Merge commit 'v2.6.28-rc6' into core/debug

114 files changed, 9635 insertions, 4506 deletions

diff --git a/kernel/Kconfig.freezer b/kernel/Kconfig.freezer
new file mode 100644
index 000000000000..a3bb4cb52539
--- /dev/null
+++ b/kernel/Kconfig.freezer
@@ -0,0 +1,2 @@
+config FREEZER
+        def_bool PM_SLEEP || CGROUP_FREEZER
diff --git a/kernel/Makefile b/kernel/Makefile
index 4e1d7df7c3e2..19fad003b19d 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -11,9 +11,7 @@ obj-y     = sched.o fork.o exec_domain.o panic.o printk.o \
             hrtimer.o rwsem.o nsproxy.o srcu.o semaphore.o \
             notifier.o ksysfs.o pm_qos_params.o sched_clock.o
 
-CFLAGS_REMOVE_sched.o = -mno-spe
-
-ifdef CONFIG_FTRACE
+ifdef CONFIG_FUNCTION_TRACER
 # Do not trace debug files and internal ftrace files
 CFLAGS_REMOVE_lockdep.o = -pg
 CFLAGS_REMOVE_lockdep_proc.o = -pg
@@ -21,9 +19,10 @@ CFLAGS_REMOVE_mutex-debug.o = -pg
 CFLAGS_REMOVE_rtmutex-debug.o = -pg
 CFLAGS_REMOVE_cgroup-debug.o = -pg
 CFLAGS_REMOVE_sched_clock.o = -pg
-CFLAGS_REMOVE_sched.o = -mno-spe -pg
+CFLAGS_REMOVE_sched.o = -pg
 endif
 
+obj-$(CONFIG_FREEZER) += freezer.o
 obj-$(CONFIG_PROFILING) += profile.o
 obj-$(CONFIG_SYSCTL_SYSCALL_CHECK) += sysctl_check.o
 obj-$(CONFIG_STACKTRACE) += stacktrace.o
@@ -55,6 +54,7 @@ obj-$(CONFIG_BACKTRACE_SELF_TEST) += backtracetest.o
 obj-$(CONFIG_COMPAT) += compat.o
 obj-$(CONFIG_CGROUPS) += cgroup.o
 obj-$(CONFIG_CGROUP_DEBUG) += cgroup_debug.o
+obj-$(CONFIG_CGROUP_FREEZER) += cgroup_freezer.o
 obj-$(CONFIG_CPUSETS) += cpuset.o
 obj-$(CONFIG_CGROUP_NS) += ns_cgroup.o
 obj-$(CONFIG_UTS_NS) += utsname.o
@@ -83,9 +83,10 @@ obj-$(CONFIG_SYSCTL) += utsname_sysctl.o
 obj-$(CONFIG_TASK_DELAY_ACCT) += delayacct.o
 obj-$(CONFIG_TASKSTATS) += taskstats.o tsacct.o
 obj-$(CONFIG_MARKERS) += marker.o
+obj-$(CONFIG_TRACEPOINTS) += tracepoint.o
 obj-$(CONFIG_LATENCYTOP) += latencytop.o
 obj-$(CONFIG_HAVE_GENERIC_DMA_COHERENT) += dma-coherent.o
-obj-$(CONFIG_FTRACE) += trace/
+obj-$(CONFIG_FUNCTION_TRACER) += trace/
 obj-$(CONFIG_TRACING) += trace/
 obj-$(CONFIG_SMP) += sched_cpupri.o
 
diff --git a/kernel/acct.c b/kernel/acct.c
index dd68b9059418..f6006a60df5d 100644
--- a/kernel/acct.c
+++ b/kernel/acct.c
@@ -548,7 +548,7 @@ static void do_acct_process(struct bsd_acct_struct *acct,
 #endif
 
         spin_lock_irq(&current->sighand->siglock);
-        tty = current->signal->tty;
+        tty = current->signal->tty;     /* Safe as we hold the siglock */
         ac.ac_tty = tty ? old_encode_dev(tty_devnum(tty)) : 0;
         ac.ac_utime = encode_comp_t(jiffies_to_AHZ(cputime_to_jiffies(pacct->ac_utime)));
         ac.ac_stime = encode_comp_t(jiffies_to_AHZ(cputime_to_jiffies(pacct->ac_stime)));
diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c
index f7921a2ecf16..8b509441f49a 100644
--- a/kernel/audit_tree.c
+++ b/kernel/audit_tree.c
@@ -24,6 +24,7 @@ struct audit_chunk {
         struct list_head trees;         /* with root here */
         int dead;
         int count;
+        atomic_long_t refs;
         struct rcu_head head;
         struct node {
                 struct list_head list;
@@ -56,7 +57,8 @@ static LIST_HEAD(prune_list);
  * tree is refcounted; one reference for "some rules on rules_list refer to
  * it", one for each chunk with pointer to it.
  *
- * chunk is refcounted by embedded inotify_watch.
+ * chunk is refcounted by embedded inotify_watch + .refs (non-zero refcount
+ * of watch contributes 1 to .refs).
  *
  * node.index allows to get from node.list to containing chunk.
  * MSB of that sucker is stolen to mark taggings that we might have to
@@ -121,6 +123,7 @@ static struct audit_chunk *alloc_chunk(int count)
         INIT_LIST_HEAD(&chunk->hash);
         INIT_LIST_HEAD(&chunk->trees);
         chunk->count = count;
+        atomic_long_set(&chunk->refs, 1);
         for (i = 0; i < count; i++) {
                 INIT_LIST_HEAD(&chunk->owners[i].list);
                 chunk->owners[i].index = i;
@@ -129,9 +132,8 @@ static struct audit_chunk *alloc_chunk(int count)
         return chunk;
 }
 
-static void __free_chunk(struct rcu_head *rcu)
+static void free_chunk(struct audit_chunk *chunk)
 {
-        struct audit_chunk *chunk = container_of(rcu, struct audit_chunk, head);
         int i;
 
         for (i = 0; i < chunk->count; i++) {
@@ -141,14 +143,16 @@ static void __free_chunk(struct rcu_head *rcu)
         kfree(chunk);
 }
 
-static inline void free_chunk(struct audit_chunk *chunk)
+void audit_put_chunk(struct audit_chunk *chunk)
 {
-        call_rcu(&chunk->head, __free_chunk);
+        if (atomic_long_dec_and_test(&chunk->refs))
+                free_chunk(chunk);
 }
 
-void audit_put_chunk(struct audit_chunk *chunk)
+static void __put_chunk(struct rcu_head *rcu)
 {
-        put_inotify_watch(&chunk->watch);
+        struct audit_chunk *chunk = container_of(rcu, struct audit_chunk, head);
+        audit_put_chunk(chunk);
 }
 
 enum {HASH_SIZE = 128};
@@ -176,7 +180,7 @@ struct audit_chunk *audit_tree_lookup(const struct inode *inode)
 
         list_for_each_entry_rcu(p, list, hash) {
                 if (p->watch.inode == inode) {
-                        get_inotify_watch(&p->watch);
+                        atomic_long_inc(&p->refs);
                         return p;
                 }
         }
@@ -194,17 +198,49 @@ int audit_tree_match(struct audit_chunk *chunk, struct audit_tree *tree)
 
 /* tagging and untagging inodes with trees */
 
-static void untag_chunk(struct audit_chunk *chunk, struct node *p)
+static struct audit_chunk *find_chunk(struct node *p)
+{
+        int index = p->index & ~(1U<<31);
+        p -= index;
+        return container_of(p, struct audit_chunk, owners[0]);
+}
+
+static void untag_chunk(struct node *p)
 {
+        struct audit_chunk *chunk = find_chunk(p);
         struct audit_chunk *new;
         struct audit_tree *owner;
         int size = chunk->count - 1;
         int i, j;
 
+        if (!pin_inotify_watch(&chunk->watch)) {
+                /*
+                 * Filesystem is shutting down; all watches are getting
+                 * evicted, just take it off the node list for this
+                 * tree and let the eviction logics take care of the
+                 * rest.
+                 */
+                owner = p->owner;
+                if (owner->root == chunk) {
+                        list_del_init(&owner->same_root);
+                        owner->root = NULL;
+                }
+                list_del_init(&p->list);
+                p->owner = NULL;
+                put_tree(owner);
+                return;
+        }
+
+        spin_unlock(&hash_lock);
+
+        /*
+         * pin_inotify_watch() succeeded, so the watch won't go away
+         * from under us.
+         */
         mutex_lock(&chunk->watch.inode->inotify_mutex);
         if (chunk->dead) {
                 mutex_unlock(&chunk->watch.inode->inotify_mutex);
-                return;
+                goto out;
         }
 
         owner = p->owner;
@@ -221,7 +257,7 @@ static void untag_chunk(struct audit_chunk *chunk, struct node *p)
                 inotify_evict_watch(&chunk->watch);
                 mutex_unlock(&chunk->watch.inode->inotify_mutex);
                 put_inotify_watch(&chunk->watch);
-                return;
+                goto out;
         }
 
         new = alloc_chunk(size);
@@ -263,7 +299,7 @@ static void untag_chunk(struct audit_chunk *chunk, struct node *p)
         inotify_evict_watch(&chunk->watch);
         mutex_unlock(&chunk->watch.inode->inotify_mutex);
         put_inotify_watch(&chunk->watch);
-        return;
+        goto out;
 
 Fallback:
         // do the best we can
@@ -277,6 +313,9 @@ Fallback:
         put_tree(owner);
         spin_unlock(&hash_lock);
         mutex_unlock(&chunk->watch.inode->inotify_mutex);
+out:
+        unpin_inotify_watch(&chunk->watch);
+        spin_lock(&hash_lock);
 }
 
 static int create_chunk(struct inode *inode, struct audit_tree *tree)
@@ -387,13 +426,6 @@ static int tag_chunk(struct inode *inode, struct audit_tree *tree)
         return 0;
 }
 
-static struct audit_chunk *find_chunk(struct node *p)
-{
-        int index = p->index & ~(1U<<31);
-        p -= index;
-        return container_of(p, struct audit_chunk, owners[0]);
-}
-
 static void kill_rules(struct audit_tree *tree)
 {
         struct audit_krule *rule, *next;
@@ -431,17 +463,10 @@ static void prune_one(struct audit_tree *victim)
         spin_lock(&hash_lock);
         while (!list_empty(&victim->chunks)) {
                 struct node *p;
-                struct audit_chunk *chunk;
 
                 p = list_entry(victim->chunks.next, struct node, list);
-                chunk = find_chunk(p);
-                get_inotify_watch(&chunk->watch);
-                spin_unlock(&hash_lock);
-
-                untag_chunk(chunk, p);
 
-                put_inotify_watch(&chunk->watch);
-                spin_lock(&hash_lock);
+                untag_chunk(p);
         }
         spin_unlock(&hash_lock);
         put_tree(victim);
@@ -469,7 +494,6 @@ static void trim_marked(struct audit_tree *tree)
 
         while (!list_empty(&tree->chunks)) {
                 struct node *node;
-                struct audit_chunk *chunk;
 
                 node = list_entry(tree->chunks.next, struct node, list);
 
@@ -477,14 +501,7 @@ static void trim_marked(struct audit_tree *tree)
                 if (!(node->index & (1U<<31)))
                         break;
 
-                chunk = find_chunk(node);
-                get_inotify_watch(&chunk->watch);
-                spin_unlock(&hash_lock);
-
-                untag_chunk(chunk, node);
-
-                put_inotify_watch(&chunk->watch);
-                spin_lock(&hash_lock);
+                untag_chunk(node);
         }
         if (!tree->root && !tree->goner) {
                 tree->goner = 1;
@@ -532,7 +549,7 @@ void audit_trim_trees(void)
         list_add(&cursor, &tree_list);
         while (cursor.next != &tree_list) {
                 struct audit_tree *tree;
-                struct nameidata nd;
+                struct path path;
                 struct vfsmount *root_mnt;
                 struct node *node;
                 struct list_head list;
@@ -544,12 +561,12 @@ void audit_trim_trees(void)
                 list_add(&cursor, &tree->list);
                 mutex_unlock(&audit_filter_mutex);
 
-                err = path_lookup(tree->pathname, 0, &nd);
+                err = kern_path(tree->pathname, 0, &path);
                 if (err)
                         goto skip_it;
 
-                root_mnt = collect_mounts(nd.path.mnt, nd.path.dentry);
-                path_put(&nd.path);
+                root_mnt = collect_mounts(path.mnt, path.dentry);
+                path_put(&path);
                 if (!root_mnt)
                         goto skip_it;
 
@@ -580,19 +597,19 @@ skip_it:
 }
 
 static int is_under(struct vfsmount *mnt, struct dentry *dentry,
-                    struct nameidata *nd)
+                    struct path *path)
 {
-        if (mnt != nd->path.mnt) {
+        if (mnt != path->mnt) {
                 for (;;) {
                         if (mnt->mnt_parent == mnt)
                                 return 0;
-                        if (mnt->mnt_parent == nd->path.mnt)
+                        if (mnt->mnt_parent == path->mnt)
                                         break;
                         mnt = mnt->mnt_parent;
                 }
                 dentry = mnt->mnt_mountpoint;
         }
-        return is_subdir(dentry, nd->path.dentry);
+        return is_subdir(dentry, path->dentry);
 }
 
 int audit_make_tree(struct audit_krule *rule, char *pathname, u32 op)
@@ -618,7 +635,7 @@ void audit_put_tree(struct audit_tree *tree)
 int audit_add_tree_rule(struct audit_krule *rule)
 {
         struct audit_tree *seed = rule->tree, *tree;
-        struct nameidata nd;
+        struct path path;
         struct vfsmount *mnt, *p;
         struct list_head list;
         int err;
@@ -637,11 +654,11 @@ int audit_add_tree_rule(struct audit_krule *rule)
         /* do not set rule->tree yet */
         mutex_unlock(&audit_filter_mutex);
 
-        err = path_lookup(tree->pathname, 0, &nd);
+        err = kern_path(tree->pathname, 0, &path);
         if (err)
                 goto Err;
-        mnt = collect_mounts(nd.path.mnt, nd.path.dentry);
-        path_put(&nd.path);
+        mnt = collect_mounts(path.mnt, path.dentry);
+        path_put(&path);
         if (!mnt) {
                 err = -ENOMEM;
                 goto Err;
@@ -690,29 +707,29 @@ int audit_tag_tree(char *old, char *new)
 {
         struct list_head cursor, barrier;
         int failed = 0;
-        struct nameidata nd;
+        struct path path;
         struct vfsmount *tagged;
         struct list_head list;
         struct vfsmount *mnt;
         struct dentry *dentry;
         int err;
 
-        err = path_lookup(new, 0, &nd);
+        err = kern_path(new, 0, &path);
         if (err)
                 return err;
-        tagged = collect_mounts(nd.path.mnt, nd.path.dentry);
-        path_put(&nd.path);
+        tagged = collect_mounts(path.mnt, path.dentry);
+        path_put(&path);
         if (!tagged)
                 return -ENOMEM;
 
-        err = path_lookup(old, 0, &nd);
+        err = kern_path(old, 0, &path);
         if (err) {
                 drop_collected_mounts(tagged);
                 return err;
         }
-        mnt = mntget(nd.path.mnt);
-        dentry = dget(nd.path.dentry);
-        path_put(&nd.path);
+        mnt = mntget(path.mnt);
+        dentry = dget(path.dentry);
+        path_put(&path);
 
         if (dentry == tagged->mnt_root && dentry == mnt->mnt_root)
                 follow_up(&mnt, &dentry);
@@ -733,7 +750,7 @@ int audit_tag_tree(char *old, char *new)
                 list_add(&cursor, &tree->list);
                 mutex_unlock(&audit_filter_mutex);
 
-                err = path_lookup(tree->pathname, 0, &nd);
+                err = kern_path(tree->pathname, 0, &path);
                 if (err) {
                         put_tree(tree);
                         mutex_lock(&audit_filter_mutex);
@@ -741,15 +758,15 @@ int audit_tag_tree(char *old, char *new)
                 }
 
                 spin_lock(&vfsmount_lock);
-                if (!is_under(mnt, dentry, &nd)) {
+                if (!is_under(mnt, dentry, &path)) {
                         spin_unlock(&vfsmount_lock);
-                        path_put(&nd.path);
+                        path_put(&path);
                         put_tree(tree);
                         mutex_lock(&audit_filter_mutex);
                         continue;
                 }
                 spin_unlock(&vfsmount_lock);
-                path_put(&nd.path);
+                path_put(&path);
 
                 list_for_each_entry(p, &list, mnt_list) {
                         failed = tag_chunk(p->mnt_root->d_inode, tree);
@@ -878,7 +895,7 @@ static void handle_event(struct inotify_watch *watch, u32 wd, u32 mask,
 static void destroy_watch(struct inotify_watch *watch)
 {
         struct audit_chunk *chunk = container_of(watch, struct audit_chunk, watch);
-        free_chunk(chunk);
+        call_rcu(&chunk->head, __put_chunk);
 }
 
 static const struct inotify_operations rtree_inotify_ops = {
diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c
index b7d354e2b0ef..9fd85a4640a0 100644
--- a/kernel/auditfilter.c
+++ b/kernel/auditfilter.c
@@ -1094,8 +1094,8 @@ static void audit_inotify_unregister(struct list_head *in_list)
         list_for_each_entry_safe(p, n, in_list, ilist) {
                 list_del(&p->ilist);
                 inotify_rm_watch(audit_ih, &p->wdata);
-                /* the put matching the get in audit_do_del_rule() */
-                put_inotify_watch(&p->wdata);
+                /* the unpin matching the pin in audit_do_del_rule() */
+                unpin_inotify_watch(&p->wdata);
         }
 }
 
@@ -1389,9 +1389,13 @@ static inline int audit_del_rule(struct audit_entry *entry,
                                 /* Put parent on the inotify un-registration
                                  * list.  Grab a reference before releasing
                                  * audit_filter_mutex, to be released in
-                                 * audit_inotify_unregister(). */
-                                list_add(&parent->ilist, &inotify_list);
-                                get_inotify_watch(&parent->wdata);
+                                 * audit_inotify_unregister().
+                                 * If filesystem is going away, just leave
+                                 * the sucker alone, eviction will take
+                                 * care of it.
+                                 */
+                                if (pin_inotify_watch(&parent->wdata))
+                                        list_add(&parent->ilist, &inotify_list);
                         }
                 }
         }
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index 59cedfb040e7..cf5bc2f5f9c3 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -246,8 +246,8 @@ static int audit_match_perm(struct audit_context *ctx, int mask)
         unsigned n;
         if (unlikely(!ctx))
                 return 0;
-
         n = ctx->major;
+
         switch (audit_classify_syscall(ctx->arch, n)) {
         case 0: /* native */
                 if ((mask & AUDIT_PERM_WRITE) &&
@@ -1204,13 +1204,13 @@ static void audit_log_exit(struct audit_context *context, struct task_struct *ts
                                  (context->return_valid==AUDITSC_SUCCESS)?"yes":"no",
                                  context->return_code);
 
-        mutex_lock(&tty_mutex);
-        read_lock(&tasklist_lock);
+        spin_lock_irq(&tsk->sighand->siglock);
         if (tsk->signal && tsk->signal->tty && tsk->signal->tty->name)
                 tty = tsk->signal->tty->name;
         else
                 tty = "(none)";
-        read_unlock(&tasklist_lock);
+        spin_unlock_irq(&tsk->sighand->siglock);
+
         audit_log_format(ab,
                   " a0=%lx a1=%lx a2=%lx a3=%lx items=%d"
                   " ppid=%d pid=%d auid=%u uid=%u gid=%u"
@@ -1230,7 +1230,6 @@ static void audit_log_exit(struct audit_context *context, struct task_struct *ts
                   context->egid, context->sgid, context->fsgid, tty,
                   tsk->sessionid);
 
-        mutex_unlock(&tty_mutex);
 
         audit_log_task_info(ab, tsk);
         if (context->filterkey) {
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 13932abde159..fe00b3b983a8 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -241,7 +241,6 @@ static void unlink_css_set(struct css_set *cg)
         struct cg_cgroup_link *link;
         struct cg_cgroup_link *saved_link;
 
-        write_lock(&css_set_lock);
         hlist_del(&cg->hlist);
         css_set_count--;
 
@@ -251,16 +250,25 @@ static void unlink_css_set(struct css_set *cg)
                 list_del(&link->cgrp_link_list);
                 kfree(link);
         }
-
-        write_unlock(&css_set_lock);
 }
 
-static void __release_css_set(struct kref *k, int taskexit)
+static void __put_css_set(struct css_set *cg, int taskexit)
 {
         int i;
-        struct css_set *cg = container_of(k, struct css_set, ref);
-
+        /*
+         * 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(&cg->refcount, -1, 1))
+                return;
+        write_lock(&css_set_lock);
+        if (!atomic_dec_and_test(&cg->refcount)) {
+                write_unlock(&css_set_lock);
+                return;
+        }
         unlink_css_set(cg);
+        write_unlock(&css_set_lock);
 
         rcu_read_lock();
         for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
@@ -276,32 +284,22 @@ static void __release_css_set(struct kref *k, int taskexit)
         kfree(cg);
 }
 
-static void release_css_set(struct kref *k)
-{
-        __release_css_set(k, 0);
-}
-
-static void release_css_set_taskexit(struct kref *k)
-{
-        __release_css_set(k, 1);
-}
-
 /*
  * refcounted get/put for css_set objects
  */
 static inline void get_css_set(struct css_set *cg)
 {
-        kref_get(&cg->ref);
+        atomic_inc(&cg->refcount);
 }
 
 static inline void put_css_set(struct css_set *cg)
 {
-        kref_put(&cg->ref, release_css_set);
+        __put_css_set(cg, 0);
 }
 
 static inline void put_css_set_taskexit(struct css_set *cg)
 {
-        kref_put(&cg->ref, release_css_set_taskexit);
+        __put_css_set(cg, 1);
 }
 
 /*
@@ -427,7 +425,7 @@ static struct css_set *find_css_set(
                 return NULL;
         }
 
-        kref_init(&res->ref);
+        atomic_set(&res->refcount, 1);
         INIT_LIST_HEAD(&res->cg_links);
         INIT_LIST_HEAD(&res->tasks);
         INIT_HLIST_NODE(&res->hlist);
@@ -870,6 +868,14 @@ static struct super_operations cgroup_ops = {
         .remount_fs = cgroup_remount,
 };
 
+static void init_cgroup_housekeeping(struct cgroup *cgrp)
+{
+        INIT_LIST_HEAD(&cgrp->sibling);
+        INIT_LIST_HEAD(&cgrp->children);
+        INIT_LIST_HEAD(&cgrp->css_sets);
+        INIT_LIST_HEAD(&cgrp->release_list);
+        init_rwsem(&cgrp->pids_mutex);
+}
 static void init_cgroup_root(struct cgroupfs_root *root)
 {
         struct cgroup *cgrp = &root->top_cgroup;
@@ -878,10 +884,7 @@ static void init_cgroup_root(struct cgroupfs_root *root)
         root->number_of_cgroups = 1;
         cgrp->root = root;
         cgrp->top_cgroup = cgrp;
-        INIT_LIST_HEAD(&cgrp->sibling);
-        INIT_LIST_HEAD(&cgrp->children);
-        INIT_LIST_HEAD(&cgrp->css_sets);
-        INIT_LIST_HEAD(&cgrp->release_list);
+        init_cgroup_housekeeping(cgrp);
 }
 
 static int cgroup_test_super(struct super_block *sb, void *data)
@@ -1728,7 +1731,7 @@ int cgroup_task_count(const struct cgroup *cgrp)
 
         read_lock(&css_set_lock);
         list_for_each_entry(link, &cgrp->css_sets, cgrp_link_list) {
-                count += atomic_read(&link->cg->ref.refcount);
+                count += atomic_read(&link->cg->refcount);
         }
         read_unlock(&css_set_lock);
         return count;
@@ -1997,16 +2000,7 @@ int cgroup_scan_tasks(struct cgroup_scanner *scan)
  * but we cannot guarantee that the information we produce is correct
  * unless we produce it entirely atomically.
  *
- * Upon tasks file open(), a struct ctr_struct is allocated, that
- * will have a pointer to an array (also allocated here).  The struct
- * ctr_struct * is stored in file->private_data.  Its resources will
- * be freed by release() when the file is closed.  The array is used
- * to sprintf the PIDs and then used by read().
  */
-struct ctr_struct {
-        char *buf;
-        int bufsz;
-};
 
 /*
  * Load into 'pidarray' up to 'npids' of the tasks using cgroup
@@ -2045,10 +2039,13 @@ int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry)
         struct cgroup *cgrp;
         struct cgroup_iter it;
         struct task_struct *tsk;
+
         /*
-         * Validate dentry by checking the superblock operations
+         * Validate dentry by checking the superblock operations,
+         * and make sure it's a directory.
          */
-        if (dentry->d_sb->s_op != &cgroup_ops)
+        if (dentry->d_sb->s_op != &cgroup_ops ||
+            !S_ISDIR(dentry->d_inode->i_mode))
                  goto err;
 
         ret = 0;
@@ -2088,42 +2085,132 @@ static int cmppid(const void *a, const void *b)
         return *(pid_t *)a - *(pid_t *)b;
 }
 
+
 /*
- * Convert array 'a' of 'npids' pid_t's to a string of newline separated
- * decimal pids in 'buf'.  Don't write more than 'sz' chars, but return
- * count 'cnt' of how many chars would be written if buf were large enough.
+ * seq_file methods for the "tasks" file. The seq_file position is the
+ * next pid to display; the seq_file iterator is a pointer to the pid
+ * in the cgroup->tasks_pids array.
  */
-static int pid_array_to_buf(char *buf, int sz, pid_t *a, int npids)
+
+static void *cgroup_tasks_start(struct seq_file *s, loff_t *pos)
 {
-        int cnt = 0;
-        int i;
+        /*
+         * Initially we receive a position value that corresponds to
+         * one more than the last pid shown (or 0 on the first call or
+         * after a seek to the start). Use a binary-search to find the
+         * next pid to display, if any
+         */
+        struct cgroup *cgrp = s->private;
+        int index = 0, pid = *pos;
+        int *iter;
+
+        down_read(&cgrp->pids_mutex);
+        if (pid) {
+                int end = cgrp->pids_length;
+
+                while (index < end) {
+                        int mid = (index + end) / 2;
+                        if (cgrp->tasks_pids[mid] == pid) {
+                                index = mid;
+                                break;
+                        } else if (cgrp->tasks_pids[mid] <= pid)
+                                index = mid + 1;
+                        else
+                                end = mid;
+                }
+        }
+        /* If we're off the end of the array, we're done */
+        if (index >= cgrp->pids_length)
+                return NULL;
+        /* Update the abstract position to be the actual pid that we found */
+        iter = cgrp->tasks_pids + index;
+        *pos = *iter;
+        return iter;
+}
 
-        for (i = 0; i < npids; i++)
-                cnt += snprintf(buf + cnt, max(sz - cnt, 0), "%d\n", a[i]);
-        return cnt;
+static void cgroup_tasks_stop(struct seq_file *s, void *v)
+{
+        struct cgroup *cgrp = s->private;
+        up_read(&cgrp->pids_mutex);
 }
 
+static void *cgroup_tasks_next(struct seq_file *s, void *v, loff_t *pos)
+{
+        struct cgroup *cgrp = s->private;
+        int *p = v;
+        int *end = cgrp->tasks_pids + cgrp->pids_length;
+
+        /*
+         * Advance to the next pid in the array. If this goes off the
+         * end, we're done
+         */
+        p++;
+        if (p >= end) {
+                return NULL;
+        } else {
+                *pos = *p;
+                return p;
+        }
+}
+
+static int cgroup_tasks_show(struct seq_file *s, void *v)
+{
+        return seq_printf(s, "%d\n", *(int *)v);
+}
+
+static struct seq_operations cgroup_tasks_seq_operations = {
+        .start = cgroup_tasks_start,
+        .stop = cgroup_tasks_stop,
+        .next = cgroup_tasks_next,
+        .show = cgroup_tasks_show,
+};
+
+static void release_cgroup_pid_array(struct cgroup *cgrp)
+{
+        down_write(&cgrp->pids_mutex);
+        BUG_ON(!cgrp->pids_use_count);
+        if (!--cgrp->pids_use_count) {
+                kfree(cgrp->tasks_pids);
+                cgrp->tasks_pids = NULL;
+                cgrp->pids_length = 0;
+        }
+        up_write(&cgrp->pids_mutex);
+}
+
+static int cgroup_tasks_release(struct inode *inode, struct file *file)
+{
+        struct cgroup *cgrp = __d_cgrp(file->f_dentry->d_parent);
+
+        if (!(file->f_mode & FMODE_READ))
+                return 0;
+
+        release_cgroup_pid_array(cgrp);
+        return seq_release(inode, file);
+}
+
+static struct file_operations cgroup_tasks_operations = {
+        .read = seq_read,
+        .llseek = seq_lseek,
+        .write = cgroup_file_write,
+        .release = cgroup_tasks_release,
+};
+
 /*
- * Handle an open on 'tasks' file.  Prepare a buffer listing the
+ * Handle an open on 'tasks' file.  Prepare an array containing the
  * process id's of tasks currently attached to the cgroup being opened.
- *
- * Does not require any specific cgroup mutexes, and does not take any.
  */
+
 static int cgroup_tasks_open(struct inode *unused, struct file *file)
 {
         struct cgroup *cgrp = __d_cgrp(file->f_dentry->d_parent);
-        struct ctr_struct *ctr;
         pid_t *pidarray;
         int npids;
-        char c;
+        int retval;
 
+        /* Nothing to do for write-only files */
         if (!(file->f_mode & FMODE_READ))
                 return 0;
 
-        ctr = kmalloc(sizeof(*ctr), GFP_KERNEL);
-        if (!ctr)
-                goto err0;
-
         /*
          * If cgroup gets more users after we read count, we won't have
          * enough space - tough.  This race is indistinguishable to the
@@ -2131,57 +2218,31 @@ static int cgroup_tasks_open(struct inode *unused, struct file *file)
          * show up until sometime later on.
          */
         npids = cgroup_task_count(cgrp);
-        if (npids) {
-                pidarray = kmalloc(npids * sizeof(pid_t), GFP_KERNEL);
-                if (!pidarray)
-                        goto err1;
-
-                npids = pid_array_load(pidarray, npids, cgrp);
-                sort(pidarray, npids, sizeof(pid_t), cmppid, NULL);
-
-                /* Call pid_array_to_buf() twice, first just to get bufsz */
-                ctr->bufsz = pid_array_to_buf(&c, sizeof(c), pidarray, npids) + 1;
-                ctr->buf = kmalloc(ctr->bufsz, GFP_KERNEL);
-                if (!ctr->buf)
-                        goto err2;
-                ctr->bufsz = pid_array_to_buf(ctr->buf, ctr->bufsz, pidarray, npids);
-
-                kfree(pidarray);
-        } else {
-                ctr->buf = NULL;
-                ctr->bufsz = 0;
-        }
-        file->private_data = ctr;
-        return 0;
-
-err2:
-        kfree(pidarray);
-err1:
-        kfree(ctr);
-err0:
-        return -ENOMEM;
-}
-
-static ssize_t cgroup_tasks_read(struct cgroup *cgrp,
-                                    struct cftype *cft,
-                                    struct file *file, char __user *buf,
-                                    size_t nbytes, loff_t *ppos)
-{
-        struct ctr_struct *ctr = file->private_data;
+        pidarray = kmalloc(npids * sizeof(pid_t), GFP_KERNEL);
+        if (!pidarray)
+                return -ENOMEM;
+        npids = pid_array_load(pidarray, npids, cgrp);
+        sort(pidarray, npids, sizeof(pid_t), cmppid, NULL);
 
-        return simple_read_from_buffer(buf, nbytes, ppos, ctr->buf, ctr->bufsz);
-}
+        /*
+         * Store the array in the cgroup, freeing the old
+         * array if necessary
+         */
+        down_write(&cgrp->pids_mutex);
+        kfree(cgrp->tasks_pids);
+        cgrp->tasks_pids = pidarray;
+        cgrp->pids_length = npids;
+        cgrp->pids_use_count++;
+        up_write(&cgrp->pids_mutex);
 
-static int cgroup_tasks_release(struct inode *unused_inode,
-                                        struct file *file)
-{
-        struct ctr_struct *ctr;
+        file->f_op = &cgroup_tasks_operations;
 
-        if (file->f_mode & FMODE_READ) {
-                ctr = file->private_data;
-                kfree(ctr->buf);
-                kfree(ctr);
+        retval = seq_open(file, &cgroup_tasks_seq_operations);
+        if (retval) {
+                release_cgroup_pid_array(cgrp);
+                return retval;
         }
+        ((struct seq_file *)file->private_data)->private = cgrp;
         return 0;
 }
 
@@ -2210,7 +2271,6 @@ static struct cftype files[] = {
         {
                 .name = "tasks",
                 .open = cgroup_tasks_open,
-                .read = cgroup_tasks_read,
                 .write_u64 = cgroup_tasks_write,
                 .release = cgroup_tasks_release,
                 .private = FILE_TASKLIST,
@@ -2300,10 +2360,7 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
 
         mutex_lock(&cgroup_mutex);
 
-        INIT_LIST_HEAD(&cgrp->sibling);
-        INIT_LIST_HEAD(&cgrp->children);
-        INIT_LIST_HEAD(&cgrp->css_sets);
-        INIT_LIST_HEAD(&cgrp->release_list);
+        init_cgroup_housekeeping(cgrp);
 
         cgrp->parent = parent;
         cgrp->root = parent->root;
@@ -2418,10 +2475,7 @@ static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry)
                 mutex_unlock(&cgroup_mutex);
                 return -EBUSY;
         }
-
-        parent = cgrp->parent;
-        root = cgrp->root;
-        sb = root->sb;
+        mutex_unlock(&cgroup_mutex);
 
         /*
          * Call pre_destroy handlers of subsys. Notify subsystems
@@ -2429,7 +2483,14 @@ static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry)
          */
         cgroup_call_pre_destroy(cgrp);
 
-        if (cgroup_has_css_refs(cgrp)) {
+        mutex_lock(&cgroup_mutex);
+        parent = cgrp->parent;
+        root = cgrp->root;
+        sb = root->sb;
+
+        if (atomic_read(&cgrp->count)
+            || !list_empty(&cgrp->children)
+            || cgroup_has_css_refs(cgrp)) {
                 mutex_unlock(&cgroup_mutex);
                 return -EBUSY;
         }
@@ -2443,7 +2504,6 @@ static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry)
         list_del(&cgrp->sibling);
         spin_lock(&cgrp->dentry->d_lock);
         d = dget(cgrp->dentry);
-        cgrp->dentry = NULL;
         spin_unlock(&d->d_lock);
 
         cgroup_d_remove_dir(d);
@@ -2495,8 +2555,7 @@ static void __init cgroup_init_subsys(struct cgroup_subsys *ss)
 int __init cgroup_init_early(void)
 {
         int i;
-        kref_init(&init_css_set.ref);
-        kref_get(&init_css_set.ref);
+        atomic_set(&init_css_set.refcount, 1);
         INIT_LIST_HEAD(&init_css_set.cg_links);
         INIT_LIST_HEAD(&init_css_set.tasks);
         INIT_HLIST_NODE(&init_css_set.hlist);
@@ -2735,21 +2794,24 @@ void cgroup_fork_callbacks(struct task_struct *child)
  * Called on every change to mm->owner. mm_init_owner() does not
  * invoke this routine, since it assigns the mm->owner the first time
  * and does not change it.
+ *
+ * The callbacks are invoked with mmap_sem held in read mode.
  */
 void cgroup_mm_owner_callbacks(struct task_struct *old, struct task_struct *new)
 {
-        struct cgroup *oldcgrp, *newcgrp;
+        struct cgroup *oldcgrp, *newcgrp = NULL;
 
         if (need_mm_owner_callback) {
                 int i;
                 for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
                         struct cgroup_subsys *ss = subsys[i];
                         oldcgrp = task_cgroup(old, ss->subsys_id);
-                        newcgrp = task_cgroup(new, ss->subsys_id);
+                        if (new)
+                                newcgrp = task_cgroup(new, ss->subsys_id);
                         if (oldcgrp == newcgrp)
                                 continue;
                         if (ss->mm_owner_changed)
-                                ss->mm_owner_changed(ss, oldcgrp, newcgrp);
+                                ss->mm_owner_changed(ss, oldcgrp, newcgrp, new);
                 }
         }
 }
diff --git a/kernel/cgroup_debug.c b/kernel/cgroup_debug.c
index c3dc3aba4c02..daca6209202d 100644
--- a/kernel/cgroup_debug.c
+++ b/kernel/cgroup_debug.c
@@ -57,7 +57,7 @@ static u64 current_css_set_refcount_read(struct cgroup *cont,
         u64 count;
 
         rcu_read_lock();
-        count = atomic_read(&current->cgroups->ref.refcount);
+        count = atomic_read(&current->cgroups->refcount);
         rcu_read_unlock();
         return count;
 }
@@ -90,7 +90,7 @@ static struct cftype files[] =  {
         {
                 .name = "releasable",
                 .read_u64 = releasable_read,
-        }
+        },
 };
 
 static int debug_populate(struct cgroup_subsys *ss, struct cgroup *cont)
diff --git a/kernel/cgroup_freezer.c b/kernel/cgroup_freezer.c
new file mode 100644
index 000000000000..fb249e2bcada
--- /dev/null
+++ b/kernel/cgroup_freezer.c
@@ -0,0 +1,379 @@
+/*
+ * cgroup_freezer.c -  control group freezer subsystem
+ *
+ * Copyright IBM Corporation, 2007
+ *
+ * Author : Cedric Le Goater <clg@fr.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of version 2.1 of the GNU Lesser General Public License
+ * as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it would be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+ */
+
+#include <linux/module.h>
+#include <linux/cgroup.h>
+#include <linux/fs.h>
+#include <linux/uaccess.h>
+#include <linux/freezer.h>
+#include <linux/seq_file.h>
+
+enum freezer_state {
+        CGROUP_THAWED = 0,
+        CGROUP_FREEZING,
+        CGROUP_FROZEN,
+};
+
+struct freezer {
+        struct cgroup_subsys_state css;
+        enum freezer_state state;
+        spinlock_t lock; /* protects _writes_ to state */
+};
+
+static inline struct freezer *cgroup_freezer(
+                struct cgroup *cgroup)
+{
+        return container_of(
+                cgroup_subsys_state(cgroup, freezer_subsys_id),
+                struct freezer, css);
+}
+
+static inline struct freezer *task_freezer(struct task_struct *task)
+{
+        return container_of(task_subsys_state(task, freezer_subsys_id),
+                            struct freezer, css);
+}
+
+int cgroup_frozen(struct task_struct *task)
+{
+        struct freezer *freezer;
+        enum freezer_state state;
+
+        task_lock(task);
+        freezer = task_freezer(task);
+        state = freezer->state;
+        task_unlock(task);
+
+        return state == CGROUP_FROZEN;
+}
+
+/*
+ * cgroups_write_string() limits the size of freezer state strings to
+ * CGROUP_LOCAL_BUFFER_SIZE
+ */
+static const char *freezer_state_strs[] = {
+        "THAWED",
+        "FREEZING",
+        "FROZEN",
+};
+
+/*
+ * State diagram
+ * Transitions are caused by userspace writes to the freezer.state file.
+ * The values in parenthesis are state labels. The rest are edge labels.
+ *
+ * (THAWED) --FROZEN--> (FREEZING) --FROZEN--> (FROZEN)
+ *    ^ ^                    |                     |
+ *    | \_______THAWED_______/                     |
+ *    \__________________________THAWED____________/
+ */
+
+struct cgroup_subsys freezer_subsys;
+
+/* Locks taken and their ordering
+ * ------------------------------
+ * css_set_lock
+ * cgroup_mutex (AKA cgroup_lock)
+ * task->alloc_lock (AKA task_lock)
+ * freezer->lock
+ * task->sighand->siglock
+ *
+ * cgroup code forces css_set_lock to be taken before task->alloc_lock
+ *
+ * freezer_create(), freezer_destroy():
+ * cgroup_mutex [ by cgroup core ]
+ *
+ * can_attach():
+ * cgroup_mutex
+ *
+ * cgroup_frozen():
+ * task->alloc_lock (to get task's cgroup)
+ *
+ * freezer_fork() (preserving fork() performance means can't take cgroup_mutex):
+ * task->alloc_lock (to get task's cgroup)
+ * freezer->lock
+ *  sighand->siglock (if the cgroup is freezing)
+ *
+ * freezer_read():
+ * cgroup_mutex
+ *  freezer->lock
+ *   read_lock css_set_lock (cgroup iterator start)
+ *
+ * freezer_write() (freeze):
+ * cgroup_mutex
+ *  freezer->lock
+ *   read_lock css_set_lock (cgroup iterator start)
+ *    sighand->siglock
+ *
+ * freezer_write() (unfreeze):
+ * cgroup_mutex
+ *  freezer->lock
+ *   read_lock css_set_lock (cgroup iterator start)
+ *    task->alloc_lock (to prevent races with freeze_task())
+ *     sighand->siglock
+ */
+static struct cgroup_subsys_state *freezer_create(struct cgroup_subsys *ss,
+                                                  struct cgroup *cgroup)
+{
+        struct freezer *freezer;
+
+        freezer = kzalloc(sizeof(struct freezer), GFP_KERNEL);
+        if (!freezer)
+                return ERR_PTR(-ENOMEM);
+
+        spin_lock_init(&freezer->lock);
+        freezer->state = CGROUP_THAWED;
+        return &freezer->css;
+}
+
+static void freezer_destroy(struct cgroup_subsys *ss,
+                            struct cgroup *cgroup)
+{
+        kfree(cgroup_freezer(cgroup));
+}
+
+/* Task is frozen or will freeze immediately when next it gets woken */
+static bool is_task_frozen_enough(struct task_struct *task)
+{
+        return frozen(task) ||
+                (task_is_stopped_or_traced(task) && freezing(task));
+}
+
+/*
+ * The call to cgroup_lock() in the freezer.state write method prevents
+ * a write to that file racing against an attach, and hence the
+ * can_attach() result will remain valid until the attach completes.
+ */
+static int freezer_can_attach(struct cgroup_subsys *ss,
+                              struct cgroup *new_cgroup,
+                              struct task_struct *task)
+{
+        struct freezer *freezer;
+
+        /*
+         * Anything frozen can't move or be moved to/from.
+         *
+         * Since orig_freezer->state == FROZEN means that @task has been
+         * frozen, so it's sufficient to check the latter condition.
+         */
+
+        if (is_task_frozen_enough(task))
+                return -EBUSY;
+
+        freezer = cgroup_freezer(new_cgroup);
+        if (freezer->state == CGROUP_FROZEN)
+                return -EBUSY;
+
+        return 0;
+}
+
+static void freezer_fork(struct cgroup_subsys *ss, struct task_struct *task)
+{
+        struct freezer *freezer;
+
+        /*
+         * No lock is needed, since the task isn't on tasklist yet,
+         * so it can't be moved to another cgroup, which means the
+         * freezer won't be removed and will be valid during this
+         * function call.
+         */
+        freezer = task_freezer(task);
+
+        /*
+         * The root cgroup is non-freezable, so we can skip the
+         * following check.
+         */
+        if (!freezer->css.cgroup->parent)
+                return;
+
+        spin_lock_irq(&freezer->lock);
+        BUG_ON(freezer->state == CGROUP_FROZEN);
+
+        /* Locking avoids race with FREEZING -> THAWED transitions. */
+        if (freezer->state == CGROUP_FREEZING)
+                freeze_task(task, true);
+        spin_unlock_irq(&freezer->lock);
+}
+
+/*
+ * caller must hold freezer->lock
+ */
+static void update_freezer_state(struct cgroup *cgroup,
+                                 struct freezer *freezer)
+{
+        struct cgroup_iter it;
+        struct task_struct *task;
+        unsigned int nfrozen = 0, ntotal = 0;
+
+        cgroup_iter_start(cgroup, &it);
+        while ((task = cgroup_iter_next(cgroup, &it))) {
+                ntotal++;
+                if (is_task_frozen_enough(task))
+                        nfrozen++;
+        }
+
+        /*
+         * Transition to FROZEN when no new tasks can be added ensures
+         * that we never exist in the FROZEN state while there are unfrozen
+         * tasks.
+         */
+        if (nfrozen == ntotal)
+                freezer->state = CGROUP_FROZEN;
+        else if (nfrozen > 0)
+                freezer->state = CGROUP_FREEZING;
+        else
+                freezer->state = CGROUP_THAWED;
+        cgroup_iter_end(cgroup, &it);
+}
+
+static int freezer_read(struct cgroup *cgroup, struct cftype *cft,
+                        struct seq_file *m)
+{
+        struct freezer *freezer;
+        enum freezer_state state;
+
+        if (!cgroup_lock_live_group(cgroup))
+                return -ENODEV;
+
+        freezer = cgroup_freezer(cgroup);
+        spin_lock_irq(&freezer->lock);
+        state = freezer->state;
+        if (state == CGROUP_FREEZING) {
+                /* We change from FREEZING to FROZEN lazily if the cgroup was
+                 * only partially frozen when we exitted write. */
+                update_freezer_state(cgroup, freezer);
+                state = freezer->state;
+        }
+        spin_unlock_irq(&freezer->lock);
+        cgroup_unlock();
+
+        seq_puts(m, freezer_state_strs[state]);
+        seq_putc(m, '\n');
+        return 0;
+}
+
+static int try_to_freeze_cgroup(struct cgroup *cgroup, struct freezer *freezer)
+{
+        struct cgroup_iter it;
+        struct task_struct *task;
+        unsigned int num_cant_freeze_now = 0;
+
+        freezer->state = CGROUP_FREEZING;
+        cgroup_iter_start(cgroup, &it);
+        while ((task = cgroup_iter_next(cgroup, &it))) {
+                if (!freeze_task(task, true))
+                        continue;
+                if (is_task_frozen_enough(task))
+                        continue;
+                if (!freezing(task) && !freezer_should_skip(task))
+                        num_cant_freeze_now++;
+        }
+        cgroup_iter_end(cgroup, &it);
+
+        return num_cant_freeze_now ? -EBUSY : 0;
+}
+
+static void unfreeze_cgroup(struct cgroup *cgroup, struct freezer *freezer)
+{
+        struct cgroup_iter it;
+        struct task_struct *task;
+
+        cgroup_iter_start(cgroup, &it);
+        while ((task = cgroup_iter_next(cgroup, &it))) {
+                thaw_process(task);
+        }
+        cgroup_iter_end(cgroup, &it);
+
+        freezer->state = CGROUP_THAWED;
+}
+
+static int freezer_change_state(struct cgroup *cgroup,
+                                enum freezer_state goal_state)
+{
+        struct freezer *freezer;
+        int retval = 0;
+
+        freezer = cgroup_freezer(cgroup);
+
+        spin_lock_irq(&freezer->lock);
+
+        update_freezer_state(cgroup, freezer);
+        if (goal_state == freezer->state)
+                goto out;
+
+        switch (goal_state) {
+        case CGROUP_THAWED:
+                unfreeze_cgroup(cgroup, freezer);
+                break;
+        case CGROUP_FROZEN:
+                retval = try_to_freeze_cgroup(cgroup, freezer);
+                break;
+        default:
+                BUG();
+        }
+out:
+        spin_unlock_irq(&freezer->lock);
+
+        return retval;
+}
+
+static int freezer_write(struct cgroup *cgroup,
+                         struct cftype *cft,
+                         const char *buffer)
+{
+        int retval;
+        enum freezer_state goal_state;
+
+        if (strcmp(buffer, freezer_state_strs[CGROUP_THAWED]) == 0)
+                goal_state = CGROUP_THAWED;
+        else if (strcmp(buffer, freezer_state_strs[CGROUP_FROZEN]) == 0)
+                goal_state = CGROUP_FROZEN;
+        else
+                return -EINVAL;
+
+        if (!cgroup_lock_live_group(cgroup))
+                return -ENODEV;
+        retval = freezer_change_state(cgroup, goal_state);
+        cgroup_unlock();
+        return retval;
+}
+
+static struct cftype files[] = {
+        {
+                .name = "state",
+                .read_seq_string = freezer_read,
+                .write_string = freezer_write,
+        },
+};
+
+static int freezer_populate(struct cgroup_subsys *ss, struct cgroup *cgroup)
+{
+        if (!cgroup->parent)
+                return 0;
+        return cgroup_add_files(cgroup, ss, files, ARRAY_SIZE(files));
+}
+
+struct cgroup_subsys freezer_subsys = {
+        .name           = "freezer",
+        .create         = freezer_create,
+        .destroy        = freezer_destroy,
+        .populate       = freezer_populate,
+        .subsys_id      = freezer_subsys_id,
+        .can_attach     = freezer_can_attach,
+        .attach         = NULL,
+        .fork           = freezer_fork,
+        .exit           = NULL,
+};
diff --git a/kernel/compat.c b/kernel/compat.c
index 32c254a8ab9a..8eafe3eb50d9 100644
--- a/kernel/compat.c
+++ b/kernel/compat.c
@@ -23,9 +23,68 @@
 #include <linux/timex.h>
 #include <linux/migrate.h>
 #include <linux/posix-timers.h>
+#include <linux/times.h>
 
 #include <asm/uaccess.h>
 
+/*
+ * Note that the native side is already converted to a timespec, because
+ * that's what we want anyway.
+ */
+static int compat_get_timeval(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(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;
+}
+
+asmlinkage long compat_sys_gettimeofday(struct compat_timeval __user *tv,
+                struct timezone __user *tz)
+{
+        if (tv) {
+                struct timeval ktv;
+                do_gettimeofday(&ktv);
+                if (compat_put_timeval(tv, &ktv))
+                        return -EFAULT;
+        }
+        if (tz) {
+                if (copy_to_user(tz, &sys_tz, sizeof(sys_tz)))
+                        return -EFAULT;
+        }
+
+        return 0;
+}
+
+asmlinkage long compat_sys_settimeofday(struct compat_timeval __user *tv,
+                struct timezone __user *tz)
+{
+        struct timespec kts;
+        struct timezone ktz;
+
+        if (tv) {
+                if (compat_get_timeval(&kts, tv))
+                        return -EFAULT;
+        }
+        if (tz) {
+                if (copy_from_user(&ktz, tz, sizeof(ktz)))
+                        return -EFAULT;
+        }
+
+        return do_sys_settimeofday(tv ? &kts : NULL, tz ? &ktz : NULL);
+}
+
 int get_compat_timespec(struct timespec *ts, const struct compat_timespec __user *cts)
 {
         return (!access_ok(VERIFY_READ, cts, sizeof(*cts)) ||
@@ -150,49 +209,23 @@ asmlinkage long compat_sys_setitimer(int which,
         return 0;
 }
 
+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)
 {
-        /*
-         *      In the SMP world we might just be unlucky and have one of
-         *      the times increment as we use it. Since the value is an
-         *      atomically safe type this is just fine. Conceptually its
-         *      as if the syscall took an instant longer to occur.
-         */
         if (tbuf) {
+                struct tms tms;
                 struct compat_tms tmp;
-                struct task_struct *tsk = current;
-                struct task_struct *t;
-                cputime_t utime, stime, cutime, cstime;
-
-                read_lock(&tasklist_lock);
-                utime = tsk->signal->utime;
-                stime = tsk->signal->stime;
-                t = tsk;
-                do {
-                        utime = cputime_add(utime, t->utime);
-                        stime = cputime_add(stime, t->stime);
-                        t = next_thread(t);
-                } while (t != tsk);
-
-                /*
-                 * While we have tasklist_lock read-locked, no dying thread
-                 * can be updating current->signal->[us]time.  Instead,
-                 * we got their counts included in the live thread loop.
-                 * However, another thread can come in right now and
-                 * do a wait call that updates current->signal->c[us]time.
-                 * To make sure we always see that pair updated atomically,
-                 * we take the siglock around fetching them.
-                 */
-                spin_lock_irq(&tsk->sighand->siglock);
-                cutime = tsk->signal->cutime;
-                cstime = tsk->signal->cstime;
-                spin_unlock_irq(&tsk->sighand->siglock);
-                read_unlock(&tasklist_lock);
-
-                tmp.tms_utime = compat_jiffies_to_clock_t(cputime_to_jiffies(utime));
-                tmp.tms_stime = compat_jiffies_to_clock_t(cputime_to_jiffies(stime));
-                tmp.tms_cutime = compat_jiffies_to_clock_t(cputime_to_jiffies(cutime));
-                tmp.tms_cstime = compat_jiffies_to_clock_t(cputime_to_jiffies(cstime));
+
+                do_sys_times(&tms);
+                /* Convert our struct tms to the compat version. */
+                tmp.tms_utime = clock_t_to_compat_clock_t(tms.tms_utime);
+                tmp.tms_stime = clock_t_to_compat_clock_t(tms.tms_stime);
+                tmp.tms_cutime = clock_t_to_compat_clock_t(tms.tms_cutime);
+                tmp.tms_cstime = clock_t_to_compat_clock_t(tms.tms_cstime);
                 if (copy_to_user(tbuf, &tmp, sizeof(tmp)))
                         return -EFAULT;
         }
diff --git a/kernel/configs.c b/kernel/configs.c
index 4c345210ed8c..abaee684ecbf 100644
--- a/kernel/configs.c
+++ b/kernel/configs.c
@@ -54,9 +54,6 @@
 
 #ifdef CONFIG_IKCONFIG_PROC
 
-/**************************************************/
-/* globals and useful constants                   */
-
 static ssize_t
 ikconfig_read_current(struct file *file, char __user *buf,
                       size_t len, loff_t * offset)
@@ -71,9 +68,6 @@ static const struct file_operations ikconfig_file_ops = {
         .read = ikconfig_read_current,
 };
 
-/***************************************************/
-/* ikconfig_init: start up everything we need to */
-
 static int __init ikconfig_init(void)
 {
         struct proc_dir_entry *entry;
@@ -89,9 +83,6 @@ static int __init ikconfig_init(void)
         return 0;
 }
 
-/***************************************************/
-/* ikconfig_cleanup: clean up our mess           */
-
 static void __exit ikconfig_cleanup(void)
 {
         remove_proc_entry("config.gz", NULL);
diff --git a/kernel/cpu.c b/kernel/cpu.c
index f17e9854c246..5a732c5ef08b 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -199,13 +199,14 @@ static int __ref take_cpu_down(void *_param)
         struct take_cpu_down_param *param = _param;
         int err;
 
-        raw_notifier_call_chain(&cpu_chain, CPU_DYING | param->mod,
-                                param->hcpu);
         /* Ensure this CPU doesn't handle any more interrupts. */
         err = __cpu_disable();
         if (err < 0)
                 return err;
 
+        raw_notifier_call_chain(&cpu_chain, CPU_DYING | param->mod,
+                                param->hcpu);
+
         /* Force idle task to run as soon as we yield: it should
            immediately notice cpu is offline and die quickly. */
         sched_idle_next();
@@ -453,6 +454,25 @@ out:
 }
 #endif /* CONFIG_PM_SLEEP_SMP */
 
+/**
+ * notify_cpu_starting(cpu) - call the CPU_STARTING notifiers
+ * @cpu: cpu that just started
+ *
+ * This function calls the cpu_chain notifiers with CPU_STARTING.
+ * It must be called by the arch code on the new cpu, before the new cpu
+ * enables interrupts and before the "boot" cpu returns from __cpu_up().
+ */
+void notify_cpu_starting(unsigned int cpu)
+{
+        unsigned long val = CPU_STARTING;
+
+#ifdef CONFIG_PM_SLEEP_SMP
+        if (cpu_isset(cpu, frozen_cpus))
+                val = CPU_STARTING_FROZEN;
+#endif /* CONFIG_PM_SLEEP_SMP */
+        raw_notifier_call_chain(&cpu_chain, val, (void *)(long)cpu);
+}
+
 #endif /* CONFIG_SMP */
 
 /*
@@ -479,3 +499,6 @@ const unsigned long cpu_bit_bitmap[BITS_PER_LONG+1][BITS_TO_LONGS(NR_CPUS)] = {
 #endif
 };
 EXPORT_SYMBOL_GPL(cpu_bit_bitmap);
+
+const DECLARE_BITMAP(cpu_all_bits, NR_CPUS) = CPU_BITS_ALL;
+EXPORT_SYMBOL(cpu_all_bits);
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index f227bc172690..da7ff6137f37 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -36,6 +36,7 @@
 #include <linux/list.h>
 #include <linux/mempolicy.h>
 #include <linux/mm.h>
+#include <linux/memory.h>
 #include <linux/module.h>
 #include <linux/mount.h>
 #include <linux/namei.h>
@@ -587,7 +588,6 @@ static int generate_sched_domains(cpumask_t **domains,
         int ndoms;              /* number of sched domains in result */
         int nslot;              /* next empty doms[] cpumask_t slot */
 
-        ndoms = 0;
         doms = NULL;
         dattr = NULL;
         csa = NULL;
@@ -674,10 +674,8 @@ restart:
          * Convert <csn, csa> to <ndoms, doms> and populate cpu masks.
          */
         doms = kmalloc(ndoms * sizeof(cpumask_t), GFP_KERNEL);
-        if (!doms) {
-                ndoms = 0;
+        if (!doms)
                 goto done;
-        }
 
         /*
          * The rest of the code, including the scheduler, can deal with
@@ -732,6 +730,13 @@ restart:
 done:
         kfree(csa);
 
+        /*
+         * Fallback to the default domain if kmalloc() failed.
+         * See comments in partition_sched_domains().
+         */
+        if (doms == NULL)
+                ndoms = 1;
+
         *domains    = doms;
         *attributes = dattr;
         return ndoms;
@@ -843,37 +848,25 @@ static void cpuset_change_cpumask(struct task_struct *tsk,
 /**
  * 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 cgroup_scan_tasks()
  *
  * Called with cgroup_mutex held
  *
  * The cgroup_scan_tasks() function will scan all the tasks in a cgroup,
  * calling callback functions for each.
  *
- * Return 0 if successful, -errno if not.
+ * No return value. It's guaranteed that cgroup_scan_tasks() always returns 0
+ * if @heap != NULL.
  */
-static int update_tasks_cpumask(struct cpuset *cs)
+static void update_tasks_cpumask(struct cpuset *cs, struct ptr_heap *heap)
 {
         struct cgroup_scanner scan;
-        struct ptr_heap heap;
-        int retval;
-
-        /*
-         * cgroup_scan_tasks() will initialize heap->gt for us.
-         * heap_init() is still needed here for we should not change
-         * cs->cpus_allowed when heap_init() fails.
-         */
-        retval = heap_init(&heap, PAGE_SIZE, GFP_KERNEL, NULL);
-        if (retval)
-                return retval;
 
         scan.cg = cs->css.cgroup;
         scan.test_task = cpuset_test_cpumask;
         scan.process_task = cpuset_change_cpumask;
-        scan.heap = &heap;
-        retval = cgroup_scan_tasks(&scan);
-
-        heap_free(&heap);
-        return retval;
+        scan.heap = heap;
+        cgroup_scan_tasks(&scan);
 }
 
 /**
@@ -883,6 +876,7 @@ static int update_tasks_cpumask(struct cpuset *cs)
  */
 static int update_cpumask(struct cpuset *cs, const char *buf)
 {
+        struct ptr_heap heap;
         struct cpuset trialcs;
         int retval;
         int is_load_balanced;
@@ -917,6 +911,10 @@ static int update_cpumask(struct cpuset *cs, const char *buf)
         if (cpus_equal(cs->cpus_allowed, trialcs.cpus_allowed))
                 return 0;
 
+        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);
@@ -927,9 +925,9 @@ static int update_cpumask(struct cpuset *cs, const char *buf)
          * Scan tasks in the cpuset, and update the cpumasks of any
          * that need an update.
          */
-        retval = update_tasks_cpumask(cs);
-        if (retval < 0)
-                return retval;
+        update_tasks_cpumask(cs, &heap);
+
+        heap_free(&heap);
 
         if (is_load_balanced)
                 async_rebuild_sched_domains();
@@ -1179,7 +1177,7 @@ static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs,
 {
         struct cpuset trialcs;
         int err;
-        int cpus_nonempty, balance_flag_changed;
+        int balance_flag_changed;
 
         trialcs = *cs;
         if (turning_on)
@@ -1191,7 +1189,6 @@ static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs,
         if (err < 0)
                 return err;
 
-        cpus_nonempty = !cpus_empty(trialcs.cpus_allowed);
         balance_flag_changed = (is_sched_load_balance(cs) !=
                                         is_sched_load_balance(&trialcs));
 
@@ -1199,7 +1196,7 @@ static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs,
         cs->flags = trialcs.flags;
         mutex_unlock(&callback_mutex);
 
-        if (cpus_nonempty && balance_flag_changed)
+        if (!cpus_empty(trialcs.cpus_allowed) && balance_flag_changed)
                 async_rebuild_sched_domains();
 
         return 0;
@@ -1928,7 +1925,7 @@ static void remove_tasks_in_empty_cpuset(struct cpuset *cs)
  * that has tasks along with an empty 'mems'.  But if we did see such
  * a cpuset, we'd handle it just like we do if its 'cpus' was empty.
  */
-static void scan_for_empty_cpusets(const struct cpuset *root)
+static void scan_for_empty_cpusets(struct cpuset *root)
 {
         LIST_HEAD(queue);
         struct cpuset *cp;      /* scans cpusets being updated */
@@ -1965,7 +1962,7 @@ static void scan_for_empty_cpusets(const struct cpuset *root)
                      nodes_empty(cp->mems_allowed))
                         remove_tasks_in_empty_cpuset(cp);
                 else {
-                        update_tasks_cpumask(cp);
+                        update_tasks_cpumask(cp, NULL);
                         update_tasks_nodemask(cp, &oldmems);
                 }
         }
@@ -2019,12 +2016,23 @@ static int cpuset_track_online_cpus(struct notifier_block *unused_nb,
  * Call this routine anytime after node_states[N_HIGH_MEMORY] changes.
  * See also the previous routine cpuset_track_online_cpus().
  */
-void cpuset_track_online_nodes(void)
+static int cpuset_track_online_nodes(struct notifier_block *self,
+                                unsigned long action, void *arg)
 {
         cgroup_lock();
-        top_cpuset.mems_allowed = node_states[N_HIGH_MEMORY];
-        scan_for_empty_cpusets(&top_cpuset);
+        switch (action) {
+        case MEM_ONLINE:
+                top_cpuset.mems_allowed = node_states[N_HIGH_MEMORY];
+                break;
+        case MEM_OFFLINE:
+                top_cpuset.mems_allowed = node_states[N_HIGH_MEMORY];
+                scan_for_empty_cpusets(&top_cpuset);
+                break;
+        default:
+                break;
+        }
         cgroup_unlock();
+        return NOTIFY_OK;
 }
 #endif
 
@@ -2040,6 +2048,7 @@ void __init cpuset_init_smp(void)
         top_cpuset.mems_allowed = node_states[N_HIGH_MEMORY];
 
         hotcpu_notifier(cpuset_track_online_cpus, 0);
+        hotplug_memory_notifier(cpuset_track_online_nodes, 10);
 }
 
 /**
@@ -2444,19 +2453,15 @@ const struct file_operations proc_cpuset_operations = {
 void cpuset_task_status_allowed(struct seq_file *m, struct task_struct *task)
 {
         seq_printf(m, "Cpus_allowed:\t");
-        m->count += cpumask_scnprintf(m->buf + m->count, m->size - m->count,
-                                        task->cpus_allowed);
+        seq_cpumask(m, &task->cpus_allowed);
         seq_printf(m, "\n");
         seq_printf(m, "Cpus_allowed_list:\t");
-        m->count += cpulist_scnprintf(m->buf + m->count, m->size - m->count,
-                                        task->cpus_allowed);
+        seq_cpumask_list(m, &task->cpus_allowed);
         seq_printf(m, "\n");
         seq_printf(m, "Mems_allowed:\t");
-        m->count += nodemask_scnprintf(m->buf + m->count, m->size - m->count,
-                                        task->mems_allowed);
+        seq_nodemask(m, &task->mems_allowed);
         seq_printf(m, "\n");
         seq_printf(m, "Mems_allowed_list:\t");
-        m->count += nodelist_scnprintf(m->buf + m->count, m->size - m->count,
-                                        task->mems_allowed);
+        seq_nodemask_list(m, &task->mems_allowed);
         seq_printf(m, "\n");
 }
diff --git a/kernel/dma-coherent.c b/kernel/dma-coherent.c
index c1d4d5b4c61c..f013a0c2e111 100644
--- a/kernel/dma-coherent.c
+++ b/kernel/dma-coherent.c
@@ -124,6 +124,7 @@ int dma_alloc_from_coherent(struct device *dev, ssize_t size,
         }
         return (mem != NULL);
 }
+EXPORT_SYMBOL(dma_alloc_from_coherent);
 
 /**
  * dma_release_from_coherent() - try to free the memory allocated from per-device coherent memory pool
@@ -151,3 +152,4 @@ int dma_release_from_coherent(struct device *dev, int order, void *vaddr)
         }
         return 0;
 }
+EXPORT_SYMBOL(dma_release_from_coherent);
diff --git a/kernel/dma.c b/kernel/dma.c
index d2c60a822790..f903189c5304 100644
--- a/kernel/dma.c
+++ b/kernel/dma.c
@@ -1,4 +1,4 @@
-/* $Id: dma.c,v 1.7 1994/12/28 03:35:33 root Exp root $
+/*
  * linux/kernel/dma.c: A DMA channel allocator. Inspired by linux/kernel/irq.c.
  *
  * Written by Hennus Bergman, 1992.
diff --git a/kernel/exec_domain.c b/kernel/exec_domain.c
index 0d407e886735..0511716e9424 100644
--- a/kernel/exec_domain.c
+++ b/kernel/exec_domain.c
@@ -12,7 +12,9 @@
 #include <linux/kmod.h>
 #include <linux/module.h>
 #include <linux/personality.h>
+#include <linux/proc_fs.h>
 #include <linux/sched.h>
+#include <linux/seq_file.h>
 #include <linux/syscalls.h>
 #include <linux/sysctl.h>
 #include <linux/types.h>
@@ -173,20 +175,39 @@ __set_personality(u_long personality)
         return 0;
 }
 
-int
-get_exec_domain_list(char *page)
+#ifdef CONFIG_PROC_FS
+static int execdomains_proc_show(struct seq_file *m, void *v)
 {
         struct exec_domain      *ep;
-        int                     len = 0;
 
         read_lock(&exec_domains_lock);
-        for (ep = exec_domains; ep && len < PAGE_SIZE - 80; ep = ep->next)
-                len += sprintf(page + len, "%d-%d\t%-16s\t[%s]\n",
+        for (ep = exec_domains; ep; ep = ep->next)
+                seq_printf(m, "%d-%d\t%-16s\t[%s]\n",
                                ep->pers_low, ep->pers_high, ep->name,
                                module_name(ep->module));
         read_unlock(&exec_domains_lock);
-        return (len);
+        return 0;
+}
+
+static int execdomains_proc_open(struct inode *inode, struct file *file)
+{
+        return single_open(file, execdomains_proc_show, NULL);
+}
+
+static const struct file_operations execdomains_proc_fops = {
+        .open           = execdomains_proc_open,
+        .read           = seq_read,
+        .llseek         = seq_lseek,
+        .release        = single_release,
+};
+
+static int __init proc_execdomains_init(void)
+{
+        proc_create("execdomains", 0, NULL, &execdomains_proc_fops);
+        return 0;
 }
+module_init(proc_execdomains_init);
+#endif
 
 asmlinkage long
 sys_personality(u_long personality)
diff --git a/kernel/exit.c b/kernel/exit.c
index 16395644a98f..2d8be7ebb0f7 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -40,13 +40,13 @@
 #include <linux/cn_proc.h>
 #include <linux/mutex.h>
 #include <linux/futex.h>
-#include <linux/compat.h>
 #include <linux/pipe_fs_i.h>
 #include <linux/audit.h> /* for audit_free() */
 #include <linux/resource.h>
 #include <linux/blkdev.h>
 #include <linux/task_io_accounting_ops.h>
 #include <linux/tracehook.h>
+#include <trace/sched.h>
 
 #include <asm/uaccess.h>
 #include <asm/unistd.h>
@@ -112,8 +112,6 @@ static void __exit_signal(struct task_struct *tsk)
                  * We won't ever get here for the group leader, since it
                  * will have been the last reference on the signal_struct.
                  */
-                sig->utime = cputime_add(sig->utime, task_utime(tsk));
-                sig->stime = cputime_add(sig->stime, task_stime(tsk));
                 sig->gtime = cputime_add(sig->gtime, task_gtime(tsk));
                 sig->min_flt += tsk->min_flt;
                 sig->maj_flt += tsk->maj_flt;
@@ -122,7 +120,6 @@ static void __exit_signal(struct task_struct *tsk)
                 sig->inblock += task_io_get_inblock(tsk);
                 sig->oublock += task_io_get_oublock(tsk);
                 task_io_accounting_add(&sig->ioac, &tsk->ioac);
-                sig->sum_sched_runtime += tsk->se.sum_exec_runtime;
                 sig = NULL; /* Marker for below. */
         }
 
@@ -143,13 +140,21 @@ static void __exit_signal(struct task_struct *tsk)
         if (sig) {
                 flush_sigqueue(&sig->shared_pending);
                 taskstats_tgid_free(sig);
+                /*
+                 * Make sure ->signal can't go away under rq->lock,
+                 * see account_group_exec_runtime().
+                 */
+                task_rq_unlock_wait(tsk);
                 __cleanup_signal(sig);
         }
 }
 
 static void delayed_put_task_struct(struct rcu_head *rhp)
 {
-        put_task_struct(container_of(rhp, struct task_struct, rcu));
+        struct task_struct *tsk = container_of(rhp, struct task_struct, rcu);
+
+        trace_sched_process_free(tsk);
+        put_task_struct(tsk);
 }
 
 
@@ -583,8 +588,6 @@ mm_need_new_owner(struct mm_struct *mm, struct task_struct *p)
          * If there are other users of the mm and the owner (us) is exiting
          * we need to find a new owner to take on the responsibility.
          */
-        if (!mm)
-                return 0;
         if (atomic_read(&mm->mm_users) <= 1)
                 return 0;
         if (mm->owner != p)
@@ -627,29 +630,38 @@ retry:
         } while_each_thread(g, c);
 
         read_unlock(&tasklist_lock);
+        /*
+         * We found no owner yet mm_users > 1: this implies that we are
+         * most likely racing with swapoff (try_to_unuse()) or /proc or
+         * ptrace or page migration (get_task_mm()).  Mark owner as NULL,
+         * so that subsystems can understand the callback and take action.
+         */
+        down_write(&mm->mmap_sem);
+        cgroup_mm_owner_callbacks(mm->owner, NULL);
+        mm->owner = NULL;
+        up_write(&mm->mmap_sem);
         return;
 
 assign_new_owner:
         BUG_ON(c == p);
         get_task_struct(c);
+        read_unlock(&tasklist_lock);
+        down_write(&mm->mmap_sem);
         /*
          * The task_lock protects c->mm from changing.
          * We always want mm->owner->mm == mm
          */
         task_lock(c);
-        /*
-         * Delay read_unlock() till we have the task_lock()
-         * to ensure that c does not slip away underneath us
-         */
-        read_unlock(&tasklist_lock);
         if (c->mm != mm) {
                 task_unlock(c);
+                up_write(&mm->mmap_sem);
                 put_task_struct(c);
                 goto retry;
         }
         cgroup_mm_owner_callbacks(mm->owner, c);
         mm->owner = c;
         task_unlock(c);
+        up_write(&mm->mmap_sem);
         put_task_struct(c);
 }
 #endif /* CONFIG_MM_OWNER */
@@ -1046,14 +1058,6 @@ NORET_TYPE void do_exit(long code)
                 exit_itimers(tsk->signal);
         }
         acct_collect(code, group_dead);
-#ifdef CONFIG_FUTEX
-        if (unlikely(tsk->robust_list))
-                exit_robust_list(tsk);
-#ifdef CONFIG_COMPAT
-        if (unlikely(tsk->compat_robust_list))
-                compat_exit_robust_list(tsk);
-#endif
-#endif
         if (group_dead)
                 tty_audit_exit();
         if (unlikely(tsk->audit_context))
@@ -1066,6 +1070,8 @@ NORET_TYPE void do_exit(long code)
 
         if (group_dead)
                 acct_process();
+        trace_sched_process_exit(tsk);
+
         exit_sem(tsk);
         exit_files(tsk);
         exit_fs(tsk);
@@ -1294,6 +1300,7 @@ static int wait_task_zombie(struct task_struct *p, int options,
         if (likely(!traced)) {
                 struct signal_struct *psig;
                 struct signal_struct *sig;
+                struct task_cputime cputime;
 
                 /*
                  * The resource counters for the group leader are in its
@@ -1309,20 +1316,23 @@ static int wait_task_zombie(struct task_struct *p, int options,
                  * need to protect the access to p->parent->signal fields,
                  * as other threads in the parent group can be right
                  * here reaping other children at the same time.
+                 *
+                 * We use thread_group_cputime() to get times for the thread
+                 * group, which consolidates times for all threads in the
+                 * group including the group leader.
                  */
                 spin_lock_irq(&p->parent->sighand->siglock);
                 psig = p->parent->signal;
                 sig = p->signal;
+                thread_group_cputime(p, &cputime);
                 psig->cutime =
                         cputime_add(psig->cutime,
-                        cputime_add(p->utime,
-                        cputime_add(sig->utime,
-                                    sig->cutime)));
+                        cputime_add(cputime.utime,
+                                    sig->cutime));
                 psig->cstime =
                         cputime_add(psig->cstime,
-                        cputime_add(p->stime,
-                        cputime_add(sig->stime,
-                                    sig->cstime)));
+                        cputime_add(cputime.stime,
+                                    sig->cstime));
                 psig->cgtime =
                         cputime_add(psig->cgtime,
                         cputime_add(p->gtime,
@@ -1667,6 +1677,8 @@ static long do_wait(enum pid_type type, struct pid *pid, int options,
         struct task_struct *tsk;
         int retval;
 
+        trace_sched_process_wait(pid);
+
         add_wait_queue(&current->signal->wait_chldexit,&wait);
 repeat:
         /*
diff --git a/kernel/fork.c b/kernel/fork.c
index 7ce2ebe84796..2a372a0e206f 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -40,6 +40,7 @@
 #include <linux/jiffies.h>
 #include <linux/tracehook.h>
 #include <linux/futex.h>
+#include <linux/compat.h>
 #include <linux/task_io_accounting_ops.h>
 #include <linux/rcupdate.h>
 #include <linux/ptrace.h>
@@ -58,6 +59,7 @@
 #include <linux/tty.h>
 #include <linux/proc_fs.h>
 #include <linux/blkdev.h>
+#include <trace/sched.h>
 
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
@@ -518,6 +520,16 @@ void mm_release(struct task_struct *tsk, struct mm_struct *mm)
 {
         struct completion *vfork_done = tsk->vfork_done;
 
+        /* Get rid of any futexes when releasing the mm */
+#ifdef CONFIG_FUTEX
+        if (unlikely(tsk->robust_list))
+                exit_robust_list(tsk);
+#ifdef CONFIG_COMPAT
+        if (unlikely(tsk->compat_robust_list))
+                compat_exit_robust_list(tsk);
+#endif
+#endif
+
         /* Get rid of any cached register state */
         deactivate_mm(tsk, mm);
 
@@ -759,15 +771,44 @@ void __cleanup_sighand(struct sighand_struct *sighand)
                 kmem_cache_free(sighand_cachep, sighand);
 }
 
+
+/*
+ * Initialize POSIX timer handling for a thread group.
+ */
+static void posix_cpu_timers_init_group(struct signal_struct *sig)
+{
+        /* Thread group counters. */
+        thread_group_cputime_init(sig);
+
+        /* Expiration times and increments. */
+        sig->it_virt_expires = cputime_zero;
+        sig->it_virt_incr = cputime_zero;
+        sig->it_prof_expires = cputime_zero;
+        sig->it_prof_incr = cputime_zero;
+
+        /* Cached expiration times. */
+        sig->cputime_expires.prof_exp = cputime_zero;
+        sig->cputime_expires.virt_exp = cputime_zero;
+        sig->cputime_expires.sched_exp = 0;
+
+        /* The timer lists. */
+        INIT_LIST_HEAD(&sig->cpu_timers[0]);
+        INIT_LIST_HEAD(&sig->cpu_timers[1]);
+        INIT_LIST_HEAD(&sig->cpu_timers[2]);
+}
+
 static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
 {
         struct signal_struct *sig;
         int ret;
 
         if (clone_flags & CLONE_THREAD) {
-                atomic_inc(&current->signal->count);
-                atomic_inc(&current->signal->live);
-                return 0;
+                ret = thread_group_cputime_clone_thread(current);
+                if (likely(!ret)) {
+                        atomic_inc(&current->signal->count);
+                        atomic_inc(&current->signal->live);
+                }
+                return ret;
         }
         sig = kmem_cache_alloc(signal_cachep, GFP_KERNEL);
         tsk->signal = sig;
@@ -795,39 +836,25 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
         sig->it_real_incr.tv64 = 0;
         sig->real_timer.function = it_real_fn;
 
-        sig->it_virt_expires = cputime_zero;
-        sig->it_virt_incr = cputime_zero;
-        sig->it_prof_expires = cputime_zero;
-        sig->it_prof_incr = cputime_zero;
-
         sig->leader = 0;        /* session leadership doesn't inherit */
         sig->tty_old_pgrp = NULL;
+        sig->tty = NULL;
 
-        sig->utime = sig->stime = sig->cutime = sig->cstime = cputime_zero;
+        sig->cutime = sig->cstime = cputime_zero;
         sig->gtime = cputime_zero;
         sig->cgtime = cputime_zero;
         sig->nvcsw = sig->nivcsw = sig->cnvcsw = sig->cnivcsw = 0;
         sig->min_flt = sig->maj_flt = sig->cmin_flt = sig->cmaj_flt = 0;
         sig->inblock = sig->oublock = sig->cinblock = sig->coublock = 0;
         task_io_accounting_init(&sig->ioac);
-        sig->sum_sched_runtime = 0;
-        INIT_LIST_HEAD(&sig->cpu_timers[0]);
-        INIT_LIST_HEAD(&sig->cpu_timers[1]);
-        INIT_LIST_HEAD(&sig->cpu_timers[2]);
         taskstats_tgid_init(sig);
 
         task_lock(current->group_leader);
         memcpy(sig->rlim, current->signal->rlim, sizeof sig->rlim);
         task_unlock(current->group_leader);
 
-        if (sig->rlim[RLIMIT_CPU].rlim_cur != RLIM_INFINITY) {
-                /*
-                 * New sole thread in the process gets an expiry time
-                 * of the whole CPU time limit.
-                 */
-                tsk->it_prof_expires =
-                        secs_to_cputime(sig->rlim[RLIMIT_CPU].rlim_cur);
-        }
+        posix_cpu_timers_init_group(sig);
+
         acct_init_pacct(&sig->pacct);
 
         tty_audit_fork(sig);
@@ -837,7 +864,9 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
 
 void __cleanup_signal(struct signal_struct *sig)
 {
+        thread_group_cputime_free(sig);
         exit_thread_group_keys(sig);
+        tty_kref_put(sig->tty);
         kmem_cache_free(signal_cachep, sig);
 }
 
@@ -886,6 +915,19 @@ void mm_init_owner(struct mm_struct *mm, struct task_struct *p)
 #endif /* CONFIG_MM_OWNER */
 
 /*
+ * Initialize POSIX timer handling for a single task.
+ */
+static void posix_cpu_timers_init(struct task_struct *tsk)
+{
+        tsk->cputime_expires.prof_exp = cputime_zero;
+        tsk->cputime_expires.virt_exp = cputime_zero;
+        tsk->cputime_expires.sched_exp = 0;
+        INIT_LIST_HEAD(&tsk->cpu_timers[0]);
+        INIT_LIST_HEAD(&tsk->cpu_timers[1]);
+        INIT_LIST_HEAD(&tsk->cpu_timers[2]);
+}
+
+/*
  * This creates a new process as a copy of the old one,
  * but does not actually start it yet.
  *
@@ -987,6 +1029,8 @@ static struct task_struct *copy_process(unsigned long clone_flags,
         p->prev_utime = cputime_zero;
         p->prev_stime = cputime_zero;
 
+        p->default_timer_slack_ns = current->timer_slack_ns;
+
 #ifdef CONFIG_DETECT_SOFTLOCKUP
         p->last_switch_count = 0;
         p->last_switch_timestamp = 0;
@@ -995,12 +1039,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
         task_io_accounting_init(&p->ioac);
         acct_clear_integrals(p);
 
-        p->it_virt_expires = cputime_zero;
-        p->it_prof_expires = cputime_zero;
-        p->it_sched_expires = 0;
-        INIT_LIST_HEAD(&p->cpu_timers[0]);
-        INIT_LIST_HEAD(&p->cpu_timers[1]);
-        INIT_LIST_HEAD(&p->cpu_timers[2]);
+        posix_cpu_timers_init(p);
 
         p->lock_depth = -1;             /* -1 = no lock */
         do_posix_clock_monotonic_gettime(&p->start_time);
@@ -1201,21 +1240,6 @@ static struct task_struct *copy_process(unsigned long clone_flags,
         if (clone_flags & CLONE_THREAD) {
                 p->group_leader = current->group_leader;
                 list_add_tail_rcu(&p->thread_group, &p->group_leader->thread_group);
-
-                if (!cputime_eq(current->signal->it_virt_expires,
-                                cputime_zero) ||
-                    !cputime_eq(current->signal->it_prof_expires,
-                                cputime_zero) ||
-                    current->signal->rlim[RLIMIT_CPU].rlim_cur != RLIM_INFINITY ||
-                    !list_empty(&current->signal->cpu_timers[0]) ||
-                    !list_empty(&current->signal->cpu_timers[1]) ||
-                    !list_empty(&current->signal->cpu_timers[2])) {
-                        /*
-                         * Have child wake up on its first tick to check
-                         * for process CPU timers.
-                         */
-                        p->it_prof_expires = jiffies_to_cputime(1);
-                }
         }
 
         if (likely(p->pid)) {
@@ -1227,7 +1251,8 @@ static struct task_struct *copy_process(unsigned long clone_flags,
                                 p->nsproxy->pid_ns->child_reaper = p;
 
                         p->signal->leader_pid = pid;
-                        p->signal->tty = current->signal->tty;
+                        tty_kref_put(p->signal->tty);
+                        p->signal->tty = tty_kref_get(current->signal->tty);
                         set_task_pgrp(p, task_pgrp_nr(current));
                         set_task_session(p, task_session_nr(current));
                         attach_pid(p, PIDTYPE_PGID, task_pgrp(current));
@@ -1361,6 +1386,8 @@ long do_fork(unsigned long clone_flags,
         if (!IS_ERR(p)) {
                 struct completion vfork;
 
+                trace_sched_process_fork(current, p);
+
                 nr = task_pid_vnr(p);
 
                 if (clone_flags & CLONE_PARENT_SETTID)
diff --git a/kernel/freezer.c b/kernel/freezer.c
new file mode 100644
index 000000000000..2f4936cf7083
--- /dev/null
+++ b/kernel/freezer.c
@@ -0,0 +1,154 @@
+/*
+ * kernel/freezer.c - Function to freeze a process
+ *
+ * Originally from kernel/power/process.c
+ */
+
+#include <linux/interrupt.h>
+#include <linux/suspend.h>
+#include <linux/module.h>
+#include <linux/syscalls.h>
+#include <linux/freezer.h>
+
+/*
+ * freezing is complete, mark current process as frozen
+ */
+static inline void frozen_process(void)
+{
+        if (!unlikely(current->flags & PF_NOFREEZE)) {
+                current->flags |= PF_FROZEN;
+                wmb();
+        }
+        clear_freeze_flag(current);
+}
+
+/* Refrigerator is place where frozen processes are stored :-). */
+void refrigerator(void)
+{
+        /* Hmm, should we be allowed to suspend when there are realtime
+           processes around? */
+        long save;
+
+        task_lock(current);
+        if (freezing(current)) {
+                frozen_process();
+                task_unlock(current);
+        } else {
+                task_unlock(current);
+                return;
+        }
+        save = current->state;
+        pr_debug("%s entered refrigerator\n", current->comm);
+
+        spin_lock_irq(&current->sighand->siglock);
+        recalc_sigpending(); /* We sent fake signal, clean it up */
+        spin_unlock_irq(&current->sighand->siglock);
+
+        for (;;) {
+                set_current_state(TASK_UNINTERRUPTIBLE);
+                if (!frozen(current))
+                        break;
+                schedule();
+        }
+        pr_debug("%s left refrigerator\n", current->comm);
+        __set_current_state(save);
+}
+EXPORT_SYMBOL(refrigerator);
+
+static void fake_signal_wake_up(struct task_struct *p)
+{
+        unsigned long flags;
+
+        spin_lock_irqsave(&p->sighand->siglock, flags);
+        signal_wake_up(p, 0);
+        spin_unlock_irqrestore(&p->sighand->siglock, flags);
+}
+
+/**
+ *      freeze_task - send a freeze request to given task
+ *      @p: task to send the request to
+ *      @sig_only: if set, the request will only be sent if the task has the
+ *              PF_FREEZER_NOSIG flag unset
+ *      Return value: 'false', if @sig_only is set and the task has
+ *              PF_FREEZER_NOSIG set or the task is frozen, 'true', otherwise
+ *
+ *      The freeze request is sent by setting the tasks's TIF_FREEZE flag and
+ *      either sending a fake signal to it or waking it up, depending on whether
+ *      or not it has PF_FREEZER_NOSIG set.  If @sig_only is set and the task
+ *      has PF_FREEZER_NOSIG set (ie. it is a typical kernel thread), its
+ *      TIF_FREEZE flag will not be set.
+ */
+bool freeze_task(struct task_struct *p, bool sig_only)
+{
+        /*
+         * We first check if the task is freezing and next if it has already
+         * been frozen to avoid the race with frozen_process() which first marks
+         * the task as frozen and next clears its TIF_FREEZE.
+         */
+        if (!freezing(p)) {
+                rmb();
+                if (frozen(p))
+                        return false;
+
+                if (!sig_only || should_send_signal(p))
+                        set_freeze_flag(p);
+                else
+                        return false;
+        }
+
+        if (should_send_signal(p)) {
+                if (!signal_pending(p))
+                        fake_signal_wake_up(p);
+        } else if (sig_only) {
+                return false;
+        } else {
+                wake_up_state(p, TASK_INTERRUPTIBLE);
+        }
+
+        return true;
+}
+
+void cancel_freezing(struct task_struct *p)
+{
+        unsigned long flags;
+
+        if (freezing(p)) {
+                pr_debug("  clean up: %s\n", p->comm);
+                clear_freeze_flag(p);
+                spin_lock_irqsave(&p->sighand->siglock, flags);
+                recalc_sigpending_and_wake(p);
+                spin_unlock_irqrestore(&p->sighand->siglock, flags);
+        }
+}
+
+static int __thaw_process(struct task_struct *p)
+{
+        if (frozen(p)) {
+                p->flags &= ~PF_FROZEN;
+                return 1;
+        }
+        clear_freeze_flag(p);
+        return 0;
+}
+
+/*
+ * Wake up a frozen process
+ *
+ * task_lock() is needed to prevent the race with refrigerator() which may
+ * occur if the freezing of tasks fails.  Namely, without the lock, if the
+ * freezing of tasks failed, thaw_tasks() might have run before a task in
+ * refrigerator() could call frozen_process(), in which case the task would be
+ * frozen and no one would thaw it.
+ */
+int thaw_process(struct task_struct *p)
+{
+        task_lock(p);
+        if (__thaw_process(p) == 1) {
+                task_unlock(p);
+                wake_up_process(p);
+                return 1;
+        }
+        task_unlock(p);
+        return 0;
+}
+EXPORT_SYMBOL(thaw_process);
diff --git a/kernel/futex.c b/kernel/futex.c
index 7d1136e97c14..8af10027514b 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -1296,13 +1296,16 @@ static int futex_wait(u32 __user *uaddr, struct rw_semaphore *fshared,
                 if (!abs_time)
                         schedule();
                 else {
+                        unsigned long slack;
+                        slack = current->timer_slack_ns;
+                        if (rt_task(current))
+                                slack = 0;
                         hrtimer_init_on_stack(&t.timer, CLOCK_MONOTONIC,
                                                 HRTIMER_MODE_ABS);
                         hrtimer_init_sleeper(&t, current);
-                        t.timer.expires = *abs_time;
+                        hrtimer_set_expires_range_ns(&t.timer, *abs_time, slack);
 
-                        hrtimer_start(&t.timer, t.timer.expires,
-                                                HRTIMER_MODE_ABS);
+                        hrtimer_start_expires(&t.timer, HRTIMER_MODE_ABS);
                         if (!hrtimer_active(&t.timer))
                                 t.task = NULL;
 
@@ -1404,7 +1407,7 @@ static int futex_lock_pi(u32 __user *uaddr, struct rw_semaphore *fshared,
                 hrtimer_init_on_stack(&to->timer, CLOCK_REALTIME,
                                       HRTIMER_MODE_ABS);
                 hrtimer_init_sleeper(to, current);
-                to->timer.expires = *time;
+                hrtimer_set_expires(&to->timer, *time);
         }
 
         q.pi_state = NULL;
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index b8e4dce80a74..47e63349d1b2 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -517,7 +517,7 @@ static void hrtimer_force_reprogram(struct hrtimer_cpu_base *cpu_base)
                 if (!base->first)
                         continue;
                 timer = rb_entry(base->first, struct hrtimer, node);
-                expires = ktime_sub(timer->expires, base->offset);
+                expires = ktime_sub(hrtimer_get_expires(timer), base->offset);
                 if (expires.tv64 < cpu_base->expires_next.tv64)
                         cpu_base->expires_next = expires;
         }
@@ -539,10 +539,10 @@ static int hrtimer_reprogram(struct hrtimer *timer,
                              struct hrtimer_clock_base *base)
 {
         ktime_t *expires_next = &__get_cpu_var(hrtimer_bases).expires_next;
-        ktime_t expires = ktime_sub(timer->expires, base->offset);
+        ktime_t expires = ktime_sub(hrtimer_get_expires(timer), base->offset);
         int res;
 
-        WARN_ON_ONCE(timer->expires.tv64 < 0);
+        WARN_ON_ONCE(hrtimer_get_expires_tv64(timer) < 0);
 
         /*
          * When the callback is running, we do not reprogram the clock event
@@ -664,25 +664,17 @@ static inline int hrtimer_enqueue_reprogram(struct hrtimer *timer,
 
                 /* Timer is expired, act upon the callback mode */
                 switch(timer->cb_mode) {
-                case HRTIMER_CB_IRQSAFE_NO_RESTART:
-                        debug_hrtimer_deactivate(timer);
-                        /*
-                         * We can call the callback from here. No restart
-                         * happens, so no danger of recursion
-                         */
-                        BUG_ON(timer->function(timer) != HRTIMER_NORESTART);
-                        return 1;
-                case HRTIMER_CB_IRQSAFE_NO_SOFTIRQ:
+                case HRTIMER_CB_IRQSAFE_PERCPU:
+                case HRTIMER_CB_IRQSAFE_UNLOCKED:
                         /*
                          * This is solely for the sched tick emulation with
                          * dynamic tick support to ensure that we do not
                          * restart the tick right on the edge and end up with
                          * the tick timer in the softirq ! The calling site
-                         * takes care of this.
+                         * takes care of this. Also used for hrtimer sleeper !
                          */
                         debug_hrtimer_deactivate(timer);
                         return 1;
-                case HRTIMER_CB_IRQSAFE:
                 case HRTIMER_CB_SOFTIRQ:
                         /*
                          * Move everything else into the softirq pending list !
@@ -794,7 +786,7 @@ u64 hrtimer_forward(struct hrtimer *timer, ktime_t now, ktime_t interval)
         u64 orun = 1;
         ktime_t delta;
 
-        delta = ktime_sub(now, timer->expires);
+        delta = ktime_sub(now, hrtimer_get_expires(timer));
 
         if (delta.tv64 < 0)
                 return 0;
@@ -806,8 +798,8 @@ u64 hrtimer_forward(struct hrtimer *timer, ktime_t now, ktime_t interval)
                 s64 incr = ktime_to_ns(interval);
 
                 orun = ktime_divns(delta, incr);
-                timer->expires = ktime_add_ns(timer->expires, incr * orun);
-                if (timer->expires.tv64 > now.tv64)
+                hrtimer_add_expires_ns(timer, incr * orun);
+                if (hrtimer_get_expires_tv64(timer) > now.tv64)
                         return orun;
                 /*
                  * This (and the ktime_add() below) is the
@@ -815,7 +807,7 @@ u64 hrtimer_forward(struct hrtimer *timer, ktime_t now, ktime_t interval)
                  */
                 orun++;
         }
-        timer->expires = ktime_add_safe(timer->expires, interval);
+        hrtimer_add_expires(timer, interval);
 
         return orun;
 }
@@ -847,7 +839,8 @@ static void enqueue_hrtimer(struct hrtimer *timer,
                  * We dont care about collisions. Nodes with
                  * the same expiry time stay together.
                  */
-                if (timer->expires.tv64 < entry->expires.tv64) {
+                if (hrtimer_get_expires_tv64(timer) <
+                                hrtimer_get_expires_tv64(entry)) {
                         link = &(*link)->rb_left;
                 } else {
                         link = &(*link)->rb_right;
@@ -944,9 +937,10 @@ remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base)
 }
 
 /**
- * hrtimer_start - (re)start an relative timer on the current CPU
+ * hrtimer_start_range_ns - (re)start an hrtimer on the current CPU
  * @timer:      the timer to be added
  * @tim:        expiry time
+ * @delta_ns:   "slack" range for the timer
  * @mode:       expiry mode: absolute (HRTIMER_ABS) or relative (HRTIMER_REL)
  *
  * Returns:
@@ -954,7 +948,8 @@ remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base)
  *  1 when the timer was active
  */
 int
-hrtimer_start(struct hrtimer *timer, ktime_t tim, const enum hrtimer_mode mode)
+hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, unsigned long delta_ns,
+                        const enum hrtimer_mode mode)
 {
         struct hrtimer_clock_base *base, *new_base;
         unsigned long flags;
@@ -982,7 +977,7 @@ hrtimer_start(struct hrtimer *timer, ktime_t tim, const enum hrtimer_mode mode)
 #endif
         }
 
-        timer->expires = tim;
+        hrtimer_set_expires_range_ns(timer, tim, delta_ns);
 
         timer_stats_hrtimer_set_start_info(timer);
 
@@ -1015,8 +1010,26 @@ hrtimer_start(struct hrtimer *timer, ktime_t tim, const enum hrtimer_mode mode)
 
         return ret;
 }
+EXPORT_SYMBOL_GPL(hrtimer_start_range_ns);
+
+/**
+ * hrtimer_start - (re)start an hrtimer on the current CPU
+ * @timer:      the timer to be added
+ * @tim:        expiry time
+ * @mode:       expiry mode: absolute (HRTIMER_ABS) or relative (HRTIMER_REL)
+ *
+ * Returns:
+ *  0 on success
+ *  1 when the timer was active
+ */
+int
+hrtimer_start(struct hrtimer *timer, ktime_t tim, const enum hrtimer_mode mode)
+{
+        return hrtimer_start_range_ns(timer, tim, 0, mode);
+}
 EXPORT_SYMBOL_GPL(hrtimer_start);
 
+
 /**
  * hrtimer_try_to_cancel - try to deactivate a timer
  * @timer:      hrtimer to stop
@@ -1076,7 +1089,7 @@ ktime_t hrtimer_get_remaining(const struct hrtimer *timer)
         ktime_t rem;
 
         base = lock_hrtimer_base(timer, &flags);
-        rem = ktime_sub(timer->expires, base->get_time());
+        rem = hrtimer_expires_remaining(timer);
         unlock_hrtimer_base(timer, &flags);
 
         return rem;
@@ -1108,7 +1121,7 @@ ktime_t hrtimer_get_next_event(void)
                                 continue;
 
                         timer = rb_entry(base->first, struct hrtimer, node);
-                        delta.tv64 = timer->expires.tv64;
+                        delta.tv64 = hrtimer_get_expires_tv64(timer);
                         delta = ktime_sub(delta, base->get_time());
                         if (delta.tv64 < mindelta.tv64)
                                 mindelta.tv64 = delta.tv64;
@@ -1187,6 +1200,7 @@ static void run_hrtimer_pending(struct hrtimer_cpu_base *cpu_base)
                 enum hrtimer_restart (*fn)(struct hrtimer *);
                 struct hrtimer *timer;
                 int restart;
+                int emulate_hardirq_ctx = 0;
 
                 timer = list_entry(cpu_base->cb_pending.next,
                                    struct hrtimer, cb_entry);
@@ -1195,10 +1209,24 @@ static void run_hrtimer_pending(struct hrtimer_cpu_base *cpu_base)
                 timer_stats_account_hrtimer(timer);
 
                 fn = timer->function;
+                /*
+                 * A timer might have been added to the cb_pending list
+                 * when it was migrated during a cpu-offline operation.
+                 * Emulate hardirq context for such timers.
+                 */
+                if (timer->cb_mode == HRTIMER_CB_IRQSAFE_PERCPU ||
+                    timer->cb_mode == HRTIMER_CB_IRQSAFE_UNLOCKED)
+                        emulate_hardirq_ctx = 1;
+
                 __remove_hrtimer(timer, timer->base, HRTIMER_STATE_CALLBACK, 0);
                 spin_unlock_irq(&cpu_base->lock);
 
-                restart = fn(timer);
+                if (unlikely(emulate_hardirq_ctx)) {
+                        local_irq_disable();
+                        restart = fn(timer);
+                        local_irq_enable();
+                } else
+                        restart = fn(timer);
 
                 spin_lock_irq(&cpu_base->lock);
 
@@ -1245,7 +1273,8 @@ static void __run_hrtimer(struct hrtimer *timer)
         timer_stats_account_hrtimer(timer);
 
         fn = timer->function;
-        if (timer->cb_mode == HRTIMER_CB_IRQSAFE_NO_SOFTIRQ) {
+        if (timer->cb_mode == HRTIMER_CB_IRQSAFE_PERCPU ||
+            timer->cb_mode == HRTIMER_CB_IRQSAFE_UNLOCKED) {
                 /*
                  * Used for scheduler timers, avoid lock inversion with
                  * rq->lock and tasklist_lock.
@@ -1308,10 +1337,23 @@ void hrtimer_interrupt(struct clock_event_device *dev)
 
                         timer = rb_entry(node, struct hrtimer, node);
 
-                        if (basenow.tv64 < timer->expires.tv64) {
+                        /*
+                         * The immediate goal for using the softexpires is
+                         * minimizing wakeups, not running timers at the
+                         * earliest interrupt after their soft expiration.
+                         * This allows us to avoid using a Priority Search
+                         * Tree, which can answer a stabbing querry for
+                         * overlapping intervals and instead use the simple
+                         * BST we already have.
+                         * We don't add extra wakeups by delaying timers that
+                         * are right-of a not yet expired timer, because that
+                         * timer will have to trigger a wakeup anyway.
+                         */
+
+                        if (basenow.tv64 < hrtimer_get_softexpires_tv64(timer)) {
                                 ktime_t expires;
 
-                                expires = ktime_sub(timer->expires,
+                                expires = ktime_sub(hrtimer_get_expires(timer),
                                                     base->offset);
                                 if (expires.tv64 < expires_next.tv64)
                                         expires_next = expires;
@@ -1347,6 +1389,30 @@ void hrtimer_interrupt(struct clock_event_device *dev)
                 raise_softirq(HRTIMER_SOFTIRQ);
 }
 
+/**
+ * hrtimer_peek_ahead_timers -- run soft-expired timers now
+ *
+ * hrtimer_peek_ahead_timers will peek at the timer queue of
+ * the current cpu and check if there are any timers for which
+ * the soft expires time has passed. If any such timers exist,
+ * they are run immediately and then removed from the timer queue.
+ *
+ */
+void hrtimer_peek_ahead_timers(void)
+{
+        struct tick_device *td;
+        unsigned long flags;
+
+        if (!hrtimer_hres_active())
+                return;
+
+        local_irq_save(flags);
+        td = &__get_cpu_var(tick_cpu_device);
+        if (td && td->evtdev)
+                hrtimer_interrupt(td->evtdev);
+        local_irq_restore(flags);
+}
+
 static void run_hrtimer_softirq(struct softirq_action *h)
 {
         run_hrtimer_pending(&__get_cpu_var(hrtimer_bases));
@@ -1401,9 +1467,7 @@ void hrtimer_run_queues(void)
                 if (!base->first)
                         continue;
 
-                if (base->get_softirq_time)
-                        base->softirq_time = base->get_softirq_time();
-                else if (gettime) {
+                if (gettime) {
                         hrtimer_get_softirq_time(cpu_base);
                         gettime = 0;
                 }
@@ -1414,7 +1478,8 @@ void hrtimer_run_queues(void)
                         struct hrtimer *timer;
 
                         timer = rb_entry(node, struct hrtimer, node);
-                        if (base->softirq_time.tv64 <= timer->expires.tv64)
+                        if (base->softirq_time.tv64 <=
+                                        hrtimer_get_expires_tv64(timer))
                                 break;
 
                         if (timer->cb_mode == HRTIMER_CB_SOFTIRQ) {
@@ -1452,7 +1517,7 @@ void hrtimer_init_sleeper(struct hrtimer_sleeper *sl, struct task_struct *task)
         sl->timer.function = hrtimer_wakeup;
         sl->task = task;
 #ifdef CONFIG_HIGH_RES_TIMERS
-        sl->timer.cb_mode = HRTIMER_CB_IRQSAFE_NO_SOFTIRQ;
+        sl->timer.cb_mode = HRTIMER_CB_IRQSAFE_UNLOCKED;
 #endif
 }
 
@@ -1462,7 +1527,7 @@ static int __sched do_nanosleep(struct hrtimer_sleeper *t, enum hrtimer_mode mod
 
         do {
                 set_current_state(TASK_INTERRUPTIBLE);
-                hrtimer_start(&t->timer, t->timer.expires, mode);
+                hrtimer_start_expires(&t->timer, mode);
                 if (!hrtimer_active(&t->timer))
                         t->task = NULL;
 
