_work(&sp->work, 0);
+                queue_delayed_work(system_power_efficient_wq, &sp->work, 0);
         }
         spin_unlock_irqrestore(&sp->queue_lock, flags);
 }
@@ -674,7 +672,8 @@ static void srcu_reschedule(struct srcu_struct *sp)
         }
 
         if (pending)
-                schedule_delayed_work(&sp->work, SRCU_INTERVAL);
+                queue_delayed_work(system_power_efficient_wq,
+                                   &sp->work, SRCU_INTERVAL);
 }
 
 /*
diff --git a/kernel/rcu/tiny.c b/kernel/rcu/tiny.c
index 1254f312d024..d9efcc13008c 100644
--- a/kernel/rcu/tiny.c
+++ b/kernel/rcu/tiny.c
@@ -12,8 +12,8 @@
  * GNU General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ * along with this program; if not, you can access it online at
+ * http://www.gnu.org/licenses/gpl-2.0.html.
  *
  * Copyright IBM Corporation, 2008
  *
@@ -37,10 +37,6 @@
 #include <linux/prefetch.h>
 #include <linux/ftrace_event.h>
 
-#ifdef CONFIG_RCU_TRACE
-#include <trace/events/rcu.h>
-#endif /* #else #ifdef CONFIG_RCU_TRACE */
-
 #include "rcu.h"
 
 /* Forward declarations for tiny_plugin.h. */
diff --git a/kernel/rcu/tiny_plugin.h b/kernel/rcu/tiny_plugin.h
index 280d06cae352..431528520562 100644
--- a/kernel/rcu/tiny_plugin.h
+++ b/kernel/rcu/tiny_plugin.h
@@ -14,8 +14,8 @@
  * GNU General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ * along with this program; if not, you can access it online at
+ * http://www.gnu.org/licenses/gpl-2.0.html.
  *
  * Copyright (c) 2010 Linaro
  *
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index b3d116cd072d..0c47e300210a 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -12,8 +12,8 @@
  * GNU General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ * along with this program; if not, you can access it online at
+ * http://www.gnu.org/licenses/gpl-2.0.html.
  *
  * Copyright IBM Corporation, 2008
  *
@@ -58,8 +58,6 @@
 #include <linux/suspend.h>
 
 #include "tree.h"
-#include <trace/events/rcu.h>
-
 #include "rcu.h"
 
 MODULE_ALIAS("rcutree");
@@ -837,7 +835,7 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp,
          * to the next.  Only do this for the primary flavor of RCU.
          */
         if (rdp->rsp == rcu_state &&
-            ULONG_CMP_GE(ACCESS_ONCE(jiffies), rdp->rsp->jiffies_resched)) {
+            ULONG_CMP_GE(jiffies, rdp->rsp->jiffies_resched)) {
                 rdp->rsp->jiffies_resched += 5;
                 resched_cpu(rdp->cpu);
         }
@@ -847,7 +845,7 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp,
 
 static void record_gp_stall_check_time(struct rcu_state *rsp)
 {
-        unsigned long j = ACCESS_ONCE(jiffies);
+        unsigned long j = jiffies;
         unsigned long j1;
 
         rsp->gp_start = j;
@@ -1005,7 +1003,7 @@ static void check_cpu_stall(struct rcu_state *rsp, struct rcu_data *rdp)
 
         if (rcu_cpu_stall_suppress || !rcu_gp_in_progress(rsp))
                 return;
-        j = ACCESS_ONCE(jiffies);
+        j = jiffies;
 
         /*
          * Lots of memory barriers to reject false positives.
@@ -1423,13 +1421,14 @@ static int rcu_gp_init(struct rcu_state *rsp)
 
         /* Advance to a new grace period and initialize state. */
         record_gp_stall_check_time(rsp);
-        smp_wmb(); /* Record GP times before starting GP. */
-        rsp->gpnum++;
+        /* Record GP times before starting GP, hence smp_store_release(). */
+        smp_store_release(&rsp->gpnum, rsp->gpnum + 1);
         trace_rcu_grace_period(rsp->name, rsp->gpnum, TPS("start"));
         raw_spin_unlock_irq(&rnp->lock);
 
         /* Exclude any concurrent CPU-hotplug operations. */
         mutex_lock(&rsp->onoff_mutex);
+        smp_mb__after_unlock_lock(); /* ->gpnum increment before GP! */
 
         /*
          * Set the quiescent-state-needed bits in all the rcu_node
@@ -1557,10 +1556,11 @@ static void rcu_gp_cleanup(struct rcu_state *rsp)
         }
         rnp = rcu_get_root(rsp);
         raw_spin_lock_irq(&rnp->lock);
-        smp_mb__after_unlock_lock();
+        smp_mb__after_unlock_lock(); /* Order GP before ->completed update. */
         rcu_nocb_gp_set(rnp, nocb);
 
-        rsp->completed = rsp->gpnum; /* Declare grace period done. */
+        /* Declare grace period done. */
+        ACCESS_ONCE(rsp->completed) = rsp->gpnum;
         trace_rcu_grace_period(rsp->name, rsp->completed, TPS("end"));
         rsp->fqs_state = RCU_GP_IDLE;
         rdp = this_cpu_ptr(rsp->rda);
@@ -2304,7 +2304,7 @@ static void force_quiescent_state(struct rcu_state *rsp)
                 if (rnp_old != NULL)
                         raw_spin_unlock(&rnp_old->fqslock);
                 if (ret) {
-                        rsp->n_force_qs_lh++;
+                        ACCESS_ONCE(rsp->n_force_qs_lh)++;
                         return;
                 }
                 rnp_old = rnp;
@@ -2316,7 +2316,7 @@ static void force_quiescent_state(struct rcu_state *rsp)
         smp_mb__after_unlock_lock();
         raw_spin_unlock(&rnp_old->fqslock);
         if (ACCESS_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) {
-                rsp->n_force_qs_lh++;
+                ACCESS_ONCE(rsp->n_force_qs_lh)++;
                 raw_spin_unlock_irqrestore(&rnp_old->lock, flags);
                 return;  /* Someone beat us to it. */
         }
@@ -2639,6 +2639,58 @@ void synchronize_rcu_bh(void)
 }
 EXPORT_SYMBOL_GPL(synchronize_rcu_bh);
 
+/**
+ * get_state_synchronize_rcu - Snapshot current RCU state
+ *
+ * Returns a cookie that is used by a later call to cond_synchronize_rcu()
+ * to determine whether or not a full grace period has elapsed in the
+ * meantime.
+ */
+unsigned long get_state_synchronize_rcu(void)
+{
+        /*
+         * Any prior manipulation of RCU-protected data must happen
+         * before the load from ->gpnum.
+         */
+        smp_mb();  /* ^^^ */
+
+        /*
+         * Make sure this load happens before the purportedly
+         * time-consuming work between get_state_synchronize_rcu()
+         * and cond_synchronize_rcu().
+         */
+        return smp_load_acquire(&rcu_state->gpnum);
+}
+EXPORT_SYMBOL_GPL(get_state_synchronize_rcu);
+
+/**
+ * cond_synchronize_rcu - Conditionally wait for an RCU grace period
+ *
+ * @oldstate: return value from earlier call to get_state_synchronize_rcu()
+ *
+ * If a full RCU grace period has elapsed since the earlier call to
+ * get_state_synchronize_rcu(), just return.  Otherwise, invoke
+ * synchronize_rcu() to wait for a full grace period.
+ *
+ * Yes, this function does not take counter wrap into account.  But
+ * counter wrap is harmless.  If the counter wraps, we have waited for
+ * more than 2 billion grace periods (and way more on a 64-bit system!),
+ * so waiting for one additional grace period should be just fine.
+ */
+void cond_synchronize_rcu(unsigned long oldstate)
+{
+        unsigned long newstate;
+
+        /*
+         * Ensure that this load happens before any RCU-destructive
+         * actions the caller might carry out after we return.
+         */
+        newstate = smp_load_acquire(&rcu_state->completed);
+        if (ULONG_CMP_GE(oldstate, newstate))
+                synchronize_rcu();
+}
+EXPORT_SYMBOL_GPL(cond_synchronize_rcu);
+
 static int synchronize_sched_expedited_cpu_stop(void *data)
 {
         /*
@@ -2880,7 +2932,7 @@ static int rcu_pending(int cpu)
  * non-NULL, store an indication of whether all callbacks are lazy.
  * (If there are no callbacks, all of them are deemed to be lazy.)
  */
-static int rcu_cpu_has_callbacks(int cpu, bool *all_lazy)
+static int __maybe_unused rcu_cpu_has_callbacks(int cpu, bool *all_lazy)
 {
         bool al = true;
         bool hc = false;
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index 8c19873f1ac9..75dc3c39a02a 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -13,8 +13,8 @@
  * GNU General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ * along with this program; if not, you can access it online at
+ * http://www.gnu.org/licenses/gpl-2.0.html.
  *
  * Copyright IBM Corporation, 2008
  *
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 6e2ef4b2b920..962d1d589929 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -14,8 +14,8 @@
  * GNU General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ * along with this program; if not, you can access it online at
+ * http://www.gnu.org/licenses/gpl-2.0.html.
  *
  * Copyright Red Hat, 2009
  * Copyright IBM Corporation, 2009
@@ -1586,11 +1586,13 @@ static void rcu_prepare_kthreads(int cpu)
  * Because we not have RCU_FAST_NO_HZ, just check whether this CPU needs
  * any flavor of RCU.
  */
+#ifndef CONFIG_RCU_NOCB_CPU_ALL
 int rcu_needs_cpu(int cpu, unsigned long *delta_jiffies)
 {
         *delta_jiffies = ULONG_MAX;
         return rcu_cpu_has_callbacks(cpu, NULL);
 }
+#endif /* #ifndef CONFIG_RCU_NOCB_CPU_ALL */
 
 /*
  * Because we do not have RCU_FAST_NO_HZ, don't bother cleaning up
@@ -1656,7 +1658,7 @@ extern int tick_nohz_active;
  * only if it has been awhile since the last time we did so.  Afterwards,
  * if there are any callbacks ready for immediate invocation, return true.
  */
-static bool rcu_try_advance_all_cbs(void)
+static bool __maybe_unused rcu_try_advance_all_cbs(void)
 {
         bool cbs_ready = false;
         struct rcu_data *rdp;
@@ -1696,6 +1698,7 @@ static bool rcu_try_advance_all_cbs(void)
  *
  * The caller must have disabled interrupts.
  */
+#ifndef CONFIG_RCU_NOCB_CPU_ALL
 int rcu_needs_cpu(int cpu, unsigned long *dj)
 {
         struct rcu_dynticks *rdtp = &per_cpu(rcu_dynticks, cpu);
@@ -1726,6 +1729,7 @@ int rcu_needs_cpu(int cpu, unsigned long *dj)
         }
         return 0;
 }
+#endif /* #ifndef CONFIG_RCU_NOCB_CPU_ALL */
 
 /*
  * Prepare a CPU for idle from an RCU perspective.  The first major task
@@ -1739,6 +1743,7 @@ int rcu_needs_cpu(int cpu, unsigned long *dj)
  */
 static void rcu_prepare_for_idle(int cpu)
 {
+#ifndef CONFIG_RCU_NOCB_CPU_ALL
         struct rcu_data *rdp;
         struct rcu_dynticks *rdtp = &per_cpu(rcu_dynticks, cpu);
         struct rcu_node *rnp;
@@ -1790,6 +1795,7 @@ static void rcu_prepare_for_idle(int cpu)
                 rcu_accelerate_cbs(rsp, rnp, rdp);
                 raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */
         }
+#endif /* #ifndef CONFIG_RCU_NOCB_CPU_ALL */
 }
 
 /*
@@ -1799,11 +1805,12 @@ static void rcu_prepare_for_idle(int cpu)
  */
 static void rcu_cleanup_after_idle(int cpu)
 {
-
+#ifndef CONFIG_RCU_NOCB_CPU_ALL
         if (rcu_is_nocb_cpu(cpu))
                 return;
         if (rcu_try_advance_all_cbs())
                 invoke_rcu_core();
+#endif /* #ifndef CONFIG_RCU_NOCB_CPU_ALL */
 }
 
 /*
@@ -2101,6 +2108,7 @@ static void rcu_init_one_nocb(struct rcu_node *rnp)
         init_waitqueue_head(&rnp->nocb_gp_wq[1]);
 }
 
+#ifndef CONFIG_RCU_NOCB_CPU_ALL
 /* Is the specified CPU a no-CPUs CPU? */
 bool rcu_is_nocb_cpu(int cpu)
 {
@@ -2108,6 +2116,7 @@ bool rcu_is_nocb_cpu(int cpu)
                 return cpumask_test_cpu(cpu, rcu_nocb_mask);
         return false;
 }
+#endif /* #ifndef CONFIG_RCU_NOCB_CPU_ALL */
 
 /*
  * Enqueue the specified string of rcu_head structures onto the specified
@@ -2893,7 +2902,7 @@ static void rcu_sysidle_init_percpu_data(struct rcu_dynticks *rdtp)
  * CPU unless the grace period has extended for too long.
  *
  * This code relies on the fact that all NO_HZ_FULL CPUs are also
- * CONFIG_RCU_NOCB_CPUs.
+ * CONFIG_RCU_NOCB_CPU CPUs.
  */
 static bool rcu_nohz_full_cpu(struct rcu_state *rsp)
 {
diff --git a/kernel/rcu/tree_trace.c b/kernel/rcu/tree_trace.c
index 4def475336d4..5cdc62e1beeb 100644
--- a/kernel/rcu/tree_trace.c
+++ b/kernel/rcu/tree_trace.c
@@ -12,8 +12,8 @@
  * GNU General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ * along with this program; if not, you can access it online at
+ * http://www.gnu.org/licenses/gpl-2.0.html.
  *
  * Copyright IBM Corporation, 2008
  *
@@ -273,7 +273,7 @@ static void print_one_rcu_state(struct seq_file *m, struct rcu_state *rsp)
         seq_printf(m, "nfqs=%lu/nfqsng=%lu(%lu) fqlh=%lu oqlen=%ld/%ld\n",
                    rsp->n_force_qs, rsp->n_force_qs_ngp,
                    rsp->n_force_qs - rsp->n_force_qs_ngp,
-                   rsp->n_force_qs_lh, rsp->qlen_lazy, rsp->qlen);
+                   ACCESS_ONCE(rsp->n_force_qs_lh), rsp->qlen_lazy, rsp->qlen);
         for (rnp = &rsp->node[0]; rnp - &rsp->node[0] < rcu_num_nodes; rnp++) {
                 if (rnp->level != level) {
                         seq_puts(m, "\n");
diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c
index c54609faf233..4c0a9b0af469 100644
--- a/kernel/rcu/update.c
+++ b/kernel/rcu/update.c
@@ -12,8 +12,8 @@
  * GNU General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ * along with this program; if not, you can access it online at
+ * http://www.gnu.org/licenses/gpl-2.0.html.
  *
  * Copyright IBM Corporation, 2001
  *
@@ -49,7 +49,6 @@
 #include <linux/module.h>
 
 #define CREATE_TRACE_POINTS
-#include <trace/events/rcu.h>
 
 #include "rcu.h"
 
diff --git a/kernel/relay.c b/kernel/relay.c
index 5001c9887db1..52d6a6f56261 100644
--- a/kernel/relay.c
+++ b/kernel/relay.c
@@ -227,7 +227,7 @@ static void relay_destroy_buf(struct rchan_buf *buf)
  *      relay_remove_buf - remove a channel buffer
  *      @kref: target kernel reference that contains the relay buffer
  *
- *      Removes the file from the fileystem, which also frees the
+ *      Removes the file from the filesystem, which also frees the
  *      rchan_buf_struct and the channel buffer.  Should only be called from
  *      kref_put().
  */
diff --git a/kernel/resource.c b/kernel/resource.c
index 3f285dce9347..8957d686e29b 100644
--- a/kernel/resource.c
+++ b/kernel/resource.c
@@ -432,11 +432,6 @@ static void resource_clip(struct resource *res, resource_size_t min,
                 res->end = max;
 }
 
-static bool resource_contains(struct resource *res1, struct resource *res2)
-{
-        return res1->start <= res2->start && res1->end >= res2->end;
-}
-
 /*
  * Find empty slot in the resource tree with the given range and
  * alignment constraints
@@ -471,10 +466,11 @@ static int __find_resource(struct resource *root, struct resource *old,
                 arch_remove_reservations(&tmp);
 
                 /* Check for overflow after ALIGN() */
-                avail = *new;
                 avail.start = ALIGN(tmp.start, constraint->align);
                 avail.end = tmp.end;
+                avail.flags = new->flags & ~IORESOURCE_UNSET;
                 if (avail.start >= tmp.start) {
+                        alloc.flags = avail.flags;
                         alloc.start = constraint->alignf(constraint->alignf_data, &avail,
                                         size, constraint->align);
                         alloc.end = alloc.start + size - 1;
@@ -515,7 +511,7 @@ static int find_resource(struct resource *root, struct resource *new,
  * @newsize: new size of the resource descriptor
  * @constraint: the size and alignment constraints to be met.
  */
-int reallocate_resource(struct resource *root, struct resource *old,
+static int reallocate_resource(struct resource *root, struct resource *old,
                         resource_size_t newsize,
                         struct resource_constraint  *constraint)
 {
@@ -949,8 +945,8 @@ struct resource * __request_region(struct resource *parent,
         res->name = name;
         res->start = start;
         res->end = start + n - 1;
-        res->flags = IORESOURCE_BUSY;
-        res->flags |= flags;
+        res->flags = resource_type(parent);
+        res->flags |= IORESOURCE_BUSY | flags;
 
         write_lock(&resource_lock);
 
diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile
index 9a95c8c2af2a..ab32b7b0db5c 100644
--- a/kernel/sched/Makefile
+++ b/kernel/sched/Makefile
@@ -13,7 +13,7 @@ endif
 
 obj-y += core.o proc.o clock.o cputime.o
 obj-y += idle_task.o fair.o rt.o deadline.o stop_task.o
-obj-y += wait.o completion.o
+obj-y += wait.o completion.o idle.o
 obj-$(CONFIG_SMP) += cpupri.o cpudeadline.o
 obj-$(CONFIG_SCHED_AUTOGROUP) += auto_group.o
 obj-$(CONFIG_SCHEDSTATS) += stats.o
diff --git a/kernel/sched/auto_group.c b/kernel/sched/auto_group.c
index 4a073539c58e..e73efba98301 100644
--- a/kernel/sched/auto_group.c
+++ b/kernel/sched/auto_group.c
@@ -203,7 +203,7 @@ int proc_sched_autogroup_set_nice(struct task_struct *p, int nice)
         struct autogroup *ag;
         int err;
 
-        if (nice < -20 || nice > 19)
+        if (nice < MIN_NICE || nice > MAX_NICE)
                 return -EINVAL;
 
         err = security_task_setnice(current, nice);
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index f5c6635b806c..0ff3f34bc7e3 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -432,7 +432,7 @@ void hrtick_start(struct rq *rq, u64 delay)
         if (rq == this_rq()) {
                 __hrtick_restart(rq);
         } else if (!rq->hrtick_csd_pending) {
-                __smp_call_function_single(cpu_of(rq), &rq->hrtick_csd, 0);
+                smp_call_function_single_async(cpu_of(rq), &rq->hrtick_csd);
                 rq->hrtick_csd_pending = 1;
         }
 }
@@ -555,12 +555,15 @@ void resched_cpu(int cpu)
  * selecting an idle cpu will add more delays to the timers than intended
  * (as that cpu's timer base may not be uptodate wrt jiffies etc).
  */
-int get_nohz_timer_target(void)
+int get_nohz_timer_target(int pinned)
 {
         int cpu = smp_processor_id();
         int i;
         struct sched_domain *sd;
 
+        if (pinned || !get_sysctl_timer_migration() || !idle_cpu(cpu))
+                return cpu;
+
         rcu_read_lock();
         for_each_domain(cpu, sd) {
                 for_each_cpu(i, sched_domain_span(sd)) {
@@ -823,19 +826,13 @@ static void update_rq_clock_task(struct rq *rq, s64 delta)
 #endif
 #ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING
         if (static_key_false((&paravirt_steal_rq_enabled))) {
-                u64 st;
-
                 steal = paravirt_steal_clock(cpu_of(rq));
                 steal -= rq->prev_steal_time_rq;
 
                 if (unlikely(steal > delta))
                         steal = delta;
 
-                st = steal_ticks(steal);
-                steal = st * TICK_NSEC;
-
                 rq->prev_steal_time_rq += steal;
-
                 delta -= steal;
         }
 #endif
@@ -1745,8 +1742,10 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p)
         p->numa_scan_seq = p->mm ? p->mm->numa_scan_seq : 0;
         p->numa_scan_period = sysctl_numa_balancing_scan_delay;
         p->numa_work.next = &p->numa_work;
-        p->numa_faults = NULL;
-        p->numa_faults_buffer = NULL;
+        p->numa_faults_memory = NULL;
+        p->numa_faults_buffer_memory = NULL;
+        p->last_task_numa_placement = 0;
+        p->last_sum_exec_runtime = 0;
 
         INIT_LIST_HEAD(&p->numa_entry);
         p->numa_group = NULL;
@@ -2149,8 +2148,6 @@ static void finish_task_switch(struct rq *rq, struct task_struct *prev)
         if (mm)
                 mmdrop(mm);
         if (unlikely(prev_state == TASK_DEAD)) {
-                task_numa_free(prev);
-
                 if (prev->sched_class->task_dead)
                         prev->sched_class->task_dead(prev);
 
@@ -2167,13 +2164,6 @@ static void finish_task_switch(struct rq *rq, struct task_struct *prev)
 
 #ifdef CONFIG_SMP
 
-/* assumes rq->lock is held */
-static inline void pre_schedule(struct rq *rq, struct task_struct *prev)
-{
-        if (prev->sched_class->pre_schedule)
-                prev->sched_class->pre_schedule(rq, prev);
-}
-
 /* rq->lock is NOT held, but preemption is disabled */
 static inline void post_schedule(struct rq *rq)
 {
@@ -2191,10 +2181,6 @@ static inline void post_schedule(struct rq *rq)
 
 #else
 
-static inline void pre_schedule(struct rq *rq, struct task_struct *p)
-{
-}
-
 static inline void post_schedule(struct rq *rq)
 {
 }
@@ -2510,8 +2496,13 @@ void __kprobes preempt_count_add(int val)
         DEBUG_LOCKS_WARN_ON((preempt_count() & PREEMPT_MASK) >=
                                 PREEMPT_MASK - 10);
 #endif
-        if (preempt_count() == val)
-                trace_preempt_off(CALLER_ADDR0, get_parent_ip(CALLER_ADDR1));
+        if (preempt_count() == val) {
+                unsigned long ip = get_parent_ip(CALLER_ADDR1);
+#ifdef CONFIG_DEBUG_PREEMPT
+                current->preempt_disable_ip = ip;
+#endif
+                trace_preempt_off(CALLER_ADDR0, ip);
+        }
 }
 EXPORT_SYMBOL(preempt_count_add);
 
@@ -2554,6 +2545,13 @@ static noinline void __schedule_bug(struct task_struct *prev)
         print_modules();
         if (irqs_disabled())
                 print_irqtrace_events(prev);
+#ifdef CONFIG_DEBUG_PREEMPT
+        if (in_atomic_preempt_off()) {
+                pr_err("Preemption disabled at:");
+                print_ip_sym(current->preempt_disable_ip);
+                pr_cont("\n");
+        }
+#endif
         dump_stack();
         add_taint(TAINT_WARN, LOCKDEP_STILL_OK);
 }
@@ -2577,36 +2575,34 @@ static inline void schedule_debug(struct task_struct *prev)
         schedstat_inc(this_rq(), sched_count);
 }
 
-static void put_prev_task(struct rq *rq, struct task_struct *prev)
-{
-        if (prev->on_rq || rq->skip_clock_update < 0)
-                update_rq_clock(rq);
-        prev->sched_class->put_prev_task(rq, prev);
-}
-
 /*
  * Pick up the highest-prio task:
  */
 static inline struct task_struct *
-pick_next_task(struct rq *rq)
+pick_next_task(struct rq *rq, struct task_struct *prev)
 {
-        const struct sched_class *class;
+        const struct sched_class *class = &fair_sched_class;
         struct task_struct *p;
 
         /*
          * Optimization: we know that if all tasks are in
          * the fair class we can call that function directly:
          */
-        if (likely(rq->nr_running == rq->cfs.h_nr_running)) {
-                p = fair_sched_class.pick_next_task(rq);
-                if (likely(p))
+        if (likely(prev->sched_class == class &&
+                   rq->nr_running == rq->cfs.h_nr_running)) {
+                p = fair_sched_class.pick_next_task(rq, prev);
+                if (likely(p && p != RETRY_TASK))
                         return p;
         }
 
+again:
         for_each_class(class) {
-                p = class->pick_next_task(rq);
-                if (p)
+                p = class->pick_next_task(rq, prev);
+                if (p) {
+                        if (unlikely(p == RETRY_TASK))
+                                goto again;
                         return p;
+                }
         }
 
         BUG(); /* the idle class will always have a runnable task */
@@ -2700,13 +2696,10 @@ need_resched:
                 switch_count = &prev->nvcsw;
         }
 
-        pre_schedule(rq, prev);
-
-        if (unlikely(!rq->nr_running))
-                idle_balance(cpu, rq);
+        if (prev->on_rq || rq->skip_clock_update < 0)
+                update_rq_clock(rq);
 
-        put_prev_task(rq, prev);
-        next = pick_next_task(rq);
+        next = pick_next_task(rq, prev);
         clear_tsk_need_resched(prev);
         clear_preempt_need_resched();
         rq->skip_clock_update = 0;
@@ -2852,52 +2845,6 @@ int default_wake_function(wait_queue_t *curr, unsigned mode, int wake_flags,
 }
 EXPORT_SYMBOL(default_wake_function);
 
-static long __sched
-sleep_on_common(wait_queue_head_t *q, int state, long timeout)
-{
-        unsigned long flags;
-        wait_queue_t wait;
-
-        init_waitqueue_entry(&wait, current);
-
-        __set_current_state(state);
-
-        spin_lock_irqsave(&q->lock, flags);
-        __add_wait_queue(q, &wait);
-        spin_unlock(&q->lock);
-        timeout = schedule_timeout(timeout);
-        spin_lock_irq(&q->lock);
-        __remove_wait_queue(q, &wait);
-        spin_unlock_irqrestore(&q->lock, flags);
-
-        return timeout;
-}
-
-void __sched interruptible_sleep_on(wait_queue_head_t *q)
-{
-        sleep_on_common(q, TASK_INTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT);
-}
-EXPORT_SYMBOL(interruptible_sleep_on);
-
-long __sched
-interruptible_sleep_on_timeout(wait_queue_head_t *q, long timeout)
-{
-        return sleep_on_common(q, TASK_INTERRUPTIBLE, timeout);
-}
-EXPORT_SYMBOL(interruptible_sleep_on_timeout);
-
-void __sched sleep_on(wait_queue_head_t *q)
-{
-        sleep_on_common(q, TASK_UNINTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT);
-}
-EXPORT_SYMBOL(sleep_on);
-
-long __sched sleep_on_timeout(wait_queue_head_t *q, long timeout)
-{
-        return sleep_on_common(q, TASK_UNINTERRUPTIBLE, timeout);
-}
-EXPORT_SYMBOL(sleep_on_timeout);
-
 #ifdef CONFIG_RT_MUTEXES
 
 /*
@@ -2908,7 +2855,8 @@ EXPORT_SYMBOL(sleep_on_timeout);
  * This function changes the 'effective' priority of a task. It does
  * not touch ->normal_prio like __setscheduler().
  *
- * Used by the rt_mutex code to implement priority inheritance logic.
+ * Used by the rt_mutex code to implement priority inheritance
+ * logic. Call site only calls if the priority of the task changed.
  */
 void rt_mutex_setprio(struct task_struct *p, int prio)
 {
@@ -2998,7 +2946,7 @@ void set_user_nice(struct task_struct *p, long nice)
         unsigned long flags;
         struct rq *rq;
 
-        if (TASK_NICE(p) == nice || nice < -20 || nice > 19)
+        if (task_nice(p) == nice || nice < MIN_NICE || nice > MAX_NICE)
                 return;
         /*
          * We have to be careful, if called from sys_setpriority(),
@@ -3076,11 +3024,11 @@ SYSCALL_DEFINE1(nice, int, increment)
         if (increment > 40)
                 increment = 40;
 
-        nice = TASK_NICE(current) + increment;
-        if (nice < -20)
-                nice = -20;
-        if (nice > 19)
-                nice = 19;
+        nice = task_nice(current) + increment;
+        if (nice < MIN_NICE)
+                nice = MIN_NICE;
+        if (nice > MAX_NICE)
+                nice = MAX_NICE;
 
         if (increment < 0 && !can_nice(current, nice))
                 return -EPERM;
@@ -3109,18 +3057,6 @@ int task_prio(const struct task_struct *p)
 }
 
 /**
- * task_nice - return the nice value of a given task.
- * @p: the task in question.
- *
- * Return: The nice value [ -20 ... 0 ... 19 ].
- */
-int task_nice(const struct task_struct *p)
-{
-        return TASK_NICE(p);
-}
-EXPORT_SYMBOL(task_nice);
-
-/**
  * idle_cpu - is a given cpu idle currently?
  * @cpu: the processor in question.
  *
@@ -3189,9 +3125,8 @@ __setparam_dl(struct task_struct *p, const struct sched_attr *attr)
         dl_se->dl_new = 1;
 }
 
-/* Actually do priority change: must hold pi & rq lock. */
-static void __setscheduler(struct rq *rq, struct task_struct *p,
-                           const struct sched_attr *attr)
+static void __setscheduler_params(struct task_struct *p,
+                const struct sched_attr *attr)
 {
         int policy = attr->sched_policy;
 
@@ -3211,9 +3146,21 @@ static void __setscheduler(struct rq *rq, struct task_struct *p,
          * getparam()/getattr() don't report silly values for !rt tasks.
          */
         p->rt_priority = attr->sched_priority;
-
         p->normal_prio = normal_prio(p);
-        p->prio = rt_mutex_getprio(p);
+        set_load_weight(p);
+}
+
+/* Actually do priority change: must hold pi & rq lock. */
+static void __setscheduler(struct rq *rq, struct task_struct *p,
+                           const struct sched_attr *attr)
+{
+        __setscheduler_params(p, attr);
+
+        /*
+         * If we get here, there was no pi waiters boosting the
+         * task. It is safe to use the normal prio.
+         */
+        p->prio = normal_prio(p);
 
         if (dl_prio(p->prio))
                 p->sched_class = &dl_sched_class;
@@ -3221,8 +3168,6 @@ static void __setscheduler(struct rq *rq, struct task_struct *p,
                 p->sched_class = &rt_sched_class;
         else
                 p->sched_class = &fair_sched_class;
-
-        set_load_weight(p);
 }
 
 static void
@@ -3275,6 +3220,8 @@ static int __sched_setscheduler(struct task_struct *p,
                                 const struct sched_attr *attr,
                                 bool user)
 {
+        int newprio = dl_policy(attr->sched_policy) ? MAX_DL_PRIO - 1 :
+                      MAX_RT_PRIO - 1 - attr->sched_priority;
         int retval, oldprio, oldpolicy = -1, on_rq, running;
         int policy = attr->sched_policy;
         unsigned long flags;
@@ -3319,7 +3266,7 @@ recheck:
          */
         if (user && !capable(CAP_SYS_NICE)) {
                 if (fair_policy(policy)) {
-                        if (attr->sched_nice < TASK_NICE(p) &&
+                        if (attr->sched_nice < task_nice(p) &&
                             !can_nice(p, attr->sched_nice))
                                 return -EPERM;
                 }
@@ -3352,7 +3299,7 @@ recheck:
                  * SCHED_NORMAL if the RLIMIT_NICE would normally permit it.
                  */
                 if (p->policy == SCHED_IDLE && policy != SCHED_IDLE) {
-                        if (!can_nice(p, TASK_NICE(p)))
+                        if (!can_nice(p, task_nice(p)))
                                 return -EPERM;
                 }
 
@@ -3389,16 +3336,18 @@ recheck:
         }
 
         /*
-         * If not changing anything there's no need to proceed further:
+         * If not changing anything there's no need to proceed further,
+         * but store a possible modification of reset_on_fork.
          */
         if (unlikely(policy == p->policy)) {
-                if (fair_policy(policy) && attr->sched_nice != TASK_NICE(p))
+                if (fair_policy(policy) && attr->sched_nice != task_nice(p))
                         goto change;
                 if (rt_policy(policy) && attr->sched_priority != p->rt_priority)
                         goto change;
                 if (dl_policy(policy))
                         goto change;
 
+                p->sched_reset_on_fork = reset_on_fork;
                 task_rq_unlock(rq, p, &flags);
                 return 0;
         }
@@ -3452,6 +3401,24 @@ change:
                 return -EBUSY;
         }
 
+        p->sched_reset_on_fork = reset_on_fork;
+        oldprio = p->prio;
+
+        /*
+         * Special case for priority boosted tasks.
+         *
+         * If the new priority is lower or equal (user space view)
+         * than the current (boosted) priority, we just store the new
+         * normal parameters and do not touch the scheduler class and
+         * the runqueue. This will be done when the task deboost
+         * itself.
+         */
+        if (rt_mutex_check_prio(p, newprio)) {
+                __setscheduler_params(p, attr);
+                task_rq_unlock(rq, p, &flags);
+                return 0;
+        }
+
         on_rq = p->on_rq;
         running = task_current(rq, p);
         if (on_rq)
@@ -3459,16 +3426,18 @@ change:
         if (running)
                 p->sched_class->put_prev_task(rq, p);
 
-        p->sched_reset_on_fork = reset_on_fork;
-
-        oldprio = p->prio;
         prev_class = p->sched_class;
         __setscheduler(rq, p, attr);
 
         if (running)
                 p->sched_class->set_curr_task(rq);
-        if (on_rq)
-                enqueue_task(rq, p, 0);
+        if (on_rq) {
+                /*
+                 * We enqueue to tail when the priority of a task is
+                 * increased (user space view).
+                 */
+                enqueue_task(rq, p, oldprio <= p->prio ? ENQUEUE_HEAD : 0);
+        }
 
         check_class_changed(rq, p, prev_class, oldprio);
         task_rq_unlock(rq, p, &flags);
@@ -3624,7 +3593,7 @@ static int sched_copy_attr(struct sched_attr __user *uattr,
          * XXX: do we want to be lenient like existing syscalls; or do we want
          * to be strict and return an error on out-of-bounds values?
          */
-        attr->sched_nice = clamp(attr->sched_nice, -20, 19);
+        attr->sched_nice = clamp(attr->sched_nice, MIN_NICE, MAX_NICE);
 
 out:
         return ret;
@@ -3845,7 +3814,7 @@ SYSCALL_DEFINE4(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr,
         else if (task_has_rt_policy(p))
                 attr.sched_priority = p->rt_priority;
         else
-                attr.sched_nice = TASK_NICE(p);
+                attr.sched_nice = task_nice(p);
 
         rcu_read_unlock();
 
