47 files changed, 1801 insertions, 1140 deletions

diff --git a/kernel/Kconfig.freezer b/kernel/Kconfig.freezer
new file mode 100644
index 000000000000..a3bb4cb52539
--- /dev/null
+++ b/kernel/Kconfig.freezer
@@ -0,0 +1,2 @@
+config FREEZER
+        def_bool PM_SLEEP || CGROUP_FREEZER
diff --git a/kernel/Makefile b/kernel/Makefile
index 85f588a9d0b1..9a3ec66a9d84 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -24,6 +24,7 @@ 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
@@ -55,6 +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
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 8c6e1c17e6d3..046c1609606b 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -241,7 +241,6 @@ static void unlink_css_set(struct css_set *cg)
         struct cg_cgroup_link *link;
         struct cg_cgroup_link *saved_link;
 
-        write_lock(&css_set_lock);
         hlist_del(&cg->hlist);
         css_set_count--;
 
@@ -251,16 +250,25 @@ static void unlink_css_set(struct css_set *cg)
                 list_del(&link->cgrp_link_list);
                 kfree(link);
         }
-
-        write_unlock(&css_set_lock);
 }
 
-static void __release_css_set(struct kref *k, int taskexit)
+static void __put_css_set(struct css_set *cg, int taskexit)
 {
         int i;
-        struct css_set *cg = container_of(k, struct css_set, ref);
-
+        /*
+         * Ensure that the refcount doesn't hit zero while any readers
+         * can see it. Similar to atomic_dec_and_lock(), but for an
+         * rwlock
+         */
+        if (atomic_add_unless(&cg->refcount, -1, 1))
+                return;
+        write_lock(&css_set_lock);
+        if (!atomic_dec_and_test(&cg->refcount)) {
+                write_unlock(&css_set_lock);
+                return;
+        }
         unlink_css_set(cg);
+        write_unlock(&css_set_lock);
 
         rcu_read_lock();
         for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
@@ -276,32 +284,22 @@ static void __release_css_set(struct kref *k, int taskexit)
         kfree(cg);
 }
 
-static void release_css_set(struct kref *k)
-{
-        __release_css_set(k, 0);
-}
-
-static void release_css_set_taskexit(struct kref *k)
-{
-        __release_css_set(k, 1);
-}
-
 /*
  * refcounted get/put for css_set objects
  */
 static inline void get_css_set(struct css_set *cg)
 {
-        kref_get(&cg->ref);
+        atomic_inc(&cg->refcount);
 }
 
 static inline void put_css_set(struct css_set *cg)
 {
-        kref_put(&cg->ref, release_css_set);
+        __put_css_set(cg, 0);
 }
 
 static inline void put_css_set_taskexit(struct css_set *cg)
 {
-        kref_put(&cg->ref, release_css_set_taskexit);
+        __put_css_set(cg, 1);
 }
 
 /*
@@ -427,7 +425,7 @@ static struct css_set *find_css_set(
                 return NULL;
         }
 
-        kref_init(&res->ref);
+        atomic_set(&res->refcount, 1);
         INIT_LIST_HEAD(&res->cg_links);
         INIT_LIST_HEAD(&res->tasks);
         INIT_HLIST_NODE(&res->hlist);
@@ -870,6 +868,14 @@ static struct super_operations cgroup_ops = {
         .remount_fs = cgroup_remount,
 };
 
+static void init_cgroup_housekeeping(struct cgroup *cgrp)
+{
+        INIT_LIST_HEAD(&cgrp->sibling);
+        INIT_LIST_HEAD(&cgrp->children);
+        INIT_LIST_HEAD(&cgrp->css_sets);
+        INIT_LIST_HEAD(&cgrp->release_list);
+        init_rwsem(&cgrp->pids_mutex);
+}
 static void init_cgroup_root(struct cgroupfs_root *root)
 {
         struct cgroup *cgrp = &root->top_cgroup;
@@ -878,10 +884,7 @@ static void init_cgroup_root(struct cgroupfs_root *root)
         root->number_of_cgroups = 1;
         cgrp->root = root;
         cgrp->top_cgroup = cgrp;
-        INIT_LIST_HEAD(&cgrp->sibling);
-        INIT_LIST_HEAD(&cgrp->children);
-        INIT_LIST_HEAD(&cgrp->css_sets);
-        INIT_LIST_HEAD(&cgrp->release_list);
+        init_cgroup_housekeeping(cgrp);
 }
 
 static int cgroup_test_super(struct super_block *sb, void *data)
@@ -1728,7 +1731,7 @@ int cgroup_task_count(const struct cgroup *cgrp)
 
         read_lock(&css_set_lock);
         list_for_each_entry(link, &cgrp->css_sets, cgrp_link_list) {
-                count += atomic_read(&link->cg->ref.refcount);
+                count += atomic_read(&link->cg->refcount);
         }
         read_unlock(&css_set_lock);
         return count;
@@ -1997,16 +2000,7 @@ int cgroup_scan_tasks(struct cgroup_scanner *scan)
  * but we cannot guarantee that the information we produce is correct
  * unless we produce it entirely atomically.
  *
- * Upon tasks file open(), a struct ctr_struct is allocated, that
- * will have a pointer to an array (also allocated here).  The struct
- * ctr_struct * is stored in file->private_data.  Its resources will
- * be freed by release() when the file is closed.  The array is used
- * to sprintf the PIDs and then used by read().
  */
-struct ctr_struct {
-        char *buf;
-        int bufsz;
-};
 
 /*
  * Load into 'pidarray' up to 'npids' of the tasks using cgroup
@@ -2088,42 +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;
 
-        for (i = 0; i < npids; i++)
-                cnt += snprintf(buf + cnt, max(sz - cnt, 0), "%d\n", a[i]);
-        return cnt;
+        down_read(&cgrp->pids_mutex);
+        if (pid) {
+                int end = cgrp->pids_length;
+                int i;
+                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,
+};
+
+static void release_cgroup_pid_array(struct cgroup *cgrp)
+{
+        down_write(&cgrp->pids_mutex);
+        BUG_ON(!cgrp->pids_use_count);
+        if (!--cgrp->pids_use_count) {
+                kfree(cgrp->tasks_pids);
+                cgrp->tasks_pids = NULL;
+                cgrp->pids_length = 0;
+        }
+        up_write(&cgrp->pids_mutex);
+}
+
+static int cgroup_tasks_release(struct inode *inode, struct file *file)
+{
+        struct cgroup *cgrp = __d_cgrp(file->f_dentry->d_parent);
+
+        if (!(file->f_mode & FMODE_READ))
+                return 0;
+
+        release_cgroup_pid_array(cgrp);
+        return seq_release(inode, file);
+}
+
+static struct file_operations cgroup_tasks_operations = {
+        .read = seq_read,
+        .llseek = seq_lseek,
+        .write = cgroup_file_write,
+        .release = cgroup_tasks_release,
+};
+
 /*
- * Handle an open on 'tasks' file.  Prepare a buffer listing the
+ * Handle an open on 'tasks' file.  Prepare an array containing the
  * process id's of tasks currently attached to the cgroup being opened.
- *
- * Does not require any specific cgroup mutexes, and does not take any.
  */
+
 static int cgroup_tasks_open(struct inode *unused, struct file *file)
 {
         struct cgroup *cgrp = __d_cgrp(file->f_dentry->d_parent);
-        struct ctr_struct *ctr;
         pid_t *pidarray;
         int npids;
-        char c;
+        int retval;
 
+        /* Nothing to do for write-only files */
         if (!(file->f_mode & FMODE_READ))
                 return 0;
 
-        ctr = kmalloc(sizeof(*ctr), GFP_KERNEL);
-        if (!ctr)
-                goto err0;
-
         /*
          * If cgroup gets more users after we read count, we won't have
          * enough space - tough.  This race is indistinguishable to the
@@ -2131,57 +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;
-}
+        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);
 
-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;
+        /*
+         * 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);
 
