Merge commit 'v2.6.28-rc2' into x86/pci-ioapic-boot-irq-quirks

138 files changed, 12801 insertions, 6111 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/Kconfig.hz b/kernel/Kconfig.hz
index 526128a2e622..94fabd534b03 100644
--- a/kernel/Kconfig.hz
+++ b/kernel/Kconfig.hz
@@ -55,4 +55,4 @@ config HZ
         default 1000 if HZ_1000
 
 config SCHED_HRTICK
-        def_bool HIGH_RES_TIMERS && X86
+        def_bool HIGH_RES_TIMERS && (!SMP || USE_GENERIC_SMP_HELPERS)
diff --git a/kernel/Makefile b/kernel/Makefile
index 985ddb7da4d0..305f11dbef21 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -2,7 +2,7 @@
 # Makefile for the linux kernel.
 #
 
-obj-y     = sched.o fork.o exec_domain.o panic.o printk.o profile.o \
+obj-y     = sched.o fork.o exec_domain.o panic.o printk.o \
             cpu.o exit.o itimer.o time.o softirq.o resource.o \
             sysctl.o capability.o ptrace.o timer.o user.o \
             signal.o sys.o kmod.o workqueue.o pid.o \
@@ -11,6 +11,8 @@ obj-y     = sched.o fork.o exec_domain.o panic.o printk.o profile.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
 # Do not trace debug files and internal ftrace files
 CFLAGS_REMOVE_lockdep.o = -pg
@@ -22,6 +24,8 @@ CFLAGS_REMOVE_sched_clock.o = -pg
 CFLAGS_REMOVE_sched.o = -mno-spe -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
 obj-y += time/
@@ -52,6 +56,7 @@ 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
@@ -80,7 +85,9 @@ 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-$(CONFIG_TRACING) += trace/
 obj-$(CONFIG_SMP) += sched_cpupri.o
diff --git a/kernel/acct.c b/kernel/acct.c
index 91e1cfd734d2..f6006a60df5d 100644
--- a/kernel/acct.c
+++ b/kernel/acct.c
@@ -75,37 +75,39 @@ int acct_parm[3] = {4, 2, 30};
 /*
  * External references and all of the globals.
  */
-static void do_acct_process(struct pid_namespace *ns, struct file *);
+static void do_acct_process(struct bsd_acct_struct *acct,
+                struct pid_namespace *ns, struct file *);
 
 /*
  * This structure is used so that all the data protected by lock
  * can be placed in the same cache line as the lock.  This primes
  * the cache line to have the data after getting the lock.
  */
-struct acct_glbs {
-        spinlock_t              lock;
+struct bsd_acct_struct {
         volatile int            active;
         volatile int            needcheck;
         struct file             *file;
         struct pid_namespace    *ns;
         struct timer_list       timer;
+        struct list_head        list;
 };
 
-static struct acct_glbs acct_globals __cacheline_aligned =
-        {__SPIN_LOCK_UNLOCKED(acct_globals.lock)};
+static DEFINE_SPINLOCK(acct_lock);
+static LIST_HEAD(acct_list);
 
 /*
  * Called whenever the timer says to check the free space.
  */
-static void acct_timeout(unsigned long unused)
+static void acct_timeout(unsigned long x)
 {
-        acct_globals.needcheck = 1;
+        struct bsd_acct_struct *acct = (struct bsd_acct_struct *)x;
+        acct->needcheck = 1;
 }
 
 /*
  * Check the amount of free space and suspend/resume accordingly.
  */
-static int check_free_space(struct file *file)
+static int check_free_space(struct bsd_acct_struct *acct, struct file *file)
 {
         struct kstatfs sbuf;
         int res;
@@ -113,11 +115,11 @@ static int check_free_space(struct file *file)
         sector_t resume;
         sector_t suspend;
 
-        spin_lock(&acct_globals.lock);
-        res = acct_globals.active;
-        if (!file || !acct_globals.needcheck)
+        spin_lock(&acct_lock);
+        res = acct->active;
+        if (!file || !acct->needcheck)
                 goto out;
-        spin_unlock(&acct_globals.lock);
+        spin_unlock(&acct_lock);
 
         /* May block */
         if (vfs_statfs(file->f_path.dentry, &sbuf))
@@ -136,35 +138,35 @@ static int check_free_space(struct file *file)
                 act = 0;
 
         /*
-         * If some joker switched acct_globals.file under us we'ld better be
+         * If some joker switched acct->file under us we'ld better be
          * silent and _not_ touch anything.
          */
-        spin_lock(&acct_globals.lock);
-        if (file != acct_globals.file) {
+        spin_lock(&acct_lock);
+        if (file != acct->file) {
                 if (act)
                         res = act>0;
                 goto out;
         }
 
-        if (acct_globals.active) {
+        if (acct->active) {
                 if (act < 0) {
-                        acct_globals.active = 0;
+                        acct->active = 0;
                         printk(KERN_INFO "Process accounting paused\n");
                 }
         } else {
                 if (act > 0) {
-                        acct_globals.active = 1;
+                        acct->active = 1;
                         printk(KERN_INFO "Process accounting resumed\n");
                 }
         }
 
-        del_timer(&acct_globals.timer);
-        acct_globals.needcheck = 0;
-        acct_globals.timer.expires = jiffies + ACCT_TIMEOUT*HZ;
-        add_timer(&acct_globals.timer);
-        res = acct_globals.active;
+        del_timer(&acct->timer);
+        acct->needcheck = 0;
+        acct->timer.expires = jiffies + ACCT_TIMEOUT*HZ;
+        add_timer(&acct->timer);
+        res = acct->active;
 out:
-        spin_unlock(&acct_globals.lock);
+        spin_unlock(&acct_lock);
         return res;
 }
 
@@ -172,39 +174,41 @@ out:
  * Close the old accounting file (if currently open) and then replace
  * it with file (if non-NULL).
  *
- * NOTE: acct_globals.lock MUST be held on entry and exit.
+ * NOTE: acct_lock MUST be held on entry and exit.
  */
-static void acct_file_reopen(struct file *file)
+static void acct_file_reopen(struct bsd_acct_struct *acct, struct file *file,
+                struct pid_namespace *ns)
 {
         struct file *old_acct = NULL;
         struct pid_namespace *old_ns = NULL;
 
-        if (acct_globals.file) {
-                old_acct = acct_globals.file;
-                old_ns = acct_globals.ns;
-                del_timer(&acct_globals.timer);
-                acct_globals.active = 0;
-                acct_globals.needcheck = 0;
-                acct_globals.file = NULL;
+        if (acct->file) {
+                old_acct = acct->file;
+                old_ns = acct->ns;
+                del_timer(&acct->timer);
+                acct->active = 0;
+                acct->needcheck = 0;
+                acct->file = NULL;
+                acct->ns = NULL;
+                list_del(&acct->list);
         }
         if (file) {
-                acct_globals.file = file;
-                acct_globals.ns = get_pid_ns(task_active_pid_ns(current));
-                acct_globals.needcheck = 0;
-                acct_globals.active = 1;
+                acct->file = file;
+                acct->ns = ns;
+                acct->needcheck = 0;
+                acct->active = 1;
+                list_add(&acct->list, &acct_list);
                 /* It's been deleted if it was used before so this is safe */
-                init_timer(&acct_globals.timer);
-                acct_globals.timer.function = acct_timeout;
-                acct_globals.timer.expires = jiffies + ACCT_TIMEOUT*HZ;
-                add_timer(&acct_globals.timer);
+                setup_timer(&acct->timer, acct_timeout, (unsigned long)acct);
+                acct->timer.expires = jiffies + ACCT_TIMEOUT*HZ;
+                add_timer(&acct->timer);
         }
         if (old_acct) {
                 mnt_unpin(old_acct->f_path.mnt);
-                spin_unlock(&acct_globals.lock);
-                do_acct_process(old_ns, old_acct);
+                spin_unlock(&acct_lock);
+                do_acct_process(acct, old_ns, old_acct);
                 filp_close(old_acct, NULL);
-                put_pid_ns(old_ns);
-                spin_lock(&acct_globals.lock);
+                spin_lock(&acct_lock);
         }
 }
 
@@ -212,6 +216,8 @@ static int acct_on(char *name)
 {
         struct file *file;
         int error;
+        struct pid_namespace *ns;
+        struct bsd_acct_struct *acct = NULL;
 
         /* Difference from BSD - they don't do O_APPEND */
         file = filp_open(name, O_WRONLY|O_APPEND|O_LARGEFILE, 0);
@@ -228,18 +234,34 @@ static int acct_on(char *name)
                 return -EIO;
         }
 
+        ns = task_active_pid_ns(current);
+        if (ns->bacct == NULL) {
+                acct = kzalloc(sizeof(struct bsd_acct_struct), GFP_KERNEL);
+                if (acct == NULL) {
+                        filp_close(file, NULL);
+                        return -ENOMEM;
+                }
+        }
+
         error = security_acct(file);
         if (error) {
+                kfree(acct);
                 filp_close(file, NULL);
                 return error;
         }
 
-        spin_lock(&acct_globals.lock);
+        spin_lock(&acct_lock);
+        if (ns->bacct == NULL) {
+                ns->bacct = acct;
+                acct = NULL;
+        }
+
         mnt_pin(file->f_path.mnt);
-        acct_file_reopen(file);
-        spin_unlock(&acct_globals.lock);
+        acct_file_reopen(ns->bacct, file, ns);
+        spin_unlock(&acct_lock);
 
         mntput(file->f_path.mnt); /* it's pinned, now give up active reference */
+        kfree(acct);
 
         return 0;
 }
@@ -269,11 +291,17 @@ asmlinkage long sys_acct(const char __user *name)
                 error = acct_on(tmp);
                 putname(tmp);
         } else {
+                struct bsd_acct_struct *acct;
+
+                acct = task_active_pid_ns(current)->bacct;
+                if (acct == NULL)
+                        return 0;
+
                 error = security_acct(NULL);
                 if (!error) {
-                        spin_lock(&acct_globals.lock);
-                        acct_file_reopen(NULL);
-                        spin_unlock(&acct_globals.lock);
+                        spin_lock(&acct_lock);
+                        acct_file_reopen(acct, NULL, NULL);
+                        spin_unlock(&acct_lock);
                 }
         }
         return error;
@@ -288,10 +316,16 @@ asmlinkage long sys_acct(const char __user *name)
  */
 void acct_auto_close_mnt(struct vfsmount *m)
 {
-        spin_lock(&acct_globals.lock);
-        if (acct_globals.file && acct_globals.file->f_path.mnt == m)
-                acct_file_reopen(NULL);
-        spin_unlock(&acct_globals.lock);
+        struct bsd_acct_struct *acct;
+
+        spin_lock(&acct_lock);
+restart:
+        list_for_each_entry(acct, &acct_list, list)
+                if (acct->file && acct->file->f_path.mnt == m) {
+                        acct_file_reopen(acct, NULL, NULL);
+                        goto restart;
+                }
+        spin_unlock(&acct_lock);
 }
 
 /**
@@ -303,12 +337,31 @@ void acct_auto_close_mnt(struct vfsmount *m)
  */
 void acct_auto_close(struct super_block *sb)
 {
-        spin_lock(&acct_globals.lock);
-        if (acct_globals.file &&
-            acct_globals.file->f_path.mnt->mnt_sb == sb) {
-                acct_file_reopen(NULL);
+        struct bsd_acct_struct *acct;
+
+        spin_lock(&acct_lock);
+restart:
+        list_for_each_entry(acct, &acct_list, list)
+                if (acct->file && acct->file->f_path.mnt->mnt_sb == sb) {
+                        acct_file_reopen(acct, NULL, NULL);
+                        goto restart;
+                }
+        spin_unlock(&acct_lock);
+}
+
+void acct_exit_ns(struct pid_namespace *ns)
+{
+        struct bsd_acct_struct *acct;
+
+        spin_lock(&acct_lock);
+        acct = ns->bacct;
+        if (acct != NULL) {
+                if (acct->file != NULL)
+                        acct_file_reopen(acct, NULL, NULL);
+
+                kfree(acct);
         }
-        spin_unlock(&acct_globals.lock);
+        spin_unlock(&acct_lock);
 }
 
 /*
@@ -425,7 +478,8 @@ static u32 encode_float(u64 value)
 /*
  *  do_acct_process does all actual work. Caller holds the reference to file.
  */
-static void do_acct_process(struct pid_namespace *ns, struct file *file)
+static void do_acct_process(struct bsd_acct_struct *acct,
+                struct pid_namespace *ns, struct file *file)
 {
         struct pacct_struct *pacct = &current->signal->pacct;
         acct_t ac;
@@ -440,7 +494,7 @@ static void do_acct_process(struct pid_namespace *ns, struct file *file)
          * First check to see if there is enough free_space to continue
          * the process accounting system.
          */
-        if (!check_free_space(file))
+        if (!check_free_space(acct, file))
                 return;
 
         /*
@@ -494,7 +548,7 @@ static void do_acct_process(struct pid_namespace *ns, struct file *file)
 #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)));
@@ -577,34 +631,46 @@ void acct_collect(long exitcode, int group_dead)
         spin_unlock_irq(&current->sighand->siglock);
 }
 
-/**
- * acct_process - now just a wrapper around do_acct_process
- * @exitcode: task exit code
- *
- * handles process accounting for an exiting task
- */
-void acct_process(void)
+static void acct_process_in_ns(struct pid_namespace *ns)
 {
         struct file *file = NULL;
-        struct pid_namespace *ns;
+        struct bsd_acct_struct *acct;
 
+        acct = ns->bacct;
         /*
          * accelerate the common fastpath:
          */
-        if (!acct_globals.file)
+        if (!acct || !acct->file)
                 return;
 
-        spin_lock(&acct_globals.lock);
-        file = acct_globals.file;
+        spin_lock(&acct_lock);
+        file = acct->file;
         if (unlikely(!file)) {
-                spin_unlock(&acct_globals.lock);
+                spin_unlock(&acct_lock);
                 return;
         }
         get_file(file);
-        ns = get_pid_ns(acct_globals.ns);
-        spin_unlock(&acct_globals.lock);
+        spin_unlock(&acct_lock);
 
-        do_acct_process(ns, file);
+        do_acct_process(acct, ns, file);
         fput(file);
-        put_pid_ns(ns);
+}
+
+/**
+ * acct_process - now just a wrapper around acct_process_in_ns,
+ * which in turn is a wrapper around do_acct_process.
+ *
+ * handles process accounting for an exiting task
+ */
+void acct_process(void)
+{
+        struct pid_namespace *ns;
+
+        /*
+         * This loop is safe lockless, since current is still
+         * alive and holds its namespace, which in turn holds
+         * its parent.
+         */
+        for (ns = task_active_pid_ns(current); ns != NULL; ns = ns->parent)
+                acct_process_in_ns(ns);
 }
diff --git a/kernel/audit.c b/kernel/audit.c
index e092f1c0ce30..4414e93d8750 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -707,12 +707,14 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
                 if (status_get->mask & AUDIT_STATUS_ENABLED) {
                         err = audit_set_enabled(status_get->enabled,
                                                 loginuid, sessionid, sid);
-                        if (err < 0) return err;
+                        if (err < 0)
+                                return err;
                 }
                 if (status_get->mask & AUDIT_STATUS_FAILURE) {
                         err = audit_set_failure(status_get->failure,
                                                 loginuid, sessionid, sid);
-                        if (err < 0) return err;
+                        if (err < 0)
+                                return err;
                 }
                 if (status_get->mask & AUDIT_STATUS_PID) {
                         int new_pid = status_get->pid;
@@ -725,9 +727,12 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
                         audit_pid = new_pid;
                         audit_nlk_pid = NETLINK_CB(skb).pid;
                 }
-                if (status_get->mask & AUDIT_STATUS_RATE_LIMIT)
+                if (status_get->mask & AUDIT_STATUS_RATE_LIMIT) {
                         err = audit_set_rate_limit(status_get->rate_limit,
                                                    loginuid, sessionid, sid);
+                        if (err < 0)
+                                return err;
+                }
                 if (status_get->mask & AUDIT_STATUS_BACKLOG_LIMIT)
                         err = audit_set_backlog_limit(status_get->backlog_limit,
                                                       loginuid, sessionid, sid);
@@ -1366,7 +1371,7 @@ int audit_string_contains_control(const char *string, size_t len)
 {
         const unsigned char *p;
         for (p = string; p < (const unsigned char *)string + len && *p; p++) {
-                if (*p == '"' || *p < 0x21 || *p > 0x7f)
+                if (*p == '"' || *p < 0x21 || *p > 0x7e)
                         return 1;
         }
         return 0;
diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c
index f7921a2ecf16..8ba0e0d934f2 100644
--- a/kernel/audit_tree.c
+++ b/kernel/audit_tree.c
@@ -532,7 +532,7 @@ 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 +544,12 @@ 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 +580,19 @@ 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 +618,7 @@ 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 +637,11 @@ 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 +690,29 @@ 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 +733,7 @@ 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 +741,15 @@ 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);
diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c
index 98c50cc671bb..b7d354e2b0ef 100644
--- a/kernel/auditfilter.c
+++ b/kernel/auditfilter.c
@@ -1022,8 +1022,11 @@ static void audit_update_watch(struct audit_parent *parent,
                         struct audit_buffer *ab;
                         ab = audit_log_start(NULL, GFP_KERNEL,
                                 AUDIT_CONFIG_CHANGE);
+                        audit_log_format(ab, "auid=%u ses=%u",
+                                audit_get_loginuid(current),
+                                audit_get_sessionid(current));
                         audit_log_format(ab,
-                                "op=updated rules specifying path=");
+                                " op=updated rules specifying path=");
                         audit_log_untrustedstring(ab, owatch->path);
                         audit_log_format(ab, " with dev=%u ino=%lu\n",
                                  dev, ino);
@@ -1058,7 +1061,10 @@ static void audit_remove_parent_watches(struct audit_parent *parent)
                                 struct audit_buffer *ab;
                                 ab = audit_log_start(NULL, GFP_KERNEL,
                                         AUDIT_CONFIG_CHANGE);
-                                audit_log_format(ab, "op=remove rule path=");
+                                audit_log_format(ab, "auid=%u ses=%u",
+                                        audit_get_loginuid(current),
+                                        audit_get_sessionid(current));
+                                audit_log_format(ab, " op=remove rule path=");
                                 audit_log_untrustedstring(ab, w->path);
                                 if (r->filterkey) {
                                         audit_log_format(ab, " key=");
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index c10e7aae04d7..cf5bc2f5f9c3 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -243,7 +243,11 @@ static inline int open_arg(int flags, int mask)
 
 static int audit_match_perm(struct audit_context *ctx, int mask)
 {
-        unsigned n = ctx->major;
+        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) &&
@@ -284,6 +288,10 @@ static int audit_match_filetype(struct audit_context *ctx, int which)
 {
         unsigned index = which & ~S_IFMT;
         mode_t mode = which & S_IFMT;
+
+        if (unlikely(!ctx))
+                return 0;
+
         if (index >= ctx->name_count)
                 return 0;
         if (ctx->names[index].ino == -1)
@@ -610,7 +618,7 @@ static int audit_filter_rules(struct task_struct *tsk,
                 if (!result)
                         return 0;
         }
-        if (rule->filterkey)
+        if (rule->filterkey && ctx)
                 ctx->filterkey = kstrdup(rule->filterkey, GFP_ATOMIC);
         switch (rule->action) {
         case AUDIT_NEVER:    *state = AUDIT_DISABLED;       break;
@@ -1196,13 +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"
@@ -1222,7 +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) {
@@ -1476,7 +1483,8 @@ void audit_syscall_entry(int arch, int major,
         struct audit_context *context = tsk->audit_context;
         enum audit_state     state;
 
-        BUG_ON(!context);
+        if (unlikely(!context))
+                return;
 
         /*
          * This happens only on certain architectures that make system
@@ -2374,7 +2382,7 @@ int __audit_signal_info(int sig, struct task_struct *t)
         struct audit_context *ctx = tsk->audit_context;
 
         if (audit_pid && t->tgid == audit_pid) {
-                if (sig == SIGTERM || sig == SIGHUP || sig == SIGUSR1) {
+                if (sig == SIGTERM || sig == SIGHUP || sig == SIGUSR1 || sig == SIGUSR2) {
                         audit_sig_pid = tsk->pid;
                         if (tsk->loginuid != -1)
                                 audit_sig_uid = tsk->loginuid;
diff --git a/kernel/capability.c b/kernel/capability.c
index 901e0fdc3fff..33e51e78c2d8 100644
--- a/kernel/capability.c
+++ b/kernel/capability.c
@@ -115,11 +115,208 @@ static int cap_validate_magic(cap_user_header_t header, unsigned *tocopy)
         return 0;
 }
 
+#ifndef CONFIG_SECURITY_FILE_CAPABILITIES
+
+/*
+ * Without filesystem capability support, we nominally support one process
+ * setting the capabilities of another
+ */
+static inline int cap_get_target_pid(pid_t pid, kernel_cap_t *pEp,
+                                     kernel_cap_t *pIp, kernel_cap_t *pPp)
+{
+        struct task_struct *target;
+        int ret;
+
+        spin_lock(&task_capability_lock);
+        read_lock(&tasklist_lock);
+
+        if (pid && pid != task_pid_vnr(current)) {
+                target = find_task_by_vpid(pid);
+                if (!target) {
+                        ret = -ESRCH;
+                        goto out;
+                }
+        } else
+                target = current;
+
+        ret = security_capget(target, pEp, pIp, pPp);
+
+out:
+        read_unlock(&tasklist_lock);
+        spin_unlock(&task_capability_lock);
+
+        return ret;
+}
+
+/*
+ * cap_set_pg - set capabilities for all processes in a given process
+ * group.  We call this holding task_capability_lock and tasklist_lock.
+ */
+static inline int cap_set_pg(int pgrp_nr, kernel_cap_t *effective,
+                             kernel_cap_t *inheritable,
+                             kernel_cap_t *permitted)
+{
+        struct task_struct *g, *target;
+        int ret = -EPERM;
+        int found = 0;
+        struct pid *pgrp;
+
+        spin_lock(&task_capability_lock);
+        read_lock(&tasklist_lock);
+
+        pgrp = find_vpid(pgrp_nr);
+        do_each_pid_task(pgrp, PIDTYPE_PGID, g) {
+                target = g;
+                while_each_thread(g, target) {
+                        if (!security_capset_check(target, effective,
+                                                   inheritable, permitted)) {
+                                security_capset_set(target, effective,
+                                                    inheritable, permitted);
+                                ret = 0;
+                        }
+                        found = 1;
+                }
+        } while_each_pid_task(pgrp, PIDTYPE_PGID, g);
+
+        read_unlock(&tasklist_lock);
+        spin_unlock(&task_capability_lock);
+
+        if (!found)
+                ret = 0;
+        return ret;
+}
+
+/*
+ * cap_set_all - set capabilities for all processes other than init
+ * and self.  We call this holding task_capability_lock and tasklist_lock.
+ */
+static inline int cap_set_all(kernel_cap_t *effective,
+                              kernel_cap_t *inheritable,
+                              kernel_cap_t *permitted)
+{
+        struct task_struct *g, *target;
+        int ret = -EPERM;
+        int found = 0;
+
+        spin_lock(&task_capability_lock);
+        read_lock(&tasklist_lock);
+
+        do_each_thread(g, target) {
+                if (target == current
+                    || is_container_init(target->group_leader))
+                        continue;
+                found = 1;
+                if (security_capset_check(target, effective, inheritable,
+                                          permitted))
+                        continue;
+                ret = 0;
+                security_capset_set(target, effective, inheritable, permitted);
+        } while_each_thread(g, target);
+
+        read_unlock(&tasklist_lock);
+        spin_unlock(&task_capability_lock);
+
+        if (!found)
+                ret = 0;
+
+        return ret;
+}
+
+/*
+ * Given the target pid does not refer to the current process we
+ * need more elaborate support... (This support is not present when
+ * filesystem capabilities are configured.)
+ */
+static inline int do_sys_capset_other_tasks(pid_t pid, kernel_cap_t *effective,
+                                            kernel_cap_t *inheritable,
+                                            kernel_cap_t *permitted)
+{
+        struct task_struct *target;
+        int ret;
+
+        if (!capable(CAP_SETPCAP))
+                return -EPERM;
+
+        if (pid == -1)            /* all procs other than current and init */
+                return cap_set_all(effective, inheritable, permitted);
+
+        else if (pid < 0)                    /* all procs in process group */
+                return cap_set_pg(-pid, effective, inheritable, permitted);
+
+        /* target != current */
+        spin_lock(&task_capability_lock);
+        read_lock(&tasklist_lock);
+
+        target = find_task_by_vpid(pid);
+        if (!target)
+                ret = -ESRCH;
+        else {
+                ret = security_capset_check(target, effective, inheritable,
+                                            permitted);
+
+                /* having verified that the proposed changes are legal,
+                   we now put them into effect. */
+                if (!ret)
+                        security_capset_set(target, effective, inheritable,
+                                            permitted);
+        }
+
+        read_unlock(&tasklist_lock);
+        spin_unlock(&task_capability_lock);
+
+        return ret;
+}
+
+#else /* ie., def CONFIG_SECURITY_FILE_CAPABILITIES */
+
 /*
- * For sys_getproccap() and sys_setproccap(), any of the three
- * capability set pointers may be NULL -- indicating that that set is
- * uninteresting and/or not to be changed.
+ * If we have configured with filesystem capability support, then the
+ * only thing that can change the capabilities of the current process
+ * is the current process. As such, we can't be in this code at the
+ * same time as we are in the process of setting capabilities in this
+ * process. The net result is that we can limit our use of locks to
+ * when we are reading the caps of another process.
  */
+static inline int cap_get_target_pid(pid_t pid, kernel_cap_t *pEp,
+                                     kernel_cap_t *pIp, kernel_cap_t *pPp)
+{
+        int ret;
+
+        if (pid && (pid != task_pid_vnr(current))) {
+                struct task_struct *target;
+
+                spin_lock(&task_capability_lock);
+                read_lock(&tasklist_lock);
+
+                target = find_task_by_vpid(pid);
+                if (!target)
+                        ret = -ESRCH;
+                else
+                        ret = security_capget(target, pEp, pIp, pPp);
+
+                read_unlock(&tasklist_lock);
+                spin_unlock(&task_capability_lock);
+        } else
+                ret = security_capget(current, pEp, pIp, pPp);
+
+        return ret;
+}
+
+/*
+ * With filesystem capability support configured, the kernel does not
+ * permit the changing of capabilities in one process by another
+ * process. (CAP_SETPCAP has much less broad semantics when configured
+ * this way.)
+ */
+static inline int do_sys_capset_other_tasks(pid_t pid,
+                                            kernel_cap_t *effective,
+                                            kernel_cap_t *inheritable,
+                                            kernel_cap_t *permitted)
+{
+        return -EPERM;
+}
+
+#endif /* ie., ndef CONFIG_SECURITY_FILE_CAPABILITIES */
 
 /*
  * Atomically modify the effective capabilities returning the original
@@ -155,7 +352,6 @@ asmlinkage long sys_capget(cap_user_header_t header, cap_user_data_t dataptr)
 {
         int ret = 0;
         pid_t pid;
-        struct task_struct *target;
         unsigned tocopy;
         kernel_cap_t pE, pI, pP;
 
@@ -169,23 +365,7 @@ asmlinkage long sys_capget(cap_user_header_t header, cap_user_data_t dataptr)
         if (pid < 0)
                 return -EINVAL;
 
-        spin_lock(&task_capability_lock);
-        read_lock(&tasklist_lock);
-
-        if (pid && pid != task_pid_vnr(current)) {
-                target = find_task_by_vpid(pid);
-                if (!target) {
-                        ret = -ESRCH;
-                        goto out;
-                }
-        } else
-                target = current;
-
-        ret = security_capget(target, &pE, &pI, &pP);
-
-out:
-        read_unlock(&tasklist_lock);
-        spin_unlock(&task_capability_lock);
+        ret = cap_get_target_pid(pid, &pE, &pI, &pP);
 
         if (!ret) {
                 struct __user_cap_data_struct kdata[_KERNEL_CAPABILITY_U32S];
@@ -216,7 +396,6 @@ out:
                  * before modification is attempted and the application
                  * fails.
                  */
-
                 if (copy_to_user(dataptr, kdata, tocopy
                                  * sizeof(struct __user_cap_data_struct))) {
                         return -EFAULT;
@@ -226,70 +405,8 @@ out:
         return ret;
 }
 
-/*
- * cap_set_pg - set capabilities for all processes in a given process
- * group.  We call this holding task_capability_lock and tasklist_lock.
- */
-static inline int cap_set_pg(int pgrp_nr, kernel_cap_t *effective,
-                              kernel_cap_t *inheritable,
-                              kernel_cap_t *permitted)
-{
-        struct task_struct *g, *target;
-        int ret = -EPERM;
-        int found = 0;
-        struct pid *pgrp;
-
-        pgrp = find_vpid(pgrp_nr);
-        do_each_pid_task(pgrp, PIDTYPE_PGID, g) {
-                target = g;
-                while_each_thread(g, target) {
-                        if (!security_capset_check(target, effective,
-                                                        inheritable,
-                                                        permitted)) {
-                                security_capset_set(target, effective,
-                                                        inheritable,
-                                                        permitted);
-                                ret = 0;
-                        }
-                        found = 1;
-                }
-        } while_each_pid_task(pgrp, PIDTYPE_PGID, g);
-
-        if (!found)
-                ret = 0;
-        return ret;
-}
-
-/*
- * cap_set_all - set capabilities for all processes other than init
- * and self.  We call this holding task_capability_lock and tasklist_lock.
- */
-static inline int cap_set_all(kernel_cap_t *effective,
-                               kernel_cap_t *inheritable,
-                               kernel_cap_t *permitted)
-{
-     struct task_struct *g, *target;
-     int ret = -EPERM;
-     int found = 0;
-
-     do_each_thread(g, target) {
-             if (target == current || is_container_init(target->group_leader))
-                     continue;
-             found = 1;
-             if (security_capset_check(target, effective, inheritable,
-                                                permitted))
-                     continue;
-             ret = 0;
-             security_capset_set(target, effective, inheritable, permitted);
-     } while_each_thread(g, target);
-
-     if (!found)
-             ret = 0;
-     return ret;
-}
-
 /**
- * sys_capset - set capabilities for a process or a group of processes
+ * sys_capset - set capabilities for a process or (*) a group of processes
  * @header: pointer to struct that contains capability version and
  *      target pid data
  * @data: pointer to struct that contains the effective, permitted,
@@ -313,7 +430,6 @@ asmlinkage long sys_capset(cap_user_header_t header, const cap_user_data_t data)
         struct __user_cap_data_struct kdata[_KERNEL_CAPABILITY_U32S];
         unsigned i, tocopy;
         kernel_cap_t inheritable, permitted, effective;
-        struct task_struct *target;
         int ret;
         pid_t pid;
 
@@ -324,9 +440,6 @@ asmlinkage long sys_capset(cap_user_header_t header, const cap_user_data_t data)
         if (get_user(pid, &header->pid))
                 return -EFAULT;
 
-        if (pid && pid != task_pid_vnr(current) && !capable(CAP_SETPCAP))
-                return -EPERM;
-
         if (copy_from_user(&kdata, data, tocopy
                            * sizeof(struct __user_cap_data_struct))) {
                 return -EFAULT;
@@ -344,55 +457,51 @@ asmlinkage long sys_capset(cap_user_header_t header, const cap_user_data_t data)
                 i++;
         }
 
-        spin_lock(&task_capability_lock);
-        read_lock(&tasklist_lock);
-
-        if (pid > 0 && pid != task_pid_vnr(current)) {
-                target = find_task_by_vpid(pid);
-                if (!target) {
-                        ret = -ESRCH;
-                        goto out;
-                }
-        } else
-                target = current;
-
-        ret = 0;
-
-        /* having verified that the proposed changes are legal,
-           we now put them into effect. */
-        if (pid < 0) {
-                if (pid == -1)  /* all procs other than current and init */
-                        ret = cap_set_all(&effective, &inheritable, &permitted);
+        if (pid && (pid != task_pid_vnr(current)))
+                ret = do_sys_capset_other_tasks(pid, &effective, &inheritable,
+                                                &permitted);
+        else {
+                /*
+                 * This lock is required even when filesystem
+                 * capability support is configured - it protects the
+                 * sys_capget() call from returning incorrect data in
+                 * the case that the targeted process is not the
+                 * current one.
+                 */
+                spin_lock(&task_capability_lock);
 
-                else            /* all procs in process group */
-                        ret = cap_set_pg(-pid, &effective, &inheritable,
-                                         &permitted);
-        } else {
-                ret = security_capset_check(target, &effective, &inheritable,
+                ret = security_capset_check(current, &effective, &inheritable,
                                             &permitted);
+                /*
+                 * Having verified that the proposed changes are
+                 * legal, we now put them into effect.
+                 */
                 if (!ret)
-                        security_capset_set(target, &effective, &inheritable,
+                        security_capset_set(current, &effective, &inheritable,
                                             &permitted);
+                spin_unlock(&task_capability_lock);
         }
 
-out:
-        read_unlock(&tasklist_lock);
-        spin_unlock(&task_capability_lock);
 
         return ret;
 }
 
-int __capable(struct task_struct *t, int cap)
+/**
+ * capable - Determine if the current task has a superior capability in effect
+ * @cap: The capability to be tested for
+ *
+ * Return true if the current task has the given superior capability currently
+ * available for use, false if not.
+ *
+ * This sets PF_SUPERPRIV on the task if the capability is available on the
+ * assumption that it's about to be used.
+ */
+int capable(int cap)
 {
-        if (security_capable(t, cap) == 0) {
-                t->flags |= PF_SUPERPRIV;
+        if (has_capability(current, cap)) {
+                current->flags |= PF_SUPERPRIV;
                 return 1;
         }
         return 0;
 }
-
-int capable(int cap)
-{
-        return __capable(current, cap);
-}
 EXPORT_SYMBOL(capable);
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 15ac0e1e4f4d..35eebd5510c2 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -45,6 +45,7 @@
 #include <linux/delayacct.h>
 #include <linux/cgroupstats.h>
 #include <linux/hash.h>
+#include <linux/namei.h>
 
 #include <asm/atomic.h>
 
@@ -89,11 +90,7 @@ struct cgroupfs_root {
         /* Hierarchy-specific flags */
         unsigned long flags;
 
-        /* The path to use for release notifications. No locking
-         * between setting and use - so if userspace updates this
-         * while child cgroups exist, you could miss a
-         * notification. We ensure that it's always a valid
-         * NUL-terminated string */
+        /* The path to use for release notifications. */
         char release_agent_path[PATH_MAX];
 };
 
@@ -118,7 +115,7 @@ static int root_count;
  * extra work in the fork/exit path if none of the subsystems need to
  * be called.
  */
-static int need_forkexit_callback;
+static int need_forkexit_callback __read_mostly;
 static int need_mm_owner_callback __read_mostly;
 
 /* convenient tests for these bits */
@@ -220,7 +217,7 @@ static struct hlist_head *css_set_hash(struct cgroup_subsys_state *css[])
  * task until after the first call to cgroup_iter_start(). This
  * reduces the fork()/exit() overhead for people who have cgroups
  * compiled into their kernel but not actually in use */
-static int use_task_css_set_links;
+static int use_task_css_set_links __read_mostly;
 
 /* When we create or destroy a css_set, the operation simply
  * takes/releases a reference count on all the cgroups referenced
@@ -241,26 +238,37 @@ static int use_task_css_set_links;
  */
 static void unlink_css_set(struct css_set *cg)
 {
-        write_lock(&css_set_lock);
+        struct cg_cgroup_link *link;
+        struct cg_cgroup_link *saved_link;
+
         hlist_del(&cg->hlist);
         css_set_count--;
-        while (!list_empty(&cg->cg_links)) {
-                struct cg_cgroup_link *link;
-                link = list_entry(cg->cg_links.next,
-                                  struct cg_cgroup_link, cg_link_list);
+
+        list_for_each_entry_safe(link, saved_link, &cg->cg_links,
+                                 cg_link_list) {
                 list_del(&link->cg_link_list);
                 list_del(&link->cgrp_link_list);
                 kfree(link);
         }
-        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);
 }
 
 /*
@@ -355,6 +353,17 @@ static struct css_set *find_existing_css_set(
         return NULL;
 }
 
+static void free_cg_links(struct list_head *tmp)
+{
+        struct cg_cgroup_link *link;
+        struct cg_cgroup_link *saved_link;
+
+        list_for_each_entry_safe(link, saved_link, tmp, cgrp_link_list) {
+                list_del(&link->cgrp_link_list);
+                kfree(link);
+        }
+}
+
 /*
  * allocate_cg_links() allocates "count" cg_cgroup_link structures
  * and chains them on tmp through their cgrp_link_list fields. Returns 0 on
@@ -368,13 +377,7 @@ static int allocate_cg_links(int count, struct list_head *tmp)
         for (i = 0; i < count; i++) {
                 link = kmalloc(sizeof(*link), GFP_KERNEL);
                 if (!link) {
-                        while (!list_empty(tmp)) {
-                                link = list_entry(tmp->next,
-                                                  struct cg_cgroup_link,
-                                                  cgrp_link_list);
-                                list_del(&link->cgrp_link_list);
-                                kfree(link);
-                        }
+                        free_cg_links(tmp);
                         return -ENOMEM;
                 }
                 list_add(&link->cgrp_link_list, tmp);
@@ -382,18 +385,6 @@ static int allocate_cg_links(int count, struct list_head *tmp)
         return 0;
 }
 
-static void free_cg_links(struct list_head *tmp)
-{
-        while (!list_empty(tmp)) {
-                struct cg_cgroup_link *link;
-                link = list_entry(tmp->next,
-                                  struct cg_cgroup_link,
-                                  cgrp_link_list);
-                list_del(&link->cgrp_link_list);
-                kfree(link);
-        }
-}
-
 /*
  * find_css_set() takes an existing cgroup group and a
  * cgroup object, and returns a css_set object that's
@@ -415,11 +406,11 @@ static struct css_set *find_css_set(
 
         /* First see if we already have a cgroup group that matches
          * the desired set */
-        write_lock(&css_set_lock);
+        read_lock(&css_set_lock);
         res = find_existing_css_set(oldcg, cgrp, template);
         if (res)
                 get_css_set(res);
-        write_unlock(&css_set_lock);
+        read_unlock(&css_set_lock);
 
         if (res)
                 return res;
@@ -434,7 +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);
@@ -507,10 +498,6 @@ static struct css_set *find_css_set(
  * knows that the cgroup won't be removed, as cgroup_rmdir()
  * needs that mutex.
  *
- * The cgroup_common_file_write handler for operations that modify
- * the cgroup hierarchy holds cgroup_mutex across the entire operation,
- * single threading all such cgroup modifications across the system.
- *
  * The fork and exit callbacks cgroup_fork() and cgroup_exit(), don't
  * (usually) take cgroup_mutex.  These are the two most performance
  * critical pieces of code here.  The exception occurs on cgroup_exit(),
@@ -881,6 +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;
@@ -889,10 +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)
@@ -962,7 +954,6 @@ static int cgroup_get_sb(struct file_system_type *fs_type,
         struct super_block *sb;
         struct cgroupfs_root *root;
         struct list_head tmp_cg_links;
-        INIT_LIST_HEAD(&tmp_cg_links);
 
         /* First find the desired set of subsystems */
         ret = parse_cgroupfs_options(data, &opts);
@@ -1093,6 +1084,8 @@ static void cgroup_kill_sb(struct super_block *sb) {
         struct cgroupfs_root *root = sb->s_fs_info;
         struct cgroup *cgrp = &root->top_cgroup;
         int ret;
+        struct cg_cgroup_link *link;
+        struct cg_cgroup_link *saved_link;
 
         BUG_ON(!root);
 
@@ -1112,10 +1105,9 @@ static void cgroup_kill_sb(struct super_block *sb) {
          * root cgroup
          */
         write_lock(&css_set_lock);
-        while (!list_empty(&cgrp->css_sets)) {
-                struct cg_cgroup_link *link;
-                link = list_entry(cgrp->css_sets.next,
-                                  struct cg_cgroup_link, cgrp_link_list);
+
+        list_for_each_entry_safe(link, saved_link, &cgrp->css_sets,
+                                 cgrp_link_list) {
                 list_del(&link->cg_link_list);
                 list_del(&link->cgrp_link_list);
                 kfree(link);
@@ -1281,18 +1273,14 @@ int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk)
 }
 
 /*
- * Attach task with pid 'pid' to cgroup 'cgrp'. Call with
- * cgroup_mutex, may take task_lock of task
+ * Attach task with pid 'pid' to cgroup 'cgrp'. Call with cgroup_mutex
+ * held. May take task_lock of task
  */
-static int attach_task_by_pid(struct cgroup *cgrp, char *pidbuf)
+static int attach_task_by_pid(struct cgroup *cgrp, u64 pid)
 {
-        pid_t pid;
         struct task_struct *tsk;
         int ret;
 
-        if (sscanf(pidbuf, "%d", &pid) != 1)
-                return -EIO;
-
         if (pid) {
                 rcu_read_lock();
                 tsk = find_task_by_vpid(pid);
@@ -1318,6 +1306,16 @@ static int attach_task_by_pid(struct cgroup *cgrp, char *pidbuf)
         return ret;
 }
 
+static int cgroup_tasks_write(struct cgroup *cgrp, struct cftype *cft, u64 pid)
+{
+        int ret;
+        if (!cgroup_lock_live_group(cgrp))
+                return -ENODEV;
+        ret = attach_task_by_pid(cgrp, pid);
+        cgroup_unlock();
+        return ret;
+}
+
 /* The various types of files and directories in a cgroup file system */
 enum cgroup_filetype {
         FILE_ROOT,
@@ -1327,12 +1325,54 @@ enum cgroup_filetype {
         FILE_RELEASE_AGENT,
 };
 
+/**
+ * cgroup_lock_live_group - take cgroup_mutex and check that cgrp is alive.
+ * @cgrp: the cgroup to be checked for liveness
+ *
+ * On success, returns true; the lock should be later released with
+ * cgroup_unlock(). On failure returns false with no lock held.
+ */
+bool cgroup_lock_live_group(struct cgroup *cgrp)
+{
+        mutex_lock(&cgroup_mutex);
+        if (cgroup_is_removed(cgrp)) {
+                mutex_unlock(&cgroup_mutex);
+                return false;
+        }
+        return true;
+}
+
+static int cgroup_release_agent_write(struct cgroup *cgrp, struct cftype *cft,
+                                      const char *buffer)
+{
+        BUILD_BUG_ON(sizeof(cgrp->root->release_agent_path) < PATH_MAX);
+        if (!cgroup_lock_live_group(cgrp))
+                return -ENODEV;
+        strcpy(cgrp->root->release_agent_path, buffer);
+        cgroup_unlock();
+        return 0;
+}
+
+static int cgroup_release_agent_show(struct cgroup *cgrp, struct cftype *cft,
+                                     struct seq_file *seq)
+{
+        if (!cgroup_lock_live_group(cgrp))
+                return -ENODEV;
+        seq_puts(seq, cgrp->root->release_agent_path);
+        seq_putc(seq, '\n');
+        cgroup_unlock();
+        return 0;
+}
+
+/* A buffer size big enough for numbers or short strings */
+#define CGROUP_LOCAL_BUFFER_SIZE 64
+
 static ssize_t cgroup_write_X64(struct cgroup *cgrp, struct cftype *cft,
                                 struct file *file,
                                 const char __user *userbuf,
                                 size_t nbytes, loff_t *unused_ppos)
 {
-        char buffer[64];
+        char buffer[CGROUP_LOCAL_BUFFER_SIZE];
         int retval = 0;
         char *end;
 
@@ -1361,68 +1401,39 @@ static ssize_t cgroup_write_X64(struct cgroup *cgrp, struct cftype *cft,
         return retval;
 }
 
-static ssize_t cgroup_common_file_write(struct cgroup *cgrp,
-                                           struct cftype *cft,
-                                           struct file *file,
-                                           const char __user *userbuf,
-                                           size_t nbytes, loff_t *unused_ppos)
+static ssize_t cgroup_write_string(struct cgroup *cgrp, struct cftype *cft,
+                                   struct file *file,
+                                   const char __user *userbuf,
+                                   size_t nbytes, loff_t *unused_ppos)
 {
-        enum cgroup_filetype type = cft->private;
-        char *buffer;
+        char local_buffer[CGROUP_LOCAL_BUFFER_SIZE];
         int retval = 0;
+        size_t max_bytes = cft->max_write_len;
+        char *buffer = local_buffer;
 
-        if (nbytes >= PATH_MAX)
+        if (!max_bytes)
+                max_bytes = sizeof(local_buffer) - 1;
+        if (nbytes >= max_bytes)
                 return -E2BIG;
-
-        /* +1 for nul-terminator */
-        buffer = kmalloc(nbytes + 1, GFP_KERNEL);
-        if (buffer == NULL)
-                return -ENOMEM;
-
-        if (copy_from_user(buffer, userbuf, nbytes)) {
+        /* Allocate a dynamic buffer if we need one */
+        if (nbytes >= sizeof(local_buffer)) {
+                buffer = kmalloc(nbytes + 1, GFP_KERNEL);
+                if (buffer == NULL)
+                        return -ENOMEM;
+        }
+        if (nbytes && copy_from_user(buffer, userbuf, nbytes)) {
                 retval = -EFAULT;
-                goto out1;
+                goto out;
         }
-        buffer[nbytes] = 0;     /* nul-terminate */
-        strstrip(buffer);       /* strip -just- trailing whitespace */
-
-        mutex_lock(&cgroup_mutex);
 
-        /*
-         * This was already checked for in cgroup_file_write(), but
-         * check again now we're holding cgroup_mutex.
-         */
-        if (cgroup_is_removed(cgrp)) {
-                retval = -ENODEV;
-                goto out2;
-        }
-
-        switch (type) {
-        case FILE_TASKLIST:
-                retval = attach_task_by_pid(cgrp, buffer);
-                break;
-        case FILE_NOTIFY_ON_RELEASE:
-                clear_bit(CGRP_RELEASABLE, &cgrp->flags);
-                if (simple_strtoul(buffer, NULL, 10) != 0)
-                        set_bit(CGRP_NOTIFY_ON_RELEASE, &cgrp->flags);
-                else
-                        clear_bit(CGRP_NOTIFY_ON_RELEASE, &cgrp->flags);
-                break;
-        case FILE_RELEASE_AGENT:
-                BUILD_BUG_ON(sizeof(cgrp->root->release_agent_path) < PATH_MAX);
-                strcpy(cgrp->root->release_agent_path, buffer);
-                break;
-        default:
-                retval = -EINVAL;
-                goto out2;
-        }
-
-        if (retval == 0)
+        buffer[nbytes] = 0;     /* nul-terminate */
+        strstrip(buffer);
+        retval = cft->write_string(cgrp, cft, buffer);
+        if (!retval)
                 retval = nbytes;
-out2:
-        mutex_unlock(&cgroup_mutex);
-out1:
-        kfree(buffer);
+out:
+        if (buffer != local_buffer)
+                kfree(buffer);
         return retval;
 }
 
@@ -1438,6 +1449,8 @@ static ssize_t cgroup_file_write(struct file *file, const char __user *buf,
                 return cft->write(cgrp, cft, file, buf, nbytes, ppos);
         if (cft->write_u64 || cft->write_s64)
                 return cgroup_write_X64(cgrp, cft, file, buf, nbytes, ppos);
+        if (cft->write_string)
+                return cgroup_write_string(cgrp, cft, file, buf, nbytes, ppos);
         if (cft->trigger) {
                 int ret = cft->trigger(cgrp, (unsigned int)cft->private);
                 return ret ? ret : nbytes;
@@ -1450,7 +1463,7 @@ static ssize_t cgroup_read_u64(struct cgroup *cgrp, struct cftype *cft,
                                char __user *buf, size_t nbytes,
                                loff_t *ppos)
 {
-        char tmp[64];
+        char tmp[CGROUP_LOCAL_BUFFER_SIZE];
         u64 val = cft->read_u64(cgrp, cft);
         int len = sprintf(tmp, "%llu\n", (unsigned long long) val);
 
@@ -1462,56 +1475,13 @@ static ssize_t cgroup_read_s64(struct cgroup *cgrp, struct cftype *cft,
                                char __user *buf, size_t nbytes,
                                loff_t *ppos)
 {
-        char tmp[64];
+        char tmp[CGROUP_LOCAL_BUFFER_SIZE];
         s64 val = cft->read_s64(cgrp, cft);
         int len = sprintf(tmp, "%lld\n", (long long) val);
 
         return simple_read_from_buffer(buf, nbytes, ppos, tmp, len);
 }
 
-static ssize_t cgroup_common_file_read(struct cgroup *cgrp,
-                                          struct cftype *cft,
-                                          struct file *file,
-                                          char __user *buf,
-                                          size_t nbytes, loff_t *ppos)
-{
-        enum cgroup_filetype type = cft->private;
-        char *page;
-        ssize_t retval = 0;
-        char *s;
-
-        if (!(page = (char *)__get_free_page(GFP_KERNEL)))
-                return -ENOMEM;
-
-        s = page;
-
-        switch (type) {
-        case FILE_RELEASE_AGENT:
-        {
-                struct cgroupfs_root *root;
-                size_t n;
-                mutex_lock(&cgroup_mutex);
-                root = cgrp->root;
-                n = strnlen(root->release_agent_path,
-                            sizeof(root->release_agent_path));
-                n = min(n, (size_t) PAGE_SIZE);
-                strncpy(s, root->release_agent_path, n);
-                mutex_unlock(&cgroup_mutex);
-                s += n;
-                break;
-        }
-        default:
-                retval = -EINVAL;
-                goto out;
-        }
-        *s++ = '\n';
-
-        retval = simple_read_from_buffer(buf, nbytes, ppos, page, s - page);
-out:
-        free_page((unsigned long)page);
-        return retval;
-}
-
 static ssize_t cgroup_file_read(struct file *file, char __user *buf,
                                    size_t nbytes, loff_t *ppos)
 {
@@ -1560,7 +1530,7 @@ static int cgroup_seqfile_show(struct seq_file *m, void *arg)
         return cft->read_seq_string(state->cgroup, cft, m);
 }
 
-int cgroup_seqfile_release(struct inode *inode, struct file *file)
+static int cgroup_seqfile_release(struct inode *inode, struct file *file)
 {
         struct seq_file *seq = file->private_data;
         kfree(seq->private);
@@ -1569,6 +1539,7 @@ int cgroup_seqfile_release(struct inode *inode, struct file *file)
 
 static struct file_operations cgroup_seqfile_operations = {
         .read = seq_read,
+        .write = cgroup_file_write,
         .llseek = seq_lseek,
         .release = cgroup_seqfile_release,
 };
@@ -1756,15 +1727,11 @@ int cgroup_add_files(struct cgroup *cgrp,
 int cgroup_task_count(const struct cgroup *cgrp)
 {
         int count = 0;
-        struct list_head *l;
+        struct cg_cgroup_link *link;
 
         read_lock(&css_set_lock);
-        l = cgrp->css_sets.next;
-        while (l != &cgrp->css_sets) {
-                struct cg_cgroup_link *link =
-                        list_entry(l, struct cg_cgroup_link, cgrp_link_list);
-                count += atomic_read(&link->cg->ref.refcount);
-                l = l->next;
+        list_for_each_entry(link, &cgrp->css_sets, cgrp_link_list) {
+                count += atomic_read(&link->cg->refcount);
         }
         read_unlock(&css_set_lock);
         return count;
@@ -2033,16 +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
@@ -2124,42 +2082,132 @@ 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;
+}
+
+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,
+};
 
-        for (i = 0; i < npids; i++)
-                cnt += snprintf(buf + cnt, max(sz - cnt, 0), "%d\n", a[i]);
-        return cnt;
+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
@@ -2167,57 +2215,31 @@ 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;
 }
 
@@ -2227,6 +2249,18 @@ static u64 cgroup_read_notify_on_release(struct cgroup *cgrp,
         return notify_on_release(cgrp);
 }
 
+static int cgroup_write_notify_on_release(struct cgroup *cgrp,
+                                          struct cftype *cft,
+                                          u64 val)
+{
+        clear_bit(CGRP_RELEASABLE, &cgrp->flags);
+        if (val)
+                set_bit(CGRP_NOTIFY_ON_RELEASE, &cgrp->flags);
+        else
+                clear_bit(CGRP_NOTIFY_ON_RELEASE, &cgrp->flags);
+        return 0;
+}
+
 /*
  * for the common functions, 'private' gives the type of file
  */
@@ -2234,8 +2268,7 @@ static struct cftype files[] = {
         {
                 .name = "tasks",
                 .open = cgroup_tasks_open,
-                .read = cgroup_tasks_read,
-                .write = cgroup_common_file_write,
+                .write_u64 = cgroup_tasks_write,
                 .release = cgroup_tasks_release,
                 .private = FILE_TASKLIST,
         },
@@ -2243,15 +2276,16 @@ static struct cftype files[] = {
         {
                 .name = "notify_on_release",
                 .read_u64 = cgroup_read_notify_on_release,
-                .write = cgroup_common_file_write,
+                .write_u64 = cgroup_write_notify_on_release,
                 .private = FILE_NOTIFY_ON_RELEASE,
         },
 };
 
 static struct cftype cft_release_agent = {
         .name = "release_agent",
-        .read = cgroup_common_file_read,
-        .write = cgroup_common_file_write,
+        .read_seq_string = cgroup_release_agent_show,
+        .write_string = cgroup_release_agent_write,
+        .max_write_len = PATH_MAX,
         .private = FILE_RELEASE_AGENT,
 };
 
@@ -2323,10 +2357,7 @@ 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;
@@ -2391,7 +2422,7 @@ static int cgroup_mkdir(struct inode *dir, struct dentry *dentry, int mode)
         return cgroup_create(c_parent, dentry, mode | S_IFDIR);
 }
 
-static inline int cgroup_has_css_refs(struct cgroup *cgrp)
+static int cgroup_has_css_refs(struct cgroup *cgrp)
 {
         /* Check the reference count on each subsystem. Since we
          * already established that there are no tasks in the
@@ -2518,8 +2549,7 @@ 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);
@@ -2758,21 +2788,24 @@ 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);
                 }
         }
 }
@@ -2869,16 +2902,17 @@ void cgroup_exit(struct task_struct *tsk, int run_callbacks)
  * cgroup_clone - clone the cgroup the given subsystem is attached to
  * @tsk: the task to be moved
  * @subsys: the given subsystem
+ * @nodename: the name for the new cgroup
  *
  * Duplicate the current cgroup in the hierarchy that the given
  * subsystem is attached to, and move this task into the new
  * child.
  */
-int cgroup_clone(struct task_struct *tsk, struct cgroup_subsys *subsys)
+int cgroup_clone(struct task_struct *tsk, struct cgroup_subsys *subsys,
+                                                        char *nodename)
 {
         struct dentry *dentry;
         int ret = 0;
-        char nodename[MAX_CGROUP_TYPE_NAMELEN];
         struct cgroup *parent, *child;
         struct inode *inode;
         struct css_set *cg;
@@ -2903,8 +2937,6 @@ int cgroup_clone(struct task_struct *tsk, struct cgroup_subsys *subsys)
         cg = tsk->cgroups;
         parent = task_cgroup(tsk, subsys->subsys_id);
 
-        snprintf(nodename, MAX_CGROUP_TYPE_NAMELEN, "%d", tsk->pid);
-
         /* Pin the hierarchy */
         atomic_inc(&parent->root->sb->s_active);
 
@@ -3078,27 +3110,24 @@ static void cgroup_release_agent(struct work_struct *work)
         while (!list_empty(&release_list)) {
                 char *argv[3], *envp[3];
                 int i;
-                char *pathbuf;
+                char *pathbuf = NULL, *agentbuf = NULL;
                 struct cgroup *cgrp = list_entry(release_list.next,
                                                     struct cgroup,
                                                     release_list);
                 list_del_init(&cgrp->release_list);
                 spin_unlock(&release_list_lock);
                 pathbuf = kmalloc(PAGE_SIZE, GFP_KERNEL);
-                if (!pathbuf) {
-                        spin_lock(&release_list_lock);
-                        continue;
-                }
-
-                if (cgroup_path(cgrp, pathbuf, PAGE_SIZE) < 0) {
-                        kfree(pathbuf);
-                        spin_lock(&release_list_lock);
-                        continue;
-                }
+                if (!pathbuf)
+                        goto continue_free;
+                if (cgroup_path(cgrp, pathbuf, PAGE_SIZE) < 0)
+                        goto continue_free;
+                agentbuf = kstrdup(cgrp->root->release_agent_path, GFP_KERNEL);
+                if (!agentbuf)
+                        goto continue_free;
 
                 i = 0;
-                argv[i++] = cgrp->root->release_agent_path;
-                argv[i++] = (char *)pathbuf;
+                argv[i++] = agentbuf;
+                argv[i++] = pathbuf;
                 argv[i] = NULL;
 
                 i = 0;
@@ -3112,8 +3141,10 @@ static void cgroup_release_agent(struct work_struct *work)
                  * be a slow process */
                 mutex_unlock(&cgroup_mutex);
                 call_usermodehelper(argv[0], argv, envp, UMH_WAIT_EXEC);
-                kfree(pathbuf);
                 mutex_lock(&cgroup_mutex);
+ continue_free:
+                kfree(pathbuf);
+                kfree(agentbuf);
                 spin_lock(&release_list_lock);
         }
         spin_unlock(&release_list_lock);
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..e95056954498
--- /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;
+        int retval;
+
+        /* Anything frozen can't move or be moved to/from */
+
+        if (is_task_frozen_enough(task))
+                return -EBUSY;
+
+        freezer = cgroup_freezer(new_cgroup);
+        if (freezer->state == CGROUP_FROZEN)
+                return -EBUSY;
+
+        retval = 0;
+        task_lock(task);
+        freezer = task_freezer(task);
+        if (freezer->state == CGROUP_FROZEN)
+                retval = -EBUSY;
+        task_unlock(task);
+        return retval;
+}
+
+static void freezer_fork(struct cgroup_subsys *ss, struct task_struct *task)
+{
+        struct freezer *freezer;
+
+        task_lock(task);
+        freezer = task_freezer(task);
+        task_unlock(task);
+
+        BUG_ON(freezer->state == CGROUP_FROZEN);
+        spin_lock_irq(&freezer->lock);
+        /* 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 int 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))) {
+                int do_wake;
+
+                task_lock(task);
+                do_wake = __thaw_process(task);
+                task_unlock(task);
+                if (do_wake)
+                        wake_up_process(task);
+        }
+        cgroup_iter_end(cgroup, &it);
+        freezer->state = CGROUP_THAWED;
+
+        return 0;
+}
+
+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 (freezer->state) {
+        case CGROUP_THAWED:
+                retval = try_to_freeze_cgroup(cgroup, freezer);
+                break;
+        case CGROUP_FREEZING:
+                if (goal_state == CGROUP_FROZEN) {
+                        /* Userspace is retrying after
+                         * "/bin/echo FROZEN > freezer.state" returned -EBUSY */
+                        retval = try_to_freeze_cgroup(cgroup, freezer);
+                        break;
+                }
+                /* state == FREEZING and goal_state == THAWED, so unfreeze */
+        case CGROUP_FROZEN:
+                retval = unfreeze_cgroup(cgroup, freezer);
+                break;
+        default:
+                break;
+        }
+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 -EIO;
+
+        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)
+{
+        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 cfb1d43ab801..86d49045daed 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -64,6 +64,8 @@ void __init cpu_hotplug_init(void)
         cpu_hotplug.refcount = 0;
 }
 
+cpumask_t cpu_active_map;
+
 #ifdef CONFIG_HOTPLUG_CPU
 
 void get_online_cpus(void)
@@ -197,13 +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();
@@ -214,7 +217,6 @@ static int __ref take_cpu_down(void *_param)
 static int __ref _cpu_down(unsigned int cpu, int tasks_frozen)
 {
         int err, nr_calls = 0;
-        struct task_struct *p;
         cpumask_t old_allowed, tmp;
         void *hcpu = (void *)(long)cpu;
         unsigned long mod = tasks_frozen ? CPU_TASKS_FROZEN : 0;
@@ -247,21 +249,18 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen)
         cpus_setall(tmp);
         cpu_clear(cpu, tmp);
         set_cpus_allowed_ptr(current, &tmp);
+        tmp = cpumask_of_cpu(cpu);
 
-        p = __stop_machine_run(take_cpu_down, &tcd_param, cpu);
-
-        if (IS_ERR(p) || cpu_online(cpu)) {
+        err = __stop_machine(take_cpu_down, &tcd_param, &tmp);
+        if (err) {
                 /* CPU didn't die: tell everyone.  Can't complain. */
                 if (raw_notifier_call_chain(&cpu_chain, CPU_DOWN_FAILED | mod,
                                             hcpu) == NOTIFY_BAD)
                         BUG();
 
-                if (IS_ERR(p)) {
-                        err = PTR_ERR(p);
-                        goto out_allowed;
-                }
-                goto out_thread;
+                goto out_allowed;
         }
+        BUG_ON(cpu_online(cpu));
 
         /* Wait for it to sleep (leaving idle task). */
         while (!idle_cpu(cpu))
@@ -277,12 +276,15 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen)
 
         check_for_tasks(cpu);
 
-out_thread:
-        err = kthread_stop(p);
 out_allowed:
         set_cpus_allowed_ptr(current, &old_allowed);
 out_release:
         cpu_hotplug_done();
+        if (!err) {
+                if (raw_notifier_call_chain(&cpu_chain, CPU_POST_DEAD | mod,
+                                            hcpu) == NOTIFY_BAD)
+                        BUG();
+        }
         return err;
 }
 
@@ -291,11 +293,30 @@ int __ref cpu_down(unsigned int cpu)
         int err = 0;
 
         cpu_maps_update_begin();
-        if (cpu_hotplug_disabled)
+
+        if (cpu_hotplug_disabled) {
                 err = -EBUSY;
-        else
-                err = _cpu_down(cpu, 0);
+                goto out;
+        }
 
+        cpu_clear(cpu, cpu_active_map);
+
+        /*
+         * Make sure the all cpus did the reschedule and are not
+         * using stale version of the cpu_active_map.
+         * This is not strictly necessary becuase stop_machine()
+         * that we run down the line already provides the required
+         * synchronization. But it's really a side effect and we do not
+         * want to depend on the innards of the stop_machine here.
+         */
+        synchronize_sched();
+
+        err = _cpu_down(cpu, 0);
+
+        if (cpu_online(cpu))
+                cpu_set(cpu, cpu_active_map);
+
+out:
         cpu_maps_update_done();
         return err;
 }
@@ -329,6 +350,8 @@ static int __cpuinit _cpu_up(unsigned int cpu, int tasks_frozen)
                 goto out_notify;
         BUG_ON(!cpu_online(cpu));
 
+        cpu_set(cpu, cpu_active_map);
+
         /* Now call notifier in preparation. */
         raw_notifier_call_chain(&cpu_chain, CPU_ONLINE | mod, hcpu);
 