@@ -4483,6 +4452,7 @@ void init_idle(struct task_struct *idle, int cpu)
         rcu_read_unlock();
 
         rq->curr = rq->idle = idle;
+        idle->on_rq = 1;
 #if defined(CONFIG_SMP)
         idle->on_cpu = 1;
 #endif
@@ -4702,8 +4672,10 @@ void idle_task_exit(void)
 
         BUG_ON(cpu_online(smp_processor_id()));
 
-        if (mm != &init_mm)
+        if (mm != &init_mm) {
                 switch_mm(mm, &init_mm, current);
+                finish_arch_post_lock_switch();
+        }
         mmdrop(mm);
 }
 
@@ -4721,6 +4693,22 @@ static void calc_load_migrate(struct rq *rq)
                 atomic_long_add(delta, &calc_load_tasks);
 }
 
+static void put_prev_task_fake(struct rq *rq, struct task_struct *prev)
+{
+}
+
+static const struct sched_class fake_sched_class = {
+        .put_prev_task = put_prev_task_fake,
+};
+
+static struct task_struct fake_task = {
+        /*
+         * Avoid pull_{rt,dl}_task()
+         */
+        .prio = MAX_PRIO + 1,
+        .sched_class = &fake_sched_class,
+};
+
 /*
  * Migrate all tasks from the rq, sleeping tasks will be migrated by
  * try_to_wake_up()->select_task_rq().
@@ -4761,7 +4749,7 @@ static void migrate_tasks(unsigned int dead_cpu)
                 if (rq->nr_running == 1)
                         break;
 
-                next = pick_next_task(rq);
+                next = pick_next_task(rq, &fake_task);
                 BUG_ON(!next);
                 next->sched_class->put_prev_task(rq, next);
 
@@ -4851,7 +4839,7 @@ set_table_entry(struct ctl_table *entry,
 static struct ctl_table *
 sd_alloc_ctl_domain_table(struct sched_domain *sd)
 {
-        struct ctl_table *table = sd_alloc_ctl_entry(13);
+        struct ctl_table *table = sd_alloc_ctl_entry(14);
 
         if (table == NULL)
                 return NULL;
@@ -4879,9 +4867,12 @@ sd_alloc_ctl_domain_table(struct sched_domain *sd)
                 sizeof(int), 0644, proc_dointvec_minmax, false);
         set_table_entry(&table[10], "flags", &sd->flags,
                 sizeof(int), 0644, proc_dointvec_minmax, false);
-        set_table_entry(&table[11], "name", sd->name,
+        set_table_entry(&table[11], "max_newidle_lb_cost",
+                &sd->max_newidle_lb_cost,
+                sizeof(long), 0644, proc_doulongvec_minmax, false);
+        set_table_entry(&table[12], "name", sd->name,
                 CORENAME_MAX_SIZE, 0444, proc_dostring, false);
-        /* &table[12] is terminator */
+        /* &table[13] is terminator */
 
         return table;
 }
@@ -6858,7 +6849,6 @@ void __init sched_init(void)
 
                 rq->rt.rt_runtime = def_rt_bandwidth.rt_runtime;
 #ifdef CONFIG_RT_GROUP_SCHED
-                INIT_LIST_HEAD(&rq->leaf_rt_rq_list);
                 init_tg_rt_entry(&root_task_group, &rq->rt, NULL, i, NULL);
 #endif
 
@@ -6947,7 +6937,8 @@ void __might_sleep(const char *file, int line, int preempt_offset)
         static unsigned long prev_jiffy;        /* ratelimiting */
 
         rcu_sleep_check(); /* WARN_ON_ONCE() by default, no rate limit reqd. */
-        if ((preempt_count_equals(preempt_offset) && !irqs_disabled()) ||
+        if ((preempt_count_equals(preempt_offset) && !irqs_disabled() &&
+             !is_idle_task(current)) ||
             system_state != SYSTEM_RUNNING || oops_in_progress)
                 return;
         if (time_before(jiffies, prev_jiffy + HZ) && prev_jiffy)
@@ -6965,6 +6956,13 @@ void __might_sleep(const char *file, int line, int preempt_offset)
         debug_show_held_locks(current);
         if (irqs_disabled())
                 print_irqtrace_events(current);
+#ifdef CONFIG_DEBUG_PREEMPT
+        if (!preempt_count_equals(preempt_offset)) {
+                pr_err("Preemption disabled at:");
+                print_ip_sym(current->preempt_disable_ip);
+                pr_cont("\n");
+        }
+#endif
         dump_stack();
 }
 EXPORT_SYMBOL(__might_sleep);
@@ -7018,7 +7016,7 @@ void normalize_rt_tasks(void)
                          * Renice negative nice level userspace
                          * tasks back to 0:
                          */
-                        if (TASK_NICE(p) < 0 && p->mm)
+                        if (task_nice(p) < 0 && p->mm)
                                 set_user_nice(p, 0);
                         continue;
                 }
@@ -7186,7 +7184,7 @@ void sched_move_task(struct task_struct *tsk)
         if (unlikely(running))
                 tsk->sched_class->put_prev_task(rq, tsk);
 
-        tg = container_of(task_css_check(tsk, cpu_cgroup_subsys_id,
+        tg = container_of(task_css_check(tsk, cpu_cgrp_id,
                                 lockdep_is_held(&tsk->sighand->siglock)),
                           struct task_group, css);
         tg = autogroup_task_group(tsk, tg);
@@ -7613,7 +7611,7 @@ static int cpu_cgroup_can_attach(struct cgroup_subsys_state *css,
 {
         struct task_struct *task;
 
-        cgroup_taskset_for_each(task, css, tset) {
+        cgroup_taskset_for_each(task, tset) {
 #ifdef CONFIG_RT_GROUP_SCHED
                 if (!sched_rt_can_attach(css_tg(css), task))
                         return -EINVAL;
@@ -7631,7 +7629,7 @@ static void cpu_cgroup_attach(struct cgroup_subsys_state *css,
 {
         struct task_struct *task;
 
-        cgroup_taskset_for_each(task, css, tset)
+        cgroup_taskset_for_each(task, tset)
                 sched_move_task(task);
 }
 
@@ -7970,8 +7968,7 @@ static struct cftype cpu_files[] = {
         { }     /* terminate */
 };
 
-struct cgroup_subsys cpu_cgroup_subsys = {
-        .name           = "cpu",
+struct cgroup_subsys cpu_cgrp_subsys = {
         .css_alloc      = cpu_cgroup_css_alloc,
         .css_free       = cpu_cgroup_css_free,
         .css_online     = cpu_cgroup_css_online,
@@ -7979,7 +7976,6 @@ struct cgroup_subsys cpu_cgroup_subsys = {
         .can_attach     = cpu_cgroup_can_attach,
         .attach         = cpu_cgroup_attach,
         .exit           = cpu_cgroup_exit,
-        .subsys_id      = cpu_cgroup_subsys_id,
         .base_cftypes   = cpu_files,
         .early_init     = 1,
 };
diff --git a/kernel/sched/cpuacct.c b/kernel/sched/cpuacct.c
index 622e0818f905..c143ee380e3a 100644
--- a/kernel/sched/cpuacct.c
+++ b/kernel/sched/cpuacct.c
@@ -41,7 +41,7 @@ static inline struct cpuacct *css_ca(struct cgroup_subsys_state *css)
 /* return cpu accounting group to which this task belongs */
 static inline struct cpuacct *task_ca(struct task_struct *tsk)
 {
-        return css_ca(task_css(tsk, cpuacct_subsys_id));
+        return css_ca(task_css(tsk, cpuacct_cgrp_id));
 }
 
 static inline struct cpuacct *parent_ca(struct cpuacct *ca)
@@ -275,11 +275,9 @@ void cpuacct_account_field(struct task_struct *p, int index, u64 val)
         rcu_read_unlock();
 }
 
-struct cgroup_subsys cpuacct_subsys = {
-        .name           = "cpuacct",
+struct cgroup_subsys cpuacct_cgrp_subsys = {
         .css_alloc      = cpuacct_css_alloc,
         .css_free       = cpuacct_css_free,
-        .subsys_id      = cpuacct_subsys_id,
         .base_cftypes   = files,
         .early_init     = 1,
 };
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index 99947919e30b..a95097cb4591 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -142,7 +142,7 @@ void account_user_time(struct task_struct *p, cputime_t cputime,
         p->utimescaled += cputime_scaled;
         account_group_user_time(p, cputime);
 
-        index = (TASK_NICE(p) > 0) ? CPUTIME_NICE : CPUTIME_USER;
+        index = (task_nice(p) > 0) ? CPUTIME_NICE : CPUTIME_USER;
 
         /* Add user time to cpustat. */
         task_group_account_field(p, index, (__force u64) cputime);
@@ -169,7 +169,7 @@ static void account_guest_time(struct task_struct *p, cputime_t cputime,
         p->gtime += cputime;
 
         /* Add guest time to cpustat. */
-        if (TASK_NICE(p) > 0) {
+        if (task_nice(p) > 0) {
                 cpustat[CPUTIME_NICE] += (__force u64) cputime;
                 cpustat[CPUTIME_GUEST_NICE] += (__force u64) cputime;
         } else {
@@ -258,16 +258,22 @@ static __always_inline bool steal_account_process_tick(void)
 {
 #ifdef CONFIG_PARAVIRT
         if (static_key_false(&paravirt_steal_enabled)) {
-                u64 steal, st = 0;
+                u64 steal;
+                cputime_t steal_ct;
 
                 steal = paravirt_steal_clock(smp_processor_id());
                 steal -= this_rq()->prev_steal_time;
 
-                st = steal_ticks(steal);
-                this_rq()->prev_steal_time += st * TICK_NSEC;
+                /*
+                 * cputime_t may be less precise than nsecs (eg: if it's
+                 * based on jiffies). Lets cast the result to cputime
+                 * granularity and account the rest on the next rounds.
+                 */
+                steal_ct = nsecs_to_cputime(steal);
+                this_rq()->prev_steal_time += cputime_to_nsecs(steal_ct);
 
-                account_steal_time(st);
-                return st;
+                account_steal_time(steal_ct);
+                return steal_ct;
         }
 #endif
         return false;
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 6e79b3faa4cd..27ef40925525 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -210,6 +210,16 @@ static inline int has_pushable_dl_tasks(struct rq *rq)
 
 static int push_dl_task(struct rq *rq);
 
+static inline bool need_pull_dl_task(struct rq *rq, struct task_struct *prev)
+{
+        return dl_task(prev);
+}
+
+static inline void set_post_schedule(struct rq *rq)
+{
+        rq->post_schedule = has_pushable_dl_tasks(rq);
+}
+
 #else
 
 static inline
@@ -232,6 +242,19 @@ void dec_dl_migration(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
 {
 }
 
+static inline bool need_pull_dl_task(struct rq *rq, struct task_struct *prev)
+{
+        return false;
+}
+
+static inline int pull_dl_task(struct rq *rq)
+{
+        return 0;
+}
+
+static inline void set_post_schedule(struct rq *rq)
+{
+}
 #endif /* CONFIG_SMP */
 
 static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags);
@@ -586,8 +609,8 @@ static void update_curr_dl(struct rq *rq)
          * approach need further study.
          */
         delta_exec = rq_clock_task(rq) - curr->se.exec_start;
-        if (unlikely((s64)delta_exec < 0))
-                delta_exec = 0;
+        if (unlikely((s64)delta_exec <= 0))
+                return;
 
         schedstat_set(curr->se.statistics.exec_max,
                       max(curr->se.statistics.exec_max, delta_exec));
@@ -942,6 +965,8 @@ static void check_preempt_equal_dl(struct rq *rq, struct task_struct *p)
         resched_task(rq->curr);
 }
 
+static int pull_dl_task(struct rq *this_rq);
+
 #endif /* CONFIG_SMP */
 
 /*
@@ -988,7 +1013,7 @@ static struct sched_dl_entity *pick_next_dl_entity(struct rq *rq,
         return rb_entry(left, struct sched_dl_entity, rb_node);
 }
 
-struct task_struct *pick_next_task_dl(struct rq *rq)
+struct task_struct *pick_next_task_dl(struct rq *rq, struct task_struct *prev)
 {
         struct sched_dl_entity *dl_se;
         struct task_struct *p;
@@ -996,9 +1021,20 @@ struct task_struct *pick_next_task_dl(struct rq *rq)
 
         dl_rq = &rq->dl;
 
+        if (need_pull_dl_task(rq, prev))
+                pull_dl_task(rq);
+        /*
+         * When prev is DL, we may throttle it in put_prev_task().
+         * So, we update time before we check for dl_nr_running.
+         */
+        if (prev->sched_class == &dl_sched_class)
+                update_curr_dl(rq);
+
         if (unlikely(!dl_rq->dl_nr_running))
                 return NULL;
 
+        put_prev_task(rq, prev);
+
         dl_se = pick_next_dl_entity(rq, dl_rq);
         BUG_ON(!dl_se);
 
@@ -1013,9 +1049,7 @@ struct task_struct *pick_next_task_dl(struct rq *rq)
                 start_hrtick_dl(rq, p);
 #endif
 
-#ifdef CONFIG_SMP
-        rq->post_schedule = has_pushable_dl_tasks(rq);
-#endif /* CONFIG_SMP */
+        set_post_schedule(rq);
 
         return p;
 }
@@ -1424,13 +1458,6 @@ skip:
         return ret;
 }
 
-static void pre_schedule_dl(struct rq *rq, struct task_struct *prev)
-{
-        /* Try to pull other tasks here */
-        if (dl_task(prev))
-                pull_dl_task(rq);
-}
-
 static void post_schedule_dl(struct rq *rq)
 {
         push_dl_tasks(rq);
@@ -1558,7 +1585,7 @@ static void switched_to_dl(struct rq *rq, struct task_struct *p)
         if (unlikely(p->dl.dl_throttled))
                 return;
 
-        if (p->on_rq || rq->curr != p) {
+        if (p->on_rq && rq->curr != p) {
 #ifdef CONFIG_SMP
                 if (rq->dl.overloaded && push_dl_task(rq) && rq != task_rq(p))
                         /* Only reschedule if pushing failed */
@@ -1623,7 +1650,6 @@ const struct sched_class dl_sched_class = {
         .set_cpus_allowed       = set_cpus_allowed_dl,
         .rq_online              = rq_online_dl,
         .rq_offline             = rq_offline_dl,
-        .pre_schedule           = pre_schedule_dl,
         .post_schedule          = post_schedule_dl,
         .task_woken             = task_woken_dl,
 #endif
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index dd52e7ffb10e..695f9773bb60 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -111,8 +111,7 @@ static char *task_group_path(struct task_group *tg)
         if (autogroup_path(tg, group_path, PATH_MAX))
                 return group_path;
 
-        cgroup_path(tg->css.cgroup, group_path, PATH_MAX);
-        return group_path;
+        return cgroup_path(tg->css.cgroup, group_path, PATH_MAX);
 }
 #endif
 
@@ -321,6 +320,7 @@ do {									\
         P(sched_goidle);
 #ifdef CONFIG_SMP
         P64(avg_idle);
+        P64(max_idle_balance_cost);
 #endif
 
         P(ttwu_count);
@@ -533,15 +533,15 @@ static void sched_show_numa(struct task_struct *p, struct seq_file *m)
                         unsigned long nr_faults = -1;
                         int cpu_current, home_node;
 
-                        if (p->numa_faults)
-                                nr_faults = p->numa_faults[2*node + i];
+                        if (p->numa_faults_memory)
+                                nr_faults = p->numa_faults_memory[2*node + i];
 
                         cpu_current = !i ? (task_node(p) == node) :
                                 (pol && node_isset(node, pol->v.nodes));
 
                         home_node = (p->numa_preferred_nid == node);
 
-                        SEQ_printf(m, "numa_faults, %d, %d, %d, %d, %ld\n",
+                        SEQ_printf(m, "numa_faults_memory, %d, %d, %d, %d, %ld\n",
                                 i, node, cpu_current, home_node, nr_faults);
                 }
         }
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 9b4c4f320130..7e9bd0b1fa9e 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -322,13 +322,13 @@ static inline void list_del_leaf_cfs_rq(struct cfs_rq *cfs_rq)
         list_for_each_entry_rcu(cfs_rq, &rq->leaf_cfs_rq_list, leaf_cfs_rq_list)
 
 /* Do the two (enqueued) entities belong to the same group ? */
-static inline int
+static inline struct cfs_rq *
 is_same_group(struct sched_entity *se, struct sched_entity *pse)
 {
         if (se->cfs_rq == pse->cfs_rq)
-                return 1;
+                return se->cfs_rq;
 
-        return 0;
+        return NULL;
 }
 
 static inline struct sched_entity *parent_entity(struct sched_entity *se)
@@ -336,17 +336,6 @@ static inline struct sched_entity *parent_entity(struct sched_entity *se)
         return se->parent;
 }
 
-/* return depth at which a sched entity is present in the hierarchy */
-static inline int depth_se(struct sched_entity *se)
-{
-        int depth = 0;
-
-        for_each_sched_entity(se)
-                depth++;
-
-        return depth;
-}
-
 static void
 find_matching_se(struct sched_entity **se, struct sched_entity **pse)
 {
@@ -360,8 +349,8 @@ find_matching_se(struct sched_entity **se, struct sched_entity **pse)
          */
 
         /* First walk up until both entities are at same depth */
-        se_depth = depth_se(*se);
-        pse_depth = depth_se(*pse);
+        se_depth = (*se)->depth;
+        pse_depth = (*pse)->depth;
 
         while (se_depth > pse_depth) {
                 se_depth--;
@@ -426,12 +415,6 @@ static inline void list_del_leaf_cfs_rq(struct cfs_rq *cfs_rq)
 #define for_each_leaf_cfs_rq(rq, cfs_rq) \
                 for (cfs_rq = &rq->cfs; cfs_rq; cfs_rq = NULL)
 
-static inline int
-is_same_group(struct sched_entity *se, struct sched_entity *pse)
-{
-        return 1;
-}
-
 static inline struct sched_entity *parent_entity(struct sched_entity *se)
 {
         return NULL;
@@ -819,14 +802,6 @@ unsigned int sysctl_numa_balancing_scan_size = 256;
 /* Scan @scan_size MB every @scan_period after an initial @scan_delay in ms */
 unsigned int sysctl_numa_balancing_scan_delay = 1000;
 
-/*
- * After skipping a page migration on a shared page, skip N more numa page
- * migrations unconditionally. This reduces the number of NUMA migrations
- * in shared memory workloads, and has the effect of pulling tasks towards
- * where their memory lives, over pulling the memory towards the task.
- */
-unsigned int sysctl_numa_balancing_migrate_deferred = 16;
-
 static unsigned int task_nr_scan_windows(struct task_struct *p)
 {
         unsigned long rss = 0;
@@ -893,10 +868,26 @@ struct numa_group {
         struct list_head task_list;
 
         struct rcu_head rcu;
+        nodemask_t active_nodes;
         unsigned long total_faults;
+        /*
+         * Faults_cpu is used to decide whether memory should move
+         * towards the CPU. As a consequence, these stats are weighted
+         * more by CPU use than by memory faults.
+         */
+        unsigned long *faults_cpu;
         unsigned long faults[0];
 };
 
+/* Shared or private faults. */
+#define NR_NUMA_HINT_FAULT_TYPES 2
+
+/* Memory and CPU locality */
+#define NR_NUMA_HINT_FAULT_STATS (NR_NUMA_HINT_FAULT_TYPES * 2)
+
+/* Averaged statistics, and temporary buffers. */
+#define NR_NUMA_HINT_FAULT_BUCKETS (NR_NUMA_HINT_FAULT_STATS * 2)
+
 pid_t task_numa_group_id(struct task_struct *p)
 {
         return p->numa_group ? p->numa_group->gid : 0;
@@ -904,16 +895,16 @@ pid_t task_numa_group_id(struct task_struct *p)
 
 static inline int task_faults_idx(int nid, int priv)
 {
-        return 2 * nid + priv;
+        return NR_NUMA_HINT_FAULT_TYPES * nid + priv;
 }
 
 static inline unsigned long task_faults(struct task_struct *p, int nid)
 {
-        if (!p->numa_faults)
+        if (!p->numa_faults_memory)
                 return 0;
 
-        return p->numa_faults[task_faults_idx(nid, 0)] +
-                p->numa_faults[task_faults_idx(nid, 1)];
+        return p->numa_faults_memory[task_faults_idx(nid, 0)] +
+                p->numa_faults_memory[task_faults_idx(nid, 1)];
 }
 
 static inline unsigned long group_faults(struct task_struct *p, int nid)
@@ -925,6 +916,12 @@ static inline unsigned long group_faults(struct task_struct *p, int nid)
                 p->numa_group->faults[task_faults_idx(nid, 1)];
 }
 
+static inline unsigned long group_faults_cpu(struct numa_group *group, int nid)
+{
+        return group->faults_cpu[task_faults_idx(nid, 0)] +
+                group->faults_cpu[task_faults_idx(nid, 1)];
+}
+
 /*
  * These return the fraction of accesses done by a particular task, or
  * task group, on a particular numa node.  The group weight is given a
@@ -935,7 +932,7 @@ static inline unsigned long task_weight(struct task_struct *p, int nid)
 {
         unsigned long total_faults;
 
-        if (!p->numa_faults)
+        if (!p->numa_faults_memory)
                 return 0;
 
         total_faults = p->total_numa_faults;
@@ -954,6 +951,69 @@ static inline unsigned long group_weight(struct task_struct *p, int nid)
         return 1000 * group_faults(p, nid) / p->numa_group->total_faults;
 }
 
+bool should_numa_migrate_memory(struct task_struct *p, struct page * page,
+                                int src_nid, int dst_cpu)
+{
+        struct numa_group *ng = p->numa_group;
+        int dst_nid = cpu_to_node(dst_cpu);
+        int last_cpupid, this_cpupid;
+
+        this_cpupid = cpu_pid_to_cpupid(dst_cpu, current->pid);
+
+        /*
+         * Multi-stage node selection is used in conjunction with a periodic
+         * migration fault to build a temporal task<->page relation. By using
+         * a two-stage filter we remove short/unlikely relations.
+         *
+         * Using P(p) ~ n_p / n_t as per frequentist probability, we can equate
+         * a task's usage of a particular page (n_p) per total usage of this
+         * page (n_t) (in a given time-span) to a probability.
+         *
+         * Our periodic faults will sample this probability and getting the
+         * same result twice in a row, given these samples are fully
+         * independent, is then given by P(n)^2, provided our sample period
+         * is sufficiently short compared to the usage pattern.
+         *
+         * This quadric squishes small probabilities, making it less likely we
+         * act on an unlikely task<->page relation.
+         */
+        last_cpupid = page_cpupid_xchg_last(page, this_cpupid);
+        if (!cpupid_pid_unset(last_cpupid) &&
+                                cpupid_to_nid(last_cpupid) != dst_nid)
+                return false;
+
+        /* Always allow migrate on private faults */
+        if (cpupid_match_pid(p, last_cpupid))
+                return true;
+
+        /* A shared fault, but p->numa_group has not been set up yet. */
+        if (!ng)
+                return true;
+
+        /*
+         * Do not migrate if the destination is not a node that
+         * is actively used by this numa group.
+         */
+        if (!node_isset(dst_nid, ng->active_nodes))
+                return false;
+
+        /*
+         * Source is a node that is not actively used by this
+         * numa group, while the destination is. Migrate.
+         */
+        if (!node_isset(src_nid, ng->active_nodes))
+                return true;
+
+        /*
+         * Both source and destination are nodes in active
+         * use by this numa group. Maximize memory bandwidth
+         * by migrating from more heavily used groups, to less
+         * heavily used ones, spreading the load around.
+         * Use a 1/4 hysteresis to avoid spurious page movement.
+         */
+        return group_faults(p, dst_nid) < (group_faults(p, src_nid) * 3 / 4);
+}
+
 static unsigned long weighted_cpuload(const int cpu);
 static unsigned long source_load(int cpu, int type);
 static unsigned long target_load(int cpu, int type);
@@ -1267,7 +1327,7 @@ static int task_numa_migrate(struct task_struct *p)
 static void numa_migrate_preferred(struct task_struct *p)
 {
         /* This task has no NUMA fault statistics yet */
-        if (unlikely(p->numa_preferred_nid == -1 || !p->numa_faults))
+        if (unlikely(p->numa_preferred_nid == -1 || !p->numa_faults_memory))
                 return;
 
         /* Periodically retry migrating the task to the preferred node */
@@ -1282,6 +1342,38 @@ static void numa_migrate_preferred(struct task_struct *p)
 }
 
 /*
+ * Find the nodes on which the workload is actively running. We do this by
+ * tracking the nodes from which NUMA hinting faults are triggered. This can
+ * be different from the set of nodes where the workload's memory is currently
+ * located.
+ *
+ * The bitmask is used to make smarter decisions on when to do NUMA page
+ * migrations, To prevent flip-flopping, and excessive page migrations, nodes
+ * are added when they cause over 6/16 of the maximum number of faults, but
+ * only removed when they drop below 3/16.
+ */
+static void update_numa_active_node_mask(struct numa_group *numa_group)
+{
+        unsigned long faults, max_faults = 0;
+        int nid;
+
+        for_each_online_node(nid) {
+                faults = group_faults_cpu(numa_group, nid);
+                if (faults > max_faults)
+                        max_faults = faults;
+        }
+
+        for_each_online_node(nid) {
+                faults = group_faults_cpu(numa_group, nid);
+                if (!node_isset(nid, numa_group->active_nodes)) {
+                        if (faults > max_faults * 6 / 16)
+                                node_set(nid, numa_group->active_nodes);
+                } else if (faults < max_faults * 3 / 16)
+                        node_clear(nid, numa_group->active_nodes);
+        }
+}
+
+/*
  * When adapting the scan rate, the period is divided into NUMA_PERIOD_SLOTS
  * increments. The more local the fault statistics are, the higher the scan
  * period will be for the next scan window. If local/remote ratio is below
@@ -1355,11 +1447,41 @@ static void update_task_scan_period(struct task_struct *p,
         memset(p->numa_faults_locality, 0, sizeof(p->numa_faults_locality));
 }
 
+/*
+ * Get the fraction of time the task has been running since the last
+ * NUMA placement cycle. The scheduler keeps similar statistics, but
+ * decays those on a 32ms period, which is orders of magnitude off
+ * from the dozens-of-seconds NUMA balancing period. Use the scheduler
+ * stats only if the task is so new there are no NUMA statistics yet.
+ */
+static u64 numa_get_avg_runtime(struct task_struct *p, u64 *period)
+{
+        u64 runtime, delta, now;
+        /* Use the start of this time slice to avoid calculations. */
+        now = p->se.exec_start;
+        runtime = p->se.sum_exec_runtime;
+
+        if (p->last_task_numa_placement) {
+                delta = runtime - p->last_sum_exec_runtime;
+                *period = now - p->last_task_numa_placement;
+        } else {
+                delta = p->se.avg.runnable_avg_sum;
+                *period = p->se.avg.runnable_avg_period;
+        }
+
+        p->last_sum_exec_runtime = runtime;
+        p->last_task_numa_placement = now;
+
+        return delta;
+}
+
 static void task_numa_placement(struct task_struct *p)
 {
         int seq, nid, max_nid = -1, max_group_nid = -1;
         unsigned long max_faults = 0, max_group_faults = 0;
         unsigned long fault_types[2] = { 0, 0 };
+        unsigned long total_faults;
+        u64 runtime, period;
         spinlock_t *group_lock = NULL;
 
         seq = ACCESS_ONCE(p->mm->numa_scan_seq);
@@ -1368,6 +1490,10 @@ static void task_numa_placement(struct task_struct *p)
         p->numa_scan_seq = seq;
         p->numa_scan_period_max = task_scan_max(p);
 
+        total_faults = p->numa_faults_locality[0] +
+                       p->numa_faults_locality[1];
+        runtime = numa_get_avg_runtime(p, &period);
+
         /* If the task is part of a group prevent parallel updates to group stats */
         if (p->numa_group) {
                 group_lock = &p->numa_group->lock;
@@ -1379,24 +1505,37 @@ static void task_numa_placement(struct task_struct *p)
                 unsigned long faults = 0, group_faults = 0;
                 int priv, i;
 
-                for (priv = 0; priv < 2; priv++) {
-                        long diff;
+                for (priv = 0; priv < NR_NUMA_HINT_FAULT_TYPES; priv++) {
+                        long diff, f_diff, f_weight;
 
                         i = task_faults_idx(nid, priv);
-                        diff = -p->numa_faults[i];
 
                         /* Decay existing window, copy faults since last scan */
-                        p->numa_faults[i] >>= 1;
-                        p->numa_faults[i] += p->numa_faults_buffer[i];
-                        fault_types[priv] += p->numa_faults_buffer[i];
-                        p->numa_faults_buffer[i] = 0;
+                        diff = p->numa_faults_buffer_memory[i] - p->numa_faults_memory[i] / 2;
+                        fault_types[priv] += p->numa_faults_buffer_memory[i];
+                        p->numa_faults_buffer_memory[i] = 0;
 
-                        faults += p->numa_faults[i];
-                        diff += p->numa_faults[i];
+                        /*
+                         * Normalize the faults_from, so all tasks in a group
+                         * count according to CPU use, instead of by the raw
+                         * number of faults. Tasks with little runtime have
+                         * little over-all impact on throughput, and thus their
+                         * faults are less important.
+                         */
+                        f_weight = div64_u64(runtime << 16, period + 1);
+                        f_weight = (f_weight * p->numa_faults_buffer_cpu[i]) /
+                                   (total_faults + 1);
+                        f_diff = f_weight - p->numa_faults_cpu[i] / 2;
+                        p->numa_faults_buffer_cpu[i] = 0;
+
+                        p->numa_faults_memory[i] += diff;
+                        p->numa_faults_cpu[i] += f_diff;
+                        faults += p->numa_faults_memory[i];
                         p->total_numa_faults += diff;
                         if (p->numa_group) {
                                 /* safe because we can only change our own group */
                                 p->numa_group->faults[i] += diff;
+                                p->numa_group->faults_cpu[i] += f_diff;
                                 p->numa_group->total_faults += diff;
                                 group_faults += p->numa_group->faults[i];
                         }
@@ -1416,6 +1555,7 @@ static void task_numa_placement(struct task_struct *p)
         update_task_scan_period(p, fault_types[0], fault_types[1]);
 
         if (p->numa_group) {
+                update_numa_active_node_mask(p->numa_group);
                 /*
                  * If the preferred task and group nids are different,
                  * iterate over the nodes again to find the best place.
@@ -1465,7 +1605,7 @@ static void task_numa_group(struct task_struct *p, int cpupid, int flags,
 
         if (unlikely(!p->numa_group)) {
                 unsigned int size = sizeof(struct numa_group) +
-                                    2*nr_node_ids*sizeof(unsigned long);
+                                    4*nr_node_ids*sizeof(unsigned long);
 
                 grp = kzalloc(size, GFP_KERNEL | __GFP_NOWARN);
                 if (!grp)
@@ -1475,9 +1615,14 @@ static void task_numa_group(struct task_struct *p, int cpupid, int flags,
                 spin_lock_init(&grp->lock);
                 INIT_LIST_HEAD(&grp->task_list);
                 grp->gid = p->pid;
+                /* Second half of the array tracks nids where faults happen */
+                grp->faults_cpu = grp->faults + NR_NUMA_HINT_FAULT_TYPES *
+                                                nr_node_ids;
+
+                node_set(task_node(current), grp->active_nodes);
 
-                for (i = 0; i < 2*nr_node_ids; i++)
-                        grp->faults[i] = p->numa_faults[i];
+                for (i = 0; i < NR_NUMA_HINT_FAULT_STATS * nr_node_ids; i++)
+                        grp->faults[i] = p->numa_faults_memory[i];
 
                 grp->total_faults = p->total_numa_faults;
 
@@ -1534,9 +1679,9 @@ static void task_numa_group(struct task_struct *p, int cpupid, int flags,
 
         double_lock(&my_grp->lock, &grp->lock);
 
-        for (i = 0; i < 2*nr_node_ids; i++) {
-                my_grp->faults[i] -= p->numa_faults[i];
-                grp->faults[i] += p->numa_faults[i];
+        for (i = 0; i < NR_NUMA_HINT_FAULT_STATS * nr_node_ids; i++) {
+                my_grp->faults[i] -= p->numa_faults_memory[i];
+                grp->faults[i] += p->numa_faults_memory[i];
         }
         my_grp->total_faults -= p->total_numa_faults;
         grp->total_faults += p->total_numa_faults;
@@ -1562,12 +1707,12 @@ void task_numa_free(struct task_struct *p)
 {
         struct numa_group *grp = p->numa_group;
         int i;
-        void *numa_faults = p->numa_faults;
+        void *numa_faults = p->numa_faults_memory;
 
         if (grp) {
                 spin_lock(&grp->lock);
-                for (i = 0; i < 2*nr_node_ids; i++)
-                        grp->faults[i] -= p->numa_faults[i];
+                for (i = 0; i < NR_NUMA_HINT_FAULT_STATS * nr_node_ids; i++)
+                        grp->faults[i] -= p->numa_faults_memory[i];
                 grp->total_faults -= p->total_numa_faults;
 
                 list_del(&p->numa_entry);
@@ -1577,18 +1722,21 @@ void task_numa_free(struct task_struct *p)
                 put_numa_group(grp);
         }
 
-        p->numa_faults = NULL;
-        p->numa_faults_buffer = NULL;
+        p->numa_faults_memory = NULL;
+        p->numa_faults_buffer_memory = NULL;
+        p->numa_faults_cpu= NULL;
+        p->numa_faults_buffer_cpu = NULL;
         kfree(numa_faults);
 }
 
 /*
  * Got a PROT_NONE fault for a page on @node.
  */
-void task_numa_fault(int last_cpupid, int node, int pages, int flags)
+void task_numa_fault(int last_cpupid, int mem_node, int pages, int flags)
 {
         struct task_struct *p = current;
         bool migrated = flags & TNF_MIGRATED;
+        int cpu_node = task_node(current);
         int priv;
 
         if (!numabalancing_enabled)
@@ -1603,16 +1751,24 @@ void task_numa_fault(int last_cpupid, int node, int pages, int flags)
                 return;
 
         /* Allocate buffer to track faults on a per-node basis */
-        if (unlikely(!p->numa_faults)) {
-                int size = sizeof(*p->numa_faults) * 2 * nr_node_ids;
+        if (unlikely(!p->numa_faults_memory)) {
+                int size = sizeof(*p->numa_faults_memory) *
+                           NR_NUMA_HINT_FAULT_BUCKETS * nr_node_ids;
 
-                /* numa_faults and numa_faults_buffer share the allocation */
-                p->numa_faults = kzalloc(size * 2, GFP_KERNEL|__GFP_NOWARN);
-                if (!p->numa_faults)
+                p->numa_faults_memory = kzalloc(size, GFP_KERNEL|__GFP_NOWARN);
+                if (!p->numa_faults_memory)
                         return;
 