-        return simple_read_from_buffer(buf, nbytes, ppos, ctr->buf, ctr->bufsz);
-}
+        file->f_op = &cgroup_tasks_operations;
 
-static int cgroup_tasks_release(struct inode *unused_inode,
-                                        struct file *file)
-{
-        struct ctr_struct *ctr;
-
-        if (file->f_mode & FMODE_READ) {
-                ctr = file->private_data;
-                kfree(ctr->buf);
-                kfree(ctr);
+        retval = seq_open(file, &cgroup_tasks_seq_operations);
+        if (retval) {
+                release_cgroup_pid_array(cgrp);
+                return retval;
         }
+        ((struct seq_file *)file->private_data)->private = cgrp;
         return 0;
 }
 
@@ -2210,7 +2268,6 @@ static struct cftype files[] = {
         {
                 .name = "tasks",
                 .open = cgroup_tasks_open,
-                .read = cgroup_tasks_read,
                 .write_u64 = cgroup_tasks_write,
                 .release = cgroup_tasks_release,
                 .private = FILE_TASKLIST,
@@ -2300,10 +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;
@@ -2495,8 +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);
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 143990e48cb9..8eafe3eb50d9 100644
--- a/kernel/compat.c
+++ b/kernel/compat.c
@@ -23,6 +23,7 @@
 #include <linux/timex.h>
 #include <linux/migrate.h>
 #include <linux/posix-timers.h>
+#include <linux/times.h>
 
 #include <asm/uaccess.h>
 
@@ -208,49 +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/cpuset.c b/kernel/cpuset.c
index eab7bd6628e0..3e00526f52ec 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -1172,7 +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)
@@ -1184,7 +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));
 
@@ -1192,7 +1191,7 @@ static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs,
         cs->flags = trialcs.flags;
         mutex_unlock(&callback_mutex);
 
-        if (cpus_nonempty && balance_flag_changed)
+        if (!cpus_empty(trialcs.cpus_allowed) && balance_flag_changed)
                 async_rebuild_sched_domains();
 
         return 0;
@@ -2437,19 +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/exit.c b/kernel/exit.c
index 138887881a11..80137a5d9467 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -113,8 +113,6 @@ static void __exit_signal(struct task_struct *tsk)
                  * We won't ever get here for the group leader, since it
                  * will have been the last reference on the signal_struct.
                  */
-                sig->utime = cputime_add(sig->utime, task_utime(tsk));
-                sig->stime = cputime_add(sig->stime, task_stime(tsk));
                 sig->gtime = cputime_add(sig->gtime, task_gtime(tsk));
                 sig->min_flt += tsk->min_flt;
                 sig->maj_flt += tsk->maj_flt;
@@ -123,7 +121,6 @@ static void __exit_signal(struct task_struct *tsk)
                 sig->inblock += task_io_get_inblock(tsk);
                 sig->oublock += task_io_get_oublock(tsk);
                 task_io_accounting_add(&sig->ioac, &tsk->ioac);
-                sig->sum_sched_runtime += tsk->se.sum_exec_runtime;
                 sig = NULL; /* Marker for below. */
         }
 
@@ -1307,6 +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
@@ -1322,20 +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,
diff --git a/kernel/fork.c b/kernel/fork.c
index cfaff92f61ff..4d093552dd6e 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -760,15 +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;
@@ -796,40 +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;
         task_io_accounting_init(&sig->ioac);
-        sig->sum_sched_runtime = 0;
-        INIT_LIST_HEAD(&sig->cpu_timers[0]);
-        INIT_LIST_HEAD(&sig->cpu_timers[1]);
-        INIT_LIST_HEAD(&sig->cpu_timers[2]);
         taskstats_tgid_init(sig);
 
         task_lock(current->group_leader);
         memcpy(sig->rlim, current->signal->rlim, sizeof sig->rlim);
         task_unlock(current->group_leader);
 
-        if (sig->rlim[RLIMIT_CPU].rlim_cur != RLIM_INFINITY) {
-                /*
-                 * New sole thread in the process gets an expiry time
-                 * of the whole CPU time limit.
-                 */
-                tsk->it_prof_expires =
-                        secs_to_cputime(sig->rlim[RLIMIT_CPU].rlim_cur);
-        }
+        posix_cpu_timers_init_group(sig);
+
         acct_init_pacct(&sig->pacct);
 
         tty_audit_fork(sig);
@@ -839,6 +853,7 @@ 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);
@@ -889,6 +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.
  *
@@ -998,12 +1026,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
         task_io_accounting_init(&p->ioac);
         acct_clear_integrals(p);
 
-        p->it_virt_expires = cputime_zero;
-        p->it_prof_expires = cputime_zero;
-        p->it_sched_expires = 0;
-        INIT_LIST_HEAD(&p->cpu_timers[0]);
-        INIT_LIST_HEAD(&p->cpu_timers[1]);
-        INIT_LIST_HEAD(&p->cpu_timers[2]);
+        posix_cpu_timers_init(p);
 
         p->lock_depth = -1;             /* -1 = no lock */
         do_posix_clock_monotonic_gettime(&p->start_time);
@@ -1204,21 +1227,6 @@ static struct task_struct *copy_process(unsigned long clone_flags,
         if (clone_flags & CLONE_THREAD) {
                 p->group_leader = current->group_leader;
                 list_add_tail_rcu(&p->thread_group, &p->group_leader->thread_group);
-
-                if (!cputime_eq(current->signal->it_virt_expires,
-                                cputime_zero) ||
-                    !cputime_eq(current->signal->it_prof_expires,
-                                cputime_zero) ||
-                    current->signal->rlim[RLIMIT_CPU].rlim_cur != RLIM_INFINITY ||
-                    !list_empty(&current->signal->cpu_timers[0]) ||
-                    !list_empty(&current->signal->cpu_timers[1]) ||
-                    !list_empty(&current->signal->cpu_timers[2])) {
-                        /*
-                         * Have child wake up on its first tick to check
-                         * for process CPU timers.
-                         */
-                        p->it_prof_expires = jiffies_to_cputime(1);
-                }
         }
 
         if (likely(p->pid)) {
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/hrtimer.c b/kernel/hrtimer.c
index cdec83e722fa..95978f48e039 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -1403,9 +1403,7 @@ 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;
                 }
@@ -1688,9 +1686,11 @@ static void migrate_hrtimers(int 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++) {
@@ -1703,8 +1703,7 @@ static void migrate_hrtimers(int cpu)
                 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)
diff --git a/kernel/irq/autoprobe.c b/kernel/irq/autoprobe.c
index 533068cfb607..cc0f7321b8ce 100644
--- a/kernel/irq/autoprobe.c
+++ b/kernel/irq/autoprobe.c
@@ -30,17 +30,16 @@ static DEFINE_MUTEX(probing_active);
 unsigned long probe_irq_on(void)
 {
         struct irq_desc *desc;
-        unsigned long mask;
-        unsigned int i;
+        unsigned long mask = 0;
+        unsigned int status;
+        int i;
 
         mutex_lock(&probing_active);
         /*
          * something may have generated an irq long ago and we want to
          * flush such a longstanding irq before considering it as spurious.
          */
-        for (i = NR_IRQS-1; i > 0; i--) {
-                desc = irq_desc + i;
-
+        for_each_irq_desc_reverse(i, desc) {
                 spin_lock_irq(&desc->lock);
                 if (!desc->action && !(desc->status & IRQ_NOPROBE)) {
                         /*
@@ -68,9 +67,7 @@ unsigned long probe_irq_on(void)
          * (we must startup again here because if a longstanding irq
          * happened in the previous stage, it may have masked itself)
          */
-        for (i = NR_IRQS-1; i > 0; i--) {
-                desc = irq_desc + i;
-
+        for_each_irq_desc_reverse(i, desc) {
                 spin_lock_irq(&desc->lock);
                 if (!desc->action && !(desc->status & IRQ_NOPROBE)) {
                         desc->status |= IRQ_AUTODETECT | IRQ_WAITING;
@@ -88,11 +85,7 @@ unsigned long probe_irq_on(void)
         /*
          * Now filter out any obviously spurious interrupts
          */
-        mask = 0;
-        for (i = 0; i < NR_IRQS; i++) {
-                unsigned int status;
-
-                desc = irq_desc + i;
+        for_each_irq_desc(i, desc) {
                 spin_lock_irq(&desc->lock);
                 status = desc->status;
 