@@ -347,7 +370,7 @@ int __cpuinit cpu_up(unsigned int cpu)
         if (!cpu_isset(cpu, cpu_possible_map)) {
                 printk(KERN_ERR "can't online cpu %d because it is not "
                         "configured as may-hotadd at boot time\n", cpu);
-#if defined(CONFIG_IA64) || defined(CONFIG_X86_64) || defined(CONFIG_S390)
+#if defined(CONFIG_IA64) || defined(CONFIG_X86_64)
                 printk(KERN_ERR "please check additional_cpus= boot "
                                 "parameter\n");
 #endif
@@ -355,11 +378,15 @@ int __cpuinit cpu_up(unsigned int cpu)
         }
 
         cpu_maps_update_begin();
-        if (cpu_hotplug_disabled)
+
+        if (cpu_hotplug_disabled) {
                 err = -EBUSY;
-        else
-                err = _cpu_up(cpu, 0);
+                goto out;
+        }
 
+        err = _cpu_up(cpu, 0);
+
+out:
         cpu_maps_update_done();
         return err;
 }
@@ -413,7 +440,7 @@ void __ref enable_nonboot_cpus(void)
                 goto out;
 
         printk("Enabling non-boot CPUs ...\n");
-        for_each_cpu_mask(cpu, frozen_cpus) {
+        for_each_cpu_mask_nr(cpu, frozen_cpus) {
                 error = _cpu_up(cpu, 1);
                 if (!error) {
                         printk("CPU%d is up\n", cpu);
@@ -427,4 +454,48 @@ 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 */
+
+/*
+ * cpu_bit_bitmap[] is a special, "compressed" data structure that
+ * represents all NR_CPUS bits binary values of 1<<nr.
+ *
+ * It is used by cpumask_of_cpu() to get a constant address to a CPU
+ * mask value that has a single bit set only.
+ */
+
+/* cpu_bit_bitmap[0] is empty - so we can back into it */
+#define MASK_DECLARE_1(x)       [x+1][0] = 1UL << (x)
+#define MASK_DECLARE_2(x)       MASK_DECLARE_1(x), MASK_DECLARE_1(x+1)
+#define MASK_DECLARE_4(x)       MASK_DECLARE_2(x), MASK_DECLARE_2(x+2)
+#define MASK_DECLARE_8(x)       MASK_DECLARE_4(x), MASK_DECLARE_4(x+4)
+
+const unsigned long cpu_bit_bitmap[BITS_PER_LONG+1][BITS_TO_LONGS(NR_CPUS)] = {
+
+        MASK_DECLARE_8(0),      MASK_DECLARE_8(8),
+        MASK_DECLARE_8(16),     MASK_DECLARE_8(24),
+#if BITS_PER_LONG > 32
+        MASK_DECLARE_8(32),     MASK_DECLARE_8(40),
+        MASK_DECLARE_8(48),     MASK_DECLARE_8(56),
+#endif
+};
+EXPORT_SYMBOL_GPL(cpu_bit_bitmap);
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 459d601947a8..3e00526f52ec 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -14,6 +14,8 @@
  *  2003-10-22 Updates by Stephen Hemminger.
  *  2004 May-July Rework by Paul Jackson.
  *  2006 Rework by Paul Menage to use generic cgroups
+ *  2008 Rework of the scheduler domains and CPU hotplug handling
+ *       by Max Krasnyansky
  *
  *  This file is subject to the terms and conditions of the GNU General Public
  *  License.  See the file COPYING in the main directory of the Linux
@@ -54,7 +56,6 @@
 #include <asm/uaccess.h>
 #include <asm/atomic.h>
 #include <linux/mutex.h>
-#include <linux/kfifo.h>
 #include <linux/workqueue.h>
 #include <linux/cgroup.h>
 
@@ -227,10 +228,6 @@ static struct cpuset top_cpuset = {
  * The task_struct fields mems_allowed and mems_generation may only
  * be accessed in the context of that task, so require no locks.
  *
- * The cpuset_common_file_write handler for operations that modify
- * the cpuset hierarchy holds cgroup_mutex across the entire operation,
- * single threading all such cpuset modifications across the system.
- *
  * The cpuset_common_file_read() handlers only hold callback_mutex across
  * small pieces of code, such as when reading out possibly multi-word
  * cpumasks and nodemasks.
@@ -241,9 +238,11 @@ static struct cpuset top_cpuset = {
 
 static DEFINE_MUTEX(callback_mutex);
 
-/* This is ugly, but preserves the userspace API for existing cpuset
+/*
+ * This is ugly, but preserves the userspace API for existing cpuset
  * users. If someone tries to mount the "cpuset" filesystem, we
- * silently switch it to mount "cgroup" instead */
+ * silently switch it to mount "cgroup" instead
+ */
 static int cpuset_get_sb(struct file_system_type *fs_type,
                          int flags, const char *unused_dev_name,
                          void *data, struct vfsmount *mnt)
@@ -369,7 +368,7 @@ void cpuset_update_task_memory_state(void)
                 my_cpusets_mem_gen = top_cpuset.mems_generation;
         } else {
                 rcu_read_lock();
-                my_cpusets_mem_gen = task_cs(current)->mems_generation;
+                my_cpusets_mem_gen = task_cs(tsk)->mems_generation;
                 rcu_read_unlock();
         }
 
@@ -478,10 +477,9 @@ static int validate_change(const struct cpuset *cur, const struct cpuset *trial)
 }
 
 /*
- * Helper routine for rebuild_sched_domains().
+ * Helper routine for generate_sched_domains().
  * Do cpusets a, b have overlapping cpus_allowed masks?
  */
-
 static int cpusets_overlap(struct cpuset *a, struct cpuset *b)
 {
         return cpus_intersects(a->cpus_allowed, b->cpus_allowed);
@@ -490,29 +488,48 @@ static int cpusets_overlap(struct cpuset *a, struct cpuset *b)
 static void
 update_domain_attr(struct sched_domain_attr *dattr, struct cpuset *c)
 {
-        if (!dattr)
-                return;
         if (dattr->relax_domain_level < c->relax_domain_level)
                 dattr->relax_domain_level = c->relax_domain_level;
         return;
 }
 
+static void
+update_domain_attr_tree(struct sched_domain_attr *dattr, struct cpuset *c)
+{
+        LIST_HEAD(q);
+
+        list_add(&c->stack_list, &q);
+        while (!list_empty(&q)) {
+                struct cpuset *cp;
+                struct cgroup *cont;
+                struct cpuset *child;
+
+                cp = list_first_entry(&q, struct cpuset, stack_list);
+                list_del(q.next);
+
+                if (cpus_empty(cp->cpus_allowed))
+                        continue;
+
+                if (is_sched_load_balance(cp))
+                        update_domain_attr(dattr, cp);
+
+                list_for_each_entry(cont, &cp->css.cgroup->children, sibling) {
+                        child = cgroup_cs(cont);
+                        list_add_tail(&child->stack_list, &q);
+                }
+        }
+}
+
 /*
- * rebuild_sched_domains()
+ * generate_sched_domains()
  *
- * If the flag 'sched_load_balance' of any cpuset with non-empty
- * 'cpus' changes, or if the 'cpus' allowed changes in any cpuset
- * which has that flag enabled, or if any cpuset with a non-empty
- * 'cpus' is removed, then call this routine to rebuild the
- * scheduler's dynamic sched domains.
- *
- * This routine builds a partial partition of the systems CPUs
- * (the set of non-overlappping cpumask_t's in the array 'part'
- * below), and passes that partial partition to the kernel/sched.c
- * partition_sched_domains() routine, which will rebuild the
- * schedulers load balancing domains (sched domains) as specified
- * by that partial partition.  A 'partial partition' is a set of
- * non-overlapping subsets whose union is a subset of that set.
+ * This function builds a partial partition of the systems CPUs
+ * A 'partial partition' is a set of non-overlapping subsets whose
+ * union is a subset of that set.
+ * The output of this function needs to be passed to kernel/sched.c
+ * partition_sched_domains() routine, which will rebuild the scheduler's
+ * load balancing domains (sched domains) as specified by that partial
+ * partition.
  *
  * See "What is sched_load_balance" in Documentation/cpusets.txt
  * for a background explanation of this.
@@ -522,16 +539,10 @@ update_domain_attr(struct sched_domain_attr *dattr, struct cpuset *c)
  * domains when operating in the severe memory shortage situations
  * that could cause allocation failures below.
  *
- * Call with cgroup_mutex held.  May take callback_mutex during
- * call due to the kfifo_alloc() and kmalloc() calls.  May nest
- * a call to the get_online_cpus()/put_online_cpus() pair.
- * Must not be called holding callback_mutex, because we must not
- * call get_online_cpus() while holding callback_mutex.  Elsewhere
- * the kernel nests callback_mutex inside get_online_cpus() calls.
- * So the reverse nesting would risk an ABBA deadlock.
+ * Must be called with cgroup_lock held.
  *
  * The three key local variables below are:
- *    q  - a kfifo queue of cpuset pointers, used to implement a
+ *    q  - a linked-list queue of cpuset pointers, used to implement a
  *         top-down scan of all cpusets.  This scan loads a pointer
  *         to each cpuset marked is_sched_load_balance into the
  *         array 'csa'.  For our purposes, rebuilding the schedulers
@@ -563,10 +574,10 @@ update_domain_attr(struct sched_domain_attr *dattr, struct cpuset *c)
  *      element of the partition (one sched domain) to be passed to
  *      partition_sched_domains().
  */
-
-static void rebuild_sched_domains(void)
+static int generate_sched_domains(cpumask_t **domains,
+                        struct sched_domain_attr **attributes)
 {
-        struct kfifo *q;        /* queue of cpusets to be scanned */
+        LIST_HEAD(q);           /* queue of cpusets to be scanned */
         struct cpuset *cp;      /* scans q */
         struct cpuset **csa;    /* array of all cpuset ptrs */
         int csn;                /* how many cpuset ptrs in csa so far */
@@ -576,44 +587,58 @@ static void rebuild_sched_domains(void)
         int ndoms;              /* number of sched domains in result */
         int nslot;              /* next empty doms[] cpumask_t slot */
 
-        q = NULL;
-        csa = NULL;
+        ndoms = 0;
         doms = NULL;
         dattr = NULL;
+        csa = NULL;
 
         /* Special case for the 99% of systems with one, full, sched domain */
         if (is_sched_load_balance(&top_cpuset)) {
-                ndoms = 1;
                 doms = kmalloc(sizeof(cpumask_t), GFP_KERNEL);
                 if (!doms)
-                        goto rebuild;
+                        goto done;
+
                 dattr = kmalloc(sizeof(struct sched_domain_attr), GFP_KERNEL);
                 if (dattr) {
                         *dattr = SD_ATTR_INIT;
-                        update_domain_attr(dattr, &top_cpuset);
+                        update_domain_attr_tree(dattr, &top_cpuset);
                 }
                 *doms = top_cpuset.cpus_allowed;
-                goto rebuild;
-        }
 
-        q = kfifo_alloc(number_of_cpusets * sizeof(cp), GFP_KERNEL, NULL);
-        if (IS_ERR(q))
+                ndoms = 1;
                 goto done;
+        }
+
         csa = kmalloc(number_of_cpusets * sizeof(cp), GFP_KERNEL);
         if (!csa)
                 goto done;
         csn = 0;
 
-        cp = &top_cpuset;
-        __kfifo_put(q, (void *)&cp, sizeof(cp));
-        while (__kfifo_get(q, (void *)&cp, sizeof(cp))) {
+        list_add(&top_cpuset.stack_list, &q);
+        while (!list_empty(&q)) {
                 struct cgroup *cont;
                 struct cpuset *child;   /* scans child cpusets of cp */
-                if (is_sched_load_balance(cp))
+
+                cp = list_first_entry(&q, struct cpuset, stack_list);
+                list_del(q.next);
+
+                if (cpus_empty(cp->cpus_allowed))
+                        continue;
+
+                /*
+                 * All child cpusets contain a subset of the parent's cpus, so
+                 * just skip them, and then we call update_domain_attr_tree()
+                 * to calc relax_domain_level of the corresponding sched
+                 * domain.
+                 */
+                if (is_sched_load_balance(cp)) {
                         csa[csn++] = cp;
+                        continue;
+                }
+
                 list_for_each_entry(cont, &cp->css.cgroup->children, sibling) {
                         child = cgroup_cs(cont);
-                        __kfifo_put(q, (void *)&child, sizeof(cp));
+                        list_add_tail(&child->stack_list, &q);
                 }
         }
 
@@ -644,91 +669,141 @@ restart:
                 }
         }
 
-        /* Convert <csn, csa> to <ndoms, doms> */
+        /*
+         * Now we know how many domains to create.
+         * Convert <csn, csa> to <ndoms, doms> and populate cpu masks.
+         */
         doms = kmalloc(ndoms * sizeof(cpumask_t), GFP_KERNEL);
-        if (!doms)
-                goto rebuild;
+        if (!doms) {
+                ndoms = 0;
+                goto done;
+        }
+
+        /*
+         * The rest of the code, including the scheduler, can deal with
+         * dattr==NULL case. No need to abort if alloc fails.
+         */
         dattr = kmalloc(ndoms * sizeof(struct sched_domain_attr), GFP_KERNEL);
 
         for (nslot = 0, i = 0; i < csn; i++) {
                 struct cpuset *a = csa[i];
+                cpumask_t *dp;
                 int apn = a->pn;
 
-                if (apn >= 0) {
-                        cpumask_t *dp = doms + nslot;
-
-                        if (nslot == ndoms) {
-                                static int warnings = 10;
-                                if (warnings) {
-                                        printk(KERN_WARNING
-                                         "rebuild_sched_domains confused:"
-                                          " nslot %d, ndoms %d, csn %d, i %d,"
-                                          " apn %d\n",
-                                          nslot, ndoms, csn, i, apn);
-                                        warnings--;
-                                }
-                                continue;
+                if (apn < 0) {
+                        /* Skip completed partitions */
+                        continue;
+                }
+
+                dp = doms + nslot;
+
+                if (nslot == ndoms) {
+                        static int warnings = 10;
+                        if (warnings) {
+                                printk(KERN_WARNING
+                                 "rebuild_sched_domains confused:"
+                                  " nslot %d, ndoms %d, csn %d, i %d,"
+                                  " apn %d\n",
+                                  nslot, ndoms, csn, i, apn);
+                                warnings--;
                         }
+                        continue;
+                }
 
-                        cpus_clear(*dp);
-                        if (dattr)
-                                *(dattr + nslot) = SD_ATTR_INIT;
-                        for (j = i; j < csn; j++) {
-                                struct cpuset *b = csa[j];
+                cpus_clear(*dp);
+                if (dattr)
+                        *(dattr + nslot) = SD_ATTR_INIT;
+                for (j = i; j < csn; j++) {
+                        struct cpuset *b = csa[j];
 
-                                if (apn == b->pn) {
-                                        cpus_or(*dp, *dp, b->cpus_allowed);
-                                        b->pn = -1;
-                                        update_domain_attr(dattr, b);
-                                }
+                        if (apn == b->pn) {
+                                cpus_or(*dp, *dp, b->cpus_allowed);
+                                if (dattr)
+                                        update_domain_attr_tree(dattr + nslot, b);
+
+                                /* Done with this partition */
+                                b->pn = -1;
                         }
-                        nslot++;
                 }
+                nslot++;
         }
         BUG_ON(nslot != ndoms);
 
-rebuild:
-        /* Have scheduler rebuild sched domains */
-        get_online_cpus();
-        partition_sched_domains(ndoms, doms, dattr);
-        put_online_cpus();
-
 done:
-        if (q && !IS_ERR(q))
-                kfifo_free(q);
         kfree(csa);
-        /* Don't kfree(doms) -- partition_sched_domains() does that. */
-        /* Don't kfree(dattr) -- partition_sched_domains() does that. */
+
+        *domains    = doms;
+        *attributes = dattr;
+        return ndoms;
 }
 
-static inline int started_after_time(struct task_struct *t1,
-                                     struct timespec *time,
-                                     struct task_struct *t2)
+/*
+ * Rebuild scheduler domains.
+ *
+ * Call with neither cgroup_mutex held nor within get_online_cpus().
+ * Takes both cgroup_mutex and get_online_cpus().
+ *
+ * Cannot be directly called from cpuset code handling changes
+ * to the cpuset pseudo-filesystem, because it cannot be called
+ * from code that already holds cgroup_mutex.
+ */
+static void do_rebuild_sched_domains(struct work_struct *unused)
 {
-        int start_diff = timespec_compare(&t1->start_time, time);
-        if (start_diff > 0) {
-                return 1;
-        } else if (start_diff < 0) {
-                return 0;
-        } else {
-                /*
-                 * Arbitrarily, if two processes started at the same
-                 * time, we'll say that the lower pointer value
-                 * started first. Note that t2 may have exited by now
-                 * so this may not be a valid pointer any longer, but
-                 * that's fine - it still serves to distinguish
-                 * between two tasks started (effectively)
-                 * simultaneously.
-                 */
-                return t1 > t2;
-        }
+        struct sched_domain_attr *attr;
+        cpumask_t *doms;
+        int ndoms;
+
+        get_online_cpus();
+
+        /* Generate domain masks and attrs */
+        cgroup_lock();
+        ndoms = generate_sched_domains(&doms, &attr);
+        cgroup_unlock();
+
+        /* Have scheduler rebuild the domains */
+        partition_sched_domains(ndoms, doms, attr);
+
+        put_online_cpus();
+}
+
+static DECLARE_WORK(rebuild_sched_domains_work, do_rebuild_sched_domains);
+
+/*
+ * Rebuild scheduler domains, asynchronously via workqueue.
+ *
+ * If the flag 'sched_load_balance' of any cpuset with non-empty
+ * 'cpus' changes, or if the 'cpus' allowed changes in any cpuset
+ * which has that flag enabled, or if any cpuset with a non-empty
+ * 'cpus' is removed, then call this routine to rebuild the
+ * scheduler's dynamic sched domains.
+ *
+ * The rebuild_sched_domains() and partition_sched_domains()
+ * routines must nest cgroup_lock() inside get_online_cpus(),
+ * but such cpuset changes as these must nest that locking the
+ * other way, holding cgroup_lock() for much of the code.
+ *
+ * So in order to avoid an ABBA deadlock, the cpuset code handling
+ * these user changes delegates the actual sched domain rebuilding
+ * to a separate workqueue thread, which ends up processing the
+ * above do_rebuild_sched_domains() function.
+ */
+static void async_rebuild_sched_domains(void)
+{
+        schedule_work(&rebuild_sched_domains_work);
 }
 
-static inline int started_after(void *p1, void *p2)
+/*
+ * Accomplishes the same scheduler domain rebuild as the above
+ * async_rebuild_sched_domains(), however it directly calls the
+ * rebuild routine synchronously rather than calling it via an
+ * asynchronous work thread.
+ *
+ * This can only be called from code that is not holding
+ * cgroup_mutex (not nested in a cgroup_lock() call.)
+ */
+void rebuild_sched_domains(void)
 {
-        struct task_struct *t1 = p1;
-        struct task_struct *t2 = p2;
-        return started_after_time(t1, &t2->start_time, t2);
+        do_rebuild_sched_domains(NULL);
 }
 
 /**
@@ -766,15 +841,38 @@ 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.
+ *
+ * No return value. It's guaranteed that cgroup_scan_tasks() always returns 0
+ * if @heap != NULL.
+ */
+static void update_tasks_cpumask(struct cpuset *cs, struct ptr_heap *heap)
+{
+        struct cgroup_scanner scan;
+
+        scan.cg = cs->css.cgroup;
+        scan.test_task = cpuset_test_cpumask;
+        scan.process_task = cpuset_change_cpumask;
+        scan.heap = heap;
+        cgroup_scan_tasks(&scan);
+}
+
+/**
  * update_cpumask - update the cpus_allowed mask of a cpuset and all tasks in it
  * @cs: the cpuset to consider
  * @buf: buffer of cpu numbers written to this cpuset
  */
-static int update_cpumask(struct cpuset *cs, char *buf)
+static int update_cpumask(struct cpuset *cs, const char *buf)
 {
-        struct cpuset trialcs;
-        struct cgroup_scanner scan;
         struct ptr_heap heap;
+        struct cpuset trialcs;
         int retval;
         int is_load_balanced;
 
@@ -790,7 +888,6 @@ static int update_cpumask(struct cpuset *cs, char *buf)
          * that parsing.  The validate_change() call ensures that cpusets
          * with tasks have cpus.
          */
-        buf = strstrip(buf);
         if (!*buf) {
                 cpus_clear(trialcs.cpus_allowed);
         } else {
@@ -809,7 +906,7 @@ static int update_cpumask(struct cpuset *cs, char *buf)
         if (cpus_equal(cs->cpus_allowed, trialcs.cpus_allowed))
                 return 0;
 
-        retval = heap_init(&heap, PAGE_SIZE, GFP_KERNEL, &started_after);
+        retval = heap_init(&heap, PAGE_SIZE, GFP_KERNEL, NULL);
         if (retval)
                 return retval;
 
@@ -823,15 +920,12 @@ static int update_cpumask(struct cpuset *cs, char *buf)
          * Scan tasks in the cpuset, and update the cpumasks of any
          * that need an update.
          */
-        scan.cg = cs->css.cgroup;
-        scan.test_task = cpuset_test_cpumask;
-        scan.process_task = cpuset_change_cpumask;
-        scan.heap = &heap;
-        cgroup_scan_tasks(&scan);
+        update_tasks_cpumask(cs, &heap);
+
         heap_free(&heap);
 
         if (is_load_balanced)
-                rebuild_sched_domains();
+                async_rebuild_sched_domains();
         return 0;
 }
 
@@ -884,74 +978,25 @@ static void cpuset_migrate_mm(struct mm_struct *mm, const nodemask_t *from,
         mutex_unlock(&callback_mutex);
 }
 
-/*
- * Handle user request to change the 'mems' memory placement
- * of a cpuset.  Needs to validate the request, update the
- * cpusets mems_allowed and mems_generation, and for each
- * task in the cpuset, rebind any vma mempolicies and if
- * the cpuset is marked 'memory_migrate', migrate the tasks
- * pages to the new memory.
- *
- * Call with cgroup_mutex held.  May take callback_mutex during call.
- * Will take tasklist_lock, scan tasklist for tasks in cpuset cs,
- * lock each such tasks mm->mmap_sem, scan its vma's and rebind
- * their mempolicies to the cpusets new mems_allowed.
- */
-
 static void *cpuset_being_rebound;
 
-static int update_nodemask(struct cpuset *cs, char *buf)
+/**
+ * update_tasks_nodemask - Update the nodemasks of tasks in the cpuset.
+ * @cs: the cpuset in which each task's mems_allowed mask needs to be changed
+ * @oldmem: old mems_allowed of cpuset cs
+ *
+ * Called with cgroup_mutex held
+ * Return 0 if successful, -errno if not.
+ */
+static int update_tasks_nodemask(struct cpuset *cs, const nodemask_t *oldmem)
 {
-        struct cpuset trialcs;
-        nodemask_t oldmem;
         struct task_struct *p;
         struct mm_struct **mmarray;
         int i, n, ntasks;
         int migrate;
         int fudge;
-        int retval;
         struct cgroup_iter it;
-
-        /*
-         * top_cpuset.mems_allowed tracks node_stats[N_HIGH_MEMORY];
-         * it's read-only
-         */
-        if (cs == &top_cpuset)
-                return -EACCES;
-
-        trialcs = *cs;
-
-        /*
-         * An empty mems_allowed is ok iff there are no tasks in the cpuset.
-         * Since nodelist_parse() fails on an empty mask, we special case
-         * that parsing.  The validate_change() call ensures that cpusets
-         * with tasks have memory.
-         */
-        buf = strstrip(buf);
-        if (!*buf) {
-                nodes_clear(trialcs.mems_allowed);
-        } else {
-                retval = nodelist_parse(buf, trialcs.mems_allowed);
-                if (retval < 0)
-                        goto done;
-
-                if (!nodes_subset(trialcs.mems_allowed,
-                                node_states[N_HIGH_MEMORY]))
-                        return -EINVAL;
-        }
-        oldmem = cs->mems_allowed;
-        if (nodes_equal(oldmem, trialcs.mems_allowed)) {
-                retval = 0;             /* Too easy - nothing to do */
-                goto done;
-        }
-        retval = validate_change(cs, &trialcs);
-        if (retval < 0)
-                goto done;
-
-        mutex_lock(&callback_mutex);
-        cs->mems_allowed = trialcs.mems_allowed;
-        cs->mems_generation = cpuset_mems_generation++;
-        mutex_unlock(&callback_mutex);
+        int retval;
 
         cpuset_being_rebound = cs;              /* causes mpol_dup() rebind */
 
@@ -1018,7 +1063,7 @@ static int update_nodemask(struct cpuset *cs, char *buf)
 
                 mpol_rebind_mm(mm, &cs->mems_allowed);
                 if (migrate)
-                        cpuset_migrate_mm(mm, &oldmem, &cs->mems_allowed);
+                        cpuset_migrate_mm(mm, oldmem, &cs->mems_allowed);
                 mmput(mm);
         }
 
@@ -1030,6 +1075,70 @@ done:
         return retval;
 }
 
+/*
+ * Handle user request to change the 'mems' memory placement
+ * of a cpuset.  Needs to validate the request, update the
+ * cpusets mems_allowed and mems_generation, and for each
+ * task in the cpuset, rebind any vma mempolicies and if
+ * the cpuset is marked 'memory_migrate', migrate the tasks
+ * pages to the new memory.
+ *
+ * Call with cgroup_mutex held.  May take callback_mutex during call.
+ * Will take tasklist_lock, scan tasklist for tasks in cpuset cs,
+ * lock each such tasks mm->mmap_sem, scan its vma's and rebind
+ * their mempolicies to the cpusets new mems_allowed.
+ */
+static int update_nodemask(struct cpuset *cs, const char *buf)
+{
+        struct cpuset trialcs;
+        nodemask_t oldmem;
+        int retval;
+
+        /*
+         * top_cpuset.mems_allowed tracks node_stats[N_HIGH_MEMORY];
+         * it's read-only
+         */
+        if (cs == &top_cpuset)
+                return -EACCES;
+
+        trialcs = *cs;
+
+        /*
+         * An empty mems_allowed is ok iff there are no tasks in the cpuset.
+         * Since nodelist_parse() fails on an empty mask, we special case
+         * that parsing.  The validate_change() call ensures that cpusets
+         * with tasks have memory.
+         */
+        if (!*buf) {
+                nodes_clear(trialcs.mems_allowed);
+        } else {
+                retval = nodelist_parse(buf, trialcs.mems_allowed);
+                if (retval < 0)
+                        goto done;
+
+                if (!nodes_subset(trialcs.mems_allowed,
+                                node_states[N_HIGH_MEMORY]))
+                        return -EINVAL;
+        }
+        oldmem = cs->mems_allowed;
+        if (nodes_equal(oldmem, trialcs.mems_allowed)) {
+                retval = 0;             /* Too easy - nothing to do */
+                goto done;
+        }
+        retval = validate_change(cs, &trialcs);
+        if (retval < 0)
+                goto done;
+
+        mutex_lock(&callback_mutex);
+        cs->mems_allowed = trialcs.mems_allowed;
+        cs->mems_generation = cpuset_mems_generation++;
+        mutex_unlock(&callback_mutex);
+
+        retval = update_tasks_nodemask(cs, &oldmem);
+done:
+        return retval;
+}
+
 int current_cpuset_is_being_rebound(void)
 {
         return task_cs(current) == cpuset_being_rebound;
@@ -1042,7 +1151,8 @@ static int update_relax_domain_level(struct cpuset *cs, s64 val)
 
         if (val != cs->relax_domain_level) {
                 cs->relax_domain_level = val;
-                rebuild_sched_domains();
+                if (!cpus_empty(cs->cpus_allowed) && is_sched_load_balance(cs))
+                        async_rebuild_sched_domains();
         }
 
         return 0;
@@ -1062,7 +1172,7 @@ 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)
@@ -1074,7 +1184,6 @@ 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));
 
@@ -1082,8 +1191,8 @@ 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)
-                rebuild_sched_domains();
+        if (!cpus_empty(trialcs.cpus_allowed) && balance_flag_changed)
+                async_rebuild_sched_domains();
 
         return 0;
 }
@@ -1254,72 +1363,14 @@ typedef enum {
         FILE_SPREAD_SLAB,
 } cpuset_filetype_t;
 
-static ssize_t cpuset_common_file_write(struct cgroup *cont,
-                                        struct cftype *cft,
-                                        struct file *file,
-                                        const char __user *userbuf,
-                                        size_t nbytes, loff_t *unused_ppos)
-{
-        struct cpuset *cs = cgroup_cs(cont);
-        cpuset_filetype_t type = cft->private;
-        char *buffer;
-        int retval = 0;
-
-        /* Crude upper limit on largest legitimate cpulist user might write. */
-        if (nbytes > 100U + 6 * max(NR_CPUS, MAX_NUMNODES))
-                return -E2BIG;
-
-        /* +1 for nul-terminator */
-        buffer = kmalloc(nbytes + 1, GFP_KERNEL);
-        if (!buffer)
-                return -ENOMEM;
-
-        if (copy_from_user(buffer, userbuf, nbytes)) {
-                retval = -EFAULT;
-                goto out1;
-        }
-        buffer[nbytes] = 0;     /* nul-terminate */
-
-        cgroup_lock();
-
-        if (cgroup_is_removed(cont)) {
-                retval = -ENODEV;
-                goto out2;
-        }
-
-        switch (type) {
-        case FILE_CPULIST:
-                retval = update_cpumask(cs, buffer);
-                break;
-        case FILE_MEMLIST:
-                retval = update_nodemask(cs, buffer);
-                break;
-        default:
-                retval = -EINVAL;
-                goto out2;
-        }
-
-        if (retval == 0)
-                retval = nbytes;
-out2:
-        cgroup_unlock();
-out1:
-        kfree(buffer);
-        return retval;
-}
-
 static int cpuset_write_u64(struct cgroup *cgrp, struct cftype *cft, u64 val)
 {
         int retval = 0;
         struct cpuset *cs = cgroup_cs(cgrp);
         cpuset_filetype_t type = cft->private;
 
-        cgroup_lock();
-
-        if (cgroup_is_removed(cgrp)) {
-                cgroup_unlock();
+        if (!cgroup_lock_live_group(cgrp))
                 return -ENODEV;
-        }
 
         switch (type) {
         case FILE_CPU_EXCLUSIVE:
@@ -1365,12 +1416,9 @@ static int cpuset_write_s64(struct cgroup *cgrp, struct cftype *cft, s64 val)
         struct cpuset *cs = cgroup_cs(cgrp);
         cpuset_filetype_t type = cft->private;
 
-        cgroup_lock();
-
-        if (cgroup_is_removed(cgrp)) {
-                cgroup_unlock();
+        if (!cgroup_lock_live_group(cgrp))
                 return -ENODEV;
-        }
+
         switch (type) {
         case FILE_SCHED_RELAX_DOMAIN_LEVEL:
                 retval = update_relax_domain_level(cs, val);
@@ -1384,6 +1432,32 @@ static int cpuset_write_s64(struct cgroup *cgrp, struct cftype *cft, s64 val)
 }
 
 /*
+ * Common handling for a write to a "cpus" or "mems" file.
+ */
+static int cpuset_write_resmask(struct cgroup *cgrp, struct cftype *cft,
+                                const char *buf)
+{
+        int retval = 0;
+
+        if (!cgroup_lock_live_group(cgrp))
+                return -ENODEV;
+
+        switch (cft->private) {
+        case FILE_CPULIST:
+                retval = update_cpumask(cgroup_cs(cgrp), buf);
+                break;
+        case FILE_MEMLIST:
+                retval = update_nodemask(cgroup_cs(cgrp), buf);
+                break;
+        default:
+                retval = -EINVAL;
+                break;
+        }
+        cgroup_unlock();
+        return retval;
+}
+
+/*
  * These ascii lists should be read in a single call, by using a user
  * buffer large enough to hold the entire map.  If read in smaller
  * chunks, there is no guarantee of atomicity.  Since the display format
@@ -1479,6 +1553,9 @@ static u64 cpuset_read_u64(struct cgroup *cont, struct cftype *cft)
         default:
                 BUG();
         }
+
+        /* Unreachable but makes gcc happy */
+        return 0;
 }
 
 static s64 cpuset_read_s64(struct cgroup *cont, struct cftype *cft)
@@ -1491,6 +1568,9 @@ static s64 cpuset_read_s64(struct cgroup *cont, struct cftype *cft)
         default:
                 BUG();
         }
+
+        /* Unrechable but makes gcc happy */
+        return 0;
 }
 
 
@@ -1502,14 +1582,16 @@ static struct cftype files[] = {
         {
                 .name = "cpus",
                 .read = cpuset_common_file_read,
-                .write = cpuset_common_file_write,
+                .write_string = cpuset_write_resmask,
+                .max_write_len = (100U + 6 * NR_CPUS),
                 .private = FILE_CPULIST,
         },
 
         {
                 .name = "mems",
                 .read = cpuset_common_file_read,
-                .write = cpuset_common_file_write,
+                .write_string = cpuset_write_resmask,
+                .max_write_len = (100U + 6 * MAX_NUMNODES),
                 .private = FILE_MEMLIST,
         },
 
@@ -1677,15 +1759,9 @@ static struct cgroup_subsys_state *cpuset_create(
 }
 
 /*
- * Locking note on the strange update_flag() call below:
- *
  * If the cpuset being removed has its flag 'sched_load_balance'
  * enabled, then simulate turning sched_load_balance off, which
- * will call rebuild_sched_domains().  The get_online_cpus()
- * call in rebuild_sched_domains() must not be made while holding
- * callback_mutex.  Elsewhere the kernel nests callback_mutex inside
- * get_online_cpus() calls.  So the reverse nesting would risk an
- * ABBA deadlock.
+ * will call async_rebuild_sched_domains().
  */
 
 static void cpuset_destroy(struct cgroup_subsys *ss, struct cgroup *cont)
@@ -1704,7 +1780,7 @@ static void cpuset_destroy(struct cgroup_subsys *ss, struct cgroup *cont)
 struct cgroup_subsys cpuset_subsys = {
         .name = "cpuset",
         .create = cpuset_create,
-        .destroy  = cpuset_destroy,
+        .destroy = cpuset_destroy,
         .can_attach = cpuset_can_attach,
         .attach = cpuset_attach,
         .populate = cpuset_populate,
@@ -1790,13 +1866,13 @@ static void move_member_tasks_to_cpuset(struct cpuset *from, struct cpuset *to)
         scan.scan.heap = NULL;
         scan.to = to->css.cgroup;
 
-        if (cgroup_scan_tasks((struct cgroup_scanner *)&scan))
+        if (cgroup_scan_tasks(&scan.scan))
                 printk(KERN_ERR "move_member_tasks_to_cpuset: "
                                 "cgroup_scan_tasks failed\n");
 }
 
 /*
- * If common_cpu_mem_hotplug_unplug(), below, unplugs any CPUs
+ * If CPU and/or memory hotplug handlers, below, unplug any CPUs
  * or memory nodes, we need to walk over the cpuset hierarchy,
  * removing that CPU or node from all cpusets.  If this removes the
  * last CPU or node from a cpuset, then move the tasks in the empty
@@ -1844,31 +1920,31 @@ 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 */
         struct cpuset *child;   /* scans child cpusets of cp */
-        struct list_head queue;
         struct cgroup *cont;
-
-        INIT_LIST_HEAD(&queue);
+        nodemask_t oldmems;
 
         list_add_tail((struct list_head *)&root->stack_list, &queue);
 
         while (!list_empty(&queue)) {
-                cp = container_of(queue.next, struct cpuset, stack_list);
+                cp = list_first_entry(&queue, struct cpuset, stack_list);
                 list_del(queue.next);
                 list_for_each_entry(cont, &cp->css.cgroup->children, sibling) {
                         child = cgroup_cs(cont);
                         list_add_tail(&child->stack_list, &queue);
                 }
-                cont = cp->css.cgroup;
 
                 /* Continue past cpusets with all cpus, mems online */
                 if (cpus_subset(cp->cpus_allowed, cpu_online_map) &&
                     nodes_subset(cp->mems_allowed, node_states[N_HIGH_MEMORY]))
                         continue;
 
+                oldmems = cp->mems_allowed;
+
                 /* Remove offline cpus and mems from this cpuset. */
                 mutex_lock(&callback_mutex);
                 cpus_and(cp->cpus_allowed, cp->cpus_allowed, cpu_online_map);
@@ -1880,39 +1956,14 @@ static void scan_for_empty_cpusets(const struct cpuset *root)
                 if (cpus_empty(cp->cpus_allowed) ||
                      nodes_empty(cp->mems_allowed))
                         remove_tasks_in_empty_cpuset(cp);
+                else {
+                        update_tasks_cpumask(cp, NULL);
+                        update_tasks_nodemask(cp, &oldmems);
+                }
         }
 }
 
 /*
- * The cpus_allowed and mems_allowed nodemasks in the top_cpuset track
- * cpu_online_map and node_states[N_HIGH_MEMORY].  Force the top cpuset to
- * track what's online after any CPU or memory node hotplug or unplug event.
- *
- * Since there are two callers of this routine, one for CPU hotplug
- * events and one for memory node hotplug events, we could have coded
- * two separate routines here.  We code it as a single common routine
- * in order to minimize text size.
- */
-
-static void common_cpu_mem_hotplug_unplug(int rebuild_sd)
-{
-        cgroup_lock();
-
-        top_cpuset.cpus_allowed = cpu_online_map;
-        top_cpuset.mems_allowed = node_states[N_HIGH_MEMORY];
-        scan_for_empty_cpusets(&top_cpuset);
-
-        /*
-         * Scheduler destroys domains on hotplug events.
-         * Rebuild them based on the current settings.
-         */
-        if (rebuild_sd)
-                rebuild_sched_domains();
-
-        cgroup_unlock();
-}
-
-/*
  * The top_cpuset tracks what CPUs and Memory Nodes are online,
  * period.  This is necessary in order to make cpusets transparent
  * (of no affect) on systems that are actively using CPU hotplug
@@ -1920,40 +1971,52 @@ static void common_cpu_mem_hotplug_unplug(int rebuild_sd)
  *
  * This routine ensures that top_cpuset.cpus_allowed tracks
  * cpu_online_map on each CPU hotplug (cpuhp) event.
+ *
+ * Called within get_online_cpus().  Needs to call cgroup_lock()
+ * before calling generate_sched_domains().
  */
-
-static int cpuset_handle_cpuhp(struct notifier_block *unused_nb,
+static int cpuset_track_online_cpus(struct notifier_block *unused_nb,
                                 unsigned long phase, void *unused_cpu)
 {
+        struct sched_domain_attr *attr;
+        cpumask_t *doms;
+        int ndoms;
+
         switch (phase) {
-        case CPU_UP_CANCELED:
-        case CPU_UP_CANCELED_FROZEN:
-        case CPU_DOWN_FAILED:
-        case CPU_DOWN_FAILED_FROZEN:
         case CPU_ONLINE:
         case CPU_ONLINE_FROZEN:
         case CPU_DEAD:
         case CPU_DEAD_FROZEN:
-                common_cpu_mem_hotplug_unplug(1);
                 break;
+
         default:
                 return NOTIFY_DONE;
         }
 
+        cgroup_lock();
+        top_cpuset.cpus_allowed = cpu_online_map;
+        scan_for_empty_cpusets(&top_cpuset);
+        ndoms = generate_sched_domains(&doms, &attr);
+        cgroup_unlock();
+
+        /* Have scheduler rebuild the domains */
+        partition_sched_domains(ndoms, doms, attr);
+
         return NOTIFY_OK;
 }
 
 #ifdef CONFIG_MEMORY_HOTPLUG
 /*
  * Keep top_cpuset.mems_allowed tracking node_states[N_HIGH_MEMORY].
- * Call this routine anytime after you change
- * node_states[N_HIGH_MEMORY].
- * See also the previous routine cpuset_handle_cpuhp().
+ * 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)
 {
-        common_cpu_mem_hotplug_unplug(0);
+        cgroup_lock();
+        top_cpuset.mems_allowed = node_states[N_HIGH_MEMORY];
+        scan_for_empty_cpusets(&top_cpuset);
+        cgroup_unlock();
 }
 #endif
 
@@ -1968,11 +2031,10 @@ void __init cpuset_init_smp(void)
         top_cpuset.cpus_allowed = cpu_online_map;
         top_cpuset.mems_allowed = node_states[N_HIGH_MEMORY];
 
-        hotcpu_notifier(cpuset_handle_cpuhp, 0);
+        hotcpu_notifier(cpuset_track_online_cpus, 0);
 }
 
 /**
-
  * cpuset_cpus_allowed - return cpus_allowed mask from a tasks cpuset.
  * @tsk: pointer to task_struct from which to obtain cpuset->cpus_allowed.
  * @pmask: pointer to cpumask_t variable to receive cpus_allowed set.
@@ -2374,19 +2436,15 @@ 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/delayacct.c b/kernel/delayacct.c
index 10e43fd8b721..b3179dad71be 100644
--- a/kernel/delayacct.c
+++ b/kernel/delayacct.c
@@ -145,8 +145,11 @@ int __delayacct_add_tsk(struct taskstats *d, struct task_struct *tsk)
         d->blkio_delay_total = (tmp < d->blkio_delay_total) ? 0 : tmp;
         tmp = d->swapin_delay_total + tsk->delays->swapin_delay;
         d->swapin_delay_total = (tmp < d->swapin_delay_total) ? 0 : tmp;
+        tmp = d->freepages_delay_total + tsk->delays->freepages_delay;
+        d->freepages_delay_total = (tmp < d->freepages_delay_total) ? 0 : tmp;
         d->blkio_count += tsk->delays->blkio_count;
         d->swapin_count += tsk->delays->swapin_count;
+        d->freepages_count += tsk->delays->freepages_count;
         spin_unlock_irqrestore(&tsk->delays->lock, flags);
 
 done:
@@ -165,3 +168,16 @@ __u64 __delayacct_blkio_ticks(struct task_struct *tsk)
         return ret;
 }
 
+void __delayacct_freepages_start(void)
+{
+        delayacct_start(&current->delays->freepages_start);
+}
+
+void __delayacct_freepages_end(void)
+{
+        delayacct_end(&current->delays->freepages_start,
+                        &current->delays->freepages_end,
+                        &current->delays->freepages_delay,
+                        &current->delays->freepages_count);
+}
+
diff --git a/kernel/dma-coherent.c b/kernel/dma-coherent.c
new file mode 100644
index 000000000000..f013a0c2e111
--- /dev/null
+++ b/kernel/dma-coherent.c
@@ -0,0 +1,155 @@
+/*
+ * Coherent per-device memory handling.
+ * Borrowed from i386
+ */
+#include <linux/kernel.h>
+#include <linux/dma-mapping.h>
+
+struct dma_coherent_mem {
+        void            *virt_base;
+        u32             device_base;
+        int             size;
+        int             flags;
+        unsigned long   *bitmap;
+};
+
+int dma_declare_coherent_memory(struct device *dev, dma_addr_t bus_addr,
+                                dma_addr_t device_addr, size_t size, int flags)
+{
+        void __iomem *mem_base = NULL;
+        int pages = size >> PAGE_SHIFT;
+        int bitmap_size = BITS_TO_LONGS(pages) * sizeof(long);
+
+        if ((flags & (DMA_MEMORY_MAP | DMA_MEMORY_IO)) == 0)
+                goto out;
+        if (!size)
+                goto out;
+        if (dev->dma_mem)
+                goto out;
+
+        /* FIXME: this routine just ignores DMA_MEMORY_INCLUDES_CHILDREN */
+
+        mem_base = ioremap(bus_addr, size);
+        if (!mem_base)
+                goto out;
+
+        dev->dma_mem = kzalloc(sizeof(struct dma_coherent_mem), GFP_KERNEL);
+        if (!dev->dma_mem)
+                goto out;
+        dev->dma_mem->bitmap = kzalloc(bitmap_size, GFP_KERNEL);
+        if (!dev->dma_mem->bitmap)
+                goto free1_out;
+
+        dev->dma_mem->virt_base = mem_base;
+        dev->dma_mem->device_base = device_addr;
+        dev->dma_mem->size = pages;
+        dev->dma_mem->flags = flags;
+
+        if (flags & DMA_MEMORY_MAP)
+                return DMA_MEMORY_MAP;
+
+        return DMA_MEMORY_IO;
+
+ free1_out:
+        kfree(dev->dma_mem);
+ out:
+        if (mem_base)
+                iounmap(mem_base);
+        return 0;
+}
+EXPORT_SYMBOL(dma_declare_coherent_memory);
+
+void dma_release_declared_memory(struct device *dev)
+{
+        struct dma_coherent_mem *mem = dev->dma_mem;
+
+        if (!mem)
+                return;
+        dev->dma_mem = NULL;
+        iounmap(mem->virt_base);
+        kfree(mem->bitmap);
+        kfree(mem);
+}
+EXPORT_SYMBOL(dma_release_declared_memory);
+
+void *dma_mark_declared_memory_occupied(struct device *dev,
+                                        dma_addr_t device_addr, size_t size)
+{
+        struct dma_coherent_mem *mem = dev->dma_mem;
+        int pos, err;
+
+        size += device_addr & ~PAGE_MASK;
+
+        if (!mem)
+                return ERR_PTR(-EINVAL);
+
+        pos = (device_addr - mem->device_base) >> PAGE_SHIFT;
+        err = bitmap_allocate_region(mem->bitmap, pos, get_order(size));
+        if (err != 0)
+                return ERR_PTR(err);
+        return mem->virt_base + (pos << PAGE_SHIFT);
+}
+EXPORT_SYMBOL(dma_mark_declared_memory_occupied);
+
+/**
+ * dma_alloc_from_coherent() - try to allocate memory from the per-device coherent area
+ *
+ * @dev:        device from which we allocate memory
+ * @size:       size of requested memory area
+ * @dma_handle: This will be filled with the correct dma handle
+ * @ret:        This pointer will be filled with the virtual address
+ *              to allocated area.
+ *
+ * This function should be only called from per-arch dma_alloc_coherent()
+ * to support allocation from per-device coherent memory pools.
+ *
+ * Returns 0 if dma_alloc_coherent should continue with allocating from
+ * generic memory areas, or !0 if dma_alloc_coherent should return @ret.
+ */
+int dma_alloc_from_coherent(struct device *dev, ssize_t size,
+                                       dma_addr_t *dma_handle, void **ret)
+{
+        struct dma_coherent_mem *mem = dev ? dev->dma_mem : NULL;
+        int order = get_order(size);
+
+        if (mem) {
+                int page = bitmap_find_free_region(mem->bitmap, mem->size,
+                                                     order);
+                if (page >= 0) {
+                        *dma_handle = mem->device_base + (page << PAGE_SHIFT);
+                        *ret = mem->virt_base + (page << PAGE_SHIFT);
+                        memset(*ret, 0, size);
+                } else if (mem->flags & DMA_MEMORY_EXCLUSIVE)
+                        *ret = NULL;
+        }
+        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
+ * @dev:        device from which the memory was allocated
+ * @order:      the order of pages allocated
+ * @vaddr:      virtual address of allocated pages
+ *
+ * This checks whether the memory was allocated from the per-device
+ * coherent memory pool and if so, releases that memory.
+ *
+ * Returns 1 if we correctly released the memory, or 0 if
+ * dma_release_coherent() should proceed with releasing memory from
+ * generic pools.
+ */
+int dma_release_from_coherent(struct device *dev, int order, void *vaddr)
+{
+        struct dma_coherent_mem *mem = dev ? dev->dma_mem : NULL;
+
+        if (mem && vaddr >= mem->virt_base && vaddr <
+                   (mem->virt_base + (mem->size << PAGE_SHIFT))) {
+                int page = (vaddr - mem->virt_base) >> PAGE_SHIFT;
+
+                bitmap_release_region(mem->bitmap, page, order);
+                return 1;
+        }
+        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 a9e6bad9f706..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>
@@ -65,7 +67,7 @@ lookup_exec_domain(u_long personality)
                                 goto out;
         }
 
-#ifdef CONFIG_KMOD
+#ifdef CONFIG_MODULES
         read_unlock(&exec_domains_lock);
         request_module("personality-%ld", pers);
         read_lock(&exec_domains_lock);
@@ -168,26 +170,44 @@ __set_personality(u_long personality)
         current->personality = personality;
         oep = current_thread_info()->exec_domain;
         current_thread_info()->exec_domain = ep;
-        set_fs_altroot();
 
         module_put(oep->module);
         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 93d2711b9381..80137a5d9467 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -46,6 +46,8 @@
 #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>
@@ -85,7 +87,6 @@ static void __exit_signal(struct task_struct *tsk)
         BUG_ON(!sig);
         BUG_ON(!atomic_read(&sig->count));
 
-        rcu_read_lock();
         sighand = rcu_dereference(tsk->sighand);
         spin_lock(&sighand->siglock);
 
@@ -112,16 +113,14 @@ 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, tsk->utime);
-                sig->stime = cputime_add(sig->stime, tsk->stime);
-                sig->gtime = cputime_add(sig->gtime, tsk->gtime);
+                sig->gtime = cputime_add(sig->gtime, task_gtime(tsk));
                 sig->min_flt += tsk->min_flt;
                 sig->maj_flt += tsk->maj_flt;
                 sig->nvcsw += tsk->nvcsw;
                 sig->nivcsw += tsk->nivcsw;
                 sig->inblock += task_io_get_inblock(tsk);
                 sig->oublock += task_io_get_oublock(tsk);
-                sig->sum_sched_runtime += tsk->se.sum_exec_runtime;
+                task_io_accounting_add(&sig->ioac, &tsk->ioac);
                 sig = NULL; /* Marker for below. */
         }
 
@@ -136,7 +135,6 @@ static void __exit_signal(struct task_struct *tsk)
         tsk->signal = NULL;
         tsk->sighand = NULL;
         spin_unlock(&sighand->siglock);
-        rcu_read_unlock();
 
         __cleanup_sighand(sighand);
         clear_tsk_thread_flag(tsk,TIF_SIGPENDING);
@@ -149,30 +147,23 @@ static void __exit_signal(struct task_struct *tsk)
 
 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);
 
-/*
- * Do final ptrace-related cleanup of a zombie being reaped.
- *
- * Called with write_lock(&tasklist_lock) held.
- */
-static void ptrace_release_task(struct task_struct *p)
-{
-        BUG_ON(!list_empty(&p->ptraced));
-        ptrace_unlink(p);
-        BUG_ON(!list_empty(&p->ptrace_entry));
+        trace_sched_process_free(tsk);
+        put_task_struct(tsk);
 }
 
+
 void release_task(struct task_struct * p)
 {
         struct task_struct *leader;
         int zap_leader;
 repeat:
+        tracehook_prepare_release_task(p);
         atomic_dec(&p->user->processes);
         proc_flush_task(p);
         write_lock_irq(&tasklist_lock);
-        ptrace_release_task(p);
+        tracehook_finish_release_task(p);
         __exit_signal(p);
 
         /*
@@ -194,6 +185,13 @@ repeat:
                  * that case.
                  */
                 zap_leader = task_detached(leader);
+
+                /*
+                 * This maintains the invariant that release_task()
+                 * only runs on a task in EXIT_DEAD, just for sanity.
+                 */
+                if (zap_leader)
+                        leader->exit_state = EXIT_DEAD;
         }
 
         write_unlock_irq(&tasklist_lock);
@@ -432,7 +430,7 @@ void daemonize(const char *name, ...)
          * We don't want to have TIF_FREEZE set if the system-wide hibernation
          * or suspend transition begins right now.
          */
-        current->flags |= PF_NOFREEZE;
+        current->flags |= (PF_NOFREEZE | PF_KTHREAD);
 
         if (current->nsproxy != &init_nsproxy) {
                 get_nsproxy(&init_nsproxy);
@@ -557,8 +555,6 @@ void put_fs_struct(struct fs_struct *fs)
         if (atomic_dec_and_test(&fs->count)) {
                 path_put(&fs->root);
                 path_put(&fs->pwd);
-                if (fs->altroot.dentry)
-                        path_put(&fs->altroot);
                 kmem_cache_free(fs_cachep, fs);
         }
 }
@@ -588,8 +584,6 @@ 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)
@@ -632,29 +626,38 @@ 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 */
@@ -666,26 +669,40 @@ assign_new_owner:
 static void exit_mm(struct task_struct * tsk)
 {
         struct mm_struct *mm = tsk->mm;
+        struct core_state *core_state;
 
         mm_release(tsk, mm);
         if (!mm)
                 return;
         /*
          * Serialize with any possible pending coredump.
-         * We must hold mmap_sem around checking core_waiters
+         * We must hold mmap_sem around checking core_state
          * and clearing tsk->mm.  The core-inducing thread
-         * will increment core_waiters for each thread in the
+         * will increment ->nr_threads for each thread in the
          * group with ->mm != NULL.
          */
         down_read(&mm->mmap_sem);
-        if (mm->core_waiters) {
+        core_state = mm->core_state;
+        if (core_state) {
+                struct core_thread self;
                 up_read(&mm->mmap_sem);
-                down_write(&mm->mmap_sem);
-                if (!--mm->core_waiters)
-                        complete(mm->core_startup_done);
-                up_write(&mm->mmap_sem);
 
-                wait_for_completion(&mm->core_done);
+                self.task = tsk;
+                self.next = xchg(&core_state->dumper.next, &self);
+                /*
+                 * Implies mb(), the result of xchg() must be visible
+                 * to core_state->dumper.
+                 */
+                if (atomic_dec_and_test(&core_state->nr_threads))
+                        complete(&core_state->startup);
+
+                for (;;) {
+                        set_task_state(tsk, TASK_UNINTERRUPTIBLE);
+                        if (!self.task) /* see coredump_finish() */
+                                break;
+                        schedule();
+                }
+                __set_task_state(tsk, TASK_RUNNING);
                 down_read(&mm->mmap_sem);
         }
         atomic_inc(&mm->mm_count);
@@ -822,26 +839,50 @@ static void reparent_thread(struct task_struct *p, struct task_struct *father)
  * the child reaper process (ie "init") in our pid
  * space.
  */
+static struct task_struct *find_new_reaper(struct task_struct *father)
+{
+        struct pid_namespace *pid_ns = task_active_pid_ns(father);
+        struct task_struct *thread;
+
+        thread = father;
+        while_each_thread(father, thread) {
+                if (thread->flags & PF_EXITING)
+                        continue;
+                if (unlikely(pid_ns->child_reaper == father))
+                        pid_ns->child_reaper = thread;
+                return thread;
+        }
+
+        if (unlikely(pid_ns->child_reaper == father)) {
+                write_unlock_irq(&tasklist_lock);
+                if (unlikely(pid_ns == &init_pid_ns))
+                        panic("Attempted to kill init!");
+
+                zap_pid_ns_processes(pid_ns);
+                write_lock_irq(&tasklist_lock);
+                /*
+                 * We can not clear ->child_reaper or leave it alone.
+                 * There may by stealth EXIT_DEAD tasks on ->children,
+                 * forget_original_parent() must move them somewhere.
+                 */
+                pid_ns->child_reaper = init_pid_ns.child_reaper;
+        }
+
+        return pid_ns->child_reaper;
+}
+
 static void forget_original_parent(struct task_struct *father)
 {
-        struct task_struct *p, *n, *reaper = father;
+        struct task_struct *p, *n, *reaper;
         LIST_HEAD(ptrace_dead);
 
         write_lock_irq(&tasklist_lock);
-
+        reaper = find_new_reaper(father);
         /*
          * First clean up ptrace if we were using it.
          */
         ptrace_exit(father, &ptrace_dead);
 
-        do {
-                reaper = next_thread(reaper);
-                if (reaper == father) {
-                        reaper = task_child_reaper(father);
-                        break;
-                }
-        } while (reaper->flags & PF_EXITING);
-
         list_for_each_entry_safe(p, n, &father->children, sibling) {
                 p->real_parent = reaper;
                 if (p->parent == father) {
@@ -863,7 +904,8 @@ static void forget_original_parent(struct task_struct *father)
  */
 static void exit_notify(struct task_struct *tsk, int group_dead)
 {
-        int state;
+        int signal;
+        void *cookie;
 
         /*
          * This does two things:
@@ -900,33 +942,24 @@ static void exit_notify(struct task_struct *tsk, int group_dead)
             !capable(CAP_KILL))
                 tsk->exit_signal = SIGCHLD;
 
-        /* If something other than our normal parent is ptracing us, then
-         * send it a SIGCHLD instead of honoring exit_signal.  exit_signal
-         * only has special meaning to our real parent.
-         */
-        if (!task_detached(tsk) && thread_group_empty(tsk)) {
-                int signal = ptrace_reparented(tsk) ?
-                                SIGCHLD : tsk->exit_signal;
-                do_notify_parent(tsk, signal);
-        } else if (tsk->ptrace) {
-                do_notify_parent(tsk, SIGCHLD);
-        }
+        signal = tracehook_notify_death(tsk, &cookie, group_dead);
+        if (signal >= 0)
+                signal = do_notify_parent(tsk, signal);
 
-        state = EXIT_ZOMBIE;
-        if (task_detached(tsk) && likely(!tsk->ptrace))
-                state = EXIT_DEAD;
-        tsk->exit_state = state;
+        tsk->exit_state = signal == DEATH_REAP ? EXIT_DEAD : EXIT_ZOMBIE;
 
         /* mt-exec, de_thread() is waiting for us */
         if (thread_group_leader(tsk) &&
-            tsk->signal->notify_count < 0 &&
-            tsk->signal->group_exit_task)
+            tsk->signal->group_exit_task &&
+            tsk->signal->notify_count < 0)
                 wake_up_process(tsk->signal->group_exit_task);
 
         write_unlock_irq(&tasklist_lock);
 
+        tracehook_report_death(tsk, signal, cookie, group_dead);
+
         /* If the process is dead, release it - nobody will wait for it */
-        if (state == EXIT_DEAD)
+        if (signal == DEATH_REAP)
                 release_task(tsk);
 }
 
@@ -958,39 +991,6 @@ static void check_stack_usage(void)
 static inline void check_stack_usage(void) {}
 #endif
 
-static inline void exit_child_reaper(struct task_struct *tsk)
-{
-        if (likely(tsk->group_leader != task_child_reaper(tsk)))
-                return;
-
-        if (tsk->nsproxy->pid_ns == &init_pid_ns)
-                panic("Attempted to kill init!");
-
-        /*
-         * @tsk is the last thread in the 'cgroup-init' and is exiting.
-         * Terminate all remaining processes in the namespace and reap them
-         * before exiting @tsk.
-         *
-         * Note that @tsk (last thread of cgroup-init) may not necessarily
-         * be the child-reaper (i.e main thread of cgroup-init) of the
-         * namespace i.e the child_reaper may have already exited.
-         *
-         * Even after a child_reaper exits, we let it inherit orphaned children,
-         * because, pid_ns->child_reaper remains valid as long as there is
-         * at least one living sub-thread in the cgroup init.
-
-         * This living sub-thread of the cgroup-init will be notified when
-         * a child inherited by the 'child-reaper' exits (do_notify_parent()
-         * uses __group_send_sig_info()). Further, when reaping child processes,
-         * do_wait() iterates over children of all living sub threads.
-
-         * i.e even though 'child_reaper' thread is listed as the parent of the
-         * orphaned children, any living sub-thread in the cgroup-init can
-         * perform the role of the child_reaper.
-         */
-        zap_pid_ns_processes(tsk->nsproxy->pid_ns);
-}
-
 NORET_TYPE void do_exit(long code)
 {
         struct task_struct *tsk = current;
@@ -1005,10 +1005,7 @@ NORET_TYPE void do_exit(long code)
         if (unlikely(!tsk->pid))
                 panic("Attempted to kill the idle task!");
 
-        if (unlikely(current->ptrace & PT_TRACE_EXIT)) {
-                current->ptrace_message = code;
-                ptrace_notify((PTRACE_EVENT_EXIT << 8) | SIGTRAP);
-        }
+        tracehook_report_exit(&code);
 
         /*
          * We're taking recursive faults here in do_exit. Safest is to just
@@ -1053,7 +1050,6 @@ NORET_TYPE void do_exit(long code)
         }
         group_dead = atomic_dec_and_test(&tsk->signal->live);
         if (group_dead) {
-                exit_child_reaper(tsk);
                 hrtimer_cancel(&tsk->signal->real_timer);
                 exit_itimers(tsk->signal);
         }
@@ -1078,6 +1074,8 @@ 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);
@@ -1306,6 +1304,7 @@ 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
@@ -1321,20 +1320,23 @@ 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,
@@ -1354,6 +1356,8 @@ static int wait_task_zombie(struct task_struct *p, int options,
                 psig->coublock +=
                         task_io_get_oublock(p) +
                         sig->oublock + sig->coublock;
+                task_io_accounting_add(&psig->ioac, &p->ioac);
+                task_io_accounting_add(&psig->ioac, &sig->ioac);
                 spin_unlock_irq(&p->parent->sighand->siglock);
         }
 
@@ -1677,6 +1681,8 @@ 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 adefc1131f27..f6083561dfe0 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -27,15 +27,18 @@
 #include <linux/key.h>
 #include <linux/binfmts.h>
 #include <linux/mman.h>
+#include <linux/mmu_notifier.h>
 #include <linux/fs.h>
 #include <linux/nsproxy.h>
 #include <linux/capability.h>
 #include <linux/cpu.h>
 #include <linux/cgroup.h>
 #include <linux/security.h>
+#include <linux/hugetlb.h>
 #include <linux/swap.h>
 #include <linux/syscalls.h>
 #include <linux/jiffies.h>
+#include <linux/tracehook.h>
 #include <linux/futex.h>
 #include <linux/task_io_accounting_ops.h>
 #include <linux/rcupdate.h>
@@ -55,6 +58,7 @@
 #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>
@@ -92,6 +96,23 @@ int nr_processes(void)
 static struct kmem_cache *task_struct_cachep;
 #endif
 
+#ifndef __HAVE_ARCH_THREAD_INFO_ALLOCATOR
+static inline struct thread_info *alloc_thread_info(struct task_struct *tsk)
+{
+#ifdef CONFIG_DEBUG_STACK_USAGE
+        gfp_t mask = GFP_KERNEL | __GFP_ZERO;
+#else
+        gfp_t mask = GFP_KERNEL;
+#endif
+        return (struct thread_info *)__get_free_pages(mask, THREAD_SIZE_ORDER);
+}
+
+static inline void free_thread_info(struct thread_info *ti)
+{
+        free_pages((unsigned long)ti, THREAD_SIZE_ORDER);
+}
+#endif
+
 /* SLAB cache for signal_struct structures (tsk->signal) */
 static struct kmem_cache *signal_cachep;
 
@@ -307,6 +328,14 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
                 }
 
                 /*
+                 * Clear hugetlb-related page reserves for children. This only
+                 * affects MAP_PRIVATE mappings. Faults generated by the child
+                 * are not guaranteed to succeed, even if read-only
+                 */
+                if (is_vm_hugetlb_page(tmp))
+                        reset_vma_resv_huge_pages(tmp);
+
+                /*
                  * Link in the new vma and copy the page table entries.
                  */
                 *pprev = tmp;
@@ -374,7 +403,7 @@ static struct mm_struct * mm_init(struct mm_struct * mm, struct task_struct *p)
         INIT_LIST_HEAD(&mm->mmlist);
         mm->flags = (current->mm) ? current->mm->flags
                                   : MMF_DUMP_FILTER_DEFAULT;
-        mm->core_waiters = 0;
+        mm->core_state = NULL;
         mm->nr_ptes = 0;
         set_mm_counter(mm, file_rss, 0);
         set_mm_counter(mm, anon_rss, 0);
@@ -387,6 +416,7 @@ static struct mm_struct * mm_init(struct mm_struct * mm, struct task_struct *p)
 
         if (likely(!mm_alloc_pgd(mm))) {
                 mm->def_flags = 0;
+                mmu_notifier_mm_init(mm);
                 return mm;
         }
 