@@ -1484,7 +1549,7 @@ static int update_rmtp(struct hrtimer *timer, struct timespec __user *rmtp)
         struct timespec rmt;
         ktime_t rem;
 
-        rem = ktime_sub(timer->expires, timer->base->get_time());
+        rem = hrtimer_expires_remaining(timer);
         if (rem.tv64 <= 0)
                 return 0;
         rmt = ktime_to_timespec(rem);
@@ -1503,7 +1568,7 @@ long __sched hrtimer_nanosleep_restart(struct restart_block *restart)
 
         hrtimer_init_on_stack(&t.timer, restart->nanosleep.index,
                                 HRTIMER_MODE_ABS);
-        t.timer.expires.tv64 = restart->nanosleep.expires;
+        hrtimer_set_expires_tv64(&t.timer, restart->nanosleep.expires);
 
         if (do_nanosleep(&t, HRTIMER_MODE_ABS))
                 goto out;
@@ -1528,9 +1593,14 @@ long hrtimer_nanosleep(struct timespec *rqtp, struct timespec __user *rmtp,
         struct restart_block *restart;
         struct hrtimer_sleeper t;
         int ret = 0;
+        unsigned long slack;
+
+        slack = current->timer_slack_ns;
+        if (rt_task(current))
+                slack = 0;
 
         hrtimer_init_on_stack(&t.timer, clockid, mode);
-        t.timer.expires = timespec_to_ktime(*rqtp);
+        hrtimer_set_expires_range_ns(&t.timer, timespec_to_ktime(*rqtp), slack);
         if (do_nanosleep(&t, mode))
                 goto out;
 
@@ -1550,7 +1620,7 @@ long hrtimer_nanosleep(struct timespec *rqtp, struct timespec __user *rmtp,
         restart->fn = hrtimer_nanosleep_restart;
         restart->nanosleep.index = t.timer.base->index;
         restart->nanosleep.rmtp = rmtp;
-        restart->nanosleep.expires = t.timer.expires.tv64;
+        restart->nanosleep.expires = hrtimer_get_expires_tv64(&t.timer);
 
         ret = -ERESTART_RESTARTBLOCK;
 out:
@@ -1591,49 +1661,123 @@ static void __cpuinit init_hrtimers_cpu(int cpu)
 
 #ifdef CONFIG_HOTPLUG_CPU
 
-static void migrate_hrtimer_list(struct hrtimer_clock_base *old_base,
-                                struct hrtimer_clock_base *new_base)
+static int migrate_hrtimer_list(struct hrtimer_clock_base *old_base,
+                                struct hrtimer_clock_base *new_base, int dcpu)
 {
         struct hrtimer *timer;
         struct rb_node *node;
+        int raise = 0;
 
         while ((node = rb_first(&old_base->active))) {
                 timer = rb_entry(node, struct hrtimer, node);
                 BUG_ON(hrtimer_callback_running(timer));
                 debug_hrtimer_deactivate(timer);
-                __remove_hrtimer(timer, old_base, HRTIMER_STATE_INACTIVE, 0);
+
+                /*
+                 * Should not happen. Per CPU timers should be
+                 * canceled _before_ the migration code is called
+                 */
+                if (timer->cb_mode == HRTIMER_CB_IRQSAFE_PERCPU) {
+                        __remove_hrtimer(timer, old_base,
+                                         HRTIMER_STATE_INACTIVE, 0);
+                        WARN(1, "hrtimer (%p %p)active but cpu %d dead\n",
+                             timer, timer->function, dcpu);
+                        continue;
+                }
+
+                /*
+                 * Mark it as STATE_MIGRATE not INACTIVE otherwise the
+                 * timer could be seen as !active and just vanish away
+                 * under us on another CPU
+                 */
+                __remove_hrtimer(timer, old_base, HRTIMER_STATE_MIGRATE, 0);
                 timer->base = new_base;
                 /*
                  * Enqueue the timer. Allow reprogramming of the event device
                  */
                 enqueue_hrtimer(timer, new_base, 1);
+
+#ifdef CONFIG_HIGH_RES_TIMERS
+                /*
+                 * Happens with high res enabled when the timer was
+                 * already expired and the callback mode is
+                 * HRTIMER_CB_IRQSAFE_UNLOCKED (hrtimer_sleeper). The
+                 * enqueue code does not move them to the soft irq
+                 * pending list for performance/latency reasons, but
+                 * in the migration state, we need to do that
+                 * otherwise we end up with a stale timer.
+                 */
+                if (timer->state == HRTIMER_STATE_MIGRATE) {
+                        timer->state = HRTIMER_STATE_PENDING;
+                        list_add_tail(&timer->cb_entry,
+                                      &new_base->cpu_base->cb_pending);
+                        raise = 1;
+                }
+#endif
+                /* Clear the migration state bit */
+                timer->state &= ~HRTIMER_STATE_MIGRATE;
+        }
+        return raise;
+}
+
+#ifdef CONFIG_HIGH_RES_TIMERS
+static int migrate_hrtimer_pending(struct hrtimer_cpu_base *old_base,
+                                   struct hrtimer_cpu_base *new_base)
+{
+        struct hrtimer *timer;
+        int raise = 0;
+
+        while (!list_empty(&old_base->cb_pending)) {
+                timer = list_entry(old_base->cb_pending.next,
+                                   struct hrtimer, cb_entry);
+
+                __remove_hrtimer(timer, timer->base, HRTIMER_STATE_PENDING, 0);
+                timer->base = &new_base->clock_base[timer->base->index];
+                list_add_tail(&timer->cb_entry, &new_base->cb_pending);
+                raise = 1;
         }
+        return raise;
+}
+#else
+static int migrate_hrtimer_pending(struct hrtimer_cpu_base *old_base,
+                                   struct hrtimer_cpu_base *new_base)
+{
+        return 0;
 }
+#endif
 
 static void migrate_hrtimers(int cpu)
 {
         struct hrtimer_cpu_base *old_base, *new_base;
-        int i;
+        int i, raise = 0;
 
         BUG_ON(cpu_online(cpu));
         old_base = &per_cpu(hrtimer_bases, cpu);
         new_base = &get_cpu_var(hrtimer_bases);
 
         tick_cancel_sched_timer(cpu);
-
-        local_irq_disable();
-        spin_lock(&new_base->lock);
+        /*
+         * The caller is globally serialized and nobody else
+         * takes two locks at once, deadlock is not possible.
+         */
+        spin_lock_irq(&new_base->lock);
         spin_lock_nested(&old_base->lock, SINGLE_DEPTH_NESTING);
 
         for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) {
-                migrate_hrtimer_list(&old_base->clock_base[i],
-                                     &new_base->clock_base[i]);
+                if (migrate_hrtimer_list(&old_base->clock_base[i],
+                                         &new_base->clock_base[i], cpu))
+                        raise = 1;
         }
 
+        if (migrate_hrtimer_pending(old_base, new_base))
+                raise = 1;
+
         spin_unlock(&old_base->lock);
-        spin_unlock(&new_base->lock);
-        local_irq_enable();
+        spin_unlock_irq(&new_base->lock);
         put_cpu_var(hrtimer_bases);
+
+        if (raise)
+                hrtimer_raise_softirq();
 }
 #endif /* CONFIG_HOTPLUG_CPU */
 
@@ -1678,3 +1822,103 @@ void __init hrtimers_init(void)
 #endif
 }
 
+/**
+ * schedule_hrtimeout_range - sleep until timeout
+ * @expires:    timeout value (ktime_t)
+ * @delta:      slack in expires timeout (ktime_t)
+ * @mode:       timer mode, HRTIMER_MODE_ABS or HRTIMER_MODE_REL
+ *
+ * Make the current task sleep until the given expiry time has
+ * elapsed. The routine will return immediately unless
+ * the current task state has been set (see set_current_state()).
+ *
+ * The @delta argument gives the kernel the freedom to schedule the
+ * actual wakeup to a time that is both power and performance friendly.
+ * The kernel give the normal best effort behavior for "@expires+@delta",
+ * but may decide to fire the timer earlier, but no earlier than @expires.
+ *
+ * You can set the task state as follows -
+ *
+ * %TASK_UNINTERRUPTIBLE - at least @timeout time is guaranteed to
+ * pass before the routine returns.
+ *
+ * %TASK_INTERRUPTIBLE - the routine may return early if a signal is
+ * delivered to the current task.
+ *
+ * The current task state is guaranteed to be TASK_RUNNING when this
+ * routine returns.
+ *
+ * Returns 0 when the timer has expired otherwise -EINTR
+ */
+int __sched schedule_hrtimeout_range(ktime_t *expires, unsigned long delta,
+                               const enum hrtimer_mode mode)
+{
+        struct hrtimer_sleeper t;
+
+        /*
+         * Optimize when a zero timeout value is given. It does not
+         * matter whether this is an absolute or a relative time.
+         */
+        if (expires && !expires->tv64) {
+                __set_current_state(TASK_RUNNING);
+                return 0;
+        }
+
+        /*
+         * A NULL parameter means "inifinte"
+         */
+        if (!expires) {
+                schedule();
+                __set_current_state(TASK_RUNNING);
+                return -EINTR;
+        }
+
+        hrtimer_init_on_stack(&t.timer, CLOCK_MONOTONIC, mode);
+        hrtimer_set_expires_range_ns(&t.timer, *expires, delta);
+
+        hrtimer_init_sleeper(&t, current);
+
+        hrtimer_start_expires(&t.timer, mode);
+        if (!hrtimer_active(&t.timer))
+                t.task = NULL;
+
+        if (likely(t.task))
+                schedule();
+
+        hrtimer_cancel(&t.timer);
+        destroy_hrtimer_on_stack(&t.timer);
+
+        __set_current_state(TASK_RUNNING);
+
+        return !t.task ? 0 : -EINTR;
+}
+EXPORT_SYMBOL_GPL(schedule_hrtimeout_range);
+
+/**
+ * schedule_hrtimeout - sleep until timeout
+ * @expires:    timeout value (ktime_t)
+ * @mode:       timer mode, HRTIMER_MODE_ABS or HRTIMER_MODE_REL
+ *
+ * Make the current task sleep until the given expiry time has
+ * elapsed. The routine will return immediately unless
+ * the current task state has been set (see set_current_state()).
+ *
+ * You can set the task state as follows -
+ *
+ * %TASK_UNINTERRUPTIBLE - at least @timeout time is guaranteed to
+ * pass before the routine returns.
+ *
+ * %TASK_INTERRUPTIBLE - the routine may return early if a signal is
+ * delivered to the current task.
+ *
+ * The current task state is guaranteed to be TASK_RUNNING when this
+ * routine returns.
+ *
+ * Returns 0 when the timer has expired otherwise -EINTR
+ */
+int __sched schedule_hrtimeout(ktime_t *expires,
+                               const enum hrtimer_mode mode)
+{
+        return schedule_hrtimeout_range(expires, 0, mode);
+}
+EXPORT_SYMBOL_GPL(schedule_hrtimeout);
diff --git a/kernel/irq/autoprobe.c b/kernel/irq/autoprobe.c
index 533068cfb607..cc0f7321b8ce 100644
--- a/kernel/irq/autoprobe.c
+++ b/kernel/irq/autoprobe.c
@@ -30,17 +30,16 @@ static DEFINE_MUTEX(probing_active);
 unsigned long probe_irq_on(void)
 {
         struct irq_desc *desc;
-        unsigned long mask;
-        unsigned int i;
+        unsigned long mask = 0;
+        unsigned int status;
+        int i;
 
         mutex_lock(&probing_active);
         /*
          * something may have generated an irq long ago and we want to
          * flush such a longstanding irq before considering it as spurious.
          */
-        for (i = NR_IRQS-1; i > 0; i--) {
-                desc = irq_desc + i;
-
+        for_each_irq_desc_reverse(i, desc) {
                 spin_lock_irq(&desc->lock);
                 if (!desc->action && !(desc->status & IRQ_NOPROBE)) {
                         /*
@@ -68,9 +67,7 @@ unsigned long probe_irq_on(void)
          * (we must startup again here because if a longstanding irq
          * happened in the previous stage, it may have masked itself)
          */
-        for (i = NR_IRQS-1; i > 0; i--) {
-                desc = irq_desc + i;
-
+        for_each_irq_desc_reverse(i, desc) {
                 spin_lock_irq(&desc->lock);
                 if (!desc->action && !(desc->status & IRQ_NOPROBE)) {
                         desc->status |= IRQ_AUTODETECT | IRQ_WAITING;
@@ -88,11 +85,7 @@ unsigned long probe_irq_on(void)
         /*
          * Now filter out any obviously spurious interrupts
          */
-        mask = 0;
-        for (i = 0; i < NR_IRQS; i++) {
-                unsigned int status;
-
-                desc = irq_desc + i;
+        for_each_irq_desc(i, desc) {
                 spin_lock_irq(&desc->lock);
                 status = desc->status;
 
@@ -126,14 +119,11 @@ EXPORT_SYMBOL(probe_irq_on);
  */
 unsigned int probe_irq_mask(unsigned long val)
 {
-        unsigned int mask;
+        unsigned int status, mask = 0;
+        struct irq_desc *desc;
         int i;
 
-        mask = 0;
-        for (i = 0; i < NR_IRQS; i++) {
-                struct irq_desc *desc = irq_desc + i;
-                unsigned int status;
-
+        for_each_irq_desc(i, desc) {
                 spin_lock_irq(&desc->lock);
                 status = desc->status;
 
@@ -171,20 +161,19 @@ EXPORT_SYMBOL(probe_irq_mask);
  */
 int probe_irq_off(unsigned long val)
 {
-        int i, irq_found = 0, nr_irqs = 0;
-
-        for (i = 0; i < NR_IRQS; i++) {
-                struct irq_desc *desc = irq_desc + i;
-                unsigned int status;
+        int i, irq_found = 0, nr_of_irqs = 0;
+        struct irq_desc *desc;
+        unsigned int status;
 
+        for_each_irq_desc(i, desc) {
                 spin_lock_irq(&desc->lock);
                 status = desc->status;
 
                 if (status & IRQ_AUTODETECT) {
                         if (!(status & IRQ_WAITING)) {
-                                if (!nr_irqs)
+                                if (!nr_of_irqs)
                                         irq_found = i;
-                                nr_irqs++;
+                                nr_of_irqs++;
                         }
                         desc->status = status & ~IRQ_AUTODETECT;
                         desc->chip->shutdown(i);
@@ -193,7 +182,7 @@ int probe_irq_off(unsigned long val)
         }
         mutex_unlock(&probing_active);
 
-        if (nr_irqs > 1)
+        if (nr_of_irqs > 1)
                 irq_found = -irq_found;
 
         return irq_found;
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index 3cd441ebf5d2..10b5092e9bfe 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -24,16 +24,15 @@
  */
 void dynamic_irq_init(unsigned int irq)
 {
-        struct irq_desc *desc;
+        struct irq_desc *desc = irq_to_desc(irq);
         unsigned long flags;
 
-        if (irq >= NR_IRQS) {
+        if (!desc) {
                 WARN(1, KERN_ERR "Trying to initialize invalid IRQ%d\n", irq);
                 return;
         }
 
         /* Ensure we don't have left over values from a previous use of this irq */
-        desc = irq_desc + irq;
         spin_lock_irqsave(&desc->lock, flags);
         desc->status = IRQ_DISABLED;
         desc->chip = &no_irq_chip;
@@ -57,15 +56,14 @@ void dynamic_irq_init(unsigned int irq)
  */
 void dynamic_irq_cleanup(unsigned int irq)
 {
-        struct irq_desc *desc;
+        struct irq_desc *desc = irq_to_desc(irq);
         unsigned long flags;
 
-        if (irq >= NR_IRQS) {
+        if (!desc) {
                 WARN(1, KERN_ERR "Trying to cleanup invalid IRQ%d\n", irq);
                 return;
         }
 
-        desc = irq_desc + irq;
         spin_lock_irqsave(&desc->lock, flags);
         if (desc->action) {
                 spin_unlock_irqrestore(&desc->lock, flags);
@@ -78,6 +76,7 @@ void dynamic_irq_cleanup(unsigned int irq)
         desc->chip_data = NULL;
         desc->handle_irq = handle_bad_irq;
         desc->chip = &no_irq_chip;
+        desc->name = NULL;
         spin_unlock_irqrestore(&desc->lock, flags);
 }
 
@@ -89,10 +88,10 @@ void dynamic_irq_cleanup(unsigned int irq)
  */
 int set_irq_chip(unsigned int irq, struct irq_chip *chip)
 {
-        struct irq_desc *desc;
+        struct irq_desc *desc = irq_to_desc(irq);
         unsigned long flags;
 
-        if (irq >= NR_IRQS) {
+        if (!desc) {
                 WARN(1, KERN_ERR "Trying to install chip for IRQ%d\n", irq);
                 return -EINVAL;
         }
@@ -100,7 +99,6 @@ int set_irq_chip(unsigned int irq, struct irq_chip *chip)
         if (!chip)
                 chip = &no_irq_chip;
 
-        desc = irq_desc + irq;
         spin_lock_irqsave(&desc->lock, flags);
         irq_chip_set_defaults(chip);
         desc->chip = chip;
@@ -111,27 +109,27 @@ int set_irq_chip(unsigned int irq, struct irq_chip *chip)
 EXPORT_SYMBOL(set_irq_chip);
 
 /**
- *      set_irq_type - set the irq type for an irq
+ *      set_irq_type - set the irq trigger type for an irq
  *      @irq:   irq number
- *      @type:  interrupt type - see include/linux/interrupt.h
+ *      @type:  IRQ_TYPE_{LEVEL,EDGE}_* value - see include/linux/irq.h
  */
 int set_irq_type(unsigned int irq, unsigned int type)
 {
-        struct irq_desc *desc;
+        struct irq_desc *desc = irq_to_desc(irq);
         unsigned long flags;
         int ret = -ENXIO;
 
-        if (irq >= NR_IRQS) {
+        if (!desc) {
                 printk(KERN_ERR "Trying to set irq type for IRQ%d\n", irq);
                 return -ENODEV;
         }
 
-        desc = irq_desc + irq;
-        if (desc->chip->set_type) {
-                spin_lock_irqsave(&desc->lock, flags);
-                ret = desc->chip->set_type(irq, type);
-                spin_unlock_irqrestore(&desc->lock, flags);
-        }
+        if (type == IRQ_TYPE_NONE)
+                return 0;
+
+        spin_lock_irqsave(&desc->lock, flags);
+        ret = __irq_set_trigger(desc, irq, type);
+        spin_unlock_irqrestore(&desc->lock, flags);
         return ret;
 }
 EXPORT_SYMBOL(set_irq_type);
@@ -145,16 +143,15 @@ EXPORT_SYMBOL(set_irq_type);
  */
 int set_irq_data(unsigned int irq, void *data)
 {
-        struct irq_desc *desc;
+        struct irq_desc *desc = irq_to_desc(irq);
         unsigned long flags;
 
-        if (irq >= NR_IRQS) {
+        if (!desc) {
                 printk(KERN_ERR
                        "Trying to install controller data for IRQ%d\n", irq);
                 return -EINVAL;
         }
 
-        desc = irq_desc + irq;
         spin_lock_irqsave(&desc->lock, flags);
         desc->handler_data = data;
         spin_unlock_irqrestore(&desc->lock, flags);
@@ -171,15 +168,15 @@ EXPORT_SYMBOL(set_irq_data);
  */
 int set_irq_msi(unsigned int irq, struct msi_desc *entry)
 {
-        struct irq_desc *desc;
+        struct irq_desc *desc = irq_to_desc(irq);
         unsigned long flags;
 
-        if (irq >= NR_IRQS) {
+        if (!desc) {
                 printk(KERN_ERR
                        "Trying to install msi data for IRQ%d\n", irq);
                 return -EINVAL;
         }
-        desc = irq_desc + irq;
+
         spin_lock_irqsave(&desc->lock, flags);
         desc->msi_desc = entry;
         if (entry)
@@ -197,10 +194,16 @@ int set_irq_msi(unsigned int irq, struct msi_desc *entry)
  */
 int set_irq_chip_data(unsigned int irq, void *data)
 {
-        struct irq_desc *desc = irq_desc + irq;
+        struct irq_desc *desc = irq_to_desc(irq);
         unsigned long flags;
 
-        if (irq >= NR_IRQS || !desc->chip) {
+        if (!desc) {
+                printk(KERN_ERR
+                       "Trying to install chip data for IRQ%d\n", irq);
+                return -EINVAL;
+        }
+
+        if (!desc->chip) {
                 printk(KERN_ERR "BUG: bad set_irq_chip_data(IRQ#%d)\n", irq);
                 return -EINVAL;
         }
@@ -218,7 +221,7 @@ EXPORT_SYMBOL(set_irq_chip_data);
  */
 static void default_enable(unsigned int irq)
 {
-        struct irq_desc *desc = irq_desc + irq;
+        struct irq_desc *desc = irq_to_desc(irq);
 
         desc->chip->unmask(irq);
         desc->status &= ~IRQ_MASKED;
@@ -236,8 +239,9 @@ static void default_disable(unsigned int irq)
  */
 static unsigned int default_startup(unsigned int irq)
 {
-        irq_desc[irq].chip->enable(irq);
+        struct irq_desc *desc = irq_to_desc(irq);
 
+        desc->chip->enable(irq);
         return 0;
 }
 
@@ -246,7 +250,7 @@ static unsigned int default_startup(unsigned int irq)
  */
 static void default_shutdown(unsigned int irq)
 {
-        struct irq_desc *desc = irq_desc + irq;
+        struct irq_desc *desc = irq_to_desc(irq);
 
         desc->chip->mask(irq);
         desc->status |= IRQ_MASKED;
@@ -305,14 +309,13 @@ handle_simple_irq(unsigned int irq, struct irq_desc *desc)
 {
         struct irqaction *action;
         irqreturn_t action_ret;
-        const unsigned int cpu = smp_processor_id();
 
         spin_lock(&desc->lock);
 
         if (unlikely(desc->status & IRQ_INPROGRESS))
                 goto out_unlock;
         desc->status &= ~(IRQ_REPLAY | IRQ_WAITING);
-        kstat_cpu(cpu).irqs[irq]++;
+        kstat_incr_irqs_this_cpu(irq, desc);
 
         action = desc->action;
         if (unlikely(!action || (desc->status & IRQ_DISABLED)))
@@ -344,7 +347,6 @@ out_unlock:
 void
 handle_level_irq(unsigned int irq, struct irq_desc *desc)
 {
-        unsigned int cpu = smp_processor_id();
         struct irqaction *action;
         irqreturn_t action_ret;
 
@@ -354,7 +356,7 @@ handle_level_irq(unsigned int irq, struct irq_desc *desc)
         if (unlikely(desc->status & IRQ_INPROGRESS))
                 goto out_unlock;
         desc->status &= ~(IRQ_REPLAY | IRQ_WAITING);
-        kstat_cpu(cpu).irqs[irq]++;
+        kstat_incr_irqs_this_cpu(irq, desc);
 
         /*
          * If its disabled or no action available
@@ -392,7 +394,6 @@ out_unlock:
 void
 handle_fasteoi_irq(unsigned int irq, struct irq_desc *desc)
 {
-        unsigned int cpu = smp_processor_id();
         struct irqaction *action;
         irqreturn_t action_ret;
 
@@ -402,7 +403,7 @@ handle_fasteoi_irq(unsigned int irq, struct irq_desc *desc)
                 goto out;
 
         desc->status &= ~(IRQ_REPLAY | IRQ_WAITING);
-        kstat_cpu(cpu).irqs[irq]++;
+        kstat_incr_irqs_this_cpu(irq, desc);
 
         /*
          * If its disabled or no action available
@@ -451,8 +452,6 @@ out:
 void
 handle_edge_irq(unsigned int irq, struct irq_desc *desc)
 {
-        const unsigned int cpu = smp_processor_id();
-
         spin_lock(&desc->lock);
 
         desc->status &= ~(IRQ_REPLAY | IRQ_WAITING);
@@ -468,8 +467,7 @@ handle_edge_irq(unsigned int irq, struct irq_desc *desc)
                 mask_ack_irq(desc, irq);
                 goto out_unlock;
         }
-
-        kstat_cpu(cpu).irqs[irq]++;
+        kstat_incr_irqs_this_cpu(irq, desc);
 
         /* Start handling the irq */
         desc->chip->ack(irq);
@@ -524,7 +522,7 @@ handle_percpu_irq(unsigned int irq, struct irq_desc *desc)
 {
         irqreturn_t action_ret;
 
-        kstat_this_cpu.irqs[irq]++;
+        kstat_incr_irqs_this_cpu(irq, desc);
 
         if (desc->chip->ack)
                 desc->chip->ack(irq);
@@ -541,17 +539,15 @@ void
 __set_irq_handler(unsigned int irq, irq_flow_handler_t handle, int is_chained,
                   const char *name)
 {
-        struct irq_desc *desc;
+        struct irq_desc *desc = irq_to_desc(irq);
         unsigned long flags;
 
-        if (irq >= NR_IRQS) {
+        if (!desc) {
                 printk(KERN_ERR
                        "Trying to install type control for IRQ%d\n", irq);
                 return;
         }
 
-        desc = irq_desc + irq;
-
         if (!handle)
                 handle = handle_bad_irq;
         else if (desc->chip == &no_irq_chip) {
@@ -583,7 +579,7 @@ __set_irq_handler(unsigned int irq, irq_flow_handler_t handle, int is_chained,
                 desc->status &= ~IRQ_DISABLED;
                 desc->status |= IRQ_NOREQUEST | IRQ_NOPROBE;
                 desc->depth = 0;
-                desc->chip->unmask(irq);
+                desc->chip->startup(irq);
         }
         spin_unlock_irqrestore(&desc->lock, flags);
 }
@@ -606,17 +602,14 @@ set_irq_chip_and_handler_name(unsigned int irq, struct irq_chip *chip,
 
 void __init set_irq_noprobe(unsigned int irq)
 {
-        struct irq_desc *desc;
+        struct irq_desc *desc = irq_to_desc(irq);
         unsigned long flags;
 
-        if (irq >= NR_IRQS) {
+        if (!desc) {
                 printk(KERN_ERR "Trying to mark IRQ%d non-probeable\n", irq);
-
                 return;
         }
 
-        desc = irq_desc + irq;
-
         spin_lock_irqsave(&desc->lock, flags);
         desc->status |= IRQ_NOPROBE;
         spin_unlock_irqrestore(&desc->lock, flags);
@@ -624,17 +617,14 @@ void __init set_irq_noprobe(unsigned int irq)
 
 void __init set_irq_probe(unsigned int irq)
 {
-        struct irq_desc *desc;
+        struct irq_desc *desc = irq_to_desc(irq);
         unsigned long flags;
 
-        if (irq >= NR_IRQS) {
+        if (!desc) {
                 printk(KERN_ERR "Trying to mark IRQ%d probeable\n", irq);
-
                 return;
         }
 
-        desc = irq_desc + irq;
-
         spin_lock_irqsave(&desc->lock, flags);
         desc->status &= ~IRQ_NOPROBE;
         spin_unlock_irqrestore(&desc->lock, flags);
diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c
index 5fa6198e9139..c815b42d0f5b 100644
--- a/kernel/irq/handle.c
+++ b/kernel/irq/handle.c
@@ -25,11 +25,10 @@
  *
  * Handles spurious and unhandled IRQ's. It also prints a debugmessage.
  */
-void
-handle_bad_irq(unsigned int irq, struct irq_desc *desc)
+void handle_bad_irq(unsigned int irq, struct irq_desc *desc)
 {
         print_irq_desc(irq, desc);
-        kstat_this_cpu.irqs[irq]++;
+        kstat_incr_irqs_this_cpu(irq, desc);
         ack_bad_irq(irq);
 }
 
@@ -47,6 +46,9 @@ handle_bad_irq(unsigned int irq, struct irq_desc *desc)
  *
  * Controller mappings for all interrupt sources:
  */
+int nr_irqs = NR_IRQS;
+EXPORT_SYMBOL_GPL(nr_irqs);
+
 struct irq_desc irq_desc[NR_IRQS] __cacheline_aligned_in_smp = {
         [0 ... NR_IRQS-1] = {
                 .status = IRQ_DISABLED,
@@ -66,7 +68,9 @@ struct irq_desc irq_desc[NR_IRQS] __cacheline_aligned_in_smp = {
  */
 static void ack_bad(unsigned int irq)
 {
-        print_irq_desc(irq, irq_desc + irq);
+        struct irq_desc *desc = irq_to_desc(irq);
+
+        print_irq_desc(irq, desc);
         ack_bad_irq(irq);
 }
 
@@ -131,8 +135,6 @@ irqreturn_t handle_IRQ_event(unsigned int irq, struct irqaction *action)
         irqreturn_t ret, retval = IRQ_NONE;
         unsigned int status = 0;
 
-        handle_dynamic_tick(action);
-
         if (!(action->flags & IRQF_DISABLED))
                 local_irq_enable_in_hardirq();
 
@@ -165,11 +167,12 @@ irqreturn_t handle_IRQ_event(unsigned int irq, struct irqaction *action)
  */
 unsigned int __do_IRQ(unsigned int irq)
 {
-        struct irq_desc *desc = irq_desc + irq;
+        struct irq_desc *desc = irq_to_desc(irq);
         struct irqaction *action;
         unsigned int status;
 
-        kstat_this_cpu.irqs[irq]++;
+        kstat_incr_irqs_this_cpu(irq, desc);
+
         if (CHECK_IRQ_PER_CPU(desc->status)) {
                 irqreturn_t action_ret;
 
@@ -256,8 +259,8 @@ out:
 }
 #endif
 
-#ifdef CONFIG_TRACE_IRQFLAGS
 
+#ifdef CONFIG_TRACE_IRQFLAGS
 /*
  * lockdep: we want to handle all irq_desc locks as a single lock-class:
  */
@@ -265,10 +268,10 @@ static struct lock_class_key irq_desc_lock_class;
 
 void early_init_irq_lock_class(void)
 {
+        struct irq_desc *desc;
         int i;
 
-        for (i = 0; i < NR_IRQS; i++)
-                lockdep_set_class(&irq_desc[i].lock, &irq_desc_lock_class);
+        for_each_irq_desc(i, desc)
+                lockdep_set_class(&desc->lock, &irq_desc_lock_class);
 }
-
 #endif
diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h
index 08a849a22447..c9767e641980 100644
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -10,12 +10,15 @@ extern void irq_chip_set_defaults(struct irq_chip *chip);
 /* Set default handler: */
 extern void compat_irq_chip_set_default_handler(struct irq_desc *desc);
 
+extern int __irq_set_trigger(struct irq_desc *desc, unsigned int irq,
+                unsigned long flags);
+
 #ifdef CONFIG_PROC_FS
-extern void register_irq_proc(unsigned int irq);
+extern void register_irq_proc(unsigned int irq, struct irq_desc *desc);
 extern void register_handler_proc(unsigned int irq, struct irqaction *action);
 extern void unregister_handler_proc(unsigned int irq, struct irqaction *action);
 #else
-static inline void register_irq_proc(unsigned int irq) { }
+static inline void register_irq_proc(unsigned int irq, struct irq_desc *desc) { }
 static inline void register_handler_proc(unsigned int irq,
                                          struct irqaction *action) { }
 static inline void unregister_handler_proc(unsigned int irq,
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 0314074fa232..c498a1b8c621 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -31,10 +31,10 @@ cpumask_t irq_default_affinity = CPU_MASK_ALL;
  */
 void synchronize_irq(unsigned int irq)
 {
-        struct irq_desc *desc = irq_desc + irq;
+        struct irq_desc *desc = irq_to_desc(irq);
         unsigned int status;
 
-        if (irq >= NR_IRQS)
+        if (!desc)
                 return;
 
         do {
@@ -64,7 +64,7 @@ EXPORT_SYMBOL(synchronize_irq);
  */
 int irq_can_set_affinity(unsigned int irq)
 {
-        struct irq_desc *desc = irq_desc + irq;
+        struct irq_desc *desc = irq_to_desc(irq);
 
         if (CHECK_IRQ_PER_CPU(desc->status) || !desc->chip ||
             !desc->chip->set_affinity)
@@ -81,15 +81,21 @@ int irq_can_set_affinity(unsigned int irq)
  */
 int irq_set_affinity(unsigned int irq, cpumask_t cpumask)
 {
-        struct irq_desc *desc = irq_desc + irq;
+        struct irq_desc *desc = irq_to_desc(irq);
 
         if (!desc->chip->set_affinity)
                 return -EINVAL;
 
-        set_balance_irq_affinity(irq, cpumask);
-
 #ifdef CONFIG_GENERIC_PENDING_IRQ
-        set_pending_irq(irq, cpumask);
+        if (desc->status & IRQ_MOVE_PCNTXT || desc->status & IRQ_DISABLED) {
+                unsigned long flags;
+
+                spin_lock_irqsave(&desc->lock, flags);
+                desc->affinity = cpumask;
+                desc->chip->set_affinity(irq, cpumask);
+                spin_unlock_irqrestore(&desc->lock, flags);
+        } else
+                set_pending_irq(irq, cpumask);
 #else
         desc->affinity = cpumask;
         desc->chip->set_affinity(irq, cpumask);
@@ -104,16 +110,17 @@ int irq_set_affinity(unsigned int irq, cpumask_t cpumask)
 int irq_select_affinity(unsigned int irq)
 {
         cpumask_t mask;
+        struct irq_desc *desc;
 
         if (!irq_can_set_affinity(irq))
                 return 0;
 
         cpus_and(mask, cpu_online_map, irq_default_affinity);
 
-        irq_desc[irq].affinity = mask;
-        irq_desc[irq].chip->set_affinity(irq, mask);
+        desc = irq_to_desc(irq);
+        desc->affinity = mask;
+        desc->chip->set_affinity(irq, mask);
 
-        set_balance_irq_affinity(irq, mask);
         return 0;
 }
 #endif
@@ -133,10 +140,10 @@ int irq_select_affinity(unsigned int irq)
  */
 void disable_irq_nosync(unsigned int irq)
 {
-        struct irq_desc *desc = irq_desc + irq;
+        struct irq_desc *desc = irq_to_desc(irq);
         unsigned long flags;
 
-        if (irq >= NR_IRQS)
+        if (!desc)
                 return;
 
         spin_lock_irqsave(&desc->lock, flags);
@@ -162,9 +169,9 @@ EXPORT_SYMBOL(disable_irq_nosync);
  */
 void disable_irq(unsigned int irq)
 {
-        struct irq_desc *desc = irq_desc + irq;
+        struct irq_desc *desc = irq_to_desc(irq);
 
-        if (irq >= NR_IRQS)
+        if (!desc)
                 return;
 
         disable_irq_nosync(irq);
@@ -204,10 +211,10 @@ static void __enable_irq(struct irq_desc *desc, unsigned int irq)
  */
 void enable_irq(unsigned int irq)
 {
-        struct irq_desc *desc = irq_desc + irq;
+        struct irq_desc *desc = irq_to_desc(irq);
         unsigned long flags;
 
-        if (irq >= NR_IRQS)
+        if (!desc)
                 return;
 
         spin_lock_irqsave(&desc->lock, flags);
@@ -216,9 +223,9 @@ void enable_irq(unsigned int irq)
 }
 EXPORT_SYMBOL(enable_irq);
 
-int set_irq_wake_real(unsigned int irq, unsigned int on)
+static int set_irq_wake_real(unsigned int irq, unsigned int on)
 {
-        struct irq_desc *desc = irq_desc + irq;
+        struct irq_desc *desc = irq_to_desc(irq);
         int ret = -ENXIO;
 
         if (desc->chip->set_wake)
@@ -241,7 +248,7 @@ int set_irq_wake_real(unsigned int irq, unsigned int on)
  */
 int set_irq_wake(unsigned int irq, unsigned int on)
 {
-        struct irq_desc *desc = irq_desc + irq;
+        struct irq_desc *desc = irq_to_desc(irq);
         unsigned long flags;
         int ret = 0;
 
@@ -281,12 +288,16 @@ EXPORT_SYMBOL(set_irq_wake);
  */
 int can_request_irq(unsigned int irq, unsigned long irqflags)
 {
+        struct irq_desc *desc = irq_to_desc(irq);
         struct irqaction *action;
 
-        if (irq >= NR_IRQS || irq_desc[irq].status & IRQ_NOREQUEST)
+        if (!desc)
+                return 0;
+
+        if (desc->status & IRQ_NOREQUEST)
                 return 0;
 
-        action = irq_desc[irq].action;
+        action = desc->action;
         if (action)
                 if (irqflags & action->flags & IRQF_SHARED)
                         action = NULL;
@@ -305,10 +316,11 @@ void compat_irq_chip_set_default_handler(struct irq_desc *desc)
                 desc->handle_irq = NULL;
 }
 
-static int __irq_set_trigger(struct irq_chip *chip, unsigned int irq,
+int __irq_set_trigger(struct irq_desc *desc, unsigned int irq,
                 unsigned long flags)
 {
         int ret;
+        struct irq_chip *chip = desc->chip;
 
         if (!chip || !chip->set_type) {
                 /*
@@ -326,6 +338,11 @@ static int __irq_set_trigger(struct irq_chip *chip, unsigned int irq,
                 pr_err("setting trigger mode %d for irq %u failed (%pF)\n",
                                 (int)(flags & IRQF_TRIGGER_MASK),
                                 irq, chip->set_type);
+        else {
+                /* note that IRQF_TRIGGER_MASK == IRQ_TYPE_SENSE_MASK */
+                desc->status &= ~IRQ_TYPE_SENSE_MASK;
+                desc->status |= flags & IRQ_TYPE_SENSE_MASK;
+        }
 
         return ret;
 }
@@ -334,16 +351,16 @@ static int __irq_set_trigger(struct irq_chip *chip, unsigned int irq,
  * Internal function to register an irqaction - typically used to
  * allocate special interrupts that are part of the architecture.
  */
-int setup_irq(unsigned int irq, struct irqaction *new)
+static int
+__setup_irq(unsigned int irq, struct irq_desc * desc, struct irqaction *new)
 {
-        struct irq_desc *desc = irq_desc + irq;
         struct irqaction *old, **p;
         const char *old_name = NULL;
         unsigned long flags;
         int shared = 0;
         int ret;
 
-        if (irq >= NR_IRQS)
+        if (!desc)
                 return -EINVAL;
 
         if (desc->chip == &no_irq_chip)
@@ -404,7 +421,7 @@ int setup_irq(unsigned int irq, struct irqaction *new)
 
                 /* Setup the type (level, edge polarity) if configured: */
                 if (new->flags & IRQF_TRIGGER_MASK) {
-                        ret = __irq_set_trigger(desc->chip, irq, new->flags);
+                        ret = __irq_set_trigger(desc, irq, new->flags);
 
                         if (ret) {
                                 spin_unlock_irqrestore(&desc->lock, flags);
@@ -423,16 +440,21 @@ int setup_irq(unsigned int irq, struct irqaction *new)
                 if (!(desc->status & IRQ_NOAUTOEN)) {
                         desc->depth = 0;
                         desc->status &= ~IRQ_DISABLED;
-                        if (desc->chip->startup)
-                                desc->chip->startup(irq);
-                        else
-                                desc->chip->enable(irq);
+                        desc->chip->startup(irq);
                 } else
                         /* Undo nested disables: */
                         desc->depth = 1;
 
                 /* Set default affinity mask once everything is setup */
                 irq_select_affinity(irq);
+
+        } else if ((new->flags & IRQF_TRIGGER_MASK)
+                        && (new->flags & IRQF_TRIGGER_MASK)
+                                != (desc->status & IRQ_TYPE_SENSE_MASK)) {
+                /* hope the handler works with the actual trigger mode... */
+                pr_warning("IRQ %d uses trigger mode %d; requested %d\n",
+                                irq, (int)(desc->status & IRQ_TYPE_SENSE_MASK),
+                                (int)(new->flags & IRQF_TRIGGER_MASK));
         }
 
         *p = new;
@@ -457,7 +479,7 @@ int setup_irq(unsigned int irq, struct irqaction *new)
         spin_unlock_irqrestore(&desc->lock, flags);
 
         new->irq = irq;
-        register_irq_proc(irq);
+        register_irq_proc(irq, desc);
         new->dir = NULL;
         register_handler_proc(irq, new);
 
@@ -477,6 +499,20 @@ mismatch:
 }
 
 /**
+ *      setup_irq - setup an interrupt
+ *      @irq: Interrupt line to setup
+ *      @act: irqaction for the interrupt
+ *
+ * Used to statically setup interrupts in the early boot process.
+ */
+int setup_irq(unsigned int irq, struct irqaction *act)
+{
+        struct irq_desc *desc = irq_to_desc(irq);
+
+        return __setup_irq(irq, desc, act);
+}
+
+/**
  *      free_irq - free an interrupt
  *      @irq: Interrupt line to free
  *      @dev_id: Device identity to free
@@ -492,15 +528,15 @@ mismatch:
  */
 void free_irq(unsigned int irq, void *dev_id)
 {
-        struct irq_desc *desc;
+        struct irq_desc *desc = irq_to_desc(irq);
         struct irqaction **p;
         unsigned long flags;
 
         WARN_ON(in_interrupt());
-        if (irq >= NR_IRQS)
+
+        if (!desc)
                 return;
 
-        desc = irq_desc + irq;
         spin_lock_irqsave(&desc->lock, flags);
         p = &desc->action;
         for (;;) {
@@ -589,12 +625,14 @@ EXPORT_SYMBOL(free_irq);
  *      IRQF_SHARED             Interrupt is shared
  *      IRQF_DISABLED   Disable local interrupts while processing
  *      IRQF_SAMPLE_RANDOM      The interrupt can be used for entropy
+ *      IRQF_TRIGGER_*          Specify active edge(s) or level
  *
  */
 int request_irq(unsigned int irq, irq_handler_t handler,
                 unsigned long irqflags, const char *devname, void *dev_id)
 {
         struct irqaction *action;
+        struct irq_desc *desc;
         int retval;
 
 #ifdef CONFIG_LOCKDEP
@@ -611,9 +649,12 @@ int request_irq(unsigned int irq, irq_handler_t handler,
          */
         if ((irqflags & IRQF_SHARED) && !dev_id)
                 return -EINVAL;
-        if (irq >= NR_IRQS)
+
+        desc = irq_to_desc(irq);
+        if (!desc)
                 return -EINVAL;
-        if (irq_desc[irq].status & IRQ_NOREQUEST)
+
+        if (desc->status & IRQ_NOREQUEST)
                 return -EINVAL;
         if (!handler)
                 return -EINVAL;
@@ -629,26 +670,29 @@ int request_irq(unsigned int irq, irq_handler_t handler,
         action->next = NULL;
         action->dev_id = dev_id;
 
+        retval = __setup_irq(irq, desc, action);
+        if (retval)
+                kfree(action);
+
 #ifdef CONFIG_DEBUG_SHIRQ
         if (irqflags & IRQF_SHARED) {
                 /*
                  * It's a shared IRQ -- the driver ought to be prepared for it
                  * to happen immediately, so let's make sure....
-                 * We do this before actually registering it, to make sure that
-                 * a 'real' IRQ doesn't run in parallel with our fake
+                 * We disable the irq to make sure that a 'real' IRQ doesn't
+                 * run in parallel with our fake.
                  */
                 unsigned long flags;
 
+                disable_irq(irq);
                 local_irq_save(flags);
+
                 handler(irq, dev_id);
+
                 local_irq_restore(flags);
+                enable_irq(irq);
         }
 #endif
-
-        retval = setup_irq(irq, action);
-        if (retval)
-                kfree(action);
-
         return retval;
 }
 EXPORT_SYMBOL(request_irq);
diff --git a/kernel/irq/migration.c b/kernel/irq/migration.c
index 77b7acc875c5..90b920d3f52b 100644
--- a/kernel/irq/migration.c
+++ b/kernel/irq/migration.c
@@ -3,18 +3,18 @@
 
 void set_pending_irq(unsigned int irq, cpumask_t mask)
 {
-        struct irq_desc *desc = irq_desc + irq;
+        struct irq_desc *desc = irq_to_desc(irq);
         unsigned long flags;
 
         spin_lock_irqsave(&desc->lock, flags);
         desc->status |= IRQ_MOVE_PENDING;
-        irq_desc[irq].pending_mask = mask;
+        desc->pending_mask = mask;
         spin_unlock_irqrestore(&desc->lock, flags);
 }
 
 void move_masked_irq(int irq)
 {
-        struct irq_desc *desc = irq_desc + irq;
+        struct irq_desc *desc = irq_to_desc(irq);
         cpumask_t tmp;
 
         if (likely(!(desc->status & IRQ_MOVE_PENDING)))
@@ -30,7 +30,7 @@ void move_masked_irq(int irq)
 
         desc->status &= ~IRQ_MOVE_PENDING;
 
-        if (unlikely(cpus_empty(irq_desc[irq].pending_mask)))
+        if (unlikely(cpus_empty(desc->pending_mask)))
                 return;
 
         if (!desc->chip->set_affinity)
@@ -38,7 +38,7 @@ void move_masked_irq(int irq)
 
         assert_spin_locked(&desc->lock);
 
-        cpus_and(tmp, irq_desc[irq].pending_mask, cpu_online_map);
+        cpus_and(tmp, desc->pending_mask, cpu_online_map);
 
         /*
          * If there was a valid mask to work with, please
@@ -55,12 +55,12 @@ void move_masked_irq(int irq)
         if (likely(!cpus_empty(tmp))) {
                 desc->chip->set_affinity(irq,tmp);
         }
-        cpus_clear(irq_desc[irq].pending_mask);
+        cpus_clear(desc->pending_mask);
 }
 
 void move_native_irq(int irq)
 {
-        struct irq_desc *desc = irq_desc + irq;
+        struct irq_desc *desc = irq_to_desc(irq);
 
         if (likely(!(desc->status & IRQ_MOVE_PENDING)))
                 return;
diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c
index a09dd29c2fd7..4d161c70ba55 100644
--- a/kernel/irq/proc.c
+++ b/kernel/irq/proc.c
@@ -19,7 +19,7 @@ static struct proc_dir_entry *root_irq_dir;
 
 static int irq_affinity_proc_show(struct seq_file *m, void *v)
 {
-        struct irq_desc *desc = irq_desc + (long)m->private;
+        struct irq_desc *desc = irq_to_desc((long)m->private);
         cpumask_t *mask = &desc->affinity;
 
 #ifdef CONFIG_GENERIC_PENDING_IRQ
@@ -43,7 +43,7 @@ static ssize_t irq_affinity_proc_write(struct file *file,
         cpumask_t new_value;
         int err;
 
-        if (!irq_desc[irq].chip->set_affinity || no_irq_affinity ||
+        if (!irq_to_desc(irq)->chip->set_affinity || no_irq_affinity ||
             irq_balancing_disabled(irq))
                 return -EIO;
 
@@ -132,20 +132,20 @@ static const struct file_operations default_affinity_proc_fops = {
 static int irq_spurious_read(char *page, char **start, off_t off,
                                   int count, int *eof, void *data)
 {
-        struct irq_desc *d = &irq_desc[(long) data];
+        struct irq_desc *desc = irq_to_desc((long) data);
         return sprintf(page, "count %u\n"
                              "unhandled %u\n"
                              "last_unhandled %u ms\n",
-                        d->irq_count,
-                        d->irqs_unhandled,
-                        jiffies_to_msecs(d->last_unhandled));
+                        desc->irq_count,
+                        desc->irqs_unhandled,
+                        jiffies_to_msecs(desc->last_unhandled));
 }
 
 #define MAX_NAMELEN 128
 
 static int name_unique(unsigned int irq, struct irqaction *new_action)
 {
-        struct irq_desc *desc = irq_desc + irq;
+        struct irq_desc *desc = irq_to_desc(irq);
         struct irqaction *action;
         unsigned long flags;
         int ret = 1;
@@ -165,8 +165,9 @@ static int name_unique(unsigned int irq, struct irqaction *new_action)
 void register_handler_proc(unsigned int irq, struct irqaction *action)
 {
         char name [MAX_NAMELEN];
+        struct irq_desc *desc = irq_to_desc(irq);
 
-        if (!irq_desc[irq].dir || action->dir || !action->name ||
+        if (!desc->dir || action->dir || !action->name ||
                                         !name_unique(irq, action))
                 return;
 
@@ -174,36 +175,34 @@ void register_handler_proc(unsigned int irq, struct irqaction *action)
         snprintf(name, MAX_NAMELEN, "%s", action->name);
 
         /* create /proc/irq/1234/handler/ */
-        action->dir = proc_mkdir(name, irq_desc[irq].dir);
+        action->dir = proc_mkdir(name, desc->dir);
 }
 
 #undef MAX_NAMELEN
 
 #define MAX_NAMELEN 10
 
-void register_irq_proc(unsigned int irq)
+void register_irq_proc(unsigned int irq, struct irq_desc *desc)
 {
         char name [MAX_NAMELEN];
         struct proc_dir_entry *entry;
 
-        if (!root_irq_dir ||
-                (irq_desc[irq].chip == &no_irq_chip) ||
-                        irq_desc[irq].dir)
+        if (!root_irq_dir || (desc->chip == &no_irq_chip) || desc->dir)
                 return;
 
         memset(name, 0, MAX_NAMELEN);
         sprintf(name, "%d", irq);
 
         /* create /proc/irq/1234 */
-        irq_desc[irq].dir = proc_mkdir(name, root_irq_dir);
+        desc->dir = proc_mkdir(name, root_irq_dir);
 
 #ifdef CONFIG_SMP
         /* create /proc/irq/<irq>/smp_affinity */
-        proc_create_data("smp_affinity", 0600, irq_desc[irq].dir,
+        proc_create_data("smp_affinity", 0600, desc->dir,
                          &irq_affinity_proc_fops, (void *)(long)irq);
 #endif
 
-        entry = create_proc_entry("spurious", 0444, irq_desc[irq].dir);
+        entry = create_proc_entry("spurious", 0444, desc->dir);
         if (entry) {
                 entry->data = (void *)(long)irq;
                 entry->read_proc = irq_spurious_read;
@@ -214,11 +213,14 @@ void register_irq_proc(unsigned int irq)
 
 void unregister_handler_proc(unsigned int irq, struct irqaction *action)
 {
-        if (action->dir)
-                remove_proc_entry(action->dir->name, irq_desc[irq].dir);
+        if (action->dir) {
+                struct irq_desc *desc = irq_to_desc(irq);
+
+                remove_proc_entry(action->dir->name, desc->dir);
+        }
 }
 
-void register_default_affinity_proc(void)
+static void register_default_affinity_proc(void)
 {
 #ifdef CONFIG_SMP
         proc_create("irq/default_smp_affinity", 0600, NULL,
@@ -228,7 +230,8 @@ void register_default_affinity_proc(void)
 
 void init_irq_proc(void)
 {
-        int i;
+        unsigned int irq;
+        struct irq_desc *desc;
 
         /* create /proc/irq */
         root_irq_dir = proc_mkdir("irq", NULL);
@@ -240,7 +243,7 @@ void init_irq_proc(void)
         /*
          * Create entries for all existing IRQs.
          */
-        for (i = 0; i < NR_IRQS; i++)
-                register_irq_proc(i);
+        for_each_irq_desc(irq, desc)
+                register_irq_proc(irq, desc);
 }
 
diff --git a/kernel/irq/resend.c b/kernel/irq/resend.c
index a8046791ba2d..89c7117acf2b 100644
--- a/kernel/irq/resend.c
+++ b/kernel/irq/resend.c
@@ -33,10 +33,10 @@ static void resend_irqs(unsigned long arg)
         struct irq_desc *desc;
         int irq;
 
-        while (!bitmap_empty(irqs_resend, NR_IRQS)) {
-                irq = find_first_bit(irqs_resend, NR_IRQS);
+        while (!bitmap_empty(irqs_resend, nr_irqs)) {
+                irq = find_first_bit(irqs_resend, nr_irqs);
                 clear_bit(irq, irqs_resend);
-                desc = irq_desc + irq;
+                desc = irq_to_desc(irq);
                 local_irq_disable();
                 desc->handle_irq(irq, desc);
                 local_irq_enable();
diff --git a/kernel/irq/spurious.c b/kernel/irq/spurious.c
index c66d3f10e853..dd364c11e56e 100644
--- a/kernel/irq/spurious.c
+++ b/kernel/irq/spurious.c
@@ -12,83 +12,122 @@
 #include <linux/kallsyms.h>
 #include <linux/interrupt.h>
 #include <linux/moduleparam.h>
+#include <linux/timer.h>
 
 static int irqfixup __read_mostly;
 
+#define POLL_SPURIOUS_IRQ_INTERVAL (HZ/10)
+static void poll_spurious_irqs(unsigned long dummy);
+static DEFINE_TIMER(poll_spurious_irq_timer, poll_spurious_irqs, 0, 0);
+
 /*
  * Recovery handler for misrouted interrupts.
  */
-static int misrouted_irq(int irq)
+static int try_one_irq(int irq, struct irq_desc *desc)
 {
-        int i;
-        int ok = 0;
-        int work = 0;   /* Did we do work for a real IRQ */
-
-        for (i = 1; i < NR_IRQS; i++) {
-                struct irq_desc *desc = irq_desc + i;
-                struct irqaction *action;
-
-                if (i == irq)   /* Already tried */
-                        continue;
+        struct irqaction *action;
+        int ok = 0, work = 0;
 
-                spin_lock(&desc->lock);
-                /* Already running on another processor */
-                if (desc->status & IRQ_INPROGRESS) {
-                        /*
-                         * Already running: If it is shared get the other
-                         * CPU to go looking for our mystery interrupt too
-                         */
-                        if (desc->action && (desc->action->flags & IRQF_SHARED))
-                                desc->status |= IRQ_PENDING;
-                        spin_unlock(&desc->lock);
-                        continue;
-                }
-                /* Honour the normal IRQ locking */
-                desc->status |= IRQ_INPROGRESS;
-                action = desc->action;
+        spin_lock(&desc->lock);
+        /* Already running on another processor */
+        if (desc->status & IRQ_INPROGRESS) {
+                /*
+                 * Already running: If it is shared get the other
+                 * CPU to go looking for our mystery interrupt too
+                 */
+                if (desc->action && (desc->action->flags & IRQF_SHARED))
+                        desc->status |= IRQ_PENDING;
                 spin_unlock(&desc->lock);
+                return ok;
+        }
+        /* Honour the normal IRQ locking */
+        desc->status |= IRQ_INPROGRESS;
+        action = desc->action;
+        spin_unlock(&desc->lock);
 
-                while (action) {
-                        /* Only shared IRQ handlers are safe to call */
-                        if (action->flags & IRQF_SHARED) {
-                                if (action->handler(i, action->dev_id) ==
-                                                IRQ_HANDLED)
-                                        ok = 1;
-                        }
-                        action = action->next;
+        while (action) {
+                /* Only shared IRQ handlers are safe to call */
+                if (action->flags & IRQF_SHARED) {
+                        if (action->handler(irq, action->dev_id) ==
+                                IRQ_HANDLED)
+                                ok = 1;
                 }
-                local_irq_disable();
-                /* Now clean up the flags */
-                spin_lock(&desc->lock);
-                action = desc->action;
+                action = action->next;
+        }
+        local_irq_disable();
+        /* Now clean up the flags */
+        spin_lock(&desc->lock);
+        action = desc->action;
 
+        /*
+         * While we were looking for a fixup someone queued a real
+         * IRQ clashing with our walk:
+         */
+        while ((desc->status & IRQ_PENDING) && action) {
                 /*
-                 * While we were looking for a fixup someone queued a real
-                 * IRQ clashing with our walk:
-                 */
-                while ((desc->status & IRQ_PENDING) && action) {
-                        /*
-                         * Perform real IRQ processing for the IRQ we deferred
-                         */
-                        work = 1;
-                        spin_unlock(&desc->lock);
-                        handle_IRQ_event(i, action);
-                        spin_lock(&desc->lock);
-                        desc->status &= ~IRQ_PENDING;
-                }
-                desc->status &= ~IRQ_INPROGRESS;
-                /*
-                 * If we did actual work for the real IRQ line we must let the
-                 * IRQ controller clean up too
+                 * Perform real IRQ processing for the IRQ we deferred
                  */
-                if (work && desc->chip && desc->chip->end)
-                        desc->chip->end(i);
+                work = 1;
                 spin_unlock(&desc->lock);
+                handle_IRQ_event(irq, action);
+                spin_lock(&desc->lock);
+                desc->status &= ~IRQ_PENDING;
+        }
+        desc->status &= ~IRQ_INPROGRESS;
+        /*
+         * If we did actual work for the real IRQ line we must let the
+         * IRQ controller clean up too
+         */
+        if (work && desc->chip && desc->chip->end)
+                desc->chip->end(irq);
+        spin_unlock(&desc->lock);
+
+        return ok;
+}
+
+static int misrouted_irq(int irq)
+{
+        struct irq_desc *desc;
+        int i, ok = 0;
+
+        for_each_irq_desc(i, desc) {
+                if (!i)
+                         continue;
+
+                if (i == irq)   /* Already tried */
+                        continue;
+
+                if (try_one_irq(i, desc))
+                        ok = 1;
         }
         /* So the caller can adjust the irq error counts */
         return ok;
 }
 
+static void poll_spurious_irqs(unsigned long dummy)
+{
+        struct irq_desc *desc;
+        int i;
+
+        for_each_irq_desc(i, desc) {
+                unsigned int status;
+
+                if (!i)
+                         continue;
+
+                /* Racy but it doesn't matter */
+                status = desc->status;
+                barrier();
+                if (!(status & IRQ_SPURIOUS_DISABLED))
+                        continue;
+
+                try_one_irq(i, desc);
+        }
+
+        mod_timer(&poll_spurious_irq_timer,
+                  jiffies + POLL_SPURIOUS_IRQ_INTERVAL);
+}
+
 /*
  * If 99,900 of the previous 100,000 interrupts have not been handled
  * then assume that the IRQ is stuck in some manner. Drop a diagnostic
@@ -137,7 +176,9 @@ report_bad_irq(unsigned int irq, struct irq_desc *desc, irqreturn_t action_ret)
         }
 }
 
-static inline int try_misrouted_irq(unsigned int irq, struct irq_desc *desc, irqreturn_t action_ret)
+static inline int
+try_misrouted_irq(unsigned int irq, struct irq_desc *desc,
+                  irqreturn_t action_ret)
 {
         struct irqaction *action;
 
@@ -212,6 +253,9 @@ void note_interrupt(unsigned int irq, struct irq_desc *desc,
                 desc->status |= IRQ_DISABLED | IRQ_SPURIOUS_DISABLED;
                 desc->depth++;
                 desc->chip->disable(irq);
+
+                mod_timer(&poll_spurious_irq_timer,
+                          jiffies + POLL_SPURIOUS_IRQ_INTERVAL);
         }
         desc->irqs_unhandled = 0;
 }
@@ -241,7 +285,7 @@ static int __init irqfixup_setup(char *str)
 
 __setup("irqfixup", irqfixup_setup);
 module_param(irqfixup, int, 0644);
-MODULE_PARM_DESC("irqfixup", "0: No fixup, 1: irqfixup mode 2: irqpoll mode");
+MODULE_PARM_DESC("irqfixup", "0: No fixup, 1: irqfixup mode, 2: irqpoll mode");
 
 static int __init irqpoll_setup(char *str)
 {
diff --git a/kernel/itimer.c b/kernel/itimer.c
index ab982747d9bd..db7c358b9a02 100644
--- a/kernel/itimer.c
+++ b/kernel/itimer.c
@@ -55,17 +55,15 @@ int do_getitimer(int which, struct itimerval *value)
                 spin_unlock_irq(&tsk->sighand->siglock);
                 break;
         case ITIMER_VIRTUAL:
-                read_lock(&tasklist_lock);
                 spin_lock_irq(&tsk->sighand->siglock);
                 cval = tsk->signal->it_virt_expires;
                 cinterval = tsk->signal->it_virt_incr;
                 if (!cputime_eq(cval, cputime_zero)) {
-                        struct task_struct *t = tsk;
-                        cputime_t utime = tsk->signal->utime;
-                        do {
-                                utime = cputime_add(utime, t->utime);
-                                t = next_thread(t);
-                        } while (t != tsk);
+                        struct task_cputime cputime;
+                        cputime_t utime;
+
+                        thread_group_cputime(tsk, &cputime);
+                        utime = cputime.utime;
                         if (cputime_le(cval, utime)) { /* about to fire */
                                 cval = jiffies_to_cputime(1);
                         } else {
@@ -73,25 +71,19 @@ int do_getitimer(int which, struct itimerval *value)
                         }
                 }
                 spin_unlock_irq(&tsk->sighand->siglock);
-                read_unlock(&tasklist_lock);
                 cputime_to_timeval(cval, &value->it_value);
                 cputime_to_timeval(cinterval, &value->it_interval);
                 break;
         case ITIMER_PROF:
-                read_lock(&tasklist_lock);
                 spin_lock_irq(&tsk->sighand->siglock);
                 cval = tsk->signal->it_prof_expires;
                 cinterval = tsk->signal->it_prof_incr;
                 if (!cputime_eq(cval, cputime_zero)) {
-                        struct task_struct *t = tsk;
-                        cputime_t ptime = cputime_add(tsk->signal->utime,
-                                                      tsk->signal->stime);
-                        do {
-                                ptime = cputime_add(ptime,
-                                                    cputime_add(t->utime,
-                                                                t->stime));
-                                t = next_thread(t);
-                        } while (t != tsk);
+                        struct task_cputime times;
+                        cputime_t ptime;
+
+                        thread_group_cputime(tsk, &times);
+                        ptime = cputime_add(times.utime, times.stime);
                         if (cputime_le(cval, ptime)) { /* about to fire */
                                 cval = jiffies_to_cputime(1);
                         } else {
@@ -99,7 +91,6 @@ int do_getitimer(int which, struct itimerval *value)
                         }
                 }
                 spin_unlock_irq(&tsk->sighand->siglock);
-                read_unlock(&tasklist_lock);
                 cputime_to_timeval(cval, &value->it_value);
                 cputime_to_timeval(cinterval, &value->it_interval);
                 break;
@@ -185,7 +176,6 @@ again:
         case ITIMER_VIRTUAL:
                 nval = timeval_to_cputime(&value->it_value);
                 ninterval = timeval_to_cputime(&value->it_interval);
-                read_lock(&tasklist_lock);
                 spin_lock_irq(&tsk->sighand->siglock);
                 cval = tsk->signal->it_virt_expires;
                 cinterval = tsk->signal->it_virt_incr;
@@ -200,7 +190,6 @@ again:
                 tsk->signal->it_virt_expires = nval;
                 tsk->signal->it_virt_incr = ninterval;
                 spin_unlock_irq(&tsk->sighand->siglock);
-                read_unlock(&tasklist_lock);
                 if (ovalue) {
                         cputime_to_timeval(cval, &ovalue->it_value);
                         cputime_to_timeval(cinterval, &ovalue->it_interval);
@@ -209,7 +198,6 @@ again:
         case ITIMER_PROF:
                 nval = timeval_to_cputime(&value->it_value);
                 ninterval = timeval_to_cputime(&value->it_interval);
-                read_lock(&tasklist_lock);
                 spin_lock_irq(&tsk->sighand->siglock);
                 cval = tsk->signal->it_prof_expires;
                 cinterval = tsk->signal->it_prof_incr;
@@ -224,7 +212,6 @@ again:
                 tsk->signal->it_prof_expires = nval;
                 tsk->signal->it_prof_incr = ninterval;
                 spin_unlock_irq(&tsk->sighand->siglock);
-                read_unlock(&tasklist_lock);
                 if (ovalue) {
                         cputime_to_timeval(cval, &ovalue->it_value);
                         cputime_to_timeval(cinterval, &ovalue->it_interval);
diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c
index 38fc10ac7541..7b8b0f21a5b1 100644
--- a/kernel/kallsyms.c
+++ b/kernel/kallsyms.c
@@ -260,7 +260,6 @@ const char *kallsyms_lookup(unsigned long addr,
         /* see if it's in a module */
         return module_address_lookup(addr, symbolsize, offset, modname,
                                      namebuf);
-        return NULL;
 }
 
 int lookup_symbol_name(unsigned long addr, char *symname)
@@ -305,17 +304,24 @@ int sprint_symbol(char *buffer, unsigned long address)
         char *modname;
         const char *name;
         unsigned long offset, size;
-        char namebuf[KSYM_NAME_LEN];
+        int len;
 
-        name = kallsyms_lookup(address, &size, &offset, &modname, namebuf);
+        name = kallsyms_lookup(address, &size, &offset, &modname, buffer);
         if (!name)
                 return sprintf(buffer, "0x%lx", address);
 
+        if (name != buffer)
+                strcpy(buffer, name);
+        len = strlen(buffer);
+        buffer += len;
+
         if (modname)
-                return sprintf(buffer, "%s+%#lx/%#lx [%s]", name, offset,
-                                size, modname);
+                len += sprintf(buffer, "+%#lx/%#lx [%s]",
+                                                offset, size, modname);
         else
-                return sprintf(buffer, "%s+%#lx/%#lx", name, offset, size);
+                len += sprintf(buffer, "+%#lx/%#lx", offset, size);
+
+        return len;
 }
 
 /* Look up a kernel symbol and print it to the kernel messages. */
diff --git a/kernel/kexec.c b/kernel/kexec.c
index 59f3f0df35d4..ac0fde7b54d0 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -30,6 +30,7 @@
 #include <linux/pm.h>
 #include <linux/cpu.h>
 #include <linux/console.h>
+#include <linux/vmalloc.h>
 
 #include <asm/page.h>
 #include <asm/uaccess.h>
@@ -753,8 +754,14 @@ static struct page *kimage_alloc_page(struct kimage *image,
                         *old = addr | (*old & ~PAGE_MASK);
 
                         /* The old page I have found cannot be a
-                         * destination page, so return it.
+                         * destination page, so return it if it's
+                         * gfp_flags honor the ones passed in.
                          */
+                        if (!(gfp_mask & __GFP_HIGHMEM) &&
+                            PageHighMem(old_page)) {
+                                kimage_free_pages(old_page);
+                                continue;
+                        }
                         addr = old_addr;
                         page = old_page;
                         break;
@@ -1365,6 +1372,7 @@ static int __init crash_save_vmcoreinfo_init(void)
         VMCOREINFO_SYMBOL(node_online_map);
         VMCOREINFO_SYMBOL(swapper_pg_dir);
         VMCOREINFO_SYMBOL(_stext);
+        VMCOREINFO_SYMBOL(vmlist);
 
 #ifndef CONFIG_NEED_MULTIPLE_NODES
         VMCOREINFO_SYMBOL(mem_map);
@@ -1400,6 +1408,7 @@ static int __init crash_save_vmcoreinfo_init(void)
         VMCOREINFO_OFFSET(free_area, free_list);
         VMCOREINFO_OFFSET(list_head, next);
         VMCOREINFO_OFFSET(list_head, prev);
+        VMCOREINFO_OFFSET(vm_struct, addr);
         VMCOREINFO_LENGTH(zone.free_area, MAX_ORDER);
         VMCOREINFO_LENGTH(free_area.free_list, MIGRATE_TYPES);
         VMCOREINFO_NUMBER(NR_FREE_PAGES);
diff --git a/kernel/kgdb.c b/kernel/kgdb.c
index eaa21fc9ad1d..e4dcfb2272a4 100644
--- a/kernel/kgdb.c
+++ b/kernel/kgdb.c
@@ -488,7 +488,7 @@ static int write_mem_msg(int binary)
                 if (err)
                         return err;
                 if (CACHE_FLUSH_IS_SAFE)
-                        flush_icache_range(addr, addr + length + 1);
+                        flush_icache_range(addr, addr + length);
                 return 0;
         }
 
@@ -590,6 +590,7 @@ static void kgdb_wait(struct pt_regs *regs)
 
         /* Signal the primary CPU that we are done: */
         atomic_set(&cpu_in_kgdb[cpu], 0);
+        touch_softlockup_watchdog();
         clocksource_touch_watchdog();
         local_irq_restore(flags);
 }
@@ -1432,6 +1433,7 @@ acquirelock:
             atomic_read(&kgdb_cpu_doing_single_step) != cpu) {
 
                 atomic_set(&kgdb_active, -1);
+                touch_softlockup_watchdog();
                 clocksource_touch_watchdog();
                 local_irq_restore(flags);
 
@@ -1462,7 +1464,7 @@ acquirelock:
          * Get the passive CPU lock which will hold all the non-primary
          * CPU in a spin state while the debugger is active
          */
-        if (!kgdb_single_step || !kgdb_contthread) {
+        if (!kgdb_single_step) {
                 for (i = 0; i < NR_CPUS; i++)
                         atomic_set(&passive_cpu_wait[i], 1);
         }
@@ -1475,7 +1477,7 @@ acquirelock:
 
 #ifdef CONFIG_SMP
         /* Signal the other CPUs to enter kgdb_wait() */
-        if ((!kgdb_single_step || !kgdb_contthread) && kgdb_do_roundup)
+        if ((!kgdb_single_step) && kgdb_do_roundup)
                 kgdb_roundup_cpus(flags);
 #endif
 
@@ -1494,7 +1496,7 @@ acquirelock:
         kgdb_post_primary_code(ks->linux_regs, ks->ex_vector, ks->err_code);
         kgdb_deactivate_sw_breakpoints();
         kgdb_single_step = 0;
-        kgdb_contthread = NULL;
+        kgdb_contthread = current;
         exception_level = 0;
 
         /* Talk to debugger with gdbserial protocol */
@@ -1508,7 +1510,7 @@ acquirelock:
         kgdb_info[ks->cpu].task = NULL;
         atomic_set(&cpu_in_kgdb[ks->cpu], 0);
 
-        if (!kgdb_single_step || !kgdb_contthread) {
+        if (!kgdb_single_step) {
                 for (i = NR_CPUS-1; i >= 0; i--)
                         atomic_set(&passive_cpu_wait[i], 0);
                 /*
@@ -1524,6 +1526,7 @@ acquirelock:
 kgdb_restore:
         /* Free kgdb_active */
         atomic_set(&kgdb_active, -1);
+        touch_softlockup_watchdog();
         clocksource_touch_watchdog();
         local_irq_restore(flags);
 
diff --git a/kernel/kmod.c b/kernel/kmod.c
index 2456d1a0befb..3d3c3ea3a023 100644
--- a/kernel/kmod.c
+++ b/kernel/kmod.c
@@ -113,7 +113,7 @@ int request_module(const char *fmt, ...)
         return ret;
 }
 EXPORT_SYMBOL(request_module);
-#endif /* CONFIG_KMOD */
+#endif /* CONFIG_MODULES */
 
 struct subprocess_info {
         struct work_struct work;
@@ -265,7 +265,7 @@ static void __call_usermodehelper(struct work_struct *work)
         }
 }
 
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 /*
  * If set, call_usermodehelper_exec() will exit immediately returning -EBUSY
  * (used for preventing user land processes from being created after the user
@@ -288,39 +288,37 @@ static DECLARE_WAIT_QUEUE_HEAD(running_helpers_waitq);
  */
 #define RUNNING_HELPERS_TIMEOUT (5 * HZ)
 
-static int usermodehelper_pm_callback(struct notifier_block *nfb,
-                                        unsigned long action,
-                                        void *ignored)
+/**
+ * usermodehelper_disable - prevent new helpers from being started
+ */
+int usermodehelper_disable(void)
 {
         long retval;
 
-        switch (action) {
-        case PM_HIBERNATION_PREPARE:
-        case PM_SUSPEND_PREPARE:
-                usermodehelper_disabled = 1;
-                smp_mb();
-                /*
-                 * From now on call_usermodehelper_exec() won't start any new
-                 * helpers, so it is sufficient if running_helpers turns out to
-                 * be zero at one point (it may be increased later, but that
-                 * doesn't matter).
-                 */
-                retval = wait_event_timeout(running_helpers_waitq,
+        usermodehelper_disabled = 1;
+        smp_mb();
+        /*
+         * From now on call_usermodehelper_exec() won't start any new
+         * helpers, so it is sufficient if running_helpers turns out to
+         * be zero at one point (it may be increased later, but that
+         * doesn't matter).
+         */
+        retval = wait_event_timeout(running_helpers_waitq,
                                         atomic_read(&running_helpers) == 0,
                                         RUNNING_HELPERS_TIMEOUT);
-                if (retval) {
-                        return NOTIFY_OK;
-                } else {
-                        usermodehelper_disabled = 0;
-                        return NOTIFY_BAD;
-                }
-        case PM_POST_HIBERNATION:
-        case PM_POST_SUSPEND:
-                usermodehelper_disabled = 0;
-                return NOTIFY_OK;
-        }
+        if (retval)
+                return 0;
 
-        return NOTIFY_DONE;
+        usermodehelper_disabled = 0;
+        return -EAGAIN;
+}
+
+/**
+ * usermodehelper_enable - allow new helpers to be started again
+ */
+void usermodehelper_enable(void)
+{
+        usermodehelper_disabled = 0;
 }
 
 static void helper_lock(void)
@@ -334,18 +332,12 @@ static void helper_unlock(void)
         if (atomic_dec_and_test(&running_helpers))
                 wake_up(&running_helpers_waitq);
 }
-
-static void register_pm_notifier_callback(void)
-{
-        pm_notifier(usermodehelper_pm_callback, 0);
-}
-#else /* CONFIG_PM */
+#else /* CONFIG_PM_SLEEP */
 #define usermodehelper_disabled 0
 
 static inline void helper_lock(void) {}
 static inline void helper_unlock(void) {}
-static inline void register_pm_notifier_callback(void) {}
-#endif /* CONFIG_PM */
+#endif /* CONFIG_PM_SLEEP */
 
 /**
  * call_usermodehelper_setup - prepare to call a usermode helper
@@ -515,5 +507,4 @@ void __init usermodehelper_init(void)
 {
         khelper_wq = create_singlethread_workqueue("khelper");
         BUG_ON(!khelper_wq);
-        register_pm_notifier_callback();
 }
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 75bc2cd9ebc6..9f8a3f25259a 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -72,7 +72,7 @@ static bool kprobe_enabled;
 DEFINE_MUTEX(kprobe_mutex);             /* Protects kprobe_table */
 static DEFINE_PER_CPU(struct kprobe *, kprobe_instance) = NULL;
 static struct {
-        spinlock_t lock ____cacheline_aligned;
+        spinlock_t lock ____cacheline_aligned_in_smp;
 } kretprobe_table_locks[KPROBE_TABLE_SIZE];
 
 static spinlock_t *kretprobe_table_lock_ptr(unsigned long hash)
@@ -404,7 +404,7 @@ void kretprobe_hash_lock(struct task_struct *tsk,
         spin_lock_irqsave(hlist_lock, *flags);
 }
 
-void kretprobe_table_lock(unsigned long hash, unsigned long *flags)
+static void kretprobe_table_lock(unsigned long hash, unsigned long *flags)
 {
         spinlock_t *hlist_lock = kretprobe_table_lock_ptr(hash);
         spin_lock_irqsave(hlist_lock, *flags);
@@ -613,30 +613,37 @@ static int __kprobes __register_kprobe(struct kprobe *p,
                 return -EINVAL;
         p->addr = addr;
 
-        if (!kernel_text_address((unsigned long) p->addr) ||
-            in_kprobes_functions((unsigned long) p->addr))
+        preempt_disable();
+        if (!__kernel_text_address((unsigned long) p->addr) ||
+            in_kprobes_functions((unsigned long) p->addr)) {
+                preempt_enable();
                 return -EINVAL;
+        }
 
         p->mod_refcounted = 0;
 
         /*
          * Check if are we probing a module.
          */
-        probed_mod = module_text_address((unsigned long) p->addr);
+        probed_mod = __module_text_address((unsigned long) p->addr);
         if (probed_mod) {
-                struct module *calling_mod = module_text_address(called_from);
+                struct module *calling_mod;
+                calling_mod = __module_text_address(called_from);
                 /*
                  * We must allow modules to probe themself and in this case
                  * avoid incrementing the module refcount, so as to allow
                  * unloading of self probing modules.
                  */
                 if (calling_mod && calling_mod != probed_mod) {
-                        if (unlikely(!try_module_get(probed_mod)))
+                        if (unlikely(!try_module_get(probed_mod))) {
+                                preempt_enable();
                                 return -EINVAL;
+                        }
                         p->mod_refcounted = 1;
                 } else
                         probed_mod = NULL;
         }
+        preempt_enable();
 
         p->nmissed = 0;
         INIT_LIST_HEAD(&p->list);
@@ -718,6 +725,10 @@ static void __kprobes __unregister_kprobe_bottom(struct kprobe *p)
         struct kprobe *old_p;
 
         if (p->mod_refcounted) {
+                /*
+                 * Since we've already incremented refcount,
+                 * we don't need to disable preemption.
+                 */
                 mod = module_text_address((unsigned long)p->addr);
                 if (mod)
                         module_put(mod);
diff --git a/kernel/ksysfs.c b/kernel/ksysfs.c
index e53bc30e9ba5..08dd8ed86c77 100644
--- a/kernel/ksysfs.c
+++ b/kernel/ksysfs.c
@@ -14,6 +14,7 @@
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/kexec.h>
+#include <linux/profile.h>
 #include <linux/sched.h>
 
 #define KERNEL_ATTR_RO(_name) \
@@ -53,6 +54,37 @@ static ssize_t uevent_helper_store(struct kobject *kobj,
 KERNEL_ATTR_RW(uevent_helper);
 #endif
 
+#ifdef CONFIG_PROFILING
+static ssize_t profiling_show(struct kobject *kobj,
+                                  struct kobj_attribute *attr, char *buf)
+{
+        return sprintf(buf, "%d\n", prof_on);
+}
+static ssize_t profiling_store(struct kobject *kobj,
+                                   struct kobj_attribute *attr,
+                                   const char *buf, size_t count)
+{
+        int ret;
+
+        if (prof_on)
+                return -EEXIST;
+        /*
+         * This eventually calls into get_option() which
+         * has a ton of callers and is not const.  It is
+         * easiest to cast it away here.
+         */
+        profile_setup((char *)buf);
+        ret = profile_init();
+        if (ret)
+                return ret;
+        ret = create_proc_profile();
+        if (ret)
+                return ret;
+        return count;
+}
+KERNEL_ATTR_RW(profiling);
+#endif
+
 #ifdef CONFIG_KEXEC
 static ssize_t kexec_loaded_show(struct kobject *kobj,
                                  struct kobj_attribute *attr, char *buf)
@@ -109,6 +141,9 @@ static struct attribute * kernel_attrs[] = {
         &uevent_seqnum_attr.attr,
         &uevent_helper_attr.attr,
 #endif
+#ifdef CONFIG_PROFILING
+        &profiling_attr.attr,
+#endif
 #ifdef CONFIG_KEXEC
         &kexec_loaded_attr.attr,
         &kexec_crash_loaded_attr.attr,
diff --git a/kernel/kthread.c b/kernel/kthread.c
index 96cff2f8710b..8e7a7ce3ed0a 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -13,6 +13,7 @@
 #include <linux/file.h>
 #include <linux/module.h>
 #include <linux/mutex.h>
+#include <trace/sched.h>
 
 #define KTHREAD_NICE_LEVEL (-5)
 
@@ -171,12 +172,11 @@ EXPORT_SYMBOL(kthread_create);
  */
 void kthread_bind(struct task_struct *k, unsigned int cpu)
 {
-        if (k->state != TASK_UNINTERRUPTIBLE) {
+        /* Must have done schedule() in kthread() before we set_task_cpu */
+        if (!wait_task_inactive(k, TASK_UNINTERRUPTIBLE)) {
                 WARN_ON(1);
                 return;
         }
-        /* Must have done schedule() in kthread() before we set_task_cpu */
-        wait_task_inactive(k, 0);
         set_task_cpu(k, cpu);
         k->cpus_allowed = cpumask_of_cpu(cpu);
         k->rt.nr_cpus_allowed = 1;
@@ -206,6 +206,8 @@ int kthread_stop(struct task_struct *k)
         /* It could exit after stop_info.k set, but before wake_up_process. */
         get_task_struct(k);
 
+        trace_sched_kthread_stop(k);
+
         /* Must init completion *before* thread sees kthread_stop_info.k */
         init_completion(&kthread_stop_info.done);
         smp_wmb();
@@ -221,6 +223,8 @@ int kthread_stop(struct task_struct *k)
         ret = kthread_stop_info.err;
         mutex_unlock(&kthread_stop_lock);
 
+        trace_sched_kthread_stop_ret(ret);
+
         return ret;
 }
 EXPORT_SYMBOL(kthread_stop);
diff --git a/kernel/lockdep.c b/kernel/lockdep.c
index dbda475b13bd..06e157119d2b 100644
--- a/kernel/lockdep.c
+++ b/kernel/lockdep.c
@@ -2169,12 +2169,11 @@ void early_boot_irqs_on(void)
 /*
  * Hardirqs will be enabled:
  */
-void trace_hardirqs_on_caller(unsigned long a0)
+void trace_hardirqs_on_caller(unsigned long ip)
 {
         struct task_struct *curr = current;
-        unsigned long ip;
 
-        time_hardirqs_on(CALLER_ADDR0, a0);
+        time_hardirqs_on(CALLER_ADDR0, ip);
 
         if (unlikely(!debug_locks || current->lockdep_recursion))
                 return;
@@ -2188,7 +2187,6 @@ void trace_hardirqs_on_caller(unsigned long a0)
         }
         /* we'll do an OFF -> ON transition: */
         curr->hardirqs_enabled = 1;
-        ip = (unsigned long) __builtin_return_address(0);
 
         if (DEBUG_LOCKS_WARN_ON(!irqs_disabled()))
                 return;
@@ -2224,11 +2222,11 @@ EXPORT_SYMBOL(trace_hardirqs_on);
 /*
  * Hardirqs were disabled:
  */
-void trace_hardirqs_off_caller(unsigned long a0)
+void trace_hardirqs_off_caller(unsigned long ip)
 {
         struct task_struct *curr = current;
 
-        time_hardirqs_off(CALLER_ADDR0, a0);
+        time_hardirqs_off(CALLER_ADDR0, ip);
 
         if (unlikely(!debug_locks || current->lockdep_recursion))
                 return;
@@ -2241,7 +2239,7 @@ void trace_hardirqs_off_caller(unsigned long a0)
                  * We have done an ON -> OFF transition:
                  */
                 curr->hardirqs_enabled = 0;
-                curr->hardirq_disable_ip = _RET_IP_;
+                curr->hardirq_disable_ip = ip;
                 curr->hardirq_disable_event = ++curr->irq_events;
                 debug_atomic_inc(&hardirqs_off_events);
         } else
@@ -3417,9 +3415,10 @@ retry:
                 }
                 printk(" ignoring it.\n");
                 unlock = 0;
+        } else {
+                if (count != 10)
+                        printk(KERN_CONT " locked it.\n");
         }
-        if (count != 10)
-                printk(" locked it.\n");
 
         do_each_thread(g, p) {
                 /*
diff --git a/kernel/marker.c b/kernel/marker.c
index 7d1faecd7a51..e9c6b2bc9400 100644
--- a/kernel/marker.c
+++ b/kernel/marker.c
@@ -62,7 +62,7 @@ struct marker_entry {
         int refcount;   /* Number of times armed. 0 if disarmed. */
         struct rcu_head rcu;
         void *oldptr;
-        unsigned char rcu_pending:1;
+        int rcu_pending;
         unsigned char ptype:1;
         char name[0];   /* Contains name'\0'format'\0' */
 };
@@ -103,11 +103,11 @@ void marker_probe_cb(const struct marker *mdata, void *call_private, ...)
         char ptype;
 
         /*
-         * preempt_disable does two things : disabling preemption to make sure
-         * the teardown of the callbacks can be done correctly when they are in
-         * modules and they insure RCU read coherency.
+         * rcu_read_lock_sched does two things : disabling preemption to make
+         * sure the teardown of the callbacks can be done correctly when they
+         * are in modules and they insure RCU read coherency.
          */
-        preempt_disable();
+        rcu_read_lock_sched();
         ptype = mdata->ptype;
         if (likely(!ptype)) {
                 marker_probe_func *func;
@@ -145,7 +145,7 @@ void marker_probe_cb(const struct marker *mdata, void *call_private, ...)
                         va_end(args);
                 }
         }
-        preempt_enable();
+        rcu_read_unlock_sched();
 }
 EXPORT_SYMBOL_GPL(marker_probe_cb);
 
@@ -162,7 +162,7 @@ void marker_probe_cb_noarg(const struct marker *mdata, void *call_private, ...)
         va_list args;   /* not initialized */
         char ptype;
 
-        preempt_disable();
+        rcu_read_lock_sched();
         ptype = mdata->ptype;
         if (likely(!ptype)) {
                 marker_probe_func *func;
@@ -195,7 +195,7 @@ void marker_probe_cb_noarg(const struct marker *mdata, void *call_private, ...)
                         multi[i].func(multi[i].probe_private, call_private,
                                 mdata->format, &args);
         }
-        preempt_enable();
+        rcu_read_unlock_sched();
 }
 EXPORT_SYMBOL_GPL(marker_probe_cb_noarg);
 
@@ -560,7 +560,7 @@ static int set_marker(struct marker_entry **entry, struct marker *elem,
  * Disable a marker and its probe callback.
  * Note: only waiting an RCU period after setting elem->call to the empty
  * function insures that the original callback is not used anymore. This insured
- * by preempt_disable around the call site.
+ * by rcu_read_lock_sched around the call site.
  */
 static void disable_marker(struct marker *elem)
 {
@@ -653,11 +653,17 @@ int marker_probe_register(const char *name, const char *format,
         entry = get_marker(name);
         if (!entry) {
                 entry = add_marker(name, format);
-                if (IS_ERR(entry)) {
+                if (IS_ERR(entry))
                         ret = PTR_ERR(entry);
-                        goto end;
-                }
+        } else if (format) {
+                if (!entry->format)
+                        ret = marker_set_format(&entry, format);
+                else if (strcmp(entry->format, format))
+                        ret = -EPERM;
         }
+        if (ret)
+                goto end;
+
         /*
          * If we detect that a call_rcu is pending for this marker,
          * make sure it's executed now.
@@ -674,6 +680,8 @@ int marker_probe_register(const char *name, const char *format,
         mutex_lock(&markers_mutex);
         entry = get_marker(name);
         WARN_ON(!entry);
+        if (entry->rcu_pending)
+                rcu_barrier_sched();
         entry->oldptr = old;
         entry->rcu_pending = 1;
         /* write rcu_pending before calling the RCU callback */
@@ -717,6 +725,8 @@ int marker_probe_unregister(const char *name,
         entry = get_marker(name);
         if (!entry)
                 goto end;
+        if (entry->rcu_pending)
+                rcu_barrier_sched();
         entry->oldptr = old;
         entry->rcu_pending = 1;
         /* write rcu_pending before calling the RCU callback */
@@ -795,6 +805,8 @@ int marker_probe_unregister_private_data(marker_probe_func *probe,
         mutex_lock(&markers_mutex);
         entry = get_marker_from_private_data(probe, probe_private);
         WARN_ON(!entry);
+        if (entry->rcu_pending)
+                rcu_barrier_sched();
         entry->oldptr = old;
         entry->rcu_pending = 1;
         /* write rcu_pending before calling the RCU callback */
diff --git a/kernel/module.c b/kernel/module.c
index 9db11911e04b..1f4cc00e0c20 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -20,11 +20,13 @@
 #include <linux/moduleloader.h>
 #include <linux/init.h>
 #include <linux/kallsyms.h>
+#include <linux/fs.h>
 #include <linux/sysfs.h>
 #include <linux/kernel.h>
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
 #include <linux/elf.h>
+#include <linux/proc_fs.h>
 #include <linux/seq_file.h>
 #include <linux/syscalls.h>
 #include <linux/fcntl.h>
@@ -42,10 +44,13 @@
 #include <linux/string.h>
 #include <linux/mutex.h>
 #include <linux/unwind.h>
+#include <linux/rculist.h>
 #include <asm/uaccess.h>
 #include <asm/cacheflush.h>
 #include <linux/license.h>
 #include <asm/sections.h>
+#include <linux/tracepoint.h>
+#include <linux/ftrace.h>
 
 #if 0
 #define DEBUGP printk
@@ -61,7 +66,7 @@
 #define INIT_OFFSET_MASK (1UL << (BITS_PER_LONG-1))
 
 /* List of modules, protected by module_mutex or preempt_disable
- * (add/delete uses stop_machine). */
+ * (delete uses stop_machine/add uses RCU list operations). */
 static DEFINE_MUTEX(module_mutex);
 static LIST_HEAD(modules);
 
@@ -100,7 +105,7 @@ static inline int strong_try_module_get(struct module *mod)
 static inline void add_taint_module(struct module *mod, unsigned flag)
 {
         add_taint(flag);
-        mod->taints |= flag;
+        mod->taints |= (1U << flag);
 }
 
 /*
@@ -130,6 +135,29 @@ static unsigned int find_sec(Elf_Ehdr *hdr,
         return 0;
 }
 
+/* Find a module section, or NULL. */
+static void *section_addr(Elf_Ehdr *hdr, Elf_Shdr *shdrs,
+                          const char *secstrings, const char *name)
+{
+        /* Section 0 has sh_addr 0. */
+        return (void *)shdrs[find_sec(hdr, shdrs, secstrings, name)].sh_addr;
+}
+
+/* Find a module section, or NULL.  Fill in number of "objects" in section. */
+static void *section_objs(Elf_Ehdr *hdr,
+                          Elf_Shdr *sechdrs,
+                          const char *secstrings,
+                          const char *name,
+                          size_t object_size,
+                          unsigned int *num)
+{
+        unsigned int sec = find_sec(hdr, sechdrs, secstrings, name);
+
+        /* Section 0 has sh_addr 0 and sh_size 0. */
+        *num = sechdrs[sec].sh_size / object_size;
+        return (void *)sechdrs[sec].sh_addr;
+}
+
 /* Provided by the linker */
 extern const struct kernel_symbol __start___ksymtab[];
 extern const struct kernel_symbol __stop___ksymtab[];
@@ -216,7 +244,7 @@ static bool each_symbol(bool (*fn)(const struct symsearch *arr,
         if (each_symbol_in_section(arr, ARRAY_SIZE(arr), NULL, fn, data))
                 return true;
 
-        list_for_each_entry(mod, &modules, list) {
+        list_for_each_entry_rcu(mod, &modules, list) {
                 struct symsearch arr[] = {
                         { mod->syms, mod->syms + mod->num_syms, mod->crcs,
                           NOT_GPL_ONLY, false },
@@ -784,6 +812,7 @@ sys_delete_module(const char __user *name_user, unsigned int flags)
         mutex_lock(&module_mutex);
         /* Store the name of the last unloaded module for diagnostic purposes */
         strlcpy(last_unloaded_module, mod->name, sizeof(last_unloaded_module));
+        unregister_dynamic_debug_module(mod->name);
         free_module(mod);
 
  out:
@@ -923,7 +952,7 @@ static const char vermagic[] = VERMAGIC_STRING;
 static int try_to_force_load(struct module *mod, const char *symname)
 {
 #ifdef CONFIG_MODULE_FORCE_LOAD
-        if (!(tainted & TAINT_FORCED_MODULE))
+        if (!test_taint(TAINT_FORCED_MODULE))
                 printk("%s: no version for \"%s\" found: kernel tainted.\n",
                        mod->name, symname);
         add_taint_module(mod, TAINT_FORCED_MODULE);
@@ -1033,7 +1062,7 @@ static unsigned long resolve_symbol(Elf_Shdr *sechdrs,
         const unsigned long *crc;
 
         ret = find_symbol(name, &owner, &crc,
-                          !(mod->taints & TAINT_PROPRIETARY_MODULE), true);
+                          !(mod->taints & (1 << TAINT_PROPRIETARY_MODULE)), true);
         if (!IS_ERR_VALUE(ret)) {
                 /* use_module can fail due to OOM,
                    or module initialization or unloading */
@@ -1173,7 +1202,7 @@ static void free_notes_attrs(struct module_notes_attrs *notes_attrs,
                 while (i-- > 0)
                         sysfs_remove_bin_file(notes_attrs->dir,
                                               &notes_attrs->attrs[i]);
-                kobject_del(notes_attrs->dir);
+                kobject_put(notes_attrs->dir);
         }
         kfree(notes_attrs);
 }
@@ -1391,17 +1420,6 @@ static void mod_kobject_remove(struct module *mod)
 }
 
 /*
- * link the module with the whole machine is stopped with interrupts off
- * - this defends against kallsyms not taking locks
- */
-static int __link_module(void *_mod)
-{
-        struct module *mod = _mod;
-        list_add(&mod->list, &modules);
-        return 0;
-}
-
-/*
  * unlink the module with the whole machine is stopped with interrupts off
  * - this defends against kallsyms not taking locks
  */
@@ -1429,6 +1447,9 @@ static void free_module(struct module *mod)
         /* Module unload stuff */
         module_unload_free(mod);
 
+        /* release any pointers to mcount in this module */
+        ftrace_release(mod->module_core, mod->core_size);
+
         /* This may be NULL, but that's OK */
         module_free(mod, mod->module_init);
         kfree(mod->args);
@@ -1634,7 +1655,7 @@ static void set_license(struct module *mod, const char *license)
                 license = "unspecified";
 
         if (!license_is_gpl_compatible(license)) {
-                if (!(tainted & TAINT_PROPRIETARY_MODULE))
+                if (!test_taint(TAINT_PROPRIETARY_MODULE))
                         printk(KERN_WARNING "%s: module license '%s' taints "
                                 "kernel.\n", mod->name, license);
                 add_taint_module(mod, TAINT_PROPRIETARY_MODULE);
@@ -1783,6 +1804,21 @@ static inline void add_kallsyms(struct module *mod,
 }
 #endif /* CONFIG_KALLSYMS */
 
+static void dynamic_printk_setup(struct mod_debug *debug, unsigned int num)
+{
+#ifdef CONFIG_DYNAMIC_PRINTK_DEBUG
+        unsigned int i;
+
+        for (i = 0; i < num; i++) {
+                register_dynamic_debug_module(debug[i].modname,
+                                              debug[i].type,
+                                              debug[i].logical_modname,
+                                              debug[i].flag_names,
+                                              debug[i].hash, debug[i].hash2);
+        }
+#endif /* CONFIG_DYNAMIC_PRINTK_DEBUG */
+}
+
 static void *module_alloc_update_bounds(unsigned long size)
 {
         void *ret = module_alloc(size);
@@ -1806,35 +1842,18 @@ static noinline struct module *load_module(void __user *umod,
         Elf_Ehdr *hdr;
         Elf_Shdr *sechdrs;
         char *secstrings, *args, *modmagic, *strtab = NULL;
+        char *staging;
         unsigned int i;
         unsigned int symindex = 0;
         unsigned int strindex = 0;
-        unsigned int setupindex;
-        unsigned int exindex;
-        unsigned int exportindex;
-        unsigned int modindex;
-        unsigned int obsparmindex;
-        unsigned int infoindex;
-        unsigned int gplindex;
-        unsigned int crcindex;
-        unsigned int gplcrcindex;
-        unsigned int versindex;
-        unsigned int pcpuindex;
-        unsigned int gplfutureindex;
-        unsigned int gplfuturecrcindex;
+        unsigned int modindex, versindex, infoindex, pcpuindex;
         unsigned int unwindex = 0;
-#ifdef CONFIG_UNUSED_SYMBOLS
-        unsigned int unusedindex;
-        unsigned int unusedcrcindex;
-        unsigned int unusedgplindex;
-        unsigned int unusedgplcrcindex;
-#endif
-        unsigned int markersindex;
-        unsigned int markersstringsindex;
+        unsigned int num_kp, num_mcount;
+        struct kernel_param *kp;
         struct module *mod;
         long err = 0;
         void *percpu = NULL, *ptr = NULL; /* Stops spurious gcc warning */
-        struct exception_table_entry *extable;
+        unsigned long *mseg;
         mm_segment_t old_fs;
 
         DEBUGP("load_module: umod=%p, len=%lu, uargs=%p\n",
@@ -1898,6 +1917,7 @@ static noinline struct module *load_module(void __user *umod,
                 err = -ENOEXEC;
                 goto free_hdr;
         }
+        /* This is temporary: point mod into copy of data. */
         mod = (void *)sechdrs[modindex].sh_addr;
 
         if (symindex == 0) {
@@ -1907,22 +1927,6 @@ static noinline struct module *load_module(void __user *umod,
                 goto free_hdr;
         }
 
-        /* Optional sections */
-        exportindex = find_sec(hdr, sechdrs, secstrings, "__ksymtab");
-        gplindex = find_sec(hdr, sechdrs, secstrings, "__ksymtab_gpl");
-        gplfutureindex = find_sec(hdr, sechdrs, secstrings, "__ksymtab_gpl_future");
-        crcindex = find_sec(hdr, sechdrs, secstrings, "__kcrctab");
-        gplcrcindex = find_sec(hdr, sechdrs, secstrings, "__kcrctab_gpl");
-        gplfuturecrcindex = find_sec(hdr, sechdrs, secstrings, "__kcrctab_gpl_future");
-#ifdef CONFIG_UNUSED_SYMBOLS
-        unusedindex = find_sec(hdr, sechdrs, secstrings, "__ksymtab_unused");
-        unusedgplindex = find_sec(hdr, sechdrs, secstrings, "__ksymtab_unused_gpl");
-        unusedcrcindex = find_sec(hdr, sechdrs, secstrings, "__kcrctab_unused");
-        unusedgplcrcindex = find_sec(hdr, sechdrs, secstrings, "__kcrctab_unused_gpl");
-#endif
-        setupindex = find_sec(hdr, sechdrs, secstrings, "__param");
-        exindex = find_sec(hdr, sechdrs, secstrings, "__ex_table");
-        obsparmindex = find_sec(hdr, sechdrs, secstrings, "__obsparm");
         versindex = find_sec(hdr, sechdrs, secstrings, "__versions");
         infoindex = find_sec(hdr, sechdrs, secstrings, ".modinfo");
         pcpuindex = find_pcpusec(hdr, sechdrs, secstrings);
@@ -1960,6 +1964,14 @@ static noinline struct module *load_module(void __user *umod,
                 goto free_hdr;
         }
 
+        staging = get_modinfo(sechdrs, infoindex, "staging");
+        if (staging) {
+                add_taint_module(mod, TAINT_CRAP);
+                printk(KERN_WARNING "%s: module is from the staging directory,"
+                       " the quality is unknown, you have been warned.\n",
+                       mod->name);
+        }
+
         /* Now copy in args */
         args = strndup_user(uargs, ~0UL >> 1);
         if (IS_ERR(args)) {
@@ -2070,42 +2082,57 @@ static noinline struct module *load_module(void __user *umod,
         if (err < 0)
                 goto cleanup;
 
-        /* Set up EXPORTed & EXPORT_GPLed symbols (section 0 is 0 length) */
-        mod->num_syms = sechdrs[exportindex].sh_size / sizeof(*mod->syms);
-        mod->syms = (void *)sechdrs[exportindex].sh_addr;
-        if (crcindex)
-                mod->crcs = (void *)sechdrs[crcindex].sh_addr;
-        mod->num_gpl_syms = sechdrs[gplindex].sh_size / sizeof(*mod->gpl_syms);
-        mod->gpl_syms = (void *)sechdrs[gplindex].sh_addr;
-        if (gplcrcindex)
-                mod->gpl_crcs = (void *)sechdrs[gplcrcindex].sh_addr;
-        mod->num_gpl_future_syms = sechdrs[gplfutureindex].sh_size /
-                                        sizeof(*mod->gpl_future_syms);
-        mod->gpl_future_syms = (void *)sechdrs[gplfutureindex].sh_addr;
-        if (gplfuturecrcindex)
-                mod->gpl_future_crcs = (void *)sechdrs[gplfuturecrcindex].sh_addr;
+        /* Now we've got everything in the final locations, we can
+         * find optional sections. */
+        kp = section_objs(hdr, sechdrs, secstrings, "__param", sizeof(*kp),
+                          &num_kp);
+        mod->syms = section_objs(hdr, sechdrs, secstrings, "__ksymtab",
+                                 sizeof(*mod->syms), &mod->num_syms);
+        mod->crcs = section_addr(hdr, sechdrs, secstrings, "__kcrctab");
+        mod->gpl_syms = section_objs(hdr, sechdrs, secstrings, "__ksymtab_gpl",
+                                     sizeof(*mod->gpl_syms),
+                                     &mod->num_gpl_syms);
+        mod->gpl_crcs = section_addr(hdr, sechdrs, secstrings, "__kcrctab_gpl");
+        mod->gpl_future_syms = section_objs(hdr, sechdrs, secstrings,
+                                            "__ksymtab_gpl_future",
+                                            sizeof(*mod->gpl_future_syms),
+                                            &mod->num_gpl_future_syms);
+        mod->gpl_future_crcs = section_addr(hdr, sechdrs, secstrings,
+                                            "__kcrctab_gpl_future");
 
 #ifdef CONFIG_UNUSED_SYMBOLS
-        mod->num_unused_syms = sechdrs[unusedindex].sh_size /
-                                        sizeof(*mod->unused_syms);
-        mod->num_unused_gpl_syms = sechdrs[unusedgplindex].sh_size /
-                                        sizeof(*mod->unused_gpl_syms);
-        mod->unused_syms = (void *)sechdrs[unusedindex].sh_addr;
-        if (unusedcrcindex)
-                mod->unused_crcs = (void *)sechdrs[unusedcrcindex].sh_addr;
-        mod->unused_gpl_syms = (void *)sechdrs[unusedgplindex].sh_addr;
-        if (unusedgplcrcindex)
-                mod->unused_gpl_crcs
-                        = (void *)sechdrs[unusedgplcrcindex].sh_addr;
+        mod->unused_syms = section_objs(hdr, sechdrs, secstrings,
+                                        "__ksymtab_unused",
+                                        sizeof(*mod->unused_syms),
+                                        &mod->num_unused_syms);
+        mod->unused_crcs = section_addr(hdr, sechdrs, secstrings,
+                                        "__kcrctab_unused");
+        mod->unused_gpl_syms = section_objs(hdr, sechdrs, secstrings,
+                                            "__ksymtab_unused_gpl",
+                                            sizeof(*mod->unused_gpl_syms),
+                                            &mod->num_unused_gpl_syms);
+        mod->unused_gpl_crcs = section_addr(hdr, sechdrs, secstrings,
+                                            "__kcrctab_unused_gpl");
+#endif
+
+#ifdef CONFIG_MARKERS
+        mod->markers = section_objs(hdr, sechdrs, secstrings, "__markers",
+                                    sizeof(*mod->markers), &mod->num_markers);
+#endif
+#ifdef CONFIG_TRACEPOINTS
+        mod->tracepoints = section_objs(hdr, sechdrs, secstrings,
+                                        "__tracepoints",
+                                        sizeof(*mod->tracepoints),
+                                        &mod->num_tracepoints);
 #endif
 