@@ -126,14 +119,11 @@ EXPORT_SYMBOL(probe_irq_on);
  */
 unsigned int probe_irq_mask(unsigned long val)
 {
-        unsigned int mask;
+        unsigned int status, mask = 0;
+        struct irq_desc *desc;
         int i;
 
-        mask = 0;
-        for (i = 0; i < NR_IRQS; i++) {
-                struct irq_desc *desc = irq_desc + i;
-                unsigned int status;
-
+        for_each_irq_desc(i, desc) {
                 spin_lock_irq(&desc->lock);
                 status = desc->status;
 
@@ -171,20 +161,19 @@ EXPORT_SYMBOL(probe_irq_mask);
  */
 int probe_irq_off(unsigned long val)
 {
-        int i, irq_found = 0, nr_irqs = 0;
-
-        for (i = 0; i < NR_IRQS; i++) {
-                struct irq_desc *desc = irq_desc + i;
-                unsigned int status;
+        int i, irq_found = 0, nr_of_irqs = 0;
+        struct irq_desc *desc;
+        unsigned int status;
 
+        for_each_irq_desc(i, desc) {
                 spin_lock_irq(&desc->lock);
                 status = desc->status;
 
                 if (status & IRQ_AUTODETECT) {
                         if (!(status & IRQ_WAITING)) {
-                                if (!nr_irqs)
+                                if (!nr_of_irqs)
                                         irq_found = i;
-                                nr_irqs++;
+                                nr_of_irqs++;
                         }
                         desc->status = status & ~IRQ_AUTODETECT;
                         desc->chip->shutdown(i);
@@ -193,7 +182,7 @@ int probe_irq_off(unsigned long val)
         }
         mutex_unlock(&probing_active);
 
-        if (nr_irqs > 1)
+        if (nr_of_irqs > 1)
                 irq_found = -irq_found;
 
         return irq_found;
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index 3cd441ebf5d2..4895fde4eb93 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -24,16 +24,15 @@
  */
 void dynamic_irq_init(unsigned int irq)
 {
-        struct irq_desc *desc;
+        struct irq_desc *desc = irq_to_desc(irq);
         unsigned long flags;
 
-        if (irq >= NR_IRQS) {
+        if (!desc) {
                 WARN(1, KERN_ERR "Trying to initialize invalid IRQ%d\n", irq);
                 return;
         }
 
         /* Ensure we don't have left over values from a previous use of this irq */
-        desc = irq_desc + irq;
         spin_lock_irqsave(&desc->lock, flags);
         desc->status = IRQ_DISABLED;
         desc->chip = &no_irq_chip;
@@ -57,15 +56,14 @@ void dynamic_irq_init(unsigned int irq)
  */
 void dynamic_irq_cleanup(unsigned int irq)
 {
-        struct irq_desc *desc;
+        struct irq_desc *desc = irq_to_desc(irq);
         unsigned long flags;
 
-        if (irq >= NR_IRQS) {
+        if (!desc) {
                 WARN(1, KERN_ERR "Trying to cleanup invalid IRQ%d\n", irq);
                 return;
         }
 
-        desc = irq_desc + irq;
         spin_lock_irqsave(&desc->lock, flags);
         if (desc->action) {
                 spin_unlock_irqrestore(&desc->lock, flags);
@@ -89,10 +87,10 @@ void dynamic_irq_cleanup(unsigned int irq)
  */
 int set_irq_chip(unsigned int irq, struct irq_chip *chip)
 {
-        struct irq_desc *desc;
+        struct irq_desc *desc = irq_to_desc(irq);
         unsigned long flags;
 
-        if (irq >= NR_IRQS) {
+        if (!desc) {
                 WARN(1, KERN_ERR "Trying to install chip for IRQ%d\n", irq);
                 return -EINVAL;
         }
@@ -100,7 +98,6 @@ int set_irq_chip(unsigned int irq, struct irq_chip *chip)
         if (!chip)
                 chip = &no_irq_chip;
 
-        desc = irq_desc + irq;
         spin_lock_irqsave(&desc->lock, flags);
         irq_chip_set_defaults(chip);
         desc->chip = chip;
@@ -111,27 +108,27 @@ 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, flags);
+        spin_unlock_irqrestore(&desc->lock, flags);
         return ret;
 }
 EXPORT_SYMBOL(set_irq_type);
@@ -145,16 +142,15 @@ EXPORT_SYMBOL(set_irq_type);
  */
 int set_irq_data(unsigned int irq, void *data)
 {
-        struct irq_desc *desc;
+        struct irq_desc *desc = irq_to_desc(irq);
         unsigned long flags;
 
-        if (irq >= NR_IRQS) {
+        if (!desc) {
                 printk(KERN_ERR
                        "Trying to install controller data for IRQ%d\n", irq);
                 return -EINVAL;
         }
 
-        desc = irq_desc + irq;
         spin_lock_irqsave(&desc->lock, flags);
         desc->handler_data = data;
         spin_unlock_irqrestore(&desc->lock, flags);
@@ -171,15 +167,15 @@ EXPORT_SYMBOL(set_irq_data);
  */
 int set_irq_msi(unsigned int irq, struct msi_desc *entry)
 {
-        struct irq_desc *desc;
+        struct irq_desc *desc = irq_to_desc(irq);
         unsigned long flags;
 
-        if (irq >= NR_IRQS) {
+        if (!desc) {
                 printk(KERN_ERR
                        "Trying to install msi data for IRQ%d\n", irq);
                 return -EINVAL;
         }
-        desc = irq_desc + irq;
+
         spin_lock_irqsave(&desc->lock, flags);
         desc->msi_desc = entry;
         if (entry)
@@ -197,10 +193,16 @@ int set_irq_msi(unsigned int irq, struct msi_desc *entry)
  */
 int set_irq_chip_data(unsigned int irq, void *data)
 {
-        struct irq_desc *desc = irq_desc + irq;
+        struct irq_desc *desc = irq_to_desc(irq);
         unsigned long flags;
 
-        if (irq >= NR_IRQS || !desc->chip) {
+        if (!desc) {
+                printk(KERN_ERR
+                       "Trying to install chip data for IRQ%d\n", irq);
+                return -EINVAL;
+        }
+
+        if (!desc->chip) {
                 printk(KERN_ERR "BUG: bad set_irq_chip_data(IRQ#%d)\n", irq);
                 return -EINVAL;
         }
@@ -218,7 +220,7 @@ EXPORT_SYMBOL(set_irq_chip_data);
  */
 static void default_enable(unsigned int irq)
 {
-        struct irq_desc *desc = irq_desc + irq;
+        struct irq_desc *desc = irq_to_desc(irq);
 
         desc->chip->unmask(irq);
         desc->status &= ~IRQ_MASKED;
@@ -236,8 +238,9 @@ static void default_disable(unsigned int irq)
  */
 static unsigned int default_startup(unsigned int irq)
 {
-        irq_desc[irq].chip->enable(irq);
+        struct irq_desc *desc = irq_to_desc(irq);
 
+        desc->chip->enable(irq);
         return 0;
 }
 
@@ -246,7 +249,7 @@ static unsigned int default_startup(unsigned int irq)
  */
 static void default_shutdown(unsigned int irq)
 {
-        struct irq_desc *desc = irq_desc + irq;
+        struct irq_desc *desc = irq_to_desc(irq);
 
         desc->chip->mask(irq);
         desc->status |= IRQ_MASKED;
@@ -305,14 +308,13 @@ handle_simple_irq(unsigned int irq, struct irq_desc *desc)
 {
         struct irqaction *action;
         irqreturn_t action_ret;
-        const unsigned int cpu = smp_processor_id();
 
         spin_lock(&desc->lock);
 
         if (unlikely(desc->status & IRQ_INPROGRESS))
                 goto out_unlock;
         desc->status &= ~(IRQ_REPLAY | IRQ_WAITING);
-        kstat_cpu(cpu).irqs[irq]++;
+        kstat_incr_irqs_this_cpu(irq, desc);
 
         action = desc->action;
         if (unlikely(!action || (desc->status & IRQ_DISABLED)))
@@ -344,7 +346,6 @@ out_unlock:
 void
 handle_level_irq(unsigned int irq, struct irq_desc *desc)
 {
-        unsigned int cpu = smp_processor_id();
         struct irqaction *action;
         irqreturn_t action_ret;
 