-                BUG_ON(p->numa_faults_buffer);
-                p->numa_faults_buffer = p->numa_faults + (2 * nr_node_ids);
+                BUG_ON(p->numa_faults_buffer_memory);
+                /*
+                 * The averaged statistics, shared & private, memory & cpu,
+                 * occupy the first half of the array. The second half of the
+                 * array is for current counters, which are averaged into the
+                 * first set by task_numa_placement.
+                 */
+                p->numa_faults_cpu = p->numa_faults_memory + (2 * nr_node_ids);
+                p->numa_faults_buffer_memory = p->numa_faults_memory + (4 * nr_node_ids);
+                p->numa_faults_buffer_cpu = p->numa_faults_memory + (6 * nr_node_ids);
                 p->total_numa_faults = 0;
                 memset(p->numa_faults_locality, 0, sizeof(p->numa_faults_locality));
         }
@@ -1641,7 +1797,8 @@ void task_numa_fault(int last_cpupid, int node, int pages, int flags)
         if (migrated)
                 p->numa_pages_migrated += pages;
 
-        p->numa_faults_buffer[task_faults_idx(node, priv)] += pages;
+        p->numa_faults_buffer_memory[task_faults_idx(mem_node, priv)] += pages;
+        p->numa_faults_buffer_cpu[task_faults_idx(cpu_node, priv)] += pages;
         p->numa_faults_locality[!!(flags & TNF_FAULT_LOCAL)] += pages;
 }
 
@@ -2219,13 +2376,20 @@ static inline void __update_group_entity_contrib(struct sched_entity *se)
                 se->avg.load_avg_contrib >>= NICE_0_SHIFT;
         }
 }
-#else
+
+static inline void update_rq_runnable_avg(struct rq *rq, int runnable)
+{
+        __update_entity_runnable_avg(rq_clock_task(rq), &rq->avg, runnable);
+        __update_tg_runnable_avg(&rq->avg, &rq->cfs);
+}
+#else /* CONFIG_FAIR_GROUP_SCHED */
 static inline void __update_cfs_rq_tg_load_contrib(struct cfs_rq *cfs_rq,
                                                  int force_update) {}
 static inline void __update_tg_runnable_avg(struct sched_avg *sa,
                                                   struct cfs_rq *cfs_rq) {}
 static inline void __update_group_entity_contrib(struct sched_entity *se) {}
-#endif
+static inline void update_rq_runnable_avg(struct rq *rq, int runnable) {}
+#endif /* CONFIG_FAIR_GROUP_SCHED */
 
 static inline void __update_task_entity_contrib(struct sched_entity *se)
 {
@@ -2323,12 +2487,6 @@ static void update_cfs_rq_blocked_load(struct cfs_rq *cfs_rq, int force_update)
         __update_cfs_rq_tg_load_contrib(cfs_rq, force_update);
 }
 
-static inline void update_rq_runnable_avg(struct rq *rq, int runnable)
-{
-        __update_entity_runnable_avg(rq_clock_task(rq), &rq->avg, runnable);
-        __update_tg_runnable_avg(&rq->avg, &rq->cfs);
-}
-
 /* Add the load generated by se into cfs_rq's child load-average */
 static inline void enqueue_entity_load_avg(struct cfs_rq *cfs_rq,
                                                   struct sched_entity *se,
@@ -2416,7 +2574,10 @@ void idle_exit_fair(struct rq *this_rq)
         update_rq_runnable_avg(this_rq, 0);
 }
 
-#else
+static int idle_balance(struct rq *this_rq);
+
+#else /* CONFIG_SMP */
+
 static inline void update_entity_load_avg(struct sched_entity *se,
                                           int update_cfs_rq) {}
 static inline void update_rq_runnable_avg(struct rq *rq, int runnable) {}
@@ -2428,7 +2589,13 @@ static inline void dequeue_entity_load_avg(struct cfs_rq *cfs_rq,
                                            int sleep) {}
 static inline void update_cfs_rq_blocked_load(struct cfs_rq *cfs_rq,
                                               int force_update) {}
-#endif
+
+static inline int idle_balance(struct rq *rq)
+{
+        return 0;
+}
+
+#endif /* CONFIG_SMP */
 
 static void enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
@@ -2578,10 +2745,10 @@ static void __clear_buddies_last(struct sched_entity *se)
 {
         for_each_sched_entity(se) {
                 struct cfs_rq *cfs_rq = cfs_rq_of(se);
-                if (cfs_rq->last == se)
-                        cfs_rq->last = NULL;
-                else
+                if (cfs_rq->last != se)
                         break;
+
+                cfs_rq->last = NULL;
         }
 }
 
@@ -2589,10 +2756,10 @@ static void __clear_buddies_next(struct sched_entity *se)
 {
         for_each_sched_entity(se) {
                 struct cfs_rq *cfs_rq = cfs_rq_of(se);
-                if (cfs_rq->next == se)
-                        cfs_rq->next = NULL;
-                else
+                if (cfs_rq->next != se)
                         break;
+
+                cfs_rq->next = NULL;
         }
 }
 
@@ -2600,10 +2767,10 @@ static void __clear_buddies_skip(struct sched_entity *se)
 {
         for_each_sched_entity(se) {
                 struct cfs_rq *cfs_rq = cfs_rq_of(se);
-                if (cfs_rq->skip == se)
-                        cfs_rq->skip = NULL;
-                else
+                if (cfs_rq->skip != se)
                         break;
+
+                cfs_rq->skip = NULL;
         }
 }
 
@@ -2746,17 +2913,36 @@ wakeup_preempt_entity(struct sched_entity *curr, struct sched_entity *se);
  * 3) pick the "last" process, for cache locality
  * 4) do not run the "skip" process, if something else is available
  */
-static struct sched_entity *pick_next_entity(struct cfs_rq *cfs_rq)
+static struct sched_entity *
+pick_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *curr)
 {
-        struct sched_entity *se = __pick_first_entity(cfs_rq);
-        struct sched_entity *left = se;
+        struct sched_entity *left = __pick_first_entity(cfs_rq);
+        struct sched_entity *se;
+
+        /*
+         * If curr is set we have to see if its left of the leftmost entity
+         * still in the tree, provided there was anything in the tree at all.
+         */
+        if (!left || (curr && entity_before(curr, left)))
+                left = curr;
+
+        se = left; /* ideally we run the leftmost entity */
 
         /*
          * Avoid running the skip buddy, if running something else can
          * be done without getting too unfair.
          */
         if (cfs_rq->skip == se) {
-                struct sched_entity *second = __pick_next_entity(se);
+                struct sched_entity *second;
+
+                if (se == curr) {
+                        second = __pick_first_entity(cfs_rq);
+                } else {
+                        second = __pick_next_entity(se);
+                        if (!second || (curr && entity_before(curr, second)))
+                                second = curr;
+                }
+
                 if (second && wakeup_preempt_entity(second, left) < 1)
                         se = second;
         }
@@ -2778,7 +2964,7 @@ static struct sched_entity *pick_next_entity(struct cfs_rq *cfs_rq)
         return se;
 }
 
-static void check_cfs_rq_runtime(struct cfs_rq *cfs_rq);
+static bool check_cfs_rq_runtime(struct cfs_rq *cfs_rq);
 
 static void put_prev_entity(struct cfs_rq *cfs_rq, struct sched_entity *prev)
 {
@@ -3433,22 +3619,23 @@ static void check_enqueue_throttle(struct cfs_rq *cfs_rq)
 }
 
 /* conditionally throttle active cfs_rq's from put_prev_entity() */
-static void check_cfs_rq_runtime(struct cfs_rq *cfs_rq)
+static bool check_cfs_rq_runtime(struct cfs_rq *cfs_rq)
 {
         if (!cfs_bandwidth_used())
-                return;
+                return false;
 
         if (likely(!cfs_rq->runtime_enabled || cfs_rq->runtime_remaining > 0))
-                return;
+                return false;
 
         /*
          * it's possible for a throttled entity to be forced into a running
          * state (e.g. set_curr_task), in this case we're finished.
          */
         if (cfs_rq_throttled(cfs_rq))
-                return;
+                return true;
 
         throttle_cfs_rq(cfs_rq);
+        return true;
 }
 
 static enum hrtimer_restart sched_cfs_slack_timer(struct hrtimer *timer)
@@ -3558,7 +3745,7 @@ static inline u64 cfs_rq_clock_task(struct cfs_rq *cfs_rq)
 }
 
 static void account_cfs_rq_runtime(struct cfs_rq *cfs_rq, u64 delta_exec) {}
-static void check_cfs_rq_runtime(struct cfs_rq *cfs_rq) {}
+static bool check_cfs_rq_runtime(struct cfs_rq *cfs_rq) { return false; }
 static void check_enqueue_throttle(struct cfs_rq *cfs_rq) {}
 static __always_inline void return_cfs_rq_runtime(struct cfs_rq *cfs_rq) {}
 
@@ -4213,13 +4400,14 @@ done:
 }
 
 /*
- * sched_balance_self: balance the current task (running on cpu) in domains
- * that have the 'flag' flag set. In practice, this is SD_BALANCE_FORK and
- * SD_BALANCE_EXEC.
+ * select_task_rq_fair: Select target runqueue for the waking task in domains
+ * that have the 'sd_flag' flag set. In practice, this is SD_BALANCE_WAKE,
+ * SD_BALANCE_FORK, or SD_BALANCE_EXEC.
  *
- * Balance, ie. select the least loaded group.
+ * Balances load by selecting the idlest cpu in the idlest group, or under
+ * certain conditions an idle sibling cpu if the domain has SD_WAKE_AFFINE set.
  *
- * Returns the target CPU number, or the same CPU if no balancing is needed.
+ * Returns the target cpu number.
  *
  * preempt must be disabled.
  */
@@ -4494,26 +4682,124 @@ preempt:
                 set_last_buddy(se);
 }
 
-static struct task_struct *pick_next_task_fair(struct rq *rq)
+static struct task_struct *
+pick_next_task_fair(struct rq *rq, struct task_struct *prev)
 {
-        struct task_struct *p;
         struct cfs_rq *cfs_rq = &rq->cfs;
         struct sched_entity *se;
+        struct task_struct *p;
+        int new_tasks;
 
+again:
+#ifdef CONFIG_FAIR_GROUP_SCHED
         if (!cfs_rq->nr_running)
-                return NULL;
+                goto idle;
+
+        if (prev->sched_class != &fair_sched_class)
+                goto simple;
+
+        /*
+         * Because of the set_next_buddy() in dequeue_task_fair() it is rather
+         * likely that a next task is from the same cgroup as the current.
+         *
+         * Therefore attempt to avoid putting and setting the entire cgroup
+         * hierarchy, only change the part that actually changes.
+         */
+
+        do {
+                struct sched_entity *curr = cfs_rq->curr;
+
+                /*
+                 * Since we got here without doing put_prev_entity() we also
+                 * have to consider cfs_rq->curr. If it is still a runnable
+                 * entity, update_curr() will update its vruntime, otherwise
+                 * forget we've ever seen it.
+                 */
+                if (curr && curr->on_rq)
+                        update_curr(cfs_rq);
+                else
+                        curr = NULL;
+
+                /*
+                 * This call to check_cfs_rq_runtime() will do the throttle and
+                 * dequeue its entity in the parent(s). Therefore the 'simple'
+                 * nr_running test will indeed be correct.
+                 */
+                if (unlikely(check_cfs_rq_runtime(cfs_rq)))
+                        goto simple;
+
+                se = pick_next_entity(cfs_rq, curr);
+                cfs_rq = group_cfs_rq(se);
+        } while (cfs_rq);
+
+        p = task_of(se);
+
+        /*
+         * Since we haven't yet done put_prev_entity and if the selected task
+         * is a different task than we started out with, try and touch the
+         * least amount of cfs_rqs.
+         */
+        if (prev != p) {
+                struct sched_entity *pse = &prev->se;
+
+                while (!(cfs_rq = is_same_group(se, pse))) {
+                        int se_depth = se->depth;
+                        int pse_depth = pse->depth;
+
+                        if (se_depth <= pse_depth) {
+                                put_prev_entity(cfs_rq_of(pse), pse);
+                                pse = parent_entity(pse);
+                        }
+                        if (se_depth >= pse_depth) {
+                                set_next_entity(cfs_rq_of(se), se);
+                                se = parent_entity(se);
+                        }
+                }
+
+                put_prev_entity(cfs_rq, pse);
+                set_next_entity(cfs_rq, se);
+        }
+
+        if (hrtick_enabled(rq))
+                hrtick_start_fair(rq, p);
+
+        return p;
+simple:
+        cfs_rq = &rq->cfs;
+#endif
+
+        if (!cfs_rq->nr_running)
+                goto idle;
+
+        put_prev_task(rq, prev);
 
         do {
-                se = pick_next_entity(cfs_rq);
+                se = pick_next_entity(cfs_rq, NULL);
                 set_next_entity(cfs_rq, se);
                 cfs_rq = group_cfs_rq(se);
         } while (cfs_rq);
 
         p = task_of(se);
+
         if (hrtick_enabled(rq))
                 hrtick_start_fair(rq, p);
 
         return p;
+
+idle:
+        new_tasks = idle_balance(rq);
+        /*
+         * Because idle_balance() releases (and re-acquires) rq->lock, it is
+         * possible for any higher priority task to appear. In that case we
+         * must re-start the pick_next_entity() loop.
+         */
+        if (new_tasks < 0)
+                return RETRY_TASK;
+
+        if (new_tasks > 0)
+                goto again;
+
+        return NULL;
 }
 
 /*
@@ -4751,7 +5037,7 @@ static void move_task(struct task_struct *p, struct lb_env *env)
  * Is this task likely cache-hot:
  */
 static int
-task_hot(struct task_struct *p, u64 now, struct sched_domain *sd)
+task_hot(struct task_struct *p, u64 now)
 {
         s64 delta;
 
@@ -4785,7 +5071,7 @@ static bool migrate_improves_locality(struct task_struct *p, struct lb_env *env)
 {
         int src_nid, dst_nid;
 
-        if (!sched_feat(NUMA_FAVOUR_HIGHER) || !p->numa_faults ||
+        if (!sched_feat(NUMA_FAVOUR_HIGHER) || !p->numa_faults_memory ||
             !(env->sd->flags & SD_NUMA)) {
                 return false;
         }
@@ -4816,7 +5102,7 @@ static bool migrate_degrades_locality(struct task_struct *p, struct lb_env *env)
         if (!sched_feat(NUMA) || !sched_feat(NUMA_RESIST_LOWER))
                 return false;
 
-        if (!p->numa_faults || !(env->sd->flags & SD_NUMA))
+        if (!p->numa_faults_memory || !(env->sd->flags & SD_NUMA))
                 return false;
 
         src_nid = cpu_to_node(env->src_cpu);
@@ -4912,7 +5198,7 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env)
          * 2) task is cache cold, or
          * 3) too many balance attempts have failed.
          */
-        tsk_cache_hot = task_hot(p, rq_clock_task(env->src_rq), env->sd);
+        tsk_cache_hot = task_hot(p, rq_clock_task(env->src_rq));
         if (!tsk_cache_hot)
                 tsk_cache_hot = migrate_degrades_locality(p, env);
 
@@ -5775,12 +6061,10 @@ void fix_small_imbalance(struct lb_env *env, struct sd_lb_stats *sds)
         pwr_now /= SCHED_POWER_SCALE;
 
         /* Amount of load we'd subtract */
-        tmp = (busiest->load_per_task * SCHED_POWER_SCALE) /
-                busiest->group_power;
-        if (busiest->avg_load > tmp) {
+        if (busiest->avg_load > scaled_busy_load_per_task) {
                 pwr_move += busiest->group_power *
                             min(busiest->load_per_task,
-                                busiest->avg_load - tmp);
+                                busiest->avg_load - scaled_busy_load_per_task);
         }
 
         /* Amount of load we'd add */
@@ -6359,17 +6643,23 @@ out:
  * idle_balance is called by schedule() if this_cpu is about to become
  * idle. Attempts to pull tasks from other CPUs.
  */
-void idle_balance(int this_cpu, struct rq *this_rq)
+static int idle_balance(struct rq *this_rq)
 {
         struct sched_domain *sd;
         int pulled_task = 0;
         unsigned long next_balance = jiffies + HZ;
         u64 curr_cost = 0;
+        int this_cpu = this_rq->cpu;
 
+        idle_enter_fair(this_rq);
+        /*
+         * We must set idle_stamp _before_ calling idle_balance(), such that we
+         * measure the duration of idle_balance() as idle time.
+         */
         this_rq->idle_stamp = rq_clock(this_rq);
 
         if (this_rq->avg_idle < sysctl_sched_migration_cost)
-                return;
+                goto out;
 
         /*
          * Drop the rq->lock, but keep IRQ/preempt disabled.
@@ -6407,15 +6697,22 @@ void idle_balance(int this_cpu, struct rq *this_rq)
                 interval = msecs_to_jiffies(sd->balance_interval);
                 if (time_after(next_balance, sd->last_balance + interval))
                         next_balance = sd->last_balance + interval;
-                if (pulled_task) {
-                        this_rq->idle_stamp = 0;
+                if (pulled_task)
                         break;
-                }
         }
         rcu_read_unlock();
 
         raw_spin_lock(&this_rq->lock);
 
+        /*
+         * While browsing the domains, we released the rq lock.
+         * A task could have be enqueued in the meantime
+         */
+        if (this_rq->cfs.h_nr_running && !pulled_task) {
+                pulled_task = 1;
+                goto out;
+        }
+
         if (pulled_task || time_after(jiffies, this_rq->next_balance)) {
                 /*
                  * We are going idle. next_balance may be set based on
@@ -6426,6 +6723,20 @@ void idle_balance(int this_cpu, struct rq *this_rq)
 
         if (curr_cost > this_rq->max_idle_balance_cost)
                 this_rq->max_idle_balance_cost = curr_cost;
+
+out:
+        /* Is there a task of a high priority class? */
+        if (this_rq->nr_running != this_rq->cfs.h_nr_running &&
+            (this_rq->dl.dl_nr_running ||
+             (this_rq->rt.rt_nr_running && !rt_rq_throttled(&this_rq->rt))))
+                pulled_task = -1;
+
+        if (pulled_task) {
+                idle_exit_fair(this_rq);
+                this_rq->idle_stamp = 0;
+        }
+
+        return pulled_task;
 }
 
 /*
@@ -6496,6 +6807,11 @@ out_unlock:
         return 0;
 }
 
+static inline int on_null_domain(struct rq *rq)
+{
+        return unlikely(!rcu_dereference_sched(rq->sd));
+}
+
 #ifdef CONFIG_NO_HZ_COMMON
 /*
  * idle load balancing details
@@ -6550,8 +6866,13 @@ static void nohz_balancer_kick(void)
 static inline void nohz_balance_exit_idle(int cpu)
 {
         if (unlikely(test_bit(NOHZ_TICK_STOPPED, nohz_flags(cpu)))) {
-                cpumask_clear_cpu(cpu, nohz.idle_cpus_mask);
-                atomic_dec(&nohz.nr_cpus);
+                /*
+                 * Completely isolated CPUs don't ever set, so we must test.
+                 */
+                if (likely(cpumask_test_cpu(cpu, nohz.idle_cpus_mask))) {
+                        cpumask_clear_cpu(cpu, nohz.idle_cpus_mask);
+                        atomic_dec(&nohz.nr_cpus);
+                }
                 clear_bit(NOHZ_TICK_STOPPED, nohz_flags(cpu));
         }
 }
@@ -6605,6 +6926,12 @@ void nohz_balance_enter_idle(int cpu)
         if (test_bit(NOHZ_TICK_STOPPED, nohz_flags(cpu)))
                 return;
 
+        /*
+         * If we're a completely isolated CPU, we don't play.
+         */
+        if (on_null_domain(cpu_rq(cpu)))
+                return;
+
         cpumask_set_cpu(cpu, nohz.idle_cpus_mask);
         atomic_inc(&nohz.nr_cpus);
         set_bit(NOHZ_TICK_STOPPED, nohz_flags(cpu));
@@ -6867,11 +7194,6 @@ static void run_rebalance_domains(struct softirq_action *h)
         nohz_idle_balance(this_rq, idle);
 }
 
-static inline int on_null_domain(struct rq *rq)
-{
-        return !rcu_dereference_sched(rq->sd);
-}
-
 /*
  * Trigger the SCHED_SOFTIRQ if it is time to do periodic load balancing.
  */
@@ -7036,7 +7358,15 @@ static void switched_from_fair(struct rq *rq, struct task_struct *p)
  */
 static void switched_to_fair(struct rq *rq, struct task_struct *p)
 {
-        if (!p->se.on_rq)
+        struct sched_entity *se = &p->se;
+#ifdef CONFIG_FAIR_GROUP_SCHED
+        /*
+         * Since the real-depth could have been changed (only FAIR
+         * class maintain depth value), reset depth properly.
+         */
+        se->depth = se->parent ? se->parent->depth + 1 : 0;
+#endif
+        if (!se->on_rq)
                 return;
 
         /*
@@ -7084,7 +7414,9 @@ void init_cfs_rq(struct cfs_rq *cfs_rq)
 #ifdef CONFIG_FAIR_GROUP_SCHED
 static void task_move_group_fair(struct task_struct *p, int on_rq)
 {
+        struct sched_entity *se = &p->se;
         struct cfs_rq *cfs_rq;
+
         /*
          * If the task was not on the rq at the time of this cgroup movement
          * it must have been asleep, sleeping tasks keep their ->vruntime
@@ -7110,23 +7442,24 @@ static void task_move_group_fair(struct task_struct *p, int on_rq)
          * To prevent boost or penalty in the new cfs_rq caused by delta
          * min_vruntime between the two cfs_rqs, we skip vruntime adjustment.
          */
-        if (!on_rq && (!p->se.sum_exec_runtime || p->state == TASK_WAKING))
+        if (!on_rq && (!se->sum_exec_runtime || p->state == TASK_WAKING))
                 on_rq = 1;
 
         if (!on_rq)
-                p->se.vruntime -= cfs_rq_of(&p->se)->min_vruntime;
+                se->vruntime -= cfs_rq_of(se)->min_vruntime;
         set_task_rq(p, task_cpu(p));
+        se->depth = se->parent ? se->parent->depth + 1 : 0;
         if (!on_rq) {
-                cfs_rq = cfs_rq_of(&p->se);
-                p->se.vruntime += cfs_rq->min_vruntime;
+                cfs_rq = cfs_rq_of(se);
+                se->vruntime += cfs_rq->min_vruntime;
 #ifdef CONFIG_SMP
                 /*
                  * migrate_task_rq_fair() will have removed our previous
                  * contribution, but we must synchronize for ongoing future
                  * decay.
                  */
-                p->se.avg.decay_count = atomic64_read(&cfs_rq->decay_counter);
-                cfs_rq->blocked_load_avg += p->se.avg.load_avg_contrib;
+                se->avg.decay_count = atomic64_read(&cfs_rq->decay_counter);
+                cfs_rq->blocked_load_avg += se->avg.load_avg_contrib;
 #endif
         }
 }
@@ -7222,10 +7555,13 @@ void init_tg_cfs_entry(struct task_group *tg, struct cfs_rq *cfs_rq,
         if (!se)
                 return;
 
-        if (!parent)
+        if (!parent) {
                 se->cfs_rq = &rq->cfs;
-        else
+                se->depth = 0;
+        } else {
                 se->cfs_rq = parent->my_q;
+                se->depth = parent->depth + 1;
+        }
 
         se->my_q = cfs_rq;
         /* guarantee group entities always have weight */
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
new file mode 100644
index 000000000000..8f4390a079c7
--- /dev/null
+++ b/kernel/sched/idle.c
@@ -0,0 +1,265 @@
+/*
+ * Generic entry point for the idle threads
+ */
+#include <linux/sched.h>
+#include <linux/cpu.h>
+#include <linux/cpuidle.h>
+#include <linux/tick.h>
+#include <linux/mm.h>
+#include <linux/stackprotector.h>
+
+#include <asm/tlb.h>
+
+#include <trace/events/power.h>
+
+static int __read_mostly cpu_idle_force_poll;
+
+void cpu_idle_poll_ctrl(bool enable)
+{
+        if (enable) {
+                cpu_idle_force_poll++;
+        } else {
+                cpu_idle_force_poll--;
+                WARN_ON_ONCE(cpu_idle_force_poll < 0);
+        }
+}
+
+#ifdef CONFIG_GENERIC_IDLE_POLL_SETUP
+static int __init cpu_idle_poll_setup(char *__unused)
+{
+        cpu_idle_force_poll = 1;
+        return 1;
+}
+__setup("nohlt", cpu_idle_poll_setup);
+
+static int __init cpu_idle_nopoll_setup(char *__unused)
+{
+        cpu_idle_force_poll = 0;
+        return 1;
+}
+__setup("hlt", cpu_idle_nopoll_setup);
+#endif
+
+static inline int cpu_idle_poll(void)
+{
+        rcu_idle_enter();
+        trace_cpu_idle_rcuidle(0, smp_processor_id());
+        local_irq_enable();
+        while (!tif_need_resched())
+                cpu_relax();
+        trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id());
+        rcu_idle_exit();
+        return 1;
+}
+
+/* Weak implementations for optional arch specific functions */
+void __weak arch_cpu_idle_prepare(void) { }
+void __weak arch_cpu_idle_enter(void) { }
+void __weak arch_cpu_idle_exit(void) { }
+void __weak arch_cpu_idle_dead(void) { }
+void __weak arch_cpu_idle(void)
+{
+        cpu_idle_force_poll = 1;
+        local_irq_enable();
+}
+
+/**
+ * cpuidle_idle_call - the main idle function
+ *
+ * NOTE: no locks or semaphores should be used here
+ * return non-zero on failure
+ */
+static int cpuidle_idle_call(void)
+{
+        struct cpuidle_device *dev = __this_cpu_read(cpuidle_devices);
+        struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev);
+        int next_state, entered_state, ret;
+        bool broadcast;
+
+        /*
+         * Check if the idle task must be rescheduled. If it is the
+         * case, exit the function after re-enabling the local irq and
+         * set again the polling flag
+         */
+        if (current_clr_polling_and_test()) {
+                local_irq_enable();
+                __current_set_polling();
+                return 0;
+        }
+
+        /*
+         * During the idle period, stop measuring the disabled irqs
+         * critical sections latencies
+         */
+        stop_critical_timings();
+
+        /*
+         * Tell the RCU framework we are entering an idle section,
+         * so no more rcu read side critical sections and one more
+         * step to the grace period
+         */
+        rcu_idle_enter();
+
+        /*
+         * Check if the cpuidle framework is ready, otherwise fallback
+         * to the default arch specific idle method
+         */
+        ret = cpuidle_enabled(drv, dev);
+
+        if (!ret) {
+                /*
+                 * Ask the governor to choose an idle state it thinks
+                 * it is convenient to go to. There is *always* a
+                 * convenient idle state
+                 */
+                next_state = cpuidle_select(drv, dev);
+
+                /*
+                 * The idle task must be scheduled, it is pointless to
+                 * go to idle, just update no idle residency and get
+                 * out of this function
+                 */
+                if (current_clr_polling_and_test()) {
+                        dev->last_residency = 0;
+                        entered_state = next_state;
+                        local_irq_enable();
+                } else {
+                        broadcast = !!(drv->states[next_state].flags &
+                                       CPUIDLE_FLAG_TIMER_STOP);
+
+                        if (broadcast)
+                                /*
+                                 * Tell the time framework to switch
+                                 * to a broadcast timer because our
+                                 * local timer will be shutdown. If a
+                                 * local timer is used from another
+                                 * cpu as a broadcast timer, this call
+                                 * may fail if it is not available
+                                 */
+                                ret = clockevents_notify(
+                                        CLOCK_EVT_NOTIFY_BROADCAST_ENTER,
+                                        &dev->cpu);
+
+                        if (!ret) {
+                                trace_cpu_idle_rcuidle(next_state, dev->cpu);
+
+                                /*
+                                 * Enter the idle state previously
+                                 * returned by the governor
+                                 * decision. This function will block
+                                 * until an interrupt occurs and will
+                                 * take care of re-enabling the local
+                                 * interrupts
+                                 */
+                                entered_state = cpuidle_enter(drv, dev,
+                                                              next_state);
+
+                                trace_cpu_idle_rcuidle(PWR_EVENT_EXIT,
+                                                       dev->cpu);
+
+                                if (broadcast)
+                                        clockevents_notify(
+                                                CLOCK_EVT_NOTIFY_BROADCAST_EXIT,
+                                                &dev->cpu);
+
+                                /*
+                                 * Give the governor an opportunity to reflect on the
+                                 * outcome
+                                 */
+                                cpuidle_reflect(dev, entered_state);
+                        }
+                }
+        }
+
+        /*
+         * We can't use the cpuidle framework, let's use the default
+         * idle routine
+         */
+        if (ret)
+                arch_cpu_idle();
+
+        __current_set_polling();
+
+        /*
+         * It is up to the idle functions to enable back the local
+         * interrupt
+         */
+        if (WARN_ON_ONCE(irqs_disabled()))
+                local_irq_enable();
+
+        rcu_idle_exit();
+        start_critical_timings();
+
+        return 0;
+}
+
+/*
+ * Generic idle loop implementation
+ */
+static void cpu_idle_loop(void)
+{
+        while (1) {
+                tick_nohz_idle_enter();
+
+                while (!need_resched()) {
+                        check_pgt_cache();
+                        rmb();
+
+                        if (cpu_is_offline(smp_processor_id()))
+                                arch_cpu_idle_dead();
+
+                        local_irq_disable();
+                        arch_cpu_idle_enter();
+
+                        /*
+                         * In poll mode we reenable interrupts and spin.
+                         *
+                         * Also if we detected in the wakeup from idle
+                         * path that the tick broadcast device expired
+                         * for us, we don't want to go deep idle as we
+                         * know that the IPI is going to arrive right
+                         * away
+                         */
+                        if (cpu_idle_force_poll || tick_check_broadcast_expired())
+                                cpu_idle_poll();
+                        else
+                                cpuidle_idle_call();
+
+                        arch_cpu_idle_exit();
+                }
+
+                /*
+                 * Since we fell out of the loop above, we know
+                 * TIF_NEED_RESCHED must be set, propagate it into
+                 * PREEMPT_NEED_RESCHED.
+                 *
+                 * This is required because for polling idle loops we will
+                 * not have had an IPI to fold the state for us.
+                 */
+                preempt_set_need_resched();
+                tick_nohz_idle_exit();
+                schedule_preempt_disabled();
+        }
+}
+
+void cpu_startup_entry(enum cpuhp_state state)
+{
+        /*
+         * This #ifdef needs to die, but it's too late in the cycle to
+         * make this generic (arm and sh have never invoked the canary
+         * init for the non boot cpus!). Will be fixed in 3.11
+         */
+#ifdef CONFIG_X86
+        /*
+         * If we're the non-boot CPU, nothing set the stack canary up
+         * for us. The boot CPU already has it initialized but no harm
+         * in doing it again. This is a good place for updating it, as
+         * we wont ever return from this function (so the invalid
+         * canaries already on the stack wont ever trigger).
+         */
+        boot_init_stack_canary();
+#endif
+        __current_set_polling();
+        arch_cpu_idle_prepare();
+        cpu_idle_loop();
+}
diff --git a/kernel/sched/idle_task.c b/kernel/sched/idle_task.c
index 516c3d9ceea1..879f2b75266a 100644
--- a/kernel/sched/idle_task.c
+++ b/kernel/sched/idle_task.c
@@ -13,18 +13,8 @@ select_task_rq_idle(struct task_struct *p, int cpu, int sd_flag, int flags)
 {
         return task_cpu(p); /* IDLE tasks as never migrated */
 }
-
-static void pre_schedule_idle(struct rq *rq, struct task_struct *prev)
-{
-        idle_exit_fair(rq);
-        rq_last_tick_reset(rq);
-}
-
-static void post_schedule_idle(struct rq *rq)
-{
-        idle_enter_fair(rq);
-}
 #endif /* CONFIG_SMP */
+
 /*
  * Idle tasks are unconditionally rescheduled:
  */
@@ -33,13 +23,12 @@ static void check_preempt_curr_idle(struct rq *rq, struct task_struct *p, int fl
         resched_task(rq->idle);
 }
 
-static struct task_struct *pick_next_task_idle(struct rq *rq)
+static struct task_struct *
+pick_next_task_idle(struct rq *rq, struct task_struct *prev)
 {
+        put_prev_task(rq, prev);
+
         schedstat_inc(rq, sched_goidle);
-#ifdef CONFIG_SMP
-        /* Trigger the post schedule to do an idle_enter for CFS */
-        rq->post_schedule = 1;
-#endif
         return rq->idle;
 }
 
@@ -58,6 +47,8 @@ dequeue_task_idle(struct rq *rq, struct task_struct *p, int flags)
 
 static void put_prev_task_idle(struct rq *rq, struct task_struct *prev)
 {
+        idle_exit_fair(rq);
+        rq_last_tick_reset(rq);
 }
 
 static void task_tick_idle(struct rq *rq, struct task_struct *curr, int queued)
@@ -101,8 +92,6 @@ const struct sched_class idle_sched_class = {
 
 #ifdef CONFIG_SMP
         .select_task_rq         = select_task_rq_idle,
-        .pre_schedule           = pre_schedule_idle,
-        .post_schedule          = post_schedule_idle,
 #endif
 
         .set_curr_task          = set_curr_task_idle,
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 1999021042c7..d8cdf1618551 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -229,6 +229,14 @@ int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent)
 
 #ifdef CONFIG_SMP
 
+static int pull_rt_task(struct rq *this_rq);
+
+static inline bool need_pull_rt_task(struct rq *rq, struct task_struct *prev)
+{
+        /* Try to pull RT tasks here if we lower this rq's prio */
+        return rq->rt.highest_prio.curr > prev->prio;
+}
+
 static inline int rt_overloaded(struct rq *rq)
 {
         return atomic_read(&rq->rd->rto_count);
@@ -315,6 +323,15 @@ static inline int has_pushable_tasks(struct rq *rq)
         return !plist_head_empty(&rq->rt.pushable_tasks);
 }
 
+static inline void set_post_schedule(struct rq *rq)
+{
+        /*
+         * We detect this state here so that we can avoid taking the RQ
+         * lock again later if there is no need to push
+         */
+        rq->post_schedule = has_pushable_tasks(rq);
+}
+
 static void enqueue_pushable_task(struct rq *rq, struct task_struct *p)
 {
         plist_del(&p->pushable_tasks, &rq->rt.pushable_tasks);
@@ -359,6 +376,19 @@ void dec_rt_migration(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
 {
 }
 