 #ifdef CONFIG_MODVERSIONS
-        if ((mod->num_syms && !crcindex)
-            || (mod->num_gpl_syms && !gplcrcindex)
-            || (mod->num_gpl_future_syms && !gplfuturecrcindex)
+        if ((mod->num_syms && !mod->crcs)
+            || (mod->num_gpl_syms && !mod->gpl_crcs)
+            || (mod->num_gpl_future_syms && !mod->gpl_future_crcs)
 #ifdef CONFIG_UNUSED_SYMBOLS
-            || (mod->num_unused_syms && !unusedcrcindex)
-            || (mod->num_unused_gpl_syms && !unusedgplcrcindex)
+            || (mod->num_unused_syms && !mod->unused_crcs)
+            || (mod->num_unused_gpl_syms && !mod->unused_gpl_crcs)
 #endif
                 ) {
                 printk(KERN_WARNING "%s: No versions for exported symbols.\n", mod->name);
@@ -2114,9 +2141,6 @@ static noinline struct module *load_module(void __user *umod,
                         goto cleanup;
         }
 #endif
-        markersindex = find_sec(hdr, sechdrs, secstrings, "__markers");
-        markersstringsindex = find_sec(hdr, sechdrs, secstrings,
-                                        "__markers_strings");
 
         /* Now do relocations. */
         for (i = 1; i < hdr->e_shnum; i++) {
@@ -2139,22 +2163,16 @@ static noinline struct module *load_module(void __user *umod,
                 if (err < 0)
                         goto cleanup;
         }
-#ifdef CONFIG_MARKERS
-        mod->markers = (void *)sechdrs[markersindex].sh_addr;
-        mod->num_markers =
-                sechdrs[markersindex].sh_size / sizeof(*mod->markers);
-#endif
 
         /* Find duplicate symbols */
         err = verify_export_symbols(mod);
-
         if (err < 0)
                 goto cleanup;
 
         /* Set up and sort exception table */
-        mod->num_exentries = sechdrs[exindex].sh_size / sizeof(*mod->extable);
-        mod->extable = extable = (void *)sechdrs[exindex].sh_addr;
-        sort_extable(extable, extable + mod->num_exentries);
+        mod->extable = section_objs(hdr, sechdrs, secstrings, "__ex_table",
+                                    sizeof(*mod->extable), &mod->num_exentries);
+        sort_extable(mod->extable, mod->extable + mod->num_exentries);
 
         /* Finally, copy percpu area over. */
         percpu_modcopy(mod->percpu, (void *)sechdrs[pcpuindex].sh_addr,
@@ -2162,11 +2180,29 @@ static noinline struct module *load_module(void __user *umod,
 
         add_kallsyms(mod, sechdrs, symindex, strindex, secstrings);
 
+        if (!mod->taints) {
+                struct mod_debug *debug;
+                unsigned int num_debug;
+
 #ifdef CONFIG_MARKERS
-        if (!mod->taints)
                 marker_update_probe_range(mod->markers,
                         mod->markers + mod->num_markers);
 #endif
+                debug = section_objs(hdr, sechdrs, secstrings, "__verbose",
+                                     sizeof(*debug), &num_debug);
+                dynamic_printk_setup(debug, num_debug);
+
+#ifdef CONFIG_TRACEPOINTS
+                tracepoint_update_probe_range(mod->tracepoints,
+                        mod->tracepoints + mod->num_tracepoints);
+#endif
+        }
+
+        /* sechdrs[0].sh_size is always zero */
+        mseg = section_objs(hdr, sechdrs, secstrings, "__mcount_loc",
+                            sizeof(*mseg), &num_mcount);
+        ftrace_init_module(mseg, mseg + num_mcount);
+
         err = module_finalize(hdr, sechdrs, mod);
         if (err < 0)
                 goto cleanup;
@@ -2190,30 +2226,24 @@ static noinline struct module *load_module(void __user *umod,
         set_fs(old_fs);
 
         mod->args = args;
-        if (obsparmindex)
+        if (section_addr(hdr, sechdrs, secstrings, "__obsparm"))
                 printk(KERN_WARNING "%s: Ignoring obsolete parameters\n",
                        mod->name);
 
         /* Now sew it into the lists so we can get lockdep and oops
-         * info during argument parsing.  Noone should access us, since
-         * strong_try_module_get() will fail. */
-        stop_machine(__link_module, mod, NULL);
-
-        /* Size of section 0 is 0, so this works well if no params */
-        err = parse_args(mod->name, mod->args,
-                         (struct kernel_param *)
-                         sechdrs[setupindex].sh_addr,
-                         sechdrs[setupindex].sh_size
-                         / sizeof(struct kernel_param),
-                         NULL);
+         * info during argument parsing.  Noone should access us, since
+         * strong_try_module_get() will fail.
+         * lockdep/oops can run asynchronous, so use the RCU list insertion
+         * function to insert in a way safe to concurrent readers.
+         * The mutex protects against concurrent writers.
+         */
+        list_add_rcu(&mod->list, &modules);
+
+        err = parse_args(mod->name, mod->args, kp, num_kp, NULL);
         if (err < 0)
                 goto unlink;
 
-        err = mod_sysfs_setup(mod,
-                              (struct kernel_param *)
-                              sechdrs[setupindex].sh_addr,
-                              sechdrs[setupindex].sh_size
-                              / sizeof(struct kernel_param));
+        err = mod_sysfs_setup(mod, kp, num_kp);
         if (err < 0)
                 goto unlink;
         add_sect_attrs(mod, hdr->e_shnum, secstrings, sechdrs);
@@ -2236,6 +2266,7 @@ static noinline struct module *load_module(void __user *umod,
  cleanup:
         kobject_del(&mod->mkobj.kobj);
         kobject_put(&mod->mkobj.kobj);
+        ftrace_release(mod->module_core, mod->core_size);
  free_unload:
         module_unload_free(mod);
         module_free(mod, mod->module_init);
@@ -2401,7 +2432,7 @@ const char *module_address_lookup(unsigned long addr,
         const char *ret = NULL;
 
         preempt_disable();
-        list_for_each_entry(mod, &modules, list) {
+        list_for_each_entry_rcu(mod, &modules, list) {
                 if (within(addr, mod->module_init, mod->init_size)
                     || within(addr, mod->module_core, mod->core_size)) {
                         if (modname)
@@ -2424,7 +2455,7 @@ int lookup_module_symbol_name(unsigned long addr, char *symname)
         struct module *mod;
 
         preempt_disable();
-        list_for_each_entry(mod, &modules, list) {
+        list_for_each_entry_rcu(mod, &modules, list) {
                 if (within(addr, mod->module_init, mod->init_size) ||
                     within(addr, mod->module_core, mod->core_size)) {
                         const char *sym;
@@ -2448,7 +2479,7 @@ int lookup_module_symbol_attrs(unsigned long addr, unsigned long *size,
         struct module *mod;
 
         preempt_disable();
-        list_for_each_entry(mod, &modules, list) {
+        list_for_each_entry_rcu(mod, &modules, list) {
                 if (within(addr, mod->module_init, mod->init_size) ||
                     within(addr, mod->module_core, mod->core_size)) {
                         const char *sym;
@@ -2475,7 +2506,7 @@ int module_get_kallsym(unsigned int symnum, unsigned long *value, char *type,
         struct module *mod;
 
         preempt_disable();
-        list_for_each_entry(mod, &modules, list) {
+        list_for_each_entry_rcu(mod, &modules, list) {
                 if (symnum < mod->num_symtab) {
                         *value = mod->symtab[symnum].st_value;
                         *type = mod->symtab[symnum].st_info;
@@ -2518,7 +2549,7 @@ unsigned long module_kallsyms_lookup_name(const char *name)
                         ret = mod_find_symname(mod, colon+1);
                 *colon = ':';
         } else {
-                list_for_each_entry(mod, &modules, list)
+                list_for_each_entry_rcu(mod, &modules, list)
                         if ((ret = mod_find_symname(mod, name)) != 0)
                                 break;
         }
@@ -2527,23 +2558,6 @@ unsigned long module_kallsyms_lookup_name(const char *name)
 }
 #endif /* CONFIG_KALLSYMS */
 
-/* Called by the /proc file system to return a list of modules. */
-static void *m_start(struct seq_file *m, loff_t *pos)
-{
-        mutex_lock(&module_mutex);
-        return seq_list_start(&modules, *pos);
-}
-
-static void *m_next(struct seq_file *m, void *p, loff_t *pos)
-{
-        return seq_list_next(p, &modules, pos);
-}
-
-static void m_stop(struct seq_file *m, void *p)
-{
-        mutex_unlock(&module_mutex);
-}
-
 static char *module_flags(struct module *mod, char *buf)
 {
         int bx = 0;
@@ -2552,10 +2566,12 @@ static char *module_flags(struct module *mod, char *buf)
             mod->state == MODULE_STATE_GOING ||
             mod->state == MODULE_STATE_COMING) {
                 buf[bx++] = '(';
-                if (mod->taints & TAINT_PROPRIETARY_MODULE)
+                if (mod->taints & (1 << TAINT_PROPRIETARY_MODULE))
                         buf[bx++] = 'P';
-                if (mod->taints & TAINT_FORCED_MODULE)
+                if (mod->taints & (1 << TAINT_FORCED_MODULE))
                         buf[bx++] = 'F';
+                if (mod->taints & (1 << TAINT_CRAP))
+                        buf[bx++] = 'C';
                 /*
                  * TAINT_FORCED_RMMOD: could be added.
                  * TAINT_UNSAFE_SMP, TAINT_MACHINE_CHECK, TAINT_BAD_PAGE don't
@@ -2575,6 +2591,24 @@ static char *module_flags(struct module *mod, char *buf)
         return buf;
 }
 
+#ifdef CONFIG_PROC_FS
+/* Called by the /proc file system to return a list of modules. */
+static void *m_start(struct seq_file *m, loff_t *pos)
+{
+        mutex_lock(&module_mutex);
+        return seq_list_start(&modules, *pos);
+}
+
+static void *m_next(struct seq_file *m, void *p, loff_t *pos)
+{
+        return seq_list_next(p, &modules, pos);
+}
+
+static void m_stop(struct seq_file *m, void *p)
+{
+        mutex_unlock(&module_mutex);
+}
+
 static int m_show(struct seq_file *m, void *p)
 {
         struct module *mod = list_entry(p, struct module, list);
@@ -2605,13 +2639,33 @@ static int m_show(struct seq_file *m, void *p)
    Where refcount is a number or -, and deps is a comma-separated list
    of depends or -.
 */
-const struct seq_operations modules_op = {
+static const struct seq_operations modules_op = {
         .start  = m_start,
         .next   = m_next,
         .stop   = m_stop,
         .show   = m_show
 };
 
+static int modules_open(struct inode *inode, struct file *file)
+{
+        return seq_open(file, &modules_op);
+}
+
+static const struct file_operations proc_modules_operations = {
+        .open           = modules_open,
+        .read           = seq_read,
+        .llseek         = seq_lseek,
+        .release        = seq_release,
+};
+
+static int __init proc_modules_init(void)
+{
+        proc_create("modules", 0, NULL, &proc_modules_operations);
+        return 0;
+}
+module_init(proc_modules_init);
+#endif
+
 /* Given an address, look for it in the module exception tables. */
 const struct exception_table_entry *search_module_extables(unsigned long addr)
 {
@@ -2619,7 +2673,7 @@ const struct exception_table_entry *search_module_extables(unsigned long addr)
         struct module *mod;
 
         preempt_disable();
-        list_for_each_entry(mod, &modules, list) {
+        list_for_each_entry_rcu(mod, &modules, list) {
                 if (mod->num_exentries == 0)
                         continue;
 
@@ -2645,7 +2699,7 @@ int is_module_address(unsigned long addr)
 
         preempt_disable();
 
-        list_for_each_entry(mod, &modules, list) {
+        list_for_each_entry_rcu(mod, &modules, list) {
                 if (within(addr, mod->module_core, mod->core_size)) {
                         preempt_enable();
                         return 1;
@@ -2666,7 +2720,7 @@ struct module *__module_text_address(unsigned long addr)
         if (addr < module_addr_min || addr > module_addr_max)
                 return NULL;
 
-        list_for_each_entry(mod, &modules, list)
+        list_for_each_entry_rcu(mod, &modules, list)
                 if (within(addr, mod->module_init, mod->init_text_size)
                     || within(addr, mod->module_core, mod->core_text_size))
                         return mod;
@@ -2691,8 +2745,11 @@ void print_modules(void)
         char buf[8];
 
         printk("Modules linked in:");
-        list_for_each_entry(mod, &modules, list)
+        /* Most callers should already have preempt disabled, but make sure */
+        preempt_disable();
+        list_for_each_entry_rcu(mod, &modules, list)
                 printk(" %s%s", mod->name, module_flags(mod, buf));
+        preempt_enable();
         if (last_unloaded_module[0])
                 printk(" [last unloaded: %s]", last_unloaded_module);
         printk("\n");
@@ -2717,3 +2774,50 @@ void module_update_markers(void)
         mutex_unlock(&module_mutex);
 }
 #endif
+
+#ifdef CONFIG_TRACEPOINTS
+void module_update_tracepoints(void)
+{
+        struct module *mod;
+
+        mutex_lock(&module_mutex);
+        list_for_each_entry(mod, &modules, list)
+                if (!mod->taints)
+                        tracepoint_update_probe_range(mod->tracepoints,
+                                mod->tracepoints + mod->num_tracepoints);
+        mutex_unlock(&module_mutex);
+}
+
+/*
+ * Returns 0 if current not found.
+ * Returns 1 if current found.
+ */
+int module_get_iter_tracepoints(struct tracepoint_iter *iter)
+{
+        struct module *iter_mod;
+        int found = 0;
+
+        mutex_lock(&module_mutex);
+        list_for_each_entry(iter_mod, &modules, list) {
+                if (!iter_mod->taints) {
+                        /*
+                         * 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,
+                                iter_mod->tracepoints
+                                        + iter_mod->num_tracepoints);
+                        if (found) {
+                                iter->module = iter_mod;
+                                break;
+                        }
+                }
+        }
+        mutex_unlock(&module_mutex);
+        return found;
+}
+#endif
diff --git a/kernel/notifier.c b/kernel/notifier.c
index 0f39e398ef60..61d5aa5eced3 100644
--- a/kernel/notifier.c
+++ b/kernel/notifier.c
@@ -558,7 +558,7 @@ EXPORT_SYMBOL(unregister_reboot_notifier);
 
 static ATOMIC_NOTIFIER_HEAD(die_chain);
 
-int notify_die(enum die_val val, const char *str,
+int notrace notify_die(enum die_val val, const char *str,
                struct pt_regs *regs, long err, int trap, int sig)
 {
         struct die_args args = {
diff --git a/kernel/panic.c b/kernel/panic.c
index 12c5a0a6c89b..6513aac8e992 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -23,7 +23,7 @@
 #include <linux/kallsyms.h>
 
 int panic_on_oops;
-int tainted;
+static unsigned long tainted_mask;
 static int pause_on_oops;
 static int pause_on_oops_flag;
 static DEFINE_SPINLOCK(pause_on_oops_lock);
@@ -34,13 +34,6 @@ ATOMIC_NOTIFIER_HEAD(panic_notifier_list);
 
 EXPORT_SYMBOL(panic_notifier_list);
 
-static int __init panic_setup(char *str)
-{
-        panic_timeout = simple_strtoul(str, NULL, 0);
-        return 1;
-}
-__setup("panic=", panic_setup);
-
 static long no_blink(long time)
 {
         return 0;
@@ -143,6 +136,27 @@ NORET_TYPE void panic(const char * fmt, ...)
 
 EXPORT_SYMBOL(panic);
 
+
+struct tnt {
+        u8 bit;
+        char true;
+        char false;
+};
+
+static const struct tnt tnts[] = {
+        { TAINT_PROPRIETARY_MODULE, 'P', 'G' },
+        { TAINT_FORCED_MODULE, 'F', ' ' },
+        { TAINT_UNSAFE_SMP, 'S', ' ' },
+        { TAINT_FORCED_RMMOD, 'R', ' ' },
+        { TAINT_MACHINE_CHECK, 'M', ' ' },
+        { TAINT_BAD_PAGE, 'B', ' ' },
+        { TAINT_USER, 'U', ' ' },
+        { TAINT_DIE, 'D', ' ' },
+        { TAINT_OVERRIDDEN_ACPI_TABLE, 'A', ' ' },
+        { TAINT_WARN, 'W', ' ' },
+        { TAINT_CRAP, 'C', ' ' },
+};
+
 /**
  *      print_tainted - return a string to represent the kernel taint state.
  *
@@ -155,44 +169,47 @@ EXPORT_SYMBOL(panic);
  *  'U' - Userspace-defined naughtiness.
  *  'A' - ACPI table overridden.
  *  'W' - Taint on warning.
+ *  'C' - modules from drivers/staging are loaded.
  *
  *      The string is overwritten by the next call to print_taint().
  */
-
 const char *print_tainted(void)
 {
-        static char buf[20];
-        if (tainted) {
-                snprintf(buf, sizeof(buf), "Tainted: %c%c%c%c%c%c%c%c%c%c",
-                        tainted & TAINT_PROPRIETARY_MODULE ? 'P' : 'G',
-                        tainted & TAINT_FORCED_MODULE ? 'F' : ' ',
-                        tainted & TAINT_UNSAFE_SMP ? 'S' : ' ',
-                        tainted & TAINT_FORCED_RMMOD ? 'R' : ' ',
-                        tainted & TAINT_MACHINE_CHECK ? 'M' : ' ',
-                        tainted & TAINT_BAD_PAGE ? 'B' : ' ',
-                        tainted & TAINT_USER ? 'U' : ' ',
-                        tainted & TAINT_DIE ? 'D' : ' ',
-                        tainted & TAINT_OVERRIDDEN_ACPI_TABLE ? 'A' : ' ',
-                        tainted & TAINT_WARN ? 'W' : ' ');
-        }
-        else
+        static char buf[ARRAY_SIZE(tnts) + sizeof("Tainted: ") + 1];
+
+        if (tainted_mask) {
+                char *s;
+                int i;
+
+                s = buf + sprintf(buf, "Tainted: ");
+                for (i = 0; i < ARRAY_SIZE(tnts); i++) {
+                        const struct tnt *t = &tnts[i];
+                        *s++ = test_bit(t->bit, &tainted_mask) ?
+                                        t->true : t->false;
+                }
+                *s = 0;
+        } else
                 snprintf(buf, sizeof(buf), "Not tainted");
         return(buf);
 }
 
-void add_taint(unsigned flag)
+int test_taint(unsigned flag)
 {
-        debug_locks = 0; /* can't trust the integrity of the kernel anymore */
-        tainted |= flag;
+        return test_bit(flag, &tainted_mask);
+}
+EXPORT_SYMBOL(test_taint);
+
+unsigned long get_taint(void)
+{
+        return tainted_mask;
 }
-EXPORT_SYMBOL(add_taint);
 
-static int __init pause_on_oops_setup(char *str)
+void add_taint(unsigned flag)
 {
-        pause_on_oops = simple_strtoul(str, NULL, 0);
-        return 1;
+        debug_locks = 0; /* can't trust the integrity of the kernel anymore */
+        set_bit(flag, &tainted_mask);
 }
-__setup("pause_on_oops=", pause_on_oops_setup);
+EXPORT_SYMBOL(add_taint);
 
 static void spin_msec(int msecs)
 {
@@ -353,3 +370,6 @@ void __stack_chk_fail(void)
 }
 EXPORT_SYMBOL(__stack_chk_fail);
 #endif
+
+core_param(panic, panic_timeout, int, 0644);
+core_param(pause_on_oops, pause_on_oops, int, 0644);
diff --git a/kernel/params.c b/kernel/params.c
index afc46a23eb6d..a1e3025b19a9 100644
--- a/kernel/params.c
+++ b/kernel/params.c
@@ -373,6 +373,8 @@ int param_get_string(char *buffer, struct kernel_param *kp)
 }
 
 /* sysfs output in /sys/modules/XYZ/parameters/ */
+#define to_module_attr(n) container_of(n, struct module_attribute, attr);
+#define to_module_kobject(n) container_of(n, struct module_kobject, kobj);
 
 extern struct kernel_param __start___param[], __stop___param[];
 
@@ -384,6 +386,7 @@ struct param_attribute
 
 struct module_param_attrs
 {
+        unsigned int num;
         struct attribute_group grp;
         struct param_attribute attrs[0];
 };
@@ -434,93 +437,120 @@ static ssize_t param_attr_store(struct module_attribute *mattr,
 
 #ifdef CONFIG_SYSFS
 /*
- * param_sysfs_setup - setup sysfs support for one module or KBUILD_MODNAME
- * @mk: struct module_kobject (contains parent kobject)
- * @kparam: array of struct kernel_param, the actual parameter definitions
- * @num_params: number of entries in array
- * @name_skip: offset where the parameter name start in kparam[].name. Needed for built-in "modules"
+ * add_sysfs_param - add a parameter to sysfs
+ * @mk: struct module_kobject
+ * @kparam: the actual parameter definition to add to sysfs
+ * @name: name of parameter
  *
- * Create a kobject for a (per-module) group of parameters, and create files
- * in sysfs. A pointer to the param_kobject is returned on success,
- * NULL if there's no parameter to export, or other ERR_PTR(err).
+ * Create a kobject if for a (per-module) parameter if mp NULL, and
+ * create file in sysfs.  Returns an error on out of memory.  Always cleans up
+ * if there's an error.
  */
-static __modinit struct module_param_attrs *
-param_sysfs_setup(struct module_kobject *mk,
-                  struct kernel_param *kparam,
-                  unsigned int num_params,
-                  unsigned int name_skip)
+static __modinit int add_sysfs_param(struct module_kobject *mk,
+                                     struct kernel_param *kp,
+                                     const char *name)
 {
-        struct module_param_attrs *mp;
-        unsigned int valid_attrs = 0;
-        unsigned int i, size[2];
-        struct param_attribute *pattr;
-        struct attribute **gattr;
-        int err;
-
-        for (i=0; i<num_params; i++) {
-                if (kparam[i].perm)
-                        valid_attrs++;
+        struct module_param_attrs *new;
+        struct attribute **attrs;
+        int err, num;
+
+        /* We don't bother calling this with invisible parameters. */
+        BUG_ON(!kp->perm);
+
+        if (!mk->mp) {
+                num = 0;
+                attrs = NULL;
+        } else {
+                num = mk->mp->num;
+                attrs = mk->mp->grp.attrs;
         }
 
-        if (!valid_attrs)
-                return NULL;
-
-        size[0] = ALIGN(sizeof(*mp) +
-                        valid_attrs * sizeof(mp->attrs[0]),
-                        sizeof(mp->grp.attrs[0]));
-        size[1] = (valid_attrs + 1) * sizeof(mp->grp.attrs[0]);
-
-        mp = kzalloc(size[0] + size[1], GFP_KERNEL);
-        if (!mp)
-                return ERR_PTR(-ENOMEM);
-
-        mp->grp.name = "parameters";
-        mp->grp.attrs = (void *)mp + size[0];
-
-        pattr = &mp->attrs[0];
-        gattr = &mp->grp.attrs[0];
-        for (i = 0; i < num_params; i++) {
-                struct kernel_param *kp = &kparam[i];
-                if (kp->perm) {
-                        pattr->param = kp;
-                        pattr->mattr.show = param_attr_show;
-                        pattr->mattr.store = param_attr_store;
-                        pattr->mattr.attr.name = (char *)&kp->name[name_skip];
-                        pattr->mattr.attr.mode = kp->perm;
-                        *(gattr++) = &(pattr++)->mattr.attr;
-                }
+        /* Enlarge. */
+        new = krealloc(mk->mp,
+                       sizeof(*mk->mp) + sizeof(mk->mp->attrs[0]) * (num+1),
+                       GFP_KERNEL);
+        if (!new) {
+                kfree(mk->mp);
+                err = -ENOMEM;
+                goto fail;
         }
-        *gattr = NULL;
-
-        if ((err = sysfs_create_group(&mk->kobj, &mp->grp))) {
-                kfree(mp);
-                return ERR_PTR(err);
+        attrs = krealloc(attrs, sizeof(new->grp.attrs[0])*(num+2), GFP_KERNEL);
+        if (!attrs) {
+                err = -ENOMEM;
+                goto fail_free_new;
         }
-        return mp;
+
+        /* Sysfs wants everything zeroed. */
+        memset(new, 0, sizeof(*new));
+        memset(&new->attrs[num], 0, sizeof(new->attrs[num]));
+        memset(&attrs[num], 0, sizeof(attrs[num]));
+        new->grp.name = "parameters";
+        new->grp.attrs = attrs;
+
+        /* Tack new one on the end. */
+        new->attrs[num].param = kp;
+        new->attrs[num].mattr.show = param_attr_show;
+        new->attrs[num].mattr.store = param_attr_store;
+        new->attrs[num].mattr.attr.name = (char *)name;
+        new->attrs[num].mattr.attr.mode = kp->perm;
+        new->num = num+1;
+
+        /* Fix up all the pointers, since krealloc can move us */
+        for (num = 0; num < new->num; num++)
+                new->grp.attrs[num] = &new->attrs[num].mattr.attr;
+        new->grp.attrs[num] = NULL;
+
+        mk->mp = new;
+        return 0;
+
+fail_free_new:
+        kfree(new);
+fail:
+        mk->mp = NULL;
+        return err;
 }
 
 #ifdef CONFIG_MODULES
+static void free_module_param_attrs(struct module_kobject *mk)
+{
+        kfree(mk->mp->grp.attrs);
+        kfree(mk->mp);
+        mk->mp = NULL;
+}
+
 /*
  * module_param_sysfs_setup - setup sysfs support for one module
  * @mod: module
  * @kparam: module parameters (array)
  * @num_params: number of module parameters
  *
- * Adds sysfs entries for module parameters, and creates a link from
- * /sys/module/[mod->name]/parameters to /sys/parameters/[mod->name]/
+ * Adds sysfs entries for module parameters under
+ * /sys/module/[mod->name]/parameters/
  */
 int module_param_sysfs_setup(struct module *mod,
                              struct kernel_param *kparam,
                              unsigned int num_params)
 {
-        struct module_param_attrs *mp;
+        int i, err;
+        bool params = false;
+
+        for (i = 0; i < num_params; i++) {
+                if (kparam[i].perm == 0)
+                        continue;
+                err = add_sysfs_param(&mod->mkobj, &kparam[i], kparam[i].name);
+                if (err)
+                        return err;
+                params = true;
+        }
 
-        mp = param_sysfs_setup(&mod->mkobj, kparam, num_params, 0);
-        if (IS_ERR(mp))
-                return PTR_ERR(mp);
+        if (!params)
+                return 0;
 
-        mod->param_attrs = mp;
-        return 0;
+        /* Create the param group. */
+        err = sysfs_create_group(&mod->mkobj.kobj, &mod->mkobj.mp->grp);
+        if (err)
+                free_module_param_attrs(&mod->mkobj);
+        return err;
 }
 
 /*
@@ -532,43 +562,55 @@ int module_param_sysfs_setup(struct module *mod,
  */
 void module_param_sysfs_remove(struct module *mod)
 {
-        if (mod->param_attrs) {
-                sysfs_remove_group(&mod->mkobj.kobj,
-                                   &mod->param_attrs->grp);
+        if (mod->mkobj.mp) {
+                sysfs_remove_group(&mod->mkobj.kobj, &mod->mkobj.mp->grp);
                 /* We are positive that no one is using any param
                  * attrs at this point.  Deallocate immediately. */
-                kfree(mod->param_attrs);
-                mod->param_attrs = NULL;
+                free_module_param_attrs(&mod->mkobj);
         }
 }
 #endif
 
-/*
- * kernel_param_sysfs_setup - wrapper for built-in params support
- */
-static void __init kernel_param_sysfs_setup(const char *name,
-                                            struct kernel_param *kparam,
-                                            unsigned int num_params,
-                                            unsigned int name_skip)
+static void __init kernel_add_sysfs_param(const char *name,
+                                          struct kernel_param *kparam,
+                                          unsigned int name_skip)
 {
         struct module_kobject *mk;
-        int ret;
+        struct kobject *kobj;
+        int err;
 
-        mk = kzalloc(sizeof(struct module_kobject), GFP_KERNEL);
-        BUG_ON(!mk);
-
-        mk->mod = THIS_MODULE;
-        mk->kobj.kset = module_kset;
-        ret = kobject_init_and_add(&mk->kobj, &module_ktype, NULL, "%s", name);
-        if (ret) {
-                kobject_put(&mk->kobj);
-                printk(KERN_ERR "Module '%s' failed to be added to sysfs, "
-                      "error number %d\n", name, ret);
-                printk(KERN_ERR "The system will be unstable now.\n");
-                return;
+        kobj = kset_find_obj(module_kset, name);
+        if (kobj) {
+                /* We already have one.  Remove params so we can add more. */
+                mk = to_module_kobject(kobj);
+                /* We need to remove it before adding parameters. */
+                sysfs_remove_group(&mk->kobj, &mk->mp->grp);
+        } else {
+                mk = kzalloc(sizeof(struct module_kobject), GFP_KERNEL);
+                BUG_ON(!mk);
+
+                mk->mod = THIS_MODULE;
+                mk->kobj.kset = module_kset;
+                err = kobject_init_and_add(&mk->kobj, &module_ktype, NULL,
+                                           "%s", name);
+                if (err) {
+                        kobject_put(&mk->kobj);
+                        printk(KERN_ERR "Module '%s' failed add to sysfs, "
+                               "error number %d\n", name, err);
+                        printk(KERN_ERR "The system will be unstable now.\n");
+                        return;
+                }
+                /* So that exit path is even. */
+                kobject_get(&mk->kobj);
         }
-        param_sysfs_setup(mk, kparam, num_params, name_skip);
+
+        /* These should not fail at boot. */
+        err = add_sysfs_param(mk, kparam, kparam->name + name_skip);
+        BUG_ON(err);
+        err = sysfs_create_group(&mk->kobj, &mk->mp->grp);
+        BUG_ON(err);
         kobject_uevent(&mk->kobj, KOBJ_ADD);
+        kobject_put(&mk->kobj);
 }
 
 /*
@@ -579,60 +621,36 @@ static void __init kernel_param_sysfs_setup(const char *name,
  * The "module" name (KBUILD_MODNAME) is stored before a dot, the
  * "parameter" name is stored behind a dot in kernel_param->name. So,
  * extract the "module" name for all built-in kernel_param-eters,
- * and for all who have the same, call kernel_param_sysfs_setup.
+ * and for all who have the same, call kernel_add_sysfs_param.
  */
 static void __init param_sysfs_builtin(void)
 {
-        struct kernel_param *kp, *kp_begin = NULL;
-        unsigned int i, name_len, count = 0;
-        char modname[MODULE_NAME_LEN + 1] = "";
+        struct kernel_param *kp;
+        unsigned int name_len;
+        char modname[MODULE_NAME_LEN];
 
-        for (i=0; i < __stop___param - __start___param; i++) {
+        for (kp = __start___param; kp < __stop___param; kp++) {
                 char *dot;
-                size_t max_name_len;
 
-                kp = &__start___param[i];
-                max_name_len =
-                        min_t(size_t, MODULE_NAME_LEN, strlen(kp->name));
+                if (kp->perm == 0)
+                        continue;
 
-                dot = memchr(kp->name, '.', max_name_len);
+                dot = strchr(kp->name, '.');
                 if (!dot) {
-                        DEBUGP("couldn't find period in first %d characters "
-                               "of %s\n", MODULE_NAME_LEN, kp->name);
-                        continue;
-                }
-                name_len = dot - kp->name;
-
-                /* new kbuild_modname? */
-                if (strlen(modname) != name_len
-                    || strncmp(modname, kp->name, name_len) != 0) {
-                        /* add a new kobject for previous kernel_params. */
-                        if (count)
-                                kernel_param_sysfs_setup(modname,
-                                                         kp_begin,
-                                                         count,
-                                                         strlen(modname)+1);
-
-                        strncpy(modname, kp->name, name_len);
-                        modname[name_len] = '\0';
-                        count = 0;
-                        kp_begin = kp;
+                        /* This happens for core_param() */
+                        strcpy(modname, "kernel");
+                        name_len = 0;
+                } else {
+                        name_len = dot - kp->name + 1;
+                        strlcpy(modname, kp->name, name_len);
                 }
-                count++;
+                kernel_add_sysfs_param(modname, kp, name_len);
         }
-
-        /* last kernel_params need to be registered as well */
-        if (count)
-                kernel_param_sysfs_setup(modname, kp_begin, count,
-                                         strlen(modname)+1);
 }
 
 
 /* module-related sysfs stuff */
 
-#define to_module_attr(n) container_of(n, struct module_attribute, attr);
-#define to_module_kobject(n) container_of(n, struct module_kobject, kobj);
-
 static ssize_t module_attr_show(struct kobject *kobj,
                                 struct attribute *attr,
                                 char *buf)
diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c
index c42a03aef36f..895337b16a24 100644
--- a/kernel/posix-cpu-timers.c
+++ b/kernel/posix-cpu-timers.c
@@ -7,6 +7,93 @@
 #include <linux/errno.h>
 #include <linux/math64.h>
 #include <asm/uaccess.h>
+#include <linux/kernel_stat.h>
+
+/*
+ * Allocate the thread_group_cputime structure appropriately and fill in the
+ * current values of the fields.  Called from copy_signal() via
+ * thread_group_cputime_clone_thread() when adding a second or subsequent
+ * thread to a thread group.  Assumes interrupts are enabled when called.
+ */
+int thread_group_cputime_alloc(struct task_struct *tsk)
+{
+        struct signal_struct *sig = tsk->signal;
+        struct task_cputime *cputime;
+
+        /*
+         * If we have multiple threads and we don't already have a
+         * per-CPU task_cputime struct (checked in the caller), allocate
+         * one and fill it in with the times accumulated so far.  We may
+         * race with another thread so recheck after we pick up the sighand
+         * lock.
+         */
+        cputime = alloc_percpu(struct task_cputime);
+        if (cputime == NULL)
+                return -ENOMEM;
+        spin_lock_irq(&tsk->sighand->siglock);
+        if (sig->cputime.totals) {
+                spin_unlock_irq(&tsk->sighand->siglock);
+                free_percpu(cputime);
+                return 0;
+        }
+        sig->cputime.totals = cputime;
+        cputime = per_cpu_ptr(sig->cputime.totals, smp_processor_id());
+        cputime->utime = tsk->utime;
+        cputime->stime = tsk->stime;
+        cputime->sum_exec_runtime = tsk->se.sum_exec_runtime;
+        spin_unlock_irq(&tsk->sighand->siglock);
+        return 0;
+}
+
+/**
+ * thread_group_cputime - Sum the thread group time fields across all CPUs.
+ *
+ * @tsk:        The task we use to identify the thread group.
+ * @times:      task_cputime structure in which we return the summed fields.
+ *
+ * Walk the list of CPUs to sum the per-CPU time fields in the thread group
+ * time structure.
+ */
+void thread_group_cputime(
+        struct task_struct *tsk,
+        struct task_cputime *times)
+{
+        struct signal_struct *sig;
+        int i;
+        struct task_cputime *tot;
+
+        sig = tsk->signal;
+        if (unlikely(!sig) || !sig->cputime.totals) {
+                times->utime = tsk->utime;
+                times->stime = tsk->stime;
+                times->sum_exec_runtime = tsk->se.sum_exec_runtime;
+                return;
+        }
+        times->stime = times->utime = cputime_zero;
+        times->sum_exec_runtime = 0;
+        for_each_possible_cpu(i) {
+                tot = per_cpu_ptr(tsk->signal->cputime.totals, i);
+                times->utime = cputime_add(times->utime, tot->utime);
+                times->stime = cputime_add(times->stime, tot->stime);
+                times->sum_exec_runtime += tot->sum_exec_runtime;
+        }
+}
+
+/*
+ * Called after updating RLIMIT_CPU to set timer expiration if necessary.
+ */
+void update_rlimit_cpu(unsigned long rlim_new)
+{
+        cputime_t cputime;
+
+        cputime = secs_to_cputime(rlim_new);
+        if (cputime_eq(current->signal->it_prof_expires, cputime_zero) ||
+            cputime_lt(current->signal->it_prof_expires, cputime)) {
+                spin_lock_irq(&current->sighand->siglock);
+                set_process_cpu_timer(current, CPUCLOCK_PROF, &cputime, NULL);
+                spin_unlock_irq(&current->sighand->siglock);
+        }
+}
 
 static int check_clock(const clockid_t which_clock)
 {
@@ -158,10 +245,6 @@ static inline cputime_t virt_ticks(struct task_struct *p)
 {
         return p->utime;
 }
-static inline unsigned long long sched_ns(struct task_struct *p)
-{
-        return task_sched_runtime(p);
-}
 
 int posix_cpu_clock_getres(const clockid_t which_clock, struct timespec *tp)
 {
@@ -211,7 +294,7 @@ static int cpu_clock_sample(const clockid_t which_clock, struct task_struct *p,
                 cpu->cpu = virt_ticks(p);
                 break;
         case CPUCLOCK_SCHED:
-                cpu->sched = sched_ns(p);
+                cpu->sched = p->se.sum_exec_runtime + task_delta_exec(p);
                 break;
         }
         return 0;
@@ -220,59 +303,30 @@ static int cpu_clock_sample(const clockid_t which_clock, struct task_struct *p,
 /*
  * Sample a process (thread group) clock for the given group_leader task.
  * Must be called with tasklist_lock held for reading.
- * Must be called with tasklist_lock held for reading, and p->sighand->siglock.
  */
-static int cpu_clock_sample_group_locked(unsigned int clock_idx,
-                                         struct task_struct *p,
-                                         union cpu_time_count *cpu)
+static int cpu_clock_sample_group(const clockid_t which_clock,
+                                  struct task_struct *p,
+                                  union cpu_time_count *cpu)
 {
-        struct task_struct *t = p;
-        switch (clock_idx) {
+        struct task_cputime cputime;
+
+        thread_group_cputime(p, &cputime);
+        switch (which_clock) {
         default:
                 return -EINVAL;
         case CPUCLOCK_PROF:
-                cpu->cpu = cputime_add(p->signal->utime, p->signal->stime);
-                do {
-                        cpu->cpu = cputime_add(cpu->cpu, prof_ticks(t));
-                        t = next_thread(t);
-                } while (t != p);
+                cpu->cpu = cputime_add(cputime.utime, cputime.stime);
                 break;
         case CPUCLOCK_VIRT:
-                cpu->cpu = p->signal->utime;
-                do {
-                        cpu->cpu = cputime_add(cpu->cpu, virt_ticks(t));
-                        t = next_thread(t);
-                } while (t != p);
+                cpu->cpu = cputime.utime;
                 break;
         case CPUCLOCK_SCHED:
-                cpu->sched = p->signal->sum_sched_runtime;
-                /* Add in each other live thread.  */
-                while ((t = next_thread(t)) != p) {
-                        cpu->sched += t->se.sum_exec_runtime;
-                }
-                cpu->sched += sched_ns(p);
+                cpu->sched = cputime.sum_exec_runtime + task_delta_exec(p);
                 break;
         }
         return 0;
 }
 
-/*
- * Sample a process (thread group) clock for the given group_leader task.
- * Must be called with tasklist_lock held for reading.
- */
-static int cpu_clock_sample_group(const clockid_t which_clock,
-                                  struct task_struct *p,
-                                  union cpu_time_count *cpu)
-{
-        int ret;
-        unsigned long flags;
-        spin_lock_irqsave(&p->sighand->siglock, flags);
-        ret = cpu_clock_sample_group_locked(CPUCLOCK_WHICH(which_clock), p,
-                                            cpu);
-        spin_unlock_irqrestore(&p->sighand->siglock, flags);
-        return ret;
-}
-
 
 int posix_cpu_clock_get(const clockid_t which_clock, struct timespec *tp)
 {
@@ -471,80 +525,11 @@ void posix_cpu_timers_exit(struct task_struct *tsk)
 }
 void posix_cpu_timers_exit_group(struct task_struct *tsk)
 {
-        cleanup_timers(tsk->signal->cpu_timers,
-                       cputime_add(tsk->utime, tsk->signal->utime),
-                       cputime_add(tsk->stime, tsk->signal->stime),
-                     tsk->se.sum_exec_runtime + tsk->signal->sum_sched_runtime);
-}
-
-
-/*
- * Set the expiry times of all the threads in the process so one of them
- * will go off before the process cumulative expiry total is reached.
- */
-static void process_timer_rebalance(struct task_struct *p,
-                                    unsigned int clock_idx,
-                                    union cpu_time_count expires,
-                                    union cpu_time_count val)
-{
-        cputime_t ticks, left;
-        unsigned long long ns, nsleft;
-        struct task_struct *t = p;
-        unsigned int nthreads = atomic_read(&p->signal->live);
+        struct task_cputime cputime;
 
-        if (!nthreads)
-                return;
-
-        switch (clock_idx) {
-        default:
-                BUG();
-                break;
-        case CPUCLOCK_PROF:
-                left = cputime_div_non_zero(cputime_sub(expires.cpu, val.cpu),
-                                       nthreads);
-                do {
-                        if (likely(!(t->flags & PF_EXITING))) {
-                                ticks = cputime_add(prof_ticks(t), left);
-                                if (cputime_eq(t->it_prof_expires,
-                                               cputime_zero) ||
-                                    cputime_gt(t->it_prof_expires, ticks)) {
-                                        t->it_prof_expires = ticks;
-                                }
-                        }
-                        t = next_thread(t);
-                } while (t != p);
-                break;
-        case CPUCLOCK_VIRT:
-                left = cputime_div_non_zero(cputime_sub(expires.cpu, val.cpu),
-                                       nthreads);
-                do {
-                        if (likely(!(t->flags & PF_EXITING))) {
-                                ticks = cputime_add(virt_ticks(t), left);
-                                if (cputime_eq(t->it_virt_expires,
-                                               cputime_zero) ||
-                                    cputime_gt(t->it_virt_expires, ticks)) {
-                                        t->it_virt_expires = ticks;
-                                }
-                        }
-                        t = next_thread(t);
-                } while (t != p);
-                break;
-        case CPUCLOCK_SCHED:
-                nsleft = expires.sched - val.sched;
-                do_div(nsleft, nthreads);
-                nsleft = max_t(unsigned long long, nsleft, 1);
-                do {
-                        if (likely(!(t->flags & PF_EXITING))) {
-                                ns = t->se.sum_exec_runtime + nsleft;
-                                if (t->it_sched_expires == 0 ||
-                                    t->it_sched_expires > ns) {
-                                        t->it_sched_expires = ns;
-                                }
-                        }
-                        t = next_thread(t);
-                } while (t != p);
-                break;
-        }
+        thread_group_cputime(tsk, &cputime);
+        cleanup_timers(tsk->signal->cpu_timers,
+                       cputime.utime, cputime.stime, cputime.sum_exec_runtime);
 }
 
 static void clear_dead_task(struct k_itimer *timer, union cpu_time_count now)
@@ -608,29 +593,32 @@ static void arm_timer(struct k_itimer *timer, union cpu_time_count now)
                         default:
                                 BUG();
                         case CPUCLOCK_PROF:
-                                if (cputime_eq(p->it_prof_expires,
+                                if (cputime_eq(p->cputime_expires.prof_exp,
                                                cputime_zero) ||
-                                    cputime_gt(p->it_prof_expires,
+                                    cputime_gt(p->cputime_expires.prof_exp,
                                                nt->expires.cpu))
-                                        p->it_prof_expires = nt->expires.cpu;
+                                        p->cputime_expires.prof_exp =
+                                                nt->expires.cpu;
                                 break;
                         case CPUCLOCK_VIRT:
-                                if (cputime_eq(p->it_virt_expires,
+                                if (cputime_eq(p->cputime_expires.virt_exp,
                                                cputime_zero) ||
-                                    cputime_gt(p->it_virt_expires,
+                                    cputime_gt(p->cputime_expires.virt_exp,
                                                nt->expires.cpu))
-                                        p->it_virt_expires = nt->expires.cpu;
+                                        p->cputime_expires.virt_exp =
+                                                nt->expires.cpu;
                                 break;
                         case CPUCLOCK_SCHED:
-                                if (p->it_sched_expires == 0 ||
-                                    p->it_sched_expires > nt->expires.sched)
-                                        p->it_sched_expires = nt->expires.sched;
+                                if (p->cputime_expires.sched_exp == 0 ||
+                                    p->cputime_expires.sched_exp >
+                                                        nt->expires.sched)
+                                        p->cputime_expires.sched_exp =
+                                                nt->expires.sched;
                                 break;
                         }
                 } else {
                         /*
-                         * For a process timer, we must balance
-                         * all the live threads' expirations.
+                         * For a process timer, set the cached expiration time.
                          */
                         switch (CPUCLOCK_WHICH(timer->it_clock)) {
                         default:
@@ -641,7 +629,9 @@ static void arm_timer(struct k_itimer *timer, union cpu_time_count now)
                                     cputime_lt(p->signal->it_virt_expires,
                                                timer->it.cpu.expires.cpu))
                                         break;
-                                goto rebalance;
+                                p->signal->cputime_expires.virt_exp =
+                                        timer->it.cpu.expires.cpu;
+                                break;
                         case CPUCLOCK_PROF:
                                 if (!cputime_eq(p->signal->it_prof_expires,
                                                 cputime_zero) &&
@@ -652,13 +642,12 @@ static void arm_timer(struct k_itimer *timer, union cpu_time_count now)
                                 if (i != RLIM_INFINITY &&
                                     i <= cputime_to_secs(timer->it.cpu.expires.cpu))
                                         break;
-                                goto rebalance;
+                                p->signal->cputime_expires.prof_exp =
+                                        timer->it.cpu.expires.cpu;
+                                break;
                         case CPUCLOCK_SCHED:
-                        rebalance:
-                                process_timer_rebalance(
-                                        timer->it.cpu.task,
-                                        CPUCLOCK_WHICH(timer->it_clock),
-                                        timer->it.cpu.expires, now);
+                                p->signal->cputime_expires.sched_exp =
+                                        timer->it.cpu.expires.sched;
                                 break;
                         }
                 }
@@ -969,13 +958,13 @@ static void check_thread_timers(struct task_struct *tsk,
         struct signal_struct *const sig = tsk->signal;
 
         maxfire = 20;
-        tsk->it_prof_expires = cputime_zero;
+        tsk->cputime_expires.prof_exp = cputime_zero;
         while (!list_empty(timers)) {
                 struct cpu_timer_list *t = list_first_entry(timers,
                                                       struct cpu_timer_list,
                                                       entry);
                 if (!--maxfire || cputime_lt(prof_ticks(tsk), t->expires.cpu)) {
-                        tsk->it_prof_expires = t->expires.cpu;
+                        tsk->cputime_expires.prof_exp = t->expires.cpu;
                         break;
                 }
                 t->firing = 1;
@@ -984,13 +973,13 @@ static void check_thread_timers(struct task_struct *tsk,
 
         ++timers;
         maxfire = 20;
-        tsk->it_virt_expires = cputime_zero;
+        tsk->cputime_expires.virt_exp = cputime_zero;
         while (!list_empty(timers)) {
                 struct cpu_timer_list *t = list_first_entry(timers,
                                                       struct cpu_timer_list,
                                                       entry);
                 if (!--maxfire || cputime_lt(virt_ticks(tsk), t->expires.cpu)) {
-                        tsk->it_virt_expires = t->expires.cpu;
+                        tsk->cputime_expires.virt_exp = t->expires.cpu;
                         break;
                 }
                 t->firing = 1;
@@ -999,13 +988,13 @@ static void check_thread_timers(struct task_struct *tsk,
 
         ++timers;
         maxfire = 20;
-        tsk->it_sched_expires = 0;
+        tsk->cputime_expires.sched_exp = 0;
         while (!list_empty(timers)) {
                 struct cpu_timer_list *t = list_first_entry(timers,
                                                       struct cpu_timer_list,
                                                       entry);
                 if (!--maxfire || tsk->se.sum_exec_runtime < t->expires.sched) {
-                        tsk->it_sched_expires = t->expires.sched;
+                        tsk->cputime_expires.sched_exp = t->expires.sched;
                         break;
                 }
                 t->firing = 1;
@@ -1055,10 +1044,10 @@ static void check_process_timers(struct task_struct *tsk,
 {
         int maxfire;
         struct signal_struct *const sig = tsk->signal;
-        cputime_t utime, stime, ptime, virt_expires, prof_expires;
+        cputime_t utime, ptime, virt_expires, prof_expires;
         unsigned long long sum_sched_runtime, sched_expires;
-        struct task_struct *t;
         struct list_head *timers = sig->cpu_timers;
+        struct task_cputime cputime;
 
         /*
          * Don't sample the current process CPU clocks if there are no timers.
@@ -1074,18 +1063,10 @@ static void check_process_timers(struct task_struct *tsk,
         /*
          * Collect the current process totals.
          */
-        utime = sig->utime;
-        stime = sig->stime;
-        sum_sched_runtime = sig->sum_sched_runtime;
-        t = tsk;
-        do {
-                utime = cputime_add(utime, t->utime);
-                stime = cputime_add(stime, t->stime);
-                sum_sched_runtime += t->se.sum_exec_runtime;
-                t = next_thread(t);
-        } while (t != tsk);
-        ptime = cputime_add(utime, stime);
-
+        thread_group_cputime(tsk, &cputime);
+        utime = cputime.utime;
+        ptime = cputime_add(utime, cputime.stime);
+        sum_sched_runtime = cputime.sum_exec_runtime;
         maxfire = 20;
         prof_expires = cputime_zero;
         while (!list_empty(timers)) {
@@ -1193,60 +1174,18 @@ static void check_process_timers(struct task_struct *tsk,
                 }
         }
 
-        if (!cputime_eq(prof_expires, cputime_zero) ||
-            !cputime_eq(virt_expires, cputime_zero) ||
-            sched_expires != 0) {
-                /*
-                 * Rebalance the threads' expiry times for the remaining
-                 * process CPU timers.
-                 */
-
-                cputime_t prof_left, virt_left, ticks;
-                unsigned long long sched_left, sched;
-                const unsigned int nthreads = atomic_read(&sig->live);
-
-                if (!nthreads)
-                        return;
-
-                prof_left = cputime_sub(prof_expires, utime);
-                prof_left = cputime_sub(prof_left, stime);
-                prof_left = cputime_div_non_zero(prof_left, nthreads);
-                virt_left = cputime_sub(virt_expires, utime);
-                virt_left = cputime_div_non_zero(virt_left, nthreads);
-                if (sched_expires) {
-                        sched_left = sched_expires - sum_sched_runtime;
-                        do_div(sched_left, nthreads);
-                        sched_left = max_t(unsigned long long, sched_left, 1);
-                } else {
-                        sched_left = 0;
-                }
-                t = tsk;
-                do {
-                        if (unlikely(t->flags & PF_EXITING))
-                                continue;
-
-                        ticks = cputime_add(cputime_add(t->utime, t->stime),
-                                            prof_left);
-                        if (!cputime_eq(prof_expires, cputime_zero) &&
-                            (cputime_eq(t->it_prof_expires, cputime_zero) ||
-                             cputime_gt(t->it_prof_expires, ticks))) {
-                                t->it_prof_expires = ticks;
-                        }
-
-                        ticks = cputime_add(t->utime, virt_left);
-                        if (!cputime_eq(virt_expires, cputime_zero) &&
-                            (cputime_eq(t->it_virt_expires, cputime_zero) ||
-                             cputime_gt(t->it_virt_expires, ticks))) {
-                                t->it_virt_expires = ticks;
-                        }
-
-                        sched = t->se.sum_exec_runtime + sched_left;
-                        if (sched_expires && (t->it_sched_expires == 0 ||
-                                              t->it_sched_expires > sched)) {
-                                t->it_sched_expires = sched;
-                        }
-                } while ((t = next_thread(t)) != tsk);
-        }
+        if (!cputime_eq(prof_expires, cputime_zero) &&
+            (cputime_eq(sig->cputime_expires.prof_exp, cputime_zero) ||
+             cputime_gt(sig->cputime_expires.prof_exp, prof_expires)))
+                sig->cputime_expires.prof_exp = prof_expires;
+        if (!cputime_eq(virt_expires, cputime_zero) &&
+            (cputime_eq(sig->cputime_expires.virt_exp, cputime_zero) ||
+             cputime_gt(sig->cputime_expires.virt_exp, virt_expires)))
+                sig->cputime_expires.virt_exp = virt_expires;
+        if (sched_expires != 0 &&
+            (sig->cputime_expires.sched_exp == 0 ||
+             sig->cputime_expires.sched_exp > sched_expires))
+                sig->cputime_expires.sched_exp = sched_expires;
 }
 
 /*
@@ -1314,6 +1253,89 @@ out:
         ++timer->it_requeue_pending;
 }
 
+/**
+ * task_cputime_zero - Check a task_cputime struct for all zero fields.
+ *
+ * @cputime:    The struct to compare.
+ *
+ * Checks @cputime to see if all fields are zero.  Returns true if all fields
+ * are zero, false if any field is nonzero.
+ */
+static inline int task_cputime_zero(const struct task_cputime *cputime)
+{
+        if (cputime_eq(cputime->utime, cputime_zero) &&
+            cputime_eq(cputime->stime, cputime_zero) &&
+            cputime->sum_exec_runtime == 0)
+                return 1;
+        return 0;
+}
+
+/**
+ * task_cputime_expired - Compare two task_cputime entities.
+ *
+ * @sample:     The task_cputime structure to be checked for expiration.
+ * @expires:    Expiration times, against which @sample will be checked.
+ *
+ * Checks @sample against @expires to see if any field of @sample has expired.
+ * Returns true if any field of the former is greater than the corresponding
+ * field of the latter if the latter field is set.  Otherwise returns false.
+ */
+static inline int task_cputime_expired(const struct task_cputime *sample,
+                                        const struct task_cputime *expires)
+{
+        if (!cputime_eq(expires->utime, cputime_zero) &&
+            cputime_ge(sample->utime, expires->utime))
+                return 1;
+        if (!cputime_eq(expires->stime, cputime_zero) &&
+            cputime_ge(cputime_add(sample->utime, sample->stime),
+                       expires->stime))
+                return 1;
+        if (expires->sum_exec_runtime != 0 &&
+            sample->sum_exec_runtime >= expires->sum_exec_runtime)
+                return 1;
+        return 0;
+}
+
+/**
+ * fastpath_timer_check - POSIX CPU timers fast path.
+ *
+ * @tsk:        The task (thread) being checked.
+ *
+ * Check the task and thread group timers.  If both are zero (there are no
+ * timers set) return false.  Otherwise snapshot the task and thread group
+ * timers and compare them with the corresponding expiration times.  Return
+ * true if a timer has expired, else return false.
+ */
+static inline int fastpath_timer_check(struct task_struct *tsk)
+{
+        struct signal_struct *sig;
+
+        /* tsk == current, ensure it is safe to use ->signal/sighand */
+        if (unlikely(tsk->exit_state))
+                return 0;
+
+        if (!task_cputime_zero(&tsk->cputime_expires)) {
+                struct task_cputime task_sample = {
+                        .utime = tsk->utime,
+                        .stime = tsk->stime,
+                        .sum_exec_runtime = tsk->se.sum_exec_runtime
+                };
+
+                if (task_cputime_expired(&task_sample, &tsk->cputime_expires))
+                        return 1;
+        }
+
+        sig = tsk->signal;
+        if (!task_cputime_zero(&sig->cputime_expires)) {
+                struct task_cputime group_sample;
+
+                thread_group_cputime(tsk, &group_sample);
+                if (task_cputime_expired(&group_sample, &sig->cputime_expires))
+                        return 1;
+        }
+        return 0;
+}
+
 /*
  * This is called from the timer interrupt handler.  The irq handler has
  * already updated our counts.  We need to check if any timers fire now.
@@ -1326,42 +1348,31 @@ void run_posix_cpu_timers(struct task_struct *tsk)
 
         BUG_ON(!irqs_disabled());
 
-#define UNEXPIRED(clock) \
-                (cputime_eq(tsk->it_##clock##_expires, cputime_zero) || \
-                 cputime_lt(clock##_ticks(tsk), tsk->it_##clock##_expires))
-
-        if (UNEXPIRED(prof) && UNEXPIRED(virt) &&
-            (tsk->it_sched_expires == 0 ||
-             tsk->se.sum_exec_runtime < tsk->it_sched_expires))
+        /*
+         * The fast path checks that there are no expired thread or thread
+         * group timers.  If that's so, just return.
+         */
+        if (!fastpath_timer_check(tsk))
                 return;
 
-#undef  UNEXPIRED
-
+        spin_lock(&tsk->sighand->siglock);
         /*
-         * Double-check with locks held.
+         * Here we take off tsk->signal->cpu_timers[N] and
+         * tsk->cpu_timers[N] all the timers that are firing, and
+         * put them on the firing list.
          */
-        read_lock(&tasklist_lock);
-        if (likely(tsk->signal != NULL)) {
-                spin_lock(&tsk->sighand->siglock);
+        check_thread_timers(tsk, &firing);
+        check_process_timers(tsk, &firing);
 
-                /*
-                 * Here we take off tsk->cpu_timers[N] and tsk->signal->cpu_timers[N]
-                 * all the timers that are firing, and put them on the firing list.
-                 */
-                check_thread_timers(tsk, &firing);
-                check_process_timers(tsk, &firing);
-
-                /*
-                 * We must release these locks before taking any timer's lock.
-                 * There is a potential race with timer deletion here, as the
-                 * siglock now protects our private firing list.  We have set
-                 * the firing flag in each timer, so that a deletion attempt
-                 * that gets the timer lock before we do will give it up and
-                 * spin until we've taken care of that timer below.
-                 */
-                spin_unlock(&tsk->sighand->siglock);
-        }
-        read_unlock(&tasklist_lock);
+        /*
+         * We must release these locks before taking any timer's lock.
+         * There is a potential race with timer deletion here, as the
+         * siglock now protects our private firing list.  We have set
+         * the firing flag in each timer, so that a deletion attempt
+         * that gets the timer lock before we do will give it up and
+         * spin until we've taken care of that timer below.
+         */
+        spin_unlock(&tsk->sighand->siglock);
 
         /*
          * Now that all the timers on our list have the firing flag,
@@ -1389,10 +1400,9 @@ void run_posix_cpu_timers(struct task_struct *tsk)
 
 /*
  * Set one of the process-wide special case CPU timers.
- * The tasklist_lock and tsk->sighand->siglock must be held by the caller.
- * The oldval argument is null for the RLIMIT_CPU timer, where *newval is
- * absolute; non-null for ITIMER_*, where *newval is relative and we update
- * it to be absolute, *oldval is absolute and we update it to be relative.
+ * The tsk->sighand->siglock must be held by the caller.
+ * The *newval argument is relative and we update it to be absolute, *oldval
+ * is absolute and we update it to be relative.
  */
 void set_process_cpu_timer(struct task_struct *tsk, unsigned int clock_idx,
                            cputime_t *newval, cputime_t *oldval)
@@ -1401,7 +1411,7 @@ void set_process_cpu_timer(struct task_struct *tsk, unsigned int clock_idx,
         struct list_head *head;
 
         BUG_ON(clock_idx == CPUCLOCK_SCHED);
-        cpu_clock_sample_group_locked(clock_idx, tsk, &now);
+        cpu_clock_sample_group(clock_idx, tsk, &now);
 
         if (oldval) {
                 if (!cputime_eq(*oldval, cputime_zero)) {
@@ -1435,13 +1445,14 @@ void set_process_cpu_timer(struct task_struct *tsk, unsigned int clock_idx,
             cputime_ge(list_first_entry(head,
                                   struct cpu_timer_list, entry)->expires.cpu,
                        *newval)) {
-                /*
-                 * Rejigger each thread's expiry time so that one will
-                 * notice before we hit the process-cumulative expiry time.
-                 */
-                union cpu_time_count expires = { .sched = 0 };
-                expires.cpu = *newval;
-                process_timer_rebalance(tsk, clock_idx, expires, now);
+                switch (clock_idx) {
+                case CPUCLOCK_PROF:
+                        tsk->signal->cputime_expires.prof_exp = *newval;
+                        break;
+                case CPUCLOCK_VIRT:
+                        tsk->signal->cputime_expires.virt_exp = *newval;
+                        break;
+                }
         }
 }
 
diff --git a/kernel/posix-timers.c b/kernel/posix-timers.c
index e36d5798cbff..5e79c662294b 100644
--- a/kernel/posix-timers.c
+++ b/kernel/posix-timers.c
@@ -223,6 +223,15 @@ static int posix_ktime_get_ts(clockid_t which_clock, struct timespec *tp)
 }
 
 /*
+ * Get monotonic time for posix timers
+ */
+static int posix_get_monotonic_raw(clockid_t which_clock, struct timespec *tp)
+{
+        getrawmonotonic(tp);
+        return 0;
+}
+
+/*
  * Initialize everything, well, just everything in Posix clocks/timers ;)
  */
 static __init int init_posix_timers(void)
@@ -235,9 +244,15 @@ static __init int init_posix_timers(void)
                 .clock_get = posix_ktime_get_ts,
                 .clock_set = do_posix_clock_nosettime,
         };
+        struct k_clock clock_monotonic_raw = {
+                .clock_getres = hrtimer_get_res,
+                .clock_get = posix_get_monotonic_raw,
+                .clock_set = do_posix_clock_nosettime,
+        };
 
         register_posix_clock(CLOCK_REALTIME, &clock_realtime);
         register_posix_clock(CLOCK_MONOTONIC, &clock_monotonic);
+        register_posix_clock(CLOCK_MONOTONIC_RAW, &clock_monotonic_raw);
 
         posix_timers_cache = kmem_cache_create("posix_timers_cache",
                                         sizeof (struct k_itimer), 0, SLAB_PANIC,
@@ -298,6 +313,7 @@ void do_schedule_next_timer(struct siginfo *info)
 
 int posix_timer_event(struct k_itimer *timr, int si_private)
 {
+        int shared, ret;
         /*
          * FIXME: if ->sigq is queued we can race with
          * dequeue_signal()->do_schedule_next_timer().
@@ -311,25 +327,10 @@ int posix_timer_event(struct k_itimer *timr, int si_private)
          */
         timr->sigq->info.si_sys_private = si_private;
 
-        timr->sigq->info.si_signo = timr->it_sigev_signo;
-        timr->sigq->info.si_code = SI_TIMER;
-        timr->sigq->info.si_tid = timr->it_id;
-        timr->sigq->info.si_value = timr->it_sigev_value;
-
-        if (timr->it_sigev_notify & SIGEV_THREAD_ID) {
-                struct task_struct *leader;
-                int ret = send_sigqueue(timr->sigq, timr->it_process, 0);
-
-                if (likely(ret >= 0))
-                        return ret;
-
-                timr->it_sigev_notify = SIGEV_SIGNAL;
-                leader = timr->it_process->group_leader;
-                put_task_struct(timr->it_process);
-                timr->it_process = leader;
-        }
-
-        return send_sigqueue(timr->sigq, timr->it_process, 1);
+        shared = !(timr->it_sigev_notify & SIGEV_THREAD_ID);
+        ret = send_sigqueue(timr->sigq, timr->it_process, shared);
+        /* If we failed to send the signal the timer stops. */
+        return ret > 0;
 }
 EXPORT_SYMBOL_GPL(posix_timer_event);
 
@@ -441,7 +442,7 @@ static struct k_itimer * alloc_posix_timer(void)
                 return tmr;
         if (unlikely(!(tmr->sigq = sigqueue_alloc()))) {
                 kmem_cache_free(posix_timers_cache, tmr);
-                tmr = NULL;
+                return NULL;
         }
         memset(&tmr->sigq->info, 0, sizeof(siginfo_t));
         return tmr;
@@ -468,11 +469,9 @@ sys_timer_create(const clockid_t which_clock,
                  struct sigevent __user *timer_event_spec,
                  timer_t __user * created_timer_id)
 {
-        int error = 0;
-        struct k_itimer *new_timer = NULL;
-        int new_timer_id;
-        struct task_struct *process = NULL;
-        unsigned long flags;
+        struct k_itimer *new_timer;
+        int error, new_timer_id;
+        struct task_struct *process;
         sigevent_t event;
         int it_id_set = IT_ID_NOT_SET;
 
@@ -490,12 +489,11 @@ sys_timer_create(const clockid_t which_clock,
                 goto out;
         }
         spin_lock_irq(&idr_lock);
-        error = idr_get_new(&posix_timers_id, (void *) new_timer,
-                            &new_timer_id);
+        error = idr_get_new(&posix_timers_id, new_timer, &new_timer_id);
         spin_unlock_irq(&idr_lock);
-        if (error == -EAGAIN)
-                goto retry;
-        else if (error) {
+        if (error) {
+                if (error == -EAGAIN)
+                        goto retry;
                 /*
                  * Weird looking, but we return EAGAIN if the IDR is
                  * full (proper POSIX return value for this)
@@ -526,67 +524,43 @@ sys_timer_create(const clockid_t which_clock,
                         error = -EFAULT;
                         goto out;
                 }
-                new_timer->it_sigev_notify = event.sigev_notify;
-                new_timer->it_sigev_signo = event.sigev_signo;
-                new_timer->it_sigev_value = event.sigev_value;
-
-                read_lock(&tasklist_lock);
-                if ((process = good_sigevent(&event))) {
-                        /*
-                         * We may be setting up this process for another
-                         * thread.  It may be exiting.  To catch this
-                         * case the we check the PF_EXITING flag.  If
-                         * the flag is not set, the siglock will catch
-                         * him before it is too late (in exit_itimers).
-                         *
-                         * The exec case is a bit more invloved but easy
-                         * to code.  If the process is in our thread
-                         * group (and it must be or we would not allow
-                         * it here) and is doing an exec, it will cause
-                         * us to be killed.  In this case it will wait
-                         * for us to die which means we can finish this
-                         * linkage with our last gasp. I.e. no code :)
-                         */
-                        spin_lock_irqsave(&process->sighand->siglock, flags);
-                        if (!(process->flags & PF_EXITING)) {
-                                new_timer->it_process = process;
-                                list_add(&new_timer->list,
-                                         &process->signal->posix_timers);
-                                if (new_timer->it_sigev_notify == (SIGEV_SIGNAL|SIGEV_THREAD_ID))
-                                        get_task_struct(process);
-                                spin_unlock_irqrestore(&process->sighand->siglock, flags);
-                        } else {
-                                spin_unlock_irqrestore(&process->sighand->siglock, flags);
-                                process = NULL;
-                        }
-                }
-                read_unlock(&tasklist_lock);
+                rcu_read_lock();
+                process = good_sigevent(&event);
+                if (process)
+                        get_task_struct(process);
+                rcu_read_unlock();
                 if (!process) {
                         error = -EINVAL;
                         goto out;
                 }
         } else {
-                new_timer->it_sigev_notify = SIGEV_SIGNAL;
-                new_timer->it_sigev_signo = SIGALRM;
-                new_timer->it_sigev_value.sival_int = new_timer->it_id;
+                event.sigev_notify = SIGEV_SIGNAL;
+                event.sigev_signo = SIGALRM;
+                event.sigev_value.sival_int = new_timer->it_id;
                 process = current->group_leader;
-                spin_lock_irqsave(&process->sighand->siglock, flags);
-                new_timer->it_process = process;
-                list_add(&new_timer->list, &process->signal->posix_timers);
-                spin_unlock_irqrestore(&process->sighand->siglock, flags);
+                get_task_struct(process);
         }
 
+        new_timer->it_sigev_notify     = event.sigev_notify;
+        new_timer->sigq->info.si_signo = event.sigev_signo;
+        new_timer->sigq->info.si_value = event.sigev_value;
+        new_timer->sigq->info.si_tid   = new_timer->it_id;
+        new_timer->sigq->info.si_code  = SI_TIMER;
+
+        spin_lock_irq(&current->sighand->siglock);
+        new_timer->it_process = process;
+        list_add(&new_timer->list, &current->signal->posix_timers);
+        spin_unlock_irq(&current->sighand->siglock);
+
+        return 0;
         /*
          * In the case of the timer belonging to another task, after
          * the task is unlocked, the timer is owned by the other task
          * and may cease to exist at any time.  Don't use or modify
          * new_timer after the unlock call.
          */
-
 out:
-        if (error)
-                release_posix_timer(new_timer, it_id_set);
-
+        release_posix_timer(new_timer, it_id_set);
         return error;
 }
 
@@ -597,7 +571,7 @@ out:
  * the find to the timer lock.  To avoid a dead lock, the timer id MUST
  * be release with out holding the timer lock.
  */
-static struct k_itimer * lock_timer(timer_t timer_id, unsigned long *flags)
+static struct k_itimer *lock_timer(timer_t timer_id, unsigned long *flags)
 {
         struct k_itimer *timr;
         /*
@@ -605,23 +579,20 @@ static struct k_itimer * lock_timer(timer_t timer_id, unsigned long *flags)
          * flags part over to the timer lock.  Must not let interrupts in
          * while we are moving the lock.
          */
-
         spin_lock_irqsave(&idr_lock, *flags);
-        timr = (struct k_itimer *) idr_find(&posix_timers_id, (int) timer_id);
+        timr = idr_find(&posix_timers_id, (int)timer_id);
         if (timr) {
                 spin_lock(&timr->it_lock);
-
-                if ((timr->it_id != timer_id) || !(timr->it_process) ||
-                                !same_thread_group(timr->it_process, current)) {
-                        spin_unlock(&timr->it_lock);
-                        spin_unlock_irqrestore(&idr_lock, *flags);
-                        timr = NULL;
-                } else
+                if (timr->it_process &&
+                    same_thread_group(timr->it_process, current)) {
                         spin_unlock(&idr_lock);
-        } else
-                spin_unlock_irqrestore(&idr_lock, *flags);
+                        return timr;
+                }
+                spin_unlock(&timr->it_lock);
+        }
+        spin_unlock_irqrestore(&idr_lock, *flags);
 
-        return timr;
+        return NULL;
 }
 
 /*
@@ -668,7 +639,7 @@ common_timer_get(struct k_itimer *timr, struct itimerspec *cur_setting)
             (timr->it_sigev_notify & ~SIGEV_THREAD_ID) == SIGEV_NONE))
                 timr->it_overrun += (unsigned int) hrtimer_forward(timer, now, iv);
 
-        remaining = ktime_sub(timer->expires, now);
+        remaining = ktime_sub(hrtimer_get_expires(timer), now);
         /* Return 0 only, when the timer is expired and not pending */
         if (remaining.tv64 <= 0) {
                 /*
@@ -762,7 +733,7 @@ common_timer_set(struct k_itimer *timr, int flags,
         hrtimer_init(&timr->it.real.timer, timr->it_clock, mode);
         timr->it.real.timer.function = posix_timer_fn;
 
-        timer->expires = timespec_to_ktime(new_setting->it_value);
+        hrtimer_set_expires(timer, timespec_to_ktime(new_setting->it_value));
 
         /* Convert interval */
         timr->it.real.interval = timespec_to_ktime(new_setting->it_interval);
@@ -771,14 +742,12 @@ common_timer_set(struct k_itimer *timr, int flags,
         if (((timr->it_sigev_notify & ~SIGEV_THREAD_ID) == SIGEV_NONE)) {
                 /* Setup correct expiry time for relative timers */
                 if (mode == HRTIMER_MODE_REL) {
-                        timer->expires =
-                                ktime_add_safe(timer->expires,
-                                               timer->base->get_time());
+                        hrtimer_add_expires(timer, timer->base->get_time());
                 }
                 return 0;
         }
 
-        hrtimer_start(timer, timer->expires, mode);
+        hrtimer_start_expires(timer, mode);
         return 0;
 }
 
@@ -862,8 +831,7 @@ retry_delete:
          * This keeps any tasks waiting on the spin lock from thinking
          * they got something (see the lock code above).
          */
-        if (timer->it_sigev_notify == (SIGEV_SIGNAL|SIGEV_THREAD_ID))
-                put_task_struct(timer->it_process);
+        put_task_struct(timer->it_process);
         timer->it_process = NULL;
 
         unlock_timer(timer, flags);
@@ -890,8 +858,7 @@ retry_delete:
          * This keeps any tasks waiting on the spin lock from thinking
          * they got something (see the lock code above).
          */
-        if (timer->it_sigev_notify == (SIGEV_SIGNAL|SIGEV_THREAD_ID))
-                put_task_struct(timer->it_process);
+        put_task_struct(timer->it_process);
         timer->it_process = NULL;
 
         unlock_timer(timer, flags);
diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig
index dcd165f92a88..23bd4daeb96b 100644
--- a/kernel/power/Kconfig
+++ b/kernel/power/Kconfig
@@ -96,7 +96,7 @@ config SUSPEND
 
 config PM_TEST_SUSPEND
         bool "Test suspend/resume and wakealarm during bootup"
-        depends on SUSPEND && PM_DEBUG && RTC_LIB=y
+        depends on SUSPEND && PM_DEBUG && RTC_CLASS=y
         ---help---
         This option will let you suspend your machine during bootup, and
         make it wake up a few seconds later using an RTC wakeup alarm.
diff --git a/kernel/power/disk.c b/kernel/power/disk.c
index bbd85c60f741..c9d74083746f 100644
--- a/kernel/power/disk.c
+++ b/kernel/power/disk.c
@@ -14,6 +14,7 @@
 #include <linux/reboot.h>
 #include <linux/string.h>
 #include <linux/device.h>
+#include <linux/kmod.h>
 #include <linux/delay.h>
 #include <linux/fs.h>
 #include <linux/mount.h>
@@ -520,6 +521,10 @@ int hibernate(void)
         if (error)
                 goto Exit;
 
+        error = usermodehelper_disable();
+        if (error)
+                goto Exit;
+
         /* Allocate memory management structures */
         error = create_basic_memory_bitmaps();
         if (error)
@@ -558,6 +563,7 @@ int hibernate(void)
         thaw_processes();
  Finish:
         free_basic_memory_bitmaps();
+        usermodehelper_enable();
  Exit:
         pm_notifier_call_chain(PM_POST_HIBERNATION);
         pm_restore_console();
@@ -634,6 +640,10 @@ static int software_resume(void)
         if (error)
                 goto Finish;
 
+        error = usermodehelper_disable();
+        if (error)
+                goto Finish;
+
         error = create_basic_memory_bitmaps();
         if (error)
                 goto Finish;
@@ -641,7 +651,7 @@ static int software_resume(void)
         pr_debug("PM: Preparing processes for restore.\n");
         error = prepare_processes();
         if (error) {
-                swsusp_close();
+                swsusp_close(FMODE_READ);
                 goto Done;
         }
 
@@ -656,6 +666,7 @@ static int software_resume(void)
         thaw_processes();
  Done:
         free_basic_memory_bitmaps();
+        usermodehelper_enable();
  Finish:
         pm_notifier_call_chain(PM_POST_RESTORE);
         pm_restore_console();
diff --git a/kernel/power/main.c b/kernel/power/main.c
index 540b16b68565..b8f7ce9473e8 100644
--- a/kernel/power/main.c
+++ b/kernel/power/main.c
@@ -14,6 +14,7 @@
 #include <linux/string.h>
 #include <linux/delay.h>
 #include <linux/errno.h>
+#include <linux/kmod.h>
 #include <linux/init.h>
 #include <linux/console.h>
 #include <linux/cpu.h>
@@ -173,7 +174,7 @@ static void suspend_test_finish(const char *label)
          * has some performance issues.  The stack dump of a WARN_ON
          * is more likely to get the right attention than a printk...
          */
-        WARN_ON(msec > (TEST_SUSPEND_SECONDS * 1000));
+        WARN(msec > (TEST_SUSPEND_SECONDS * 1000), "Component: %s\n", label);
 }
 
 #else
@@ -237,6 +238,10 @@ static int suspend_prepare(void)
         if (error)
                 goto Finish;
 
+        error = usermodehelper_disable();
+        if (error)
+                goto Finish;
+
         if (suspend_freeze_processes()) {
                 error = -EAGAIN;
                 goto Thaw;
@@ -256,6 +261,7 @@ static int suspend_prepare(void)
 
  Thaw:
         suspend_thaw_processes();
+        usermodehelper_enable();
  Finish:
         pm_notifier_call_chain(PM_POST_SUSPEND);
         pm_restore_console();
@@ -376,6 +382,7 @@ int suspend_devices_and_enter(suspend_state_t state)
 static void suspend_finish(void)
 {
         suspend_thaw_processes();
+        usermodehelper_enable();
         pm_notifier_call_chain(PM_POST_SUSPEND);
         pm_restore_console();
 }
diff --git a/kernel/power/power.h b/kernel/power/power.h
index acc0c101dbd5..46b5ec7a3afb 100644
--- a/kernel/power/power.h
+++ b/kernel/power/power.h
@@ -153,7 +153,7 @@ extern int swsusp_shrink_memory(void);
 extern void swsusp_free(void);
 extern int swsusp_read(unsigned int *flags_p);
 extern int swsusp_write(unsigned int flags);
-extern void swsusp_close(void);
+extern void swsusp_close(fmode_t);
 
 struct timeval;
 /* kernel/power/swsusp.c */
diff --git a/kernel/power/process.c b/kernel/power/process.c
index 278946aecaf0..ca634019497a 100644
--- a/kernel/power/process.c
+++ b/kernel/power/process.c
@@ -28,121 +28,6 @@ static inline int freezeable(struct task_struct * p)
         return 1;
 }
 
-/*
- * freezing is complete, mark current process as frozen
- */
-static inline void frozen_process(void)
-{
-        if (!unlikely(current->flags & PF_NOFREEZE)) {
-                current->flags |= PF_FROZEN;
-                wmb();
-        }
-        clear_freeze_flag(current);
-}
-
-/* Refrigerator is place where frozen processes are stored :-). */
-void refrigerator(void)
-{
-        /* Hmm, should we be allowed to suspend when there are realtime
-           processes around? */
-        long save;
-
-        task_lock(current);
-        if (freezing(current)) {
-                frozen_process();
-                task_unlock(current);
-        } else {
-                task_unlock(current);
-                return;
-        }
-        save = current->state;
-        pr_debug("%s entered refrigerator\n", current->comm);
-
-        spin_lock_irq(&current->sighand->siglock);
-        recalc_sigpending(); /* We sent fake signal, clean it up */
-        spin_unlock_irq(&current->sighand->siglock);
-
-        for (;;) {
-                set_current_state(TASK_UNINTERRUPTIBLE);
-                if (!frozen(current))
-                        break;
-                schedule();
-        }
-        pr_debug("%s left refrigerator\n", current->comm);
-        __set_current_state(save);
-}
-
-static void fake_signal_wake_up(struct task_struct *p)
-{
-        unsigned long flags;
-
-        spin_lock_irqsave(&p->sighand->siglock, flags);
-        signal_wake_up(p, 0);
-        spin_unlock_irqrestore(&p->sighand->siglock, flags);
-}
-
-static inline bool should_send_signal(struct task_struct *p)
-{
-        return !(p->flags & PF_FREEZER_NOSIG);
-}
-
-/**
- *      freeze_task - send a freeze request to given task
- *      @p: task to send the request to
- *      @sig_only: if set, the request will only be sent if the task has the
- *              PF_FREEZER_NOSIG flag unset
- *      Return value: 'false', if @sig_only is set and the task has
- *              PF_FREEZER_NOSIG set or the task is frozen, 'true', otherwise
- *
- *      The freeze request is sent by setting the tasks's TIF_FREEZE flag and
- *      either sending a fake signal to it or waking it up, depending on whether
- *      or not it has PF_FREEZER_NOSIG set.  If @sig_only is set and the task
- *      has PF_FREEZER_NOSIG set (ie. it is a typical kernel thread), its
- *      TIF_FREEZE flag will not be set.
- */
-static bool freeze_task(struct task_struct *p, bool sig_only)
-{
-        /*
-         * We first check if the task is freezing and next if it has already
-         * been frozen to avoid the race with frozen_process() which first marks
-         * the task as frozen and next clears its TIF_FREEZE.
-         */
-        if (!freezing(p)) {
-                rmb();
-                if (frozen(p))
-                        return false;
-
-                if (!sig_only || should_send_signal(p))
-                        set_freeze_flag(p);
-                else
-                        return false;
-        }
-
-        if (should_send_signal(p)) {
-                if (!signal_pending(p))
-                        fake_signal_wake_up(p);
-        } else if (sig_only) {
-                return false;
-        } else {
-                wake_up_state(p, TASK_INTERRUPTIBLE);
-        }
-
-        return true;
-}
-
-static void cancel_freezing(struct task_struct *p)
-{
-        unsigned long flags;
-
-        if (freezing(p)) {
-                pr_debug("  clean up: %s\n", p->comm);
-                clear_freeze_flag(p);
-                spin_lock_irqsave(&p->sighand->siglock, flags);
-                recalc_sigpending_and_wake(p);
-                spin_unlock_irqrestore(&p->sighand->siglock, flags);
-        }
-}
-
 static int try_to_freeze_tasks(bool sig_only)
 {
         struct task_struct *g, *p;
@@ -250,6 +135,9 @@ static void thaw_tasks(bool nosig_only)
                 if (nosig_only && should_send_signal(p))
                         continue;
 
+                if (cgroup_frozen(p))
+                        continue;
+
                 thaw_process(p);
         } while_each_thread(g, p);
         read_unlock(&tasklist_lock);
@@ -264,4 +152,3 @@ void thaw_processes(void)
         printk("done.\n");
 }
 
-EXPORT_SYMBOL(refrigerator);
diff --git a/kernel/power/swap.c b/kernel/power/swap.c
index 80ccac849e46..b7713b53d07a 100644
--- a/kernel/power/swap.c
+++ b/kernel/power/swap.c
@@ -172,13 +172,13 @@ static int swsusp_swap_check(void) /* This is called before saving image */
                 return res;
 
         root_swap = res;
-        res = blkdev_get(resume_bdev, FMODE_WRITE, O_RDWR);
+        res = blkdev_get(resume_bdev, FMODE_WRITE);
         if (res)
                 return res;
 
         res = set_blocksize(resume_bdev, PAGE_SIZE);
         if (res < 0)
-                blkdev_put(resume_bdev);
+                blkdev_put(resume_bdev, FMODE_WRITE);
 
         return res;
 }
@@ -426,7 +426,7 @@ int swsusp_write(unsigned int flags)
 
         release_swap_writer(&handle);
  out:
-        swsusp_close();
+        swsusp_close(FMODE_WRITE);
         return error;
 }
 
@@ -574,7 +574,7 @@ int swsusp_read(unsigned int *flags_p)
                 error = load_image(&handle, &snapshot, header->pages - 1);
         release_swap_reader(&handle);
 
-        blkdev_put(resume_bdev);
+        blkdev_put(resume_bdev, FMODE_READ);
 
         if (!error)
                 pr_debug("PM: Image successfully loaded\n");
@@ -609,7 +609,7 @@ int swsusp_check(void)
                         return -EINVAL;
                 }
                 if (error)
-                        blkdev_put(resume_bdev);
+                        blkdev_put(resume_bdev, FMODE_READ);
                 else
                         pr_debug("PM: Signature found, resuming\n");
         } else {
@@ -626,14 +626,14 @@ int swsusp_check(void)
  *      swsusp_close - close swap device.
  */
 
-void swsusp_close(void)
+void swsusp_close(fmode_t mode)
 {
         if (IS_ERR(resume_bdev)) {
                 pr_debug("PM: Image device not initialised\n");
                 return;
         }
 
-        blkdev_put(resume_bdev);
+        blkdev_put(resume_bdev, mode); /* move up */
 }
 
 static int swsusp_header_init(void)
diff --git a/kernel/power/user.c b/kernel/power/user.c
index a6332a313262..005b93d839ba 100644
--- a/kernel/power/user.c
+++ b/kernel/power/user.c
@@ -212,13 +212,20 @@ static long snapshot_ioctl(struct file *filp, unsigned int cmd,
         case SNAPSHOT_FREEZE:
                 if (data->frozen)
                         break;
+
                 printk("Syncing filesystems ... ");
                 sys_sync();
                 printk("done.\n");
 
-                error = freeze_processes();
+                error = usermodehelper_disable();
                 if (error)
+                        break;
+
+                error = freeze_processes();
+                if (error) {
                         thaw_processes();
+                        usermodehelper_enable();
+                }
                 if (!error)
                         data->frozen = 1;
                 break;
@@ -227,6 +234,7 @@ static long snapshot_ioctl(struct file *filp, unsigned int cmd,
                 if (!data->frozen || data->ready)
                         break;
                 thaw_processes();
+                usermodehelper_enable();
                 data->frozen = 0;
                 break;
 
diff --git a/kernel/printk.c b/kernel/printk.c
index b51b1567bb55..f492f1583d77 100644
--- a/kernel/printk.c
+++ b/kernel/printk.c
@@ -13,7 +13,7 @@
  * Fixed SMP synchronization, 08/08/99, Manfred Spraul
  *     manfred@colorfullife.com
  * Rewrote bits to get rid of console_lock
- *      01Mar01 Andrew Morton <andrewm@uow.edu.au>
+ *      01Mar01 Andrew Morton
  */
 
 #include <linux/kernel.h>
@@ -233,45 +233,6 @@ static inline void boot_delay_msec(void)
 #endif
 
 /*
- * Return the number of unread characters in the log buffer.
- */
-static int log_buf_get_len(void)
-{
-        return logged_chars;
-}
-
-/*
- * Copy a range of characters from the log buffer.
- */
-int log_buf_copy(char *dest, int idx, int len)
-{
-        int ret, max;
-        bool took_lock = false;
-
-        if (!oops_in_progress) {
-                spin_lock_irq(&logbuf_lock);
-                took_lock = true;
-        }
-
-        max = log_buf_get_len();
-        if (idx < 0 || idx >= max) {
-                ret = -1;
-        } else {
-                if (len > max)
-                        len = max;
-                ret = len;
-                idx += (log_end - max);
-                while (len-- > 0)
-                        dest[len] = LOG_BUF(idx + len);
-        }
-
-        if (took_lock)
-                spin_unlock_irq(&logbuf_lock);
-
-        return ret;
-}
-
-/*
  * Commands to do_syslog:
  *
  *      0 -- Close the log.  Currently a NOP.
@@ -577,9 +538,6 @@ static int have_callable_console(void)
  * @fmt: format string
  *
  * This is printk().  It can be called from any context.  We want it to work.
- * Be aware of the fact that if oops_in_progress is not set, we might try to
- * wake klogd up which could deadlock on runqueue lock if printk() is called
- * from scheduler code.
  *
  * We try to grab the console_sem.  If we succeed, it's easy - we log the output and
  * call the console drivers.  If we fail to get the semaphore we place the output
@@ -593,6 +551,8 @@ static int have_callable_console(void)
  *
  * See also:
  * printf(3)
+ *
+ * See the vsnprintf() documentation for format string extensions over C99.
  */
 
 asmlinkage int printk(const char *fmt, ...)
@@ -982,10 +942,25 @@ int is_console_locked(void)
         return console_locked;
 }
 
-void wake_up_klogd(void)
+static DEFINE_PER_CPU(int, printk_pending);
+
+void printk_tick(void)
 {
-        if (!oops_in_progress && waitqueue_active(&log_wait))
+        if (__get_cpu_var(printk_pending)) {
+                __get_cpu_var(printk_pending) = 0;
                 wake_up_interruptible(&log_wait);
+        }
+}
+
+int printk_needs_cpu(int cpu)
+{
+        return per_cpu(printk_pending, cpu);
+}
+
+void wake_up_klogd(void)
+{
+        if (waitqueue_active(&log_wait))
+                __raw_get_cpu_var(printk_pending) = 1;
 }
 
 /**
@@ -1291,22 +1266,6 @@ static int __init disable_boot_consoles(void)
 }
 late_initcall(disable_boot_consoles);
 
-/**
- * tty_write_message - write a message to a certain tty, not just the console.
- * @tty: the destination tty_struct
- * @msg: the message to write
- *
- * This is used for messages that need to be redirected to a specific tty.
- * We don't put it into the syslog queue right now maybe in the future if
- * really needed.
- */
-void tty_write_message(struct tty_struct *tty, char *msg)
-{
-        if (tty && tty->ops->write)
-                tty->ops->write(tty, msg, strlen(msg));
-        return;
-}
-
 #if defined CONFIG_PRINTK
 
 /*
diff --git a/kernel/profile.c b/kernel/profile.c
index cd26bed4cc26..5b7d1ac7124c 100644
--- a/kernel/profile.c
+++ b/kernel/profile.c
@@ -22,6 +22,8 @@
 #include <linux/cpu.h>
 #include <linux/highmem.h>
 #include <linux/mutex.h>
+#include <linux/slab.h>
+#include <linux/vmalloc.h>
 #include <asm/sections.h>
 #include <asm/irq_regs.h>
 #include <asm/ptrace.h>
@@ -50,11 +52,11 @@ static DEFINE_PER_CPU(int, cpu_profile_flip);
 static DEFINE_MUTEX(profile_flip_mutex);
 #endif /* CONFIG_SMP */
 
-static int __init profile_setup(char *str)
+int profile_setup(char *str)
 {
-        static char __initdata schedstr[] = "schedule";
-        static char __initdata sleepstr[] = "sleep";
-        static char __initdata kvmstr[] = "kvm";
+        static char schedstr[] = "schedule";
+        static char sleepstr[] = "sleep";
+        static char kvmstr[] = "kvm";
         int par;
 
         if (!strncmp(str, sleepstr, strlen(sleepstr))) {
@@ -100,14 +102,33 @@ static int __init profile_setup(char *str)
 __setup("profile=", profile_setup);
 
 
-void __init profile_init(void)
+int __ref profile_init(void)
 {
+        int buffer_bytes;
         if (!prof_on)
-                return;
+                return 0;
 
         /* only text is profiled */
         prof_len = (_etext - _stext) >> prof_shift;
-        prof_buffer = alloc_bootmem(prof_len*sizeof(atomic_t));
+        buffer_bytes = prof_len*sizeof(atomic_t);
+        if (!slab_is_available()) {
+                prof_buffer = alloc_bootmem(buffer_bytes);
+                return 0;
+        }
+
+        prof_buffer = kzalloc(buffer_bytes, GFP_KERNEL);
+        if (prof_buffer)
+                return 0;
+
+        prof_buffer = alloc_pages_exact(buffer_bytes, GFP_KERNEL|__GFP_ZERO);
+        if (prof_buffer)
+                return 0;
+
+        prof_buffer = vmalloc(buffer_bytes);
+        if (prof_buffer)
+                return 0;
+
+        return -ENOMEM;
 }
 
 /* Profile event notifications */
@@ -523,11 +544,11 @@ static const struct file_operations proc_profile_operations = {
 };
 
 #ifdef CONFIG_SMP
-static void __init profile_nop(void *unused)
+static inline void profile_nop(void *unused)
 {
 }
 
-static int __init create_hash_tables(void)
+static int create_hash_tables(void)
 {
         int cpu;
 
@@ -575,14 +596,14 @@ out_cleanup:
 #define create_hash_tables()                    ({ 0; })
 #endif
 
-static int __init create_proc_profile(void)
+int create_proc_profile(void)
 {
         struct proc_dir_entry *entry;
 
         if (!prof_on)
                 return 0;
         if (create_hash_tables())
-                return -1;
+                return -ENOMEM;
         entry = proc_create("profile", S_IWUSR | S_IRUGO,
                             NULL, &proc_profile_operations);
         if (!entry)
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 356699a96d56..1e68e4c39e2c 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -45,7 +45,7 @@ void __ptrace_link(struct task_struct *child, struct task_struct *new_parent)
  * TASK_TRACED, resume it now.
  * Requires that irqs be disabled.
  */
-void ptrace_untrace(struct task_struct *child)
+static void ptrace_untrace(struct task_struct *child)
 {
         spin_lock(&child->sighand->siglock);
         if (task_is_traced(child)) {
diff --git a/kernel/rcuclassic.c b/kernel/rcuclassic.c
index aad93cdc9f68..37f72e551542 100644
--- a/kernel/rcuclassic.c
+++ b/kernel/rcuclassic.c
@@ -47,6 +47,7 @@
 #include <linux/notifier.h>
 #include <linux/cpu.h>
 #include <linux/mutex.h>
+#include <linux/time.h>
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 static struct lock_class_key rcu_lock_key;
@@ -60,12 +61,14 @@ EXPORT_SYMBOL_GPL(rcu_lock_map);
 static struct rcu_ctrlblk rcu_ctrlblk = {
         .cur = -300,
         .completed = -300,
+        .pending = -300,
         .lock = __SPIN_LOCK_UNLOCKED(&rcu_ctrlblk.lock),
         .cpumask = CPU_MASK_NONE,
 };
 static struct rcu_ctrlblk rcu_bh_ctrlblk = {
         .cur = -300,
         .completed = -300,
+        .pending = -300,
         .lock = __SPIN_LOCK_UNLOCKED(&rcu_bh_ctrlblk.lock),
         .cpumask = CPU_MASK_NONE,
 };
@@ -83,7 +86,10 @@ static void force_quiescent_state(struct rcu_data *rdp,
 {
         int cpu;
         cpumask_t cpumask;
+        unsigned long flags;
+
         set_need_resched();
+        spin_lock_irqsave(&rcp->lock, flags);
         if (unlikely(!rcp->signaled)) {
                 rcp->signaled = 1;
                 /*
@@ -109,6 +115,7 @@ static void force_quiescent_state(struct rcu_data *rdp,
                 for_each_cpu_mask_nr(cpu, cpumask)
                         smp_send_reschedule(cpu);
         }
+        spin_unlock_irqrestore(&rcp->lock, flags);
 }
 #else
 static inline void force_quiescent_state(struct rcu_data *rdp,
@@ -118,6 +125,126 @@ static inline void force_quiescent_state(struct rcu_data *rdp,
 }
 #endif
 
+static void __call_rcu(struct rcu_head *head, struct rcu_ctrlblk *rcp,
+                struct rcu_data *rdp)
+{
+        long batch;
+
+        head->next = NULL;
+        smp_mb(); /* Read of rcu->cur must happen after any change by caller. */
+
+        /*
+         * Determine the batch number of this callback.
+         *
+         * Using ACCESS_ONCE to avoid the following error when gcc eliminates
+         * local variable "batch" and emits codes like this:
+         *      1) rdp->batch = rcp->cur + 1 # gets old value
+         *      ......
+         *      2)rcu_batch_after(rcp->cur + 1, rdp->batch) # gets new value
+         * then [*nxttail[0], *nxttail[1]) may contain callbacks
+         * that batch# = rdp->batch, see the comment of struct rcu_data.
+         */
+        batch = ACCESS_ONCE(rcp->cur) + 1;
+
+        if (rdp->nxtlist && rcu_batch_after(batch, rdp->batch)) {
+                /* process callbacks */
+                rdp->nxttail[0] = rdp->nxttail[1];
+                rdp->nxttail[1] = rdp->nxttail[2];
+                if (rcu_batch_after(batch - 1, rdp->batch))
+                        rdp->nxttail[0] = rdp->nxttail[2];
+        }
+
+        rdp->batch = batch;
+        *rdp->nxttail[2] = head;
+        rdp->nxttail[2] = &head->next;
+
+        if (unlikely(++rdp->qlen > qhimark)) {
+                rdp->blimit = INT_MAX;
+                force_quiescent_state(rdp, &rcu_ctrlblk);
+        }
+}
+
+#ifdef CONFIG_RCU_CPU_STALL_DETECTOR
+
+static void record_gp_stall_check_time(struct rcu_ctrlblk *rcp)
+{
+        rcp->gp_start = jiffies;
+        rcp->jiffies_stall = jiffies + RCU_SECONDS_TILL_STALL_CHECK;
+}
+
+static void print_other_cpu_stall(struct rcu_ctrlblk *rcp)
+{
+        int cpu;
+        long delta;
+        unsigned long flags;
+
+        /* Only let one CPU complain about others per time interval. */
+
+        spin_lock_irqsave(&rcp->lock, flags);
+        delta = jiffies - rcp->jiffies_stall;
+        if (delta < 2 || rcp->cur != rcp->completed) {
+                spin_unlock_irqrestore(&rcp->lock, flags);
+                return;
+        }
+        rcp->jiffies_stall = jiffies + RCU_SECONDS_TILL_STALL_RECHECK;
+        spin_unlock_irqrestore(&rcp->lock, flags);
+
+        /* OK, time to rat on our buddy... */
+
+        printk(KERN_ERR "RCU detected CPU stalls:");
+        for_each_possible_cpu(cpu) {
+                if (cpu_isset(cpu, rcp->cpumask))
+                        printk(" %d", cpu);
+        }
+        printk(" (detected by %d, t=%ld jiffies)\n",
+               smp_processor_id(), (long)(jiffies - rcp->gp_start));
+}
+
+static void print_cpu_stall(struct rcu_ctrlblk *rcp)
+{
+        unsigned long flags;
+
+        printk(KERN_ERR "RCU detected CPU %d stall (t=%lu/%lu jiffies)\n",
+                        smp_processor_id(), jiffies,
+                        jiffies - rcp->gp_start);
+        dump_stack();
+        spin_lock_irqsave(&rcp->lock, flags);
+        if ((long)(jiffies - rcp->jiffies_stall) >= 0)
+                rcp->jiffies_stall =
+                        jiffies + RCU_SECONDS_TILL_STALL_RECHECK;
+        spin_unlock_irqrestore(&rcp->lock, flags);
+        set_need_resched();  /* kick ourselves to get things going. */
+}
+
+static void check_cpu_stall(struct rcu_ctrlblk *rcp)
+{
+        long delta;
+
+        delta = jiffies - rcp->jiffies_stall;
+        if (cpu_isset(smp_processor_id(), rcp->cpumask) && delta >= 0) {
+
+                /* We haven't checked in, so go dump stack. */
+                print_cpu_stall(rcp);
+
+        } else if (rcp->cur != rcp->completed && delta >= 2) {
+
+                /* They had two seconds to dump stack, so complain. */
+                print_other_cpu_stall(rcp);
+        }
+}
+
+#else /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
+
+static void record_gp_stall_check_time(struct rcu_ctrlblk *rcp)
+{
+}
+
+static inline void check_cpu_stall(struct rcu_ctrlblk *rcp)
+{
+}
+
+#endif /* #else #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
+
 /**
  * call_rcu - Queue an RCU callback for invocation after a grace period.
  * @head: structure to be used for queueing the RCU updates.
@@ -133,18 +260,10 @@ void call_rcu(struct rcu_head *head,
                                 void (*func)(struct rcu_head *rcu))
 {
         unsigned long flags;
-        struct rcu_data *rdp;
 
         head->func = func;
-        head->next = NULL;
         local_irq_save(flags);
-        rdp = &__get_cpu_var(rcu_data);
-        *rdp->nxttail = head;
-        rdp->nxttail = &head->next;
-        if (unlikely(++rdp->qlen > qhimark)) {
-                rdp->blimit = INT_MAX;
-                force_quiescent_state(rdp, &rcu_ctrlblk);
-        }
+        __call_rcu(head, &rcu_ctrlblk, &__get_cpu_var(rcu_data));
         local_irq_restore(flags);
 }
 EXPORT_SYMBOL_GPL(call_rcu);
@@ -169,20 +288,10 @@ void call_rcu_bh(struct rcu_head *head,
                                 void (*func)(struct rcu_head *rcu))
 {
         unsigned long flags;
-        struct rcu_data *rdp;
 
         head->func = func;
-        head->next = NULL;
         local_irq_save(flags);
-        rdp = &__get_cpu_var(rcu_bh_data);
-        *rdp->nxttail = head;
-        rdp->nxttail = &head->next;
-
-        if (unlikely(++rdp->qlen > qhimark)) {
-                rdp->blimit = INT_MAX;
-                force_quiescent_state(rdp, &rcu_bh_ctrlblk);
-        }
-
+        __call_rcu(head, &rcu_bh_ctrlblk, &__get_cpu_var(rcu_bh_data));
         local_irq_restore(flags);
 }
 EXPORT_SYMBOL_GPL(call_rcu_bh);
@@ -211,12 +320,6 @@ EXPORT_SYMBOL_GPL(rcu_batches_completed_bh);
 static inline void raise_rcu_softirq(void)
 {
         raise_softirq(RCU_SOFTIRQ);
-        /*
-         * The smp_mb() here is required to ensure that this cpu's
-         * __rcu_process_callbacks() reads the most recently updated
-         * value of rcu->cur.
-         */
-        smp_mb();
 }
 
 /*
@@ -225,6 +328,7 @@ static inline void raise_rcu_softirq(void)
  */
 static void rcu_do_batch(struct rcu_data *rdp)
 {
+        unsigned long flags;
         struct rcu_head *next, *list;
         int count = 0;
 
@@ -239,9 +343,9 @@ static void rcu_do_batch(struct rcu_data *rdp)
         }
         rdp->donelist = list;
 
-        local_irq_disable();
+        local_irq_save(flags);
         rdp->qlen -= count;
-        local_irq_enable();
+        local_irq_restore(flags);
         if (rdp->blimit == INT_MAX && rdp->qlen <= qlowmark)
                 rdp->blimit = blimit;
 
@@ -269,6 +373,7 @@ static void rcu_do_batch(struct rcu_data *rdp)
  *   rcu_check_quiescent_state calls rcu_start_batch(0) to start the next grace
  *   period (if necessary).
  */
+
 /*
  * Register a new batch of callbacks, and start it up if there is currently no
  * active batch and the batch to be registered has not already occurred.
@@ -276,15 +381,10 @@ static void rcu_do_batch(struct rcu_data *rdp)
  */
 static void rcu_start_batch(struct rcu_ctrlblk *rcp)
 {
-        if (rcp->next_pending &&
+        if (rcp->cur != rcp->pending &&
                         rcp->completed == rcp->cur) {
-                rcp->next_pending = 0;
-                /*
-                 * next_pending == 0 must be visible in
-                 * __rcu_process_callbacks() before it can see new value of cur.
-                 */
-                smp_wmb();
                 rcp->cur++;
+                record_gp_stall_check_time(rcp);
 