@@ -354,7 +355,7 @@ handle_level_irq(unsigned int irq, struct irq_desc *desc)
         if (unlikely(desc->status & IRQ_INPROGRESS))
                 goto out_unlock;
         desc->status &= ~(IRQ_REPLAY | IRQ_WAITING);
-        kstat_cpu(cpu).irqs[irq]++;
+        kstat_incr_irqs_this_cpu(irq, desc);
 
         /*
          * If its disabled or no action available
@@ -392,7 +393,6 @@ out_unlock:
 void
 handle_fasteoi_irq(unsigned int irq, struct irq_desc *desc)
 {
-        unsigned int cpu = smp_processor_id();
         struct irqaction *action;
         irqreturn_t action_ret;
 
@@ -402,7 +402,7 @@ handle_fasteoi_irq(unsigned int irq, struct irq_desc *desc)
                 goto out;
 
         desc->status &= ~(IRQ_REPLAY | IRQ_WAITING);
-        kstat_cpu(cpu).irqs[irq]++;
+        kstat_incr_irqs_this_cpu(irq, desc);
 
         /*
          * If its disabled or no action available
@@ -451,8 +451,6 @@ out:
 void
 handle_edge_irq(unsigned int irq, struct irq_desc *desc)
 {
-        const unsigned int cpu = smp_processor_id();
-
         spin_lock(&desc->lock);
 
         desc->status &= ~(IRQ_REPLAY | IRQ_WAITING);
@@ -468,8 +466,7 @@ handle_edge_irq(unsigned int irq, struct irq_desc *desc)
                 mask_ack_irq(desc, irq);
                 goto out_unlock;
         }
-
-        kstat_cpu(cpu).irqs[irq]++;
+        kstat_incr_irqs_this_cpu(irq, desc);
 
         /* Start handling the irq */
         desc->chip->ack(irq);
@@ -524,7 +521,7 @@ handle_percpu_irq(unsigned int irq, struct irq_desc *desc)
 {
         irqreturn_t action_ret;
 
-        kstat_this_cpu.irqs[irq]++;
+        kstat_incr_irqs_this_cpu(irq, desc);
 
         if (desc->chip->ack)
                 desc->chip->ack(irq);
@@ -541,17 +538,15 @@ void
 __set_irq_handler(unsigned int irq, irq_flow_handler_t handle, int is_chained,
                   const char *name)
 {
-        struct irq_desc *desc;
+        struct irq_desc *desc = irq_to_desc(irq);
         unsigned long flags;
 
-        if (irq >= NR_IRQS) {
+        if (!desc) {
                 printk(KERN_ERR
                        "Trying to install type control for IRQ%d\n", irq);
                 return;
         }
 
-        desc = irq_desc + irq;
-
         if (!handle)
                 handle = handle_bad_irq;
         else if (desc->chip == &no_irq_chip) {
@@ -583,7 +578,7 @@ __set_irq_handler(unsigned int irq, irq_flow_handler_t handle, int is_chained,
                 desc->status &= ~IRQ_DISABLED;
                 desc->status |= IRQ_NOREQUEST | IRQ_NOPROBE;
                 desc->depth = 0;
-                desc->chip->unmask(irq);
+                desc->chip->startup(irq);
         }
         spin_unlock_irqrestore(&desc->lock, flags);
 }
@@ -606,17 +601,14 @@ set_irq_chip_and_handler_name(unsigned int irq, struct irq_chip *chip,
 
 void __init set_irq_noprobe(unsigned int irq)
 {
-        struct irq_desc *desc;
+        struct irq_desc *desc = irq_to_desc(irq);
         unsigned long flags;
 
-        if (irq >= NR_IRQS) {
+        if (!desc) {
                 printk(KERN_ERR "Trying to mark IRQ%d non-probeable\n", irq);
-
                 return;
         }
 
-        desc = irq_desc + irq;
-
         spin_lock_irqsave(&desc->lock, flags);
         desc->status |= IRQ_NOPROBE;
         spin_unlock_irqrestore(&desc->lock, flags);
@@ -624,17 +616,14 @@ 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 60c49e324390..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)
@@ -81,18 +81,17 @@ 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
-        if (desc->status & IRQ_MOVE_PCNTXT) {
+        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
@@ -111,16 +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
@@ -140,10 +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);
@@ -169,9 +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);
@@ -211,10 +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);
@@ -223,9 +223,9 @@ void enable_irq(unsigned int irq)
 }
 EXPORT_SYMBOL(enable_irq);
 
-int set_irq_wake_real(unsigned int irq, unsigned int on)
+static int set_irq_wake_real(unsigned int irq, unsigned int on)
 {
-        struct irq_desc *desc = irq_desc + irq;
+        struct irq_desc *desc = irq_to_desc(irq);
         int ret = -ENXIO;
 
         if (desc->chip->set_wake)
@@ -248,7 +248,7 @@ int set_irq_wake_real(unsigned int irq, unsigned int on)
  */
 int set_irq_wake(unsigned int irq, unsigned int on)
 {
-        struct irq_desc *desc = irq_desc + irq;
+        struct irq_desc *desc = irq_to_desc(irq);
         unsigned long flags;
         int ret = 0;
 
@@ -288,12 +288,16 @@ EXPORT_SYMBOL(set_irq_wake);
  */
 int can_request_irq(unsigned int irq, unsigned long irqflags)
 {
+        struct irq_desc *desc = irq_to_desc(irq);
         struct irqaction *action;
 
-        if (irq >= NR_IRQS || irq_desc[irq].status & IRQ_NOREQUEST)
+        if (!desc)
+                return 0;
+
+        if (desc->status & IRQ_NOREQUEST)
                 return 0;
 
-        action = irq_desc[irq].action;
+        action = desc->action;
         if (action)
                 if (irqflags & action->flags & IRQF_SHARED)
                         action = NULL;
@@ -312,10 +316,11 @@ void compat_irq_chip_set_default_handler(struct irq_desc *desc)
                 desc->handle_irq = NULL;
 }
 
-static int __irq_set_trigger(struct irq_chip *chip, unsigned int irq,
+int __irq_set_trigger(struct irq_desc *desc, unsigned int irq,
                 unsigned long flags)
 {
         int ret;
+        struct irq_chip *chip = desc->chip;
 
         if (!chip || !chip->set_type) {
                 /*
@@ -333,6 +338,11 @@ static int __irq_set_trigger(struct irq_chip *chip, unsigned int irq,
                 pr_err("setting trigger mode %d for irq %u failed (%pF)\n",
                                 (int)(flags & IRQF_TRIGGER_MASK),
                                 irq, chip->set_type);
+        else {
+                /* note that IRQF_TRIGGER_MASK == IRQ_TYPE_SENSE_MASK */
+                desc->status &= ~IRQ_TYPE_SENSE_MASK;
+                desc->status |= flags & IRQ_TYPE_SENSE_MASK;
+        }
 
         return ret;
 }
@@ -341,16 +351,16 @@ static int __irq_set_trigger(struct irq_chip *chip, unsigned int irq,
  * Internal function to register an irqaction - typically used to
  * allocate special interrupts that are part of the architecture.
  */
-int setup_irq(unsigned int irq, struct irqaction *new)
+static int
+__setup_irq(unsigned int irq, struct irq_desc * desc, struct irqaction *new)
 {
-        struct irq_desc *desc = irq_desc + irq;
         struct irqaction *old, **p;
         const char *old_name = NULL;
         unsigned long flags;
         int shared = 0;
         int ret;
 