+static inline bool need_pull_rt_task(struct rq *rq, struct task_struct *prev)
+{
+        return false;
+}
+
+static inline int pull_rt_task(struct rq *this_rq)
+{
+        return 0;
+}
+
+static inline void set_post_schedule(struct rq *rq)
+{
+}
 #endif /* CONFIG_SMP */
 
 static inline int on_rt_rq(struct sched_rt_entity *rt_se)
@@ -440,11 +470,6 @@ static void sched_rt_rq_dequeue(struct rt_rq *rt_rq)
                 dequeue_rt_entity(rt_se);
 }
 
-static inline int rt_rq_throttled(struct rt_rq *rt_rq)
-{
-        return rt_rq->rt_throttled && !rt_rq->rt_nr_boosted;
-}
-
 static int rt_se_boosted(struct sched_rt_entity *rt_se)
 {
         struct rt_rq *rt_rq = group_rt_rq(rt_se);
@@ -515,11 +540,6 @@ static inline void sched_rt_rq_dequeue(struct rt_rq *rt_rq)
 {
 }
 
-static inline int rt_rq_throttled(struct rt_rq *rt_rq)
-{
-        return rt_rq->rt_throttled;
-}
-
 static inline const struct cpumask *sched_rt_period_mask(void)
 {
         return cpu_online_mask;
@@ -1318,15 +1338,7 @@ static struct task_struct *_pick_next_task_rt(struct rq *rq)
 {
         struct sched_rt_entity *rt_se;
         struct task_struct *p;
-        struct rt_rq *rt_rq;
-
-        rt_rq = &rq->rt;
-
-        if (!rt_rq->rt_nr_running)
-                return NULL;
-
-        if (rt_rq_throttled(rt_rq))
-                return NULL;
+        struct rt_rq *rt_rq  = &rq->rt;
 
         do {
                 rt_se = pick_next_rt_entity(rq, rt_rq);
@@ -1340,21 +1352,45 @@ static struct task_struct *_pick_next_task_rt(struct rq *rq)
         return p;
 }
 
-static struct task_struct *pick_next_task_rt(struct rq *rq)
+static struct task_struct *
+pick_next_task_rt(struct rq *rq, struct task_struct *prev)
 {
-        struct task_struct *p = _pick_next_task_rt(rq);
+        struct task_struct *p;
+        struct rt_rq *rt_rq = &rq->rt;
+
+        if (need_pull_rt_task(rq, prev)) {
+                pull_rt_task(rq);
+                /*
+                 * pull_rt_task() can drop (and re-acquire) rq->lock; this
+                 * means a dl task can slip in, in which case we need to
+                 * re-start task selection.
+                 */
+                if (unlikely(rq->dl.dl_nr_running))
+                        return RETRY_TASK;
+        }
+
+        /*
+         * We may dequeue prev's rt_rq in put_prev_task().
+         * So, we update time before rt_nr_running check.
+         */
+        if (prev->sched_class == &rt_sched_class)
+                update_curr_rt(rq);
+
+        if (!rt_rq->rt_nr_running)
+                return NULL;
+
+        if (rt_rq_throttled(rt_rq))
+                return NULL;
+
+        put_prev_task(rq, prev);
+
+        p = _pick_next_task_rt(rq);
 
         /* The running task is never eligible for pushing */
         if (p)
                 dequeue_pushable_task(rq, p);
 
-#ifdef CONFIG_SMP
-        /*
-         * We detect this state here so that we can avoid taking the RQ
-         * lock again later if there is no need to push
-         */
-        rq->post_schedule = has_pushable_tasks(rq);
-#endif
+        set_post_schedule(rq);
 
         return p;
 }
@@ -1724,13 +1760,6 @@ skip:
         return ret;
 }
 
-static void pre_schedule_rt(struct rq *rq, struct task_struct *prev)
-{
-        /* Try to pull RT tasks here if we lower this rq's prio */
-        if (rq->rt.highest_prio.curr > prev->prio)
-                pull_rt_task(rq);
-}
-
 static void post_schedule_rt(struct rq *rq)
 {
         push_rt_tasks(rq);
@@ -1833,7 +1862,7 @@ static void switched_from_rt(struct rq *rq, struct task_struct *p)
                 resched_task(rq->curr);
 }
 
-void init_sched_rt_class(void)
+void __init init_sched_rt_class(void)
 {
         unsigned int i;
 
@@ -2007,7 +2036,6 @@ const struct sched_class rt_sched_class = {
         .set_cpus_allowed       = set_cpus_allowed_rt,
         .rq_online              = rq_online_rt,
         .rq_offline             = rq_offline_rt,
-        .pre_schedule           = pre_schedule_rt,
         .post_schedule          = post_schedule_rt,
         .task_woken             = task_woken_rt,
         .switched_from          = switched_from_rt,
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index f964add50f38..c9007f28d3a2 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -24,24 +24,6 @@ extern long calc_load_fold_active(struct rq *this_rq);
 extern void update_cpu_load_active(struct rq *this_rq);
 
 /*
- * Convert user-nice values [ -20 ... 0 ... 19 ]
- * to static priority [ MAX_RT_PRIO..MAX_PRIO-1 ],
- * and back.
- */
-#define NICE_TO_PRIO(nice)      (MAX_RT_PRIO + (nice) + 20)
-#define PRIO_TO_NICE(prio)      ((prio) - MAX_RT_PRIO - 20)
-#define TASK_NICE(p)            PRIO_TO_NICE((p)->static_prio)
-
-/*
- * 'User priority' is the nice value converted to something we
- * can work with better when scaling various scheduler parameters,
- * it's a [ 0 ... 39 ] range.
- */
-#define USER_PRIO(p)            ((p)-MAX_RT_PRIO)
-#define TASK_USER_PRIO(p)       USER_PRIO((p)->static_prio)
-#define MAX_USER_PRIO           (USER_PRIO(MAX_PRIO))
-
-/*
  * Helpers for converting nanosecond timing to jiffy resolution
  */
 #define NS_TO_JIFFIES(TIME)     ((unsigned long)(TIME) / (NSEC_PER_SEC / HZ))
@@ -441,6 +423,18 @@ struct rt_rq {
 #endif
 };
 
+#ifdef CONFIG_RT_GROUP_SCHED
+static inline int rt_rq_throttled(struct rt_rq *rt_rq)
+{
+        return rt_rq->rt_throttled && !rt_rq->rt_nr_boosted;
+}
+#else
+static inline int rt_rq_throttled(struct rt_rq *rt_rq)
+{
+        return rt_rq->rt_throttled;
+}
+#endif
+
 /* Deadline class' related fields in a runqueue */
 struct dl_rq {
         /* runqueue is an rbtree, ordered by deadline */
@@ -558,11 +552,9 @@ struct rq {
 #ifdef CONFIG_FAIR_GROUP_SCHED
         /* list of leaf cfs_rq on this cpu: */
         struct list_head leaf_cfs_rq_list;
-#endif /* CONFIG_FAIR_GROUP_SCHED */
 
-#ifdef CONFIG_RT_GROUP_SCHED
-        struct list_head leaf_rt_rq_list;
-#endif
+        struct sched_avg avg;
+#endif /* CONFIG_FAIR_GROUP_SCHED */
 
         /*
          * This is part of a global counter where only the total sum
@@ -651,8 +643,6 @@ struct rq {
 #ifdef CONFIG_SMP
         struct llist_head wake_list;
 #endif
-
-        struct sched_avg avg;
 };
 
 static inline int cpu_of(struct rq *rq)
@@ -1112,6 +1102,8 @@ static const u32 prio_to_wmult[40] = {
 
 #define DEQUEUE_SLEEP           1
 
+#define RETRY_TASK              ((void *)-1UL)
+
 struct sched_class {
         const struct sched_class *next;
 
@@ -1122,14 +1114,22 @@ struct sched_class {
 
         void (*check_preempt_curr) (struct rq *rq, struct task_struct *p, int flags);
 
-        struct task_struct * (*pick_next_task) (struct rq *rq);
+        /*
+         * It is the responsibility of the pick_next_task() method that will
+         * return the next task to call put_prev_task() on the @prev task or
+         * something equivalent.
+         *
+         * May return RETRY_TASK when it finds a higher prio class has runnable
+         * tasks.
+         */
+        struct task_struct * (*pick_next_task) (struct rq *rq,
+                                                struct task_struct *prev);
         void (*put_prev_task) (struct rq *rq, struct task_struct *p);
 
 #ifdef CONFIG_SMP
         int  (*select_task_rq)(struct task_struct *p, int task_cpu, int sd_flag, int flags);
         void (*migrate_task_rq)(struct task_struct *p, int next_cpu);
 
-        void (*pre_schedule) (struct rq *this_rq, struct task_struct *task);
         void (*post_schedule) (struct rq *this_rq);
         void (*task_waking) (struct task_struct *task);
         void (*task_woken) (struct rq *this_rq, struct task_struct *task);
@@ -1159,6 +1159,11 @@ struct sched_class {
 #endif
 };
 
+static inline void put_prev_task(struct rq *rq, struct task_struct *prev)
+{
+        prev->sched_class->put_prev_task(rq, prev);
+}
+
 #define sched_class_highest (&stop_sched_class)
 #define for_each_class(class) \
    for (class = sched_class_highest; class; class = class->next)
@@ -1175,16 +1180,14 @@ extern const struct sched_class idle_sched_class;
 extern void update_group_power(struct sched_domain *sd, int cpu);
 
 extern void trigger_load_balance(struct rq *rq);
-extern void idle_balance(int this_cpu, struct rq *this_rq);
 
 extern void idle_enter_fair(struct rq *this_rq);
 extern void idle_exit_fair(struct rq *this_rq);
 
-#else   /* CONFIG_SMP */
+#else
 
-static inline void idle_balance(int cpu, struct rq *rq)
-{
-}
+static inline void idle_enter_fair(struct rq *rq) { }
+static inline void idle_exit_fair(struct rq *rq) { }
 
 #endif
 
@@ -1213,16 +1216,6 @@ extern void update_idle_cpu_load(struct rq *this_rq);
 
 extern void init_task_runnable_average(struct task_struct *p);
 
-#ifdef CONFIG_PARAVIRT
-static inline u64 steal_ticks(u64 steal)
-{
-        if (unlikely(steal > NSEC_PER_SEC))
-                return div_u64(steal, TICK_NSEC);
-
-        return __iter_div_u64_rem(steal, TICK_NSEC, &steal);
-}
-#endif
-
 static inline void inc_nr_running(struct rq *rq)
 {
         rq->nr_running++;
diff --git a/kernel/sched/stats.c b/kernel/sched/stats.c
index da98af347e8b..a476bea17fbc 100644
--- a/kernel/sched/stats.c
+++ b/kernel/sched/stats.c
@@ -142,4 +142,4 @@ static int __init proc_schedstat_init(void)
         proc_create("schedstat", 0, NULL, &proc_schedstat_operations);
         return 0;
 }
-module_init(proc_schedstat_init);
+subsys_initcall(proc_schedstat_init);
diff --git a/kernel/sched/stop_task.c b/kernel/sched/stop_task.c
index fdb6bb0b3356..d6ce65dde541 100644
--- a/kernel/sched/stop_task.c
+++ b/kernel/sched/stop_task.c
@@ -23,16 +23,19 @@ check_preempt_curr_stop(struct rq *rq, struct task_struct *p, int flags)
         /* we're never preempted */
 }
 
-static struct task_struct *pick_next_task_stop(struct rq *rq)
+static struct task_struct *
+pick_next_task_stop(struct rq *rq, struct task_struct *prev)
 {
         struct task_struct *stop = rq->stop;
 
-        if (stop && stop->on_rq) {
-                stop->se.exec_start = rq_clock_task(rq);
-                return stop;
-        }
+        if (!stop || !stop->on_rq)
+                return NULL;
 
-        return NULL;
+        put_prev_task(rq, prev);
+
+        stop->se.exec_start = rq_clock_task(rq);
+
+        return stop;
 }
 
 static void
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index b7a10048a32c..fd609bd9d6dd 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -55,60 +55,33 @@ struct seccomp_filter {
         atomic_t usage;
         struct seccomp_filter *prev;
         unsigned short len;  /* Instruction count */
-        struct sock_filter insns[];
+        struct sock_filter_int insnsi[];
 };
 
 /* Limit any path through the tree to 256KB worth of instructions. */
 #define MAX_INSNS_PER_PATH ((1 << 18) / sizeof(struct sock_filter))
 
-/**
- * get_u32 - returns a u32 offset into data
- * @data: a unsigned 64 bit value
- * @index: 0 or 1 to return the first or second 32-bits
- *
- * This inline exists to hide the length of unsigned long.  If a 32-bit
- * unsigned long is passed in, it will be extended and the top 32-bits will be
- * 0. If it is a 64-bit unsigned long, then whatever data is resident will be
- * properly returned.
- *
+/*
  * Endianness is explicitly ignored and left for BPF program authors to manage
  * as per the specific architecture.
  */
-static inline u32 get_u32(u64 data, int index)
+static void populate_seccomp_data(struct seccomp_data *sd)
 {
-        return ((u32 *)&data)[index];
-}
+        struct task_struct *task = current;
+        struct pt_regs *regs = task_pt_regs(task);
 
-/* Helper for bpf_load below. */
-#define BPF_DATA(_name) offsetof(struct seccomp_data, _name)
-/**
- * bpf_load: checks and returns a pointer to the requested offset
- * @off: offset into struct seccomp_data to load from
- *
- * Returns the requested 32-bits of data.
- * seccomp_check_filter() should assure that @off is 32-bit aligned
- * and not out of bounds.  Failure to do so is a BUG.
- */
-u32 seccomp_bpf_load(int off)
-{
-        struct pt_regs *regs = task_pt_regs(current);
-        if (off == BPF_DATA(nr))
-                return syscall_get_nr(current, regs);
-        if (off == BPF_DATA(arch))
-                return syscall_get_arch(current, regs);
-        if (off >= BPF_DATA(args[0]) && off < BPF_DATA(args[6])) {
-                unsigned long value;
-                int arg = (off - BPF_DATA(args[0])) / sizeof(u64);
-                int index = !!(off % sizeof(u64));
-                syscall_get_arguments(current, regs, arg, 1, &value);
-                return get_u32(value, index);
-        }
-        if (off == BPF_DATA(instruction_pointer))
-                return get_u32(KSTK_EIP(current), 0);
-        if (off == BPF_DATA(instruction_pointer) + sizeof(u32))
-                return get_u32(KSTK_EIP(current), 1);
-        /* seccomp_check_filter should make this impossible. */
-        BUG();
+        sd->nr = syscall_get_nr(task, regs);
+        sd->arch = syscall_get_arch(task, regs);
+
+        /* Unroll syscall_get_args to help gcc on arm. */
+        syscall_get_arguments(task, regs, 0, 1, (unsigned long *) &sd->args[0]);
+        syscall_get_arguments(task, regs, 1, 1, (unsigned long *) &sd->args[1]);
+        syscall_get_arguments(task, regs, 2, 1, (unsigned long *) &sd->args[2]);
+        syscall_get_arguments(task, regs, 3, 1, (unsigned long *) &sd->args[3]);
+        syscall_get_arguments(task, regs, 4, 1, (unsigned long *) &sd->args[4]);
+        syscall_get_arguments(task, regs, 5, 1, (unsigned long *) &sd->args[5]);
+
+        sd->instruction_pointer = KSTK_EIP(task);
 }
 
 /**
@@ -133,17 +106,17 @@ static int seccomp_check_filter(struct sock_filter *filter, unsigned int flen)
 
                 switch (code) {
                 case BPF_S_LD_W_ABS:
-                        ftest->code = BPF_S_ANC_SECCOMP_LD_W;
+                        ftest->code = BPF_LDX | BPF_W | BPF_ABS;
                         /* 32-bit aligned and not out of bounds. */
                         if (k >= sizeof(struct seccomp_data) || k & 3)
                                 return -EINVAL;
                         continue;
                 case BPF_S_LD_W_LEN:
-                        ftest->code = BPF_S_LD_IMM;
+                        ftest->code = BPF_LD | BPF_IMM;
                         ftest->k = sizeof(struct seccomp_data);
                         continue;
                 case BPF_S_LDX_W_LEN:
-                        ftest->code = BPF_S_LDX_IMM;
+                        ftest->code = BPF_LDX | BPF_IMM;
                         ftest->k = sizeof(struct seccomp_data);
                         continue;
                 /* Explicitly include allowed calls. */
@@ -185,6 +158,7 @@ static int seccomp_check_filter(struct sock_filter *filter, unsigned int flen)
                 case BPF_S_JMP_JGT_X:
                 case BPF_S_JMP_JSET_K:
                 case BPF_S_JMP_JSET_X:
+                        sk_decode_filter(ftest, ftest);
                         continue;
                 default:
                         return -EINVAL;
@@ -202,18 +176,21 @@ static int seccomp_check_filter(struct sock_filter *filter, unsigned int flen)
 static u32 seccomp_run_filters(int syscall)
 {
         struct seccomp_filter *f;
+        struct seccomp_data sd;
         u32 ret = SECCOMP_RET_ALLOW;
 
         /* Ensure unexpected behavior doesn't result in failing open. */
         if (WARN_ON(current->seccomp.filter == NULL))
                 return SECCOMP_RET_KILL;
 
+        populate_seccomp_data(&sd);
+
         /*
          * All filters in the list are evaluated and the lowest BPF return
          * value always takes priority (ignoring the DATA).
          */
         for (f = current->seccomp.filter; f; f = f->prev) {
-                u32 cur_ret = sk_run_filter(NULL, f->insns);
+                u32 cur_ret = sk_run_filter_int_seccomp(&sd, f->insnsi);
                 if ((cur_ret & SECCOMP_RET_ACTION) < (ret & SECCOMP_RET_ACTION))
                         ret = cur_ret;
         }
@@ -231,6 +208,8 @@ static long seccomp_attach_filter(struct sock_fprog *fprog)
         struct seccomp_filter *filter;
         unsigned long fp_size = fprog->len * sizeof(struct sock_filter);
         unsigned long total_insns = fprog->len;
+        struct sock_filter *fp;
+        int new_len;
         long ret;
 
         if (fprog->len == 0 || fprog->len > BPF_MAXINSNS)
@@ -252,28 +231,43 @@ static long seccomp_attach_filter(struct sock_fprog *fprog)
                                      CAP_SYS_ADMIN) != 0)
                 return -EACCES;
 
-        /* Allocate a new seccomp_filter */
-        filter = kzalloc(sizeof(struct seccomp_filter) + fp_size,
-                         GFP_KERNEL|__GFP_NOWARN);
-        if (!filter)
+        fp = kzalloc(fp_size, GFP_KERNEL|__GFP_NOWARN);
+        if (!fp)
                 return -ENOMEM;
-        atomic_set(&filter->usage, 1);
-        filter->len = fprog->len;
 
         /* Copy the instructions from fprog. */
         ret = -EFAULT;
-        if (copy_from_user(filter->insns, fprog->filter, fp_size))
-                goto fail;
+        if (copy_from_user(fp, fprog->filter, fp_size))
+                goto free_prog;
 
         /* Check and rewrite the fprog via the skb checker */
-        ret = sk_chk_filter(filter->insns, filter->len);
+        ret = sk_chk_filter(fp, fprog->len);
         if (ret)
-                goto fail;
+                goto free_prog;
 
         /* Check and rewrite the fprog for seccomp use */
-        ret = seccomp_check_filter(filter->insns, filter->len);
+        ret = seccomp_check_filter(fp, fprog->len);
+        if (ret)
+                goto free_prog;
+
+        /* Convert 'sock_filter' insns to 'sock_filter_int' insns */
+        ret = sk_convert_filter(fp, fprog->len, NULL, &new_len);
+        if (ret)
+                goto free_prog;
+
+        /* Allocate a new seccomp_filter */
+        filter = kzalloc(sizeof(struct seccomp_filter) +
+                         sizeof(struct sock_filter_int) * new_len,
+                         GFP_KERNEL|__GFP_NOWARN);
+        if (!filter)
+                goto free_prog;
+
+        ret = sk_convert_filter(fp, fprog->len, filter->insnsi, &new_len);
         if (ret)
-                goto fail;
+                goto free_filter;
+
+        atomic_set(&filter->usage, 1);
+        filter->len = new_len;
 
         /*
          * If there is an existing filter, make it the prev and don't drop its
@@ -282,8 +276,11 @@ static long seccomp_attach_filter(struct sock_fprog *fprog)
         filter->prev = current->seccomp.filter;
         current->seccomp.filter = filter;
         return 0;
-fail:
+
+free_filter:
         kfree(filter);
+free_prog:
+        kfree(fp);
         return ret;
 }
 
@@ -293,7 +290,7 @@ fail:
  *
  * Returns 0 on success and non-zero otherwise.
  */
-long seccomp_attach_user_filter(char __user *user_filter)
+static long seccomp_attach_user_filter(char __user *user_filter)
 {
         struct sock_fprog fprog;
         long ret = -EFAULT;
diff --git a/kernel/signal.c b/kernel/signal.c
index 52f881db1ca0..5d4b05a229a6 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -2382,7 +2382,7 @@ relock:
  * @regs:               user register state
  * @stepping:           nonzero if debugger single-step or block-step in use
  *
- * This function should be called when a signal has succesfully been
+ * This function should be called when a signal has successfully been
  * delivered. It updates the blocked signals accordingly (@ka->sa.sa_mask
  * is always blocked, and the signal itself is blocked unless %SA_NODEFER
  * is set in @ka->sa.sa_flags.  Tracing is notified.
diff --git a/kernel/smp.c b/kernel/smp.c
index ffee35bef179..06d574e42c72 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -117,13 +117,43 @@ static void csd_unlock(struct call_single_data *csd)
         csd->flags &= ~CSD_FLAG_LOCK;
 }
 
+static DEFINE_PER_CPU_SHARED_ALIGNED(struct call_single_data, csd_data);
+
 /*
  * Insert a previously allocated call_single_data element
  * for execution on the given CPU. data must already have
  * ->func, ->info, and ->flags set.
  */
-static void generic_exec_single(int cpu, struct call_single_data *csd, int wait)
+static int generic_exec_single(int cpu, struct call_single_data *csd,
+                               smp_call_func_t func, void *info, int wait)
 {
+        struct call_single_data csd_stack = { .flags = 0 };
+        unsigned long flags;
+
+
+        if (cpu == smp_processor_id()) {
+                local_irq_save(flags);
+                func(info);
+                local_irq_restore(flags);
+                return 0;
+        }
+
+
+        if ((unsigned)cpu >= nr_cpu_ids || !cpu_online(cpu))
+                return -ENXIO;
+
+
+        if (!csd) {
+                csd = &csd_stack;
+                if (!wait)
+                        csd = &__get_cpu_var(csd_data);
+        }
+
+        csd_lock(csd);
+
+        csd->func = func;
+        csd->info = info;
+
         if (wait)
                 csd->flags |= CSD_FLAG_WAIT;
 
@@ -143,6 +173,8 @@ static void generic_exec_single(int cpu, struct call_single_data *csd, int wait)
 
         if (wait)
                 csd_lock_wait(csd);
+
+        return 0;
 }
 
 /*
@@ -151,7 +183,8 @@ static void generic_exec_single(int cpu, struct call_single_data *csd, int wait)
  */
 void generic_smp_call_function_single_interrupt(void)
 {
-        struct llist_node *entry, *next;
+        struct llist_node *entry;
+        struct call_single_data *csd, *csd_next;
 
         /*
          * Shouldn't receive this interrupt on a cpu that is not yet online.
@@ -161,21 +194,12 @@ void generic_smp_call_function_single_interrupt(void)
         entry = llist_del_all(&__get_cpu_var(call_single_queue));
         entry = llist_reverse_order(entry);
 
-        while (entry) {
-                struct call_single_data *csd;
-
-                next = entry->next;
-
-                csd = llist_entry(entry, struct call_single_data, llist);
+        llist_for_each_entry_safe(csd, csd_next, entry, llist) {
                 csd->func(csd->info);
                 csd_unlock(csd);
-
-                entry = next;
         }
 }
 
-static DEFINE_PER_CPU_SHARED_ALIGNED(struct call_single_data, csd_data);
-
 /*
  * smp_call_function_single - Run a function on a specific CPU
  * @func: The function to run. This must be fast and non-blocking.
@@ -187,12 +211,8 @@ static DEFINE_PER_CPU_SHARED_ALIGNED(struct call_single_data, csd_data);
 int smp_call_function_single(int cpu, smp_call_func_t func, void *info,
                              int wait)
 {
-        struct call_single_data d = {
-                .flags = 0,
-        };
-        unsigned long flags;
         int this_cpu;
-        int err = 0;
+        int err;
 
         /*
          * prevent preemption and reschedule on another processor,
@@ -209,32 +229,41 @@ int smp_call_function_single(int cpu, smp_call_func_t func, void *info,
         WARN_ON_ONCE(cpu_online(this_cpu) && irqs_disabled()
                      && !oops_in_progress);
 
-        if (cpu == this_cpu) {
-                local_irq_save(flags);
-                func(info);
-                local_irq_restore(flags);
-        } else {
-                if ((unsigned)cpu < nr_cpu_ids && cpu_online(cpu)) {
-                        struct call_single_data *csd = &d;
+        err = generic_exec_single(cpu, NULL, func, info, wait);
 
-                        if (!wait)
-                                csd = &__get_cpu_var(csd_data);
+        put_cpu();
 
-                        csd_lock(csd);
+        return err;
+}
+EXPORT_SYMBOL(smp_call_function_single);
 
-                        csd->func = func;
-                        csd->info = info;
-                        generic_exec_single(cpu, csd, wait);
-                } else {
-                        err = -ENXIO;   /* CPU not online */
-                }
-        }
+/**
+ * smp_call_function_single_async(): Run an asynchronous function on a
+ *                               specific CPU.
+ * @cpu: The CPU to run on.
+ * @csd: Pre-allocated and setup data structure
+ *
+ * Like smp_call_function_single(), but the call is asynchonous and
+ * can thus be done from contexts with disabled interrupts.
+ *
+ * The caller passes his own pre-allocated data structure
+ * (ie: embedded in an object) and is responsible for synchronizing it
+ * such that the IPIs performed on the @csd are strictly serialized.
+ *
+ * NOTE: Be careful, there is unfortunately no current debugging facility to
+ * validate the correctness of this serialization.
+ */
+int smp_call_function_single_async(int cpu, struct call_single_data *csd)
+{
+        int err = 0;
 
-        put_cpu();
+        preempt_disable();
+        err = generic_exec_single(cpu, csd, csd->func, csd->info, 0);
+        preempt_enable();
 
         return err;
 }
-EXPORT_SYMBOL(smp_call_function_single);
+EXPORT_SYMBOL_GPL(smp_call_function_single_async);
 
 /*
  * smp_call_function_any - Run a function on any of the given cpus
@@ -280,44 +309,6 @@ call:
 EXPORT_SYMBOL_GPL(smp_call_function_any);
 
 /**
- * __smp_call_function_single(): Run a function on a specific CPU
- * @cpu: The CPU to run on.
- * @data: Pre-allocated and setup data structure
- * @wait: If true, wait until function has completed on specified CPU.
- *
- * Like smp_call_function_single(), but allow caller to pass in a
- * pre-allocated data structure. Useful for embedding @data inside
- * other structures, for instance.
- */
-void __smp_call_function_single(int cpu, struct call_single_data *csd,
-                                int wait)
-{
-        unsigned int this_cpu;
-        unsigned long flags;
-
-        this_cpu = get_cpu();
-        /*
-         * Can deadlock when called with interrupts disabled.
-         * We allow cpu's that are not yet online though, as no one else can
-         * send smp call function interrupt to this cpu and as such deadlocks
-         * can't happen.
-         */
-        WARN_ON_ONCE(cpu_online(smp_processor_id()) && wait && irqs_disabled()
-                     && !oops_in_progress);
-
-        if (cpu == this_cpu) {
-                local_irq_save(flags);
-                csd->func(csd->info);
-                local_irq_restore(flags);
-        } else {
-                csd_lock(csd);
-                generic_exec_single(cpu, csd, wait);
-        }
-        put_cpu();
-}
-EXPORT_SYMBOL_GPL(__smp_call_function_single);
-
-/**
  * smp_call_function_many(): Run a function on a set of other CPUs.
  * @mask: The set of cpus to run on (only runs on online subset).
  * @func: The function to run. This must be fast and non-blocking.
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 490fcbb1dc5b..b50990a5bea0 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -25,6 +25,7 @@
 #include <linux/smp.h>
 #include <linux/smpboot.h>
 #include <linux/tick.h>
+#include <linux/irq.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/irq.h>
diff --git a/kernel/sys.c b/kernel/sys.c
index c0a58be780a4..adaeab6f7a87 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -174,10 +174,10 @@ SYSCALL_DEFINE3(setpriority, int, which, int, who, int, niceval)
 
         /* normalize: avoid signed division (rounding problems) */
         error = -ESRCH;
-        if (niceval < -20)
-                niceval = -20;
-        if (niceval > 19)
-                niceval = 19;
+        if (niceval < MIN_NICE)
+                niceval = MIN_NICE;
+        if (niceval > MAX_NICE)
+                niceval = MAX_NICE;
 
         rcu_read_lock();
         read_lock(&tasklist_lock);
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index 7078052284fd..bc8d1b74a6b9 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -146,11 +146,13 @@ cond_syscall(sys_io_destroy);
 cond_syscall(sys_io_submit);
 cond_syscall(sys_io_cancel);
 cond_syscall(sys_io_getevents);
+cond_syscall(sys_sysfs);
 cond_syscall(sys_syslog);
 cond_syscall(sys_process_vm_readv);
 cond_syscall(sys_process_vm_writev);
 cond_syscall(compat_sys_process_vm_readv);
 cond_syscall(compat_sys_process_vm_writev);
+cond_syscall(sys_uselib);
 
 /* arch-specific weak syscall entries */
 cond_syscall(sys_pciconfig_read);
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 49e13e1f8fe6..5c14b547882e 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -112,9 +112,6 @@ extern int sysctl_nr_open_min, sysctl_nr_open_max;
 #ifndef CONFIG_MMU
 extern int sysctl_nr_trim_pages;
 #endif
-#ifdef CONFIG_BLOCK
-extern int blk_iopoll_enabled;
-#endif
 
 /* Constants used for minimum and  maximum */
 #ifdef CONFIG_LOCKUP_DETECTOR
@@ -126,7 +123,7 @@ static int __maybe_unused neg_one = -1;
 static int zero;
 static int __maybe_unused one = 1;
 static int __maybe_unused two = 2;
-static int __maybe_unused three = 3;
+static int __maybe_unused four = 4;
 static unsigned long one_ul = 1;
 static int one_hundred = 100;
 #ifdef CONFIG_PRINTK
@@ -386,13 +383,6 @@ static struct ctl_table kern_table[] = {
                 .proc_handler   = proc_dointvec,
         },
         {
-                .procname       = "numa_balancing_migrate_deferred",
-                .data           = &sysctl_numa_balancing_migrate_deferred,
-                .maxlen         = sizeof(unsigned int),
-                .mode           = 0644,
-                .proc_handler   = proc_dointvec,
-        },
-        {
                 .procname       = "numa_balancing",
                 .data           = NULL, /* filled in by handler */
                 .maxlen         = sizeof(unsigned int),
@@ -1094,15 +1084,6 @@ static struct ctl_table kern_table[] = {
                 .proc_handler   = proc_dointvec,
         },
 #endif
-#ifdef CONFIG_BLOCK
-        {
-                .procname       = "blk_iopoll",
-                .data           = &blk_iopoll_enabled,
-                .maxlen         = sizeof(int),
-                .mode           = 0644,
-                .proc_handler   = proc_dointvec,
-        },
-#endif
         { }
 };
 
@@ -1283,7 +1264,7 @@ static struct ctl_table vm_table[] = {
                 .mode           = 0644,
                 .proc_handler   = drop_caches_sysctl_handler,
                 .extra1         = &one,
-                .extra2         = &three,
+                .extra2         = &four,
         },
 #ifdef CONFIG_COMPACTION
         {
diff --git a/kernel/time/Kconfig b/kernel/time/Kconfig
index 3ce6e8c5f3fc..f448513a45ed 100644
--- a/kernel/time/Kconfig
+++ b/kernel/time/Kconfig
@@ -124,7 +124,7 @@ config NO_HZ_FULL
 endchoice
 
 config NO_HZ_FULL_ALL
-       bool "Full dynticks system on all CPUs by default"
+       bool "Full dynticks system on all CPUs by default (except CPU 0)"
        depends on NO_HZ_FULL
        help
          If the user doesn't pass the nohz_full boot option to
diff --git a/kernel/time/Makefile b/kernel/time/Makefile
index 9250130646f5..57a413fd0ebf 100644
--- a/kernel/time/Makefile
+++ b/kernel/time/Makefile
@@ -3,7 +3,10 @@ obj-y += timeconv.o posix-clock.o alarmtimer.o
 
 obj-$(CONFIG_GENERIC_CLOCKEVENTS_BUILD)         += clockevents.o
 obj-$(CONFIG_GENERIC_CLOCKEVENTS)               += tick-common.o
-obj-$(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST)     += tick-broadcast.o
+ifeq ($(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST),y)
+ obj-y                                          += tick-broadcast.o
+ obj-$(CONFIG_TICK_ONESHOT)                     += tick-broadcast-hrtimer.o
+endif
 obj-$(CONFIG_GENERIC_SCHED_CLOCK)               += sched_clock.o
 obj-$(CONFIG_TICK_ONESHOT)                      += tick-oneshot.o
 obj-$(CONFIG_TICK_ONESHOT)                      += tick-sched.o
diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c
index 086ad6043bcb..ad362c260ef4 100644
--- a/kernel/time/clockevents.c
+++ b/kernel/time/clockevents.c
@@ -439,6 +439,19 @@ void clockevents_config_and_register(struct clock_event_device *dev,
 }
 EXPORT_SYMBOL_GPL(clockevents_config_and_register);
 
+int __clockevents_update_freq(struct clock_event_device *dev, u32 freq)
+{
+        clockevents_config(dev, freq);
+
+        if (dev->mode == CLOCK_EVT_MODE_ONESHOT)
+                return clockevents_program_event(dev, dev->next_event, false);
+
+        if (dev->mode == CLOCK_EVT_MODE_PERIODIC)
+                dev->set_mode(CLOCK_EVT_MODE_PERIODIC, dev);
+
+        return 0;
+}
+
 /**
  * clockevents_update_freq - Update frequency and reprogram a clock event device.
  * @dev:        device to modify
@@ -446,17 +459,22 @@ EXPORT_SYMBOL_GPL(clockevents_config_and_register);
  *
  * Reconfigure and reprogram a clock event device in oneshot
  * mode. Must be called on the cpu for which the device delivers per
- * cpu timer events with interrupts disabled!  Returns 0 on success,
- * -ETIME when the event is in the past.
+ * cpu timer events. If called for the broadcast device the core takes
+ * care of serialization.
+ *
+ * Returns 0 on success, -ETIME when the event is in the past.
  */
 int clockevents_update_freq(struct clock_event_device *dev, u32 freq)
 {
-        clockevents_config(dev, freq);
-
-        if (dev->mode != CLOCK_EVT_MODE_ONESHOT)
-                return 0;
+        unsigned long flags;
+        int ret;
 