                 /*
                  * Accessing nohz_cpu_mask before incrementing rcp->cur needs a
@@ -322,6 +422,8 @@ static void cpu_quiet(int cpu, struct rcu_ctrlblk *rcp)
 static void rcu_check_quiescent_state(struct rcu_ctrlblk *rcp,
                                         struct rcu_data *rdp)
 {
+        unsigned long flags;
+
         if (rdp->quiescbatch != rcp->cur) {
                 /* start new grace period: */
                 rdp->qs_pending = 1;
@@ -345,7 +447,7 @@ static void rcu_check_quiescent_state(struct rcu_ctrlblk *rcp,
                 return;
         rdp->qs_pending = 0;
 
-        spin_lock(&rcp->lock);
+        spin_lock_irqsave(&rcp->lock, flags);
         /*
          * rdp->quiescbatch/rcp->cur and the cpu bitmap can come out of sync
          * during cpu startup. Ignore the quiescent state.
@@ -353,7 +455,7 @@ static void rcu_check_quiescent_state(struct rcu_ctrlblk *rcp,
         if (likely(rdp->quiescbatch == rcp->cur))
                 cpu_quiet(rdp->cpu, rcp);
 
-        spin_unlock(&rcp->lock);
+        spin_unlock_irqrestore(&rcp->lock, flags);
 }
 
 
@@ -364,33 +466,38 @@ static void rcu_check_quiescent_state(struct rcu_ctrlblk *rcp,
  * which is dead and hence not processing interrupts.
  */
 static void rcu_move_batch(struct rcu_data *this_rdp, struct rcu_head *list,
-                                struct rcu_head **tail)
+                                struct rcu_head **tail, long batch)
 {
-        local_irq_disable();
-        *this_rdp->nxttail = list;
-        if (list)
-                this_rdp->nxttail = tail;
-        local_irq_enable();
+        unsigned long flags;
+
+        if (list) {
+                local_irq_save(flags);
+                this_rdp->batch = batch;
+                *this_rdp->nxttail[2] = list;
+                this_rdp->nxttail[2] = tail;
+                local_irq_restore(flags);
+        }
 }
 
 static void __rcu_offline_cpu(struct rcu_data *this_rdp,
                                 struct rcu_ctrlblk *rcp, struct rcu_data *rdp)
 {
-        /* if the cpu going offline owns the grace period
+        unsigned long flags;
+
+        /*
+         * if the cpu going offline owns the grace period
          * we can block indefinitely waiting for it, so flush
          * it here
          */
-        spin_lock_bh(&rcp->lock);
+        spin_lock_irqsave(&rcp->lock, flags);
         if (rcp->cur != rcp->completed)
                 cpu_quiet(rdp->cpu, rcp);
-        spin_unlock_bh(&rcp->lock);
-        rcu_move_batch(this_rdp, rdp->donelist, rdp->donetail);
-        rcu_move_batch(this_rdp, rdp->curlist, rdp->curtail);
-        rcu_move_batch(this_rdp, rdp->nxtlist, rdp->nxttail);
+        rcu_move_batch(this_rdp, rdp->donelist, rdp->donetail, rcp->cur + 1);
+        rcu_move_batch(this_rdp, rdp->nxtlist, rdp->nxttail[2], rcp->cur + 1);
+        spin_unlock(&rcp->lock);
 
-        local_irq_disable();
         this_rdp->qlen += rdp->qlen;
-        local_irq_enable();
+        local_irq_restore(flags);
 }
 
 static void rcu_offline_cpu(int cpu)
@@ -420,38 +527,52 @@ static void rcu_offline_cpu(int cpu)
 static void __rcu_process_callbacks(struct rcu_ctrlblk *rcp,
                                         struct rcu_data *rdp)
 {
-        if (rdp->curlist && !rcu_batch_before(rcp->completed, rdp->batch)) {
-                *rdp->donetail = rdp->curlist;
-                rdp->donetail = rdp->curtail;
-                rdp->curlist = NULL;
-                rdp->curtail = &rdp->curlist;
-        }
+        unsigned long flags;
+        long completed_snap;
 
-        if (rdp->nxtlist && !rdp->curlist) {
-                local_irq_disable();
-                rdp->curlist = rdp->nxtlist;
-                rdp->curtail = rdp->nxttail;
-                rdp->nxtlist = NULL;
-                rdp->nxttail = &rdp->nxtlist;
-                local_irq_enable();
+        if (rdp->nxtlist) {
+                local_irq_save(flags);
+                completed_snap = ACCESS_ONCE(rcp->completed);
 
                 /*
-                 * start the next batch of callbacks
+                 * move the other grace-period-completed entries to
+                 * [rdp->nxtlist, *rdp->nxttail[0]) temporarily
                  */
+                if (!rcu_batch_before(completed_snap, rdp->batch))
+                        rdp->nxttail[0] = rdp->nxttail[1] = rdp->nxttail[2];
+                else if (!rcu_batch_before(completed_snap, rdp->batch - 1))
+                        rdp->nxttail[0] = rdp->nxttail[1];
 
-                /* determine batch number */
-                rdp->batch = rcp->cur + 1;
-                /* see the comment and corresponding wmb() in
-                 * the rcu_start_batch()
+                /*
+                 * the grace period for entries in
+                 * [rdp->nxtlist, *rdp->nxttail[0]) has completed and
+                 * move these entries to donelist
                  */
-                smp_rmb();
+                if (rdp->nxttail[0] != &rdp->nxtlist) {
+                        *rdp->donetail = rdp->nxtlist;
+                        rdp->donetail = rdp->nxttail[0];
+                        rdp->nxtlist = *rdp->nxttail[0];
+                        *rdp->donetail = NULL;
+
+                        if (rdp->nxttail[1] == rdp->nxttail[0])
+                                rdp->nxttail[1] = &rdp->nxtlist;
+                        if (rdp->nxttail[2] == rdp->nxttail[0])
+                                rdp->nxttail[2] = &rdp->nxtlist;
+                        rdp->nxttail[0] = &rdp->nxtlist;
+                }
+
+                local_irq_restore(flags);
+
+                if (rcu_batch_after(rdp->batch, rcp->pending)) {
+                        unsigned long flags2;
 
-                if (!rcp->next_pending) {
                         /* and start it/schedule start if it's a new batch */
-                        spin_lock(&rcp->lock);
-                        rcp->next_pending = 1;
-                        rcu_start_batch(rcp);
-                        spin_unlock(&rcp->lock);
+                        spin_lock_irqsave(&rcp->lock, flags2);
+                        if (rcu_batch_after(rdp->batch, rcp->pending)) {
+                                rcp->pending = rdp->batch;
+                                rcu_start_batch(rcp);
+                        }
+                        spin_unlock_irqrestore(&rcp->lock, flags2);
                 }
         }
 
@@ -462,21 +583,53 @@ static void __rcu_process_callbacks(struct rcu_ctrlblk *rcp,
 
 static void rcu_process_callbacks(struct softirq_action *unused)
 {
+        /*
+         * Memory references from any prior RCU read-side critical sections
+         * executed by the interrupted code must be see before any RCU
+         * grace-period manupulations below.
+         */
+
+        smp_mb(); /* See above block comment. */
+
         __rcu_process_callbacks(&rcu_ctrlblk, &__get_cpu_var(rcu_data));
         __rcu_process_callbacks(&rcu_bh_ctrlblk, &__get_cpu_var(rcu_bh_data));
+
+        /*
+         * Memory references from any later RCU read-side critical sections
+         * executed by the interrupted code must be see after any RCU
+         * grace-period manupulations above.
+         */
+
+        smp_mb(); /* See above block comment. */
 }
 
 static int __rcu_pending(struct rcu_ctrlblk *rcp, struct rcu_data *rdp)
 {
-        /* This cpu has pending rcu entries and the grace period
-         * for them has completed.
-         */
-        if (rdp->curlist && !rcu_batch_before(rcp->completed, rdp->batch))
-                return 1;
+        /* Check for CPU stalls, if enabled. */
+        check_cpu_stall(rcp);
 
-        /* This cpu has no pending entries, but there are new entries */
-        if (!rdp->curlist && rdp->nxtlist)
-                return 1;
+        if (rdp->nxtlist) {
+                long completed_snap = ACCESS_ONCE(rcp->completed);
+
+                /*
+                 * This cpu has pending rcu entries and the grace period
+                 * for them has completed.
+                 */
+                if (!rcu_batch_before(completed_snap, rdp->batch))
+                        return 1;
+                if (!rcu_batch_before(completed_snap, rdp->batch - 1) &&
+                                rdp->nxttail[0] != rdp->nxttail[1])
+                        return 1;
+                if (rdp->nxttail[0] != &rdp->nxtlist)
+                        return 1;
+
+                /*
+                 * This cpu has pending rcu entries and the new batch
+                 * for then hasn't been started nor scheduled start
+                 */
+                if (rcu_batch_after(rdp->batch, rcp->pending))
+                        return 1;
+        }
 
         /* This cpu has finished callbacks to invoke */
         if (rdp->donelist)
@@ -512,9 +665,15 @@ int rcu_needs_cpu(int cpu)
         struct rcu_data *rdp = &per_cpu(rcu_data, cpu);
         struct rcu_data *rdp_bh = &per_cpu(rcu_bh_data, cpu);
 
-        return (!!rdp->curlist || !!rdp_bh->curlist || rcu_pending(cpu));
+        return !!rdp->nxtlist || !!rdp_bh->nxtlist || rcu_pending(cpu);
 }
 
+/*
+ * Top-level function driving RCU grace-period detection, normally
+ * invoked from the scheduler-clock interrupt.  This function simply
+ * increments counters that are read only from softirq by this same
+ * CPU, so there are no memory barriers required.
+ */
 void rcu_check_callbacks(int cpu, int user)
 {
         if (user ||
@@ -558,14 +717,17 @@ void rcu_check_callbacks(int cpu, int user)
 static void rcu_init_percpu_data(int cpu, struct rcu_ctrlblk *rcp,
                                                 struct rcu_data *rdp)
 {
+        unsigned long flags;
+
+        spin_lock_irqsave(&rcp->lock, flags);
         memset(rdp, 0, sizeof(*rdp));
-        rdp->curtail = &rdp->curlist;
-        rdp->nxttail = &rdp->nxtlist;
+        rdp->nxttail[0] = rdp->nxttail[1] = rdp->nxttail[2] = &rdp->nxtlist;
         rdp->donetail = &rdp->donelist;
         rdp->quiescbatch = rcp->completed;
         rdp->qs_pending = 0;
         rdp->cpu = cpu;
         rdp->blimit = blimit;
+        spin_unlock_irqrestore(&rcp->lock, flags);
 }
 
 static void __cpuinit rcu_online_cpu(int cpu)
@@ -610,6 +772,9 @@ static struct notifier_block __cpuinitdata rcu_nb = {
  */
 void __init __rcu_init(void)
 {
+#ifdef CONFIG_RCU_CPU_STALL_DETECTOR
+        printk(KERN_INFO "RCU-based detection of stalled CPUs is enabled.\n");
+#endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
         rcu_cpu_notify(&rcu_nb, CPU_UP_PREPARE,
                         (void *)(long)smp_processor_id());
         /* Register notifier for non-boot CPUs */
diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c
index 467d5940f624..ad63af8b2521 100644
--- a/kernel/rcupdate.c
+++ b/kernel/rcupdate.c
@@ -119,18 +119,19 @@ static void _rcu_barrier(enum rcu_barrier type)
         /* Take cpucontrol mutex to protect against CPU hotplug */
         mutex_lock(&rcu_barrier_mutex);
         init_completion(&rcu_barrier_completion);
-        atomic_set(&rcu_barrier_cpu_count, 0);
         /*
-         * The queueing of callbacks in all CPUs must be atomic with
-         * respect to RCU, otherwise one CPU may queue a callback,
-         * wait for a grace period, decrement barrier count and call
-         * complete(), while other CPUs have not yet queued anything.
-         * So, we need to make sure that grace periods cannot complete
-         * until all the callbacks are queued.
+         * Initialize rcu_barrier_cpu_count to 1, then invoke
+         * rcu_barrier_func() on each CPU, so that each CPU also has
+         * incremented rcu_barrier_cpu_count.  Only then is it safe to
+         * decrement rcu_barrier_cpu_count -- otherwise the first CPU
+         * might complete its grace period before all of the other CPUs
+         * did their increment, causing this function to return too
+         * early.
          */
-        rcu_read_lock();
+        atomic_set(&rcu_barrier_cpu_count, 1);
         on_each_cpu(rcu_barrier_func, (void *)type, 1);
-        rcu_read_unlock();
+        if (atomic_dec_and_test(&rcu_barrier_cpu_count))
+                complete(&rcu_barrier_completion);
         wait_for_completion(&rcu_barrier_completion);
         mutex_unlock(&rcu_barrier_mutex);
 }
diff --git a/kernel/rcupreempt.c b/kernel/rcupreempt.c
index 27827931ca0d..59236e8b9daa 100644
--- a/kernel/rcupreempt.c
+++ b/kernel/rcupreempt.c
@@ -54,17 +54,9 @@
 #include <linux/cpu.h>
 #include <linux/random.h>
 #include <linux/delay.h>
-#include <linux/byteorder/swabb.h>
 #include <linux/cpumask.h>
 #include <linux/rcupreempt_trace.h>
-
-/*
- * Macro that prevents the compiler from reordering accesses, but does
- * absolutely -nothing- to prevent CPUs from reordering.  This is used
- * only to mediate communication between mainline code and hardware
- * interrupt and NMI handlers.
- */
-#define ACCESS_ONCE(x) (*(volatile typeof(x) *)&(x))
+#include <asm/byteorder.h>
 
 /*
  * PREEMPT_RCU data structures.
diff --git a/kernel/rcupreempt_trace.c b/kernel/rcupreempt_trace.c
index 5edf82c34bbc..35c2d3360ecf 100644
--- a/kernel/rcupreempt_trace.c
+++ b/kernel/rcupreempt_trace.c
@@ -308,11 +308,16 @@ out:
 
 static int __init rcupreempt_trace_init(void)
 {
+        int ret;
+
         mutex_init(&rcupreempt_trace_mutex);
         rcupreempt_trace_buf = kmalloc(RCUPREEMPT_TRACE_BUF_SIZE, GFP_KERNEL);
         if (!rcupreempt_trace_buf)
                 return 1;
-        return rcupreempt_debugfs_init();
+        ret = rcupreempt_debugfs_init();
+        if (ret)
+                kfree(rcupreempt_trace_buf);
+        return ret;
 }
 
 static void __exit rcupreempt_trace_cleanup(void)
diff --git a/kernel/rcutorture.c b/kernel/rcutorture.c
index 90b5b123f7a1..85cb90588a55 100644
--- a/kernel/rcutorture.c
+++ b/kernel/rcutorture.c
@@ -42,10 +42,10 @@
 #include <linux/freezer.h>
 #include <linux/cpu.h>
 #include <linux/delay.h>
-#include <linux/byteorder/swabb.h>
 #include <linux/stat.h>
 #include <linux/srcu.h>
 #include <linux/slab.h>
+#include <asm/byteorder.h>
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Paul E. McKenney <paulmck@us.ibm.com> and "
diff --git a/kernel/relay.c b/kernel/relay.c
index 8d13a7855c08..32b0befdcb6a 100644
--- a/kernel/relay.c
+++ b/kernel/relay.c
@@ -400,7 +400,7 @@ void relay_reset(struct rchan *chan)
         }
 
         mutex_lock(&relay_channels_mutex);
-        for_each_online_cpu(i)
+        for_each_possible_cpu(i)
                 if (chan->buf[i])
                         __relay_reset(chan->buf[i], 0);
         mutex_unlock(&relay_channels_mutex);
@@ -611,10 +611,9 @@ struct rchan *relay_open(const char *base_filename,
         return chan;
 
 free_bufs:
-        for_each_online_cpu(i) {
-                if (!chan->buf[i])
-                        break;
-                relay_close_buf(chan->buf[i]);
+        for_each_possible_cpu(i) {
+                if (chan->buf[i])
+                        relay_close_buf(chan->buf[i]);
         }
 
         kref_put(&chan->kref, relay_destroy_channel);
diff --git a/kernel/resource.c b/kernel/resource.c
index 03d796c1b2e9..4337063663ef 100644
--- a/kernel/resource.c
+++ b/kernel/resource.c
@@ -17,6 +17,7 @@
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
 #include <linux/device.h>
+#include <linux/pfn.h>
 #include <asm/io.h>
 
 
@@ -38,10 +39,6 @@ EXPORT_SYMBOL(iomem_resource);
 
 static DEFINE_RWLOCK(resource_lock);
 
-#ifdef CONFIG_PROC_FS
-
-enum { MAX_IORES_LEVEL = 5 };
-
 static void *r_next(struct seq_file *m, void *v, loff_t *pos)
 {
         struct resource *p = v;
@@ -53,6 +50,10 @@ static void *r_next(struct seq_file *m, void *v, loff_t *pos)
         return p->sibling;
 }
 
+#ifdef CONFIG_PROC_FS
+
+enum { MAX_IORES_LEVEL = 5 };
+
 static void *r_start(struct seq_file *m, loff_t *pos)
         __acquires(resource_lock)
 {
@@ -516,6 +517,70 @@ int adjust_resource(struct resource *res, resource_size_t start, resource_size_t
         return result;
 }
 
+static void __init __reserve_region_with_split(struct resource *root,
+                resource_size_t start, resource_size_t end,
+                const char *name)
+{
+        struct resource *parent = root;
+        struct resource *conflict;
+        struct resource *res = kzalloc(sizeof(*res), GFP_ATOMIC);
+
+        if (!res)
+                return;
+
+        res->name = name;
+        res->start = start;
+        res->end = end;
+        res->flags = IORESOURCE_BUSY;
+
+        for (;;) {
+                conflict = __request_resource(parent, res);
+                if (!conflict)
+                        break;
+                if (conflict != parent) {
+                        parent = conflict;
+                        if (!(conflict->flags & IORESOURCE_BUSY))
+                                continue;
+                }
+
+                /* Uhhuh, that didn't work out.. */
+                kfree(res);
+                res = NULL;
+                break;
+        }
+
+        if (!res) {
+                /* failed, split and try again */
+
+                /* conflict covered whole area */
+                if (conflict->start <= start && conflict->end >= end)
+                        return;
+
+                if (conflict->start > start)
+                        __reserve_region_with_split(root, start, conflict->start-1, name);
+                if (!(conflict->flags & IORESOURCE_BUSY)) {
+                        resource_size_t common_start, common_end;
+
+                        common_start = max(conflict->start, start);
+                        common_end = min(conflict->end, end);
+                        if (common_start < common_end)
+                                __reserve_region_with_split(root, common_start, common_end, name);
+                }
+                if (conflict->end < end)
+                        __reserve_region_with_split(root, conflict->end+1, end, name);
+        }
+
+}
+
+void __init reserve_region_with_split(struct resource *root,
+                resource_size_t start, resource_size_t end,
+                const char *name)
+{
+        write_lock(&resource_lock);
+        __reserve_region_with_split(root, start, end, name);
+        write_unlock(&resource_lock);
+}
+
 EXPORT_SYMBOL(adjust_resource);
 
 /**
@@ -562,33 +627,34 @@ struct resource * __request_region(struct resource *parent,
 {
         struct resource *res = kzalloc(sizeof(*res), GFP_KERNEL);
 
-        if (res) {
-                res->name = name;
-                res->start = start;
-                res->end = start + n - 1;
-                res->flags = IORESOURCE_BUSY;
+        if (!res)
+                return NULL;
 
-                write_lock(&resource_lock);
+        res->name = name;
+        res->start = start;
+        res->end = start + n - 1;
+        res->flags = IORESOURCE_BUSY;
 
-                for (;;) {
-                        struct resource *conflict;
+        write_lock(&resource_lock);
 
-                        conflict = __request_resource(parent, res);
-                        if (!conflict)
-                                break;
-                        if (conflict != parent) {
-                                parent = conflict;
-                                if (!(conflict->flags & IORESOURCE_BUSY))
-                                        continue;
-                        }
+        for (;;) {
+                struct resource *conflict;
 
-                        /* Uhhuh, that didn't work out.. */
-                        kfree(res);
-                        res = NULL;
+                conflict = __request_resource(parent, res);
+                if (!conflict)
                         break;
+                if (conflict != parent) {
+                        parent = conflict;
+                        if (!(conflict->flags & IORESOURCE_BUSY))
+                                continue;
                 }
-                write_unlock(&resource_lock);
+
+                /* Uhhuh, that didn't work out.. */
+                kfree(res);
+                res = NULL;
+                break;
         }
+        write_unlock(&resource_lock);
         return res;
 }
 EXPORT_SYMBOL(__request_region);
@@ -763,3 +829,41 @@ static int __init reserve_setup(char *str)
 }
 
 __setup("reserve=", reserve_setup);
+
+/*
+ * Check if the requested addr and size spans more than any slot in the
+ * iomem resource tree.
+ */
+int iomem_map_sanity_check(resource_size_t addr, unsigned long size)
+{
+        struct resource *p = &iomem_resource;
+        int err = 0;
+        loff_t l;
+
+        read_lock(&resource_lock);
+        for (p = p->child; p ; p = r_next(NULL, p, &l)) {
+                /*
+                 * We can probably skip the resources without
+                 * IORESOURCE_IO attribute?
+                 */
+                if (p->start >= addr + size)
+                        continue;
+                if (p->end < addr)
+                        continue;
+                if (PFN_DOWN(p->start) <= PFN_DOWN(addr) &&
+                    PFN_DOWN(p->end) >= PFN_DOWN(addr + size - 1))
+                        continue;
+                printk(KERN_WARNING "resource map sanity check conflict: "
+                       "0x%llx 0x%llx 0x%llx 0x%llx %s\n",
+                       (unsigned long long)addr,
+                       (unsigned long long)(addr + size - 1),
+                       (unsigned long long)p->start,
+                       (unsigned long long)p->end,
+                       p->name);
+                err = -1;
+                break;
+        }
+        read_unlock(&resource_lock);
+
+        return err;
+}
diff --git a/kernel/rtmutex.c b/kernel/rtmutex.c
index 6522ae5b14a2..69d9cb921ffa 100644
--- a/kernel/rtmutex.c
+++ b/kernel/rtmutex.c
@@ -631,8 +631,7 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state,
 
         /* Setup the timer, when timeout != NULL */
         if (unlikely(timeout)) {
-                hrtimer_start(&timeout->timer, timeout->timer.expires,
-                              HRTIMER_MODE_ABS);
+                hrtimer_start_expires(&timeout->timer, HRTIMER_MODE_ABS);
                 if (!hrtimer_active(&timeout->timer))
                         timeout->task = NULL;
         }
diff --git a/kernel/sched.c b/kernel/sched.c
index cc1f81b50b82..9b1e79371c20 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -55,6 +55,7 @@
 #include <linux/cpuset.h>
 #include <linux/percpu.h>
 #include <linux/kthread.h>
+#include <linux/proc_fs.h>
 #include <linux/seq_file.h>
 #include <linux/sysctl.h>
 #include <linux/syscalls.h>
@@ -71,6 +72,7 @@
 #include <linux/debugfs.h>
 #include <linux/ctype.h>
 #include <linux/ftrace.h>
+#include <trace/sched.h>
 
 #include <asm/tlb.h>
 #include <asm/irq_regs.h>
@@ -201,14 +203,19 @@ void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime)
         hrtimer_init(&rt_b->rt_period_timer,
                         CLOCK_MONOTONIC, HRTIMER_MODE_REL);
         rt_b->rt_period_timer.function = sched_rt_period_timer;
-        rt_b->rt_period_timer.cb_mode = HRTIMER_CB_IRQSAFE_NO_SOFTIRQ;
+        rt_b->rt_period_timer.cb_mode = HRTIMER_CB_IRQSAFE_UNLOCKED;
+}
+
+static inline int rt_bandwidth_enabled(void)
+{
+        return sysctl_sched_rt_runtime >= 0;
 }
 
 static void start_rt_bandwidth(struct rt_bandwidth *rt_b)
 {
         ktime_t now;
 
-        if (rt_b->rt_runtime == RUNTIME_INF)
+        if (rt_bandwidth_enabled() && rt_b->rt_runtime == RUNTIME_INF)
                 return;
 
         if (hrtimer_active(&rt_b->rt_period_timer))
@@ -221,9 +228,8 @@ static void start_rt_bandwidth(struct rt_bandwidth *rt_b)
 
                 now = hrtimer_cb_get_time(&rt_b->rt_period_timer);
                 hrtimer_forward(&rt_b->rt_period_timer, now, rt_b->rt_period);
-                hrtimer_start(&rt_b->rt_period_timer,
-                              rt_b->rt_period_timer.expires,
-                              HRTIMER_MODE_ABS);
+                hrtimer_start_expires(&rt_b->rt_period_timer,
+                                HRTIMER_MODE_ABS);
         }
         spin_unlock(&rt_b->rt_runtime_lock);
 }
@@ -298,9 +304,9 @@ static DEFINE_PER_CPU(struct cfs_rq, init_cfs_rq) ____cacheline_aligned_in_smp;
 static DEFINE_PER_CPU(struct sched_rt_entity, init_sched_rt_entity);
 static DEFINE_PER_CPU(struct rt_rq, init_rt_rq) ____cacheline_aligned_in_smp;
 #endif /* CONFIG_RT_GROUP_SCHED */
-#else /* !CONFIG_FAIR_GROUP_SCHED */
+#else /* !CONFIG_USER_SCHED */
 #define root_task_group init_task_group
-#endif /* CONFIG_FAIR_GROUP_SCHED */
+#endif /* CONFIG_USER_SCHED */
 
 /* task_group_lock serializes add/remove of task groups and also changes to
  * a task group's cpu shares.
@@ -380,7 +386,6 @@ struct cfs_rq {
 
         u64 exec_clock;
         u64 min_vruntime;
-        u64 pair_start;
 
         struct rb_root tasks_timeline;
         struct rb_node *rb_leftmost;
@@ -392,9 +397,9 @@ struct cfs_rq {
          * 'curr' points to currently running entity on this cfs_rq.
          * It is set to NULL otherwise (i.e when none are currently running).
          */
-        struct sched_entity *curr, *next;
+        struct sched_entity *curr, *next, *last;
 
-        unsigned long nr_spread_over;
+        unsigned int nr_spread_over;
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
         struct rq *rq;  /* cpu runqueue to which this cfs_rq is attached */
@@ -604,9 +609,9 @@ struct rq {
 
 static DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
 
-static inline void check_preempt_curr(struct rq *rq, struct task_struct *p)
+static inline void check_preempt_curr(struct rq *rq, struct task_struct *p, int sync)
 {
-        rq->curr->sched_class->check_preempt_curr(rq, p);
+        rq->curr->sched_class->check_preempt_curr(rq, p, sync);
 }
 
 static inline int cpu_of(struct rq *rq)
@@ -813,6 +818,13 @@ const_debug unsigned int sysctl_sched_nr_migrate = 32;
 unsigned int sysctl_sched_shares_ratelimit = 250000;
 
 /*
+ * Inject some fuzzyness into changing the per-cpu group shares
+ * this avoids remote rq-locks at the expense of fairness.
+ * default: 4
+ */
+unsigned int sysctl_sched_shares_thresh = 4;
+
+/*
  * period over which we measure -rt task cpu usage in us.
  * default: 1s
  */
@@ -957,6 +969,14 @@ static struct rq *task_rq_lock(struct task_struct *p, unsigned long *flags)
         }
 }
 
+void task_rq_unlock_wait(struct task_struct *p)
+{
+        struct rq *rq = task_rq(p);
+
+        smp_mb(); /* spin-unlock-wait is not a full memory barrier */
+        spin_unlock_wait(&rq->lock);
+}
+
 static void __task_rq_unlock(struct rq *rq)
         __releases(rq->lock)
 {
@@ -1058,7 +1078,7 @@ static void hrtick_start(struct rq *rq, u64 delay)
         struct hrtimer *timer = &rq->hrtick_timer;
         ktime_t time = ktime_add_ns(timer->base->get_time(), delay);
 
-        timer->expires = time;
+        hrtimer_set_expires(timer, time);
 
         if (rq == this_rq()) {
                 hrtimer_restart(timer);
@@ -1087,7 +1107,7 @@ hotplug_hrtick(struct notifier_block *nfb, unsigned long action, void *hcpu)
         return NOTIFY_DONE;
 }
 
-static void init_hrtick(void)
+static __init void init_hrtick(void)
 {
         hotcpu_notifier(hotplug_hrtick, 0);
 }
@@ -1102,7 +1122,7 @@ static void hrtick_start(struct rq *rq, u64 delay)
         hrtimer_start(&rq->hrtick_timer, ns_to_ktime(delay), HRTIMER_MODE_REL);
 }
 
-static void init_hrtick(void)
+static inline void init_hrtick(void)
 {
 }
 #endif /* CONFIG_SMP */
@@ -1119,9 +1139,9 @@ static void init_rq_hrtick(struct rq *rq)
 
         hrtimer_init(&rq->hrtick_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
         rq->hrtick_timer.function = hrtick;
-        rq->hrtick_timer.cb_mode = HRTIMER_CB_IRQSAFE_NO_SOFTIRQ;
+        rq->hrtick_timer.cb_mode = HRTIMER_CB_IRQSAFE_PERCPU;
 }
-#else
+#else   /* CONFIG_SCHED_HRTICK */
 static inline void hrtick_clear(struct rq *rq)
 {
 }
@@ -1133,7 +1153,7 @@ static inline void init_rq_hrtick(struct rq *rq)
 static inline void init_hrtick(void)
 {
 }
-#endif
+#endif  /* CONFIG_SCHED_HRTICK */
 
 /*
  * resched_task - mark a task 'to be rescheduled now'.
@@ -1380,38 +1400,24 @@ static inline void dec_cpu_load(struct rq *rq, unsigned long load)
         update_load_sub(&rq->load, load);
 }
 
-#ifdef CONFIG_SMP
-static unsigned long source_load(int cpu, int type);
-static unsigned long target_load(int cpu, int type);
-static int task_hot(struct task_struct *p, u64 now, struct sched_domain *sd);
-
-static unsigned long cpu_avg_load_per_task(int cpu)
-{
-        struct rq *rq = cpu_rq(cpu);
-
-        if (rq->nr_running)
-                rq->avg_load_per_task = rq->load.weight / rq->nr_running;
-
-        return rq->avg_load_per_task;
-}
-
-#ifdef CONFIG_FAIR_GROUP_SCHED
-
-typedef void (*tg_visitor)(struct task_group *, int, struct sched_domain *);
+#if (defined(CONFIG_SMP) && defined(CONFIG_FAIR_GROUP_SCHED)) || defined(CONFIG_RT_GROUP_SCHED)
+typedef int (*tg_visitor)(struct task_group *, void *);
 
 /*
  * Iterate the full tree, calling @down when first entering a node and @up when
  * leaving it for the final time.
  */
-static void
-walk_tg_tree(tg_visitor down, tg_visitor up, int cpu, struct sched_domain *sd)
+static int walk_tg_tree(tg_visitor down, tg_visitor up, void *data)
 {
         struct task_group *parent, *child;
+        int ret;
 
         rcu_read_lock();
         parent = &root_task_group;
 down:
-        (*down)(parent, cpu, sd);
+        ret = (*down)(parent, data);
+        if (ret)
+                goto out_unlock;
         list_for_each_entry_rcu(child, &parent->children, siblings) {
                 parent = child;
                 goto down;
@@ -1419,23 +1425,53 @@ down:
 up:
                 continue;
         }
-        (*up)(parent, cpu, sd);
+        ret = (*up)(parent, data);
+        if (ret)
+                goto out_unlock;
 
         child = parent;
         parent = parent->parent;
         if (parent)
                 goto up;
+out_unlock:
         rcu_read_unlock();
+
+        return ret;
 }
 
+static int tg_nop(struct task_group *tg, void *data)
+{
+        return 0;
+}
+#endif
+
+#ifdef CONFIG_SMP
+static unsigned long source_load(int cpu, int type);
+static unsigned long target_load(int cpu, int type);
+static int task_hot(struct task_struct *p, u64 now, struct sched_domain *sd);
+
+static unsigned long cpu_avg_load_per_task(int cpu)
+{
+        struct rq *rq = cpu_rq(cpu);
+
+        if (rq->nr_running)
+                rq->avg_load_per_task = rq->load.weight / rq->nr_running;
+        else
+                rq->avg_load_per_task = 0;
+
+        return rq->avg_load_per_task;
+}
+
+#ifdef CONFIG_FAIR_GROUP_SCHED
+
 static void __set_se_shares(struct sched_entity *se, unsigned long shares);
 
 /*
  * Calculate and set the cpu's group shares.
  */
 static void
-__update_group_shares_cpu(struct task_group *tg, int cpu,
-                          unsigned long sd_shares, unsigned long sd_rq_weight)
+update_group_shares_cpu(struct task_group *tg, int cpu,
+                        unsigned long sd_shares, unsigned long sd_rq_weight)
 {
         int boost = 0;
         unsigned long shares;
@@ -1466,19 +1502,23 @@ __update_group_shares_cpu(struct task_group *tg, int cpu,
          *
          */
         shares = (sd_shares * rq_weight) / (sd_rq_weight + 1);
+        shares = clamp_t(unsigned long, shares, MIN_SHARES, MAX_SHARES);
 
-        /*
-         * record the actual number of shares, not the boosted amount.
-         */
-        tg->cfs_rq[cpu]->shares = boost ? 0 : shares;
-        tg->cfs_rq[cpu]->rq_weight = rq_weight;
+        if (abs(shares - tg->se[cpu]->load.weight) >
+                        sysctl_sched_shares_thresh) {
+                struct rq *rq = cpu_rq(cpu);
+                unsigned long flags;
 
-        if (shares < MIN_SHARES)
-                shares = MIN_SHARES;
-        else if (shares > MAX_SHARES)
-                shares = MAX_SHARES;
+                spin_lock_irqsave(&rq->lock, flags);
+                /*
+                 * record the actual number of shares, not the boosted amount.
+                 */
+                tg->cfs_rq[cpu]->shares = boost ? 0 : shares;
+                tg->cfs_rq[cpu]->rq_weight = rq_weight;
 
-        __set_se_shares(tg->se[cpu], shares);
+                __set_se_shares(tg->se[cpu], shares);
+                spin_unlock_irqrestore(&rq->lock, flags);
+        }
 }
 
 /*
@@ -1486,11 +1526,11 @@ __update_group_shares_cpu(struct task_group *tg, int cpu,
  * This needs to be done in a bottom-up fashion because the rq weight of a
  * parent group depends on the shares of its child groups.
  */
-static void
-tg_shares_up(struct task_group *tg, int cpu, struct sched_domain *sd)
+static int tg_shares_up(struct task_group *tg, void *data)
 {
         unsigned long rq_weight = 0;
         unsigned long shares = 0;
+        struct sched_domain *sd = data;
         int i;
 
         for_each_cpu_mask(i, sd->span) {
@@ -1507,14 +1547,10 @@ tg_shares_up(struct task_group *tg, int cpu, struct sched_domain *sd)
         if (!rq_weight)
                 rq_weight = cpus_weight(sd->span) * NICE_0_LOAD;
 
-        for_each_cpu_mask(i, sd->span) {
-                struct rq *rq = cpu_rq(i);
-                unsigned long flags;
+        for_each_cpu_mask(i, sd->span)
+                update_group_shares_cpu(tg, i, shares, rq_weight);
 
-                spin_lock_irqsave(&rq->lock, flags);
-                __update_group_shares_cpu(tg, i, shares, rq_weight);
-                spin_unlock_irqrestore(&rq->lock, flags);
-        }
+        return 0;
 }
 
 /*
@@ -1522,10 +1558,10 @@ tg_shares_up(struct task_group *tg, int cpu, struct sched_domain *sd)
  * This needs to be done in a top-down fashion because the load of a child
  * group is a fraction of its parents load.
  */
-static void
-tg_load_down(struct task_group *tg, int cpu, struct sched_domain *sd)
+static int tg_load_down(struct task_group *tg, void *data)
 {
         unsigned long load;
+        long cpu = (long)data;
 
         if (!tg->parent) {
                 load = cpu_rq(cpu)->load.weight;
@@ -1536,11 +1572,8 @@ tg_load_down(struct task_group *tg, int cpu, struct sched_domain *sd)
         }
 
         tg->cfs_rq[cpu]->h_load = load;
-}
 
-static void
-tg_nop(struct task_group *tg, int cpu, struct sched_domain *sd)
-{
+        return 0;
 }
 
 static void update_shares(struct sched_domain *sd)
@@ -1550,7 +1583,7 @@ static void update_shares(struct sched_domain *sd)
 
         if (elapsed >= (s64)(u64)sysctl_sched_shares_ratelimit) {
                 sd->last_update = now;
-                walk_tg_tree(tg_nop, tg_shares_up, 0, sd);
+                walk_tg_tree(tg_nop, tg_shares_up, sd);
         }
 }
 
@@ -1561,9 +1594,9 @@ static void update_shares_locked(struct rq *rq, struct sched_domain *sd)
         spin_lock(&rq->lock);
 }
 
-static void update_h_load(int cpu)
+static void update_h_load(long cpu)
 {
-        walk_tg_tree(tg_load_down, tg_nop, cpu, NULL);
+        walk_tg_tree(tg_load_down, tg_nop, (void *)cpu);
 }
 
 #else
@@ -1782,7 +1815,9 @@ task_hot(struct task_struct *p, u64 now, struct sched_domain *sd)
         /*
          * Buddy candidates are cache hot:
          */
-        if (sched_feat(CACHE_HOT_BUDDY) && (&p->se == cfs_rq_of(&p->se)->next))
+        if (sched_feat(CACHE_HOT_BUDDY) &&
+                        (&p->se == cfs_rq_of(&p->se)->next ||
+                         &p->se == cfs_rq_of(&p->se)->last))
                 return 1;
 
         if (p->sched_class != &fair_sched_class)
@@ -1918,14 +1953,12 @@ unsigned long wait_task_inactive(struct task_struct *p, long match_state)
                  * just go back and repeat.
                  */
                 rq = task_rq_lock(p, &flags);
+                trace_sched_wait_task(rq, p);
                 running = task_running(rq, p);
                 on_rq = p->se.on_rq;
                 ncsw = 0;
-                if (!match_state || p->state == match_state) {
-                        ncsw = p->nivcsw + p->nvcsw;
-                        if (unlikely(!ncsw))
-                                ncsw = 1;
-                }
+                if (!match_state || p->state == match_state)
+                        ncsw = p->nvcsw | LONG_MIN; /* sets MSB */
                 task_rq_unlock(rq, &flags);
 
                 /*
@@ -2282,10 +2315,8 @@ out_activate:
         success = 1;
 
 out_running:
-        trace_mark(kernel_sched_wakeup,
-                "pid %d state %ld ## rq %p task %p rq->curr %p",
-                p->pid, p->state, rq, p, rq->curr);
-        check_preempt_curr(rq, p);
+        trace_sched_wakeup(rq, p);
+        check_preempt_curr(rq, p, sync);
 
         p->state = TASK_RUNNING;
 #ifdef CONFIG_SMP
@@ -2417,10 +2448,8 @@ void wake_up_new_task(struct task_struct *p, unsigned long clone_flags)
                 p->sched_class->task_new(rq, p);
                 inc_nr_running(rq);
         }
-        trace_mark(kernel_sched_wakeup_new,
-                "pid %d state %ld ## rq %p task %p rq->curr %p",
-                p->pid, p->state, rq, p, rq->curr);
-        check_preempt_curr(rq, p);
+        trace_sched_wakeup_new(rq, p);
+        check_preempt_curr(rq, p, 0);
 #ifdef CONFIG_SMP
         if (p->sched_class->task_wake_up)
                 p->sched_class->task_wake_up(rq, p);
@@ -2592,11 +2621,7 @@ context_switch(struct rq *rq, struct task_struct *prev,
         struct mm_struct *mm, *oldmm;
 
         prepare_task_switch(rq, prev, next);
-        trace_mark(kernel_sched_schedule,
-                "prev_pid %d next_pid %d prev_state %ld "
-                "## rq %p prev %p next %p",
-                prev->pid, next->pid, prev->state,
-                rq, prev, next);
+        trace_sched_switch(rq, prev, next);
         mm = next->mm;
         oldmm = prev->active_mm;
         /*
@@ -2836,6 +2861,7 @@ static void sched_migrate_task(struct task_struct *p, int dest_cpu)
             || unlikely(!cpu_active(dest_cpu)))
                 goto out;
 
+        trace_sched_migrate_task(rq, p, dest_cpu);
         /* force the process onto the specified CPU */
         if (migrate_task(p, dest_cpu, &req)) {
                 /* Need to wait for migration thread (might exit: take ref). */
@@ -2880,7 +2906,7 @@ static void pull_task(struct rq *src_rq, struct task_struct *p,
          * Note that idle threads have a prio of MAX_PRIO, for this test
          * to be always true for them.
          */
-        check_preempt_curr(this_rq, p);
+        check_preempt_curr(this_rq, p, 0);
 }
 
 /*
@@ -3329,7 +3355,7 @@ small_imbalance:
                 } else
                         this_load_per_task = cpu_avg_load_per_task(this_cpu);
 
-                if (max_load - this_load + 2*busiest_load_per_task >=
+                if (max_load - this_load + busiest_load_per_task >=
                                         busiest_load_per_task * imbn) {
                         *imbalance = busiest_load_per_task;
                         return busiest;
@@ -4037,23 +4063,26 @@ DEFINE_PER_CPU(struct kernel_stat, kstat);
 EXPORT_PER_CPU_SYMBOL(kstat);
 
 /*
- * Return p->sum_exec_runtime plus any more ns on the sched_clock
- * that have not yet been banked in case the task is currently running.
+ * Return any ns on the sched_clock that have not yet been banked in
+ * @p in case that task is currently running.
  */
-unsigned long long task_sched_runtime(struct task_struct *p)
+unsigned long long task_delta_exec(struct task_struct *p)
 {
         unsigned long flags;
-        u64 ns, delta_exec;
         struct rq *rq;
+        u64 ns = 0;
 
         rq = task_rq_lock(p, &flags);
-        ns = p->se.sum_exec_runtime;
+
         if (task_current(rq, p)) {
+                u64 delta_exec;
+
                 update_rq_clock(rq);
                 delta_exec = rq->clock - p->se.exec_start;
                 if ((s64)delta_exec > 0)
-                        ns += delta_exec;
+                        ns = delta_exec;
         }
+
         task_rq_unlock(rq, &flags);
 
         return ns;
@@ -4070,6 +4099,7 @@ void account_user_time(struct task_struct *p, cputime_t cputime)
         cputime64_t tmp;
 
         p->utime = cputime_add(p->utime, cputime);
+        account_group_user_time(p, cputime);
 
         /* Add user time to cpustat. */
         tmp = cputime_to_cputime64(cputime);
@@ -4094,6 +4124,7 @@ static void account_guest_time(struct task_struct *p, cputime_t cputime)
         tmp = cputime_to_cputime64(cputime);
 
         p->utime = cputime_add(p->utime, cputime);
+        account_group_user_time(p, cputime);
         p->gtime = cputime_add(p->gtime, cputime);
 
         cpustat->user = cputime64_add(cpustat->user, tmp);
@@ -4129,6 +4160,7 @@ void account_system_time(struct task_struct *p, int hardirq_offset,
         }
 
         p->stime = cputime_add(p->stime, cputime);
+        account_group_system_time(p, cputime);
 
         /* Add system time to cpustat. */
         tmp = cputime_to_cputime64(cputime);
@@ -4170,6 +4202,7 @@ void account_steal_time(struct task_struct *p, cputime_t steal)
 
         if (p == rq->idle) {
                 p->stime = cputime_add(p->stime, steal);
+                account_group_system_time(p, steal);
                 if (atomic_read(&rq->nr_iowait) > 0)
                         cpustat->iowait = cputime64_add(cpustat->iowait, tmp);
                 else
@@ -4426,12 +4459,8 @@ need_resched_nonpreemptible:
         if (sched_feat(HRTICK))
                 hrtick_clear(rq);
 
-        /*
-         * Do the rq-clock update outside the rq lock:
-         */
-        local_irq_disable();
+        spin_lock_irq(&rq->lock);
         update_rq_clock(rq);
-        spin_lock(&rq->lock);
         clear_tsk_need_resched(prev);
 
         if (prev->state && !(preempt_count() & PREEMPT_ACTIVE)) {
@@ -4627,6 +4656,15 @@ __wake_up_sync(wait_queue_head_t *q, unsigned int mode, int nr_exclusive)
 }
 EXPORT_SYMBOL_GPL(__wake_up_sync);      /* For internal use only */
 
+/**
+ * complete: - signals a single thread waiting on this completion
+ * @x:  holds the state of this particular completion
+ *
+ * This will wake up a single thread waiting on this completion. Threads will be
+ * awakened in the same order in which they were queued.
+ *
+ * See also complete_all(), wait_for_completion() and related routines.
+ */
 void complete(struct completion *x)
 {
         unsigned long flags;
@@ -4638,6 +4676,12 @@ void complete(struct completion *x)
 }
 EXPORT_SYMBOL(complete);
 
+/**
+ * complete_all: - signals all threads waiting on this completion
+ * @x:  holds the state of this particular completion
+ *
+ * This will wake up all threads waiting on this particular completion event.
+ */
 void complete_all(struct completion *x)
 {
         unsigned long flags;
@@ -4658,10 +4702,7 @@ do_wait_for_common(struct completion *x, long timeout, int state)
                 wait.flags |= WQ_FLAG_EXCLUSIVE;
                 __add_wait_queue_tail(&x->wait, &wait);
                 do {
-                        if ((state == TASK_INTERRUPTIBLE &&
-                             signal_pending(current)) ||
-                            (state == TASK_KILLABLE &&
-                             fatal_signal_pending(current))) {
+                        if (signal_pending_state(state, current)) {
                                 timeout = -ERESTARTSYS;
                                 break;
                         }
@@ -4689,12 +4730,31 @@ wait_for_common(struct completion *x, long timeout, int state)
         return timeout;
 }
 
+/**
+ * wait_for_completion: - waits for completion of a task
+ * @x:  holds the state of this particular completion
+ *
+ * This waits to be signaled for completion of a specific task. It is NOT
+ * interruptible and there is no timeout.
+ *
+ * See also similar routines (i.e. wait_for_completion_timeout()) with timeout
+ * and interrupt capability. Also see complete().
+ */
 void __sched wait_for_completion(struct completion *x)
 {
         wait_for_common(x, MAX_SCHEDULE_TIMEOUT, TASK_UNINTERRUPTIBLE);
 }
 EXPORT_SYMBOL(wait_for_completion);
 
+/**
+ * wait_for_completion_timeout: - waits for completion of a task (w/timeout)
+ * @x:  holds the state of this particular completion
+ * @timeout:  timeout value in jiffies
+ *
+ * This waits for either a completion of a specific task to be signaled or for a
+ * specified timeout to expire. The timeout is in jiffies. It is not
+ * interruptible.
+ */
 unsigned long __sched
 wait_for_completion_timeout(struct completion *x, unsigned long timeout)
 {
@@ -4702,6 +4762,13 @@ wait_for_completion_timeout(struct completion *x, unsigned long timeout)
 }
 EXPORT_SYMBOL(wait_for_completion_timeout);
 
+/**
+ * wait_for_completion_interruptible: - waits for completion of a task (w/intr)
+ * @x:  holds the state of this particular completion
+ *
+ * This waits for completion of a specific task to be signaled. It is
+ * interruptible.
+ */
 int __sched wait_for_completion_interruptible(struct completion *x)
 {
         long t = wait_for_common(x, MAX_SCHEDULE_TIMEOUT, TASK_INTERRUPTIBLE);
@@ -4711,6 +4778,14 @@ int __sched wait_for_completion_interruptible(struct completion *x)
 }
 EXPORT_SYMBOL(wait_for_completion_interruptible);
 
+/**
+ * wait_for_completion_interruptible_timeout: - waits for completion (w/(to,intr))
+ * @x:  holds the state of this particular completion
+ * @timeout:  timeout value in jiffies
+ *
+ * This waits for either a completion of a specific task to be signaled or for a
+ * specified timeout to expire. It is interruptible. The timeout is in jiffies.
+ */
 unsigned long __sched
 wait_for_completion_interruptible_timeout(struct completion *x,
                                           unsigned long timeout)
@@ -4719,6 +4794,13 @@ wait_for_completion_interruptible_timeout(struct completion *x,
 }
 EXPORT_SYMBOL(wait_for_completion_interruptible_timeout);
 
+/**
+ * wait_for_completion_killable: - waits for completion of a task (killable)
+ * @x:  holds the state of this particular completion
+ *
+ * This waits to be signaled for completion of a specific task. It can be
+ * interrupted by a kill signal.
+ */
 int __sched wait_for_completion_killable(struct completion *x)
 {
         long t = wait_for_common(x, MAX_SCHEDULE_TIMEOUT, TASK_KILLABLE);
@@ -5121,7 +5203,8 @@ recheck:
                  * Do not allow realtime tasks into groups that have no runtime
                  * assigned.
                  */
-                if (rt_policy(policy) && task_group(p)->rt_bandwidth.rt_runtime == 0)
+                if (rt_bandwidth_enabled() && rt_policy(policy) &&
+                                task_group(p)->rt_bandwidth.rt_runtime == 0)
                         return -EPERM;
 #endif
 
@@ -5787,6 +5870,8 @@ void __cpuinit init_idle(struct task_struct *idle, int cpu)
         struct rq *rq = cpu_rq(cpu);
         unsigned long flags;
 
+        spin_lock_irqsave(&rq->lock, flags);
+
         __sched_fork(idle);
         idle->se.exec_start = sched_clock();
 
@@ -5794,7 +5879,6 @@ void __cpuinit init_idle(struct task_struct *idle, int cpu)
         idle->cpus_allowed = cpumask_of_cpu(cpu);
         __set_task_cpu(idle, cpu);
 
-        spin_lock_irqsave(&rq->lock, flags);
         rq->curr = rq->idle = idle;
 #if defined(CONFIG_SMP) && defined(__ARCH_WANT_UNLOCKED_CTXSW)
         idle->oncpu = 1;
@@ -5957,7 +6041,7 @@ static int __migrate_task(struct task_struct *p, int src_cpu, int dest_cpu)
         set_task_cpu(p, dest_cpu);
         if (on_rq) {
                 activate_task(rq_dest, p, 0);
-                check_preempt_curr(rq_dest, p);
+                check_preempt_curr(rq_dest, p, 0);
         }
 done:
         ret = 1;
@@ -6282,7 +6366,7 @@ 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(12);
+        struct ctl_table *table = sd_alloc_ctl_entry(13);
 
         if (table == NULL)
                 return NULL;
@@ -6310,7 +6394,9 @@ sd_alloc_ctl_domain_table(struct sched_domain *sd)
                 sizeof(int), 0644, proc_dointvec_minmax);
         set_table_entry(&table[10], "flags", &sd->flags,
                 sizeof(int), 0644, proc_dointvec_minmax);
-        /* &table[11] is terminator */
+        set_table_entry(&table[11], "name", sd->name,
+                CORENAME_MAX_SIZE, 0444, proc_dostring);
+        /* &table[12] is terminator */
 
         return table;
 }
@@ -6802,15 +6888,17 @@ cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu)
         struct sched_domain *tmp;
 
         /* Remove the sched domains which do not contribute to scheduling. */
-        for (tmp = sd; tmp; tmp = tmp->parent) {
+        for (tmp = sd; tmp; ) {
                 struct sched_domain *parent = tmp->parent;
                 if (!parent)
                         break;
+
                 if (sd_parent_degenerate(tmp, parent)) {
                         tmp->parent = parent->parent;
                         if (parent->parent)
                                 parent->parent->child = tmp;
-                }
+                } else
+                        tmp = tmp->parent;
         }
 
         if (sd && sd_degenerate(sd)) {
@@ -7194,13 +7282,21 @@ static void init_sched_groups_power(int cpu, struct sched_domain *sd)
  * Non-inlined to reduce accumulated stack pressure in build_sched_domains()
  */
 
+#ifdef CONFIG_SCHED_DEBUG
+# define SD_INIT_NAME(sd, type)         sd->name = #type
+#else
+# define SD_INIT_NAME(sd, type)         do { } while (0)
+#endif
+
 #define SD_INIT(sd, type)       sd_init_##type(sd)
+
 #define SD_INIT_FUNC(type)      \
 static noinline void sd_init_##type(struct sched_domain *sd)    \
 {                                                               \
         memset(sd, 0, sizeof(*sd));                             \
         *sd = SD_##type##_INIT;                                 \
         sd->level = SD_LV_##type;                               \
+        SD_INIT_NAME(sd, type);                                 \
 }
 
 SD_INIT_FUNC(CPU)
@@ -7591,6 +7687,7 @@ static int __build_sched_domains(const cpumask_t *cpu_map,
 error:
         free_sched_groups(cpu_map, tmpmask);
         SCHED_CPUMASK_FREE((void *)allmasks);
+        kfree(rd);
         return -ENOMEM;
 #endif
 }
@@ -7692,13 +7789,14 @@ static int dattrs_equal(struct sched_domain_attr *cur, int idx_cur,
  *
  * The passed in 'doms_new' should be kmalloc'd. This routine takes
  * ownership of it and will kfree it when done with it. If the caller
- * failed the kmalloc call, then it can pass in doms_new == NULL,
- * and partition_sched_domains() will fallback to the single partition
- * 'fallback_doms', it also forces the domains to be rebuilt.
+ * failed the kmalloc call, then it can pass in doms_new == NULL &&
+ * ndoms_new == 1, and partition_sched_domains() will fallback to
+ * the single partition 'fallback_doms', it also forces the domains
+ * to be rebuilt.
  *
- * If doms_new==NULL it will be replaced with cpu_online_map.
- * ndoms_new==0 is a special case for destroying existing domains.
- * It will not create the default domain.
+ * If doms_new == NULL it will be replaced with cpu_online_map.
+ * ndoms_new == 0 is a special case for destroying existing domains,
+ * and it will not create the default domain.
  *
  * Call with hotplug lock held
  */
@@ -8242,20 +8340,25 @@ void __might_sleep(char *file, int line)
 #ifdef in_atomic
         static unsigned long prev_jiffy;        /* ratelimiting */
 
-        if ((in_atomic() || irqs_disabled()) &&
-            system_state == SYSTEM_RUNNING && !oops_in_progress) {
-                if (time_before(jiffies, prev_jiffy + HZ) && prev_jiffy)
-                        return;
-                prev_jiffy = jiffies;
-                printk(KERN_ERR "BUG: sleeping function called from invalid"
-                                " context at %s:%d\n", file, line);
-                printk("in_atomic():%d, irqs_disabled():%d\n",
-                        in_atomic(), irqs_disabled());
-                debug_show_held_locks(current);
-                if (irqs_disabled())
-                        print_irqtrace_events(current);
-                dump_stack();
-        }
+        if ((!in_atomic() && !irqs_disabled()) ||
+                    system_state != SYSTEM_RUNNING || oops_in_progress)
+                return;
+        if (time_before(jiffies, prev_jiffy + HZ) && prev_jiffy)
+                return;
+        prev_jiffy = jiffies;
+
+        printk(KERN_ERR
+                "BUG: sleeping function called from invalid context at %s:%d\n",
+                        file, line);
+        printk(KERN_ERR
+                "in_atomic(): %d, irqs_disabled(): %d, pid: %d, name: %s\n",
+                        in_atomic(), irqs_disabled(),
+                        current->pid, current->comm);
+
+        debug_show_held_locks(current);
+        if (irqs_disabled())
+                print_irqtrace_events(current);
+        dump_stack();
 #endif
 }
 EXPORT_SYMBOL(__might_sleep);
@@ -8753,73 +8856,95 @@ static DEFINE_MUTEX(rt_constraints_mutex);
 static unsigned long to_ratio(u64 period, u64 runtime)
 {
         if (runtime == RUNTIME_INF)
-                return 1ULL << 16;
+                return 1ULL << 20;
 
-        return div64_u64(runtime << 16, period);
+        return div64_u64(runtime << 20, period);
 }
 
-#ifdef CONFIG_CGROUP_SCHED
-static int __rt_schedulable(struct task_group *tg, u64 period, u64 runtime)
+/* Must be called with tasklist_lock held */
+static inline int tg_has_rt_tasks(struct task_group *tg)
 {
-        struct task_group *tgi, *parent = tg->parent;
-        unsigned long total = 0;
+        struct task_struct *g, *p;
 
-        if (!parent) {
-                if (global_rt_period() < period)
-                        return 0;
+        do_each_thread(g, p) {
+                if (rt_task(p) && rt_rq_of_se(&p->rt)->tg == tg)
+                        return 1;
+        } while_each_thread(g, p);
 
-                return to_ratio(period, runtime) <
-                        to_ratio(global_rt_period(), global_rt_runtime());
-        }
+        return 0;
+}
 
-        if (ktime_to_ns(parent->rt_bandwidth.rt_period) < period)
-                return 0;
+struct rt_schedulable_data {
+        struct task_group *tg;
+        u64 rt_period;
+        u64 rt_runtime;
+};
 
-        rcu_read_lock();
-        list_for_each_entry_rcu(tgi, &parent->children, siblings) {
-                if (tgi == tg)
-                        continue;
+static int tg_schedulable(struct task_group *tg, void *data)
+{
+        struct rt_schedulable_data *d = data;
+        struct task_group *child;
+        unsigned long total, sum = 0;
+        u64 period, runtime;
+
+        period = ktime_to_ns(tg->rt_bandwidth.rt_period);
+        runtime = tg->rt_bandwidth.rt_runtime;
 
-                total += to_ratio(ktime_to_ns(tgi->rt_bandwidth.rt_period),
-                                tgi->rt_bandwidth.rt_runtime);
+        if (tg == d->tg) {
+                period = d->rt_period;
+                runtime = d->rt_runtime;
         }
-        rcu_read_unlock();
 
-        return total + to_ratio(period, runtime) <=
-                to_ratio(ktime_to_ns(parent->rt_bandwidth.rt_period),
-                                parent->rt_bandwidth.rt_runtime);
-}
-#elif defined CONFIG_USER_SCHED
-static int __rt_schedulable(struct task_group *tg, u64 period, u64 runtime)
-{
-        struct task_group *tgi;
-        unsigned long total = 0;
-        unsigned long global_ratio =
-                to_ratio(global_rt_period(), global_rt_runtime());
+        /*
+         * Cannot have more runtime than the period.
+         */
+        if (runtime > period && runtime != RUNTIME_INF)
+                return -EINVAL;
 
-        rcu_read_lock();
-        list_for_each_entry_rcu(tgi, &task_groups, list) {
-                if (tgi == tg)
-                        continue;
+        /*
+         * Ensure we don't starve existing RT tasks.
+         */
+        if (rt_bandwidth_enabled() && !runtime && tg_has_rt_tasks(tg))
+                return -EBUSY;
+
+        total = to_ratio(period, runtime);
+
+        /*
+         * Nobody can have more than the global setting allows.
+         */
+        if (total > to_ratio(global_rt_period(), global_rt_runtime()))
+                return -EINVAL;
 
-                total += to_ratio(ktime_to_ns(tgi->rt_bandwidth.rt_period),
-                                tgi->rt_bandwidth.rt_runtime);
+        /*
+         * The sum of our children's runtime should not exceed our own.
+         */
+        list_for_each_entry_rcu(child, &tg->children, siblings) {
+                period = ktime_to_ns(child->rt_bandwidth.rt_period);
+                runtime = child->rt_bandwidth.rt_runtime;
+
+                if (child == d->tg) {
+                        period = d->rt_period;
+                        runtime = d->rt_runtime;
+                }
+
+                sum += to_ratio(period, runtime);
         }
-        rcu_read_unlock();
 
-        return total + to_ratio(period, runtime) < global_ratio;
+        if (sum > total)
+                return -EINVAL;
+
+        return 0;
 }
-#endif
 
-/* Must be called with tasklist_lock held */
-static inline int tg_has_rt_tasks(struct task_group *tg)
+static int __rt_schedulable(struct task_group *tg, u64 period, u64 runtime)
 {
-        struct task_struct *g, *p;
-        do_each_thread(g, p) {
-                if (rt_task(p) && rt_rq_of_se(&p->rt)->tg == tg)
-                        return 1;
-        } while_each_thread(g, p);
-        return 0;
+        struct rt_schedulable_data data = {
+                .tg = tg,
+                .rt_period = period,
+                .rt_runtime = runtime,
+        };
+
+        return walk_tg_tree(tg_schedulable, tg_nop, &data);
 }
 
 static int tg_set_bandwidth(struct task_group *tg,
@@ -8829,14 +8954,9 @@ static int tg_set_bandwidth(struct task_group *tg,
 
         mutex_lock(&rt_constraints_mutex);
         read_lock(&tasklist_lock);
-        if (rt_runtime == 0 && tg_has_rt_tasks(tg)) {
-                err = -EBUSY;
-                goto unlock;
-        }
-        if (!__rt_schedulable(tg, rt_period, rt_runtime)) {
-                err = -EINVAL;
+        err = __rt_schedulable(tg, rt_period, rt_runtime);
+        if (err)
                 goto unlock;
-        }
 
         spin_lock_irq(&tg->rt_bandwidth.rt_runtime_lock);
         tg->rt_bandwidth.rt_period = ns_to_ktime(rt_period);
@@ -8905,16 +9025,25 @@ long sched_group_rt_period(struct task_group *tg)
 
 static int sched_rt_global_constraints(void)
 {
-        struct task_group *tg = &root_task_group;
-        u64 rt_runtime, rt_period;
+        u64 runtime, period;
         int ret = 0;
 
-        rt_period = ktime_to_ns(tg->rt_bandwidth.rt_period);
-        rt_runtime = tg->rt_bandwidth.rt_runtime;
+        if (sysctl_sched_rt_period <= 0)
+                return -EINVAL;
+
+        runtime = global_rt_runtime();
+        period = global_rt_period();
+
+        /*
+         * Sanity check on the sysctl variables.
+         */
+        if (runtime > period && runtime != RUNTIME_INF)
+                return -EINVAL;
 
         mutex_lock(&rt_constraints_mutex);
-        if (!__rt_schedulable(tg, rt_period, rt_runtime))
-                ret = -EINVAL;
+        read_lock(&tasklist_lock);
+        ret = __rt_schedulable(NULL, 0, 0);
+        read_unlock(&tasklist_lock);
         mutex_unlock(&rt_constraints_mutex);
 
         return ret;
@@ -8925,6 +9054,9 @@ static int sched_rt_global_constraints(void)
         unsigned long flags;
         int i;
 
+        if (sysctl_sched_rt_period <= 0)
+                return -EINVAL;
+
         spin_lock_irqsave(&def_rt_bandwidth.rt_runtime_lock, flags);
         for_each_possible_cpu(i) {
                 struct rt_rq *rt_rq = &cpu_rq(i)->rt;
@@ -8985,7 +9117,6 @@ cpu_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cgrp)
 
         if (!cgrp->parent) {
                 /* This is early initialization for the top cgroup */
-                init_task_group.css.cgroup = cgrp;
                 return &init_task_group.css;
         }
 
@@ -8994,9 +9125,6 @@ cpu_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cgrp)
         if (IS_ERR(tg))
                 return ERR_PTR(-ENOMEM);
 
-        /* Bind the cgroup to task_group object we just created */
-        tg->css.cgroup = cgrp;
-
         return &tg->css;
 }
 
diff --git a/kernel/sched_clock.c b/kernel/sched_clock.c
index e8ab096ddfe3..81787248b60f 100644
--- a/kernel/sched_clock.c
+++ b/kernel/sched_clock.c
@@ -118,13 +118,13 @@ static u64 __update_sched_clock(struct sched_clock_data *scd, u64 now)
 
         /*
          * scd->clock = clamp(scd->tick_gtod + delta,
-         *                    max(scd->tick_gtod, scd->clock),
-         *                    scd->tick_gtod + TICK_NSEC);
+         *                    max(scd->tick_gtod, scd->clock),
+         *                    max(scd->clock, scd->tick_gtod + TICK_NSEC));
          */
 
         clock = scd->tick_gtod + delta;
         min_clock = wrap_max(scd->tick_gtod, scd->clock);
-        max_clock = scd->tick_gtod + TICK_NSEC;
+        max_clock = wrap_max(scd->clock, scd->tick_gtod + TICK_NSEC);
 
         clock = wrap_max(clock, min_clock);
         clock = wrap_min(clock, max_clock);
diff --git a/kernel/sched_debug.c b/kernel/sched_debug.c
index bbe6b31c3c56..26ed8e3d1c15 100644
--- a/kernel/sched_debug.c
+++ b/kernel/sched_debug.c
@@ -144,7 +144,7 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
         last = __pick_last_entity(cfs_rq);
         if (last)
                 max_vruntime = last->vruntime;
-        min_vruntime = rq->cfs.min_vruntime;
+        min_vruntime = cfs_rq->min_vruntime;
         rq0_min_vruntime = per_cpu(runqueues, 0).cfs.min_vruntime;
         spin_unlock_irqrestore(&rq->lock, flags);
         SEQ_printf(m, "  .%-30s: %Ld.%06ld\n", "MIN_vruntime",
@@ -161,26 +161,8 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
                         SPLIT_NS(spread0));
         SEQ_printf(m, "  .%-30s: %ld\n", "nr_running", cfs_rq->nr_running);
         SEQ_printf(m, "  .%-30s: %ld\n", "load", cfs_rq->load.weight);
-#ifdef CONFIG_SCHEDSTATS
-#define P(n) SEQ_printf(m, "  .%-30s: %d\n", #n, rq->n);
-
-        P(yld_exp_empty);
-        P(yld_act_empty);
-        P(yld_both_empty);
-        P(yld_count);
 
-        P(sched_switch);
-        P(sched_count);
-        P(sched_goidle);
-
-        P(ttwu_count);
-        P(ttwu_local);
-
-        P(bkl_count);
-
-#undef P
-#endif
-        SEQ_printf(m, "  .%-30s: %ld\n", "nr_spread_over",
+        SEQ_printf(m, "  .%-30s: %d\n", "nr_spread_over",
                         cfs_rq->nr_spread_over);
 #ifdef CONFIG_FAIR_GROUP_SCHED
 #ifdef CONFIG_SMP
@@ -260,6 +242,25 @@ static void print_cpu(struct seq_file *m, int cpu)
 #undef P
 #undef PN
 
+#ifdef CONFIG_SCHEDSTATS
+#define P(n) SEQ_printf(m, "  .%-30s: %d\n", #n, rq->n);
+
+        P(yld_exp_empty);
+        P(yld_act_empty);
+        P(yld_both_empty);
+        P(yld_count);
+
+        P(sched_switch);
+        P(sched_count);
+        P(sched_goidle);
+
+        P(ttwu_count);
+        P(ttwu_local);
+
+        P(bkl_count);
+
+#undef P
+#endif
         print_cfs_stats(m, cpu);
         print_rt_stats(m, cpu);
 
@@ -319,7 +320,7 @@ static int __init init_sched_debug_procfs(void)
 {
         struct proc_dir_entry *pe;
 
-        pe = proc_create("sched_debug", 0644, NULL, &sched_debug_fops);
+        pe = proc_create("sched_debug", 0444, NULL, &sched_debug_fops);
         if (!pe)
                 return -ENOMEM;
         return 0;
@@ -333,12 +334,10 @@ void proc_sched_show_task(struct task_struct *p, struct seq_file *m)
         unsigned long flags;
         int num_threads = 1;
 
-        rcu_read_lock();
         if (lock_task_sighand(p, &flags)) {
                 num_threads = atomic_read(&p->signal->count);
                 unlock_task_sighand(p, &flags);
         }
-        rcu_read_unlock();
 
         SEQ_printf(m, "%s (%d, #threads: %d)\n", p->comm, p->pid, num_threads);
         SEQ_printf(m,
@@ -424,10 +423,11 @@ void proc_sched_show_task(struct task_struct *p, struct seq_file *m)
 #undef __P
 
         {
+                unsigned int this_cpu = raw_smp_processor_id();
                 u64 t0, t1;
 
-                t0 = sched_clock();
-                t1 = sched_clock();
+                t0 = cpu_clock(this_cpu);
+                t1 = cpu_clock(this_cpu);
                 SEQ_printf(m, "%-35s:%21Ld\n",
                            "clock-delta", (long long)(t1-t0));
         }
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index fb8994c6d4bb..98345e45b059 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -73,6 +73,8 @@ unsigned int sysctl_sched_wakeup_granularity = 5000000UL;
 
 const_debug unsigned int sysctl_sched_migration_cost = 500000UL;
 
+static const struct sched_class fair_sched_class;
+
 /**************************************************************
  * CFS operations on generic schedulable entities:
  */
@@ -141,6 +143,49 @@ 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)
+{
+        int se_depth, pse_depth;
+
+        /*
+         * preemption test can be made between sibling entities who are in the
+         * same cfs_rq i.e who have a common parent. Walk up the hierarchy of
+         * both tasks until we find their ancestors who are siblings of common
+         * parent.
+         */
+
+        /* First walk up until both entities are at same depth */
+        se_depth = depth_se(*se);
+        pse_depth = depth_se(*pse);
+
+        while (se_depth > pse_depth) {
+                se_depth--;
+                *se = parent_entity(*se);
+        }
+
+        while (pse_depth > se_depth) {
+                pse_depth--;
+                *pse = parent_entity(*pse);
+        }
+
+        while (!is_same_group(*se, *pse)) {
+                *se = parent_entity(*se);
+                *pse = parent_entity(*pse);
+        }
+}
+
 #else   /* CONFIG_FAIR_GROUP_SCHED */
 
 static inline struct rq *rq_of(struct cfs_rq *cfs_rq)
@@ -191,6 +236,11 @@ static inline struct sched_entity *parent_entity(struct sched_entity *se)
         return NULL;
 }
 
+static inline void
+find_matching_se(struct sched_entity **se, struct sched_entity **pse)
+{
+}
+
 #endif  /* CONFIG_FAIR_GROUP_SCHED */
 
 
@@ -221,6 +271,27 @@ static inline s64 entity_key(struct cfs_rq *cfs_rq, struct sched_entity *se)
         return se->vruntime - cfs_rq->min_vruntime;
 }
 
+static void update_min_vruntime(struct cfs_rq *cfs_rq)
+{
+        u64 vruntime = cfs_rq->min_vruntime;
+
+        if (cfs_rq->curr)
+                vruntime = cfs_rq->curr->vruntime;
+
+        if (cfs_rq->rb_leftmost) {
+                struct sched_entity *se = rb_entry(cfs_rq->rb_leftmost,
+                                                   struct sched_entity,
+                                                   run_node);
+
+                if (vruntime == cfs_rq->min_vruntime)
+                        vruntime = se->vruntime;
+                else
+                        vruntime = min_vruntime(vruntime, se->vruntime);
+        }
+
+        cfs_rq->min_vruntime = max_vruntime(cfs_rq->min_vruntime, vruntime);
+}
+
 /*
  * Enqueue an entity into the rb-tree:
  */
@@ -254,15 +325,8 @@ static void __enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
          * Maintain a cache of leftmost tree entries (it is frequently
          * used):
          */
-        if (leftmost) {
+        if (leftmost)
                 cfs_rq->rb_leftmost = &se->run_node;
-                /*
-                 * maintain cfs_rq->min_vruntime to be a monotonic increasing
-                 * value tracking the leftmost vruntime in the tree.
-                 */
-                cfs_rq->min_vruntime =
-                        max_vruntime(cfs_rq->min_vruntime, se->vruntime);
-        }
 
         rb_link_node(&se->run_node, parent, link);
         rb_insert_color(&se->run_node, &cfs_rq->tasks_timeline);
@@ -272,37 +336,25 @@ static void __dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
         if (cfs_rq->rb_leftmost == &se->run_node) {
                 struct rb_node *next_node;
-                struct sched_entity *next;
 
                 next_node = rb_next(&se->run_node);
                 cfs_rq->rb_leftmost = next_node;
-
-                if (next_node) {
-                        next = rb_entry(next_node,
-                                        struct sched_entity, run_node);
-                        cfs_rq->min_vruntime =
-                                max_vruntime(cfs_rq->min_vruntime,
-                                             next->vruntime);
-                }
         }
 
-        if (cfs_rq->next == se)
-                cfs_rq->next = NULL;
-
         rb_erase(&se->run_node, &cfs_rq->tasks_timeline);
 }
 
-static inline struct rb_node *first_fair(struct cfs_rq *cfs_rq)
-{
-        return cfs_rq->rb_leftmost;
-}
-
 static struct sched_entity *__pick_next_entity(struct cfs_rq *cfs_rq)
 {
-        return rb_entry(first_fair(cfs_rq), struct sched_entity, run_node);
+        struct rb_node *left = cfs_rq->rb_leftmost;
+
+        if (!left)
+                return NULL;
+
+        return rb_entry(left, struct sched_entity, run_node);
 }
 
-static inline struct sched_entity *__pick_last_entity(struct cfs_rq *cfs_rq)
+static struct sched_entity *__pick_last_entity(struct cfs_rq *cfs_rq)
 {
         struct rb_node *last = rb_last(&cfs_rq->tasks_timeline);
 
@@ -334,7 +386,7 @@ int sched_nr_latency_handler(struct ctl_table *table, int write,
 #endif
 
 /*
- * delta *= w / rw
+ * delta *= P[w / rw]
  */
 static inline unsigned long
 calc_delta_weight(unsigned long delta, struct sched_entity *se)
@@ -348,15 +400,13 @@ calc_delta_weight(unsigned long delta, struct sched_entity *se)
 }
 
 /*
- * delta *= rw / w
+ * delta /= w
  */
 static inline unsigned long
 calc_delta_fair(unsigned long delta, struct sched_entity *se)
 {
-        for_each_sched_entity(se) {
-                delta = calc_delta_mine(delta,
-                                cfs_rq_of(se)->load.weight, &se->load);
-        }
+        if (unlikely(se->load.weight != NICE_0_LOAD))
+                delta = calc_delta_mine(delta, NICE_0_LOAD, &se->load);
 
         return delta;
 }
@@ -386,84 +436,26 @@ static u64 __sched_period(unsigned long nr_running)
  * We calculate the wall-time slice from the period by taking a part
  * proportional to the weight.
  *
- * s = p*w/rw
+ * s = p*P[w/rw]
  */
 static u64 sched_slice(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
-        return calc_delta_weight(__sched_period(cfs_rq->nr_running), se);
-}
-
-/*
- * We calculate the vruntime slice of a to be inserted task
- *
- * vs = s*rw/w = p
- */
-static u64 sched_vslice_add(struct cfs_rq *cfs_rq, struct sched_entity *se)
-{
         unsigned long nr_running = cfs_rq->nr_running;
 
-        if (!se->on_rq)
+        if (unlikely(!se->on_rq))
                 nr_running++;
 
-        return __sched_period(nr_running);
+        return calc_delta_weight(__sched_period(nr_running), se);
 }
 
 /*
- * The goal of calc_delta_asym() is to be asymmetrically around NICE_0_LOAD, in
- * that it favours >=0 over <0.
- *
- *   -20         |
- *               |
- *     0 --------+-------
- *             .'
- *    19     .'
+ * We calculate the vruntime slice of a to be inserted task
  *
+ * vs = s/w
  */
-static unsigned long
-calc_delta_asym(unsigned long delta, struct sched_entity *se)
+static u64 sched_vslice(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
-        struct load_weight lw = {
-                .weight = NICE_0_LOAD,
-                .inv_weight = 1UL << (WMULT_SHIFT-NICE_0_SHIFT)
-        };
-
-        for_each_sched_entity(se) {
-                struct load_weight *se_lw = &se->load;
-                unsigned long rw = cfs_rq_of(se)->load.weight;
-
-#ifdef CONFIG_FAIR_SCHED_GROUP
-                struct cfs_rq *cfs_rq = se->my_q;
-                struct task_group *tg = NULL
-
-                if (cfs_rq)
-                        tg = cfs_rq->tg;
-
-                if (tg && tg->shares < NICE_0_LOAD) {
-                        /*
-                         * scale shares to what it would have been had
-                         * tg->weight been NICE_0_LOAD:
-                         *
-                         *   weight = 1024 * shares / tg->weight
-                         */
-                        lw.weight *= se->load.weight;
-                        lw.weight /= tg->shares;
-
-                        lw.inv_weight = 0;
-
-                        se_lw = &lw;
-                        rw += lw.weight - se->load.weight;
-                } else
-#endif
-
-                if (se->load.weight < NICE_0_LOAD) {
-                        se_lw = &lw;
-                        rw += NICE_0_LOAD - se->load.weight;
-                }
-
-                delta = calc_delta_mine(delta, rw, se_lw);
-        }
-
-        return delta;
+        return calc_delta_fair(sched_slice(cfs_rq, se), se);
 }
 
 /*
@@ -482,6 +474,7 @@ __update_curr(struct cfs_rq *cfs_rq, struct sched_entity *curr,
         schedstat_add(cfs_rq, exec_clock, delta_exec);
         delta_exec_weighted = calc_delta_fair(delta_exec, curr);
         curr->vruntime += delta_exec_weighted;
+        update_min_vruntime(cfs_rq);
 }
 
 static void update_curr(struct cfs_rq *cfs_rq)
@@ -507,6 +500,7 @@ static void update_curr(struct cfs_rq *cfs_rq)
                 struct task_struct *curtask = task_of(curr);
 
                 cpuacct_charge(curtask, delta_exec);
+                account_group_exec_runtime(curtask, delta_exec);
         }
 }
 
@@ -586,11 +580,12 @@ account_entity_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se)
         update_load_add(&cfs_rq->load, se->load.weight);
         if (!parent_entity(se))
                 inc_cpu_load(rq_of(cfs_rq), se->load.weight);
-        if (entity_is_task(se))
+        if (entity_is_task(se)) {
                 add_cfs_task_weight(cfs_rq, se->load.weight);
+                list_add(&se->group_node, &cfs_rq->tasks);
+        }
         cfs_rq->nr_running++;
         se->on_rq = 1;
-        list_add(&se->group_node, &cfs_rq->tasks);
 }
 
 static void
@@ -599,11 +594,12 @@ account_entity_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se)
         update_load_sub(&cfs_rq->load, se->load.weight);
         if (!parent_entity(se))
                 dec_cpu_load(rq_of(cfs_rq), se->load.weight);
-        if (entity_is_task(se))
+        if (entity_is_task(se)) {
                 add_cfs_task_weight(cfs_rq, -se->load.weight);
+                list_del_init(&se->group_node);
+        }
         cfs_rq->nr_running--;
         se->on_rq = 0;
-        list_del_init(&se->group_node);
 }
 
 static void enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se)
@@ -668,13 +664,7 @@ static void check_spread(struct cfs_rq *cfs_rq, struct sched_entity *se)
 static void
 place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial)
 {
-        u64 vruntime;
-
-        if (first_fair(cfs_rq)) {
-                vruntime = min_vruntime(cfs_rq->min_vruntime,
-                                __pick_next_entity(cfs_rq)->vruntime);
-        } else
-                vruntime = cfs_rq->min_vruntime;
+        u64 vruntime = cfs_rq->min_vruntime;
 
         /*
          * The 'current' period is already promised to the current tasks,
@@ -683,7 +673,7 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial)
          * stays open at the end.
          */
         if (initial && sched_feat(START_DEBIT))
-                vruntime += sched_vslice_add(cfs_rq, se);
+                vruntime += sched_vslice(cfs_rq, se);
 
         if (!initial) {
                 /* sleeps upto a single latency don't count. */
@@ -726,6 +716,15 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int wakeup)
                 __enqueue_entity(cfs_rq, se);
 }
 
+static void clear_buddies(struct cfs_rq *cfs_rq, struct sched_entity *se)
+{
+        if (cfs_rq->last == se)
+                cfs_rq->last = NULL;
+
+        if (cfs_rq->next == se)
+                cfs_rq->next = NULL;
+}
+
 static void
 dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int sleep)
 {
@@ -748,9 +747,12 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int sleep)
 #endif
         }
 
+        clear_buddies(cfs_rq, se);
+
         if (se != cfs_rq->curr)
                 __dequeue_entity(cfs_rq, se);
         account_entity_dequeue(cfs_rq, se);
+        update_min_vruntime(cfs_rq);
 }
 
 /*
@@ -797,29 +799,18 @@ set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
         se->prev_sum_exec_runtime = se->sum_exec_runtime;
 }
 
-static struct sched_entity *
-pick_next(struct cfs_rq *cfs_rq, struct sched_entity *se)
-{
-        struct rq *rq = rq_of(cfs_rq);
-        u64 pair_slice = rq->clock - cfs_rq->pair_start;
-
-        if (!cfs_rq->next || pair_slice > sched_slice(cfs_rq, cfs_rq->next)) {
-                cfs_rq->pair_start = rq->clock;
-                return se;
-        }
-
-        return cfs_rq->next;
-}
+static int
+wakeup_preempt_entity(struct sched_entity *curr, struct sched_entity *se);
 
 static struct sched_entity *pick_next_entity(struct cfs_rq *cfs_rq)
 {
-        struct sched_entity *se = NULL;
+        struct sched_entity *se = __pick_next_entity(cfs_rq);
 
-        if (first_fair(cfs_rq)) {
-                se = __pick_next_entity(cfs_rq);
-                se = pick_next(cfs_rq, se);
-                set_next_entity(cfs_rq, se);
-        }
+        if (cfs_rq->next && wakeup_preempt_entity(cfs_rq->next, se) < 1)
+                return cfs_rq->next;
+
+        if (cfs_rq->last && wakeup_preempt_entity(cfs_rq->last, se) < 1)
+                return cfs_rq->last;
 
         return se;
 }
@@ -904,11 +895,31 @@ static void hrtick_start_fair(struct rq *rq, struct task_struct *p)
                 hrtick_start(rq, delta);
         }
 }
+
+/*
+ * called from enqueue/dequeue and updates the hrtick when the
+ * current task is from our class and nr_running is low enough
+ * to matter.
+ */
+static void hrtick_update(struct rq *rq)
+{
+        struct task_struct *curr = rq->curr;
+
+        if (curr->sched_class != &fair_sched_class)
+                return;
+
+        if (cfs_rq_of(&curr->se)->nr_running < sched_nr_latency)
+                hrtick_start_fair(rq, curr);
+}
 #else /* !CONFIG_SCHED_HRTICK */
 static inline void
 hrtick_start_fair(struct rq *rq, struct task_struct *p)
 {
 }
+
+static inline void hrtick_update(struct rq *rq)
+{
+}
 #endif
 
 /*
@@ -929,7 +940,7 @@ static void enqueue_task_fair(struct rq *rq, struct task_struct *p, int wakeup)
                 wakeup = 1;
         }
 
-        hrtick_start_fair(rq, rq->curr);
+        hrtick_update(rq);
 }
 
 /*
@@ -951,7 +962,7 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int sleep)
                 sleep = 1;
         }
 
-        hrtick_start_fair(rq, rq->curr);
+        hrtick_update(rq);
 }
 
 /*
@@ -971,6 +982,8 @@ static void yield_task_fair(struct rq *rq)
         if (unlikely(cfs_rq->nr_running == 1))
                 return;
 
+        clear_buddies(cfs_rq, se);
+
         if (likely(!sysctl_sched_compat_yield) && curr->policy != SCHED_BATCH) {
                 update_rq_clock(rq);
                 /*
@@ -1057,8 +1070,6 @@ static inline int wake_idle(int cpu, struct task_struct *p)
 
 #ifdef CONFIG_SMP
 
-static const struct sched_class fair_sched_class;
-
 #ifdef CONFIG_FAIR_GROUP_SCHED
 /*
  * effective_load() calculates the load change as seen from the root_task_group
@@ -1085,7 +1096,6 @@ static long effective_load(struct task_group *tg, int cpu,
                 long wl, long wg)
 {
         struct sched_entity *se = tg->se[cpu];
-        long more_w;
 
         if (!tg->parent)
                 return wl;
@@ -1097,18 +1107,17 @@ static long effective_load(struct task_group *tg, int cpu,
         if (!wl && sched_feat(ASYM_EFF_LOAD))
                 return wl;
 
-        /*
-         * Instead of using this increment, also add the difference
-         * between when the shares were last updated and now.
-         */
-        more_w = se->my_q->load.weight - se->my_q->rq_weight;
-        wl += more_w;
-        wg += more_w;
-
         for_each_sched_entity(se) {
-#define D(n) (likely(n) ? (n) : 1)
-
                 long S, rw, s, a, b;
+                long more_w;
+
+                /*
+                 * Instead of using this increment, also add the difference
+                 * between when the shares were last updated and now.
+                 */
+                more_w = se->my_q->load.weight - se->my_q->rq_weight;
+                wl += more_w;
+                wg += more_w;
 
                 S = se->my_q->tg->shares;
                 s = se->my_q->shares;
@@ -1117,7 +1126,11 @@ static long effective_load(struct task_group *tg, int cpu,
                 a = S*(rw + wl);
                 b = S*rw + s*wg;
 
-                wl = s*(a-b)/D(b);
+                wl = s*(a-b);
+
+                if (likely(b))
+                        wl /= b;
+
                 /*
                  * Assume the group is already running and will
                  * thus already be accounted for in the weight.
@@ -1126,7 +1139,6 @@ static long effective_load(struct task_group *tg, int cpu,
                  * alter the group weight.
                  */
                 wg = 0;
-#undef D
         }
 
         return wl;
@@ -1143,7 +1155,7 @@ static inline unsigned long effective_load(struct task_group *tg, int cpu,
 #endif
 
 static int
-wake_affine(struct rq *rq, struct sched_domain *this_sd, struct rq *this_rq,
+wake_affine(struct sched_domain *this_sd, struct rq *this_rq,
             struct task_struct *p, int prev_cpu, int this_cpu, int sync,
             int idx, unsigned long load, unsigned long this_load,
             unsigned int imbalance)
@@ -1158,6 +1170,10 @@ wake_affine(struct rq *rq, struct sched_domain *this_sd, struct rq *this_rq,
         if (!(this_sd->flags & SD_WAKE_AFFINE) || !sched_feat(AFFINE_WAKEUPS))
                 return 0;
 
+        if (sync && (curr->se.avg_overlap > sysctl_sched_migration_cost ||
+                        p->se.avg_overlap > sysctl_sched_migration_cost))
+                sync = 0;
+
         /*
          * If sync wakeup then subtract the (maximum possible)
          * effect of the currently running task from the load
@@ -1182,17 +1198,14 @@ wake_affine(struct rq *rq, struct sched_domain *this_sd, struct rq *this_rq,
          * a reasonable amount of time then attract this newly
          * woken task:
          */
-        if (sync && balanced) {
-                if (curr->se.avg_overlap < sysctl_sched_migration_cost &&
-                    p->se.avg_overlap < sysctl_sched_migration_cost)
-                        return 1;
-        }
+        if (sync && balanced)
+                return 1;
 
         schedstat_inc(p, se.nr_wakeups_affine_attempts);
         tl_per_task = cpu_avg_load_per_task(this_cpu);
 
-        if ((tl <= load && tl + target_load(prev_cpu, idx) <= tl_per_task) ||
-                        balanced) {
+        if (balanced || (tl <= load && tl + target_load(prev_cpu, idx) <=
+                        tl_per_task)) {
                 /*
                  * This domain has SD_WAKE_AFFINE and
                  * p is cache cold in this domain, and
@@ -1211,16 +1224,17 @@ static int select_task_rq_fair(struct task_struct *p, int sync)
         struct sched_domain *sd, *this_sd = NULL;
         int prev_cpu, this_cpu, new_cpu;
         unsigned long load, this_load;
-        struct rq *rq, *this_rq;
+        struct rq *this_rq;
         unsigned int imbalance;
         int idx;
 
         prev_cpu        = task_cpu(p);
-        rq              = task_rq(p);
         this_cpu        = smp_processor_id();
         this_rq         = cpu_rq(this_cpu);
         new_cpu         = prev_cpu;
 
+        if (prev_cpu == this_cpu)
+                goto out;
         /*
          * 'this_sd' is the first domain that both
          * this_cpu and prev_cpu are present in:
@@ -1248,13 +1262,10 @@ static int select_task_rq_fair(struct task_struct *p, int sync)
         load = source_load(prev_cpu, idx);
         this_load = target_load(this_cpu, idx);
 
-        if (wake_affine(rq, this_sd, this_rq, p, prev_cpu, this_cpu, sync, idx,
+        if (wake_affine(this_sd, this_rq, p, prev_cpu, this_cpu, sync, idx,
                                      load, this_load, imbalance))
                 return this_cpu;
 
-        if (prev_cpu == this_cpu)
-                goto out;
-
         /*
          * Start passive balancing when half the imbalance_pct
          * limit is reached.
@@ -1280,9 +1291,7 @@ static unsigned long wakeup_gran(struct sched_entity *se)
          * More easily preempt - nice tasks, while not making it harder for
          * + nice tasks.
          */
-        if (sched_feat(ASYM_GRAN))
-                gran = calc_delta_asym(sysctl_sched_wakeup_granularity, se);
-        else
+        if (!sched_feat(ASYM_GRAN) || se->load.weight > NICE_0_LOAD)
                 gran = calc_delta_fair(sysctl_sched_wakeup_granularity, se);
 
         return gran;
@@ -1307,7 +1316,7 @@ wakeup_preempt_entity(struct sched_entity *curr, struct sched_entity *se)
 {
         s64 gran, vdiff = curr->vruntime - se->vruntime;
 
-        if (vdiff < 0)
+        if (vdiff <= 0)
                 return -1;
 
         gran = wakeup_gran(curr);
@@ -1317,38 +1326,60 @@ wakeup_preempt_entity(struct sched_entity *curr, struct sched_entity *se)
         return 0;
 }
 
-/* return depth at which a sched entity is present in the hierarchy */
-static inline int depth_se(struct sched_entity *se)
+static void set_last_buddy(struct sched_entity *se)
 {
-        int depth = 0;
-
         for_each_sched_entity(se)
-                depth++;
+                cfs_rq_of(se)->last = se;
+}
 
-        return depth;
+static void set_next_buddy(struct sched_entity *se)
+{
+        for_each_sched_entity(se)
+                cfs_rq_of(se)->next = se;
 }
 
 /*
  * Preempt the current task with a newly woken task if needed:
  */
-static void check_preempt_wakeup(struct rq *rq, struct task_struct *p)
+static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int sync)
 {
         struct task_struct *curr = rq->curr;
-        struct cfs_rq *cfs_rq = task_cfs_rq(curr);
         struct sched_entity *se = &curr->se, *pse = &p->se;
-        int se_depth, pse_depth;
 
         if (unlikely(rt_prio(p->prio))) {
+                struct cfs_rq *cfs_rq = task_cfs_rq(curr);
+
                 update_rq_clock(rq);
                 update_curr(cfs_rq);
                 resched_task(curr);
                 return;
         }
 
+        if (unlikely(p->sched_class != &fair_sched_class))
+                return;
+
         if (unlikely(se == pse))
                 return;
 
-        cfs_rq_of(pse)->next = pse;
+        /*
+         * Only set the backward buddy when the current task is still on the
+         * rq. This can happen when a wakeup gets interleaved with schedule on
+         * the ->pre_schedule() or idle_balance() point, either of which can
+         * drop the rq lock.
+         *
+         * Also, during early boot the idle thread is in the fair class, for
+         * obvious reasons its a bad idea to schedule back to the idle thread.
+         */
+        if (sched_feat(LAST_BUDDY) && likely(se->on_rq && curr != rq->idle))
+                set_last_buddy(se);
+        set_next_buddy(pse);
+
+        /*
+         * We can come here with TIF_NEED_RESCHED already set from new task
+         * wake up path.
+         */
+        if (test_tsk_need_resched(curr))
+                return;
 
         /*
          * Batch tasks do not preempt (their preemption is driven by
@@ -1360,34 +1391,26 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p)
         if (!sched_feat(WAKEUP_PREEMPT))
                 return;
 
-        /*
-         * preemption test can be made between sibling entities who are in the
-         * same cfs_rq i.e who have a common parent. Walk up the hierarchy of
-         * both tasks until we find their ancestors who are siblings of common
-         * parent.
-         */
+        if (sched_feat(WAKEUP_OVERLAP) && (sync ||
+                        (se->avg_overlap < sysctl_sched_migration_cost &&
+                         pse->avg_overlap < sysctl_sched_migration_cost))) {
+                resched_task(curr);
+                return;
+        }
 
-        /* First walk up until both entities are at same depth */
-        se_depth = depth_se(se);
-        pse_depth = depth_se(pse);
+        find_matching_se(&se, &pse);
 
-        while (se_depth > pse_depth) {
-                se_depth--;
-                se = parent_entity(se);
-        }
+        while (se) {
+                BUG_ON(!pse);
 
-        while (pse_depth > se_depth) {
-                pse_depth--;
-                pse = parent_entity(pse);
-        }
+                if (wakeup_preempt_entity(se, pse) == 1) {
+                        resched_task(curr);
+                        break;
+                }
 
-        while (!is_same_group(se, pse)) {
                 se = parent_entity(se);
                 pse = parent_entity(pse);
         }
-
-        if (wakeup_preempt_entity(se, pse) == 1)
-                resched_task(curr);
 }
 
 static struct task_struct *pick_next_task_fair(struct rq *rq)
@@ -1401,6 +1424,7 @@ static struct task_struct *pick_next_task_fair(struct rq *rq)
 
         do {
                 se = pick_next_entity(cfs_rq);
+                set_next_entity(cfs_rq, se);
                 cfs_rq = group_cfs_rq(se);
         } while (cfs_rq);
 
@@ -1445,19 +1469,9 @@ __load_balance_iterator(struct cfs_rq *cfs_rq, struct list_head *next)
         if (next == &cfs_rq->tasks)
                 return NULL;
 
-        /* Skip over entities that are not tasks */
-        do {
-                se = list_entry(next, struct sched_entity, group_node);
-                next = next->next;
-        } while (next != &cfs_rq->tasks && !entity_is_task(se));
-
-        if (next == &cfs_rq->tasks)
-                return NULL;
-
-        cfs_rq->balance_iterator = next;
-
-        if (entity_is_task(se))
-                p = task_of(se);
+        se = list_entry(next, struct sched_entity, group_node);
+        p = task_of(se);
+        cfs_rq->balance_iterator = next->next;
 
         return p;
 }
@@ -1507,7 +1521,7 @@ load_balance_fair(struct rq *this_rq, int this_cpu, struct rq *busiest,
         rcu_read_lock();
         update_h_load(busiest_cpu);
 
-        list_for_each_entry(tg, &task_groups, list) {
+        list_for_each_entry_rcu(tg, &task_groups, list) {
                 struct cfs_rq *busiest_cfs_rq = tg->cfs_rq[busiest_cpu];
                 unsigned long busiest_h_load = busiest_cfs_rq->h_load;
                 unsigned long busiest_weight = busiest_cfs_rq->load.weight;
@@ -1620,10 +1634,10 @@ static void task_new_fair(struct rq *rq, struct task_struct *p)
                  * 'current' within the tree based on its new key value.
                  */
                 swap(curr->vruntime, se->vruntime);
+                resched_task(rq->curr);
         }
 
         enqueue_task_fair(rq, p, 0);
-        resched_task(rq->curr);
 }
 
 /*
@@ -1642,7 +1656,7 @@ static void prio_changed_fair(struct rq *rq, struct task_struct *p,
                 if (p->prio > oldprio)
                         resched_task(rq->curr);
         } else
-                check_preempt_curr(rq, p);
+                check_preempt_curr(rq, p, 0);
 }
 
 /*
@@ -1659,7 +1673,7 @@ static void switched_to_fair(struct rq *rq, struct task_struct *p,
         if (running)
                 resched_task(rq->curr);
         else
-                check_preempt_curr(rq, p);
+                check_preempt_curr(rq, p, 0);
 }
 
 /* Account for a task changing its policy or group.
@@ -1693,9 +1707,6 @@ static const struct sched_class fair_sched_class = {
         .enqueue_task           = enqueue_task_fair,
         .dequeue_task           = dequeue_task_fair,
         .yield_task             = yield_task_fair,
-#ifdef CONFIG_SMP
-        .select_task_rq         = select_task_rq_fair,
-#endif /* CONFIG_SMP */
 
         .check_preempt_curr     = check_preempt_wakeup,
 
@@ -1703,6 +1714,8 @@ static const struct sched_class fair_sched_class = {
         .put_prev_task          = put_prev_task_fair,
 
 #ifdef CONFIG_SMP
+        .select_task_rq         = select_task_rq_fair,
+
         .load_balance           = load_balance_fair,
         .move_one_task          = move_one_task_fair,
 #endif
diff --git a/kernel/sched_features.h b/kernel/sched_features.h
index 9353ca78154e..da5d93b5d2c6 100644
--- a/kernel/sched_features.h
+++ b/kernel/sched_features.h
@@ -5,9 +5,11 @@ SCHED_FEAT(START_DEBIT, 1)
 SCHED_FEAT(AFFINE_WAKEUPS, 1)
 SCHED_FEAT(CACHE_HOT_BUDDY, 1)
 SCHED_FEAT(SYNC_WAKEUPS, 1)
-SCHED_FEAT(HRTICK, 1)
+SCHED_FEAT(HRTICK, 0)
 SCHED_FEAT(DOUBLE_TICK, 0)
 SCHED_FEAT(ASYM_GRAN, 1)
 SCHED_FEAT(LB_BIAS, 1)
 SCHED_FEAT(LB_WAKEUP_UPDATE, 1)
 SCHED_FEAT(ASYM_EFF_LOAD, 1)
+SCHED_FEAT(WAKEUP_OVERLAP, 0)
+SCHED_FEAT(LAST_BUDDY, 1)
diff --git a/kernel/sched_idletask.c b/kernel/sched_idletask.c
index 3a4f92dbbe66..8a21a2e28c13 100644
--- a/kernel/sched_idletask.c
+++ b/kernel/sched_idletask.c
@@ -14,7 +14,7 @@ static int select_task_rq_idle(struct task_struct *p, int sync)
 /*
  * Idle tasks are unconditionally rescheduled:
  */
-static void check_preempt_curr_idle(struct rq *rq, struct task_struct *p)
+static void check_preempt_curr_idle(struct rq *rq, struct task_struct *p, int sync)
 {
         resched_task(rq->idle);
 }
@@ -76,7 +76,7 @@ static void switched_to_idle(struct rq *rq, struct task_struct *p,
         if (running)
                 resched_task(rq->curr);
         else
-                check_preempt_curr(rq, p);
+                check_preempt_curr(rq, p, 0);
 }
 
 static void prio_changed_idle(struct rq *rq, struct task_struct *p,
@@ -93,7 +93,7 @@ static void prio_changed_idle(struct rq *rq, struct task_struct *p,
                 if (p->prio > oldprio)
                         resched_task(rq->curr);
         } else
-                check_preempt_curr(rq, p);
+                check_preempt_curr(rq, p, 0);
 }
 
 /*
@@ -105,9 +105,6 @@ static const struct sched_class idle_sched_class = {
 
         /* dequeue is not valid, we print a debug message there: */
         .dequeue_task           = dequeue_task_idle,
-#ifdef CONFIG_SMP
-        .select_task_rq         = select_task_rq_idle,
-#endif /* CONFIG_SMP */
 
         .check_preempt_curr     = check_preempt_curr_idle,
 
@@ -115,6 +112,8 @@ static const struct sched_class idle_sched_class = {
         .put_prev_task          = put_prev_task_idle,
 
 #ifdef CONFIG_SMP
+        .select_task_rq         = select_task_rq_idle,
+
         .load_balance           = load_balance_idle,
         .move_one_task          = move_one_task_idle,
 #endif
diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c
index 552310798dad..d9ba9d5f99d6 100644
--- a/kernel/sched_rt.c
+++ b/kernel/sched_rt.c
@@ -102,12 +102,12 @@ static void dequeue_rt_entity(struct sched_rt_entity *rt_se);
 
 static void sched_rt_rq_enqueue(struct rt_rq *rt_rq)
 {
+        struct task_struct *curr = rq_of_rt_rq(rt_rq)->curr;
         struct sched_rt_entity *rt_se = rt_rq->rt_se;
 
-        if (rt_se && !on_rt_rq(rt_se) && rt_rq->rt_nr_running) {
-                struct task_struct *curr = rq_of_rt_rq(rt_rq)->curr;
-
-                enqueue_rt_entity(rt_se);
+        if (rt_rq->rt_nr_running) {
+                if (rt_se && !on_rt_rq(rt_se))
+                        enqueue_rt_entity(rt_se);
                 if (rt_rq->highest_prio < curr->prio)
                         resched_task(curr);
         }
@@ -231,6 +231,9 @@ static inline struct rt_bandwidth *sched_rt_bandwidth(struct rt_rq *rt_rq)
 #endif /* CONFIG_RT_GROUP_SCHED */
 
 #ifdef CONFIG_SMP
+/*
+ * We ran out of runtime, see if we can borrow some from our neighbours.
+ */
 static int do_balance_runtime(struct rt_rq *rt_rq)
 {
         struct rt_bandwidth *rt_b = sched_rt_bandwidth(rt_rq);
@@ -250,9 +253,18 @@ static int do_balance_runtime(struct rt_rq *rt_rq)
                         continue;
 
                 spin_lock(&iter->rt_runtime_lock);
+                /*
+                 * Either all rqs have inf runtime and there's nothing to steal
+                 * or __disable_runtime() below sets a specific rq to inf to
+                 * indicate its been disabled and disalow stealing.
+                 */
                 if (iter->rt_runtime == RUNTIME_INF)
                         goto next;
 
+                /*
+                 * From runqueues with spare time, take 1/n part of their
+                 * spare time, but no more than our period.
+                 */
                 diff = iter->rt_runtime - iter->rt_time;
                 if (diff > 0) {
                         diff = div_u64((u64)diff, weight);
@@ -274,6 +286,9 @@ next:
         return more;
 }
 