@@ -419,6 +449,7 @@ void __mmdrop(struct mm_struct *mm)
         BUG_ON(mm == &init_mm);
         mm_free_pgd(mm);
         destroy_context(mm);
+        mmu_notifier_mm_destroy(mm);
         free_mm(mm);
 }
 EXPORT_SYMBOL_GPL(__mmdrop);
@@ -448,7 +479,7 @@ EXPORT_SYMBOL_GPL(mmput);
 /**
  * get_task_mm - acquire a reference to the task's mm
  *
- * Returns %NULL if the task has no mm.  Checks PF_BORROWED_MM (meaning
+ * Returns %NULL if the task has no mm.  Checks PF_KTHREAD (meaning
  * this kernel workthread has transiently adopted a user mm with use_mm,
  * to do its AIO) is not set and if so returns a reference to it, after
  * bumping up the use count.  User must release the mm via mmput()
@@ -461,7 +492,7 @@ struct mm_struct *get_task_mm(struct task_struct *task)
         task_lock(task);
         mm = task->mm;
         if (mm) {
-                if (task->flags & PF_BORROWED_MM)
+                if (task->flags & PF_KTHREAD)
                         mm = NULL;
                 else
                         atomic_inc(&mm->mm_users);
@@ -630,13 +661,6 @@ static struct fs_struct *__copy_fs_struct(struct fs_struct *old)
                 path_get(&old->root);
                 fs->pwd = old->pwd;
                 path_get(&old->pwd);
-                if (old->altroot.dentry) {
-                        fs->altroot = old->altroot;
-                        path_get(&old->altroot);
-                } else {
-                        fs->altroot.mnt = NULL;
-                        fs->altroot.dentry = NULL;
-                }
                 read_unlock(&old->lock);
         }
         return fs;
@@ -736,15 +760,44 @@ 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;
@@ -772,38 +825,25 @@ 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;
-        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]);
+        task_io_accounting_init(&sig->ioac);
         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);
@@ -813,7 +853,9 @@ 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);
 }
 
@@ -833,8 +875,7 @@ static void copy_flags(unsigned long clone_flags, struct task_struct *p)
 
         new_flags &= ~PF_SUPERPRIV;
         new_flags |= PF_FORKNOEXEC;
-        if (!(clone_flags & CLONE_PTRACE))
-                p->ptrace = 0;
+        new_flags |= PF_STARTING;
         p->flags = new_flags;
         clear_freeze_flag(p);
 }
@@ -863,6 +904,19 @@ 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.
  *
@@ -875,7 +929,8 @@ static struct task_struct *copy_process(unsigned long clone_flags,
                                         struct pt_regs *regs,
                                         unsigned long stack_size,
                                         int __user *child_tidptr,
-                                        struct pid *pid)
+                                        struct pid *pid,
+                                        int trace)
 {
         int retval;
         struct task_struct *p;
@@ -963,26 +1018,17 @@ 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;
 #endif
 
-#ifdef CONFIG_TASK_XACCT
-        p->rchar = 0;           /* I/O counter: bytes read */
-        p->wchar = 0;           /* I/O counter: bytes written */
-        p->syscr = 0;           /* I/O counter: read syscalls */
-        p->syscw = 0;           /* I/O counter: write syscalls */
-#endif
-        task_io_accounting_init(p);
+        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);
@@ -1081,6 +1127,12 @@ static struct task_struct *copy_process(unsigned long clone_flags,
         if (clone_flags & CLONE_THREAD)
                 p->tgid = current->tgid;
 
+        if (current->nsproxy != p->nsproxy) {
+                retval = ns_cgroup_clone(p, pid);
+                if (retval)
+                        goto bad_fork_free_pid;
+        }
+
         p->set_child_tid = (clone_flags & CLONE_CHILD_SETTID) ? child_tidptr : NULL;
         /*
          * Clear TID on mm_release()?
@@ -1125,8 +1177,6 @@ static struct task_struct *copy_process(unsigned long clone_flags,
          */
         p->group_leader = p;
         INIT_LIST_HEAD(&p->thread_group);
-        INIT_LIST_HEAD(&p->ptrace_entry);
-        INIT_LIST_HEAD(&p->ptraced);
 
         /* Now that the task is set up, run cgroup callbacks if
          * necessary. We need to run them before the task is visible
@@ -1157,7 +1207,6 @@ static struct task_struct *copy_process(unsigned long clone_flags,
                 p->real_parent = current->real_parent;
         else
                 p->real_parent = current;
-        p->parent = p->real_parent;
 
         spin_lock(&current->sighand->siglock);
 
@@ -1180,34 +1229,19 @@ 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)) {
                 list_add_tail(&p->sibling, &p->real_parent->children);
-                if (unlikely(p->ptrace & PT_PTRACED))
-                        __ptrace_link(p, current->parent);
+                tracehook_finish_clone(p, clone_flags, trace);
 
                 if (thread_group_leader(p)) {
                         if (clone_flags & CLONE_NEWPID)
                                 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));
@@ -1285,29 +1319,13 @@ struct task_struct * __cpuinit fork_idle(int cpu)
         struct pt_regs regs;
 
         task = copy_process(CLONE_VM, 0, idle_regs(&regs), 0, NULL,
-                                &init_struct_pid);
+                            &init_struct_pid, 0);
         if (!IS_ERR(task))
                 init_idle(task, cpu);
 
         return task;
 }
 
-static int fork_traceflag(unsigned clone_flags)
-{
-        if (clone_flags & CLONE_UNTRACED)
-                return 0;
-        else if (clone_flags & CLONE_VFORK) {
-                if (current->ptrace & PT_TRACE_VFORK)
-                        return PTRACE_EVENT_VFORK;
-        } else if ((clone_flags & CSIGNAL) != SIGCHLD) {
-                if (current->ptrace & PT_TRACE_CLONE)
-                        return PTRACE_EVENT_CLONE;
-        } else if (current->ptrace & PT_TRACE_FORK)
-                return PTRACE_EVENT_FORK;
-
-        return 0;
-}
-
 /*
  *  Ok, this is the main fork-routine.
  *
@@ -1342,14 +1360,14 @@ long do_fork(unsigned long clone_flags,
                 }
         }
 
-        if (unlikely(current->ptrace)) {
-                trace = fork_traceflag (clone_flags);
-                if (trace)
-                        clone_flags |= CLONE_PTRACE;
-        }
+        /*
+         * When called from kernel_thread, don't do user tracing stuff.
+         */
+        if (likely(user_mode(regs)))
+                trace = tracehook_prepare_clone(clone_flags);
 
         p = copy_process(clone_flags, stack_start, regs, stack_size,
-                        child_tidptr, NULL);
+                         child_tidptr, NULL, trace);
         /*
          * Do this prior waking up the new thread - the thread pointer
          * might get invalid after that point, if the thread exits quickly.
@@ -1357,6 +1375,8 @@ 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)
@@ -1367,32 +1387,35 @@ long do_fork(unsigned long clone_flags,
                         init_completion(&vfork);
                 }
 
-                if ((p->ptrace & PT_PTRACED) || (clone_flags & CLONE_STOPPED)) {
+                tracehook_report_clone(trace, regs, clone_flags, nr, p);
+
+                /*
+                 * We set PF_STARTING at creation in case tracing wants to
+                 * use this to distinguish a fully live task from one that
+                 * hasn't gotten to tracehook_report_clone() yet.  Now we
+                 * clear it and set the child going.
+                 */
+                p->flags &= ~PF_STARTING;
+
+                if (unlikely(clone_flags & CLONE_STOPPED)) {
                         /*
                          * We'll start up with an immediate SIGSTOP.
                          */
                         sigaddset(&p->pending.signal, SIGSTOP);
                         set_tsk_thread_flag(p, TIF_SIGPENDING);
-                }
-
-                if (!(clone_flags & CLONE_STOPPED))
-                        wake_up_new_task(p, clone_flags);
-                else
                         __set_task_state(p, TASK_STOPPED);
-
-                if (unlikely (trace)) {
-                        current->ptrace_message = nr;
-                        ptrace_notify ((trace << 8) | SIGTRAP);
+                } else {
+                        wake_up_new_task(p, clone_flags);
                 }
 
+                tracehook_report_clone_complete(trace, regs,
+                                                clone_flags, nr, p);
+
                 if (clone_flags & CLONE_VFORK) {
                         freezer_do_not_count();
                         wait_for_completion(&vfork);
                         freezer_count();
-                        if (unlikely (current->ptrace & PT_TRACE_VFORK_DONE)) {
-                                current->ptrace_message = nr;
-                                ptrace_notify ((PTRACE_EVENT_VFORK_DONE << 8) | SIGTRAP);
-                        }
+                        tracehook_report_vfork_done(p, nr);
                 }
         } else {
                 nr = PTR_ERR(p);
@@ -1404,7 +1427,7 @@ long do_fork(unsigned long clone_flags,
 #define ARCH_MIN_MMSTRUCT_ALIGN 0
 #endif
 
-static void sighand_ctor(struct kmem_cache *cachep, void *data)
+static void sighand_ctor(void *data)
 {
         struct sighand_struct *sighand = data;
 
diff --git a/kernel/freezer.c b/kernel/freezer.c
new file mode 100644
index 000000000000..ba6248b323ef
--- /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);
+        }
+}
+
+/*
+ * 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)
+{
+        if (frozen(p)) {
+                p->flags &= ~PF_FROZEN;
+                return 1;
+        }
+        clear_freeze_flag(p);
+        return 0;
+}
+
+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..2b465dfde426 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
@@ -672,13 +672,14 @@ static inline int hrtimer_enqueue_reprogram(struct hrtimer *timer,
                          */
                         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;
@@ -794,7 +795,7 @@ 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 +807,8 @@ 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 +816,7 @@ 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 +848,8 @@ 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 +946,10 @@ 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 +957,8 @@ 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 +986,7 @@ 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 +1019,26 @@ 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 +1098,7 @@ 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 +1130,7 @@ 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;
@@ -1245,7 +1267,8 @@ 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 +1331,23 @@ 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 +1383,30 @@ 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 +1461,7 @@ 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 +1472,8 @@ 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 +1511,7 @@ 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 +1521,7 @@ 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 +1543,7 @@ 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 +1562,7 @@ 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 +1587,14 @@ 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 +1614,7 @@ 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 +1655,123 @@ 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 +1816,103 @@ 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 964964baefa2..10b5092e9bfe 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -24,17 +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) {
-                printk(KERN_ERR "Trying to initialize invalid IRQ%d\n", irq);
-                WARN_ON(1);
+        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;
@@ -58,22 +56,19 @@ 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) {
-                printk(KERN_ERR "Trying to cleanup invalid IRQ%d\n", irq);
-                WARN_ON(1);
+        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);
-                printk(KERN_ERR "Destroying IRQ%d without calling free_irq\n",
+                WARN(1, KERN_ERR "Destroying IRQ%d without calling free_irq\n",
                         irq);
-                WARN_ON(1);
                 return;
         }
         desc->msi_desc = NULL;
@@ -81,6 +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);
 }
 
@@ -92,19 +88,17 @@ 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) {
-                printk(KERN_ERR "Trying to install chip for IRQ%d\n", irq);
-                WARN_ON(1);
+        if (!desc) {
+                WARN(1, KERN_ERR "Trying to install chip for IRQ%d\n", irq);
                 return -EINVAL;
         }
 
         if (!chip)
                 chip = &no_irq_chip;
 
-        desc = irq_desc + irq;
         spin_lock_irqsave(&desc->lock, flags);
         irq_chip_set_defaults(chip);
         desc->chip = chip;
@@ -115,27 +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);
@@ -149,16 +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);
@@ -175,15 +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)
@@ -201,10 +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;
         }
@@ -222,7 +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;
@@ -240,8 +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;
 }
 
@@ -250,7 +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;
@@ -309,14 +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)))
@@ -348,7 +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;
 
@@ -358,7 +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
@@ -396,7 +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;
 
@@ -406,7 +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
@@ -455,8 +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);
@@ -472,8 +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);
@@ -528,7 +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);
@@ -545,17 +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) {
@@ -587,7 +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);
 }
@@ -610,17 +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);
@@ -628,17 +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 77a51be36010..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);
@@ -177,8 +184,7 @@ static void __enable_irq(struct irq_desc *desc, unsigned int irq)
 {
         switch (desc->depth) {
         case 0:
-                printk(KERN_WARNING "Unbalanced enable for IRQ %d\n", irq);
-                WARN_ON(1);
+                WARN(1, KERN_WARNING "Unbalanced enable for IRQ %d\n", irq);
                 break;
         case 1: {
                 unsigned int status = desc->status & ~IRQ_DISABLED;
@@ -205,10 +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);
@@ -217,6 +223,17 @@ void enable_irq(unsigned int irq)
 }
 EXPORT_SYMBOL(enable_irq);
 
+static int set_irq_wake_real(unsigned int irq, unsigned int on)
+{
+        struct irq_desc *desc = irq_to_desc(irq);
+        int ret = -ENXIO;
+
+        if (desc->chip->set_wake)
+                ret = desc->chip->set_wake(irq, on);
+
+        return ret;
+}
+
 /**
  *      set_irq_wake - control irq power management wakeup
  *      @irq:   interrupt to control
@@ -231,32 +248,34 @@ EXPORT_SYMBOL(enable_irq);
  */
 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 = -ENXIO;
-        int (*set_wake)(unsigned, unsigned) = desc->chip->set_wake;
+        int ret = 0;
 
         /* wakeup-capable irqs can be shared between drivers that
          * don't need to have the same sleep mode behaviors.
          */
         spin_lock_irqsave(&desc->lock, flags);
         if (on) {
-                if (desc->wake_depth++ == 0)
-                        desc->status |= IRQ_WAKEUP;
-                else
-                        set_wake = NULL;
+                if (desc->wake_depth++ == 0) {
+                        ret = set_irq_wake_real(irq, on);
+                        if (ret)
+                                desc->wake_depth = 0;
+                        else
+                                desc->status |= IRQ_WAKEUP;
+                }
         } else {
                 if (desc->wake_depth == 0) {
-                        printk(KERN_WARNING "Unbalanced IRQ %d "
-                                        "wake disable\n", irq);
-                        WARN_ON(1);
-                } else if (--desc->wake_depth == 0)
-                        desc->status &= ~IRQ_WAKEUP;
-                else
-                        set_wake = NULL;
+                        WARN(1, "Unbalanced IRQ %d wake disable\n", irq);
+                } else if (--desc->wake_depth == 0) {
+                        ret = set_irq_wake_real(irq, on);
+                        if (ret)
+                                desc->wake_depth = 1;
+                        else
+                                desc->status &= ~IRQ_WAKEUP;
+                }
         }
-        if (set_wake)
-                ret = desc->chip->set_wake(irq, on);
+
         spin_unlock_irqrestore(&desc->lock, flags);
         return ret;
 }
@@ -269,12 +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;
 
-        action = irq_desc[irq].action;
+        if (desc->status & IRQ_NOREQUEST)
+                return 0;
+
+        action = desc->action;
         if (action)
                 if (irqflags & action->flags & IRQF_SHARED)
                         action = NULL;
@@ -293,19 +316,51 @@ void compat_irq_chip_set_default_handler(struct irq_desc *desc)
                 desc->handle_irq = NULL;
 }
 
+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) {
+                /*
+                 * IRQF_TRIGGER_* but the PIC does not support multiple
+                 * flow-types?
+                 */
+                pr_warning("No set_type function for IRQ %d (%s)\n", irq,
+                                chip ? (chip->name ? : "unknown") : "unknown");
+                return 0;
+        }
+
+        ret = chip->set_type(irq, flags & IRQF_TRIGGER_MASK);
+
+        if (ret)
+                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;
+}
+
 /*
  * 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)
@@ -361,35 +416,23 @@ int setup_irq(unsigned int irq, struct irqaction *new)
                 shared = 1;
         }
 
-        *p = new;
-
-        /* Exclude IRQ from balancing */
-        if (new->flags & IRQF_NOBALANCING)
-                desc->status |= IRQ_NO_BALANCING;
-
         if (!shared) {
                 irq_chip_set_defaults(desc->chip);
 
-#if defined(CONFIG_IRQ_PER_CPU)
-                if (new->flags & IRQF_PERCPU)
-                        desc->status |= IRQ_PER_CPU;
-#endif
-
                 /* Setup the type (level, edge polarity) if configured: */
                 if (new->flags & IRQF_TRIGGER_MASK) {
-                        if (desc->chip->set_type)
-                                desc->chip->set_type(irq,
-                                                new->flags & IRQF_TRIGGER_MASK);
-                        else
-                                /*
-                                 * IRQF_TRIGGER_* but the PIC does not support
-                                 * multiple flow-types?
-                                 */
-                                printk(KERN_WARNING "No IRQF_TRIGGER set_type "
-                                       "function for IRQ %d (%s)\n", irq,
-                                       desc->chip->name);
+                        ret = __irq_set_trigger(desc, irq, new->flags);
+
+                        if (ret) {
+                                spin_unlock_irqrestore(&desc->lock, flags);
+                                return ret;
+                        }
                 } else
                         compat_irq_chip_set_default_handler(desc);
+#if defined(CONFIG_IRQ_PER_CPU)
+                if (new->flags & IRQF_PERCPU)
+                        desc->status |= IRQ_PER_CPU;
+#endif
 
                 desc->status &= ~(IRQ_AUTODETECT | IRQ_WAITING |
                                   IRQ_INPROGRESS | IRQ_SPURIOUS_DISABLED);
@@ -397,17 +440,29 @@ 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;
+
+        /* Exclude IRQ from balancing */
+        if (new->flags & IRQF_NOBALANCING)
+                desc->status |= IRQ_NO_BALANCING;
+
         /* Reset broken irq detection when installing new handler */
         desc->irq_count = 0;
         desc->irqs_unhandled = 0;
@@ -424,7 +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);
 
@@ -444,6 +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
@@ -459,15 +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 (;;) {
@@ -556,12 +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
@@ -578,9 +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;
@@ -596,26 +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 6c6d35d68ee9..fac014a81b24 100644
--- a/kernel/irq/proc.c
+++ b/kernel/irq/proc.c
@@ -8,6 +8,7 @@
 
 #include <linux/irq.h>
 #include <linux/proc_fs.h>
+#include <linux/seq_file.h>
 #include <linux/interrupt.h>
 
 #include "internals.h"
@@ -16,23 +17,18 @@ static struct proc_dir_entry *root_irq_dir;
 
 #ifdef CONFIG_SMP
 
-static int irq_affinity_read_proc(char *page, char **start, off_t off,
-                                  int count, int *eof, void *data)
+static int irq_affinity_proc_show(struct seq_file *m, void *v)
 {
-        struct irq_desc *desc = irq_desc + (long)data;
+        struct irq_desc *desc = irq_to_desc((long)m->private);
         cpumask_t *mask = &desc->affinity;
-        int len;
 
 #ifdef CONFIG_GENERIC_PENDING_IRQ
         if (desc->status & IRQ_MOVE_PENDING)
                 mask = &desc->pending_mask;
 #endif
-        len = cpumask_scnprintf(page, count, *mask);
-
-        if (count - len < 2)
-                return -EINVAL;
-        len += sprintf(page + len, "\n");
-        return len;
+        seq_cpumask(m, mask);
+        seq_putc(m, '\n');
+        return 0;
 }
 
 #ifndef is_affinity_mask_valid
@@ -40,13 +36,14 @@ static int irq_affinity_read_proc(char *page, char **start, off_t off,
 #endif
 
 int no_irq_affinity;
-static int irq_affinity_write_proc(struct file *file, const char __user *buffer,
-                                   unsigned long count, void *data)
+static ssize_t irq_affinity_proc_write(struct file *file,
+                const char __user *buffer, size_t count, loff_t *pos)
 {
-        unsigned int irq = (int)(long)data, full_count = count, err;
+        unsigned int irq = (int)(long)PDE(file->f_path.dentry->d_inode)->data;
         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;
 
@@ -65,28 +62,38 @@ static int irq_affinity_write_proc(struct file *file, const char __user *buffer,
         if (!cpus_intersects(new_value, cpu_online_map))
                 /* Special case for empty set - allow the architecture
                    code to set default SMP affinity. */
-                return irq_select_affinity(irq) ? -EINVAL : full_count;
+                return irq_select_affinity(irq) ? -EINVAL : count;
 
         irq_set_affinity(irq, new_value);
 
-        return full_count;
+        return count;
 }
 
-static int default_affinity_read(char *page, char **start, off_t off,
-                                  int count, int *eof, void *data)
+static int irq_affinity_proc_open(struct inode *inode, struct file *file)
 {
-        int len = cpumask_scnprintf(page, count, irq_default_affinity);
-        if (count - len < 2)
-                return -EINVAL;
-        len += sprintf(page + len, "\n");
-        return len;
+        return single_open(file, irq_affinity_proc_show, PDE(inode)->data);
 }
 
-static int default_affinity_write(struct file *file, const char __user *buffer,
-                                   unsigned long count, void *data)
+static const struct file_operations irq_affinity_proc_fops = {
+        .open           = irq_affinity_proc_open,
+        .read           = seq_read,
+        .llseek         = seq_lseek,
+        .release        = single_release,
+        .write          = irq_affinity_proc_write,
+};
+
+static int default_affinity_show(struct seq_file *m, void *v)
+{
+        seq_cpumask(m, &irq_default_affinity);
+        seq_putc(m, '\n');
+        return 0;
+}
+
+static ssize_t default_affinity_write(struct file *file,
+                const char __user *buffer, size_t count, loff_t *ppos)
 {
-        unsigned int full_count = count, err;
         cpumask_t new_value;
+        int err;
 
         err = cpumask_parse_user(buffer, count, new_value);
         if (err)
@@ -105,27 +112,40 @@ static int default_affinity_write(struct file *file, const char __user *buffer,
 
         irq_default_affinity = new_value;
 
-        return full_count;
+        return count;
 }
+
+static int default_affinity_open(struct inode *inode, struct file *file)
+{
+        return single_open(file, default_affinity_show, NULL);
+}
+
+static const struct file_operations default_affinity_proc_fops = {
+        .open           = default_affinity_open,
+        .read           = seq_read,
+        .llseek         = seq_lseek,
+        .release        = single_release,
+        .write          = default_affinity_write,
+};
 #endif
 
 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;
@@ -145,8 +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;
 
@@ -154,43 +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 */
-                entry = create_proc_entry("smp_affinity", 0600, irq_desc[irq].dir);
-
-                if (entry) {
-                        entry->data = (void *)(long)irq;
-                        entry->read_proc = irq_affinity_read_proc;
-                        entry->write_proc = irq_affinity_write_proc;
-                }
-        }
+        /* create /proc/irq/<irq>/smp_affinity */
+        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;
@@ -201,28 +213,25 @@ 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)
 {
 #ifdef CONFIG_SMP
-        struct proc_dir_entry *entry;
-
-        /* create /proc/irq/default_smp_affinity */
-        entry = create_proc_entry("default_smp_affinity", 0600, root_irq_dir);
-        if (entry) {
-                entry->data = NULL;
-                entry->read_proc  = default_affinity_read;
-                entry->write_proc = default_affinity_write;
-        }
+        proc_create("irq/default_smp_affinity", 0600, NULL,
+                    &default_affinity_proc_fops);
 #endif
 }
 
 void init_irq_proc(void)
 {
-        int i;
+        unsigned int irq;
+        struct irq_desc *desc;
 
         /* create /proc/irq */
         root_irq_dir = proc_mkdir("irq", NULL);
@@ -234,7 +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 6fc0040f3e3a..5072cf1685a2 100644
--- a/kernel/kallsyms.c
+++ b/kernel/kallsyms.c
@@ -176,7 +176,7 @@ static unsigned long get_symbol_pos(unsigned long addr,
         high = kallsyms_num_syms;
 
         while (high - low > 1) {
-                mid = (low + high) / 2;
+                mid = low + (high - low) / 2;
                 if (kallsyms_addresses[mid] <= addr)
                         low = mid;
                 else
@@ -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)
diff --git a/kernel/kexec.c b/kernel/kexec.c
index 1c5fcacbcf33..ac0fde7b54d0 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -12,7 +12,7 @@
 #include <linux/slab.h>
 #include <linux/fs.h>
 #include <linux/kexec.h>
-#include <linux/spinlock.h>
+#include <linux/mutex.h>
 #include <linux/list.h>
 #include <linux/highmem.h>
 #include <linux/syscalls.h>
@@ -24,6 +24,13 @@
 #include <linux/utsrelease.h>
 #include <linux/utsname.h>
 #include <linux/numa.h>
+#include <linux/suspend.h>
+#include <linux/device.h>
+#include <linux/freezer.h>
+#include <linux/pm.h>
+#include <linux/cpu.h>
+#include <linux/console.h>
+#include <linux/vmalloc.h>
 
 #include <asm/page.h>
 #include <asm/uaccess.h>
@@ -71,7 +78,7 @@ int kexec_should_crash(struct task_struct *p)
  *
  * The code for the transition from the current kernel to the
  * the new kernel is placed in the control_code_buffer, whose size
- * is given by KEXEC_CONTROL_CODE_SIZE.  In the best case only a single
+ * is given by KEXEC_CONTROL_PAGE_SIZE.  In the best case only a single
  * page of memory is necessary, but some architectures require more.
  * Because this memory must be identity mapped in the transition from
  * virtual to physical addresses it must live in the range
@@ -236,12 +243,18 @@ static int kimage_normal_alloc(struct kimage **rimage, unsigned long entry,
          */
         result = -ENOMEM;
         image->control_code_page = kimage_alloc_control_pages(image,
-                                           get_order(KEXEC_CONTROL_CODE_SIZE));
+                                           get_order(KEXEC_CONTROL_PAGE_SIZE));
         if (!image->control_code_page) {
                 printk(KERN_ERR "Could not allocate control_code_buffer\n");
                 goto out;
         }
 
+        image->swap_page = kimage_alloc_control_pages(image, 0);
+        if (!image->swap_page) {
+                printk(KERN_ERR "Could not allocate swap buffer\n");
+                goto out;
+        }
+
         result = 0;
  out:
         if (result == 0)
@@ -305,7 +318,7 @@ static int kimage_crash_alloc(struct kimage **rimage, unsigned long entry,
          */
         result = -ENOMEM;
         image->control_code_page = kimage_alloc_control_pages(image,
-                                           get_order(KEXEC_CONTROL_CODE_SIZE));
+                                           get_order(KEXEC_CONTROL_PAGE_SIZE));
         if (!image->control_code_page) {
                 printk(KERN_ERR "Could not allocate control_code_buffer\n");
                 goto out;
@@ -589,14 +602,12 @@ static void kimage_free_extra_pages(struct kimage *image)
         kimage_free_page_list(&image->unuseable_pages);
 
 }
-static int kimage_terminate(struct kimage *image)
+static void kimage_terminate(struct kimage *image)
 {
         if (*image->entry != 0)
                 image->entry++;
 
         *image->entry = IND_DONE;
-
-        return 0;
 }
 
 #define for_each_kimage_entry(image, ptr, entry) \
@@ -743,8 +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;
@@ -914,19 +931,14 @@ static int kimage_load_segment(struct kimage *image,
  */
 struct kimage *kexec_image;
 struct kimage *kexec_crash_image;
-/*
- * A home grown binary mutex.
- * Nothing can wait so this mutex is safe to use
- * in interrupt context :)
- */
-static int kexec_lock;
+
+static DEFINE_MUTEX(kexec_mutex);
 
 asmlinkage long sys_kexec_load(unsigned long entry, unsigned long nr_segments,
                                 struct kexec_segment __user *segments,
                                 unsigned long flags)
 {
         struct kimage **dest_image, *image;
-        int locked;
         int result;
 
         /* We only trust the superuser with rebooting the system. */
@@ -962,8 +974,7 @@ asmlinkage long sys_kexec_load(unsigned long entry, unsigned long nr_segments,
          *
          * KISS: always take the mutex.
          */
-        locked = xchg(&kexec_lock, 1);
-        if (locked)
+        if (!mutex_trylock(&kexec_mutex))
                 return -EBUSY;
 
         dest_image = &kexec_image;
@@ -988,6 +999,8 @@ asmlinkage long sys_kexec_load(unsigned long entry, unsigned long nr_segments,
                 if (result)
                         goto out;
 
+                if (flags & KEXEC_PRESERVE_CONTEXT)
+                        image->preserve_context = 1;
                 result = machine_kexec_prepare(image);
                 if (result)
                         goto out;
@@ -997,16 +1010,13 @@ asmlinkage long sys_kexec_load(unsigned long entry, unsigned long nr_segments,
                         if (result)
                                 goto out;
                 }
-                result = kimage_terminate(image);
-                if (result)
-                        goto out;
+                kimage_terminate(image);
         }
         /* Install the new kernel, and  Uninstall the old */
         image = xchg(dest_image, image);
 
 out:
-        locked = xchg(&kexec_lock, 0); /* Release the mutex */
-        BUG_ON(!locked);
+        mutex_unlock(&kexec_mutex);
         kimage_free(image);
 
         return result;
@@ -1053,10 +1063,7 @@ asmlinkage long compat_sys_kexec_load(unsigned long entry,
 
 void crash_kexec(struct pt_regs *regs)
 {
-        int locked;
-
-
-        /* Take the kexec_lock here to prevent sys_kexec_load
+        /* Take the kexec_mutex here to prevent sys_kexec_load
          * running on one cpu from replacing the crash kernel
          * we are using after a panic on a different cpu.
          *
@@ -1064,8 +1071,7 @@ void crash_kexec(struct pt_regs *regs)
          * of memory the xchg(&kexec_crash_image) would be
          * sufficient.  But since I reuse the memory...
          */
-        locked = xchg(&kexec_lock, 1);
-        if (!locked) {
+        if (mutex_trylock(&kexec_mutex)) {
                 if (kexec_crash_image) {
                         struct pt_regs fixed_regs;
                         crash_setup_regs(&fixed_regs, regs);
@@ -1073,8 +1079,7 @@ void crash_kexec(struct pt_regs *regs)
                         machine_crash_shutdown(&fixed_regs);
                         machine_kexec(kexec_crash_image);
                 }
-                locked = xchg(&kexec_lock, 0);
-                BUG_ON(!locked);
+                mutex_unlock(&kexec_mutex);
         }
 }
 
@@ -1367,6 +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);
@@ -1402,6 +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);
@@ -1415,3 +1422,79 @@ static int __init crash_save_vmcoreinfo_init(void)
 }
 
 module_init(crash_save_vmcoreinfo_init)
+
+/*
+ * Move into place and start executing a preloaded standalone
+ * executable.  If nothing was preloaded return an error.
+ */
+int kernel_kexec(void)
+{
+        int error = 0;
+
+        if (!mutex_trylock(&kexec_mutex))
+                return -EBUSY;
+        if (!kexec_image) {
+                error = -EINVAL;
+                goto Unlock;
+        }
+
+#ifdef CONFIG_KEXEC_JUMP
+        if (kexec_image->preserve_context) {
+                mutex_lock(&pm_mutex);
+                pm_prepare_console();
+                error = freeze_processes();
+                if (error) {
+                        error = -EBUSY;
+                        goto Restore_console;
+                }
+                suspend_console();
+                error = device_suspend(PMSG_FREEZE);
+                if (error)
+                        goto Resume_console;
+                error = disable_nonboot_cpus();
+                if (error)
+                        goto Resume_devices;
+                device_pm_lock();
+                local_irq_disable();
+                /* At this point, device_suspend() has been called,
+                 * but *not* device_power_down(). We *must*
+                 * device_power_down() now.  Otherwise, drivers for
+                 * some devices (e.g. interrupt controllers) become
+                 * desynchronized with the actual state of the
+                 * hardware at resume time, and evil weirdness ensues.
+                 */
+                error = device_power_down(PMSG_FREEZE);
+                if (error)
+                        goto Enable_irqs;
+        } else
+#endif
+        {
+                kernel_restart_prepare(NULL);
+                printk(KERN_EMERG "Starting new kernel\n");
+                machine_shutdown();
+        }
+
+        machine_kexec(kexec_image);
+
+#ifdef CONFIG_KEXEC_JUMP
+        if (kexec_image->preserve_context) {
+                device_power_up(PMSG_RESTORE);
+ Enable_irqs:
+                local_irq_enable();
+                device_pm_unlock();
+                enable_nonboot_cpus();
+ Resume_devices:
+                device_resume(PMSG_RESTORE);
+ Resume_console:
+                resume_console();
+                thaw_processes();
+ Restore_console:
+                pm_restore_console();
+                mutex_unlock(&pm_mutex);
+        }
+#endif
+
+ Unlock:
+        mutex_unlock(&kexec_mutex);
+        return error;
+}
diff --git a/kernel/kgdb.c b/kernel/kgdb.c
index 3ec23c3ec97f..e4dcfb2272a4 100644
--- a/kernel/kgdb.c
+++ b/kernel/kgdb.c
@@ -56,12 +56,14 @@
 
 static int kgdb_break_asap;
 
+#define KGDB_MAX_THREAD_QUERY 17
 struct kgdb_state {
         int                     ex_vector;
         int                     signo;
         int                     err_code;
         int                     cpu;
         int                     pass_exception;
+        unsigned long           thr_query;
         unsigned long           threadid;
         long                    kgdb_usethreadid;
         struct pt_regs          *linux_regs;
@@ -166,13 +168,6 @@ early_param("nokgdbroundup", opt_nokgdbroundup);
  * Weak aliases for breakpoint management,
  * can be overriden by architectures when needed:
  */
-int __weak kgdb_validate_break_address(unsigned long addr)
-{
-        char tmp_variable[BREAK_INSTR_SIZE];
-
-        return probe_kernel_read(tmp_variable, (char *)addr, BREAK_INSTR_SIZE);
-}
-
 int __weak kgdb_arch_set_breakpoint(unsigned long addr, char *saved_instr)
 {
         int err;
@@ -191,6 +186,25 @@ int __weak kgdb_arch_remove_breakpoint(unsigned long addr, char *bundle)
                                   (char *)bundle, BREAK_INSTR_SIZE);
 }
 
+int __weak kgdb_validate_break_address(unsigned long addr)
+{
+        char tmp_variable[BREAK_INSTR_SIZE];
+        int err;
+        /* Validate setting the breakpoint and then removing it.  In the
+         * remove fails, the kernel needs to emit a bad message because we
+         * are deep trouble not being able to put things back the way we
+         * found them.
+         */
+        err = kgdb_arch_set_breakpoint(addr, tmp_variable);
+        if (err)
+                return err;
+        err = kgdb_arch_remove_breakpoint(addr, tmp_variable);
+        if (err)
+                printk(KERN_ERR "KGDB: Critical breakpoint error, kernel "
+                   "memory destroyed at: %lx", addr);
+        return err;
+}
+
 unsigned long __weak kgdb_arch_pc(int exception, struct pt_regs *regs)
 {
         return instruction_pointer(regs);
@@ -433,9 +447,14 @@ int kgdb_hex2long(char **ptr, unsigned long *long_val)
 {
         int hex_val;
         int num = 0;
+        int negate = 0;
 
         *long_val = 0;
 
+        if (**ptr == '-') {
+                negate = 1;
+                (*ptr)++;
+        }
         while (**ptr) {
                 hex_val = hex(**ptr);
                 if (hex_val < 0)
@@ -446,6 +465,9 @@ int kgdb_hex2long(char **ptr, unsigned long *long_val)
                 (*ptr)++;
         }
 
+        if (negate)
+                *long_val = -*long_val;
+
         return num;
 }
 
@@ -466,7 +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;
         }
 
@@ -515,10 +537,16 @@ static void int_to_threadref(unsigned char *id, int value)
 static struct task_struct *getthread(struct pt_regs *regs, int tid)
 {
         /*
-         * Non-positive TIDs are remapped idle tasks:
+         * Non-positive TIDs are remapped to the cpu shadow information
          */
-        if (tid <= 0)
-                return idle_task(-tid);
+        if (tid == 0 || tid == -1)
+                tid = -atomic_read(&kgdb_active) - 2;
+        if (tid < 0) {
+                if (kgdb_info[-tid - 2].task)
+                        return kgdb_info[-tid - 2].task;
+                else
+                        return idle_task(-tid - 2);
+        }
 
         /*
          * find_task_by_pid_ns() does not take the tasklist lock anymore
@@ -562,6 +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);
 }
@@ -725,14 +754,15 @@ setundefined:
 }
 
 /*
- * Remap normal tasks to their real PID, idle tasks to -1 ... -NR_CPUs:
+ * Remap normal tasks to their real PID,
+ * CPU shadow threads are mapped to -CPU - 2
  */
 static inline int shadow_pid(int realpid)
 {
         if (realpid)
                 return realpid;
 
-        return -1-raw_smp_processor_id();
+        return -raw_smp_processor_id() - 2;
 }
 
 static char gdbmsgbuf[BUFMAX + 1];
@@ -826,7 +856,7 @@ static void gdb_cmd_getregs(struct kgdb_state *ks)
                 local_debuggerinfo = kgdb_info[ks->cpu].debuggerinfo;
         } else {
                 local_debuggerinfo = NULL;
-                for (i = 0; i < NR_CPUS; i++) {
+                for_each_online_cpu(i) {
                         /*
                          * Try to find the task on some other
                          * or possibly this node if we do not
@@ -960,10 +990,13 @@ static int gdb_cmd_reboot(struct kgdb_state *ks)
 /* Handle the 'q' query packets */
 static void gdb_cmd_query(struct kgdb_state *ks)
 {
-        struct task_struct *thread;
+        struct task_struct *g;
+        struct task_struct *p;
         unsigned char thref[8];
         char *ptr;
         int i;
+        int cpu;
+        int finished = 0;
 
         switch (remcom_in_buffer[1]) {
         case 's':
@@ -973,22 +1006,34 @@ static void gdb_cmd_query(struct kgdb_state *ks)
                         break;
                 }
 
-                if (remcom_in_buffer[1] == 'f')
-                        ks->threadid = 1;
-
+                i = 0;
                 remcom_out_buffer[0] = 'm';
                 ptr = remcom_out_buffer + 1;
-
-                for (i = 0; i < 17; ks->threadid++) {
-                        thread = getthread(ks->linux_regs, ks->threadid);
-                        if (thread) {
-                                int_to_threadref(thref, ks->threadid);
+                if (remcom_in_buffer[1] == 'f') {
+                        /* Each cpu is a shadow thread */
+                        for_each_online_cpu(cpu) {
+                                ks->thr_query = 0;
+                                int_to_threadref(thref, -cpu - 2);
                                 pack_threadid(ptr, thref);
                                 ptr += BUF_THREAD_ID_SIZE;
                                 *(ptr++) = ',';
                                 i++;
                         }
                 }
+
+                do_each_thread(g, p) {
+                        if (i >= ks->thr_query && !finished) {
+                                int_to_threadref(thref, p->pid);
+                                pack_threadid(ptr, thref);
+                                ptr += BUF_THREAD_ID_SIZE;
+                                *(ptr++) = ',';
+                                ks->thr_query++;
+                                if (ks->thr_query % KGDB_MAX_THREAD_QUERY == 0)
+                                        finished = 1;
+                        }
+                        i++;
+                } while_each_thread(g, p);
+
                 *(--ptr) = '\0';
                 break;
 
@@ -1011,15 +1056,15 @@ static void gdb_cmd_query(struct kgdb_state *ks)
                         error_packet(remcom_out_buffer, -EINVAL);
                         break;
                 }
-                if (ks->threadid > 0) {
+                if ((int)ks->threadid > 0) {
                         kgdb_mem2hex(getthread(ks->linux_regs,
                                         ks->threadid)->comm,
                                         remcom_out_buffer, 16);
                 } else {
                         static char tmpstr[23 + BUF_THREAD_ID_SIZE];
 
-                        sprintf(tmpstr, "Shadow task %d for pid 0",
-                                        (int)(-ks->threadid-1));
+                        sprintf(tmpstr, "shadowCPU%d",
+                                        (int)(-ks->threadid - 2));
                         kgdb_mem2hex(tmpstr, remcom_out_buffer, strlen(tmpstr));
                 }
                 break;
@@ -1388,6 +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);
 
@@ -1418,7 +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);
         }
@@ -1431,7 +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
 
@@ -1450,7 +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 */
@@ -1464,7 +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);
                 /*
@@ -1480,6 +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 8df97d3dfda8..3d3c3ea3a023 100644
--- a/kernel/kmod.c
+++ b/kernel/kmod.c
@@ -42,7 +42,7 @@ extern int max_threads;
 
 static struct workqueue_struct *khelper_wq;
 
-#ifdef CONFIG_KMOD
+#ifdef CONFIG_MODULES
 
 /*
         modprobe_path is set via /proc/sys.
@@ -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)
@@ -334,34 +332,29 @@ 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
  * @path: path to usermode executable
  * @argv: arg vector for process
  * @envp: environment for process
+ * @gfp_mask: gfp mask for memory allocation
  *
  * Returns either %NULL on allocation failure, or a subprocess_info
  * structure.  This should be passed to call_usermodehelper_exec to
  * exec the process and free the structure.
  */
-struct subprocess_info *call_usermodehelper_setup(char *path,
-                                                  char **argv, char **envp)
+struct subprocess_info *call_usermodehelper_setup(char *path, char **argv,
+                                                  char **envp, gfp_t gfp_mask)
 {
         struct subprocess_info *sub_info;
-        sub_info = kzalloc(sizeof(struct subprocess_info),  GFP_ATOMIC);
+        sub_info = kzalloc(sizeof(struct subprocess_info), gfp_mask);
         if (!sub_info)
                 goto out;
 
@@ -417,12 +410,12 @@ int call_usermodehelper_stdinpipe(struct subprocess_info *sub_info,
 {
         struct file *f;
 
-        f = create_write_pipe();
+        f = create_write_pipe(0);
         if (IS_ERR(f))
                 return PTR_ERR(f);
         *filp = f;
 
-        f = create_read_pipe(f);
+        f = create_read_pipe(f, 0);
         if (IS_ERR(f)) {
                 free_write_pipe(*filp);
                 return PTR_ERR(f);
@@ -494,7 +487,7 @@ int call_usermodehelper_pipe(char *path, char **argv, char **envp,
         struct subprocess_info *sub_info;
         int ret;
 
-        sub_info = call_usermodehelper_setup(path, argv, envp);
+        sub_info = call_usermodehelper_setup(path, argv, envp, GFP_KERNEL);
         if (sub_info == NULL)
                 return -ENOMEM;
 
@@ -514,5 +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 1485ca8d0e00..8b57a2597f21 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -62,6 +62,7 @@
         addr = ((kprobe_opcode_t *)(kallsyms_lookup_name(name)))
 #endif
 
+static int kprobes_initialized;
 static struct hlist_head kprobe_table[KPROBE_TABLE_SIZE];
 static struct hlist_head kretprobe_inst_table[KPROBE_TABLE_SIZE];
 
@@ -69,8 +70,15 @@ static struct hlist_head kretprobe_inst_table[KPROBE_TABLE_SIZE];
 static bool kprobe_enabled;
 
 DEFINE_MUTEX(kprobe_mutex);             /* Protects kprobe_table */
-DEFINE_SPINLOCK(kretprobe_lock);        /* Protects kretprobe_inst_table */
 static DEFINE_PER_CPU(struct kprobe *, kprobe_instance) = NULL;
+static struct {
+        spinlock_t lock ____cacheline_aligned;
+} kretprobe_table_locks[KPROBE_TABLE_SIZE];
+
+static spinlock_t *kretprobe_table_lock_ptr(unsigned long hash)
+{
+        return &(kretprobe_table_locks[hash].lock);
+}
 
 /*
  * Normally, functions that we'd want to prohibit kprobes in, are marked
@@ -368,26 +376,53 @@ void __kprobes kprobes_inc_nmissed_count(struct kprobe *p)
         return;
 }
 
-/* Called with kretprobe_lock held */
 void __kprobes recycle_rp_inst(struct kretprobe_instance *ri,
                                 struct hlist_head *head)
 {
+        struct kretprobe *rp = ri->rp;
+
         /* remove rp inst off the rprobe_inst_table */
         hlist_del(&ri->hlist);
-        if (ri->rp) {
-                /* remove rp inst off the used list */
-                hlist_del(&ri->uflist);
-                /* put rp inst back onto the free list */
-                INIT_HLIST_NODE(&ri->uflist);
-                hlist_add_head(&ri->uflist, &ri->rp->free_instances);
+        INIT_HLIST_NODE(&ri->hlist);
+        if (likely(rp)) {
+                spin_lock(&rp->lock);
+                hlist_add_head(&ri->hlist, &rp->free_instances);
+                spin_unlock(&rp->lock);
         } else
                 /* Unregistering */
                 hlist_add_head(&ri->hlist, head);
 }
 
-struct hlist_head __kprobes *kretprobe_inst_table_head(struct task_struct *tsk)
+void kretprobe_hash_lock(struct task_struct *tsk,
+                         struct hlist_head **head, unsigned long *flags)
 {
-        return &kretprobe_inst_table[hash_ptr(tsk, KPROBE_HASH_BITS)];
+        unsigned long hash = hash_ptr(tsk, KPROBE_HASH_BITS);
+        spinlock_t *hlist_lock;
+
+        *head = &kretprobe_inst_table[hash];
+        hlist_lock = kretprobe_table_lock_ptr(hash);
+        spin_lock_irqsave(hlist_lock, *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);
+}
+
+void kretprobe_hash_unlock(struct task_struct *tsk, unsigned long *flags)
+{
+        unsigned long hash = hash_ptr(tsk, KPROBE_HASH_BITS);
+        spinlock_t *hlist_lock;
+
+        hlist_lock = kretprobe_table_lock_ptr(hash);
+        spin_unlock_irqrestore(hlist_lock, *flags);
+}
+
+void kretprobe_table_unlock(unsigned long hash, unsigned long *flags)
+{
+        spinlock_t *hlist_lock = kretprobe_table_lock_ptr(hash);
+        spin_unlock_irqrestore(hlist_lock, *flags);
 }
 
 /*
@@ -401,17 +436,21 @@ void __kprobes kprobe_flush_task(struct task_struct *tk)
         struct kretprobe_instance *ri;
         struct hlist_head *head, empty_rp;
         struct hlist_node *node, *tmp;
-        unsigned long flags = 0;
+        unsigned long hash, flags = 0;
 
-        INIT_HLIST_HEAD(&empty_rp);
-        spin_lock_irqsave(&kretprobe_lock, flags);
-        head = kretprobe_inst_table_head(tk);
+        if (unlikely(!kprobes_initialized))
+                /* Early boot.  kretprobe_table_locks not yet initialized. */
+                return;
+
+        hash = hash_ptr(tk, KPROBE_HASH_BITS);
+        head = &kretprobe_inst_table[hash];
+        kretprobe_table_lock(hash, &flags);
         hlist_for_each_entry_safe(ri, node, tmp, head, hlist) {
                 if (ri->task == tk)
                         recycle_rp_inst(ri, &empty_rp);
         }
-        spin_unlock_irqrestore(&kretprobe_lock, flags);
-
+        kretprobe_table_unlock(hash, &flags);
+        INIT_HLIST_HEAD(&empty_rp);
         hlist_for_each_entry_safe(ri, node, tmp, &empty_rp, hlist) {
                 hlist_del(&ri->hlist);
                 kfree(ri);
@@ -423,24 +462,29 @@ static inline void free_rp_inst(struct kretprobe *rp)
         struct kretprobe_instance *ri;
         struct hlist_node *pos, *next;
 
-        hlist_for_each_entry_safe(ri, pos, next, &rp->free_instances, uflist) {
-                hlist_del(&ri->uflist);
+        hlist_for_each_entry_safe(ri, pos, next, &rp->free_instances, hlist) {
+                hlist_del(&ri->hlist);
                 kfree(ri);
         }
 }
 
 static void __kprobes cleanup_rp_inst(struct kretprobe *rp)
 {
-        unsigned long flags;
+        unsigned long flags, hash;
         struct kretprobe_instance *ri;
         struct hlist_node *pos, *next;
+        struct hlist_head *head;
+
         /* No race here */
-        spin_lock_irqsave(&kretprobe_lock, flags);
-        hlist_for_each_entry_safe(ri, pos, next, &rp->used_instances, uflist) {
-                ri->rp = NULL;
-                hlist_del(&ri->uflist);
+        for (hash = 0; hash < KPROBE_TABLE_SIZE; hash++) {
+                kretprobe_table_lock(hash, &flags);
+                head = &kretprobe_inst_table[hash];
+                hlist_for_each_entry_safe(ri, pos, next, head, hlist) {
+                        if (ri->rp == rp)
+                                ri->rp = NULL;
+                }
+                kretprobe_table_unlock(hash, &flags);
         }
-        spin_unlock_irqrestore(&kretprobe_lock, flags);
         free_rp_inst(rp);
 }
 
@@ -831,32 +875,37 @@ static int __kprobes pre_handler_kretprobe(struct kprobe *p,
                                            struct pt_regs *regs)
 {
         struct kretprobe *rp = container_of(p, struct kretprobe, kp);
-        unsigned long flags = 0;
+        unsigned long hash, flags = 0;
+        struct kretprobe_instance *ri;
 
         /*TODO: consider to only swap the RA after the last pre_handler fired */
-        spin_lock_irqsave(&kretprobe_lock, flags);
+        hash = hash_ptr(current, KPROBE_HASH_BITS);
+        spin_lock_irqsave(&rp->lock, flags);
         if (!hlist_empty(&rp->free_instances)) {
-                struct kretprobe_instance *ri;
-
                 ri = hlist_entry(rp->free_instances.first,
-                                 struct kretprobe_instance, uflist);
+                                struct kretprobe_instance, hlist);
+                hlist_del(&ri->hlist);
+                spin_unlock_irqrestore(&rp->lock, flags);
+
                 ri->rp = rp;
                 ri->task = current;
 
                 if (rp->entry_handler && rp->entry_handler(ri, regs)) {
-                        spin_unlock_irqrestore(&kretprobe_lock, flags);
+                        spin_unlock_irqrestore(&rp->lock, flags);
                         return 0;
                 }
 
                 arch_prepare_kretprobe(ri, regs);
 
                 /* XXX(hch): why is there no hlist_move_head? */
-                hlist_del(&ri->uflist);
-                hlist_add_head(&ri->uflist, &ri->rp->used_instances);
-                hlist_add_head(&ri->hlist, kretprobe_inst_table_head(ri->task));
-        } else
+                INIT_HLIST_NODE(&ri->hlist);
+                kretprobe_table_lock(hash, &flags);
+                hlist_add_head(&ri->hlist, &kretprobe_inst_table[hash]);
+                kretprobe_table_unlock(hash, &flags);
+        } else {
                 rp->nmissed++;
-        spin_unlock_irqrestore(&kretprobe_lock, flags);
+                spin_unlock_irqrestore(&rp->lock, flags);
+        }
         return 0;
 }
 
@@ -892,7 +941,7 @@ static int __kprobes __register_kretprobe(struct kretprobe *rp,
                 rp->maxactive = NR_CPUS;
 #endif
         }
-        INIT_HLIST_HEAD(&rp->used_instances);
+        spin_lock_init(&rp->lock);
         INIT_HLIST_HEAD(&rp->free_instances);
         for (i = 0; i < rp->maxactive; i++) {
                 inst = kmalloc(sizeof(struct kretprobe_instance) +
@@ -901,8 +950,8 @@ static int __kprobes __register_kretprobe(struct kretprobe *rp,
                         free_rp_inst(rp);
                         return -ENOMEM;
                 }
-                INIT_HLIST_NODE(&inst->uflist);
-                hlist_add_head(&inst->uflist, &rp->free_instances);
+                INIT_HLIST_NODE(&inst->hlist);
+                hlist_add_head(&inst->hlist, &rp->free_instances);
         }
 
         rp->nmissed = 0;
@@ -1009,6 +1058,7 @@ static int __init init_kprobes(void)
         for (i = 0; i < KPROBE_TABLE_SIZE; i++) {
                 INIT_HLIST_HEAD(&kprobe_table[i]);
                 INIT_HLIST_HEAD(&kretprobe_inst_table[i]);
+                spin_lock_init(&(kretprobe_table_locks[i].lock));
         }
 
         /*
@@ -1050,6 +1100,7 @@ static int __init init_kprobes(void)
         err = arch_init_kprobes();
         if (!err)
                 err = register_die_notifier(&kprobe_exceptions_nb);
+        kprobes_initialized = (err == 0);
 
         if (!err)
                 init_test_probes();
@@ -1286,13 +1337,8 @@ EXPORT_SYMBOL_GPL(register_jprobe);
 EXPORT_SYMBOL_GPL(unregister_jprobe);
 EXPORT_SYMBOL_GPL(register_jprobes);
 EXPORT_SYMBOL_GPL(unregister_jprobes);
-#ifdef CONFIG_KPROBES
 EXPORT_SYMBOL_GPL(jprobe_return);
-#endif
-
-#ifdef CONFIG_KPROBES
 EXPORT_SYMBOL_GPL(register_kretprobe);
 EXPORT_SYMBOL_GPL(unregister_kretprobe);
 EXPORT_SYMBOL_GPL(register_kretprobes);
 EXPORT_SYMBOL_GPL(unregister_kretprobes);
-#endif
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 ac3fb7326641..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)
 
@@ -106,7 +107,7 @@ static void create_kthread(struct kthread_create_info *create)
                  */
                 sched_setscheduler(create->result, SCHED_NORMAL, &param);
                 set_user_nice(create->result, KTHREAD_NICE_LEVEL);
-                set_cpus_allowed(create->result, CPU_MASK_ALL);
+                set_cpus_allowed_ptr(create->result, CPU_MASK_ALL_PTR);
         }
         complete(&create->done);
 }
@@ -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);
         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);
@@ -233,7 +237,7 @@ int kthreadd(void *unused)
         set_task_comm(tsk, "kthreadd");
         ignore_signals(tsk);
         set_user_nice(tsk, KTHREAD_NICE_LEVEL);
-        set_cpus_allowed(tsk, CPU_MASK_ALL);
+        set_cpus_allowed_ptr(tsk, CPU_MASK_ALL_PTR);
 
         current->flags |= PF_NOFREEZE | PF_FREEZER_NOSIG;
 
diff --git a/kernel/lockdep.c b/kernel/lockdep.c
index d38a64362973..dbda475b13bd 100644
--- a/kernel/lockdep.c
+++ b/kernel/lockdep.c
@@ -124,6 +124,15 @@ static struct lock_list list_entries[MAX_LOCKDEP_ENTRIES];
 unsigned long nr_lock_classes;
 static struct lock_class lock_classes[MAX_LOCKDEP_KEYS];
 
+static inline struct lock_class *hlock_class(struct held_lock *hlock)
+{
+        if (!hlock->class_idx) {
+                DEBUG_LOCKS_WARN_ON(1);
+                return NULL;
+        }
+        return lock_classes + hlock->class_idx - 1;
+}
+
 #ifdef CONFIG_LOCK_STAT
 static DEFINE_PER_CPU(struct lock_class_stats[MAX_LOCKDEP_KEYS], lock_stats);
 
@@ -222,7 +231,7 @@ static void lock_release_holdtime(struct held_lock *hlock)
 
         holdtime = sched_clock() - hlock->holdtime_stamp;
 
-        stats = get_lock_stats(hlock->class);
+        stats = get_lock_stats(hlock_class(hlock));
         if (hlock->read)
                 lock_time_inc(&stats->read_holdtime, holdtime);
         else
@@ -372,6 +381,19 @@ unsigned int nr_process_chains;
 unsigned int max_lockdep_depth;
 unsigned int max_recursion_depth;
 
+static unsigned int lockdep_dependency_gen_id;
+
+static bool lockdep_dependency_visit(struct lock_class *source,
+                                     unsigned int depth)
+{
+        if (!depth)
+                lockdep_dependency_gen_id++;
+        if (source->dep_gen_id == lockdep_dependency_gen_id)
+                return true;
+        source->dep_gen_id = lockdep_dependency_gen_id;
+        return false;
+}
+
 #ifdef CONFIG_DEBUG_LOCKDEP
 /*
  * We cannot printk in early bootup code. Not even early_printk()
@@ -505,7 +527,7 @@ static void print_lockdep_cache(struct lockdep_map *lock)
 
 static void print_lock(struct held_lock *hlock)
 {
-        print_lock_name(hlock->class);
+        print_lock_name(hlock_class(hlock));
         printk(", at: ");
         print_ip_sym(hlock->acquire_ip);
 }
@@ -558,6 +580,9 @@ static void print_lock_dependencies(struct lock_class *class, int depth)
 {
         struct lock_list *entry;
 
+        if (lockdep_dependency_visit(class, depth))
+                return;
+
         if (DEBUG_LOCKS_WARN_ON(depth >= 20))
                 return;
 
@@ -850,11 +875,11 @@ static int add_lock_to_list(struct lock_class *class, struct lock_class *this,
         if (!entry)
                 return 0;
 
-        entry->class = this;
-        entry->distance = distance;
         if (!save_trace(&entry->trace))
                 return 0;
 
+        entry->class = this;
+        entry->distance = distance;
         /*
          * Since we never remove from the dependency list, the list can
          * be walked lockless by other CPUs, it's only allocation
@@ -932,7 +957,7 @@ static noinline int print_circular_bug_tail(void)
         if (debug_locks_silent)
                 return 0;
 
-        this.class = check_source->class;
+        this.class = hlock_class(check_source);
         if (!save_trace(&this.trace))
                 return 0;
 
@@ -959,6 +984,67 @@ static int noinline print_infinite_recursion_bug(void)
         return 0;
 }
 
+unsigned long __lockdep_count_forward_deps(struct lock_class *class,
+                                           unsigned int depth)
+{
+        struct lock_list *entry;
+        unsigned long ret = 1;
+
+        if (lockdep_dependency_visit(class, depth))
+                return 0;
+
+        /*
+         * Recurse this class's dependency list:
+         */
+        list_for_each_entry(entry, &class->locks_after, entry)
+                ret += __lockdep_count_forward_deps(entry->class, depth + 1);
+
+        return ret;
+}
+
+unsigned long lockdep_count_forward_deps(struct lock_class *class)
+{
+        unsigned long ret, flags;
+
+        local_irq_save(flags);
+        __raw_spin_lock(&lockdep_lock);
+        ret = __lockdep_count_forward_deps(class, 0);
+        __raw_spin_unlock(&lockdep_lock);
+        local_irq_restore(flags);
+
+        return ret;
+}
+
+unsigned long __lockdep_count_backward_deps(struct lock_class *class,
+                                            unsigned int depth)
+{
+        struct lock_list *entry;
+        unsigned long ret = 1;
+
+        if (lockdep_dependency_visit(class, depth))
+                return 0;
+        /*
+         * Recurse this class's dependency list:
+         */
+        list_for_each_entry(entry, &class->locks_before, entry)
+                ret += __lockdep_count_backward_deps(entry->class, depth + 1);
+
+        return ret;
+}
+
+unsigned long lockdep_count_backward_deps(struct lock_class *class)
+{
+        unsigned long ret, flags;
+
+        local_irq_save(flags);
+        __raw_spin_lock(&lockdep_lock);
+        ret = __lockdep_count_backward_deps(class, 0);
+        __raw_spin_unlock(&lockdep_lock);
+        local_irq_restore(flags);
+
+        return ret;
+}
+
 /*
  * Prove that the dependency graph starting at <entry> can not
  * lead to <target>. Print an error and return 0 if it does.
@@ -968,6 +1054,9 @@ check_noncircular(struct lock_class *source, unsigned int depth)
 {
         struct lock_list *entry;
 
+        if (lockdep_dependency_visit(source, depth))
+                return 1;
+
         debug_atomic_inc(&nr_cyclic_check_recursions);
         if (depth > max_recursion_depth)
                 max_recursion_depth = depth;
@@ -977,7 +1066,7 @@ check_noncircular(struct lock_class *source, unsigned int depth)
          * Check this lock's dependency list:
          */
         list_for_each_entry(entry, &source->locks_after, entry) {
-                if (entry->class == check_target->class)
+                if (entry->class == hlock_class(check_target))
                         return print_circular_bug_header(entry, depth+1);
                 debug_atomic_inc(&nr_cyclic_checks);
                 if (!check_noncircular(entry->class, depth+1))
@@ -1011,6 +1100,9 @@ find_usage_forwards(struct lock_class *source, unsigned int depth)
         struct lock_list *entry;
         int ret;
 
+        if (lockdep_dependency_visit(source, depth))
+                return 1;
+
         if (depth > max_recursion_depth)
                 max_recursion_depth = depth;
         if (depth >= RECURSION_LIMIT)
@@ -1050,6 +1142,9 @@ find_usage_backwards(struct lock_class *source, unsigned int depth)
         struct lock_list *entry;
         int ret;
 
+        if (lockdep_dependency_visit(source, depth))
+                return 1;
+
         if (!__raw_spin_is_locked(&lockdep_lock))
                 return DEBUG_LOCKS_WARN_ON(1);
 
@@ -1064,6 +1159,11 @@ find_usage_backwards(struct lock_class *source, unsigned int depth)
                 return 2;
         }
 
+        if (!source && debug_locks_off_graph_unlock()) {
+                WARN_ON(1);
+                return 0;
+        }
+
         /*
          * Check this lock's dependency list:
          */
@@ -1103,9 +1203,9 @@ print_bad_irq_dependency(struct task_struct *curr,
         printk("\nand this task is already holding:\n");
         print_lock(prev);
         printk("which would create a new lock dependency:\n");
-        print_lock_name(prev->class);
+        print_lock_name(hlock_class(prev));
         printk(" ->");
-        print_lock_name(next->class);
+        print_lock_name(hlock_class(next));
         printk("\n");
 
         printk("\nbut this new dependency connects a %s-irq-safe lock:\n",
@@ -1146,12 +1246,12 @@ check_usage(struct task_struct *curr, struct held_lock *prev,
 
         find_usage_bit = bit_backwards;
         /* fills in <backwards_match> */
-        ret = find_usage_backwards(prev->class, 0);
+        ret = find_usage_backwards(hlock_class(prev), 0);
         if (!ret || ret == 1)
                 return ret;
 
         find_usage_bit = bit_forwards;
-        ret = find_usage_forwards(next->class, 0);
+        ret = find_usage_forwards(hlock_class(next), 0);
         if (!ret || ret == 1)
                 return ret;
         /* ret == 2 */
@@ -1272,18 +1372,32 @@ check_deadlock(struct task_struct *curr, struct held_lock *next,
                struct lockdep_map *next_instance, int read)
 {
         struct held_lock *prev;
+        struct held_lock *nest = NULL;
         int i;
 
         for (i = 0; i < curr->lockdep_depth; i++) {
                 prev = curr->held_locks + i;
-                if (prev->class != next->class)
+
+                if (prev->instance == next->nest_lock)
+                        nest = prev;
+
+                if (hlock_class(prev) != hlock_class(next))
                         continue;
+
                 /*
                  * Allow read-after-read recursion of the same
                  * lock class (i.e. read_lock(lock)+read_lock(lock)):
                  */
                 if ((read == 2) && prev->read)
                         return 2;
+
+                /*
+                 * We're holding the nest_lock, which serializes this lock's
+                 * nesting behaviour.
+                 */
+                if (nest)
+                        return 2;
+
                 return print_deadlock_bug(curr, prev, next);
         }
         return 1;
@@ -1329,7 +1443,7 @@ check_prev_add(struct task_struct *curr, struct held_lock *prev,
          */
         check_source = next;
         check_target = prev;
-        if (!(check_noncircular(next->class, 0)))
+        if (!(check_noncircular(hlock_class(next), 0)))
                 return print_circular_bug_tail();
 
         if (!check_prev_add_irq(curr, prev, next))
@@ -1353,8 +1467,8 @@ check_prev_add(struct task_struct *curr, struct held_lock *prev,
          *  chains - the second one will be new, but L1 already has
          *  L2 added to its dependency list, due to the first chain.)
          */
-        list_for_each_entry(entry, &prev->class->locks_after, entry) {
-                if (entry->class == next->class) {
+        list_for_each_entry(entry, &hlock_class(prev)->locks_after, entry) {
+                if (entry->class == hlock_class(next)) {
                         if (distance == 1)
                                 entry->distance = 1;
                         return 2;
@@ -1365,26 +1479,28 @@ check_prev_add(struct task_struct *curr, struct held_lock *prev,
          * Ok, all validations passed, add the new lock
          * to the previous lock's dependency list:
          */
-        ret = add_lock_to_list(prev->class, next->class,
-                               &prev->class->locks_after, next->acquire_ip, distance);
+        ret = add_lock_to_list(hlock_class(prev), hlock_class(next),
+                               &hlock_class(prev)->locks_after,
+                               next->acquire_ip, distance);
 
         if (!ret)
                 return 0;
 