-        return clockevents_program_event(dev, dev->next_event, false);
+        local_irq_save(flags);
+        ret = tick_broadcast_update_freq(dev, freq);
+        if (ret == -ENODEV)
+                ret = __clockevents_update_freq(dev, freq);
+        local_irq_restore(flags);
+        return ret;
 }
 
 /*
@@ -524,12 +542,13 @@ void clockevents_resume(void)
 #ifdef CONFIG_GENERIC_CLOCKEVENTS
 /**
  * clockevents_notify - notification about relevant events
+ * Returns 0 on success, any other value on error
  */
-void clockevents_notify(unsigned long reason, void *arg)
+int clockevents_notify(unsigned long reason, void *arg)
 {
         struct clock_event_device *dev, *tmp;
         unsigned long flags;
-        int cpu;
+        int cpu, ret = 0;
 
         raw_spin_lock_irqsave(&clockevents_lock, flags);
 
@@ -542,7 +561,7 @@ void clockevents_notify(unsigned long reason, void *arg)
 
         case CLOCK_EVT_NOTIFY_BROADCAST_ENTER:
         case CLOCK_EVT_NOTIFY_BROADCAST_EXIT:
-                tick_broadcast_oneshot_control(reason);
+                ret = tick_broadcast_oneshot_control(reason);
                 break;
 
         case CLOCK_EVT_NOTIFY_CPU_DYING:
@@ -585,6 +604,7 @@ void clockevents_notify(unsigned long reason, void *arg)
                 break;
         }
         raw_spin_unlock_irqrestore(&clockevents_lock, flags);
+        return ret;
 }
 EXPORT_SYMBOL_GPL(clockevents_notify);
 
diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
index af8d1d4f3d55..419a52cecd20 100644
--- a/kernel/time/ntp.c
+++ b/kernel/time/ntp.c
@@ -514,12 +514,13 @@ static void sync_cmos_clock(struct work_struct *work)
                 next.tv_sec++;
                 next.tv_nsec -= NSEC_PER_SEC;
         }
-        schedule_delayed_work(&sync_cmos_work, timespec_to_jiffies(&next));
+        queue_delayed_work(system_power_efficient_wq,
+                           &sync_cmos_work, timespec_to_jiffies(&next));
 }
 
 void ntp_notify_cmos_timer(void)
 {
-        schedule_delayed_work(&sync_cmos_work, 0);
+        queue_delayed_work(system_power_efficient_wq, &sync_cmos_work, 0);
 }
 
 #else
diff --git a/kernel/time/tick-broadcast-hrtimer.c b/kernel/time/tick-broadcast-hrtimer.c
new file mode 100644
index 000000000000..eb682d5c697c
--- /dev/null
+++ b/kernel/time/tick-broadcast-hrtimer.c
@@ -0,0 +1,106 @@
+/*
+ * linux/kernel/time/tick-broadcast-hrtimer.c
+ * This file emulates a local clock event device
+ * via a pseudo clock device.
+ */
+#include <linux/cpu.h>
+#include <linux/err.h>
+#include <linux/hrtimer.h>
+#include <linux/interrupt.h>
+#include <linux/percpu.h>
+#include <linux/profile.h>
+#include <linux/clockchips.h>
+#include <linux/sched.h>
+#include <linux/smp.h>
+#include <linux/module.h>
+
+#include "tick-internal.h"
+
+static struct hrtimer bctimer;
+
+static void bc_set_mode(enum clock_event_mode mode,
+                        struct clock_event_device *bc)
+{
+        switch (mode) {
+        case CLOCK_EVT_MODE_SHUTDOWN:
+                /*
+                 * Note, we cannot cancel the timer here as we might
+                 * run into the following live lock scenario:
+                 *
+                 * cpu 0                cpu1
+                 * lock(broadcast_lock);
+                 *                      hrtimer_interrupt()
+                 *                      bc_handler()
+                 *                         tick_handle_oneshot_broadcast();
+                 *                          lock(broadcast_lock);
+                 * hrtimer_cancel()
+                 *  wait_for_callback()
+                 */
+                hrtimer_try_to_cancel(&bctimer);
+                break;
+        default:
+                break;
+        }
+}
+
+/*
+ * This is called from the guts of the broadcast code when the cpu
+ * which is about to enter idle has the earliest broadcast timer event.
+ */
+static int bc_set_next(ktime_t expires, struct clock_event_device *bc)
+{
+        /*
+         * We try to cancel the timer first. If the callback is on
+         * flight on some other cpu then we let it handle it. If we
+         * were able to cancel the timer nothing can rearm it as we
+         * own broadcast_lock.
+         *
+         * However we can also be called from the event handler of
+         * ce_broadcast_hrtimer itself when it expires. We cannot
+         * restart the timer because we are in the callback, but we
+         * can set the expiry time and let the callback return
+         * HRTIMER_RESTART.
+         */
+        if (hrtimer_try_to_cancel(&bctimer) >= 0) {
+                hrtimer_start(&bctimer, expires, HRTIMER_MODE_ABS_PINNED);
+                /* Bind the "device" to the cpu */
+                bc->bound_on = smp_processor_id();
+        } else if (bc->bound_on == smp_processor_id()) {
+                hrtimer_set_expires(&bctimer, expires);
+        }
+        return 0;
+}
+
+static struct clock_event_device ce_broadcast_hrtimer = {
+        .set_mode               = bc_set_mode,
+        .set_next_ktime         = bc_set_next,
+        .features               = CLOCK_EVT_FEAT_ONESHOT |
+                                  CLOCK_EVT_FEAT_KTIME |
+                                  CLOCK_EVT_FEAT_HRTIMER,
+        .rating                 = 0,
+        .bound_on               = -1,
+        .min_delta_ns           = 1,
+        .max_delta_ns           = KTIME_MAX,
+        .min_delta_ticks        = 1,
+        .max_delta_ticks        = ULONG_MAX,
+        .mult                   = 1,
+        .shift                  = 0,
+        .cpumask                = cpu_all_mask,
+};
+
+static enum hrtimer_restart bc_handler(struct hrtimer *t)
+{
+        ce_broadcast_hrtimer.event_handler(&ce_broadcast_hrtimer);
+
+        if (ce_broadcast_hrtimer.next_event.tv64 == KTIME_MAX)
+                return HRTIMER_NORESTART;
+
+        return HRTIMER_RESTART;
+}
+
+void tick_setup_hrtimer_broadcast(void)
+{
+        hrtimer_init(&bctimer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
+        bctimer.function = bc_handler;
+        clockevents_register_device(&ce_broadcast_hrtimer);
+}
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index 98977a57ac72..64c5990fd500 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -120,6 +120,19 @@ int tick_is_broadcast_device(struct clock_event_device *dev)
         return (dev && tick_broadcast_device.evtdev == dev);
 }
 
+int tick_broadcast_update_freq(struct clock_event_device *dev, u32 freq)
+{
+        int ret = -ENODEV;
+
+        if (tick_is_broadcast_device(dev)) {
+                raw_spin_lock(&tick_broadcast_lock);
+                ret = __clockevents_update_freq(dev, freq);
+                raw_spin_unlock(&tick_broadcast_lock);
+        }
+        return ret;
+}
+
+
 static void err_broadcast(const struct cpumask *mask)
 {
         pr_crit_once("Failed to broadcast timer tick. Some CPUs may be unresponsive.\n");
@@ -272,12 +285,8 @@ static void tick_do_broadcast(struct cpumask *mask)
  */
 static void tick_do_periodic_broadcast(void)
 {
-        raw_spin_lock(&tick_broadcast_lock);
-
         cpumask_and(tmpmask, cpu_online_mask, tick_broadcast_mask);
         tick_do_broadcast(tmpmask);
-
-        raw_spin_unlock(&tick_broadcast_lock);
 }
 
 /*
@@ -287,13 +296,15 @@ static void tick_handle_periodic_broadcast(struct clock_event_device *dev)
 {
         ktime_t next;
 
+        raw_spin_lock(&tick_broadcast_lock);
+
         tick_do_periodic_broadcast();
 
         /*
          * The device is in periodic mode. No reprogramming necessary:
          */
         if (dev->mode == CLOCK_EVT_MODE_PERIODIC)
-                return;
+                goto unlock;
 
         /*
          * Setup the next period for devices, which do not have
@@ -306,9 +317,11 @@ static void tick_handle_periodic_broadcast(struct clock_event_device *dev)
                 next = ktime_add(next, tick_period);
 
                 if (!clockevents_program_event(dev, next, false))
-                        return;
+                        goto unlock;
                 tick_do_periodic_broadcast();
         }
+unlock:
+        raw_spin_unlock(&tick_broadcast_lock);
 }
 
 /*
@@ -630,24 +643,61 @@ again:
         raw_spin_unlock(&tick_broadcast_lock);
 }
 
+static int broadcast_needs_cpu(struct clock_event_device *bc, int cpu)
+{
+        if (!(bc->features & CLOCK_EVT_FEAT_HRTIMER))
+                return 0;
+        if (bc->next_event.tv64 == KTIME_MAX)
+                return 0;
+        return bc->bound_on == cpu ? -EBUSY : 0;
+}
+
+static void broadcast_shutdown_local(struct clock_event_device *bc,
+                                     struct clock_event_device *dev)
+{
+        /*
+         * For hrtimer based broadcasting we cannot shutdown the cpu
+         * local device if our own event is the first one to expire or
+         * if we own the broadcast timer.
+         */
+        if (bc->features & CLOCK_EVT_FEAT_HRTIMER) {
+                if (broadcast_needs_cpu(bc, smp_processor_id()))
+                        return;
+                if (dev->next_event.tv64 < bc->next_event.tv64)
+                        return;
+        }
+        clockevents_set_mode(dev, CLOCK_EVT_MODE_SHUTDOWN);
+}
+
+static void broadcast_move_bc(int deadcpu)
+{
+        struct clock_event_device *bc = tick_broadcast_device.evtdev;
+
+        if (!bc || !broadcast_needs_cpu(bc, deadcpu))
+                return;
+        /* This moves the broadcast assignment to this cpu */
+        clockevents_program_event(bc, bc->next_event, 1);
+}
+
 /*
  * Powerstate information: The system enters/leaves a state, where
  * affected devices might stop
+ * Returns 0 on success, -EBUSY if the cpu is used to broadcast wakeups.
  */
-void tick_broadcast_oneshot_control(unsigned long reason)
+int tick_broadcast_oneshot_control(unsigned long reason)
 {
         struct clock_event_device *bc, *dev;
         struct tick_device *td;
         unsigned long flags;
         ktime_t now;
-        int cpu;
+        int cpu, ret = 0;
 
         /*
          * Periodic mode does not care about the enter/exit of power
          * states
          */
         if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC)
-                return;
+                return 0;
 
         /*
          * We are called with preemtion disabled from the depth of the
@@ -658,7 +708,7 @@ void tick_broadcast_oneshot_control(unsigned long reason)
         dev = td->evtdev;
 
         if (!(dev->features & CLOCK_EVT_FEAT_C3STOP))
-                return;
+                return 0;
 
         bc = tick_broadcast_device.evtdev;
 
@@ -666,7 +716,7 @@ void tick_broadcast_oneshot_control(unsigned long reason)
         if (reason == CLOCK_EVT_NOTIFY_BROADCAST_ENTER) {
                 if (!cpumask_test_and_set_cpu(cpu, tick_broadcast_oneshot_mask)) {
                         WARN_ON_ONCE(cpumask_test_cpu(cpu, tick_broadcast_pending_mask));
-                        clockevents_set_mode(dev, CLOCK_EVT_MODE_SHUTDOWN);
+                        broadcast_shutdown_local(bc, dev);
                         /*
                          * We only reprogram the broadcast timer if we
                          * did not mark ourself in the force mask and
@@ -679,6 +729,16 @@ void tick_broadcast_oneshot_control(unsigned long reason)
                             dev->next_event.tv64 < bc->next_event.tv64)
                                 tick_broadcast_set_event(bc, cpu, dev->next_event, 1);
                 }
+                /*
+                 * If the current CPU owns the hrtimer broadcast
+                 * mechanism, it cannot go deep idle and we remove the
+                 * CPU from the broadcast mask. We don't have to go
+                 * through the EXIT path as the local timer is not
+                 * shutdown.
+                 */
+                ret = broadcast_needs_cpu(bc, cpu);
+                if (ret)
+                        cpumask_clear_cpu(cpu, tick_broadcast_oneshot_mask);
         } else {
                 if (cpumask_test_and_clear_cpu(cpu, tick_broadcast_oneshot_mask)) {
                         clockevents_set_mode(dev, CLOCK_EVT_MODE_ONESHOT);
@@ -746,6 +806,7 @@ void tick_broadcast_oneshot_control(unsigned long reason)
         }
 out:
         raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags);
+        return ret;
 }
 
 /*
@@ -852,6 +913,8 @@ void tick_shutdown_broadcast_oneshot(unsigned int *cpup)
         cpumask_clear_cpu(cpu, tick_broadcast_pending_mask);
         cpumask_clear_cpu(cpu, tick_broadcast_force_mask);
 
+        broadcast_move_bc(cpu);
+
         raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags);
 }
 
diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c
index 20b2fe37d105..015661279b68 100644
--- a/kernel/time/tick-common.c
+++ b/kernel/time/tick-common.c
@@ -98,18 +98,19 @@ static void tick_periodic(int cpu)
 void tick_handle_periodic(struct clock_event_device *dev)
 {
         int cpu = smp_processor_id();
-        ktime_t next;
+        ktime_t next = dev->next_event;
 
         tick_periodic(cpu);
 
         if (dev->mode != CLOCK_EVT_MODE_ONESHOT)
                 return;
-        /*
-         * Setup the next period for devices, which do not have
-         * periodic mode:
-         */
-        next = ktime_add(dev->next_event, tick_period);
         for (;;) {
+                /*
+                 * Setup the next period for devices, which do not have
+                 * periodic mode:
+                 */
+                next = ktime_add(next, tick_period);
+
                 if (!clockevents_program_event(dev, next, false))
                         return;
                 /*
@@ -118,12 +119,11 @@ void tick_handle_periodic(struct clock_event_device *dev)
                  * to be sure we're using a real hardware clocksource.
                  * Otherwise we could get trapped in an infinite
                  * loop, as the tick_periodic() increments jiffies,
-                 * when then will increment time, posibly causing
+                 * which then will increment time, possibly causing
                  * the loop to trigger again and again.
                  */
                 if (timekeeping_valid_for_hres())
                         tick_periodic(cpu);
-                next = ktime_add(next, tick_period);
         }
 }
 
diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h
index 8329669b51ec..7ab92b19965a 100644
--- a/kernel/time/tick-internal.h
+++ b/kernel/time/tick-internal.h
@@ -46,7 +46,7 @@ extern int tick_switch_to_oneshot(void (*handler)(struct clock_event_device *));
 extern void tick_resume_oneshot(void);
 # ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
 extern void tick_broadcast_setup_oneshot(struct clock_event_device *bc);
-extern void tick_broadcast_oneshot_control(unsigned long reason);
+extern int tick_broadcast_oneshot_control(unsigned long reason);
 extern void tick_broadcast_switch_to_oneshot(void);
 extern void tick_shutdown_broadcast_oneshot(unsigned int *cpup);
 extern int tick_resume_broadcast_oneshot(struct clock_event_device *bc);
@@ -58,7 +58,7 @@ static inline void tick_broadcast_setup_oneshot(struct clock_event_device *bc)
 {
         BUG();
 }
-static inline void tick_broadcast_oneshot_control(unsigned long reason) { }
+static inline int tick_broadcast_oneshot_control(unsigned long reason) { return 0; }
 static inline void tick_broadcast_switch_to_oneshot(void) { }
 static inline void tick_shutdown_broadcast_oneshot(unsigned int *cpup) { }
 static inline int tick_broadcast_oneshot_active(void) { return 0; }
@@ -87,7 +87,7 @@ static inline void tick_broadcast_setup_oneshot(struct clock_event_device *bc)
 {
         BUG();
 }
-static inline void tick_broadcast_oneshot_control(unsigned long reason) { }
+static inline int tick_broadcast_oneshot_control(unsigned long reason) { return 0; }
 static inline void tick_shutdown_broadcast_oneshot(unsigned int *cpup) { }
 static inline int tick_resume_broadcast_oneshot(struct clock_event_device *bc)
 {
@@ -111,6 +111,7 @@ extern int tick_resume_broadcast(void);
 extern void tick_broadcast_init(void);
 extern void
 tick_set_periodic_handler(struct clock_event_device *dev, int broadcast);
+int tick_broadcast_update_freq(struct clock_event_device *dev, u32 freq);
 
 #else /* !BROADCAST */
 
@@ -133,6 +134,8 @@ static inline void tick_shutdown_broadcast(unsigned int *cpup) { }
 static inline void tick_suspend_broadcast(void) { }
 static inline int tick_resume_broadcast(void) { return 0; }
 static inline void tick_broadcast_init(void) { }
+static inline int tick_broadcast_update_freq(struct clock_event_device *dev,
+                                             u32 freq) { return -ENODEV; }
 
 /*
  * Set the periodic handler in non broadcast mode
@@ -152,6 +155,8 @@ static inline int tick_device_is_functional(struct clock_event_device *dev)
         return !(dev->features & CLOCK_EVT_FEAT_DUMMY);
 }
 
+int __clockevents_update_freq(struct clock_event_device *dev, u32 freq);
+
 #endif
 
 extern void do_timer(unsigned long ticks);
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 0aa4ce81bc16..5b40279ecd71 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -1435,7 +1435,8 @@ void update_wall_time(void)
 out:
         raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
         if (clock_set)
-                clock_was_set();
+                /* Have to call _delayed version, since in irq context*/
+                clock_was_set_delayed();
 }
 
 /**
diff --git a/kernel/time/timekeeping_debug.c b/kernel/time/timekeeping_debug.c
index 802433a4f5eb..4d54f97558df 100644
--- a/kernel/time/timekeeping_debug.c
+++ b/kernel/time/timekeeping_debug.c
@@ -21,6 +21,8 @@
 #include <linux/seq_file.h>
 #include <linux/time.h>
 
+#include "timekeeping_internal.h"
+
 static unsigned int sleep_time_bin[32] = {0};
 
 static int tk_debug_show_sleep_time(struct seq_file *s, void *data)
diff --git a/kernel/timer.c b/kernel/timer.c
index accfd241b9e5..87bd529879c2 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -52,7 +52,7 @@
 #define CREATE_TRACE_POINTS
 #include <trace/events/timer.h>
 
-u64 jiffies_64 __cacheline_aligned_in_smp = INITIAL_JIFFIES;
+__visible u64 jiffies_64 __cacheline_aligned_in_smp = INITIAL_JIFFIES;
 
 EXPORT_SYMBOL(jiffies_64);
 
@@ -81,6 +81,7 @@ struct tvec_base {
         unsigned long timer_jiffies;
         unsigned long next_timer;
         unsigned long active_timers;
+        unsigned long all_timers;
         struct tvec_root tv1;
         struct tvec tv2;
         struct tvec tv3;
@@ -337,6 +338,20 @@ void set_timer_slack(struct timer_list *timer, int slack_hz)
 }
 EXPORT_SYMBOL_GPL(set_timer_slack);
 
+/*
+ * If the list is empty, catch up ->timer_jiffies to the current time.
+ * The caller must hold the tvec_base lock.  Returns true if the list
+ * was empty and therefore ->timer_jiffies was updated.
+ */
+static bool catchup_timer_jiffies(struct tvec_base *base)
+{
+        if (!base->all_timers) {
+                base->timer_jiffies = jiffies;
+                return true;
+        }
+        return false;
+}
+
 static void
 __internal_add_timer(struct tvec_base *base, struct timer_list *timer)
 {
@@ -383,15 +398,17 @@ __internal_add_timer(struct tvec_base *base, struct timer_list *timer)
 
 static void internal_add_timer(struct tvec_base *base, struct timer_list *timer)
 {
+        (void)catchup_timer_jiffies(base);
         __internal_add_timer(base, timer);
         /*
          * Update base->active_timers and base->next_timer
          */
         if (!tbase_get_deferrable(timer->base)) {
-                if (time_before(timer->expires, base->next_timer))
+                if (!base->active_timers++ ||
+                    time_before(timer->expires, base->next_timer))
                         base->next_timer = timer->expires;
-                base->active_timers++;
         }
+        base->all_timers++;
 }
 
 #ifdef CONFIG_TIMER_STATS
@@ -671,6 +688,8 @@ detach_expired_timer(struct timer_list *timer, struct tvec_base *base)
         detach_timer(timer, true);
         if (!tbase_get_deferrable(timer->base))
                 base->active_timers--;
+        base->all_timers--;
+        (void)catchup_timer_jiffies(base);
 }
 
 static int detach_if_pending(struct timer_list *timer, struct tvec_base *base,
@@ -685,6 +704,8 @@ static int detach_if_pending(struct timer_list *timer, struct tvec_base *base,
                 if (timer->expires == base->next_timer)
                         base->next_timer = base->timer_jiffies;
         }
+        base->all_timers--;
+        (void)catchup_timer_jiffies(base);
         return 1;
 }
 
@@ -739,12 +760,7 @@ __mod_timer(struct timer_list *timer, unsigned long expires,
 
         debug_activate(timer, expires);
 
-        cpu = smp_processor_id();
-
-#if defined(CONFIG_NO_HZ_COMMON) && defined(CONFIG_SMP)
-        if (!pinned && get_sysctl_timer_migration() && idle_cpu(cpu))
-                cpu = get_nohz_timer_target();
-#endif
+        cpu = get_nohz_timer_target(pinned);
         new_base = per_cpu(tvec_bases, cpu);
 
         if (base != new_base) {
@@ -939,8 +955,15 @@ void add_timer_on(struct timer_list *timer, int cpu)
          * with the timer by holding the timer base lock. This also
          * makes sure that a CPU on the way to stop its tick can not
          * evaluate the timer wheel.
+         *
+         * Spare the IPI for deferrable timers on idle targets though.
+         * The next busy ticks will take care of it. Except full dynticks
+         * require special care against races with idle_cpu(), lets deal
+         * with that later.
          */
-        wake_up_nohz_cpu(cpu);
+        if (!tbase_get_deferrable(timer->base) || tick_nohz_full_cpu(cpu))
+                wake_up_nohz_cpu(cpu);
+
         spin_unlock_irqrestore(&base->lock, flags);
 }
 EXPORT_SYMBOL_GPL(add_timer_on);
@@ -1146,6 +1169,10 @@ static inline void __run_timers(struct tvec_base *base)
         struct timer_list *timer;
 
         spin_lock_irq(&base->lock);
+        if (catchup_timer_jiffies(base)) {
+                spin_unlock_irq(&base->lock);
+                return;
+        }
         while (time_after_eq(jiffies, base->timer_jiffies)) {
                 struct list_head work_list;
                 struct list_head *head = &work_list;
@@ -1160,7 +1187,7 @@ static inline void __run_timers(struct tvec_base *base)
                                         !cascade(base, &base->tv4, INDEX(2)))
                         cascade(base, &base->tv5, INDEX(3));
                 ++base->timer_jiffies;
-                list_replace_init(base->tv1.vec + index, &work_list);
+                list_replace_init(base->tv1.vec + index, head);
                 while (!list_empty(head)) {
                         void (*fn)(unsigned long);
                         unsigned long data;
@@ -1523,9 +1550,8 @@ static int init_timers_cpu(int cpu)
                         if (!base)
                                 return -ENOMEM;
 
-                        /* Make sure that tvec_base is 2 byte aligned */
-                        if (tbase_get_deferrable(base)) {
-                                WARN_ON(1);
+                        /* Make sure tvec_base has TIMER_FLAG_MASK bits free */
+                        if (WARN_ON(base != tbase_get_base(base))) {
                                 kfree(base);
                                 return -ENOMEM;
                         }
@@ -1559,6 +1585,7 @@ static int init_timers_cpu(int cpu)
         base->timer_jiffies = jiffies;
         base->next_timer = base->timer_jiffies;
         base->active_timers = 0;
+        base->all_timers = 0;
         return 0;
 }
 
@@ -1648,9 +1675,9 @@ void __init init_timers(void)
 