+/*
+ * Ensure this RQ takes back all the runtime it lend to its neighbours.
+ */
 static void __disable_runtime(struct rq *rq)
 {
         struct root_domain *rd = rq->rd;
@@ -289,17 +304,33 @@ static void __disable_runtime(struct rq *rq)
 
                 spin_lock(&rt_b->rt_runtime_lock);
                 spin_lock(&rt_rq->rt_runtime_lock);
+                /*
+                 * Either we're all inf and nobody needs to borrow, or we're
+                 * already disabled and thus have nothing to do, or we have
+                 * exactly the right amount of runtime to take out.
+                 */
                 if (rt_rq->rt_runtime == RUNTIME_INF ||
                                 rt_rq->rt_runtime == rt_b->rt_runtime)
                         goto balanced;
                 spin_unlock(&rt_rq->rt_runtime_lock);
 
+                /*
+                 * Calculate the difference between what we started out with
+                 * and what we current have, that's the amount of runtime
+                 * we lend and now have to reclaim.
+                 */
                 want = rt_b->rt_runtime - rt_rq->rt_runtime;
 
+                /*
+                 * Greedy reclaim, take back as much as we can.
+                 */
                 for_each_cpu_mask(i, rd->span) {
                         struct rt_rq *iter = sched_rt_period_rt_rq(rt_b, i);
                         s64 diff;
 
+                        /*
+                         * Can't reclaim from ourselves or disabled runqueues.
+                         */
                         if (iter == rt_rq || iter->rt_runtime == RUNTIME_INF)
                                 continue;
 
@@ -319,8 +350,16 @@ static void __disable_runtime(struct rq *rq)
                 }
 
                 spin_lock(&rt_rq->rt_runtime_lock);
+                /*
+                 * We cannot be left wanting - that would mean some runtime
+                 * leaked out of the system.
+                 */
                 BUG_ON(want);
 balanced:
+                /*
+                 * Disable all the borrow logic by pretending we have inf
+                 * runtime - in which case borrowing doesn't make sense.
+                 */
                 rt_rq->rt_runtime = RUNTIME_INF;
                 spin_unlock(&rt_rq->rt_runtime_lock);
                 spin_unlock(&rt_b->rt_runtime_lock);
@@ -343,6 +382,9 @@ static void __enable_runtime(struct rq *rq)
         if (unlikely(!scheduler_running))
                 return;
 
+        /*
+         * Reset each runqueue's bandwidth settings
+         */
         for_each_leaf_rt_rq(rt_rq, rq) {
                 struct rt_bandwidth *rt_b = sched_rt_bandwidth(rt_rq);
 
@@ -350,6 +392,7 @@ static void __enable_runtime(struct rq *rq)
                 spin_lock(&rt_rq->rt_runtime_lock);
                 rt_rq->rt_runtime = rt_b->rt_runtime;
                 rt_rq->rt_time = 0;
+                rt_rq->rt_throttled = 0;
                 spin_unlock(&rt_rq->rt_runtime_lock);
                 spin_unlock(&rt_b->rt_runtime_lock);
         }
@@ -388,7 +431,7 @@ static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun)
         int i, idle = 1;
         cpumask_t span;
 
-        if (rt_b->rt_runtime == RUNTIME_INF)
+        if (!rt_bandwidth_enabled() || rt_b->rt_runtime == RUNTIME_INF)
                 return 1;
 
         span = sched_rt_period_mask();
@@ -483,9 +526,14 @@ static void update_curr_rt(struct rq *rq)
         schedstat_set(curr->se.exec_max, max(curr->se.exec_max, delta_exec));
 
         curr->se.sum_exec_runtime += delta_exec;
+        account_group_exec_runtime(curr, delta_exec);
+
         curr->se.exec_start = rq->clock;
         cpuacct_charge(curr, delta_exec);
 
+        if (!rt_bandwidth_enabled())
+                return;
+
         for_each_sched_rt_entity(rt_se) {
                 rt_rq = rt_rq_of_se(rt_se);
 
@@ -783,7 +831,7 @@ static void check_preempt_equal_prio(struct rq *rq, struct task_struct *p)
 /*
  * Preempt the current task with a newly woken task if needed:
  */
-static void check_preempt_curr_rt(struct rq *rq, struct task_struct *p)
+static void check_preempt_curr_rt(struct rq *rq, struct task_struct *p, int sync)
 {
         if (p->prio < rq->curr->prio) {
                 resched_task(rq->curr);
@@ -1412,7 +1460,7 @@ static void watchdog(struct rq *rq, struct task_struct *p)
                 p->rt.timeout++;
                 next = DIV_ROUND_UP(min(soft, hard), USEC_PER_SEC/HZ);
                 if (p->rt.timeout > next)
-                        p->it_sched_expires = p->se.sum_exec_runtime;
+                        p->cputime_expires.sched_exp = p->se.sum_exec_runtime;
         }
 }
 
@@ -1456,9 +1504,6 @@ static const struct sched_class rt_sched_class = {
         .enqueue_task           = enqueue_task_rt,
         .dequeue_task           = dequeue_task_rt,
         .yield_task             = yield_task_rt,
-#ifdef CONFIG_SMP
-        .select_task_rq         = select_task_rq_rt,
-#endif /* CONFIG_SMP */
 
         .check_preempt_curr     = check_preempt_curr_rt,
 
@@ -1466,6 +1511,8 @@ static const struct sched_class rt_sched_class = {
         .put_prev_task          = put_prev_task_rt,
 
 #ifdef CONFIG_SMP
+        .select_task_rq         = select_task_rq_rt,
+
         .load_balance           = load_balance_rt,
         .move_one_task          = move_one_task_rt,
         .set_cpus_allowed       = set_cpus_allowed_rt,
diff --git a/kernel/sched_stats.h b/kernel/sched_stats.h
index 8385d43987e2..7dbf72a2b02c 100644
--- a/kernel/sched_stats.h
+++ b/kernel/sched_stats.h
@@ -9,7 +9,7 @@
 static int show_schedstat(struct seq_file *seq, void *v)
 {
         int cpu;
-        int mask_len = NR_CPUS/32 * 9;
+        int mask_len = DIV_ROUND_UP(NR_CPUS, 32) * 9;
         char *mask_str = kmalloc(mask_len, GFP_KERNEL);
 
         if (mask_str == NULL)
@@ -90,13 +90,20 @@ static int schedstat_open(struct inode *inode, struct file *file)
         return res;
 }
 
-const struct file_operations proc_schedstat_operations = {
+static const struct file_operations proc_schedstat_operations = {
         .open    = schedstat_open,
         .read    = seq_read,
         .llseek  = seq_lseek,
         .release = single_release,
 };
 
+static int __init proc_schedstat_init(void)
+{
+        proc_create("schedstat", 0, NULL, &proc_schedstat_operations);
+        return 0;
+}
+module_init(proc_schedstat_init);
+
 /*
  * Expects runqueue lock to be held for atomicity of update
  */
@@ -270,3 +277,96 @@ sched_info_switch(struct task_struct *prev, struct task_struct *next)
 #define sched_info_switch(t, next)              do { } while (0)
 #endif /* CONFIG_SCHEDSTATS || CONFIG_TASK_DELAY_ACCT */
 
+/*
+ * The following are functions that support scheduler-internal time accounting.
+ * These functions are generally called at the timer tick.  None of this depends
+ * on CONFIG_SCHEDSTATS.
+ */
+
+/**
+ * account_group_user_time - Maintain utime for a thread group.
+ *
+ * @tsk:        Pointer to task structure.
+ * @cputime:    Time value by which to increment the utime field of the
+ *              thread_group_cputime structure.
+ *
+ * If thread group time is being maintained, get the structure for the
+ * running CPU and update the utime field there.
+ */
+static inline void account_group_user_time(struct task_struct *tsk,
+                                           cputime_t cputime)
+{
+        struct signal_struct *sig;
+
+        /* tsk == current, ensure it is safe to use ->signal */
+        if (unlikely(tsk->exit_state))
+                return;
+
+        sig = tsk->signal;
+        if (sig->cputime.totals) {
+                struct task_cputime *times;
+
+                times = per_cpu_ptr(sig->cputime.totals, get_cpu());
+                times->utime = cputime_add(times->utime, cputime);
+                put_cpu_no_resched();
+        }
+}
+
+/**
+ * account_group_system_time - Maintain stime for a thread group.
+ *
+ * @tsk:        Pointer to task structure.
+ * @cputime:    Time value by which to increment the stime field of the
+ *              thread_group_cputime structure.
+ *
+ * If thread group time is being maintained, get the structure for the
+ * running CPU and update the stime field there.
+ */
+static inline void account_group_system_time(struct task_struct *tsk,
+                                             cputime_t cputime)
+{
+        struct signal_struct *sig;
+
+        /* tsk == current, ensure it is safe to use ->signal */
+        if (unlikely(tsk->exit_state))
+                return;
+
+        sig = tsk->signal;
+        if (sig->cputime.totals) {
+                struct task_cputime *times;
+
+                times = per_cpu_ptr(sig->cputime.totals, get_cpu());
+                times->stime = cputime_add(times->stime, cputime);
+                put_cpu_no_resched();
+        }
+}
+
+/**
+ * account_group_exec_runtime - Maintain exec runtime for a thread group.
+ *
+ * @tsk:        Pointer to task structure.
+ * @ns:         Time value by which to increment the sum_exec_runtime field
+ *              of the thread_group_cputime structure.
+ *
+ * If thread group time is being maintained, get the structure for the
+ * running CPU and update the sum_exec_runtime field there.
+ */
+static inline void account_group_exec_runtime(struct task_struct *tsk,
+                                              unsigned long long ns)
+{
+        struct signal_struct *sig;
+
+        sig = tsk->signal;
+        /* see __exit_signal()->task_rq_unlock_wait() */
+        barrier();
+        if (unlikely(!sig))
+                return;
+
+        if (sig->cputime.totals) {
+                struct task_cputime *times;
+
+                times = per_cpu_ptr(sig->cputime.totals, get_cpu());
+                times->sum_exec_runtime += ns;
+                put_cpu_no_resched();
+        }
+}
diff --git a/kernel/signal.c b/kernel/signal.c
index e661b01d340f..4530fc654455 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -27,6 +27,7 @@
 #include <linux/freezer.h>
 #include <linux/pid_namespace.h>
 #include <linux/nsproxy.h>
+#include <trace/sched.h>
 
 #include <asm/param.h>
 #include <asm/uaccess.h>
@@ -803,6 +804,8 @@ static int send_signal(int sig, struct siginfo *info, struct task_struct *t,
         struct sigpending *pending;
         struct sigqueue *q;
 
+        trace_sched_signal_send(sig, t);
+
         assert_spin_locked(&t->sighand->siglock);
         if (!prepare_signal(sig, t))
                 return 0;
@@ -1141,7 +1144,8 @@ static int kill_something_info(int sig, struct siginfo *info, pid_t pid)
                 struct task_struct * p;
 
                 for_each_process(p) {
-                        if (p->pid > 1 && !same_thread_group(p, current)) {
+                        if (task_pid_vnr(p) > 1 &&
+                                        !same_thread_group(p, current)) {
                                 int err = group_send_sig_info(sig, info, p);
                                 ++count;
                                 if (err != -EPERM)
@@ -1338,6 +1342,7 @@ int do_notify_parent(struct task_struct *tsk, int sig)
         struct siginfo info;
         unsigned long flags;
         struct sighand_struct *psig;
+        struct task_cputime cputime;
         int ret = sig;
 
         BUG_ON(sig == -1);
@@ -1368,10 +1373,9 @@ int do_notify_parent(struct task_struct *tsk, int sig)
 
         info.si_uid = tsk->uid;
 
-        info.si_utime = cputime_to_clock_t(cputime_add(tsk->utime,
-                                                       tsk->signal->utime));
-        info.si_stime = cputime_to_clock_t(cputime_add(tsk->stime,
-                                                       tsk->signal->stime));
+        thread_group_cputime(tsk, &cputime);
+        info.si_utime = cputime_to_jiffies(cputime.utime);
+        info.si_stime = cputime_to_jiffies(cputime.stime);
 
         info.si_status = tsk->exit_code & 0x7f;
         if (tsk->exit_code & 0x80)
diff --git a/kernel/smp.c b/kernel/smp.c
index f362a8553777..75c8dde58c55 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -51,10 +51,6 @@ static void csd_flag_wait(struct call_single_data *data)
 {
         /* Wait for response */
         do {
-                /*
-                 * We need to see the flags store in the IPI handler
-                 */
-                smp_mb();
                 if (!(data->flags & CSD_FLAG_WAIT))
                         break;
                 cpu_relax();
@@ -76,6 +72,11 @@ static void generic_exec_single(int cpu, struct call_single_data *data)
         list_add_tail(&data->list, &dst->list);
         spin_unlock_irqrestore(&dst->lock, flags);
 
+        /*
+         * Make the list addition visible before sending the ipi.
+         */
+        smp_mb();
+
         if (ipi)
                 arch_send_call_function_single_ipi(cpu);
 
@@ -157,7 +158,7 @@ void generic_smp_call_function_single_interrupt(void)
          * Need to see other stores to list head for checking whether
          * list is empty without holding q->lock
          */
-        smp_mb();
+        smp_read_barrier_depends();
         while (!list_empty(&q->list)) {
                 unsigned int data_flags;
 
@@ -191,7 +192,7 @@ void generic_smp_call_function_single_interrupt(void)
                 /*
                  * See comment on outer loop
                  */
-                smp_mb();
+                smp_read_barrier_depends();
         }
 }
 
@@ -370,6 +371,11 @@ int smp_call_function_mask(cpumask_t mask, void (*func)(void *), void *info,
         list_add_tail_rcu(&data->csd.list, &call_function_queue);
         spin_unlock_irqrestore(&call_function_lock, flags);
 
+        /*
+         * Make the list addition visible before sending the ipi.
+         */
+        smp_mb();
+
         /* Send a message to all CPUs in the map */
         arch_send_call_function_ipi(mask);
 
diff --git a/kernel/softirq.c b/kernel/softirq.c
index c506f266a6b9..e7c69a720d69 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -6,6 +6,8 @@
  *      Distribute under GPLv2.
  *
  *      Rewritten. Old one was good in 2.2, but in 2.3 it was immoral. --ANK (990903)
+ *
+ *      Remote softirq infrastructure is by Jens Axboe.
  */
 
 #include <linux/module.h>
@@ -46,7 +48,7 @@ irq_cpustat_t irq_stat[NR_CPUS] ____cacheline_aligned;
 EXPORT_SYMBOL(irq_stat);
 #endif
 
-static struct softirq_action softirq_vec[32] __cacheline_aligned_in_smp;
+static struct softirq_action softirq_vec[NR_SOFTIRQS] __cacheline_aligned_in_smp;
 
 static DEFINE_PER_CPU(struct task_struct *, ksoftirqd);
 
@@ -205,7 +207,18 @@ restart:
 
         do {
                 if (pending & 1) {
+                        int prev_count = preempt_count();
+
                         h->action(h);
+
+                        if (unlikely(prev_count != preempt_count())) {
+                                printk(KERN_ERR "huh, entered softirq %td %p"
+                                       "with preempt_count %08x,"
+                                       " exited with %08x?\n", h - softirq_vec,
+                                       h->action, prev_count, preempt_count());
+                                preempt_count() = prev_count;
+                        }
+
                         rcu_bh_qsctr_inc(cpu);
                 }
                 h++;
@@ -254,16 +267,13 @@ asmlinkage void do_softirq(void)
  */
 void irq_enter(void)
 {
-#ifdef CONFIG_NO_HZ
         int cpu = smp_processor_id();
-        if (idle_cpu(cpu) && !in_interrupt())
-                tick_nohz_stop_idle(cpu);
-#endif
-        __irq_enter();
-#ifdef CONFIG_NO_HZ
-        if (idle_cpu(cpu))
-                tick_nohz_update_jiffies();
-#endif
+
+        if (idle_cpu(cpu) && !in_interrupt()) {
+                __irq_enter();
+                tick_check_idle(cpu);
+        } else
+                __irq_enter();
 }
 
 #ifdef __ARCH_IRQ_EXIT_IRQS_DISABLED
@@ -463,17 +473,144 @@ void tasklet_kill(struct tasklet_struct *t)
 
 EXPORT_SYMBOL(tasklet_kill);
 
+DEFINE_PER_CPU(struct list_head [NR_SOFTIRQS], softirq_work_list);
+EXPORT_PER_CPU_SYMBOL(softirq_work_list);
+
+static void __local_trigger(struct call_single_data *cp, int softirq)
+{
+        struct list_head *head = &__get_cpu_var(softirq_work_list[softirq]);
+
+        list_add_tail(&cp->list, head);
+
+        /* Trigger the softirq only if the list was previously empty.  */
+        if (head->next == &cp->list)
+                raise_softirq_irqoff(softirq);
+}
+
+#ifdef CONFIG_USE_GENERIC_SMP_HELPERS
+static void remote_softirq_receive(void *data)
+{
+        struct call_single_data *cp = data;
+        unsigned long flags;
+        int softirq;
+
+        softirq = cp->priv;
+
+        local_irq_save(flags);
+        __local_trigger(cp, softirq);
+        local_irq_restore(flags);
+}
+
+static int __try_remote_softirq(struct call_single_data *cp, int cpu, int softirq)
+{
+        if (cpu_online(cpu)) {
+                cp->func = remote_softirq_receive;
+                cp->info = cp;
+                cp->flags = 0;
+                cp->priv = softirq;
+
+                __smp_call_function_single(cpu, cp);
+                return 0;
+        }
+        return 1;
+}
+#else /* CONFIG_USE_GENERIC_SMP_HELPERS */
+static int __try_remote_softirq(struct call_single_data *cp, int cpu, int softirq)
+{
+        return 1;
+}
+#endif
+
+/**
+ * __send_remote_softirq - try to schedule softirq work on a remote cpu
+ * @cp: private SMP call function data area
+ * @cpu: the remote cpu
+ * @this_cpu: the currently executing cpu
+ * @softirq: the softirq for the work
+ *
+ * Attempt to schedule softirq work on a remote cpu.  If this cannot be
+ * done, the work is instead queued up on the local cpu.
+ *
+ * Interrupts must be disabled.
+ */
+void __send_remote_softirq(struct call_single_data *cp, int cpu, int this_cpu, int softirq)
+{
+        if (cpu == this_cpu || __try_remote_softirq(cp, cpu, softirq))
+                __local_trigger(cp, softirq);
+}
+EXPORT_SYMBOL(__send_remote_softirq);
+
+/**
+ * send_remote_softirq - try to schedule softirq work on a remote cpu
+ * @cp: private SMP call function data area
+ * @cpu: the remote cpu
+ * @softirq: the softirq for the work
+ *
+ * Like __send_remote_softirq except that disabling interrupts and
+ * computing the current cpu is done for the caller.
+ */
+void send_remote_softirq(struct call_single_data *cp, int cpu, int softirq)
+{
+        unsigned long flags;
+        int this_cpu;
+
+        local_irq_save(flags);
+        this_cpu = smp_processor_id();
+        __send_remote_softirq(cp, cpu, this_cpu, softirq);
+        local_irq_restore(flags);
+}
+EXPORT_SYMBOL(send_remote_softirq);
+
+static int __cpuinit remote_softirq_cpu_notify(struct notifier_block *self,
+                                               unsigned long action, void *hcpu)
+{
+        /*
+         * If a CPU goes away, splice its entries to the current CPU
+         * and trigger a run of the softirq
+         */
+        if (action == CPU_DEAD || action == CPU_DEAD_FROZEN) {
+                int cpu = (unsigned long) hcpu;
+                int i;
+
+                local_irq_disable();
+                for (i = 0; i < NR_SOFTIRQS; i++) {
+                        struct list_head *head = &per_cpu(softirq_work_list[i], cpu);
+                        struct list_head *local_head;
+
+                        if (list_empty(head))
+                                continue;
+
+                        local_head = &__get_cpu_var(softirq_work_list[i]);
+                        list_splice_init(head, local_head);
+                        raise_softirq_irqoff(i);
+                }
+                local_irq_enable();
+        }
+
+        return NOTIFY_OK;
+}
+
+static struct notifier_block __cpuinitdata remote_softirq_cpu_notifier = {
+        .notifier_call  = remote_softirq_cpu_notify,
+};
+
 void __init softirq_init(void)
 {
         int cpu;
 
         for_each_possible_cpu(cpu) {
+                int i;
+
                 per_cpu(tasklet_vec, cpu).tail =
                         &per_cpu(tasklet_vec, cpu).head;
                 per_cpu(tasklet_hi_vec, cpu).tail =
                         &per_cpu(tasklet_hi_vec, cpu).head;
+                for (i = 0; i < NR_SOFTIRQS; i++)
+                        INIT_LIST_HEAD(&per_cpu(softirq_work_list[i], cpu));
         }
 
+        register_hotcpu_notifier(&remote_softirq_cpu_notifier);
+
         open_softirq(TASKLET_SOFTIRQ, tasklet_action);
         open_softirq(HI_SOFTIRQ, tasklet_hi_action);
 }
diff --git a/kernel/softlockup.c b/kernel/softlockup.c
index b9a528f22736..884e6cd2769c 100644
--- a/kernel/softlockup.c
+++ b/kernel/softlockup.c
@@ -226,7 +226,7 @@ static void check_hung_uninterruptible_tasks(int this_cpu)
          * If the system crashed already then all bets are off,
          * do not report extra hung tasks:
          */
-        if ((tainted & TAINT_DIE) || did_panic)
+        if (test_taint(TAINT_DIE) || did_panic)
                 return;
 
         read_lock(&tasklist_lock);
diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c
index af3c7cea258b..24e8ceacc388 100644
--- a/kernel/stop_machine.c
+++ b/kernel/stop_machine.c
@@ -37,9 +37,13 @@ struct stop_machine_data {
 /* Like num_online_cpus(), but hotplug cpu uses us, so we need this. */
 static unsigned int num_threads;
 static atomic_t thread_ack;
-static struct completion finished;
 static DEFINE_MUTEX(lock);
 
+static struct workqueue_struct *stop_machine_wq;
+static struct stop_machine_data active, idle;
+static const cpumask_t *active_cpus;
+static void *stop_machine_work;
+
 static void set_state(enum stopmachine_state newstate)
 {
         /* Reset ack counter. */
@@ -51,21 +55,26 @@ static void set_state(enum stopmachine_state newstate)
 /* Last one to ack a state moves to the next state. */
 static void ack_state(void)
 {
-        if (atomic_dec_and_test(&thread_ack)) {
-                /* If we're the last one to ack the EXIT, we're finished. */
-                if (state == STOPMACHINE_EXIT)
-                        complete(&finished);
-                else
-                        set_state(state + 1);
-        }
+        if (atomic_dec_and_test(&thread_ack))
+                set_state(state + 1);
 }
 
-/* This is the actual thread which stops the CPU.  It exits by itself rather
- * than waiting for kthread_stop(), because it's easier for hotplug CPU. */
-static int stop_cpu(struct stop_machine_data *smdata)
+/* This is the actual function which stops the CPU. It runs
+ * in the context of a dedicated stopmachine workqueue. */
+static void stop_cpu(struct work_struct *unused)
 {
         enum stopmachine_state curstate = STOPMACHINE_NONE;
-
+        struct stop_machine_data *smdata = &idle;
+        int cpu = smp_processor_id();
+        int err;
+
+        if (!active_cpus) {
+                if (cpu == first_cpu(cpu_online_map))
+                        smdata = &active;
+        } else {
+                if (cpu_isset(cpu, *active_cpus))
+                        smdata = &active;
+        }
         /* Simple state machine */
         do {
                 /* Chill out and ensure we re-read stopmachine_state. */
@@ -78,9 +87,11 @@ static int stop_cpu(struct stop_machine_data *smdata)
                                 hard_irq_disable();
                                 break;
                         case STOPMACHINE_RUN:
-                                /* |= allows error detection if functions on
-                                 * multiple CPUs. */
-                                smdata->fnret |= smdata->fn(smdata->data);
+                                /* On multiple CPUs only a single error code
+                                 * is needed to tell that something failed. */
+                                err = smdata->fn(smdata->data);
+                                if (err)
+                                        smdata->fnret = err;
                                 break;
                         default:
                                 break;
@@ -90,7 +101,6 @@ static int stop_cpu(struct stop_machine_data *smdata)
         } while (curstate != STOPMACHINE_EXIT);
 
         local_irq_enable();
-        do_exit(0);
 }
 
 /* Callback for CPUs which aren't supposed to do anything. */
@@ -101,78 +111,35 @@ static int chill(void *unused)
 
 int __stop_machine(int (*fn)(void *), void *data, const cpumask_t *cpus)
 {
-        int i, err;
-        struct stop_machine_data active, idle;
-        struct task_struct **threads;
+        struct work_struct *sm_work;
+        int i, ret;
 
+        /* Set up initial state. */
+        mutex_lock(&lock);
+        num_threads = num_online_cpus();
+        active_cpus = cpus;
         active.fn = fn;
         active.data = data;
         active.fnret = 0;
         idle.fn = chill;
         idle.data = NULL;
 
-        /* This could be too big for stack on large machines. */
-        threads = kcalloc(NR_CPUS, sizeof(threads[0]), GFP_KERNEL);
-        if (!threads)
-                return -ENOMEM;
-
-        /* Set up initial state. */
-        mutex_lock(&lock);
-        init_completion(&finished);
-        num_threads = num_online_cpus();
         set_state(STOPMACHINE_PREPARE);
 
-        for_each_online_cpu(i) {
-                struct stop_machine_data *smdata = &idle;
-                struct sched_param param = { .sched_priority = MAX_RT_PRIO-1 };
-
-                if (!cpus) {
-                        if (i == first_cpu(cpu_online_map))
-                                smdata = &active;
-                } else {
-                        if (cpu_isset(i, *cpus))
-                                smdata = &active;
-                }
-
-                threads[i] = kthread_create((void *)stop_cpu, smdata, "kstop%u",
-                                            i);
-                if (IS_ERR(threads[i])) {
-                        err = PTR_ERR(threads[i]);
-                        threads[i] = NULL;
-                        goto kill_threads;
-                }
-
-                /* Place it onto correct cpu. */
-                kthread_bind(threads[i], i);
-
-                /* Make it highest prio. */
-                if (sched_setscheduler_nocheck(threads[i], SCHED_FIFO, &param))
-                        BUG();
-        }
-
-        /* We've created all the threads.  Wake them all: hold this CPU so one
+        /* Schedule the stop_cpu work on all cpus: hold this CPU so one
          * doesn't hit this CPU until we're ready. */
         get_cpu();
-        for_each_online_cpu(i)
-                wake_up_process(threads[i]);
-
+        for_each_online_cpu(i) {
+                sm_work = percpu_ptr(stop_machine_work, i);
+                INIT_WORK(sm_work, stop_cpu);
+                queue_work_on(i, stop_machine_wq, sm_work);
+        }
         /* This will release the thread on our CPU. */
         put_cpu();
-        wait_for_completion(&finished);
-        mutex_unlock(&lock);
-
-        kfree(threads);
-
-        return active.fnret;
-
-kill_threads:
-        for_each_online_cpu(i)
-                if (threads[i])
-                        kthread_stop(threads[i]);
+        flush_workqueue(stop_machine_wq);
+        ret = active.fnret;
         mutex_unlock(&lock);
-
-        kfree(threads);
-        return err;
+        return ret;
 }
 
 int stop_machine(int (*fn)(void *), void *data, const cpumask_t *cpus)
@@ -187,3 +154,11 @@ int stop_machine(int (*fn)(void *), void *data, const cpumask_t *cpus)
         return ret;
 }
 EXPORT_SYMBOL_GPL(stop_machine);
+
+static int __init stop_machine_init(void)
+{
+        stop_machine_wq = create_rt_workqueue("kstop");
+        stop_machine_work = alloc_percpu(struct work_struct);
+        return 0;
+}
+core_initcall(stop_machine_init);
diff --git a/kernel/sys.c b/kernel/sys.c
index 038a7bc0901d..31deba8f7d16 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -853,38 +853,28 @@ asmlinkage long sys_setfsgid(gid_t gid)
         return old_fsgid;
 }
 
+void do_sys_times(struct tms *tms)
+{
+        struct task_cputime cputime;
+        cputime_t cutime, cstime;
+
+        spin_lock_irq(&current->sighand->siglock);
+        thread_group_cputime(current, &cputime);
+        cutime = current->signal->cutime;
+        cstime = current->signal->cstime;
+        spin_unlock_irq(&current->sighand->siglock);
+        tms->tms_utime = cputime_to_clock_t(cputime.utime);
+        tms->tms_stime = cputime_to_clock_t(cputime.stime);
+        tms->tms_cutime = cputime_to_clock_t(cutime);
+        tms->tms_cstime = cputime_to_clock_t(cstime);
+}
+
 asmlinkage long sys_times(struct tms __user * tbuf)
 {
-        /*
-         *      In the SMP world we might just be unlucky and have one of
-         *      the times increment as we use it. Since the value is an
-         *      atomically safe type this is just fine. Conceptually its
-         *      as if the syscall took an instant longer to occur.
-         */
         if (tbuf) {
                 struct tms tmp;
-                struct task_struct *tsk = current;
-                struct task_struct *t;
-                cputime_t utime, stime, cutime, cstime;
-
-                spin_lock_irq(&tsk->sighand->siglock);
-                utime = tsk->signal->utime;
-                stime = tsk->signal->stime;
-                t = tsk;
-                do {
-                        utime = cputime_add(utime, t->utime);
-                        stime = cputime_add(stime, t->stime);
-                        t = next_thread(t);
-                } while (t != tsk);
-
-                cutime = tsk->signal->cutime;
-                cstime = tsk->signal->cstime;
-                spin_unlock_irq(&tsk->sighand->siglock);
-
-                tmp.tms_utime = cputime_to_clock_t(utime);
-                tmp.tms_stime = cputime_to_clock_t(stime);
-                tmp.tms_cutime = cputime_to_clock_t(cutime);
-                tmp.tms_cstime = cputime_to_clock_t(cstime);
+
+                do_sys_times(&tmp);
                 if (copy_to_user(tbuf, &tmp, sizeof(struct tms)))
                         return -EFAULT;
         }
@@ -1060,9 +1050,7 @@ asmlinkage long sys_setsid(void)
         group_leader->signal->leader = 1;
         __set_special_pids(sid);
 
-        spin_lock(&group_leader->sighand->siglock);
-        group_leader->signal->tty = NULL;
-        spin_unlock(&group_leader->sighand->siglock);
+        proc_clear_tty(group_leader);
 
         err = session;
 out:
@@ -1351,8 +1339,10 @@ asmlinkage long sys_sethostname(char __user *name, int len)
         down_write(&uts_sem);
         errno = -EFAULT;
         if (!copy_from_user(tmp, name, len)) {
-                memcpy(utsname()->nodename, tmp, len);
-                utsname()->nodename[len] = 0;
+                struct new_utsname *u = utsname();
+
+                memcpy(u->nodename, tmp, len);
+                memset(u->nodename + len, 0, sizeof(u->nodename) - len);
                 errno = 0;
         }
         up_write(&uts_sem);
@@ -1364,15 +1354,17 @@ asmlinkage long sys_sethostname(char __user *name, int len)
 asmlinkage long sys_gethostname(char __user *name, int len)
 {
         int i, errno;
+        struct new_utsname *u;
 
         if (len < 0)
                 return -EINVAL;
         down_read(&uts_sem);
-        i = 1 + strlen(utsname()->nodename);
+        u = utsname();
+        i = 1 + strlen(u->nodename);
         if (i > len)
                 i = len;
         errno = 0;
-        if (copy_to_user(name, utsname()->nodename, i))
+        if (copy_to_user(name, u->nodename, i))
                 errno = -EFAULT;
         up_read(&uts_sem);
         return errno;
@@ -1397,8 +1389,10 @@ asmlinkage long sys_setdomainname(char __user *name, int len)
         down_write(&uts_sem);
         errno = -EFAULT;
         if (!copy_from_user(tmp, name, len)) {
-                memcpy(utsname()->domainname, tmp, len);
-                utsname()->domainname[len] = 0;
+                struct new_utsname *u = utsname();
+
+                memcpy(u->domainname, tmp, len);
+                memset(u->domainname + len, 0, sizeof(u->domainname) - len);
                 errno = 0;
         }
         up_write(&uts_sem);
@@ -1445,21 +1439,28 @@ asmlinkage long sys_old_getrlimit(unsigned int resource, struct rlimit __user *r
 asmlinkage long sys_setrlimit(unsigned int resource, struct rlimit __user *rlim)
 {
         struct rlimit new_rlim, *old_rlim;
-        unsigned long it_prof_secs;
         int retval;
 
         if (resource >= RLIM_NLIMITS)
                 return -EINVAL;
         if (copy_from_user(&new_rlim, rlim, sizeof(*rlim)))
                 return -EFAULT;
-        if (new_rlim.rlim_cur > new_rlim.rlim_max)
-                return -EINVAL;
         old_rlim = current->signal->rlim + resource;
         if ((new_rlim.rlim_max > old_rlim->rlim_max) &&
             !capable(CAP_SYS_RESOURCE))
                 return -EPERM;
-        if (resource == RLIMIT_NOFILE && new_rlim.rlim_max > sysctl_nr_open)
-                return -EPERM;
+
+        if (resource == RLIMIT_NOFILE) {
+                if (new_rlim.rlim_max == RLIM_INFINITY)
+                        new_rlim.rlim_max = sysctl_nr_open;
+                if (new_rlim.rlim_cur == RLIM_INFINITY)
+                        new_rlim.rlim_cur = sysctl_nr_open;
+                if (new_rlim.rlim_max > sysctl_nr_open)
+                        return -EPERM;
+        }
+
+        if (new_rlim.rlim_cur > new_rlim.rlim_max)
+                return -EINVAL;
 
         retval = security_task_setrlimit(resource, &new_rlim);
         if (retval)
@@ -1491,18 +1492,7 @@ asmlinkage long sys_setrlimit(unsigned int resource, struct rlimit __user *rlim)
         if (new_rlim.rlim_cur == RLIM_INFINITY)
                 goto out;
 
-        it_prof_secs = cputime_to_secs(current->signal->it_prof_expires);
-        if (it_prof_secs == 0 || new_rlim.rlim_cur <= it_prof_secs) {
-                unsigned long rlim_cur = new_rlim.rlim_cur;
-                cputime_t cputime;
-
-                cputime = secs_to_cputime(rlim_cur);
-                read_lock(&tasklist_lock);
-                spin_lock_irq(&current->sighand->siglock);
-                set_process_cpu_timer(current, CPUCLOCK_PROF, &cputime, NULL);
-                spin_unlock_irq(&current->sighand->siglock);
-                read_unlock(&tasklist_lock);
-        }
+        update_rlimit_cpu(new_rlim.rlim_cur);
 out:
         return 0;
 }
@@ -1540,11 +1530,8 @@ out:
  *
  */
 
-static void accumulate_thread_rusage(struct task_struct *t, struct rusage *r,
-                                     cputime_t *utimep, cputime_t *stimep)
+static void accumulate_thread_rusage(struct task_struct *t, struct rusage *r)
 {
-        *utimep = cputime_add(*utimep, t->utime);
-        *stimep = cputime_add(*stimep, t->stime);
         r->ru_nvcsw += t->nvcsw;
         r->ru_nivcsw += t->nivcsw;
         r->ru_minflt += t->min_flt;
@@ -1558,12 +1545,13 @@ static void k_getrusage(struct task_struct *p, int who, struct rusage *r)
         struct task_struct *t;
         unsigned long flags;
         cputime_t utime, stime;
+        struct task_cputime cputime;
 
         memset((char *) r, 0, sizeof *r);
         utime = stime = cputime_zero;
 
         if (who == RUSAGE_THREAD) {
-                accumulate_thread_rusage(p, r, &utime, &stime);
+                accumulate_thread_rusage(p, r);
                 goto out;
         }
 
@@ -1586,8 +1574,9 @@ static void k_getrusage(struct task_struct *p, int who, struct rusage *r)
                                 break;
 
                 case RUSAGE_SELF:
-                        utime = cputime_add(utime, p->signal->utime);
-                        stime = cputime_add(stime, p->signal->stime);
+                        thread_group_cputime(p, &cputime);
+                        utime = cputime_add(utime, cputime.utime);
+                        stime = cputime_add(stime, cputime.stime);
                         r->ru_nvcsw += p->signal->nvcsw;
                         r->ru_nivcsw += p->signal->nivcsw;
                         r->ru_minflt += p->signal->min_flt;
@@ -1596,7 +1585,7 @@ static void k_getrusage(struct task_struct *p, int who, struct rusage *r)
                         r->ru_oublock += p->signal->oublock;
                         t = p;
                         do {
-                                accumulate_thread_rusage(t, r, &utime, &stime);
+                                accumulate_thread_rusage(t, r);
                                 t = next_thread(t);
                         } while (t != p);
                         break;
@@ -1727,6 +1716,16 @@ asmlinkage long sys_prctl(int option, unsigned long arg2, unsigned long arg3,
                 case PR_SET_TSC:
                         error = SET_TSC_CTL(arg2);
                         break;
+                case PR_GET_TIMERSLACK:
+                        error = current->timer_slack_ns;
+                        break;
+                case PR_SET_TIMERSLACK:
+                        if (arg2 <= 0)
+                                current->timer_slack_ns =
+                                        current->default_timer_slack_ns;
+                        else
+                                current->timer_slack_ns = arg2;
+                        break;
                 default:
                         error = -EINVAL;
                         break;
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index 08d6e1bb99ac..e14a23281707 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -31,7 +31,7 @@ cond_syscall(sys_socketpair);
 cond_syscall(sys_bind);
 cond_syscall(sys_listen);
 cond_syscall(sys_accept);
-cond_syscall(sys_paccept);
+cond_syscall(sys_accept4);
 cond_syscall(sys_connect);
 cond_syscall(sys_getsockname);
 cond_syscall(sys_getpeername);
@@ -125,6 +125,12 @@ cond_syscall(sys_vm86old);
 cond_syscall(sys_vm86);
 cond_syscall(compat_sys_ipc);
 cond_syscall(compat_sys_sysctl);
+cond_syscall(sys_flock);
+cond_syscall(sys_io_setup);
+cond_syscall(sys_io_destroy);
+cond_syscall(sys_io_submit);
+cond_syscall(sys_io_cancel);
+cond_syscall(sys_io_getevents);
 
 /* arch-specific weak syscall entries */
 cond_syscall(sys_pciconfig_read);
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 50ec0886fa3d..9d048fa2d902 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -80,7 +80,6 @@ extern int pid_max_min, pid_max_max;
 extern int sysctl_drop_caches;
 extern int percpu_pagelist_fraction;
 extern int compat_log;
-extern int maps_protect;
 extern int latencytop_enabled;
 extern int sysctl_nr_open_min, sysctl_nr_open_max;
 #ifdef CONFIG_RCU_TORTURE_TEST
@@ -97,7 +96,7 @@ static int sixty = 60;
 static int neg_one = -1;
 #endif
 
-#ifdef CONFIG_MMU
+#if defined(CONFIG_MMU) && defined(CONFIG_FILE_LOCKING)
 static int two = 2;
 #endif
 
@@ -118,10 +117,8 @@ extern char modprobe_path[];
 extern int sg_big_buff;
 #endif
 
-#ifdef __sparc__
-extern char reboot_command [];
-extern int stop_a_enabled;
-extern int scons_pwroff;
+#ifdef CONFIG_SPARC
+#include <asm/system.h>
 #endif
 
 #ifdef __hppa__
@@ -152,7 +149,7 @@ extern int max_lock_depth;
 #ifdef CONFIG_PROC_SYSCTL
 static int proc_do_cad_pid(struct ctl_table *table, int write, struct file *filp,
                   void __user *buffer, size_t *lenp, loff_t *ppos);
-static int proc_dointvec_taint(struct ctl_table *table, int write, struct file *filp,
+static int proc_taint(struct ctl_table *table, int write, struct file *filp,
                                void __user *buffer, size_t *lenp, loff_t *ppos);
 #endif
 
@@ -279,6 +276,16 @@ static struct ctl_table kern_table[] = {
         },
         {
                 .ctl_name       = CTL_UNNUMBERED,
+                .procname       = "sched_shares_thresh",
+                .data           = &sysctl_sched_shares_thresh,
+                .maxlen         = sizeof(unsigned int),
+                .mode           = 0644,
+                .proc_handler   = &proc_dointvec_minmax,
+                .strategy       = &sysctl_intvec,
+                .extra1         = &zero,
+        },
+        {
+                .ctl_name       = CTL_UNNUMBERED,
                 .procname       = "sched_child_runs_first",
                 .data           = &sysctl_sched_child_runs_first,
                 .maxlen         = sizeof(unsigned int),
@@ -382,10 +389,9 @@ static struct ctl_table kern_table[] = {
 #ifdef CONFIG_PROC_SYSCTL
         {
                 .procname       = "tainted",
-                .data           = &tainted,
-                .maxlen         = sizeof(int),
+                .maxlen         = sizeof(long),
                 .mode           = 0644,
-                .proc_handler   = &proc_dointvec_taint,
+                .proc_handler   = &proc_taint,
         },
 #endif
 #ifdef CONFIG_LATENCYTOP
@@ -415,7 +421,7 @@ static struct ctl_table kern_table[] = {
                 .mode           = 0644,
                 .proc_handler   = &proc_dointvec,
         },
-#ifdef __sparc__
+#ifdef CONFIG_SPARC
         {
                 .ctl_name       = KERN_SPARC_REBOOT,
                 .procname       = "reboot-cmd",
@@ -468,7 +474,7 @@ static struct ctl_table kern_table[] = {
                 .mode           = 0644,
                 .proc_handler   = &proc_dointvec,
         },
-#ifdef CONFIG_FTRACE
+#ifdef CONFIG_FUNCTION_TRACER
         {
                 .ctl_name       = CTL_UNNUMBERED,
                 .procname       = "ftrace_enabled",
@@ -810,16 +816,6 @@ static struct ctl_table kern_table[] = {
                 .proc_handler   = &proc_dointvec,
         },
 #endif
-#ifdef CONFIG_PROC_FS
-        {
-                .ctl_name       = CTL_UNNUMBERED,
-                .procname       = "maps_protect",
-                .data           = &maps_protect,
-                .maxlen         = sizeof(int),
-                .mode           = 0644,
-                .proc_handler   = &proc_dointvec,
-        },
-#endif
         {
                 .ctl_name       = CTL_UNNUMBERED,
                 .procname       = "poweroff_cmd",
@@ -847,6 +843,16 @@ static struct ctl_table kern_table[] = {
                 .proc_handler   = &proc_dointvec,
         },
 #endif
+#ifdef CONFIG_UNEVICTABLE_LRU
+        {
+                .ctl_name       = CTL_UNNUMBERED,
+                .procname       = "scan_unevictable_pages",
+                .data           = &scan_unevictable_pages,
+                .maxlen         = sizeof(scan_unevictable_pages),
+                .mode           = 0644,
+                .proc_handler   = &scan_unevictable_handler,
+        },
+#endif
 /*
  * NOTE: do not add new entries to this table unless you have read
  * Documentation/sysctl/ctl_unnumbered.txt
@@ -1261,6 +1267,7 @@ static struct ctl_table fs_table[] = {
                 .extra1         = &minolduid,
                 .extra2         = &maxolduid,
         },
+#ifdef CONFIG_FILE_LOCKING
         {
                 .ctl_name       = FS_LEASES,
                 .procname       = "leases-enable",
@@ -1269,6 +1276,7 @@ static struct ctl_table fs_table[] = {
                 .mode           = 0644,
                 .proc_handler   = &proc_dointvec,
         },
+#endif
 #ifdef CONFIG_DNOTIFY
         {
                 .ctl_name       = FS_DIR_NOTIFY,
@@ -1280,6 +1288,7 @@ static struct ctl_table fs_table[] = {
         },
 #endif
 #ifdef CONFIG_MMU
+#ifdef CONFIG_FILE_LOCKING
         {
                 .ctl_name       = FS_LEASE_TIME,
                 .procname       = "lease-break-time",
@@ -1291,6 +1300,8 @@ static struct ctl_table fs_table[] = {
                 .extra1         = &zero,
                 .extra2         = &two,
         },
+#endif
+#ifdef CONFIG_AIO
         {
                 .procname       = "aio-nr",
                 .data           = &aio_nr,
@@ -1305,6 +1316,7 @@ static struct ctl_table fs_table[] = {
                 .mode           = 0644,
                 .proc_handler   = &proc_doulongvec_minmax,
         },
+#endif /* CONFIG_AIO */
 #ifdef CONFIG_INOTIFY_USER
         {
                 .ctl_name       = FS_INOTIFY,
@@ -1510,7 +1522,6 @@ void register_sysctl_root(struct ctl_table_root *root)
 /* Perform the actual read/write of a sysctl table entry. */
 static int do_sysctl_strategy(struct ctl_table_root *root,
                         struct ctl_table *table,
-                        int __user *name, int nlen,
                         void __user *oldval, size_t __user *oldlenp,
                         void __user *newval, size_t newlen)
 {
@@ -1524,8 +1535,7 @@ static int do_sysctl_strategy(struct ctl_table_root *root,
                 return -EPERM;
 
         if (table->strategy) {
-                rc = table->strategy(table, name, nlen, oldval, oldlenp,
-                                     newval, newlen);
+                rc = table->strategy(table, oldval, oldlenp, newval, newlen);
                 if (rc < 0)
                         return rc;
                 if (rc > 0)
@@ -1535,8 +1545,7 @@ static int do_sysctl_strategy(struct ctl_table_root *root,
         /* If there is no strategy routine, or if the strategy returns
          * zero, proceed with automatic r/w */
         if (table->data && table->maxlen) {
-                rc = sysctl_data(table, name, nlen, oldval, oldlenp,
-                                 newval, newlen);
+                rc = sysctl_data(table, oldval, oldlenp, newval, newlen);
                 if (rc < 0)
                         return rc;
         }
@@ -1568,7 +1577,7 @@ repeat:
                                 table = table->child;
                                 goto repeat;
                         }
-                        error = do_sysctl_strategy(root, table, name, nlen,
+                        error = do_sysctl_strategy(root, table,
                                                    oldval, oldlenp,
                                                    newval, newlen);
                         return error;
@@ -2237,49 +2246,39 @@ int proc_dointvec(struct ctl_table *table, int write, struct file *filp,
                             NULL,NULL);
 }
 
-#define OP_SET  0
-#define OP_AND  1
-#define OP_OR   2
-
-static int do_proc_dointvec_bset_conv(int *negp, unsigned long *lvalp,
-                                      int *valp,
-                                      int write, void *data)
-{
-        int op = *(int *)data;
-        if (write) {
-                int val = *negp ? -*lvalp : *lvalp;
-                switch(op) {
-                case OP_SET:    *valp = val; break;
-                case OP_AND:    *valp &= val; break;
-                case OP_OR:     *valp |= val; break;
-                }
-        } else {
-                int val = *valp;
-                if (val < 0) {
-                        *negp = -1;
-                        *lvalp = (unsigned long)-val;
-                } else {
-                        *negp = 0;
-                        *lvalp = (unsigned long)val;
-                }
-        }
-        return 0;
-}
-
 /*
- *      Taint values can only be increased
+ * Taint values can only be increased
+ * This means we can safely use a temporary.
  */
-static int proc_dointvec_taint(struct ctl_table *table, int write, struct file *filp,
+static int proc_taint(struct ctl_table *table, int write, struct file *filp,
                                void __user *buffer, size_t *lenp, loff_t *ppos)
 {
-        int op;
+        struct ctl_table t;
+        unsigned long tmptaint = get_taint();
+        int err;
 
         if (write && !capable(CAP_SYS_ADMIN))
                 return -EPERM;
 
-        op = OP_OR;
-        return do_proc_dointvec(table,write,filp,buffer,lenp,ppos,
-                                do_proc_dointvec_bset_conv,&op);
+        t = *table;
+        t.data = &tmptaint;
+        err = proc_doulongvec_minmax(&t, write, filp, buffer, lenp, ppos);
+        if (err < 0)
+                return err;
+
+        if (write) {
+                /*
+                 * Poor man's atomic or. Not worth adding a primitive
+                 * to everyone's atomic.h for this
+                 */
+                int i;
+                for (i = 0; i < BITS_PER_LONG && tmptaint >> i; i++) {
+                        if ((tmptaint >> i) & 1)
+                                add_taint(i);
+                }
+        }
+
+        return err;
 }
 
 struct do_proc_dointvec_minmax_conv_param {
@@ -2727,7 +2726,7 @@ int proc_doulongvec_ms_jiffies_minmax(struct ctl_table *table, int write,
  */
 
 /* The generic sysctl data routine (used if no strategy routine supplied) */
-int sysctl_data(struct ctl_table *table, int __user *name, int nlen,
+int sysctl_data(struct ctl_table *table,
                 void __user *oldval, size_t __user *oldlenp,
                 void __user *newval, size_t newlen)
 {
@@ -2761,7 +2760,7 @@ int sysctl_data(struct ctl_table *table, int __user *name, int nlen,
 }
 
 /* The generic string strategy routine: */
-int sysctl_string(struct ctl_table *table, int __user *name, int nlen,
+int sysctl_string(struct ctl_table *table,
                   void __user *oldval, size_t __user *oldlenp,
                   void __user *newval, size_t newlen)
 {
@@ -2807,7 +2806,7 @@ int sysctl_string(struct ctl_table *table, int __user *name, int nlen,
  * are between the minimum and maximum values given in the arrays
  * table->extra1 and table->extra2, respectively.
  */
-int sysctl_intvec(struct ctl_table *table, int __user *name, int nlen,
+int sysctl_intvec(struct ctl_table *table,
                 void __user *oldval, size_t __user *oldlenp,
                 void __user *newval, size_t newlen)
 {
@@ -2843,7 +2842,7 @@ int sysctl_intvec(struct ctl_table *table, int __user *name, int nlen,
 }
 
 /* Strategy function to convert jiffies to seconds */ 
-int sysctl_jiffies(struct ctl_table *table, int __user *name, int nlen,
+int sysctl_jiffies(struct ctl_table *table,
                 void __user *oldval, size_t __user *oldlenp,
                 void __user *newval, size_t newlen)
 {
@@ -2877,7 +2876,7 @@ int sysctl_jiffies(struct ctl_table *table, int __user *name, int nlen,
 }
 
 /* Strategy function to convert jiffies to seconds */ 
-int sysctl_ms_jiffies(struct ctl_table *table, int __user *name, int nlen,
+int sysctl_ms_jiffies(struct ctl_table *table,
                 void __user *oldval, size_t __user *oldlenp,
                 void __user *newval, size_t newlen)
 {
@@ -2932,35 +2931,35 @@ asmlinkage long sys_sysctl(struct __sysctl_args __user *args)
         return error;
 }
 
-int sysctl_data(struct ctl_table *table, int __user *name, int nlen,
+int sysctl_data(struct ctl_table *table,
                   void __user *oldval, size_t __user *oldlenp,
                   void __user *newval, size_t newlen)
 {
         return -ENOSYS;
 }
 
-int sysctl_string(struct ctl_table *table, int __user *name, int nlen,
+int sysctl_string(struct ctl_table *table,
                   void __user *oldval, size_t __user *oldlenp,
                   void __user *newval, size_t newlen)
 {
         return -ENOSYS;
 }
 
-int sysctl_intvec(struct ctl_table *table, int __user *name, int nlen,
+int sysctl_intvec(struct ctl_table *table,
                 void __user *oldval, size_t __user *oldlenp,
                 void __user *newval, size_t newlen)
 {
         return -ENOSYS;
 }
 
-int sysctl_jiffies(struct ctl_table *table, int __user *name, int nlen,
+int sysctl_jiffies(struct ctl_table *table,
                 void __user *oldval, size_t __user *oldlenp,
                 void __user *newval, size_t newlen)
 {
         return -ENOSYS;
 }
 
-int sysctl_ms_jiffies(struct ctl_table *table, int __user *name, int nlen,
+int sysctl_ms_jiffies(struct ctl_table *table,
                 void __user *oldval, size_t __user *oldlenp,
                 void __user *newval, size_t newlen)
 {
diff --git a/kernel/time.c b/kernel/time.c
index 6a08660b4fac..d63a4336fad6 100644
--- a/kernel/time.c
+++ b/kernel/time.c
@@ -669,3 +669,21 @@ EXPORT_SYMBOL(get_jiffies_64);
 #endif
 
 EXPORT_SYMBOL(jiffies);
+
+/*
+ * Add two timespec values and do a safety check for overflow.
+ * It's assumed that both values are valid (>= 0)
+ */
+struct timespec timespec_add_safe(const struct timespec lhs,
+                                  const struct timespec rhs)
+{
+        struct timespec res;
+
+        set_normalized_timespec(&res, lhs.tv_sec + rhs.tv_sec,
+                                lhs.tv_nsec + rhs.tv_nsec);
+
+        if (res.tv_sec < lhs.tv_sec || res.tv_sec < rhs.tv_sec)
+                res.tv_sec = TIME_T_MAX;
+
+        return res;
+}
diff --git a/kernel/time/Kconfig b/kernel/time/Kconfig
index 8d53106a0a92..95ed42951e0a 100644
--- a/kernel/time/Kconfig
+++ b/kernel/time/Kconfig
@@ -3,7 +3,6 @@
 #
 config TICK_ONESHOT
         bool
-        default n
 
 config NO_HZ
         bool "Tickless System (Dynamic Ticks)"
diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c
index 1876b526c778..f8d968063cea 100644
--- a/kernel/time/clockevents.c
+++ b/kernel/time/clockevents.c
@@ -72,6 +72,16 @@ void clockevents_set_mode(struct clock_event_device *dev,
 }
 
 /**
+ * clockevents_shutdown - shutdown the device and clear next_event
+ * @dev:        device to shutdown
+ */
+void clockevents_shutdown(struct clock_event_device *dev)
+{
+        clockevents_set_mode(dev, CLOCK_EVT_MODE_SHUTDOWN);
+        dev->next_event.tv64 = KTIME_MAX;
+}
+
+/**
  * clockevents_program_event - Reprogram the clock event device.
  * @expires:    absolute expiry time (monotonic clock)
  *
@@ -206,7 +216,7 @@ void clockevents_exchange_device(struct clock_event_device *old,
 
         if (new) {
                 BUG_ON(new->mode != CLOCK_EVT_MODE_UNUSED);
-                clockevents_set_mode(new, CLOCK_EVT_MODE_SHUTDOWN);
+                clockevents_shutdown(new);
         }
         local_irq_restore(flags);
 }
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index 093d4acf993b..9ed2eec97526 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -325,6 +325,9 @@ int clocksource_register(struct clocksource *c)
         unsigned long flags;
         int ret;
 
+        /* save mult_orig on registration */
+        c->mult_orig = c->mult;
+
         spin_lock_irqsave(&clocksource_lock, flags);
         ret = clocksource_enqueue(c);
         if (!ret)
diff --git a/kernel/time/jiffies.c b/kernel/time/jiffies.c
index 4c256fdb8875..1ca99557e929 100644
--- a/kernel/time/jiffies.c
+++ b/kernel/time/jiffies.c
@@ -61,6 +61,7 @@ struct clocksource clocksource_jiffies = {
         .read           = jiffies_read,
         .mask           = 0xffffffff, /*32bits*/
         .mult           = NSEC_PER_JIFFY << JIFFIES_SHIFT, /* details above */
+        .mult_orig      = NSEC_PER_JIFFY << JIFFIES_SHIFT,
         .shift          = JIFFIES_SHIFT,
 };
 
diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
index 1ad46f3df6e7..8ff15e5d486b 100644
--- a/kernel/time/ntp.c
+++ b/kernel/time/ntp.c
@@ -10,13 +10,13 @@
 
 #include <linux/mm.h>
 #include <linux/time.h>
-#include <linux/timer.h>
 #include <linux/timex.h>
 #include <linux/jiffies.h>
 #include <linux/hrtimer.h>
 #include <linux/capability.h>
 #include <linux/math64.h>
 #include <linux/clocksource.h>
+#include <linux/workqueue.h>
 #include <asm/timex.h>
 
 /*
@@ -142,8 +142,7 @@ static enum hrtimer_restart ntp_leap_second(struct hrtimer *timer)
                 time_state = TIME_OOP;
                 printk(KERN_NOTICE "Clock: "
                        "inserting leap second 23:59:60 UTC\n");
-                leap_timer.expires = ktime_add_ns(leap_timer.expires,
-                                                  NSEC_PER_SEC);
+                hrtimer_add_expires_ns(&leap_timer, NSEC_PER_SEC);
                 res = HRTIMER_RESTART;
                 break;
         case TIME_DEL:
@@ -218,11 +217,11 @@ void second_overflow(void)
 /* Disable the cmos update - used by virtualization and embedded */
 int no_sync_cmos_clock  __read_mostly;
 
-static void sync_cmos_clock(unsigned long dummy);
+static void sync_cmos_clock(struct work_struct *work);
 
-static DEFINE_TIMER(sync_cmos_timer, sync_cmos_clock, 0, 0);
+static DECLARE_DELAYED_WORK(sync_cmos_work, sync_cmos_clock);
 
-static void sync_cmos_clock(unsigned long dummy)
+static void sync_cmos_clock(struct work_struct *work)
 {
         struct timespec now, next;
         int fail = 1;
@@ -258,13 +257,13 @@ static void sync_cmos_clock(unsigned long dummy)
                 next.tv_sec++;
                 next.tv_nsec -= NSEC_PER_SEC;
         }
-        mod_timer(&sync_cmos_timer, jiffies + timespec_to_jiffies(&next));
+        schedule_delayed_work(&sync_cmos_work, timespec_to_jiffies(&next));
 }
 
 static void notify_cmos_timer(void)
 {
         if (!no_sync_cmos_clock)
-                mod_timer(&sync_cmos_timer, jiffies + 1);
+                schedule_delayed_work(&sync_cmos_work, 0);
 }
 
 #else
@@ -277,38 +276,50 @@ static inline void notify_cmos_timer(void) { }
 int do_adjtimex(struct timex *txc)
 {
         struct timespec ts;
-        long save_adjust, sec;
         int result;
 
-        /* In order to modify anything, you gotta be super-user! */
-        if (txc->modes && !capable(CAP_SYS_TIME))
-                return -EPERM;
-
-        /* Now we validate the data before disabling interrupts */
-
-        if ((txc->modes & ADJ_OFFSET_SINGLESHOT) == ADJ_OFFSET_SINGLESHOT) {
+        /* Validate the data before disabling interrupts */
+        if (txc->modes & ADJ_ADJTIME) {
                 /* singleshot must not be used with any other mode bits */
-                if (txc->modes & ~ADJ_OFFSET_SS_READ)
+                if (!(txc->modes & ADJ_OFFSET_SINGLESHOT))
                         return -EINVAL;
+                if (!(txc->modes & ADJ_OFFSET_READONLY) &&
+                    !capable(CAP_SYS_TIME))
+                        return -EPERM;
+        } else {
+                /* In order to modify anything, you gotta be super-user! */
+                 if (txc->modes && !capable(CAP_SYS_TIME))
+                        return -EPERM;
+
+                /* if the quartz is off by more than 10% something is VERY wrong! */
+                if (txc->modes & ADJ_TICK &&
+                    (txc->tick <  900000/USER_HZ ||
+                     txc->tick > 1100000/USER_HZ))
+                                return -EINVAL;
+
+                if (txc->modes & ADJ_STATUS && time_state != TIME_OK)
+                        hrtimer_cancel(&leap_timer);
         }
 
-        /* if the quartz is off by more than 10% something is VERY wrong ! */
-        if (txc->modes & ADJ_TICK)
-                if (txc->tick <  900000/USER_HZ ||
-                    txc->tick > 1100000/USER_HZ)
-                        return -EINVAL;
-
-        if (time_state != TIME_OK && txc->modes & ADJ_STATUS)
-                hrtimer_cancel(&leap_timer);
         getnstimeofday(&ts);
 
         write_seqlock_irq(&xtime_lock);
 
-        /* Save for later - semantics of adjtime is to return old value */
-        save_adjust = time_adjust;
-
         /* If there are input parameters, then process them */
+        if (txc->modes & ADJ_ADJTIME) {
+                long save_adjust = time_adjust;
+
+                if (!(txc->modes & ADJ_OFFSET_READONLY)) {
+                        /* adjtime() is independent from ntp_adjtime() */
+                        time_adjust = txc->offset;
+                        ntp_update_frequency();
+                }
+                txc->offset = save_adjust;
+                goto adj_done;
+        }
         if (txc->modes) {
+                long sec;
+
                 if (txc->modes & ADJ_STATUS) {
                         if ((time_status & STA_PLL) &&
                             !(txc->status & STA_PLL)) {
@@ -375,13 +386,8 @@ int do_adjtimex(struct timex *txc)
                 if (txc->modes & ADJ_TAI && txc->constant > 0)
                         time_tai = txc->constant;
 
-                if (txc->modes & ADJ_OFFSET) {
-                        if (txc->modes == ADJ_OFFSET_SINGLESHOT)
-                                /* adjtime() is independent from ntp_adjtime() */
-                                time_adjust = txc->offset;
-                        else
-                                ntp_update_offset(txc->offset);
-                }
+                if (txc->modes & ADJ_OFFSET)
+                        ntp_update_offset(txc->offset);
                 if (txc->modes & ADJ_TICK)
                         tick_usec = txc->tick;
 
@@ -389,22 +395,18 @@ int do_adjtimex(struct timex *txc)
                         ntp_update_frequency();
         }
 
+        txc->offset = shift_right(time_offset * NTP_INTERVAL_FREQ,
+                                  NTP_SCALE_SHIFT);
+        if (!(time_status & STA_NANO))
+                txc->offset /= NSEC_PER_USEC;
+
+adj_done:
         result = time_state;    /* mostly `TIME_OK' */
         if (time_status & (STA_UNSYNC|STA_CLOCKERR))
                 result = TIME_ERROR;
 
-        if ((txc->modes == ADJ_OFFSET_SINGLESHOT) ||
-            (txc->modes == ADJ_OFFSET_SS_READ))
-                txc->offset = save_adjust;
-        else {
-                txc->offset = shift_right(time_offset * NTP_INTERVAL_FREQ,
-                                          NTP_SCALE_SHIFT);
-                if (!(time_status & STA_NANO))
-                        txc->offset /= NSEC_PER_USEC;
-        }
-        txc->freq          = shift_right((s32)(time_freq >> PPM_SCALE_INV_SHIFT) *
-                                         (s64)PPM_SCALE_INV,
-                                         NTP_SCALE_SHIFT);
+        txc->freq          = shift_right((time_freq >> PPM_SCALE_INV_SHIFT) *
+                                         (s64)PPM_SCALE_INV, NTP_SCALE_SHIFT);
         txc->maxerror      = time_maxerror;
         txc->esterror      = time_esterror;
         txc->status        = time_status;
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index 2f5a38294bf9..f98a1b7b16e9 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -235,9 +235,9 @@ static void tick_do_broadcast_on_off(void *why)
         case CLOCK_EVT_NOTIFY_BROADCAST_FORCE:
                 if (!cpu_isset(cpu, tick_broadcast_mask)) {
                         cpu_set(cpu, tick_broadcast_mask);
-                        if (td->mode == TICKDEV_MODE_PERIODIC)
-                                clockevents_set_mode(dev,
-                                                     CLOCK_EVT_MODE_SHUTDOWN);
+                        if (tick_broadcast_device.mode ==
+                            TICKDEV_MODE_PERIODIC)
+                                clockevents_shutdown(dev);
                 }
                 if (*reason == CLOCK_EVT_NOTIFY_BROADCAST_FORCE)
                         tick_broadcast_force = 1;
@@ -246,7 +246,8 @@ static void tick_do_broadcast_on_off(void *why)
                 if (!tick_broadcast_force &&
                     cpu_isset(cpu, tick_broadcast_mask)) {
                         cpu_clear(cpu, tick_broadcast_mask);
-                        if (td->mode == TICKDEV_MODE_PERIODIC)
+                        if (tick_broadcast_device.mode ==
+                            TICKDEV_MODE_PERIODIC)
                                 tick_setup_periodic(dev, 0);
                 }
                 break;
@@ -254,7 +255,7 @@ static void tick_do_broadcast_on_off(void *why)
 
         if (cpus_empty(tick_broadcast_mask)) {
                 if (!bc_stopped)
-                        clockevents_set_mode(bc, CLOCK_EVT_MODE_SHUTDOWN);
+                        clockevents_shutdown(bc);
         } else if (bc_stopped) {
                 if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC)
                         tick_broadcast_start_periodic(bc);
@@ -306,7 +307,7 @@ void tick_shutdown_broadcast(unsigned int *cpup)
 
         if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC) {
                 if (bc && cpus_empty(tick_broadcast_mask))
-                        clockevents_set_mode(bc, CLOCK_EVT_MODE_SHUTDOWN);
+                        clockevents_shutdown(bc);
         }
 
         spin_unlock_irqrestore(&tick_broadcast_lock, flags);
@@ -321,7 +322,7 @@ void tick_suspend_broadcast(void)
 
         bc = tick_broadcast_device.evtdev;
         if (bc)
-                clockevents_set_mode(bc, CLOCK_EVT_MODE_SHUTDOWN);
+                clockevents_shutdown(bc);
 
         spin_unlock_irqrestore(&tick_broadcast_lock, flags);
 }
@@ -383,6 +384,19 @@ int tick_resume_broadcast_oneshot(struct clock_event_device *bc)
 }
 
 /*
+ * Called from irq_enter() when idle was interrupted to reenable the
+ * per cpu device.
+ */
+void tick_check_oneshot_broadcast(int cpu)
+{
+        if (cpu_isset(cpu, tick_broadcast_oneshot_mask)) {
+                struct tick_device *td = &per_cpu(tick_cpu_device, cpu);
+
+                clockevents_set_mode(td->evtdev, CLOCK_EVT_MODE_ONESHOT);
+        }
+}
+
+/*
  * Handle oneshot mode broadcasting
  */
 static void tick_handle_oneshot_broadcast(struct clock_event_device *dev)
@@ -576,4 +590,12 @@ void tick_shutdown_broadcast_oneshot(unsigned int *cpup)
         spin_unlock_irqrestore(&tick_broadcast_lock, flags);
 }
 
+/*
+ * Check, whether the broadcast device is in one shot mode
+ */
+int tick_broadcast_oneshot_active(void)
+{
+        return tick_broadcast_device.mode == TICKDEV_MODE_ONESHOT;
+}
+
 #endif
diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c
index c4777193d567..df12434b43ca 100644
--- a/kernel/time/tick-common.c
+++ b/kernel/time/tick-common.c
@@ -33,7 +33,7 @@ DEFINE_PER_CPU(struct tick_device, tick_cpu_device);
  */
 ktime_t tick_next_period;
 ktime_t tick_period;
-int tick_do_timer_cpu __read_mostly = -1;
+int tick_do_timer_cpu __read_mostly = TICK_DO_TIMER_BOOT;
 DEFINE_SPINLOCK(tick_device_lock);
 
 /*
@@ -109,7 +109,8 @@ void tick_setup_periodic(struct clock_event_device *dev, int broadcast)
         if (!tick_device_is_functional(dev))
                 return;
 
-        if (dev->features & CLOCK_EVT_FEAT_PERIODIC) {
+        if ((dev->features & CLOCK_EVT_FEAT_PERIODIC) &&
+            !tick_broadcast_oneshot_active()) {
                 clockevents_set_mode(dev, CLOCK_EVT_MODE_PERIODIC);
         } else {
                 unsigned long seq;
@@ -148,7 +149,7 @@ static void tick_setup_device(struct tick_device *td,
                  * If no cpu took the do_timer update, assign it to
                  * this cpu:
                  */
-                if (tick_do_timer_cpu == -1) {
+                if (tick_do_timer_cpu == TICK_DO_TIMER_BOOT) {
                         tick_do_timer_cpu = cpu;
                         tick_next_period = ktime_get();
                         tick_period = ktime_set(0, NSEC_PER_SEC / HZ);
@@ -249,7 +250,7 @@ static int tick_check_new_device(struct clock_event_device *newdev)
          * not give it back to the clockevents layer !
          */
         if (tick_is_broadcast_device(curdev)) {
-                clockevents_set_mode(curdev, CLOCK_EVT_MODE_SHUTDOWN);
+                clockevents_shutdown(curdev);
                 curdev = NULL;
         }
         clockevents_exchange_device(curdev, newdev);
@@ -300,7 +301,8 @@ static void tick_shutdown(unsigned int *cpup)
         if (*cpup == tick_do_timer_cpu) {
                 int cpu = first_cpu(cpu_online_map);
 
-                tick_do_timer_cpu = (cpu != NR_CPUS) ? cpu : -1;
+                tick_do_timer_cpu = (cpu != NR_CPUS) ? cpu :
+                        TICK_DO_TIMER_NONE;
         }
         spin_unlock_irqrestore(&tick_device_lock, flags);
 }
@@ -311,7 +313,7 @@ static void tick_suspend(void)
         unsigned long flags;
 
         spin_lock_irqsave(&tick_device_lock, flags);
-        clockevents_set_mode(td->evtdev, CLOCK_EVT_MODE_SHUTDOWN);
+        clockevents_shutdown(td->evtdev);
         spin_unlock_irqrestore(&tick_device_lock, flags);
 }
 
diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h
index 0ffc2918ea6f..b1c05bf75ee0 100644
--- a/kernel/time/tick-internal.h
+++ b/kernel/time/tick-internal.h
@@ -1,6 +1,10 @@
 /*
  * tick internal variable and functions used by low/high res code
  */
+
+#define TICK_DO_TIMER_NONE      -1
+#define TICK_DO_TIMER_BOOT      -2
+
 DECLARE_PER_CPU(struct tick_device, tick_cpu_device);
 extern spinlock_t tick_device_lock;
 extern ktime_t tick_next_period;
@@ -10,6 +14,8 @@ extern int tick_do_timer_cpu __read_mostly;
 extern void tick_setup_periodic(struct clock_event_device *dev, int broadcast);
 extern void tick_handle_periodic(struct clock_event_device *dev);
 
+extern void clockevents_shutdown(struct clock_event_device *dev);
+
 /*
  * NO_HZ / high resolution timer shared code
  */
@@ -29,6 +35,8 @@ extern void 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);
+extern int tick_broadcast_oneshot_active(void);
+extern void tick_check_oneshot_broadcast(int cpu);
 # else /* BROADCAST */
 static inline void tick_broadcast_setup_oneshot(struct clock_event_device *bc)
 {
@@ -37,6 +45,8 @@ static inline void tick_broadcast_setup_oneshot(struct clock_event_device *bc)
 static inline void tick_broadcast_oneshot_control(unsigned long reason) { }
 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; }
+static inline void tick_check_oneshot_broadcast(int cpu) { }
 # endif /* !BROADCAST */
 
 #else /* !ONESHOT */
@@ -66,6 +76,7 @@ static inline int tick_resume_broadcast_oneshot(struct clock_event_device *bc)
 {
         return 0;
 }
+static inline int tick_broadcast_oneshot_active(void) { return 0; }
 #endif /* !TICK_ONESHOT */
 
 /*
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index a87b0468568b..342fc9ccab46 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -20,6 +20,7 @@
 #include <linux/profile.h>
 #include <linux/sched.h>
 #include <linux/tick.h>
+#include <linux/module.h>
 
 #include <asm/irq_regs.h>
 
@@ -75,6 +76,9 @@ static void tick_do_update_jiffies64(ktime_t now)
                                                            incr * ticks);
                 }
                 do_timer(++ticks);
+
+                /* Keep the tick_next_period variable up to date */
+                tick_next_period = ktime_add(last_jiffies_update, tick_period);
         }
         write_sequnlock(&xtime_lock);
 }
@@ -151,7 +155,7 @@ void tick_nohz_update_jiffies(void)
         touch_softlockup_watchdog();
 }
 
-void tick_nohz_stop_idle(int cpu)
+static void tick_nohz_stop_idle(int cpu)
 {
         struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
 
@@ -187,9 +191,17 @@ u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time)
 {
         struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
 
-        *last_update_time = ktime_to_us(ts->idle_lastupdate);
+        if (!tick_nohz_enabled)
+                return -1;
+
+        if (ts->idle_active)
+                *last_update_time = ktime_to_us(ts->idle_lastupdate);
+        else
+                *last_update_time = ktime_to_us(ktime_get());
+
         return ktime_to_us(ts->idle_sleeptime);
 }
+EXPORT_SYMBOL_GPL(get_cpu_idle_time_us);
 
 /**
  * tick_nohz_stop_sched_tick - stop the idle tick from the idle task
@@ -221,7 +233,7 @@ void tick_nohz_stop_sched_tick(int inidle)
          */
         if (unlikely(!cpu_online(cpu))) {
                 if (cpu == tick_do_timer_cpu)
-                        tick_do_timer_cpu = -1;
+                        tick_do_timer_cpu = TICK_DO_TIMER_NONE;
         }
 
         if (unlikely(ts->nohz_mode == NOHZ_MODE_INACTIVE))
@@ -258,7 +270,7 @@ void tick_nohz_stop_sched_tick(int inidle)
         next_jiffies = get_next_timer_interrupt(last_jiffies);
         delta_jiffies = next_jiffies - last_jiffies;
 
-        if (rcu_needs_cpu(cpu))
+        if (rcu_needs_cpu(cpu) || printk_needs_cpu(cpu))
                 delta_jiffies = 1;
         /*
          * Do not stop the tick, if we are only one off
@@ -288,7 +300,7 @@ void tick_nohz_stop_sched_tick(int inidle)
                                 goto out;
                         }
 
-                        ts->idle_tick = ts->sched_timer.expires;
+                        ts->idle_tick = hrtimer_get_expires(&ts->sched_timer);
                         ts->tick_stopped = 1;
                         ts->idle_jiffies = last_jiffies;
                         rcu_enter_nohz();
@@ -303,7 +315,7 @@ void tick_nohz_stop_sched_tick(int inidle)
                  * invoked.
                  */
                 if (cpu == tick_do_timer_cpu)
-                        tick_do_timer_cpu = -1;
+                        tick_do_timer_cpu = TICK_DO_TIMER_NONE;
 
                 ts->idle_sleeps++;
 
@@ -365,6 +377,32 @@ ktime_t tick_nohz_get_sleep_length(void)
         return ts->sleep_length;
 }
 
+static void tick_nohz_restart(struct tick_sched *ts, ktime_t now)
+{
+        hrtimer_cancel(&ts->sched_timer);
+        hrtimer_set_expires(&ts->sched_timer, ts->idle_tick);
+
+        while (1) {
+                /* Forward the time to expire in the future */
+                hrtimer_forward(&ts->sched_timer, now, tick_period);
+
+                if (ts->nohz_mode == NOHZ_MODE_HIGHRES) {
+                        hrtimer_start_expires(&ts->sched_timer,
+                                      HRTIMER_MODE_ABS);
+                        /* Check, if the timer was already in the past */
+                        if (hrtimer_active(&ts->sched_timer))
+                                break;
+                } else {
+                        if (!tick_program_event(
+                                hrtimer_get_expires(&ts->sched_timer), 0))
+                                break;
+                }
+                /* Update jiffies and reread time */
+                tick_do_update_jiffies64(now);
+                now = ktime_get();
+        }
+}
+
 /**
  * tick_nohz_restart_sched_tick - restart the idle tick from the idle task
  *
@@ -418,35 +456,16 @@ void tick_nohz_restart_sched_tick(void)
          */
         ts->tick_stopped  = 0;
         ts->idle_exittime = now;
-        hrtimer_cancel(&ts->sched_timer);
-        ts->sched_timer.expires = ts->idle_tick;
 
-        while (1) {
-                /* Forward the time to expire in the future */
-                hrtimer_forward(&ts->sched_timer, now, tick_period);
+        tick_nohz_restart(ts, now);
 
-                if (ts->nohz_mode == NOHZ_MODE_HIGHRES) {
-                        hrtimer_start(&ts->sched_timer,
-                                      ts->sched_timer.expires,
-                                      HRTIMER_MODE_ABS);
-                        /* Check, if the timer was already in the past */
-                        if (hrtimer_active(&ts->sched_timer))
-                                break;
-                } else {
-                        if (!tick_program_event(ts->sched_timer.expires, 0))
-                                break;
-                }
-                /* Update jiffies and reread time */
-                tick_do_update_jiffies64(now);
-                now = ktime_get();
-        }
         local_irq_enable();
 }
 
 static int tick_nohz_reprogram(struct tick_sched *ts, ktime_t now)
 {
         hrtimer_forward(&ts->sched_timer, now, tick_period);
-        return tick_program_event(ts->sched_timer.expires, 0);
+        return tick_program_event(hrtimer_get_expires(&ts->sched_timer), 0);
 }
 
 /*
@@ -468,7 +487,7 @@ static void tick_nohz_handler(struct clock_event_device *dev)
          * this duty, then the jiffies update is still serialized by
          * xtime_lock.
          */
-        if (unlikely(tick_do_timer_cpu == -1))
+        if (unlikely(tick_do_timer_cpu == TICK_DO_TIMER_NONE))
                 tick_do_timer_cpu = cpu;
 
         /* Check, if the jiffies need an update */
@@ -491,10 +510,6 @@ static void tick_nohz_handler(struct clock_event_device *dev)
         update_process_times(user_mode(regs));
         profile_tick(CPU_PROFILING);
 
-        /* Do not restart, when we are in the idle loop */
-        if (ts->tick_stopped)
-                return;
-
         while (tick_nohz_reprogram(ts, now)) {
                 now = ktime_get();
                 tick_do_update_jiffies64(now);
@@ -529,7 +544,7 @@ static void tick_nohz_switch_to_nohz(void)
         next = tick_init_jiffy_update();
 
         for (;;) {
-                ts->sched_timer.expires = next;
+                hrtimer_set_expires(&ts->sched_timer, next);
                 if (!tick_program_event(next, 0))
                         break;
                 next = ktime_add(next, tick_period);
@@ -540,6 +555,41 @@ static void tick_nohz_switch_to_nohz(void)
                smp_processor_id());
 }
 
+/*
+ * When NOHZ is enabled and the tick is stopped, we need to kick the
+ * tick timer from irq_enter() so that the jiffies update is kept
+ * alive during long running softirqs. That's ugly as hell, but
+ * correctness is key even if we need to fix the offending softirq in
+ * the first place.
+ *
+ * Note, this is different to tick_nohz_restart. We just kick the
+ * timer and do not touch the other magic bits which need to be done
+ * when idle is left.
+ */
+static void tick_nohz_kick_tick(int cpu)
+{
+#if 0
+        /* Switch back to 2.6.27 behaviour */
+
+        struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
+        ktime_t delta, now;
+
+        if (!ts->tick_stopped)
+                return;
+
+        /*
+         * Do not touch the tick device, when the next expiry is either
+         * already reached or less/equal than the tick period.
+         */
+        now = ktime_get();
+        delta = ktime_sub(hrtimer_get_expires(&ts->sched_timer), now);
+        if (delta.tv64 <= tick_period.tv64)
+                return;
+
+        tick_nohz_restart(ts, now);
+#endif
+}
+
 #else
 
 static inline void tick_nohz_switch_to_nohz(void) { }
@@ -547,6 +597,19 @@ static inline void tick_nohz_switch_to_nohz(void) { }
 #endif /* NO_HZ */
 
 /*
+ * Called from irq_enter to notify about the possible interruption of idle()
+ */
+void tick_check_idle(int cpu)
+{
+        tick_check_oneshot_broadcast(cpu);
+#ifdef CONFIG_NO_HZ
+        tick_nohz_stop_idle(cpu);
+        tick_nohz_update_jiffies();
+        tick_nohz_kick_tick(cpu);
+#endif
+}
+
+/*
  * High resolution timer specific code
  */
 #ifdef CONFIG_HIGH_RES_TIMERS
@@ -570,7 +633,7 @@ static enum hrtimer_restart tick_sched_timer(struct hrtimer *timer)
          * this duty, then the jiffies update is still serialized by
          * xtime_lock.
          */
-        if (unlikely(tick_do_timer_cpu == -1))
+        if (unlikely(tick_do_timer_cpu == TICK_DO_TIMER_NONE))
                 tick_do_timer_cpu = cpu;
 #endif
 
@@ -599,10 +662,6 @@ static enum hrtimer_restart tick_sched_timer(struct hrtimer *timer)
                 profile_tick(CPU_PROFILING);
         }
 
-        /* Do not restart, when we are in the idle loop */
-        if (ts->tick_stopped)
-                return HRTIMER_NORESTART;
-
         hrtimer_forward(timer, now, tick_period);
 
         return HRTIMER_RESTART;
@@ -622,19 +681,18 @@ void tick_setup_sched_timer(void)
          */
         hrtimer_init(&ts->sched_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
         ts->sched_timer.function = tick_sched_timer;
-        ts->sched_timer.cb_mode = HRTIMER_CB_IRQSAFE_NO_SOFTIRQ;
+        ts->sched_timer.cb_mode = HRTIMER_CB_IRQSAFE_PERCPU;
 
         /* Get the next period (per cpu) */
-        ts->sched_timer.expires = tick_init_jiffy_update();
+        hrtimer_set_expires(&ts->sched_timer, tick_init_jiffy_update());
         offset = ktime_to_ns(tick_period) >> 1;
         do_div(offset, num_possible_cpus());
         offset *= smp_processor_id();
-        ts->sched_timer.expires = ktime_add_ns(ts->sched_timer.expires, offset);
+        hrtimer_add_expires_ns(&ts->sched_timer, offset);
 
         for (;;) {
                 hrtimer_forward(&ts->sched_timer, now, tick_period);
-                hrtimer_start(&ts->sched_timer, ts->sched_timer.expires,
-                              HRTIMER_MODE_ABS);
+                hrtimer_start_expires(&ts->sched_timer, HRTIMER_MODE_ABS);
                 /* Check, if the timer was already in the past */
                 if (hrtimer_active(&ts->sched_timer))
                         break;
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index e91c29f961c9..e7acfb482a68 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -58,27 +58,26 @@ struct clocksource *clock;
 
 #ifdef CONFIG_GENERIC_TIME
 /**
- * __get_nsec_offset - Returns nanoseconds since last call to periodic_hook
+ * clocksource_forward_now - update clock to the current time
  *
- * private function, must hold xtime_lock lock when being
- * called. Returns the number of nanoseconds since the
- * last call to update_wall_time() (adjusted by NTP scaling)
+ * Forward the current clock to update its state since the last call to
+ * update_wall_time(). This is useful before significant clock changes,
+ * as it avoids having to deal with this time offset explicitly.
  */
-static inline s64 __get_nsec_offset(void)
+static void clocksource_forward_now(void)
 {
         cycle_t cycle_now, cycle_delta;
-        s64 ns_offset;
+        s64 nsec;
 
-        /* read clocksource: */
         cycle_now = clocksource_read(clock);
-
-        /* calculate the delta since the last update_wall_time: */
         cycle_delta = (cycle_now - clock->cycle_last) & clock->mask;
+        clock->cycle_last = cycle_now;
 
-        /* convert to nanoseconds: */
-        ns_offset = cyc2ns(clock, cycle_delta);
+        nsec = cyc2ns(clock, cycle_delta);
+        timespec_add_ns(&xtime, nsec);
 
-        return ns_offset;
+        nsec = ((s64)cycle_delta * clock->mult_orig) >> clock->shift;
+        clock->raw_time.tv_nsec += nsec;
 }
 
 /**
@@ -89,6 +88,7 @@ static inline s64 __get_nsec_offset(void)
  */
 void getnstimeofday(struct timespec *ts)
 {
+        cycle_t cycle_now, cycle_delta;
         unsigned long seq;
         s64 nsecs;
 
@@ -96,7 +96,15 @@ void getnstimeofday(struct timespec *ts)
                 seq = read_seqbegin(&xtime_lock);
 
                 *ts = xtime;
-                nsecs = __get_nsec_offset();
+
+                /* read clocksource: */
+                cycle_now = clocksource_read(clock);
+
+                /* calculate the delta since the last update_wall_time: */
+                cycle_delta = (cycle_now - clock->cycle_last) & clock->mask;
+
+                /* convert to nanoseconds: */
+                nsecs = cyc2ns(clock, cycle_delta);
 
         } while (read_seqretry(&xtime_lock, seq));
 
@@ -129,22 +137,22 @@ EXPORT_SYMBOL(do_gettimeofday);
  */
 int do_settimeofday(struct timespec *tv)
 {
+        struct timespec ts_delta;
         unsigned long flags;
-        time_t wtm_sec, sec = tv->tv_sec;
-        long wtm_nsec, nsec = tv->tv_nsec;
 
         if ((unsigned long)tv->tv_nsec >= NSEC_PER_SEC)
                 return -EINVAL;
 
         write_seqlock_irqsave(&xtime_lock, flags);
 
-        nsec -= __get_nsec_offset();
+        clocksource_forward_now();
+
+        ts_delta.tv_sec = tv->tv_sec - xtime.tv_sec;
+        ts_delta.tv_nsec = tv->tv_nsec - xtime.tv_nsec;
+        wall_to_monotonic = timespec_sub(wall_to_monotonic, ts_delta);
 
-        wtm_sec  = wall_to_monotonic.tv_sec + (xtime.tv_sec - sec);
-        wtm_nsec = wall_to_monotonic.tv_nsec + (xtime.tv_nsec - nsec);
+        xtime = *tv;
 
-        set_normalized_timespec(&xtime, sec, nsec);
-        set_normalized_timespec(&wall_to_monotonic, wtm_sec, wtm_nsec);
         update_xtime_cache(0);
 
         clock->error = 0;
@@ -170,22 +178,19 @@ EXPORT_SYMBOL(do_settimeofday);
 static void change_clocksource(void)
 {
         struct clocksource *new;
-        cycle_t now;
-        u64 nsec;
 
         new = clocksource_get_next();
 
         if (clock == new)
                 return;
 
-        new->cycle_last = 0;
-        now = clocksource_read(new);
-        nsec =  __get_nsec_offset();
-        timespec_add_ns(&xtime, nsec);
+        clocksource_forward_now();
 
-        clock = new;
-        clock->cycle_last = now;
+        new->raw_time = clock->raw_time;
 
+        clock = new;
+        clock->cycle_last = 0;
+        clock->cycle_last = clocksource_read(new);
         clock->error = 0;
         clock->xtime_nsec = 0;
         clocksource_calculate_interval(clock, NTP_INTERVAL_LENGTH);
@@ -200,11 +205,44 @@ static void change_clocksource(void)
          */
 }
 #else
+static inline void clocksource_forward_now(void) { }
 static inline void change_clocksource(void) { }
-static inline s64 __get_nsec_offset(void) { return 0; }
 #endif
 
 /**
+ * getrawmonotonic - Returns the raw monotonic time in a timespec
+ * @ts:         pointer to the timespec to be set
+ *
+ * Returns the raw monotonic time (completely un-modified by ntp)
+ */
+void getrawmonotonic(struct timespec *ts)
+{
+        unsigned long seq;
+        s64 nsecs;
+        cycle_t cycle_now, cycle_delta;
+
+        do {
+                seq = read_seqbegin(&xtime_lock);
+
+                /* read clocksource: */
+                cycle_now = clocksource_read(clock);
+
+                /* calculate the delta since the last update_wall_time: */
+                cycle_delta = (cycle_now - clock->cycle_last) & clock->mask;
+
+                /* convert to nanoseconds: */
+                nsecs = ((s64)cycle_delta * clock->mult_orig) >> clock->shift;
+
+                *ts = clock->raw_time;
+
+        } while (read_seqretry(&xtime_lock, seq));
+
+        timespec_add_ns(ts, nsecs);
+}
+EXPORT_SYMBOL(getrawmonotonic);
+
+
+/**
  * timekeeping_valid_for_hres - Check if timekeeping is suitable for hres
  */
 int timekeeping_valid_for_hres(void)
@@ -265,8 +303,6 @@ void __init timekeeping_init(void)
 static int timekeeping_suspended;
 /* time in seconds when suspend began */
 static unsigned long timekeeping_suspend_time;
-/* xtime offset when we went into suspend */
-static s64 timekeeping_suspend_nsecs;
 
 /**
  * timekeeping_resume - Resumes the generic timekeeping subsystem.
@@ -292,8 +328,6 @@ static int timekeeping_resume(struct sys_device *dev)
                 wall_to_monotonic.tv_sec -= sleep_length;
                 total_sleep_time += sleep_length;
         }
-        /* Make sure that we have the correct xtime reference */
-        timespec_add_ns(&xtime, timekeeping_suspend_nsecs);
         update_xtime_cache(0);
         /* re-base the last cycle value */
         clock->cycle_last = 0;
@@ -319,8 +353,7 @@ static int timekeeping_suspend(struct sys_device *dev, pm_message_t state)
         timekeeping_suspend_time = read_persistent_clock();
 
         write_seqlock_irqsave(&xtime_lock, flags);
-        /* Get the current xtime offset */
-        timekeeping_suspend_nsecs = __get_nsec_offset();
+        clocksource_forward_now();
         timekeeping_suspended = 1;
         write_sequnlock_irqrestore(&xtime_lock, flags);
 
@@ -454,23 +487,29 @@ void update_wall_time(void)
 #else
         offset = clock->cycle_interval;
 #endif
-        clock->xtime_nsec += (s64)xtime.tv_nsec << clock->shift;
+        clock->xtime_nsec = (s64)xtime.tv_nsec << clock->shift;
 
         /* normally this loop will run just once, however in the
          * case of lost or late ticks, it will accumulate correctly.
          */
         while (offset >= clock->cycle_interval) {
                 /* accumulate one interval */
-                clock->xtime_nsec += clock->xtime_interval;
-                clock->cycle_last += clock->cycle_interval;
                 offset -= clock->cycle_interval;
+                clock->cycle_last += clock->cycle_interval;
 
+                clock->xtime_nsec += clock->xtime_interval;
                 if (clock->xtime_nsec >= (u64)NSEC_PER_SEC << clock->shift) {
                         clock->xtime_nsec -= (u64)NSEC_PER_SEC << clock->shift;
                         xtime.tv_sec++;
                         second_overflow();
                 }
 
+                clock->raw_time.tv_nsec += clock->raw_interval;
+                if (clock->raw_time.tv_nsec >= NSEC_PER_SEC) {
+                        clock->raw_time.tv_nsec -= NSEC_PER_SEC;
+                        clock->raw_time.tv_sec++;
+                }
+
                 /* accumulate error between NTP and clock interval */
                 clock->error += tick_length;
                 clock->error -= clock->xtime_interval << (NTP_SCALE_SHIFT - clock->shift);
@@ -479,9 +518,12 @@ void update_wall_time(void)
         /* correct the clock when NTP error is too big */
         clocksource_adjust(offset);
 
-        /* store full nanoseconds into xtime */
-        xtime.tv_nsec = (s64)clock->xtime_nsec >> clock->shift;
+        /* store full nanoseconds into xtime after rounding it up and
+         * add the remainder to the error difference.
+         */
+        xtime.tv_nsec = ((s64)clock->xtime_nsec >> clock->shift) + 1;
         clock->xtime_nsec -= (s64)xtime.tv_nsec << clock->shift;
+        clock->error += clock->xtime_nsec << (NTP_SCALE_SHIFT - clock->shift);
 
         update_xtime_cache(cyc2ns(clock, offset));
 
diff --git a/kernel/time/timer_list.c b/kernel/time/timer_list.c
index a40e20fd0001..a999b92a1277 100644
--- a/kernel/time/timer_list.c
+++ b/kernel/time/timer_list.c
@@ -47,13 +47,14 @@ static void print_name_offset(struct seq_file *m, void *sym)
 }
 
 static void
-print_timer(struct seq_file *m, struct hrtimer *timer, int idx, u64 now)
+print_timer(struct seq_file *m, struct hrtimer *taddr, struct hrtimer *timer,
+            int idx, u64 now)
 {
 #ifdef CONFIG_TIMER_STATS
         char tmp[TASK_COMM_LEN + 1];
 #endif
         SEQ_printf(m, " #%d: ", idx);
-        print_name_offset(m, timer);
+        print_name_offset(m, taddr);
         SEQ_printf(m, ", ");
         print_name_offset(m, timer->function);
         SEQ_printf(m, ", S:%02lx", timer->state);
@@ -65,9 +66,11 @@ print_timer(struct seq_file *m, struct hrtimer *timer, int idx, u64 now)
         SEQ_printf(m, ", %s/%d", tmp, timer->start_pid);
 #endif
         SEQ_printf(m, "\n");
-        SEQ_printf(m, " # expires at %Lu nsecs [in %Ld nsecs]\n",
-                (unsigned long long)ktime_to_ns(timer->expires),
-                (long long)(ktime_to_ns(timer->expires) - now));
+        SEQ_printf(m, " # expires at %Lu-%Lu nsecs [in %Ld to %Ld nsecs]\n",
+                (unsigned long long)ktime_to_ns(hrtimer_get_softexpires(timer)),
+                (unsigned long long)ktime_to_ns(hrtimer_get_expires(timer)),
+                (long long)(ktime_to_ns(hrtimer_get_softexpires(timer)) - now),
+                (long long)(ktime_to_ns(hrtimer_get_expires(timer)) - now));
 }
 
 static void
@@ -99,7 +102,7 @@ next_one:
                 tmp = *timer;
                 spin_unlock_irqrestore(&base->cpu_base->lock, flags);
 
-                print_timer(m, &tmp, i, now);
+                print_timer(m, timer, &tmp, i, now);
                 next++;
                 goto next_one;
         }
@@ -109,6 +112,7 @@ next_one:
 static void
 print_base(struct seq_file *m, struct hrtimer_clock_base *base, u64 now)
 {
+        SEQ_printf(m, "  .base:       %p\n", base);
         SEQ_printf(m, "  .index:      %d\n",
                         base->index);
         SEQ_printf(m, "  .resolution: %Lu nsecs\n",
@@ -183,12 +187,16 @@ static void print_cpu(struct seq_file *m, int cpu, u64 now)
 
 #ifdef CONFIG_GENERIC_CLOCKEVENTS
 static void
-print_tickdevice(struct seq_file *m, struct tick_device *td)
+print_tickdevice(struct seq_file *m, struct tick_device *td, int cpu)
 {
         struct clock_event_device *dev = td->evtdev;
 
         SEQ_printf(m, "\n");
         SEQ_printf(m, "Tick Device: mode:     %d\n", td->mode);
+        if (cpu < 0)
+                SEQ_printf(m, "Broadcast device\n");
+        else
+                SEQ_printf(m, "Per CPU device: %d\n", cpu);
 
         SEQ_printf(m, "Clock Event Device: ");
         if (!dev) {
@@ -222,7 +230,7 @@ static void timer_list_show_tickdevices(struct seq_file *m)
         int cpu;
 
 #ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
-        print_tickdevice(m, tick_get_broadcast_device());
+        print_tickdevice(m, tick_get_broadcast_device(), -1);
         SEQ_printf(m, "tick_broadcast_mask: %08lx\n",
                    tick_get_broadcast_mask()->bits[0]);
 #ifdef CONFIG_TICK_ONESHOT
@@ -232,7 +240,7 @@ static void timer_list_show_tickdevices(struct seq_file *m)
         SEQ_printf(m, "\n");
 #endif
         for_each_online_cpu(cpu)
-                   print_tickdevice(m, tick_get_device(cpu));
+                print_tickdevice(m, tick_get_device(cpu), cpu);
         SEQ_printf(m, "\n");
 }
 #else
@@ -244,7 +252,7 @@ static int timer_list_show(struct seq_file *m, void *v)
         u64 now = ktime_to_ns(ktime_get());
         int cpu;
 
-        SEQ_printf(m, "Timer List Version: v0.3\n");
+        SEQ_printf(m, "Timer List Version: v0.4\n");
         SEQ_printf(m, "HRTIMER_MAX_CLOCK_BASES: %d\n", HRTIMER_MAX_CLOCK_BASES);
         SEQ_printf(m, "now at %Ld nsecs\n", (unsigned long long)now);
 
diff --git a/kernel/timer.c b/kernel/timer.c
index 03bc7f1f1593..dbd50fabe4c7 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -112,27 +112,8 @@ timer_set_base(struct timer_list *timer, struct tvec_base *new_base)
                                       tbase_get_deferrable(timer->base));
 }
 
-/**
- * __round_jiffies - function to round jiffies to a full second
- * @j: the time in (absolute) jiffies that should be rounded
- * @cpu: the processor number on which the timeout will happen
- *
- * __round_jiffies() rounds an absolute time in the future (in jiffies)
- * up or down to (approximately) full seconds. This is useful for timers
- * for which the exact time they fire does not matter too much, as long as
- * they fire approximately every X seconds.
- *
- * By rounding these timers to whole seconds, all such timers will fire
- * at the same time, rather than at various times spread out. The goal
- * of this is to have the CPU wake up less, which saves power.
- *
- * The exact rounding is skewed for each processor to avoid all
- * processors firing at the exact same time, which could lead
- * to lock contention or spurious cache line bouncing.
- *
- * The return value is the rounded version of the @j parameter.
- */
-unsigned long __round_jiffies(unsigned long j, int cpu)
+static unsigned long round_jiffies_common(unsigned long j, int cpu,
+                bool force_up)
 {
         int rem;
         unsigned long original = j;
@@ -154,8 +135,9 @@ unsigned long __round_jiffies(unsigned long j, int cpu)
          * due to delays of the timer irq, long irq off times etc etc) then
          * we should round down to the whole second, not up. Use 1/4th second
          * as cutoff for this rounding as an extreme upper bound for this.
+         * But never round down if @force_up is set.
          */
-        if (rem < HZ/4) /* round down */
+        if (rem < HZ/4 && !force_up) /* round down */
                 j = j - rem;
         else /* round up */
                 j = j - rem + HZ;
@@ -167,6 +149,31 @@ unsigned long __round_jiffies(unsigned long j, int cpu)
                 return original;
         return j;
 }
+
+/**
+ * __round_jiffies - function to round jiffies to a full second
+ * @j: the time in (absolute) jiffies that should be rounded
+ * @cpu: the processor number on which the timeout will happen
+ *
+ * __round_jiffies() rounds an absolute time in the future (in jiffies)
+ * up or down to (approximately) full seconds. This is useful for timers
+ * for which the exact time they fire does not matter too much, as long as
+ * they fire approximately every X seconds.
+ *
+ * By rounding these timers to whole seconds, all such timers will fire
+ * at the same time, rather than at various times spread out. The goal
+ * of this is to have the CPU wake up less, which saves power.
+ *
+ * The exact rounding is skewed for each processor to avoid all
+ * processors firing at the exact same time, which could lead
+ * to lock contention or spurious cache line bouncing.
+ *
+ * The return value is the rounded version of the @j parameter.
+ */
+unsigned long __round_jiffies(unsigned long j, int cpu)
+{
+        return round_jiffies_common(j, cpu, false);
+}
 EXPORT_SYMBOL_GPL(__round_jiffies);
 
 /**
@@ -191,13 +198,10 @@ EXPORT_SYMBOL_GPL(__round_jiffies);
  */
 unsigned long __round_jiffies_relative(unsigned long j, int cpu)
 {
-        /*
-         * In theory the following code can skip a jiffy in case jiffies
-         * increments right between the addition and the later subtraction.
-         * However since the entire point of this function is to use approximate
-         * timeouts, it's entirely ok to not handle that.
-         */
-        return  __round_jiffies(j + jiffies, cpu) - jiffies;
+        unsigned long j0 = jiffies;
+
+        /* Use j0 because jiffies might change while we run */
+        return round_jiffies_common(j + j0, cpu, false) - j0;
 }
 EXPORT_SYMBOL_GPL(__round_jiffies_relative);
 
@@ -218,7 +222,7 @@ EXPORT_SYMBOL_GPL(__round_jiffies_relative);
  */
 unsigned long round_jiffies(unsigned long j)
 {
-        return __round_jiffies(j, raw_smp_processor_id());
+        return round_jiffies_common(j, raw_smp_processor_id(), false);
 }
 EXPORT_SYMBOL_GPL(round_jiffies);
 
@@ -243,6 +247,71 @@ unsigned long round_jiffies_relative(unsigned long j)
 }
 EXPORT_SYMBOL_GPL(round_jiffies_relative);
 
+/**
+ * __round_jiffies_up - function to round jiffies up to a full second
+ * @j: the time in (absolute) jiffies that should be rounded
+ * @cpu: the processor number on which the timeout will happen
+ *
+ * This is the same as __round_jiffies() except that it will never
+ * round down.  This is useful for timeouts for which the exact time
+ * of firing does not matter too much, as long as they don't fire too
+ * early.
+ */
+unsigned long __round_jiffies_up(unsigned long j, int cpu)
+{
+        return round_jiffies_common(j, cpu, true);
+}
+EXPORT_SYMBOL_GPL(__round_jiffies_up);
+
+/**
+ * __round_jiffies_up_relative - function to round jiffies up to a full second
+ * @j: the time in (relative) jiffies that should be rounded
+ * @cpu: the processor number on which the timeout will happen
+ *
+ * This is the same as __round_jiffies_relative() except that it will never
+ * round down.  This is useful for timeouts for which the exact time
+ * of firing does not matter too much, as long as they don't fire too
+ * early.
+ */
+unsigned long __round_jiffies_up_relative(unsigned long j, int cpu)
+{
+        unsigned long j0 = jiffies;
+
+        /* Use j0 because jiffies might change while we run */
+        return round_jiffies_common(j + j0, cpu, true) - j0;
+}
+EXPORT_SYMBOL_GPL(__round_jiffies_up_relative);
+
+/**
+ * round_jiffies_up - function to round jiffies up to a full second
+ * @j: the time in (absolute) jiffies that should be rounded
+ *
+ * This is the same as round_jiffies() except that it will never
+ * round down.  This is useful for timeouts for which the exact time
+ * of firing does not matter too much, as long as they don't fire too
+ * early.
+ */
+unsigned long round_jiffies_up(unsigned long j)
+{
+        return round_jiffies_common(j, raw_smp_processor_id(), true);
+}
+EXPORT_SYMBOL_GPL(round_jiffies_up);
+
+/**
+ * round_jiffies_up_relative - function to round jiffies up to a full second
+ * @j: the time in (relative) jiffies that should be rounded
+ *
+ * This is the same as round_jiffies_relative() except that it will never
+ * round down.  This is useful for timeouts for which the exact time
+ * of firing does not matter too much, as long as they don't fire too
+ * early.
+ */
+unsigned long round_jiffies_up_relative(unsigned long j)
+{
+        return __round_jiffies_up_relative(j, raw_smp_processor_id());
+}
+EXPORT_SYMBOL_GPL(round_jiffies_up_relative);
+
 
 static inline void set_running_timer(struct tvec_base *base,
                                         struct timer_list *timer)
@@ -978,6 +1047,7 @@ void update_process_times(int user_tick)
         run_local_timers();
         if (rcu_pending(cpu))
                 rcu_check_callbacks(cpu, user_tick);
+        printk_tick();
         scheduler_tick();
         run_posix_cpu_timers(p);
 }
@@ -1435,9 +1505,11 @@ static void __cpuinit migrate_timers(int cpu)
         BUG_ON(cpu_online(cpu));
         old_base = per_cpu(tvec_bases, cpu);
         new_base = get_cpu_var(tvec_bases);
-
-        local_irq_disable();
-        spin_lock(&new_base->lock);
+        /*
+         * The caller is globally serialized and nobody else
+         * takes two locks at once, deadlock is not possible.
+         */
+        spin_lock_irq(&new_base->lock);
         spin_lock_nested(&old_base->lock, SINGLE_DEPTH_NESTING);
 
         BUG_ON(old_base->running_timer);
@@ -1452,8 +1524,7 @@ static void __cpuinit migrate_timers(int cpu)
         }
 
         spin_unlock(&old_base->lock);
-        spin_unlock(&new_base->lock);
-        local_irq_enable();
+        spin_unlock_irq(&new_base->lock);
         put_cpu_var(tvec_bases);
 }
 #endif /* CONFIG_HOTPLUG_CPU */
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 263e9e6bbd60..33dbefd471e8 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -1,23 +1,40 @@
 #
-# Architectures that offer an FTRACE implementation should select HAVE_FTRACE:
+# Architectures that offer an FUNCTION_TRACER implementation should
+#  select HAVE_FUNCTION_TRACER:
 #
-config HAVE_FTRACE
+
+config NOP_TRACER
+        bool
+
+config HAVE_FUNCTION_TRACER
         bool
 
 config HAVE_DYNAMIC_FTRACE
         bool
 
+config HAVE_FTRACE_MCOUNT_RECORD
+        bool
+
 config TRACER_MAX_TRACE
         bool
 
+config RING_BUFFER
+        bool
+
 config TRACING
         bool
         select DEBUG_FS
-        select STACKTRACE
+        select RING_BUFFER
+        select STACKTRACE if STACKTRACE_SUPPORT
+        select TRACEPOINTS
+        select NOP_TRACER
 
-config FTRACE
+menu "Tracers"
+
+config FUNCTION_TRACER
         bool "Kernel Function Tracer"
-        depends on HAVE_FTRACE
+        depends on HAVE_FUNCTION_TRACER
+        depends on DEBUG_KERNEL
         select FRAME_POINTER
         select TRACING
         select CONTEXT_SWITCH_TRACER
@@ -35,7 +52,7 @@ config IRQSOFF_TRACER
         default n
         depends on TRACE_IRQFLAGS_SUPPORT
         depends on GENERIC_TIME
-        depends on HAVE_FTRACE
+        depends on DEBUG_KERNEL
         select TRACE_IRQFLAGS
         select TRACING
         select TRACER_MAX_TRACE
@@ -58,7 +75,7 @@ config PREEMPT_TRACER
         default n
         depends on GENERIC_TIME
         depends on PREEMPT
-        depends on HAVE_FTRACE
+        depends on DEBUG_KERNEL
         select TRACING
         select TRACER_MAX_TRACE
         help
@@ -85,7 +102,7 @@ config SYSPROF_TRACER
 
 config SCHED_TRACER
         bool "Scheduling Latency Tracer"
-        depends on HAVE_FTRACE
+        depends on DEBUG_KERNEL
         select TRACING
         select CONTEXT_SWITCH_TRACER
         select TRACER_MAX_TRACE
@@ -95,17 +112,56 @@ config SCHED_TRACER
 
 config CONTEXT_SWITCH_TRACER
         bool "Trace process context switches"
-        depends on HAVE_FTRACE
+        depends on DEBUG_KERNEL
         select TRACING
         select MARKERS
         help
           This tracer gets called from the context switch and records
           all switching of tasks.
 