-        ret = add_lock_to_list(next->class, prev->class,
-                               &next->class->locks_before, next->acquire_ip, distance);
+        ret = add_lock_to_list(hlock_class(next), hlock_class(prev),
+                               &hlock_class(next)->locks_before,
+                               next->acquire_ip, distance);
         if (!ret)
                 return 0;
 
         /*
          * Debugging printouts:
          */
-        if (verbose(prev->class) || verbose(next->class)) {
+        if (verbose(hlock_class(prev)) || verbose(hlock_class(next))) {
                 graph_unlock();
                 printk("\n new dependency: ");
-                print_lock_name(prev->class);
+                print_lock_name(hlock_class(prev));
                 printk(" => ");
-                print_lock_name(next->class);
+                print_lock_name(hlock_class(next));
                 printk("\n");
                 dump_stack();
                 return graph_lock();
@@ -1481,7 +1597,7 @@ static inline int lookup_chain_cache(struct task_struct *curr,
                                      struct held_lock *hlock,
                                      u64 chain_key)
 {
-        struct lock_class *class = hlock->class;
+        struct lock_class *class = hlock_class(hlock);
         struct list_head *hash_head = chainhashentry(chain_key);
         struct lock_chain *chain;
         struct held_lock *hlock_curr, *hlock_next;
@@ -1554,7 +1670,7 @@ cache_hit:
         if (likely(cn + chain->depth <= MAX_LOCKDEP_CHAIN_HLOCKS)) {
                 chain->base = cn;
                 for (j = 0; j < chain->depth - 1; j++, i++) {
-                        int lock_id = curr->held_locks[i].class - lock_classes;
+                        int lock_id = curr->held_locks[i].class_idx - 1;
                         chain_hlocks[chain->base + j] = lock_id;
                 }
                 chain_hlocks[chain->base + j] = class - lock_classes;
@@ -1643,14 +1759,13 @@ static void check_chain_key(struct task_struct *curr)
                 hlock = curr->held_locks + i;
                 if (chain_key != hlock->prev_chain_key) {
                         debug_locks_off();
-                        printk("hm#1, depth: %u [%u], %016Lx != %016Lx\n",
+                        WARN(1, "hm#1, depth: %u [%u], %016Lx != %016Lx\n",
                                 curr->lockdep_depth, i,
                                 (unsigned long long)chain_key,
                                 (unsigned long long)hlock->prev_chain_key);
-                        WARN_ON(1);
                         return;
                 }
-                id = hlock->class - lock_classes;
+                id = hlock->class_idx - 1;
                 if (DEBUG_LOCKS_WARN_ON(id >= MAX_LOCKDEP_KEYS))
                         return;
 
@@ -1662,11 +1777,10 @@ static void check_chain_key(struct task_struct *curr)
         }
         if (chain_key != curr->curr_chain_key) {
                 debug_locks_off();
-                printk("hm#2, depth: %u [%u], %016Lx != %016Lx\n",
+                WARN(1, "hm#2, depth: %u [%u], %016Lx != %016Lx\n",
                         curr->lockdep_depth, i,
                         (unsigned long long)chain_key,
                         (unsigned long long)curr->curr_chain_key);
-                WARN_ON(1);
         }
 #endif
 }
@@ -1695,7 +1809,7 @@ print_usage_bug(struct task_struct *curr, struct held_lock *this,
         print_lock(this);
 
         printk("{%s} state was registered at:\n", usage_str[prev_bit]);
-        print_stack_trace(this->class->usage_traces + prev_bit, 1);
+        print_stack_trace(hlock_class(this)->usage_traces + prev_bit, 1);
 
         print_irqtrace_events(curr);
         printk("\nother info that might help us debug this:\n");
@@ -1714,7 +1828,7 @@ static inline int
 valid_state(struct task_struct *curr, struct held_lock *this,
             enum lock_usage_bit new_bit, enum lock_usage_bit bad_bit)
 {
-        if (unlikely(this->class->usage_mask & (1 << bad_bit)))
+        if (unlikely(hlock_class(this)->usage_mask & (1 << bad_bit)))
                 return print_usage_bug(curr, this, bad_bit, new_bit);
         return 1;
 }
@@ -1753,7 +1867,7 @@ print_irq_inversion_bug(struct task_struct *curr, struct lock_class *other,
         lockdep_print_held_locks(curr);
 
         printk("\nthe first lock's dependencies:\n");
-        print_lock_dependencies(this->class, 0);
+        print_lock_dependencies(hlock_class(this), 0);
 
         printk("\nthe second lock's dependencies:\n");
         print_lock_dependencies(other, 0);
@@ -1776,7 +1890,7 @@ check_usage_forwards(struct task_struct *curr, struct held_lock *this,
 
         find_usage_bit = bit;
         /* fills in <forwards_match> */
-        ret = find_usage_forwards(this->class, 0);
+        ret = find_usage_forwards(hlock_class(this), 0);
         if (!ret || ret == 1)
                 return ret;
 
@@ -1795,7 +1909,7 @@ check_usage_backwards(struct task_struct *curr, struct held_lock *this,
 
         find_usage_bit = bit;
         /* fills in <backwards_match> */
-        ret = find_usage_backwards(this->class, 0);
+        ret = find_usage_backwards(hlock_class(this), 0);
         if (!ret || ret == 1)
                 return ret;
 
@@ -1861,7 +1975,7 @@ static int mark_lock_irq(struct task_struct *curr, struct held_lock *this,
                                 LOCK_ENABLED_HARDIRQS_READ, "hard-read"))
                         return 0;
 #endif
-                if (hardirq_verbose(this->class))
+                if (hardirq_verbose(hlock_class(this)))
                         ret = 2;
                 break;
         case LOCK_USED_IN_SOFTIRQ:
@@ -1886,7 +2000,7 @@ static int mark_lock_irq(struct task_struct *curr, struct held_lock *this,
                                 LOCK_ENABLED_SOFTIRQS_READ, "soft-read"))
                         return 0;
 #endif
-                if (softirq_verbose(this->class))
+                if (softirq_verbose(hlock_class(this)))
                         ret = 2;
                 break;
         case LOCK_USED_IN_HARDIRQ_READ:
@@ -1899,7 +2013,7 @@ static int mark_lock_irq(struct task_struct *curr, struct held_lock *this,
                 if (!check_usage_forwards(curr, this,
                                           LOCK_ENABLED_HARDIRQS, "hard"))
                         return 0;
-                if (hardirq_verbose(this->class))
+                if (hardirq_verbose(hlock_class(this)))
                         ret = 2;
                 break;
         case LOCK_USED_IN_SOFTIRQ_READ:
@@ -1912,7 +2026,7 @@ static int mark_lock_irq(struct task_struct *curr, struct held_lock *this,
                 if (!check_usage_forwards(curr, this,
                                           LOCK_ENABLED_SOFTIRQS, "soft"))
                         return 0;
-                if (softirq_verbose(this->class))
+                if (softirq_verbose(hlock_class(this)))
                         ret = 2;
                 break;
         case LOCK_ENABLED_HARDIRQS:
@@ -1938,7 +2052,7 @@ static int mark_lock_irq(struct task_struct *curr, struct held_lock *this,
                                    LOCK_USED_IN_HARDIRQ_READ, "hard-read"))
                         return 0;
 #endif
-                if (hardirq_verbose(this->class))
+                if (hardirq_verbose(hlock_class(this)))
                         ret = 2;
                 break;
         case LOCK_ENABLED_SOFTIRQS:
@@ -1964,7 +2078,7 @@ static int mark_lock_irq(struct task_struct *curr, struct held_lock *this,
                                    LOCK_USED_IN_SOFTIRQ_READ, "soft-read"))
                         return 0;
 #endif
-                if (softirq_verbose(this->class))
+                if (softirq_verbose(hlock_class(this)))
                         ret = 2;
                 break;
         case LOCK_ENABLED_HARDIRQS_READ:
@@ -1979,7 +2093,7 @@ static int mark_lock_irq(struct task_struct *curr, struct held_lock *this,
                                            LOCK_USED_IN_HARDIRQ, "hard"))
                         return 0;
 #endif
-                if (hardirq_verbose(this->class))
+                if (hardirq_verbose(hlock_class(this)))
                         ret = 2;
                 break;
         case LOCK_ENABLED_SOFTIRQS_READ:
@@ -1994,7 +2108,7 @@ static int mark_lock_irq(struct task_struct *curr, struct held_lock *this,
                                            LOCK_USED_IN_SOFTIRQ, "soft"))
                         return 0;
 #endif
-                if (softirq_verbose(this->class))
+                if (softirq_verbose(hlock_class(this)))
                         ret = 2;
                 break;
         default:
@@ -2310,7 +2424,7 @@ static int mark_lock(struct task_struct *curr, struct held_lock *this,
          * If already set then do not dirty the cacheline,
          * nor do any checks:
          */
-        if (likely(this->class->usage_mask & new_mask))
+        if (likely(hlock_class(this)->usage_mask & new_mask))
                 return 1;
 
         if (!graph_lock())
@@ -2318,14 +2432,14 @@ static int mark_lock(struct task_struct *curr, struct held_lock *this,
         /*
          * Make sure we didnt race:
          */
-        if (unlikely(this->class->usage_mask & new_mask)) {
+        if (unlikely(hlock_class(this)->usage_mask & new_mask)) {
                 graph_unlock();
                 return 1;
         }
 
-        this->class->usage_mask |= new_mask;
+        hlock_class(this)->usage_mask |= new_mask;
 
-        if (!save_trace(this->class->usage_traces + new_bit))
+        if (!save_trace(hlock_class(this)->usage_traces + new_bit))
                 return 0;
 
         switch (new_bit) {
@@ -2405,7 +2519,7 @@ EXPORT_SYMBOL_GPL(lockdep_init_map);
  */
 static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass,
                           int trylock, int read, int check, int hardirqs_off,
-                          unsigned long ip)
+                          struct lockdep_map *nest_lock, unsigned long ip)
 {
         struct task_struct *curr = current;
         struct lock_class *class = NULL;
@@ -2459,14 +2573,16 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass,
                 return 0;
 
         hlock = curr->held_locks + depth;
-
-        hlock->class = class;
+        if (DEBUG_LOCKS_WARN_ON(!class))
+                return 0;
+        hlock->class_idx = class - lock_classes + 1;
         hlock->acquire_ip = ip;
         hlock->instance = lock;
+        hlock->nest_lock = nest_lock;
         hlock->trylock = trylock;
         hlock->read = read;
         hlock->check = check;
-        hlock->hardirqs_off = hardirqs_off;
+        hlock->hardirqs_off = !!hardirqs_off;
 #ifdef CONFIG_LOCK_STAT
         hlock->waittime_stamp = 0;
         hlock->holdtime_stamp = sched_clock();
@@ -2574,6 +2690,55 @@ static int check_unlock(struct task_struct *curr, struct lockdep_map *lock,
         return 1;
 }
 
+static int
+__lock_set_subclass(struct lockdep_map *lock,
+                    unsigned int subclass, unsigned long ip)
+{
+        struct task_struct *curr = current;
+        struct held_lock *hlock, *prev_hlock;
+        struct lock_class *class;
+        unsigned int depth;
+        int i;
+
+        depth = curr->lockdep_depth;
+        if (DEBUG_LOCKS_WARN_ON(!depth))
+                return 0;
+
+        prev_hlock = NULL;
+        for (i = depth-1; i >= 0; i--) {
+                hlock = curr->held_locks + i;
+                /*
+                 * We must not cross into another context:
+                 */
+                if (prev_hlock && prev_hlock->irq_context != hlock->irq_context)
+                        break;
+                if (hlock->instance == lock)
+                        goto found_it;
+                prev_hlock = hlock;
+        }
+        return print_unlock_inbalance_bug(curr, lock, ip);
+
+found_it:
+        class = register_lock_class(lock, subclass, 0);
+        hlock->class_idx = class - lock_classes + 1;
+
+        curr->lockdep_depth = i;
+        curr->curr_chain_key = hlock->prev_chain_key;
+
+        for (; i < depth; i++) {
+                hlock = curr->held_locks + i;
+                if (!__lock_acquire(hlock->instance,
+                        hlock_class(hlock)->subclass, hlock->trylock,
+                                hlock->read, hlock->check, hlock->hardirqs_off,
+                                hlock->nest_lock, hlock->acquire_ip))
+                        return 0;
+        }
+
+        if (DEBUG_LOCKS_WARN_ON(curr->lockdep_depth != depth))
+                return 0;
+        return 1;
+}
+
 /*
  * Remove the lock to the list of currently held locks in a
  * potentially non-nested (out of order) manner. This is a
@@ -2624,9 +2789,9 @@ found_it:
         for (i++; i < depth; i++) {
                 hlock = curr->held_locks + i;
                 if (!__lock_acquire(hlock->instance,
-                        hlock->class->subclass, hlock->trylock,
+                        hlock_class(hlock)->subclass, hlock->trylock,
                                 hlock->read, hlock->check, hlock->hardirqs_off,
-                                hlock->acquire_ip))
+                                hlock->nest_lock, hlock->acquire_ip))
                         return 0;
         }
 
@@ -2669,7 +2834,7 @@ static int lock_release_nested(struct task_struct *curr,
 
 #ifdef CONFIG_DEBUG_LOCKDEP
         hlock->prev_chain_key = 0;
-        hlock->class = NULL;
+        hlock->class_idx = 0;
         hlock->acquire_ip = 0;
         hlock->irq_context = 0;
 #endif
@@ -2738,18 +2903,36 @@ static void check_flags(unsigned long flags)
 #endif
 }
 
+void
+lock_set_subclass(struct lockdep_map *lock,
+                  unsigned int subclass, unsigned long ip)
+{
+        unsigned long flags;
+
+        if (unlikely(current->lockdep_recursion))
+                return;
+
+        raw_local_irq_save(flags);
+        current->lockdep_recursion = 1;
+        check_flags(flags);
+        if (__lock_set_subclass(lock, subclass, ip))
+                check_chain_key(current);
+        current->lockdep_recursion = 0;
+        raw_local_irq_restore(flags);
+}
+
+EXPORT_SYMBOL_GPL(lock_set_subclass);
+
 /*
  * We are not always called with irqs disabled - do that here,
  * and also avoid lockdep recursion:
  */
 void lock_acquire(struct lockdep_map *lock, unsigned int subclass,
-                          int trylock, int read, int check, unsigned long ip)
+                          int trylock, int read, int check,
+                          struct lockdep_map *nest_lock, unsigned long ip)
 {
         unsigned long flags;
 
-        if (unlikely(!lock_stat && !prove_locking))
-                return;
-
         if (unlikely(current->lockdep_recursion))
                 return;
 
@@ -2758,7 +2941,7 @@ void lock_acquire(struct lockdep_map *lock, unsigned int subclass,
 
         current->lockdep_recursion = 1;
         __lock_acquire(lock, subclass, trylock, read, check,
-                       irqs_disabled_flags(flags), ip);
+                       irqs_disabled_flags(flags), nest_lock, ip);
         current->lockdep_recursion = 0;
         raw_local_irq_restore(flags);
 }
@@ -2770,9 +2953,6 @@ void lock_release(struct lockdep_map *lock, int nested,
 {
         unsigned long flags;
 
-        if (unlikely(!lock_stat && !prove_locking))
-                return;
-
         if (unlikely(current->lockdep_recursion))
                 return;
 
@@ -2845,11 +3025,11 @@ __lock_contended(struct lockdep_map *lock, unsigned long ip)
 found_it:
         hlock->waittime_stamp = sched_clock();
 
-        point = lock_contention_point(hlock->class, ip);
+        point = lock_contention_point(hlock_class(hlock), ip);
 
-        stats = get_lock_stats(hlock->class);
+        stats = get_lock_stats(hlock_class(hlock));
         if (point < ARRAY_SIZE(stats->contention_point))
-                stats->contention_point[i]++;
+                stats->contention_point[point]++;
         if (lock->cpu != smp_processor_id())
                 stats->bounces[bounce_contended + !!hlock->read]++;
         put_lock_stats(stats);
@@ -2893,7 +3073,7 @@ found_it:
                 hlock->holdtime_stamp = now;
         }
 
-        stats = get_lock_stats(hlock->class);
+        stats = get_lock_stats(hlock_class(hlock));
         if (waittime) {
                 if (hlock->read)
                         lock_time_inc(&stats->read_waittime, waittime);
@@ -2988,6 +3168,7 @@ static void zap_class(struct lock_class *class)
         list_del_rcu(&class->hash_entry);
         list_del_rcu(&class->lock_entry);
 
+        class->key = NULL;
 }
 
 static inline int within(const void *addr, void *start, unsigned long size)
diff --git a/kernel/lockdep_internals.h b/kernel/lockdep_internals.h
index c3600a091a28..56b196932c08 100644
--- a/kernel/lockdep_internals.h
+++ b/kernel/lockdep_internals.h
@@ -17,9 +17,6 @@
  */
 #define MAX_LOCKDEP_ENTRIES     8192UL
 
-#define MAX_LOCKDEP_KEYS_BITS   11
-#define MAX_LOCKDEP_KEYS        (1UL << MAX_LOCKDEP_KEYS_BITS)
-
 #define MAX_LOCKDEP_CHAINS_BITS 14
 #define MAX_LOCKDEP_CHAINS      (1UL << MAX_LOCKDEP_CHAINS_BITS)
 
@@ -53,6 +50,22 @@ extern unsigned int nr_process_chains;
 extern unsigned int max_lockdep_depth;
 extern unsigned int max_recursion_depth;
 
+#ifdef CONFIG_PROVE_LOCKING
+extern unsigned long lockdep_count_forward_deps(struct lock_class *);
+extern unsigned long lockdep_count_backward_deps(struct lock_class *);
+#else
+static inline unsigned long
+lockdep_count_forward_deps(struct lock_class *class)
+{
+        return 0;
+}
+static inline unsigned long
+lockdep_count_backward_deps(struct lock_class *class)
+{
+        return 0;
+}
+#endif
+
 #ifdef CONFIG_DEBUG_LOCKDEP
 /*
  * Various lockdep statistics:
diff --git a/kernel/lockdep_proc.c b/kernel/lockdep_proc.c
index 9b0e940e2545..20dbcbf9c7dd 100644
--- a/kernel/lockdep_proc.c
+++ b/kernel/lockdep_proc.c
@@ -63,34 +63,6 @@ static void l_stop(struct seq_file *m, void *v)
 {
 }
 
-static unsigned long count_forward_deps(struct lock_class *class)
-{
-        struct lock_list *entry;
-        unsigned long ret = 1;
-
-        /*
-         * Recurse this class's dependency list:
-         */
-        list_for_each_entry(entry, &class->locks_after, entry)
-                ret += count_forward_deps(entry->class);
-
-        return ret;
-}
-
-static unsigned long count_backward_deps(struct lock_class *class)
-{
-        struct lock_list *entry;
-        unsigned long ret = 1;
-
-        /*
-         * Recurse this class's dependency list:
-         */
-        list_for_each_entry(entry, &class->locks_before, entry)
-                ret += count_backward_deps(entry->class);
-
-        return ret;
-}
-
 static void print_name(struct seq_file *m, struct lock_class *class)
 {
         char str[128];
@@ -110,7 +82,6 @@ static void print_name(struct seq_file *m, struct lock_class *class)
 
 static int l_show(struct seq_file *m, void *v)
 {
-        unsigned long nr_forward_deps, nr_backward_deps;
         struct lock_class *class = v;
         struct lock_list *entry;
         char c1, c2, c3, c4;
@@ -124,11 +95,10 @@ static int l_show(struct seq_file *m, void *v)
 #ifdef CONFIG_DEBUG_LOCKDEP
         seq_printf(m, " OPS:%8ld", class->ops);
 #endif
-        nr_forward_deps = count_forward_deps(class);
-        seq_printf(m, " FD:%5ld", nr_forward_deps);
-
-        nr_backward_deps = count_backward_deps(class);
-        seq_printf(m, " BD:%5ld", nr_backward_deps);
+#ifdef CONFIG_PROVE_LOCKING
+        seq_printf(m, " FD:%5ld", lockdep_count_forward_deps(class));
+        seq_printf(m, " BD:%5ld", lockdep_count_backward_deps(class));
+#endif
 
         get_usage_chars(class, &c1, &c2, &c3, &c4);
         seq_printf(m, " %c%c%c%c", c1, c2, c3, c4);
@@ -229,6 +199,9 @@ static int lc_show(struct seq_file *m, void *v)
 
         for (i = 0; i < chain->depth; i++) {
                 class = lock_chain_get_class(chain, i);
+                if (!class->key)
+                        continue;
+
                 seq_printf(m, "[%p] ", class->key);
                 print_name(m, class);
                 seq_puts(m, "\n");
@@ -350,7 +323,9 @@ static int lockdep_stats_show(struct seq_file *m, void *v)
                 if (class->usage_mask & LOCKF_ENABLED_HARDIRQS_READ)
                         nr_hardirq_read_unsafe++;
 
-                sum_forward_deps += count_forward_deps(class);
+#ifdef CONFIG_PROVE_LOCKING
+                sum_forward_deps += lockdep_count_forward_deps(class);
+#endif
         }
 #ifdef CONFIG_DEBUG_LOCKDEP
         DEBUG_LOCKS_WARN_ON(debug_atomic_read(&nr_unused_locks) != nr_unused);
@@ -497,8 +472,9 @@ static void snprint_time(char *buf, size_t bufsiz, s64 nr)
 {
         unsigned long rem;
 
+        nr += 5; /* for display rounding */
         rem = do_div(nr, 1000); /* XXX: do_div_signed */
-        snprintf(buf, bufsiz, "%lld.%02d", (long long)nr, ((int)rem+5)/10);
+        snprintf(buf, bufsiz, "%lld.%02d", (long long)nr, (int)rem/10);
 }
 
 static void seq_time(struct seq_file *m, s64 time)
diff --git a/kernel/marker.c b/kernel/marker.c
index 1abfb923b761..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;
@@ -126,6 +126,11 @@ void marker_probe_cb(const struct marker *mdata, void *call_private, ...)
                 struct marker_probe_closure *multi;
                 int i;
                 /*
+                 * Read mdata->ptype before mdata->multi.
+                 */
+                smp_rmb();
+                multi = mdata->multi;
+                /*
                  * multi points to an array, therefore accessing the array
                  * depends on reading multi. However, even in this case,
                  * we must insure that the pointer is read _before_ the array
@@ -133,7 +138,6 @@ void marker_probe_cb(const struct marker *mdata, void *call_private, ...)
                  * in the fast path, so put the explicit barrier here.
                  */
                 smp_read_barrier_depends();
-                multi = mdata->multi;
                 for (i = 0; multi[i].func; i++) {
                         va_start(args, call_private);
                         multi[i].func(multi[i].probe_private, call_private,
@@ -141,7 +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);
 
@@ -158,7 +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;
@@ -175,6 +179,11 @@ void marker_probe_cb_noarg(const struct marker *mdata, void *call_private, ...)
                 struct marker_probe_closure *multi;
                 int i;
                 /*
+                 * Read mdata->ptype before mdata->multi.
+                 */
+                smp_rmb();
+                multi = mdata->multi;
+                /*
                  * multi points to an array, therefore accessing the array
                  * depends on reading multi. However, even in this case,
                  * we must insure that the pointer is read _before_ the array
@@ -182,12 +191,11 @@ void marker_probe_cb_noarg(const struct marker *mdata, void *call_private, ...)
                  * in the fast path, so put the explicit barrier here.
                  */
                 smp_read_barrier_depends();
-                multi = mdata->multi;
                 for (i = 0; multi[i].func; i++)
                         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);
 
@@ -441,7 +449,7 @@ static int remove_marker(const char *name)
         hlist_del(&e->hlist);
         /* Make sure the call_rcu has been executed */
         if (e->rcu_pending)
-                rcu_barrier();
+                rcu_barrier_sched();
         kfree(e);
         return 0;
 }
@@ -476,7 +484,7 @@ static int marker_set_format(struct marker_entry **entry, const char *format)
         hlist_del(&(*entry)->hlist);
         /* Make sure the call_rcu has been executed */
         if ((*entry)->rcu_pending)
-                rcu_barrier();
+                rcu_barrier_sched();
         kfree(*entry);
         *entry = e;
         trace_mark(core_marker_format, "name %s format %s",
@@ -552,7 +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)
 {
@@ -645,17 +653,23 @@ 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.
          */
         if (entry->rcu_pending)
-                rcu_barrier();
+                rcu_barrier_sched();
         old = marker_entry_add_probe(entry, probe, probe_private);
         if (IS_ERR(old)) {
                 ret = PTR_ERR(old);
@@ -666,14 +680,13 @@ 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 */
         smp_wmb();
-#ifdef CONFIG_PREEMPT_RCU
-        synchronize_sched();    /* Until we have the call_rcu_sched() */
-#endif
-        call_rcu(&entry->rcu, free_old_closure);
+        call_rcu_sched(&entry->rcu, free_old_closure);
 end:
         mutex_unlock(&markers_mutex);
         return ret;
@@ -704,7 +717,7 @@ int marker_probe_unregister(const char *name,
         if (!entry)
                 goto end;
         if (entry->rcu_pending)
-                rcu_barrier();
+                rcu_barrier_sched();
         old = marker_entry_remove_probe(entry, probe, probe_private);
         mutex_unlock(&markers_mutex);
         marker_update_probes();         /* may update entry */
@@ -712,14 +725,13 @@ 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 */
         smp_wmb();
-#ifdef CONFIG_PREEMPT_RCU
-        synchronize_sched();    /* Until we have the call_rcu_sched() */
-#endif
-        call_rcu(&entry->rcu, free_old_closure);
+        call_rcu_sched(&entry->rcu, free_old_closure);
         remove_marker(name);    /* Ignore busy error message */
         ret = 0;
 end:
@@ -786,21 +798,20 @@ int marker_probe_unregister_private_data(marker_probe_func *probe,
                 goto end;
         }
         if (entry->rcu_pending)
-                rcu_barrier();
+                rcu_barrier_sched();
         old = marker_entry_remove_probe(entry, NULL, probe_private);
         mutex_unlock(&markers_mutex);
         marker_update_probes();         /* may update entry */
         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 */
         smp_wmb();
-#ifdef CONFIG_PREEMPT_RCU
-        synchronize_sched();    /* Until we have the call_rcu_sched() */
-#endif
-        call_rcu(&entry->rcu, free_old_closure);
+        call_rcu_sched(&entry->rcu, free_old_closure);
         remove_marker(entry->name);     /* Ignore busy error message */
 end:
         mutex_unlock(&markers_mutex);
diff --git a/kernel/module.c b/kernel/module.c
index 5f80478b746d..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);
 
@@ -70,6 +75,9 @@ static DECLARE_WAIT_QUEUE_HEAD(module_wq);
 
 static BLOCKING_NOTIFIER_HEAD(module_notify_list);
 
+/* Bounds of module allocation, for speeding __module_text_address */
+static unsigned long module_addr_min = -1UL, module_addr_max = 0;
+
 int register_module_notifier(struct notifier_block * nb)
 {
         return blocking_notifier_chain_register(&module_notify_list, nb);
@@ -97,7 +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);
 }
 
 /*
@@ -127,6 +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[];
@@ -134,17 +165,19 @@ extern const struct kernel_symbol __start___ksymtab_gpl[];
 extern const struct kernel_symbol __stop___ksymtab_gpl[];
 extern const struct kernel_symbol __start___ksymtab_gpl_future[];
 extern const struct kernel_symbol __stop___ksymtab_gpl_future[];
-extern const struct kernel_symbol __start___ksymtab_unused[];
-extern const struct kernel_symbol __stop___ksymtab_unused[];
-extern const struct kernel_symbol __start___ksymtab_unused_gpl[];
-extern const struct kernel_symbol __stop___ksymtab_unused_gpl[];
 extern const struct kernel_symbol __start___ksymtab_gpl_future[];
 extern const struct kernel_symbol __stop___ksymtab_gpl_future[];
 extern const unsigned long __start___kcrctab[];
 extern const unsigned long __start___kcrctab_gpl[];
 extern const unsigned long __start___kcrctab_gpl_future[];
+#ifdef CONFIG_UNUSED_SYMBOLS
+extern const struct kernel_symbol __start___ksymtab_unused[];
+extern const struct kernel_symbol __stop___ksymtab_unused[];
+extern const struct kernel_symbol __start___ksymtab_unused_gpl[];
+extern const struct kernel_symbol __stop___ksymtab_unused_gpl[];
 extern const unsigned long __start___kcrctab_unused[];
 extern const unsigned long __start___kcrctab_unused_gpl[];
+#endif
 
 #ifndef CONFIG_MODVERSIONS
 #define symversion(base, idx) NULL
@@ -152,152 +185,170 @@ extern const unsigned long __start___kcrctab_unused_gpl[];
 #define symversion(base, idx) ((base != NULL) ? ((base) + (idx)) : NULL)
 #endif
 
-/* lookup symbol in given range of kernel_symbols */
-static const struct kernel_symbol *lookup_symbol(const char *name,
-        const struct kernel_symbol *start,
-        const struct kernel_symbol *stop)
-{
-        const struct kernel_symbol *ks = start;
-        for (; ks < stop; ks++)
-                if (strcmp(ks->name, name) == 0)
-                        return ks;
-        return NULL;
-}
-
-static bool always_ok(bool gplok, bool warn, const char *name)
-{
-        return true;
-}
-
-static bool printk_unused_warning(bool gplok, bool warn, const char *name)
-{
-        if (warn) {
-                printk(KERN_WARNING "Symbol %s is marked as UNUSED, "
-                       "however this module is using it.\n", name);
-                printk(KERN_WARNING
-                       "This symbol will go away in the future.\n");
-                printk(KERN_WARNING
-                       "Please evalute if this is the right api to use and if "
-                       "it really is, submit a report the linux kernel "
-                       "mailinglist together with submitting your code for "
-                       "inclusion.\n");
-        }
-        return true;
-}
-
-static bool gpl_only_unused_warning(bool gplok, bool warn, const char *name)
-{
-        if (!gplok)
-                return false;
-        return printk_unused_warning(gplok, warn, name);
-}
-
-static bool gpl_only(bool gplok, bool warn, const char *name)
-{
-        return gplok;
-}
-
-static bool warn_if_not_gpl(bool gplok, bool warn, const char *name)
-{
-        if (!gplok && warn) {
-                printk(KERN_WARNING "Symbol %s is being used "
-                       "by a non-GPL module, which will not "
-                       "be allowed in the future\n", name);
-                printk(KERN_WARNING "Please see the file "
-                       "Documentation/feature-removal-schedule.txt "
-                       "in the kernel source tree for more details.\n");
-        }
-        return true;
-}
-
 struct symsearch {
         const struct kernel_symbol *start, *stop;
         const unsigned long *crcs;
-        bool (*check)(bool gplok, bool warn, const char *name);
+        enum {
+                NOT_GPL_ONLY,
+                GPL_ONLY,
+                WILL_BE_GPL_ONLY,
+        } licence;
+        bool unused;
 };
 
-/* Look through this array of symbol tables for a symbol match which
- * passes the check function. */
-static const struct kernel_symbol *search_symarrays(const struct symsearch *arr,
-                                                    unsigned int num,
-                                                    const char *name,
-                                                    bool gplok,
-                                                    bool warn,
-                                                    const unsigned long **crc)
+static bool each_symbol_in_section(const struct symsearch *arr,
+                                   unsigned int arrsize,
+                                   struct module *owner,
+                                   bool (*fn)(const struct symsearch *syms,
+                                              struct module *owner,
+                                              unsigned int symnum, void *data),
+                                   void *data)
 {
-        unsigned int i;
-        const struct kernel_symbol *ks;
-
-        for (i = 0; i < num; i++) {
-                ks = lookup_symbol(name, arr[i].start, arr[i].stop);
-                if (!ks || !arr[i].check(gplok, warn, name))
-                        continue;
+        unsigned int i, j;
 
-                if (crc)
-                        *crc = symversion(arr[i].crcs, ks - arr[i].start);
-                return ks;
+        for (j = 0; j < arrsize; j++) {
+                for (i = 0; i < arr[j].stop - arr[j].start; i++)
+                        if (fn(&arr[j], owner, i, data))
+                                return true;
         }
-        return NULL;
+
+        return false;
 }
 
-/* Find a symbol, return value, (optional) crc and (optional) module
- * which owns it */
-static unsigned long find_symbol(const char *name,
-                                 struct module **owner,
-                                 const unsigned long **crc,
-                                 bool gplok,
-                                 bool warn)
+/* Returns true as soon as fn returns true, otherwise false. */
+static bool each_symbol(bool (*fn)(const struct symsearch *arr,
+                                   struct module *owner,
+                                   unsigned int symnum, void *data),
+                        void *data)
 {
         struct module *mod;
-        const struct kernel_symbol *ks;
         const struct symsearch arr[] = {
                 { __start___ksymtab, __stop___ksymtab, __start___kcrctab,
-                  always_ok },
+                  NOT_GPL_ONLY, false },
                 { __start___ksymtab_gpl, __stop___ksymtab_gpl,
-                  __start___kcrctab_gpl, gpl_only },
+                  __start___kcrctab_gpl,
+                  GPL_ONLY, false },
                 { __start___ksymtab_gpl_future, __stop___ksymtab_gpl_future,
-                  __start___kcrctab_gpl_future, warn_if_not_gpl },
+                  __start___kcrctab_gpl_future,
+                  WILL_BE_GPL_ONLY, false },
+#ifdef CONFIG_UNUSED_SYMBOLS
                 { __start___ksymtab_unused, __stop___ksymtab_unused,
-                  __start___kcrctab_unused, printk_unused_warning },
+                  __start___kcrctab_unused,
+                  NOT_GPL_ONLY, true },
                 { __start___ksymtab_unused_gpl, __stop___ksymtab_unused_gpl,
-                  __start___kcrctab_unused_gpl, gpl_only_unused_warning },
+                  __start___kcrctab_unused_gpl,
+                  GPL_ONLY, true },
+#endif
         };
 
-        /* Core kernel first. */
-        ks = search_symarrays(arr, ARRAY_SIZE(arr), name, gplok, warn, crc);
-        if (ks) {
-                if (owner)
-                        *owner = NULL;
-                return ks->value;
-        }
+        if (each_symbol_in_section(arr, ARRAY_SIZE(arr), NULL, fn, data))
+                return true;
 
-        /* Now try modules. */
-        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,
-                          always_ok },
+                          NOT_GPL_ONLY, false },
                         { mod->gpl_syms, mod->gpl_syms + mod->num_gpl_syms,
-                          mod->gpl_crcs, gpl_only },
+                          mod->gpl_crcs,
+                          GPL_ONLY, false },
                         { mod->gpl_future_syms,
                           mod->gpl_future_syms + mod->num_gpl_future_syms,
-                          mod->gpl_future_crcs, warn_if_not_gpl },
+                          mod->gpl_future_crcs,
+                          WILL_BE_GPL_ONLY, false },
+#ifdef CONFIG_UNUSED_SYMBOLS
                         { mod->unused_syms,
                           mod->unused_syms + mod->num_unused_syms,
-                          mod->unused_crcs, printk_unused_warning },
+                          mod->unused_crcs,
+                          NOT_GPL_ONLY, true },
                         { mod->unused_gpl_syms,
                           mod->unused_gpl_syms + mod->num_unused_gpl_syms,
-                          mod->unused_gpl_crcs, gpl_only_unused_warning },
+                          mod->unused_gpl_crcs,
+                          GPL_ONLY, true },
+#endif
                 };
 
-                ks = search_symarrays(arr, ARRAY_SIZE(arr),
-                                      name, gplok, warn, crc);
-                if (ks) {
-                        if (owner)
-                                *owner = mod;
-                        return ks->value;
+                if (each_symbol_in_section(arr, ARRAY_SIZE(arr), mod, fn, data))
+                        return true;
+        }
+        return false;
+}
+
+struct find_symbol_arg {
+        /* Input */
+        const char *name;
+        bool gplok;
+        bool warn;
+
+        /* Output */
+        struct module *owner;
+        const unsigned long *crc;
+        unsigned long value;
+};
+
+static bool find_symbol_in_section(const struct symsearch *syms,
+                                   struct module *owner,
+                                   unsigned int symnum, void *data)
+{
+        struct find_symbol_arg *fsa = data;
+
+        if (strcmp(syms->start[symnum].name, fsa->name) != 0)
+                return false;
+
+        if (!fsa->gplok) {
+                if (syms->licence == GPL_ONLY)
+                        return false;
+                if (syms->licence == WILL_BE_GPL_ONLY && fsa->warn) {
+                        printk(KERN_WARNING "Symbol %s is being used "
+                               "by a non-GPL module, which will not "
+                               "be allowed in the future\n", fsa->name);
+                        printk(KERN_WARNING "Please see the file "
+                               "Documentation/feature-removal-schedule.txt "
+                               "in the kernel source tree for more details.\n");
                 }
         }
 
+#ifdef CONFIG_UNUSED_SYMBOLS
+        if (syms->unused && fsa->warn) {
+                printk(KERN_WARNING "Symbol %s is marked as UNUSED, "
+                       "however this module is using it.\n", fsa->name);
+                printk(KERN_WARNING
+                       "This symbol will go away in the future.\n");
+                printk(KERN_WARNING
+                       "Please evalute if this is the right api to use and if "
+                       "it really is, submit a report the linux kernel "
+                       "mailinglist together with submitting your code for "
+                       "inclusion.\n");
+        }
+#endif
+
+        fsa->owner = owner;
+        fsa->crc = symversion(syms->crcs, symnum);
+        fsa->value = syms->start[symnum].value;
+        return true;
+}
+
+/* Find a symbol, return value, (optional) crc and (optional) module
+ * which owns it */
+static unsigned long find_symbol(const char *name,
+                                 struct module **owner,
+                                 const unsigned long **crc,
+                                 bool gplok,
+                                 bool warn)
+{
+        struct find_symbol_arg fsa;
+
+        fsa.name = name;
+        fsa.gplok = gplok;
+        fsa.warn = warn;
+
+        if (each_symbol(find_symbol_in_section, &fsa)) {
+                if (owner)
+                        *owner = fsa.owner;
+                if (crc)
+                        *crc = fsa.crc;
+                return fsa.value;
+        }
+
         DEBUGP("Failed to find symbol %s\n", name);
         return -ENOENT;
 }
@@ -639,8 +690,8 @@ static int __try_stop_module(void *_sref)
 {
         struct stopref *sref = _sref;
 
-        /* If it's not unused, quit unless we are told to block. */
-        if ((sref->flags & O_NONBLOCK) && module_refcount(sref->mod) != 0) {
+        /* If it's not unused, quit unless we're forcing. */
+        if (module_refcount(sref->mod) != 0) {
                 if (!(*sref->forced = try_force_unload(sref->flags)))
                         return -EWOULDBLOCK;
         }
@@ -652,9 +703,16 @@ static int __try_stop_module(void *_sref)
 
 static int try_stop_module(struct module *mod, int flags, int *forced)
 {
-        struct stopref sref = { mod, flags, forced };
+        if (flags & O_NONBLOCK) {
+                struct stopref sref = { mod, flags, forced };
 
-        return stop_machine_run(__try_stop_module, &sref, NR_CPUS);
+                return stop_machine(__try_stop_module, &sref, NULL);
+        } else {
+                /* We don't need to stop the machine for this. */
+                mod->state = MODULE_STATE_GOING;
+                synchronize_sched();
+                return 0;
+        }
 }
 
 unsigned int module_refcount(struct module *mod)
@@ -754,6 +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:
@@ -893,7 +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);
@@ -1003,7 +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 */
@@ -1143,7 +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);
 }
@@ -1361,17 +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
  */
@@ -1386,7 +1434,7 @@ static int __unlink_module(void *_mod)
 static void free_module(struct module *mod)
 {
         /* Delete from various lists */
-        stop_machine_run(__unlink_module, mod, NR_CPUS);
+        stop_machine(__unlink_module, mod, NULL);
         remove_notes_attrs(mod);
         remove_sect_attrs(mod);
         mod_kobject_remove(mod);
@@ -1399,6 +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);
@@ -1445,8 +1496,10 @@ static int verify_export_symbols(struct module *mod)
                 { mod->syms, mod->num_syms },
                 { mod->gpl_syms, mod->num_gpl_syms },
                 { mod->gpl_future_syms, mod->num_gpl_future_syms },
+#ifdef CONFIG_UNUSED_SYMBOLS
                 { mod->unused_syms, mod->num_unused_syms },
                 { mod->unused_gpl_syms, mod->num_unused_gpl_syms },
+#endif
         };
 
         for (i = 0; i < ARRAY_SIZE(arr); i++) {
@@ -1526,7 +1579,7 @@ static int simplify_symbols(Elf_Shdr *sechdrs,
 }
 
 /* Update size with this section: return offset. */
-static long get_offset(unsigned long *size, Elf_Shdr *sechdr)
+static long get_offset(unsigned int *size, Elf_Shdr *sechdr)
 {
         long ret;
 
@@ -1602,7 +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);
@@ -1659,6 +1712,19 @@ static void setup_modinfo(struct module *mod, Elf_Shdr *sechdrs,
 }
 
 #ifdef CONFIG_KALLSYMS
+
+/* lookup symbol in given range of kernel_symbols */
+static const struct kernel_symbol *lookup_symbol(const char *name,
+        const struct kernel_symbol *start,
+        const struct kernel_symbol *stop)
+{
+        const struct kernel_symbol *ks = start;
+        for (; ks < stop; ks++)
+                if (strcmp(ks->name, name) == 0)
+                        return ks;
+        return NULL;
+}
+
 static int is_exported(const char *name, const struct module *mod)
 {
         if (!mod && lookup_symbol(name, __start___ksymtab, __stop___ksymtab))
@@ -1738,42 +1804,56 @@ 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);
+
+        if (ret) {
+                /* Update module bounds. */
+                if ((unsigned long)ret < module_addr_min)
+                        module_addr_min = (unsigned long)ret;
+                if ((unsigned long)ret + size > module_addr_max)
+                        module_addr_max = (unsigned long)ret + size;
+        }
+        return ret;
+}
+
 /* Allocate and load the module: note that size of section 0 is always
    zero, and we rely on this for optional sections. */
-static struct module *load_module(void __user *umod,
+static noinline struct module *load_module(void __user *umod,
                                   unsigned long len,
                                   const char __user *uargs)
 {
         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;
-        unsigned int unusedindex;
-        unsigned int unusedcrcindex;
-        unsigned int unusedgplindex;
-        unsigned int unusedgplcrcindex;
-        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",
@@ -1837,6 +1917,7 @@ static 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) {
@@ -1846,20 +1927,6 @@ static 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");
-        unusedindex = find_sec(hdr, sechdrs, secstrings, "__ksymtab_unused");
-        unusedgplindex = find_sec(hdr, sechdrs, secstrings, "__ksymtab_unused_gpl");
-        crcindex = find_sec(hdr, sechdrs, secstrings, "__kcrctab");
-        gplcrcindex = find_sec(hdr, sechdrs, secstrings, "__kcrctab_gpl");
-        gplfuturecrcindex = find_sec(hdr, sechdrs, secstrings, "__kcrctab_gpl_future");
-        unusedcrcindex = find_sec(hdr, sechdrs, secstrings, "__kcrctab_unused");
-        unusedgplcrcindex = find_sec(hdr, sechdrs, secstrings, "__kcrctab_unused_gpl");
-        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);
@@ -1897,6 +1964,14 @@ static 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)) {
@@ -1935,7 +2010,7 @@ static struct module *load_module(void __user *umod,
         layout_sections(mod, hdr, sechdrs, secstrings);
 
         /* Do the allocs. */
-        ptr = module_alloc(mod->core_size);
+        ptr = module_alloc_update_bounds(mod->core_size);
         if (!ptr) {
                 err = -ENOMEM;
                 goto free_percpu;
@@ -1943,7 +2018,7 @@ static struct module *load_module(void __user *umod,
         memset(ptr, 0, mod->core_size);
         mod->module_core = ptr;
 
-        ptr = module_alloc(mod->init_size);
+        ptr = module_alloc_update_bounds(mod->init_size);
         if (!ptr && mod->init_size) {
                 err = -ENOMEM;
                 goto free_core;
@@ -2007,48 +2082,65 @@ static 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->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->gpl_future_syms = (void *)sechdrs[gplfutureindex].sh_addr;
-        if (gplfuturecrcindex)
-                mod->gpl_future_crcs = (void *)sechdrs[gplfuturecrcindex].sh_addr;
-
-        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;
+        /* 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->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) ||
-            (mod->num_unused_syms && !unusedcrcindex) ||
-            (mod->num_unused_gpl_syms && !unusedgplcrcindex)) {
+        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 && !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);
                 err = try_to_force_load(mod, "nocrc");
                 if (err)
                         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++) {
@@ -2071,22 +2163,16 @@ static 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,
@@ -2094,11 +2180,29 @@ static 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;
@@ -2122,30 +2226,24 @@ static 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_run(__link_module, mod, NR_CPUS);
-
-        /* 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);
@@ -2163,11 +2261,12 @@ static struct module *load_module(void __user *umod,
         return mod;
 
  unlink:
-        stop_machine_run(__unlink_module, mod, NR_CPUS);
+        stop_machine(__unlink_module, mod, NULL);
         module_arch_cleanup(mod);
  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);
@@ -2220,7 +2319,7 @@ sys_init_module(void __user *umod,
 
         /* Start the module */
         if (mod->init != NULL)
-                ret = mod->init();
+                ret = do_one_initcall(mod->init);
         if (ret < 0) {
                 /* Init routine failed: abort.  Try to protect us from
                    buggy refcounters. */
@@ -2333,7 +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)
@@ -2356,7 +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;
@@ -2380,7 +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;
@@ -2407,7 +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;
@@ -2450,7 +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;
         }
@@ -2459,23 +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;
@@ -2484,10 +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
@@ -2507,12 +2591,30 @@ 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);
         char buf[8];
 
-        seq_printf(m, "%s %lu",
+        seq_printf(m, "%s %u",
                    mod->name, mod->init_size + mod->core_size);
         print_unload_info(m, mod);
 
@@ -2537,13 +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)
 {
@@ -2551,7 +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;
 
@@ -2577,7 +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;
@@ -2595,7 +2717,10 @@ struct module *__module_text_address(unsigned long addr)
 {
         struct module *mod;
 
-        list_for_each_entry(mod, &modules, list)
+        if (addr < module_addr_min || addr > module_addr_max)
+                return NULL;
+
+        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;
@@ -2620,8 +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");
@@ -2646,3 +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/mutex.c b/kernel/mutex.c
index bcdc9ac8ef60..12c779dc65d4 100644
--- a/kernel/mutex.c
+++ b/kernel/mutex.c
@@ -34,6 +34,7 @@
 /***
  * mutex_init - initialize the mutex
  * @lock: the mutex to be initialized
+ * @key: the lock_class_key for the class; used by mutex lock debugging
  *
  * Initialize the mutex to unlocked state.
  *
diff --git a/kernel/notifier.c b/kernel/notifier.c
index 823be11584ef..4282c0a40a57 100644
--- a/kernel/notifier.c
+++ b/kernel/notifier.c
@@ -550,7 +550,7 @@ 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/ns_cgroup.c b/kernel/ns_cgroup.c
index 48d7ed6fc3a4..43c2111cd54d 100644
--- a/kernel/ns_cgroup.c
+++ b/kernel/ns_cgroup.c
@@ -7,6 +7,7 @@
 #include <linux/module.h>
 #include <linux/cgroup.h>
 #include <linux/fs.h>
+#include <linux/proc_fs.h>
 #include <linux/slab.h>
 #include <linux/nsproxy.h>
 
@@ -24,9 +25,12 @@ static inline struct ns_cgroup *cgroup_to_ns(
                             struct ns_cgroup, css);
 }
 
-int ns_cgroup_clone(struct task_struct *task)
+int ns_cgroup_clone(struct task_struct *task, struct pid *pid)
 {
-        return cgroup_clone(task, &ns_subsys);
+        char name[PROC_NUMBUF];
+
+        snprintf(name, PROC_NUMBUF, "%d", pid_vnr(pid));
+        return cgroup_clone(task, &ns_subsys, name);
 }
 
 /*
diff --git a/kernel/nsproxy.c b/kernel/nsproxy.c
index adc785146a1c..1d3ef29a2583 100644
--- a/kernel/nsproxy.c
+++ b/kernel/nsproxy.c
@@ -14,7 +14,6 @@
  */
 
 #include <linux/module.h>
-#include <linux/version.h>
 #include <linux/nsproxy.h>
 #include <linux/init_task.h>
 #include <linux/mnt_namespace.h>
@@ -157,12 +156,6 @@ int copy_namespaces(unsigned long flags, struct task_struct *tsk)
                 goto out;
         }
 
-        err = ns_cgroup_clone(tsk);
-        if (err) {
-                put_nsproxy(new_ns);
-                goto out;
-        }
-
         tsk->nsproxy = new_ns;
 
 out:
@@ -209,7 +202,7 @@ int unshare_nsproxy_namespaces(unsigned long unshare_flags,
                 goto out;
         }
 
-        err = ns_cgroup_clone(current);
+        err = ns_cgroup_clone(current, task_pid(current));
         if (err)
                 put_nsproxy(*new_nsp);
 
diff --git a/kernel/panic.c b/kernel/panic.c
index 425567f45b9f..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(add_taint);
+EXPORT_SYMBOL(test_taint);
 
-static int __init pause_on_oops_setup(char *str)
+unsigned long get_taint(void)
 {
-        pause_on_oops = simple_strtoul(str, NULL, 0);
-        return 1;
+        return tainted_mask;
 }
-__setup("pause_on_oops=", pause_on_oops_setup);
+
+void add_taint(unsigned flag)
+{
+        debug_locks = 0; /* can't trust the integrity of the kernel anymore */
+        set_bit(flag, &tainted_mask);
+}
+EXPORT_SYMBOL(add_taint);
 
 static void spin_msec(int msecs)
 {
@@ -318,6 +335,28 @@ void warn_on_slowpath(const char *file, int line)
         add_taint(TAINT_WARN);
 }
 EXPORT_SYMBOL(warn_on_slowpath);
+
+
+void warn_slowpath(const char *file, int line, const char *fmt, ...)
+{
+        va_list args;
+        char function[KSYM_SYMBOL_LEN];
+        unsigned long caller = (unsigned long)__builtin_return_address(0);
+        sprint_symbol(function, caller);
+
+        printk(KERN_WARNING "------------[ cut here ]------------\n");
+        printk(KERN_WARNING "WARNING: at %s:%d %s()\n", file,
+                line, function);
+        va_start(args, fmt);
+        vprintk(fmt, args);
+        va_end(args);
+
+        print_modules();
+        dump_stack();
+        print_oops_end_marker();
+        add_taint(TAINT_WARN);
+}
+EXPORT_SYMBOL(warn_slowpath);
 #endif
 
 #ifdef CONFIG_CC_STACKPROTECTOR
@@ -331,3 +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/pid.c b/kernel/pid.c
index 30bd5d4b2ac7..064e76afa507 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -309,12 +309,6 @@ struct pid *find_vpid(int nr)
 }
 EXPORT_SYMBOL_GPL(find_vpid);
 
-struct pid *find_pid(int nr)
-{
-        return find_pid_ns(nr, &init_pid_ns);
-}
-EXPORT_SYMBOL_GPL(find_pid);
-
 /*
  * attach_pid() must be called with the tasklist_lock write-held.
  */
@@ -435,6 +429,7 @@ struct pid *find_get_pid(pid_t nr)
 
         return pid;
 }
+EXPORT_SYMBOL_GPL(find_get_pid);
 
 pid_t pid_nr_ns(struct pid *pid, struct pid_namespace *ns)
 {
@@ -482,7 +477,7 @@ EXPORT_SYMBOL(task_session_nr_ns);
 /*
  * Used by proc to find the first pid that is greater then or equal to nr.
  *
- * If there is a pid at nr this function is exactly the same as find_pid.
+ * If there is a pid at nr this function is exactly the same as find_pid_ns.
  */
 struct pid *find_ge_pid(int nr, struct pid_namespace *ns)
 {
@@ -497,7 +492,6 @@ struct pid *find_ge_pid(int nr, struct pid_namespace *ns)
 
         return pid;
 }
-EXPORT_SYMBOL_GPL(find_get_pid);
 
 /*
  * The pid hash table is scaled according to the amount of memory in the
diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c
index 98702b4b8851..fab8ea86fac3 100644
--- a/kernel/pid_namespace.c
+++ b/kernel/pid_namespace.c
@@ -12,6 +12,7 @@
 #include <linux/pid_namespace.h>
 #include <linux/syscalls.h>
 #include <linux/err.h>
+#include <linux/acct.h>
 
 #define BITS_PER_PAGE           (PAGE_SIZE*8)
 
@@ -71,7 +72,7 @@ static struct pid_namespace *create_pid_namespace(unsigned int level)
         struct pid_namespace *ns;
         int i;
 
-        ns = kmem_cache_alloc(pid_ns_cachep, GFP_KERNEL);
+        ns = kmem_cache_zalloc(pid_ns_cachep, GFP_KERNEL);
         if (ns == NULL)
                 goto out;
 
@@ -84,17 +85,13 @@ static struct pid_namespace *create_pid_namespace(unsigned int level)
                 goto out_free_map;
 
         kref_init(&ns->kref);
-        ns->last_pid = 0;
-        ns->child_reaper = NULL;
         ns->level = level;
 
         set_bit(0, ns->pidmap[0].page);
         atomic_set(&ns->pidmap[0].nr_free, BITS_PER_PAGE - 1);
 
-        for (i = 1; i < PIDMAP_ENTRIES; i++) {
-                ns->pidmap[i].page = NULL;
+        for (i = 1; i < PIDMAP_ENTRIES; i++)
                 atomic_set(&ns->pidmap[i].nr_free, BITS_PER_PAGE);
-        }
 
         return ns;
 
@@ -182,9 +179,7 @@ void zap_pid_ns_processes(struct pid_namespace *pid_ns)
                 rc = sys_wait4(-1, NULL, __WALL, NULL);
         } while (rc != -ECHILD);
 
-
-        /* Child reaper for the pid namespace is going away */
-        pid_ns->child_reaper = NULL;
+        acct_exit_ns(pid_ns);
         return;
 }
 
diff --git a/kernel/pm_qos_params.c b/kernel/pm_qos_params.c
index 8cb757026386..dfdec524d1b7 100644
--- a/kernel/pm_qos_params.c
+++ b/kernel/pm_qos_params.c
@@ -24,7 +24,7 @@
  * requirement that the application has is cleaned up when closes the file
  * pointer or exits the pm_qos_object will get an opportunity to clean up.
  *
- * mark gross mgross@linux.intel.com
+ * Mark Gross <mgross@linux.intel.com>
  */
 
 #include <linux/pm_qos_params.h>
@@ -43,7 +43,7 @@
 #include <linux/uaccess.h>
 
 /*
- * locking rule: all changes to target_value or requirements or notifiers lists
+ * locking rule: all changes to requirements or notifiers lists
  * or pm_qos_object list and pm_qos_objects need to happen with pm_qos_lock
  * held, taken with _irqsave.  One lock to rule them all
  */
@@ -66,7 +66,7 @@ struct pm_qos_object {
         struct miscdevice pm_qos_power_miscdev;
         char *name;
         s32 default_value;
-        s32 target_value;
+        atomic_t target_value;
         s32 (*comparitor)(s32, s32);
 };
 
@@ -77,7 +77,7 @@ static struct pm_qos_object cpu_dma_pm_qos = {
         .notifiers = &cpu_dma_lat_notifier,
         .name = "cpu_dma_latency",
         .default_value = 2000 * USEC_PER_SEC,
-        .target_value = 2000 * USEC_PER_SEC,
+        .target_value = ATOMIC_INIT(2000 * USEC_PER_SEC),
         .comparitor = min_compare
 };
 
@@ -87,7 +87,7 @@ static struct pm_qos_object network_lat_pm_qos = {
         .notifiers = &network_lat_notifier,
         .name = "network_latency",
         .default_value = 2000 * USEC_PER_SEC,
-        .target_value = 2000 * USEC_PER_SEC,
+        .target_value = ATOMIC_INIT(2000 * USEC_PER_SEC),
         .comparitor = min_compare
 };
 
@@ -99,7 +99,7 @@ static struct pm_qos_object network_throughput_pm_qos = {
         .notifiers = &network_throughput_notifier,
         .name = "network_throughput",
         .default_value = 0,
-        .target_value = 0,
+        .target_value = ATOMIC_INIT(0),
         .comparitor = max_compare
 };
 
@@ -150,11 +150,11 @@ static void update_target(int target)
                 extreme_value = pm_qos_array[target]->comparitor(
                                 extreme_value, node->value);
         }
-        if (pm_qos_array[target]->target_value != extreme_value) {
+        if (atomic_read(&pm_qos_array[target]->target_value) != extreme_value) {
                 call_notifier = 1;
-                pm_qos_array[target]->target_value = extreme_value;
+                atomic_set(&pm_qos_array[target]->target_value, extreme_value);
                 pr_debug(KERN_ERR "new target for qos %d is %d\n", target,
-                        pm_qos_array[target]->target_value);
+                        atomic_read(&pm_qos_array[target]->target_value));
         }
         spin_unlock_irqrestore(&pm_qos_lock, flags);
 
@@ -193,14 +193,7 @@ static int find_pm_qos_object_by_minor(int minor)
  */
 int pm_qos_requirement(int pm_qos_class)
 {
-        int ret_val;
-        unsigned long flags;
-
-        spin_lock_irqsave(&pm_qos_lock, flags);
-        ret_val = pm_qos_array[pm_qos_class]->target_value;
-        spin_unlock_irqrestore(&pm_qos_lock, flags);
-
-        return ret_val;
+        return atomic_read(&pm_qos_array[pm_qos_class]->target_value);
 }
 EXPORT_SYMBOL_GPL(pm_qos_requirement);
 
@@ -211,8 +204,8 @@ EXPORT_SYMBOL_GPL(pm_qos_requirement);
  * @value: defines the qos request
  *
  * This function inserts a new entry in the pm_qos_class list of requested qos
- * performance charactoistics.  It recomputes the agregate QoS expectations for
- * the pm_qos_class of parrameters.
+ * performance characteristics.  It recomputes the aggregate QoS expectations
+ * for the pm_qos_class of parameters.
  */
 int pm_qos_add_requirement(int pm_qos_class, char *name, s32 value)
 {
@@ -250,10 +243,10 @@ EXPORT_SYMBOL_GPL(pm_qos_add_requirement);
  * @name: identifies the request
  * @value: defines the qos request
  *
- * Updates an existing qos requierement for the pm_qos_class of parameters along
+ * Updates an existing qos requirement for the pm_qos_class of parameters along
  * with updating the target pm_qos_class value.
  *
- * If the named request isn't in the lest then no change is made.
+ * If the named request isn't in the list then no change is made.
  */
 int pm_qos_update_requirement(int pm_qos_class, char *name, s32 new_value)
 {
@@ -287,7 +280,7 @@ EXPORT_SYMBOL_GPL(pm_qos_update_requirement);
  * @pm_qos_class: identifies which list of qos request to us
  * @name: identifies the request
  *
- * Will remove named qos request from pm_qos_class list of parrameters and
+ * Will remove named qos request from pm_qos_class list of parameters and
  * recompute the current target value for the pm_qos_class.
  */
 void pm_qos_remove_requirement(int pm_qos_class, char *name)
@@ -319,7 +312,7 @@ EXPORT_SYMBOL_GPL(pm_qos_remove_requirement);
  * @notifier: notifier block managed by caller.
  *
  * will register the notifier into a notification chain that gets called
- * uppon changes to the pm_qos_class target value.
+ * upon changes to the pm_qos_class target value.
  */
  int pm_qos_add_notifier(int pm_qos_class, struct notifier_block *notifier)
 {
@@ -338,7 +331,7 @@ EXPORT_SYMBOL_GPL(pm_qos_add_notifier);
  * @notifier: notifier block to be removed.
  *
  * will remove the notifier from the notification chain that gets called
- * uppon changes to the pm_qos_class target value.
+ * upon changes to the pm_qos_class target value.
  */
 int pm_qos_remove_notifier(int pm_qos_class, struct notifier_block *notifier)
 {
diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c
index c42a03aef36f..153dcb2639c3 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);
-}
+        struct task_cputime cputime;
 
-
-/*
- * 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);
-
-        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 +1253,86 @@ 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->signal;
+
+        if (unlikely(!sig))
+                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;
+        }
+        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 +1345,31 @@ 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 +1397,9 @@ 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 +1408,7 @@ 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 +1442,14 @@ 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 dbd8398ddb0b..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,
@@ -289,39 +304,33 @@ void do_schedule_next_timer(struct siginfo *info)
                 else
                         schedule_next_timer(timr);
 
-                info->si_overrun = timr->it_overrun_last;
+                info->si_overrun += timr->it_overrun_last;
         }
 
         if (timr)
                 unlock_timer(timr, flags);
 }
 
-int posix_timer_event(struct k_itimer *timr,int si_private)
+int posix_timer_event(struct k_itimer *timr, int si_private)
 {
-        memset(&timr->sigq->info, 0, sizeof(siginfo_t));
+        int shared, ret;
+        /*
+         * FIXME: if ->sigq is queued we can race with
+         * dequeue_signal()->do_schedule_next_timer().
+         *
+         * If dequeue_signal() sees the "right" value of
+         * si_sys_private it calls do_schedule_next_timer().
+         * We re-queue ->sigq and drop ->it_lock().
+         * do_schedule_next_timer() locks the timer
+         * and re-schedules it while ->sigq is pending.
+         * Not really bad, but not that we want.
+         */
         timr->sigq->info.si_sys_private = si_private;
-        /* Send signal to the process that owns this timer.*/
-
-        timr->sigq->info.si_signo = timr->it_sigev_signo;
-        timr->sigq->info.si_errno = 0;
-        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);
 
@@ -433,8 +442,9 @@ 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;
 }
 
@@ -449,9 +459,6 @@ static void release_posix_timer(struct k_itimer *tmr, int it_id_set)
                 spin_unlock_irqrestore(&idr_lock, flags);
         }
         sigqueue_free(tmr->sigq);
-        if (unlikely(tmr->it_process) &&
-            tmr->it_sigev_notify == (SIGEV_SIGNAL|SIGEV_THREAD_ID))
-                put_task_struct(tmr->it_process);
         kmem_cache_free(posix_timers_cache, tmr);
 }
 
@@ -462,11 +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;
 
@@ -484,12 +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)
@@ -520,67 +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;
 }
 
@@ -591,7 +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;
         /*
@@ -599,23 +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;
 }
 
 /*
@@ -662,7 +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) {
                 /*
@@ -756,7 +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);
@@ -765,14 +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;
 }
 
@@ -856,11 +831,9 @@ retry_delete:
          * This keeps any tasks waiting on the spin lock from thinking
          * they got something (see the lock code above).
          */
-        if (timer->it_process) {
-                if (timer->it_sigev_notify == (SIGEV_SIGNAL|SIGEV_THREAD_ID))
-                        put_task_struct(timer->it_process);
-                timer->it_process = NULL;
-        }
+        put_task_struct(timer->it_process);
+        timer->it_process = NULL;
+
         unlock_timer(timer, flags);
         release_posix_timer(timer, IT_ID_SET);
         return 0;
@@ -885,11 +858,9 @@ retry_delete:
          * This keeps any tasks waiting on the spin lock from thinking
          * they got something (see the lock code above).
          */
-        if (timer->it_process) {
-                if (timer->it_sigev_notify == (SIGEV_SIGNAL|SIGEV_THREAD_ID))
-                        put_task_struct(timer->it_process);
-                timer->it_process = NULL;
-        }
+        put_task_struct(timer->it_process);
+        timer->it_process = NULL;
+
         unlock_timer(timer, flags);
         release_posix_timer(timer, IT_ID_SET);
 }
diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig
index b45da40e8d25..dcd165f92a88 100644
--- a/kernel/power/Kconfig
+++ b/kernel/power/Kconfig
@@ -82,7 +82,7 @@ config PM_SLEEP_SMP
 
 config PM_SLEEP
         bool
-        depends on SUSPEND || HIBERNATION
+        depends on SUSPEND || HIBERNATION || XEN_SAVE_RESTORE
         default y
 
 config SUSPEND
@@ -94,6 +94,17 @@ config SUSPEND
           powered and thus its contents are preserved, such as the
           suspend-to-RAM state (e.g. the ACPI S3 state).
 