         err = timer_cpu_notify(&timers_nb, (unsigned long)CPU_UP_PREPARE,
                                (void *)(long)smp_processor_id());
-        init_timer_stats();
-
         BUG_ON(err != NOTIFY_OK);
+
+        init_timer_stats();
         register_cpu_notifier(&timers_nb);
         open_softirq(TIMER_SOFTIRQ, run_timer_softirq);
 }
diff --git a/kernel/torture.c b/kernel/torture.c
new file mode 100644
index 000000000000..acc9afc2f26e
--- /dev/null
+++ b/kernel/torture.c
@@ -0,0 +1,719 @@
+/*
+ * Common functions for in-kernel torture tests.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program 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 General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, you can access it online at
+ * http://www.gnu.org/licenses/gpl-2.0.html.
+ *
+ * Copyright (C) IBM Corporation, 2014
+ *
+ * Author: Paul E. McKenney <paulmck@us.ibm.com>
+ *      Based on kernel/rcu/torture.c.
+ */
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/kthread.h>
+#include <linux/err.h>
+#include <linux/spinlock.h>
+#include <linux/smp.h>
+#include <linux/interrupt.h>
+#include <linux/sched.h>
+#include <linux/atomic.h>
+#include <linux/bitops.h>
+#include <linux/completion.h>
+#include <linux/moduleparam.h>
+#include <linux/percpu.h>
+#include <linux/notifier.h>
+#include <linux/reboot.h>
+#include <linux/freezer.h>
+#include <linux/cpu.h>
+#include <linux/delay.h>
+#include <linux/stat.h>
+#include <linux/slab.h>
+#include <linux/trace_clock.h>
+#include <asm/byteorder.h>
+#include <linux/torture.h>
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Paul E. McKenney <paulmck@us.ibm.com>");
+
+static char *torture_type;
+static bool verbose;
+
+/* Mediate rmmod and system shutdown.  Concurrent rmmod & shutdown illegal! */
+#define FULLSTOP_DONTSTOP 0     /* Normal operation. */
+#define FULLSTOP_SHUTDOWN 1     /* System shutdown with torture running. */
+#define FULLSTOP_RMMOD    2     /* Normal rmmod of torture. */
+static int fullstop = FULLSTOP_RMMOD;
+static DEFINE_MUTEX(fullstop_mutex);
+static int *torture_runnable;
+
+#ifdef CONFIG_HOTPLUG_CPU
+
+/*
+ * Variables for online-offline handling.  Only present if CPU hotplug
+ * is enabled, otherwise does nothing.
+ */
+
+static struct task_struct *onoff_task;
+static long onoff_holdoff;
+static long onoff_interval;
+static long n_offline_attempts;
+static long n_offline_successes;
+static unsigned long sum_offline;
+static int min_offline = -1;
+static int max_offline;
+static long n_online_attempts;
+static long n_online_successes;
+static unsigned long sum_online;
+static int min_online = -1;
+static int max_online;
+
+/*
+ * Execute random CPU-hotplug operations at the interval specified
+ * by the onoff_interval.
+ */
+static int
+torture_onoff(void *arg)
+{
+        int cpu;
+        unsigned long delta;
+        int maxcpu = -1;
+        DEFINE_TORTURE_RANDOM(rand);
+        int ret;
+        unsigned long starttime;
+
+        VERBOSE_TOROUT_STRING("torture_onoff task started");
+        for_each_online_cpu(cpu)
+                maxcpu = cpu;
+        WARN_ON(maxcpu < 0);
+        if (onoff_holdoff > 0) {
+                VERBOSE_TOROUT_STRING("torture_onoff begin holdoff");
+                schedule_timeout_interruptible(onoff_holdoff);
+                VERBOSE_TOROUT_STRING("torture_onoff end holdoff");
+        }
+        while (!torture_must_stop()) {
+                cpu = (torture_random(&rand) >> 4) % (maxcpu + 1);
+                if (cpu_online(cpu) && cpu_is_hotpluggable(cpu)) {
+                        if (verbose)
+                                pr_alert("%s" TORTURE_FLAG
+                                         "torture_onoff task: offlining %d\n",
+                                         torture_type, cpu);
+                        starttime = jiffies;
+                        n_offline_attempts++;
+                        ret = cpu_down(cpu);
+                        if (ret) {
+                                if (verbose)
+                                        pr_alert("%s" TORTURE_FLAG
+                                                 "torture_onoff task: offline %d failed: errno %d\n",
+                                                 torture_type, cpu, ret);
+                        } else {
+                                if (verbose)
+                                        pr_alert("%s" TORTURE_FLAG
+                                                 "torture_onoff task: offlined %d\n",
+                                                 torture_type, cpu);
+                                n_offline_successes++;
+                                delta = jiffies - starttime;
+                                sum_offline += delta;
+                                if (min_offline < 0) {
+                                        min_offline = delta;
+                                        max_offline = delta;
+                                }
+                                if (min_offline > delta)
+                                        min_offline = delta;
+                                if (max_offline < delta)
+                                        max_offline = delta;
+                        }
+                } else if (cpu_is_hotpluggable(cpu)) {
+                        if (verbose)
+                                pr_alert("%s" TORTURE_FLAG
+                                         "torture_onoff task: onlining %d\n",
+                                         torture_type, cpu);
+                        starttime = jiffies;
+                        n_online_attempts++;
+                        ret = cpu_up(cpu);
+                        if (ret) {
+                                if (verbose)
+                                        pr_alert("%s" TORTURE_FLAG
+                                                 "torture_onoff task: online %d failed: errno %d\n",
+                                                 torture_type, cpu, ret);
+                        } else {
+                                if (verbose)
+                                        pr_alert("%s" TORTURE_FLAG
+                                                 "torture_onoff task: onlined %d\n",
+                                                 torture_type, cpu);
+                                n_online_successes++;
+                                delta = jiffies - starttime;
+                                sum_online += delta;
+                                if (min_online < 0) {
+                                        min_online = delta;
+                                        max_online = delta;
+                                }
+                                if (min_online > delta)
+                                        min_online = delta;
+                                if (max_online < delta)
+                                        max_online = delta;
+                        }
+                }
+                schedule_timeout_interruptible(onoff_interval);
+        }
+        torture_kthread_stopping("torture_onoff");
+        return 0;
+}
+
+#endif /* #ifdef CONFIG_HOTPLUG_CPU */
+
+/*
+ * Initiate online-offline handling.
+ */
+int torture_onoff_init(long ooholdoff, long oointerval)
+{
+        int ret = 0;
+
+#ifdef CONFIG_HOTPLUG_CPU
+        onoff_holdoff = ooholdoff;
+        onoff_interval = oointerval;
+        if (onoff_interval <= 0)
+                return 0;
+        ret = torture_create_kthread(torture_onoff, NULL, onoff_task);
+#endif /* #ifdef CONFIG_HOTPLUG_CPU */
+        return ret;
+}
+EXPORT_SYMBOL_GPL(torture_onoff_init);
+
+/*
+ * Clean up after online/offline testing.
+ */
+static void torture_onoff_cleanup(void)
+{
+#ifdef CONFIG_HOTPLUG_CPU
+        if (onoff_task == NULL)
+                return;
+        VERBOSE_TOROUT_STRING("Stopping torture_onoff task");
+        kthread_stop(onoff_task);
+        onoff_task = NULL;
+#endif /* #ifdef CONFIG_HOTPLUG_CPU */
+}
+EXPORT_SYMBOL_GPL(torture_onoff_cleanup);
+
+/*
+ * Print online/offline testing statistics.
+ */
+char *torture_onoff_stats(char *page)
+{
+#ifdef CONFIG_HOTPLUG_CPU
+        page += sprintf(page,
+                       "onoff: %ld/%ld:%ld/%ld %d,%d:%d,%d %lu:%lu (HZ=%d) ",
+                       n_online_successes, n_online_attempts,
+                       n_offline_successes, n_offline_attempts,
+                       min_online, max_online,
+                       min_offline, max_offline,
+                       sum_online, sum_offline, HZ);
+#endif /* #ifdef CONFIG_HOTPLUG_CPU */
+        return page;
+}
+EXPORT_SYMBOL_GPL(torture_onoff_stats);
+
+/*
+ * Were all the online/offline operations successful?
+ */
+bool torture_onoff_failures(void)
+{
+#ifdef CONFIG_HOTPLUG_CPU
+        return n_online_successes != n_online_attempts ||
+               n_offline_successes != n_offline_attempts;
+#else /* #ifdef CONFIG_HOTPLUG_CPU */
+        return false;
+#endif /* #else #ifdef CONFIG_HOTPLUG_CPU */
+}
+EXPORT_SYMBOL_GPL(torture_onoff_failures);
+
+#define TORTURE_RANDOM_MULT     39916801  /* prime */
+#define TORTURE_RANDOM_ADD      479001701 /* prime */
+#define TORTURE_RANDOM_REFRESH  10000
+
+/*
+ * Crude but fast random-number generator.  Uses a linear congruential
+ * generator, with occasional help from cpu_clock().
+ */
+unsigned long
+torture_random(struct torture_random_state *trsp)
+{
+        if (--trsp->trs_count < 0) {
+                trsp->trs_state += (unsigned long)local_clock();
+                trsp->trs_count = TORTURE_RANDOM_REFRESH;
+        }
+        trsp->trs_state = trsp->trs_state * TORTURE_RANDOM_MULT +
+                TORTURE_RANDOM_ADD;
+        return swahw32(trsp->trs_state);
+}
+EXPORT_SYMBOL_GPL(torture_random);
+
+/*
+ * Variables for shuffling.  The idea is to ensure that each CPU stays
+ * idle for an extended period to test interactions with dyntick idle,
+ * as well as interactions with any per-CPU varibles.
+ */
+struct shuffle_task {
+        struct list_head st_l;
+        struct task_struct *st_t;
+};
+
+static long shuffle_interval;   /* In jiffies. */
+static struct task_struct *shuffler_task;
+static cpumask_var_t shuffle_tmp_mask;
+static int shuffle_idle_cpu;    /* Force all torture tasks off this CPU */
+static struct list_head shuffle_task_list = LIST_HEAD_INIT(shuffle_task_list);
+static DEFINE_MUTEX(shuffle_task_mutex);
+
+/*
+ * Register a task to be shuffled.  If there is no memory, just splat
+ * and don't bother registering.
+ */
+void torture_shuffle_task_register(struct task_struct *tp)
+{
+        struct shuffle_task *stp;
+
+        if (WARN_ON_ONCE(tp == NULL))
+                return;
+        stp = kmalloc(sizeof(*stp), GFP_KERNEL);
+        if (WARN_ON_ONCE(stp == NULL))
+                return;
+        stp->st_t = tp;
+        mutex_lock(&shuffle_task_mutex);
+        list_add(&stp->st_l, &shuffle_task_list);
+        mutex_unlock(&shuffle_task_mutex);
+}
+EXPORT_SYMBOL_GPL(torture_shuffle_task_register);
+
+/*
+ * Unregister all tasks, for example, at the end of the torture run.
+ */
+static void torture_shuffle_task_unregister_all(void)
+{
+        struct shuffle_task *stp;
+        struct shuffle_task *p;
+
+        mutex_lock(&shuffle_task_mutex);
+        list_for_each_entry_safe(stp, p, &shuffle_task_list, st_l) {
+                list_del(&stp->st_l);
+                kfree(stp);
+        }
+        mutex_unlock(&shuffle_task_mutex);
+}
+
+/* Shuffle tasks such that we allow shuffle_idle_cpu to become idle.
+ * A special case is when shuffle_idle_cpu = -1, in which case we allow
+ * the tasks to run on all CPUs.
+ */
+static void torture_shuffle_tasks(void)
+{
+        struct shuffle_task *stp;
+
+        cpumask_setall(shuffle_tmp_mask);
+        get_online_cpus();
+
+        /* No point in shuffling if there is only one online CPU (ex: UP) */
+        if (num_online_cpus() == 1) {
+                put_online_cpus();
+                return;
+        }
+
+        /* Advance to the next CPU.  Upon overflow, don't idle any CPUs. */
+        shuffle_idle_cpu = cpumask_next(shuffle_idle_cpu, shuffle_tmp_mask);
+        if (shuffle_idle_cpu >= nr_cpu_ids)
+                shuffle_idle_cpu = -1;
+        if (shuffle_idle_cpu != -1) {
+                cpumask_clear_cpu(shuffle_idle_cpu, shuffle_tmp_mask);
+                if (cpumask_empty(shuffle_tmp_mask)) {
+                        put_online_cpus();
+                        return;
+                }
+        }
+
+        mutex_lock(&shuffle_task_mutex);
+        list_for_each_entry(stp, &shuffle_task_list, st_l)
+                set_cpus_allowed_ptr(stp->st_t, shuffle_tmp_mask);
+        mutex_unlock(&shuffle_task_mutex);
+
+        put_online_cpus();
+}
+
+/* Shuffle tasks across CPUs, with the intent of allowing each CPU in the
+ * system to become idle at a time and cut off its timer ticks. This is meant
+ * to test the support for such tickless idle CPU in RCU.
+ */
+static int torture_shuffle(void *arg)
+{
+        VERBOSE_TOROUT_STRING("torture_shuffle task started");
+        do {
+                schedule_timeout_interruptible(shuffle_interval);
+                torture_shuffle_tasks();
+                torture_shutdown_absorb("torture_shuffle");
+        } while (!torture_must_stop());
+        torture_kthread_stopping("torture_shuffle");
+        return 0;
+}
+
+/*
+ * Start the shuffler, with shuffint in jiffies.
+ */
+int torture_shuffle_init(long shuffint)
+{
+        shuffle_interval = shuffint;
+
+        shuffle_idle_cpu = -1;
+
+        if (!alloc_cpumask_var(&shuffle_tmp_mask, GFP_KERNEL)) {
+                VERBOSE_TOROUT_ERRSTRING("Failed to alloc mask");
+                return -ENOMEM;
+        }
+
+        /* Create the shuffler thread */
+        return torture_create_kthread(torture_shuffle, NULL, shuffler_task);
+}
+EXPORT_SYMBOL_GPL(torture_shuffle_init);
+
+/*
+ * Stop the shuffling.
+ */
+static void torture_shuffle_cleanup(void)
+{
+        torture_shuffle_task_unregister_all();
+        if (shuffler_task) {
+                VERBOSE_TOROUT_STRING("Stopping torture_shuffle task");
+                kthread_stop(shuffler_task);
+                free_cpumask_var(shuffle_tmp_mask);
+        }
+        shuffler_task = NULL;
+}
+EXPORT_SYMBOL_GPL(torture_shuffle_cleanup);
+
+/*
+ * Variables for auto-shutdown.  This allows "lights out" torture runs
+ * to be fully scripted.
+ */
+static int shutdown_secs;               /* desired test duration in seconds. */
+static struct task_struct *shutdown_task;
+static unsigned long shutdown_time;     /* jiffies to system shutdown. */
+static void (*torture_shutdown_hook)(void);
+
+/*
+ * Absorb kthreads into a kernel function that won't return, so that
+ * they won't ever access module text or data again.
+ */
+void torture_shutdown_absorb(const char *title)
+{
+        while (ACCESS_ONCE(fullstop) == FULLSTOP_SHUTDOWN) {
+                pr_notice("torture thread %s parking due to system shutdown\n",
+                          title);
+                schedule_timeout_uninterruptible(MAX_SCHEDULE_TIMEOUT);
+        }
+}
+EXPORT_SYMBOL_GPL(torture_shutdown_absorb);
+
+/*
+ * Cause the torture test to shutdown the system after the test has
+ * run for the time specified by the shutdown_secs parameter.
+ */
+static int torture_shutdown(void *arg)
+{
+        long delta;
+        unsigned long jiffies_snap;
+
+        VERBOSE_TOROUT_STRING("torture_shutdown task started");
+        jiffies_snap = jiffies;
+        while (ULONG_CMP_LT(jiffies_snap, shutdown_time) &&
+               !torture_must_stop()) {
+                delta = shutdown_time - jiffies_snap;
+                if (verbose)
+                        pr_alert("%s" TORTURE_FLAG
+                                 "torture_shutdown task: %lu jiffies remaining\n",
+                                 torture_type, delta);
+                schedule_timeout_interruptible(delta);
+                jiffies_snap = jiffies;
+        }
+        if (torture_must_stop()) {
+                torture_kthread_stopping("torture_shutdown");
+                return 0;
+        }
+
+        /* OK, shut down the system. */
+
+        VERBOSE_TOROUT_STRING("torture_shutdown task shutting down system");
+        shutdown_task = NULL;   /* Avoid self-kill deadlock. */
+        if (torture_shutdown_hook)
+                torture_shutdown_hook();
+        else
+                VERBOSE_TOROUT_STRING("No torture_shutdown_hook(), skipping.");
+        kernel_power_off();     /* Shut down the system. */
+        return 0;
+}
+
+/*
+ * Start up the shutdown task.
+ */
+int torture_shutdown_init(int ssecs, void (*cleanup)(void))
+{
+        int ret = 0;
+
+        shutdown_secs = ssecs;
+        torture_shutdown_hook = cleanup;
+        if (shutdown_secs > 0) {
+                shutdown_time = jiffies + shutdown_secs * HZ;
+                ret = torture_create_kthread(torture_shutdown, NULL,
+                                             shutdown_task);
+        }
+        return ret;
+}
+EXPORT_SYMBOL_GPL(torture_shutdown_init);
+
+/*
+ * Detect and respond to a system shutdown.
+ */
+static int torture_shutdown_notify(struct notifier_block *unused1,
+                                   unsigned long unused2, void *unused3)
+{
+        mutex_lock(&fullstop_mutex);
+        if (ACCESS_ONCE(fullstop) == FULLSTOP_DONTSTOP) {
+                VERBOSE_TOROUT_STRING("Unscheduled system shutdown detected");
+                ACCESS_ONCE(fullstop) = FULLSTOP_SHUTDOWN;
+        } else {
+                pr_warn("Concurrent rmmod and shutdown illegal!\n");
+        }
+        mutex_unlock(&fullstop_mutex);
+        return NOTIFY_DONE;
+}
+
+static struct notifier_block torture_shutdown_nb = {
+        .notifier_call = torture_shutdown_notify,
+};
+
+/*
+ * Shut down the shutdown task.  Say what???  Heh!  This can happen if
+ * the torture module gets an rmmod before the shutdown time arrives.  ;-)
+ */
+static void torture_shutdown_cleanup(void)
+{
+        unregister_reboot_notifier(&torture_shutdown_nb);
+        if (shutdown_task != NULL) {
+                VERBOSE_TOROUT_STRING("Stopping torture_shutdown task");
+                kthread_stop(shutdown_task);
+        }
+        shutdown_task = NULL;
+}
+
+/*
+ * Variables for stuttering, which means to periodically pause and
+ * restart testing in order to catch bugs that appear when load is
+ * suddenly applied to or removed from the system.
+ */
+static struct task_struct *stutter_task;
+static int stutter_pause_test;
+static int stutter;
+
+/*
+ * Block until the stutter interval ends.  This must be called periodically
+ * by all running kthreads that need to be subject to stuttering.
+ */
+void stutter_wait(const char *title)
+{
+        while (ACCESS_ONCE(stutter_pause_test) ||
+               (torture_runnable && !ACCESS_ONCE(*torture_runnable))) {
+                if (stutter_pause_test)
+                        schedule_timeout_interruptible(1);
+                else
+                        schedule_timeout_interruptible(round_jiffies_relative(HZ));
+                torture_shutdown_absorb(title);
+        }
+}
+EXPORT_SYMBOL_GPL(stutter_wait);
+
+/*
+ * Cause the torture test to "stutter", starting and stopping all
+ * threads periodically.
+ */
+static int torture_stutter(void *arg)
+{
+        VERBOSE_TOROUT_STRING("torture_stutter task started");
+        do {
+                if (!torture_must_stop()) {
+                        schedule_timeout_interruptible(stutter);
+                        ACCESS_ONCE(stutter_pause_test) = 1;
+                }
+                if (!torture_must_stop())
+                        schedule_timeout_interruptible(stutter);
+                ACCESS_ONCE(stutter_pause_test) = 0;
+                torture_shutdown_absorb("torture_stutter");
+        } while (!torture_must_stop());
+        torture_kthread_stopping("torture_stutter");
+        return 0;
+}
+
+/*
+ * Initialize and kick off the torture_stutter kthread.
+ */
+int torture_stutter_init(int s)
+{
+        int ret;
+
+        stutter = s;
+        ret = torture_create_kthread(torture_stutter, NULL, stutter_task);
+        return ret;
+}
+EXPORT_SYMBOL_GPL(torture_stutter_init);
+
+/*
+ * Cleanup after the torture_stutter kthread.
+ */
+static void torture_stutter_cleanup(void)
+{
+        if (!stutter_task)
+                return;
+        VERBOSE_TOROUT_STRING("Stopping torture_stutter task");
+        kthread_stop(stutter_task);
+        stutter_task = NULL;
+}
+
+/*
+ * Initialize torture module.  Please note that this is -not- invoked via
+ * the usual module_init() mechanism, but rather by an explicit call from
+ * the client torture module.  This call must be paired with a later
+ * torture_init_end().
+ *
+ * The runnable parameter points to a flag that controls whether or not
+ * the test is currently runnable.  If there is no such flag, pass in NULL.
+ */
+void __init torture_init_begin(char *ttype, bool v, int *runnable)
+{
+        mutex_lock(&fullstop_mutex);
+        torture_type = ttype;
+        verbose = v;
+        torture_runnable = runnable;
+        fullstop = FULLSTOP_DONTSTOP;
+
+}
+EXPORT_SYMBOL_GPL(torture_init_begin);
+
+/*
+ * Tell the torture module that initialization is complete.
+ */
+void __init torture_init_end(void)
+{
+        mutex_unlock(&fullstop_mutex);
+        register_reboot_notifier(&torture_shutdown_nb);
+}
+EXPORT_SYMBOL_GPL(torture_init_end);
+
+/*
+ * Clean up torture module.  Please note that this is -not- invoked via
+ * the usual module_exit() mechanism, but rather by an explicit call from
+ * the client torture module.  Returns true if a race with system shutdown
+ * is detected, otherwise, all kthreads started by functions in this file
+ * will be shut down.
+ *
+ * This must be called before the caller starts shutting down its own
+ * kthreads.
+ */
+bool torture_cleanup(void)
+{
+        mutex_lock(&fullstop_mutex);
+        if (ACCESS_ONCE(fullstop) == FULLSTOP_SHUTDOWN) {
+                pr_warn("Concurrent rmmod and shutdown illegal!\n");
+                mutex_unlock(&fullstop_mutex);
+                schedule_timeout_uninterruptible(10);
+                return true;
+        }
+        ACCESS_ONCE(fullstop) = FULLSTOP_RMMOD;
+        mutex_unlock(&fullstop_mutex);
+        torture_shutdown_cleanup();
+        torture_shuffle_cleanup();
+        torture_stutter_cleanup();
+        torture_onoff_cleanup();
+        return false;
+}
+EXPORT_SYMBOL_GPL(torture_cleanup);
+
+/*
+ * Is it time for the current torture test to stop?
+ */
+bool torture_must_stop(void)
+{
+        return torture_must_stop_irq() || kthread_should_stop();
+}
+EXPORT_SYMBOL_GPL(torture_must_stop);
+
+/*
+ * Is it time for the current torture test to stop?  This is the irq-safe
+ * version, hence no check for kthread_should_stop().
+ */
+bool torture_must_stop_irq(void)
+{
+        return ACCESS_ONCE(fullstop) != FULLSTOP_DONTSTOP;
+}
+EXPORT_SYMBOL_GPL(torture_must_stop_irq);
+
+/*
+ * Each kthread must wait for kthread_should_stop() before returning from
+ * its top-level function, otherwise segfaults ensue.  This function
+ * prints a "stopping" message and waits for kthread_should_stop(), and
+ * should be called from all torture kthreads immediately prior to
+ * returning.
+ */
+void torture_kthread_stopping(char *title)
+{
+        if (verbose)
+                VERBOSE_TOROUT_STRING(title);
+        while (!kthread_should_stop()) {
+                torture_shutdown_absorb(title);
+                schedule_timeout_uninterruptible(1);
+        }
+}
+EXPORT_SYMBOL_GPL(torture_kthread_stopping);
+
+/*
+ * Create a generic torture kthread that is immediately runnable.  If you
+ * need the kthread to be stopped so that you can do something to it before
+ * it starts, you will need to open-code your own.
+ */
+int _torture_create_kthread(int (*fn)(void *arg), void *arg, char *s, char *m,
+                            char *f, struct task_struct **tp)
+{
+        int ret = 0;
+
+        VERBOSE_TOROUT_STRING(m);
+        *tp = kthread_run(fn, arg, s);
+        if (IS_ERR(*tp)) {
+                ret = PTR_ERR(*tp);
+                VERBOSE_TOROUT_ERRSTRING(f);
+                *tp = NULL;
+        }
+        torture_shuffle_task_register(*tp);
+        return ret;
+}
+EXPORT_SYMBOL_GPL(_torture_create_kthread);
+
+/*
+ * Stop a generic kthread, emitting a message.
+ */
+void _torture_stop_kthread(char *m, struct task_struct **tp)
+{
+        if (*tp == NULL)
+                return;
+        VERBOSE_TOROUT_STRING(m);
+        kthread_stop(*tp);
+        *tp = NULL;
+}
+EXPORT_SYMBOL_GPL(_torture_stop_kthread);
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 015f85aaca08..8639819f6cef 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -424,6 +424,7 @@ config UPROBE_EVENT
         bool "Enable uprobes-based dynamic events"
         depends on ARCH_SUPPORTS_UPROBES
         depends on MMU
+        depends on PERF_EVENTS
         select UPROBES
         select PROBE_EVENTS
         select TRACING
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index b418cb0d7242..c1bd4ada2a04 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -702,6 +702,7 @@ void blk_trace_shutdown(struct request_queue *q)
  * blk_add_trace_rq - Add a trace for a request oriented action
  * @q:          queue the io is for
  * @rq:         the source request
+ * @nr_bytes:   number of completed bytes
  * @what:       the action
  *
  * Description:
@@ -709,7 +710,7 @@ void blk_trace_shutdown(struct request_queue *q)
  *
  **/
 static void blk_add_trace_rq(struct request_queue *q, struct request *rq,
-                             u32 what)
+                             unsigned int nr_bytes, u32 what)
 {
         struct blk_trace *bt = q->blk_trace;
 
@@ -718,11 +719,11 @@ static void blk_add_trace_rq(struct request_queue *q, struct request *rq,
 
         if (rq->cmd_type == REQ_TYPE_BLOCK_PC) {
                 what |= BLK_TC_ACT(BLK_TC_PC);
-                __blk_add_trace(bt, 0, blk_rq_bytes(rq), rq->cmd_flags,
+                __blk_add_trace(bt, 0, nr_bytes, rq->cmd_flags,
                                 what, rq->errors, rq->cmd_len, rq->cmd);
         } else  {
                 what |= BLK_TC_ACT(BLK_TC_FS);
-                __blk_add_trace(bt, blk_rq_pos(rq), blk_rq_bytes(rq),
+                __blk_add_trace(bt, blk_rq_pos(rq), nr_bytes,
                                 rq->cmd_flags, what, rq->errors, 0, NULL);
         }
 }
@@ -730,33 +731,34 @@ static void blk_add_trace_rq(struct request_queue *q, struct request *rq,
 static void blk_add_trace_rq_abort(void *ignore,
                                    struct request_queue *q, struct request *rq)
 {
-        blk_add_trace_rq(q, rq, BLK_TA_ABORT);
+        blk_add_trace_rq(q, rq, blk_rq_bytes(rq), BLK_TA_ABORT);
 }
 
 static void blk_add_trace_rq_insert(void *ignore,
                                     struct request_queue *q, struct request *rq)
 {
-        blk_add_trace_rq(q, rq, BLK_TA_INSERT);
+        blk_add_trace_rq(q, rq, blk_rq_bytes(rq), BLK_TA_INSERT);
 }
 
 static void blk_add_trace_rq_issue(void *ignore,
                                    struct request_queue *q, struct request *rq)
 {
-        blk_add_trace_rq(q, rq, BLK_TA_ISSUE);
+        blk_add_trace_rq(q, rq, blk_rq_bytes(rq), BLK_TA_ISSUE);
 }
 
 static void blk_add_trace_rq_requeue(void *ignore,
                                      struct request_queue *q,
                                      struct request *rq)
 {
-        blk_add_trace_rq(q, rq, BLK_TA_REQUEUE);
+        blk_add_trace_rq(q, rq, blk_rq_bytes(rq), BLK_TA_REQUEUE);
 }
 
 static void blk_add_trace_rq_complete(void *ignore,
                                       struct request_queue *q,
-                                      struct request *rq)
+                                      struct request *rq,
+                                      unsigned int nr_bytes)
 {
-        blk_add_trace_rq(q, rq, BLK_TA_COMPLETE);
+        blk_add_trace_rq(q, rq, nr_bytes, BLK_TA_COMPLETE);
 }
 
 /**
@@ -1427,7 +1429,8 @@ static enum print_line_t blk_tracer_print_line(struct trace_iterator *iter)
         return print_one_line(iter, true);
 }
 
-static int blk_tracer_set_flag(u32 old_flags, u32 bit, int set)
+static int
+blk_tracer_set_flag(struct trace_array *tr, u32 old_flags, u32 bit, int set)
 {
         /* don't output context-info for blk_classic output */
         if (bit == TRACE_BLK_OPT_CLASSIC) {
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index cd7f76d1eb86..1fd4b9479210 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -237,14 +237,13 @@ static int control_ops_alloc(struct ftrace_ops *ops)
         return 0;
 }
 
-static void control_ops_free(struct ftrace_ops *ops)
-{
-        free_percpu(ops->disabled);
-}
-
 static void update_global_ops(void)
 {
-        ftrace_func_t func;
+        ftrace_func_t func = ftrace_global_list_func;
+        void *private = NULL;
+
+        /* The list has its own recursion protection. */
+        global_ops.flags |= FTRACE_OPS_FL_RECURSION_SAFE;
 
         /*
          * If there's only one function registered, then call that
@@ -254,23 +253,17 @@ static void update_global_ops(void)
         if (ftrace_global_list == &ftrace_list_end ||
             ftrace_global_list->next == &ftrace_list_end) {
                 func = ftrace_global_list->func;
+                private = ftrace_global_list->private;
                 /*
                  * As we are calling the function directly.
                  * If it does not have recursion protection,
                  * the function_trace_op needs to be updated
                  * accordingly.
                  */
-                if (ftrace_global_list->flags & FTRACE_OPS_FL_RECURSION_SAFE)
-                        global_ops.flags |= FTRACE_OPS_FL_RECURSION_SAFE;
-                else
+                if (!(ftrace_global_list->flags & FTRACE_OPS_FL_RECURSION_SAFE))
                         global_ops.flags &= ~FTRACE_OPS_FL_RECURSION_SAFE;
-        } else {
-                func = ftrace_global_list_func;
-                /* The list has its own recursion protection. */
-                global_ops.flags |= FTRACE_OPS_FL_RECURSION_SAFE;
         }
 
-
         /* If we filter on pids, update to use the pid function */
         if (!list_empty(&ftrace_pids)) {
                 set_ftrace_pid_function(func);
@@ -278,6 +271,7 @@ static void update_global_ops(void)
         }
 
         global_ops.func = func;
+        global_ops.private = private;
 }
 
 static void ftrace_sync(struct work_struct *work)
@@ -437,6 +431,9 @@ static int remove_ftrace_list_ops(struct ftrace_ops **list,
 
 static int __register_ftrace_function(struct ftrace_ops *ops)
 {
+        if (ops->flags & FTRACE_OPS_FL_DELETED)
+                return -EINVAL;
+
         if (FTRACE_WARN_ON(ops == &global_ops))
                 return -EINVAL;
 
@@ -1172,8 +1169,6 @@ struct ftrace_page {
         int                     size;
 };
 
-static struct ftrace_page *ftrace_new_pgs;
-
 #define ENTRY_SIZE sizeof(struct dyn_ftrace)
 #define ENTRIES_PER_PAGE (PAGE_SIZE / ENTRY_SIZE)
 
@@ -1560,7 +1555,7 @@ unsigned long ftrace_location(unsigned long ip)
  * the function tracer. It checks the ftrace internal tables to
  * determine if the address belongs or not.
  */
-int ftrace_text_reserved(void *start, void *end)
+int ftrace_text_reserved(const void *start, const void *end)
 {
         unsigned long ret;
 
@@ -1994,6 +1989,7 @@ int __weak ftrace_arch_code_modify_post_process(void)
 void ftrace_modify_all_code(int command)
 {
         int update = command & FTRACE_UPDATE_TRACE_FUNC;
+        int err = 0;
 
         /*
          * If the ftrace_caller calls a ftrace_ops func directly,
@@ -2005,8 +2001,11 @@ void ftrace_modify_all_code(int command)
          * to make sure the ops are having the right functions
          * traced.
          */
-        if (update)
-                ftrace_update_ftrace_func(ftrace_ops_list_func);
+        if (update) {
+                err = ftrace_update_ftrace_func(ftrace_ops_list_func);
+                if (FTRACE_WARN_ON(err))
+                        return;
+        }
 
         if (command & FTRACE_UPDATE_CALLS)
                 ftrace_replace_code(1);
@@ -2019,13 +2018,16 @@ void ftrace_modify_all_code(int command)
                 /* If irqs are disabled, we are in stop machine */
                 if (!irqs_disabled())
                         smp_call_function(ftrace_sync_ipi, NULL, 1);
-                ftrace_update_ftrace_func(ftrace_trace_function);
+                err = ftrace_update_ftrace_func(ftrace_trace_function);
+                if (FTRACE_WARN_ON(err))
+                        return;
         }
 
         if (command & FTRACE_START_FUNC_RET)
-                ftrace_enable_ftrace_graph_caller();
+                err = ftrace_enable_ftrace_graph_caller();
         else if (command & FTRACE_STOP_FUNC_RET)
-                ftrace_disable_ftrace_graph_caller();
+                err = ftrace_disable_ftrace_graph_caller();
+        FTRACE_WARN_ON(err);
 }
 
 static int __ftrace_modify_code(void *data)
@@ -2093,6 +2095,11 @@ static ftrace_func_t saved_ftrace_func;
 static int ftrace_start_up;
 static int global_start_up;
 
+static void control_ops_free(struct ftrace_ops *ops)
+{
+        free_percpu(ops->disabled);
+}
+
 static void ftrace_startup_enable(int command)
 {
         if (saved_ftrace_func != ftrace_trace_function) {
@@ -2244,7 +2251,6 @@ static void ftrace_shutdown_sysctl(void)
 }
 
 static cycle_t          ftrace_update_time;
-static unsigned long    ftrace_update_cnt;
 unsigned long           ftrace_update_tot_cnt;
 
 static inline int ops_traces_mod(struct ftrace_ops *ops)
@@ -2300,11 +2306,12 @@ static int referenced_filters(struct dyn_ftrace *rec)
         return cnt;
 }
 
-static int ftrace_update_code(struct module *mod)
+static int ftrace_update_code(struct module *mod, struct ftrace_page *new_pgs)
 {
         struct ftrace_page *pg;
         struct dyn_ftrace *p;
         cycle_t start, stop;
+        unsigned long update_cnt = 0;
         unsigned long ref = 0;
         bool test = false;
         int i;
@@ -2330,9 +2337,8 @@ static int ftrace_update_code(struct module *mod)
         }
 
         start = ftrace_now(raw_smp_processor_id());
-        ftrace_update_cnt = 0;
 
-        for (pg = ftrace_new_pgs; pg; pg = pg->next) {
+        for (pg = new_pgs; pg; pg = pg->next) {
 
                 for (i = 0; i < pg->index; i++) {
                         int cnt = ref;
@@ -2353,7 +2359,7 @@ static int ftrace_update_code(struct module *mod)
                         if (!ftrace_code_disable(mod, p))
                                 break;
 
-                        ftrace_update_cnt++;
+                        update_cnt++;
 
                         /*
                          * If the tracing is enabled, go ahead and enable the record.
@@ -2372,11 +2378,9 @@ static int ftrace_update_code(struct module *mod)
                 }
         }
 
-        ftrace_new_pgs = NULL;
-
         stop = ftrace_now(raw_smp_processor_id());
         ftrace_update_time = stop - start;
-        ftrace_update_tot_cnt += ftrace_update_cnt;
+        ftrace_update_tot_cnt += update_cnt;
 
         return 0;
 }
@@ -2468,22 +2472,6 @@ ftrace_allocate_pages(unsigned long num_to_init)
         return NULL;
 }
 
-static int __init ftrace_dyn_table_alloc(unsigned long num_to_init)
-{
-        int cnt;
-
-        if (!num_to_init) {
-                pr_info("ftrace: No functions to be traced?\n");
-                return -1;
-        }
-
-        cnt = num_to_init / ENTRIES_PER_PAGE;
-        pr_info("ftrace: allocating %ld entries in %d pages\n",
-                num_to_init, cnt + 1);
-
-        return 0;
-}
-
 #define FTRACE_BUFF_MAX (KSYM_SYMBOL_LEN+4) /* room for wildcards */
 
 struct ftrace_iterator {
@@ -2871,7 +2859,9 @@ ftrace_regex_open(struct ftrace_ops *ops, int flag,
 static int
 ftrace_filter_open(struct inode *inode, struct file *file)
 {
-        return ftrace_regex_open(&global_ops,
+        struct ftrace_ops *ops = inode->i_private;
+
+        return ftrace_regex_open(ops,
                         FTRACE_ITER_FILTER | FTRACE_ITER_DO_HASH,
                         inode, file);
 }
@@ -2879,7 +2869,9 @@ ftrace_filter_open(struct inode *inode, struct file *file)
 static int
 ftrace_notrace_open(struct inode *inode, struct file *file)
 {
-        return ftrace_regex_open(&global_ops, FTRACE_ITER_NOTRACE,
+        struct ftrace_ops *ops = inode->i_private;
+
+        return ftrace_regex_open(ops, FTRACE_ITER_NOTRACE,
                                  inode, file);
 }
 
@@ -4109,6 +4101,36 @@ static const struct file_operations ftrace_graph_notrace_fops = {
 };
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */
 
+void ftrace_create_filter_files(struct ftrace_ops *ops,
+                                struct dentry *parent)
+{
+
+        trace_create_file("set_ftrace_filter", 0644, parent,
+                          ops, &ftrace_filter_fops);
+
+        trace_create_file("set_ftrace_notrace", 0644, parent,
+                          ops, &ftrace_notrace_fops);
+}
+
+/*
+ * The name "destroy_filter_files" is really a misnomer. Although
+ * in the future, it may actualy delete the files, but this is
+ * really intended to make sure the ops passed in are disabled
+ * and that when this function returns, the caller is free to
+ * free the ops.
+ *
+ * The "destroy" name is only to match the "create" name that this
+ * should be paired with.
+ */
+void ftrace_destroy_filter_files(struct ftrace_ops *ops)
+{
+        mutex_lock(&ftrace_lock);
+        if (ops->flags & FTRACE_OPS_FL_ENABLED)
+                ftrace_shutdown(ops, 0);
+        ops->flags |= FTRACE_OPS_FL_DELETED;
+        mutex_unlock(&ftrace_lock);
+}
+
 static __init int ftrace_init_dyn_debugfs(struct dentry *d_tracer)
 {
 
@@ -4118,11 +4140,7 @@ static __init int ftrace_init_dyn_debugfs(struct dentry *d_tracer)
         trace_create_file("enabled_functions", 0444,
                         d_tracer, NULL, &ftrace_enabled_fops);
 
-        trace_create_file("set_ftrace_filter", 0644, d_tracer,
-                        NULL, &ftrace_filter_fops);
-
-        trace_create_file("set_ftrace_notrace", 0644, d_tracer,
-                                    NULL, &ftrace_notrace_fops);
+        ftrace_create_filter_files(&global_ops, d_tracer);
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
         trace_create_file("set_graph_function", 0444, d_tracer,
@@ -4238,9 +4256,6 @@ static int ftrace_process_locs(struct module *mod,
         /* Assign the last page to ftrace_pages */
         ftrace_pages = pg;
 
-        /* These new locations need to be initialized */
-        ftrace_new_pgs = start_pg;
-
         /*
          * We only need to disable interrupts on start up
          * because we are modifying code that an interrupt
@@ -4251,7 +4266,7 @@ static int ftrace_process_locs(struct module *mod,
          */
         if (!mod)
                 local_irq_save(flags);
-        ftrace_update_code(mod);
+        ftrace_update_code(mod, start_pg);
         if (!mod)
                 local_irq_restore(flags);
         ret = 0;
@@ -4360,30 +4375,27 @@ struct notifier_block ftrace_module_exit_nb = {
         .priority = INT_MIN,    /* Run after anything that can remove kprobes */
 };
 
-extern unsigned long __start_mcount_loc[];
-extern unsigned long __stop_mcount_loc[];
-
 void __init ftrace_init(void)
 {
-        unsigned long count, addr, flags;
+        extern unsigned long __start_mcount_loc[];
+        extern unsigned long __stop_mcount_loc[];
+        unsigned long count, flags;
         int ret;
 
-        /* Keep the ftrace pointer to the stub */
-        addr = (unsigned long)ftrace_stub;
-
         local_irq_save(flags);
-        ftrace_dyn_arch_init(&addr);
+        ret = ftrace_dyn_arch_init();
         local_irq_restore(flags);
-
-        /* ftrace_dyn_arch_init places the return code in addr */
-        if (addr)
+        if (ret)
                 goto failed;
 
         count = __stop_mcount_loc - __start_mcount_loc;
-
-        ret = ftrace_dyn_table_alloc(count);
-        if (ret)
+        if (!count) {
+                pr_info("ftrace: No functions to be traced?\n");
                 goto failed;
+        }
+
+        pr_info("ftrace: allocating %ld entries in %ld pages\n",
+                count, count / ENTRIES_PER_PAGE + 1);
 
         last_ftrace_enabled = ftrace_enabled = 1;
 
@@ -4431,7 +4443,13 @@ static inline void ftrace_startup_enable(int command) { }
                         (ops)->flags |= FTRACE_OPS_FL_ENABLED;          \
                 ___ret;                                                 \
         })
-# define ftrace_shutdown(ops, command) __unregister_ftrace_function(ops)
+# define ftrace_shutdown(ops, command)                                  \
+        ({                                                              \
+                int ___ret = __unregister_ftrace_function(ops);         \
+                if (!___ret)                                            \
+                        (ops)->flags &= ~FTRACE_OPS_FL_ENABLED;         \
+                ___ret;                                                 \
+        })
 
 # define ftrace_startup_sysctl()        do { } while (0)
 # define ftrace_shutdown_sysctl()       do { } while (0)
diff --git a/kernel/trace/ring_buffer_benchmark.c b/kernel/trace/ring_buffer_benchmark.c
index a5457d577b98..0434ff1b808e 100644
--- a/kernel/trace/ring_buffer_benchmark.c
+++ b/kernel/trace/ring_buffer_benchmark.c
@@ -40,8 +40,8 @@ static int write_iteration = 50;
 module_param(write_iteration, uint, 0644);
 MODULE_PARM_DESC(write_iteration, "# of writes between timestamp readings");
 
-static int producer_nice = 19;
-static int consumer_nice = 19;
+static int producer_nice = MAX_NICE;
+static int consumer_nice = MAX_NICE;
 
 static int producer_fifo = -1;
 static int consumer_fifo = -1;
@@ -308,7 +308,7 @@ static void ring_buffer_producer(void)
 
         /* Let the user know that the test is running at low priority */
         if (producer_fifo < 0 && consumer_fifo < 0 &&
-            producer_nice == 19 && consumer_nice == 19)
+            producer_nice == MAX_NICE && consumer_nice == MAX_NICE)
                 trace_printk("WARNING!!! This test is running at lowest priority.\n");
 
         trace_printk("Time:     %lld (usecs)\n", time);
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 815c878f409b..9be67c5e5b0f 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -73,7 +73,8 @@ static struct tracer_flags dummy_tracer_flags = {
         .opts = dummy_tracer_opt
 };
 
-static int dummy_set_flag(u32 old_flags, u32 bit, int set)
+static int
+dummy_set_flag(struct trace_array *tr, u32 old_flags, u32 bit, int set)
 {
         return 0;
 }
@@ -118,7 +119,7 @@ enum ftrace_dump_mode ftrace_dump_on_oops;
 /* When set, tracing will stop when a WARN*() is hit */
 int __disable_trace_on_warning;
 
-static int tracing_set_tracer(const char *buf);
+static int tracing_set_tracer(struct trace_array *tr, const char *buf);
 
 #define MAX_TRACER_SIZE         100
 static char bootup_tracer_buf[MAX_TRACER_SIZE] __initdata;
@@ -180,6 +181,17 @@ static int __init set_trace_boot_options(char *str)
 }
 __setup("trace_options=", set_trace_boot_options);
 
+static char trace_boot_clock_buf[MAX_TRACER_SIZE] __initdata;
+static char *trace_boot_clock __initdata;
+
+static int __init set_trace_boot_clock(char *str)
+{
+        strlcpy(trace_boot_clock_buf, str, MAX_TRACER_SIZE);
+        trace_boot_clock = trace_boot_clock_buf;
+        return 0;
+}
+__setup("trace_clock=", set_trace_boot_clock);
+
 
 unsigned long long ns2usecs(cycle_t nsec)
 {
@@ -1230,7 +1242,7 @@ int register_tracer(struct tracer *type)
 
         printk(KERN_INFO "Starting tracer '%s'\n", type->name);
         /* Do we want this tracer to start on bootup? */
-        tracing_set_tracer(type->name);
+        tracing_set_tracer(&global_trace, type->name);
         default_bootup_tracer = NULL;
         /* disable other selftests, since this will break it. */
         tracing_selftest_disabled = true;
@@ -1600,15 +1612,31 @@ void trace_buffer_unlock_commit(struct ring_buffer *buffer,
 }
 EXPORT_SYMBOL_GPL(trace_buffer_unlock_commit);
 