+config BOOT_TRACER
+        bool "Trace boot initcalls"
+        depends on DEBUG_KERNEL
+        select TRACING
+        select CONTEXT_SWITCH_TRACER
+        help
+          This tracer helps developers to optimize boot times: it records
+          the timings of the initcalls and traces key events and the identity
+          of tasks that can cause boot delays, such as context-switches.
+
+          Its aim is to be parsed by the /scripts/bootgraph.pl tool to
+          produce pretty graphics about boot inefficiencies, giving a visual
+          representation of the delays during initcalls - but the raw
+          /debug/tracing/trace text output is readable too.
+
+          ( Note that tracing self tests can't be enabled if this tracer is
+            selected, because the self-tests are an initcall as well and that
+            would invalidate the boot trace. )
+
+config STACK_TRACER
+        bool "Trace max stack"
+        depends on HAVE_FUNCTION_TRACER
+        depends on DEBUG_KERNEL
+        select FUNCTION_TRACER
+        select STACKTRACE
+        help
+          This special tracer records the maximum stack footprint of the
+          kernel and displays it in debugfs/tracing/stack_trace.
+
+          This tracer works by hooking into every function call that the
+          kernel executes, and keeping a maximum stack depth value and
+          stack-trace saved. Because this logic has to execute in every
+          kernel function, all the time, this option can slow down the
+          kernel measurably and is generally intended for kernel
+          developers only.
+
+          Say N if unsure.
+
 config DYNAMIC_FTRACE
         bool "enable/disable ftrace tracepoints dynamically"
-        depends on FTRACE
+        depends on FUNCTION_TRACER
         depends on HAVE_DYNAMIC_FTRACE
+        depends on DEBUG_KERNEL
         default y
         help
          This option will modify all the calls to ftrace dynamically
@@ -113,7 +169,7 @@ config DYNAMIC_FTRACE
          with a No-Op instruction) as they are called. A table is
          created to dynamically enable them again.
 
-         This way a CONFIG_FTRACE kernel is slightly larger, but otherwise
+         This way a CONFIG_FUNCTION_TRACER kernel is slightly larger, but otherwise
          has native performance as long as no tracing is active.
 
          The changes to the code are done by a kernel thread that
@@ -121,15 +177,22 @@ config DYNAMIC_FTRACE
          were made. If so, it runs stop_machine (stops all CPUS)
          and modifies the code to jump over the call to ftrace.
 
+config FTRACE_MCOUNT_RECORD
+        def_bool y
+        depends on DYNAMIC_FTRACE
+        depends on HAVE_FTRACE_MCOUNT_RECORD
+
 config FTRACE_SELFTEST
         bool
 
 config FTRACE_STARTUP_TEST
         bool "Perform a startup test on ftrace"
-        depends on TRACING
+        depends on TRACING && DEBUG_KERNEL && !BOOT_TRACER
         select FTRACE_SELFTEST
         help
           This option performs a series of startup tests on ftrace. On bootup
           a series of tests are made to verify that the tracer is
           functioning properly. It will do tests on all the configured
           tracers of ftrace.
+
+endmenu
diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile
index 71d17de17288..c8228b1a49e9 100644
--- a/kernel/trace/Makefile
+++ b/kernel/trace/Makefile
@@ -1,7 +1,7 @@
 
 # Do not instrument the tracer itself:
 
-ifdef CONFIG_FTRACE
+ifdef CONFIG_FUNCTION_TRACER
 ORIG_CFLAGS := $(KBUILD_CFLAGS)
 KBUILD_CFLAGS = $(subst -pg,,$(ORIG_CFLAGS))
 
@@ -10,15 +10,19 @@ CFLAGS_trace_selftest_dynamic.o = -pg
 obj-y += trace_selftest_dynamic.o
 endif
 
-obj-$(CONFIG_FTRACE) += libftrace.o
+obj-$(CONFIG_FUNCTION_TRACER) += libftrace.o
+obj-$(CONFIG_RING_BUFFER) += ring_buffer.o
 
 obj-$(CONFIG_TRACING) += trace.o
 obj-$(CONFIG_CONTEXT_SWITCH_TRACER) += trace_sched_switch.o
 obj-$(CONFIG_SYSPROF_TRACER) += trace_sysprof.o
-obj-$(CONFIG_FTRACE) += trace_functions.o
+obj-$(CONFIG_FUNCTION_TRACER) += trace_functions.o
 obj-$(CONFIG_IRQSOFF_TRACER) += trace_irqsoff.o
 obj-$(CONFIG_PREEMPT_TRACER) += trace_irqsoff.o
 obj-$(CONFIG_SCHED_TRACER) += trace_sched_wakeup.o
+obj-$(CONFIG_NOP_TRACER) += trace_nop.o
+obj-$(CONFIG_STACK_TRACER) += trace_stack.o
 obj-$(CONFIG_MMIOTRACE) += trace_mmiotrace.o
+obj-$(CONFIG_BOOT_TRACER) += trace_boot.o
 
 libftrace-y := ftrace.o
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index f6e3af31b403..78db083390f0 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -25,13 +25,24 @@
 #include <linux/ftrace.h>
 #include <linux/sysctl.h>
 #include <linux/ctype.h>
-#include <linux/hash.h>
 #include <linux/list.h>
 
 #include <asm/ftrace.h>
 
 #include "trace.h"
 
+#define FTRACE_WARN_ON(cond)                    \
+        do {                                    \
+                if (WARN_ON(cond))              \
+                        ftrace_kill();          \
+        } while (0)
+
+#define FTRACE_WARN_ON_ONCE(cond)               \
+        do {                                    \
+                if (WARN_ON_ONCE(cond))         \
+                        ftrace_kill();          \
+        } while (0)
+
 /* ftrace_enabled is a method to turn ftrace on or off */
 int ftrace_enabled __read_mostly;
 static int last_ftrace_enabled;
@@ -81,7 +92,7 @@ void clear_ftrace_function(void)
 
 static int __register_ftrace_function(struct ftrace_ops *ops)
 {
-        /* Should never be called by interrupts */
+        /* should not be called from interrupt context */
         spin_lock(&ftrace_lock);
 
         ops->next = ftrace_list;
@@ -115,6 +126,7 @@ static int __unregister_ftrace_function(struct ftrace_ops *ops)
         struct ftrace_ops **p;
         int ret = 0;
 
+        /* should not be called from interrupt context */
         spin_lock(&ftrace_lock);
 
         /*
@@ -152,8 +164,17 @@ static int __unregister_ftrace_function(struct ftrace_ops *ops)
 }
 
 #ifdef CONFIG_DYNAMIC_FTRACE
+#ifndef CONFIG_FTRACE_MCOUNT_RECORD
+# error Dynamic ftrace depends on MCOUNT_RECORD
+#endif
 
-static struct task_struct *ftraced_task;
+/*
+ * Since MCOUNT_ADDR may point to mcount itself, we do not want
+ * to get it confused by reading a reference in the code as we
+ * are parsing on objcopy output of text. Use a variable for
+ * it instead.
+ */
+static unsigned long mcount_addr = MCOUNT_ADDR;
 
 enum {
         FTRACE_ENABLE_CALLS             = (1 << 0),
@@ -164,15 +185,9 @@ enum {
 };
 
 static int ftrace_filtered;
-static int tracing_on;
-static int frozen_record_count;
-
-static struct hlist_head ftrace_hash[FTRACE_HASHSIZE];
 
-static DEFINE_PER_CPU(int, ftrace_shutdown_disable_cpu);
+static LIST_HEAD(ftrace_new_addrs);
 
-static DEFINE_SPINLOCK(ftrace_shutdown_lock);
-static DEFINE_MUTEX(ftraced_lock);
 static DEFINE_MUTEX(ftrace_regex_lock);
 
 struct ftrace_page {
@@ -190,16 +205,13 @@ struct ftrace_page {
 static struct ftrace_page       *ftrace_pages_start;
 static struct ftrace_page       *ftrace_pages;
 
-static int ftraced_trigger;
-static int ftraced_suspend;
-static int ftraced_stop;
-
-static int ftrace_record_suspend;
-
 static struct dyn_ftrace *ftrace_free_records;
 
 
 #ifdef CONFIG_KPROBES
+
+static int frozen_record_count;
+
 static inline void freeze_record(struct dyn_ftrace *rec)
 {
         if (!(rec->flags & FTRACE_FL_FROZEN)) {
@@ -226,79 +238,36 @@ static inline int record_frozen(struct dyn_ftrace *rec)
 # define record_frozen(rec)                     ({ 0; })
 #endif /* CONFIG_KPROBES */
 
-int skip_trace(unsigned long ip)
+static void ftrace_free_rec(struct dyn_ftrace *rec)
 {
-        unsigned long fl;
-        struct dyn_ftrace *rec;
-        struct hlist_node *t;
-        struct hlist_head *head;
-
-        if (frozen_record_count == 0)
-                return 0;
-
-        head = &ftrace_hash[hash_long(ip, FTRACE_HASHBITS)];
-        hlist_for_each_entry_rcu(rec, t, head, node) {
-                if (rec->ip == ip) {
-                        if (record_frozen(rec)) {
-                                if (rec->flags & FTRACE_FL_FAILED)
-                                        return 1;
-
-                                if (!(rec->flags & FTRACE_FL_CONVERTED))
-                                        return 1;
-
-                                if (!tracing_on || !ftrace_enabled)
-                                        return 1;
-
-                                if (ftrace_filtered) {
-                                        fl = rec->flags & (FTRACE_FL_FILTER |
-                                                           FTRACE_FL_NOTRACE);
-                                        if (!fl || (fl & FTRACE_FL_NOTRACE))
-                                                return 1;
-                                }
-                        }
-                        break;
-                }
-        }
-
-        return 0;
+        rec->ip = (unsigned long)ftrace_free_records;
+        ftrace_free_records = rec;
+        rec->flags |= FTRACE_FL_FREE;
 }
 
-static inline int
-ftrace_ip_in_hash(unsigned long ip, unsigned long key)
+void ftrace_release(void *start, unsigned long size)
 {
-        struct dyn_ftrace *p;
-        struct hlist_node *t;
-        int found = 0;
-
-        hlist_for_each_entry_rcu(p, t, &ftrace_hash[key], node) {
-                if (p->ip == ip) {
-                        found = 1;
-                        break;
-                }
-        }
-
-        return found;
-}
+        struct dyn_ftrace *rec;
+        struct ftrace_page *pg;
+        unsigned long s = (unsigned long)start;
+        unsigned long e = s + size;
+        int i;
 
-static inline void
-ftrace_add_hash(struct dyn_ftrace *node, unsigned long key)
-{
-        hlist_add_head_rcu(&node->node, &ftrace_hash[key]);
-}
+        if (ftrace_disabled || !start)
+                return;
 
-/* called from kstop_machine */
-static inline void ftrace_del_hash(struct dyn_ftrace *node)
-{
-        hlist_del(&node->node);
-}
+        /* should not be called from interrupt context */
+        spin_lock(&ftrace_lock);
 
-static void ftrace_free_rec(struct dyn_ftrace *rec)
-{
-        /* no locking, only called from kstop_machine */
+        for (pg = ftrace_pages_start; pg; pg = pg->next) {
+                for (i = 0; i < pg->index; i++) {
+                        rec = &pg->records[i];
 
-        rec->ip = (unsigned long)ftrace_free_records;
-        ftrace_free_records = rec;
-        rec->flags |= FTRACE_FL_FREE;
+                        if ((rec->ip >= s) && (rec->ip < e))
+                                ftrace_free_rec(rec);
+                }
+        }
+        spin_unlock(&ftrace_lock);
 }
 
 static struct dyn_ftrace *ftrace_alloc_dyn_node(unsigned long ip)
@@ -310,10 +279,8 @@ static struct dyn_ftrace *ftrace_alloc_dyn_node(unsigned long ip)
                 rec = ftrace_free_records;
 
                 if (unlikely(!(rec->flags & FTRACE_FL_FREE))) {
-                        WARN_ON_ONCE(1);
+                        FTRACE_WARN_ON_ONCE(1);
                         ftrace_free_records = NULL;
-                        ftrace_disabled = 1;
-                        ftrace_enabled = 0;
                         return NULL;
                 }
 
@@ -323,175 +290,125 @@ static struct dyn_ftrace *ftrace_alloc_dyn_node(unsigned long ip)
         }
 
         if (ftrace_pages->index == ENTRIES_PER_PAGE) {
-                if (!ftrace_pages->next)
-                        return NULL;
+                if (!ftrace_pages->next) {
+                        /* allocate another page */
+                        ftrace_pages->next =
+                                (void *)get_zeroed_page(GFP_KERNEL);
+                        if (!ftrace_pages->next)
+                                return NULL;
+                }
                 ftrace_pages = ftrace_pages->next;
         }
 
         return &ftrace_pages->records[ftrace_pages->index++];
 }
 
-static void
+static struct dyn_ftrace *
 ftrace_record_ip(unsigned long ip)
 {
-        struct dyn_ftrace *node;
-        unsigned long flags;
-        unsigned long key;
-        int resched;
-        int atomic;
-        int cpu;
+        struct dyn_ftrace *rec;
 
         if (!ftrace_enabled || ftrace_disabled)
-                return;
-
-        resched = need_resched();
-        preempt_disable_notrace();
-
-        /*
-         * We simply need to protect against recursion.
-         * Use the the raw version of smp_processor_id and not
-         * __get_cpu_var which can call debug hooks that can
-         * cause a recursive crash here.
-         */
-        cpu = raw_smp_processor_id();
-        per_cpu(ftrace_shutdown_disable_cpu, cpu)++;
-        if (per_cpu(ftrace_shutdown_disable_cpu, cpu) != 1)
-                goto out;
-
-        if (unlikely(ftrace_record_suspend))
-                goto out;
-
-        key = hash_long(ip, FTRACE_HASHBITS);
-
-        WARN_ON_ONCE(key >= FTRACE_HASHSIZE);
+                return NULL;
 
-        if (ftrace_ip_in_hash(ip, key))
-                goto out;
-
-        atomic = irqs_disabled();
-
-        spin_lock_irqsave(&ftrace_shutdown_lock, flags);
-
-        /* This ip may have hit the hash before the lock */
-        if (ftrace_ip_in_hash(ip, key))
-                goto out_unlock;
-
-        node = ftrace_alloc_dyn_node(ip);
-        if (!node)
-                goto out_unlock;
-
-        node->ip = ip;
-
-        ftrace_add_hash(node, key);
+        rec = ftrace_alloc_dyn_node(ip);
+        if (!rec)
+                return NULL;
 
-        ftraced_trigger = 1;
+        rec->ip = ip;
 
- out_unlock:
-        spin_unlock_irqrestore(&ftrace_shutdown_lock, flags);
- out:
-        per_cpu(ftrace_shutdown_disable_cpu, cpu)--;
+        list_add(&rec->list, &ftrace_new_addrs);
 
-        /* prevent recursion with scheduler */
-        if (resched)
-                preempt_enable_no_resched_notrace();
-        else
-                preempt_enable_notrace();
+        return rec;
 }
 
 #define FTRACE_ADDR ((long)(ftrace_caller))
 
 static int
 __ftrace_replace_code(struct dyn_ftrace *rec,
-                      unsigned char *old, unsigned char *new, int enable)
+                      unsigned char *nop, int enable)
 {
         unsigned long ip, fl;
+        unsigned char *call, *old, *new;
 
         ip = rec->ip;
 
-        if (ftrace_filtered && enable) {
+        /*
+         * If this record is not to be traced and
+         * it is not enabled then do nothing.
+         *
+         * If this record is not to be traced and
+         * it is enabled then disabled it.
+         *
+         */
+        if (rec->flags & FTRACE_FL_NOTRACE) {
+                if (rec->flags & FTRACE_FL_ENABLED)
+                        rec->flags &= ~FTRACE_FL_ENABLED;
+                else
+                        return 0;
+
+        } else if (ftrace_filtered && enable) {
                 /*
-                 * If filtering is on:
-                 *
-                 * If this record is set to be filtered and
-                 * is enabled then do nothing.
-                 *
-                 * If this record is set to be filtered and
-                 * it is not enabled, enable it.
-                 *
-                 * If this record is not set to be filtered
-                 * and it is not enabled do nothing.
-                 *
-                 * If this record is set not to trace then
-                 * do nothing.
-                 *
-                 * If this record is set not to trace and
-                 * it is enabled then disable it.
-                 *
-                 * If this record is not set to be filtered and
-                 * it is enabled, disable it.
+                 * Filtering is on:
                  */
 
-                fl = rec->flags & (FTRACE_FL_FILTER | FTRACE_FL_NOTRACE |
-                                   FTRACE_FL_ENABLED);
+                fl = rec->flags & (FTRACE_FL_FILTER | FTRACE_FL_ENABLED);
 
-                if ((fl ==  (FTRACE_FL_FILTER | FTRACE_FL_ENABLED)) ||
-                    (fl ==  (FTRACE_FL_FILTER | FTRACE_FL_NOTRACE)) ||
-                    !fl || (fl == FTRACE_FL_NOTRACE))
+                /* Record is filtered and enabled, do nothing */
+                if (fl == (FTRACE_FL_FILTER | FTRACE_FL_ENABLED))
                         return 0;
 
-                /*
-                 * If it is enabled disable it,
-                 * otherwise enable it!
-                 */
-                if (fl & FTRACE_FL_ENABLED) {
-                        /* swap new and old */
-                        new = old;
-                        old = ftrace_call_replace(ip, FTRACE_ADDR);
+                /* Record is not filtered and is not enabled do nothing */
+                if (!fl)
+                        return 0;
+
+                /* Record is not filtered but enabled, disable it */
+                if (fl == FTRACE_FL_ENABLED)
                         rec->flags &= ~FTRACE_FL_ENABLED;
-                } else {
-                        new = ftrace_call_replace(ip, FTRACE_ADDR);
+                else
+                /* Otherwise record is filtered but not enabled, enable it */
                         rec->flags |= FTRACE_FL_ENABLED;
-                }
         } else {
+                /* Disable or not filtered */
 
                 if (enable) {
-                        /*
-                         * If this record is set not to trace and is
-                         * not enabled, do nothing.
-                         */
-                        fl = rec->flags & (FTRACE_FL_NOTRACE | FTRACE_FL_ENABLED);
-                        if (fl == FTRACE_FL_NOTRACE)
-                                return 0;
-
-                        new = ftrace_call_replace(ip, FTRACE_ADDR);
-                } else
-                        old = ftrace_call_replace(ip, FTRACE_ADDR);
-
-                if (enable) {
+                        /* if record is enabled, do nothing */
                         if (rec->flags & FTRACE_FL_ENABLED)
                                 return 0;
+
                         rec->flags |= FTRACE_FL_ENABLED;
+
                 } else {
+
+                        /* if record is not enabled do nothing */
                         if (!(rec->flags & FTRACE_FL_ENABLED))
                                 return 0;
+
                         rec->flags &= ~FTRACE_FL_ENABLED;
                 }
         }
 
+        call = ftrace_call_replace(ip, FTRACE_ADDR);
+
+        if (rec->flags & FTRACE_FL_ENABLED) {
+                old = nop;
+                new = call;
+        } else {
+                old = call;
+                new = nop;
+        }
+
         return ftrace_modify_code(ip, old, new);
 }
 
 static void ftrace_replace_code(int enable)
 {
         int i, failed;
-        unsigned char *new = NULL, *old = NULL;
+        unsigned char *nop = NULL;
         struct dyn_ftrace *rec;
         struct ftrace_page *pg;
 
-        if (enable)
-                old = ftrace_nop_replace();
-        else
-                new = ftrace_nop_replace();
+        nop = ftrace_nop_replace();
 
         for (pg = ftrace_pages_start; pg; pg = pg->next) {
                 for (i = 0; i < pg->index; i++) {
@@ -509,12 +426,11 @@ static void ftrace_replace_code(int enable)
                                 unfreeze_record(rec);
                         }
 
-                        failed = __ftrace_replace_code(rec, old, new, enable);
+                        failed = __ftrace_replace_code(rec, nop, enable);
                         if (failed && (rec->flags & FTRACE_FL_CONVERTED)) {
                                 rec->flags |= FTRACE_FL_FAILED;
                                 if ((system_state == SYSTEM_BOOTING) ||
                                     !core_kernel_text(rec->ip)) {
-                                        ftrace_del_hash(rec);
                                         ftrace_free_rec(rec);
                                 }
                         }
@@ -522,13 +438,14 @@ static void ftrace_replace_code(int enable)
         }
 }
 
-static void ftrace_shutdown_replenish(void)
+static void print_ip_ins(const char *fmt, unsigned char *p)
 {
-        if (ftrace_pages->next)
-                return;
+        int i;
 
-        /* allocate another page */
-        ftrace_pages->next = (void *)get_zeroed_page(GFP_KERNEL);
+        printk(KERN_CONT "%s", fmt);
+
+        for (i = 0; i < MCOUNT_INSN_SIZE; i++)
+                printk(KERN_CONT "%s%02x", i ? ":" : "", p[i]);
 }
 
 static int
@@ -536,52 +453,59 @@ ftrace_code_disable(struct dyn_ftrace *rec)
 {
         unsigned long ip;
         unsigned char *nop, *call;
-        int failed;
+        int ret;
 
         ip = rec->ip;
 
         nop = ftrace_nop_replace();
-        call = ftrace_call_replace(ip, MCOUNT_ADDR);
+        call = ftrace_call_replace(ip, mcount_addr);
+
+        ret = ftrace_modify_code(ip, call, nop);
+        if (ret) {
+                switch (ret) {
+                case -EFAULT:
+                        FTRACE_WARN_ON_ONCE(1);
+                        pr_info("ftrace faulted on modifying ");
+                        print_ip_sym(ip);
+                        break;
+                case -EINVAL:
+                        FTRACE_WARN_ON_ONCE(1);
+                        pr_info("ftrace failed to modify ");
+                        print_ip_sym(ip);
+                        print_ip_ins(" expected: ", call);
+                        print_ip_ins(" actual: ", (unsigned char *)ip);
+                        print_ip_ins(" replace: ", nop);
+                        printk(KERN_CONT "\n");
+                        break;
+                case -EPERM:
+                        FTRACE_WARN_ON_ONCE(1);
+                        pr_info("ftrace faulted on writing ");
+                        print_ip_sym(ip);
+                        break;
+                default:
+                        FTRACE_WARN_ON_ONCE(1);
+                        pr_info("ftrace faulted on unknown error ");
+                        print_ip_sym(ip);
+                }
 
-        failed = ftrace_modify_code(ip, call, nop);
-        if (failed) {
                 rec->flags |= FTRACE_FL_FAILED;
                 return 0;
         }
         return 1;
 }
 
-static int __ftrace_update_code(void *ignore);
-
 static int __ftrace_modify_code(void *data)
 {
-        unsigned long addr;
         int *command = data;
 
-        if (*command & FTRACE_ENABLE_CALLS) {
-                /*
-                 * Update any recorded ips now that we have the
-                 * machine stopped
-                 */
-                __ftrace_update_code(NULL);
+        if (*command & FTRACE_ENABLE_CALLS)
                 ftrace_replace_code(1);
-                tracing_on = 1;
-        } else if (*command & FTRACE_DISABLE_CALLS) {
+        else if (*command & FTRACE_DISABLE_CALLS)
                 ftrace_replace_code(0);
-                tracing_on = 0;
-        }
 
         if (*command & FTRACE_UPDATE_TRACE_FUNC)
                 ftrace_update_ftrace_func(ftrace_trace_function);
 
-        if (*command & FTRACE_ENABLE_MCOUNT) {
-                addr = (unsigned long)ftrace_record_ip;
-                ftrace_mcount_set(&addr);
-        } else if (*command & FTRACE_DISABLE_MCOUNT) {
-                addr = (unsigned long)ftrace_stub;
-                ftrace_mcount_set(&addr);
-        }
-
         return 0;
 }
 
@@ -590,26 +514,9 @@ static void ftrace_run_update_code(int command)
         stop_machine(__ftrace_modify_code, &command, NULL);
 }
 
-void ftrace_disable_daemon(void)
-{
-        /* Stop the daemon from calling kstop_machine */
-        mutex_lock(&ftraced_lock);
-        ftraced_stop = 1;
-        mutex_unlock(&ftraced_lock);
-
-        ftrace_force_update();
-}
-
-void ftrace_enable_daemon(void)
-{
-        mutex_lock(&ftraced_lock);
-        ftraced_stop = 0;
-        mutex_unlock(&ftraced_lock);
-
-        ftrace_force_update();
-}
-
 static ftrace_func_t saved_ftrace_func;
+static int ftrace_start;
+static DEFINE_MUTEX(ftrace_start_lock);
 
 static void ftrace_startup(void)
 {
@@ -618,10 +525,9 @@ static void ftrace_startup(void)
         if (unlikely(ftrace_disabled))
                 return;
 
-        mutex_lock(&ftraced_lock);
-        ftraced_suspend++;
-        if (ftraced_suspend == 1)
-                command |= FTRACE_ENABLE_CALLS;
+        mutex_lock(&ftrace_start_lock);
+        ftrace_start++;
+        command |= FTRACE_ENABLE_CALLS;
 
         if (saved_ftrace_func != ftrace_trace_function) {
                 saved_ftrace_func = ftrace_trace_function;
@@ -633,7 +539,7 @@ static void ftrace_startup(void)
 
         ftrace_run_update_code(command);
  out:
-        mutex_unlock(&ftraced_lock);
+        mutex_unlock(&ftrace_start_lock);
 }
 
 static void ftrace_shutdown(void)
@@ -643,9 +549,9 @@ static void ftrace_shutdown(void)
         if (unlikely(ftrace_disabled))
                 return;
 
-        mutex_lock(&ftraced_lock);
-        ftraced_suspend--;
-        if (!ftraced_suspend)
+        mutex_lock(&ftrace_start_lock);
+        ftrace_start--;
+        if (!ftrace_start)
                 command |= FTRACE_DISABLE_CALLS;
 
         if (saved_ftrace_func != ftrace_trace_function) {
@@ -658,7 +564,7 @@ static void ftrace_shutdown(void)
 
         ftrace_run_update_code(command);
  out:
-        mutex_unlock(&ftraced_lock);
+        mutex_unlock(&ftrace_start_lock);
 }
 
 static void ftrace_startup_sysctl(void)
@@ -668,15 +574,15 @@ static void ftrace_startup_sysctl(void)
         if (unlikely(ftrace_disabled))
                 return;
 
-        mutex_lock(&ftraced_lock);
+        mutex_lock(&ftrace_start_lock);
         /* Force update next time */
         saved_ftrace_func = NULL;
-        /* ftraced_suspend is true if we want ftrace running */
-        if (ftraced_suspend)
+        /* ftrace_start is true if we want ftrace running */
+        if (ftrace_start)
                 command |= FTRACE_ENABLE_CALLS;
 
         ftrace_run_update_code(command);
-        mutex_unlock(&ftraced_lock);
+        mutex_unlock(&ftrace_start_lock);
 }
 
 static void ftrace_shutdown_sysctl(void)
@@ -686,153 +592,51 @@ static void ftrace_shutdown_sysctl(void)
         if (unlikely(ftrace_disabled))
                 return;
 
-        mutex_lock(&ftraced_lock);
-        /* ftraced_suspend is true if ftrace is running */
-        if (ftraced_suspend)
+        mutex_lock(&ftrace_start_lock);
+        /* ftrace_start is true if ftrace is running */
+        if (ftrace_start)
                 command |= FTRACE_DISABLE_CALLS;
 
         ftrace_run_update_code(command);
-        mutex_unlock(&ftraced_lock);
+        mutex_unlock(&ftrace_start_lock);
 }
 
 static cycle_t          ftrace_update_time;
 static unsigned long    ftrace_update_cnt;
 unsigned long           ftrace_update_tot_cnt;
 
-static int __ftrace_update_code(void *ignore)
+static int ftrace_update_code(void)
 {
-        int i, save_ftrace_enabled;
+        struct dyn_ftrace *p, *t;
         cycle_t start, stop;
-        struct dyn_ftrace *p;
-        struct hlist_node *t, *n;
-        struct hlist_head *head, temp_list;
-
-        /* Don't be recording funcs now */
-        ftrace_record_suspend++;
-        save_ftrace_enabled = ftrace_enabled;
-        ftrace_enabled = 0;
 
         start = ftrace_now(raw_smp_processor_id());
         ftrace_update_cnt = 0;
 
-        /* No locks needed, the machine is stopped! */
-        for (i = 0; i < FTRACE_HASHSIZE; i++) {
-                INIT_HLIST_HEAD(&temp_list);
-                head = &ftrace_hash[i];
-
-                /* all CPUS are stopped, we are safe to modify code */
-                hlist_for_each_entry_safe(p, t, n, head, node) {
-                        /* Skip over failed records which have not been
-                         * freed. */
-                        if (p->flags & FTRACE_FL_FAILED)
-                                continue;
-
-                        /* Unconverted records are always at the head of the
-                         * hash bucket. Once we encounter a converted record,
-                         * simply skip over to the next bucket. Saves ftraced
-                         * some processor cycles (ftrace does its bid for
-                         * global warming :-p ). */
-                        if (p->flags & (FTRACE_FL_CONVERTED))
-                                break;
+        list_for_each_entry_safe(p, t, &ftrace_new_addrs, list) {
 
-                        /* Ignore updates to this record's mcount site.
-                         * Reintroduce this record at the head of this
-                         * bucket to attempt to "convert" it again if
-                         * the kprobe on it is unregistered before the
-                         * next run. */
-                        if (get_kprobe((void *)p->ip)) {
-                                ftrace_del_hash(p);
-                                INIT_HLIST_NODE(&p->node);
-                                hlist_add_head(&p->node, &temp_list);
-                                freeze_record(p);
-                                continue;
-                        } else {
-                                unfreeze_record(p);
-                        }
+                /* If something went wrong, bail without enabling anything */
+                if (unlikely(ftrace_disabled))
+                        return -1;
 
-                        /* convert record (i.e, patch mcount-call with NOP) */
-                        if (ftrace_code_disable(p)) {
-                                p->flags |= FTRACE_FL_CONVERTED;
-                                ftrace_update_cnt++;
-                        } else {
-                                if ((system_state == SYSTEM_BOOTING) ||
-                                    !core_kernel_text(p->ip)) {
-                                        ftrace_del_hash(p);
-                                        ftrace_free_rec(p);
-                                }
-                        }
-                }
+                list_del_init(&p->list);
 
-                hlist_for_each_entry_safe(p, t, n, &temp_list, node) {
-                        hlist_del(&p->node);
-                        INIT_HLIST_NODE(&p->node);
-                        hlist_add_head(&p->node, head);
-                }
+                /* convert record (i.e, patch mcount-call with NOP) */
+                if (ftrace_code_disable(p)) {
+                        p->flags |= FTRACE_FL_CONVERTED;
+                        ftrace_update_cnt++;
+                } else
+                        ftrace_free_rec(p);
         }
 
         stop = ftrace_now(raw_smp_processor_id());
         ftrace_update_time = stop - start;
         ftrace_update_tot_cnt += ftrace_update_cnt;
-        ftraced_trigger = 0;
-
-        ftrace_enabled = save_ftrace_enabled;
-        ftrace_record_suspend--;
-
-        return 0;
-}
 
-static int ftrace_update_code(void)
-{
-        if (unlikely(ftrace_disabled) ||
-            !ftrace_enabled || !ftraced_trigger)
-                return 0;
-
-        stop_machine(__ftrace_update_code, NULL, NULL);
-
-        return 1;
-}
-
-static int ftraced(void *ignore)
-{
-        unsigned long usecs;
-
-        while (!kthread_should_stop()) {
-
-                set_current_state(TASK_INTERRUPTIBLE);
-
-                /* check once a second */
-                schedule_timeout(HZ);
-
-                if (unlikely(ftrace_disabled))
-                        continue;
-
-                mutex_lock(&ftrace_sysctl_lock);
-                mutex_lock(&ftraced_lock);
-                if (!ftraced_suspend && !ftraced_stop &&
-                    ftrace_update_code()) {
-                        usecs = nsecs_to_usecs(ftrace_update_time);
-                        if (ftrace_update_tot_cnt > 100000) {
-                                ftrace_update_tot_cnt = 0;
-                                pr_info("hm, dftrace overflow: %lu change%s"
-                                        " (%lu total) in %lu usec%s\n",
-                                        ftrace_update_cnt,
-                                        ftrace_update_cnt != 1 ? "s" : "",
-                                        ftrace_update_tot_cnt,
-                                        usecs, usecs != 1 ? "s" : "");
-                                ftrace_disabled = 1;
-                                WARN_ON_ONCE(1);
-                        }
-                }
-                mutex_unlock(&ftraced_lock);
-                mutex_unlock(&ftrace_sysctl_lock);
-
-                ftrace_shutdown_replenish();
-        }
-        __set_current_state(TASK_RUNNING);
         return 0;
 }
 
-static int __init ftrace_dyn_table_alloc(void)
+static int __init ftrace_dyn_table_alloc(unsigned long num_to_init)
 {
         struct ftrace_page *pg;
         int cnt;
@@ -859,7 +663,9 @@ static int __init ftrace_dyn_table_alloc(void)
 
         pg = ftrace_pages = ftrace_pages_start;
 
-        cnt = NR_TO_INIT / ENTRIES_PER_PAGE;
+        cnt = num_to_init / ENTRIES_PER_PAGE;
+        pr_info("ftrace: allocating %ld entries in %d pages\n",
+                num_to_init, cnt + 1);
 
         for (i = 0; i < cnt; i++) {
                 pg->next = (void *)get_zeroed_page(GFP_KERNEL);
@@ -901,6 +707,8 @@ t_next(struct seq_file *m, void *v, loff_t *pos)
 
         (*pos)++;
 
+        /* should not be called from interrupt context */
+        spin_lock(&ftrace_lock);
  retry:
         if (iter->idx >= iter->pg->index) {
                 if (iter->pg->next) {
@@ -910,12 +718,13 @@ t_next(struct seq_file *m, void *v, loff_t *pos)
                 }
         } else {
                 rec = &iter->pg->records[iter->idx++];
-                if ((!(iter->flags & FTRACE_ITER_FAILURES) &&
+                if ((rec->flags & FTRACE_FL_FREE) ||
+
+                    (!(iter->flags & FTRACE_ITER_FAILURES) &&
                      (rec->flags & FTRACE_FL_FAILED)) ||
 
                     ((iter->flags & FTRACE_ITER_FAILURES) &&
-                     (!(rec->flags & FTRACE_FL_FAILED) ||
-                      (rec->flags & FTRACE_FL_FREE))) ||
+                     !(rec->flags & FTRACE_FL_FAILED)) ||
 
                     ((iter->flags & FTRACE_ITER_FILTER) &&
                      !(rec->flags & FTRACE_FL_FILTER)) ||
@@ -926,6 +735,7 @@ t_next(struct seq_file *m, void *v, loff_t *pos)
                         goto retry;
                 }
         }
+        spin_unlock(&ftrace_lock);
 
         iter->pos = *pos;
 
@@ -938,13 +748,11 @@ static void *t_start(struct seq_file *m, loff_t *pos)
         void *p = NULL;
         loff_t l = -1;
 
-        if (*pos != iter->pos) {
-                for (p = t_next(m, p, &l); p && l < *pos; p = t_next(m, p, &l))
-                        ;
-        } else {
-                l = *pos;
-                p = t_next(m, p, &l);
-        }
+        if (*pos > iter->pos)
+                *pos = iter->pos;
+
+        l = *pos;
+        p = t_next(m, p, &l);
 
         return p;
 }
@@ -955,15 +763,21 @@ static void t_stop(struct seq_file *m, void *p)
 
 static int t_show(struct seq_file *m, void *v)
 {
+        struct ftrace_iterator *iter = m->private;
         struct dyn_ftrace *rec = v;
         char str[KSYM_SYMBOL_LEN];
+        int ret = 0;
 
         if (!rec)
                 return 0;
 
         kallsyms_lookup(rec->ip, NULL, NULL, NULL, str);
 
-        seq_printf(m, "%s\n", str);
+        ret = seq_printf(m, "%s\n", str);
+        if (ret < 0) {
+                iter->pos--;
+                iter->idx--;
+        }
 
         return 0;
 }
@@ -989,7 +803,7 @@ ftrace_avail_open(struct inode *inode, struct file *file)
                 return -ENOMEM;
 
         iter->pg = ftrace_pages_start;
-        iter->pos = -1;
+        iter->pos = 0;
 
         ret = seq_open(file, &show_ftrace_seq_ops);
         if (!ret) {
@@ -1039,8 +853,8 @@ static void ftrace_filter_reset(int enable)
         unsigned long type = enable ? FTRACE_FL_FILTER : FTRACE_FL_NOTRACE;
         unsigned i;
 
-        /* keep kstop machine from running */
-        preempt_disable();
+        /* should not be called from interrupt context */
+        spin_lock(&ftrace_lock);
         if (enable)
                 ftrace_filtered = 0;
         pg = ftrace_pages_start;
@@ -1053,7 +867,7 @@ static void ftrace_filter_reset(int enable)
                 }
                 pg = pg->next;
         }
-        preempt_enable();
+        spin_unlock(&ftrace_lock);
 }
 
 static int
@@ -1076,7 +890,7 @@ ftrace_regex_open(struct inode *inode, struct file *file, int enable)
 
         if (file->f_mode & FMODE_READ) {
                 iter->pg = ftrace_pages_start;
-                iter->pos = -1;
+                iter->pos = 0;
                 iter->flags = enable ? FTRACE_ITER_FILTER :
                         FTRACE_ITER_NOTRACE;
 
@@ -1165,8 +979,8 @@ ftrace_match(unsigned char *buff, int len, int enable)
                 }
         }
 
-        /* keep kstop machine from running */
-        preempt_disable();
+        /* should not be called from interrupt context */
+        spin_lock(&ftrace_lock);
         if (enable)
                 ftrace_filtered = 1;
         pg = ftrace_pages_start;
@@ -1203,7 +1017,7 @@ ftrace_match(unsigned char *buff, int len, int enable)
                 }
                 pg = pg->next;
         }
-        preempt_enable();
+        spin_unlock(&ftrace_lock);
 }
 
 static ssize_t
@@ -1366,10 +1180,10 @@ ftrace_regex_release(struct inode *inode, struct file *file, int enable)
         }
 
         mutex_lock(&ftrace_sysctl_lock);
-        mutex_lock(&ftraced_lock);
-        if (iter->filtered && ftraced_suspend && ftrace_enabled)
+        mutex_lock(&ftrace_start_lock);
+        if (ftrace_start && ftrace_enabled)
                 ftrace_run_update_code(FTRACE_ENABLE_CALLS);
-        mutex_unlock(&ftraced_lock);
+        mutex_unlock(&ftrace_start_lock);
         mutex_unlock(&ftrace_sysctl_lock);
 
         kfree(iter);
@@ -1389,55 +1203,6 @@ ftrace_notrace_release(struct inode *inode, struct file *file)
         return ftrace_regex_release(inode, file, 0);
 }
 
-static ssize_t
-ftraced_read(struct file *filp, char __user *ubuf,
-                     size_t cnt, loff_t *ppos)
-{
-        /* don't worry about races */
-        char *buf = ftraced_stop ? "disabled\n" : "enabled\n";
-        int r = strlen(buf);
-
-        return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
-}
-
-static ssize_t
-ftraced_write(struct file *filp, const char __user *ubuf,
-                      size_t cnt, loff_t *ppos)
-{
-        char buf[64];
-        long val;
-        int ret;
-
-        if (cnt >= sizeof(buf))
-                return -EINVAL;
-
-        if (copy_from_user(&buf, ubuf, cnt))
-                return -EFAULT;
-
-        if (strncmp(buf, "enable", 6) == 0)
-                val = 1;
-        else if (strncmp(buf, "disable", 7) == 0)
-                val = 0;
-        else {
-                buf[cnt] = 0;
-
-                ret = strict_strtoul(buf, 10, &val);
-                if (ret < 0)
-                        return ret;
-
-                val = !!val;
-        }
-
-        if (val)
-                ftrace_enable_daemon();
-        else
-                ftrace_disable_daemon();
-
-        filp->f_pos += cnt;
-
-        return cnt;
-}
-
 static struct file_operations ftrace_avail_fops = {
         .open = ftrace_avail_open,
         .read = seq_read,
@@ -1468,54 +1233,6 @@ static struct file_operations ftrace_notrace_fops = {
         .release = ftrace_notrace_release,
 };
 
-static struct file_operations ftraced_fops = {
-        .open = tracing_open_generic,
-        .read = ftraced_read,
-        .write = ftraced_write,
-};
-
-/**
- * ftrace_force_update - force an update to all recording ftrace functions
- */
-int ftrace_force_update(void)
-{
-        int ret = 0;
-
-        if (unlikely(ftrace_disabled))
-                return -ENODEV;
-
-        mutex_lock(&ftrace_sysctl_lock);
-        mutex_lock(&ftraced_lock);
-
-        /*
-         * If ftraced_trigger is not set, then there is nothing
-         * to update.
-         */
-        if (ftraced_trigger && !ftrace_update_code())
-                ret = -EBUSY;
-
-        mutex_unlock(&ftraced_lock);
-        mutex_unlock(&ftrace_sysctl_lock);
-
-        return ret;
-}
-
-static void ftrace_force_shutdown(void)
-{
-        struct task_struct *task;
-        int command = FTRACE_DISABLE_CALLS | FTRACE_UPDATE_TRACE_FUNC;
-
-        mutex_lock(&ftraced_lock);
-        task = ftraced_task;
-        ftraced_task = NULL;
-        ftraced_suspend = -1;
-        ftrace_run_update_code(command);
-        mutex_unlock(&ftraced_lock);
-
-        if (task)
-                kthread_stop(task);
-}
-
 static __init int ftrace_init_debugfs(void)
 {
         struct dentry *d_tracer;
@@ -1546,97 +1263,103 @@ static __init int ftrace_init_debugfs(void)
                 pr_warning("Could not create debugfs "
                            "'set_ftrace_notrace' entry\n");
 
-        entry = debugfs_create_file("ftraced_enabled", 0644, d_tracer,
-                                    NULL, &ftraced_fops);
-        if (!entry)
-                pr_warning("Could not create debugfs "
-                           "'ftraced_enabled' entry\n");
         return 0;
 }
 
 fs_initcall(ftrace_init_debugfs);
 
-static int __init ftrace_dynamic_init(void)
+static int ftrace_convert_nops(unsigned long *start,
+                               unsigned long *end)
 {
-        struct task_struct *p;
+        unsigned long *p;
         unsigned long addr;
+        unsigned long flags;
+
+        mutex_lock(&ftrace_start_lock);
+        p = start;
+        while (p < end) {
+                addr = ftrace_call_adjust(*p++);
+                ftrace_record_ip(addr);
+        }
+
+        /* disable interrupts to prevent kstop machine */
+        local_irq_save(flags);
+        ftrace_update_code();
+        local_irq_restore(flags);
+        mutex_unlock(&ftrace_start_lock);
+
+        return 0;
+}
+
+void ftrace_init_module(unsigned long *start, unsigned long *end)
+{
+        if (ftrace_disabled || start == end)
+                return;
+        ftrace_convert_nops(start, end);
+}
+
+extern unsigned long __start_mcount_loc[];
+extern unsigned long __stop_mcount_loc[];
+
+void __init ftrace_init(void)
+{
+        unsigned long count, addr, flags;
         int ret;
 
-        addr = (unsigned long)ftrace_record_ip;
+        /* Keep the ftrace pointer to the stub */
+        addr = (unsigned long)ftrace_stub;
 
-        stop_machine(ftrace_dyn_arch_init, &addr, NULL);
+        local_irq_save(flags);
+        ftrace_dyn_arch_init(&addr);
+        local_irq_restore(flags);
 
         /* ftrace_dyn_arch_init places the return code in addr */
-        if (addr) {
-                ret = (int)addr;
+        if (addr)
                 goto failed;
-        }
 
-        ret = ftrace_dyn_table_alloc();
-        if (ret)
-                goto failed;
+        count = __stop_mcount_loc - __start_mcount_loc;
 
-        p = kthread_run(ftraced, NULL, "ftraced");
-        if (IS_ERR(p)) {
-                ret = -1;
+        ret = ftrace_dyn_table_alloc(count);
+        if (ret)
                 goto failed;
-        }
 
         last_ftrace_enabled = ftrace_enabled = 1;
-        ftraced_task = p;
 
-        return 0;
+        ret = ftrace_convert_nops(__start_mcount_loc,
+                                  __stop_mcount_loc);
 
+        return;
  failed:
         ftrace_disabled = 1;
-        return ret;
 }
 
-core_initcall(ftrace_dynamic_init);
 #else
+
+static int __init ftrace_nodyn_init(void)
+{
+        ftrace_enabled = 1;
+        return 0;
+}
+device_initcall(ftrace_nodyn_init);
+
 # define ftrace_startup()               do { } while (0)
 # define ftrace_shutdown()              do { } while (0)
 # define ftrace_startup_sysctl()        do { } while (0)
 # define ftrace_shutdown_sysctl()       do { } while (0)
-# define ftrace_force_shutdown()        do { } while (0)
 #endif /* CONFIG_DYNAMIC_FTRACE */
 
 /**
- * ftrace_kill_atomic - kill ftrace from critical sections
+ * ftrace_kill - kill ftrace
  *
  * This function should be used by panic code. It stops ftrace
  * but in a not so nice way. If you need to simply kill ftrace
  * from a non-atomic section, use ftrace_kill.
  */
-void ftrace_kill_atomic(void)
-{
-        ftrace_disabled = 1;
-        ftrace_enabled = 0;
-#ifdef CONFIG_DYNAMIC_FTRACE
-        ftraced_suspend = -1;
-#endif
-        clear_ftrace_function();
-}
-
-/**
- * ftrace_kill - totally shutdown ftrace
- *
- * This is a safety measure. If something was detected that seems
- * wrong, calling this function will keep ftrace from doing
- * any more modifications, and updates.
- * used when something went wrong.
- */
 void ftrace_kill(void)
 {
-        mutex_lock(&ftrace_sysctl_lock);
         ftrace_disabled = 1;
         ftrace_enabled = 0;
-
         clear_ftrace_function();
-        mutex_unlock(&ftrace_sysctl_lock);
-
-        /* Try to totally disable ftrace */
-        ftrace_force_shutdown();
 }
 
 /**
@@ -1725,3 +1448,4 @@ ftrace_enable_sysctl(struct ctl_table *table, int write,
         mutex_unlock(&ftrace_sysctl_lock);
         return ret;
 }
+
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
new file mode 100644
index 000000000000..f780e9552f91
--- /dev/null
+++ b/kernel/trace/ring_buffer.c
@@ -0,0 +1,2186 @@
+/*
+ * Generic ring buffer
+ *
+ * Copyright (C) 2008 Steven Rostedt <srostedt@redhat.com>
+ */
+#include <linux/ring_buffer.h>
+#include <linux/spinlock.h>
+#include <linux/debugfs.h>
+#include <linux/uaccess.h>
+#include <linux/module.h>
+#include <linux/percpu.h>
+#include <linux/mutex.h>
+#include <linux/sched.h>        /* used for sched_clock() (for now) */
+#include <linux/init.h>
+#include <linux/hash.h>
+#include <linux/list.h>
+#include <linux/fs.h>
+
+#include "trace.h"
+
+/* Global flag to disable all recording to ring buffers */
+static int ring_buffers_off __read_mostly;
+
+/**
+ * tracing_on - enable all tracing buffers
+ *
+ * This function enables all tracing buffers that may have been
+ * disabled with tracing_off.
+ */
+void tracing_on(void)
+{
+        ring_buffers_off = 0;
+}
+
+/**
+ * tracing_off - turn off all tracing buffers
+ *
+ * This function stops all tracing buffers from recording data.
+ * It does not disable any overhead the tracers themselves may
+ * be causing. This function simply causes all recording to
+ * the ring buffers to fail.
+ */
+void tracing_off(void)
+{
+        ring_buffers_off = 1;
+}
+
+/* Up this if you want to test the TIME_EXTENTS and normalization */
+#define DEBUG_SHIFT 0
+
+/* FIXME!!! */
+u64 ring_buffer_time_stamp(int cpu)
+{
+        u64 time;
+
+        preempt_disable_notrace();
+        /* shift to debug/test normalization and TIME_EXTENTS */
+        time = sched_clock() << DEBUG_SHIFT;
+        preempt_enable_notrace();
+
+        return time;
+}
+
+void ring_buffer_normalize_time_stamp(int cpu, u64 *ts)
+{
+        /* Just stupid testing the normalize function and deltas */
+        *ts >>= DEBUG_SHIFT;
+}
+
+#define RB_EVNT_HDR_SIZE (sizeof(struct ring_buffer_event))
+#define RB_ALIGNMENT_SHIFT      2
+#define RB_ALIGNMENT            (1 << RB_ALIGNMENT_SHIFT)
+#define RB_MAX_SMALL_DATA       28
+
+enum {
+        RB_LEN_TIME_EXTEND = 8,
+        RB_LEN_TIME_STAMP = 16,
+};
+
+/* inline for ring buffer fast paths */
+static inline unsigned
+rb_event_length(struct ring_buffer_event *event)
+{
+        unsigned length;
+
+        switch (event->type) {
+        case RINGBUF_TYPE_PADDING:
+                /* undefined */
+                return -1;
+
+        case RINGBUF_TYPE_TIME_EXTEND:
+                return RB_LEN_TIME_EXTEND;
+
+        case RINGBUF_TYPE_TIME_STAMP:
+                return RB_LEN_TIME_STAMP;
+
+        case RINGBUF_TYPE_DATA:
+                if (event->len)
+                        length = event->len << RB_ALIGNMENT_SHIFT;
+                else
+                        length = event->array[0];
+                return length + RB_EVNT_HDR_SIZE;
+        default:
+                BUG();
+        }
+        /* not hit */
+        return 0;
+}
+
+/**
+ * ring_buffer_event_length - return the length of the event
+ * @event: the event to get the length of
+ */
+unsigned ring_buffer_event_length(struct ring_buffer_event *event)
+{
+        return rb_event_length(event);
+}
+
+/* inline for ring buffer fast paths */
+static inline void *
+rb_event_data(struct ring_buffer_event *event)
+{
+        BUG_ON(event->type != RINGBUF_TYPE_DATA);
+        /* If length is in len field, then array[0] has the data */
+        if (event->len)
+                return (void *)&event->array[0];
+        /* Otherwise length is in array[0] and array[1] has the data */
+        return (void *)&event->array[1];
+}
+
+/**
+ * ring_buffer_event_data - return the data of the event
+ * @event: the event to get the data from
+ */
+void *ring_buffer_event_data(struct ring_buffer_event *event)
+{
+        return rb_event_data(event);
+}
+
+#define for_each_buffer_cpu(buffer, cpu)                \
+        for_each_cpu_mask(cpu, buffer->cpumask)
+
+#define TS_SHIFT        27
+#define TS_MASK         ((1ULL << TS_SHIFT) - 1)
+#define TS_DELTA_TEST   (~TS_MASK)
+
+/*
+ * This hack stolen from mm/slob.c.
+ * We can store per page timing information in the page frame of the page.
+ * Thanks to Peter Zijlstra for suggesting this idea.
+ */
+struct buffer_page {
+        u64              time_stamp;    /* page time stamp */
+        local_t          write;         /* index for next write */
+        local_t          commit;        /* write commited index */
+        unsigned         read;          /* index for next read */
+        struct list_head list;          /* list of free pages */
+        void *page;                     /* Actual data page */
+};
+
+/*
+ * Also stolen from mm/slob.c. Thanks to Mathieu Desnoyers for pointing
+ * this issue out.
+ */
+static inline void free_buffer_page(struct buffer_page *bpage)
+{
+        if (bpage->page)
+                free_page((unsigned long)bpage->page);
+        kfree(bpage);
+}
+
+/*
+ * We need to fit the time_stamp delta into 27 bits.
+ */
+static inline int test_time_stamp(u64 delta)
+{
+        if (delta & TS_DELTA_TEST)
+                return 1;
+        return 0;
+}
+
+#define BUF_PAGE_SIZE PAGE_SIZE
+
+/*
+ * head_page == tail_page && head == tail then buffer is empty.
+ */
+struct ring_buffer_per_cpu {
+        int                             cpu;
+        struct ring_buffer              *buffer;
+        spinlock_t                      lock;
+        struct lock_class_key           lock_key;
+        struct list_head                pages;
+        struct buffer_page              *head_page;     /* read from head */
+        struct buffer_page              *tail_page;     /* write to tail */
+        struct buffer_page              *commit_page;   /* commited pages */
+        struct buffer_page              *reader_page;
+        unsigned long                   overrun;
+        unsigned long                   entries;
+        u64                             write_stamp;
+        u64                             read_stamp;
+        atomic_t                        record_disabled;
+};
+
+struct ring_buffer {
+        unsigned long                   size;
+        unsigned                        pages;
+        unsigned                        flags;
+        int                             cpus;
+        cpumask_t                       cpumask;
+        atomic_t                        record_disabled;
+
+        struct mutex                    mutex;
+
+        struct ring_buffer_per_cpu      **buffers;
+};
+
+struct ring_buffer_iter {
+        struct ring_buffer_per_cpu      *cpu_buffer;
+        unsigned long                   head;
+        struct buffer_page              *head_page;
+        u64                             read_stamp;
+};
+
+#define RB_WARN_ON(buffer, cond)                                \
+        do {                                                    \
+                if (unlikely(cond)) {                           \
+                        atomic_inc(&buffer->record_disabled);   \
+                        WARN_ON(1);                             \
+                }                                               \
+        } while (0)
+
+#define RB_WARN_ON_RET(buffer, cond)                            \
+        do {                                                    \
+                if (unlikely(cond)) {                           \
+                        atomic_inc(&buffer->record_disabled);   \
+                        WARN_ON(1);                             \
+                        return -1;                              \
+                }                                               \
+        } while (0)
+
+#define RB_WARN_ON_ONCE(buffer, cond)                           \
+        do {                                                    \
+                static int once;                                \
+                if (unlikely(cond) && !once) {                  \
+                        once++;                                 \
+                        atomic_inc(&buffer->record_disabled);   \
+                        WARN_ON(1);                             \
+                }                                               \
+        } while (0)
+
+/**
+ * check_pages - integrity check of buffer pages
+ * @cpu_buffer: CPU buffer with pages to test
+ *
+ * As a safty measure we check to make sure the data pages have not
+ * been corrupted.
+ */
+static int rb_check_pages(struct ring_buffer_per_cpu *cpu_buffer)
+{
+        struct list_head *head = &cpu_buffer->pages;
+        struct buffer_page *page, *tmp;
+
+        RB_WARN_ON_RET(cpu_buffer, head->next->prev != head);
+        RB_WARN_ON_RET(cpu_buffer, head->prev->next != head);
+
+        list_for_each_entry_safe(page, tmp, head, list) {
+                RB_WARN_ON_RET(cpu_buffer,
+                               page->list.next->prev != &page->list);
+                RB_WARN_ON_RET(cpu_buffer,
+                               page->list.prev->next != &page->list);
+        }
+
+        return 0;
+}
+
+static int rb_allocate_pages(struct ring_buffer_per_cpu *cpu_buffer,
+                             unsigned nr_pages)
+{
+        struct list_head *head = &cpu_buffer->pages;
+        struct buffer_page *page, *tmp;
+        unsigned long addr;
+        LIST_HEAD(pages);
+        unsigned i;
+
+        for (i = 0; i < nr_pages; i++) {
+                page = kzalloc_node(ALIGN(sizeof(*page), cache_line_size()),
+                                    GFP_KERNEL, cpu_to_node(cpu_buffer->cpu));
+                if (!page)
+                        goto free_pages;
+                list_add(&page->list, &pages);
+
+                addr = __get_free_page(GFP_KERNEL);
+                if (!addr)
+                        goto free_pages;
+                page->page = (void *)addr;
+        }
+
+        list_splice(&pages, head);
+
+        rb_check_pages(cpu_buffer);
+
+        return 0;
+
+ free_pages:
+        list_for_each_entry_safe(page, tmp, &pages, list) {
+                list_del_init(&page->list);
+                free_buffer_page(page);
+        }
+        return -ENOMEM;
+}
+
+static struct ring_buffer_per_cpu *
+rb_allocate_cpu_buffer(struct ring_buffer *buffer, int cpu)
+{
+        struct ring_buffer_per_cpu *cpu_buffer;
+        struct buffer_page *page;
+        unsigned long addr;
+        int ret;
+
+        cpu_buffer = kzalloc_node(ALIGN(sizeof(*cpu_buffer), cache_line_size()),
+                                  GFP_KERNEL, cpu_to_node(cpu));
+        if (!cpu_buffer)
+                return NULL;
+
+        cpu_buffer->cpu = cpu;
+        cpu_buffer->buffer = buffer;
+        spin_lock_init(&cpu_buffer->lock);
+        INIT_LIST_HEAD(&cpu_buffer->pages);
+
+        page = kzalloc_node(ALIGN(sizeof(*page), cache_line_size()),
+                            GFP_KERNEL, cpu_to_node(cpu));
+        if (!page)
+                goto fail_free_buffer;
+
+        cpu_buffer->reader_page = page;
+        addr = __get_free_page(GFP_KERNEL);
+        if (!addr)
+                goto fail_free_reader;
+        page->page = (void *)addr;
+
+        INIT_LIST_HEAD(&cpu_buffer->reader_page->list);
+
+        ret = rb_allocate_pages(cpu_buffer, buffer->pages);
+        if (ret < 0)
+                goto fail_free_reader;
+
+        cpu_buffer->head_page
+                = list_entry(cpu_buffer->pages.next, struct buffer_page, list);
+        cpu_buffer->tail_page = cpu_buffer->commit_page = cpu_buffer->head_page;
+
+        return cpu_buffer;
+
+ fail_free_reader:
+        free_buffer_page(cpu_buffer->reader_page);
+
+ fail_free_buffer:
+        kfree(cpu_buffer);
+        return NULL;
+}
+
+static void rb_free_cpu_buffer(struct ring_buffer_per_cpu *cpu_buffer)
+{
+        struct list_head *head = &cpu_buffer->pages;
+        struct buffer_page *page, *tmp;
+
+        list_del_init(&cpu_buffer->reader_page->list);
+        free_buffer_page(cpu_buffer->reader_page);
+
+        list_for_each_entry_safe(page, tmp, head, list) {
+                list_del_init(&page->list);
+                free_buffer_page(page);
+        }
+        kfree(cpu_buffer);
+}
+
+/*
+ * Causes compile errors if the struct buffer_page gets bigger
+ * than the struct page.
+ */
+extern int ring_buffer_page_too_big(void);
+
+/**
+ * ring_buffer_alloc - allocate a new ring_buffer
+ * @size: the size in bytes that is needed.
+ * @flags: attributes to set for the ring buffer.
+ *
+ * Currently the only flag that is available is the RB_FL_OVERWRITE
+ * flag. This flag means that the buffer will overwrite old data
+ * when the buffer wraps. If this flag is not set, the buffer will
+ * drop data when the tail hits the head.
+ */
+struct ring_buffer *ring_buffer_alloc(unsigned long size, unsigned flags)
+{
+        struct ring_buffer *buffer;
+        int bsize;
+        int cpu;
+
+        /* Paranoid! Optimizes out when all is well */
+        if (sizeof(struct buffer_page) > sizeof(struct page))
+                ring_buffer_page_too_big();
+
+
+        /* keep it in its own cache line */
+        buffer = kzalloc(ALIGN(sizeof(*buffer), cache_line_size()),
+                         GFP_KERNEL);
+        if (!buffer)
+                return NULL;
+
+        buffer->pages = DIV_ROUND_UP(size, BUF_PAGE_SIZE);
+        buffer->flags = flags;
+
+        /* need at least two pages */
+        if (buffer->pages == 1)
+                buffer->pages++;
+
+        buffer->cpumask = cpu_possible_map;
+        buffer->cpus = nr_cpu_ids;
+
+        bsize = sizeof(void *) * nr_cpu_ids;
+        buffer->buffers = kzalloc(ALIGN(bsize, cache_line_size()),
+                                  GFP_KERNEL);
+        if (!buffer->buffers)
+                goto fail_free_buffer;
+
+        for_each_buffer_cpu(buffer, cpu) {
+                buffer->buffers[cpu] =
+                        rb_allocate_cpu_buffer(buffer, cpu);
+                if (!buffer->buffers[cpu])
+                        goto fail_free_buffers;
+        }
+
+        mutex_init(&buffer->mutex);
+
+        return buffer;
+
+ fail_free_buffers:
+        for_each_buffer_cpu(buffer, cpu) {
+                if (buffer->buffers[cpu])
+                        rb_free_cpu_buffer(buffer->buffers[cpu]);
+        }
+        kfree(buffer->buffers);
+
+ fail_free_buffer:
+        kfree(buffer);
+        return NULL;
+}
+
+/**
+ * ring_buffer_free - free a ring buffer.
+ * @buffer: the buffer to free.
+ */
+void
+ring_buffer_free(struct ring_buffer *buffer)
+{
+        int cpu;
+
+        for_each_buffer_cpu(buffer, cpu)
+                rb_free_cpu_buffer(buffer->buffers[cpu]);
+
+        kfree(buffer);
+}
+
+static void rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer);
+
+static void
+rb_remove_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned nr_pages)
+{
+        struct buffer_page *page;
+        struct list_head *p;
+        unsigned i;
+
+        atomic_inc(&cpu_buffer->record_disabled);
+        synchronize_sched();
+
+        for (i = 0; i < nr_pages; i++) {
+                BUG_ON(list_empty(&cpu_buffer->pages));
+                p = cpu_buffer->pages.next;
+                page = list_entry(p, struct buffer_page, list);
+                list_del_init(&page->list);
+                free_buffer_page(page);
+        }
+        BUG_ON(list_empty(&cpu_buffer->pages));
+
+        rb_reset_cpu(cpu_buffer);
+
+        rb_check_pages(cpu_buffer);
+
+        atomic_dec(&cpu_buffer->record_disabled);
+
+}
+
+static void
+rb_insert_pages(struct ring_buffer_per_cpu *cpu_buffer,
+                struct list_head *pages, unsigned nr_pages)
+{
+        struct buffer_page *page;
+        struct list_head *p;
+        unsigned i;
+
+        atomic_inc(&cpu_buffer->record_disabled);
+        synchronize_sched();
+
+        for (i = 0; i < nr_pages; i++) {
+                BUG_ON(list_empty(pages));
+                p = pages->next;
+                page = list_entry(p, struct buffer_page, list);
+                list_del_init(&page->list);
+                list_add_tail(&page->list, &cpu_buffer->pages);
+        }
+        rb_reset_cpu(cpu_buffer);
+
+        rb_check_pages(cpu_buffer);
+
+        atomic_dec(&cpu_buffer->record_disabled);
+}
+
+/**
+ * ring_buffer_resize - resize the ring buffer
+ * @buffer: the buffer to resize.
+ * @size: the new size.
+ *
+ * The tracer is responsible for making sure that the buffer is
+ * not being used while changing the size.
+ * Note: We may be able to change the above requirement by using
+ *  RCU synchronizations.
+ *
+ * Minimum size is 2 * BUF_PAGE_SIZE.
+ *
+ * Returns -1 on failure.
+ */
+int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size)
+{
+        struct ring_buffer_per_cpu *cpu_buffer;
+        unsigned nr_pages, rm_pages, new_pages;
+        struct buffer_page *page, *tmp;
+        unsigned long buffer_size;
+        unsigned long addr;
+        LIST_HEAD(pages);
+        int i, cpu;
+
+        /*
+         * Always succeed at resizing a non-existent buffer:
+         */
+        if (!buffer)
+                return size;
+
+        size = DIV_ROUND_UP(size, BUF_PAGE_SIZE);
+        size *= BUF_PAGE_SIZE;
+        buffer_size = buffer->pages * BUF_PAGE_SIZE;
+
+        /* we need a minimum of two pages */
+        if (size < BUF_PAGE_SIZE * 2)
+                size = BUF_PAGE_SIZE * 2;
+
+        if (size == buffer_size)
+                return size;
+
+        mutex_lock(&buffer->mutex);
+
+        nr_pages = DIV_ROUND_UP(size, BUF_PAGE_SIZE);
+
+        if (size < buffer_size) {
+
+                /* easy case, just free pages */
+                BUG_ON(nr_pages >= buffer->pages);
+
+                rm_pages = buffer->pages - nr_pages;
+
+                for_each_buffer_cpu(buffer, cpu) {
+                        cpu_buffer = buffer->buffers[cpu];
+                        rb_remove_pages(cpu_buffer, rm_pages);
+                }
+                goto out;
+        }
+
+        /*
+         * This is a bit more difficult. We only want to add pages
+         * when we can allocate enough for all CPUs. We do this
+         * by allocating all the pages and storing them on a local
+         * link list. If we succeed in our allocation, then we
+         * add these pages to the cpu_buffers. Otherwise we just free
+         * them all and return -ENOMEM;
+         */
+        BUG_ON(nr_pages <= buffer->pages);
+        new_pages = nr_pages - buffer->pages;
+
+        for_each_buffer_cpu(buffer, cpu) {
+                for (i = 0; i < new_pages; i++) {
+                        page = kzalloc_node(ALIGN(sizeof(*page),
+                                                  cache_line_size()),
+                                            GFP_KERNEL, cpu_to_node(cpu));
+                        if (!page)
+                                goto free_pages;
+                        list_add(&page->list, &pages);
+                        addr = __get_free_page(GFP_KERNEL);
+                        if (!addr)
+                                goto free_pages;
+                        page->page = (void *)addr;
+                }
+        }
+
+        for_each_buffer_cpu(buffer, cpu) {
+                cpu_buffer = buffer->buffers[cpu];
+                rb_insert_pages(cpu_buffer, &pages, new_pages);
+        }
+
+        BUG_ON(!list_empty(&pages));
+
+ out:
+        buffer->pages = nr_pages;
+        mutex_unlock(&buffer->mutex);
+
+        return size;
+
+ free_pages:
+        list_for_each_entry_safe(page, tmp, &pages, list) {
+                list_del_init(&page->list);
+                free_buffer_page(page);
+        }
+        mutex_unlock(&buffer->mutex);
+        return -ENOMEM;
+}
+
+static inline int rb_null_event(struct ring_buffer_event *event)
+{
+        return event->type == RINGBUF_TYPE_PADDING;
+}
+
+static inline void *__rb_page_index(struct buffer_page *page, unsigned index)
+{
+        return page->page + index;
+}
+
+static inline struct ring_buffer_event *
+rb_reader_event(struct ring_buffer_per_cpu *cpu_buffer)
+{
+        return __rb_page_index(cpu_buffer->reader_page,
+                               cpu_buffer->reader_page->read);
+}
+
+static inline struct ring_buffer_event *
+rb_head_event(struct ring_buffer_per_cpu *cpu_buffer)
+{
+        return __rb_page_index(cpu_buffer->head_page,
+                               cpu_buffer->head_page->read);
+}
+
+static inline struct ring_buffer_event *
+rb_iter_head_event(struct ring_buffer_iter *iter)
+{
+        return __rb_page_index(iter->head_page, iter->head);
+}
+
+static inline unsigned rb_page_write(struct buffer_page *bpage)
+{
+        return local_read(&bpage->write);
+}
+
+static inline unsigned rb_page_commit(struct buffer_page *bpage)
+{
+        return local_read(&bpage->commit);
+}
+
+/* Size is determined by what has been commited */
+static inline unsigned rb_page_size(struct buffer_page *bpage)
+{
+        return rb_page_commit(bpage);
+}
+
+static inline unsigned
+rb_commit_index(struct ring_buffer_per_cpu *cpu_buffer)
+{
+        return rb_page_commit(cpu_buffer->commit_page);
+}
+
+static inline unsigned rb_head_size(struct ring_buffer_per_cpu *cpu_buffer)
+{
+        return rb_page_commit(cpu_buffer->head_page);
+}
+
+/*
+ * When the tail hits the head and the buffer is in overwrite mode,
+ * the head jumps to the next page and all content on the previous
+ * page is discarded. But before doing so, we update the overrun
+ * variable of the buffer.
+ */
+static void rb_update_overflow(struct ring_buffer_per_cpu *cpu_buffer)
+{
+        struct ring_buffer_event *event;
+        unsigned long head;
+
+        for (head = 0; head < rb_head_size(cpu_buffer);
+             head += rb_event_length(event)) {
+
+                event = __rb_page_index(cpu_buffer->head_page, head);
+                BUG_ON(rb_null_event(event));
+                /* Only count data entries */
+                if (event->type != RINGBUF_TYPE_DATA)
+                        continue;
+                cpu_buffer->overrun++;
+                cpu_buffer->entries--;
+        }
+}
+
+static inline void rb_inc_page(struct ring_buffer_per_cpu *cpu_buffer,
+                               struct buffer_page **page)
+{
+        struct list_head *p = (*page)->list.next;
+
+        if (p == &cpu_buffer->pages)
+                p = p->next;
+
+        *page = list_entry(p, struct buffer_page, list);
+}
+
+static inline unsigned
+rb_event_index(struct ring_buffer_event *event)
+{
+        unsigned long addr = (unsigned long)event;
+
+        return (addr & ~PAGE_MASK) - (PAGE_SIZE - BUF_PAGE_SIZE);
+}
+
+static inline int
+rb_is_commit(struct ring_buffer_per_cpu *cpu_buffer,
+             struct ring_buffer_event *event)
+{
+        unsigned long addr = (unsigned long)event;
+        unsigned long index;
+
+        index = rb_event_index(event);
+        addr &= PAGE_MASK;
+
+        return cpu_buffer->commit_page->page == (void *)addr &&
+                rb_commit_index(cpu_buffer) == index;
+}
+
+static inline void
+rb_set_commit_event(struct ring_buffer_per_cpu *cpu_buffer,
+                    struct ring_buffer_event *event)
+{
+        unsigned long addr = (unsigned long)event;
+        unsigned long index;
+
+        index = rb_event_index(event);
+        addr &= PAGE_MASK;
+
+        while (cpu_buffer->commit_page->page != (void *)addr) {
+                RB_WARN_ON(cpu_buffer,
+                           cpu_buffer->commit_page == cpu_buffer->tail_page);
+                cpu_buffer->commit_page->commit =
+                        cpu_buffer->commit_page->write;
+                rb_inc_page(cpu_buffer, &cpu_buffer->commit_page);
+                cpu_buffer->write_stamp = cpu_buffer->commit_page->time_stamp;
+        }
+
+        /* Now set the commit to the event's index */
+        local_set(&cpu_buffer->commit_page->commit, index);
+}
+
+static inline void
+rb_set_commit_to_write(struct ring_buffer_per_cpu *cpu_buffer)
+{
+        /*
+         * We only race with interrupts and NMIs on this CPU.
+         * If we own the commit event, then we can commit
+         * all others that interrupted us, since the interruptions
+         * are in stack format (they finish before they come
+         * back to us). This allows us to do a simple loop to
+         * assign the commit to the tail.
+         */
+        while (cpu_buffer->commit_page != cpu_buffer->tail_page) {
+                cpu_buffer->commit_page->commit =
+                        cpu_buffer->commit_page->write;
+                rb_inc_page(cpu_buffer, &cpu_buffer->commit_page);
+                cpu_buffer->write_stamp = cpu_buffer->commit_page->time_stamp;
+                /* add barrier to keep gcc from optimizing too much */
+                barrier();
+        }
+        while (rb_commit_index(cpu_buffer) !=
+               rb_page_write(cpu_buffer->commit_page)) {
+                cpu_buffer->commit_page->commit =
+                        cpu_buffer->commit_page->write;
+                barrier();
+        }
+}
+
+static void rb_reset_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
+{
+        cpu_buffer->read_stamp = cpu_buffer->reader_page->time_stamp;
+        cpu_buffer->reader_page->read = 0;
+}
+
+static inline void rb_inc_iter(struct ring_buffer_iter *iter)
+{
+        struct ring_buffer_per_cpu *cpu_buffer = iter->cpu_buffer;
+
+        /*
+         * The iterator could be on the reader page (it starts there).
+         * But the head could have moved, since the reader was
+         * found. Check for this case and assign the iterator
+         * to the head page instead of next.
+         */
+        if (iter->head_page == cpu_buffer->reader_page)
+                iter->head_page = cpu_buffer->head_page;
+        else
+                rb_inc_page(cpu_buffer, &iter->head_page);
+
+        iter->read_stamp = iter->head_page->time_stamp;
+        iter->head = 0;
+}
+
+/**
+ * ring_buffer_update_event - update event type and data
+ * @event: the even to update
+ * @type: the type of event
+ * @length: the size of the event field in the ring buffer
+ *
+ * Update the type and data fields of the event. The length
+ * is the actual size that is written to the ring buffer,
+ * and with this, we can determine what to place into the
+ * data field.
+ */
+static inline void
+rb_update_event(struct ring_buffer_event *event,
+                         unsigned type, unsigned length)
+{
+        event->type = type;
+
+        switch (type) {
+
+        case RINGBUF_TYPE_PADDING:
+                break;
+
+        case RINGBUF_TYPE_TIME_EXTEND:
+                event->len =
+                        (RB_LEN_TIME_EXTEND + (RB_ALIGNMENT-1))
+                        >> RB_ALIGNMENT_SHIFT;
+                break;
+
+        case RINGBUF_TYPE_TIME_STAMP:
+                event->len =
+                        (RB_LEN_TIME_STAMP + (RB_ALIGNMENT-1))
+                        >> RB_ALIGNMENT_SHIFT;
+                break;
+
+        case RINGBUF_TYPE_DATA:
+                length -= RB_EVNT_HDR_SIZE;
+                if (length > RB_MAX_SMALL_DATA) {
+                        event->len = 0;
+                        event->array[0] = length;
+                } else
+                        event->len =
+                                (length + (RB_ALIGNMENT-1))
+                                >> RB_ALIGNMENT_SHIFT;
+                break;
+        default:
+                BUG();
+        }
+}
+
+static inline unsigned rb_calculate_event_length(unsigned length)
+{
+        struct ring_buffer_event event; /* Used only for sizeof array */
+
+        /* zero length can cause confusions */
+        if (!length)
+                length = 1;
+
+        if (length > RB_MAX_SMALL_DATA)
+                length += sizeof(event.array[0]);
+
+        length += RB_EVNT_HDR_SIZE;
+        length = ALIGN(length, RB_ALIGNMENT);
+
+        return length;
+}
+
+static struct ring_buffer_event *
+__rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
+                  unsigned type, unsigned long length, u64 *ts)
+{
+        struct buffer_page *tail_page, *head_page, *reader_page;
+        unsigned long tail, write;
+        struct ring_buffer *buffer = cpu_buffer->buffer;
+        struct ring_buffer_event *event;
+        unsigned long flags;
+
+        tail_page = cpu_buffer->tail_page;
+        write = local_add_return(length, &tail_page->write);
+        tail = write - length;
+
+        /* See if we shot pass the end of this buffer page */
+        if (write > BUF_PAGE_SIZE) {
+                struct buffer_page *next_page = tail_page;
+
+                spin_lock_irqsave(&cpu_buffer->lock, flags);
+
+                rb_inc_page(cpu_buffer, &next_page);
+
+                head_page = cpu_buffer->head_page;
+                reader_page = cpu_buffer->reader_page;
+
+                /* we grabbed the lock before incrementing */
+                RB_WARN_ON(cpu_buffer, next_page == reader_page);
+
+                /*
+                 * If for some reason, we had an interrupt storm that made
+                 * it all the way around the buffer, bail, and warn
+                 * about it.
+                 */
+                if (unlikely(next_page == cpu_buffer->commit_page)) {
+                        WARN_ON_ONCE(1);
+                        goto out_unlock;
+                }
+
+                if (next_page == head_page) {
+                        if (!(buffer->flags & RB_FL_OVERWRITE)) {
+                                /* reset write */
+                                if (tail <= BUF_PAGE_SIZE)
+                                        local_set(&tail_page->write, tail);
+                                goto out_unlock;
+                        }
+
+                        /* tail_page has not moved yet? */
+                        if (tail_page == cpu_buffer->tail_page) {
+                                /* count overflows */
+                                rb_update_overflow(cpu_buffer);
+
+                                rb_inc_page(cpu_buffer, &head_page);
+                                cpu_buffer->head_page = head_page;
+                                cpu_buffer->head_page->read = 0;
+                        }
+                }
+
+                /*
+                 * If the tail page is still the same as what we think
+                 * it is, then it is up to us to update the tail
+                 * pointer.
+                 */
+                if (tail_page == cpu_buffer->tail_page) {
+                        local_set(&next_page->write, 0);
+                        local_set(&next_page->commit, 0);
+                        cpu_buffer->tail_page = next_page;
+
+                        /* reread the time stamp */
+                        *ts = ring_buffer_time_stamp(cpu_buffer->cpu);
+                        cpu_buffer->tail_page->time_stamp = *ts;
+                }
+
+                /*
+                 * The actual tail page has moved forward.
+                 */
+                if (tail < BUF_PAGE_SIZE) {
+                        /* Mark the rest of the page with padding */
+                        event = __rb_page_index(tail_page, tail);
+                        event->type = RINGBUF_TYPE_PADDING;
+                }
+
+                if (tail <= BUF_PAGE_SIZE)
+                        /* Set the write back to the previous setting */
+                        local_set(&tail_page->write, tail);
+
+                /*
+                 * If this was a commit entry that failed,
+                 * increment that too
+                 */
+                if (tail_page == cpu_buffer->commit_page &&
+                    tail == rb_commit_index(cpu_buffer)) {
+                        rb_set_commit_to_write(cpu_buffer);
+                }
+
+                spin_unlock_irqrestore(&cpu_buffer->lock, flags);
+
+                /* fail and let the caller try again */
+                return ERR_PTR(-EAGAIN);
+        }
+
+        /* We reserved something on the buffer */
+
+        BUG_ON(write > BUF_PAGE_SIZE);
+
+        event = __rb_page_index(tail_page, tail);
+        rb_update_event(event, type, length);
+
+        /*
+         * If this is a commit and the tail is zero, then update
+         * this page's time stamp.
+         */
+        if (!tail && rb_is_commit(cpu_buffer, event))
+                cpu_buffer->commit_page->time_stamp = *ts;
+
+        return event;
+
+ out_unlock:
+        spin_unlock_irqrestore(&cpu_buffer->lock, flags);
+        return NULL;
+}
+
+static int
+rb_add_time_stamp(struct ring_buffer_per_cpu *cpu_buffer,
+                  u64 *ts, u64 *delta)
+{
+        struct ring_buffer_event *event;
+        static int once;
+        int ret;
+
+        if (unlikely(*delta > (1ULL << 59) && !once++)) {
+                printk(KERN_WARNING "Delta way too big! %llu"
+                       " ts=%llu write stamp = %llu\n",
+                       (unsigned long long)*delta,
+                       (unsigned long long)*ts,
+                       (unsigned long long)cpu_buffer->write_stamp);
+                WARN_ON(1);
+        }
+
+        /*
+         * The delta is too big, we to add a
+         * new timestamp.
+         */
+        event = __rb_reserve_next(cpu_buffer,
+                                  RINGBUF_TYPE_TIME_EXTEND,
+                                  RB_LEN_TIME_EXTEND,
+                                  ts);
+        if (!event)
+                return -EBUSY;
+
+        if (PTR_ERR(event) == -EAGAIN)
+                return -EAGAIN;
+
+        /* Only a commited time event can update the write stamp */
+        if (rb_is_commit(cpu_buffer, event)) {
+                /*
+                 * If this is the first on the page, then we need to
+                 * update the page itself, and just put in a zero.
+                 */
+                if (rb_event_index(event)) {
+                        event->time_delta = *delta & TS_MASK;
+                        event->array[0] = *delta >> TS_SHIFT;
+                } else {
+                        cpu_buffer->commit_page->time_stamp = *ts;
+                        event->time_delta = 0;
+                        event->array[0] = 0;
+                }
+                cpu_buffer->write_stamp = *ts;
+                /* let the caller know this was the commit */
+                ret = 1;
+        } else {
+                /* Darn, this is just wasted space */
+                event->time_delta = 0;
+                event->array[0] = 0;
+                ret = 0;
+        }
+
+        *delta = 0;
+
+        return ret;
+}
+
+static struct ring_buffer_event *
+rb_reserve_next_event(struct ring_buffer_per_cpu *cpu_buffer,
+                      unsigned type, unsigned long length)
+{
+        struct ring_buffer_event *event;
+        u64 ts, delta;
+        int commit = 0;
+        int nr_loops = 0;
+
+ again:
+        /*
+         * We allow for interrupts to reenter here and do a trace.
+         * If one does, it will cause this original code to loop
+         * back here. Even with heavy interrupts happening, this
+         * should only happen a few times in a row. If this happens
+         * 1000 times in a row, there must be either an interrupt
+         * storm or we have something buggy.
+         * Bail!
+         */
+        if (unlikely(++nr_loops > 1000)) {
+                RB_WARN_ON(cpu_buffer, 1);
+                return NULL;
+        }
+
+        ts = ring_buffer_time_stamp(cpu_buffer->cpu);
+
+        /*
+         * Only the first commit can update the timestamp.
+         * Yes there is a race here. If an interrupt comes in
+         * just after the conditional and it traces too, then it
+         * will also check the deltas. More than one timestamp may
+         * also be made. But only the entry that did the actual
+         * commit will be something other than zero.
+         */
+        if (cpu_buffer->tail_page == cpu_buffer->commit_page &&
+            rb_page_write(cpu_buffer->tail_page) ==
+            rb_commit_index(cpu_buffer)) {
+
+                delta = ts - cpu_buffer->write_stamp;
+
+                /* make sure this delta is calculated here */
+                barrier();
+
+                /* Did the write stamp get updated already? */
+                if (unlikely(ts < cpu_buffer->write_stamp))
+                        delta = 0;
+
+                if (test_time_stamp(delta)) {
+
+                        commit = rb_add_time_stamp(cpu_buffer, &ts, &delta);
+
+                        if (commit == -EBUSY)
+                                return NULL;
+
+                        if (commit == -EAGAIN)
+                                goto again;
+
+                        RB_WARN_ON(cpu_buffer, commit < 0);
+                }
+        } else
+                /* Non commits have zero deltas */
+                delta = 0;
+
+        event = __rb_reserve_next(cpu_buffer, type, length, &ts);
+        if (PTR_ERR(event) == -EAGAIN)
+                goto again;
+
+        if (!event) {
+                if (unlikely(commit))
+                        /*
+                         * Ouch! We needed a timestamp and it was commited. But
+                         * we didn't get our event reserved.
+                         */
+                        rb_set_commit_to_write(cpu_buffer);
+                return NULL;
+        }
+
+        /*
+         * If the timestamp was commited, make the commit our entry
+         * now so that we will update it when needed.
+         */
+        if (commit)
+                rb_set_commit_event(cpu_buffer, event);
+        else if (!rb_is_commit(cpu_buffer, event))
+                delta = 0;
+
+        event->time_delta = delta;
+
+        return event;
+}
+
+static DEFINE_PER_CPU(int, rb_need_resched);
+
+/**
+ * ring_buffer_lock_reserve - reserve a part of the buffer
+ * @buffer: the ring buffer to reserve from
+ * @length: the length of the data to reserve (excluding event header)
+ * @flags: a pointer to save the interrupt flags
+ *
+ * Returns a reseverd event on the ring buffer to copy directly to.
+ * The user of this interface will need to get the body to write into
+ * and can use the ring_buffer_event_data() interface.
+ *
+ * The length is the length of the data needed, not the event length
+ * which also includes the event header.
+ *
+ * Must be paired with ring_buffer_unlock_commit, unless NULL is returned.
+ * If NULL is returned, then nothing has been allocated or locked.
+ */
+struct ring_buffer_event *
+ring_buffer_lock_reserve(struct ring_buffer *buffer,
+                         unsigned long length,
+                         unsigned long *flags)
+{
+        struct ring_buffer_per_cpu *cpu_buffer;
+        struct ring_buffer_event *event;
+        int cpu, resched;
+
+        if (ring_buffers_off)
+                return NULL;
+
+        if (atomic_read(&buffer->record_disabled))
+                return NULL;
+
+        /* If we are tracing schedule, we don't want to recurse */
+        resched = need_resched();
+        preempt_disable_notrace();
+
+        cpu = raw_smp_processor_id();
+
+        if (!cpu_isset(cpu, buffer->cpumask))
+                goto out;
+
+        cpu_buffer = buffer->buffers[cpu];
+
+        if (atomic_read(&cpu_buffer->record_disabled))
+                goto out;
+
+        length = rb_calculate_event_length(length);
+        if (length > BUF_PAGE_SIZE)
+                goto out;
+
+        event = rb_reserve_next_event(cpu_buffer, RINGBUF_TYPE_DATA, length);
+        if (!event)
+                goto out;
+
+        /*
+         * Need to store resched state on this cpu.
+         * Only the first needs to.
+         */
+
+        if (preempt_count() == 1)
+                per_cpu(rb_need_resched, cpu) = resched;
+
+        return event;
+
+ out:
+        if (resched)
+                preempt_enable_notrace();
+        else
+                preempt_enable_notrace();
+        return NULL;
+}
+
+static void rb_commit(struct ring_buffer_per_cpu *cpu_buffer,
+                      struct ring_buffer_event *event)
+{
+        cpu_buffer->entries++;
+
+        /* Only process further if we own the commit */
+        if (!rb_is_commit(cpu_buffer, event))
+                return;
+
+        cpu_buffer->write_stamp += event->time_delta;
+
+        rb_set_commit_to_write(cpu_buffer);
+}
+
+/**
+ * ring_buffer_unlock_commit - commit a reserved
+ * @buffer: The buffer to commit to
+ * @event: The event pointer to commit.
+ * @flags: the interrupt flags received from ring_buffer_lock_reserve.
+ *
+ * This commits the data to the ring buffer, and releases any locks held.
+ *
+ * Must be paired with ring_buffer_lock_reserve.
+ */
+int ring_buffer_unlock_commit(struct ring_buffer *buffer,
+                              struct ring_buffer_event *event,
+                              unsigned long flags)
+{
+        struct ring_buffer_per_cpu *cpu_buffer;
+        int cpu = raw_smp_processor_id();
+
+        cpu_buffer = buffer->buffers[cpu];
+
+        rb_commit(cpu_buffer, event);
+
+        /*
+         * Only the last preempt count needs to restore preemption.
+         */
+        if (preempt_count() == 1) {
+                if (per_cpu(rb_need_resched, cpu))
+                        preempt_enable_no_resched_notrace();
+                else
+                        preempt_enable_notrace();
+        } else
+                preempt_enable_no_resched_notrace();
+
+        return 0;
+}
+
+/**
+ * ring_buffer_write - write data to the buffer without reserving
+ * @buffer: The ring buffer to write to.
+ * @length: The length of the data being written (excluding the event header)
+ * @data: The data to write to the buffer.
+ *
+ * This is like ring_buffer_lock_reserve and ring_buffer_unlock_commit as
+ * one function. If you already have the data to write to the buffer, it
+ * may be easier to simply call this function.
+ *
+ * Note, like ring_buffer_lock_reserve, the length is the length of the data
+ * and not the length of the event which would hold the header.
+ */
+int ring_buffer_write(struct ring_buffer *buffer,
+                        unsigned long length,
+                        void *data)
+{
+        struct ring_buffer_per_cpu *cpu_buffer;
+        struct ring_buffer_event *event;
+        unsigned long event_length;
+        void *body;
+        int ret = -EBUSY;
+        int cpu, resched;
+
+        if (ring_buffers_off)
+                return -EBUSY;
+
+        if (atomic_read(&buffer->record_disabled))
+                return -EBUSY;
+
+        resched = need_resched();
+        preempt_disable_notrace();
+
+        cpu = raw_smp_processor_id();
+
+        if (!cpu_isset(cpu, buffer->cpumask))
+                goto out;
+
+        cpu_buffer = buffer->buffers[cpu];
+
+        if (atomic_read(&cpu_buffer->record_disabled))
+                goto out;
+
+        event_length = rb_calculate_event_length(length);
+        event = rb_reserve_next_event(cpu_buffer,
+                                      RINGBUF_TYPE_DATA, event_length);
+        if (!event)
+                goto out;
+
+        body = rb_event_data(event);
+
+        memcpy(body, data, length);
+
+        rb_commit(cpu_buffer, event);
+
+        ret = 0;
+ out:
+        if (resched)
+                preempt_enable_no_resched_notrace();
+        else
+                preempt_enable_notrace();
+
+        return ret;
+}
+
+static inline int rb_per_cpu_empty(struct ring_buffer_per_cpu *cpu_buffer)
+{
+        struct buffer_page *reader = cpu_buffer->reader_page;
+        struct buffer_page *head = cpu_buffer->head_page;
+        struct buffer_page *commit = cpu_buffer->commit_page;
+
+        return reader->read == rb_page_commit(reader) &&
+                (commit == reader ||
+                 (commit == head &&
+                  head->read == rb_page_commit(commit)));
+}
+
+/**
+ * ring_buffer_record_disable - stop all writes into the buffer
+ * @buffer: The ring buffer to stop writes to.
+ *
+ * This prevents all writes to the buffer. Any attempt to write
+ * to the buffer after this will fail and return NULL.
+ *
+ * The caller should call synchronize_sched() after this.
+ */
+void ring_buffer_record_disable(struct ring_buffer *buffer)
+{
+        atomic_inc(&buffer->record_disabled);
+}
+
+/**
+ * ring_buffer_record_enable - enable writes to the buffer
+ * @buffer: The ring buffer to enable writes
+ *
+ * Note, multiple disables will need the same number of enables
+ * to truely enable the writing (much like preempt_disable).
+ */
+void ring_buffer_record_enable(struct ring_buffer *buffer)
+{
+        atomic_dec(&buffer->record_disabled);
+}
+
+/**
+ * ring_buffer_record_disable_cpu - stop all writes into the cpu_buffer
+ * @buffer: The ring buffer to stop writes to.
+ * @cpu: The CPU buffer to stop
+ *
+ * This prevents all writes to the buffer. Any attempt to write
+ * to the buffer after this will fail and return NULL.
+ *
+ * The caller should call synchronize_sched() after this.
+ */
+void ring_buffer_record_disable_cpu(struct ring_buffer *buffer, int cpu)
+{
+        struct ring_buffer_per_cpu *cpu_buffer;
+
+        if (!cpu_isset(cpu, buffer->cpumask))
+                return;
+
+        cpu_buffer = buffer->buffers[cpu];
+        atomic_inc(&cpu_buffer->record_disabled);
+}
+
+/**
+ * ring_buffer_record_enable_cpu - enable writes to the buffer
+ * @buffer: The ring buffer to enable writes
+ * @cpu: The CPU to enable.
+ *
+ * Note, multiple disables will need the same number of enables
+ * to truely enable the writing (much like preempt_disable).
+ */
+void ring_buffer_record_enable_cpu(struct ring_buffer *buffer, int cpu)
+{
+        struct ring_buffer_per_cpu *cpu_buffer;
+
+        if (!cpu_isset(cpu, buffer->cpumask))
+                return;
+
+        cpu_buffer = buffer->buffers[cpu];
+        atomic_dec(&cpu_buffer->record_disabled);
+}
+
+/**
+ * ring_buffer_entries_cpu - get the number of entries in a cpu buffer
+ * @buffer: The ring buffer
+ * @cpu: The per CPU buffer to get the entries from.
+ */
+unsigned long ring_buffer_entries_cpu(struct ring_buffer *buffer, int cpu)
+{
+        struct ring_buffer_per_cpu *cpu_buffer;
+
+        if (!cpu_isset(cpu, buffer->cpumask))
+                return 0;
+
+        cpu_buffer = buffer->buffers[cpu];
+        return cpu_buffer->entries;
+}
+
+/**
+ * ring_buffer_overrun_cpu - get the number of overruns in a cpu_buffer
+ * @buffer: The ring buffer
+ * @cpu: The per CPU buffer to get the number of overruns from
+ */
+unsigned long ring_buffer_overrun_cpu(struct ring_buffer *buffer, int cpu)
+{
+        struct ring_buffer_per_cpu *cpu_buffer;
+
+        if (!cpu_isset(cpu, buffer->cpumask))
+                return 0;
+
+        cpu_buffer = buffer->buffers[cpu];
+        return cpu_buffer->overrun;
+}
+
+/**
+ * ring_buffer_entries - get the number of entries in a buffer
+ * @buffer: The ring buffer
+ *
+ * Returns the total number of entries in the ring buffer
+ * (all CPU entries)
+ */
+unsigned long ring_buffer_entries(struct ring_buffer *buffer)
+{
+        struct ring_buffer_per_cpu *cpu_buffer;
+        unsigned long entries = 0;
+        int cpu;
+
+        /* if you care about this being correct, lock the buffer */
+        for_each_buffer_cpu(buffer, cpu) {
+                cpu_buffer = buffer->buffers[cpu];
+                entries += cpu_buffer->entries;
+        }
+
+        return entries;
+}
+
+/**
+ * ring_buffer_overrun_cpu - get the number of overruns in buffer
+ * @buffer: The ring buffer
+ *
+ * Returns the total number of overruns in the ring buffer
+ * (all CPU entries)
+ */
+unsigned long ring_buffer_overruns(struct ring_buffer *buffer)
+{
+        struct ring_buffer_per_cpu *cpu_buffer;
+        unsigned long overruns = 0;
+        int cpu;
+
+        /* if you care about this being correct, lock the buffer */
+        for_each_buffer_cpu(buffer, cpu) {
+                cpu_buffer = buffer->buffers[cpu];
+                overruns += cpu_buffer->overrun;
+        }
+
+        return overruns;
+}
+
+/**
+ * ring_buffer_iter_reset - reset an iterator
+ * @iter: The iterator to reset
+ *
+ * Resets the iterator, so that it will start from the beginning
+ * again.
+ */
+void ring_buffer_iter_reset(struct ring_buffer_iter *iter)
+{
+        struct ring_buffer_per_cpu *cpu_buffer = iter->cpu_buffer;
+
+        /* Iterator usage is expected to have record disabled */
+        if (list_empty(&cpu_buffer->reader_page->list)) {
+                iter->head_page = cpu_buffer->head_page;
+                iter->head = cpu_buffer->head_page->read;
+        } else {
+                iter->head_page = cpu_buffer->reader_page;
+                iter->head = cpu_buffer->reader_page->read;
+        }
+        if (iter->head)
+                iter->read_stamp = cpu_buffer->read_stamp;
+        else
+                iter->read_stamp = iter->head_page->time_stamp;
+}
+
+/**
+ * ring_buffer_iter_empty - check if an iterator has no more to read
+ * @iter: The iterator to check
+ */
+int ring_buffer_iter_empty(struct ring_buffer_iter *iter)
+{
+        struct ring_buffer_per_cpu *cpu_buffer;
+
+        cpu_buffer = iter->cpu_buffer;
+
+        return iter->head_page == cpu_buffer->commit_page &&
+                iter->head == rb_commit_index(cpu_buffer);
+}
+
+static void
+rb_update_read_stamp(struct ring_buffer_per_cpu *cpu_buffer,
+                     struct ring_buffer_event *event)
+{
+        u64 delta;
+
+        switch (event->type) {
+        case RINGBUF_TYPE_PADDING:
+                return;
+
+        case RINGBUF_TYPE_TIME_EXTEND:
+                delta = event->array[0];
+                delta <<= TS_SHIFT;
+                delta += event->time_delta;
+                cpu_buffer->read_stamp += delta;
+                return;
+
+        case RINGBUF_TYPE_TIME_STAMP:
+                /* FIXME: not implemented */
+                return;
+
+        case RINGBUF_TYPE_DATA:
+                cpu_buffer->read_stamp += event->time_delta;
+                return;
+
+        default:
+                BUG();
+        }
+        return;
+}
+
+static void
+rb_update_iter_read_stamp(struct ring_buffer_iter *iter,
+                          struct ring_buffer_event *event)
+{
+        u64 delta;
+
+        switch (event->type) {
+        case RINGBUF_TYPE_PADDING:
+                return;
+
+        case RINGBUF_TYPE_TIME_EXTEND:
+                delta = event->array[0];
+                delta <<= TS_SHIFT;
+                delta += event->time_delta;
+                iter->read_stamp += delta;
+                return;
+
+        case RINGBUF_TYPE_TIME_STAMP:
+                /* FIXME: not implemented */
+                return;
+
+        case RINGBUF_TYPE_DATA:
+                iter->read_stamp += event->time_delta;
+                return;
+
+        default:
+                BUG();
+        }
+        return;
+}
+
+static struct buffer_page *
+rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
+{
+        struct buffer_page *reader = NULL;
+        unsigned long flags;
+        int nr_loops = 0;
+
+        spin_lock_irqsave(&cpu_buffer->lock, flags);
+
+ again:
+        /*
+         * This should normally only loop twice. But because the
+         * start of the reader inserts an empty page, it causes
+         * a case where we will loop three times. There should be no
+         * reason to loop four times (that I know of).
+         */
+        if (unlikely(++nr_loops > 3)) {
+                RB_WARN_ON(cpu_buffer, 1);
+                reader = NULL;
+                goto out;
+        }
+
+        reader = cpu_buffer->reader_page;
+
+        /* If there's more to read, return this page */
+        if (cpu_buffer->reader_page->read < rb_page_size(reader))
+                goto out;
+
+        /* Never should we have an index greater than the size */
+        RB_WARN_ON(cpu_buffer,
+                   cpu_buffer->reader_page->read > rb_page_size(reader));
+
+        /* check if we caught up to the tail */
+        reader = NULL;
+        if (cpu_buffer->commit_page == cpu_buffer->reader_page)
+                goto out;
+
+        /*
+         * Splice the empty reader page into the list around the head.
+         * Reset the reader page to size zero.
+         */
+
+        reader = cpu_buffer->head_page;
+        cpu_buffer->reader_page->list.next = reader->list.next;
+        cpu_buffer->reader_page->list.prev = reader->list.prev;
+
+        local_set(&cpu_buffer->reader_page->write, 0);
+        local_set(&cpu_buffer->reader_page->commit, 0);
+
+        /* Make the reader page now replace the head */
+        reader->list.prev->next = &cpu_buffer->reader_page->list;
+        reader->list.next->prev = &cpu_buffer->reader_page->list;
+
+        /*
+         * If the tail is on the reader, then we must set the head
+         * to the inserted page, otherwise we set it one before.
+         */
+        cpu_buffer->head_page = cpu_buffer->reader_page;
+
+        if (cpu_buffer->commit_page != reader)
+                rb_inc_page(cpu_buffer, &cpu_buffer->head_page);
+
+        /* Finally update the reader page to the new head */
+        cpu_buffer->reader_page = reader;
+        rb_reset_reader_page(cpu_buffer);
+
+        goto again;
+
+ out:
+        spin_unlock_irqrestore(&cpu_buffer->lock, flags);
+
+        return reader;
+}
+
+static void rb_advance_reader(struct ring_buffer_per_cpu *cpu_buffer)
+{
+        struct ring_buffer_event *event;
+        struct buffer_page *reader;
+        unsigned length;
+
+        reader = rb_get_reader_page(cpu_buffer);
+
+        /* This function should not be called when buffer is empty */
+        BUG_ON(!reader);
+
+        event = rb_reader_event(cpu_buffer);
+
+        if (event->type == RINGBUF_TYPE_DATA)
+                cpu_buffer->entries--;
+
+        rb_update_read_stamp(cpu_buffer, event);
+
+        length = rb_event_length(event);
+        cpu_buffer->reader_page->read += length;
+}
+
+static void rb_advance_iter(struct ring_buffer_iter *iter)
+{
+        struct ring_buffer *buffer;
+        struct ring_buffer_per_cpu *cpu_buffer;
+        struct ring_buffer_event *event;
+        unsigned length;
+
+        cpu_buffer = iter->cpu_buffer;
+        buffer = cpu_buffer->buffer;
+
+        /*
+         * Check if we are at the end of the buffer.
+         */
+        if (iter->head >= rb_page_size(iter->head_page)) {
+                BUG_ON(iter->head_page == cpu_buffer->commit_page);
+                rb_inc_iter(iter);
+                return;
+        }
+
+        event = rb_iter_head_event(iter);
+
+        length = rb_event_length(event);
+
+        /*
+         * This should not be called to advance the header if we are
+         * at the tail of the buffer.
+         */
+        BUG_ON((iter->head_page == cpu_buffer->commit_page) &&
+               (iter->head + length > rb_commit_index(cpu_buffer)));
+
+        rb_update_iter_read_stamp(iter, event);
+
+        iter->head += length;
+
+        /* check for end of page padding */
+        if ((iter->head >= rb_page_size(iter->head_page)) &&
+            (iter->head_page != cpu_buffer->commit_page))
+                rb_advance_iter(iter);
+}
+
+/**
+ * ring_buffer_peek - peek at the next event to be read
+ * @buffer: The ring buffer to read
+ * @cpu: The cpu to peak at
+ * @ts: The timestamp counter of this event.
+ *
+ * This will return the event that will be read next, but does
+ * not consume the data.
+ */
+struct ring_buffer_event *
+ring_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts)
+{
+        struct ring_buffer_per_cpu *cpu_buffer;
+        struct ring_buffer_event *event;
+        struct buffer_page *reader;
+        int nr_loops = 0;
+
+        if (!cpu_isset(cpu, buffer->cpumask))
+                return NULL;
+
+        cpu_buffer = buffer->buffers[cpu];
+
+ again:
+        /*
+         * We repeat when a timestamp is encountered. It is possible
+         * to get multiple timestamps from an interrupt entering just
+         * as one timestamp is about to be written. The max times
+         * that this can happen is the number of nested interrupts we
+         * can have.  Nesting 10 deep of interrupts is clearly
+         * an anomaly.
+         */
+        if (unlikely(++nr_loops > 10)) {
+                RB_WARN_ON(cpu_buffer, 1);
+                return NULL;
+        }
+
+        reader = rb_get_reader_page(cpu_buffer);
+        if (!reader)
+                return NULL;
+
+        event = rb_reader_event(cpu_buffer);
+
+        switch (event->type) {
+        case RINGBUF_TYPE_PADDING:
+                RB_WARN_ON(cpu_buffer, 1);
+                rb_advance_reader(cpu_buffer);
+                return NULL;
+
+        case RINGBUF_TYPE_TIME_EXTEND:
+                /* Internal data, OK to advance */
+                rb_advance_reader(cpu_buffer);
+                goto again;
+
+        case RINGBUF_TYPE_TIME_STAMP:
+                /* FIXME: not implemented */
+                rb_advance_reader(cpu_buffer);
+                goto again;
+
+        case RINGBUF_TYPE_DATA:
+                if (ts) {
+                        *ts = cpu_buffer->read_stamp + event->time_delta;
+                        ring_buffer_normalize_time_stamp(cpu_buffer->cpu, ts);
+                }
+                return event;
+
+        default:
+                BUG();
+        }
+
+        return NULL;
+}
+
+/**
+ * ring_buffer_iter_peek - peek at the next event to be read
+ * @iter: The ring buffer iterator
+ * @ts: The timestamp counter of this event.
+ *
+ * This will return the event that will be read next, but does
+ * not increment the iterator.
+ */
+struct ring_buffer_event *
+ring_buffer_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
+{
+        struct ring_buffer *buffer;
+        struct ring_buffer_per_cpu *cpu_buffer;
+        struct ring_buffer_event *event;
+        int nr_loops = 0;
+
+        if (ring_buffer_iter_empty(iter))
+                return NULL;
+
+        cpu_buffer = iter->cpu_buffer;
+        buffer = cpu_buffer->buffer;
+
+ again:
+        /*
+         * We repeat when a timestamp is encountered. It is possible
+         * to get multiple timestamps from an interrupt entering just
+         * as one timestamp is about to be written. The max times
+         * that this can happen is the number of nested interrupts we
+         * can have. Nesting 10 deep of interrupts is clearly
+         * an anomaly.
+         */
+        if (unlikely(++nr_loops > 10)) {
+                RB_WARN_ON(cpu_buffer, 1);
+                return NULL;
+        }
+
+        if (rb_per_cpu_empty(cpu_buffer))
+                return NULL;
+
+        event = rb_iter_head_event(iter);
+
+        switch (event->type) {
+        case RINGBUF_TYPE_PADDING:
+                rb_inc_iter(iter);
+                goto again;
+
+        case RINGBUF_TYPE_TIME_EXTEND:
+                /* Internal data, OK to advance */
+                rb_advance_iter(iter);
+                goto again;
+
+        case RINGBUF_TYPE_TIME_STAMP:
+                /* FIXME: not implemented */
+                rb_advance_iter(iter);
+                goto again;
+
+        case RINGBUF_TYPE_DATA:
+                if (ts) {
+                        *ts = iter->read_stamp + event->time_delta;
+                        ring_buffer_normalize_time_stamp(cpu_buffer->cpu, ts);
+                }
+                return event;
+
+        default:
+                BUG();
+        }
+
+        return NULL;
+}
+
+/**
+ * ring_buffer_consume - return an event and consume it
+ * @buffer: The ring buffer to get the next event from
+ *
+ * Returns the next event in the ring buffer, and that event is consumed.
+ * Meaning, that sequential reads will keep returning a different event,
+ * and eventually empty the ring buffer if the producer is slower.
+ */
+struct ring_buffer_event *
+ring_buffer_consume(struct ring_buffer *buffer, int cpu, u64 *ts)
+{
+        struct ring_buffer_per_cpu *cpu_buffer;
+        struct ring_buffer_event *event;
+
+        if (!cpu_isset(cpu, buffer->cpumask))
+                return NULL;
+
+        event = ring_buffer_peek(buffer, cpu, ts);
+        if (!event)
+                return NULL;
+
+        cpu_buffer = buffer->buffers[cpu];
+        rb_advance_reader(cpu_buffer);
+
+        return event;
+}
+
+/**
+ * ring_buffer_read_start - start a non consuming read of the buffer
+ * @buffer: The ring buffer to read from
+ * @cpu: The cpu buffer to iterate over
+ *
+ * This starts up an iteration through the buffer. It also disables
+ * the recording to the buffer until the reading is finished.
+ * This prevents the reading from being corrupted. This is not
+ * a consuming read, so a producer is not expected.
+ *
+ * Must be paired with ring_buffer_finish.
+ */
+struct ring_buffer_iter *
+ring_buffer_read_start(struct ring_buffer *buffer, int cpu)
+{
+        struct ring_buffer_per_cpu *cpu_buffer;
+        struct ring_buffer_iter *iter;
+        unsigned long flags;
+
+        if (!cpu_isset(cpu, buffer->cpumask))
+                return NULL;
+
+        iter = kmalloc(sizeof(*iter), GFP_KERNEL);
+        if (!iter)
+                return NULL;
+
+        cpu_buffer = buffer->buffers[cpu];
+
+        iter->cpu_buffer = cpu_buffer;
+
+        atomic_inc(&cpu_buffer->record_disabled);
+        synchronize_sched();
+
+        spin_lock_irqsave(&cpu_buffer->lock, flags);
+        ring_buffer_iter_reset(iter);
+        spin_unlock_irqrestore(&cpu_buffer->lock, flags);
+
+        return iter;
+}
+
+/**
+ * ring_buffer_finish - finish reading the iterator of the buffer
+ * @iter: The iterator retrieved by ring_buffer_start
+ *
+ * This re-enables the recording to the buffer, and frees the
+ * iterator.
+ */
+void
+ring_buffer_read_finish(struct ring_buffer_iter *iter)
+{
+        struct ring_buffer_per_cpu *cpu_buffer = iter->cpu_buffer;
+
+        atomic_dec(&cpu_buffer->record_disabled);
+        kfree(iter);
+}
+
+/**
+ * ring_buffer_read - read the next item in the ring buffer by the iterator
+ * @iter: The ring buffer iterator
+ * @ts: The time stamp of the event read.
+ *
+ * This reads the next event in the ring buffer and increments the iterator.
+ */
+struct ring_buffer_event *
+ring_buffer_read(struct ring_buffer_iter *iter, u64 *ts)
+{
+        struct ring_buffer_event *event;
+
+        event = ring_buffer_iter_peek(iter, ts);
+        if (!event)
+                return NULL;
+
+        rb_advance_iter(iter);
+
+        return event;
+}
+
+/**
+ * ring_buffer_size - return the size of the ring buffer (in bytes)
+ * @buffer: The ring buffer.
+ */
+unsigned long ring_buffer_size(struct ring_buffer *buffer)
+{
+        return BUF_PAGE_SIZE * buffer->pages;
+}
+
+static void
+rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer)
+{
+        cpu_buffer->head_page
+                = list_entry(cpu_buffer->pages.next, struct buffer_page, list);
+        local_set(&cpu_buffer->head_page->write, 0);
+        local_set(&cpu_buffer->head_page->commit, 0);
+
+        cpu_buffer->head_page->read = 0;
+
+        cpu_buffer->tail_page = cpu_buffer->head_page;
+        cpu_buffer->commit_page = cpu_buffer->head_page;
+
+        INIT_LIST_HEAD(&cpu_buffer->reader_page->list);
+        local_set(&cpu_buffer->reader_page->write, 0);
+        local_set(&cpu_buffer->reader_page->commit, 0);
+        cpu_buffer->reader_page->read = 0;
+
+        cpu_buffer->overrun = 0;
+        cpu_buffer->entries = 0;
+}
+
+/**
+ * ring_buffer_reset_cpu - reset a ring buffer per CPU buffer
+ * @buffer: The ring buffer to reset a per cpu buffer of
+ * @cpu: The CPU buffer to be reset
+ */
+void ring_buffer_reset_cpu(struct ring_buffer *buffer, int cpu)
+{
+        struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[cpu];
+        unsigned long flags;
+
+        if (!cpu_isset(cpu, buffer->cpumask))
+                return;
+
+        spin_lock_irqsave(&cpu_buffer->lock, flags);
+
+        rb_reset_cpu(cpu_buffer);
+
+        spin_unlock_irqrestore(&cpu_buffer->lock, flags);
+}
+
+/**
+ * ring_buffer_reset - reset a ring buffer
+ * @buffer: The ring buffer to reset all cpu buffers
+ */
+void ring_buffer_reset(struct ring_buffer *buffer)
+{
+        int cpu;
+
+        for_each_buffer_cpu(buffer, cpu)
+                ring_buffer_reset_cpu(buffer, cpu);
+}
+
+/**
+ * rind_buffer_empty - is the ring buffer empty?
+ * @buffer: The ring buffer to test
+ */
+int ring_buffer_empty(struct ring_buffer *buffer)
+{
+        struct ring_buffer_per_cpu *cpu_buffer;
+        int cpu;
+
+        /* yes this is racy, but if you don't like the race, lock the buffer */
+        for_each_buffer_cpu(buffer, cpu) {
+                cpu_buffer = buffer->buffers[cpu];
+                if (!rb_per_cpu_empty(cpu_buffer))
+                        return 0;
+        }
+        return 1;
+}
+
+/**
+ * ring_buffer_empty_cpu - is a cpu buffer of a ring buffer empty?
+ * @buffer: The ring buffer
+ * @cpu: The CPU buffer to test
+ */
+int ring_buffer_empty_cpu(struct ring_buffer *buffer, int cpu)
+{
+        struct ring_buffer_per_cpu *cpu_buffer;
+
+        if (!cpu_isset(cpu, buffer->cpumask))
+                return 1;
+
+        cpu_buffer = buffer->buffers[cpu];
+        return rb_per_cpu_empty(cpu_buffer);
+}
+
+/**
+ * ring_buffer_swap_cpu - swap a CPU buffer between two ring buffers
+ * @buffer_a: One buffer to swap with
+ * @buffer_b: The other buffer to swap with
+ *
+ * This function is useful for tracers that want to take a "snapshot"
+ * of a CPU buffer and has another back up buffer lying around.
+ * it is expected that the tracer handles the cpu buffer not being
+ * used at the moment.
+ */
+int ring_buffer_swap_cpu(struct ring_buffer *buffer_a,
+                         struct ring_buffer *buffer_b, int cpu)
+{
+        struct ring_buffer_per_cpu *cpu_buffer_a;
+        struct ring_buffer_per_cpu *cpu_buffer_b;
+
+        if (!cpu_isset(cpu, buffer_a->cpumask) ||
+            !cpu_isset(cpu, buffer_b->cpumask))
+                return -EINVAL;
+
+        /* At least make sure the two buffers are somewhat the same */
+        if (buffer_a->size != buffer_b->size ||
+            buffer_a->pages != buffer_b->pages)
+                return -EINVAL;
+
+        cpu_buffer_a = buffer_a->buffers[cpu];
+        cpu_buffer_b = buffer_b->buffers[cpu];
+
+        /*
+         * We can't do a synchronize_sched here because this
+         * function can be called in atomic context.
+         * Normally this will be called from the same CPU as cpu.
+         * If not it's up to the caller to protect this.
+         */
+        atomic_inc(&cpu_buffer_a->record_disabled);
+        atomic_inc(&cpu_buffer_b->record_disabled);
+
+        buffer_a->buffers[cpu] = cpu_buffer_b;
+        buffer_b->buffers[cpu] = cpu_buffer_a;
+
+        cpu_buffer_b->buffer = buffer_a;
+        cpu_buffer_a->buffer = buffer_b;
+
+        atomic_dec(&cpu_buffer_a->record_disabled);
+        atomic_dec(&cpu_buffer_b->record_disabled);
+
+        return 0;
+}
+
+static ssize_t
+rb_simple_read(struct file *filp, char __user *ubuf,
+               size_t cnt, loff_t *ppos)
+{
+        int *p = filp->private_data;
+        char buf[64];
+        int r;
+
+        /* !ring_buffers_off == tracing_on */
+        r = sprintf(buf, "%d\n", !*p);
+
+        return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
+}
+
+static ssize_t
+rb_simple_write(struct file *filp, const char __user *ubuf,
+                size_t cnt, loff_t *ppos)
+{
+        int *p = filp->private_data;
+        char buf[64];
+        long val;
+        int ret;
+
+        if (cnt >= sizeof(buf))
+                return -EINVAL;
+
+        if (copy_from_user(&buf, ubuf, cnt))
+                return -EFAULT;
+
+        buf[cnt] = 0;
+
+        ret = strict_strtoul(buf, 10, &val);
+        if (ret < 0)
+                return ret;
+
+        /* !ring_buffers_off == tracing_on */
+        *p = !val;
+
+        (*ppos)++;
+
+        return cnt;
+}
+
+static struct file_operations rb_simple_fops = {
+        .open           = tracing_open_generic,
+        .read           = rb_simple_read,
+        .write          = rb_simple_write,
+};
+
+
+static __init int rb_init_debugfs(void)
+{
+        struct dentry *d_tracer;
+        struct dentry *entry;
+
+        d_tracer = tracing_init_dentry();
+
+        entry = debugfs_create_file("tracing_on", 0644, d_tracer,
+                                    &ring_buffers_off, &rb_simple_fops);
+        if (!entry)
+                pr_warning("Could not create debugfs 'tracing_on' entry\n");
+
+        return 0;
+}
+
+fs_initcall(rb_init_debugfs);
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 8f3fb3db61c3..d86e3252f300 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -14,6 +14,7 @@
 #include <linux/utsrelease.h>
 #include <linux/kallsyms.h>
 #include <linux/seq_file.h>
+#include <linux/notifier.h>
 #include <linux/debugfs.h>
 #include <linux/pagemap.h>
 #include <linux/hardirq.h>
@@ -22,6 +23,7 @@
 #include <linux/ftrace.h>
 #include <linux/module.h>
 #include <linux/percpu.h>
+#include <linux/kdebug.h>
 #include <linux/ctype.h>
 #include <linux/init.h>
 #include <linux/poll.h>
@@ -31,25 +33,37 @@
 #include <linux/writeback.h>
 