+config PM_TEST_SUSPEND
+        bool "Test suspend/resume and wakealarm during bootup"
+        depends on SUSPEND && PM_DEBUG && RTC_LIB=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.
+        Enable this with a kernel parameter like "test_suspend=mem".
+
+        You probably want to have your system's RTC driver statically
+        linked, ensuring that it's available when this test runs.
+
 config SUSPEND_FREEZER
         bool "Enable freezer for suspend to RAM/standby" \
                 if ARCH_WANTS_FREEZER_CONTROL || BROKEN
diff --git a/kernel/power/disk.c b/kernel/power/disk.c
index f011e0870b52..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>
@@ -21,6 +22,7 @@
 #include <linux/console.h>
 #include <linux/cpu.h>
 #include <linux/freezer.h>
+#include <linux/ftrace.h>
 
 #include "power.h"
 
@@ -255,7 +257,7 @@ static int create_image(int platform_mode)
 
 int hibernation_snapshot(int platform_mode)
 {
-        int error;
+        int error, ftrace_save;
 
         /* Free memory before shutting down devices. */
         error = swsusp_shrink_memory();
@@ -267,6 +269,7 @@ int hibernation_snapshot(int platform_mode)
                 goto Close;
 
         suspend_console();
+        ftrace_save = __ftrace_enabled_save();
         error = device_suspend(PMSG_FREEZE);
         if (error)
                 goto Recover_platform;
@@ -296,6 +299,7 @@ int hibernation_snapshot(int platform_mode)
  Resume_devices:
         device_resume(in_suspend ?
                 (error ? PMSG_RECOVER : PMSG_THAW) : PMSG_RESTORE);
+        __ftrace_enabled_restore(ftrace_save);
         resume_console();
  Close:
         platform_end(platform_mode);
@@ -366,10 +370,11 @@ static int resume_target_kernel(void)
 
 int hibernation_restore(int platform_mode)
 {
-        int error;
+        int error, ftrace_save;
 
         pm_prepare_console();
         suspend_console();
+        ftrace_save = __ftrace_enabled_save();
         error = device_suspend(PMSG_QUIESCE);
         if (error)
                 goto Finish;
@@ -384,6 +389,7 @@ int hibernation_restore(int platform_mode)
         platform_restore_cleanup(platform_mode);
         device_resume(PMSG_RECOVER);
  Finish:
+        __ftrace_enabled_restore(ftrace_save);
         resume_console();
         pm_restore_console();
         return error;
@@ -396,7 +402,7 @@ int hibernation_restore(int platform_mode)
 
 int hibernation_platform_enter(void)
 {
-        int error;
+        int error, ftrace_save;
 
         if (!hibernation_ops)
                 return -ENOSYS;
@@ -411,6 +417,7 @@ int hibernation_platform_enter(void)
                 goto Close;
 
         suspend_console();
+        ftrace_save = __ftrace_enabled_save();
         error = device_suspend(PMSG_HIBERNATE);
         if (error) {
                 if (hibernation_ops->recover)
@@ -445,6 +452,7 @@ int hibernation_platform_enter(void)
         hibernation_ops->finish();
  Resume_devices:
         device_resume(PMSG_RESTORE);
+        __ftrace_enabled_restore(ftrace_save);
         resume_console();
  Close:
         hibernation_ops->end();
@@ -513,6 +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)
@@ -551,6 +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();
@@ -627,6 +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;
@@ -634,7 +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;
         }
 
@@ -649,6 +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 3398f4651aa1..19122cf6d827 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>
@@ -21,6 +22,7 @@
 #include <linux/freezer.h>
 #include <linux/vmstat.h>
 #include <linux/syscalls.h>
+#include <linux/ftrace.h>
 
 #include "power.h"
 
@@ -132,6 +134,61 @@ static inline int suspend_test(int level) { return 0; }
 
 #ifdef CONFIG_SUSPEND
 
+#ifdef CONFIG_PM_TEST_SUSPEND
+
+/*
+ * We test the system suspend code by setting an RTC wakealarm a short
+ * time in the future, then suspending.  Suspending the devices won't
+ * normally take long ... some systems only need a few milliseconds.
+ *
+ * The time it takes is system-specific though, so when we test this
+ * during system bootup we allow a LOT of time.
+ */
+#define TEST_SUSPEND_SECONDS    5
+
+static unsigned long suspend_test_start_time;
+
+static void suspend_test_start(void)
+{
+        /* FIXME Use better timebase than "jiffies", ideally a clocksource.
+         * What we want is a hardware counter that will work correctly even
+         * during the irqs-are-off stages of the suspend/resume cycle...
+         */
+        suspend_test_start_time = jiffies;
+}
+
+static void suspend_test_finish(const char *label)
+{
+        long nj = jiffies - suspend_test_start_time;
+        unsigned msec;
+
+        msec = jiffies_to_msecs(abs(nj));
+        pr_info("PM: %s took %d.%03d seconds\n", label,
+                        msec / 1000, msec % 1000);
+
+        /* Warning on suspend means the RTC alarm period needs to be
+         * larger -- the system was sooo slooowwww to suspend that the
+         * alarm (should have) fired before the system went to sleep!
+         *
+         * Warning on either suspend or resume also means the system
+         * 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));
+}
+
+#else
+
+static void suspend_test_start(void)
+{
+}
+
+static void suspend_test_finish(const char *label)
+{
+}
+
+#endif
+
 /* This is just an arbitrary number */
 #define FREE_PAGE_NUMBER (100)
 
@@ -181,6 +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;
@@ -200,6 +261,7 @@ static int suspend_prepare(void)
 
  Thaw:
         suspend_thaw_processes();
+        usermodehelper_enable();
  Finish:
         pm_notifier_call_chain(PM_POST_SUSPEND);
         pm_restore_console();
@@ -255,7 +317,7 @@ static int suspend_enter(suspend_state_t state)
  */
 int suspend_devices_and_enter(suspend_state_t state)
 {
-        int error;
+        int error, ftrace_save;
 
         if (!suspend_ops)
                 return -ENOSYS;
@@ -266,12 +328,14 @@ int suspend_devices_and_enter(suspend_state_t state)
                         goto Close;
         }
         suspend_console();
+        ftrace_save = __ftrace_enabled_save();
+        suspend_test_start();
         error = device_suspend(PMSG_SUSPEND);
         if (error) {
                 printk(KERN_ERR "PM: Some devices failed to suspend\n");
                 goto Recover_platform;
         }
-
+        suspend_test_finish("suspend devices");
         if (suspend_test(TEST_DEVICES))
                 goto Recover_platform;
 
@@ -293,7 +357,10 @@ int suspend_devices_and_enter(suspend_state_t state)
         if (suspend_ops->finish)
                 suspend_ops->finish();
  Resume_devices:
+        suspend_test_start();
         device_resume(PMSG_RESUME);
+        suspend_test_finish("resume devices");
+        __ftrace_enabled_restore(ftrace_save);
         resume_console();
  Close:
         if (suspend_ops->end)
@@ -315,6 +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();
 }
@@ -521,3 +589,144 @@ static int __init pm_init(void)
 }
 
 core_initcall(pm_init);
+
+
+#ifdef CONFIG_PM_TEST_SUSPEND
+
+#include <linux/rtc.h>
+
+/*
+ * To test system suspend, we need a hands-off mechanism to resume the
+ * system.  RTCs wake alarms are a common self-contained mechanism.
+ */
+
+static void __init test_wakealarm(struct rtc_device *rtc, suspend_state_t state)
+{
+        static char err_readtime[] __initdata =
+                KERN_ERR "PM: can't read %s time, err %d\n";
+        static char err_wakealarm [] __initdata =
+                KERN_ERR "PM: can't set %s wakealarm, err %d\n";
+        static char err_suspend[] __initdata =
+                KERN_ERR "PM: suspend test failed, error %d\n";
+        static char info_test[] __initdata =
+                KERN_INFO "PM: test RTC wakeup from '%s' suspend\n";
+
+        unsigned long           now;
+        struct rtc_wkalrm       alm;
+        int                     status;
+
+        /* this may fail if the RTC hasn't been initialized */
+        status = rtc_read_time(rtc, &alm.time);
+        if (status < 0) {
+                printk(err_readtime, rtc->dev.bus_id, status);
+                return;
+        }
+        rtc_tm_to_time(&alm.time, &now);
+
+        memset(&alm, 0, sizeof alm);
+        rtc_time_to_tm(now + TEST_SUSPEND_SECONDS, &alm.time);
+        alm.enabled = true;
+
+        status = rtc_set_alarm(rtc, &alm);
+        if (status < 0) {
+                printk(err_wakealarm, rtc->dev.bus_id, status);
+                return;
+        }
+
+        if (state == PM_SUSPEND_MEM) {
+                printk(info_test, pm_states[state]);
+                status = pm_suspend(state);
+                if (status == -ENODEV)
+                        state = PM_SUSPEND_STANDBY;
+        }
+        if (state == PM_SUSPEND_STANDBY) {
+                printk(info_test, pm_states[state]);
+                status = pm_suspend(state);
+        }
+        if (status < 0)
+                printk(err_suspend, status);
+
+        /* Some platforms can't detect that the alarm triggered the
+         * wakeup, or (accordingly) disable it after it afterwards.
+         * It's supposed to give oneshot behavior; cope.
+         */
+        alm.enabled = false;
+        rtc_set_alarm(rtc, &alm);
+}
+
+static int __init has_wakealarm(struct device *dev, void *name_ptr)
+{
+        struct rtc_device *candidate = to_rtc_device(dev);
+
+        if (!candidate->ops->set_alarm)
+                return 0;
+        if (!device_may_wakeup(candidate->dev.parent))
+                return 0;
+
+        *(char **)name_ptr = dev->bus_id;
+        return 1;
+}
+
+/*
+ * Kernel options like "test_suspend=mem" force suspend/resume sanity tests
+ * at startup time.  They're normally disabled, for faster boot and because
+ * we can't know which states really work on this particular system.
+ */
+static suspend_state_t test_state __initdata = PM_SUSPEND_ON;
+
+static char warn_bad_state[] __initdata =
+        KERN_WARNING "PM: can't test '%s' suspend state\n";
+
+static int __init setup_test_suspend(char *value)
+{
+        unsigned i;
+
+        /* "=mem" ==> "mem" */
+        value++;
+        for (i = 0; i < PM_SUSPEND_MAX; i++) {
+                if (!pm_states[i])
+                        continue;
+                if (strcmp(pm_states[i], value) != 0)
+                        continue;
+                test_state = (__force suspend_state_t) i;
+                return 0;
+        }
+        printk(warn_bad_state, value);
+        return 0;
+}
+__setup("test_suspend", setup_test_suspend);
+
+static int __init test_suspend(void)
+{
+        static char             warn_no_rtc[] __initdata =
+                KERN_WARNING "PM: no wakealarm-capable RTC driver is ready\n";
+
+        char                    *pony = NULL;
+        struct rtc_device       *rtc = NULL;
+
+        /* PM is initialized by now; is that state testable? */
+        if (test_state == PM_SUSPEND_ON)
+                goto done;
+        if (!valid_state(test_state)) {
+                printk(warn_bad_state, pm_states[test_state]);
+                goto done;
+        }
+
+        /* RTCs have initialized by now too ... can we use one? */
+        class_find_device(rtc_class, NULL, &pony, has_wakealarm);
+        if (pony)
+                rtc = rtc_class_open(pony);
+        if (!rtc) {
+                printk(warn_no_rtc);
+                goto done;
+        }
+
+        /* go for it */
+        test_wakealarm(rtc, test_state);
+        rtc_class_close(rtc);
+done:
+        return 0;
+}
+late_initcall(test_suspend);
+
+#endif /* CONFIG_PM_TEST_SUSPEND */
diff --git a/kernel/power/power.h b/kernel/power/power.h
index 700f44ec8406..46b5ec7a3afb 100644
--- a/kernel/power/power.h
+++ b/kernel/power/power.h
@@ -53,8 +53,6 @@ extern int hibernation_platform_enter(void);
 
 extern int pfn_is_nosave(unsigned long);
 
-extern struct mutex pm_mutex;
-
 #define power_attr(_name) \
 static struct kobj_attribute _name##_attr = {   \
         .attr   = {                             \
@@ -155,7 +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/poweroff.c b/kernel/power/poweroff.c
index 678ec736076b..72016f051477 100644
--- a/kernel/power/poweroff.c
+++ b/kernel/power/poweroff.c
@@ -10,6 +10,7 @@
 #include <linux/pm.h>
 #include <linux/workqueue.h>
 #include <linux/reboot.h>
+#include <linux/cpumask.h>
 
 /*
  * When the user hits Sys-Rq o to power down the machine this is the
@@ -25,7 +26,8 @@ static DECLARE_WORK(poweroff_work, do_poweroff);
 
 static void handle_poweroff(int key, struct tty_struct *tty)
 {
-        schedule_work(&poweroff_work);
+        /* run sysrq poweroff on boot cpu */
+        schedule_work_on(first_cpu(cpu_online_map), &poweroff_work);
 }
 
 static struct sysrq_key_op      sysrq_poweroff_op = {
diff --git a/kernel/power/process.c b/kernel/power/process.c
index 5fb87652f214..ca634019497a 100644
--- a/kernel/power/process.c
+++ b/kernel/power/process.c
@@ -28,128 +28,13 @@ 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;
         unsigned long end_time;
         unsigned int todo;
         struct timeval start, end;
-        s64 elapsed_csecs64;
+        u64 elapsed_csecs64;
         unsigned int elapsed_csecs;
 
         do_gettimeofday(&start);
@@ -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/snapshot.c b/kernel/power/snapshot.c
index 5f91a07c4eac..5d2ab836e998 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -205,8 +205,7 @@ static void chain_free(struct chain_allocator *ca, int clear_page_nosave)
  *      objects.  The main list's elements are of type struct zone_bitmap
  *      and each of them corresonds to one zone.  For each zone bitmap
  *      object there is a list of objects of type struct bm_block that
- *      represent each blocks of bit chunks in which information is
- *      stored.
+ *      represent each blocks of bitmap in which information is stored.
  *
  *      struct memory_bitmap contains a pointer to the main list of zone
  *      bitmap objects, a struct bm_position used for browsing the bitmap,
@@ -224,26 +223,27 @@ static void chain_free(struct chain_allocator *ca, int clear_page_nosave)
  *      pfns that correspond to the start and end of the represented zone.
  *
  *      struct bm_block contains a pointer to the memory page in which
- *      information is stored (in the form of a block of bit chunks
- *      of type unsigned long each).  It also contains the pfns that
- *      correspond to the start and end of the represented memory area and
- *      the number of bit chunks in the block.
+ *      information is stored (in the form of a block of bitmap)
+ *      It also contains the pfns that correspond to the start and end of
+ *      the represented memory area.
  */
 
 #define BM_END_OF_MAP   (~0UL)
 
-#define BM_CHUNKS_PER_BLOCK     (PAGE_SIZE / sizeof(long))
-#define BM_BITS_PER_CHUNK       (sizeof(long) << 3)
 #define BM_BITS_PER_BLOCK       (PAGE_SIZE << 3)
 
 struct bm_block {
         struct bm_block *next;          /* next element of the list */
         unsigned long start_pfn;        /* pfn represented by the first bit */
         unsigned long end_pfn;  /* pfn represented by the last bit plus 1 */
-        unsigned int size;      /* number of bit chunks */
-        unsigned long *data;    /* chunks of bits representing pages */
+        unsigned long *data;    /* bitmap representing pages */
 };
 
+static inline unsigned long bm_block_bits(struct bm_block *bb)
+{
+        return bb->end_pfn - bb->start_pfn;
+}
+
 struct zone_bitmap {
         struct zone_bitmap *next;       /* next element of the list */
         unsigned long start_pfn;        /* minimal pfn in this zone */
@@ -257,7 +257,6 @@ struct zone_bitmap {
 struct bm_position {
         struct zone_bitmap *zone_bm;
         struct bm_block *block;
-        int chunk;
         int bit;
 };
 
@@ -272,12 +271,6 @@ struct memory_bitmap {
 
 /* Functions that operate on memory bitmaps */
 
-static inline void memory_bm_reset_chunk(struct memory_bitmap *bm)
-{
-        bm->cur.chunk = 0;
-        bm->cur.bit = -1;
-}
-
 static void memory_bm_position_reset(struct memory_bitmap *bm)
 {
         struct zone_bitmap *zone_bm;
@@ -285,7 +278,7 @@ static void memory_bm_position_reset(struct memory_bitmap *bm)
         zone_bm = bm->zone_bm_list;
         bm->cur.zone_bm = zone_bm;
         bm->cur.block = zone_bm->bm_blocks;
-        memory_bm_reset_chunk(bm);
+        bm->cur.bit = 0;
 }
 
 static void memory_bm_free(struct memory_bitmap *bm, int clear_nosave_free);
@@ -394,12 +387,10 @@ memory_bm_create(struct memory_bitmap *bm, gfp_t gfp_mask, int safe_needed)
                         bb->start_pfn = pfn;
                         if (nr >= BM_BITS_PER_BLOCK) {
                                 pfn += BM_BITS_PER_BLOCK;
-                                bb->size = BM_CHUNKS_PER_BLOCK;
                                 nr -= BM_BITS_PER_BLOCK;
                         } else {
                                 /* This is executed only once in the loop */
                                 pfn += nr;
-                                bb->size = DIV_ROUND_UP(nr, BM_BITS_PER_CHUNK);
                         }
                         bb->end_pfn = pfn;
                         bb = bb->next;
@@ -478,8 +469,8 @@ static int memory_bm_find_bit(struct memory_bitmap *bm, unsigned long pfn,
         }
         zone_bm->cur_block = bb;
         pfn -= bb->start_pfn;
-        *bit_nr = pfn % BM_BITS_PER_CHUNK;
-        *addr = bb->data + pfn / BM_BITS_PER_CHUNK;
+        *bit_nr = pfn;
+        *addr = bb->data;
         return 0;
 }
 
@@ -528,36 +519,6 @@ static int memory_bm_test_bit(struct memory_bitmap *bm, unsigned long pfn)
         return test_bit(bit, addr);
 }
 
-/* Two auxiliary functions for memory_bm_next_pfn */
-
-/* Find the first set bit in the given chunk, if there is one */
-
-static inline int next_bit_in_chunk(int bit, unsigned long *chunk_p)
-{
-        bit++;
-        while (bit < BM_BITS_PER_CHUNK) {
-                if (test_bit(bit, chunk_p))
-                        return bit;
-
-                bit++;
-        }
-        return -1;
-}
-
-/* Find a chunk containing some bits set in given block of bits */
-
-static inline int next_chunk_in_block(int n, struct bm_block *bb)
-{
-        n++;
-        while (n < bb->size) {
-                if (bb->data[n])
-                        return n;
-
-                n++;
-        }
-        return -1;
-}
-
 /**
  *      memory_bm_next_pfn - find the pfn that corresponds to the next set bit
  *      in the bitmap @bm.  If the pfn cannot be found, BM_END_OF_MAP is
@@ -571,40 +532,33 @@ static unsigned long memory_bm_next_pfn(struct memory_bitmap *bm)
 {
         struct zone_bitmap *zone_bm;
         struct bm_block *bb;
-        int chunk;
         int bit;
 
         do {
                 bb = bm->cur.block;
                 do {
-                        chunk = bm->cur.chunk;
                         bit = bm->cur.bit;
-                        do {
-                                bit = next_bit_in_chunk(bit, bb->data + chunk);
-                                if (bit >= 0)
-                                        goto Return_pfn;
-
-                                chunk = next_chunk_in_block(chunk, bb);
-                                bit = -1;
-                        } while (chunk >= 0);
+                        bit = find_next_bit(bb->data, bm_block_bits(bb), bit);
+                        if (bit < bm_block_bits(bb))
+                                goto Return_pfn;
+
                         bb = bb->next;
                         bm->cur.block = bb;
-                        memory_bm_reset_chunk(bm);
+                        bm->cur.bit = 0;
                 } while (bb);
                 zone_bm = bm->cur.zone_bm->next;
                 if (zone_bm) {
                         bm->cur.zone_bm = zone_bm;
                         bm->cur.block = zone_bm->bm_blocks;
-                        memory_bm_reset_chunk(bm);
+                        bm->cur.bit = 0;
                 }
         } while (zone_bm);
         memory_bm_position_reset(bm);
         return BM_END_OF_MAP;
 
  Return_pfn:
-        bm->cur.chunk = chunk;
-        bm->cur.bit = bit;
-        return bb->start_pfn + chunk * BM_BITS_PER_CHUNK + bit;
+        bm->cur.bit = bit + 1;
+        return bb->start_pfn + bit;
 }
 
 /**
diff --git a/kernel/power/swap.c b/kernel/power/swap.c
index a0abf9a463f9..b7713b53d07a 100644
--- a/kernel/power/swap.c
+++ b/kernel/power/swap.c
@@ -14,7 +14,6 @@
 #include <linux/module.h>
 #include <linux/file.h>
 #include <linux/utsname.h>
-#include <linux/version.h>
 #include <linux/delay.h>
 #include <linux/bitops.h>
 #include <linux/genhd.h>
@@ -173,13 +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;
 }
@@ -427,7 +426,7 @@ int swsusp_write(unsigned int flags)
 
         release_swap_writer(&handle);
  out:
-        swsusp_close();
+        swsusp_close(FMODE_WRITE);
         return error;
 }
 
@@ -575,7 +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");
@@ -610,7 +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 {
@@ -627,14 +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 07ad9e7f7a66..6341af77eb65 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>
@@ -577,9 +577,6 @@ 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 +590,8 @@ 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, ...)
@@ -933,7 +932,7 @@ void suspend_console(void)
 {
         if (!console_suspend_enabled)
                 return;
-        printk("Suspending console(s)\n");
+        printk("Suspending console(s) (use no_console_suspend to debug)\n");
         acquire_console_sem();
         console_suspended = 1;
 }
@@ -982,10 +981,25 @@ 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;
 }
 
 /**
@@ -1291,46 +1305,19 @@ 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
+
 /*
  * printk rate limiting, lifted from the networking subsystem.
  *
- * This enforces a rate limit: not more than one kernel message
- * every printk_ratelimit_jiffies to make a denial-of-service
- * attack impossible.
+ * This enforces a rate limit: not more than 10 kernel messages
+ * every 5s to make a denial-of-service attack impossible.
  */
-int __printk_ratelimit(int ratelimit_jiffies, int ratelimit_burst)
-{
-        return __ratelimit(ratelimit_jiffies, ratelimit_burst);
-}
-EXPORT_SYMBOL(__printk_ratelimit);
-
-/* minimum time in jiffies between messages */
-int printk_ratelimit_jiffies = 5 * HZ;
-
-/* number of messages we send before ratelimiting */
-int printk_ratelimit_burst = 10;
+DEFINE_RATELIMIT_STATE(printk_ratelimit_state, 5 * HZ, 10);
 
 int printk_ratelimit(void)
 {
-        return __printk_ratelimit(printk_ratelimit_jiffies,
-                                printk_ratelimit_burst);
+        return __ratelimit(&printk_ratelimit_state);
 }
 EXPORT_SYMBOL(printk_ratelimit);
 
diff --git a/kernel/profile.c b/kernel/profile.c
index 58926411eb2a..a9e422df6bf6 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))) {
@@ -100,20 +102,37 @@ static int __init profile_setup(char *str)
 __setup("profile=", profile_setup);
 
 
-void __init profile_init(void)
+int 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 */
 
-#ifdef CONFIG_PROFILING
-
 static BLOCKING_NOTIFIER_HEAD(task_exit_notifier);
 static ATOMIC_NOTIFIER_HEAD(task_free_notifier);
 static BLOCKING_NOTIFIER_HEAD(munmap_notifier);
@@ -203,8 +222,6 @@ void unregister_timer_hook(int (*hook)(struct pt_regs *))
 }
 EXPORT_SYMBOL_GPL(unregister_timer_hook);
 
-#endif /* CONFIG_PROFILING */
-
 
 #ifdef CONFIG_SMP
 /*
@@ -531,7 +548,7 @@ static void __init profile_nop(void *unused)
 {
 }
 
-static int __init create_hash_tables(void)
+static int create_hash_tables(void)
 {
         int cpu;
 
@@ -579,14 +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 8392a9da6450..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)) {
@@ -107,7 +107,7 @@ int ptrace_check_attach(struct task_struct *child, int kill)
         read_unlock(&tasklist_lock);
 
         if (!ret && !kill)
-                wait_task_inactive(child);
+                ret = wait_task_inactive(child, TASK_TRACED) ? 0 : -ESRCH;
 
         /* All systems go.. */
         return ret;
@@ -140,7 +140,7 @@ int __ptrace_may_access(struct task_struct *task, unsigned int mode)
         if (!dumpable && !capable(CAP_SYS_PTRACE))
                 return -EPERM;
 
-        return security_ptrace(current, task, mode);
+        return security_ptrace_may_access(task, mode);
 }
 
 bool ptrace_may_access(struct task_struct *task, unsigned int mode)
@@ -499,8 +499,7 @@ repeat:
                         goto repeat;
                 }
 
-                ret = security_ptrace(current->parent, current,
-                                      PTRACE_MODE_ATTACH);
+                ret = security_ptrace_traceme(current->parent);
 
                 /*
                  * Set the ptrace bit in the process ptrace flags.
diff --git a/kernel/rcuclassic.c b/kernel/rcuclassic.c
index 16eeeaa9d618..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;
                 /*
@@ -91,8 +97,8 @@ static void force_quiescent_state(struct rcu_data *rdp,
                  * rdp->cpu is the current cpu.
                  *
                  * cpu_online_map is updated by the _cpu_down()
-                 * using stop_machine_run(). Since we're in irqs disabled
-                 * section, stop_machine_run() is not exectuting, hence
+                 * using __stop_machine(). Since we're in irqs disabled
+                 * section, __stop_machine() is not exectuting, hence
                  * the cpu_online_map is stable.
                  *
                  * However,  a cpu might have been offlined _just_ before
@@ -106,9 +112,10 @@ static void force_quiescent_state(struct rcu_data *rdp,
                  */
                 cpus_and(cpumask, rcp->cpumask, cpu_online_map);
                 cpu_clear(rdp->cpu, cpumask);
-                for_each_cpu_mask(cpu, cpumask)
+                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 f14f372cf6f5..ad63af8b2521 100644
--- a/kernel/rcupdate.c
+++ b/kernel/rcupdate.c
@@ -77,6 +77,7 @@ void wakeme_after_rcu(struct rcu_head  *head)
  * sections are delimited by rcu_read_lock() and rcu_read_unlock(),
  * and may be nested.
  */
+void synchronize_rcu(void);     /* Makes kernel-doc tools happy */
 synchronize_rcu_xxx(synchronize_rcu, call_rcu)
 EXPORT_SYMBOL_GPL(synchronize_rcu);
 
@@ -118,18 +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 6f62b77d93c4..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.
@@ -756,7 +748,7 @@ rcu_try_flip_idle(void)
 
         /* Now ask each CPU for acknowledgement of the flip. */
 
-        for_each_cpu_mask(cpu, rcu_cpu_online_map) {
+        for_each_cpu_mask_nr(cpu, rcu_cpu_online_map) {
                 per_cpu(rcu_flip_flag, cpu) = rcu_flipped;
                 dyntick_save_progress_counter(cpu);
         }
@@ -774,7 +766,7 @@ rcu_try_flip_waitack(void)
         int cpu;
 
         RCU_TRACE_ME(rcupreempt_trace_try_flip_a1);
-        for_each_cpu_mask(cpu, rcu_cpu_online_map)
+        for_each_cpu_mask_nr(cpu, rcu_cpu_online_map)
                 if (rcu_try_flip_waitack_needed(cpu) &&
                     per_cpu(rcu_flip_flag, cpu) != rcu_flip_seen) {
                         RCU_TRACE_ME(rcupreempt_trace_try_flip_ae1);
@@ -806,7 +798,7 @@ rcu_try_flip_waitzero(void)
         /* Check to see if the sum of the "last" counters is zero. */
 
         RCU_TRACE_ME(rcupreempt_trace_try_flip_z1);
-        for_each_cpu_mask(cpu, rcu_cpu_online_map)
+        for_each_cpu_mask_nr(cpu, rcu_cpu_online_map)
                 sum += RCU_DATA_CPU(cpu)->rcu_flipctr[lastidx];
         if (sum != 0) {
                 RCU_TRACE_ME(rcupreempt_trace_try_flip_ze1);
@@ -821,7 +813,7 @@ rcu_try_flip_waitzero(void)
         smp_mb();  /*  ^^^^^^^^^^^^ */
 
         /* Call for a memory barrier from each CPU. */
-        for_each_cpu_mask(cpu, rcu_cpu_online_map) {
+        for_each_cpu_mask_nr(cpu, rcu_cpu_online_map) {
                 per_cpu(rcu_mb_flag, cpu) = rcu_mb_needed;
                 dyntick_save_progress_counter(cpu);
         }
@@ -841,7 +833,7 @@ rcu_try_flip_waitmb(void)
         int cpu;
 
         RCU_TRACE_ME(rcupreempt_trace_try_flip_m1);
-        for_each_cpu_mask(cpu, rcu_cpu_online_map)
+        for_each_cpu_mask_nr(cpu, rcu_cpu_online_map)
                 if (rcu_try_flip_waitmb_needed(cpu) &&
                     per_cpu(rcu_mb_flag, cpu) != rcu_mb_done) {
                         RCU_TRACE_ME(rcupreempt_trace_try_flip_me1);
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 7de644cdec43..8d13a7855c08 100644
--- a/kernel/relay.c
+++ b/kernel/relay.c
@@ -407,6 +407,35 @@ void relay_reset(struct rchan *chan)
 }
 EXPORT_SYMBOL_GPL(relay_reset);
 
+static inline void relay_set_buf_dentry(struct rchan_buf *buf,
+                                        struct dentry *dentry)
+{
+        buf->dentry = dentry;
+        buf->dentry->d_inode->i_size = buf->early_bytes;
+}
+
+static struct dentry *relay_create_buf_file(struct rchan *chan,
+                                            struct rchan_buf *buf,
+                                            unsigned int cpu)
+{
+        struct dentry *dentry;
+        char *tmpname;
+
+        tmpname = kzalloc(NAME_MAX + 1, GFP_KERNEL);
+        if (!tmpname)
+                return NULL;
+        snprintf(tmpname, NAME_MAX, "%s%d", chan->base_filename, cpu);
+
+        /* Create file in fs */
+        dentry = chan->cb->create_buf_file(tmpname, chan->parent,
+                                           S_IRUSR, buf,
+                                           &chan->is_global);
+
+        kfree(tmpname);
+
+        return dentry;
+}
+
 /*
  *      relay_open_buf - create a new relay channel buffer
  *
@@ -416,45 +445,34 @@ static struct rchan_buf *relay_open_buf(struct rchan *chan, unsigned int cpu)
 {
         struct rchan_buf *buf = NULL;
         struct dentry *dentry;
-        char *tmpname;
 
         if (chan->is_global)
                 return chan->buf[0];
 
-        tmpname = kzalloc(NAME_MAX + 1, GFP_KERNEL);
-        if (!tmpname)
-                goto end;
-        snprintf(tmpname, NAME_MAX, "%s%d", chan->base_filename, cpu);
-
         buf = relay_create_buf(chan);
         if (!buf)
-                goto free_name;
+                return NULL;
+
+        if (chan->has_base_filename) {
+                dentry = relay_create_buf_file(chan, buf, cpu);
+                if (!dentry)
+                        goto free_buf;
+                relay_set_buf_dentry(buf, dentry);
+        }
 
         buf->cpu = cpu;
         __relay_reset(buf, 1);
 
-        /* Create file in fs */
-        dentry = chan->cb->create_buf_file(tmpname, chan->parent, S_IRUSR,
-                                           buf, &chan->is_global);
-        if (!dentry)
-                goto free_buf;
-
-        buf->dentry = dentry;
-
         if(chan->is_global) {
                 chan->buf[0] = buf;
                 buf->cpu = 0;
         }
 
-        goto free_name;
+        return buf;
 
 free_buf:
         relay_destroy_buf(buf);
-        buf = NULL;
-free_name:
-        kfree(tmpname);
-end:
-        return buf;
+        return NULL;
 }
 
 /**
@@ -537,8 +555,8 @@ static int __cpuinit relay_hotcpu_callback(struct notifier_block *nb,
 
 /**
  *      relay_open - create a new relay channel
- *      @base_filename: base name of files to create
- *      @parent: dentry of parent directory, %NULL for root directory
+ *      @base_filename: base name of files to create, %NULL for buffering only
+ *      @parent: dentry of parent directory, %NULL for root directory or buffer
  *      @subbuf_size: size of sub-buffers
  *      @n_subbufs: number of sub-buffers
  *      @cb: client callback functions
@@ -560,8 +578,6 @@ struct rchan *relay_open(const char *base_filename,
 {
         unsigned int i;
         struct rchan *chan;
-        if (!base_filename)
-                return NULL;
 
         if (!(subbuf_size && n_subbufs))
                 return NULL;
@@ -576,7 +592,10 @@ struct rchan *relay_open(const char *base_filename,
         chan->alloc_size = FIX_SIZE(subbuf_size * n_subbufs);
         chan->parent = parent;
         chan->private_data = private_data;
-        strlcpy(chan->base_filename, base_filename, NAME_MAX);
+        if (base_filename) {
+                chan->has_base_filename = 1;
+                strlcpy(chan->base_filename, base_filename, NAME_MAX);
+        }
         setup_callbacks(chan, cb);
         kref_init(&chan->kref);
 
@@ -604,6 +623,94 @@ free_bufs:
 }
 EXPORT_SYMBOL_GPL(relay_open);
 
+struct rchan_percpu_buf_dispatcher {
+        struct rchan_buf *buf;
+        struct dentry *dentry;
+};
+
+/* Called in atomic context. */
+static void __relay_set_buf_dentry(void *info)
+{
+        struct rchan_percpu_buf_dispatcher *p = info;
+
+        relay_set_buf_dentry(p->buf, p->dentry);
+}
+
+/**
+ *      relay_late_setup_files - triggers file creation
+ *      @chan: channel to operate on
+ *      @base_filename: base name of files to create
+ *      @parent: dentry of parent directory, %NULL for root directory
+ *
+ *      Returns 0 if successful, non-zero otherwise.
+ *
+ *      Use to setup files for a previously buffer-only channel.
+ *      Useful to do early tracing in kernel, before VFS is up, for example.
+ */
+int relay_late_setup_files(struct rchan *chan,
+                           const char *base_filename,
+                           struct dentry *parent)
+{
+        int err = 0;
+        unsigned int i, curr_cpu;
+        unsigned long flags;
+        struct dentry *dentry;
+        struct rchan_percpu_buf_dispatcher disp;
+
+        if (!chan || !base_filename)
+                return -EINVAL;
+
+        strlcpy(chan->base_filename, base_filename, NAME_MAX);
+
+        mutex_lock(&relay_channels_mutex);
+        /* Is chan already set up? */
+        if (unlikely(chan->has_base_filename))
+                return -EEXIST;
+        chan->has_base_filename = 1;
+        chan->parent = parent;
+        curr_cpu = get_cpu();
+        /*
+         * The CPU hotplug notifier ran before us and created buffers with
+         * no files associated. So it's safe to call relay_setup_buf_file()
+         * on all currently online CPUs.
+         */
+        for_each_online_cpu(i) {
+                if (unlikely(!chan->buf[i])) {
+                        printk(KERN_ERR "relay_late_setup_files: CPU %u "
+                                        "has no buffer, it must have!\n", i);
+                        BUG();
+                        err = -EINVAL;
+                        break;
+                }
+
+                dentry = relay_create_buf_file(chan, chan->buf[i], i);
+                if (unlikely(!dentry)) {
+                        err = -EINVAL;
+                        break;
+                }
+
+                if (curr_cpu == i) {
+                        local_irq_save(flags);
+                        relay_set_buf_dentry(chan->buf[i], dentry);
+                        local_irq_restore(flags);
+                } else {
+                        disp.buf = chan->buf[i];
+                        disp.dentry = dentry;
+                        smp_mb();
+                        /* relay_channels_mutex must be held, so wait. */
+                        err = smp_call_function_single(i,
+                                                       __relay_set_buf_dentry,
+                                                       &disp, 1);
+                }
+                if (unlikely(err))
+                        break;
+        }
+        put_cpu();
+        mutex_unlock(&relay_channels_mutex);
+
+        return err;
+}
+
 /**
  *      relay_switch_subbuf - switch to a new sub-buffer
  *      @buf: channel buffer
@@ -627,8 +734,13 @@ size_t relay_switch_subbuf(struct rchan_buf *buf, size_t length)
                 old_subbuf = buf->subbufs_produced % buf->chan->n_subbufs;
                 buf->padding[old_subbuf] = buf->prev_padding;
                 buf->subbufs_produced++;
-                buf->dentry->d_inode->i_size += buf->chan->subbuf_size -
-                        buf->padding[old_subbuf];
+                if (buf->dentry)
+                        buf->dentry->d_inode->i_size +=
+                                buf->chan->subbuf_size -
+                                buf->padding[old_subbuf];
+                else
+                        buf->early_bytes += buf->chan->subbuf_size -
+                                            buf->padding[old_subbuf];
                 smp_mb();
                 if (waitqueue_active(&buf->read_wait))
                         /*
@@ -832,6 +944,10 @@ static void relay_file_read_consume(struct rchan_buf *buf,
         size_t n_subbufs = buf->chan->n_subbufs;
         size_t read_subbuf;
 
+        if (buf->subbufs_produced == buf->subbufs_consumed &&
+            buf->offset == buf->bytes_consumed)
+                return;
+
         if (buf->bytes_consumed + bytes_consumed > subbuf_size) {
                 relay_subbufs_consumed(buf->chan, buf->cpu, 1);
                 buf->bytes_consumed = 0;
@@ -863,6 +979,8 @@ static int relay_file_read_avail(struct rchan_buf *buf, size_t read_pos)
 
         relay_file_read_consume(buf, read_pos, 0);
 
+        consumed = buf->subbufs_consumed;
+
         if (unlikely(buf->offset > subbuf_size)) {
                 if (produced == consumed)
                         return 0;
@@ -881,8 +999,12 @@ static int relay_file_read_avail(struct rchan_buf *buf, size_t read_pos)
         if (consumed > produced)
                 produced += n_subbufs * subbuf_size;
 
-        if (consumed == produced)
+        if (consumed == produced) {
+                if (buf->offset == subbuf_size &&
+                    buf->subbufs_produced > buf->subbufs_consumed)
+                        return 1;
                 return 0;
+        }
 
         return 1;
 }
@@ -1237,4 +1359,4 @@ static __init int relay_init(void)
         return 0;
 }
 
-module_init(relay_init);
+early_initcall(relay_init);
diff --git a/kernel/res_counter.c b/kernel/res_counter.c
index d3c61b4ebef2..f275c8eca772 100644
--- a/kernel/res_counter.c
+++ b/kernel/res_counter.c
@@ -13,6 +13,7 @@
 #include <linux/slab.h>
 #include <linux/res_counter.h>
 #include <linux/uaccess.h>
+#include <linux/mm.h>
 
 void res_counter_init(struct res_counter *counter)
 {
@@ -102,44 +103,37 @@ u64 res_counter_read_u64(struct res_counter *counter, int member)
         return *res_counter_member(counter, member);
 }
 
-ssize_t res_counter_write(struct res_counter *counter, int member,
-                const char __user *userbuf, size_t nbytes, loff_t *pos,
-                int (*write_strategy)(char *st_buf, unsigned long long *val))
+int res_counter_memparse_write_strategy(const char *buf,
+                                        unsigned long long *res)
 {
-        int ret;
-        char *buf, *end;
-        unsigned long flags;
-        unsigned long long tmp, *val;
-
-        buf = kmalloc(nbytes + 1, GFP_KERNEL);
-        ret = -ENOMEM;
-        if (buf == NULL)
-                goto out;
+        char *end;
+        /* FIXME - make memparse() take const char* args */
+        *res = memparse((char *)buf, &end);
+        if (*end != '\0')
+                return -EINVAL;
 
-        buf[nbytes] = '\0';
-        ret = -EFAULT;
-        if (copy_from_user(buf, userbuf, nbytes))
-                goto out_free;
+        *res = PAGE_ALIGN(*res);
+        return 0;
+}
 
-        ret = -EINVAL;
+int res_counter_write(struct res_counter *counter, int member,
+                      const char *buf, write_strategy_fn write_strategy)
+{
+        char *end;
+        unsigned long flags;
+        unsigned long long tmp, *val;
 
-        strstrip(buf);
         if (write_strategy) {
-                if (write_strategy(buf, &tmp)) {
-                        goto out_free;
-                }
+                if (write_strategy(buf, &tmp))
+                        return -EINVAL;
         } else {
                 tmp = simple_strtoull(buf, &end, 10);
                 if (*end != '\0')
-                        goto out_free;
+                        return -EINVAL;
         }
         spin_lock_irqsave(&counter->lock, flags);
         val = res_counter_member(counter, member);
         *val = tmp;
         spin_unlock_irqrestore(&counter->lock, flags);
-        ret = nbytes;
-out_free:
-        kfree(buf);
-out:
-        return ret;
+        return 0;
 }
diff --git a/kernel/resource.c b/kernel/resource.c
index 74af2d7cb5a1..4089d12af6e0 100644
--- a/kernel/resource.c
+++ b/kernel/resource.c
@@ -38,10 +38,6 @@ 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 +49,10 @@ 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)
 {
@@ -362,35 +362,21 @@ int allocate_resource(struct resource *root, struct resource *new,
 
 EXPORT_SYMBOL(allocate_resource);
 
-/**
- * insert_resource - Inserts a resource in the resource tree
- * @parent: parent of the new resource
- * @new: new resource to insert
- *
- * Returns 0 on success, -EBUSY if the resource can't be inserted.
- *
- * This function is equivalent to request_resource when no conflict
- * happens. If a conflict happens, and the conflicting resources
- * entirely fit within the range of the new resource, then the new
- * resource is inserted and the conflicting resources become children of
- * the new resource.
+/*
+ * Insert a resource into the resource tree. If successful, return NULL,
+ * otherwise return the conflicting resource (compare to __request_resource())
  */
-int insert_resource(struct resource *parent, struct resource *new)
+static struct resource * __insert_resource(struct resource *parent, struct resource *new)
 {
-        int result;
         struct resource *first, *next;
 
-        write_lock(&resource_lock);
-
         for (;; parent = first) {
-                result = 0;
                 first = __request_resource(parent, new);
                 if (!first)
-                        goto out;
+                        return first;
 
-                result = -EBUSY;
                 if (first == parent)
-                        goto out;
+                        return first;
 
                 if ((first->start > new->start) || (first->end < new->end))
                         break;
@@ -401,15 +387,13 @@ int insert_resource(struct resource *parent, struct resource *new)
         for (next = first; ; next = next->sibling) {
                 /* Partial overlap? Bad, and unfixable */
                 if (next->start < new->start || next->end > new->end)
-                        goto out;
+                        return next;
                 if (!next->sibling)
                         break;
                 if (next->sibling->start > new->end)
                         break;
         }
 
-        result = 0;
-
         new->parent = parent;
         new->sibling = next->sibling;
         new->child = first;
@@ -426,10 +410,64 @@ int insert_resource(struct resource *parent, struct resource *new)
                         next = next->sibling;
                 next->sibling = new;
         }
+        return NULL;
+}
 
- out:
+/**
+ * insert_resource - Inserts a resource in the resource tree
+ * @parent: parent of the new resource
+ * @new: new resource to insert
+ *
+ * Returns 0 on success, -EBUSY if the resource can't be inserted.
+ *
+ * This function is equivalent to request_resource when no conflict
+ * happens. If a conflict happens, and the conflicting resources
+ * entirely fit within the range of the new resource, then the new
+ * resource is inserted and the conflicting resources become children of
+ * the new resource.
+ */
+int insert_resource(struct resource *parent, struct resource *new)
+{
+        struct resource *conflict;
+
+        write_lock(&resource_lock);
+        conflict = __insert_resource(parent, new);
+        write_unlock(&resource_lock);
+        return conflict ? -EBUSY : 0;
+}
+
+/**
+ * insert_resource_expand_to_fit - Insert a resource into the resource tree
+ * @root: root resource descriptor
+ * @new: new resource to insert
+ *
+ * Insert a resource into the resource tree, possibly expanding it in order
+ * to make it encompass any conflicting resources.
+ */
+void insert_resource_expand_to_fit(struct resource *root, struct resource *new)
+{
+        if (new->parent)
+                return;
+
+        write_lock(&resource_lock);
+        for (;;) {
+                struct resource *conflict;
+
+                conflict = __insert_resource(root, new);
+                if (!conflict)
+                        break;
+                if (conflict == root)
+                        break;
+
+                /* Ok, expand resource to cover the conflict, then try again .. */
+                if (conflict->start < new->start)
+                        new->start = conflict->start;
+                if (conflict->end > new->end)
+                        new->end = conflict->end;
+
+                printk("Expanded resource %s due to conflict with %s\n", new->name, conflict->name);
+        }
         write_unlock(&resource_lock);
-        return result;
 }
 
 /**
@@ -478,6 +516,70 @@ 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_KERNEL);
+
+        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 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);
 
 /**
@@ -490,7 +592,7 @@ resource_size_t resource_alignment(struct resource *res)
 {
         switch (res->flags & (IORESOURCE_SIZEALIGN | IORESOURCE_STARTALIGN)) {
         case IORESOURCE_SIZEALIGN:
-                return res->end - res->start + 1;
+                return resource_size(res);
         case IORESOURCE_STARTALIGN:
                 return res->start;
         default:
@@ -524,33 +626,34 @@ 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);
@@ -725,3 +828,40 @@ 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 (p->start <= addr && (p->end >= 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-tester.c b/kernel/rtmutex-tester.c
index 092e4c620af9..a56f629b057a 100644
--- a/kernel/rtmutex-tester.c
+++ b/kernel/rtmutex-tester.c
@@ -297,8 +297,8 @@ static int test_func(void *data)
  *
  * opcode:data
  */
-static ssize_t sysfs_test_command(struct sys_device *dev, const char *buf,
-                                  size_t count)
+static ssize_t sysfs_test_command(struct sys_device *dev, struct sysdev_attribute *attr,
+                                  const char *buf, size_t count)
 {
         struct sched_param schedpar;
         struct test_thread_data *td;
@@ -360,7 +360,8 @@ static ssize_t sysfs_test_command(struct sys_device *dev, const char *buf,
  * @dev:        thread to query
  * @buf:        char buffer to be filled with thread status info
  */
-static ssize_t sysfs_test_status(struct sys_device *dev, char *buf)
+static ssize_t sysfs_test_status(struct sys_device *dev, struct sysdev_attribute *attr,
+                                 char *buf)
 {
         struct test_thread_data *td;
         struct task_struct *tsk;
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 99e6d850ecab..6625c3c4b10d 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.
@@ -571,8 +577,10 @@ struct rq {
 #endif
 
 #ifdef CONFIG_SCHED_HRTICK
-        unsigned long hrtick_flags;
-        ktime_t hrtick_expire;
+#ifdef CONFIG_SMP
+        int hrtick_csd_pending;
+        struct call_single_data hrtick_csd;
+#endif
         struct hrtimer hrtick_timer;
 #endif
 
@@ -598,14 +606,13 @@ struct rq {
         /* BKL stats */
         unsigned int bkl_count;
 #endif
-        struct lock_class_key rq_lock_key;
 };
 
 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)
@@ -807,9 +814,16 @@ const_debug unsigned int sysctl_sched_nr_migrate = 32;
 
 /*
  * ratelimit for updating the group shares.
- * default: 0.5ms
+ * default: 0.25ms
  */
-const_debug unsigned int sysctl_sched_shares_ratelimit = 500000;
+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.
@@ -832,7 +846,7 @@ static inline u64 global_rt_period(void)
 
 static inline u64 global_rt_runtime(void)
 {
-        if (sysctl_sched_rt_period < 0)
+        if (sysctl_sched_rt_runtime < 0)
                 return RUNTIME_INF;
 
         return (u64)sysctl_sched_rt_runtime * NSEC_PER_USEC;
@@ -983,13 +997,6 @@ static struct rq *this_rq_lock(void)
         return rq;
 }
 
-static void __resched_task(struct task_struct *p, int tif_bit);
-
-static inline void resched_task(struct task_struct *p)
-{
-        __resched_task(p, TIF_NEED_RESCHED);
-}
-
 #ifdef CONFIG_SCHED_HRTICK
 /*
  * Use HR-timers to deliver accurate preemption points.
@@ -1001,25 +1008,6 @@ static inline void resched_task(struct task_struct *p)
  * When we get rescheduled we reprogram the hrtick_timer outside of the
  * rq->lock.
  */
-static inline void resched_hrt(struct task_struct *p)
-{
-        __resched_task(p, TIF_HRTICK_RESCHED);
-}
-
-static inline void resched_rq(struct rq *rq)
-{
-        unsigned long flags;
-
-        spin_lock_irqsave(&rq->lock, flags);
-        resched_task(rq->curr);
-        spin_unlock_irqrestore(&rq->lock, flags);
-}
-
-enum {
-        HRTICK_SET,             /* re-programm hrtick_timer */
-        HRTICK_RESET,           /* not a new slice */
-        HRTICK_BLOCK,           /* stop hrtick operations */
-};
 
 /*
  * Use hrtick when:
@@ -1030,40 +1018,11 @@ static inline int hrtick_enabled(struct rq *rq)
 {
         if (!sched_feat(HRTICK))
                 return 0;
-        if (unlikely(test_bit(HRTICK_BLOCK, &rq->hrtick_flags)))
+        if (!cpu_active(cpu_of(rq)))
                 return 0;
         return hrtimer_is_hres_active(&rq->hrtick_timer);
 }
 
-/*
- * Called to set the hrtick timer state.
- *
- * called with rq->lock held and irqs disabled
- */
-static void hrtick_start(struct rq *rq, u64 delay, int reset)
-{
-        assert_spin_locked(&rq->lock);
-
-        /*
-         * preempt at: now + delay
-         */
-        rq->hrtick_expire =
-                ktime_add_ns(rq->hrtick_timer.base->get_time(), delay);
-        /*
-         * indicate we need to program the timer
-         */
-        __set_bit(HRTICK_SET, &rq->hrtick_flags);
-        if (reset)
-                __set_bit(HRTICK_RESET, &rq->hrtick_flags);
-
-        /*
-         * New slices are called from the schedule path and don't need a
-         * forced reschedule.
-         */
-        if (reset)
-                resched_hrt(rq->curr);
-}
-
 static void hrtick_clear(struct rq *rq)
 {
         if (hrtimer_active(&rq->hrtick_timer))
@@ -1071,32 +1030,6 @@ static void hrtick_clear(struct rq *rq)
 }
 
 /*
- * Update the timer from the possible pending state.
- */
-static void hrtick_set(struct rq *rq)
-{
-        ktime_t time;
-        int set, reset;
-        unsigned long flags;
-
-        WARN_ON_ONCE(cpu_of(rq) != smp_processor_id());
-
-        spin_lock_irqsave(&rq->lock, flags);
-        set = __test_and_clear_bit(HRTICK_SET, &rq->hrtick_flags);
-        reset = __test_and_clear_bit(HRTICK_RESET, &rq->hrtick_flags);
-        time = rq->hrtick_expire;
-        clear_thread_flag(TIF_HRTICK_RESCHED);
-        spin_unlock_irqrestore(&rq->lock, flags);
-
-        if (set) {
-                hrtimer_start(&rq->hrtick_timer, time, HRTIMER_MODE_ABS);
-                if (reset && !hrtimer_active(&rq->hrtick_timer))
-                        resched_rq(rq);
-        } else
-                hrtick_clear(rq);
-}
-
-/*
  * High-resolution timer tick.
  * Runs from hardirq context with interrupts disabled.
  */
@@ -1115,27 +1048,37 @@ static enum hrtimer_restart hrtick(struct hrtimer *timer)
 }
 
 #ifdef CONFIG_SMP
-static void hotplug_hrtick_disable(int cpu)
+/*
+ * called from hardirq (IPI) context
+ */
+static void __hrtick_start(void *arg)
 {
-        struct rq *rq = cpu_rq(cpu);
-        unsigned long flags;
-
-        spin_lock_irqsave(&rq->lock, flags);
-        rq->hrtick_flags = 0;
-        __set_bit(HRTICK_BLOCK, &rq->hrtick_flags);
-        spin_unlock_irqrestore(&rq->lock, flags);
+        struct rq *rq = arg;
 
-        hrtick_clear(rq);
+        spin_lock(&rq->lock);
+        hrtimer_restart(&rq->hrtick_timer);
+        rq->hrtick_csd_pending = 0;
+        spin_unlock(&rq->lock);
 }
 
-static void hotplug_hrtick_enable(int cpu)
+/*
+ * Called to set the hrtick timer state.
+ *
+ * called with rq->lock held and irqs disabled
+ */
+static void hrtick_start(struct rq *rq, u64 delay)
 {
-        struct rq *rq = cpu_rq(cpu);
-        unsigned long flags;
+        struct hrtimer *timer = &rq->hrtick_timer;
+        ktime_t time = ktime_add_ns(timer->base->get_time(), delay);
 
-        spin_lock_irqsave(&rq->lock, flags);
-        __clear_bit(HRTICK_BLOCK, &rq->hrtick_flags);
-        spin_unlock_irqrestore(&rq->lock, flags);
+        hrtimer_set_expires(timer, time);
+
+        if (rq == this_rq()) {
+                hrtimer_restart(timer);
+        } else if (!rq->hrtick_csd_pending) {
+                __smp_call_function_single(cpu_of(rq), &rq->hrtick_csd);
+                rq->hrtick_csd_pending = 1;
+        }
 }
 
 static int
@@ -1150,70 +1093,60 @@ hotplug_hrtick(struct notifier_block *nfb, unsigned long action, void *hcpu)
         case CPU_DOWN_PREPARE_FROZEN:
         case CPU_DEAD:
         case CPU_DEAD_FROZEN:
-                hotplug_hrtick_disable(cpu);
-                return NOTIFY_OK;
-
-        case CPU_UP_PREPARE:
-        case CPU_UP_PREPARE_FROZEN:
-        case CPU_DOWN_FAILED:
-        case CPU_DOWN_FAILED_FROZEN:
-        case CPU_ONLINE:
-        case CPU_ONLINE_FROZEN:
-                hotplug_hrtick_enable(cpu);
+                hrtick_clear(cpu_rq(cpu));
                 return NOTIFY_OK;
         }
 
         return NOTIFY_DONE;
 }
 
-static void init_hrtick(void)
+static __init void init_hrtick(void)
 {
         hotcpu_notifier(hotplug_hrtick, 0);
 }
-#endif /* CONFIG_SMP */
+#else
+/*
+ * Called to set the hrtick timer state.
+ *
+ * called with rq->lock held and irqs disabled
+ */
+static void hrtick_start(struct rq *rq, u64 delay)
+{
+        hrtimer_start(&rq->hrtick_timer, ns_to_ktime(delay), HRTIMER_MODE_REL);
+}
 
-static void init_rq_hrtick(struct rq *rq)
+static inline void init_hrtick(void)
 {
-        rq->hrtick_flags = 0;
-        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;
 }
+#endif /* CONFIG_SMP */
 
-void hrtick_resched(void)
+static void init_rq_hrtick(struct rq *rq)
 {
-        struct rq *rq;
-        unsigned long flags;
+#ifdef CONFIG_SMP
+        rq->hrtick_csd_pending = 0;
 
-        if (!test_thread_flag(TIF_HRTICK_RESCHED))
-                return;
+        rq->hrtick_csd.flags = 0;
+        rq->hrtick_csd.func = __hrtick_start;
+        rq->hrtick_csd.info = rq;
+#endif
 
-        local_irq_save(flags);
-        rq = cpu_rq(smp_processor_id());
-        hrtick_set(rq);
-        local_irq_restore(flags);
+        hrtimer_init(&rq->hrtick_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+        rq->hrtick_timer.function = hrtick;
+        rq->hrtick_timer.cb_mode = HRTIMER_CB_IRQSAFE_PERCPU;
 }
-#else
+#else   /* CONFIG_SCHED_HRTICK */
 static inline void hrtick_clear(struct rq *rq)
 {
 }
 
-static inline void hrtick_set(struct rq *rq)
-{
-}
-
 static inline void init_rq_hrtick(struct rq *rq)
 {
 }
 
-void hrtick_resched(void)
-{
-}
-
 static inline void init_hrtick(void)
 {
 }
-#endif
+#endif  /* CONFIG_SCHED_HRTICK */
 
 /*
  * resched_task - mark a task 'to be rescheduled now'.
@@ -1228,16 +1161,16 @@ static inline void init_hrtick(void)
 #define tsk_is_polling(t) test_tsk_thread_flag(t, TIF_POLLING_NRFLAG)
 #endif
 
-static void __resched_task(struct task_struct *p, int tif_bit)
+static void resched_task(struct task_struct *p)
 {
         int cpu;
 
         assert_spin_locked(&task_rq(p)->lock);
 
-        if (unlikely(test_tsk_thread_flag(p, tif_bit)))
+        if (unlikely(test_tsk_thread_flag(p, TIF_NEED_RESCHED)))
                 return;
 
-        set_tsk_thread_flag(p, tif_bit);
+        set_tsk_thread_flag(p, TIF_NEED_RESCHED);
 
         cpu = task_cpu(p);
         if (cpu == smp_processor_id())
@@ -1303,10 +1236,10 @@ void wake_up_idle_cpu(int cpu)
 #endif /* CONFIG_NO_HZ */
 
 #else /* !CONFIG_SMP */
-static void __resched_task(struct task_struct *p, int tif_bit)
+static void resched_task(struct task_struct *p)
 {
         assert_spin_locked(&task_rq(p)->lock);
-        set_tsk_thread_flag(p, tif_bit);
+        set_tsk_need_resched(p);
 }
 #endif /* CONFIG_SMP */
 
@@ -1460,38 +1393,24 @@ 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;
@@ -1499,23 +1418,51 @@ 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;
+
+        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;
@@ -1546,19 +1493,23 @@ __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);
+        }
 }
 
 /*
@@ -1566,11 +1517,11 @@ __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) {
@@ -1587,14 +1538,10 @@ 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;
 }
 
 /*
@@ -1602,10 +1549,10 @@ 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;
@@ -1616,11 +1563,8 @@ 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)
@@ -1630,7 +1574,7 @@ 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);
         }
 }
 
@@ -1641,9 +1585,9 @@ 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
@@ -1946,16 +1890,24 @@ migrate_task(struct task_struct *p, int dest_cpu, struct migration_req *req)
 /*
  * wait_task_inactive - wait for a thread to unschedule.
  *
+ * If @match_state is nonzero, it's the @p->state value just checked and
+ * not expected to change.  If it changes, i.e. @p might have woken up,
+ * then return zero.  When we succeed in waiting for @p to be off its CPU,
+ * we return a positive number (its total switch count).  If a second call
+ * a short while later returns the same number, the caller can be sure that
+ * @p has remained unscheduled the whole time.
+ *
  * The caller must ensure that the task *will* unschedule sometime soon,
  * else this function might spin for a *long* time. This function can't
  * be called with interrupts off, or it may introduce deadlock with
  * smp_call_function() if an IPI is sent by the same process we are
  * waiting to become inactive.
  */
-void wait_task_inactive(struct task_struct *p)
+unsigned long wait_task_inactive(struct task_struct *p, long match_state)
 {
         unsigned long flags;
         int running, on_rq;
+        unsigned long ncsw;
         struct rq *rq;
 
         for (;;) {
@@ -1978,8 +1930,11 @@ void wait_task_inactive(struct task_struct *p)
                  * return false if the runqueue has changed and p
                  * is actually now running somewhere else!
                  */
-                while (task_running(rq, p))
+                while (task_running(rq, p)) {
+                        if (match_state && unlikely(p->state != match_state))
+                                return 0;
                         cpu_relax();
+                }
 
                 /*
                  * Ok, time to look more closely! We need the rq
@@ -1987,11 +1942,21 @@ void wait_task_inactive(struct task_struct *p)
                  * 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->nvcsw | LONG_MIN; /* sets MSB */
                 task_rq_unlock(rq, &flags);
 
                 /*
+                 * If it changed from the expected state, bail out now.
+                 */
+                if (unlikely(!ncsw))
+                        break;
+
+                /*
                  * Was it really running after all now that we
                  * checked with the proper locks actually held?
                  *
@@ -2023,6 +1988,8 @@ void wait_task_inactive(struct task_struct *p)
                  */
                 break;
         }
+
+        return ncsw;
 }
 