+static struct ring_buffer *temp_buffer;
+
 struct ring_buffer_event *
 trace_event_buffer_lock_reserve(struct ring_buffer **current_rb,
                           struct ftrace_event_file *ftrace_file,
                           int type, unsigned long len,
                           unsigned long flags, int pc)
 {
+        struct ring_buffer_event *entry;
+
         *current_rb = ftrace_file->tr->trace_buffer.buffer;
-        return trace_buffer_lock_reserve(*current_rb,
+        entry = trace_buffer_lock_reserve(*current_rb,
                                          type, len, flags, pc);
+        /*
+         * If tracing is off, but we have triggers enabled
+         * we still need to look at the event data. Use the temp_buffer
+         * to store the trace event for the tigger to use. It's recusive
+         * safe and will not be recorded anywhere.
+         */
+        if (!entry && ftrace_file->flags & FTRACE_EVENT_FL_TRIGGER_COND) {
+                *current_rb = temp_buffer;
+                entry = trace_buffer_lock_reserve(*current_rb,
+                                                  type, len, flags, pc);
+        }
+        return entry;
 }
 EXPORT_SYMBOL_GPL(trace_event_buffer_lock_reserve);
 
@@ -3121,27 +3149,52 @@ static int tracing_open(struct inode *inode, struct file *file)
         return ret;
 }
 
+/*
+ * Some tracers are not suitable for instance buffers.
+ * A tracer is always available for the global array (toplevel)
+ * or if it explicitly states that it is.
+ */
+static bool
+trace_ok_for_array(struct tracer *t, struct trace_array *tr)
+{
+        return (tr->flags & TRACE_ARRAY_FL_GLOBAL) || t->allow_instances;
+}
+
+/* Find the next tracer that this trace array may use */
+static struct tracer *
+get_tracer_for_array(struct trace_array *tr, struct tracer *t)
+{
+        while (t && !trace_ok_for_array(t, tr))
+                t = t->next;
+
+        return t;
+}
+
 static void *
 t_next(struct seq_file *m, void *v, loff_t *pos)
 {
+        struct trace_array *tr = m->private;
         struct tracer *t = v;
 
         (*pos)++;
 
         if (t)
-                t = t->next;
+                t = get_tracer_for_array(tr, t->next);
 
         return t;
 }
 
 static void *t_start(struct seq_file *m, loff_t *pos)
 {
+        struct trace_array *tr = m->private;
         struct tracer *t;
         loff_t l = 0;
 
         mutex_lock(&trace_types_lock);
-        for (t = trace_types; t && l < *pos; t = t_next(m, t, &l))
-                ;
+
+        t = get_tracer_for_array(tr, trace_types);
+        for (; t && l < *pos; t = t_next(m, t, &l))
+                        ;
 
         return t;
 }
@@ -3176,10 +3229,21 @@ static const struct seq_operations show_traces_seq_ops = {
 
 static int show_traces_open(struct inode *inode, struct file *file)
 {
+        struct trace_array *tr = inode->i_private;
+        struct seq_file *m;
+        int ret;
+
         if (tracing_disabled)
                 return -ENODEV;
 
-        return seq_open(file, &show_traces_seq_ops);
+        ret = seq_open(file, &show_traces_seq_ops);
+        if (ret)
+                return ret;
+
+        m = file->private_data;
+        m->private = tr;
+
+        return 0;
 }
 
 static ssize_t
@@ -3339,13 +3403,14 @@ static int tracing_trace_options_show(struct seq_file *m, void *v)
         return 0;
 }
 
-static int __set_tracer_option(struct tracer *trace,
+static int __set_tracer_option(struct trace_array *tr,
                                struct tracer_flags *tracer_flags,
                                struct tracer_opt *opts, int neg)
 {
+        struct tracer *trace = tr->current_trace;
         int ret;
 
-        ret = trace->set_flag(tracer_flags->val, opts->bit, !neg);
+        ret = trace->set_flag(tr, tracer_flags->val, opts->bit, !neg);
         if (ret)
                 return ret;
 
@@ -3357,8 +3422,9 @@ static int __set_tracer_option(struct tracer *trace,
 }
 
 /* Try to assign a tracer specific option */
-static int set_tracer_option(struct tracer *trace, char *cmp, int neg)
+static int set_tracer_option(struct trace_array *tr, char *cmp, int neg)
 {
+        struct tracer *trace = tr->current_trace;
         struct tracer_flags *tracer_flags = trace->flags;
         struct tracer_opt *opts = NULL;
         int i;
@@ -3367,8 +3433,7 @@ static int set_tracer_option(struct tracer *trace, char *cmp, int neg)
                 opts = &tracer_flags->opts[i];
 
                 if (strcmp(cmp, opts->name) == 0)
-                        return __set_tracer_option(trace, trace->flags,
-                                                   opts, neg);
+                        return __set_tracer_option(tr, trace->flags, opts, neg);
         }
 
         return -EINVAL;
@@ -3391,7 +3456,7 @@ int set_tracer_flag(struct trace_array *tr, unsigned int mask, int enabled)
 
         /* Give the tracer a chance to approve the change */
         if (tr->current_trace->flag_changed)
-                if (tr->current_trace->flag_changed(tr->current_trace, mask, !!enabled))
+                if (tr->current_trace->flag_changed(tr, mask, !!enabled))
                         return -EINVAL;
 
         if (enabled)
@@ -3440,7 +3505,7 @@ static int trace_set_options(struct trace_array *tr, char *option)
 
         /* If no option could be set, test the specific tracer options */
         if (!trace_options[i])
-                ret = set_tracer_option(tr->current_trace, cmp, neg);
+                ret = set_tracer_option(tr, cmp, neg);
 
         mutex_unlock(&trace_types_lock);
 
@@ -3869,10 +3934,26 @@ create_trace_option_files(struct trace_array *tr, struct tracer *tracer);
 static void
 destroy_trace_option_files(struct trace_option_dentry *topts);
 
-static int tracing_set_tracer(const char *buf)
+/*
+ * Used to clear out the tracer before deletion of an instance.
+ * Must have trace_types_lock held.
+ */
+static void tracing_set_nop(struct trace_array *tr)
+{
+        if (tr->current_trace == &nop_trace)
+                return;
+        
+        tr->current_trace->enabled--;
+
+        if (tr->current_trace->reset)
+                tr->current_trace->reset(tr);
+
+        tr->current_trace = &nop_trace;
+}
+
+static int tracing_set_tracer(struct trace_array *tr, const char *buf)
 {
         static struct trace_option_dentry *topts;
-        struct trace_array *tr = &global_trace;
         struct tracer *t;
 #ifdef CONFIG_TRACER_MAX_TRACE
         bool had_max_tr;
@@ -3900,9 +3981,15 @@ static int tracing_set_tracer(const char *buf)
         if (t == tr->current_trace)
                 goto out;
 
+        /* Some tracers are only allowed for the top level buffer */
+        if (!trace_ok_for_array(t, tr)) {
+                ret = -EINVAL;
+                goto out;
+        }
+
         trace_branch_disable();
 
-        tr->current_trace->enabled = false;
+        tr->current_trace->enabled--;
 
         if (tr->current_trace->reset)
                 tr->current_trace->reset(tr);
@@ -3925,9 +4012,11 @@ static int tracing_set_tracer(const char *buf)
                 free_snapshot(tr);
         }
 #endif
-        destroy_trace_option_files(topts);
-
-        topts = create_trace_option_files(tr, t);
+        /* Currently, only the top instance has options */
+        if (tr->flags & TRACE_ARRAY_FL_GLOBAL) {
+                destroy_trace_option_files(topts);
+                topts = create_trace_option_files(tr, t);
+        }
 
 #ifdef CONFIG_TRACER_MAX_TRACE
         if (t->use_max_tr && !had_max_tr) {
@@ -3944,7 +4033,7 @@ static int tracing_set_tracer(const char *buf)
         }
 
         tr->current_trace = t;
-        tr->current_trace->enabled = true;
+        tr->current_trace->enabled++;
         trace_branch_enable(tr);
  out:
         mutex_unlock(&trace_types_lock);
@@ -3956,6 +4045,7 @@ static ssize_t
 tracing_set_trace_write(struct file *filp, const char __user *ubuf,
                         size_t cnt, loff_t *ppos)
 {
+        struct trace_array *tr = filp->private_data;
         char buf[MAX_TRACER_SIZE+1];
         int i;
         size_t ret;
@@ -3975,7 +4065,7 @@ tracing_set_trace_write(struct file *filp, const char __user *ubuf,
         for (i = cnt - 1; i > 0 && isspace(buf[i]); i--)
                 buf[i] = 0;
 
-        err = tracing_set_tracer(buf);
+        err = tracing_set_tracer(tr, buf);
         if (err)
                 return err;
 
@@ -4683,25 +4773,10 @@ static int tracing_clock_show(struct seq_file *m, void *v)
         return 0;
 }
 
-static ssize_t tracing_clock_write(struct file *filp, const char __user *ubuf,
-                                   size_t cnt, loff_t *fpos)
+static int tracing_set_clock(struct trace_array *tr, const char *clockstr)
 {
-        struct seq_file *m = filp->private_data;
-        struct trace_array *tr = m->private;
-        char buf[64];
-        const char *clockstr;
         int i;
 
-        if (cnt >= sizeof(buf))
-                return -EINVAL;
-
-        if (copy_from_user(&buf, ubuf, cnt))
-                return -EFAULT;
-
-        buf[cnt] = 0;
-
-        clockstr = strstrip(buf);
-
         for (i = 0; i < ARRAY_SIZE(trace_clocks); i++) {
                 if (strcmp(trace_clocks[i].name, clockstr) == 0)
                         break;
@@ -4729,6 +4804,32 @@ static ssize_t tracing_clock_write(struct file *filp, const char __user *ubuf,
 
         mutex_unlock(&trace_types_lock);
 
+        return 0;
+}
+
+static ssize_t tracing_clock_write(struct file *filp, const char __user *ubuf,
+                                   size_t cnt, loff_t *fpos)
+{
+        struct seq_file *m = filp->private_data;
+        struct trace_array *tr = m->private;
+        char buf[64];
+        const char *clockstr;
+        int ret;
+
+        if (cnt >= sizeof(buf))
+                return -EINVAL;
+
+        if (copy_from_user(&buf, ubuf, cnt))
+                return -EFAULT;
+
+        buf[cnt] = 0;
+
+        clockstr = strstrip(buf);
+
+        ret = tracing_set_clock(tr, clockstr);
+        if (ret)
+                return ret;
+
         *fpos += cnt;
 
         return cnt;
@@ -5689,7 +5790,7 @@ trace_options_write(struct file *filp, const char __user *ubuf, size_t cnt,
 
         if (!!(topt->flags->val & topt->opt->bit) != val) {
                 mutex_lock(&trace_types_lock);
-                ret = __set_tracer_option(topt->tr->current_trace, topt->flags,
+                ret = __set_tracer_option(topt->tr, topt->flags,
                                           topt->opt, !val);
                 mutex_unlock(&trace_types_lock);
                 if (ret)
@@ -6096,7 +6197,9 @@ static int instance_delete(const char *name)
 
         list_del(&tr->list);
 
+        tracing_set_nop(tr);
         event_trace_del_tracer(tr);
+        ftrace_destroy_function_files(tr);
         debugfs_remove_recursive(tr->dir);
         free_percpu(tr->trace_buffer.data);
         ring_buffer_free(tr->trace_buffer.buffer);
@@ -6191,6 +6294,12 @@ init_tracer_debugfs(struct trace_array *tr, struct dentry *d_tracer)
 {
         int cpu;
 
+        trace_create_file("available_tracers", 0444, d_tracer,
+                        tr, &show_traces_fops);
+
+        trace_create_file("current_tracer", 0644, d_tracer,
+                        tr, &set_tracer_fops);
+
         trace_create_file("tracing_cpumask", 0644, d_tracer,
                           tr, &tracing_cpumask_fops);
 
@@ -6221,6 +6330,9 @@ init_tracer_debugfs(struct trace_array *tr, struct dentry *d_tracer)
         trace_create_file("tracing_on", 0644, d_tracer,
                           tr, &rb_simple_fops);
 
+        if (ftrace_create_function_files(tr, d_tracer))
+                WARN(1, "Could not allocate function filter files");
+
 #ifdef CONFIG_TRACER_SNAPSHOT
         trace_create_file("snapshot", 0644, d_tracer,
                           tr, &snapshot_fops);
@@ -6243,12 +6355,6 @@ static __init int tracer_init_debugfs(void)
 
         init_tracer_debugfs(&global_trace, d_tracer);
 
-        trace_create_file("available_tracers", 0444, d_tracer,
-                        &global_trace, &show_traces_fops);
-
-        trace_create_file("current_tracer", 0644, d_tracer,
-                        &global_trace, &set_tracer_fops);
-
 #ifdef CONFIG_TRACER_MAX_TRACE
         trace_create_file("tracing_max_latency", 0644, d_tracer,
                         &tracing_max_latency, &tracing_max_lat_fops);
@@ -6494,11 +6600,16 @@ __init static int tracer_alloc_buffers(void)
 
         raw_spin_lock_init(&global_trace.start_lock);
 
+        /* Used for event triggers */
+        temp_buffer = ring_buffer_alloc(PAGE_SIZE, RB_FL_OVERWRITE);
+        if (!temp_buffer)
+                goto out_free_cpumask;
+
         /* TODO: make the number of buffers hot pluggable with CPUS */
         if (allocate_trace_buffers(&global_trace, ring_buf_size) < 0) {
                 printk(KERN_ERR "tracer: failed to allocate ring buffer!\n");
                 WARN_ON(1);
-                goto out_free_cpumask;
+                goto out_free_temp_buffer;
         }
 
         if (global_trace.buffer_disabled)
@@ -6506,6 +6617,13 @@ __init static int tracer_alloc_buffers(void)
 
         trace_init_cmdlines();
 
+        if (trace_boot_clock) {
+                ret = tracing_set_clock(&global_trace, trace_boot_clock);
+                if (ret < 0)
+                        pr_warning("Trace clock %s not defined, going back to default\n",
+                                   trace_boot_clock);
+        }
+
         /*
          * register_tracer() might reference current_trace, so it
          * needs to be set before we register anything. This is
@@ -6540,6 +6658,8 @@ __init static int tracer_alloc_buffers(void)
 
         return 0;
 
+out_free_temp_buffer:
+        ring_buffer_free(temp_buffer);
 out_free_cpumask:
         free_percpu(global_trace.trace_buffer.data);
 #ifdef CONFIG_TRACER_MAX_TRACE
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 02b592f2d4b7..ffc314b7e92b 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -210,6 +210,11 @@ struct trace_array {
         struct list_head        events;
         cpumask_var_t           tracing_cpumask; /* only trace on set CPUs */
         int                     ref;
+#ifdef CONFIG_FUNCTION_TRACER
+        struct ftrace_ops       *ops;
+        /* function tracing enabled */
+        int                     function_enabled;
+#endif
 };
 
 enum {
@@ -355,14 +360,16 @@ struct tracer {
         void                    (*print_header)(struct seq_file *m);
         enum print_line_t       (*print_line)(struct trace_iterator *iter);
         /* If you handled the flag setting, return 0 */
-        int                     (*set_flag)(u32 old_flags, u32 bit, int set);
+        int                     (*set_flag)(struct trace_array *tr,
+                                            u32 old_flags, u32 bit, int set);
         /* Return 0 if OK with change, else return non-zero */
-        int                     (*flag_changed)(struct tracer *tracer,
+        int                     (*flag_changed)(struct trace_array *tr,
                                                 u32 mask, int set);
         struct tracer           *next;
         struct tracer_flags     *flags;
+        int                     enabled;
         bool                    print_max;
-        bool                    enabled;
+        bool                    allow_instances;
 #ifdef CONFIG_TRACER_MAX_TRACE
         bool                    use_max_tr;
 #endif
@@ -812,13 +819,36 @@ static inline int ftrace_trace_task(struct task_struct *task)
         return test_tsk_trace_trace(task);
 }
 extern int ftrace_is_dead(void);
+int ftrace_create_function_files(struct trace_array *tr,
+                                 struct dentry *parent);
+void ftrace_destroy_function_files(struct trace_array *tr);
 #else
 static inline int ftrace_trace_task(struct task_struct *task)
 {
         return 1;
 }
 static inline int ftrace_is_dead(void) { return 0; }
-#endif
+static inline int
+ftrace_create_function_files(struct trace_array *tr,
+                             struct dentry *parent)
+{
+        return 0;
+}
+static inline void ftrace_destroy_function_files(struct trace_array *tr) { }
+#endif /* CONFIG_FUNCTION_TRACER */
+
+#if defined(CONFIG_FUNCTION_TRACER) && defined(CONFIG_DYNAMIC_FTRACE)
+void ftrace_create_filter_files(struct ftrace_ops *ops,
+                                struct dentry *parent);
+void ftrace_destroy_filter_files(struct ftrace_ops *ops);
+#else
+/*
+ * The ops parameter passed in is usually undefined.
+ * This must be a macro.
+ */
+#define ftrace_create_filter_files(ops, parent) do { } while (0)
+#define ftrace_destroy_filter_files(ops) do { } while (0)
+#endif /* CONFIG_FUNCTION_TRACER && CONFIG_DYNAMIC_FTRACE */
 
 int ftrace_event_is_function(struct ftrace_event_call *call);
 
diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c
index e854f420e033..c894614de14d 100644
--- a/kernel/trace/trace_event_perf.c
+++ b/kernel/trace/trace_event_perf.c
@@ -31,9 +31,25 @@ static int perf_trace_event_perm(struct ftrace_event_call *tp_event,
         }
 
         /* The ftrace function trace is allowed only for root. */
-        if (ftrace_event_is_function(tp_event) &&
-            perf_paranoid_tracepoint_raw() && !capable(CAP_SYS_ADMIN))
-                return -EPERM;
+        if (ftrace_event_is_function(tp_event)) {
+                if (perf_paranoid_tracepoint_raw() && !capable(CAP_SYS_ADMIN))
+                        return -EPERM;
+
+                /*
+                 * We don't allow user space callchains for  function trace
+                 * event, due to issues with page faults while tracing page
+                 * fault handler and its overall trickiness nature.
+                 */
+                if (!p_event->attr.exclude_callchain_user)
+                        return -EINVAL;
+
+                /*
+                 * Same reason to disable user stack dump as for user space
+                 * callchains above.
+                 */
+                if (p_event->attr.sample_type & PERF_SAMPLE_STACK_USER)
+                        return -EINVAL;
+        }
 
         /* No tracing, just counting, so no obvious leak */
         if (!(p_event->attr.sample_type & PERF_SAMPLE_RAW))
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index f3989ceb5cd5..83a4378dc5e0 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -27,12 +27,6 @@
 
 DEFINE_MUTEX(event_mutex);
 
-DEFINE_MUTEX(event_storage_mutex);
-EXPORT_SYMBOL_GPL(event_storage_mutex);
-
-char event_storage[EVENT_STORAGE_SIZE];
-EXPORT_SYMBOL_GPL(event_storage);
-
 LIST_HEAD(ftrace_events);
 static LIST_HEAD(ftrace_common_fields);
 
@@ -194,6 +188,36 @@ int trace_event_raw_init(struct ftrace_event_call *call)
 }
 EXPORT_SYMBOL_GPL(trace_event_raw_init);
 
+void *ftrace_event_buffer_reserve(struct ftrace_event_buffer *fbuffer,
+                                  struct ftrace_event_file *ftrace_file,
+                                  unsigned long len)
+{
+        struct ftrace_event_call *event_call = ftrace_file->event_call;
+
+        local_save_flags(fbuffer->flags);
+        fbuffer->pc = preempt_count();
+        fbuffer->ftrace_file = ftrace_file;
+
+        fbuffer->event =
+                trace_event_buffer_lock_reserve(&fbuffer->buffer, ftrace_file,
+                                                event_call->event.type, len,
+                                                fbuffer->flags, fbuffer->pc);
+        if (!fbuffer->event)
+                return NULL;
+
+        fbuffer->entry = ring_buffer_event_data(fbuffer->event);
+        return fbuffer->entry;
+}
+EXPORT_SYMBOL_GPL(ftrace_event_buffer_reserve);
+
+void ftrace_event_buffer_commit(struct ftrace_event_buffer *fbuffer)
+{
+        event_trigger_unlock_commit(fbuffer->ftrace_file, fbuffer->buffer,
+                                    fbuffer->event, fbuffer->entry,
+                                    fbuffer->flags, fbuffer->pc);
+}
+EXPORT_SYMBOL_GPL(ftrace_event_buffer_commit);
+
 int ftrace_event_reg(struct ftrace_event_call *call,
                      enum trace_reg type, void *data)
 {
diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c
index 7c3e3e72e2b6..ee0a5098ac43 100644
--- a/kernel/trace/trace_export.c
+++ b/kernel/trace/trace_export.c
@@ -95,15 +95,12 @@ static void __always_unused ____ftrace_check_##name(void)		\
 #undef __array
 #define __array(type, item, len)                                        \
         do {                                                            \
+                char *type_str = #type"["__stringify(len)"]";           \
                 BUILD_BUG_ON(len > MAX_FILTER_STR_VAL);                 \
-                mutex_lock(&event_storage_mutex);                       \
-                snprintf(event_storage, sizeof(event_storage),          \
-                         "%s[%d]", #type, len);                         \
-                ret = trace_define_field(event_call, event_storage, #item, \
+                ret = trace_define_field(event_call, type_str, #item,   \
                                  offsetof(typeof(field), item),         \
                                  sizeof(field.item),                    \
                                  is_signed_type(type), filter_type);    \
-                mutex_unlock(&event_storage_mutex);                     \
                 if (ret)                                                \
                         return ret;                                     \
         } while (0);
diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c
index 38fe1483c508..5b781d2be383 100644
--- a/kernel/trace/trace_functions.c
+++ b/kernel/trace/trace_functions.c
@@ -13,32 +13,106 @@
 #include <linux/debugfs.h>
 #include <linux/uaccess.h>
 #include <linux/ftrace.h>
+#include <linux/slab.h>
 #include <linux/fs.h>
 
 #include "trace.h"
 
-/* function tracing enabled */
-static int                      ftrace_function_enabled;
+static void tracing_start_function_trace(struct trace_array *tr);
+static void tracing_stop_function_trace(struct trace_array *tr);
+static void
+function_trace_call(unsigned long ip, unsigned long parent_ip,
+                    struct ftrace_ops *op, struct pt_regs *pt_regs);
+static void
+function_stack_trace_call(unsigned long ip, unsigned long parent_ip,
+                          struct ftrace_ops *op, struct pt_regs *pt_regs);
+static struct ftrace_ops trace_ops;
+static struct ftrace_ops trace_stack_ops;
+static struct tracer_flags func_flags;
+
+/* Our option */
+enum {
+        TRACE_FUNC_OPT_STACK    = 0x1,
+};
+
+static int allocate_ftrace_ops(struct trace_array *tr)
+{
+        struct ftrace_ops *ops;
+
+        ops = kzalloc(sizeof(*ops), GFP_KERNEL);
+        if (!ops)
+                return -ENOMEM;
 
-static struct trace_array       *func_trace;
+        /* Currently only the non stack verision is supported */
+        ops->func = function_trace_call;
+        ops->flags = FTRACE_OPS_FL_RECURSION_SAFE;
+
+        tr->ops = ops;
+        ops->private = tr;
+        return 0;
+}
+
+
+int ftrace_create_function_files(struct trace_array *tr,
+                                 struct dentry *parent)
+{
+        int ret;
+
+        /* The top level array uses the "global_ops". */
+        if (!(tr->flags & TRACE_ARRAY_FL_GLOBAL)) {
+                ret = allocate_ftrace_ops(tr);
+                if (ret)
+                        return ret;
+        }
+
+        ftrace_create_filter_files(tr->ops, parent);
+
+        return 0;
+}
 
-static void tracing_start_function_trace(void);
-static void tracing_stop_function_trace(void);
+void ftrace_destroy_function_files(struct trace_array *tr)
+{
+        ftrace_destroy_filter_files(tr->ops);
+        kfree(tr->ops);
+        tr->ops = NULL;
+}
 
 static int function_trace_init(struct trace_array *tr)
 {
-        func_trace = tr;
+        struct ftrace_ops *ops;
+
+        if (tr->flags & TRACE_ARRAY_FL_GLOBAL) {
+                /* There's only one global tr */
+                if (!trace_ops.private) {
+                        trace_ops.private = tr;
+                        trace_stack_ops.private = tr;
+                }
+
+                if (func_flags.val & TRACE_FUNC_OPT_STACK)
+                        ops = &trace_stack_ops;
+                else
+                        ops = &trace_ops;
+                tr->ops = ops;
+        } else if (!tr->ops) {
+                /*
+                 * Instance trace_arrays get their ops allocated
+                 * at instance creation. Unless it failed
+                 * the allocation.
+                 */
+                return -ENOMEM;
+        }
+
         tr->trace_buffer.cpu = get_cpu();
         put_cpu();
 
         tracing_start_cmdline_record();
-        tracing_start_function_trace();
+        tracing_start_function_trace(tr);
         return 0;
 }
 
 static void function_trace_reset(struct trace_array *tr)
 {
-        tracing_stop_function_trace();
+        tracing_stop_function_trace(tr);
         tracing_stop_cmdline_record();
 }
 
@@ -47,25 +121,18 @@ static void function_trace_start(struct trace_array *tr)
         tracing_reset_online_cpus(&tr->trace_buffer);
 }
 
-/* Our option */
-enum {
-        TRACE_FUNC_OPT_STACK    = 0x1,
-};
-
-static struct tracer_flags func_flags;
-
 static void
 function_trace_call(unsigned long ip, unsigned long parent_ip,
                     struct ftrace_ops *op, struct pt_regs *pt_regs)
 {
-        struct trace_array *tr = func_trace;
+        struct trace_array *tr = op->private;
         struct trace_array_cpu *data;
         unsigned long flags;
         int bit;
         int cpu;
         int pc;
 
-        if (unlikely(!ftrace_function_enabled))
+        if (unlikely(!tr->function_enabled))
                 return;
 
         pc = preempt_count();
@@ -91,14 +158,14 @@ static void
 function_stack_trace_call(unsigned long ip, unsigned long parent_ip,
                           struct ftrace_ops *op, struct pt_regs *pt_regs)
 {
-        struct trace_array *tr = func_trace;
+        struct trace_array *tr = op->private;
         struct trace_array_cpu *data;
         unsigned long flags;
         long disabled;
         int cpu;
         int pc;
 
-        if (unlikely(!ftrace_function_enabled))
+        if (unlikely(!tr->function_enabled))
                 return;
 
         /*
@@ -128,7 +195,6 @@ function_stack_trace_call(unsigned long ip, unsigned long parent_ip,
         local_irq_restore(flags);
 }
 
-
 static struct ftrace_ops trace_ops __read_mostly =
 {
         .func = function_trace_call,
@@ -153,29 +219,21 @@ static struct tracer_flags func_flags = {
         .opts = func_opts
 };
 
-static void tracing_start_function_trace(void)
+static void tracing_start_function_trace(struct trace_array *tr)
 {
-        ftrace_function_enabled = 0;
-
-        if (func_flags.val & TRACE_FUNC_OPT_STACK)
-                register_ftrace_function(&trace_stack_ops);
-        else
-                register_ftrace_function(&trace_ops);
-
-        ftrace_function_enabled = 1;
+        tr->function_enabled = 0;
+        register_ftrace_function(tr->ops);
+        tr->function_enabled = 1;
 }
 
-static void tracing_stop_function_trace(void)
+static void tracing_stop_function_trace(struct trace_array *tr)
 {
-        ftrace_function_enabled = 0;
-
-        if (func_flags.val & TRACE_FUNC_OPT_STACK)
-                unregister_ftrace_function(&trace_stack_ops);
-        else
-                unregister_ftrace_function(&trace_ops);
+        tr->function_enabled = 0;
+        unregister_ftrace_function(tr->ops);
 }
 
-static int func_set_flag(u32 old_flags, u32 bit, int set)
+static int
+func_set_flag(struct trace_array *tr, u32 old_flags, u32 bit, int set)
 {
         switch (bit) {
         case TRACE_FUNC_OPT_STACK:
@@ -183,12 +241,14 @@ static int func_set_flag(u32 old_flags, u32 bit, int set)
                 if (!!set == !!(func_flags.val & TRACE_FUNC_OPT_STACK))
                         break;
 
+                unregister_ftrace_function(tr->ops);
+
                 if (set) {
-                        unregister_ftrace_function(&trace_ops);
-                        register_ftrace_function(&trace_stack_ops);
+                        tr->ops = &trace_stack_ops;
+                        register_ftrace_function(tr->ops);
                 } else {
-                        unregister_ftrace_function(&trace_stack_ops);
-                        register_ftrace_function(&trace_ops);
+                        tr->ops = &trace_ops;
+                        register_ftrace_function(tr->ops);
                 }
 
                 break;
@@ -208,6 +268,7 @@ static struct tracer function_trace __tracer_data =
         .wait_pipe      = poll_wait_pipe,
         .flags          = &func_flags,
         .set_flag       = func_set_flag,
+        .allow_instances = true,
 #ifdef CONFIG_FTRACE_SELFTEST
         .selftest       = trace_selftest_startup_function,
 #endif
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index 0b99120d395c..deff11200261 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -1476,7 +1476,8 @@ void graph_trace_close(struct trace_iterator *iter)
         }
 }
 
-static int func_graph_set_flag(u32 old_flags, u32 bit, int set)
+static int
+func_graph_set_flag(struct trace_array *tr, u32 old_flags, u32 bit, int set)
 {
         if (bit == TRACE_GRAPH_PRINT_IRQS)
                 ftrace_graph_skip_irqs = !set;
diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c
index 2aefbee93a6d..8ff02cbb892f 100644
--- a/kernel/trace/trace_irqsoff.c
+++ b/kernel/trace/trace_irqsoff.c
@@ -160,7 +160,8 @@ static struct ftrace_ops trace_ops __read_mostly =
 #endif /* CONFIG_FUNCTION_TRACER */
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
-static int irqsoff_set_flag(u32 old_flags, u32 bit, int set)
+static int
+irqsoff_set_flag(struct trace_array *tr, u32 old_flags, u32 bit, int set)
 {
         int cpu;
 
@@ -266,7 +267,8 @@ __trace_function(struct trace_array *tr,
 #else
 #define __trace_function trace_function
 
-static int irqsoff_set_flag(u32 old_flags, u32 bit, int set)
+static int
+irqsoff_set_flag(struct trace_array *tr, u32 old_flags, u32 bit, int set)
 {
         return -EINVAL;
 }
@@ -498,14 +500,14 @@ void trace_hardirqs_off(void)
 }
 EXPORT_SYMBOL(trace_hardirqs_off);
 
-void trace_hardirqs_on_caller(unsigned long caller_addr)
+__visible void trace_hardirqs_on_caller(unsigned long caller_addr)
 {
         if (!preempt_trace() && irq_trace())
                 stop_critical_timing(CALLER_ADDR0, caller_addr);
 }
 EXPORT_SYMBOL(trace_hardirqs_on_caller);
 
-void trace_hardirqs_off_caller(unsigned long caller_addr)
+__visible void trace_hardirqs_off_caller(unsigned long caller_addr)
 {
         if (!preempt_trace() && irq_trace())
                 start_critical_timing(CALLER_ADDR0, caller_addr);
@@ -570,8 +572,10 @@ static void irqsoff_function_set(int set)
                 unregister_irqsoff_function(is_graph());
 }
 
-static int irqsoff_flag_changed(struct tracer *tracer, u32 mask, int set)
+static int irqsoff_flag_changed(struct trace_array *tr, u32 mask, int set)
 {
+        struct tracer *tracer = tr->current_trace;
+
         if (mask & TRACE_ITER_FUNCTION)
                 irqsoff_function_set(set);
 
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index bdbae450c13e..d021d21dd150 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -35,11 +35,6 @@ struct trace_kprobe {
         struct trace_probe      tp;
 };
 
-struct event_file_link {
-        struct ftrace_event_file        *file;
-        struct list_head                list;
-};
-
 #define SIZEOF_TRACE_KPROBE(n)                          \
         (offsetof(struct trace_kprobe, tp.args) +       \
         (sizeof(struct probe_arg) * (n)))
@@ -387,18 +382,6 @@ enable_trace_kprobe(struct trace_kprobe *tk, struct ftrace_event_file *file)
         return ret;
 }
 
-static struct event_file_link *
-find_event_file_link(struct trace_probe *tp, struct ftrace_event_file *file)
-{
-        struct event_file_link *link;
-
-        list_for_each_entry(link, &tp->files, list)
-                if (link->file == file)
-                        return link;
-
-        return NULL;
-}
-
 /*
  * Disable trace_probe
  * if the file is NULL, disable "perf" handler, or disable "trace" handler.
diff --git a/kernel/trace/trace_nop.c b/kernel/trace/trace_nop.c
index 394f94417e2f..69a5cc94c01a 100644
--- a/kernel/trace/trace_nop.c
+++ b/kernel/trace/trace_nop.c
@@ -62,7 +62,7 @@ static void nop_trace_reset(struct trace_array *tr)
  * If you don't implement it, then the flag setting will be
  * automatically accepted.
  */
-static int nop_set_flag(u32 old_flags, u32 bit, int set)
+static int nop_set_flag(struct trace_array *tr, u32 old_flags, u32 bit, int set)
 {
         /*
          * Note that you don't need to update nop_flags.val yourself.
@@ -96,6 +96,7 @@ struct tracer nop_trace __read_mostly =
         .selftest       = trace_selftest_startup_nop,
 #endif
         .flags          = &nop_flags,
-        .set_flag       = nop_set_flag
+        .set_flag       = nop_set_flag,
+        .allow_instances = true,
 };
 
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index ed32284fbe32..ca0e79e2abaa 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -439,6 +439,37 @@ int ftrace_raw_output_prep(struct trace_iterator *iter,
 }
 EXPORT_SYMBOL(ftrace_raw_output_prep);
 
+static int ftrace_output_raw(struct trace_iterator *iter, char *name,
+                             char *fmt, va_list ap)
+{
+        struct trace_seq *s = &iter->seq;
+        int ret;
+
+        ret = trace_seq_printf(s, "%s: ", name);
+        if (!ret)
+                return TRACE_TYPE_PARTIAL_LINE;
+
+        ret = trace_seq_vprintf(s, fmt, ap);
+
+        if (!ret)
+                return TRACE_TYPE_PARTIAL_LINE;
+
+        return TRACE_TYPE_HANDLED;
+}
+
+int ftrace_output_call(struct trace_iterator *iter, char *name, char *fmt, ...)
+{
+        va_list ap;
+        int ret;
+
+        va_start(ap, fmt);
+        ret = ftrace_output_raw(iter, name, fmt, ap);
+        va_end(ap);
+
+        return ret;
+}
+EXPORT_SYMBOL_GPL(ftrace_output_call);
+
 #ifdef CONFIG_KRETPROBES
 static inline const char *kretprobed(const char *name)
 {
diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h
index b73574a5f429..fb1ab5dfbd42 100644
--- a/kernel/trace/trace_probe.h
+++ b/kernel/trace/trace_probe.h
@@ -288,6 +288,11 @@ struct trace_probe {
         struct probe_arg                args[];
 };
 