 #include <linux/stacktrace.h>
+#include <linux/ring_buffer.h>
+#include <linux/irqflags.h>
 
 #include "trace.h"
 
+#define TRACE_BUFFER_FLAGS      (RB_FL_OVERWRITE)
+
 unsigned long __read_mostly     tracing_max_latency = (cycle_t)ULONG_MAX;
 unsigned long __read_mostly     tracing_thresh;
 
-static unsigned long __read_mostly      tracing_nr_buffers;
+static DEFINE_PER_CPU(local_t, ftrace_cpu_disabled);
+
+static inline void ftrace_disable_cpu(void)
+{
+        preempt_disable();
+        local_inc(&__get_cpu_var(ftrace_cpu_disabled));
+}
+
+static inline void ftrace_enable_cpu(void)
+{
+        local_dec(&__get_cpu_var(ftrace_cpu_disabled));
+        preempt_enable();
+}
+
 static cpumask_t __read_mostly          tracing_buffer_mask;
 
 #define for_each_tracing_cpu(cpu)       \
         for_each_cpu_mask(cpu, tracing_buffer_mask)
 
-static int trace_alloc_page(void);
-static int trace_free_page(void);
-
 static int tracing_disabled = 1;
 
-static unsigned long tracing_pages_allocated;
-
 long
 ns2usecs(cycle_t nsec)
 {
@@ -60,7 +74,9 @@ ns2usecs(cycle_t nsec)
 
 cycle_t ftrace_now(int cpu)
 {
-        return cpu_clock(cpu);
+        u64 ts = ring_buffer_time_stamp(cpu);
+        ring_buffer_normalize_time_stamp(cpu, &ts);
+        return ts;
 }
 
 /*
@@ -100,11 +116,18 @@ static int			tracer_enabled = 1;
 int                             ftrace_function_enabled;
 
 /*
- * trace_nr_entries is the number of entries that is allocated
- * for a buffer. Note, the number of entries is always rounded
- * to ENTRIES_PER_PAGE.
+ * trace_buf_size is the size in bytes that is allocated
+ * for a buffer. Note, the number of bytes is always rounded
+ * to page size.
+ *
+ * This number is purposely set to a low number of 16384.
+ * If the dump on oops happens, it will be much appreciated
+ * to not have to wait for all that output. Anyway this can be
+ * boot time and run time configurable.
  */
-static unsigned long            trace_nr_entries = 65536UL;
+#define TRACE_BUF_SIZE_DEFAULT  1441792UL /* 16384 * 88 (sizeof(entry)) */
+
+static unsigned long            trace_buf_size = TRACE_BUF_SIZE_DEFAULT;
 
 /* trace_types holds a link list of available tracers. */
 static struct tracer            *trace_types __read_mostly;
@@ -133,24 +156,6 @@ static DECLARE_WAIT_QUEUE_HEAD(trace_wait);
 /* trace_flags holds iter_ctrl options */
 unsigned long trace_flags = TRACE_ITER_PRINT_PARENT;
 
-static notrace void no_trace_init(struct trace_array *tr)
-{
-        int cpu;
-
-        ftrace_function_enabled = 0;
-        if(tr->ctrl)
-                for_each_online_cpu(cpu)
-                        tracing_reset(tr->data[cpu]);
-        tracer_enabled = 0;
-}
-
-/* dummy trace to disable tracing */
-static struct tracer no_tracer __read_mostly = {
-        .name           = "none",
-        .init           = no_trace_init
-};
-
-
 /**
  * trace_wake_up - wake up tasks waiting for trace input
  *
@@ -167,23 +172,21 @@ void trace_wake_up(void)
                 wake_up(&trace_wait);
 }
 
-#define ENTRIES_PER_PAGE (PAGE_SIZE / sizeof(struct trace_entry))
-
-static int __init set_nr_entries(char *str)
+static int __init set_buf_size(char *str)
 {
-        unsigned long nr_entries;
+        unsigned long buf_size;
         int ret;
 
         if (!str)
                 return 0;
-        ret = strict_strtoul(str, 0, &nr_entries);
+        ret = strict_strtoul(str, 0, &buf_size);
         /* nr_entries can not be zero */
-        if (ret < 0 || nr_entries == 0)
+        if (ret < 0 || buf_size == 0)
                 return 0;
-        trace_nr_entries = nr_entries;
+        trace_buf_size = buf_size;
         return 1;
 }
-__setup("trace_entries=", set_nr_entries);
+__setup("trace_buf_size=", set_buf_size);
 
 unsigned long nsecs_to_usecs(unsigned long nsecs)
 {
@@ -191,21 +194,6 @@ unsigned long nsecs_to_usecs(unsigned long nsecs)
 }
 
 /*
- * trace_flag_type is an enumeration that holds different
- * states when a trace occurs. These are:
- *  IRQS_OFF    - interrupts were disabled
- *  NEED_RESCED - reschedule is requested
- *  HARDIRQ     - inside an interrupt handler
- *  SOFTIRQ     - inside a softirq handler
- */
-enum trace_flag_type {
-        TRACE_FLAG_IRQS_OFF             = 0x01,
-        TRACE_FLAG_NEED_RESCHED         = 0x02,
-        TRACE_FLAG_HARDIRQ              = 0x04,
-        TRACE_FLAG_SOFTIRQ              = 0x08,
-};
-
-/*
  * TRACE_ITER_SYM_MASK masks the options in trace_flags that
  * control the output of kernel symbols.
  */
@@ -224,6 +212,7 @@ static const char *trace_options[] = {
         "block",
         "stacktrace",
         "sched-tree",
+        "ftrace_printk",
         NULL
 };
 
@@ -266,54 +255,6 @@ __update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
         tracing_record_cmdline(current);
 }
 
-#define CHECK_COND(cond)                        \
-        if (unlikely(cond)) {                   \
-                tracing_disabled = 1;           \
-                WARN_ON(1);                     \
-                return -1;                      \
-        }
-
-/**
- * check_pages - integrity check of trace buffers
- *
- * As a safty measure we check to make sure the data pages have not
- * been corrupted.
- */
-int check_pages(struct trace_array_cpu *data)
-{
-        struct page *page, *tmp;
-
-        CHECK_COND(data->trace_pages.next->prev != &data->trace_pages);
-        CHECK_COND(data->trace_pages.prev->next != &data->trace_pages);
-
-        list_for_each_entry_safe(page, tmp, &data->trace_pages, lru) {
-                CHECK_COND(page->lru.next->prev != &page->lru);
-                CHECK_COND(page->lru.prev->next != &page->lru);
-        }
-
-        return 0;
-}
-
-/**
- * head_page - page address of the first page in per_cpu buffer.
- *
- * head_page returns the page address of the first page in
- * a per_cpu buffer. This also preforms various consistency
- * checks to make sure the buffer has not been corrupted.
- */
-void *head_page(struct trace_array_cpu *data)
-{
-        struct page *page;
-
-        if (list_empty(&data->trace_pages))
-                return NULL;
-
-        page = list_entry(data->trace_pages.next, struct page, lru);
-        BUG_ON(&page->lru == &data->trace_pages);
-
-        return page_address(page);
-}
-
 /**
  * trace_seq_printf - sequence printing of trace information
  * @s: trace sequence descriptor
@@ -395,28 +336,23 @@ trace_seq_putmem(struct trace_seq *s, void *mem, size_t len)
         return len;
 }
 
-#define HEX_CHARS 17
-static const char hex2asc[] = "0123456789abcdef";
+#define MAX_MEMHEX_BYTES        8
+#define HEX_CHARS               (MAX_MEMHEX_BYTES*2 + 1)
 
 static int
 trace_seq_putmem_hex(struct trace_seq *s, void *mem, size_t len)
 {
         unsigned char hex[HEX_CHARS];
         unsigned char *data = mem;
-        unsigned char byte;
         int i, j;
 
-        BUG_ON(len >= HEX_CHARS);
-
 #ifdef __BIG_ENDIAN
         for (i = 0, j = 0; i < len; i++) {
 #else
         for (i = len-1, j = 0; i >= 0; i--) {
 #endif
-                byte = data[i];
-
-                hex[j++] = hex2asc[byte & 0x0f];
-                hex[j++] = hex2asc[byte >> 4];
+                hex[j++] = hex_asc_hi(data[i]);
+                hex[j++] = hex_asc_lo(data[i]);
         }
         hex[j++] = ' ';
 
@@ -460,34 +396,6 @@ trace_print_seq(struct seq_file *m, struct trace_seq *s)
         trace_seq_reset(s);
 }
 
-/*
- * flip the trace buffers between two trace descriptors.
- * This usually is the buffers between the global_trace and
- * the max_tr to record a snapshot of a current trace.
- *
- * The ftrace_max_lock must be held.
- */
-static void
-flip_trace(struct trace_array_cpu *tr1, struct trace_array_cpu *tr2)
-{
-        struct list_head flip_pages;
-
-        INIT_LIST_HEAD(&flip_pages);
-
-        memcpy(&tr1->trace_head_idx, &tr2->trace_head_idx,
-                sizeof(struct trace_array_cpu) -
-                offsetof(struct trace_array_cpu, trace_head_idx));
-
-        check_pages(tr1);
-        check_pages(tr2);
-        list_splice_init(&tr1->trace_pages, &flip_pages);
-        list_splice_init(&tr2->trace_pages, &tr1->trace_pages);
-        list_splice_init(&flip_pages, &tr2->trace_pages);
-        BUG_ON(!list_empty(&flip_pages));
-        check_pages(tr1);
-        check_pages(tr2);
-}
-
 /**
  * update_max_tr - snapshot all trace buffers from global_trace to max_tr
  * @tr: tracer
@@ -500,17 +408,17 @@ flip_trace(struct trace_array_cpu *tr1, struct trace_array_cpu *tr2)
 void
 update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
 {
-        struct trace_array_cpu *data;
-        int i;
+        struct ring_buffer *buf = tr->buffer;
 
         WARN_ON_ONCE(!irqs_disabled());
         __raw_spin_lock(&ftrace_max_lock);
-        /* clear out all the previous traces */
-        for_each_tracing_cpu(i) {
-                data = tr->data[i];
-                flip_trace(max_tr.data[i], data);
-                tracing_reset(data);
-        }
+
+        tr->buffer = max_tr.buffer;
+        max_tr.buffer = buf;
+
+        ftrace_disable_cpu();
+        ring_buffer_reset(tr->buffer);
+        ftrace_enable_cpu();
 
         __update_max_tr(tr, tsk, cpu);
         __raw_spin_unlock(&ftrace_max_lock);
@@ -527,16 +435,19 @@ update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
 void
 update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu)
 {
-        struct trace_array_cpu *data = tr->data[cpu];
-        int i;
+        int ret;
 
         WARN_ON_ONCE(!irqs_disabled());
         __raw_spin_lock(&ftrace_max_lock);
-        for_each_tracing_cpu(i)
-                tracing_reset(max_tr.data[i]);
 
-        flip_trace(max_tr.data[cpu], data);
-        tracing_reset(data);
+        ftrace_disable_cpu();
+
+        ring_buffer_reset(max_tr.buffer);
+        ret = ring_buffer_swap_cpu(max_tr.buffer, tr->buffer, cpu);
+
+        ftrace_enable_cpu();
+
+        WARN_ON_ONCE(ret);
 
         __update_max_tr(tr, tsk, cpu);
         __raw_spin_unlock(&ftrace_max_lock);
@@ -573,7 +484,6 @@ int register_tracer(struct tracer *type)
 #ifdef CONFIG_FTRACE_STARTUP_TEST
         if (type->selftest) {
                 struct tracer *saved_tracer = current_trace;
-                struct trace_array_cpu *data;
                 struct trace_array *tr = &global_trace;
                 int saved_ctrl = tr->ctrl;
                 int i;
@@ -585,10 +495,7 @@ int register_tracer(struct tracer *type)
                  * If we fail, we do not register this tracer.
                  */
                 for_each_tracing_cpu(i) {
-                        data = tr->data[i];
-                        if (!head_page(data))
-                                continue;
-                        tracing_reset(data);
+                        tracing_reset(tr, i);
                 }
                 current_trace = type;
                 tr->ctrl = 0;
@@ -604,10 +511,7 @@ int register_tracer(struct tracer *type)
                 }
                 /* Only reset on passing, to avoid touching corrupted buffers */
                 for_each_tracing_cpu(i) {
-                        data = tr->data[i];
-                        if (!head_page(data))
-                                continue;
-                        tracing_reset(data);
+                        tracing_reset(tr, i);
                 }
                 printk(KERN_CONT "PASSED\n");
         }
@@ -653,13 +557,11 @@ void unregister_tracer(struct tracer *type)
         mutex_unlock(&trace_types_lock);
 }
 
-void tracing_reset(struct trace_array_cpu *data)
+void tracing_reset(struct trace_array *tr, int cpu)
 {
-        data->trace_idx = 0;
-        data->overrun = 0;
-        data->trace_head = data->trace_tail = head_page(data);
-        data->trace_head_idx = 0;
-        data->trace_tail_idx = 0;
+        ftrace_disable_cpu();
+        ring_buffer_reset_cpu(tr->buffer, cpu);
+        ftrace_enable_cpu();
 }
 
 #define SAVED_CMDLINES 128
@@ -745,82 +647,20 @@ void tracing_record_cmdline(struct task_struct *tsk)
         trace_save_cmdline(tsk);
 }
 
-static inline struct list_head *
-trace_next_list(struct trace_array_cpu *data, struct list_head *next)
-{
-        /*
-         * Roundrobin - but skip the head (which is not a real page):
-         */
-        next = next->next;
-        if (unlikely(next == &data->trace_pages))
-                next = next->next;
-        BUG_ON(next == &data->trace_pages);
-
-        return next;
-}
-
-static inline void *
-trace_next_page(struct trace_array_cpu *data, void *addr)
-{
-        struct list_head *next;
-        struct page *page;
-
-        page = virt_to_page(addr);
-
-        next = trace_next_list(data, &page->lru);
-        page = list_entry(next, struct page, lru);
-
-        return page_address(page);
-}
-
-static inline struct trace_entry *
-tracing_get_trace_entry(struct trace_array *tr, struct trace_array_cpu *data)
-{
-        unsigned long idx, idx_next;
-        struct trace_entry *entry;
-
-        data->trace_idx++;
-        idx = data->trace_head_idx;
-        idx_next = idx + 1;
-
-        BUG_ON(idx * TRACE_ENTRY_SIZE >= PAGE_SIZE);
-
-        entry = data->trace_head + idx * TRACE_ENTRY_SIZE;
-
-        if (unlikely(idx_next >= ENTRIES_PER_PAGE)) {
-                data->trace_head = trace_next_page(data, data->trace_head);
-                idx_next = 0;
-        }
-
-        if (data->trace_head == data->trace_tail &&
-            idx_next == data->trace_tail_idx) {
-                /* overrun */
-                data->overrun++;
-                data->trace_tail_idx++;
-                if (data->trace_tail_idx >= ENTRIES_PER_PAGE) {
-                        data->trace_tail =
-                                trace_next_page(data, data->trace_tail);
-                        data->trace_tail_idx = 0;
-                }
-        }
-
-        data->trace_head_idx = idx_next;
-
-        return entry;
-}
-
-static inline void
-tracing_generic_entry_update(struct trace_entry *entry, unsigned long flags)
+void
+tracing_generic_entry_update(struct trace_entry *entry, unsigned long flags,
+                             int pc)
 {
         struct task_struct *tsk = current;
-        unsigned long pc;
-
-        pc = preempt_count();
 
-        entry->preempt_count    = pc & 0xff;
-        entry->pid              = (tsk) ? tsk->pid : 0;
-        entry->t                = ftrace_now(raw_smp_processor_id());
-        entry->flags = (irqs_disabled_flags(flags) ? TRACE_FLAG_IRQS_OFF : 0) |
+        entry->preempt_count            = pc & 0xff;
+        entry->pid                      = (tsk) ? tsk->pid : 0;
+        entry->flags =
+#ifdef CONFIG_TRACE_IRQFLAGS_SUPPORT
+                (irqs_disabled_flags(flags) ? TRACE_FLAG_IRQS_OFF : 0) |
+#else
+                TRACE_FLAG_IRQS_NOSUPPORT |
+#endif
                 ((pc & HARDIRQ_MASK) ? TRACE_FLAG_HARDIRQ : 0) |
                 ((pc & SOFTIRQ_MASK) ? TRACE_FLAG_SOFTIRQ : 0) |
                 (need_resched() ? TRACE_FLAG_NEED_RESCHED : 0);
@@ -828,145 +668,141 @@ tracing_generic_entry_update(struct trace_entry *entry, unsigned long flags)
 
 void
 trace_function(struct trace_array *tr, struct trace_array_cpu *data,
-               unsigned long ip, unsigned long parent_ip, unsigned long flags)
+               unsigned long ip, unsigned long parent_ip, unsigned long flags,
+               int pc)
 {
-        struct trace_entry *entry;
+        struct ring_buffer_event *event;
+        struct ftrace_entry *entry;
         unsigned long irq_flags;
 
-        raw_local_irq_save(irq_flags);
-        __raw_spin_lock(&data->lock);
-        entry                   = tracing_get_trace_entry(tr, data);
-        tracing_generic_entry_update(entry, flags);
-        entry->type             = TRACE_FN;
-        entry->fn.ip            = ip;
-        entry->fn.parent_ip     = parent_ip;
-        __raw_spin_unlock(&data->lock);
-        raw_local_irq_restore(irq_flags);
+        /* If we are reading the ring buffer, don't trace */
+        if (unlikely(local_read(&__get_cpu_var(ftrace_cpu_disabled))))
+                return;
+
+        event = ring_buffer_lock_reserve(tr->buffer, sizeof(*entry),
+                                         &irq_flags);
+        if (!event)
+                return;
+        entry   = ring_buffer_event_data(event);
+        tracing_generic_entry_update(&entry->ent, flags, pc);
+        entry->ent.type                 = TRACE_FN;
+        entry->ip                       = ip;
+        entry->parent_ip                = parent_ip;
+        ring_buffer_unlock_commit(tr->buffer, event, irq_flags);
 }
 
 void
 ftrace(struct trace_array *tr, struct trace_array_cpu *data,
-       unsigned long ip, unsigned long parent_ip, unsigned long flags)
+       unsigned long ip, unsigned long parent_ip, unsigned long flags,
+       int pc)
 {
         if (likely(!atomic_read(&data->disabled)))
-                trace_function(tr, data, ip, parent_ip, flags);
+                trace_function(tr, data, ip, parent_ip, flags, pc);
 }
 
-#ifdef CONFIG_MMIOTRACE
-void __trace_mmiotrace_rw(struct trace_array *tr, struct trace_array_cpu *data,
-                                                struct mmiotrace_rw *rw)
+static void ftrace_trace_stack(struct trace_array *tr,
+                               struct trace_array_cpu *data,
+                               unsigned long flags,
+                               int skip, int pc)
 {
-        struct trace_entry *entry;
+#ifdef CONFIG_STACKTRACE
+        struct ring_buffer_event *event;
+        struct stack_entry *entry;
+        struct stack_trace trace;
         unsigned long irq_flags;
 
-        raw_local_irq_save(irq_flags);
-        __raw_spin_lock(&data->lock);
-
-        entry                   = tracing_get_trace_entry(tr, data);
-        tracing_generic_entry_update(entry, 0);
-        entry->type             = TRACE_MMIO_RW;
-        entry->mmiorw           = *rw;
-
-        __raw_spin_unlock(&data->lock);
-        raw_local_irq_restore(irq_flags);
-
-        trace_wake_up();
-}
-
-void __trace_mmiotrace_map(struct trace_array *tr, struct trace_array_cpu *data,
-                                                struct mmiotrace_map *map)
-{
-        struct trace_entry *entry;
-        unsigned long irq_flags;
+        if (!(trace_flags & TRACE_ITER_STACKTRACE))
+                return;
 
-        raw_local_irq_save(irq_flags);
-        __raw_spin_lock(&data->lock);
+        event = ring_buffer_lock_reserve(tr->buffer, sizeof(*entry),
+                                         &irq_flags);
+        if (!event)
+                return;
+        entry   = ring_buffer_event_data(event);
+        tracing_generic_entry_update(&entry->ent, flags, pc);
+        entry->ent.type         = TRACE_STACK;
 
-        entry                   = tracing_get_trace_entry(tr, data);
-        tracing_generic_entry_update(entry, 0);
-        entry->type             = TRACE_MMIO_MAP;
-        entry->mmiomap          = *map;
+        memset(&entry->caller, 0, sizeof(entry->caller));
 
-        __raw_spin_unlock(&data->lock);
-        raw_local_irq_restore(irq_flags);
+        trace.nr_entries        = 0;
+        trace.max_entries       = FTRACE_STACK_ENTRIES;
+        trace.skip              = skip;
+        trace.entries           = entry->caller;
 
-        trace_wake_up();
-}
+        save_stack_trace(&trace);
+        ring_buffer_unlock_commit(tr->buffer, event, irq_flags);
 #endif
+}
 
 void __trace_stack(struct trace_array *tr,
                    struct trace_array_cpu *data,
                    unsigned long flags,
                    int skip)
 {
-        struct trace_entry *entry;
-        struct stack_trace trace;
-
-        if (!(trace_flags & TRACE_ITER_STACKTRACE))
-                return;
-
-        entry                   = tracing_get_trace_entry(tr, data);
-        tracing_generic_entry_update(entry, flags);
-        entry->type             = TRACE_STACK;
-
-        memset(&entry->stack, 0, sizeof(entry->stack));
-
-        trace.nr_entries        = 0;
-        trace.max_entries       = FTRACE_STACK_ENTRIES;
-        trace.skip              = skip;
-        trace.entries           = entry->stack.caller;
-
-        save_stack_trace(&trace);
+        ftrace_trace_stack(tr, data, flags, skip, preempt_count());
 }
 
-void
-__trace_special(void *__tr, void *__data,
-                unsigned long arg1, unsigned long arg2, unsigned long arg3)
+static void
+ftrace_trace_special(void *__tr, void *__data,
+                     unsigned long arg1, unsigned long arg2, unsigned long arg3,
+                     int pc)
 {
+        struct ring_buffer_event *event;
         struct trace_array_cpu *data = __data;
         struct trace_array *tr = __tr;
-        struct trace_entry *entry;
+        struct special_entry *entry;
         unsigned long irq_flags;
 
-        raw_local_irq_save(irq_flags);
-        __raw_spin_lock(&data->lock);
-        entry                   = tracing_get_trace_entry(tr, data);
-        tracing_generic_entry_update(entry, 0);
-        entry->type             = TRACE_SPECIAL;
-        entry->special.arg1     = arg1;
-        entry->special.arg2     = arg2;
-        entry->special.arg3     = arg3;
-        __trace_stack(tr, data, irq_flags, 4);
-        __raw_spin_unlock(&data->lock);
-        raw_local_irq_restore(irq_flags);
+        event = ring_buffer_lock_reserve(tr->buffer, sizeof(*entry),
+                                         &irq_flags);
+        if (!event)
+                return;
+        entry   = ring_buffer_event_data(event);
+        tracing_generic_entry_update(&entry->ent, 0, pc);
+        entry->ent.type                 = TRACE_SPECIAL;
+        entry->arg1                     = arg1;
+        entry->arg2                     = arg2;
+        entry->arg3                     = arg3;
+        ring_buffer_unlock_commit(tr->buffer, event, irq_flags);
+        ftrace_trace_stack(tr, data, irq_flags, 4, pc);
 
         trace_wake_up();
 }
 
 void
+__trace_special(void *__tr, void *__data,
+                unsigned long arg1, unsigned long arg2, unsigned long arg3)
+{
+        ftrace_trace_special(__tr, __data, arg1, arg2, arg3, preempt_count());
+}
+
+void
 tracing_sched_switch_trace(struct trace_array *tr,
                            struct trace_array_cpu *data,
                            struct task_struct *prev,
                            struct task_struct *next,
-                           unsigned long flags)
+                           unsigned long flags, int pc)
 {
-        struct trace_entry *entry;
+        struct ring_buffer_event *event;
+        struct ctx_switch_entry *entry;
         unsigned long irq_flags;
 
-        raw_local_irq_save(irq_flags);
-        __raw_spin_lock(&data->lock);
-        entry                   = tracing_get_trace_entry(tr, data);
-        tracing_generic_entry_update(entry, flags);
-        entry->type             = TRACE_CTX;
-        entry->ctx.prev_pid     = prev->pid;
-        entry->ctx.prev_prio    = prev->prio;
-        entry->ctx.prev_state   = prev->state;
-        entry->ctx.next_pid     = next->pid;
-        entry->ctx.next_prio    = next->prio;
-        entry->ctx.next_state   = next->state;
-        __trace_stack(tr, data, flags, 5);
-        __raw_spin_unlock(&data->lock);
-        raw_local_irq_restore(irq_flags);
+        event = ring_buffer_lock_reserve(tr->buffer, sizeof(*entry),
+                                           &irq_flags);
+        if (!event)
+                return;
+        entry   = ring_buffer_event_data(event);
+        tracing_generic_entry_update(&entry->ent, flags, pc);
+        entry->ent.type                 = TRACE_CTX;
+        entry->prev_pid                 = prev->pid;
+        entry->prev_prio                = prev->prio;
+        entry->prev_state               = prev->state;
+        entry->next_pid                 = next->pid;
+        entry->next_prio                = next->prio;
+        entry->next_state               = next->state;
+        entry->next_cpu = task_cpu(next);
+        ring_buffer_unlock_commit(tr->buffer, event, irq_flags);
+        ftrace_trace_stack(tr, data, flags, 5, pc);
 }
 
 void
@@ -974,25 +810,28 @@ tracing_sched_wakeup_trace(struct trace_array *tr,
                            struct trace_array_cpu *data,
                            struct task_struct *wakee,
                            struct task_struct *curr,
-                           unsigned long flags)
+                           unsigned long flags, int pc)
 {
-        struct trace_entry *entry;
+        struct ring_buffer_event *event;
+        struct ctx_switch_entry *entry;
         unsigned long irq_flags;
 
-        raw_local_irq_save(irq_flags);
-        __raw_spin_lock(&data->lock);
-        entry                   = tracing_get_trace_entry(tr, data);
-        tracing_generic_entry_update(entry, flags);
-        entry->type             = TRACE_WAKE;
-        entry->ctx.prev_pid     = curr->pid;
-        entry->ctx.prev_prio    = curr->prio;
-        entry->ctx.prev_state   = curr->state;
-        entry->ctx.next_pid     = wakee->pid;
-        entry->ctx.next_prio    = wakee->prio;
-        entry->ctx.next_state   = wakee->state;
-        __trace_stack(tr, data, flags, 6);
-        __raw_spin_unlock(&data->lock);
-        raw_local_irq_restore(irq_flags);
+        event = ring_buffer_lock_reserve(tr->buffer, sizeof(*entry),
+                                           &irq_flags);
+        if (!event)
+                return;
+        entry   = ring_buffer_event_data(event);
+        tracing_generic_entry_update(&entry->ent, flags, pc);
+        entry->ent.type                 = TRACE_WAKE;
+        entry->prev_pid                 = curr->pid;
+        entry->prev_prio                = curr->prio;
+        entry->prev_state               = curr->state;
+        entry->next_pid                 = wakee->pid;
+        entry->next_prio                = wakee->prio;
+        entry->next_state               = wakee->state;
+        entry->next_cpu                 = task_cpu(wakee);
+        ring_buffer_unlock_commit(tr->buffer, event, irq_flags);
+        ftrace_trace_stack(tr, data, flags, 6, pc);
 
         trace_wake_up();
 }
@@ -1002,26 +841,24 @@ ftrace_special(unsigned long arg1, unsigned long arg2, unsigned long arg3)
 {
         struct trace_array *tr = &global_trace;
         struct trace_array_cpu *data;
-        unsigned long flags;
-        long disabled;
         int cpu;
+        int pc;
 
-        if (tracing_disabled || current_trace == &no_tracer || !tr->ctrl)
+        if (tracing_disabled || !tr->ctrl)
                 return;
 
-        local_irq_save(flags);
+        pc = preempt_count();
+        preempt_disable_notrace();
         cpu = raw_smp_processor_id();
         data = tr->data[cpu];
-        disabled = atomic_inc_return(&data->disabled);
 
-        if (likely(disabled == 1))
-                __trace_special(tr, data, arg1, arg2, arg3);
+        if (likely(!atomic_read(&data->disabled)))
+                ftrace_trace_special(tr, data, arg1, arg2, arg3, pc);
 
-        atomic_dec(&data->disabled);
-        local_irq_restore(flags);
+        preempt_enable_notrace();
 }
 
-#ifdef CONFIG_FTRACE
+#ifdef CONFIG_FUNCTION_TRACER
 static void
 function_trace_call(unsigned long ip, unsigned long parent_ip)
 {
@@ -1029,24 +866,28 @@ function_trace_call(unsigned long ip, unsigned long parent_ip)
         struct trace_array_cpu *data;
         unsigned long flags;
         long disabled;
-        int cpu;
+        int cpu, resched;
+        int pc;
 
         if (unlikely(!ftrace_function_enabled))
                 return;
 
-        if (skip_trace(ip))
-                return;
-
-        local_irq_save(flags);
+        pc = preempt_count();
+        resched = need_resched();
+        preempt_disable_notrace();
+        local_save_flags(flags);
         cpu = raw_smp_processor_id();
         data = tr->data[cpu];
         disabled = atomic_inc_return(&data->disabled);
 
         if (likely(disabled == 1))
-                trace_function(tr, data, ip, parent_ip, flags);
+                trace_function(tr, data, ip, parent_ip, flags, pc);
 
         atomic_dec(&data->disabled);
-        local_irq_restore(flags);
+        if (resched)
+                preempt_enable_no_resched_notrace();
+        else
+                preempt_enable_notrace();
 }
 
 static struct ftrace_ops trace_ops __read_mostly =
@@ -1073,111 +914,96 @@ enum trace_file_type {
         TRACE_FILE_LAT_FMT      = 1,
 };
 
-static struct trace_entry *
-trace_entry_idx(struct trace_array *tr, struct trace_array_cpu *data,
-                struct trace_iterator *iter, int cpu)
+static void trace_iterator_increment(struct trace_iterator *iter, int cpu)
 {
-        struct page *page;
-        struct trace_entry *array;
+        /* Don't allow ftrace to trace into the ring buffers */
+        ftrace_disable_cpu();
 
-        if (iter->next_idx[cpu] >= tr->entries ||
-            iter->next_idx[cpu] >= data->trace_idx ||
-            (data->trace_head == data->trace_tail &&
-             data->trace_head_idx == data->trace_tail_idx))
-                return NULL;
+        iter->idx++;
+        if (iter->buffer_iter[iter->cpu])
+                ring_buffer_read(iter->buffer_iter[iter->cpu], NULL);
 
-        if (!iter->next_page[cpu]) {
-                /* Initialize the iterator for this cpu trace buffer */
-                WARN_ON(!data->trace_tail);
-                page = virt_to_page(data->trace_tail);
-                iter->next_page[cpu] = &page->lru;
-                iter->next_page_idx[cpu] = data->trace_tail_idx;
-        }
+        ftrace_enable_cpu();
+}
 
-        page = list_entry(iter->next_page[cpu], struct page, lru);
-        BUG_ON(&data->trace_pages == &page->lru);
+static struct trace_entry *
+peek_next_entry(struct trace_iterator *iter, int cpu, u64 *ts)
+{
+        struct ring_buffer_event *event;
+        struct ring_buffer_iter *buf_iter = iter->buffer_iter[cpu];
+
+        /* Don't allow ftrace to trace into the ring buffers */
+        ftrace_disable_cpu();
+
+        if (buf_iter)
+                event = ring_buffer_iter_peek(buf_iter, ts);
+        else
+                event = ring_buffer_peek(iter->tr->buffer, cpu, ts);
 
-        array = page_address(page);
+        ftrace_enable_cpu();
 
-        WARN_ON(iter->next_page_idx[cpu] >= ENTRIES_PER_PAGE);
-        return &array[iter->next_page_idx[cpu]];
+        return event ? ring_buffer_event_data(event) : NULL;
 }
 
 static struct trace_entry *
-find_next_entry(struct trace_iterator *iter, int *ent_cpu)
+__find_next_entry(struct trace_iterator *iter, int *ent_cpu, u64 *ent_ts)
 {
-        struct trace_array *tr = iter->tr;
+        struct ring_buffer *buffer = iter->tr->buffer;
         struct trace_entry *ent, *next = NULL;
+        u64 next_ts = 0, ts;
         int next_cpu = -1;
         int cpu;
 
         for_each_tracing_cpu(cpu) {
-                if (!head_page(tr->data[cpu]))
+
+                if (ring_buffer_empty_cpu(buffer, cpu))
                         continue;
-                ent = trace_entry_idx(tr, tr->data[cpu], iter, cpu);
+
+                ent = peek_next_entry(iter, cpu, &ts);
+
                 /*
                  * Pick the entry with the smallest timestamp:
                  */
-                if (ent && (!next || ent->t < next->t)) {
+                if (ent && (!next || ts < next_ts)) {
                         next = ent;
                         next_cpu = cpu;
+                        next_ts = ts;
                 }
         }
 
         if (ent_cpu)
                 *ent_cpu = next_cpu;
 
+        if (ent_ts)
+                *ent_ts = next_ts;
+
         return next;
 }
 
-static void trace_iterator_increment(struct trace_iterator *iter)
+/* Find the next real entry, without updating the iterator itself */
+static struct trace_entry *
+find_next_entry(struct trace_iterator *iter, int *ent_cpu, u64 *ent_ts)
 {
-        iter->idx++;
-        iter->next_idx[iter->cpu]++;
-        iter->next_page_idx[iter->cpu]++;
-
-        if (iter->next_page_idx[iter->cpu] >= ENTRIES_PER_PAGE) {
-                struct trace_array_cpu *data = iter->tr->data[iter->cpu];
-
-                iter->next_page_idx[iter->cpu] = 0;
-                iter->next_page[iter->cpu] =
-                        trace_next_list(data, iter->next_page[iter->cpu]);
-        }
+        return __find_next_entry(iter, ent_cpu, ent_ts);
 }
 
-static void trace_consume(struct trace_iterator *iter)
+/* Find the next real entry, and increment the iterator to the next entry */
+static void *find_next_entry_inc(struct trace_iterator *iter)
 {
-        struct trace_array_cpu *data = iter->tr->data[iter->cpu];
+        iter->ent = __find_next_entry(iter, &iter->cpu, &iter->ts);
 
-        data->trace_tail_idx++;
-        if (data->trace_tail_idx >= ENTRIES_PER_PAGE) {
-                data->trace_tail = trace_next_page(data, data->trace_tail);
-                data->trace_tail_idx = 0;
-        }
+        if (iter->ent)
+                trace_iterator_increment(iter, iter->cpu);
 
-        /* Check if we empty it, then reset the index */
-        if (data->trace_head == data->trace_tail &&
-            data->trace_head_idx == data->trace_tail_idx)
-                data->trace_idx = 0;
+        return iter->ent ? iter : NULL;
 }
 
-static void *find_next_entry_inc(struct trace_iterator *iter)
+static void trace_consume(struct trace_iterator *iter)
 {
-        struct trace_entry *next;
-        int next_cpu = -1;
-
-        next = find_next_entry(iter, &next_cpu);
-
-        iter->prev_ent = iter->ent;
-        iter->prev_cpu = iter->cpu;
-
-        iter->ent = next;
-        iter->cpu = next_cpu;
-
-        if (next)
-                trace_iterator_increment(iter);
-
-        return next ? iter : NULL;
+        /* Don't allow ftrace to trace into the ring buffers */
+        ftrace_disable_cpu();
+        ring_buffer_consume(iter->tr->buffer, iter->cpu, &iter->ts);
+        ftrace_enable_cpu();
 }
 
 static void *s_next(struct seq_file *m, void *v, loff_t *pos)
@@ -1210,7 +1036,7 @@ static void *s_start(struct seq_file *m, loff_t *pos)
         struct trace_iterator *iter = m->private;
         void *p = NULL;
         loff_t l = 0;
-        int i;
+        int cpu;
 
         mutex_lock(&trace_types_lock);
 
@@ -1229,14 +1055,15 @@ static void *s_start(struct seq_file *m, loff_t *pos)
                 iter->ent = NULL;
                 iter->cpu = 0;
                 iter->idx = -1;
-                iter->prev_ent = NULL;
-                iter->prev_cpu = -1;
 
-                for_each_tracing_cpu(i) {
-                        iter->next_idx[i] = 0;
-                        iter->next_page[i] = NULL;
+                ftrace_disable_cpu();
+
+                for_each_tracing_cpu(cpu) {
+                        ring_buffer_iter_reset(iter->buffer_iter[cpu]);
                 }
 
+                ftrace_enable_cpu();
+
                 for (p = iter; p && l < *pos; p = s_next(m, p, &l))
                         ;
 
@@ -1261,17 +1088,20 @@ static void s_stop(struct seq_file *m, void *p)
         mutex_unlock(&trace_types_lock);
 }
 
-#define KRETPROBE_MSG "[unknown/kretprobe'd]"
-
 #ifdef CONFIG_KRETPROBES
-static inline int kretprobed(unsigned long addr)
+static inline const char *kretprobed(const char *name)
 {
-        return addr == (unsigned long)kretprobe_trampoline;
+        static const char tramp_name[] = "kretprobe_trampoline";
+        int size = sizeof(tramp_name);
+
+        if (strncmp(tramp_name, name, size) == 0)
+                return "[unknown/kretprobe'd]";
+        return name;
 }
 #else
-static inline int kretprobed(unsigned long addr)
+static inline const char *kretprobed(const char *name)
 {
-        return 0;
+        return name;
 }
 #endif /* CONFIG_KRETPROBES */
 
@@ -1280,10 +1110,13 @@ seq_print_sym_short(struct trace_seq *s, const char *fmt, unsigned long address)
 {
 #ifdef CONFIG_KALLSYMS
         char str[KSYM_SYMBOL_LEN];
+        const char *name;
 
         kallsyms_lookup(address, NULL, NULL, NULL, str);
 
-        return trace_seq_printf(s, fmt, str);
+        name = kretprobed(str);
+
+        return trace_seq_printf(s, fmt, name);
 #endif
         return 1;
 }
@@ -1294,9 +1127,12 @@ seq_print_sym_offset(struct trace_seq *s, const char *fmt,
 {
 #ifdef CONFIG_KALLSYMS
         char str[KSYM_SYMBOL_LEN];
+        const char *name;
 
         sprint_symbol(str, address);
-        return trace_seq_printf(s, fmt, str);
+        name = kretprobed(str);
+
+        return trace_seq_printf(s, fmt, name);
 #endif
         return 1;
 }
@@ -1330,21 +1166,21 @@ seq_print_ip_sym(struct trace_seq *s, unsigned long ip, unsigned long sym_flags)
 
 static void print_lat_help_header(struct seq_file *m)
 {
-        seq_puts(m, "#                _------=> CPU#            \n");
-        seq_puts(m, "#               / _-----=> irqs-off        \n");
-        seq_puts(m, "#              | / _----=> need-resched    \n");
-        seq_puts(m, "#              || / _---=> hardirq/softirq \n");
-        seq_puts(m, "#              ||| / _--=> preempt-depth   \n");
-        seq_puts(m, "#              |||| /                      \n");
-        seq_puts(m, "#              |||||     delay             \n");
-        seq_puts(m, "#  cmd     pid ||||| time  |   caller      \n");
-        seq_puts(m, "#     \\   /    |||||   \\   |   /           \n");
+        seq_puts(m, "#                  _------=> CPU#            \n");
+        seq_puts(m, "#                 / _-----=> irqs-off        \n");
+        seq_puts(m, "#                | / _----=> need-resched    \n");
+        seq_puts(m, "#                || / _---=> hardirq/softirq \n");
+        seq_puts(m, "#                ||| / _--=> preempt-depth   \n");
+        seq_puts(m, "#                |||| /                      \n");
+        seq_puts(m, "#                |||||     delay             \n");
+        seq_puts(m, "#  cmd     pid   ||||| time  |   caller      \n");
+        seq_puts(m, "#     \\   /      |||||   \\   |   /           \n");
 }
 
 static void print_func_help_header(struct seq_file *m)
 {
-        seq_puts(m, "#           TASK-PID   CPU#    TIMESTAMP  FUNCTION\n");
-        seq_puts(m, "#              | |      |          |         |\n");
+        seq_puts(m, "#           TASK-PID    CPU#    TIMESTAMP  FUNCTION\n");
+        seq_puts(m, "#              | |       |          |         |\n");
 }
 
 
@@ -1355,23 +1191,16 @@ print_trace_header(struct seq_file *m, struct trace_iterator *iter)
         struct trace_array *tr = iter->tr;
         struct trace_array_cpu *data = tr->data[tr->cpu];
         struct tracer *type = current_trace;
-        unsigned long total   = 0;
-        unsigned long entries = 0;
-        int cpu;
+        unsigned long total;
+        unsigned long entries;
         const char *name = "preemption";
 
         if (type)
                 name = type->name;
 
-        for_each_tracing_cpu(cpu) {
-                if (head_page(tr->data[cpu])) {
-                        total += tr->data[cpu]->trace_idx;
-                        if (tr->data[cpu]->trace_idx > tr->entries)
-                                entries += tr->entries;
-                        else
-                                entries += tr->data[cpu]->trace_idx;
-                }
-        }
+        entries = ring_buffer_entries(iter->tr->buffer);
+        total = entries +
+                ring_buffer_overruns(iter->tr->buffer);
 
         seq_printf(m, "%s latency trace v1.1.5 on %s\n",
                    name, UTS_RELEASE);
@@ -1428,9 +1257,10 @@ lat_print_generic(struct trace_seq *s, struct trace_entry *entry, int cpu)
         comm = trace_find_cmdline(entry->pid);
 
         trace_seq_printf(s, "%8.8s-%-5d ", comm, entry->pid);
-        trace_seq_printf(s, "%d", cpu);
+        trace_seq_printf(s, "%3d", cpu);
         trace_seq_printf(s, "%c%c",
-                        (entry->flags & TRACE_FLAG_IRQS_OFF) ? 'd' : '.',
+                        (entry->flags & TRACE_FLAG_IRQS_OFF) ? 'd' :
+                         (entry->flags & TRACE_FLAG_IRQS_NOSUPPORT) ? 'X' : '.',
                         ((entry->flags & TRACE_FLAG_NEED_RESCHED) ? 'N' : '.'));
 
         hardirq = entry->flags & TRACE_FLAG_HARDIRQ;
@@ -1457,7 +1287,7 @@ lat_print_generic(struct trace_seq *s, struct trace_entry *entry, int cpu)
 unsigned long preempt_mark_thresh = 100;
 
 static void
-lat_print_timestamp(struct trace_seq *s, unsigned long long abs_usecs,
+lat_print_timestamp(struct trace_seq *s, u64 abs_usecs,
                     unsigned long rel_usecs)
 {
         trace_seq_printf(s, " %4lldus", abs_usecs);
@@ -1471,34 +1301,76 @@ lat_print_timestamp(struct trace_seq *s, unsigned long long abs_usecs,
 
 static const char state_to_char[] = TASK_STATE_TO_CHAR_STR;
 
-static int
+/*
+ * The message is supposed to contain an ending newline.
+ * If the printing stops prematurely, try to add a newline of our own.
+ */
+void trace_seq_print_cont(struct trace_seq *s, struct trace_iterator *iter)
+{
+        struct trace_entry *ent;
+        struct trace_field_cont *cont;
+        bool ok = true;
+
+        ent = peek_next_entry(iter, iter->cpu, NULL);
+        if (!ent || ent->type != TRACE_CONT) {
+                trace_seq_putc(s, '\n');
+                return;
+        }
+
+        do {
+                cont = (struct trace_field_cont *)ent;
+                if (ok)
+                        ok = (trace_seq_printf(s, "%s", cont->buf) > 0);
+
+                ftrace_disable_cpu();
+
+                if (iter->buffer_iter[iter->cpu])
+                        ring_buffer_read(iter->buffer_iter[iter->cpu], NULL);
+                else
+                        ring_buffer_consume(iter->tr->buffer, iter->cpu, NULL);
+
+                ftrace_enable_cpu();
+
+                ent = peek_next_entry(iter, iter->cpu, NULL);
+        } while (ent && ent->type == TRACE_CONT);
+
+        if (!ok)
+                trace_seq_putc(s, '\n');
+}
+
+static enum print_line_t
 print_lat_fmt(struct trace_iterator *iter, unsigned int trace_idx, int cpu)
 {
         struct trace_seq *s = &iter->seq;
         unsigned long sym_flags = (trace_flags & TRACE_ITER_SYM_MASK);
-        struct trace_entry *next_entry = find_next_entry(iter, NULL);
+        struct trace_entry *next_entry;
         unsigned long verbose = (trace_flags & TRACE_ITER_VERBOSE);
         struct trace_entry *entry = iter->ent;
         unsigned long abs_usecs;
         unsigned long rel_usecs;
+        u64 next_ts;
         char *comm;
         int S, T;
         int i;
         unsigned state;
 
+        if (entry->type == TRACE_CONT)
+                return TRACE_TYPE_HANDLED;
+
+        next_entry = find_next_entry(iter, NULL, &next_ts);
         if (!next_entry)
-                next_entry = entry;
-        rel_usecs = ns2usecs(next_entry->t - entry->t);
-        abs_usecs = ns2usecs(entry->t - iter->tr->time_start);
+                next_ts = iter->ts;
+        rel_usecs = ns2usecs(next_ts - iter->ts);
+        abs_usecs = ns2usecs(iter->ts - iter->tr->time_start);
 
         if (verbose) {
                 comm = trace_find_cmdline(entry->pid);
-                trace_seq_printf(s, "%16s %5d %d %d %08x %08x [%08lx]"
+                trace_seq_printf(s, "%16s %5d %3d %d %08x %08x [%08lx]"
                                  " %ld.%03ldms (+%ld.%03ldms): ",
                                  comm,
                                  entry->pid, cpu, entry->flags,
                                  entry->preempt_count, trace_idx,
-                                 ns2usecs(entry->t),
+                                 ns2usecs(iter->ts),
                                  abs_usecs/1000,
                                  abs_usecs % 1000, rel_usecs/1000,
                                  rel_usecs % 1000);
@@ -1507,52 +1379,82 @@ print_lat_fmt(struct trace_iterator *iter, unsigned int trace_idx, int cpu)
                 lat_print_timestamp(s, abs_usecs, rel_usecs);
         }
         switch (entry->type) {
-        case TRACE_FN:
-                seq_print_ip_sym(s, entry->fn.ip, sym_flags);
+        case TRACE_FN: {
+                struct ftrace_entry *field;
+
+                trace_assign_type(field, entry);
+
+                seq_print_ip_sym(s, field->ip, sym_flags);
                 trace_seq_puts(s, " (");
-                if (kretprobed(entry->fn.parent_ip))
-                        trace_seq_puts(s, KRETPROBE_MSG);
-                else
-                        seq_print_ip_sym(s, entry->fn.parent_ip, sym_flags);
+                seq_print_ip_sym(s, field->parent_ip, sym_flags);
                 trace_seq_puts(s, ")\n");
                 break;
+        }
         case TRACE_CTX:
-        case TRACE_WAKE:
-                T = entry->ctx.next_state < sizeof(state_to_char) ?
-                        state_to_char[entry->ctx.next_state] : 'X';
+        case TRACE_WAKE: {
+                struct ctx_switch_entry *field;
+
+                trace_assign_type(field, entry);
+
+                T = field->next_state < sizeof(state_to_char) ?
+                        state_to_char[field->next_state] : 'X';
 
-                state = entry->ctx.prev_state ? __ffs(entry->ctx.prev_state) + 1 : 0;
+                state = field->prev_state ?
+                        __ffs(field->prev_state) + 1 : 0;
                 S = state < sizeof(state_to_char) - 1 ? state_to_char[state] : 'X';
-                comm = trace_find_cmdline(entry->ctx.next_pid);
-                trace_seq_printf(s, " %5d:%3d:%c %s %5d:%3d:%c %s\n",
-                                 entry->ctx.prev_pid,
-                                 entry->ctx.prev_prio,
+                comm = trace_find_cmdline(field->next_pid);
+                trace_seq_printf(s, " %5d:%3d:%c %s [%03d] %5d:%3d:%c %s\n",
+                                 field->prev_pid,
+                                 field->prev_prio,
                                  S, entry->type == TRACE_CTX ? "==>" : "  +",
-                                 entry->ctx.next_pid,
-                                 entry->ctx.next_prio,
+                                 field->next_cpu,
+                                 field->next_pid,
+                                 field->next_prio,
                                  T, comm);
                 break;
-        case TRACE_SPECIAL:
+        }
+        case TRACE_SPECIAL: {
+                struct special_entry *field;
+
+                trace_assign_type(field, entry);
+
                 trace_seq_printf(s, "# %ld %ld %ld\n",
-                                 entry->special.arg1,
-                                 entry->special.arg2,
-                                 entry->special.arg3);
+                                 field->arg1,
+                                 field->arg2,
+                                 field->arg3);
                 break;
-        case TRACE_STACK:
+        }
+        case TRACE_STACK: {
+                struct stack_entry *field;
+
+                trace_assign_type(field, entry);
+
                 for (i = 0; i < FTRACE_STACK_ENTRIES; i++) {
                         if (i)
                                 trace_seq_puts(s, " <= ");
-                        seq_print_ip_sym(s, entry->stack.caller[i], sym_flags);
+                        seq_print_ip_sym(s, field->caller[i], sym_flags);
                 }
                 trace_seq_puts(s, "\n");
                 break;
+        }
+        case TRACE_PRINT: {
+                struct print_entry *field;
+
+                trace_assign_type(field, entry);
+
+                seq_print_ip_sym(s, field->ip, sym_flags);
+                trace_seq_printf(s, ": %s", field->buf);
+                if (entry->flags & TRACE_FLAG_CONT)
+                        trace_seq_print_cont(s, iter);
+                break;
+        }
         default:
                 trace_seq_printf(s, "Unknown type %d\n", entry->type);
         }
-        return 1;
+        return TRACE_TYPE_HANDLED;
 }
 
-static int print_trace_fmt(struct trace_iterator *iter)
+static enum print_line_t print_trace_fmt(struct trace_iterator *iter)
 {
         struct trace_seq *s = &iter->seq;
         unsigned long sym_flags = (trace_flags & TRACE_ITER_SYM_MASK);
@@ -1567,90 +1469,123 @@ static int print_trace_fmt(struct trace_iterator *iter)
 
         entry = iter->ent;
 
+        if (entry->type == TRACE_CONT)
+                return TRACE_TYPE_HANDLED;
+
         comm = trace_find_cmdline(iter->ent->pid);
 
-        t = ns2usecs(entry->t);
+        t = ns2usecs(iter->ts);
         usec_rem = do_div(t, 1000000ULL);
         secs = (unsigned long)t;
 
         ret = trace_seq_printf(s, "%16s-%-5d ", comm, entry->pid);
         if (!ret)
-                return 0;
-        ret = trace_seq_printf(s, "[%02d] ", iter->cpu);
+                return TRACE_TYPE_PARTIAL_LINE;
+        ret = trace_seq_printf(s, "[%03d] ", iter->cpu);
         if (!ret)
-                return 0;
+                return TRACE_TYPE_PARTIAL_LINE;
         ret = trace_seq_printf(s, "%5lu.%06lu: ", secs, usec_rem);
         if (!ret)
-                return 0;
+                return TRACE_TYPE_PARTIAL_LINE;
 
         switch (entry->type) {
-        case TRACE_FN:
-                ret = seq_print_ip_sym(s, entry->fn.ip, sym_flags);
+        case TRACE_FN: {
+                struct ftrace_entry *field;
+
+                trace_assign_type(field, entry);
+
+                ret = seq_print_ip_sym(s, field->ip, sym_flags);
                 if (!ret)
-                        return 0;
+                        return TRACE_TYPE_PARTIAL_LINE;
                 if ((sym_flags & TRACE_ITER_PRINT_PARENT) &&
-                                                entry->fn.parent_ip) {
+                                                field->parent_ip) {
                         ret = trace_seq_printf(s, " <-");
                         if (!ret)
-                                return 0;
-                        if (kretprobed(entry->fn.parent_ip))
-                                ret = trace_seq_puts(s, KRETPROBE_MSG);
-                        else
-                                ret = seq_print_ip_sym(s, entry->fn.parent_ip,
-                                                       sym_flags);
+                                return TRACE_TYPE_PARTIAL_LINE;
+                        ret = seq_print_ip_sym(s,
+                                               field->parent_ip,
+                                               sym_flags);
                         if (!ret)
-                                return 0;
+                                return TRACE_TYPE_PARTIAL_LINE;
                 }
                 ret = trace_seq_printf(s, "\n");
                 if (!ret)
-                        return 0;
+                        return TRACE_TYPE_PARTIAL_LINE;
                 break;
+        }
         case TRACE_CTX:
-        case TRACE_WAKE:
-                S = entry->ctx.prev_state < sizeof(state_to_char) ?
-                        state_to_char[entry->ctx.prev_state] : 'X';
-                T = entry->ctx.next_state < sizeof(state_to_char) ?
-                        state_to_char[entry->ctx.next_state] : 'X';
-                ret = trace_seq_printf(s, " %5d:%3d:%c %s %5d:%3d:%c\n",
-                                       entry->ctx.prev_pid,
-                                       entry->ctx.prev_prio,
+        case TRACE_WAKE: {
+                struct ctx_switch_entry *field;
+
+                trace_assign_type(field, entry);
+
+                S = field->prev_state < sizeof(state_to_char) ?
+                        state_to_char[field->prev_state] : 'X';
+                T = field->next_state < sizeof(state_to_char) ?
+                        state_to_char[field->next_state] : 'X';
+                ret = trace_seq_printf(s, " %5d:%3d:%c %s [%03d] %5d:%3d:%c\n",
+                                       field->prev_pid,
+                                       field->prev_prio,
                                        S,
                                        entry->type == TRACE_CTX ? "==>" : "  +",
-                                       entry->ctx.next_pid,
-                                       entry->ctx.next_prio,
+                                       field->next_cpu,
+                                       field->next_pid,
+                                       field->next_prio,
                                        T);
                 if (!ret)
-                        return 0;
+                        return TRACE_TYPE_PARTIAL_LINE;
                 break;
-        case TRACE_SPECIAL:
+        }
+        case TRACE_SPECIAL: {
+                struct special_entry *field;
+
+                trace_assign_type(field, entry);
+
                 ret = trace_seq_printf(s, "# %ld %ld %ld\n",
-                                 entry->special.arg1,
-                                 entry->special.arg2,
-                                 entry->special.arg3);
+                                 field->arg1,
+                                 field->arg2,
+                                 field->arg3);
                 if (!ret)
-                        return 0;
+                        return TRACE_TYPE_PARTIAL_LINE;
                 break;
-        case TRACE_STACK:
+        }
+        case TRACE_STACK: {
+                struct stack_entry *field;
+
+                trace_assign_type(field, entry);
+
                 for (i = 0; i < FTRACE_STACK_ENTRIES; i++) {
                         if (i) {
                                 ret = trace_seq_puts(s, " <= ");
                                 if (!ret)
-                                        return 0;
+                                        return TRACE_TYPE_PARTIAL_LINE;
                         }
-                        ret = seq_print_ip_sym(s, entry->stack.caller[i],
+                        ret = seq_print_ip_sym(s, field->caller[i],
                                                sym_flags);
                         if (!ret)
-                                return 0;
+                                return TRACE_TYPE_PARTIAL_LINE;
                 }
                 ret = trace_seq_puts(s, "\n");
                 if (!ret)
-                        return 0;
+                        return TRACE_TYPE_PARTIAL_LINE;
                 break;
         }
-        return 1;
+        case TRACE_PRINT: {
+                struct print_entry *field;
+
+                trace_assign_type(field, entry);
+
+                seq_print_ip_sym(s, field->ip, sym_flags);
+                trace_seq_printf(s, ": %s", field->buf);
+                if (entry->flags & TRACE_FLAG_CONT)
+                        trace_seq_print_cont(s, iter);
+                break;
+        }
+        }
+        return TRACE_TYPE_HANDLED;
 }
 
-static int print_raw_fmt(struct trace_iterator *iter)
+static enum print_line_t print_raw_fmt(struct trace_iterator *iter)
 {
         struct trace_seq *s = &iter->seq;
         struct trace_entry *entry;
@@ -1659,47 +1594,77 @@ static int print_raw_fmt(struct trace_iterator *iter)
 
         entry = iter->ent;
 
+        if (entry->type == TRACE_CONT)
+                return TRACE_TYPE_HANDLED;
+
         ret = trace_seq_printf(s, "%d %d %llu ",
-                entry->pid, iter->cpu, entry->t);
+                entry->pid, iter->cpu, iter->ts);
         if (!ret)
-                return 0;
+                return TRACE_TYPE_PARTIAL_LINE;
 
         switch (entry->type) {
-        case TRACE_FN:
+        case TRACE_FN: {
+                struct ftrace_entry *field;
+
+                trace_assign_type(field, entry);
+
                 ret = trace_seq_printf(s, "%x %x\n",
-                                        entry->fn.ip, entry->fn.parent_ip);
+                                        field->ip,
+                                        field->parent_ip);
                 if (!ret)
-                        return 0;
+                        return TRACE_TYPE_PARTIAL_LINE;
                 break;
+        }
         case TRACE_CTX:
-        case TRACE_WAKE:
-                S = entry->ctx.prev_state < sizeof(state_to_char) ?
-                        state_to_char[entry->ctx.prev_state] : 'X';
-                T = entry->ctx.next_state < sizeof(state_to_char) ?
-                        state_to_char[entry->ctx.next_state] : 'X';
+        case TRACE_WAKE: {
+                struct ctx_switch_entry *field;
+
+                trace_assign_type(field, entry);
+
+                S = field->prev_state < sizeof(state_to_char) ?
+                        state_to_char[field->prev_state] : 'X';
+                T = field->next_state < sizeof(state_to_char) ?
+                        state_to_char[field->next_state] : 'X';
                 if (entry->type == TRACE_WAKE)
                         S = '+';
-                ret = trace_seq_printf(s, "%d %d %c %d %d %c\n",
-                                       entry->ctx.prev_pid,
-                                       entry->ctx.prev_prio,
+                ret = trace_seq_printf(s, "%d %d %c %d %d %d %c\n",
+                                       field->prev_pid,
+                                       field->prev_prio,
                                        S,
-                                       entry->ctx.next_pid,
-                                       entry->ctx.next_prio,
+                                       field->next_cpu,
+                                       field->next_pid,
+                                       field->next_prio,
                                        T);
                 if (!ret)
-                        return 0;
+                        return TRACE_TYPE_PARTIAL_LINE;
                 break;
+        }
         case TRACE_SPECIAL:
-        case TRACE_STACK:
+        case TRACE_STACK: {
+                struct special_entry *field;
+
+                trace_assign_type(field, entry);
+
                 ret = trace_seq_printf(s, "# %ld %ld %ld\n",
-                                 entry->special.arg1,
-                                 entry->special.arg2,
-                                 entry->special.arg3);
+                                 field->arg1,
+                                 field->arg2,
+                                 field->arg3);
                 if (!ret)
-                        return 0;
+                        return TRACE_TYPE_PARTIAL_LINE;
                 break;
         }
-        return 1;
+        case TRACE_PRINT: {
+                struct print_entry *field;
+
+                trace_assign_type(field, entry);
+
+                trace_seq_printf(s, "# %lx %s", field->ip, field->buf);
+                if (entry->flags & TRACE_FLAG_CONT)
+                        trace_seq_print_cont(s, iter);
+                break;
+        }
+        }
+        return TRACE_TYPE_HANDLED;
 }
 
 #define SEQ_PUT_FIELD_RET(s, x)                         \
@@ -1710,11 +1675,12 @@ do {							\
 
 #define SEQ_PUT_HEX_FIELD_RET(s, x)                     \
 do {                                                    \
+        BUILD_BUG_ON(sizeof(x) > MAX_MEMHEX_BYTES);     \
         if (!trace_seq_putmem_hex(s, &(x), sizeof(x)))  \
                 return 0;                               \
 } while (0)
 
-static int print_hex_fmt(struct trace_iterator *iter)
+static enum print_line_t print_hex_fmt(struct trace_iterator *iter)
 {
         struct trace_seq *s = &iter->seq;
         unsigned char newline = '\n';
@@ -1723,97 +1689,139 @@ static int print_hex_fmt(struct trace_iterator *iter)
 
         entry = iter->ent;
 
+        if (entry->type == TRACE_CONT)
+                return TRACE_TYPE_HANDLED;
+
         SEQ_PUT_HEX_FIELD_RET(s, entry->pid);
         SEQ_PUT_HEX_FIELD_RET(s, iter->cpu);
-        SEQ_PUT_HEX_FIELD_RET(s, entry->t);
+        SEQ_PUT_HEX_FIELD_RET(s, iter->ts);
 
         switch (entry->type) {
-        case TRACE_FN:
-                SEQ_PUT_HEX_FIELD_RET(s, entry->fn.ip);
-                SEQ_PUT_HEX_FIELD_RET(s, entry->fn.parent_ip);
+        case TRACE_FN: {
+                struct ftrace_entry *field;
+
+                trace_assign_type(field, entry);
+
+                SEQ_PUT_HEX_FIELD_RET(s, field->ip);
+                SEQ_PUT_HEX_FIELD_RET(s, field->parent_ip);
                 break;
+        }
         case TRACE_CTX:
-        case TRACE_WAKE:
-                S = entry->ctx.prev_state < sizeof(state_to_char) ?
-                        state_to_char[entry->ctx.prev_state] : 'X';
-                T = entry->ctx.next_state < sizeof(state_to_char) ?
-                        state_to_char[entry->ctx.next_state] : 'X';
+        case TRACE_WAKE: {
+                struct ctx_switch_entry *field;
+
+                trace_assign_type(field, entry);
+
+                S = field->prev_state < sizeof(state_to_char) ?
+                        state_to_char[field->prev_state] : 'X';
+                T = field->next_state < sizeof(state_to_char) ?
+                        state_to_char[field->next_state] : 'X';
                 if (entry->type == TRACE_WAKE)
                         S = '+';
-                SEQ_PUT_HEX_FIELD_RET(s, entry->ctx.prev_pid);
-                SEQ_PUT_HEX_FIELD_RET(s, entry->ctx.prev_prio);
+                SEQ_PUT_HEX_FIELD_RET(s, field->prev_pid);
+                SEQ_PUT_HEX_FIELD_RET(s, field->prev_prio);
                 SEQ_PUT_HEX_FIELD_RET(s, S);
-                SEQ_PUT_HEX_FIELD_RET(s, entry->ctx.next_pid);
-                SEQ_PUT_HEX_FIELD_RET(s, entry->ctx.next_prio);
-                SEQ_PUT_HEX_FIELD_RET(s, entry->fn.parent_ip);
+                SEQ_PUT_HEX_FIELD_RET(s, field->next_cpu);
+                SEQ_PUT_HEX_FIELD_RET(s, field->next_pid);
+                SEQ_PUT_HEX_FIELD_RET(s, field->next_prio);
                 SEQ_PUT_HEX_FIELD_RET(s, T);
                 break;
+        }
         case TRACE_SPECIAL:
-        case TRACE_STACK:
-                SEQ_PUT_HEX_FIELD_RET(s, entry->special.arg1);
-                SEQ_PUT_HEX_FIELD_RET(s, entry->special.arg2);
-                SEQ_PUT_HEX_FIELD_RET(s, entry->special.arg3);
+        case TRACE_STACK: {
+                struct special_entry *field;
+
+                trace_assign_type(field, entry);
+
+                SEQ_PUT_HEX_FIELD_RET(s, field->arg1);
+                SEQ_PUT_HEX_FIELD_RET(s, field->arg2);
+                SEQ_PUT_HEX_FIELD_RET(s, field->arg3);
                 break;
         }
+        }
         SEQ_PUT_FIELD_RET(s, newline);
 
-        return 1;
+        return TRACE_TYPE_HANDLED;
 }
 
-static int print_bin_fmt(struct trace_iterator *iter)
+static enum print_line_t print_bin_fmt(struct trace_iterator *iter)
 {
         struct trace_seq *s = &iter->seq;
         struct trace_entry *entry;
 
         entry = iter->ent;
 
+        if (entry->type == TRACE_CONT)
+                return TRACE_TYPE_HANDLED;
+
         SEQ_PUT_FIELD_RET(s, entry->pid);
         SEQ_PUT_FIELD_RET(s, entry->cpu);
-        SEQ_PUT_FIELD_RET(s, entry->t);
+        SEQ_PUT_FIELD_RET(s, iter->ts);
 
         switch (entry->type) {
-        case TRACE_FN:
-                SEQ_PUT_FIELD_RET(s, entry->fn.ip);
-                SEQ_PUT_FIELD_RET(s, entry->fn.parent_ip);
+        case TRACE_FN: {
+                struct ftrace_entry *field;
+
+                trace_assign_type(field, entry);
+
+                SEQ_PUT_FIELD_RET(s, field->ip);
+                SEQ_PUT_FIELD_RET(s, field->parent_ip);
                 break;
-        case TRACE_CTX:
-                SEQ_PUT_FIELD_RET(s, entry->ctx.prev_pid);
-                SEQ_PUT_FIELD_RET(s, entry->ctx.prev_prio);
-                SEQ_PUT_FIELD_RET(s, entry->ctx.prev_state);
-                SEQ_PUT_FIELD_RET(s, entry->ctx.next_pid);
-                SEQ_PUT_FIELD_RET(s, entry->ctx.next_prio);
-                SEQ_PUT_FIELD_RET(s, entry->ctx.next_state);
+        }
+        case TRACE_CTX: {
+                struct ctx_switch_entry *field;
+
+                trace_assign_type(field, entry);
+
+                SEQ_PUT_FIELD_RET(s, field->prev_pid);
+                SEQ_PUT_FIELD_RET(s, field->prev_prio);
+                SEQ_PUT_FIELD_RET(s, field->prev_state);
+                SEQ_PUT_FIELD_RET(s, field->next_pid);
+                SEQ_PUT_FIELD_RET(s, field->next_prio);
+                SEQ_PUT_FIELD_RET(s, field->next_state);
                 break;
+        }
         case TRACE_SPECIAL:
-        case TRACE_STACK:
-                SEQ_PUT_FIELD_RET(s, entry->special.arg1);
-                SEQ_PUT_FIELD_RET(s, entry->special.arg2);
-                SEQ_PUT_FIELD_RET(s, entry->special.arg3);
+        case TRACE_STACK: {
+                struct special_entry *field;
+
+                trace_assign_type(field, entry);
+
+                SEQ_PUT_FIELD_RET(s, field->arg1);
+                SEQ_PUT_FIELD_RET(s, field->arg2);
+                SEQ_PUT_FIELD_RET(s, field->arg3);
                 break;
         }
+        }
         return 1;
 }
 
 static int trace_empty(struct trace_iterator *iter)
 {
-        struct trace_array_cpu *data;
         int cpu;
 
         for_each_tracing_cpu(cpu) {
-                data = iter->tr->data[cpu];
-
-                if (head_page(data) && data->trace_idx &&
-                    (data->trace_tail != data->trace_head ||
-                     data->trace_tail_idx != data->trace_head_idx))
-                        return 0;
+                if (iter->buffer_iter[cpu]) {
+                        if (!ring_buffer_iter_empty(iter->buffer_iter[cpu]))
+                                return 0;
+                } else {
+                        if (!ring_buffer_empty_cpu(iter->tr->buffer, cpu))
+                                return 0;
+                }
         }
+
         return 1;
 }
 
-static int print_trace_line(struct trace_iterator *iter)
+static enum print_line_t print_trace_line(struct trace_iterator *iter)
 {
-        if (iter->trace && iter->trace->print_line)
-                return iter->trace->print_line(iter);
+        enum print_line_t ret;
+
+        if (iter->trace && iter->trace->print_line) {
+                ret = iter->trace->print_line(iter);
+                if (ret != TRACE_TYPE_UNHANDLED)
+                        return ret;
+        }
 
         if (trace_flags & TRACE_ITER_BIN)
                 return print_bin_fmt(iter);
@@ -1869,6 +1877,8 @@ static struct trace_iterator *
 __tracing_open(struct inode *inode, struct file *file, int *ret)
 {
         struct trace_iterator *iter;
+        struct seq_file *m;
+        int cpu;
 
         if (tracing_disabled) {
                 *ret = -ENODEV;
@@ -1889,28 +1899,46 @@ __tracing_open(struct inode *inode, struct file *file, int *ret)
         iter->trace = current_trace;
         iter->pos = -1;
 
+        for_each_tracing_cpu(cpu) {
+
+                iter->buffer_iter[cpu] =
+                        ring_buffer_read_start(iter->tr->buffer, cpu);
+
+                if (!iter->buffer_iter[cpu])
+                        goto fail_buffer;
+        }
+
         /* TODO stop tracer */
         *ret = seq_open(file, &tracer_seq_ops);
-        if (!*ret) {
-                struct seq_file *m = file->private_data;
-                m->private = iter;
+        if (*ret)
+                goto fail_buffer;
 
-                /* stop the trace while dumping */
-                if (iter->tr->ctrl) {
-                        tracer_enabled = 0;
-                        ftrace_function_enabled = 0;
-                }
+        m = file->private_data;
+        m->private = iter;
 
-                if (iter->trace && iter->trace->open)
-                        iter->trace->open(iter);
-        } else {
-                kfree(iter);
-                iter = NULL;
+        /* stop the trace while dumping */
+        if (iter->tr->ctrl) {
+                tracer_enabled = 0;
+                ftrace_function_enabled = 0;
         }
+
+        if (iter->trace && iter->trace->open)
+                        iter->trace->open(iter);
+
         mutex_unlock(&trace_types_lock);
 
  out:
         return iter;
+
+ fail_buffer:
+        for_each_tracing_cpu(cpu) {
+                if (iter->buffer_iter[cpu])
+                        ring_buffer_read_finish(iter->buffer_iter[cpu]);
+        }
+        mutex_unlock(&trace_types_lock);
+        kfree(iter);
+
+        return ERR_PTR(-ENOMEM);
 }
 
 int tracing_open_generic(struct inode *inode, struct file *filp)
@@ -1926,8 +1954,14 @@ int tracing_release(struct inode *inode, struct file *file)
 {
         struct seq_file *m = (struct seq_file *)file->private_data;
         struct trace_iterator *iter = m->private;
+        int cpu;
 
         mutex_lock(&trace_types_lock);
+        for_each_tracing_cpu(cpu) {
+                if (iter->buffer_iter[cpu])
+                        ring_buffer_read_finish(iter->buffer_iter[cpu]);
+        }
+
         if (iter->trace && iter->trace->close)
                 iter->trace->close(iter);
 
@@ -2352,6 +2386,9 @@ tracing_set_trace_write(struct file *filp, const char __user *ubuf,
         struct tracer *t;
         char buf[max_tracer_type_len+1];
         int i;
+        size_t ret;
+
+        ret = cnt;
 
         if (cnt > max_tracer_type_len)
                 cnt = max_tracer_type_len;
@@ -2370,7 +2407,11 @@ tracing_set_trace_write(struct file *filp, const char __user *ubuf,
                 if (strcmp(t->name, buf) == 0)
                         break;
         }
-        if (!t || t == current_trace)
+        if (!t) {
+                ret = -EINVAL;
+                goto out;
+        }
+        if (t == current_trace)
                 goto out;
 
         if (current_trace && current_trace->reset)
@@ -2383,9 +2424,10 @@ tracing_set_trace_write(struct file *filp, const char __user *ubuf,
  out:
         mutex_unlock(&trace_types_lock);
 
-        filp->f_pos += cnt;
+        if (ret > 0)
+                filp->f_pos += ret;
 
-        return cnt;
+        return ret;
 }
 
 static ssize_t
@@ -2500,20 +2542,12 @@ tracing_read_pipe(struct file *filp, char __user *ubuf,
                   size_t cnt, loff_t *ppos)
 {
         struct trace_iterator *iter = filp->private_data;
-        struct trace_array_cpu *data;
-        static cpumask_t mask;
-        unsigned long flags;
-#ifdef CONFIG_FTRACE
-        int ftrace_save;
-#endif
-        int cpu;
         ssize_t sret;
 
         /* return any leftover data */
         sret = trace_seq_to_user(&iter->seq, ubuf, cnt);
         if (sret != -EBUSY)
                 return sret;
-        sret = 0;
 
         trace_seq_reset(&iter->seq);
 
@@ -2524,6 +2558,8 @@ tracing_read_pipe(struct file *filp, char __user *ubuf,
                         goto out;
         }
 
+waitagain:
+        sret = 0;
         while (trace_empty(iter)) {
 
                 if ((filp->f_flags & O_NONBLOCK)) {
@@ -2588,46 +2624,12 @@ tracing_read_pipe(struct file *filp, char __user *ubuf,
                offsetof(struct trace_iterator, seq));
         iter->pos = -1;
 
-        /*
-         * We need to stop all tracing on all CPUS to read the
-         * the next buffer. This is a bit expensive, but is
-         * not done often. We fill all what we can read,
-         * and then release the locks again.
-         */
-
-        cpus_clear(mask);
-        local_irq_save(flags);
-#ifdef CONFIG_FTRACE
-        ftrace_save = ftrace_enabled;
-        ftrace_enabled = 0;
-#endif
-        smp_wmb();
-        for_each_tracing_cpu(cpu) {
-                data = iter->tr->data[cpu];
-
-                if (!head_page(data) || !data->trace_idx)
-                        continue;
-
-                atomic_inc(&data->disabled);
-                cpu_set(cpu, mask);
-        }
-
-        for_each_cpu_mask(cpu, mask) {
-                data = iter->tr->data[cpu];
-                __raw_spin_lock(&data->lock);
-
-                if (data->overrun > iter->last_overrun[cpu])
-                        iter->overrun[cpu] +=
-                                data->overrun - iter->last_overrun[cpu];
-                iter->last_overrun[cpu] = data->overrun;
-        }
-
         while (find_next_entry_inc(iter) != NULL) {
-                int ret;
+                enum print_line_t ret;
                 int len = iter->seq.len;
 
                 ret = print_trace_line(iter);
-                if (!ret) {
+                if (ret == TRACE_TYPE_PARTIAL_LINE) {
                         /* don't print partial lines */
                         iter->seq.len = len;
                         break;
@@ -2639,26 +2641,17 @@ tracing_read_pipe(struct file *filp, char __user *ubuf,
                         break;
         }
 
-        for_each_cpu_mask(cpu, mask) {
-                data = iter->tr->data[cpu];
-                __raw_spin_unlock(&data->lock);
-        }
-
-        for_each_cpu_mask(cpu, mask) {
-                data = iter->tr->data[cpu];
-                atomic_dec(&data->disabled);
-        }
-#ifdef CONFIG_FTRACE
-        ftrace_enabled = ftrace_save;
-#endif
-        local_irq_restore(flags);
-
         /* Now copy what we have to the user */
         sret = trace_seq_to_user(&iter->seq, ubuf, cnt);
         if (iter->seq.readpos >= iter->seq.len)
                 trace_seq_reset(&iter->seq);
+
+        /*
+         * If there was nothing to send to user, inspite of consuming trace
+         * entries, go back to wait for more entries.
+         */
         if (sret == -EBUSY)
-                sret = 0;
+                goto waitagain;
 
 out:
         mutex_unlock(&trace_types_lock);
@@ -2684,7 +2677,8 @@ tracing_entries_write(struct file *filp, const char __user *ubuf,
 {
         unsigned long val;
         char buf[64];
-        int i, ret;
+        int ret, cpu;
+        struct trace_array *tr = filp->private_data;
 
         if (cnt >= sizeof(buf))
                 return -EINVAL;
@@ -2704,71 +2698,111 @@ tracing_entries_write(struct file *filp, const char __user *ubuf,
 
         mutex_lock(&trace_types_lock);
 
-        if (current_trace != &no_tracer) {
+        if (tr->ctrl) {
                 cnt = -EBUSY;
-                pr_info("ftrace: set current_tracer to none"
+                pr_info("ftrace: please disable tracing"
                         " before modifying buffer size\n");
                 goto out;
         }
 
-        if (val > global_trace.entries) {
-                long pages_requested;
-                unsigned long freeable_pages;
-
-                /* make sure we have enough memory before mapping */
-                pages_requested =
-                        (val + (ENTRIES_PER_PAGE-1)) / ENTRIES_PER_PAGE;
-
-                /* account for each buffer (and max_tr) */
-                pages_requested *= tracing_nr_buffers * 2;
-
-                /* Check for overflow */
-                if (pages_requested < 0) {
-                        cnt = -ENOMEM;
-                        goto out;
-                }
-
-                freeable_pages = determine_dirtyable_memory();
+        /* disable all cpu buffers */
+        for_each_tracing_cpu(cpu) {
+                if (global_trace.data[cpu])
+                        atomic_inc(&global_trace.data[cpu]->disabled);
+                if (max_tr.data[cpu])
+                        atomic_inc(&max_tr.data[cpu]->disabled);
+        }
 
-                /* we only allow to request 1/4 of useable memory */
-                if (pages_requested >
-                    ((freeable_pages + tracing_pages_allocated) / 4)) {
-                        cnt = -ENOMEM;
+        if (val != global_trace.entries) {
+                ret = ring_buffer_resize(global_trace.buffer, val);
+                if (ret < 0) {
+                        cnt = ret;
                         goto out;
                 }
 
-                while (global_trace.entries < val) {
-                        if (trace_alloc_page()) {
-                                cnt = -ENOMEM;
-                                goto out;
+                ret = ring_buffer_resize(max_tr.buffer, val);
+                if (ret < 0) {
+                        int r;
+                        cnt = ret;
+                        r = ring_buffer_resize(global_trace.buffer,
+                                               global_trace.entries);
+                        if (r < 0) {
+                                /* AARGH! We are left with different
+                                 * size max buffer!!!! */
+                                WARN_ON(1);
+                                tracing_disabled = 1;
                         }
-                        /* double check that we don't go over the known pages */
-                        if (tracing_pages_allocated > pages_requested)
-                                break;
+                        goto out;
                 }
 
-        } else {
-                /* include the number of entries in val (inc of page entries) */
-                while (global_trace.entries > val + (ENTRIES_PER_PAGE - 1))
-                        trace_free_page();
+                global_trace.entries = val;
         }
 
-        /* check integrity */
-        for_each_tracing_cpu(i)
-                check_pages(global_trace.data[i]);
-
         filp->f_pos += cnt;
 
         /* If check pages failed, return ENOMEM */
         if (tracing_disabled)
                 cnt = -ENOMEM;
  out:
+        for_each_tracing_cpu(cpu) {
+                if (global_trace.data[cpu])
+                        atomic_dec(&global_trace.data[cpu]->disabled);
+                if (max_tr.data[cpu])
+                        atomic_dec(&max_tr.data[cpu]->disabled);
+        }
+
         max_tr.entries = global_trace.entries;
         mutex_unlock(&trace_types_lock);
 
         return cnt;
 }
 
+static int mark_printk(const char *fmt, ...)
+{
+        int ret;
+        va_list args;
+        va_start(args, fmt);
+        ret = trace_vprintk(0, fmt, args);
+        va_end(args);
+        return ret;
+}
+
+static ssize_t
+tracing_mark_write(struct file *filp, const char __user *ubuf,
+                                        size_t cnt, loff_t *fpos)
+{
+        char *buf;
+        char *end;
+        struct trace_array *tr = &global_trace;
+
+        if (!tr->ctrl || tracing_disabled)
+                return -EINVAL;
+
+        if (cnt > TRACE_BUF_SIZE)
+                cnt = TRACE_BUF_SIZE;
+
+        buf = kmalloc(cnt + 1, GFP_KERNEL);
+        if (buf == NULL)
+                return -ENOMEM;
+
+        if (copy_from_user(buf, ubuf, cnt)) {
+                kfree(buf);
+                return -EFAULT;
+        }
+
+        /* Cut from the first nil or newline. */
+        buf[cnt] = '\0';
+        end = strchr(buf, '\n');
+        if (end)
+                *end = '\0';
+
+        cnt = mark_printk("%s\n", buf);
+        kfree(buf);
+        *fpos += cnt;
+
+        return cnt;
+}
+
 static struct file_operations tracing_max_lat_fops = {
         .open           = tracing_open_generic,
         .read           = tracing_max_lat_read,
@@ -2800,6 +2834,11 @@ static struct file_operations tracing_entries_fops = {
         .write          = tracing_entries_write,
 };
 
+static struct file_operations tracing_mark_fops = {
+        .open           = tracing_open_generic,
+        .write          = tracing_mark_write,
+};
+
 #ifdef CONFIG_DYNAMIC_FTRACE
 
 static ssize_t
@@ -2846,7 +2885,7 @@ struct dentry *tracing_init_dentry(void)
 #include "trace_selftest.c"
 #endif
 
-static __init void tracer_init_debugfs(void)
+static __init int tracer_init_debugfs(void)
 {
         struct dentry *d_tracer;
         struct dentry *entry;
@@ -2881,12 +2920,12 @@ static __init void tracer_init_debugfs(void)
         entry = debugfs_create_file("available_tracers", 0444, d_tracer,
                                     &global_trace, &show_traces_fops);
         if (!entry)
-                pr_warning("Could not create debugfs 'trace' entry\n");
+                pr_warning("Could not create debugfs 'available_tracers' entry\n");
 
         entry = debugfs_create_file("current_tracer", 0444, d_tracer,
                                     &global_trace, &set_tracer_fops);
         if (!entry)
-                pr_warning("Could not create debugfs 'trace' entry\n");
+                pr_warning("Could not create debugfs 'current_tracer' entry\n");
 
         entry = debugfs_create_file("tracing_max_latency", 0644, d_tracer,
                                     &tracing_max_latency,
@@ -2899,7 +2938,7 @@ static __init void tracer_init_debugfs(void)
                                     &tracing_thresh, &tracing_max_lat_fops);
         if (!entry)
                 pr_warning("Could not create debugfs "
-                           "'tracing_threash' entry\n");
+                           "'tracing_thresh' entry\n");
         entry = debugfs_create_file("README", 0644, d_tracer,
                                     NULL, &tracing_readme_fops);
         if (!entry)
@@ -2909,13 +2948,19 @@ static __init void tracer_init_debugfs(void)
                                     NULL, &tracing_pipe_fops);
         if (!entry)
                 pr_warning("Could not create debugfs "
-                           "'tracing_threash' entry\n");
+                           "'trace_pipe' entry\n");
 
         entry = debugfs_create_file("trace_entries", 0644, d_tracer,
                                     &global_trace, &tracing_entries_fops);
         if (!entry)
                 pr_warning("Could not create debugfs "
-                           "'tracing_threash' entry\n");
+                           "'trace_entries' entry\n");
+
+        entry = debugfs_create_file("trace_marker", 0220, d_tracer,
+                                    NULL, &tracing_mark_fops);
+        if (!entry)
+                pr_warning("Could not create debugfs "
+                           "'trace_marker' entry\n");
 
 #ifdef CONFIG_DYNAMIC_FTRACE
         entry = debugfs_create_file("dyn_ftrace_total_info", 0444, d_tracer,
@@ -2928,230 +2973,263 @@ static __init void tracer_init_debugfs(void)
 #ifdef CONFIG_SYSPROF_TRACER
         init_tracer_sysprof_debugfs(d_tracer);
 #endif
+        return 0;
 }
 
-static int trace_alloc_page(void)
+int trace_vprintk(unsigned long ip, const char *fmt, va_list args)
 {
+        static DEFINE_SPINLOCK(trace_buf_lock);
+        static char trace_buf[TRACE_BUF_SIZE];
+
+        struct ring_buffer_event *event;
+        struct trace_array *tr = &global_trace;
         struct trace_array_cpu *data;
-        struct page *page, *tmp;
-        LIST_HEAD(pages);
-        void *array;
-        unsigned pages_allocated = 0;
-        int i;
+        struct print_entry *entry;
+        unsigned long flags, irq_flags;
+        int cpu, len = 0, size, pc;
 
-        /* first allocate a page for each CPU */
-        for_each_tracing_cpu(i) {
-                array = (void *)__get_free_page(GFP_KERNEL);
-                if (array == NULL) {
-                        printk(KERN_ERR "tracer: failed to allocate page"
-                               "for trace buffer!\n");
-                        goto free_pages;
-                }
+        if (!tr->ctrl || tracing_disabled)
+                return 0;
 
-                pages_allocated++;
-                page = virt_to_page(array);
-                list_add(&page->lru, &pages);
+        pc = preempt_count();
+        preempt_disable_notrace();
+        cpu = raw_smp_processor_id();
+        data = tr->data[cpu];
 
-/* Only allocate if we are actually using the max trace */
-#ifdef CONFIG_TRACER_MAX_TRACE
-                array = (void *)__get_free_page(GFP_KERNEL);
-                if (array == NULL) {
-                        printk(KERN_ERR "tracer: failed to allocate page"
-                               "for trace buffer!\n");
-                        goto free_pages;
-                }
-                pages_allocated++;
-                page = virt_to_page(array);
-                list_add(&page->lru, &pages);
-#endif
-        }
+        if (unlikely(atomic_read(&data->disabled)))
+                goto out;
 