-        if (irq >= NR_IRQS)
+        if (!desc)
                 return -EINVAL;
 
         if (desc->chip == &no_irq_chip)
@@ -411,7 +421,7 @@ int setup_irq(unsigned int irq, struct irqaction *new)
 
                 /* Setup the type (level, edge polarity) if configured: */
                 if (new->flags & IRQF_TRIGGER_MASK) {
-                        ret = __irq_set_trigger(desc->chip, irq, new->flags);
+                        ret = __irq_set_trigger(desc, irq, new->flags);
 
                         if (ret) {
                                 spin_unlock_irqrestore(&desc->lock, flags);
@@ -430,16 +440,21 @@ int setup_irq(unsigned int irq, struct irqaction *new)
                 if (!(desc->status & IRQ_NOAUTOEN)) {
                         desc->depth = 0;
                         desc->status &= ~IRQ_DISABLED;
-                        if (desc->chip->startup)
-                                desc->chip->startup(irq);
-                        else
-                                desc->chip->enable(irq);
+                        desc->chip->startup(irq);
                 } else
                         /* Undo nested disables: */
                         desc->depth = 1;
 
                 /* Set default affinity mask once everything is setup */
                 irq_select_affinity(irq);
+
+        } else if ((new->flags & IRQF_TRIGGER_MASK)
+                        && (new->flags & IRQF_TRIGGER_MASK)
+                                != (desc->status & IRQ_TYPE_SENSE_MASK)) {
+                /* hope the handler works with the actual trigger mode... */
+                pr_warning("IRQ %d uses trigger mode %d; requested %d\n",
+                                irq, (int)(desc->status & IRQ_TYPE_SENSE_MASK),
+                                (int)(new->flags & IRQF_TRIGGER_MASK));
         }
 
         *p = new;
@@ -464,7 +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);
 
@@ -484,6 +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
@@ -499,15 +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 (;;) {
@@ -596,12 +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
@@ -618,9 +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;
@@ -636,26 +670,29 @@ int request_irq(unsigned int irq, irq_handler_t handler,
         action->next = NULL;
         action->dev_id = dev_id;
 
+        retval = __setup_irq(irq, desc, action);
+        if (retval)
+                kfree(action);
+
 #ifdef CONFIG_DEBUG_SHIRQ
         if (irqflags & IRQF_SHARED) {
                 /*
                  * It's a shared IRQ -- the driver ought to be prepared for it
                  * to happen immediately, so let's make sure....
-                 * We do this before actually registering it, to make sure that
-                 * a 'real' IRQ doesn't run in parallel with our fake
+                 * We disable the irq to make sure that a 'real' IRQ doesn't
+                 * run in parallel with our fake.
                  */
                 unsigned long flags;
 
+                disable_irq(irq);
                 local_irq_save(flags);
+
                 handler(irq, dev_id);
+
                 local_irq_restore(flags);
+                enable_irq(irq);
         }
 #endif
-
-        retval = setup_irq(irq, action);
-        if (retval)
-                kfree(action);
-
         return retval;
 }
 EXPORT_SYMBOL(request_irq);
diff --git a/kernel/irq/migration.c b/kernel/irq/migration.c
index 77b7acc875c5..90b920d3f52b 100644
--- a/kernel/irq/migration.c
+++ b/kernel/irq/migration.c
@@ -3,18 +3,18 @@
 
 void set_pending_irq(unsigned int irq, cpumask_t mask)
 {
-        struct irq_desc *desc = irq_desc + irq;
+        struct irq_desc *desc = irq_to_desc(irq);
         unsigned long flags;
 
         spin_lock_irqsave(&desc->lock, flags);
         desc->status |= IRQ_MOVE_PENDING;
-        irq_desc[irq].pending_mask = mask;
+        desc->pending_mask = mask;
         spin_unlock_irqrestore(&desc->lock, flags);
 }
 
 void move_masked_irq(int irq)
 {
-        struct irq_desc *desc = irq_desc + irq;
+        struct irq_desc *desc = irq_to_desc(irq);
         cpumask_t tmp;
 
         if (likely(!(desc->status & IRQ_MOVE_PENDING)))
@@ -30,7 +30,7 @@ void move_masked_irq(int irq)
 
         desc->status &= ~IRQ_MOVE_PENDING;
 
-        if (unlikely(cpus_empty(irq_desc[irq].pending_mask)))
+        if (unlikely(cpus_empty(desc->pending_mask)))
                 return;
 
         if (!desc->chip->set_affinity)
@@ -38,7 +38,7 @@ void move_masked_irq(int irq)
 
         assert_spin_locked(&desc->lock);
 
-        cpus_and(tmp, irq_desc[irq].pending_mask, cpu_online_map);
+        cpus_and(tmp, desc->pending_mask, cpu_online_map);
 
         /*
          * If there was a valid mask to work with, please
@@ -55,12 +55,12 @@ void move_masked_irq(int irq)
         if (likely(!cpus_empty(tmp))) {
                 desc->chip->set_affinity(irq,tmp);
         }
-        cpus_clear(irq_desc[irq].pending_mask);
+        cpus_clear(desc->pending_mask);
 }
 
 void move_native_irq(int irq)
 {
-        struct irq_desc *desc = irq_desc + irq;
+        struct irq_desc *desc = irq_to_desc(irq);
 
         if (likely(!(desc->status & IRQ_MOVE_PENDING)))
                 return;
diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c
index a09dd29c2fd7..fac014a81b24 100644
--- a/kernel/irq/proc.c
+++ b/kernel/irq/proc.c
@@ -19,7 +19,7 @@ static struct proc_dir_entry *root_irq_dir;
 
 static int irq_affinity_proc_show(struct seq_file *m, void *v)
 {
-        struct irq_desc *desc = irq_desc + (long)m->private;
+        struct irq_desc *desc = irq_to_desc((long)m->private);
         cpumask_t *mask = &desc->affinity;
 
 #ifdef CONFIG_GENERIC_PENDING_IRQ
@@ -43,7 +43,7 @@ static ssize_t irq_affinity_proc_write(struct file *file,
         cpumask_t new_value;
         int err;
 
-        if (!irq_desc[irq].chip->set_affinity || no_irq_affinity ||
+        if (!irq_to_desc(irq)->chip->set_affinity || no_irq_affinity ||
             irq_balancing_disabled(irq))
                 return -EIO;
 
@@ -132,20 +132,20 @@ static const struct file_operations default_affinity_proc_fops = {
 static int irq_spurious_read(char *page, char **start, off_t off,
                                   int count, int *eof, void *data)
 {
-        struct irq_desc *d = &irq_desc[(long) data];
+        struct irq_desc *desc = irq_to_desc((long) data);
         return sprintf(page, "count %u\n"
                              "unhandled %u\n"
                              "last_unhandled %u ms\n",
-                        d->irq_count,
-                        d->irqs_unhandled,
-                        jiffies_to_msecs(d->last_unhandled));
+                        desc->irq_count,
+                        desc->irqs_unhandled,
+                        jiffies_to_msecs(desc->last_unhandled));
 }
 
 #define MAX_NAMELEN 128
 
 static int name_unique(unsigned int irq, struct irqaction *new_action)
 {
-        struct irq_desc *desc = irq_desc + irq;
+        struct irq_desc *desc = irq_to_desc(irq);
         struct irqaction *action;
         unsigned long flags;
         int ret = 1;
@@ -165,8 +165,9 @@ static int name_unique(unsigned int irq, struct irqaction *new_action)
 void register_handler_proc(unsigned int irq, struct irqaction *action)
 {
         char name [MAX_NAMELEN];
+        struct irq_desc *desc = irq_to_desc(irq);
 
-        if (!irq_desc[irq].dir || action->dir || !action->name ||
+        if (!desc->dir || action->dir || !action->name ||
                                         !name_unique(irq, action))
                 return;
 