 /***
@@ -2108,7 +2075,7 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p, int this_cpu)
                 /* Tally up the load of all CPUs in the group */
                 avg_load = 0;
 
-                for_each_cpu_mask(i, group->cpumask) {
+                for_each_cpu_mask_nr(i, group->cpumask) {
                         /* Bias balancing toward cpus of our domain */
                         if (local_group)
                                 load = source_load(i, load_idx);
@@ -2150,7 +2117,7 @@ find_idlest_cpu(struct sched_group *group, struct task_struct *p, int this_cpu,
         /* Traverse only the allowed CPUs */
         cpus_and(*tmp, group->cpumask, p->cpus_allowed);
 
-        for_each_cpu_mask(i, *tmp) {
+        for_each_cpu_mask_nr(i, *tmp) {
                 load = weighted_cpuload(i);
 
                 if (load < min_load || (load == min_load && i == this_cpu)) {
@@ -2337,10 +2304,8 @@ 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
@@ -2472,10 +2437,8 @@ 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);
@@ -2647,11 +2610,7 @@ 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;
         /*
@@ -2813,10 +2772,10 @@ static void double_rq_lock(struct rq *rq1, struct rq *rq2)
         } else {
                 if (rq1 < rq2) {
                         spin_lock(&rq1->lock);
-                        spin_lock(&rq2->lock);
+                        spin_lock_nested(&rq2->lock, SINGLE_DEPTH_NESTING);
                 } else {
                         spin_lock(&rq2->lock);
-                        spin_lock(&rq1->lock);
+                        spin_lock_nested(&rq1->lock, SINGLE_DEPTH_NESTING);
                 }
         }
         update_rq_clock(rq1);
@@ -2859,14 +2818,21 @@ static int double_lock_balance(struct rq *this_rq, struct rq *busiest)
                 if (busiest < this_rq) {
                         spin_unlock(&this_rq->lock);
                         spin_lock(&busiest->lock);
-                        spin_lock(&this_rq->lock);
+                        spin_lock_nested(&this_rq->lock, SINGLE_DEPTH_NESTING);
                         ret = 1;
                 } else
-                        spin_lock(&busiest->lock);
+                        spin_lock_nested(&busiest->lock, SINGLE_DEPTH_NESTING);
         }
         return ret;
 }
 
+static void double_unlock_balance(struct rq *this_rq, struct rq *busiest)
+        __releases(busiest->lock)
+{
+        spin_unlock(&busiest->lock);
+        lock_set_subclass(&this_rq->lock.dep_map, 0, _RET_IP_);
+}
+
 /*
  * If dest_cpu is allowed for this process, migrate the task to it.
  * This is accomplished by forcing the cpu_allowed mask to only
@@ -2881,9 +2847,10 @@ static void sched_migrate_task(struct task_struct *p, int dest_cpu)
 
         rq = task_rq_lock(p, &flags);
         if (!cpu_isset(dest_cpu, p->cpus_allowed)
-            || unlikely(cpu_is_offline(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). */
@@ -2928,7 +2895,7 @@ 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);
 }
 
 /*
@@ -3168,7 +3135,7 @@ find_busiest_group(struct sched_domain *sd, int this_cpu,
                 max_cpu_load = 0;
                 min_cpu_load = ~0UL;
 
-                for_each_cpu_mask(i, group->cpumask) {
+                for_each_cpu_mask_nr(i, group->cpumask) {
                         struct rq *rq;
 
                         if (!cpu_isset(i, *cpus))
@@ -3447,7 +3414,7 @@ find_busiest_queue(struct sched_group *group, enum cpu_idle_type idle,
         unsigned long max_load = 0;
         int i;
 
-        for_each_cpu_mask(i, group->cpumask) {
+        for_each_cpu_mask_nr(i, group->cpumask) {
                 unsigned long wl;
 
                 if (!cpu_isset(i, *cpus))
@@ -3691,7 +3658,7 @@ redo:
                 ld_moved = move_tasks(this_rq, this_cpu, busiest,
                                         imbalance, sd, CPU_NEWLY_IDLE,
                                         &all_pinned);
-                spin_unlock(&busiest->lock);
+                double_unlock_balance(this_rq, busiest);
 
                 if (unlikely(all_pinned)) {
                         cpu_clear(cpu_of(busiest), *cpus);
@@ -3806,7 +3773,7 @@ static void active_load_balance(struct rq *busiest_rq, int busiest_cpu)
                 else
                         schedstat_inc(sd, alb_failed);
         }
-        spin_unlock(&target_rq->lock);
+        double_unlock_balance(busiest_rq, target_rq);
 }
 
 #ifdef CONFIG_NO_HZ
@@ -3849,7 +3816,7 @@ int select_nohz_load_balancer(int stop_tick)
                 /*
                  * If we are going offline and still the leader, give up!
                  */
-                if (cpu_is_offline(cpu) &&
+                if (!cpu_active(cpu) &&
                     atomic_read(&nohz.load_balancer) == cpu) {
                         if (atomic_cmpxchg(&nohz.load_balancer, cpu, -1) != cpu)
                                 BUG();
@@ -3989,7 +3956,7 @@ static void run_rebalance_domains(struct softirq_action *h)
                 int balance_cpu;
 
                 cpu_clear(this_cpu, cpus);
-                for_each_cpu_mask(balance_cpu, cpus) {
+                for_each_cpu_mask_nr(balance_cpu, cpus) {
                         /*
                          * If this cpu gets work to do, stop the load balancing
                          * work being done for other cpus. Next load
@@ -4085,23 +4052,26 @@ 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;
@@ -4118,6 +4088,7 @@ 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);
@@ -4125,6 +4096,8 @@ void account_user_time(struct task_struct *p, cputime_t cputime)
                 cpustat->nice = cputime64_add(cpustat->nice, tmp);
         else
                 cpustat->user = cputime64_add(cpustat->user, tmp);
+        /* Account for user time used */
+        acct_update_integrals(p);
 }
 
 /*
@@ -4140,6 +4113,7 @@ 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);
@@ -4175,6 +4149,7 @@ 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);
@@ -4216,6 +4191,7 @@ 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
@@ -4225,6 +4201,65 @@ void account_steal_time(struct task_struct *p, cputime_t steal)
 }
 
 /*
+ * Use precise platform statistics if available:
+ */
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING
+cputime_t task_utime(struct task_struct *p)
+{
+        return p->utime;
+}
+
+cputime_t task_stime(struct task_struct *p)
+{
+        return p->stime;
+}
+#else
+cputime_t task_utime(struct task_struct *p)
+{
+        clock_t utime = cputime_to_clock_t(p->utime),
+                total = utime + cputime_to_clock_t(p->stime);
+        u64 temp;
+
+        /*
+         * Use CFS's precise accounting:
+         */
+        temp = (u64)nsec_to_clock_t(p->se.sum_exec_runtime);
+
+        if (total) {
+                temp *= utime;
+                do_div(temp, total);
+        }
+        utime = (clock_t)temp;
+
+        p->prev_utime = max(p->prev_utime, clock_t_to_cputime(utime));
+        return p->prev_utime;
+}
+
+cputime_t task_stime(struct task_struct *p)
+{
+        clock_t stime;
+
+        /*
+         * Use CFS's precise accounting. (we subtract utime from
+         * the total, to make sure the total observed by userspace
+         * grows monotonically - apps rely on that):
+         */
+        stime = nsec_to_clock_t(p->se.sum_exec_runtime) -
+                        cputime_to_clock_t(task_utime(p));
+
+        if (stime >= 0)
+                p->prev_stime = max(p->prev_stime, clock_t_to_cputime(stime));
+
+        return p->prev_stime;
+}
+#endif
+
+inline cputime_t task_gtime(struct task_struct *p)
+{
+        return p->gtime;
+}
+
+/*
  * This function gets called by the timer code, with HZ frequency.
  * We call it with interrupts disabled.
  *
@@ -4395,7 +4430,7 @@ asmlinkage void __sched schedule(void)
         struct task_struct *prev, *next;
         unsigned long *switch_count;
         struct rq *rq;
-        int cpu, hrtick = sched_feat(HRTICK);
+        int cpu;
 
 need_resched:
         preempt_disable();
@@ -4410,15 +4445,11 @@ need_resched_nonpreemptible:
 
         schedule_debug(prev);
 
-        if (hrtick)
+        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)) {
@@ -4457,9 +4488,6 @@ need_resched_nonpreemptible:
         } else
                 spin_unlock_irq(&rq->lock);
 
-        if (hrtick)
-                hrtick_set(rq);
-
         if (unlikely(reacquire_kernel_lock(current) < 0))
                 goto need_resched_nonpreemptible;
 
@@ -4617,6 +4645,15 @@ __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;
@@ -4628,6 +4665,12 @@ 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;
@@ -4648,10 +4691,7 @@ 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;
                         }
@@ -4679,12 +4719,31 @@ 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)
 {
@@ -4692,6 +4751,13 @@ 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);
@@ -4701,6 +4767,14 @@ 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)
@@ -4709,6 +4783,13 @@ 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);
@@ -4718,6 +4799,52 @@ int __sched wait_for_completion_killable(struct completion *x)
 }
 EXPORT_SYMBOL(wait_for_completion_killable);
 
+/**
+ *      try_wait_for_completion - try to decrement a completion without blocking
+ *      @x:     completion structure
+ *
+ *      Returns: 0 if a decrement cannot be done without blocking
+ *               1 if a decrement succeeded.
+ *
+ *      If a completion is being used as a counting completion,
+ *      attempt to decrement the counter without blocking. This
+ *      enables us to avoid waiting if the resource the completion
+ *      is protecting is not available.
+ */
+bool try_wait_for_completion(struct completion *x)
+{
+        int ret = 1;
+
+        spin_lock_irq(&x->wait.lock);
+        if (!x->done)
+                ret = 0;
+        else
+                x->done--;
+        spin_unlock_irq(&x->wait.lock);
+        return ret;
+}
+EXPORT_SYMBOL(try_wait_for_completion);
+
+/**
+ *      completion_done - Test to see if a completion has any waiters
+ *      @x:     completion structure
+ *
+ *      Returns: 0 if there are waiters (wait_for_completion() in progress)
+ *               1 if there are no waiters.
+ *
+ */
+bool completion_done(struct completion *x)
+{
+        int ret = 1;
+
+        spin_lock_irq(&x->wait.lock);
+        if (!x->done)
+                ret = 0;
+        spin_unlock_irq(&x->wait.lock);
+        return ret;
+}
+EXPORT_SYMBOL(completion_done);
+
 static long __sched
 sleep_on_common(wait_queue_head_t *q, int state, long timeout)
 {
@@ -5059,19 +5186,22 @@ recheck:
                         return -EPERM;
         }
 
+        if (user) {
 #ifdef CONFIG_RT_GROUP_SCHED
-        /*
-         * Do not allow realtime tasks into groups that have no runtime
-         * assigned.
-         */
-        if (user
-            && rt_policy(policy) && task_group(p)->rt_bandwidth.rt_runtime == 0)
-                return -EPERM;
+                /*
+                 * Do not allow realtime tasks into groups that have no runtime
+                 * assigned.
+                 */
+                if (rt_bandwidth_enabled() && rt_policy(policy) &&
+                                task_group(p)->rt_bandwidth.rt_runtime == 0)
+                        return -EPERM;
 #endif
 
-        retval = security_task_setscheduler(p, policy, param);
-        if (retval)
-                return retval;
+                retval = security_task_setscheduler(p, policy, param);
+                if (retval)
+                        return retval;
+        }
+
         /*
          * make sure no PI-waiters arrive (or leave) while we are
          * changing the priority of the task:
@@ -5787,6 +5917,8 @@ static inline void sched_init_granularity(void)
                 sysctl_sched_latency = limit;
 
         sysctl_sched_wakeup_granularity *= factor;
+
+        sysctl_sched_shares_ratelimit *= factor;
 }
 
 #ifdef CONFIG_SMP
@@ -5876,7 +6008,7 @@ static int __migrate_task(struct task_struct *p, int src_cpu, int dest_cpu)
         struct rq *rq_dest, *rq_src;
         int ret = 0, on_rq;
 
-        if (unlikely(cpu_is_offline(dest_cpu)))
+        if (unlikely(!cpu_active(dest_cpu)))
                 return ret;
 
         rq_src = cpu_rq(src_cpu);
@@ -5897,7 +6029,7 @@ 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;
@@ -6222,7 +6354,7 @@ 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;
@@ -6250,7 +6382,9 @@ 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;
 }
@@ -6469,7 +6603,7 @@ static struct notifier_block __cpuinitdata migration_notifier = {
         .priority = 10
 };
 
-void __init migration_init(void)
+static int __init migration_init(void)
 {
         void *cpu = (void *)(long)smp_processor_id();
         int err;
@@ -6479,7 +6613,10 @@ void __init migration_init(void)
         BUG_ON(err == NOTIFY_BAD);
         migration_call(&migration_notifier, CPU_ONLINE, cpu);
         register_cpu_notifier(&migration_notifier);
+
+        return err;
 }
+early_initcall(migration_init);
 #endif
 
 #ifdef CONFIG_SMP
@@ -6768,7 +6905,8 @@ static cpumask_t cpu_isolated_map = CPU_MASK_NONE;
 /* Setup the mask of cpus configured for isolated domains */
 static int __init isolated_cpu_setup(char *str)
 {
-        int ints[NR_CPUS], i;
+        static int __initdata ints[NR_CPUS];
+        int i;
 
         str = get_options(str, ARRAY_SIZE(ints), ints);
         cpus_clear(cpu_isolated_map);
@@ -6802,7 +6940,7 @@ init_sched_build_groups(const cpumask_t *span, const cpumask_t *cpu_map,
 
         cpus_clear(*covered);
 
-        for_each_cpu_mask(i, *span) {
+        for_each_cpu_mask_nr(i, *span) {
                 struct sched_group *sg;
                 int group = group_fn(i, cpu_map, &sg, tmpmask);
                 int j;
@@ -6813,7 +6951,7 @@ init_sched_build_groups(const cpumask_t *span, const cpumask_t *cpu_map,
                 cpus_clear(sg->cpumask);
                 sg->__cpu_power = 0;
 
-                for_each_cpu_mask(j, *span) {
+                for_each_cpu_mask_nr(j, *span) {
                         if (group_fn(j, cpu_map, NULL, tmpmask) != group)
                                 continue;
 
@@ -7013,7 +7151,7 @@ static void init_numa_sched_groups_power(struct sched_group *group_head)
         if (!sg)
                 return;
         do {
-                for_each_cpu_mask(j, sg->cpumask) {
+                for_each_cpu_mask_nr(j, sg->cpumask) {
                         struct sched_domain *sd;
 
                         sd = &per_cpu(phys_domains, j);
@@ -7038,7 +7176,7 @@ static void free_sched_groups(const cpumask_t *cpu_map, cpumask_t *nodemask)
 {
         int cpu, i;
 
-        for_each_cpu_mask(cpu, *cpu_map) {
+        for_each_cpu_mask_nr(cpu, *cpu_map) {
                 struct sched_group **sched_group_nodes
                         = sched_group_nodes_bycpu[cpu];
 
@@ -7130,13 +7268,21 @@ 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)
@@ -7277,7 +7423,7 @@ static int __build_sched_domains(const cpumask_t *cpu_map,
         /*
          * Set up domains for cpus specified by the cpu_map.
          */
-        for_each_cpu_mask(i, *cpu_map) {
+        for_each_cpu_mask_nr(i, *cpu_map) {
                 struct sched_domain *sd = NULL, *p;
                 SCHED_CPUMASK_VAR(nodemask, allmasks);
 
@@ -7344,7 +7490,7 @@ static int __build_sched_domains(const cpumask_t *cpu_map,
 
 #ifdef CONFIG_SCHED_SMT
         /* Set up CPU (sibling) groups */
-        for_each_cpu_mask(i, *cpu_map) {
+        for_each_cpu_mask_nr(i, *cpu_map) {
                 SCHED_CPUMASK_VAR(this_sibling_map, allmasks);
                 SCHED_CPUMASK_VAR(send_covered, allmasks);
 
@@ -7361,7 +7507,7 @@ static int __build_sched_domains(const cpumask_t *cpu_map,
 
 #ifdef CONFIG_SCHED_MC
         /* Set up multi-core groups */
-        for_each_cpu_mask(i, *cpu_map) {
+        for_each_cpu_mask_nr(i, *cpu_map) {
                 SCHED_CPUMASK_VAR(this_core_map, allmasks);
                 SCHED_CPUMASK_VAR(send_covered, allmasks);
 
@@ -7428,7 +7574,7 @@ static int __build_sched_domains(const cpumask_t *cpu_map,
                         goto error;
                 }
                 sched_group_nodes[i] = sg;
-                for_each_cpu_mask(j, *nodemask) {
+                for_each_cpu_mask_nr(j, *nodemask) {
                         struct sched_domain *sd;
 
                         sd = &per_cpu(node_domains, j);
@@ -7474,21 +7620,21 @@ static int __build_sched_domains(const cpumask_t *cpu_map,
 
         /* Calculate CPU power for physical packages and nodes */
 #ifdef CONFIG_SCHED_SMT
-        for_each_cpu_mask(i, *cpu_map) {
+        for_each_cpu_mask_nr(i, *cpu_map) {
                 struct sched_domain *sd = &per_cpu(cpu_domains, i);
 
                 init_sched_groups_power(i, sd);
         }
 #endif
 #ifdef CONFIG_SCHED_MC
-        for_each_cpu_mask(i, *cpu_map) {
+        for_each_cpu_mask_nr(i, *cpu_map) {
                 struct sched_domain *sd = &per_cpu(core_domains, i);
 
                 init_sched_groups_power(i, sd);
         }
 #endif
 
-        for_each_cpu_mask(i, *cpu_map) {
+        for_each_cpu_mask_nr(i, *cpu_map) {
                 struct sched_domain *sd = &per_cpu(phys_domains, i);
 
                 init_sched_groups_power(i, sd);
@@ -7508,7 +7654,7 @@ static int __build_sched_domains(const cpumask_t *cpu_map,
 #endif
 
         /* Attach the domains */
-        for_each_cpu_mask(i, *cpu_map) {
+        for_each_cpu_mask_nr(i, *cpu_map) {
                 struct sched_domain *sd;
 #ifdef CONFIG_SCHED_SMT
                 sd = &per_cpu(cpu_domains, i);
@@ -7553,18 +7699,6 @@ void __attribute__((weak)) arch_update_cpu_topology(void)
 }
 
 /*
- * Free current domain masks.
- * Called after all cpus are attached to NULL domain.
- */
-static void free_sched_domains(void)
-{
-        ndoms_cur = 0;
-        if (doms_cur != &fallback_doms)
-                kfree(doms_cur);
-        doms_cur = &fallback_doms;
-}
-
-/*
  * Set up scheduler domains and groups. Callers must hold the hotplug lock.
  * For now this just excludes isolated cpus, but could be used to
  * exclude other special cases in the future.
@@ -7603,7 +7737,7 @@ static void detach_destroy_domains(const cpumask_t *cpu_map)
 
         unregister_sched_domain_sysctl();
 
-        for_each_cpu_mask(i, *cpu_map)
+        for_each_cpu_mask_nr(i, *cpu_map)
                 cpu_attach_domain(NULL, &def_root_domain, i);
         synchronize_sched();
         arch_destroy_sched_domains(cpu_map, &tmpmask);
@@ -7642,30 +7776,29 @@ static int dattrs_equal(struct sched_domain_attr *cur, int idx_cur,
  * 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'.
+ * '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.
  *
  * Call with hotplug lock held
  */
 void partition_sched_domains(int ndoms_new, cpumask_t *doms_new,
                              struct sched_domain_attr *dattr_new)
 {
-        int i, j;
+        int i, j, n;
 
         mutex_lock(&sched_domains_mutex);
 
         /* always unregister in case we don't destroy any domains */
         unregister_sched_domain_sysctl();
 
-        if (doms_new == NULL) {
-                ndoms_new = 1;
-                doms_new = &fallback_doms;
-                cpus_andnot(doms_new[0], cpu_online_map, cpu_isolated_map);
-                dattr_new = NULL;
-        }
+        n = doms_new ? ndoms_new : 0;
 
         /* Destroy deleted domains */
         for (i = 0; i < ndoms_cur; i++) {
-                for (j = 0; j < ndoms_new; j++) {
+                for (j = 0; j < n; j++) {
                         if (cpus_equal(doms_cur[i], doms_new[j])
                             && dattrs_equal(dattr_cur, i, dattr_new, j))
                                 goto match1;
@@ -7676,6 +7809,13 @@ match1:
                 ;
         }
 
+        if (doms_new == NULL) {
+                ndoms_cur = 0;
+                doms_new = &fallback_doms;
+                cpus_andnot(doms_new[0], cpu_online_map, cpu_isolated_map);
+                dattr_new = NULL;
+        }
+
         /* Build new domains */
         for (i = 0; i < ndoms_new; i++) {
                 for (j = 0; j < ndoms_cur; j++) {
@@ -7706,17 +7846,15 @@ match2:
 #if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT)
 int arch_reinit_sched_domains(void)
 {
-        int err;
-
         get_online_cpus();
-        mutex_lock(&sched_domains_mutex);
-        detach_destroy_domains(&cpu_online_map);
-        free_sched_domains();
-        err = arch_init_sched_domains(&cpu_online_map);
-        mutex_unlock(&sched_domains_mutex);
+
+        /* Destroy domains first to force the rebuild */
+        partition_sched_domains(0, NULL, NULL);
+
+        rebuild_sched_domains();
         put_online_cpus();
 
-        return err;
+        return 0;
 }
 
 static ssize_t sched_power_savings_store(const char *buf, size_t count, int smt)
@@ -7737,30 +7875,34 @@ static ssize_t sched_power_savings_store(const char *buf, size_t count, int smt)
 }
 
 #ifdef CONFIG_SCHED_MC
-static ssize_t sched_mc_power_savings_show(struct sys_device *dev, char *page)
+static ssize_t sched_mc_power_savings_show(struct sysdev_class *class,
+                                           char *page)
 {
         return sprintf(page, "%u\n", sched_mc_power_savings);
 }
-static ssize_t sched_mc_power_savings_store(struct sys_device *dev,
+static ssize_t sched_mc_power_savings_store(struct sysdev_class *class,
                                             const char *buf, size_t count)
 {
         return sched_power_savings_store(buf, count, 0);
 }
-static SYSDEV_ATTR(sched_mc_power_savings, 0644, sched_mc_power_savings_show,
-                   sched_mc_power_savings_store);
+static SYSDEV_CLASS_ATTR(sched_mc_power_savings, 0644,
+                         sched_mc_power_savings_show,
+                         sched_mc_power_savings_store);
 #endif
 
 #ifdef CONFIG_SCHED_SMT
-static ssize_t sched_smt_power_savings_show(struct sys_device *dev, char *page)
+static ssize_t sched_smt_power_savings_show(struct sysdev_class *dev,
+                                            char *page)
 {
         return sprintf(page, "%u\n", sched_smt_power_savings);
 }
-static ssize_t sched_smt_power_savings_store(struct sys_device *dev,
+static ssize_t sched_smt_power_savings_store(struct sysdev_class *dev,
                                              const char *buf, size_t count)
 {
         return sched_power_savings_store(buf, count, 1);
 }
-static SYSDEV_ATTR(sched_smt_power_savings, 0644, sched_smt_power_savings_show,
+static SYSDEV_CLASS_ATTR(sched_smt_power_savings, 0644,
+                   sched_smt_power_savings_show,
                    sched_smt_power_savings_store);
 #endif
 
@@ -7782,59 +7924,49 @@ int sched_create_sysfs_power_savings_entries(struct sysdev_class *cls)
 }
 #endif /* CONFIG_SCHED_MC || CONFIG_SCHED_SMT */
 
+#ifndef CONFIG_CPUSETS
 /*
- * Force a reinitialization of the sched domains hierarchy. The domains
- * and groups cannot be updated in place without racing with the balancing
- * code, so we temporarily attach all running cpus to the NULL domain
- * which will prevent rebalancing while the sched domains are recalculated.
+ * Add online and remove offline CPUs from the scheduler domains.
+ * When cpusets are enabled they take over this function.
  */
 static int update_sched_domains(struct notifier_block *nfb,
                                 unsigned long action, void *hcpu)
 {
+        switch (action) {
+        case CPU_ONLINE:
+        case CPU_ONLINE_FROZEN:
+        case CPU_DEAD:
+        case CPU_DEAD_FROZEN:
+                partition_sched_domains(1, NULL, NULL);
+                return NOTIFY_OK;
+
+        default:
+                return NOTIFY_DONE;
+        }
+}
+#endif
+
+static int update_runtime(struct notifier_block *nfb,
+                                unsigned long action, void *hcpu)
+{
         int cpu = (int)(long)hcpu;
 
         switch (action) {
         case CPU_DOWN_PREPARE:
         case CPU_DOWN_PREPARE_FROZEN:
                 disable_runtime(cpu_rq(cpu));
-                /* fall-through */
-        case CPU_UP_PREPARE:
-        case CPU_UP_PREPARE_FROZEN:
-                detach_destroy_domains(&cpu_online_map);
-                free_sched_domains();
                 return NOTIFY_OK;
 
-
         case CPU_DOWN_FAILED:
         case CPU_DOWN_FAILED_FROZEN:
         case CPU_ONLINE:
         case CPU_ONLINE_FROZEN:
                 enable_runtime(cpu_rq(cpu));
-                /* fall-through */
-        case CPU_UP_CANCELED:
-        case CPU_UP_CANCELED_FROZEN:
-        case CPU_DEAD:
-        case CPU_DEAD_FROZEN:
-                /*
-                 * Fall through and re-initialise the domains.
-                 */
-                break;
+                return NOTIFY_OK;
+
         default:
                 return NOTIFY_DONE;
         }
-
-#ifndef CONFIG_CPUSETS
-        /*
-         * Create default domain partitioning if cpusets are disabled.
-         * Otherwise we let cpusets rebuild the domains based on the
-         * current setup.
-         */
-
-        /* The hotplug lock is already held by cpu_up/cpu_down */
-        arch_init_sched_domains(&cpu_online_map);
-#endif
-
-        return NOTIFY_OK;
 }
 
 void __init sched_init_smp(void)
@@ -7854,8 +7986,15 @@ void __init sched_init_smp(void)
                 cpu_set(smp_processor_id(), non_isolated_cpus);
         mutex_unlock(&sched_domains_mutex);
         put_online_cpus();
+
+#ifndef CONFIG_CPUSETS
         /* XXX: Theoretical race here - CPU may be hotplugged now */
         hotcpu_notifier(update_sched_domains, 0);
+#endif
+
+        /* RT runtime code needs to handle some hotplug events */
+        hotcpu_notifier(update_runtime, 0);
+
         init_hrtick();
 
         /* Move init over to a non-isolated CPU */
@@ -8063,7 +8202,6 @@ void __init sched_init(void)
 
                 rq = cpu_rq(i);
                 spin_lock_init(&rq->lock);
-                lockdep_set_class(&rq->lock, &rq->rq_lock_key);
                 rq->nr_running = 0;
                 init_cfs_rq(&rq->cfs, rq);
                 init_rt_rq(&rq->rt, rq);
@@ -8186,20 +8324,25 @@ 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);
@@ -8520,8 +8663,8 @@ struct task_group *sched_create_group(struct task_group *parent)
         WARN_ON(!parent); /* root should already exist */
 
         tg->parent = parent;
-        list_add_rcu(&tg->siblings, &parent->children);
         INIT_LIST_HEAD(&tg->children);
+        list_add_rcu(&tg->siblings, &parent->children);
         spin_unlock_irqrestore(&task_group_lock, flags);
 
         return tg;
@@ -8697,73 +8840,95 @@ 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;
 
-                total += to_ratio(ktime_to_ns(tgi->rt_bandwidth.rt_period),
-                                tgi->rt_bandwidth.rt_runtime);
+        period = ktime_to_ns(tg->rt_bandwidth.rt_period);
+        runtime = tg->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);
 
-                total += to_ratio(ktime_to_ns(tgi->rt_bandwidth.rt_period),
-                                tgi->rt_bandwidth.rt_runtime);
+        /*
+         * Nobody can have more than the global setting allows.
+         */
+        if (total > to_ratio(global_rt_period(), global_rt_runtime()))
+                return -EINVAL;
+
+        /*
+         * 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,
@@ -8773,14 +8938,9 @@ 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;
+        err = __rt_schedulable(tg, rt_period, rt_runtime);
+        if (err)
                 goto unlock;
-        }
-        if (!__rt_schedulable(tg, rt_period, rt_runtime)) {
-                err = -EINVAL;
-                goto unlock;
-        }
 
         spin_lock_irq(&tg->rt_bandwidth.rt_runtime_lock);
         tg->rt_bandwidth.rt_period = ns_to_ktime(rt_period);
@@ -8849,16 +9009,25 @@ 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;
@@ -8869,6 +9038,9 @@ 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;
@@ -8929,7 +9101,6 @@ 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;
         }
 
@@ -8938,9 +9109,6 @@ 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 22ed55d1167f..81787248b60f 100644
--- a/kernel/sched_clock.c
+++ b/kernel/sched_clock.c
@@ -12,19 +12,17 @@
  *
  * Create a semi stable clock from a mixture of other events, including:
  *  - gtod
- *  - jiffies
  *  - sched_clock()
  *  - explicit idle events
  *
  * We use gtod as base and the unstable clock deltas. The deltas are filtered,
- * making it monotonic and keeping it within an expected window.  This window
- * is set up using jiffies.
+ * making it monotonic and keeping it within an expected window.
  *
  * Furthermore, explicit sleep and wakeup hooks allow us to account for time
  * that is otherwise invisible (TSC gets stopped).
  *
  * The clock: sched_clock_cpu() is monotonic per cpu, and should be somewhat
- * consistent between cpus (never more than 1 jiffies difference).
+ * consistent between cpus (never more than 2 jiffies difference).
  */
 #include <linux/sched.h>
 #include <linux/percpu.h>
@@ -32,13 +30,19 @@
 #include <linux/ktime.h>
 #include <linux/module.h>
 
+/*
+ * Scheduler clock - returns current time in nanosec units.
+ * This is default implementation.
+ * Architectures and sub-architectures can override this.
+ */
+unsigned long long __attribute__((weak)) sched_clock(void)
+{
+        return (unsigned long long)jiffies * (NSEC_PER_SEC / HZ);
+}
 
-#ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
+static __read_mostly int sched_clock_running;
 
-#define MULTI_SHIFT 15
-/* Max is double, Min is 1/2 */
-#define MAX_MULTI (2LL << MULTI_SHIFT)
-#define MIN_MULTI (1LL << (MULTI_SHIFT-1))
+#ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
 
 struct sched_clock_data {
         /*
@@ -48,15 +52,9 @@ struct sched_clock_data {
          */
         raw_spinlock_t          lock;
 
-        unsigned long           tick_jiffies;
-        u64                     prev_raw;
         u64                     tick_raw;
         u64                     tick_gtod;
         u64                     clock;
-        s64                     multi;
-#ifdef CONFIG_NO_HZ
-        int                     check_max;
-#endif
 };
 
 static DEFINE_PER_CPU_SHARED_ALIGNED(struct sched_clock_data, sched_clock_data);
@@ -71,121 +69,69 @@ static inline struct sched_clock_data *cpu_sdc(int cpu)
         return &per_cpu(sched_clock_data, cpu);
 }
 
-static __read_mostly int sched_clock_running;
-
 void sched_clock_init(void)
 {
         u64 ktime_now = ktime_to_ns(ktime_get());
-        unsigned long now_jiffies = jiffies;
         int cpu;
 
         for_each_possible_cpu(cpu) {
                 struct sched_clock_data *scd = cpu_sdc(cpu);
 
                 scd->lock = (raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED;
-                scd->tick_jiffies = now_jiffies;
-                scd->prev_raw = 0;
                 scd->tick_raw = 0;
                 scd->tick_gtod = ktime_now;
                 scd->clock = ktime_now;
-                scd->multi = 1 << MULTI_SHIFT;
-#ifdef CONFIG_NO_HZ
-                scd->check_max = 1;
-#endif
         }
 
         sched_clock_running = 1;
 }
 
-#ifdef CONFIG_NO_HZ
 /*
- * The dynamic ticks makes the delta jiffies inaccurate. This
- * prevents us from checking the maximum time update.
- * Disable the maximum check during stopped ticks.
+ * min,max except they take wrapping into account
  */
-void sched_clock_tick_stop(int cpu)
-{
-        struct sched_clock_data *scd = cpu_sdc(cpu);
-
-        scd->check_max = 0;
-}
 
-void sched_clock_tick_start(int cpu)
+static inline u64 wrap_min(u64 x, u64 y)
 {
-        struct sched_clock_data *scd = cpu_sdc(cpu);
-
-        scd->check_max = 1;
+        return (s64)(x - y) < 0 ? x : y;
 }
 
-static int check_max(struct sched_clock_data *scd)
+static inline u64 wrap_max(u64 x, u64 y)
 {
-        return scd->check_max;
+        return (s64)(x - y) > 0 ? x : y;
 }
-#else
-static int check_max(struct sched_clock_data *scd)
-{
-        return 1;
-}
-#endif /* CONFIG_NO_HZ */
 
 /*
  * update the percpu scd from the raw @now value
  *
  *  - filter out backward motion
- *  - use jiffies to generate a min,max window to clip the raw values
+ *  - use the GTOD tick value to create a window to filter crazy TSC values
  */
-static void __update_sched_clock(struct sched_clock_data *scd, u64 now, u64 *time)
+static u64 __update_sched_clock(struct sched_clock_data *scd, u64 now)
 {
-        unsigned long now_jiffies = jiffies;
-        long delta_jiffies = now_jiffies - scd->tick_jiffies;
-        u64 clock = scd->clock;
-        u64 min_clock, max_clock;
-        s64 delta = now - scd->prev_raw;
+        s64 delta = now - scd->tick_raw;
+        u64 clock, min_clock, max_clock;
 
         WARN_ON_ONCE(!irqs_disabled());
 
-        /*
-         * At schedule tick the clock can be just under the gtod. We don't
-         * want to push it too prematurely.
-         */
-        min_clock = scd->tick_gtod + (delta_jiffies * TICK_NSEC);
-        if (min_clock > TICK_NSEC)
-                min_clock -= TICK_NSEC / 2;
-
-        if (unlikely(delta < 0)) {
-                clock++;
-                goto out;
-        }
+        if (unlikely(delta < 0))
+                delta = 0;
 
         /*
-         * The clock must stay within a jiffie of the gtod.
-         * But since we may be at the start of a jiffy or the end of one
-         * we add another jiffy buffer.
+         * scd->clock = clamp(scd->tick_gtod + delta,
+         *                    max(scd->tick_gtod, scd->clock),
+         *                    max(scd->clock, scd->tick_gtod + TICK_NSEC));
          */
-        max_clock = scd->tick_gtod + (2 + delta_jiffies) * TICK_NSEC;
 
-        delta *= scd->multi;
-        delta >>= MULTI_SHIFT;
+        clock = scd->tick_gtod + delta;
+        min_clock = wrap_max(scd->tick_gtod, scd->clock);
+        max_clock = wrap_max(scd->clock, scd->tick_gtod + TICK_NSEC);
 
-        if (unlikely(clock + delta > max_clock) && check_max(scd)) {
-                if (clock < max_clock)
-                        clock = max_clock;
-                else
-                        clock++;
-        } else {
-                clock += delta;
-        }
+        clock = wrap_max(clock, min_clock);
+        clock = wrap_min(clock, max_clock);
 
- out:
-        if (unlikely(clock < min_clock))
-                clock = min_clock;
+        scd->clock = clock;
 
-        if (time)
-                *time = clock;
-        else {
-                scd->prev_raw = now;
-                scd->clock = clock;
-        }
+        return scd->clock;
 }
 
 static void lock_double_clock(struct sched_clock_data *data1,
@@ -203,7 +149,7 @@ static void lock_double_clock(struct sched_clock_data *data1,
 u64 sched_clock_cpu(int cpu)
 {
         struct sched_clock_data *scd = cpu_sdc(cpu);
-        u64 now, clock;
+        u64 now, clock, this_clock, remote_clock;
 
         if (unlikely(!sched_clock_running))
                 return 0ull;
@@ -212,43 +158,44 @@ u64 sched_clock_cpu(int cpu)
         now = sched_clock();
 
         if (cpu != raw_smp_processor_id()) {
-                /*
-                 * in order to update a remote cpu's clock based on our
-                 * unstable raw time rebase it against:
-                 *   tick_raw           (offset between raw counters)
-                 *   tick_gotd          (tick offset between cpus)
-                 */
                 struct sched_clock_data *my_scd = this_scd();
 
                 lock_double_clock(scd, my_scd);
 
-                now -= my_scd->tick_raw;
-                now += scd->tick_raw;
+                this_clock = __update_sched_clock(my_scd, now);
+                remote_clock = scd->clock;
 
-                now += my_scd->tick_gtod;
-                now -= scd->tick_gtod;
+                /*
+                 * Use the opportunity that we have both locks
+                 * taken to couple the two clocks: we take the
+                 * larger time as the latest time for both
+                 * runqueues. (this creates monotonic movement)
+                 */
+                if (likely((s64)(remote_clock - this_clock) < 0)) {
+                        clock = this_clock;
+                        scd->clock = clock;
+                } else {
+                        /*
+                         * Should be rare, but possible:
+                         */
+                        clock = remote_clock;
+                        my_scd->clock = remote_clock;
+                }
 
                 __raw_spin_unlock(&my_scd->lock);
-
-                __update_sched_clock(scd, now, &clock);
-
-                __raw_spin_unlock(&scd->lock);
-
         } else {
                 __raw_spin_lock(&scd->lock);
-                __update_sched_clock(scd, now, NULL);
-                clock = scd->clock;
-                __raw_spin_unlock(&scd->lock);
+                clock = __update_sched_clock(scd, now);
         }
 
+        __raw_spin_unlock(&scd->lock);
+
         return clock;
 }
 
 void sched_clock_tick(void)
 {
         struct sched_clock_data *scd = this_scd();
-        unsigned long now_jiffies = jiffies;
-        s64 mult, delta_gtod, delta_raw;
         u64 now, now_gtod;
 
         if (unlikely(!sched_clock_running))
@@ -260,29 +207,9 @@ void sched_clock_tick(void)
         now = sched_clock();
 
         __raw_spin_lock(&scd->lock);
-        __update_sched_clock(scd, now, NULL);
-        /*
-         * update tick_gtod after __update_sched_clock() because that will
-         * already observe 1 new jiffy; adding a new tick_gtod to that would
-         * increase the clock 2 jiffies.
-         */
-        delta_gtod = now_gtod - scd->tick_gtod;
-        delta_raw = now - scd->tick_raw;
-
-        if ((long)delta_raw > 0) {
-                mult = delta_gtod << MULTI_SHIFT;
-                do_div(mult, delta_raw);
-                scd->multi = mult;
-                if (scd->multi > MAX_MULTI)
-                        scd->multi = MAX_MULTI;
-                else if (scd->multi < MIN_MULTI)
-                        scd->multi = MIN_MULTI;
-        } else
-                scd->multi = 1 << MULTI_SHIFT;
-
         scd->tick_raw = now;
         scd->tick_gtod = now_gtod;
-        scd->tick_jiffies = now_jiffies;
+        __update_sched_clock(scd, now);
         __raw_spin_unlock(&scd->lock);
 }
 
@@ -300,37 +227,28 @@ EXPORT_SYMBOL_GPL(sched_clock_idle_sleep_event);
  */
 void sched_clock_idle_wakeup_event(u64 delta_ns)
 {
-        struct sched_clock_data *scd = this_scd();
-        u64 now = sched_clock();
-
-        /*
-         * Override the previous timestamp and ignore all
-         * sched_clock() deltas that occured while we idled,
-         * and use the PM-provided delta_ns to advance the
-         * rq clock:
-         */
-        __raw_spin_lock(&scd->lock);
-        scd->prev_raw = now;
-        scd->clock += delta_ns;
-        scd->multi = 1 << MULTI_SHIFT;
-        __raw_spin_unlock(&scd->lock);
-
+        sched_clock_tick();
         touch_softlockup_watchdog();
 }
 EXPORT_SYMBOL_GPL(sched_clock_idle_wakeup_event);
 
-#endif
+#else /* CONFIG_HAVE_UNSTABLE_SCHED_CLOCK */
 
-/*
- * Scheduler clock - returns current time in nanosec units.
- * This is default implementation.
- * Architectures and sub-architectures can override this.
- */
-unsigned long long __attribute__((weak)) sched_clock(void)
+void sched_clock_init(void)
 {
-        return (unsigned long long)jiffies * (NSEC_PER_SEC / HZ);
+        sched_clock_running = 1;
 }
 
+u64 sched_clock_cpu(int cpu)
+{
+        if (unlikely(!sched_clock_running))
+                return 0;
+
+        return sched_clock();
+}
+
+#endif
+
 unsigned long long cpu_clock(int cpu)
 {
         unsigned long long clock;
diff --git a/kernel/sched_debug.c b/kernel/sched_debug.c
index bbe6b31c3c56..ad958c1ec708 100644
--- a/kernel/sched_debug.c
+++ b/kernel/sched_debug.c
@@ -333,12 +333,10 @@ 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,
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index f2aa987027d6..9573c33688b8 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:
  */
@@ -334,7 +336,7 @@ 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 +350,13 @@ 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 +386,26 @@ 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);
 }
 
 /*
@@ -507,6 +449,7 @@ 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 +529,12 @@ 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 +543,12 @@ 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)
@@ -683,7 +628,7 @@ 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. */
@@ -803,7 +748,7 @@ 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)) {
+        if (!cfs_rq->next || pair_slice > sysctl_sched_min_granularity) {
                 cfs_rq->pair_start = rq->clock;
                 return se;
         }
@@ -878,7 +823,6 @@ entity_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr, int queued)
 #ifdef CONFIG_SCHED_HRTICK
 static void hrtick_start_fair(struct rq *rq, struct task_struct *p)
 {
-        int requeue = rq->curr == p;
         struct sched_entity *se = &p->se;
         struct cfs_rq *cfs_rq = cfs_rq_of(se);
 
@@ -899,17 +843,37 @@ static void hrtick_start_fair(struct rq *rq, struct task_struct *p)
                  * Don't schedule slices shorter than 10000ns, that just
                  * doesn't make sense. Rely on vruntime for fairness.
                  */
-                if (!requeue)
-                        delta = max(10000LL, delta);
+                if (rq->curr != p)
+                        delta = max_t(s64, 10000LL, delta);
 
-                hrtick_start(rq, delta, requeue);
+                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
 
 /*
@@ -930,7 +894,7 @@ 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);
 }
 
 /*
@@ -952,7 +916,7 @@ 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);
 }
 
 /*
@@ -1004,6 +968,8 @@ static void yield_task_fair(struct rq *rq)
  * not idle and an idle cpu is available.  The span of cpus to
  * search starts with cpus closest then further out as needed,
  * so we always favor a closer, idle cpu.
+ * Domains may include CPUs that are not usable for migration,
+ * hence we need to mask them out (cpu_active_map)
  *
  * Returns the CPU we should wake onto.
  */
@@ -1031,7 +997,8 @@ static int wake_idle(int cpu, struct task_struct *p)
                     || ((sd->flags & SD_WAKE_IDLE_FAR)
                         && !task_hot(p, task_rq(p)->clock, sd))) {
                         cpus_and(tmp, sd->span, p->cpus_allowed);
-                        for_each_cpu_mask(i, tmp) {
+                        cpus_and(tmp, tmp, cpu_active_map);
+                        for_each_cpu_mask_nr(i, tmp) {
                                 if (idle_cpu(i)) {
                                         if (i != task_cpu(p)) {
                                                 schedstat_inc(p,
@@ -1055,8 +1022,6 @@ 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
@@ -1083,7 +1048,6 @@ 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;
@@ -1095,18 +1059,17 @@ 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;
@@ -1115,7 +1078,11 @@ 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.
@@ -1124,7 +1091,6 @@ static long effective_load(struct task_group *tg, int cpu,
                  * alter the group weight.
                  */
                 wg = 0;
-#undef D
         }
 
         return wl;
@@ -1141,7 +1107,7 @@ 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)
@@ -1156,6 +1122,11 @@ 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 && sched_feat(SYNC_WAKEUPS) &&
+            curr->se.avg_overlap < sysctl_sched_migration_cost &&
+            p->se.avg_overlap < sysctl_sched_migration_cost)
+                sync = 1;
+
         /*
          * If sync wakeup then subtract the (maximum possible)
          * effect of the currently running task from the load
@@ -1180,17 +1151,14 @@ 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
@@ -1209,16 +1177,17 @@ 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:
@@ -1246,13 +1215,10 @@ 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.
@@ -1279,62 +1245,20 @@ static unsigned long wakeup_gran(struct sched_entity *se)
          * + nice tasks.
          */
         if (sched_feat(ASYM_GRAN))
-                gran = calc_delta_asym(sysctl_sched_wakeup_granularity, se);
-        else
-                gran = calc_delta_fair(sysctl_sched_wakeup_granularity, se);
+                gran = calc_delta_mine(gran, NICE_0_LOAD, &se->load);
 
         return gran;
 }
 
 /*
- * Should 'se' preempt 'curr'.
- *
- *             |s1
- *        |s2
- *   |s3
- *         g
- *      |<--->|c
- *
- *  w(c, s1) = -1
- *  w(c, s2) =  0
- *  w(c, s3) =  1
- *
- */
-static int
-wakeup_preempt_entity(struct sched_entity *curr, struct sched_entity *se)
-{
-        s64 gran, vdiff = curr->vruntime - se->vruntime;
-
-        if (vdiff < 0)
-                return -1;
-
-        gran = wakeup_gran(curr);
-        if (vdiff > gran)
-                return 1;
-
-        return 0;
-}
-
-/* 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;
-}
-
-/*
  * 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;
+        s64 delta_exec;
 
         if (unlikely(rt_prio(p->prio))) {
                 update_rq_clock(rq);
@@ -1349,6 +1273,13 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p)
         cfs_rq_of(pse)->next = 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
          * the tick):
          */
@@ -1358,33 +1289,15 @@ 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.
-         */
-
-        /* 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);
+        if (sched_feat(WAKEUP_OVERLAP) && (sync ||
+                        (se->avg_overlap < sysctl_sched_migration_cost &&
+                         pse->avg_overlap < sysctl_sched_migration_cost))) {
+                resched_task(curr);
+                return;
         }
 
-        if (wakeup_preempt_entity(se, pse) == 1)
+        delta_exec = se->sum_exec_runtime - se->prev_sum_exec_runtime;
+        if (delta_exec > wakeup_gran(pse))
                 resched_task(curr);
 }
 
@@ -1440,18 +1353,13 @@ __load_balance_iterator(struct cfs_rq *cfs_rq, struct list_head *next)
         struct task_struct *p = NULL;
         struct sched_entity *se;
 
-        while (next != &cfs_rq->tasks) {
-                se = list_entry(next, struct sched_entity, group_node);
-                next = next->next;
+        if (next == &cfs_rq->tasks)
+                return NULL;
 
-                /* Skip over entities that are not tasks */
-                if (entity_is_task(se)) {
-                        p = task_of(se);
-                        break;
-                }
-        }
+        se = list_entry(next, struct sched_entity, group_node);
+        p = task_of(se);
+        cfs_rq->balance_iterator = next->next;
 
-        cfs_rq->balance_iterator = next;
         return p;
 }
 
@@ -1500,7 +1408,7 @@ 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;
@@ -1613,10 +1521,10 @@ 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);
 }
 
 /*
@@ -1635,7 +1543,7 @@ 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);
 }
 
 /*
@@ -1652,7 +1560,7 @@ 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.
diff --git a/kernel/sched_features.h b/kernel/sched_features.h
index 862b06bd560a..fda016218296 100644
--- a/kernel/sched_features.h
+++ b/kernel/sched_features.h
@@ -5,9 +5,10 @@ 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, 0)
+SCHED_FEAT(LB_BIAS, 1)
 SCHED_FEAT(LB_WAKEUP_UPDATE, 1)
 SCHED_FEAT(ASYM_EFF_LOAD, 1)
+SCHED_FEAT(WAKEUP_OVERLAP, 0)
diff --git a/kernel/sched_idletask.c b/kernel/sched_idletask.c
index 3a4f92dbbe66..dec4ccabe2f5 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);
 }
 
 /*
diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c
index 47ceac9e8552..b446dc87494f 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);
         }
@@ -199,6 +199,8 @@ static inline struct rt_rq *group_rt_rq(struct sched_rt_entity *rt_se)
 
 static inline void sched_rt_rq_enqueue(struct rt_rq *rt_rq)
 {
+        if (rt_rq->rt_nr_running)
+                resched_task(rq_of_rt_rq(rt_rq)->curr);
 }
 
 static inline void sched_rt_rq_dequeue(struct rt_rq *rt_rq)
@@ -229,6 +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);
@@ -240,7 +245,7 @@ static int do_balance_runtime(struct rt_rq *rt_rq)
 
         spin_lock(&rt_b->rt_runtime_lock);
         rt_period = ktime_to_ns(rt_b->rt_period);
-        for_each_cpu_mask(i, rd->span) {
+        for_each_cpu_mask_nr(i, rd->span) {
                 struct rt_rq *iter = sched_rt_period_rt_rq(rt_b, i);
                 s64 diff;
 
@@ -248,12 +253,21 @@ 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) {
-                        do_div(diff, weight);
+                        diff = div_u64((u64)diff, weight);
                         if (rt_rq->rt_runtime + diff > rt_period)
                                 diff = rt_period - rt_rq->rt_runtime;
                         iter->rt_runtime -= diff;
@@ -272,6 +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;
@@ -287,18 +304,34 @@ 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;
 
-                        if (iter == rt_rq)
+                        /*
+                         * Can't reclaim from ourselves or disabled runqueues.
+                         */
+                        if (iter == rt_rq || iter->rt_runtime == RUNTIME_INF)
                                 continue;
 
                         spin_lock(&iter->rt_runtime_lock);
@@ -317,8 +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);
@@ -341,6 +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);
 
@@ -348,6 +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);
         }
@@ -386,7 +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();
@@ -438,9 +483,6 @@ static int sched_rt_runtime_exceeded(struct rt_rq *rt_rq)
 {
         u64 runtime = sched_rt_runtime(rt_rq);
 
-        if (runtime == RUNTIME_INF)
-                return 0;
-
         if (rt_rq->rt_throttled)
                 return rt_rq_throttled(rt_rq);
 
@@ -484,16 +526,23 @@ 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);
 
                 spin_lock(&rt_rq->rt_runtime_lock);
-                rt_rq->rt_time += delta_exec;
-                if (sched_rt_runtime_exceeded(rt_rq))
-                        resched_task(curr);
+                if (sched_rt_runtime(rt_rq) != RUNTIME_INF) {
+                        rt_rq->rt_time += delta_exec;
+                        if (sched_rt_runtime_exceeded(rt_rq))
+                                resched_task(curr);
+                }
                 spin_unlock(&rt_rq->rt_runtime_lock);
         }
 }
@@ -505,7 +554,9 @@ void inc_rt_tasks(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
         rt_rq->rt_nr_running++;
 #if defined CONFIG_SMP || defined CONFIG_RT_GROUP_SCHED
         if (rt_se_prio(rt_se) < rt_rq->highest_prio) {
+#ifdef CONFIG_SMP
                 struct rq *rq = rq_of_rt_rq(rt_rq);
+#endif
 
                 rt_rq->highest_prio = rt_se_prio(rt_se);
 #ifdef CONFIG_SMP
@@ -599,11 +650,7 @@ static void __enqueue_rt_entity(struct sched_rt_entity *rt_se)
         if (group_rq && (rt_rq_throttled(group_rq) || !group_rq->rt_nr_running))
                 return;
 
-        if (rt_se->nr_cpus_allowed == 1)
-                list_add(&rt_se->run_list, queue);
-        else
-                list_add_tail(&rt_se->run_list, queue);
-
+        list_add_tail(&rt_se->run_list, queue);
         __set_bit(rt_se_prio(rt_se), array->bitmap);
 
         inc_rt_tasks(rt_se, rt_rq);
@@ -688,32 +735,34 @@ static void dequeue_task_rt(struct rq *rq, struct task_struct *p, int sleep)
  * Put task to the end of the run list without the overhead of dequeue
  * followed by enqueue.
  */
-static
-void requeue_rt_entity(struct rt_rq *rt_rq, struct sched_rt_entity *rt_se)
+static void
+requeue_rt_entity(struct rt_rq *rt_rq, struct sched_rt_entity *rt_se, int head)
 {
-        struct rt_prio_array *array = &rt_rq->active;
-
         if (on_rt_rq(rt_se)) {
-                list_del_init(&rt_se->run_list);
-                list_add_tail(&rt_se->run_list,
-                              array->queue + rt_se_prio(rt_se));
+                struct rt_prio_array *array = &rt_rq->active;
+                struct list_head *queue = array->queue + rt_se_prio(rt_se);
+
+                if (head)
+                        list_move(&rt_se->run_list, queue);
+                else
+                        list_move_tail(&rt_se->run_list, queue);
         }
 }
 
-static void requeue_task_rt(struct rq *rq, struct task_struct *p)
+static void requeue_task_rt(struct rq *rq, struct task_struct *p, int head)
 {
         struct sched_rt_entity *rt_se = &p->rt;
         struct rt_rq *rt_rq;
 
         for_each_sched_rt_entity(rt_se) {
                 rt_rq = rt_rq_of_se(rt_se);
-                requeue_rt_entity(rt_rq, rt_se);
+                requeue_rt_entity(rt_rq, rt_se, head);
         }
 }
 
 static void yield_task_rt(struct rq *rq)
 {
-        requeue_task_rt(rq, rq->curr);
+        requeue_task_rt(rq, rq->curr, 0);
 }
 
 #ifdef CONFIG_SMP
@@ -753,12 +802,36 @@ static int select_task_rq_rt(struct task_struct *p, int sync)
          */
         return task_cpu(p);
 }
+
+static void check_preempt_equal_prio(struct rq *rq, struct task_struct *p)
+{
+        cpumask_t mask;
+
+        if (rq->curr->rt.nr_cpus_allowed == 1)
+                return;
+
+        if (p->rt.nr_cpus_allowed != 1
+            && cpupri_find(&rq->rd->cpupri, p, &mask))
+                return;
+
+        if (!cpupri_find(&rq->rd->cpupri, rq->curr, &mask))
+                return;
+
+        /*
+         * There appears to be other cpus that can accept
+         * current and none to run 'p', so lets reschedule
+         * to try and push current away:
+         */
+        requeue_task_rt(rq, p, 1);
+        resched_task(rq->curr);
+}
+
 #endif /* CONFIG_SMP */
 
 /*
  * 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);
@@ -778,18 +851,8 @@ static void check_preempt_curr_rt(struct rq *rq, struct task_struct *p)
          * to move current somewhere else, making room for our non-migratable
          * task.
          */
-        if((p->prio == rq->curr->prio)
-           && p->rt.nr_cpus_allowed == 1
-           && rq->curr->rt.nr_cpus_allowed != 1) {
-                cpumask_t mask;
-
-                if (cpupri_find(&rq->rd->cpupri, rq->curr, &mask))
-                        /*
-                         * There appears to be other cpus that can accept
-                         * current, so lets reschedule to try and push it away
-                         */
-                        resched_task(rq->curr);
-        }
+        if (p->prio == rq->curr->prio && !need_resched())
+                check_preempt_equal_prio(rq, p);
 #endif
 }
 
@@ -847,6 +910,8 @@ static void put_prev_task_rt(struct rq *rq, struct task_struct *p)
 #define RT_MAX_TRIES 3
 
 static int double_lock_balance(struct rq *this_rq, struct rq *busiest);
+static void double_unlock_balance(struct rq *this_rq, struct rq *busiest);
+
 static void deactivate_task(struct rq *rq, struct task_struct *p, int sleep);
 
 static int pick_rt_task(struct rq *rq, struct task_struct *p, int cpu)
@@ -922,6 +987,13 @@ static int find_lowest_rq(struct task_struct *task)
                 return -1; /* No targets found */
 
         /*
+         * Only consider CPUs that are usable for migration.
+         * I guess we might want to change cpupri_find() to ignore those
+         * in the first place.
+         */
+        cpus_and(*lowest_mask, *lowest_mask, cpu_active_map);
+
+        /*
          * At this point we have built a mask of cpus representing the
          * lowest priority tasks in the system.  Now we want to elect
          * the best one based on our affinity and topology.
@@ -1001,7 +1073,7 @@ static struct rq *find_lock_lowest_rq(struct task_struct *task, struct rq *rq)
                         break;
 
                 /* try again */
-                spin_unlock(&lowest_rq->lock);
+                double_unlock_balance(rq, lowest_rq);
                 lowest_rq = NULL;
         }
 
@@ -1070,7 +1142,7 @@ static int push_rt_task(struct rq *rq)
 
         resched_task(lowest_rq->curr);
 
-        spin_unlock(&lowest_rq->lock);
+        double_unlock_balance(rq, lowest_rq);
 
         ret = 1;
 out:
@@ -1107,7 +1179,7 @@ static int pull_rt_task(struct rq *this_rq)
 
         next = pick_next_task_rt(this_rq);
 
-        for_each_cpu_mask(cpu, this_rq->rd->rto_mask) {
+        for_each_cpu_mask_nr(cpu, this_rq->rd->rto_mask) {
                 if (this_cpu == cpu)
                         continue;
 
@@ -1176,7 +1248,7 @@ static int pull_rt_task(struct rq *this_rq)
 
                 }
  skip:
-                spin_unlock(&src_rq->lock);
+                double_unlock_balance(this_rq, src_rq);
         }
 
         return ret;
@@ -1388,7 +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;
         }
 }
 
@@ -1415,7 +1487,7 @@ static void task_tick_rt(struct rq *rq, struct task_struct *p, int queued)
          * on the queue:
          */
         if (p->rt.run_list.prev != p->rt.run_list.next) {
-                requeue_task_rt(rq, p);
+                requeue_task_rt(rq, p, 0);
                 set_tsk_need_resched(p);
         }
 }
diff --git a/kernel/sched_stats.h b/kernel/sched_stats.h
index 8385d43987e2..ee71bec1da66 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 +277,89 @@ 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;
+
+        sig = tsk->signal;
+        if (unlikely(!sig))
+                return;
+        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;
+
+        sig = tsk->signal;
+        if (unlikely(!sig))
+                return;
+        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;
+        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/semaphore.c b/kernel/semaphore.c
index aaaeae8244e7..94a62c0d4ade 100644
--- a/kernel/semaphore.c
+++ b/kernel/semaphore.c
@@ -212,9 +212,7 @@ static inline int __sched __down_common(struct semaphore *sem, long state,
         waiter.up = 0;
 
         for (;;) {
-                if (state == TASK_INTERRUPTIBLE && signal_pending(task))
-                        goto interrupted;
-                if (state == TASK_KILLABLE && fatal_signal_pending(task))
+                if (signal_pending_state(state, task))
                         goto interrupted;
                 if (timeout <= 0)
                         goto timed_out;
diff --git a/kernel/signal.c b/kernel/signal.c
index 6c0958e52ea7..105217da5c82 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -22,10 +22,12 @@
 #include <linux/ptrace.h>
 #include <linux/signal.h>
 #include <linux/signalfd.h>
+#include <linux/tracehook.h>
 #include <linux/capability.h>
 #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>
@@ -39,24 +41,21 @@
 
 static struct kmem_cache *sigqueue_cachep;
 
-static int __sig_ignored(struct task_struct *t, int sig)
+static void __user *sig_handler(struct task_struct *t, int sig)
 {
-        void __user *handler;
+        return t->sighand->action[sig - 1].sa.sa_handler;
+}
 
+static int sig_handler_ignored(void __user *handler, int sig)
+{
         /* Is it explicitly or implicitly ignored? */
-
-        handler = t->sighand->action[sig - 1].sa.sa_handler;
         return handler == SIG_IGN ||
                 (handler == SIG_DFL && sig_kernel_ignore(sig));
 }
 
 static int sig_ignored(struct task_struct *t, int sig)
 {
-        /*
-         * Tracers always want to know about signals..
-         */
-        if (t->ptrace & PT_PTRACED)
-                return 0;
+        void __user *handler;
 
         /*
          * Blocked signals are never ignored, since the
@@ -66,7 +65,14 @@ static int sig_ignored(struct task_struct *t, int sig)
         if (sigismember(&t->blocked, sig) || sigismember(&t->real_blocked, sig))
                 return 0;
 
-        return __sig_ignored(t, sig);
+        handler = sig_handler(t, sig);
+        if (!sig_handler_ignored(handler, sig))
+                return 0;
+
+        /*
+         * Tracers may want to know about even ignored signals.
+         */
+        return !tracehook_consider_ignored_signal(t, sig, handler);
 }
 
 /*
@@ -129,7 +135,9 @@ void recalc_sigpending_and_wake(struct task_struct *t)
 
 void recalc_sigpending(void)
 {
-        if (!recalc_sigpending_tsk(current) && !freezing(current))
+        if (unlikely(tracehook_force_sigpending()))
+                set_thread_flag(TIF_SIGPENDING);
+        else if (!recalc_sigpending_tsk(current) && !freezing(current))
                 clear_thread_flag(TIF_SIGPENDING);
 
 }
@@ -295,12 +303,12 @@ flush_signal_handlers(struct task_struct *t, int force_default)
 
 int unhandled_signal(struct task_struct *tsk, int sig)
 {
+        void __user *handler = tsk->sighand->action[sig-1].sa.sa_handler;
         if (is_global_init(tsk))
                 return 1;
-        if (tsk->ptrace & PT_PTRACED)
+        if (handler != SIG_IGN && handler != SIG_DFL)
                 return 0;
-        return (tsk->sighand->action[sig-1].sa.sa_handler == SIG_IGN) ||
-                (tsk->sighand->action[sig-1].sa.sa_handler == SIG_DFL);
+        return !tracehook_consider_fatal_signal(tsk, sig, handler);
 }
 
 
@@ -338,13 +346,9 @@ unblock_all_signals(void)
         spin_unlock_irqrestore(&current->sighand->siglock, flags);
 }
 
-static int collect_signal(int sig, struct sigpending *list, siginfo_t *info)
+static void collect_signal(int sig, struct sigpending *list, siginfo_t *info)
 {
         struct sigqueue *q, *first = NULL;
-        int still_pending = 0;
-
-        if (unlikely(!sigismember(&list->signal, sig)))
-                return 0;
 
         /*
          * Collect the siginfo appropriate to this signal.  Check if
@@ -352,33 +356,30 @@ static int collect_signal(int sig, struct sigpending *list, siginfo_t *info)
         */
         list_for_each_entry(q, &list->list, list) {
                 if (q->info.si_signo == sig) {
-                        if (first) {
-                                still_pending = 1;
-                                break;
-                        }
+                        if (first)
+                                goto still_pending;
                         first = q;
                 }
         }
+
+        sigdelset(&list->signal, sig);
+
         if (first) {
+still_pending:
                 list_del_init(&first->list);
                 copy_siginfo(info, &first->info);
                 __sigqueue_free(first);
-                if (!still_pending)
-                        sigdelset(&list->signal, sig);
         } else {
-
                 /* Ok, it wasn't in the queue.  This must be
                    a fast-pathed signal or we must have been
                    out of queue space.  So zero out the info.
                  */
-                sigdelset(&list->signal, sig);
                 info->si_signo = sig;
                 info->si_errno = 0;
                 info->si_code = 0;
                 info->si_pid = 0;
                 info->si_uid = 0;
         }
-        return 1;
 }
 
 static int __dequeue_signal(struct sigpending *pending, sigset_t *mask,
@@ -396,8 +397,7 @@ static int __dequeue_signal(struct sigpending *pending, sigset_t *mask,
                         }
                 }
 