+struct event_file_link {
+        struct ftrace_event_file        *file;
+        struct list_head                list;
+};
+
 static inline bool trace_probe_is_enabled(struct trace_probe *tp)
 {
         return !!(tp->flags & (TP_FLAG_TRACE | TP_FLAG_PROFILE));
@@ -316,6 +321,18 @@ static inline int is_good_name(const char *name)
         return 1;
 }
 
+static inline struct event_file_link *
+find_event_file_link(struct trace_probe *tp, struct ftrace_event_file *file)
+{
+        struct event_file_link *link;
+
+        list_for_each_entry(link, &tp->files, list)
+                if (link->file == file)
+                        return link;
+
+        return NULL;
+}
+
 extern int traceprobe_parse_probe_arg(char *arg, ssize_t *size,
                    struct probe_arg *parg, bool is_return, bool is_kprobe);
 
diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c
index 6e32635e5e57..e14da5e97a69 100644
--- a/kernel/trace/trace_sched_wakeup.c
+++ b/kernel/trace/trace_sched_wakeup.c
@@ -179,8 +179,10 @@ static void wakeup_function_set(int set)
                 unregister_wakeup_function(is_graph());
 }
 
-static int wakeup_flag_changed(struct tracer *tracer, u32 mask, int set)
+static int wakeup_flag_changed(struct trace_array *tr, u32 mask, int set)
 {
+        struct tracer *tracer = tr->current_trace;
+
         if (mask & TRACE_ITER_FUNCTION)
                 wakeup_function_set(set);
 
@@ -209,7 +211,8 @@ static void stop_func_tracer(int graph)
 }
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
-static int wakeup_set_flag(u32 old_flags, u32 bit, int set)
+static int
+wakeup_set_flag(struct trace_array *tr, u32 old_flags, u32 bit, int set)
 {
 
         if (!(bit & TRACE_DISPLAY_GRAPH))
@@ -311,7 +314,8 @@ __trace_function(struct trace_array *tr,
 #else
 #define __trace_function trace_function
 
-static int wakeup_set_flag(u32 old_flags, u32 bit, int set)
+static int
+wakeup_set_flag(struct trace_array *tr, u32 old_flags, u32 bit, int set)
 {
         return -EINVAL;
 }
diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index e6be585cf06a..21b320e5d163 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -13,6 +13,7 @@
 #include <linux/sysctl.h>
 #include <linux/init.h>
 #include <linux/fs.h>
+#include <linux/magic.h>
 
 #include <asm/setup.h>
 
@@ -144,6 +145,8 @@ check_stack(unsigned long ip, unsigned long *stack)
                         i++;
         }
 
+        BUG_ON(current != &init_task &&
+                *(end_of_stack(current)) != STACK_END_MAGIC);
  out:
         arch_spin_unlock(&max_stack_lock);
         local_irq_restore(flags);
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index 79e52d93860b..e4473367e7a4 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -260,6 +260,7 @@ alloc_trace_uprobe(const char *group, const char *event, int nargs, bool is_ret)
                 goto error;
 
         INIT_LIST_HEAD(&tu->list);
+        INIT_LIST_HEAD(&tu->tp.files);
         tu->consumer.handler = uprobe_dispatcher;
         if (is_ret)
                 tu->consumer.ret_handler = uretprobe_dispatcher;
@@ -758,31 +759,32 @@ static void uprobe_buffer_put(struct uprobe_cpu_buffer *ucb)
         mutex_unlock(&ucb->mutex);
 }
 
-static void uprobe_trace_print(struct trace_uprobe *tu,
-                                unsigned long func, struct pt_regs *regs)
+static void __uprobe_trace_func(struct trace_uprobe *tu,
+                                unsigned long func, struct pt_regs *regs,
+                                struct uprobe_cpu_buffer *ucb, int dsize,
+                                struct ftrace_event_file *ftrace_file)
 {
         struct uprobe_trace_entry_head *entry;
         struct ring_buffer_event *event;
         struct ring_buffer *buffer;
-        struct uprobe_cpu_buffer *ucb;
         void *data;
-        int size, dsize, esize;
+        int size, esize;
         struct ftrace_event_call *call = &tu->tp.call;
 
-        dsize = __get_data_size(&tu->tp, regs);
-        esize = SIZEOF_TRACE_ENTRY(is_ret_probe(tu));
+        WARN_ON(call != ftrace_file->event_call);
 
-        if (WARN_ON_ONCE(!uprobe_cpu_buffer || tu->tp.size + dsize > PAGE_SIZE))
+        if (WARN_ON_ONCE(tu->tp.size + dsize > PAGE_SIZE))
                 return;
 
-        ucb = uprobe_buffer_get();
-        store_trace_args(esize, &tu->tp, regs, ucb->buf, dsize);
+        if (ftrace_trigger_soft_disabled(ftrace_file))
+                return;
 
+        esize = SIZEOF_TRACE_ENTRY(is_ret_probe(tu));
         size = esize + tu->tp.size + dsize;
-        event = trace_current_buffer_lock_reserve(&buffer, call->event.type,
-                                                  size, 0, 0);
+        event = trace_event_buffer_lock_reserve(&buffer, ftrace_file,
+                                                call->event.type, size, 0, 0);
         if (!event)
-                goto out;
+                return;
 
         entry = ring_buffer_event_data(event);
         if (is_ret_probe(tu)) {
@@ -796,25 +798,36 @@ static void uprobe_trace_print(struct trace_uprobe *tu,
 
         memcpy(data, ucb->buf, tu->tp.size + dsize);
 
-        if (!call_filter_check_discard(call, entry, buffer, event))
-                trace_buffer_unlock_commit(buffer, event, 0, 0);
-
-out:
-        uprobe_buffer_put(ucb);
+        event_trigger_unlock_commit(ftrace_file, buffer, event, entry, 0, 0);
 }
 
 /* uprobe handler */
-static int uprobe_trace_func(struct trace_uprobe *tu, struct pt_regs *regs)
+static int uprobe_trace_func(struct trace_uprobe *tu, struct pt_regs *regs,
+                             struct uprobe_cpu_buffer *ucb, int dsize)
 {
-        if (!is_ret_probe(tu))
-                uprobe_trace_print(tu, 0, regs);
+        struct event_file_link *link;
+
+        if (is_ret_probe(tu))
+                return 0;
+
+        rcu_read_lock();
+        list_for_each_entry_rcu(link, &tu->tp.files, list)
+                __uprobe_trace_func(tu, 0, regs, ucb, dsize, link->file);
+        rcu_read_unlock();
+
         return 0;
 }
 
 static void uretprobe_trace_func(struct trace_uprobe *tu, unsigned long func,
-                                struct pt_regs *regs)
+                                 struct pt_regs *regs,
+                                 struct uprobe_cpu_buffer *ucb, int dsize)
 {
-        uprobe_trace_print(tu, func, regs);
+        struct event_file_link *link;
+
+        rcu_read_lock();
+        list_for_each_entry_rcu(link, &tu->tp.files, list)
+                __uprobe_trace_func(tu, func, regs, ucb, dsize, link->file);
+        rcu_read_unlock();
 }
 
 /* Event entry printers */
@@ -861,12 +874,24 @@ typedef bool (*filter_func_t)(struct uprobe_consumer *self,
                                 struct mm_struct *mm);
 
 static int
-probe_event_enable(struct trace_uprobe *tu, int flag, filter_func_t filter)
+probe_event_enable(struct trace_uprobe *tu, struct ftrace_event_file *file,
+                   filter_func_t filter)
 {
-        int ret = 0;
+        bool enabled = trace_probe_is_enabled(&tu->tp);
+        struct event_file_link *link = NULL;
+        int ret;
+
+        if (file) {
+                link = kmalloc(sizeof(*link), GFP_KERNEL);
+                if (!link)
+                        return -ENOMEM;
 
-        if (trace_probe_is_enabled(&tu->tp))
-                return -EINTR;
+                link->file = file;
+                list_add_tail_rcu(&link->list, &tu->tp.files);
+
+                tu->tp.flags |= TP_FLAG_TRACE;
+        } else
+                tu->tp.flags |= TP_FLAG_PROFILE;
 
         ret = uprobe_buffer_enable();
         if (ret < 0)
@@ -874,24 +899,49 @@ probe_event_enable(struct trace_uprobe *tu, int flag, filter_func_t filter)
 
         WARN_ON(!uprobe_filter_is_empty(&tu->filter));
 
-        tu->tp.flags |= flag;
+        if (enabled)
+                return 0;
+
         tu->consumer.filter = filter;
         ret = uprobe_register(tu->inode, tu->offset, &tu->consumer);
-        if (ret)
-                tu->tp.flags &= ~flag;
+        if (ret) {
+                if (file) {
+                        list_del(&link->list);
+                        kfree(link);
+                        tu->tp.flags &= ~TP_FLAG_TRACE;
+                } else
+                        tu->tp.flags &= ~TP_FLAG_PROFILE;
+        }
 
         return ret;
 }
 
-static void probe_event_disable(struct trace_uprobe *tu, int flag)
+static void
+probe_event_disable(struct trace_uprobe *tu, struct ftrace_event_file *file)
 {
         if (!trace_probe_is_enabled(&tu->tp))
                 return;
 
+        if (file) {
+                struct event_file_link *link;
+
+                link = find_event_file_link(&tu->tp, file);
+                if (!link)
+                        return;
+
+                list_del_rcu(&link->list);
+                /* synchronize with u{,ret}probe_trace_func */
+                synchronize_sched();
+                kfree(link);
+
+                if (!list_empty(&tu->tp.files))
+                        return;
+        }
+
         WARN_ON(!uprobe_filter_is_empty(&tu->filter));
 
         uprobe_unregister(tu->inode, tu->offset, &tu->consumer);
-        tu->tp.flags &= ~flag;
+        tu->tp.flags &= file ? ~TP_FLAG_TRACE : ~TP_FLAG_PROFILE;
 
         uprobe_buffer_disable();
 }
@@ -1014,31 +1064,24 @@ static bool uprobe_perf_filter(struct uprobe_consumer *uc,
         return ret;
 }
 
-static void uprobe_perf_print(struct trace_uprobe *tu,
-                                unsigned long func, struct pt_regs *regs)
+static void __uprobe_perf_func(struct trace_uprobe *tu,
+                               unsigned long func, struct pt_regs *regs,
+                               struct uprobe_cpu_buffer *ucb, int dsize)
 {
         struct ftrace_event_call *call = &tu->tp.call;
         struct uprobe_trace_entry_head *entry;
         struct hlist_head *head;
-        struct uprobe_cpu_buffer *ucb;
         void *data;
-        int size, dsize, esize;
+        int size, esize;
         int rctx;
 
-        dsize = __get_data_size(&tu->tp, regs);
         esize = SIZEOF_TRACE_ENTRY(is_ret_probe(tu));
 
-        if (WARN_ON_ONCE(!uprobe_cpu_buffer))
-                return;
-
         size = esize + tu->tp.size + dsize;
         size = ALIGN(size + sizeof(u32), sizeof(u64)) - sizeof(u32);
         if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE, "profile buffer not large enough"))
                 return;
 
-        ucb = uprobe_buffer_get();
-        store_trace_args(esize, &tu->tp, regs, ucb->buf, dsize);
-
         preempt_disable();
         head = this_cpu_ptr(call->perf_events);
         if (hlist_empty(head))
@@ -1068,46 +1111,49 @@ static void uprobe_perf_print(struct trace_uprobe *tu,
         perf_trace_buf_submit(entry, size, rctx, 0, 1, regs, head, NULL);
  out:
         preempt_enable();
-        uprobe_buffer_put(ucb);
 }
 
 /* uprobe profile handler */
-static int uprobe_perf_func(struct trace_uprobe *tu, struct pt_regs *regs)
+static int uprobe_perf_func(struct trace_uprobe *tu, struct pt_regs *regs,
+                            struct uprobe_cpu_buffer *ucb, int dsize)
 {
         if (!uprobe_perf_filter(&tu->consumer, 0, current->mm))
                 return UPROBE_HANDLER_REMOVE;
 
         if (!is_ret_probe(tu))
-                uprobe_perf_print(tu, 0, regs);
+                __uprobe_perf_func(tu, 0, regs, ucb, dsize);
         return 0;
 }
 
 static void uretprobe_perf_func(struct trace_uprobe *tu, unsigned long func,
-                                struct pt_regs *regs)
+                                struct pt_regs *regs,
+                                struct uprobe_cpu_buffer *ucb, int dsize)
 {
-        uprobe_perf_print(tu, func, regs);
+        __uprobe_perf_func(tu, func, regs, ucb, dsize);
 }
 #endif  /* CONFIG_PERF_EVENTS */
 
-static
-int trace_uprobe_register(struct ftrace_event_call *event, enum trace_reg type, void *data)
+static int
+trace_uprobe_register(struct ftrace_event_call *event, enum trace_reg type,
+                      void *data)
 {
         struct trace_uprobe *tu = event->data;
+        struct ftrace_event_file *file = data;
 
         switch (type) {
         case TRACE_REG_REGISTER:
-                return probe_event_enable(tu, TP_FLAG_TRACE, NULL);
+                return probe_event_enable(tu, file, NULL);
 
         case TRACE_REG_UNREGISTER:
-                probe_event_disable(tu, TP_FLAG_TRACE);
+                probe_event_disable(tu, file);
                 return 0;
 
 #ifdef CONFIG_PERF_EVENTS
         case TRACE_REG_PERF_REGISTER:
-                return probe_event_enable(tu, TP_FLAG_PROFILE, uprobe_perf_filter);
+                return probe_event_enable(tu, NULL, uprobe_perf_filter);
 
         case TRACE_REG_PERF_UNREGISTER:
-                probe_event_disable(tu, TP_FLAG_PROFILE);
+                probe_event_disable(tu, NULL);
                 return 0;
 
         case TRACE_REG_PERF_OPEN:
@@ -1127,8 +1173,11 @@ static int uprobe_dispatcher(struct uprobe_consumer *con, struct pt_regs *regs)
 {
         struct trace_uprobe *tu;
         struct uprobe_dispatch_data udd;
+        struct uprobe_cpu_buffer *ucb;
+        int dsize, esize;
         int ret = 0;
 
+
         tu = container_of(con, struct trace_uprobe, consumer);
         tu->nhit++;
 
@@ -1137,13 +1186,29 @@ static int uprobe_dispatcher(struct uprobe_consumer *con, struct pt_regs *regs)
 
         current->utask->vaddr = (unsigned long) &udd;
 
+#ifdef CONFIG_PERF_EVENTS
+        if ((tu->tp.flags & TP_FLAG_TRACE) == 0 &&
+            !uprobe_perf_filter(&tu->consumer, 0, current->mm))
+                return UPROBE_HANDLER_REMOVE;
+#endif
+
+        if (WARN_ON_ONCE(!uprobe_cpu_buffer))
+                return 0;
+
+        dsize = __get_data_size(&tu->tp, regs);
+        esize = SIZEOF_TRACE_ENTRY(is_ret_probe(tu));
+
+        ucb = uprobe_buffer_get();
+        store_trace_args(esize, &tu->tp, regs, ucb->buf, dsize);
+
         if (tu->tp.flags & TP_FLAG_TRACE)
-                ret |= uprobe_trace_func(tu, regs);
+                ret |= uprobe_trace_func(tu, regs, ucb, dsize);
 
 #ifdef CONFIG_PERF_EVENTS
         if (tu->tp.flags & TP_FLAG_PROFILE)
-                ret |= uprobe_perf_func(tu, regs);
+                ret |= uprobe_perf_func(tu, regs, ucb, dsize);
 #endif
+        uprobe_buffer_put(ucb);
         return ret;
 }
 
@@ -1152,6 +1217,8 @@ static int uretprobe_dispatcher(struct uprobe_consumer *con,
 {
         struct trace_uprobe *tu;
         struct uprobe_dispatch_data udd;
+        struct uprobe_cpu_buffer *ucb;
+        int dsize, esize;
 
         tu = container_of(con, struct trace_uprobe, consumer);
 
@@ -1160,13 +1227,23 @@ static int uretprobe_dispatcher(struct uprobe_consumer *con,
 
         current->utask->vaddr = (unsigned long) &udd;
 
+        if (WARN_ON_ONCE(!uprobe_cpu_buffer))
+                return 0;
+
+        dsize = __get_data_size(&tu->tp, regs);
+        esize = SIZEOF_TRACE_ENTRY(is_ret_probe(tu));
+
+        ucb = uprobe_buffer_get();
+        store_trace_args(esize, &tu->tp, regs, ucb->buf, dsize);
+
         if (tu->tp.flags & TP_FLAG_TRACE)
-                uretprobe_trace_func(tu, func, regs);
+                uretprobe_trace_func(tu, func, regs, ucb, dsize);
 
 #ifdef CONFIG_PERF_EVENTS
         if (tu->tp.flags & TP_FLAG_PROFILE)
-                uretprobe_perf_func(tu, func, regs);
+                uretprobe_perf_func(tu, func, regs, ucb, dsize);
 #endif
+        uprobe_buffer_put(ucb);
         return 0;
 }
 
diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c
index 031cc5655a51..fb0a38a26555 100644
--- a/kernel/tracepoint.c
+++ b/kernel/tracepoint.c
@@ -62,14 +62,12 @@ struct tracepoint_entry {
         struct hlist_node hlist;
         struct tracepoint_func *funcs;
         int refcount;   /* Number of times armed. 0 if disarmed. */
+        int enabled;    /* Tracepoint enabled */
         char name[0];
 };
 
 struct tp_probes {
-        union {
-                struct rcu_head rcu;
-                struct list_head list;
-        } u;
+        struct rcu_head rcu;
         struct tracepoint_func probes[0];
 };
 
@@ -82,7 +80,7 @@ static inline void *allocate_probes(int count)
 
 static void rcu_free_old_probes(struct rcu_head *head)
 {
-        kfree(container_of(head, struct tp_probes, u.rcu));
+        kfree(container_of(head, struct tp_probes, rcu));
 }
 
 static inline void release_probes(struct tracepoint_func *old)
@@ -90,7 +88,7 @@ static inline void release_probes(struct tracepoint_func *old)
         if (old) {
                 struct tp_probes *tp_probes = container_of(old,
                         struct tp_probes, probes[0]);
-                call_rcu_sched(&tp_probes->u.rcu, rcu_free_old_probes);
+                call_rcu_sched(&tp_probes->rcu, rcu_free_old_probes);
         }
 }
 
@@ -237,6 +235,7 @@ static struct tracepoint_entry *add_tracepoint(const char *name)
         memcpy(&e->name[0], name, name_len);
         e->funcs = NULL;
         e->refcount = 0;
+        e->enabled = 0;
         hlist_add_head(&e->hlist, head);
         return e;
 }
@@ -316,6 +315,7 @@ static void tracepoint_update_probe_range(struct tracepoint * const *begin,
                 if (mark_entry) {
                         set_tracepoint(&mark_entry, *iter,
                                         !!mark_entry->refcount);
+                        mark_entry->enabled = !!mark_entry->refcount;
                 } else {
                         disable_tracepoint(*iter);
                 }
@@ -373,13 +373,26 @@ tracepoint_add_probe(const char *name, void *probe, void *data)
  * tracepoint_probe_register -  Connect a probe to a tracepoint
  * @name: tracepoint name
  * @probe: probe handler
+ * @data: probe private data
+ *
+ * Returns:
+ * - 0 if the probe was successfully registered, and tracepoint
+ *   callsites are currently loaded for that probe,
+ * - -ENODEV if the probe was successfully registered, but no tracepoint
+ *   callsite is currently loaded for that probe,
+ * - other negative error value on error.
+ *
+ * When tracepoint_probe_register() returns either 0 or -ENODEV,
+ * parameters @name, @probe, and @data may be used by the tracepoint
+ * infrastructure until the probe is unregistered.
  *
- * Returns 0 if ok, error value on error.
  * The probe address must at least be aligned on the architecture pointer size.
  */
 int tracepoint_probe_register(const char *name, void *probe, void *data)
 {
         struct tracepoint_func *old;
+        struct tracepoint_entry *entry;
+        int ret = 0;
 
         mutex_lock(&tracepoints_mutex);
         old = tracepoint_add_probe(name, probe, data);
@@ -388,9 +401,13 @@ int tracepoint_probe_register(const char *name, void *probe, void *data)
                 return PTR_ERR(old);
         }
         tracepoint_update_probes();             /* may update entry */
+        entry = get_tracepoint(name);
+        /* Make sure the entry was enabled */
+        if (!entry || !entry->enabled)
+                ret = -ENODEV;
         mutex_unlock(&tracepoints_mutex);
         release_probes(old);
-        return 0;
+        return ret;
 }
 EXPORT_SYMBOL_GPL(tracepoint_probe_register);
 
@@ -415,6 +432,7 @@ tracepoint_remove_probe(const char *name, void *probe, void *data)
  * tracepoint_probe_unregister -  Disconnect a probe from a tracepoint
  * @name: tracepoint name
  * @probe: probe function pointer
+ * @data: probe private data
  *
  * We do not need to call a synchronize_sched to make sure the probes have
  * finished running before doing a module unload, because the module unload
@@ -438,213 +456,26 @@ int tracepoint_probe_unregister(const char *name, void *probe, void *data)
 }
 EXPORT_SYMBOL_GPL(tracepoint_probe_unregister);
 
-static LIST_HEAD(old_probes);
-static int need_update;
-
-static void tracepoint_add_old_probes(void *old)
-{
-        need_update = 1;
-        if (old) {
-                struct tp_probes *tp_probes = container_of(old,
-                        struct tp_probes, probes[0]);
-                list_add(&tp_probes->u.list, &old_probes);
-        }
-}
-
-/**
- * tracepoint_probe_register_noupdate -  register a probe but not connect
- * @name: tracepoint name
- * @probe: probe handler
- *
- * caller must call tracepoint_probe_update_all()
- */
-int tracepoint_probe_register_noupdate(const char *name, void *probe,
-                                       void *data)
-{
-        struct tracepoint_func *old;
-
-        mutex_lock(&tracepoints_mutex);
-        old = tracepoint_add_probe(name, probe, data);
-        if (IS_ERR(old)) {
-                mutex_unlock(&tracepoints_mutex);
-                return PTR_ERR(old);
-        }
-        tracepoint_add_old_probes(old);
-        mutex_unlock(&tracepoints_mutex);
-        return 0;
-}
-EXPORT_SYMBOL_GPL(tracepoint_probe_register_noupdate);
-
-/**
- * tracepoint_probe_unregister_noupdate -  remove a probe but not disconnect
- * @name: tracepoint name
- * @probe: probe function pointer
- *
- * caller must call tracepoint_probe_update_all()
- */
-int tracepoint_probe_unregister_noupdate(const char *name, void *probe,
-                                         void *data)
-{
-        struct tracepoint_func *old;
-
-        mutex_lock(&tracepoints_mutex);
-        old = tracepoint_remove_probe(name, probe, data);
-        if (IS_ERR(old)) {
-                mutex_unlock(&tracepoints_mutex);
-                return PTR_ERR(old);
-        }
-        tracepoint_add_old_probes(old);
-        mutex_unlock(&tracepoints_mutex);
-        return 0;
-}
-EXPORT_SYMBOL_GPL(tracepoint_probe_unregister_noupdate);
-
-/**
- * tracepoint_probe_update_all -  update tracepoints
- */
-void tracepoint_probe_update_all(void)
-{
-        LIST_HEAD(release_probes);
-        struct tp_probes *pos, *next;
-
-        mutex_lock(&tracepoints_mutex);
-        if (!need_update) {
-                mutex_unlock(&tracepoints_mutex);
-                return;
-        }
-        if (!list_empty(&old_probes))
-                list_replace_init(&old_probes, &release_probes);
-        need_update = 0;
-        tracepoint_update_probes();
-        mutex_unlock(&tracepoints_mutex);
-        list_for_each_entry_safe(pos, next, &release_probes, u.list) {
-                list_del(&pos->u.list);
-                call_rcu_sched(&pos->u.rcu, rcu_free_old_probes);
-        }
-}
-EXPORT_SYMBOL_GPL(tracepoint_probe_update_all);
-
-/**
- * tracepoint_get_iter_range - Get a next tracepoint iterator given a range.
- * @tracepoint: current tracepoints (in), next tracepoint (out)
- * @begin: beginning of the range
- * @end: end of the range
- *
- * Returns whether a next tracepoint has been found (1) or not (0).
- * Will return the first tracepoint in the range if the input tracepoint is
- * NULL.
- */
-static int tracepoint_get_iter_range(struct tracepoint * const **tracepoint,
-        struct tracepoint * const *begin, struct tracepoint * const *end)
-{
-        if (!*tracepoint && begin != end) {
-                *tracepoint = begin;
-                return 1;
-        }
-        if (*tracepoint >= begin && *tracepoint < end)
-                return 1;
-        return 0;
-}
-
-#ifdef CONFIG_MODULES
-static void tracepoint_get_iter(struct tracepoint_iter *iter)
-{
-        int found = 0;
-        struct tp_module *iter_mod;
-
-        /* Core kernel tracepoints */
-        if (!iter->module) {
-                found = tracepoint_get_iter_range(&iter->tracepoint,
-                                __start___tracepoints_ptrs,
-                                __stop___tracepoints_ptrs);
-                if (found)
-                        goto end;
-        }
-        /* Tracepoints in modules */
-        mutex_lock(&tracepoints_mutex);
-        list_for_each_entry(iter_mod, &tracepoint_module_list, list) {
-                /*
-                 * Sorted module list
-                 */
-                if (iter_mod < iter->module)
-                        continue;
-                else if (iter_mod > iter->module)
-                        iter->tracepoint = NULL;
-                found = tracepoint_get_iter_range(&iter->tracepoint,
-                        iter_mod->tracepoints_ptrs,
-                        iter_mod->tracepoints_ptrs
-                                + iter_mod->num_tracepoints);
-                if (found) {
-                        iter->module = iter_mod;
-                        break;
-                }
-        }
-        mutex_unlock(&tracepoints_mutex);
-end:
-        if (!found)
-                tracepoint_iter_reset(iter);
-}
-#else /* CONFIG_MODULES */
-static void tracepoint_get_iter(struct tracepoint_iter *iter)
-{
-        int found = 0;
-
-        /* Core kernel tracepoints */
-        found = tracepoint_get_iter_range(&iter->tracepoint,
-                        __start___tracepoints_ptrs,
-                        __stop___tracepoints_ptrs);
-        if (!found)
-                tracepoint_iter_reset(iter);
-}
-#endif /* CONFIG_MODULES */
-
-void tracepoint_iter_start(struct tracepoint_iter *iter)
-{
-        tracepoint_get_iter(iter);
-}
-EXPORT_SYMBOL_GPL(tracepoint_iter_start);
-
-void tracepoint_iter_next(struct tracepoint_iter *iter)
-{
-        iter->tracepoint++;
-        /*
-         * iter->tracepoint may be invalid because we blindly incremented it.
-         * Make sure it is valid by marshalling on the tracepoints, getting the
-         * tracepoints from following modules if necessary.
-         */
-        tracepoint_get_iter(iter);
-}
-EXPORT_SYMBOL_GPL(tracepoint_iter_next);
-
-void tracepoint_iter_stop(struct tracepoint_iter *iter)
-{
-}
-EXPORT_SYMBOL_GPL(tracepoint_iter_stop);
-
-void tracepoint_iter_reset(struct tracepoint_iter *iter)
-{
-#ifdef CONFIG_MODULES
-        iter->module = NULL;
-#endif /* CONFIG_MODULES */
-        iter->tracepoint = NULL;
-}
-EXPORT_SYMBOL_GPL(tracepoint_iter_reset);
 
 #ifdef CONFIG_MODULES
 bool trace_module_has_bad_taint(struct module *mod)
 {
-        return mod->taints & ~((1 << TAINT_OOT_MODULE) | (1 << TAINT_CRAP));
+        return mod->taints & ~((1 << TAINT_OOT_MODULE) | (1 << TAINT_CRAP) |
+                               (1 << TAINT_UNSIGNED_MODULE));
 }
 
 static int tracepoint_module_coming(struct module *mod)
 {
-        struct tp_module *tp_mod, *iter;
+        struct tp_module *tp_mod;
         int ret = 0;
 
+        if (!mod->num_tracepoints)
+                return 0;
+
         /*
          * We skip modules that taint the kernel, especially those with different
          * module headers (for forced load), to make sure we don't cause a crash.
-         * Staging and out-of-tree GPL modules are fine.
+         * Staging, out-of-tree, and unsigned GPL modules are fine.
          */
         if (trace_module_has_bad_taint(mod))
                 return 0;
@@ -656,23 +487,7 @@ static int tracepoint_module_coming(struct module *mod)
         }
         tp_mod->num_tracepoints = mod->num_tracepoints;
         tp_mod->tracepoints_ptrs = mod->tracepoints_ptrs;
-
-        /*
-         * tracepoint_module_list is kept sorted by struct module pointer
-         * address for iteration on tracepoints from a seq_file that can release
-         * the mutex between calls.
-         */
-        list_for_each_entry_reverse(iter, &tracepoint_module_list, list) {
-                BUG_ON(iter == tp_mod); /* Should never be in the list twice */
-                if (iter < tp_mod) {
-                        /* We belong to the location right after iter. */
-                        list_add(&tp_mod->list, &iter->list);
-                        goto module_added;
-                }
-        }
-        /* We belong to the beginning of the list */
-        list_add(&tp_mod->list, &tracepoint_module_list);
-module_added:
+        list_add_tail(&tp_mod->list, &tracepoint_module_list);
         tracepoint_update_probe_range(mod->tracepoints_ptrs,
                 mod->tracepoints_ptrs + mod->num_tracepoints);
 end:
@@ -684,6 +499,9 @@ static int tracepoint_module_going(struct module *mod)
 {
         struct tp_module *pos;
 
+        if (!mod->num_tracepoints)
+                return 0;
+
         mutex_lock(&tracepoints_mutex);
         tracepoint_update_probe_range(mod->tracepoints_ptrs,
                 mod->tracepoints_ptrs + mod->num_tracepoints);
diff --git a/kernel/up.c b/kernel/up.c
index 509403e3fbc6..1760bf3d1463 100644
--- a/kernel/up.c
+++ b/kernel/up.c
@@ -22,16 +22,16 @@ int smp_call_function_single(int cpu, void (*func) (void *info), void *info,
 }
 EXPORT_SYMBOL(smp_call_function_single);
 
-void __smp_call_function_single(int cpu, struct call_single_data *csd,
-                                int wait)
+int smp_call_function_single_async(int cpu, struct call_single_data *csd)
 {
         unsigned long flags;
 
         local_irq_save(flags);
         csd->func(csd->info);
         local_irq_restore(flags);
+        return 0;
 }
-EXPORT_SYMBOL(__smp_call_function_single);
+EXPORT_SYMBOL(smp_call_function_single_async);
 
 int on_each_cpu(smp_call_func_t func, void *info, int wait)
 {
diff --git a/kernel/user.c b/kernel/user.c
index c006131beb77..294fc6a94168 100644
--- a/kernel/user.c
+++ b/kernel/user.c
@@ -222,5 +222,4 @@ static int __init uid_cache_init(void)
 
         return 0;
 }
-
-module_init(uid_cache_init);
+subsys_initcall(uid_cache_init);
diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c
index dd06439b9c84..0d8f6023fd8d 100644
--- a/kernel/user_namespace.c
+++ b/kernel/user_namespace.c
@@ -902,4 +902,4 @@ static __init int user_namespaces_init(void)
         user_ns_cachep = KMEM_CACHE(user_namespace, SLAB_PANIC);
         return 0;
 }
-module_init(user_namespaces_init);
+subsys_initcall(user_namespaces_init);
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 4431610f049a..e90089fd78e0 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -158,14 +158,14 @@ void touch_all_softlockup_watchdogs(void)
 #ifdef CONFIG_HARDLOCKUP_DETECTOR
 void touch_nmi_watchdog(void)
 {
-        if (watchdog_user_enabled) {
-                unsigned cpu;
-
-                for_each_present_cpu(cpu) {
-                        if (per_cpu(watchdog_nmi_touch, cpu) != true)
-                                per_cpu(watchdog_nmi_touch, cpu) = true;
-                }
-        }
+        /*
+         * Using __raw here because some code paths have
+         * preemption enabled.  If preemption is enabled
+         * then interrupts should be enabled too, in which
+         * case we shouldn't have to worry about the watchdog
+         * going off.
+         */
+        __raw_get_cpu_var(watchdog_nmi_touch) = true;
         touch_softlockup_watchdog();
 }
 EXPORT_SYMBOL(touch_nmi_watchdog);
@@ -505,7 +505,6 @@ static void restart_watchdog_hrtimer(void *info)
 
 static void update_timers(int cpu)
 {
-        struct call_single_data data = {.func = restart_watchdog_hrtimer};
         /*
          * Make sure that perf event counter will adopt to a new
          * sampling period. Updating the sampling period directly would
@@ -515,7 +514,7 @@ static void update_timers(int cpu)
          * might be late already so we have to restart the timer as well.
          */
         watchdog_nmi_disable(cpu);
-        __smp_call_function_single(cpu, &data, 1);
+        smp_call_function_single(cpu, restart_watchdog_hrtimer, NULL, 1);
         watchdog_nmi_enable(cpu);
 }
 
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 193e977a10ea..0ee63af30bd1 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -516,6 +516,13 @@ void destroy_work_on_stack(struct work_struct *work)
 }
 EXPORT_SYMBOL_GPL(destroy_work_on_stack);
 
+void destroy_delayed_work_on_stack(struct delayed_work *work)
+{
+        destroy_timer_on_stack(&work->timer);
+        debug_object_free(&work->work, &work_debug_descr);
+}
+EXPORT_SYMBOL_GPL(destroy_delayed_work_on_stack);
+
 #else
 static inline void debug_work_activate(struct work_struct *work) { }
 static inline void debug_work_deactivate(struct work_struct *work) { }
@@ -3225,7 +3232,7 @@ static ssize_t wq_nice_store(struct device *dev, struct device_attribute *attr,
                 return -ENOMEM;
 
         if (sscanf(buf, "%d", &attrs->nice) == 1 &&
-            attrs->nice >= -20 && attrs->nice <= 19)
+            attrs->nice >= MIN_NICE && attrs->nice <= MAX_NICE)
                 ret = apply_workqueue_attrs(wq, attrs);
         else
                 ret = -EINVAL;