@@ -174,36 +175,34 @@ void register_handler_proc(unsigned int irq, struct irqaction *action)
         snprintf(name, MAX_NAMELEN, "%s", action->name);
 
         /* create /proc/irq/1234/handler/ */
-        action->dir = proc_mkdir(name, irq_desc[irq].dir);
+        action->dir = proc_mkdir(name, desc->dir);
 }
 
 #undef MAX_NAMELEN
 
 #define MAX_NAMELEN 10
 
-void register_irq_proc(unsigned int irq)
+void register_irq_proc(unsigned int irq, struct irq_desc *desc)
 {
         char name [MAX_NAMELEN];
         struct proc_dir_entry *entry;
 
-        if (!root_irq_dir ||
-                (irq_desc[irq].chip == &no_irq_chip) ||
-                        irq_desc[irq].dir)
+        if (!root_irq_dir || (desc->chip == &no_irq_chip) || desc->dir)
                 return;
 
         memset(name, 0, MAX_NAMELEN);
         sprintf(name, "%d", irq);
 
         /* create /proc/irq/1234 */
-        irq_desc[irq].dir = proc_mkdir(name, root_irq_dir);
+        desc->dir = proc_mkdir(name, root_irq_dir);
 
 #ifdef CONFIG_SMP
         /* create /proc/irq/<irq>/smp_affinity */
-        proc_create_data("smp_affinity", 0600, irq_desc[irq].dir,
+        proc_create_data("smp_affinity", 0600, desc->dir,
                          &irq_affinity_proc_fops, (void *)(long)irq);
 #endif
 
-        entry = create_proc_entry("spurious", 0444, irq_desc[irq].dir);
+        entry = create_proc_entry("spurious", 0444, desc->dir);
         if (entry) {
                 entry->data = (void *)(long)irq;
                 entry->read_proc = irq_spurious_read;
@@ -214,8 +213,11 @@ 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)
@@ -228,7 +230,8 @@ void register_default_affinity_proc(void)
 
 void init_irq_proc(void)
 {
-        int i;
+        unsigned int irq;
+        struct irq_desc *desc;
 
         /* create /proc/irq */
         root_irq_dir = proc_mkdir("irq", NULL);
@@ -240,7 +243,7 @@ void init_irq_proc(void)
         /*
          * Create entries for all existing IRQs.
          */
-        for (i = 0; i < NR_IRQS; i++)
-                register_irq_proc(i);
+        for_each_irq_desc(irq, desc)
+                register_irq_proc(irq, desc);
 }
 
diff --git a/kernel/irq/resend.c b/kernel/irq/resend.c
index a8046791ba2d..89c7117acf2b 100644
--- a/kernel/irq/resend.c
+++ b/kernel/irq/resend.c
@@ -33,10 +33,10 @@ static void resend_irqs(unsigned long arg)
         struct irq_desc *desc;
         int irq;
 
-        while (!bitmap_empty(irqs_resend, NR_IRQS)) {
-                irq = find_first_bit(irqs_resend, NR_IRQS);
+        while (!bitmap_empty(irqs_resend, nr_irqs)) {
+                irq = find_first_bit(irqs_resend, nr_irqs);
                 clear_bit(irq, irqs_resend);
-                desc = irq_desc + irq;
+                desc = irq_to_desc(irq);
                 local_irq_disable();
                 desc->handle_irq(irq, desc);
                 local_irq_enable();
diff --git a/kernel/irq/spurious.c b/kernel/irq/spurious.c
index c66d3f10e853..dd364c11e56e 100644
--- a/kernel/irq/spurious.c
+++ b/kernel/irq/spurious.c
@@ -12,83 +12,122 @@
 #include <linux/kallsyms.h>
 #include <linux/interrupt.h>
 #include <linux/moduleparam.h>
+#include <linux/timer.h>
 
 static int irqfixup __read_mostly;
 
+#define POLL_SPURIOUS_IRQ_INTERVAL (HZ/10)
+static void poll_spurious_irqs(unsigned long dummy);
+static DEFINE_TIMER(poll_spurious_irq_timer, poll_spurious_irqs, 0, 0);
+
 /*
  * Recovery handler for misrouted interrupts.
  */
-static int misrouted_irq(int irq)
+static int try_one_irq(int irq, struct irq_desc *desc)
 {
-        int i;
-        int ok = 0;
-        int work = 0;   /* Did we do work for a real IRQ */
-
-        for (i = 1; i < NR_IRQS; i++) {
-                struct irq_desc *desc = irq_desc + i;
-                struct irqaction *action;
-
-                if (i == irq)   /* Already tried */
-                        continue;
+        struct irqaction *action;
+        int ok = 0, work = 0;
 
-                spin_lock(&desc->lock);
-                /* Already running on another processor */
-                if (desc->status & IRQ_INPROGRESS) {
-                        /*
-                         * Already running: If it is shared get the other
-                         * CPU to go looking for our mystery interrupt too
-                         */
-                        if (desc->action && (desc->action->flags & IRQF_SHARED))
-                                desc->status |= IRQ_PENDING;
-                        spin_unlock(&desc->lock);
-                        continue;
-                }
-                /* Honour the normal IRQ locking */
-                desc->status |= IRQ_INPROGRESS;
-                action = desc->action;
+        spin_lock(&desc->lock);
+        /* Already running on another processor */
+        if (desc->status & IRQ_INPROGRESS) {
+                /*
+                 * Already running: If it is shared get the other
+                 * CPU to go looking for our mystery interrupt too
+                 */
+                if (desc->action && (desc->action->flags & IRQF_SHARED))
+                        desc->status |= IRQ_PENDING;
                 spin_unlock(&desc->lock);
+                return ok;
+        }
+        /* Honour the normal IRQ locking */
+        desc->status |= IRQ_INPROGRESS;
+        action = desc->action;
+        spin_unlock(&desc->lock);
 
-                while (action) {
-                        /* Only shared IRQ handlers are safe to call */
-                        if (action->flags & IRQF_SHARED) {
-                                if (action->handler(i, action->dev_id) ==
-                                                IRQ_HANDLED)
-                                        ok = 1;
-                        }
-                        action = action->next;
+        while (action) {
+                /* Only shared IRQ handlers are safe to call */
+                if (action->flags & IRQF_SHARED) {
+                        if (action->handler(irq, action->dev_id) ==
+                                IRQ_HANDLED)
+                                ok = 1;
                 }
-                local_irq_disable();
-                /* Now clean up the flags */
-                spin_lock(&desc->lock);
-                action = desc->action;
+                action = action->next;
+        }
+        local_irq_disable();
+        /* Now clean up the flags */
+        spin_lock(&desc->lock);
+        action = desc->action;
 
+        /*
+         * While we were looking for a fixup someone queued a real
+         * IRQ clashing with our walk:
+         */
+        while ((desc->status & IRQ_PENDING) && action) {
                 /*
-                 * While we were looking for a fixup someone queued a real
-                 * IRQ clashing with our walk:
-                 */
-                while ((desc->status & IRQ_PENDING) && action) {
-                        /*
-                         * Perform real IRQ processing for the IRQ we deferred
-                         */
-                        work = 1;
-                        spin_unlock(&desc->lock);
-                        handle_IRQ_event(i, action);
-                        spin_lock(&desc->lock);
-                        desc->status &= ~IRQ_PENDING;
-                }
-                desc->status &= ~IRQ_INPROGRESS;
-                /*
-                 * If we did actual work for the real IRQ line we must let the
-                 * IRQ controller clean up too
+                 * Perform real IRQ processing for the IRQ we deferred
                  */
-                if (work && desc->chip && desc->chip->end)
-                        desc->chip->end(i);
+                work = 1;
                 spin_unlock(&desc->lock);
+                handle_IRQ_event(irq, action);
+                spin_lock(&desc->lock);
+                desc->status &= ~IRQ_PENDING;
+        }
+        desc->status &= ~IRQ_INPROGRESS;
+        /*
+         * If we did actual work for the real IRQ line we must let the
+         * IRQ controller clean up too
+         */
+        if (work && desc->chip && desc->chip->end)
+                desc->chip->end(irq);
+        spin_unlock(&desc->lock);
+
+        return ok;
+}
+
+static int misrouted_irq(int irq)
+{
+        struct irq_desc *desc;
+        int i, ok = 0;
+
+        for_each_irq_desc(i, desc) {
+                if (!i)
+                         continue;
+
+                if (i == irq)   /* Already tried */
+                        continue;
+
+                if (try_one_irq(i, desc))
+                        ok = 1;
         }
         /* So the caller can adjust the irq error counts */
         return ok;
 }
 