-        /* Now that we successfully allocate a page per CPU, add them */
-        for_each_tracing_cpu(i) {
-                data = global_trace.data[i];
-                page = list_entry(pages.next, struct page, lru);
-                list_del_init(&page->lru);
-                list_add_tail(&page->lru, &data->trace_pages);
-                ClearPageLRU(page);
+        spin_lock_irqsave(&trace_buf_lock, flags);
+        len = vsnprintf(trace_buf, TRACE_BUF_SIZE, fmt, args);
 
-#ifdef CONFIG_TRACER_MAX_TRACE
-                data = max_tr.data[i];
-                page = list_entry(pages.next, struct page, lru);
-                list_del_init(&page->lru);
-                list_add_tail(&page->lru, &data->trace_pages);
-                SetPageLRU(page);
-#endif
-        }
-        tracing_pages_allocated += pages_allocated;
-        global_trace.entries += ENTRIES_PER_PAGE;
+        len = min(len, TRACE_BUF_SIZE-1);
+        trace_buf[len] = 0;
 
-        return 0;
+        size = sizeof(*entry) + len + 1;
+        event = ring_buffer_lock_reserve(tr->buffer, size, &irq_flags);
+        if (!event)
+                goto out_unlock;
+        entry = ring_buffer_event_data(event);
+        tracing_generic_entry_update(&entry->ent, flags, pc);
+        entry->ent.type                 = TRACE_PRINT;
+        entry->ip                       = ip;
 
- free_pages:
-        list_for_each_entry_safe(page, tmp, &pages, lru) {
-                list_del_init(&page->lru);
-                __free_page(page);
-        }
-        return -ENOMEM;
+        memcpy(&entry->buf, trace_buf, len);
+        entry->buf[len] = 0;
+        ring_buffer_unlock_commit(tr->buffer, event, irq_flags);
+
+ out_unlock:
+        spin_unlock_irqrestore(&trace_buf_lock, flags);
+
+ out:
+        preempt_enable_notrace();
+
+        return len;
 }
+EXPORT_SYMBOL_GPL(trace_vprintk);
 
-static int trace_free_page(void)
+int __ftrace_printk(unsigned long ip, const char *fmt, ...)
 {
-        struct trace_array_cpu *data;
-        struct page *page;
-        struct list_head *p;
-        int i;
-        int ret = 0;
+        int ret;
+        va_list ap;
 
-        /* free one page from each buffer */
-        for_each_tracing_cpu(i) {
-                data = global_trace.data[i];
-                p = data->trace_pages.next;
-                if (p == &data->trace_pages) {
-                        /* should never happen */
-                        WARN_ON(1);
-                        tracing_disabled = 1;
-                        ret = -1;
-                        break;
-                }
-                page = list_entry(p, struct page, lru);
-                ClearPageLRU(page);
-                list_del(&page->lru);
-                tracing_pages_allocated--;
-                tracing_pages_allocated--;
-                __free_page(page);
+        if (!(trace_flags & TRACE_ITER_PRINTK))
+                return 0;
 
-                tracing_reset(data);
+        va_start(ap, fmt);
+        ret = trace_vprintk(ip, fmt, ap);
+        va_end(ap);
+        return ret;
+}
+EXPORT_SYMBOL_GPL(__ftrace_printk);
 
-#ifdef CONFIG_TRACER_MAX_TRACE
-                data = max_tr.data[i];
-                p = data->trace_pages.next;
-                if (p == &data->trace_pages) {
-                        /* should never happen */
-                        WARN_ON(1);
-                        tracing_disabled = 1;
-                        ret = -1;
-                        break;
-                }
-                page = list_entry(p, struct page, lru);
-                ClearPageLRU(page);
-                list_del(&page->lru);
-                __free_page(page);
+static int trace_panic_handler(struct notifier_block *this,
+                               unsigned long event, void *unused)
+{
+        ftrace_dump();
+        return NOTIFY_OK;
+}
 
-                tracing_reset(data);
-#endif
-        }
-        global_trace.entries -= ENTRIES_PER_PAGE;
+static struct notifier_block trace_panic_notifier = {
+        .notifier_call  = trace_panic_handler,
+        .next           = NULL,
+        .priority       = 150   /* priority: INT_MAX >= x >= 0 */
+};
 
-        return ret;
+static int trace_die_handler(struct notifier_block *self,
+                             unsigned long val,
+                             void *data)
+{
+        switch (val) {
+        case DIE_OOPS:
+                ftrace_dump();
+                break;
+        default:
+                break;
+        }
+        return NOTIFY_OK;
 }
 
-__init static int tracer_alloc_buffers(void)
+static struct notifier_block trace_die_notifier = {
+        .notifier_call = trace_die_handler,
+        .priority = 200
+};
+
+/*
+ * printk is set to max of 1024, we really don't need it that big.
+ * Nothing should be printing 1000 characters anyway.
+ */
+#define TRACE_MAX_PRINT         1000
+
+/*
+ * Define here KERN_TRACE so that we have one place to modify
+ * it if we decide to change what log level the ftrace dump
+ * should be at.
+ */
+#define KERN_TRACE              KERN_INFO
+
+static void
+trace_printk_seq(struct trace_seq *s)
 {
-        struct trace_array_cpu *data;
-        void *array;
-        struct page *page;
-        int pages = 0;
-        int ret = -ENOMEM;
-        int i;
+        /* Probably should print a warning here. */
+        if (s->len >= 1000)
+                s->len = 1000;
 
-        /* TODO: make the number of buffers hot pluggable with CPUS */
-        tracing_nr_buffers = num_possible_cpus();
-        tracing_buffer_mask = cpu_possible_map;
+        /* should be zero ended, but we are paranoid. */
+        s->buffer[s->len] = 0;
 
-        /* Allocate the first page for all buffers */
-        for_each_tracing_cpu(i) {
-                data = global_trace.data[i] = &per_cpu(global_trace_cpu, i);
-                max_tr.data[i] = &per_cpu(max_data, i);
+        printk(KERN_TRACE "%s", s->buffer);
+
+        trace_seq_reset(s);
+}
 
-                array = (void *)__get_free_page(GFP_KERNEL);
-                if (array == NULL) {
-                        printk(KERN_ERR "tracer: failed to allocate page"
-                               "for trace buffer!\n");
-                        goto free_buffers;
-                }
 
-                /* set the array to the list */
-                INIT_LIST_HEAD(&data->trace_pages);
-                page = virt_to_page(array);
-                list_add(&page->lru, &data->trace_pages);
-                /* use the LRU flag to differentiate the two buffers */
-                ClearPageLRU(page);
+void ftrace_dump(void)
+{
+        static DEFINE_SPINLOCK(ftrace_dump_lock);
+        /* use static because iter can be a bit big for the stack */
+        static struct trace_iterator iter;
+        static cpumask_t mask;
+        static int dump_ran;
+        unsigned long flags;
+        int cnt = 0, cpu;
 
-                data->lock = (raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED;
-                max_tr.data[i]->lock = (raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED;
+        /* only one dump */
+        spin_lock_irqsave(&ftrace_dump_lock, flags);
+        if (dump_ran)
+                goto out;
 
-/* Only allocate if we are actually using the max trace */
-#ifdef CONFIG_TRACER_MAX_TRACE
-                array = (void *)__get_free_page(GFP_KERNEL);
-                if (array == NULL) {
-                        printk(KERN_ERR "tracer: failed to allocate page"
-                               "for trace buffer!\n");
-                        goto free_buffers;
-                }
+        dump_ran = 1;
 
-                INIT_LIST_HEAD(&max_tr.data[i]->trace_pages);
-                page = virt_to_page(array);
-                list_add(&page->lru, &max_tr.data[i]->trace_pages);
-                SetPageLRU(page);
-#endif
+        /* No turning back! */
+        ftrace_kill();
+
+        for_each_tracing_cpu(cpu) {
+                atomic_inc(&global_trace.data[cpu]->disabled);
         }
 
+        printk(KERN_TRACE "Dumping ftrace buffer:\n");
+
+        iter.tr = &global_trace;
+        iter.trace = current_trace;
+
         /*
-         * Since we allocate by orders of pages, we may be able to
-         * round up a bit.
+         * We need to stop all tracing on all CPUS to read the
+         * the next buffer. This is a bit expensive, but is
+         * not done often. We fill all what we can read,
+         * and then release the locks again.
          */
-        global_trace.entries = ENTRIES_PER_PAGE;
-        pages++;
 
-        while (global_trace.entries < trace_nr_entries) {
-                if (trace_alloc_page())
-                        break;
-                pages++;
+        cpus_clear(mask);
+
+        while (!trace_empty(&iter)) {
+
+                if (!cnt)
+                        printk(KERN_TRACE "---------------------------------\n");
+
+                cnt++;
+
+                /* reset all but tr, trace, and overruns */
+                memset(&iter.seq, 0,
+                       sizeof(struct trace_iterator) -
+                       offsetof(struct trace_iterator, seq));
+                iter.iter_flags |= TRACE_FILE_LAT_FMT;
+                iter.pos = -1;
+
+                if (find_next_entry_inc(&iter) != NULL) {
+                        print_trace_line(&iter);
+                        trace_consume(&iter);
+                }
+
+                trace_printk_seq(&iter.seq);
         }
-        max_tr.entries = global_trace.entries;
 
-        pr_info("tracer: %d pages allocated for %ld entries of %ld bytes\n",
-                pages, trace_nr_entries, (long)TRACE_ENTRY_SIZE);
-        pr_info("   actual entries %ld\n", global_trace.entries);
+        if (!cnt)
+                printk(KERN_TRACE "   (ftrace buffer empty)\n");
+        else
+                printk(KERN_TRACE "---------------------------------\n");
+
+ out:
+        spin_unlock_irqrestore(&ftrace_dump_lock, flags);
+}
+
+__init static int tracer_alloc_buffers(void)
+{
+        struct trace_array_cpu *data;
+        int i;
+
+        /* TODO: make the number of buffers hot pluggable with CPUS */
+        tracing_buffer_mask = cpu_possible_map;
+
+        global_trace.buffer = ring_buffer_alloc(trace_buf_size,
+                                                   TRACE_BUFFER_FLAGS);
+        if (!global_trace.buffer) {
+                printk(KERN_ERR "tracer: failed to allocate ring buffer!\n");
+                WARN_ON(1);
+                return 0;
+        }
+        global_trace.entries = ring_buffer_size(global_trace.buffer);
+
+#ifdef CONFIG_TRACER_MAX_TRACE
+        max_tr.buffer = ring_buffer_alloc(trace_buf_size,
+                                             TRACE_BUFFER_FLAGS);
+        if (!max_tr.buffer) {
+                printk(KERN_ERR "tracer: failed to allocate max ring buffer!\n");
+                WARN_ON(1);
+                ring_buffer_free(global_trace.buffer);
+                return 0;
+        }
+        max_tr.entries = ring_buffer_size(max_tr.buffer);
+        WARN_ON(max_tr.entries != global_trace.entries);
+#endif
 
-        tracer_init_debugfs();
+        /* Allocate the first page for all buffers */
+        for_each_tracing_cpu(i) {
+                data = global_trace.data[i] = &per_cpu(global_trace_cpu, i);
+                max_tr.data[i] = &per_cpu(max_data, i);
+        }
 
         trace_init_cmdlines();
 
-        register_tracer(&no_tracer);
-        current_trace = &no_tracer;
+        register_tracer(&nop_trace);
+#ifdef CONFIG_BOOT_TRACER
+        register_tracer(&boot_tracer);
+        current_trace = &boot_tracer;
+        current_trace->init(&global_trace);
+#else
+        current_trace = &nop_trace;
+#endif
 
         /* All seems OK, enable tracing */
         global_trace.ctrl = tracer_enabled;
         tracing_disabled = 0;
 
-        return 0;
-
- free_buffers:
-        for (i-- ; i >= 0; i--) {
-                struct page *page, *tmp;
-                struct trace_array_cpu *data = global_trace.data[i];
+        atomic_notifier_chain_register(&panic_notifier_list,
+                                       &trace_panic_notifier);
 
-                if (data) {
-                        list_for_each_entry_safe(page, tmp,
-                                                 &data->trace_pages, lru) {
-                                list_del_init(&page->lru);
-                                __free_page(page);
-                        }
-                }
+        register_die_notifier(&trace_die_notifier);
 
-#ifdef CONFIG_TRACER_MAX_TRACE
-                data = max_tr.data[i];
-                if (data) {
-                        list_for_each_entry_safe(page, tmp,
-                                                 &data->trace_pages, lru) {
-                                list_del_init(&page->lru);
-                                __free_page(page);
-                        }
-                }
-#endif
-        }
-        return ret;
+        return 0;
 }
-fs_initcall(tracer_alloc_buffers);
+early_initcall(tracer_alloc_buffers);
+fs_initcall(tracer_init_debugfs);
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index f69f86788c2b..8465ad052707 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -5,7 +5,9 @@
 #include <asm/atomic.h>
 #include <linux/sched.h>
 #include <linux/clocksource.h>
+#include <linux/ring_buffer.h>
 #include <linux/mmiotrace.h>
+#include <linux/ftrace.h>
 
 enum trace_type {
         __TRACE_FIRST_TYPE = 0,
@@ -13,38 +15,60 @@ enum trace_type {
         TRACE_FN,
         TRACE_CTX,
         TRACE_WAKE,
+        TRACE_CONT,
         TRACE_STACK,
+        TRACE_PRINT,
         TRACE_SPECIAL,
         TRACE_MMIO_RW,
         TRACE_MMIO_MAP,
+        TRACE_BOOT,
 
         __TRACE_LAST_TYPE
 };
 
 /*
+ * The trace entry - the most basic unit of tracing. This is what
+ * is printed in the end as a single line in the trace output, such as:
+ *
+ *     bash-15816 [01]   235.197585: idle_cpu <- irq_enter
+ */
+struct trace_entry {
+        unsigned char           type;
+        unsigned char           cpu;
+        unsigned char           flags;
+        unsigned char           preempt_count;
+        int                     pid;
+};
+
+/*
  * Function trace entry - function address and parent function addres:
  */
 struct ftrace_entry {
+        struct trace_entry      ent;
         unsigned long           ip;
         unsigned long           parent_ip;
 };
+extern struct tracer boot_tracer;
 
 /*
  * Context switch trace entry - which task (and prio) we switched from/to:
  */
 struct ctx_switch_entry {
+        struct trace_entry      ent;
         unsigned int            prev_pid;
         unsigned char           prev_prio;
         unsigned char           prev_state;
         unsigned int            next_pid;
         unsigned char           next_prio;
         unsigned char           next_state;
+        unsigned int            next_cpu;
 };
 
 /*
  * Special (free-form) trace entry:
  */
 struct special_entry {
+        struct trace_entry      ent;
         unsigned long           arg1;
         unsigned long           arg2;
         unsigned long           arg3;
@@ -57,33 +81,62 @@ struct special_entry {
 #define FTRACE_STACK_ENTRIES    8
 
 struct stack_entry {
+        struct trace_entry      ent;
         unsigned long           caller[FTRACE_STACK_ENTRIES];
 };
 
 /*
- * The trace entry - the most basic unit of tracing. This is what
- * is printed in the end as a single line in the trace output, such as:
- *
- *     bash-15816 [01]   235.197585: idle_cpu <- irq_enter
+ * ftrace_printk entry:
  */
-struct trace_entry {
-        char                    type;
-        char                    cpu;
-        char                    flags;
-        char                    preempt_count;
-        int                     pid;
-        cycle_t                 t;
-        union {
-                struct ftrace_entry             fn;
-                struct ctx_switch_entry         ctx;
-                struct special_entry            special;
-                struct stack_entry              stack;
-                struct mmiotrace_rw             mmiorw;
-                struct mmiotrace_map            mmiomap;
-        };
+struct print_entry {
+        struct trace_entry      ent;
+        unsigned long           ip;
+        char                    buf[];
+};
+
+#define TRACE_OLD_SIZE          88
+
+struct trace_field_cont {
+        unsigned char           type;
+        /* Temporary till we get rid of this completely */
+        char                    buf[TRACE_OLD_SIZE - 1];
+};
+
+struct trace_mmiotrace_rw {
+        struct trace_entry      ent;
+        struct mmiotrace_rw     rw;
+};
+
+struct trace_mmiotrace_map {
+        struct trace_entry      ent;
+        struct mmiotrace_map    map;
+};
+
+struct trace_boot {
+        struct trace_entry      ent;
+        struct boot_trace       initcall;
+};
+
+/*
+ * trace_flag_type is an enumeration that holds different
+ * states when a trace occurs. These are:
+ *  IRQS_OFF            - interrupts were disabled
+ *  IRQS_NOSUPPORT      - arch does not support irqs_disabled_flags
+ *  NEED_RESCED         - reschedule is requested
+ *  HARDIRQ             - inside an interrupt handler
+ *  SOFTIRQ             - inside a softirq handler
+ *  CONT                - multiple entries hold the trace item
+ */
+enum trace_flag_type {
+        TRACE_FLAG_IRQS_OFF             = 0x01,
+        TRACE_FLAG_IRQS_NOSUPPORT       = 0x02,
+        TRACE_FLAG_NEED_RESCHED         = 0x04,
+        TRACE_FLAG_HARDIRQ              = 0x08,
+        TRACE_FLAG_SOFTIRQ              = 0x10,
+        TRACE_FLAG_CONT                 = 0x20,
 };
 
-#define TRACE_ENTRY_SIZE        sizeof(struct trace_entry)
+#define TRACE_BUF_SIZE          1024
 
 /*
  * The CPU trace array - it consists of thousands of trace entries
@@ -91,16 +144,9 @@ struct trace_entry {
  * the trace, etc.)
  */
 struct trace_array_cpu {
-        struct list_head        trace_pages;
         atomic_t                disabled;
-        raw_spinlock_t          lock;
-        struct lock_class_key   lock_key;
 
         /* these fields get copied into max-trace: */
-        unsigned                trace_head_idx;
-        unsigned                trace_tail_idx;
-        void                    *trace_head; /* producer */
-        void                    *trace_tail; /* consumer */
         unsigned long           trace_idx;
         unsigned long           overrun;
         unsigned long           saved_latency;
@@ -124,6 +170,7 @@ struct trace_iterator;
  * They have on/off state as well:
  */
 struct trace_array {
+        struct ring_buffer      *buffer;
         unsigned long           entries;
         long                    ctrl;
         int                     cpu;
@@ -132,6 +179,56 @@ struct trace_array {
         struct trace_array_cpu  *data[NR_CPUS];
 };
 
+#define FTRACE_CMP_TYPE(var, type) \
+        __builtin_types_compatible_p(typeof(var), type *)
+
+#undef IF_ASSIGN
+#define IF_ASSIGN(var, entry, etype, id)                \
+        if (FTRACE_CMP_TYPE(var, etype)) {              \
+                var = (typeof(var))(entry);             \
+                WARN_ON(id && (entry)->type != id);     \
+                break;                                  \
+        }
+
+/* Will cause compile errors if type is not found. */
+extern void __ftrace_bad_type(void);
+
+/*
+ * The trace_assign_type is a verifier that the entry type is
+ * the same as the type being assigned. To add new types simply
+ * add a line with the following format:
+ *
+ * IF_ASSIGN(var, ent, type, id);
+ *
+ *  Where "type" is the trace type that includes the trace_entry
+ *  as the "ent" item. And "id" is the trace identifier that is
+ *  used in the trace_type enum.
+ *
+ *  If the type can have more than one id, then use zero.
+ */
+#define trace_assign_type(var, ent)                                     \
+        do {                                                            \
+                IF_ASSIGN(var, ent, struct ftrace_entry, TRACE_FN);     \
+                IF_ASSIGN(var, ent, struct ctx_switch_entry, 0);        \
+                IF_ASSIGN(var, ent, struct trace_field_cont, TRACE_CONT); \
+                IF_ASSIGN(var, ent, struct stack_entry, TRACE_STACK);   \
+                IF_ASSIGN(var, ent, struct print_entry, TRACE_PRINT);   \
+                IF_ASSIGN(var, ent, struct special_entry, 0);           \
+                IF_ASSIGN(var, ent, struct trace_mmiotrace_rw,          \
+                          TRACE_MMIO_RW);                               \
+                IF_ASSIGN(var, ent, struct trace_mmiotrace_map,         \
+                          TRACE_MMIO_MAP);                              \
+                IF_ASSIGN(var, ent, struct trace_boot, TRACE_BOOT);     \
+                __ftrace_bad_type();                                    \
+        } while (0)
+
+/* Return values for print_line callback */
+enum print_line_t {
+        TRACE_TYPE_PARTIAL_LINE = 0,    /* Retry after flushing the seq */
+        TRACE_TYPE_HANDLED      = 1,
+        TRACE_TYPE_UNHANDLED    = 2     /* Relay to other output functions */
+};
+
 /*
  * A specific tracer, represented by methods that operate on a trace array:
  */
@@ -152,7 +249,7 @@ struct tracer {
         int                     (*selftest)(struct tracer *trace,
                                             struct trace_array *tr);
 #endif
-        int                     (*print_line)(struct trace_iterator *iter);
+        enum print_line_t       (*print_line)(struct trace_iterator *iter);
         struct tracer           *next;
         int                     print_max;
 };
@@ -171,57 +268,58 @@ struct trace_iterator {
         struct trace_array      *tr;
         struct tracer           *trace;
         void                    *private;
-        long                    last_overrun[NR_CPUS];
-        long                    overrun[NR_CPUS];
+        struct ring_buffer_iter *buffer_iter[NR_CPUS];
 
         /* The below is zeroed out in pipe_read */
         struct trace_seq        seq;
         struct trace_entry      *ent;
         int                     cpu;
-
-        struct trace_entry      *prev_ent;
-        int                     prev_cpu;
+        u64                     ts;
 
         unsigned long           iter_flags;
         loff_t                  pos;
-        unsigned long           next_idx[NR_CPUS];
-        struct list_head        *next_page[NR_CPUS];
-        unsigned                next_page_idx[NR_CPUS];
         long                    idx;
 };
 
-void tracing_reset(struct trace_array_cpu *data);
+void trace_wake_up(void);
+void tracing_reset(struct trace_array *tr, int cpu);
 int tracing_open_generic(struct inode *inode, struct file *filp);
 struct dentry *tracing_init_dentry(void);
 void init_tracer_sysprof_debugfs(struct dentry *d_tracer);
 
+struct trace_entry *tracing_get_trace_entry(struct trace_array *tr,
+                                                struct trace_array_cpu *data);
+void tracing_generic_entry_update(struct trace_entry *entry,
+                                  unsigned long flags,
+                                  int pc);
+
 void ftrace(struct trace_array *tr,
                             struct trace_array_cpu *data,
                             unsigned long ip,
                             unsigned long parent_ip,
-                            unsigned long flags);
+                            unsigned long flags, int pc);
 void tracing_sched_switch_trace(struct trace_array *tr,
                                 struct trace_array_cpu *data,
                                 struct task_struct *prev,
                                 struct task_struct *next,
-                                unsigned long flags);
+                                unsigned long flags, int pc);
 void tracing_record_cmdline(struct task_struct *tsk);
 
 void tracing_sched_wakeup_trace(struct trace_array *tr,
                                 struct trace_array_cpu *data,
                                 struct task_struct *wakee,
                                 struct task_struct *cur,
-                                unsigned long flags);
+                                unsigned long flags, int pc);
 void trace_special(struct trace_array *tr,
                    struct trace_array_cpu *data,
                    unsigned long arg1,
                    unsigned long arg2,
-                   unsigned long arg3);
+                   unsigned long arg3, int pc);
 void trace_function(struct trace_array *tr,
                     struct trace_array_cpu *data,
                     unsigned long ip,
                     unsigned long parent_ip,
-                    unsigned long flags);
+                    unsigned long flags, int pc);
 
 void tracing_start_cmdline_record(void);
 void tracing_stop_cmdline_record(void);
@@ -239,7 +337,7 @@ void update_max_tr_single(struct trace_array *tr,
 
 extern cycle_t ftrace_now(int cpu);
 
-#ifdef CONFIG_FTRACE
+#ifdef CONFIG_FUNCTION_TRACER
 void tracing_start_function_trace(void);
 void tracing_stop_function_trace(void);
 #else
@@ -268,51 +366,33 @@ extern unsigned long ftrace_update_tot_cnt;
 extern int DYN_FTRACE_TEST_NAME(void);
 #endif
 
-#ifdef CONFIG_MMIOTRACE
-extern void __trace_mmiotrace_rw(struct trace_array *tr,
-                                struct trace_array_cpu *data,
-                                struct mmiotrace_rw *rw);
-extern void __trace_mmiotrace_map(struct trace_array *tr,
-                                struct trace_array_cpu *data,
-                                struct mmiotrace_map *map);
-#endif
-
 #ifdef CONFIG_FTRACE_STARTUP_TEST
-#ifdef CONFIG_FTRACE
 extern int trace_selftest_startup_function(struct tracer *trace,
                                            struct trace_array *tr);
-#endif
-#ifdef CONFIG_IRQSOFF_TRACER
 extern int trace_selftest_startup_irqsoff(struct tracer *trace,
                                           struct trace_array *tr);
-#endif
-#ifdef CONFIG_PREEMPT_TRACER
 extern int trace_selftest_startup_preemptoff(struct tracer *trace,
                                              struct trace_array *tr);
-#endif
-#if defined(CONFIG_IRQSOFF_TRACER) && defined(CONFIG_PREEMPT_TRACER)
 extern int trace_selftest_startup_preemptirqsoff(struct tracer *trace,
                                                  struct trace_array *tr);
-#endif
-#ifdef CONFIG_SCHED_TRACER
 extern int trace_selftest_startup_wakeup(struct tracer *trace,
                                          struct trace_array *tr);
-#endif
-#ifdef CONFIG_CONTEXT_SWITCH_TRACER
+extern int trace_selftest_startup_nop(struct tracer *trace,
+                                         struct trace_array *tr);
 extern int trace_selftest_startup_sched_switch(struct tracer *trace,
                                                struct trace_array *tr);
-#endif
-#ifdef CONFIG_SYSPROF_TRACER
 extern int trace_selftest_startup_sysprof(struct tracer *trace,
                                                struct trace_array *tr);
-#endif
 #endif /* CONFIG_FTRACE_STARTUP_TEST */
 
 extern void *head_page(struct trace_array_cpu *data);
 extern int trace_seq_printf(struct trace_seq *s, const char *fmt, ...);
+extern void trace_seq_print_cont(struct trace_seq *s,
+                                 struct trace_iterator *iter);
 extern ssize_t trace_seq_to_user(struct trace_seq *s, char __user *ubuf,
                                  size_t cnt);
 extern long ns2usecs(cycle_t nsec);
+extern int trace_vprintk(unsigned long ip, const char *fmt, va_list args);
 
 extern unsigned long trace_flags;
 
@@ -334,6 +414,9 @@ enum trace_iterator_flags {
         TRACE_ITER_BLOCK                = 0x80,
         TRACE_ITER_STACKTRACE           = 0x100,
         TRACE_ITER_SCHED_TREE           = 0x200,
+        TRACE_ITER_PRINTK               = 0x400,
 };
 
+extern struct tracer nop_trace;
+
 #endif /* _LINUX_KERNEL_TRACE_H */
diff --git a/kernel/trace/trace_boot.c b/kernel/trace/trace_boot.c
new file mode 100644
index 000000000000..d0a5e50eeff2
--- /dev/null
+++ b/kernel/trace/trace_boot.c
@@ -0,0 +1,126 @@
+/*
+ * ring buffer based initcalls tracer
+ *
+ * Copyright (C) 2008 Frederic Weisbecker <fweisbec@gmail.com>
+ *
+ */
+
+#include <linux/init.h>
+#include <linux/debugfs.h>
+#include <linux/ftrace.h>
+#include <linux/kallsyms.h>
+
+#include "trace.h"
+
+static struct trace_array *boot_trace;
+static int trace_boot_enabled;
+
+
+/* Should be started after do_pre_smp_initcalls() in init/main.c */
+void start_boot_trace(void)
+{
+        trace_boot_enabled = 1;
+}
+
+void stop_boot_trace(void)
+{
+        trace_boot_enabled = 0;
+}
+
+void reset_boot_trace(struct trace_array *tr)
+{
+        stop_boot_trace();
+}
+
+static void boot_trace_init(struct trace_array *tr)
+{
+        int cpu;
+        boot_trace = tr;
+
+        trace_boot_enabled = 0;
+
+        for_each_cpu_mask(cpu, cpu_possible_map)
+                tracing_reset(tr, cpu);
+}
+
+static void boot_trace_ctrl_update(struct trace_array *tr)
+{
+        if (tr->ctrl)
+                start_boot_trace();
+        else
+                stop_boot_trace();
+}
+
+static enum print_line_t initcall_print_line(struct trace_iterator *iter)
+{
+        int ret;
+        struct trace_entry *entry = iter->ent;
+        struct trace_boot *field = (struct trace_boot *)entry;
+        struct boot_trace *it = &field->initcall;
+        struct trace_seq *s = &iter->seq;
+        struct timespec calltime = ktime_to_timespec(it->calltime);
+        struct timespec rettime = ktime_to_timespec(it->rettime);
+
+        if (entry->type == TRACE_BOOT) {
+                ret = trace_seq_printf(s, "[%5ld.%09ld] calling  %s @ %i\n",
+                                          calltime.tv_sec,
+                                          calltime.tv_nsec,
+                                          it->func, it->caller);
+                if (!ret)
+                        return TRACE_TYPE_PARTIAL_LINE;
+
+                ret = trace_seq_printf(s, "[%5ld.%09ld] initcall %s "
+                                          "returned %d after %lld msecs\n",
+                                          rettime.tv_sec,
+                                          rettime.tv_nsec,
+                                          it->func, it->result, it->duration);
+
+                if (!ret)
+                        return TRACE_TYPE_PARTIAL_LINE;
+                return TRACE_TYPE_HANDLED;
+        }
+        return TRACE_TYPE_UNHANDLED;
+}
+
+struct tracer boot_tracer __read_mostly =
+{
+        .name           = "initcall",
+        .init           = boot_trace_init,
+        .reset          = reset_boot_trace,
+        .ctrl_update    = boot_trace_ctrl_update,
+        .print_line     = initcall_print_line,
+};
+
+void trace_boot(struct boot_trace *it, initcall_t fn)
+{
+        struct ring_buffer_event *event;
+        struct trace_boot *entry;
+        struct trace_array_cpu *data;
+        unsigned long irq_flags;
+        struct trace_array *tr = boot_trace;
+
+        if (!trace_boot_enabled)
+                return;
+
+        /* Get its name now since this function could
+         * disappear because it is in the .init section.
+         */
+        sprint_symbol(it->func, (unsigned long)fn);
+        preempt_disable();
+        data = tr->data[smp_processor_id()];
+
+        event = ring_buffer_lock_reserve(tr->buffer, sizeof(*entry),
+                                         &irq_flags);
+        if (!event)
+                goto out;
+        entry   = ring_buffer_event_data(event);
+        tracing_generic_entry_update(&entry->ent, 0, 0);
+        entry->ent.type = TRACE_BOOT;
+        entry->initcall = *it;
+        ring_buffer_unlock_commit(tr->buffer, event, irq_flags);
+
+        trace_wake_up();
+
+ out:
+        preempt_enable();
+}
diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c
index 312144897970..0f85a64003d3 100644
--- a/kernel/trace/trace_functions.c
+++ b/kernel/trace/trace_functions.c
@@ -23,7 +23,7 @@ static void function_reset(struct trace_array *tr)
         tr->time_start = ftrace_now(tr->cpu);
 
         for_each_online_cpu(cpu)
-                tracing_reset(tr->data[cpu]);
+                tracing_reset(tr, cpu);
 }
 
 static void start_function_trace(struct trace_array *tr)
@@ -64,7 +64,7 @@ static void function_trace_ctrl_update(struct trace_array *tr)
 
 static struct tracer function_trace __read_mostly =
 {
-        .name        = "ftrace",
+        .name        = "function",
         .init        = function_trace_init,
         .reset       = function_trace_reset,
         .ctrl_update = function_trace_ctrl_update,
diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c
index ece6cfb649fa..9c74071c10e0 100644
--- a/kernel/trace/trace_irqsoff.c
+++ b/kernel/trace/trace_irqsoff.c
@@ -63,7 +63,7 @@ irq_trace(void)
  */
 static __cacheline_aligned_in_smp       unsigned long max_sequence;
 
-#ifdef CONFIG_FTRACE
+#ifdef CONFIG_FUNCTION_TRACER
 /*
  * irqsoff uses its own tracer function to keep the overhead down:
  */
@@ -95,7 +95,7 @@ irqsoff_tracer_call(unsigned long ip, unsigned long parent_ip)
         disabled = atomic_inc_return(&data->disabled);
 
         if (likely(disabled == 1))
-                trace_function(tr, data, ip, parent_ip, flags);
+                trace_function(tr, data, ip, parent_ip, flags, preempt_count());
 
         atomic_dec(&data->disabled);
 }
@@ -104,7 +104,7 @@ static struct ftrace_ops trace_ops __read_mostly =
 {
         .func = irqsoff_tracer_call,
 };
-#endif /* CONFIG_FTRACE */
+#endif /* CONFIG_FUNCTION_TRACER */
 
 /*
  * Should this new latency be reported/recorded?
@@ -130,6 +130,7 @@ check_critical_timing(struct trace_array *tr,
         unsigned long latency, t0, t1;
         cycle_t T0, T1, delta;
         unsigned long flags;
+        int pc;
 
         /*
          * usecs conversion is slow so we try to delay the conversion
@@ -141,6 +142,8 @@ check_critical_timing(struct trace_array *tr,
 
         local_save_flags(flags);
 
+        pc = preempt_count();
+
         if (!report_latency(delta))
                 goto out;
 
@@ -150,7 +153,7 @@ check_critical_timing(struct trace_array *tr,
         if (!report_latency(delta))
                 goto out_unlock;
 
-        trace_function(tr, data, CALLER_ADDR0, parent_ip, flags);
+        trace_function(tr, data, CALLER_ADDR0, parent_ip, flags, pc);
 
         latency = nsecs_to_usecs(delta);
 
@@ -173,8 +176,8 @@ out_unlock:
 out:
         data->critical_sequence = max_sequence;
         data->preempt_timestamp = ftrace_now(cpu);
-        tracing_reset(data);
-        trace_function(tr, data, CALLER_ADDR0, parent_ip, flags);
+        tracing_reset(tr, cpu);
+        trace_function(tr, data, CALLER_ADDR0, parent_ip, flags, pc);
 }
 
 static inline void
@@ -203,11 +206,11 @@ start_critical_timing(unsigned long ip, unsigned long parent_ip)
         data->critical_sequence = max_sequence;
         data->preempt_timestamp = ftrace_now(cpu);
         data->critical_start = parent_ip ? : ip;
-        tracing_reset(data);
+        tracing_reset(tr, cpu);
 
         local_save_flags(flags);
 
-        trace_function(tr, data, ip, parent_ip, flags);
+        trace_function(tr, data, ip, parent_ip, flags, preempt_count());
 
         per_cpu(tracing_cpu, cpu) = 1;
 
@@ -234,14 +237,14 @@ stop_critical_timing(unsigned long ip, unsigned long parent_ip)
 
         data = tr->data[cpu];
 
-        if (unlikely(!data) || unlikely(!head_page(data)) ||
+        if (unlikely(!data) ||
             !data->critical_start || atomic_read(&data->disabled))
                 return;
 
         atomic_inc(&data->disabled);
 
         local_save_flags(flags);
-        trace_function(tr, data, ip, parent_ip, flags);
+        trace_function(tr, data, ip, parent_ip, flags, preempt_count());
         check_critical_timing(tr, data, parent_ip ? : ip, cpu);
         data->critical_start = 0;
         atomic_dec(&data->disabled);
diff --git a/kernel/trace/trace_mmiotrace.c b/kernel/trace/trace_mmiotrace.c
index b13dc19dcbb4..f28484618ff0 100644
--- a/kernel/trace/trace_mmiotrace.c
+++ b/kernel/trace/trace_mmiotrace.c
@@ -27,7 +27,7 @@ static void mmio_reset_data(struct trace_array *tr)
         tr->time_start = ftrace_now(tr->cpu);
 
         for_each_online_cpu(cpu)
-                tracing_reset(tr->data[cpu]);
+                tracing_reset(tr, cpu);
 }
 
 static void mmio_trace_init(struct trace_array *tr)
@@ -130,10 +130,14 @@ static unsigned long count_overruns(struct trace_iterator *iter)
 {
         int cpu;
         unsigned long cnt = 0;
+/* FIXME: */
+#if 0
         for_each_online_cpu(cpu) {
                 cnt += iter->overrun[cpu];
                 iter->overrun[cpu] = 0;
         }
+#endif
+        (void)cpu;
         return cnt;
 }
 
@@ -171,17 +175,21 @@ print_out:
         return (ret == -EBUSY) ? 0 : ret;
 }
 
-static int mmio_print_rw(struct trace_iterator *iter)
+static enum print_line_t mmio_print_rw(struct trace_iterator *iter)
 {
         struct trace_entry *entry = iter->ent;
-        struct mmiotrace_rw *rw = &entry->mmiorw;
+        struct trace_mmiotrace_rw *field;
+        struct mmiotrace_rw *rw;
         struct trace_seq *s     = &iter->seq;
-        unsigned long long t    = ns2usecs(entry->t);
+        unsigned long long t    = ns2usecs(iter->ts);
         unsigned long usec_rem  = do_div(t, 1000000ULL);
         unsigned secs           = (unsigned long)t;
         int ret = 1;
 
-        switch (entry->mmiorw.opcode) {
+        trace_assign_type(field, entry);
+        rw = &field->rw;
+
+        switch (rw->opcode) {
         case MMIO_READ:
                 ret = trace_seq_printf(s,
                         "R %d %lu.%06lu %d 0x%llx 0x%lx 0x%lx %d\n",
@@ -209,21 +217,25 @@ static int mmio_print_rw(struct trace_iterator *iter)
                 break;
         }
         if (ret)
-                return 1;
-        return 0;
+                return TRACE_TYPE_HANDLED;
+        return TRACE_TYPE_PARTIAL_LINE;
 }
 
-static int mmio_print_map(struct trace_iterator *iter)
+static enum print_line_t mmio_print_map(struct trace_iterator *iter)
 {
         struct trace_entry *entry = iter->ent;
-        struct mmiotrace_map *m = &entry->mmiomap;
+        struct trace_mmiotrace_map *field;
+        struct mmiotrace_map *m;
         struct trace_seq *s     = &iter->seq;
-        unsigned long long t    = ns2usecs(entry->t);
+        unsigned long long t    = ns2usecs(iter->ts);
         unsigned long usec_rem  = do_div(t, 1000000ULL);
         unsigned secs           = (unsigned long)t;
-        int ret = 1;
+        int ret;
 
-        switch (entry->mmiorw.opcode) {
+        trace_assign_type(field, entry);
+        m = &field->map;
+
+        switch (m->opcode) {
         case MMIO_PROBE:
                 ret = trace_seq_printf(s,
                         "MAP %lu.%06lu %d 0x%llx 0x%lx 0x%lx 0x%lx %d\n",
@@ -241,20 +253,43 @@ static int mmio_print_map(struct trace_iterator *iter)
                 break;
         }
         if (ret)
-                return 1;
-        return 0;
+                return TRACE_TYPE_HANDLED;
+        return TRACE_TYPE_PARTIAL_LINE;
+}
+
+static enum print_line_t mmio_print_mark(struct trace_iterator *iter)
+{
+        struct trace_entry *entry = iter->ent;
+        struct print_entry *print = (struct print_entry *)entry;
+        const char *msg         = print->buf;
+        struct trace_seq *s     = &iter->seq;
+        unsigned long long t    = ns2usecs(iter->ts);
+        unsigned long usec_rem  = do_div(t, 1000000ULL);
+        unsigned secs           = (unsigned long)t;
+        int ret;
+
+        /* The trailing newline must be in the message. */
+        ret = trace_seq_printf(s, "MARK %lu.%06lu %s", secs, usec_rem, msg);
+        if (!ret)
+                return TRACE_TYPE_PARTIAL_LINE;
+
+        if (entry->flags & TRACE_FLAG_CONT)
+                trace_seq_print_cont(s, iter);
+
+        return TRACE_TYPE_HANDLED;
 }
 
-/* return 0 to abort printing without consuming current entry in pipe mode */
-static int mmio_print_line(struct trace_iterator *iter)
+static enum print_line_t mmio_print_line(struct trace_iterator *iter)
 {
         switch (iter->ent->type) {
         case TRACE_MMIO_RW:
                 return mmio_print_rw(iter);
         case TRACE_MMIO_MAP:
                 return mmio_print_map(iter);
+        case TRACE_PRINT:
+                return mmio_print_mark(iter);
         default:
-                return 1; /* ignore unknown entries */
+                return TRACE_TYPE_HANDLED; /* ignore unknown entries */
         }
 }
 
@@ -276,6 +311,27 @@ __init static int init_mmio_trace(void)
 }
 device_initcall(init_mmio_trace);
 
+static void __trace_mmiotrace_rw(struct trace_array *tr,
+                                struct trace_array_cpu *data,
+                                struct mmiotrace_rw *rw)
+{
+        struct ring_buffer_event *event;
+        struct trace_mmiotrace_rw *entry;
+        unsigned long irq_flags;
+
+        event   = ring_buffer_lock_reserve(tr->buffer, sizeof(*entry),
+                                           &irq_flags);
+        if (!event)
+                return;
+        entry   = ring_buffer_event_data(event);
+        tracing_generic_entry_update(&entry->ent, 0, preempt_count());
+        entry->ent.type                 = TRACE_MMIO_RW;
+        entry->rw                       = *rw;
+        ring_buffer_unlock_commit(tr->buffer, event, irq_flags);
+
+        trace_wake_up();
+}
+
 void mmio_trace_rw(struct mmiotrace_rw *rw)
 {
         struct trace_array *tr = mmio_trace_array;
@@ -283,6 +339,27 @@ void mmio_trace_rw(struct mmiotrace_rw *rw)
         __trace_mmiotrace_rw(tr, data, rw);
 }
 
+static void __trace_mmiotrace_map(struct trace_array *tr,
+                                struct trace_array_cpu *data,
+                                struct mmiotrace_map *map)
+{
+        struct ring_buffer_event *event;
+        struct trace_mmiotrace_map *entry;
+        unsigned long irq_flags;
+
+        event   = ring_buffer_lock_reserve(tr->buffer, sizeof(*entry),
+                                           &irq_flags);
+        if (!event)
+                return;
+        entry   = ring_buffer_event_data(event);
+        tracing_generic_entry_update(&entry->ent, 0, preempt_count());
+        entry->ent.type                 = TRACE_MMIO_MAP;
+        entry->map                      = *map;
+        ring_buffer_unlock_commit(tr->buffer, event, irq_flags);
+
+        trace_wake_up();
+}
+
 void mmio_trace_mapping(struct mmiotrace_map *map)
 {
         struct trace_array *tr = mmio_trace_array;
@@ -293,3 +370,8 @@ void mmio_trace_mapping(struct mmiotrace_map *map)
         __trace_mmiotrace_map(tr, data, map);
         preempt_enable();
 }
+
+int mmio_trace_printk(const char *fmt, va_list args)
+{
+        return trace_vprintk(0, fmt, args);
+}
diff --git a/kernel/trace/trace_nop.c b/kernel/trace/trace_nop.c
new file mode 100644
index 000000000000..4592b4862515
--- /dev/null
+++ b/kernel/trace/trace_nop.c
@@ -0,0 +1,64 @@
+/*
+ * nop tracer
+ *
+ * Copyright (C) 2008 Steven Noonan <steven@uplinklabs.net>
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/fs.h>
+#include <linux/debugfs.h>
+#include <linux/ftrace.h>
+
+#include "trace.h"
+
+static struct trace_array       *ctx_trace;
+
+static void start_nop_trace(struct trace_array *tr)
+{
+        /* Nothing to do! */
+}
+
+static void stop_nop_trace(struct trace_array *tr)
+{
+        /* Nothing to do! */
+}
+
+static void nop_trace_init(struct trace_array *tr)
+{
+        int cpu;
+        ctx_trace = tr;
+
+        for_each_online_cpu(cpu)
+                tracing_reset(tr, cpu);
+
+        if (tr->ctrl)
+                start_nop_trace(tr);
+}
+
+static void nop_trace_reset(struct trace_array *tr)
+{
+        if (tr->ctrl)
+                stop_nop_trace(tr);
+}
+
+static void nop_trace_ctrl_update(struct trace_array *tr)
+{
+        /* When starting a new trace, reset the buffers */
+        if (tr->ctrl)
+                start_nop_trace(tr);
+        else
+                stop_nop_trace(tr);
+}
+
+struct tracer nop_trace __read_mostly =
+{
+        .name           = "nop",
+        .init           = nop_trace_init,
+        .reset          = nop_trace_reset,
+        .ctrl_update    = nop_trace_ctrl_update,
+#ifdef CONFIG_FTRACE_SELFTEST
+        .selftest       = trace_selftest_startup_nop,
+#endif
+};
+
diff --git a/kernel/trace/trace_sched_switch.c b/kernel/trace/trace_sched_switch.c
index cb817a209aa0..b8f56beb1a62 100644
--- a/kernel/trace/trace_sched_switch.c
+++ b/kernel/trace/trace_sched_switch.c
@@ -9,8 +9,8 @@
 #include <linux/debugfs.h>
 #include <linux/kallsyms.h>
 #include <linux/uaccess.h>
-#include <linux/marker.h>
 #include <linux/ftrace.h>
+#include <trace/sched.h>
 
 #include "trace.h"
 
@@ -19,15 +19,16 @@ static int __read_mostly	tracer_enabled;
 static atomic_t                 sched_ref;
 
 static void
-sched_switch_func(void *private, void *__rq, struct task_struct *prev,
+probe_sched_switch(struct rq *__rq, struct task_struct *prev,
                         struct task_struct *next)
 {
-        struct trace_array **ptr = private;
-        struct trace_array *tr = *ptr;
         struct trace_array_cpu *data;
         unsigned long flags;
-        long disabled;
         int cpu;
+        int pc;
+
+        if (!atomic_read(&sched_ref))
+                return;
 
         tracing_record_cmdline(prev);
         tracing_record_cmdline(next);
@@ -35,97 +36,41 @@ sched_switch_func(void *private, void *__rq, struct task_struct *prev,
         if (!tracer_enabled)
                 return;
 
+        pc = preempt_count();
         local_irq_save(flags);
         cpu = raw_smp_processor_id();
-        data = tr->data[cpu];
-        disabled = atomic_inc_return(&data->disabled);
+        data = ctx_trace->data[cpu];
 
-        if (likely(disabled == 1))
-                tracing_sched_switch_trace(tr, data, prev, next, flags);
+        if (likely(!atomic_read(&data->disabled)))
+                tracing_sched_switch_trace(ctx_trace, data, prev, next, flags, pc);
 
-        atomic_dec(&data->disabled);
         local_irq_restore(flags);
 }
 
-static notrace void
-sched_switch_callback(void *probe_data, void *call_data,
-                      const char *format, va_list *args)
-{
-        struct task_struct *prev;
-        struct task_struct *next;
-        struct rq *__rq;
-
-        if (!atomic_read(&sched_ref))
-                return;
-
-        /* skip prev_pid %d next_pid %d prev_state %ld */
-        (void)va_arg(*args, int);
-        (void)va_arg(*args, int);
-        (void)va_arg(*args, long);
-        __rq = va_arg(*args, typeof(__rq));
-        prev = va_arg(*args, typeof(prev));
-        next = va_arg(*args, typeof(next));
-
-        /*
-         * If tracer_switch_func only points to the local
-         * switch func, it still needs the ptr passed to it.
-         */
-        sched_switch_func(probe_data, __rq, prev, next);
-}
-
 static void
-wakeup_func(void *private, void *__rq, struct task_struct *wakee, struct
-                        task_struct *curr)
+probe_sched_wakeup(struct rq *__rq, struct task_struct *wakee)
 {
-        struct trace_array **ptr = private;
-        struct trace_array *tr = *ptr;
         struct trace_array_cpu *data;
         unsigned long flags;
-        long disabled;
-        int cpu;
+        int cpu, pc;
 
-        if (!tracer_enabled)
+        if (!likely(tracer_enabled))
                 return;
 
-        tracing_record_cmdline(curr);
+        pc = preempt_count();
+        tracing_record_cmdline(current);
 
         local_irq_save(flags);
         cpu = raw_smp_processor_id();
-        data = tr->data[cpu];
-        disabled = atomic_inc_return(&data->disabled);
+        data = ctx_trace->data[cpu];
 
-        if (likely(disabled == 1))
-                tracing_sched_wakeup_trace(tr, data, wakee, curr, flags);
+        if (likely(!atomic_read(&data->disabled)))
+                tracing_sched_wakeup_trace(ctx_trace, data, wakee, current,
+                                           flags, pc);
 
-        atomic_dec(&data->disabled);
         local_irq_restore(flags);
 }
 
-static notrace void
-wake_up_callback(void *probe_data, void *call_data,
-                 const char *format, va_list *args)
-{
-        struct task_struct *curr;
-        struct task_struct *task;
-        struct rq *__rq;
-
-        if (likely(!tracer_enabled))
-                return;
-
-        /* Skip pid %d state %ld */
-        (void)va_arg(*args, int);
-        (void)va_arg(*args, long);
-        /* now get the meat: "rq %p task %p rq->curr %p" */
-        __rq = va_arg(*args, typeof(__rq));
-        task = va_arg(*args, typeof(task));
-        curr = va_arg(*args, typeof(curr));
-
-        tracing_record_cmdline(task);
-        tracing_record_cmdline(curr);
-
-        wakeup_func(probe_data, __rq, task, curr);
-}
-
 static void sched_switch_reset(struct trace_array *tr)
 {
         int cpu;
@@ -133,67 +78,47 @@ static void sched_switch_reset(struct trace_array *tr)
         tr->time_start = ftrace_now(tr->cpu);
 
         for_each_online_cpu(cpu)
-                tracing_reset(tr->data[cpu]);
+                tracing_reset(tr, cpu);
 }
 
 static int tracing_sched_register(void)
 {
         int ret;
 
-        ret = marker_probe_register("kernel_sched_wakeup",
-                        "pid %d state %ld ## rq %p task %p rq->curr %p",
-                        wake_up_callback,
-                        &ctx_trace);
+        ret = register_trace_sched_wakeup(probe_sched_wakeup);
         if (ret) {
-                pr_info("wakeup trace: Couldn't add marker"
+                pr_info("wakeup trace: Couldn't activate tracepoint"
                         " probe to kernel_sched_wakeup\n");
                 return ret;
         }
 
-        ret = marker_probe_register("kernel_sched_wakeup_new",
-                        "pid %d state %ld ## rq %p task %p rq->curr %p",
-                        wake_up_callback,
-                        &ctx_trace);
+        ret = register_trace_sched_wakeup_new(probe_sched_wakeup);
         if (ret) {
-                pr_info("wakeup trace: Couldn't add marker"
+                pr_info("wakeup trace: Couldn't activate tracepoint"
                         " probe to kernel_sched_wakeup_new\n");
                 goto fail_deprobe;
         }
 
-        ret = marker_probe_register("kernel_sched_schedule",
-                "prev_pid %d next_pid %d prev_state %ld "
-                "## rq %p prev %p next %p",
-                sched_switch_callback,
-                &ctx_trace);
+        ret = register_trace_sched_switch(probe_sched_switch);
         if (ret) {
-                pr_info("sched trace: Couldn't add marker"
+                pr_info("sched trace: Couldn't activate tracepoint"
                         " probe to kernel_sched_schedule\n");
                 goto fail_deprobe_wake_new;
         }
 
         return ret;
 fail_deprobe_wake_new:
-        marker_probe_unregister("kernel_sched_wakeup_new",
-                                wake_up_callback,
-                                &ctx_trace);
+        unregister_trace_sched_wakeup_new(probe_sched_wakeup);
 fail_deprobe:
-        marker_probe_unregister("kernel_sched_wakeup",
-                                wake_up_callback,
-                                &ctx_trace);
+        unregister_trace_sched_wakeup(probe_sched_wakeup);
         return ret;
 }
 
 static void tracing_sched_unregister(void)
 {
-        marker_probe_unregister("kernel_sched_schedule",
-                                sched_switch_callback,
-                                &ctx_trace);
-        marker_probe_unregister("kernel_sched_wakeup_new",
-                                wake_up_callback,
-                                &ctx_trace);
-        marker_probe_unregister("kernel_sched_wakeup",
-                                wake_up_callback,
-                                &ctx_trace);
+        unregister_trace_sched_switch(probe_sched_switch);
+        unregister_trace_sched_wakeup_new(probe_sched_wakeup);
+        unregister_trace_sched_wakeup(probe_sched_wakeup);
 }
 
 static void tracing_start_sched_switch(void)
diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c
index e303ccb62cdf..3ae93f16b565 100644
--- a/kernel/trace/trace_sched_wakeup.c
+++ b/kernel/trace/trace_sched_wakeup.c
@@ -15,7 +15,7 @@
 #include <linux/kallsyms.h>
 #include <linux/uaccess.h>
 #include <linux/ftrace.h>
-#include <linux/marker.h>
+#include <trace/sched.h>
 
 #include "trace.h"
 
@@ -31,7 +31,7 @@ static raw_spinlock_t wakeup_lock =
 
 static void __wakeup_reset(struct trace_array *tr);
 
-#ifdef CONFIG_FTRACE
+#ifdef CONFIG_FUNCTION_TRACER
 /*
  * irqsoff uses its own tracer function to keep the overhead down:
  */
@@ -44,10 +44,12 @@ wakeup_tracer_call(unsigned long ip, unsigned long parent_ip)
         long disabled;
         int resched;
         int cpu;
+        int pc;
 
         if (likely(!wakeup_task))
                 return;
 
+        pc = preempt_count();
         resched = need_resched();
         preempt_disable_notrace();
 
@@ -70,7 +72,7 @@ wakeup_tracer_call(unsigned long ip, unsigned long parent_ip)
         if (task_cpu(wakeup_task) != cpu)
                 goto unlock;
 
-        trace_function(tr, data, ip, parent_ip, flags);
+        trace_function(tr, data, ip, parent_ip, flags, pc);
 
  unlock:
         __raw_spin_unlock(&wakeup_lock);
@@ -94,7 +96,7 @@ static struct ftrace_ops trace_ops __read_mostly =
 {
         .func = wakeup_tracer_call,
 };
-#endif /* CONFIG_FTRACE */
+#endif /* CONFIG_FUNCTION_TRACER */
 
 /*
  * Should this new latency be reported/recorded?
@@ -112,17 +114,18 @@ static int report_latency(cycle_t delta)
 }
 
 static void notrace
-wakeup_sched_switch(void *private, void *rq, struct task_struct *prev,
+probe_wakeup_sched_switch(struct rq *rq, struct task_struct *prev,
         struct task_struct *next)
 {
         unsigned long latency = 0, t0 = 0, t1 = 0;
-        struct trace_array **ptr = private;
-        struct trace_array *tr = *ptr;
         struct trace_array_cpu *data;
         cycle_t T0, T1, delta;
         unsigned long flags;
         long disabled;
         int cpu;
+        int pc;
+
+        tracing_record_cmdline(prev);
 
         if (unlikely(!tracer_enabled))
                 return;
@@ -139,12 +142,14 @@ wakeup_sched_switch(void *private, void *rq, struct task_struct *prev,
         if (next != wakeup_task)
                 return;
 
+        pc = preempt_count();
+
         /* The task we are waiting for is waking up */
-        data = tr->data[wakeup_cpu];
+        data = wakeup_trace->data[wakeup_cpu];
 
         /* disable local data, not wakeup_cpu data */
         cpu = raw_smp_processor_id();
-        disabled = atomic_inc_return(&tr->data[cpu]->disabled);
+        disabled = atomic_inc_return(&wakeup_trace->data[cpu]->disabled);
         if (likely(disabled != 1))
                 goto out;
 
@@ -155,7 +160,7 @@ wakeup_sched_switch(void *private, void *rq, struct task_struct *prev,
         if (unlikely(!tracer_enabled || next != wakeup_task))
                 goto out_unlock;
 
-        trace_function(tr, data, CALLER_ADDR1, CALLER_ADDR2, flags);
+        trace_function(wakeup_trace, data, CALLER_ADDR1, CALLER_ADDR2, flags, pc);
 
         /*
          * usecs conversion is slow so we try to delay the conversion
@@ -174,39 +179,14 @@ wakeup_sched_switch(void *private, void *rq, struct task_struct *prev,
         t0 = nsecs_to_usecs(T0);
         t1 = nsecs_to_usecs(T1);
 
-        update_max_tr(tr, wakeup_task, wakeup_cpu);
+        update_max_tr(wakeup_trace, wakeup_task, wakeup_cpu);
 
 out_unlock:
-        __wakeup_reset(tr);
+        __wakeup_reset(wakeup_trace);
         __raw_spin_unlock(&wakeup_lock);
         local_irq_restore(flags);
 out:
-        atomic_dec(&tr->data[cpu]->disabled);
-}
-
-static notrace void
-sched_switch_callback(void *probe_data, void *call_data,
-                      const char *format, va_list *args)
-{
-        struct task_struct *prev;
-        struct task_struct *next;
-        struct rq *__rq;
-
-        /* skip prev_pid %d next_pid %d prev_state %ld */
-        (void)va_arg(*args, int);
-        (void)va_arg(*args, int);
-        (void)va_arg(*args, long);
-        __rq = va_arg(*args, typeof(__rq));
-        prev = va_arg(*args, typeof(prev));
-        next = va_arg(*args, typeof(next));
-
-        tracing_record_cmdline(prev);
-
-        /*
-         * If tracer_switch_func only points to the local
-         * switch func, it still needs the ptr passed to it.
-         */
-        wakeup_sched_switch(probe_data, __rq, prev, next);
+        atomic_dec(&wakeup_trace->data[cpu]->disabled);
 }
 
 static void __wakeup_reset(struct trace_array *tr)
@@ -216,7 +196,7 @@ static void __wakeup_reset(struct trace_array *tr)
 
         for_each_possible_cpu(cpu) {
                 data = tr->data[cpu];
-                tracing_reset(data);
+                tracing_reset(tr, cpu);
         }
 
         wakeup_cpu = -1;
@@ -240,19 +220,26 @@ static void wakeup_reset(struct trace_array *tr)
 }
 
 static void
-wakeup_check_start(struct trace_array *tr, struct task_struct *p,
-                   struct task_struct *curr)
+probe_wakeup(struct rq *rq, struct task_struct *p)
 {
         int cpu = smp_processor_id();
         unsigned long flags;
         long disabled;
+        int pc;
+
+        if (likely(!tracer_enabled))
+                return;
+
+        tracing_record_cmdline(p);
+        tracing_record_cmdline(current);
 
         if (likely(!rt_task(p)) ||
                         p->prio >= wakeup_prio ||
-                        p->prio >= curr->prio)
+                        p->prio >= current->prio)
                 return;
 
-        disabled = atomic_inc_return(&tr->data[cpu]->disabled);
+        pc = preempt_count();
+        disabled = atomic_inc_return(&wakeup_trace->data[cpu]->disabled);
         if (unlikely(disabled != 1))
                 goto out;
 
@@ -264,7 +251,7 @@ wakeup_check_start(struct trace_array *tr, struct task_struct *p,
                 goto out_locked;
 
         /* reset the trace */
-        __wakeup_reset(tr);
+        __wakeup_reset(wakeup_trace);
 
         wakeup_cpu = task_cpu(p);
         wakeup_prio = p->prio;
@@ -274,74 +261,37 @@ wakeup_check_start(struct trace_array *tr, struct task_struct *p,
 
         local_save_flags(flags);
 
-        tr->data[wakeup_cpu]->preempt_timestamp = ftrace_now(cpu);
-        trace_function(tr, tr->data[wakeup_cpu],
-                       CALLER_ADDR1, CALLER_ADDR2, flags);
+        wakeup_trace->data[wakeup_cpu]->preempt_timestamp = ftrace_now(cpu);
+        trace_function(wakeup_trace, wakeup_trace->data[wakeup_cpu],
+                       CALLER_ADDR1, CALLER_ADDR2, flags, pc);
 
 out_locked:
         __raw_spin_unlock(&wakeup_lock);
 out:
-        atomic_dec(&tr->data[cpu]->disabled);
-}
-
-static notrace void
-wake_up_callback(void *probe_data, void *call_data,
-                 const char *format, va_list *args)
-{
-        struct trace_array **ptr = probe_data;
-        struct trace_array *tr = *ptr;
-        struct task_struct *curr;
-        struct task_struct *task;
-        struct rq *__rq;
-
-        if (likely(!tracer_enabled))
-                return;
-
-        /* Skip pid %d state %ld */
-        (void)va_arg(*args, int);
-        (void)va_arg(*args, long);
-        /* now get the meat: "rq %p task %p rq->curr %p" */
-        __rq = va_arg(*args, typeof(__rq));
-        task = va_arg(*args, typeof(task));
-        curr = va_arg(*args, typeof(curr));
-
-        tracing_record_cmdline(task);
-        tracing_record_cmdline(curr);
-
-        wakeup_check_start(tr, task, curr);
+        atomic_dec(&wakeup_trace->data[cpu]->disabled);
 }
 
 static void start_wakeup_tracer(struct trace_array *tr)
 {
         int ret;
 
-        ret = marker_probe_register("kernel_sched_wakeup",
-                        "pid %d state %ld ## rq %p task %p rq->curr %p",
-                        wake_up_callback,
-                        &wakeup_trace);
+        ret = register_trace_sched_wakeup(probe_wakeup);
         if (ret) {
-                pr_info("wakeup trace: Couldn't add marker"
+                pr_info("wakeup trace: Couldn't activate tracepoint"
                         " probe to kernel_sched_wakeup\n");
                 return;
         }
 
-        ret = marker_probe_register("kernel_sched_wakeup_new",
-                        "pid %d state %ld ## rq %p task %p rq->curr %p",
-                        wake_up_callback,
-                        &wakeup_trace);
+        ret = register_trace_sched_wakeup_new(probe_wakeup);
         if (ret) {
-                pr_info("wakeup trace: Couldn't add marker"
+                pr_info("wakeup trace: Couldn't activate tracepoint"
                         " probe to kernel_sched_wakeup_new\n");
                 goto fail_deprobe;
         }
 
-        ret = marker_probe_register("kernel_sched_schedule",
-                "prev_pid %d next_pid %d prev_state %ld "
-                "## rq %p prev %p next %p",
-                sched_switch_callback,
-                &wakeup_trace);
+        ret = register_trace_sched_switch(probe_wakeup_sched_switch);
         if (ret) {
-                pr_info("sched trace: Couldn't add marker"
+                pr_info("sched trace: Couldn't activate tracepoint"
                         " probe to kernel_sched_schedule\n");
                 goto fail_deprobe_wake_new;
         }
@@ -363,28 +313,18 @@ static void start_wakeup_tracer(struct trace_array *tr)
 
         return;
 fail_deprobe_wake_new:
-        marker_probe_unregister("kernel_sched_wakeup_new",
-                                wake_up_callback,
-                                &wakeup_trace);
+        unregister_trace_sched_wakeup_new(probe_wakeup);
 fail_deprobe:
-        marker_probe_unregister("kernel_sched_wakeup",
-                                wake_up_callback,
-                                &wakeup_trace);
+        unregister_trace_sched_wakeup(probe_wakeup);
 }
 
 static void stop_wakeup_tracer(struct trace_array *tr)
 {
         tracer_enabled = 0;
         unregister_ftrace_function(&trace_ops);
-        marker_probe_unregister("kernel_sched_schedule",
-                                sched_switch_callback,
-                                &wakeup_trace);
-        marker_probe_unregister("kernel_sched_wakeup_new",
-                                wake_up_callback,
-                                &wakeup_trace);
-        marker_probe_unregister("kernel_sched_wakeup",
-                                wake_up_callback,
-                                &wakeup_trace);
+        unregister_trace_sched_switch(probe_wakeup_sched_switch);
+        unregister_trace_sched_wakeup_new(probe_wakeup);
+        unregister_trace_sched_wakeup(probe_wakeup);
 }
 
 static void wakeup_tracer_init(struct trace_array *tr)
diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c
index 0911b7e073bf..90bc752a7580 100644
--- a/kernel/trace/trace_selftest.c
+++ b/kernel/trace/trace_selftest.c
@@ -9,65 +9,29 @@ static inline int trace_valid_entry(struct trace_entry *entry)
         case TRACE_FN:
         case TRACE_CTX:
         case TRACE_WAKE:
+        case TRACE_CONT:
         case TRACE_STACK:
+        case TRACE_PRINT:
         case TRACE_SPECIAL:
                 return 1;
         }
         return 0;
 }
 
-static int
-trace_test_buffer_cpu(struct trace_array *tr, struct trace_array_cpu *data)
+static int trace_test_buffer_cpu(struct trace_array *tr, int cpu)
 {
-        struct trace_entry *entries;
-        struct page *page;
-        int idx = 0;
-        int i;
+        struct ring_buffer_event *event;
+        struct trace_entry *entry;
 
-        BUG_ON(list_empty(&data->trace_pages));
-        page = list_entry(data->trace_pages.next, struct page, lru);
-        entries = page_address(page);
+        while ((event = ring_buffer_consume(tr->buffer, cpu, NULL))) {
+                entry = ring_buffer_event_data(event);
 
-        check_pages(data);
-        if (head_page(data) != entries)
-                goto failed;
-
-        /*
-         * The starting trace buffer always has valid elements,
-         * if any element exists.
-         */
-        entries = head_page(data);
-
-        for (i = 0; i < tr->entries; i++) {
-
-                if (i < data->trace_idx && !trace_valid_entry(&entries[idx])) {
+                if (!trace_valid_entry(entry)) {
                         printk(KERN_CONT ".. invalid entry %d ",
-                                entries[idx].type);
+                                entry->type);
                         goto failed;
                 }
-
-                idx++;
-                if (idx >= ENTRIES_PER_PAGE) {
-                        page = virt_to_page(entries);
-                        if (page->lru.next == &data->trace_pages) {
-                                if (i != tr->entries - 1) {
-                                        printk(KERN_CONT ".. entries buffer mismatch");
-                                        goto failed;
-                                }
-                        } else {
-                                page = list_entry(page->lru.next, struct page, lru);
-                                entries = page_address(page);
-                        }
-                        idx = 0;
-                }
-        }
-
-        page = virt_to_page(entries);
-        if (page->lru.next != &data->trace_pages) {
-                printk(KERN_CONT ".. too many entries");
-                goto failed;
         }
-
         return 0;
 
  failed:
@@ -89,13 +53,11 @@ static int trace_test_buffer(struct trace_array *tr, unsigned long *count)
         /* Don't allow flipping of max traces now */
         raw_local_irq_save(flags);
         __raw_spin_lock(&ftrace_max_lock);
-        for_each_possible_cpu(cpu) {
-                if (!head_page(tr->data[cpu]))
-                        continue;
 
-                cnt += tr->data[cpu]->trace_idx;
+        cnt = ring_buffer_entries(tr->buffer);
 
-                ret = trace_test_buffer_cpu(tr, tr->data[cpu]);
+        for_each_possible_cpu(cpu) {
+                ret = trace_test_buffer_cpu(tr, cpu);
                 if (ret)
                         break;
         }
@@ -108,7 +70,7 @@ static int trace_test_buffer(struct trace_array *tr, unsigned long *count)
         return ret;
 }
 
-#ifdef CONFIG_FTRACE
+#ifdef CONFIG_FUNCTION_TRACER
 
 #ifdef CONFIG_DYNAMIC_FTRACE
 
@@ -120,11 +82,11 @@ int trace_selftest_startup_dynamic_tracing(struct tracer *trace,
                                            struct trace_array *tr,
                                            int (*func)(void))
 {
-        unsigned long count;
-        int ret;
         int save_ftrace_enabled = ftrace_enabled;
         int save_tracer_enabled = tracer_enabled;
+        unsigned long count;
         char *func_name;
+        int ret;
 
         /* The ftrace test PASSED */
         printk(KERN_CONT "PASSED\n");
@@ -137,13 +99,6 @@ int trace_selftest_startup_dynamic_tracing(struct tracer *trace,
         /* passed in by parameter to fool gcc from optimizing */
         func();
 
-        /* update the records */
-        ret = ftrace_force_update();
-        if (ret) {
-                printk(KERN_CONT ".. ftraced failed .. ");
-                return ret;
-        }
-
         /*
          * Some archs *cough*PowerPC*cough* add charachters to the
          * start of the function names. We simply put a '*' to
@@ -157,6 +112,7 @@ int trace_selftest_startup_dynamic_tracing(struct tracer *trace,
         /* enable tracing */
         tr->ctrl = 1;
         trace->init(tr);
+
         /* Sleep for a 1/10 of a second */
         msleep(100);
 
@@ -212,21 +168,14 @@ int trace_selftest_startup_dynamic_tracing(struct tracer *trace,
 int
 trace_selftest_startup_function(struct tracer *trace, struct trace_array *tr)
 {
-        unsigned long count;
-        int ret;
         int save_ftrace_enabled = ftrace_enabled;
         int save_tracer_enabled = tracer_enabled;
+        unsigned long count;
+        int ret;
 
         /* make sure msleep has been recorded */
         msleep(1);
 
-        /* force the recorded functions to be traced */
-        ret = ftrace_force_update();
-        if (ret) {
-                printk(KERN_CONT ".. ftraced failed .. ");
-                return ret;
-        }
-
         /* start the tracing */
         ftrace_enabled = 1;
         tracer_enabled = 1;
@@ -263,7 +212,7 @@ trace_selftest_startup_function(struct tracer *trace, struct trace_array *tr)
 
         return ret;
 }
-#endif /* CONFIG_FTRACE */
+#endif /* CONFIG_FUNCTION_TRACER */
 
 #ifdef CONFIG_IRQSOFF_TRACER
 int
@@ -415,6 +364,15 @@ trace_selftest_startup_preemptirqsoff(struct tracer *trace, struct trace_array *
 }
 #endif /* CONFIG_IRQSOFF_TRACER && CONFIG_PREEMPT_TRACER */
 
+#ifdef CONFIG_NOP_TRACER
+int
+trace_selftest_startup_nop(struct tracer *trace, struct trace_array *tr)
+{
+        /* What could possibly go wrong? */
+        return 0;
+}
+#endif
+
 #ifdef CONFIG_SCHED_TRACER
 static int trace_wakeup_test_thread(void *data)
 {
@@ -486,6 +444,9 @@ trace_selftest_startup_wakeup(struct tracer *trace, struct trace_array *tr)
 
         wake_up_process(p);
 
+        /* give a little time to let the thread wake up */
+        msleep(100);
+
         /* stop the tracing. */
         tr->ctrl = 0;
         trace->ctrl_update(tr);
diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
new file mode 100644
index 000000000000..be682b62fe58
--- /dev/null
+++ b/kernel/trace/trace_stack.c
@@ -0,0 +1,314 @@
+/*
+ * Copyright (C) 2008 Steven Rostedt <srostedt@redhat.com>
+ *
+ */
+#include <linux/stacktrace.h>
+#include <linux/kallsyms.h>
+#include <linux/seq_file.h>
+#include <linux/spinlock.h>
+#include <linux/uaccess.h>
+#include <linux/debugfs.h>
+#include <linux/ftrace.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/fs.h>
+#include "trace.h"
+
+#define STACK_TRACE_ENTRIES 500
+
+static unsigned long stack_dump_trace[STACK_TRACE_ENTRIES+1] =
+         { [0 ... (STACK_TRACE_ENTRIES)] = ULONG_MAX };
+static unsigned stack_dump_index[STACK_TRACE_ENTRIES];
+
+static struct stack_trace max_stack_trace = {
+        .max_entries            = STACK_TRACE_ENTRIES,
+        .entries                = stack_dump_trace,
+};
+
+static unsigned long max_stack_size;
+static raw_spinlock_t max_stack_lock =
+        (raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED;
+
+static int stack_trace_disabled __read_mostly;
+static DEFINE_PER_CPU(int, trace_active);
+
+static inline void check_stack(void)
+{
+        unsigned long this_size, flags;
+        unsigned long *p, *top, *start;
+        int i;
+
+        this_size = ((unsigned long)&this_size) & (THREAD_SIZE-1);
+        this_size = THREAD_SIZE - this_size;
+
+        if (this_size <= max_stack_size)
+                return;
+
+        /* we do not handle interrupt stacks yet */
+        if (!object_is_on_stack(&this_size))
+                return;
+
+        raw_local_irq_save(flags);
+        __raw_spin_lock(&max_stack_lock);
+
+        /* a race could have already updated it */
+        if (this_size <= max_stack_size)
+                goto out;
+
+        max_stack_size = this_size;
+
+        max_stack_trace.nr_entries      = 0;
+        max_stack_trace.skip            = 3;
+
+        save_stack_trace(&max_stack_trace);
+
+        /*
+         * Now find where in the stack these are.
+         */
+        i = 0;
+        start = &this_size;
+        top = (unsigned long *)
+                (((unsigned long)start & ~(THREAD_SIZE-1)) + THREAD_SIZE);
+
+        /*
+         * Loop through all the entries. One of the entries may
+         * for some reason be missed on the stack, so we may
+         * have to account for them. If they are all there, this
+         * loop will only happen once. This code only takes place
+         * on a new max, so it is far from a fast path.
+         */
+        while (i < max_stack_trace.nr_entries) {
+
+                stack_dump_index[i] = this_size;
+                p = start;
+
+                for (; p < top && i < max_stack_trace.nr_entries; p++) {
+                        if (*p == stack_dump_trace[i]) {
+                                this_size = stack_dump_index[i++] =
+                                        (top - p) * sizeof(unsigned long);
+                                /* Start the search from here */
+                                start = p + 1;
+                        }
+                }
+
+                i++;
+        }
+
+ out:
+        __raw_spin_unlock(&max_stack_lock);
+        raw_local_irq_restore(flags);
+}
+
+static void
+stack_trace_call(unsigned long ip, unsigned long parent_ip)
+{
+        int cpu, resched;
+
+        if (unlikely(!ftrace_enabled || stack_trace_disabled))
+                return;
+
+        resched = need_resched();
+        preempt_disable_notrace();
+
+        cpu = raw_smp_processor_id();
+        /* no atomic needed, we only modify this variable by this cpu */
+        if (per_cpu(trace_active, cpu)++ != 0)
+                goto out;
+
+        check_stack();
+
+ out:
+        per_cpu(trace_active, cpu)--;
+        /* prevent recursion in schedule */
+        if (resched)
+                preempt_enable_no_resched_notrace();
+        else
+                preempt_enable_notrace();
+}
+
+static struct ftrace_ops trace_ops __read_mostly =
+{
+        .func = stack_trace_call,
+};
+
+static ssize_t
+stack_max_size_read(struct file *filp, char __user *ubuf,
+                    size_t count, loff_t *ppos)
+{
+        unsigned long *ptr = filp->private_data;
+        char buf[64];
+        int r;
+
+        r = snprintf(buf, sizeof(buf), "%ld\n", *ptr);
+        if (r > sizeof(buf))
+                r = sizeof(buf);
+        return simple_read_from_buffer(ubuf, count, ppos, buf, r);
+}
+
+static ssize_t
+stack_max_size_write(struct file *filp, const char __user *ubuf,
+                     size_t count, loff_t *ppos)
+{
+        long *ptr = filp->private_data;
+        unsigned long val, flags;
+        char buf[64];
+        int ret;
+
+        if (count >= sizeof(buf))
+                return -EINVAL;
+
+        if (copy_from_user(&buf, ubuf, count))
+                return -EFAULT;
+
+        buf[count] = 0;
+
+        ret = strict_strtoul(buf, 10, &val);
+        if (ret < 0)
+                return ret;
+
+        raw_local_irq_save(flags);
+        __raw_spin_lock(&max_stack_lock);
+        *ptr = val;
+        __raw_spin_unlock(&max_stack_lock);
+        raw_local_irq_restore(flags);
+
+        return count;
+}
+
+static struct file_operations stack_max_size_fops = {
+        .open           = tracing_open_generic,
+        .read           = stack_max_size_read,
+        .write          = stack_max_size_write,
+};
+
+static void *
+t_next(struct seq_file *m, void *v, loff_t *pos)
+{
+        long i = (long)m->private;
+
+        (*pos)++;
+
+        i++;
+
+        if (i >= max_stack_trace.nr_entries ||
+            stack_dump_trace[i] == ULONG_MAX)
+                return NULL;
+
+        m->private = (void *)i;
+
+        return &m->private;
+}
+
+static void *t_start(struct seq_file *m, loff_t *pos)
+{
+        void *t = &m->private;
+        loff_t l = 0;
+
+        local_irq_disable();
+        __raw_spin_lock(&max_stack_lock);
+
+        for (; t && l < *pos; t = t_next(m, t, &l))
+                ;
+
+        return t;
+}
+
+static void t_stop(struct seq_file *m, void *p)
+{
+        __raw_spin_unlock(&max_stack_lock);
+        local_irq_enable();
+}
+
+static int trace_lookup_stack(struct seq_file *m, long i)
+{
+        unsigned long addr = stack_dump_trace[i];
+#ifdef CONFIG_KALLSYMS
+        char str[KSYM_SYMBOL_LEN];
+
+        sprint_symbol(str, addr);
+
+        return seq_printf(m, "%s\n", str);
+#else
+        return seq_printf(m, "%p\n", (void*)addr);
+#endif
+}
+
+static int t_show(struct seq_file *m, void *v)
+{
+        long i = *(long *)v;
+        int size;
+
+        if (i < 0) {
+                seq_printf(m, "        Depth   Size      Location"
+                           "    (%d entries)\n"
+                           "        -----   ----      --------\n",
+                           max_stack_trace.nr_entries);
+                return 0;
+        }
+
+        if (i >= max_stack_trace.nr_entries ||
+            stack_dump_trace[i] == ULONG_MAX)
+                return 0;
+
+        if (i+1 == max_stack_trace.nr_entries ||
+            stack_dump_trace[i+1] == ULONG_MAX)
+                size = stack_dump_index[i];
+        else
+                size = stack_dump_index[i] - stack_dump_index[i+1];
+
+        seq_printf(m, "%3ld) %8d   %5d   ", i, stack_dump_index[i], size);
+
+        trace_lookup_stack(m, i);
+
+        return 0;
+}
+
+static struct seq_operations stack_trace_seq_ops = {
+        .start          = t_start,
+        .next           = t_next,
+        .stop           = t_stop,
+        .show           = t_show,
+};
+
+static int stack_trace_open(struct inode *inode, struct file *file)
+{
+        int ret;
+
+        ret = seq_open(file, &stack_trace_seq_ops);
+        if (!ret) {
+                struct seq_file *m = file->private_data;
+                m->private = (void *)-1;
+        }
+
+        return ret;
+}
+
+static struct file_operations stack_trace_fops = {
+        .open           = stack_trace_open,
+        .read           = seq_read,
+        .llseek         = seq_lseek,
+};
+
+static __init int stack_trace_init(void)
+{
+        struct dentry *d_tracer;
+        struct dentry *entry;
+
+        d_tracer = tracing_init_dentry();
+
+        entry = debugfs_create_file("stack_max_size", 0644, d_tracer,
+                                    &max_stack_size, &stack_max_size_fops);
+        if (!entry)
+                pr_warning("Could not create debugfs 'stack_max_size' entry\n");
+
+        entry = debugfs_create_file("stack_trace", 0444, d_tracer,
+                                    NULL, &stack_trace_fops);
+        if (!entry)
+                pr_warning("Could not create debugfs 'stack_trace' entry\n");
+
+        register_ftrace_function(&trace_ops);
+
+        return 0;
+}
+
+device_initcall(stack_trace_init);
diff --git a/kernel/trace/trace_sysprof.c b/kernel/trace/trace_sysprof.c
index bb948e52ce20..9587d3bcba55 100644
--- a/kernel/trace/trace_sysprof.c
+++ b/kernel/trace/trace_sysprof.c
@@ -202,7 +202,7 @@ static void start_stack_timer(int cpu)
 
         hrtimer_init(hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
         hrtimer->function = stack_trace_timer_fn;
-        hrtimer->cb_mode = HRTIMER_CB_IRQSAFE_NO_SOFTIRQ;
+        hrtimer->cb_mode = HRTIMER_CB_IRQSAFE_PERCPU;
 
         hrtimer_start(hrtimer, ns_to_ktime(sample_period), HRTIMER_MODE_REL);
 }
@@ -241,7 +241,7 @@ static void stack_reset(struct trace_array *tr)
         tr->time_start = ftrace_now(tr->cpu);
 
         for_each_online_cpu(cpu)
-                tracing_reset(tr->data[cpu]);
+                tracing_reset(tr, cpu);
 }
 
 static void start_stack_trace(struct trace_array *tr)
diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c
new file mode 100644
index 000000000000..af8c85664882
--- /dev/null
+++ b/kernel/tracepoint.c
@@ -0,0 +1,485 @@
+/*
+ * Copyright (C) 2008 Mathieu Desnoyers
+ *
+ * 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, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ */
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/types.h>
+#include <linux/jhash.h>
+#include <linux/list.h>
+#include <linux/rcupdate.h>
+#include <linux/tracepoint.h>
+#include <linux/err.h>
+#include <linux/slab.h>
+
+extern struct tracepoint __start___tracepoints[];
+extern struct tracepoint __stop___tracepoints[];
+
+/* Set to 1 to enable tracepoint debug output */
+static const int tracepoint_debug;
+
+/*
+ * tracepoints_mutex nests inside module_mutex. Tracepoints mutex protects the
+ * builtin and module tracepoints and the hash table.
+ */
+static DEFINE_MUTEX(tracepoints_mutex);
+
+/*
+ * Tracepoint hash table, containing the active tracepoints.
+ * Protected by tracepoints_mutex.
+ */
+#define TRACEPOINT_HASH_BITS 6
+#define TRACEPOINT_TABLE_SIZE (1 << TRACEPOINT_HASH_BITS)
+
+/*
+ * Note about RCU :
+ * It is used to to delay the free of multiple probes array until a quiescent
+ * state is reached.
+ * Tracepoint entries modifications are protected by the tracepoints_mutex.
+ */
+struct tracepoint_entry {
+        struct hlist_node hlist;
+        void **funcs;
+        int refcount;   /* Number of times armed. 0 if disarmed. */
+        struct rcu_head rcu;
+        void *oldptr;
+        unsigned char rcu_pending:1;
+        char name[0];
+};
+
+static struct hlist_head tracepoint_table[TRACEPOINT_TABLE_SIZE];
+
+static void free_old_closure(struct rcu_head *head)
+{
+        struct tracepoint_entry *entry = container_of(head,
+                struct tracepoint_entry, rcu);
+        kfree(entry->oldptr);
+        /* Make sure we free the data before setting the pending flag to 0 */
+        smp_wmb();
+        entry->rcu_pending = 0;
+}
+
+static void tracepoint_entry_free_old(struct tracepoint_entry *entry, void *old)
+{
+        if (!old)
+                return;
+        entry->oldptr = old;
+        entry->rcu_pending = 1;
+        /* write rcu_pending before calling the RCU callback */
+        smp_wmb();
+        call_rcu_sched(&entry->rcu, free_old_closure);
+}
+
+static void debug_print_probes(struct tracepoint_entry *entry)
+{
+        int i;
+
+        if (!tracepoint_debug)
+                return;
+
+        for (i = 0; entry->funcs[i]; i++)
+                printk(KERN_DEBUG "Probe %d : %p\n", i, entry->funcs[i]);
+}
+
+static void *
+tracepoint_entry_add_probe(struct tracepoint_entry *entry, void *probe)
+{
+        int nr_probes = 0;
+        void **old, **new;
+
+        WARN_ON(!probe);
+
+        debug_print_probes(entry);
+        old = entry->funcs;
+        if (old) {
+                /* (N -> N+1), (N != 0, 1) probes */
+                for (nr_probes = 0; old[nr_probes]; nr_probes++)
+                        if (old[nr_probes] == probe)
+                                return ERR_PTR(-EEXIST);
+        }
+        /* + 2 : one for new probe, one for NULL func */
+        new = kzalloc((nr_probes + 2) * sizeof(void *), GFP_KERNEL);
+        if (new == NULL)
+                return ERR_PTR(-ENOMEM);
+        if (old)
+                memcpy(new, old, nr_probes * sizeof(void *));
+        new[nr_probes] = probe;
+        entry->refcount = nr_probes + 1;
+        entry->funcs = new;
+        debug_print_probes(entry);
+        return old;
+}
+
+static void *
+tracepoint_entry_remove_probe(struct tracepoint_entry *entry, void *probe)
+{
+        int nr_probes = 0, nr_del = 0, i;
+        void **old, **new;
+
+        old = entry->funcs;
+
+        if (!old)
+                return NULL;
+
+        debug_print_probes(entry);
+        /* (N -> M), (N > 1, M >= 0) probes */
+        for (nr_probes = 0; old[nr_probes]; nr_probes++) {
+                if ((!probe || old[nr_probes] == probe))
+                        nr_del++;
+        }
+
+        if (nr_probes - nr_del == 0) {
+                /* N -> 0, (N > 1) */
+                entry->funcs = NULL;
+                entry->refcount = 0;
+                debug_print_probes(entry);
+                return old;
+        } else {
+                int j = 0;
+                /* N -> M, (N > 1, M > 0) */
+                /* + 1 for NULL */
+                new = kzalloc((nr_probes - nr_del + 1)
+                        * sizeof(void *), GFP_KERNEL);
+                if (new == NULL)
+                        return ERR_PTR(-ENOMEM);
+                for (i = 0; old[i]; i++)
+                        if ((probe && old[i] != probe))
+                                new[j++] = old[i];
+                entry->refcount = nr_probes - nr_del;
+                entry->funcs = new;
+        }
+        debug_print_probes(entry);
+        return old;
+}
+
+/*
+ * Get tracepoint if the tracepoint is present in the tracepoint hash table.
+ * Must be called with tracepoints_mutex held.
+ * Returns NULL if not present.
+ */
+static struct tracepoint_entry *get_tracepoint(const char *name)
+{
+        struct hlist_head *head;
+        struct hlist_node *node;
+        struct tracepoint_entry *e;
+        u32 hash = jhash(name, strlen(name), 0);
+
+        head = &tracepoint_table[hash & (TRACEPOINT_TABLE_SIZE - 1)];
+        hlist_for_each_entry(e, node, head, hlist) {
+                if (!strcmp(name, e->name))
+                        return e;
+        }
+        return NULL;
+}
+
+/*
+ * Add the tracepoint to the tracepoint hash table. Must be called with
+ * tracepoints_mutex held.
+ */
+static struct tracepoint_entry *add_tracepoint(const char *name)
+{
+        struct hlist_head *head;
+        struct hlist_node *node;
+        struct tracepoint_entry *e;
+        size_t name_len = strlen(name) + 1;
+        u32 hash = jhash(name, name_len-1, 0);
+
+        head = &tracepoint_table[hash & (TRACEPOINT_TABLE_SIZE - 1)];
+        hlist_for_each_entry(e, node, head, hlist) {
+                if (!strcmp(name, e->name)) {
+                        printk(KERN_NOTICE
+                                "tracepoint %s busy\n", name);
+                        return ERR_PTR(-EEXIST);        /* Already there */
+                }
+        }
+        /*
+         * Using kmalloc here to allocate a variable length element. Could
+         * cause some memory fragmentation if overused.
+         */
+        e = kmalloc(sizeof(struct tracepoint_entry) + name_len, GFP_KERNEL);
+        if (!e)
+                return ERR_PTR(-ENOMEM);
+        memcpy(&e->name[0], name, name_len);
+        e->funcs = NULL;
+        e->refcount = 0;
+        e->rcu_pending = 0;
+        hlist_add_head(&e->hlist, head);
+        return e;
+}
+
+/*
+ * Remove the tracepoint from the tracepoint hash table. Must be called with
+ * mutex_lock held.
+ */
+static int remove_tracepoint(const char *name)
+{
+        struct hlist_head *head;
+        struct hlist_node *node;
+        struct tracepoint_entry *e;
+        int found = 0;
+        size_t len = strlen(name) + 1;
+        u32 hash = jhash(name, len-1, 0);
+
+        head = &tracepoint_table[hash & (TRACEPOINT_TABLE_SIZE - 1)];
+        hlist_for_each_entry(e, node, head, hlist) {
+                if (!strcmp(name, e->name)) {
+                        found = 1;
+                        break;
+                }
+        }
+        if (!found)
+                return -ENOENT;
+        if (e->refcount)
+                return -EBUSY;
+        hlist_del(&e->hlist);
+        /* Make sure the call_rcu_sched has been executed */
+        if (e->rcu_pending)
+                rcu_barrier_sched();
+        kfree(e);
+        return 0;
+}
+
+/*
+ * Sets the probe callback corresponding to one tracepoint.
+ */
+static void set_tracepoint(struct tracepoint_entry **entry,
+        struct tracepoint *elem, int active)
+{
+        WARN_ON(strcmp((*entry)->name, elem->name) != 0);
+
+        /*
+         * rcu_assign_pointer has a smp_wmb() which makes sure that the new
+         * probe callbacks array is consistent before setting a pointer to it.
+         * This array is referenced by __DO_TRACE from
+         * include/linux/tracepoints.h. A matching smp_read_barrier_depends()
+         * is used.
+         */
+        rcu_assign_pointer(elem->funcs, (*entry)->funcs);
+        elem->state = active;
+}
+
+/*
+ * Disable a tracepoint and its probe callback.
+ * Note: only waiting an RCU period after setting elem->call to the empty
+ * function insures that the original callback is not used anymore. This insured
+ * by preempt_disable around the call site.
+ */
+static void disable_tracepoint(struct tracepoint *elem)
+{
+        elem->state = 0;
+}
+
+/**
+ * tracepoint_update_probe_range - Update a probe range
+ * @begin: beginning of the range
+ * @end: end of the range
+ *
+ * Updates the probe callback corresponding to a range of tracepoints.
+ */
+void tracepoint_update_probe_range(struct tracepoint *begin,
+        struct tracepoint *end)
+{
+        struct tracepoint *iter;
+        struct tracepoint_entry *mark_entry;
+
+        mutex_lock(&tracepoints_mutex);
+        for (iter = begin; iter < end; iter++) {
+                mark_entry = get_tracepoint(iter->name);
+                if (mark_entry) {
+                        set_tracepoint(&mark_entry, iter,
+                                        !!mark_entry->refcount);
+                } else {
+                        disable_tracepoint(iter);
+                }
+        }
+        mutex_unlock(&tracepoints_mutex);
+}
+
+/*
+ * Update probes, removing the faulty probes.
+ */
+static void tracepoint_update_probes(void)
+{
+        /* Core kernel tracepoints */
+        tracepoint_update_probe_range(__start___tracepoints,
+                __stop___tracepoints);
+        /* tracepoints in modules. */
+        module_update_tracepoints();
+}
+
+/**
+ * tracepoint_probe_register -  Connect a probe to a tracepoint
+ * @name: tracepoint name
+ * @probe: probe handler
+ *
+ * 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)
+{
+        struct tracepoint_entry *entry;
+        int ret = 0;
+        void *old;
+
+        mutex_lock(&tracepoints_mutex);
+        entry = get_tracepoint(name);
+        if (!entry) {
+                entry = add_tracepoint(name);
+                if (IS_ERR(entry)) {
+                        ret = PTR_ERR(entry);
+                        goto end;
+                }
+        }
+        /*
+         * If we detect that a call_rcu_sched is pending for this tracepoint,
+         * make sure it's executed now.
+         */
+        if (entry->rcu_pending)
+                rcu_barrier_sched();
+        old = tracepoint_entry_add_probe(entry, probe);
+        if (IS_ERR(old)) {
+                ret = PTR_ERR(old);
+                goto end;
+        }
+        mutex_unlock(&tracepoints_mutex);
+        tracepoint_update_probes();             /* may update entry */
+        mutex_lock(&tracepoints_mutex);
+        entry = get_tracepoint(name);
+        WARN_ON(!entry);
+        if (entry->rcu_pending)
+                rcu_barrier_sched();
+        tracepoint_entry_free_old(entry, old);
+end:
+        mutex_unlock(&tracepoints_mutex);
+        return ret;
+}
+EXPORT_SYMBOL_GPL(tracepoint_probe_register);
+
+/**
+ * tracepoint_probe_unregister -  Disconnect a probe from a tracepoint
+ * @name: tracepoint name
+ * @probe: probe function pointer
+ *
+ * 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
+ * itself uses stop_machine(), which insures that every preempt disabled section
+ * have finished.
+ */
+int tracepoint_probe_unregister(const char *name, void *probe)
+{
+        struct tracepoint_entry *entry;
+        void *old;
+        int ret = -ENOENT;
+
+        mutex_lock(&tracepoints_mutex);
+        entry = get_tracepoint(name);
+        if (!entry)
+                goto end;
+        if (entry->rcu_pending)
+                rcu_barrier_sched();
+        old = tracepoint_entry_remove_probe(entry, probe);
+        if (!old) {
+                printk(KERN_WARNING "Warning: Trying to unregister a probe"
+                                    "that doesn't exist\n");
+                goto end;
+        }
+        mutex_unlock(&tracepoints_mutex);
+        tracepoint_update_probes();             /* may update entry */
+        mutex_lock(&tracepoints_mutex);
+        entry = get_tracepoint(name);
+        if (!entry)
+                goto end;
+        if (entry->rcu_pending)
+                rcu_barrier_sched();
+        tracepoint_entry_free_old(entry, old);
+        remove_tracepoint(name);        /* Ignore busy error message */
+        ret = 0;
+end:
+        mutex_unlock(&tracepoints_mutex);
+        return ret;
+}
+EXPORT_SYMBOL_GPL(tracepoint_probe_unregister);
+
+/**
+ * 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.
+ */
+int tracepoint_get_iter_range(struct tracepoint **tracepoint,
+        struct tracepoint *begin, struct tracepoint *end)
+{
+        if (!*tracepoint && begin != end) {
+                *tracepoint = begin;
+                return 1;
+        }
+        if (*tracepoint >= begin && *tracepoint < end)
+                return 1;
+        return 0;
+}
+EXPORT_SYMBOL_GPL(tracepoint_get_iter_range);
+
+static void tracepoint_get_iter(struct tracepoint_iter *iter)
+{
+        int found = 0;
+
+        /* Core kernel tracepoints */
+        if (!iter->module) {
+                found = tracepoint_get_iter_range(&iter->tracepoint,
+                                __start___tracepoints, __stop___tracepoints);
+                if (found)
+                        goto end;
+        }
+        /* tracepoints in modules. */
+        found = module_get_iter_tracepoints(iter);
+end:
+        if (!found)
+                tracepoint_iter_reset(iter);
+}
+
+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)
+{
+        iter->module = NULL;
+        iter->tracepoint = NULL;
+}
+EXPORT_SYMBOL_GPL(tracepoint_iter_reset);
diff --git a/kernel/user.c b/kernel/user.c
index 865ecf57a096..39d6159fae43 100644
--- a/kernel/user.c
+++ b/kernel/user.c
@@ -169,7 +169,7 @@ static ssize_t cpu_rt_runtime_show(struct kobject *kobj,
 {
         struct user_struct *up = container_of(kobj, struct user_struct, kobj);
 
-        return sprintf(buf, "%lu\n", sched_group_rt_runtime(up->tg));
+        return sprintf(buf, "%ld\n", sched_group_rt_runtime(up->tg));
 }
 
 static ssize_t cpu_rt_runtime_store(struct kobject *kobj,
@@ -180,7 +180,7 @@ static ssize_t cpu_rt_runtime_store(struct kobject *kobj,
         unsigned long rt_runtime;
         int rc;
 
-        sscanf(buf, "%lu", &rt_runtime);
+        sscanf(buf, "%ld", &rt_runtime);
 
         rc = sched_group_set_rt_runtime(up->tg, rt_runtime);
 
diff --git a/kernel/utsname_sysctl.c b/kernel/utsname_sysctl.c
index 4ab9659d269e..3b34b3545936 100644
--- a/kernel/utsname_sysctl.c
+++ b/kernel/utsname_sysctl.c
@@ -60,7 +60,7 @@ static int proc_do_uts_string(ctl_table *table, int write, struct file *filp,
 
 #ifdef CONFIG_SYSCTL_SYSCALL
 /* The generic string strategy routine: */
-static int sysctl_uts_string(ctl_table *table, int __user *name, int nlen,
+static int sysctl_uts_string(ctl_table *table,
                   void __user *oldval, size_t __user *oldlenp,
                   void __user *newval, size_t newlen)
 {
@@ -69,8 +69,7 @@ static int sysctl_uts_string(ctl_table *table, int __user *name, int nlen,
         write = newval && newlen;
         memcpy(&uts_table, table, sizeof(uts_table));
         uts_table.data = get_uts(table, write);
-        r = sysctl_string(&uts_table, name, nlen,
-                oldval, oldlenp, newval, newlen);
+        r = sysctl_string(&uts_table, oldval, oldlenp, newval, newlen);
         put_uts(table, write, uts_table.data);
         return r;
 }
diff --git a/kernel/wait.c b/kernel/wait.c
index c275c56cf2d3..cd87131f2fc2 100644
--- a/kernel/wait.c
+++ b/kernel/wait.c
@@ -72,12 +72,7 @@ prepare_to_wait(wait_queue_head_t *q, wait_queue_t *wait, int state)
         spin_lock_irqsave(&q->lock, flags);
         if (list_empty(&wait->task_list))
                 __add_wait_queue(q, wait);
-        /*
-         * don't alter the task state if this is just going to
-         * queue an async wait queue callback
-         */
-        if (is_sync_wait(wait))
-                set_current_state(state);
+        set_current_state(state);
         spin_unlock_irqrestore(&q->lock, flags);
 }
 EXPORT_SYMBOL(prepare_to_wait);
@@ -91,12 +86,7 @@ prepare_to_wait_exclusive(wait_queue_head_t *q, wait_queue_t *wait, int state)
         spin_lock_irqsave(&q->lock, flags);
         if (list_empty(&wait->task_list))
                 __add_wait_queue_tail(q, wait);
-        /*
-         * don't alter the task state if this is just going to
-         * queue an async wait queue callback
-         */
-        if (is_sync_wait(wait))
-                set_current_state(state);
+        set_current_state(state);
         spin_unlock_irqrestore(&q->lock, flags);
 }
 EXPORT_SYMBOL(prepare_to_wait_exclusive);
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 4048e92aa04f..d4dc69ddebd7 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -9,7 +9,7 @@
  * Derived from the taskqueue/keventd code by:
  *
  *   David Woodhouse <dwmw2@infradead.org>
- *   Andrew Morton <andrewm@uow.edu.au>
+ *   Andrew Morton
  *   Kai Petzke <wpp@marie.physik.tu-berlin.de>
  *   Theodore Ts'o <tytso@mit.edu>
  *
@@ -62,6 +62,7 @@ struct workqueue_struct {
         const char *name;
         int singlethread;
         int freezeable;         /* Freeze threads during suspend */
+        int rt;
 #ifdef CONFIG_LOCKDEP
         struct lockdep_map lockdep_map;
 #endif
@@ -766,6 +767,7 @@ init_cpu_workqueue(struct workqueue_struct *wq, int cpu)
 
 static int create_workqueue_thread(struct cpu_workqueue_struct *cwq, int cpu)
 {
+        struct sched_param param = { .sched_priority = MAX_RT_PRIO-1 };
         struct workqueue_struct *wq = cwq->wq;
         const char *fmt = is_single_threaded(wq) ? "%s" : "%s/%d";
         struct task_struct *p;
@@ -781,7 +783,8 @@ static int create_workqueue_thread(struct cpu_workqueue_struct *cwq, int cpu)
          */
         if (IS_ERR(p))
                 return PTR_ERR(p);
-
+        if (cwq->wq->rt)
+                sched_setscheduler_nocheck(p, SCHED_FIFO, &param);
         cwq->thread = p;
 
         return 0;
@@ -801,6 +804,7 @@ static void start_workqueue_thread(struct cpu_workqueue_struct *cwq, int cpu)
 struct workqueue_struct *__create_workqueue_key(const char *name,
                                                 int singlethread,
                                                 int freezeable,
+                                                int rt,
                                                 struct lock_class_key *key,
                                                 const char *lock_name)
 {
@@ -822,6 +826,7 @@ struct workqueue_struct *__create_workqueue_key(const char *name,
         lockdep_init_map(&wq->lockdep_map, lock_name, key, 0);
         wq->singlethread = singlethread;
         wq->freezeable = freezeable;
+        wq->rt = rt;
         INIT_LIST_HEAD(&wq->list);
 
         if (singlethread) {
@@ -965,6 +970,51 @@ undo:
         return ret;
 }
 
+#ifdef CONFIG_SMP
+struct work_for_cpu {
+        struct work_struct work;
+        long (*fn)(void *);
+        void *arg;
+        long ret;
+};
+
+static void do_work_for_cpu(struct work_struct *w)
+{
+        struct work_for_cpu *wfc = container_of(w, struct work_for_cpu, work);
+
+        wfc->ret = wfc->fn(wfc->arg);
+}
+
+/**
+ * work_on_cpu - run a function in user context on a particular cpu
+ * @cpu: the cpu to run on
+ * @fn: the function to run
+ * @arg: the function arg
+ *
+ * This will return -EINVAL in the cpu is not online, or the return value
+ * of @fn otherwise.
+ */
+long work_on_cpu(unsigned int cpu, long (*fn)(void *), void *arg)
+{
+        struct work_for_cpu wfc;
+
+        INIT_WORK(&wfc.work, do_work_for_cpu);
+        wfc.fn = fn;
+        wfc.arg = arg;
+        get_online_cpus();
+        if (unlikely(!cpu_online(cpu)))
+                wfc.ret = -EINVAL;
+        else {
+                schedule_work_on(cpu, &wfc.work);
+                flush_work(&wfc.work);
+        }
+        put_online_cpus();
+
+        return wfc.ret;
+}
+EXPORT_SYMBOL_GPL(work_on_cpu);
+#endif /* CONFIG_SMP */
+
 void __init init_workqueues(void)
 {
         cpu_populated_map = cpu_online_map;