-                if (!collect_signal(sig, pending, info))
-                        sig = 0;
+                collect_signal(sig, pending, info);
         }
 
         return sig;
@@ -462,8 +462,7 @@ int dequeue_signal(struct task_struct *tsk, sigset_t *mask, siginfo_t *info)
                  * is to alert stop-signal processing code when another
                  * processor has come along and cleared the flag.
                  */
-                if (!(tsk->signal->flags & SIGNAL_GROUP_EXIT))
-                        tsk->signal->flags |= SIGNAL_STOP_DEQUEUED;
+                tsk->signal->flags |= SIGNAL_STOP_DEQUEUED;
         }
         if ((info->si_code & __SI_MASK) == __SI_TIMER && info->si_sys_private) {
                 /*
@@ -600,9 +599,6 @@ static int check_kill_permission(int sig, struct siginfo *info,
         return security_task_kill(t, info, sig, 0);
 }
 
-/* forward decl */
-static void do_notify_parent_cldstop(struct task_struct *tsk, int why);
-
 /*
  * Handle magic process-wide effects of stop/continue signals. Unlike
  * the signal actions, these happen immediately at signal-generation
@@ -765,7 +761,8 @@ static void complete_signal(int sig, struct task_struct *p, int group)
         if (sig_fatal(p, sig) &&
             !(signal->flags & (SIGNAL_UNKILLABLE | SIGNAL_GROUP_EXIT)) &&
             !sigismember(&t->real_blocked, sig) &&
-            (sig == SIGKILL || !(t->ptrace & PT_PTRACED))) {
+            (sig == SIGKILL ||
+             !tracehook_consider_fatal_signal(t, sig, SIG_DFL))) {
                 /*
                  * This signal will be fatal to the whole group.
                  */
@@ -807,6 +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;
@@ -1125,7 +1124,7 @@ EXPORT_SYMBOL_GPL(kill_pid_info_as_uid);
  * is probably wrong.  Should make it like BSD or SYSV.
  */
 
-static int kill_something_info(int sig, struct siginfo *info, int pid)
+static int kill_something_info(int sig, struct siginfo *info, pid_t pid)
 {
         int ret;
 
@@ -1237,17 +1236,6 @@ int kill_pid(struct pid *pid, int sig, int priv)
 }
 EXPORT_SYMBOL(kill_pid);
 
-int
-kill_proc(pid_t pid, int sig, int priv)
-{
-        int ret;
-
-        rcu_read_lock();
-        ret = kill_pid_info(sig, __si_special(priv), find_pid(pid));
-        rcu_read_unlock();
-        return ret;
-}
-
 /*
  * These functions support sending signals using preallocated sigqueue
  * structures.  This is needed "because realtime applications cannot
@@ -1319,6 +1307,7 @@ int send_sigqueue(struct sigqueue *q, struct task_struct *t, int group)
                 q->info.si_overrun++;
                 goto out;
         }
+        q->info.si_overrun = 0;
 
         signalfd_notify(t, sig);
         pending = group ? &t->signal->shared_pending : &t->pending;
@@ -1343,13 +1332,17 @@ static inline void __wake_up_parent(struct task_struct *p,
 /*
  * Let a parent know about the death of a child.
  * For a stopped/continued status change, use do_notify_parent_cldstop instead.
+ *
+ * Returns -1 if our parent ignored us and so we've switched to
+ * self-reaping, or else @sig.
  */
-
-void do_notify_parent(struct task_struct *tsk, int sig)
+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);
 
@@ -1379,11 +1372,9 @@ void do_notify_parent(struct task_struct *tsk, int sig)
 
         info.si_uid = tsk->uid;
 
-        /* FIXME: find out whether or not this is supposed to be c*time. */
-        info.si_utime = cputime_to_jiffies(cputime_add(tsk->utime,
-                                                       tsk->signal->utime));
-        info.si_stime = cputime_to_jiffies(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)
@@ -1415,14 +1406,16 @@ void do_notify_parent(struct task_struct *tsk, int sig)
                  * is implementation-defined: we do (if you don't want
                  * it, just use SIG_IGN instead).
                  */
-                tsk->exit_signal = -1;
+                ret = tsk->exit_signal = -1;
                 if (psig->action[SIGCHLD-1].sa.sa_handler == SIG_IGN)
-                        sig = 0;
+                        sig = -1;
         }
         if (valid_signal(sig) && sig > 0)
                 __group_send_sig_info(sig, &info, tsk->parent);
         __wake_up_parent(tsk, tsk->parent);
         spin_unlock_irqrestore(&psig->siglock, flags);
+
+        return ret;
 }
 
 static void do_notify_parent_cldstop(struct task_struct *tsk, int why)
@@ -1450,9 +1443,8 @@ static void do_notify_parent_cldstop(struct task_struct *tsk, int why)
 
         info.si_uid = tsk->uid;
 
-        /* FIXME: find out whether or not this is supposed to be c*time. */
-        info.si_utime = cputime_to_jiffies(tsk->utime);
-        info.si_stime = cputime_to_jiffies(tsk->stime);
+        info.si_utime = cputime_to_clock_t(tsk->utime);
+        info.si_stime = cputime_to_clock_t(tsk->stime);
 
         info.si_code = why;
         switch (why) {
@@ -1491,10 +1483,10 @@ static inline int may_ptrace_stop(void)
          * is a deadlock situation, and pointless because our tracer
          * is dead so don't allow us to stop.
          * If SIGKILL was already sent before the caller unlocked
-         * ->siglock we must see ->core_waiters != 0. Otherwise it
+         * ->siglock we must see ->core_state != NULL. Otherwise it
          * is safe to enter schedule().
          */
-        if (unlikely(current->mm->core_waiters) &&
+        if (unlikely(current->mm->core_state) &&
             unlikely(current->mm == current->parent->mm))
                 return 0;
 
@@ -1507,9 +1499,8 @@ static inline int may_ptrace_stop(void)
  */
 static int sigkill_pending(struct task_struct *tsk)
 {
-        return ((sigismember(&tsk->pending.signal, SIGKILL) ||
-                 sigismember(&tsk->signal->shared_pending.signal, SIGKILL)) &&
-                !unlikely(sigismember(&tsk->blocked, SIGKILL)));
+        return  sigismember(&tsk->pending.signal, SIGKILL) ||
+                sigismember(&tsk->signal->shared_pending.signal, SIGKILL);
 }
 
 /*
@@ -1525,8 +1516,6 @@ static int sigkill_pending(struct task_struct *tsk)
  */
 static void ptrace_stop(int exit_code, int clear_code, siginfo_t *info)
 {
-        int killed = 0;
-
         if (arch_ptrace_stop_needed(exit_code, info)) {
                 /*
                  * The arch code has something special to do before a
@@ -1542,7 +1531,8 @@ static void ptrace_stop(int exit_code, int clear_code, siginfo_t *info)
                 spin_unlock_irq(&current->sighand->siglock);
                 arch_ptrace_stop(exit_code, info);
                 spin_lock_irq(&current->sighand->siglock);
-                killed = sigkill_pending(current);
+                if (sigkill_pending(current))
+                        return;
         }
 
         /*
@@ -1559,7 +1549,7 @@ static void ptrace_stop(int exit_code, int clear_code, siginfo_t *info)
         __set_current_state(TASK_TRACED);
         spin_unlock_irq(&current->sighand->siglock);
         read_lock(&tasklist_lock);
-        if (!unlikely(killed) && may_ptrace_stop()) {
+        if (may_ptrace_stop()) {
                 do_notify_parent_cldstop(current, CLD_TRAPPED);
                 read_unlock(&tasklist_lock);
                 schedule();
@@ -1623,7 +1613,7 @@ finish_stop(int stop_count)
          * a group stop in progress and we are the last to stop,
          * report to the parent.  When ptraced, every thread reports itself.
          */
-        if (stop_count == 0 || (current->ptrace & PT_PTRACED)) {
+        if (tracehook_notify_jctl(stop_count == 0, CLD_STOPPED)) {
                 read_lock(&tasklist_lock);
                 do_notify_parent_cldstop(current, CLD_STOPPED);
                 read_unlock(&tasklist_lock);
@@ -1658,8 +1648,7 @@ static int do_signal_stop(int signr)
         } else {
                 struct task_struct *t;
 
-                if (unlikely((sig->flags & (SIGNAL_STOP_DEQUEUED | SIGNAL_UNKILLABLE))
-                                         != SIGNAL_STOP_DEQUEUED) ||
+                if (!likely(sig->flags & SIGNAL_STOP_DEQUEUED) ||
                     unlikely(signal_group_exit(sig)))
                         return 0;
                 /*
@@ -1760,6 +1749,9 @@ relock:
                 signal->flags &= ~SIGNAL_CLD_MASK;
                 spin_unlock_irq(&sighand->siglock);
 
+                if (unlikely(!tracehook_notify_jctl(1, why)))
+                        goto relock;
+
                 read_lock(&tasklist_lock);
                 do_notify_parent_cldstop(current->group_leader, why);
                 read_unlock(&tasklist_lock);
@@ -1773,17 +1765,33 @@ relock:
                     do_signal_stop(0))
                         goto relock;
 
-                signr = dequeue_signal(current, &current->blocked, info);
-                if (!signr)
-                        break; /* will return 0 */
+                /*
+                 * Tracing can induce an artifical signal and choose sigaction.
+                 * The return value in @signr determines the default action,
+                 * but @info->si_signo is the signal number we will report.
+                 */
+                signr = tracehook_get_signal(current, regs, info, return_ka);
+                if (unlikely(signr < 0))
+                        goto relock;
+                if (unlikely(signr != 0))
+                        ka = return_ka;
+                else {
+                        signr = dequeue_signal(current, &current->blocked,
+                                               info);
 
-                if (signr != SIGKILL) {
-                        signr = ptrace_signal(signr, info, regs, cookie);
                         if (!signr)
-                                continue;
+                                break; /* will return 0 */
+
+                        if (signr != SIGKILL) {
+                                signr = ptrace_signal(signr, info,
+                                                      regs, cookie);
+                                if (!signr)
+                                        continue;
+                        }
+
+                        ka = &sighand->action[signr-1];
                 }
 
-                ka = &sighand->action[signr-1];
                 if (ka->sa.sa_handler == SIG_IGN) /* Do nothing.  */
                         continue;
                 if (ka->sa.sa_handler != SIG_DFL) {
@@ -1831,7 +1839,7 @@ relock:
                                 spin_lock_irq(&sighand->siglock);
                         }
 
-                        if (likely(do_signal_stop(signr))) {
+                        if (likely(do_signal_stop(info->si_signo))) {
                                 /* It released the siglock.  */
                                 goto relock;
                         }
@@ -1852,7 +1860,7 @@ relock:
 
                 if (sig_kernel_coredump(signr)) {
                         if (print_fatal_signals)
-                                print_fatal_signal(regs, signr);
+                                print_fatal_signal(regs, info->si_signo);
                         /*
                          * If it was able to dump core, this kills all
                          * other threads in the group and synchronizes with
@@ -1861,13 +1869,13 @@ relock:
                          * first and our do_group_exit call below will use
                          * that value and ignore the one we pass it.
                          */
-                        do_coredump((long)signr, signr, regs);
+                        do_coredump(info->si_signo, info->si_signo, regs);
                 }
 
                 /*
                  * Death signals, no core dump.
                  */
-                do_group_exit(signr);
+                do_group_exit(info->si_signo);
                 /* NOTREACHED */
         }
         spin_unlock_irq(&sighand->siglock);
@@ -1909,7 +1917,7 @@ void exit_signals(struct task_struct *tsk)
 out:
         spin_unlock_irq(&tsk->sighand->siglock);
 
-        if (unlikely(group_stop)) {
+        if (unlikely(group_stop) && tracehook_notify_jctl(1, CLD_STOPPED)) {
                 read_lock(&tasklist_lock);
                 do_notify_parent_cldstop(tsk, CLD_STOPPED);
                 read_unlock(&tasklist_lock);
@@ -1920,8 +1928,6 @@ EXPORT_SYMBOL(recalc_sigpending);
 EXPORT_SYMBOL_GPL(dequeue_signal);
 EXPORT_SYMBOL(flush_signals);
 EXPORT_SYMBOL(force_sig);
-EXPORT_SYMBOL(kill_proc);
-EXPORT_SYMBOL(ptrace_notify);
 EXPORT_SYMBOL(send_sig);
 EXPORT_SYMBOL(send_sig_info);
 EXPORT_SYMBOL(sigprocmask);
@@ -2196,7 +2202,7 @@ sys_rt_sigtimedwait(const sigset_t __user *uthese,
 }
 
 asmlinkage long
-sys_kill(int pid, int sig)
+sys_kill(pid_t pid, int sig)
 {
         struct siginfo info;
 
@@ -2209,7 +2215,7 @@ sys_kill(int pid, int sig)
         return kill_something_info(sig, &info, pid);
 }
 
-static int do_tkill(int tgid, int pid, int sig)
+static int do_tkill(pid_t tgid, pid_t pid, int sig)
 {
         int error;
         struct siginfo info;
@@ -2255,7 +2261,7 @@ static int do_tkill(int tgid, int pid, int sig)
  *  exists but it's not belonging to the target process anymore. This
  *  method solves the problem of threads exiting and PIDs getting reused.
  */
-asmlinkage long sys_tgkill(int tgid, int pid, int sig)
+asmlinkage long sys_tgkill(pid_t tgid, pid_t pid, int sig)
 {
         /* This is only valid for single tasks */
         if (pid <= 0 || tgid <= 0)
@@ -2268,7 +2274,7 @@ asmlinkage long sys_tgkill(int tgid, int pid, int sig)
  *  Send a signal to only one task, even if it's a CLONE_THREAD task.
  */
 asmlinkage long
-sys_tkill(int pid, int sig)
+sys_tkill(pid_t pid, int sig)
 {
         /* This is only valid for single tasks */
         if (pid <= 0)
@@ -2278,7 +2284,7 @@ sys_tkill(int pid, int sig)
 }
 
 asmlinkage long
-sys_rt_sigqueueinfo(int pid, int sig, siginfo_t __user *uinfo)
+sys_rt_sigqueueinfo(pid_t pid, int sig, siginfo_t __user *uinfo)
 {
         siginfo_t info;
 
@@ -2325,7 +2331,7 @@ int do_sigaction(int sig, struct k_sigaction *act, struct k_sigaction *oact)
                  *   (for example, SIGCHLD), shall cause the pending signal to
                  *   be discarded, whether or not it is blocked"
                  */
-                if (__sig_ignored(t, sig)) {
+                if (sig_handler_ignored(sig_handler(t, sig), sig)) {
                         sigemptyset(&mask);
                         sigaddset(&mask, sig);
                         rm_from_queue_full(&mask, &t->signal->shared_pending);
diff --git a/kernel/smp.c b/kernel/smp.c
index 462c785ca1ee..f362a8553777 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -33,7 +33,7 @@ struct call_single_queue {
         spinlock_t lock;
 };
 
-void __cpuinit init_call_single_data(void)
+static int __cpuinit init_call_single_data(void)
 {
         int i;
 
@@ -43,7 +43,9 @@ void __cpuinit init_call_single_data(void)
                 spin_lock_init(&q->lock);
                 INIT_LIST_HEAD(&q->list);
         }
+        return 0;
 }
+early_initcall(init_call_single_data);
 
 static void csd_flag_wait(struct call_single_data *data)
 {
@@ -133,7 +135,8 @@ void generic_smp_call_function_interrupt(void)
                          */
                         smp_wmb();
                         data->csd.flags &= ~CSD_FLAG_WAIT;
-                } else
+                }
+                if (data->csd.flags & CSD_FLAG_ALLOC)
                         call_rcu(&data->rcu_head, rcu_free_call_data);
         }
         rcu_read_unlock();
@@ -207,8 +210,10 @@ int smp_call_function_single(int cpu, void (*func) (void *info), void *info,
 {
         struct call_single_data d;
         unsigned long flags;
-        /* prevent preemption and reschedule on another processor */
+        /* prevent preemption and reschedule on another processor,
+           as well as CPU removal */
         int me = get_cpu();
+        int err = 0;
 
         /* Can deadlock when called with interrupts disabled */
         WARN_ON(irqs_disabled());
@@ -217,7 +222,7 @@ int smp_call_function_single(int cpu, void (*func) (void *info), void *info,
                 local_irq_save(flags);
                 func(info);
                 local_irq_restore(flags);
-        } else {
+        } else if ((unsigned)cpu < NR_CPUS && cpu_online(cpu)) {
                 struct call_single_data *data = NULL;
 
                 if (!wait) {
@@ -233,10 +238,12 @@ int smp_call_function_single(int cpu, void (*func) (void *info), void *info,
                 data->func = func;
                 data->info = info;
                 generic_exec_single(cpu, data);
+        } else {
+                err = -ENXIO;   /* CPU not online */
         }
 
         put_cpu();
-        return 0;
+        return err;
 }
 EXPORT_SYMBOL(smp_call_function_single);
 
@@ -258,6 +265,42 @@ void __smp_call_function_single(int cpu, struct call_single_data *data)
         generic_exec_single(cpu, data);
 }
 
+/* Dummy function */
+static void quiesce_dummy(void *unused)
+{
+}
+
+/*
+ * Ensure stack based data used in call function mask is safe to free.
+ *
+ * This is needed by smp_call_function_mask when using on-stack data, because
+ * a single call function queue is shared by all CPUs, and any CPU may pick up
+ * the data item on the queue at any time before it is deleted. So we need to
+ * ensure that all CPUs have transitioned through a quiescent state after
+ * this call.
+ *
+ * This is a very slow function, implemented by sending synchronous IPIs to
+ * all possible CPUs. For this reason, we have to alloc data rather than use
+ * stack based data even in the case of synchronous calls. The stack based
+ * data is then just used for deadlock/oom fallback which will be very rare.
+ *
+ * If a faster scheme can be made, we could go back to preferring stack based
+ * data -- the data allocation/free is non-zero cost.
+ */
+static void smp_call_function_mask_quiesce_stack(cpumask_t mask)
+{
+        struct call_single_data data;
+        int cpu;
+
+        data.func = quiesce_dummy;
+        data.info = NULL;
+
+        for_each_cpu_mask(cpu, mask) {
+                data.flags = CSD_FLAG_WAIT;
+                generic_exec_single(cpu, &data);
+        }
+}
+
 /**
  * smp_call_function_mask(): Run a function on a set of other CPUs.
  * @mask: The set of cpus to run on.
@@ -283,6 +326,7 @@ int smp_call_function_mask(cpumask_t mask, void (*func)(void *), void *info,
         cpumask_t allbutself;
         unsigned long flags;
         int cpu, num_cpus;
+        int slowpath = 0;
 
         /* Can deadlock when called with interrupts disabled */
         WARN_ON(irqs_disabled());
@@ -304,15 +348,16 @@ int smp_call_function_mask(cpumask_t mask, void (*func)(void *), void *info,
                 return smp_call_function_single(cpu, func, info, wait);
         }
 
-        if (!wait) {
-                data = kmalloc(sizeof(*data), GFP_ATOMIC);
-                if (data)
-                        data->csd.flags = CSD_FLAG_ALLOC;
-        }
-        if (!data) {
+        data = kmalloc(sizeof(*data), GFP_ATOMIC);
+        if (data) {
+                data->csd.flags = CSD_FLAG_ALLOC;
+                if (wait)
+                        data->csd.flags |= CSD_FLAG_WAIT;
+        } else {
                 data = &d;
                 data->csd.flags = CSD_FLAG_WAIT;
                 wait = 1;
+                slowpath = 1;
         }
 
         spin_lock_init(&data->lock);
@@ -329,8 +374,11 @@ int smp_call_function_mask(cpumask_t mask, void (*func)(void *), void *info,
         arch_send_call_function_ipi(mask);
 
         /* optionally wait for the CPUs to complete */
-        if (wait)
+        if (wait) {
                 csd_flag_wait(&data->csd);
+                if (unlikely(slowpath))
+                        smp_call_function_mask_quiesce_stack(mask);
+        }
 
         return 0;
 }
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 81e2fe0f983a..7110daeb9a90 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 +267,12 @@ 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
+                tick_check_idle(cpu);
+
         __irq_enter();
-#ifdef CONFIG_NO_HZ
-        if (idle_cpu(cpu))
-                tick_nohz_update_jiffies();
-#endif
 }
 
 #ifdef __ARCH_IRQ_EXIT_IRQS_DISABLED
@@ -286,7 +295,7 @@ void irq_exit(void)
 #ifdef CONFIG_NO_HZ
         /* Make sure that timer wheel updates are propagated */
         if (!in_interrupt() && idle_cpu(smp_processor_id()) && !need_resched())
-                tick_nohz_stop_sched_tick();
+                tick_nohz_stop_sched_tick(0);
         rcu_irq_exit();
 #endif
         preempt_enable_no_resched();
@@ -463,17 +472,144 @@ 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);
 }
@@ -630,7 +766,7 @@ static struct notifier_block __cpuinitdata cpu_nfb = {
         .notifier_call = cpu_callback
 };
 
-__init int spawn_ksoftirqd(void)
+static __init int spawn_ksoftirqd(void)
 {
         void *cpu = (void *)(long)smp_processor_id();
         int err = cpu_callback(&cpu_nfb, CPU_UP_PREPARE, cpu);
@@ -640,6 +776,7 @@ __init int spawn_ksoftirqd(void)
         register_cpu_notifier(&cpu_nfb);
         return 0;
 }
+early_initcall(spawn_ksoftirqd);
 
 #ifdef CONFIG_SMP
 /*
diff --git a/kernel/softlockup.c b/kernel/softlockup.c
index a272d78185eb..3953e4aed733 100644
--- a/kernel/softlockup.c
+++ b/kernel/softlockup.c
@@ -13,6 +13,7 @@
 #include <linux/delay.h>
 #include <linux/freezer.h>
 #include <linux/kthread.h>
+#include <linux/lockdep.h>
 #include <linux/notifier.h>
 #include <linux/module.h>
 
@@ -25,7 +26,22 @@ static DEFINE_PER_CPU(unsigned long, print_timestamp);
 static DEFINE_PER_CPU(struct task_struct *, watchdog_task);
 
 static int __read_mostly did_panic;
-unsigned long __read_mostly softlockup_thresh = 60;
+int __read_mostly softlockup_thresh = 60;
+
+/*
+ * Should we panic (and reboot, if panic_timeout= is set) when a
+ * soft-lockup occurs:
+ */
+unsigned int __read_mostly softlockup_panic =
+                                CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC_VALUE;
+
+static int __init softlockup_panic_setup(char *str)
+{
+        softlockup_panic = simple_strtoul(str, NULL, 0);
+
+        return 1;
+}
+__setup("softlockup_panic=", softlockup_panic_setup);
 
 static int
 softlock_panic(struct notifier_block *this, unsigned long event, void *ptr)
@@ -84,6 +100,14 @@ void softlockup_tick(void)
         struct pt_regs *regs = get_irq_regs();
         unsigned long now;
 
+        /* Is detection switched off? */
+        if (!per_cpu(watchdog_task, this_cpu) || softlockup_thresh <= 0) {
+                /* Be sure we don't false trigger if switched back on */
+                if (touch_timestamp)
+                        per_cpu(touch_timestamp, this_cpu) = 0;
+                return;
+        }
+
         if (touch_timestamp == 0) {
                 __touch_softlockup_watchdog();
                 return;
@@ -92,11 +116,8 @@ void softlockup_tick(void)
         print_timestamp = per_cpu(print_timestamp, this_cpu);
 
         /* report at most once a second */
-        if ((print_timestamp >= touch_timestamp &&
-                        print_timestamp < (touch_timestamp + 1)) ||
-                        did_panic || !per_cpu(watchdog_task, this_cpu)) {
+        if (print_timestamp == touch_timestamp || did_panic)
                 return;
-        }
 
         /* do not print during early bootup: */
         if (unlikely(system_state != SYSTEM_RUNNING)) {
@@ -106,8 +127,11 @@ void softlockup_tick(void)
 
         now = get_timestamp(this_cpu);
 
-        /* Wake up the high-prio watchdog task every second: */
-        if (now > (touch_timestamp + 1))
+        /*
+         * Wake up the high-prio watchdog task twice per
+         * threshold timespan.
+         */
+        if (now > touch_timestamp + softlockup_thresh/2)
                 wake_up_process(per_cpu(watchdog_task, this_cpu));
 
         /* Warn about unreasonable delays: */
@@ -121,11 +145,15 @@ void softlockup_tick(void)
                         this_cpu, now - touch_timestamp,
                         current->comm, task_pid_nr(current));
         print_modules();
+        print_irqtrace_events(current);
         if (regs)
                 show_regs(regs);
         else
                 dump_stack();
         spin_unlock(&print_lock);
+
+        if (softlockup_panic)
+                panic("softlockup: hung tasks");
 }
 
 /*
@@ -178,6 +206,9 @@ static void check_hung_task(struct task_struct *t, unsigned long now)
 
         t->last_switch_timestamp = now;
         touch_nmi_watchdog();
+
+        if (softlockup_panic)
+                panic("softlockup: blocked tasks");
 }
 
 /*
@@ -195,14 +226,15 @@ 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);
         do_each_thread(g, t) {
                 if (!--max_count)
                         goto unlock;
-                if (t->state & TASK_UNINTERRUPTIBLE)
+                /* use "==" to skip the TASK_KILLABLE tasks waiting on NFS */
+                if (t->state == TASK_UNINTERRUPTIBLE)
                         check_hung_task(t, now);
         } while_each_thread(g, t);
  unlock:
@@ -307,14 +339,33 @@ static struct notifier_block __cpuinitdata cpu_nfb = {
         .notifier_call = cpu_callback
 };
 
-__init void spawn_softlockup_task(void)
+static int __initdata nosoftlockup;
+
+static int __init nosoftlockup_setup(char *str)
+{
+        nosoftlockup = 1;
+        return 1;
+}
+__setup("nosoftlockup", nosoftlockup_setup);
+
+static int __init spawn_softlockup_task(void)
 {
         void *cpu = (void *)(long)smp_processor_id();
-        int err = cpu_callback(&cpu_nfb, CPU_UP_PREPARE, cpu);
+        int err;
+
+        if (nosoftlockup)
+                return 0;
 
-        BUG_ON(err == NOTIFY_BAD);
+        err = cpu_callback(&cpu_nfb, CPU_UP_PREPARE, cpu);
+        if (err == NOTIFY_BAD) {
+                BUG();
+                return 1;
+        }
         cpu_callback(&cpu_nfb, CPU_ONLINE, cpu);
         register_cpu_notifier(&cpu_nfb);
 
         atomic_notifier_chain_register(&panic_notifier_list, &panic_block);
+
+        return 0;
 }
+early_initcall(spawn_softlockup_task);
diff --git a/kernel/spinlock.c b/kernel/spinlock.c
index a1fb54c93cdd..29ab20749dd3 100644
--- a/kernel/spinlock.c
+++ b/kernel/spinlock.c
@@ -290,8 +290,8 @@ void __lockfunc _spin_lock_nested(spinlock_t *lock, int subclass)
         spin_acquire(&lock->dep_map, subclass, 0, _RET_IP_);
         LOCK_CONTENDED(lock, _raw_spin_trylock, _raw_spin_lock);
 }
-
 EXPORT_SYMBOL(_spin_lock_nested);
+
 unsigned long __lockfunc _spin_lock_irqsave_nested(spinlock_t *lock, int subclass)
 {
         unsigned long flags;
@@ -311,9 +311,17 @@ unsigned long __lockfunc _spin_lock_irqsave_nested(spinlock_t *lock, int subclas
 #endif
         return flags;
 }
-
 EXPORT_SYMBOL(_spin_lock_irqsave_nested);
 
+void __lockfunc _spin_lock_nest_lock(spinlock_t *lock,
+                                     struct lockdep_map *nest_lock)
+{
+        preempt_disable();
+        spin_acquire_nest(&lock->dep_map, 0, 0, nest_lock, _RET_IP_);
+        LOCK_CONTENDED(lock, _raw_spin_trylock, _raw_spin_lock);
+}
+EXPORT_SYMBOL(_spin_lock_nest_lock);
+
 #endif
 
 void __lockfunc _spin_unlock(spinlock_t *lock)
diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c
index ba9b2054ecbd..9bc4c00872c9 100644
--- a/kernel/stop_machine.c
+++ b/kernel/stop_machine.c
@@ -1,4 +1,4 @@
-/* Copyright 2005 Rusty Russell rusty@rustcorp.com.au IBM Corporation.
+/* Copyright 2008, 2005 Rusty Russell rusty@rustcorp.com.au IBM Corporation.
  * GPL v2 and any later version.
  */
 #include <linux/cpu.h>
@@ -13,203 +13,151 @@
 #include <asm/atomic.h>
 #include <asm/uaccess.h>
 
-/* Since we effect priority and affinity (both of which are visible
- * to, and settable by outside processes) we do indirection via a
- * kthread. */
-
-/* Thread to stop each CPU in user context. */
+/* This controls the threads on each CPU. */
 enum stopmachine_state {
-        STOPMACHINE_WAIT,
+        /* Dummy starting state for thread. */
+        STOPMACHINE_NONE,
+        /* Awaiting everyone to be scheduled. */
         STOPMACHINE_PREPARE,
+        /* Disable interrupts. */
         STOPMACHINE_DISABLE_IRQ,
+        /* Run the function */
+        STOPMACHINE_RUN,
+        /* Exit */
         STOPMACHINE_EXIT,
 };
+static enum stopmachine_state state;
 
-static enum stopmachine_state stopmachine_state;
-static unsigned int stopmachine_num_threads;
-static atomic_t stopmachine_thread_ack;
-
-static int stopmachine(void *cpu)
-{
-        int irqs_disabled = 0;
-        int prepared = 0;
-
-        set_cpus_allowed_ptr(current, &cpumask_of_cpu((int)(long)cpu));
-
-        /* Ack: we are alive */
-        smp_mb(); /* Theoretically the ack = 0 might not be on this CPU yet. */
-        atomic_inc(&stopmachine_thread_ack);
-
-        /* Simple state machine */
-        while (stopmachine_state != STOPMACHINE_EXIT) {
-                if (stopmachine_state == STOPMACHINE_DISABLE_IRQ 
-                    && !irqs_disabled) {
-                        local_irq_disable();
-                        hard_irq_disable();
-                        irqs_disabled = 1;
-                        /* Ack: irqs disabled. */
-                        smp_mb(); /* Must read state first. */
-                        atomic_inc(&stopmachine_thread_ack);
-                } else if (stopmachine_state == STOPMACHINE_PREPARE
-                           && !prepared) {
-                        /* Everyone is in place, hold CPU. */
-                        preempt_disable();
-                        prepared = 1;
-                        smp_mb(); /* Must read state first. */
-                        atomic_inc(&stopmachine_thread_ack);
-                }
-                /* Yield in first stage: migration threads need to
-                 * help our sisters onto their CPUs. */
-                if (!prepared && !irqs_disabled)
-                        yield();
-                cpu_relax();
-        }
+struct stop_machine_data {
+        int (*fn)(void *);
+        void *data;
+        int fnret;
+};
 
-        /* Ack: we are exiting. */
-        smp_mb(); /* Must read state first. */
-        atomic_inc(&stopmachine_thread_ack);
+/* Like num_online_cpus(), but hotplug cpu uses us, so we need this. */
+static unsigned int num_threads;
+static atomic_t thread_ack;
+static DEFINE_MUTEX(lock);
 
-        if (irqs_disabled)
-                local_irq_enable();
-        if (prepared)
-                preempt_enable();
+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;
 
-        return 0;
-}
-
-/* Change the thread state */
-static void stopmachine_set_state(enum stopmachine_state state)
+static void set_state(enum stopmachine_state newstate)
 {
-        atomic_set(&stopmachine_thread_ack, 0);
+        /* Reset ack counter. */
+        atomic_set(&thread_ack, num_threads);
         smp_wmb();
-        stopmachine_state = state;
-        while (atomic_read(&stopmachine_thread_ack) != stopmachine_num_threads)
-                cpu_relax();
+        state = newstate;
 }
 
-static int stop_machine(void)
+/* Last one to ack a state moves to the next state. */
+static void ack_state(void)
 {
-        int i, ret = 0;
-
-        atomic_set(&stopmachine_thread_ack, 0);
-        stopmachine_num_threads = 0;
-        stopmachine_state = STOPMACHINE_WAIT;
+        if (atomic_dec_and_test(&thread_ack))
+                set_state(state + 1);
+}
 
-        for_each_online_cpu(i) {
-                if (i == raw_smp_processor_id())
-                        continue;
-                ret = kernel_thread(stopmachine, (void *)(long)i,CLONE_KERNEL);
-                if (ret < 0)
-                        break;
-                stopmachine_num_threads++;
+/* 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;
         }
-
-        /* Wait for them all to come to life. */
-        while (atomic_read(&stopmachine_thread_ack) != stopmachine_num_threads) {
-                yield();
+        /* Simple state machine */
+        do {
+                /* Chill out and ensure we re-read stopmachine_state. */
                 cpu_relax();
-        }
-
-        /* If some failed, kill them all. */
-        if (ret < 0) {
-                stopmachine_set_state(STOPMACHINE_EXIT);
-                return ret;
-        }
-
-        /* Now they are all started, make them hold the CPUs, ready. */
-        preempt_disable();
-        stopmachine_set_state(STOPMACHINE_PREPARE);
-
-        /* Make them disable irqs. */
-        local_irq_disable();
-        hard_irq_disable();
-        stopmachine_set_state(STOPMACHINE_DISABLE_IRQ);
-
-        return 0;
-}
+                if (state != curstate) {
+                        curstate = state;
+                        switch (curstate) {
+                        case STOPMACHINE_DISABLE_IRQ:
+                                local_irq_disable();
+                                hard_irq_disable();
+                                break;
+                        case STOPMACHINE_RUN:
+                                /* 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;
+                        }
+                        ack_state();
+                }
+        } while (curstate != STOPMACHINE_EXIT);
 
-static void restart_machine(void)
-{
-        stopmachine_set_state(STOPMACHINE_EXIT);
         local_irq_enable();
-        preempt_enable_no_resched();
 }
 
-struct stop_machine_data {
-        int (*fn)(void *);
-        void *data;
-        struct completion done;
-};
-
-static int do_stop(void *_smdata)
+/* Callback for CPUs which aren't supposed to do anything. */
+static int chill(void *unused)
 {
-        struct stop_machine_data *smdata = _smdata;
-        int ret;
-
-        ret = stop_machine();
-        if (ret == 0) {
-                ret = smdata->fn(smdata->data);
-                restart_machine();
-        }
-
-        /* We're done: you can kthread_stop us now */
-        complete(&smdata->done);
-
-        /* Wait for kthread_stop */
-        set_current_state(TASK_INTERRUPTIBLE);
-        while (!kthread_should_stop()) {
-                schedule();
-                set_current_state(TASK_INTERRUPTIBLE);
-        }
-        __set_current_state(TASK_RUNNING);
-        return ret;
+        return 0;
 }
 
-struct task_struct *__stop_machine_run(int (*fn)(void *), void *data,
-                                       unsigned int cpu)
+int __stop_machine(int (*fn)(void *), void *data, const cpumask_t *cpus)
 {
-        static DEFINE_MUTEX(stopmachine_mutex);
-        struct stop_machine_data smdata;
-        struct task_struct *p;
-
-        smdata.fn = fn;
-        smdata.data = data;
-        init_completion(&smdata.done);
-
-        mutex_lock(&stopmachine_mutex);
-
-        /* If they don't care which CPU fn runs on, bind to any online one. */
-        if (cpu == NR_CPUS)
-                cpu = raw_smp_processor_id();
-
-        p = kthread_create(do_stop, &smdata, "kstopmachine");
-        if (!IS_ERR(p)) {
-                struct sched_param param = { .sched_priority = MAX_RT_PRIO-1 };
-
-                /* One high-prio thread per cpu.  We'll do this one. */
-                sched_setscheduler_nocheck(p, SCHED_FIFO, &param);
-                kthread_bind(p, cpu);
-                wake_up_process(p);
-                wait_for_completion(&smdata.done);
+        struct work_struct *sm_work;
+        int i;
+
+        /* 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;
+
+        set_state(STOPMACHINE_PREPARE);
+
+        /* 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) {
+                sm_work = percpu_ptr(stop_machine_work, i);
+                INIT_WORK(sm_work, stop_cpu);
+                queue_work_on(i, stop_machine_wq, sm_work);
         }
-        mutex_unlock(&stopmachine_mutex);
-        return p;
+        /* This will release the thread on our CPU. */
+        put_cpu();
+        flush_workqueue(stop_machine_wq);
+        mutex_unlock(&lock);
+        return active.fnret;
 }
 
-int stop_machine_run(int (*fn)(void *), void *data, unsigned int cpu)
+int stop_machine(int (*fn)(void *), void *data, const cpumask_t *cpus)
 {
-        struct task_struct *p;
         int ret;
 
         /* No CPUs can come up or down during this. */
         get_online_cpus();
-        p = __stop_machine_run(fn, data, cpu);
-        if (!IS_ERR(p))
-                ret = kthread_stop(p);
-        else
-                ret = PTR_ERR(p);
+        ret = __stop_machine(fn, data, cpus);
         put_online_cpus();
 
         return ret;
 }
-EXPORT_SYMBOL_GPL(stop_machine_run);
+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 14e97282eb6c..31deba8f7d16 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -169,9 +169,9 @@ asmlinkage long sys_setpriority(int which, int who, int niceval)
                                 pgrp = find_vpid(who);
                         else
                                 pgrp = task_pgrp(current);
-                        do_each_pid_task(pgrp, PIDTYPE_PGID, p) {
+                        do_each_pid_thread(pgrp, PIDTYPE_PGID, p) {
                                 error = set_one_prio(p, niceval, error);
-                        } while_each_pid_task(pgrp, PIDTYPE_PGID, p);
+                        } while_each_pid_thread(pgrp, PIDTYPE_PGID, p);
                         break;
                 case PRIO_USER:
                         user = current->user;
@@ -229,11 +229,11 @@ asmlinkage long sys_getpriority(int which, int who)
                                 pgrp = find_vpid(who);
                         else
                                 pgrp = task_pgrp(current);
-                        do_each_pid_task(pgrp, PIDTYPE_PGID, p) {
+                        do_each_pid_thread(pgrp, PIDTYPE_PGID, p) {
                                 niceval = 20 - task_nice(p);
                                 if (niceval > retval)
                                         retval = niceval;
-                        } while_each_pid_task(pgrp, PIDTYPE_PGID, p);
+                        } while_each_pid_thread(pgrp, PIDTYPE_PGID, p);
                         break;
                 case PRIO_USER:
                         user = current->user;
@@ -274,7 +274,7 @@ void emergency_restart(void)
 }
 EXPORT_SYMBOL_GPL(emergency_restart);
 
-static void kernel_restart_prepare(char *cmd)
+void kernel_restart_prepare(char *cmd)
 {
         blocking_notifier_call_chain(&reboot_notifier_list, SYS_RESTART, cmd);
         system_state = SYSTEM_RESTART;
@@ -301,26 +301,6 @@ void kernel_restart(char *cmd)
 }
 EXPORT_SYMBOL_GPL(kernel_restart);
 
-/**
- *      kernel_kexec - reboot the system
- *
- *      Move into place and start executing a preloaded standalone
- *      executable.  If nothing was preloaded return an error.
- */
-static void kernel_kexec(void)
-{
-#ifdef CONFIG_KEXEC
-        struct kimage *image;
-        image = xchg(&kexec_image, NULL);
-        if (!image)
-                return;
-        kernel_restart_prepare(NULL);
-        printk(KERN_EMERG "Starting new kernel\n");
-        machine_shutdown();
-        machine_kexec(image);
-#endif
-}
-
 static void kernel_shutdown_prepare(enum system_states state)
 {
         blocking_notifier_call_chain(&reboot_notifier_list,
@@ -425,10 +405,15 @@ asmlinkage long sys_reboot(int magic1, int magic2, unsigned int cmd, void __user
                 kernel_restart(buffer);
                 break;
 
+#ifdef CONFIG_KEXEC
         case LINUX_REBOOT_CMD_KEXEC:
-                kernel_kexec();
-                unlock_kernel();
-                return -EINVAL;
+                {
+                        int ret;
+                        ret = kernel_kexec();
+                        unlock_kernel();
+                        return ret;
+                }
+#endif
 
 #ifdef CONFIG_HIBERNATION
         case LINUX_REBOOT_CMD_SW_SUSPEND:
@@ -868,38 +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;
         }
@@ -1075,9 +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:
@@ -1343,8 +1316,6 @@ EXPORT_SYMBOL(in_egroup_p);
 
 DECLARE_RWSEM(uts_sem);
 
-EXPORT_SYMBOL(uts_sem);
-
 asmlinkage long sys_newuname(struct new_utsname __user * name)
 {
         int errno = 0;
@@ -1368,8 +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);
@@ -1381,15 +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;
@@ -1414,8 +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);
@@ -1462,21 +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)
@@ -1508,18 +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;
 }
@@ -1557,11 +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;
@@ -1575,12 +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;
         }
 
@@ -1603,8 +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;
@@ -1613,7 +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;
@@ -1744,6 +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;
@@ -1795,7 +1777,7 @@ int orderly_poweroff(bool force)
                 goto out;
         }
 
-        info = call_usermodehelper_setup(argv[0], argv, envp);
+        info = call_usermodehelper_setup(argv[0], argv, envp, GFP_ATOMIC);
         if (info == NULL) {
                 argv_free(argv);
                 goto out;
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index 5b9b467de070..a77b27b11b04 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -31,6 +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_connect);
 cond_syscall(sys_getsockname);
 cond_syscall(sys_getpeername);
@@ -56,9 +57,11 @@ cond_syscall(compat_sys_set_robust_list);
 cond_syscall(sys_get_robust_list);
 cond_syscall(compat_sys_get_robust_list);
 cond_syscall(sys_epoll_create);
+cond_syscall(sys_epoll_create1);
 cond_syscall(sys_epoll_ctl);
 cond_syscall(sys_epoll_wait);
 cond_syscall(sys_epoll_pwait);
+cond_syscall(compat_sys_epoll_pwait);
 cond_syscall(sys_semget);
 cond_syscall(sys_semop);
 cond_syscall(sys_semtimedop);
@@ -94,6 +97,7 @@ cond_syscall(sys_keyctl);
 cond_syscall(compat_sys_keyctl);
 cond_syscall(compat_sys_socketcall);
 cond_syscall(sys_inotify_init);
+cond_syscall(sys_inotify_init1);
 cond_syscall(sys_inotify_add_watch);
 cond_syscall(sys_inotify_rm_watch);
 cond_syscall(sys_migrate_pages);
@@ -121,6 +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);
@@ -154,10 +164,13 @@ cond_syscall(sys_ioprio_get);
 
 /* New file descriptors */
 cond_syscall(sys_signalfd);
+cond_syscall(sys_signalfd4);
 cond_syscall(compat_sys_signalfd);
+cond_syscall(compat_sys_signalfd4);
 cond_syscall(sys_timerfd_create);
 cond_syscall(sys_timerfd_settime);
 cond_syscall(sys_timerfd_gettime);
 cond_syscall(compat_sys_timerfd_settime);
 cond_syscall(compat_sys_timerfd_gettime);
 cond_syscall(sys_eventfd);
+cond_syscall(sys_eventfd2);
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 6b16e16428d8..a13bd4dfaeb1 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -43,6 +43,7 @@
 #include <linux/limits.h>
 #include <linux/dcache.h>
 #include <linux/syscalls.h>
+#include <linux/vmstat.h>
 #include <linux/nfs_fs.h>
 #include <linux/acpi.h>
 #include <linux/reboot.h>
@@ -79,8 +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 sysctl_stat_interval;
 extern int latencytop_enabled;
 extern int sysctl_nr_open_min, sysctl_nr_open_max;
 #ifdef CONFIG_RCU_TORTURE_TEST
@@ -88,15 +87,16 @@ extern int rcutorture_runnable;
 #endif /* #ifdef CONFIG_RCU_TORTURE_TEST */
 
 /* Constants used for minimum and  maximum */
-#if defined(CONFIG_DETECT_SOFTLOCKUP) || defined(CONFIG_HIGHMEM)
+#if defined(CONFIG_HIGHMEM) || defined(CONFIG_DETECT_SOFTLOCKUP)
 static int one = 1;
 #endif
 
 #ifdef CONFIG_DETECT_SOFTLOCKUP
 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
 
@@ -110,17 +110,15 @@ static int min_percpu_pagelist_fract = 8;
 
 static int ngroups_max = NGROUPS_MAX;
 
-#ifdef CONFIG_KMOD
+#ifdef CONFIG_MODULES
 extern char modprobe_path[];
 #endif
 #ifdef CONFIG_CHR_DEV_SG
 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__
@@ -151,20 +149,22 @@ 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
 
 static struct ctl_table root_table[];
 static struct ctl_table_root sysctl_table_root;
 static struct ctl_table_header root_table_header = {
+        .count = 1,
         .ctl_table = root_table,
-        .ctl_entry = LIST_HEAD_INIT(sysctl_table_root.header_list),
+        .ctl_entry = LIST_HEAD_INIT(sysctl_table_root.default_set.list),
         .root = &sysctl_table_root,
+        .set = &sysctl_table_root.default_set,
 };
 static struct ctl_table_root sysctl_table_root = {
         .root_list = LIST_HEAD_INIT(sysctl_table_root.root_list),
-        .header_list = LIST_HEAD_INIT(root_table_header.ctl_entry),
+        .default_set.list = LIST_HEAD_INIT(root_table_header.ctl_entry),
 };
 
 static struct ctl_table kern_table[];
@@ -276,6 +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),
@@ -379,10 +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
@@ -412,7 +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",
@@ -475,7 +484,7 @@ static struct ctl_table kern_table[] = {
                 .proc_handler   = &ftrace_enable_sysctl,
         },
 #endif
-#ifdef CONFIG_KMOD
+#ifdef CONFIG_MODULES
         {
                 .ctl_name       = KERN_MODPROBE,
                 .procname       = "modprobe",
@@ -623,7 +632,7 @@ static struct ctl_table kern_table[] = {
         {
                 .ctl_name       = KERN_PRINTK_RATELIMIT,
                 .procname       = "printk_ratelimit",
-                .data           = &printk_ratelimit_jiffies,
+                .data           = &printk_ratelimit_state.interval,
                 .maxlen         = sizeof(int),
                 .mode           = 0644,
                 .proc_handler   = &proc_dointvec_jiffies,
@@ -632,7 +641,7 @@ static struct ctl_table kern_table[] = {
         {
                 .ctl_name       = KERN_PRINTK_RATELIMIT_BURST,
                 .procname       = "printk_ratelimit_burst",
-                .data           = &printk_ratelimit_burst,
+                .data           = &printk_ratelimit_state.burst,
                 .maxlen         = sizeof(int),
                 .mode           = 0644,
                 .proc_handler   = &proc_dointvec,
@@ -739,13 +748,24 @@ static struct ctl_table kern_table[] = {
 #ifdef CONFIG_DETECT_SOFTLOCKUP
         {
                 .ctl_name       = CTL_UNNUMBERED,
+                .procname       = "softlockup_panic",
+                .data           = &softlockup_panic,
+                .maxlen         = sizeof(int),
+                .mode           = 0644,
+                .proc_handler   = &proc_dointvec_minmax,
+                .strategy       = &sysctl_intvec,
+                .extra1         = &zero,
+                .extra2         = &one,
+        },
+        {
+                .ctl_name       = CTL_UNNUMBERED,
                 .procname       = "softlockup_thresh",
                 .data           = &softlockup_thresh,
-                .maxlen         = sizeof(unsigned long),
+                .maxlen         = sizeof(int),
                 .mode           = 0644,
-                .proc_handler   = &proc_doulongvec_minmax,
+                .proc_handler   = &proc_dointvec_minmax,
                 .strategy       = &sysctl_intvec,
-                .extra1         = &one,
+                .extra1         = &neg_one,
                 .extra2         = &sixty,
         },
         {
@@ -796,16 +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",
@@ -833,6 +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
@@ -947,7 +967,7 @@ static struct ctl_table vm_table[] = {
 #ifdef CONFIG_HUGETLB_PAGE
          {
                 .procname       = "nr_hugepages",
-                .data           = &max_huge_pages,
+                .data           = NULL,
                 .maxlen         = sizeof(unsigned long),
                 .mode           = 0644,
                 .proc_handler   = &hugetlb_sysctl_handler,
@@ -973,10 +993,12 @@ static struct ctl_table vm_table[] = {
         {
                 .ctl_name       = CTL_UNNUMBERED,
                 .procname       = "nr_overcommit_hugepages",
-                .data           = &sysctl_overcommit_huge_pages,
-                .maxlen         = sizeof(sysctl_overcommit_huge_pages),
+                .data           = NULL,
+                .maxlen         = sizeof(unsigned long),
                 .mode           = 0644,
                 .proc_handler   = &hugetlb_overcommit_handler,
+                .extra1         = (void *)&hugetlb_zero,
+                .extra2         = (void *)&hugetlb_infinity,
         },
 #endif
         {
@@ -1245,6 +1267,7 @@ static struct ctl_table fs_table[] = {
                 .extra1         = &minolduid,
                 .extra2         = &maxolduid,
         },
+#ifdef CONFIG_FILE_LOCKING
         {
                 .ctl_name       = FS_LEASES,
                 .procname       = "leases-enable",
@@ -1253,6 +1276,7 @@ static struct ctl_table fs_table[] = {
                 .mode           = 0644,
                 .proc_handler   = &proc_dointvec,
         },
+#endif
 #ifdef CONFIG_DNOTIFY
         {
                 .ctl_name       = FS_DIR_NOTIFY,
@@ -1264,6 +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",
@@ -1275,6 +1300,8 @@ static struct ctl_table fs_table[] = {
                 .extra1         = &zero,
                 .extra2         = &two,
         },
+#endif
+#ifdef CONFIG_AIO
         {
                 .procname       = "aio-nr",
                 .data           = &aio_nr,
@@ -1289,6 +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,
@@ -1372,6 +1400,9 @@ static void start_unregistering(struct ctl_table_header *p)
                 spin_unlock(&sysctl_lock);
                 wait_for_completion(&wait);
                 spin_lock(&sysctl_lock);
+        } else {
+                /* anything non-NULL; we'll never dereference it */
+                p->unregistering = ERR_PTR(-EINVAL);
         }
         /*
          * do not remove from the list until nobody holds it; walking the
@@ -1380,6 +1411,32 @@ static void start_unregistering(struct ctl_table_header *p)
         list_del_init(&p->ctl_entry);
 }
 
+void sysctl_head_get(struct ctl_table_header *head)
+{
+        spin_lock(&sysctl_lock);
+        head->count++;
+        spin_unlock(&sysctl_lock);
+}
+
+void sysctl_head_put(struct ctl_table_header *head)
+{
+        spin_lock(&sysctl_lock);
+        if (!--head->count)
+                kfree(head);
+        spin_unlock(&sysctl_lock);
+}
+
+struct ctl_table_header *sysctl_head_grab(struct ctl_table_header *head)
+{
+        if (!head)
+                BUG();
+        spin_lock(&sysctl_lock);
+        if (!use_table(head))
+                head = ERR_PTR(-ENOENT);
+        spin_unlock(&sysctl_lock);
+        return head;
+}
+
 void sysctl_head_finish(struct ctl_table_header *head)
 {
         if (!head)
@@ -1389,14 +1446,20 @@ void sysctl_head_finish(struct ctl_table_header *head)
         spin_unlock(&sysctl_lock);
 }
 
+static struct ctl_table_set *
+lookup_header_set(struct ctl_table_root *root, struct nsproxy *namespaces)
+{
+        struct ctl_table_set *set = &root->default_set;
+        if (root->lookup)
+                set = root->lookup(root, namespaces);
+        return set;
+}
+
 static struct list_head *
 lookup_header_list(struct ctl_table_root *root, struct nsproxy *namespaces)
 {
-        struct list_head *header_list;
-        header_list = &root->header_list;
-        if (root->lookup)
-                header_list = root->lookup(root, namespaces);
-        return header_list;
+        struct ctl_table_set *set = lookup_header_set(root, namespaces);
+        return &set->list;
 }
 
 struct ctl_table_header *__sysctl_head_next(struct nsproxy *namespaces,
@@ -1459,22 +1522,20 @@ 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)
 {
         int op = 0, rc;
 
         if (oldval)
-                op |= 004;
+                op |= MAY_READ;
         if (newval)
-                op |= 002;
+                op |= MAY_WRITE;
         if (sysctl_perm(root, table, op))
                 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)
@@ -1484,8 +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;
         }
@@ -1510,14 +1570,14 @@ repeat:
                 if (n == table->ctl_name) {
                         int error;
                         if (table->child) {
-                                if (sysctl_perm(root, table, 001))
+                                if (sysctl_perm(root, table, MAY_EXEC))
                                         return -EPERM;
                                 name++;
                                 nlen--;
                                 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;
@@ -1585,7 +1645,7 @@ static int test_perm(int mode, int op)
                 mode >>= 6;
         else if (in_egroup_p(0))
                 mode >>= 3;
-        if ((mode & op & 0007) == op)
+        if ((op & ~mode & (MAY_READ|MAY_WRITE|MAY_EXEC)) == 0)
                 return 0;
         return -EACCES;
 }
@@ -1595,7 +1655,7 @@ int sysctl_perm(struct ctl_table_root *root, struct ctl_table *table, int op)
         int error;
         int mode;
 
-        error = security_sysctl(table, op);
+        error = security_sysctl(table, op & (MAY_READ | MAY_WRITE | MAY_EXEC));
         if (error)
                 return error;
 
@@ -1630,6 +1690,54 @@ static __init int sysctl_init(void)
 
 core_initcall(sysctl_init);
 
+static struct ctl_table *is_branch_in(struct ctl_table *branch,
+                                      struct ctl_table *table)
+{
+        struct ctl_table *p;
+        const char *s = branch->procname;
+
+        /* branch should have named subdirectory as its first element */
+        if (!s || !branch->child)
+                return NULL;
+
+        /* ... and nothing else */
+        if (branch[1].procname || branch[1].ctl_name)
+                return NULL;
+
+        /* table should contain subdirectory with the same name */
+        for (p = table; p->procname || p->ctl_name; p++) {
+                if (!p->child)
+                        continue;
+                if (p->procname && strcmp(p->procname, s) == 0)
+                        return p;
+        }
+        return NULL;
+}
+
+/* see if attaching q to p would be an improvement */
+static void try_attach(struct ctl_table_header *p, struct ctl_table_header *q)
+{
+        struct ctl_table *to = p->ctl_table, *by = q->ctl_table;
+        struct ctl_table *next;
+        int is_better = 0;
+        int not_in_parent = !p->attached_by;
+
+        while ((next = is_branch_in(by, to)) != NULL) {
+                if (by == q->attached_by)
+                        is_better = 1;
+                if (to == p->attached_by)
+                        not_in_parent = 1;
+                by = by->child;
+                to = next->child;
+        }
+
+        if (is_better && not_in_parent) {
+                q->attached_by = by;
+                q->attached_to = to;
+                q->parent = p;
+        }
+}
+
 /**
  * __register_sysctl_paths - register a sysctl hierarchy
  * @root: List of sysctl headers to register on
@@ -1706,10 +1814,10 @@ struct ctl_table_header *__register_sysctl_paths(
         struct nsproxy *namespaces,
         const struct ctl_path *path, struct ctl_table *table)
 {
-        struct list_head *header_list;
         struct ctl_table_header *header;
         struct ctl_table *new, **prevp;
         unsigned int n, npath;
+        struct ctl_table_set *set;
 
         /* Count the path components */
         for (npath = 0; path[npath].ctl_name || path[npath].procname; ++npath)
@@ -1751,6 +1859,7 @@ struct ctl_table_header *__register_sysctl_paths(
         header->unregistering = NULL;
         header->root = root;
         sysctl_set_parent(NULL, header->ctl_table);
+        header->count = 1;
 #ifdef CONFIG_SYSCTL_SYSCALL_CHECK
         if (sysctl_check_table(namespaces, header->ctl_table)) {
                 kfree(header);
@@ -1758,8 +1867,20 @@ struct ctl_table_header *__register_sysctl_paths(
         }
 #endif
         spin_lock(&sysctl_lock);
-        header_list = lookup_header_list(root, namespaces);
-        list_add_tail(&header->ctl_entry, header_list);
+        header->set = lookup_header_set(root, namespaces);
+        header->attached_by = header->ctl_table;
+        header->attached_to = root_table;
+        header->parent = &root_table_header;
+        for (set = header->set; set; set = set->parent) {
+                struct ctl_table_header *p;
+                list_for_each_entry(p, &set->list, ctl_entry) {
+                        if (p->unregistering)
+                                continue;
+                        try_attach(p, header);
+                }
+        }
+        header->parent->count++;
+        list_add_tail(&header->ctl_entry, &header->set->list);
         spin_unlock(&sysctl_lock);
 
         return header;
@@ -1814,8 +1935,37 @@ void unregister_sysctl_table(struct ctl_table_header * header)
 
         spin_lock(&sysctl_lock);
         start_unregistering(header);
+        if (!--header->parent->count) {
+                WARN_ON(1);
+                kfree(header->parent);
+        }
+        if (!--header->count)
+                kfree(header);
+        spin_unlock(&sysctl_lock);
+}
+
+int sysctl_is_seen(struct ctl_table_header *p)
+{
+        struct ctl_table_set *set = p->set;
+        int res;
+        spin_lock(&sysctl_lock);
+        if (p->unregistering)
+                res = 0;
+        else if (!set->is_seen)
+                res = 1;
+        else
+                res = set->is_seen(set);
         spin_unlock(&sysctl_lock);
-        kfree(header);
+        return res;
+}
+
+void setup_sysctl_set(struct ctl_table_set *p,
+        struct ctl_table_set *parent,
+        int (*is_seen)(struct ctl_table_set *))
+{
+        INIT_LIST_HEAD(&p->list);
+        p->parent = parent ? parent : &sysctl_table_root.default_set;
+        p->is_seen = is_seen;
 }
 
 #else /* !CONFIG_SYSCTL */
@@ -1834,6 +1984,16 @@ void unregister_sysctl_table(struct ctl_table_header * table)
 {
 }
 
+void setup_sysctl_set(struct ctl_table_set *p,
+        struct ctl_table_set *parent,
+        int (*is_seen)(struct ctl_table_set *))
+{
+}
+
+void sysctl_head_put(struct ctl_table_header *head)
+{
+}
+
 #endif /* CONFIG_SYSCTL */
 
 /*
@@ -2086,49 +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 {
@@ -2576,7 +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)
 {
@@ -2610,7 +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)
 {
@@ -2656,7 +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)
 {
@@ -2692,7 +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)
 {
@@ -2726,7 +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)
 {
@@ -2781,35 +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/sysctl_check.c b/kernel/sysctl_check.c
index c09350d564f2..c35da23ab8fb 100644
--- a/kernel/sysctl_check.c
+++ b/kernel/sysctl_check.c
@@ -1532,6 +1532,8 @@ int sysctl_check_table(struct nsproxy *namespaces, struct ctl_table *table)
                         sysctl_check_leaf(namespaces, table, &fail);
                 }
                 sysctl_check_bin_path(table, &fail);
+                if (table->mode > 0777)
+                        set_fail(&fail, table, "bogus .mode");
                 if (fail) {
                         set_fail(&fail, table, NULL);
                         error = -EINVAL;
diff --git a/kernel/taskstats.c b/kernel/taskstats.c
index 4a23517169a6..bd6be76303cf 100644
--- a/kernel/taskstats.c
+++ b/kernel/taskstats.c
@@ -35,7 +35,7 @@
  */
 #define TASKSTATS_CPUMASK_MAXLEN        (100+6*NR_CPUS)
 
-static DEFINE_PER_CPU(__u32, taskstats_seqnum) = { 0 };
+static DEFINE_PER_CPU(__u32, taskstats_seqnum);
 static int family_registered;
 struct kmem_cache *taskstats_cache;
 
@@ -301,7 +301,7 @@ static int add_del_listener(pid_t pid, cpumask_t *maskp, int isadd)
                 return -EINVAL;
 
         if (isadd == REGISTER) {
-                for_each_cpu_mask(cpu, mask) {
+                for_each_cpu_mask_nr(cpu, mask) {
                         s = kmalloc_node(sizeof(struct listener), GFP_KERNEL,
                                          cpu_to_node(cpu));
                         if (!s)
@@ -320,7 +320,7 @@ static int add_del_listener(pid_t pid, cpumask_t *maskp, int isadd)
 
         /* Deregister or cleanup */
 cleanup:
-        for_each_cpu_mask(cpu, mask) {
+        for_each_cpu_mask_nr(cpu, mask) {
                 listeners = &per_cpu(listener_array, cpu);
                 down_write(&listeners->sem);
                 list_for_each_entry_safe(s, tmp, &listeners->list, list) {
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 3d1e3e1a1971..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)
  *
@@ -177,7 +187,7 @@ void clockevents_register_device(struct clock_event_device *dev)
 /*
  * Noop handler when we shut down an event device
  */
-static void clockevents_handle_noop(struct clock_event_device *dev)
+void clockevents_handle_noop(struct clock_event_device *dev)
 {
 }
 
@@ -199,7 +209,6 @@ void clockevents_exchange_device(struct clock_event_device *old,
          * released list and do a notify add later.
          */
         if (old) {
-                old->event_handler = clockevents_handle_noop;
                 clockevents_set_mode(old, CLOCK_EVT_MODE_UNUSED);
                 list_del(&old->list);
                 list_add(&old->list, &clockevents_released);
@@ -207,7 +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 dadde5361f32..9ed2eec97526 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -145,9 +145,9 @@ static void clocksource_watchdog(unsigned long data)
                  * Cycle through CPUs to check if the CPUs stay
                  * synchronized to each other.
                  */
-                int next_cpu = next_cpu(raw_smp_processor_id(), cpu_online_map);
+                int next_cpu = next_cpu_nr(raw_smp_processor_id(), cpu_online_map);
 
-                if (next_cpu >= NR_CPUS)
+                if (next_cpu >= nr_cpu_ids)
                         next_cpu = first_cpu(cpu_online_map);
                 watchdog_timer.expires += WATCHDOG_INTERVAL;
                 add_timer_on(&watchdog_timer, next_cpu);
@@ -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)
@@ -376,7 +379,8 @@ void clocksource_unregister(struct clocksource *cs)
  * Provides sysfs interface for listing current clocksource.
  */
 static ssize_t
-sysfs_show_current_clocksources(struct sys_device *dev, char *buf)
+sysfs_show_current_clocksources(struct sys_device *dev,
+                                struct sysdev_attribute *attr, char *buf)
 {
         ssize_t count = 0;
 