+static void poll_spurious_irqs(unsigned long dummy)
+{
+        struct irq_desc *desc;
+        int i;
+
+        for_each_irq_desc(i, desc) {
+                unsigned int status;
+
+                if (!i)
+                         continue;
+
+                /* Racy but it doesn't matter */
+                status = desc->status;
+                barrier();
+                if (!(status & IRQ_SPURIOUS_DISABLED))
+                        continue;
+
+                try_one_irq(i, desc);
+        }
+
+        mod_timer(&poll_spurious_irq_timer,
+                  jiffies + POLL_SPURIOUS_IRQ_INTERVAL);
+}
+
 /*
  * If 99,900 of the previous 100,000 interrupts have not been handled
  * then assume that the IRQ is stuck in some manner. Drop a diagnostic
@@ -137,7 +176,9 @@ report_bad_irq(unsigned int irq, struct irq_desc *desc, irqreturn_t action_ret)
         }
 }
 
-static inline int try_misrouted_irq(unsigned int irq, struct irq_desc *desc, irqreturn_t action_ret)
+static inline int
+try_misrouted_irq(unsigned int irq, struct irq_desc *desc,
+                  irqreturn_t action_ret)
 {
         struct irqaction *action;
 
@@ -212,6 +253,9 @@ void note_interrupt(unsigned int irq, struct irq_desc *desc,
                 desc->status |= IRQ_DISABLED | IRQ_SPURIOUS_DISABLED;
                 desc->depth++;
                 desc->chip->disable(irq);
+
+                mod_timer(&poll_spurious_irq_timer,
+                          jiffies + POLL_SPURIOUS_IRQ_INTERVAL);
         }
         desc->irqs_unhandled = 0;
 }
@@ -241,7 +285,7 @@ static int __init irqfixup_setup(char *str)
 
 __setup("irqfixup", irqfixup_setup);
 module_param(irqfixup, int, 0644);
-MODULE_PARM_DESC("irqfixup", "0: No fixup, 1: irqfixup mode 2: irqpoll mode");
+MODULE_PARM_DESC("irqfixup", "0: No fixup, 1: irqfixup mode, 2: irqpoll mode");
 
 static int __init irqpoll_setup(char *str)
 {
diff --git a/kernel/itimer.c b/kernel/itimer.c
index ab982747d9bd..db7c358b9a02 100644
--- a/kernel/itimer.c
+++ b/kernel/itimer.c
@@ -55,17 +55,15 @@ int do_getitimer(int which, struct itimerval *value)
                 spin_unlock_irq(&tsk->sighand->siglock);
                 break;
         case ITIMER_VIRTUAL:
-                read_lock(&tasklist_lock);
                 spin_lock_irq(&tsk->sighand->siglock);
                 cval = tsk->signal->it_virt_expires;
                 cinterval = tsk->signal->it_virt_incr;
                 if (!cputime_eq(cval, cputime_zero)) {
-                        struct task_struct *t = tsk;
-                        cputime_t utime = tsk->signal->utime;
-                        do {
-                                utime = cputime_add(utime, t->utime);
-                                t = next_thread(t);
-                        } while (t != tsk);
+                        struct task_cputime cputime;
+                        cputime_t utime;
+
+                        thread_group_cputime(tsk, &cputime);
+                        utime = cputime.utime;
                         if (cputime_le(cval, utime)) { /* about to fire */
                                 cval = jiffies_to_cputime(1);
                         } else {
@@ -73,25 +71,19 @@ int do_getitimer(int which, struct itimerval *value)
                         }
                 }
                 spin_unlock_irq(&tsk->sighand->siglock);
-                read_unlock(&tasklist_lock);
                 cputime_to_timeval(cval, &value->it_value);
                 cputime_to_timeval(cinterval, &value->it_interval);
                 break;
         case ITIMER_PROF:
-                read_lock(&tasklist_lock);
                 spin_lock_irq(&tsk->sighand->siglock);
                 cval = tsk->signal->it_prof_expires;
                 cinterval = tsk->signal->it_prof_incr;
                 if (!cputime_eq(cval, cputime_zero)) {
-                        struct task_struct *t = tsk;
-                        cputime_t ptime = cputime_add(tsk->signal->utime,
-                                                      tsk->signal->stime);
-                        do {
-                                ptime = cputime_add(ptime,
-                                                    cputime_add(t->utime,
-                                                                t->stime));
-                                t = next_thread(t);
-                        } while (t != tsk);
+                        struct task_cputime times;
+                        cputime_t ptime;
+
+                        thread_group_cputime(tsk, &times);
+                        ptime = cputime_add(times.utime, times.stime);
                         if (cputime_le(cval, ptime)) { /* about to fire */
                                 cval = jiffies_to_cputime(1);
                         } else {
@@ -99,7 +91,6 @@ int do_getitimer(int which, struct itimerval *value)
                         }
                 }
                 spin_unlock_irq(&tsk->sighand->siglock);
-                read_unlock(&tasklist_lock);
                 cputime_to_timeval(cval, &value->it_value);
                 cputime_to_timeval(cinterval, &value->it_interval);
                 break;
@@ -185,7 +176,6 @@ again:
         case ITIMER_VIRTUAL:
                 nval = timeval_to_cputime(&value->it_value);
                 ninterval = timeval_to_cputime(&value->it_interval);
-                read_lock(&tasklist_lock);
                 spin_lock_irq(&tsk->sighand->siglock);
                 cval = tsk->signal->it_virt_expires;
                 cinterval = tsk->signal->it_virt_incr;
@@ -200,7 +190,6 @@ again:
                 tsk->signal->it_virt_expires = nval;
                 tsk->signal->it_virt_incr = ninterval;
                 spin_unlock_irq(&tsk->sighand->siglock);
-                read_unlock(&tasklist_lock);
                 if (ovalue) {
                         cputime_to_timeval(cval, &ovalue->it_value);
                         cputime_to_timeval(cinterval, &ovalue->it_interval);
@@ -209,7 +198,6 @@ again:
         case ITIMER_PROF:
                 nval = timeval_to_cputime(&value->it_value);
                 ninterval = timeval_to_cputime(&value->it_interval);
-                read_lock(&tasklist_lock);
                 spin_lock_irq(&tsk->sighand->siglock);
                 cval = tsk->signal->it_prof_expires;
                 cinterval = tsk->signal->it_prof_incr;
@@ -224,7 +212,6 @@ again:
                 tsk->signal->it_prof_expires = nval;
                 tsk->signal->it_prof_incr = ninterval;
                 spin_unlock_irq(&tsk->sighand->siglock);
-                read_unlock(&tasklist_lock);
                 if (ovalue) {
                         cputime_to_timeval(cval, &ovalue->it_value);
                         cputime_to_timeval(cinterval, &ovalue->it_interval);
diff --git a/kernel/kexec.c b/kernel/kexec.c
index aef265325cd3..ac0fde7b54d0 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -30,6 +30,7 @@
 #include <linux/pm.h>
 #include <linux/cpu.h>
 #include <linux/console.h>
+#include <linux/vmalloc.h>
 