@@ -397,6 +401,7 @@ sysfs_show_current_clocksources(struct sys_device *dev, char *buf)
  * clocksource selction.
  */
 static ssize_t sysfs_override_clocksource(struct sys_device *dev,
+                                          struct sysdev_attribute *attr,
                                           const char *buf, size_t count)
 {
         struct clocksource *ovr = NULL;
@@ -449,7 +454,9 @@ static ssize_t sysfs_override_clocksource(struct sys_device *dev,
  * Provides sysfs interface for listing registered clocksources
  */
 static ssize_t
-sysfs_show_available_clocksources(struct sys_device *dev, char *buf)
+sysfs_show_available_clocksources(struct sys_device *dev,
+                                  struct sysdev_attribute *attr,
+                                  char *buf)
 {
         struct clocksource *src;
         ssize_t count = 0;
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 5125ddd8196b..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;
@@ -245,7 +244,7 @@ static void sync_cmos_clock(unsigned long dummy)
         if (abs(now.tv_nsec - (NSEC_PER_SEC / 2)) <= tick_nsec / 2)
                 fail = update_persistent_clock(now);
 
-        next.tv_nsec = (NSEC_PER_SEC / 2) - now.tv_nsec;
+        next.tv_nsec = (NSEC_PER_SEC / 2) - now.tv_nsec - (TICK_NSEC / 2);
         if (next.tv_nsec <= 0)
                 next.tv_nsec += NSEC_PER_SEC;
 
@@ -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 f48d0f09d32f..f98a1b7b16e9 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -175,6 +175,8 @@ static void tick_do_periodic_broadcast(void)
  */
 static void tick_handle_periodic_broadcast(struct clock_event_device *dev)
 {
+        ktime_t next;
+
         tick_do_periodic_broadcast();
 
         /*
@@ -185,10 +187,13 @@ static void tick_handle_periodic_broadcast(struct clock_event_device *dev)
 
         /*
          * Setup the next period for devices, which do not have
-         * periodic mode:
+         * periodic mode. We read dev->next_event first and add to it
+         * when the event alrady expired. clockevents_program_event()
+         * sets dev->next_event only when the event is really
+         * programmed to the device.
          */
-        for (;;) {
-                ktime_t next = ktime_add(dev->next_event, tick_period);
+        for (next = dev->next_event; ;) {
+                next = ktime_add(next, tick_period);
 
                 if (!clockevents_program_event(dev, next, ktime_get()))
                         return;
@@ -205,7 +210,7 @@ static void tick_do_broadcast_on_off(void *why)
         struct clock_event_device *bc, *dev;
         struct tick_device *td;
         unsigned long flags, *reason = why;
-        int cpu;
+        int cpu, bc_stopped;
 
         spin_lock_irqsave(&tick_broadcast_lock, flags);
 
@@ -223,14 +228,16 @@ static void tick_do_broadcast_on_off(void *why)
         if (!tick_device_is_functional(dev))
                 goto out;
 
+        bc_stopped = cpus_empty(tick_broadcast_mask);
+
         switch (*reason) {
         case CLOCK_EVT_NOTIFY_BROADCAST_ON:
         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;
@@ -239,15 +246,17 @@ 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;
         }
 
-        if (cpus_empty(tick_broadcast_mask))
-                clockevents_set_mode(bc, CLOCK_EVT_MODE_SHUTDOWN);
-        else {
+        if (cpus_empty(tick_broadcast_mask)) {
+                if (!bc_stopped)
+                        clockevents_shutdown(bc);
+        } else if (bc_stopped) {
                 if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC)
                         tick_broadcast_start_periodic(bc);
                 else
@@ -298,7 +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);
@@ -313,7 +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);
 }
@@ -364,16 +373,8 @@ cpumask_t *tick_get_broadcast_oneshot_mask(void)
 static int tick_broadcast_set_event(ktime_t expires, int force)
 {
         struct clock_event_device *bc = tick_broadcast_device.evtdev;
-        ktime_t now = ktime_get();
-        int res;
-
-        for(;;) {
-                res = clockevents_program_event(bc, expires, now);
-                if (!res || !force)
-                        return res;
-                now = ktime_get();
-                expires = ktime_add(now, ktime_set(0, bc->min_delta_ns));
-        }
+
+        return tick_dev_program_event(bc, expires, force);
 }
 
 int tick_resume_broadcast_oneshot(struct clock_event_device *bc)
@@ -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)
@@ -399,8 +413,7 @@ again:
         mask = CPU_MASK_NONE;
         now = ktime_get();
         /* Find all expired events */
-        for (cpu = first_cpu(tick_broadcast_oneshot_mask); cpu != NR_CPUS;
-             cpu = next_cpu(cpu, tick_broadcast_oneshot_mask)) {
+        for_each_cpu_mask_nr(cpu, tick_broadcast_oneshot_mask) {
                 td = &per_cpu(tick_cpu_device, cpu);
                 if (td->evtdev->next_event.tv64 <= now.tv64)
                         cpu_set(cpu, mask);
@@ -492,14 +505,52 @@ static void tick_broadcast_clear_oneshot(int cpu)
         cpu_clear(cpu, tick_broadcast_oneshot_mask);
 }
 
+static void tick_broadcast_init_next_event(cpumask_t *mask, ktime_t expires)
+{
+        struct tick_device *td;
+        int cpu;
+
+        for_each_cpu_mask_nr(cpu, *mask) {
+                td = &per_cpu(tick_cpu_device, cpu);
+                if (td->evtdev)
+                        td->evtdev->next_event = expires;
+        }
+}
+
 /**
  * tick_broadcast_setup_oneshot - setup the broadcast device
  */
 void tick_broadcast_setup_oneshot(struct clock_event_device *bc)
 {
-        bc->event_handler = tick_handle_oneshot_broadcast;
-        clockevents_set_mode(bc, CLOCK_EVT_MODE_ONESHOT);
-        bc->next_event.tv64 = KTIME_MAX;
+        /* Set it up only once ! */
+        if (bc->event_handler != tick_handle_oneshot_broadcast) {
+                int was_periodic = bc->mode == CLOCK_EVT_MODE_PERIODIC;
+                int cpu = smp_processor_id();
+                cpumask_t mask;
+
+                bc->event_handler = tick_handle_oneshot_broadcast;
+                clockevents_set_mode(bc, CLOCK_EVT_MODE_ONESHOT);
+
+                /* Take the do_timer update */
+                tick_do_timer_cpu = cpu;
+
+                /*
+                 * We must be careful here. There might be other CPUs
+                 * waiting for periodic broadcast. We need to set the
+                 * oneshot_mask bits for those and program the
+                 * broadcast device to fire.
+                 */
+                mask = tick_broadcast_mask;
+                cpu_clear(cpu, mask);
+                cpus_or(tick_broadcast_oneshot_mask,
+                        tick_broadcast_oneshot_mask, mask);
+
+                if (was_periodic && !cpus_empty(mask)) {
+                        tick_broadcast_init_next_event(&mask, tick_next_period);
+                        tick_broadcast_set_event(tick_next_period, 1);
+                } else
+                        bc->next_event.tv64 = KTIME_MAX;
+        }
 }
 
 /*
@@ -539,4 +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 4f3886562b8c..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;
@@ -135,7 +136,7 @@ void tick_setup_periodic(struct clock_event_device *dev, int broadcast)
  */
 static void tick_setup_device(struct tick_device *td,
                               struct clock_event_device *newdev, int cpu,
-                              cpumask_t cpumask)
+                              const cpumask_t *cpumask)
 {
         ktime_t next_event;
         void (*handler)(struct clock_event_device *) = NULL;
@@ -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);
@@ -161,6 +162,7 @@ static void tick_setup_device(struct tick_device *td,
         } else {
                 handler = td->evtdev->event_handler;
                 next_event = td->evtdev->next_event;
+                td->evtdev->event_handler = clockevents_handle_noop;
         }
 
         td->evtdev = newdev;
@@ -169,8 +171,8 @@ static void tick_setup_device(struct tick_device *td,
          * When the device is not per cpu, pin the interrupt to the
          * current cpu:
          */
-        if (!cpus_equal(newdev->cpumask, cpumask))
-                irq_set_affinity(newdev->irq, cpumask);
+        if (!cpus_equal(newdev->cpumask, *cpumask))
+                irq_set_affinity(newdev->irq, *cpumask);
 
         /*
          * When global broadcasting is active, check if the current
@@ -196,7 +198,6 @@ static int tick_check_new_device(struct clock_event_device *newdev)
         struct tick_device *td;
         int cpu, ret = NOTIFY_OK;
         unsigned long flags;
-        cpumask_t cpumask;
 
         spin_lock_irqsave(&tick_device_lock, flags);
 
@@ -206,10 +207,9 @@ static int tick_check_new_device(struct clock_event_device *newdev)
 
         td = &per_cpu(tick_cpu_device, cpu);
         curdev = td->evtdev;
-        cpumask = cpumask_of_cpu(cpu);
 
         /* cpu local device ? */
-        if (!cpus_equal(newdev->cpumask, cpumask)) {
+        if (!cpus_equal(newdev->cpumask, cpumask_of_cpu(cpu))) {
 
                 /*
                  * If the cpu affinity of the device interrupt can not
@@ -222,7 +222,7 @@ static int tick_check_new_device(struct clock_event_device *newdev)
                  * If we have a cpu local device already, do not replace it
                  * by a non cpu local device
                  */
-                if (curdev && cpus_equal(curdev->cpumask, cpumask))
+                if (curdev && cpus_equal(curdev->cpumask, cpumask_of_cpu(cpu)))
                         goto out_bc;
         }
 
@@ -250,11 +250,11 @@ 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);
-        tick_setup_device(td, newdev, cpu, cpumask);
+        tick_setup_device(td, newdev, cpu, &cpumask_of_cpu(cpu));
         if (newdev->features & CLOCK_EVT_FEAT_ONESHOT)
                 tick_oneshot_notify();
 
@@ -301,7 +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);
 }
@@ -312,7 +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 f13f2b7f4fd4..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
  */
@@ -17,6 +23,8 @@ extern void tick_handle_periodic(struct clock_event_device *dev);
 extern void tick_setup_oneshot(struct clock_event_device *newdev,
                                void (*handler)(struct clock_event_device *),
                                ktime_t nextevt);
+extern int tick_dev_program_event(struct clock_event_device *dev,
+                                  ktime_t expires, int force);
 extern int tick_program_event(ktime_t expires, int force);
 extern void tick_oneshot_notify(void);
 extern int tick_switch_to_oneshot(void (*handler)(struct clock_event_device *));
@@ -27,6 +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)
 {
@@ -35,6 +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 */
@@ -64,6 +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-oneshot.c b/kernel/time/tick-oneshot.c
index 450c04935b66..2e8de678e767 100644
--- a/kernel/time/tick-oneshot.c
+++ b/kernel/time/tick-oneshot.c
@@ -23,24 +23,56 @@
 #include "tick-internal.h"
 
 /**
- * tick_program_event
+ * tick_program_event internal worker function
  */
-int tick_program_event(ktime_t expires, int force)
+int tick_dev_program_event(struct clock_event_device *dev, ktime_t expires,
+                           int force)
 {
-        struct clock_event_device *dev = __get_cpu_var(tick_cpu_device).evtdev;
         ktime_t now = ktime_get();
+        int i;
 
-        while (1) {
+        for (i = 0;;) {
                 int ret = clockevents_program_event(dev, expires, now);
 
                 if (!ret || !force)
                         return ret;
+
+                /*
+                 * We tried 2 times to program the device with the given
+                 * min_delta_ns. If that's not working then we double it
+                 * and emit a warning.
+                 */
+                if (++i > 2) {
+                        /* Increase the min. delta and try again */
+                        if (!dev->min_delta_ns)
+                                dev->min_delta_ns = 5000;
+                        else
+                                dev->min_delta_ns += dev->min_delta_ns >> 1;
+
+                        printk(KERN_WARNING
+                               "CE: %s increasing min_delta_ns to %lu nsec\n",
+                               dev->name ? dev->name : "?",
+                               dev->min_delta_ns << 1);
+
+                        i = 0;
+                }
+
                 now = ktime_get();
-                expires = ktime_add(now, ktime_set(0, dev->min_delta_ns));
+                expires = ktime_add_ns(now, dev->min_delta_ns);
         }
 }
 
 /**
+ * tick_program_event
+ */
+int tick_program_event(ktime_t expires, int force)
+{
+        struct clock_event_device *dev = __get_cpu_var(tick_cpu_device).evtdev;
+
+        return tick_dev_program_event(dev, expires, force);
+}
+
+/**
  * tick_resume_onshot - resume oneshot mode
  */
 void tick_resume_oneshot(void)
@@ -61,7 +93,7 @@ void tick_setup_oneshot(struct clock_event_device *newdev,
 {
         newdev->event_handler = handler;
         clockevents_set_mode(newdev, CLOCK_EVT_MODE_ONESHOT);
-        clockevents_program_event(newdev, next_event, ktime_get());
+        tick_dev_program_event(newdev, next_event, 1);
 }
 
 /**
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index beef7ccdf842..5bbb1044f847 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);
 }
@@ -140,8 +144,6 @@ void tick_nohz_update_jiffies(void)
         if (!ts->tick_stopped)
                 return;
 
-        touch_softlockup_watchdog();
-
         cpu_clear(cpu, nohz_cpu_mask);
         now = ktime_get();
         ts->idle_waketime = now;
@@ -149,9 +151,11 @@ void tick_nohz_update_jiffies(void)
         local_irq_save(flags);
         tick_do_update_jiffies64(now);
         local_irq_restore(flags);
+
+        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);
 
@@ -162,6 +166,8 @@ void tick_nohz_stop_idle(int cpu)
                 ts->idle_lastupdate = now;
                 ts->idle_sleeptime = ktime_add(ts->idle_sleeptime, delta);
                 ts->idle_active = 0;
+
+                sched_clock_idle_wakeup_event(0);
         }
 }
 
@@ -177,6 +183,7 @@ static ktime_t tick_nohz_start_idle(struct tick_sched *ts)
         }
         ts->idle_entrytime = now;
         ts->idle_active = 1;
+        sched_clock_idle_sleep_event();
         return now;
 }
 
@@ -184,9 +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
@@ -195,7 +210,7 @@ u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time)
  * Called either from the idle loop or from irq_exit() when an idle period was
  * just interrupted by an interrupt which did not cause a reschedule.
  */
-void tick_nohz_stop_sched_tick(void)
+void tick_nohz_stop_sched_tick(int inidle)
 {
         unsigned long seq, last_jiffies, next_jiffies, delta_jiffies, flags;
         struct tick_sched *ts;
@@ -218,12 +233,17 @@ void tick_nohz_stop_sched_tick(void)
          */
         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))
                 goto end;
 
+        if (!inidle && !ts->inidle)
+                goto end;
+
+        ts->inidle = 1;
+
         if (need_resched())
                 goto end;
 
@@ -250,7 +270,7 @@ void tick_nohz_stop_sched_tick(void)
         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
@@ -280,11 +300,10 @@ void tick_nohz_stop_sched_tick(void)
                                 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();
-                        sched_clock_tick_stop(cpu);
                 }
 
                 /*
@@ -296,7 +315,7 @@ void tick_nohz_stop_sched_tick(void)
                  * invoked.
                  */
                 if (cpu == tick_do_timer_cpu)
-                        tick_do_timer_cpu = -1;
+                        tick_do_timer_cpu = TICK_DO_TIMER_NONE;
 
                 ts->idle_sleeps++;
 
@@ -358,6 +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
  *
@@ -373,18 +418,20 @@ void tick_nohz_restart_sched_tick(void)
         local_irq_disable();
         tick_nohz_stop_idle(cpu);
 
-        if (!ts->tick_stopped) {
+        if (!ts->inidle || !ts->tick_stopped) {
+                ts->inidle = 0;
                 local_irq_enable();
                 return;
         }
 
+        ts->inidle = 0;
+
         rcu_exit_nohz();
 
         /* Update jiffies first */
         select_nohz_load_balancer(0);
         now = ktime_get();
         tick_do_update_jiffies64(now);
-        sched_clock_tick_start(cpu);
         cpu_clear(cpu, nohz_cpu_mask);
 
         /*
@@ -409,35 +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);
 }
 
 /*
@@ -459,7 +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 */
@@ -482,10 +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);
@@ -520,7 +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);
@@ -531,6 +555,37 @@ 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)
+{
+        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);
+}
+
 #else
 
 static inline void tick_nohz_switch_to_nohz(void) { }
@@ -538,6 +593,19 @@ 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
@@ -561,7 +629,7 @@ 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
 
@@ -590,10 +658,6 @@ 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;
@@ -613,19 +677,18 @@ 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;
@@ -637,17 +700,21 @@ void tick_setup_sched_timer(void)
                 ts->nohz_mode = NOHZ_MODE_HIGHRES;
 #endif
 }
+#endif /* HIGH_RES_TIMERS */
 
+#if defined CONFIG_NO_HZ || defined CONFIG_HIGH_RES_TIMERS
 void tick_cancel_sched_timer(int cpu)
 {
         struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
 
+# ifdef CONFIG_HIGH_RES_TIMERS
         if (ts->sched_timer.base)
                 hrtimer_cancel(&ts->sched_timer);
+# endif
 
         ts->nohz_mode = NOHZ_MODE_INACTIVE;
 }
-#endif /* HIGH_RES_TIMERS */
+#endif
 
 /**
  * Async notification about clocksource changes
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..56becf373c58 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -978,6 +978,7 @@ 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 +1436,11 @@ 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 +1455,7 @@ 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..1cb3e1f616af 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -1,23 +1,37 @@
 #
 # Architectures that offer an FTRACE implementation should select HAVE_FTRACE:
 #
+
+config NOP_TRACER
+        bool
+
 config HAVE_FTRACE
         bool
+        select NOP_TRACER
 
 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 RING_BUFFER
         select STACKTRACE
+        select TRACEPOINTS
 
 config FTRACE
         bool "Kernel Function Tracer"
         depends on HAVE_FTRACE
+        depends on DEBUG_KERNEL
         select FRAME_POINTER
         select TRACING
         select CONTEXT_SWITCH_TRACER
@@ -36,6 +50,7 @@ config IRQSOFF_TRACER
         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
@@ -59,6 +74,7 @@ config PREEMPT_TRACER
         depends on GENERIC_TIME
         depends on PREEMPT
         depends on HAVE_FTRACE
+        depends on DEBUG_KERNEL
         select TRACING
         select TRACER_MAX_TRACE
         help
@@ -86,6 +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
@@ -96,16 +113,56 @@ 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 HAVE_FTRACE
+        depends on DEBUG_KERNEL
+        select TRACING
+        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_FTRACE
+        depends on DEBUG_KERNEL
+        select FTRACE
+        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 HAVE_DYNAMIC_FTRACE
+        depends on DEBUG_KERNEL
         default y
         help
          This option will modify all the calls to ftrace dynamically
@@ -121,12 +178,17 @@ 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
diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile
index 71d17de17288..a85dfba88ba0 100644
--- a/kernel/trace/Makefile
+++ b/kernel/trace/Makefile
@@ -11,6 +11,7 @@ obj-y += trace_selftest_dynamic.o
 endif
 
 obj-$(CONFIG_FTRACE) += libftrace.o
+obj-$(CONFIG_RING_BUFFER) += ring_buffer.o
 
 obj-$(CONFIG_TRACING) += trace.o
 obj-$(CONFIG_CONTEXT_SWITCH_TRACER) += trace_sched_switch.o
@@ -19,6 +20,9 @@ obj-$(CONFIG_FTRACE) += trace_functions.o
 obj-$(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 4231a3dc224a..4dda4f60a2a9 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -81,7 +81,7 @@ 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 +115,7 @@ 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);
 
         /*
@@ -153,6 +154,30 @@ static int __unregister_ftrace_function(struct ftrace_ops *ops)
 
 #ifdef CONFIG_DYNAMIC_FTRACE
 
+#ifndef CONFIG_FTRACE_MCOUNT_RECORD
+/*
+ * The hash lock is only needed when the recording of the mcount
+ * callers are dynamic. That is, by the caller themselves and
+ * not recorded via the compilation.
+ */
+static DEFINE_SPINLOCK(ftrace_hash_lock);
+#define ftrace_hash_lock(flags)   spin_lock_irqsave(&ftrace_hash_lock, flags)
+#define ftrace_hash_unlock(flags) \
+                        spin_unlock_irqrestore(&ftrace_hash_lock, flags)
+#else
+/* This is protected via the ftrace_lock with MCOUNT_RECORD. */
+#define ftrace_hash_lock(flags)   do { (void)(flags); } while (0)
+#define ftrace_hash_unlock(flags) do { } while(0)
+#endif
+
+/*
+ * 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;
+
 static struct task_struct *ftraced_task;
 
 enum {
@@ -171,7 +196,6 @@ static struct hlist_head ftrace_hash[FTRACE_HASHSIZE];
 
 static DEFINE_PER_CPU(int, ftrace_shutdown_disable_cpu);
 
-static DEFINE_SPINLOCK(ftrace_shutdown_lock);
 static DEFINE_MUTEX(ftraced_lock);
 static DEFINE_MUTEX(ftrace_regex_lock);
 
@@ -294,13 +318,37 @@ static inline void ftrace_del_hash(struct dyn_ftrace *node)
 
 static void ftrace_free_rec(struct dyn_ftrace *rec)
 {
-        /* no locking, only called from kstop_machine */
-
         rec->ip = (unsigned long)ftrace_free_records;
         ftrace_free_records = rec;
         rec->flags |= FTRACE_FL_FREE;
 }
 
+void ftrace_release(void *start, unsigned long size)
+{
+        struct dyn_ftrace *rec;
+        struct ftrace_page *pg;
+        unsigned long s = (unsigned long)start;
+        unsigned long e = s + size;
+        int i;
+
+        if (ftrace_disabled || !start)
+                return;
+
+        /* should not be called from interrupt context */
+        spin_lock(&ftrace_lock);
+
+        for (pg = ftrace_pages_start; pg; pg = pg->next) {
+                for (i = 0; i < pg->index; i++) {
+                        rec = &pg->records[i];
+
+                        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)
 {
         struct dyn_ftrace *rec;
@@ -338,7 +386,6 @@ ftrace_record_ip(unsigned long ip)
         unsigned long flags;
         unsigned long key;
         int resched;
-        int atomic;
         int cpu;
 
         if (!ftrace_enabled || ftrace_disabled)
@@ -368,9 +415,7 @@ ftrace_record_ip(unsigned long ip)
         if (ftrace_ip_in_hash(ip, key))
                 goto out;
 
-        atomic = irqs_disabled();
-
-        spin_lock_irqsave(&ftrace_shutdown_lock, flags);
+        ftrace_hash_lock(flags);
 
         /* This ip may have hit the hash before the lock */
         if (ftrace_ip_in_hash(ip, key))
@@ -387,7 +432,7 @@ ftrace_record_ip(unsigned long ip)
         ftraced_trigger = 1;
 
  out_unlock:
-        spin_unlock_irqrestore(&ftrace_shutdown_lock, flags);
+        ftrace_hash_unlock(flags);
  out:
         per_cpu(ftrace_shutdown_disable_cpu, cpu)--;
 
@@ -531,6 +576,16 @@ static void ftrace_shutdown_replenish(void)
         ftrace_pages->next = (void *)get_zeroed_page(GFP_KERNEL);
 }
 
+static void print_ip_ins(const char *fmt, unsigned char *p)
+{
+        int i;
+
+        printk(KERN_CONT "%s", fmt);
+
+        for (i = 0; i < MCOUNT_INSN_SIZE; i++)
+                printk(KERN_CONT "%s%02x", i ? ":" : "", p[i]);
+}
+
 static int
 ftrace_code_disable(struct dyn_ftrace *rec)
 {
@@ -541,10 +596,27 @@ ftrace_code_disable(struct dyn_ftrace *rec)
         ip = rec->ip;
 
         nop = ftrace_nop_replace();
-        call = ftrace_call_replace(ip, MCOUNT_ADDR);
+        call = ftrace_call_replace(ip, mcount_addr);
 
         failed = ftrace_modify_code(ip, call, nop);
         if (failed) {
+                switch (failed) {
+                case 1:
+                        WARN_ON_ONCE(1);
+                        pr_info("ftrace faulted on modifying ");
+                        print_ip_sym(ip);
+                        break;
+                case 2:
+                        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;
+                }
+
                 rec->flags |= FTRACE_FL_FAILED;
                 return 0;
         }
@@ -587,7 +659,7 @@ static int __ftrace_modify_code(void *data)
 
 static void ftrace_run_update_code(int command)
 {
-        stop_machine_run(__ftrace_modify_code, &command, NR_CPUS);
+        stop_machine(__ftrace_modify_code, &command, NULL);
 }
 
 void ftrace_disable_daemon(void)
@@ -787,52 +859,12 @@ static int ftrace_update_code(void)
             !ftrace_enabled || !ftraced_trigger)
                 return 0;
 
-        stop_machine_run(__ftrace_update_code, NULL, NR_CPUS);
+        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 +891,9 @@ 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 hash entries in %d pages\n",
+                num_to_init, cnt);
 
         for (i = 0; i < cnt; i++) {
                 pg->next = (void *)get_zeroed_page(GFP_KERNEL);
@@ -901,6 +935,8 @@ 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) {
@@ -910,15 +946,13 @@ 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))) ||
-
-                    ((iter->flags & FTRACE_ITER_FILTER) &&
-                     !(rec->flags & FTRACE_FL_FILTER)) ||
+                     !(rec->flags & FTRACE_FL_FAILED)) ||
 
                     ((iter->flags & FTRACE_ITER_NOTRACE) &&
                      !(rec->flags & FTRACE_FL_NOTRACE))) {
@@ -926,6 +960,7 @@ t_next(struct seq_file *m, void *v, loff_t *pos)
                         goto retry;
                 }
         }
+        spin_unlock(&ftrace_lock);
 
         iter->pos = *pos;
 
@@ -1039,8 +1074,8 @@ 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 +1088,7 @@ static void ftrace_filter_reset(int enable)
                 }
                 pg = pg->next;
         }
-        preempt_enable();
+        spin_unlock(&ftrace_lock);
 }
 
 static int
@@ -1165,8 +1200,8 @@ 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 +1238,7 @@ ftrace_match(unsigned char *buff, int len, int enable)
                 }
                 pg = pg->next;
         }
-        preempt_enable();
+        spin_unlock(&ftrace_lock);
 }
 
 static ssize_t
@@ -1556,6 +1591,114 @@ static __init int ftrace_init_debugfs(void)
 
 fs_initcall(ftrace_init_debugfs);
 
+#ifdef CONFIG_FTRACE_MCOUNT_RECORD
+static int ftrace_convert_nops(unsigned long *start,
+                               unsigned long *end)
+{
+        unsigned long *p;
+        unsigned long addr;
+        unsigned long flags;
+
+        p = start;
+        while (p < end) {
+                addr = ftrace_call_adjust(*p++);
+                /* should not be called from interrupt context */
+                spin_lock(&ftrace_lock);
+                ftrace_record_ip(addr);
+                spin_unlock(&ftrace_lock);
+                ftrace_shutdown_replenish();
+        }
+
+        /* p is ignored */
+        local_irq_save(flags);
+        __ftrace_update_code(p);
+        local_irq_restore(flags);
+
+        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;
+
+        /* Keep the ftrace pointer to the stub */
+        addr = (unsigned long)ftrace_stub;
+
+        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)
+                goto failed;
+
+        count = __stop_mcount_loc - __start_mcount_loc;
+
+        ret = ftrace_dyn_table_alloc(count);
+        if (ret)
+                goto failed;
+
+        last_ftrace_enabled = ftrace_enabled = 1;
+
+        ret = ftrace_convert_nops(__start_mcount_loc,
+                                  __stop_mcount_loc);
+
+        return;
+ failed:
+        ftrace_disabled = 1;
+}
+#else /* CONFIG_FTRACE_MCOUNT_RECORD */
+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_dynamic_init(void)
 {
         struct task_struct *p;
@@ -1564,7 +1707,7 @@ static int __init ftrace_dynamic_init(void)
 
         addr = (unsigned long)ftrace_record_ip;
 
-        stop_machine_run(ftrace_dyn_arch_init, &addr, NR_CPUS);
+        stop_machine(ftrace_dyn_arch_init, &addr, NULL);
 
         /* ftrace_dyn_arch_init places the return code in addr */
         if (addr) {
@@ -1572,7 +1715,7 @@ static int __init ftrace_dynamic_init(void)
                 goto failed;
         }
 
-        ret = ftrace_dyn_table_alloc();
+        ret = ftrace_dyn_table_alloc(NR_TO_INIT);
         if (ret)
                 goto failed;
 
@@ -1593,6 +1736,8 @@ static int __init ftrace_dynamic_init(void)
 }
 
 core_initcall(ftrace_dynamic_init);
+#endif /* CONFIG_FTRACE_MCOUNT_RECORD */
+
 #else
 # define ftrace_startup()               do { } while (0)
 # define ftrace_shutdown()              do { } while (0)
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
new file mode 100644
index 000000000000..94af1fe56bb4
--- /dev/null
+++ b/kernel/trace/ring_buffer.c
@@ -0,0 +1,2014 @@
+/*
+ * 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>
+
+/* Up this if you want to test the TIME_EXTENTS and normalization */
+#define DEBUG_SHIFT 0
+
+/* FIXME!!! */
+u64 ring_buffer_time_stamp(int cpu)
+{
+        /* shift to debug/test normalization and TIME_EXTENTS */
+        return sched_clock() << DEBUG_SHIFT;
+}
+
+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(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;
+
+        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);
+        }
+        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",
+                       *delta, *ts, 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;
+
+ again:
+        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))
+                        goto again;
+
+                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 (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 (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;
+
+        spin_lock_irqsave(&cpu_buffer->lock, flags);
+
+ again:
+        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;
+
+        if (!cpu_isset(cpu, buffer->cpumask))
+                return NULL;
+
+        cpu_buffer = buffer->buffers[cpu];
+
+ again:
+        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;
+
+        if (ring_buffer_iter_empty(iter))
+                return NULL;
+
+        cpu_buffer = iter->cpu_buffer;
+        buffer = cpu_buffer->buffer;
+
+ again:
+        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;
+}
+
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 868e121c8e38..d345d649d073 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 +33,36 @@
 #include <linux/writeback.h>
 
 #include <linux/stacktrace.h>
+#include <linux/ring_buffer.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 +73,9 @@ 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 +115,18 @@ 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 +155,6 @@ 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 +171,21 @@ 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 +193,6 @@ 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 +211,7 @@ static const char *trace_options[] = {
         "block",
         "stacktrace",
         "sched-tree",
+        "ftrace_printk",
         NULL
 };
 
@@ -266,54 +254,6 @@ __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 +335,23 @@ 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 +395,6 @@ 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 +407,17 @@ 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 +434,19 @@ 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 +483,6 @@ 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 +494,7 @@ 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 +510,7 @@ 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 +556,11 @@ 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 +646,16 @@ 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 =
+                (irqs_disabled_flags(flags) ? TRACE_FLAG_IRQS_OFF : 0) |
                 ((pc & HARDIRQ_MASK) ? TRACE_FLAG_HARDIRQ : 0) |
                 ((pc & SOFTIRQ_MASK) ? TRACE_FLAG_SOFTIRQ : 0) |
                 (need_resched() ? TRACE_FLAG_NEED_RESCHED : 0);
@@ -828,145 +663,139 @@ 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;
+        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 +803,28 @@ 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();
 }
@@ -1002,23 +834,21 @@ 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
@@ -1029,7 +859,8 @@ 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;
@@ -1037,16 +868,22 @@ function_trace_call(unsigned long ip, unsigned long parent_ip)
         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 =
@@ -1073,117 +910,101 @@ 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();
+}
+
+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];
 
-        page = list_entry(iter->next_page[cpu], struct page, lru);
-        BUG_ON(&data->trace_pages == &page->lru);
+        /* 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)
 {
         struct trace_iterator *iter = m->private;
-        void *last_ent = iter->ent;
         int i = (int)*pos;
         void *ent;
 
@@ -1203,9 +1024,6 @@ static void *s_next(struct seq_file *m, void *v, loff_t *pos)
 
         iter->pos = *pos;
 
-        if (last_ent && !ent)
-                seq_puts(m, "\n\nvim:ft=help\n");
-
         return ent;
 }
 
@@ -1214,7 +1032,7 @@ 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);
 
@@ -1233,14 +1051,15 @@ 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))
                         ;
 
@@ -1334,21 +1153,21 @@ 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");
 }
 
 
@@ -1359,23 +1178,16 @@ 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);
@@ -1432,7 +1244,7 @@ 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_NEED_RESCHED) ? 'N' : '.'));
@@ -1461,7 +1273,7 @@ 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);
@@ -1475,34 +1287,76 @@ 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);
@@ -1511,52 +1365,85 @@ 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))
+                if (kretprobed(field->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);
 
-                state = entry->ctx.prev_state ? __ffs(entry->ctx.prev_state) + 1 : 0;
+                T = field->next_state < sizeof(state_to_char) ?
+                        state_to_char[field->next_state] : 'X';
+
+                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);
@@ -1571,90 +1458,126 @@ 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))
+                                return TRACE_TYPE_PARTIAL_LINE;
+                        if (kretprobed(field->parent_ip))
                                 ret = trace_seq_puts(s, KRETPROBE_MSG);
                         else
-                                ret = seq_print_ip_sym(s, entry->fn.parent_ip,
+                                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;
@@ -1663,47 +1586,77 @@ 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)                         \
@@ -1714,11 +1667,12 @@ 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';
@@ -1727,97 +1681,139 @@ 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->cpu);
+        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);
@@ -1873,6 +1869,8 @@ 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;
@@ -1893,28 +1891,45 @@ __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);
+
+        return ERR_PTR(-ENOMEM);
 }
 
 int tracing_open_generic(struct inode *inode, struct file *filp)
@@ -1930,8 +1945,14 @@ 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);
 
@@ -2356,9 +2377,11 @@ 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;
 
         if (cnt > max_tracer_type_len)
                 cnt = max_tracer_type_len;
+        ret = cnt;
 
         if (copy_from_user(&buf, ubuf, cnt))
                 return -EFAULT;
@@ -2374,7 +2397,11 @@ 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)
@@ -2387,9 +2414,10 @@ tracing_set_trace_write(struct file *filp, const char __user *ubuf,
  out:
         mutex_unlock(&trace_types_lock);
 
-        filp->f_pos += cnt;
+        if (ret == cnt)
+                filp->f_pos += cnt;
 
-        return cnt;
+        return ret;
 }
 
 static ssize_t
@@ -2504,20 +2532,12 @@ 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);
 
@@ -2528,6 +2548,8 @@ tracing_read_pipe(struct file *filp, char __user *ubuf,
                         goto out;
         }
 
+waitagain:
+        sret = 0;
         while (trace_empty(iter)) {
 
                 if ((filp->f_flags & O_NONBLOCK)) {
@@ -2592,46 +2614,12 @@ 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;
@@ -2643,26 +2631,17 @@ 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);
@@ -2688,7 +2667,8 @@ tracing_entries_write(struct file *filp, const char __user *ubuf,
 {
         unsigned long val;
         char buf[64];
-        int i, ret;
+        int ret;
+        struct trace_array *tr = filp->private_data;
 
         if (cnt >= sizeof(buf))
                 return -EINVAL;
@@ -2708,59 +2688,38 @@ 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();
-
-                /* 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 */
@@ -2773,6 +2732,52 @@ tracing_entries_write(struct file *filp, const char __user *ubuf,
         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,
@@ -2804,6 +2809,11 @@ 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
@@ -2850,7 +2860,7 @@ 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;
@@ -2885,12 +2895,12 @@ 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,
@@ -2903,7 +2913,7 @@ 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)
@@ -2913,13 +2923,19 @@ 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,
@@ -2932,230 +2948,263 @@ 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);
 
-                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;
-                }
+        trace_seq_reset(s);
+}
+
+
+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;
 
-                /* 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);
+        /* only one dump */
+        spin_lock_irqsave(&ftrace_dump_lock, flags);
+        if (dump_ran)
+                goto out;
 
-                data->lock = (raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED;
-                max_tr.data[i]->lock = (raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED;
+        dump_ran = 1;
 
-/* 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;
-                }
+        /* No turning back! */
+        ftrace_kill_atomic();
 
-                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
+        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);
 
-        tracer_init_debugfs();
+#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
+
+        /* 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;
+        atomic_notifier_chain_register(&panic_notifier_list,
+                                       &trace_panic_notifier);
 
- free_buffers:
-        for (i-- ; i >= 0; i--) {
-                struct page *page, *tmp;
-                struct trace_array_cpu *data = global_trace.data[i];
+        register_die_notifier(&trace_die_notifier);
 
-                if (data) {
-                        list_for_each_entry_safe(page, tmp,
-                                                 &data->trace_pages, lru) {
-                                list_del_init(&page->lru);
-                                __free_page(page);
-                        }
-                }
-
-#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..f1f99572cde7 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 +81,60 @@ 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;
 };
 
-#define TRACE_ENTRY_SIZE        sizeof(struct trace_entry)
+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
+ *  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_NEED_RESCHED         = 0x02,
+        TRACE_FLAG_HARDIRQ              = 0x04,
+        TRACE_FLAG_SOFTIRQ              = 0x08,
+        TRACE_FLAG_CONT                 = 0x10,
+};
+
+#define TRACE_BUF_SIZE          1024
 
 /*
  * The CPU trace array - it consists of thousands of trace entries
@@ -91,16 +142,9 @@ 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 +168,7 @@ 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 +177,56 @@ 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 +247,7 @@ 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 +266,58 @@ 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);
@@ -268,51 +364,33 @@ 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 +412,9 @@ 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..e90eb0c2c56c 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)
diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c
index 421d6fe3650e..a7db7f040ae0 100644
--- a/kernel/trace/trace_irqsoff.c
+++ b/kernel/trace/trace_irqsoff.c
@@ -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);
 }
@@ -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);
@@ -253,12 +256,14 @@ void start_critical_timings(void)
         if (preempt_trace() || irq_trace())
                 start_critical_timing(CALLER_ADDR0, CALLER_ADDR1);
 }
+EXPORT_SYMBOL_GPL(start_critical_timings);
 
 void stop_critical_timings(void)
 {
         if (preempt_trace() || irq_trace())
                 stop_critical_timing(CALLER_ADDR0, CALLER_ADDR1);
 }
+EXPORT_SYMBOL_GPL(stop_critical_timings);
 
 #ifdef CONFIG_IRQSOFF_TRACER
 #ifdef CONFIG_PROVE_LOCKING
@@ -337,12 +342,14 @@ EXPORT_SYMBOL(trace_hardirqs_off_caller);
 #ifdef CONFIG_PREEMPT_TRACER
 void trace_preempt_on(unsigned long a0, unsigned long a1)
 {
-        stop_critical_timing(a0, a1);
+        if (preempt_trace())
+                stop_critical_timing(a0, a1);
 }
 
 void trace_preempt_off(unsigned long a0, unsigned long a1)
 {
-        start_critical_timing(a0, a1);
+        if (preempt_trace())
+                start_critical_timing(a0, a1);
 }
 #endif /* CONFIG_PREEMPT_TRACER */
 
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 3c8d61df4474..fe4a252c2363 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"
 
@@ -26,7 +26,8 @@ static struct task_struct	*wakeup_task;
 static int                      wakeup_cpu;
 static unsigned                 wakeup_prio = -1;
 
-static DEFINE_SPINLOCK(wakeup_lock);
+static raw_spinlock_t wakeup_lock =
+        (raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED;
 
 static void __wakeup_reset(struct trace_array *tr);
 
@@ -43,10 +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();
 
@@ -56,7 +59,8 @@ wakeup_tracer_call(unsigned long ip, unsigned long parent_ip)
         if (unlikely(disabled != 1))
                 goto out;
 
-        spin_lock_irqsave(&wakeup_lock, flags);
+        local_irq_save(flags);
+        __raw_spin_lock(&wakeup_lock);
 
         if (unlikely(!wakeup_task))
                 goto unlock;
@@ -68,10 +72,11 @@ 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:
-        spin_unlock_irqrestore(&wakeup_lock, flags);
+        __raw_spin_unlock(&wakeup_lock);
+        local_irq_restore(flags);
 
  out:
         atomic_dec(&data->disabled);
@@ -109,17 +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;
@@ -136,22 +142,25 @@ 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;
 
-        spin_lock_irqsave(&wakeup_lock, flags);
+        local_irq_save(flags);
+        __raw_spin_lock(&wakeup_lock);
 
         /* We could race with grabbing wakeup_lock */
         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
@@ -170,38 +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);
-        spin_unlock_irqrestore(&wakeup_lock, flags);
+        __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)
@@ -209,11 +194,9 @@ static void __wakeup_reset(struct trace_array *tr)
         struct trace_array_cpu *data;
         int cpu;
 
-        assert_spin_locked(&wakeup_lock);
-
         for_each_possible_cpu(cpu) {
                 data = tr->data[cpu];
-                tracing_reset(data);
+                tracing_reset(tr, cpu);
         }
 
         wakeup_cpu = -1;
@@ -229,37 +212,46 @@ static void wakeup_reset(struct trace_array *tr)
 {
         unsigned long flags;
 
-        spin_lock_irqsave(&wakeup_lock, flags);
+        local_irq_save(flags);
+        __raw_spin_lock(&wakeup_lock);
         __wakeup_reset(tr);
-        spin_unlock_irqrestore(&wakeup_lock, flags);
+        __raw_spin_unlock(&wakeup_lock);
+        local_irq_restore(flags);
 }
 
 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;
 
         /* interrupts should be off from try_to_wake_up */
-        spin_lock(&wakeup_lock);
+        __raw_spin_lock(&wakeup_lock);
 
         /* check for races. */
         if (!tracer_enabled || p->prio >= wakeup_prio)
                 goto out_locked;
 
         /* reset the trace */
-        __wakeup_reset(tr);
+        __wakeup_reset(wakeup_trace);
 
         wakeup_cpu = task_cpu(p);
         wakeup_prio = p->prio;
@@ -269,74 +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:
-        spin_unlock(&wakeup_lock);
+        __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;
         }
@@ -358,28 +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..09cf230d7eca 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;
         }
@@ -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");
@@ -157,6 +119,7 @@ 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);
 
@@ -212,10 +175,10 @@ 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);
@@ -415,6 +378,15 @@ 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 +458,9 @@ 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..74c5d9a3afae
--- /dev/null
+++ b/kernel/trace/trace_stack.c
@@ -0,0 +1,310 @@
+/*
+ * 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;
+
+        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 2301e1e7c606..9587d3bcba55 100644
--- a/kernel/trace/trace_sysprof.c
+++ b/kernel/trace/trace_sysprof.c
@@ -161,7 +161,7 @@ static void timer_notify(struct pt_regs *regs, int cpu)
                 __trace_special(tr, data, 2, regs->ip, 0);
 
                 while (i < sample_max_depth) {
-                        frame.next_fp = 0;
+                        frame.next_fp = NULL;
                         frame.return_address = 0;
                         if (!copy_stack_frame(fp, &frame))
                                 break;
@@ -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..f2b7c28a4708
--- /dev/null
+++ b/kernel/tracepoint.c
@@ -0,0 +1,477 @@
+/*
+ * 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;
+
+        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);
+        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/tsacct.c b/kernel/tsacct.c
index 4ab1b584961b..8ebcd8532dfb 100644
--- a/kernel/tsacct.c
+++ b/kernel/tsacct.c
@@ -28,14 +28,14 @@
 void bacct_add_tsk(struct taskstats *stats, struct task_struct *tsk)
 {
         struct timespec uptime, ts;
-        s64 ac_etime;
+        u64 ac_etime;
 
         BUILD_BUG_ON(TS_COMM_LEN < TASK_COMM_LEN);
 
         /* calculate task elapsed time in timespec */
         do_posix_clock_monotonic_gettime(&uptime);
         ts = timespec_sub(uptime, tsk->start_time);
-        /* rebase elapsed time to usec */
+        /* rebase elapsed time to usec (should never be negative) */
         ac_etime = timespec_to_ns(&ts);
         do_div(ac_etime, NSEC_PER_USEC);
         stats->ac_etime = ac_etime;
@@ -84,9 +84,9 @@ void xacct_add_tsk(struct taskstats *stats, struct task_struct *p)
 {
         struct mm_struct *mm;
 
-        /* convert pages-jiffies to Mbyte-usec */
-        stats->coremem = jiffies_to_usecs(p->acct_rss_mem1) * PAGE_SIZE / MB;
-        stats->virtmem = jiffies_to_usecs(p->acct_vm_mem1) * PAGE_SIZE / MB;
+        /* convert pages-usec to Mbyte-usec */
+        stats->coremem = p->acct_rss_mem1 * PAGE_SIZE / MB;
+        stats->virtmem = p->acct_vm_mem1 * PAGE_SIZE / MB;
         mm = get_task_mm(p);
         if (mm) {
                 /* adjust to KB unit */
@@ -94,10 +94,10 @@ void xacct_add_tsk(struct taskstats *stats, struct task_struct *p)
                 stats->hiwater_vm    = mm->hiwater_vm * PAGE_SIZE / KB;
                 mmput(mm);
         }
-        stats->read_char        = p->rchar;
-        stats->write_char       = p->wchar;
-        stats->read_syscalls    = p->syscr;
-        stats->write_syscalls   = p->syscw;
+        stats->read_char        = p->ioac.rchar;
+        stats->write_char       = p->ioac.wchar;
+        stats->read_syscalls    = p->ioac.syscr;
+        stats->write_syscalls   = p->ioac.syscw;
 #ifdef CONFIG_TASK_IO_ACCOUNTING
         stats->read_bytes       = p->ioac.read_bytes;
         stats->write_bytes      = p->ioac.write_bytes;
@@ -118,12 +118,19 @@ void xacct_add_tsk(struct taskstats *stats, struct task_struct *p)
 void acct_update_integrals(struct task_struct *tsk)
 {
         if (likely(tsk->mm)) {
-                long delta = cputime_to_jiffies(
-                        cputime_sub(tsk->stime, tsk->acct_stimexpd));
+                cputime_t time, dtime;
+                struct timeval value;
+                u64 delta;
+
+                time = tsk->stime + tsk->utime;
+                dtime = cputime_sub(time, tsk->acct_timexpd);
+                jiffies_to_timeval(cputime_to_jiffies(dtime), &value);
+                delta = value.tv_sec;
+                delta = delta * USEC_PER_SEC + value.tv_usec;
 
                 if (delta == 0)
                         return;
-                tsk->acct_stimexpd = tsk->stime;
+                tsk->acct_timexpd = time;
                 tsk->acct_rss_mem1 += delta * get_mm_rss(tsk->mm);
                 tsk->acct_vm_mem1 += delta * tsk->mm->total_vm;
         }
@@ -135,7 +142,7 @@ void acct_update_integrals(struct task_struct *tsk)
  */
 void acct_clear_integrals(struct task_struct *tsk)
 {
-        tsk->acct_stimexpd = 0;
+        tsk->acct_timexpd = 0;
         tsk->acct_rss_mem1 = 0;
         tsk->acct_vm_mem1 = 0;
 }
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/user_namespace.c b/kernel/user_namespace.c
index a9ab0596de44..532858fa5b88 100644
--- a/kernel/user_namespace.c
+++ b/kernel/user_namespace.c
@@ -6,7 +6,6 @@
  */
 
 #include <linux/module.h>
-#include <linux/version.h>
 #include <linux/nsproxy.h>
 #include <linux/slab.h>
 #include <linux/user_namespace.h>
diff --git a/kernel/utsname.c b/kernel/utsname.c
index 64d398f12444..815237a55af8 100644
--- a/kernel/utsname.c
+++ b/kernel/utsname.c
@@ -12,7 +12,6 @@
 #include <linux/module.h>
 #include <linux/uts.h>
 #include <linux/utsname.h>
-#include <linux/version.h>
 #include <linux/err.h>
 #include <linux/slab.h>
 
diff --git a/kernel/utsname_sysctl.c b/kernel/utsname_sysctl.c
index fe3a56c2256d..3b34b3545936 100644
--- a/kernel/utsname_sysctl.c
+++ b/kernel/utsname_sysctl.c
@@ -12,7 +12,6 @@
 #include <linux/module.h>
 #include <linux/uts.h>
 #include <linux/utsname.h>
-#include <linux/version.h>
 #include <linux/sysctl.h>
 
 static void *get_uts(ctl_table *table, int write)
@@ -61,7 +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)
 {
@@ -70,8 +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 ce7799540c91..f928f2a87b9b 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
@@ -125,7 +126,7 @@ struct cpu_workqueue_struct *get_wq_data(struct work_struct *work)
 }
 
 static void insert_work(struct cpu_workqueue_struct *cwq,
-                                struct work_struct *work, int tail)
+                        struct work_struct *work, struct list_head *head)
 {
         set_wq_data(work, cwq);
         /*
@@ -133,21 +134,17 @@ static void insert_work(struct cpu_workqueue_struct *cwq,
          * result of list_add() below, see try_to_grab_pending().
          */
         smp_wmb();
-        if (tail)
-                list_add_tail(&work->entry, &cwq->worklist);
-        else
-                list_add(&work->entry, &cwq->worklist);
+        list_add_tail(&work->entry, head);
         wake_up(&cwq->more_work);
 }
 
-/* Preempt must be disabled. */
 static void __queue_work(struct cpu_workqueue_struct *cwq,
                          struct work_struct *work)
 {
         unsigned long flags;
 
         spin_lock_irqsave(&cwq->lock, flags);
-        insert_work(cwq, work, 1);
+        insert_work(cwq, work, &cwq->worklist);
         spin_unlock_irqrestore(&cwq->lock, flags);
 }
 
@@ -163,17 +160,39 @@ static void __queue_work(struct cpu_workqueue_struct *cwq,
  */
 int queue_work(struct workqueue_struct *wq, struct work_struct *work)
 {
+        int ret;
+
+        ret = queue_work_on(get_cpu(), wq, work);
+        put_cpu();
+
+        return ret;
+}
+EXPORT_SYMBOL_GPL(queue_work);
+
+/**
+ * queue_work_on - queue work on specific cpu
+ * @cpu: CPU number to execute work on
+ * @wq: workqueue to use
+ * @work: work to queue
+ *
+ * Returns 0 if @work was already on a queue, non-zero otherwise.
+ *
+ * We queue the work to a specific CPU, the caller must ensure it
+ * can't go away.
+ */
+int
+queue_work_on(int cpu, struct workqueue_struct *wq, struct work_struct *work)
+{
         int ret = 0;
 
         if (!test_and_set_bit(WORK_STRUCT_PENDING, work_data_bits(work))) {
                 BUG_ON(!list_empty(&work->entry));
-                __queue_work(wq_per_cpu(wq, get_cpu()), work);
-                put_cpu();
+                __queue_work(wq_per_cpu(wq, cpu), work);
                 ret = 1;
         }
         return ret;
 }
-EXPORT_SYMBOL_GPL(queue_work);
+EXPORT_SYMBOL_GPL(queue_work_on);
 
 static void delayed_work_timer_fn(unsigned long __data)
 {
@@ -272,11 +291,11 @@ static void run_workqueue(struct cpu_workqueue_struct *cwq)
 
                 BUG_ON(get_wq_data(work) != cwq);
                 work_clear_pending(work);
-                lock_acquire(&cwq->wq->lockdep_map, 0, 0, 0, 2, _THIS_IP_);
-                lock_acquire(&lockdep_map, 0, 0, 0, 2, _THIS_IP_);
+                lock_map_acquire(&cwq->wq->lockdep_map);
+                lock_map_acquire(&lockdep_map);
                 f(work);
-                lock_release(&lockdep_map, 1, _THIS_IP_);
-                lock_release(&cwq->wq->lockdep_map, 1, _THIS_IP_);
+                lock_map_release(&lockdep_map);
+                lock_map_release(&cwq->wq->lockdep_map);
 
                 if (unlikely(in_atomic() || lockdep_depth(current) > 0)) {
                         printk(KERN_ERR "BUG: workqueue leaked lock or atomic: "
@@ -337,14 +356,14 @@ static void wq_barrier_func(struct work_struct *work)
 }
 
 static void insert_wq_barrier(struct cpu_workqueue_struct *cwq,
-                                        struct wq_barrier *barr, int tail)
+                        struct wq_barrier *barr, struct list_head *head)
 {
         INIT_WORK(&barr->work, wq_barrier_func);
         __set_bit(WORK_STRUCT_PENDING, work_data_bits(&barr->work));
 
         init_completion(&barr->done);
 
-        insert_work(cwq, &barr->work, tail);
+        insert_work(cwq, &barr->work, head);
 }
 
 static int flush_cpu_workqueue(struct cpu_workqueue_struct *cwq)
@@ -364,7 +383,7 @@ static int flush_cpu_workqueue(struct cpu_workqueue_struct *cwq)
                 active = 0;
                 spin_lock_irq(&cwq->lock);
                 if (!list_empty(&cwq->worklist) || cwq->current_work != NULL) {
-                        insert_wq_barrier(cwq, &barr, 1);
+                        insert_wq_barrier(cwq, &barr, &cwq->worklist);
                         active = 1;
                 }
                 spin_unlock_irq(&cwq->lock);
@@ -395,13 +414,64 @@ void flush_workqueue(struct workqueue_struct *wq)
         int cpu;
 
         might_sleep();
-        lock_acquire(&wq->lockdep_map, 0, 0, 0, 2, _THIS_IP_);
-        lock_release(&wq->lockdep_map, 1, _THIS_IP_);
-        for_each_cpu_mask(cpu, *cpu_map)
+        lock_map_acquire(&wq->lockdep_map);
+        lock_map_release(&wq->lockdep_map);
+        for_each_cpu_mask_nr(cpu, *cpu_map)
                 flush_cpu_workqueue(per_cpu_ptr(wq->cpu_wq, cpu));
 }
 EXPORT_SYMBOL_GPL(flush_workqueue);
 
+/**
+ * flush_work - block until a work_struct's callback has terminated
+ * @work: the work which is to be flushed
+ *
+ * Returns false if @work has already terminated.
+ *
+ * It is expected that, prior to calling flush_work(), the caller has
+ * arranged for the work to not be requeued, otherwise it doesn't make
+ * sense to use this function.
+ */
+int flush_work(struct work_struct *work)
+{
+        struct cpu_workqueue_struct *cwq;
+        struct list_head *prev;
+        struct wq_barrier barr;
+
+        might_sleep();
+        cwq = get_wq_data(work);
+        if (!cwq)
+                return 0;
+
+        lock_map_acquire(&cwq->wq->lockdep_map);
+        lock_map_release(&cwq->wq->lockdep_map);
+
+        prev = NULL;
+        spin_lock_irq(&cwq->lock);
+        if (!list_empty(&work->entry)) {
+                /*
+                 * See the comment near try_to_grab_pending()->smp_rmb().
+                 * If it was re-queued under us we are not going to wait.
+                 */
+                smp_rmb();
+                if (unlikely(cwq != get_wq_data(work)))
+                        goto out;
+                prev = &work->entry;
+        } else {
+                if (cwq->current_work != work)
+                        goto out;
+                prev = &cwq->worklist;
+        }
+        insert_wq_barrier(cwq, &barr, prev->next);
+out:
+        spin_unlock_irq(&cwq->lock);
+        if (!prev)
+                return 0;
+
+        wait_for_completion(&barr.done);
+        return 1;
+}
+EXPORT_SYMBOL_GPL(flush_work);
+
 /*
  * Upon a successful return (>= 0), the caller "owns" WORK_STRUCT_PENDING bit,
  * so this work can't be re-armed in any way.
@@ -449,7 +519,7 @@ static void wait_on_cpu_work(struct cpu_workqueue_struct *cwq,
 
         spin_lock_irq(&cwq->lock);
         if (unlikely(cwq->current_work == work)) {
-                insert_wq_barrier(cwq, &barr, 0);
+                insert_wq_barrier(cwq, &barr, cwq->worklist.next);
                 running = 1;
         }
         spin_unlock_irq(&cwq->lock);
@@ -467,8 +537,8 @@ static void wait_on_work(struct work_struct *work)
 
         might_sleep();
 
-        lock_acquire(&work->lockdep_map, 0, 0, 0, 2, _THIS_IP_);
-        lock_release(&work->lockdep_map, 1, _THIS_IP_);
+        lock_map_acquire(&work->lockdep_map);
+        lock_map_release(&work->lockdep_map);
 
         cwq = get_wq_data(work);
         if (!cwq)
@@ -477,7 +547,7 @@ static void wait_on_work(struct work_struct *work)
         wq = cwq->wq;
         cpu_map = wq_cpu_map(wq);
 
-        for_each_cpu_mask(cpu, *cpu_map)
+        for_each_cpu_mask_nr(cpu, *cpu_map)
                 wait_on_cpu_work(per_cpu_ptr(wq->cpu_wq, cpu), work);
 }
 
@@ -553,6 +623,19 @@ int schedule_work(struct work_struct *work)
 }
 EXPORT_SYMBOL(schedule_work);
 
+/*
+ * schedule_work_on - put work task on a specific cpu
+ * @cpu: cpu to put the work task on
+ * @work: job to be done
+ *
+ * This puts a job on a specific cpu
+ */
+int schedule_work_on(int cpu, struct work_struct *work)
+{
+        return queue_work_on(cpu, keventd_wq, work);
+}
+EXPORT_SYMBOL(schedule_work_on);
+
 /**
  * schedule_delayed_work - put work task in global workqueue after delay
  * @dwork: job to be done
@@ -607,10 +690,10 @@ int schedule_on_each_cpu(work_func_t func)
                 struct work_struct *work = per_cpu_ptr(works, cpu);
 
                 INIT_WORK(work, func);
-                set_bit(WORK_STRUCT_PENDING, work_data_bits(work));
-                __queue_work(per_cpu_ptr(keventd_wq->cpu_wq, cpu), work);
+                schedule_work_on(cpu, work);
         }
-        flush_workqueue(keventd_wq);
+        for_each_online_cpu(cpu)
+                flush_work(per_cpu_ptr(works, cpu));
         put_online_cpus();
         free_percpu(works);
         return 0;
@@ -684,6 +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;
@@ -699,7 +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;
@@ -719,6 +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)
 {
@@ -740,6 +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) {
@@ -747,11 +834,22 @@ struct workqueue_struct *__create_workqueue_key(const char *name,
                 err = create_workqueue_thread(cwq, singlethread_cpu);
                 start_workqueue_thread(cwq, -1);
         } else {
-                get_online_cpus();
+                cpu_maps_update_begin();
+                /*
+                 * We must place this wq on list even if the code below fails.
+                 * cpu_down(cpu) can remove cpu from cpu_populated_map before
+                 * destroy_workqueue() takes the lock, in that case we leak
+                 * cwq[cpu]->thread.
+                 */
                 spin_lock(&workqueue_lock);
                 list_add(&wq->list, &workqueues);
                 spin_unlock(&workqueue_lock);
-
+                /*
+                 * We must initialize cwqs for each possible cpu even if we
+                 * are going to call destroy_workqueue() finally. Otherwise
+                 * cpu_up() can hit the uninitialized cwq once we drop the
+                 * lock.
+                 */
                 for_each_possible_cpu(cpu) {
                         cwq = init_cpu_workqueue(wq, cpu);
                         if (err || !cpu_online(cpu))
@@ -759,7 +857,7 @@ struct workqueue_struct *__create_workqueue_key(const char *name,
                         err = create_workqueue_thread(cwq, cpu);
                         start_workqueue_thread(cwq, cpu);
                 }
-                put_online_cpus();
+                cpu_maps_update_done();
         }
 
         if (err) {
@@ -773,18 +871,18 @@ EXPORT_SYMBOL_GPL(__create_workqueue_key);
 static void cleanup_workqueue_thread(struct cpu_workqueue_struct *cwq)
 {
         /*
-         * Our caller is either destroy_workqueue() or CPU_DEAD,
-         * get_online_cpus() protects cwq->thread.
+         * Our caller is either destroy_workqueue() or CPU_POST_DEAD,
+         * cpu_add_remove_lock protects cwq->thread.
          */
         if (cwq->thread == NULL)
                 return;
 
-        lock_acquire(&cwq->wq->lockdep_map, 0, 0, 0, 2, _THIS_IP_);
-        lock_release(&cwq->wq->lockdep_map, 1, _THIS_IP_);
+        lock_map_acquire(&cwq->wq->lockdep_map);
+        lock_map_release(&cwq->wq->lockdep_map);
 
         flush_cpu_workqueue(cwq);
         /*
-         * If the caller is CPU_DEAD and cwq->worklist was not empty,
+         * If the caller is CPU_POST_DEAD and cwq->worklist was not empty,
          * a concurrent flush_workqueue() can insert a barrier after us.
          * However, in that case run_workqueue() won't return and check
          * kthread_should_stop() until it flushes all work_struct's.
@@ -808,14 +906,14 @@ void destroy_workqueue(struct workqueue_struct *wq)
         const cpumask_t *cpu_map = wq_cpu_map(wq);
         int cpu;
 
-        get_online_cpus();
+        cpu_maps_update_begin();
         spin_lock(&workqueue_lock);
         list_del(&wq->list);
         spin_unlock(&workqueue_lock);
 
-        for_each_cpu_mask(cpu, *cpu_map)
+        for_each_cpu_mask_nr(cpu, *cpu_map)
                 cleanup_workqueue_thread(per_cpu_ptr(wq->cpu_wq, cpu));
-        put_online_cpus();
+        cpu_maps_update_done();
 
         free_percpu(wq->cpu_wq);
         kfree(wq);
@@ -829,6 +927,7 @@ static int __devinit workqueue_cpu_callback(struct notifier_block *nfb,
         unsigned int cpu = (unsigned long)hcpu;
         struct cpu_workqueue_struct *cwq;
         struct workqueue_struct *wq;
+        int ret = NOTIFY_OK;
 
         action &= ~CPU_TASKS_FROZEN;
 
@@ -836,7 +935,7 @@ static int __devinit workqueue_cpu_callback(struct notifier_block *nfb,
         case CPU_UP_PREPARE:
                 cpu_set(cpu, cpu_populated_map);
         }
-
+undo:
         list_for_each_entry(wq, &workqueues, list) {
                 cwq = per_cpu_ptr(wq->cpu_wq, cpu);
 
@@ -846,7 +945,9 @@ static int __devinit workqueue_cpu_callback(struct notifier_block *nfb,
                                 break;
                         printk(KERN_ERR "workqueue [%s] for %i failed\n",
                                 wq->name, cpu);
-                        return NOTIFY_BAD;
+                        action = CPU_UP_CANCELED;
+                        ret = NOTIFY_BAD;
+                        goto undo;
 
                 case CPU_ONLINE:
                         start_workqueue_thread(cwq, cpu);
@@ -854,7 +955,7 @@ static int __devinit workqueue_cpu_callback(struct notifier_block *nfb,
 
                 case CPU_UP_CANCELED:
                         start_workqueue_thread(cwq, -1);
-                case CPU_DEAD:
+                case CPU_POST_DEAD:
                         cleanup_workqueue_thread(cwq);
                         break;
                 }
@@ -862,11 +963,11 @@ static int __devinit workqueue_cpu_callback(struct notifier_block *nfb,
 
         switch (action) {
         case CPU_UP_CANCELED:
-        case CPU_DEAD:
+        case CPU_POST_DEAD:
                 cpu_clear(cpu, cpu_populated_map);
         }
 
-        return NOTIFY_OK;
+        return ret;
 }
 
 void __init init_workqueues(void)