 #include <asm/page.h>
 #include <asm/uaccess.h>
@@ -1371,6 +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);
@@ -1406,6 +1408,7 @@ static int __init crash_save_vmcoreinfo_init(void)
         VMCOREINFO_OFFSET(free_area, free_list);
         VMCOREINFO_OFFSET(list_head, next);
         VMCOREINFO_OFFSET(list_head, prev);
+        VMCOREINFO_OFFSET(vm_struct, addr);
         VMCOREINFO_LENGTH(zone.free_area, MAX_ORDER);
         VMCOREINFO_LENGTH(free_area.free_list, MIGRATE_TYPES);
         VMCOREINFO_NUMBER(NR_FREE_PAGES);
diff --git a/kernel/kthread.c b/kernel/kthread.c
index 50598e29439a..8e7a7ce3ed0a 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -172,12 +172,11 @@ EXPORT_SYMBOL(kthread_create);
  */
 void kthread_bind(struct task_struct *k, unsigned int cpu)
 {
-        if (k->state != TASK_UNINTERRUPTIBLE) {
+        /* Must have done schedule() in kthread() before we set_task_cpu */
+        if (!wait_task_inactive(k, TASK_UNINTERRUPTIBLE)) {
                 WARN_ON(1);
                 return;
         }
-        /* Must have done schedule() in kthread() before we set_task_cpu */
-        wait_task_inactive(k, 0);
         set_task_cpu(k, cpu);
         k->cpus_allowed = cpumask_of_cpu(cpu);
         k->rt.nr_cpus_allowed = 1;
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 5131e5471169..b931d7cedbfa 100644
--- a/kernel/posix-timers.c
+++ b/kernel/posix-timers.c
@@ -223,6 +223,15 @@ static int posix_ktime_get_ts(clockid_t which_clock, struct timespec *tp)
 }
 
 /*
+ * Get monotonic time for posix timers
+ */
+static int posix_get_monotonic_raw(clockid_t which_clock, struct timespec *tp)
+{
+        getrawmonotonic(tp);
+        return 0;
+}
+
+/*
  * Initialize everything, well, just everything in Posix clocks/timers ;)
  */
 static __init int init_posix_timers(void)
@@ -235,9 +244,15 @@ static __init int init_posix_timers(void)
                 .clock_get = posix_ktime_get_ts,
                 .clock_set = do_posix_clock_nosettime,
         };
+        struct k_clock clock_monotonic_raw = {
+                .clock_getres = hrtimer_get_res,
+                .clock_get = posix_get_monotonic_raw,
+                .clock_set = do_posix_clock_nosettime,
+        };
 
         register_posix_clock(CLOCK_REALTIME, &clock_realtime);
         register_posix_clock(CLOCK_MONOTONIC, &clock_monotonic);
+        register_posix_clock(CLOCK_MONOTONIC_RAW, &clock_monotonic_raw);
 
         posix_timers_cache = kmem_cache_create("posix_timers_cache",
                                         sizeof (struct k_itimer), 0, SLAB_PANIC,
@@ -298,6 +313,7 @@ void do_schedule_next_timer(struct siginfo *info)
 
 int posix_timer_event(struct k_itimer *timr, int si_private)
 {
+        int shared, ret;
         /*
          * FIXME: if ->sigq is queued we can race with
          * dequeue_signal()->do_schedule_next_timer().
@@ -311,25 +327,10 @@ int posix_timer_event(struct k_itimer *timr, int si_private)
          */
         timr->sigq->info.si_sys_private = si_private;
 
-        timr->sigq->info.si_signo = timr->it_sigev_signo;
-        timr->sigq->info.si_code = SI_TIMER;
-        timr->sigq->info.si_tid = timr->it_id;
-        timr->sigq->info.si_value = timr->it_sigev_value;
-
-        if (timr->it_sigev_notify & SIGEV_THREAD_ID) {
-                struct task_struct *leader;
-                int ret = send_sigqueue(timr->sigq, timr->it_process, 0);
-
-                if (likely(ret >= 0))
-                        return ret;
-
-                timr->it_sigev_notify = SIGEV_SIGNAL;
-                leader = timr->it_process->group_leader;
-                put_task_struct(timr->it_process);
-                timr->it_process = leader;
-        }
-
-        return send_sigqueue(timr->sigq, timr->it_process, 1);
+        shared = !(timr->it_sigev_notify & SIGEV_THREAD_ID);
+        ret = send_sigqueue(timr->sigq, timr->it_process, shared);
+        /* If we failed to send the signal the timer stops. */
+        return ret > 0;
 }
 EXPORT_SYMBOL_GPL(posix_timer_event);
 
@@ -468,11 +469,9 @@ sys_timer_create(const clockid_t which_clock,
                  struct sigevent __user *timer_event_spec,
                  timer_t __user * created_timer_id)
 {
-        int error = 0;
-        struct k_itimer *new_timer = NULL;
-        int new_timer_id;
-        struct task_struct *process = NULL;
-        unsigned long flags;
+        struct k_itimer *new_timer;
+        int error, new_timer_id;
+        struct task_struct *process;
         sigevent_t event;
         int it_id_set = IT_ID_NOT_SET;
 
@@ -490,12 +489,11 @@ sys_timer_create(const clockid_t which_clock,
                 goto out;
         }
         spin_lock_irq(&idr_lock);
-        error = idr_get_new(&posix_timers_id, (void *) new_timer,
-                            &new_timer_id);
+        error = idr_get_new(&posix_timers_id, new_timer, &new_timer_id);
         spin_unlock_irq(&idr_lock);
-        if (error == -EAGAIN)
-                goto retry;
-        else if (error) {
+        if (error) {
+                if (error == -EAGAIN)
+                        goto retry;
                 /*
                  * Weird looking, but we return EAGAIN if the IDR is
                  * full (proper POSIX return value for this)
@@ -526,67 +524,43 @@ sys_timer_create(const clockid_t which_clock,
                         error = -EFAULT;
                         goto out;
                 }
-                new_timer->it_sigev_notify = event.sigev_notify;
-                new_timer->it_sigev_signo = event.sigev_signo;
-                new_timer->it_sigev_value = event.sigev_value;
-
-                read_lock(&tasklist_lock);
-                if ((process = good_sigevent(&event))) {
-                        /*
-                         * We may be setting up this process for another
-                         * thread.  It may be exiting.  To catch this
-                         * case the we check the PF_EXITING flag.  If
-                         * the flag is not set, the siglock will catch
-                         * him before it is too late (in exit_itimers).
-                         *
-                         * The exec case is a bit more invloved but easy
-                         * to code.  If the process is in our thread
-                         * group (and it must be or we would not allow
-                         * it here) and is doing an exec, it will cause
-                         * us to be killed.  In this case it will wait
-                         * for us to die which means we can finish this
-                         * linkage with our last gasp. I.e. no code :)
-                         */
-                        spin_lock_irqsave(&process->sighand->siglock, flags);
-                        if (!(process->flags & PF_EXITING)) {
-                                new_timer->it_process = process;
-                                list_add(&new_timer->list,
-                                         &process->signal->posix_timers);
-                                if (new_timer->it_sigev_notify == (SIGEV_SIGNAL|SIGEV_THREAD_ID))
-                                        get_task_struct(process);
-                                spin_unlock_irqrestore(&process->sighand->siglock, flags);
-                        } else {
-                                spin_unlock_irqrestore(&process->sighand->siglock, flags);
-                                process = NULL;
-                        }
-                }
-                read_unlock(&tasklist_lock);
+                rcu_read_lock();
+                process = good_sigevent(&event);
+                if (process)
+                        get_task_struct(process);
+                rcu_read_unlock();
                 if (!process) {
                         error = -EINVAL;
                         goto out;
                 }
         } else {
-                new_timer->it_sigev_notify = SIGEV_SIGNAL;
-                new_timer->it_sigev_signo = SIGALRM;
-                new_timer->it_sigev_value.sival_int = new_timer->it_id;
+                event.sigev_notify = SIGEV_SIGNAL;
+                event.sigev_signo = SIGALRM;
+                event.sigev_value.sival_int = new_timer->it_id;
                 process = current->group_leader;
-                spin_lock_irqsave(&process->sighand->siglock, flags);
-                new_timer->it_process = process;
-                list_add(&new_timer->list, &process->signal->posix_timers);
-                spin_unlock_irqrestore(&process->sighand->siglock, flags);
+                get_task_struct(process);
         }
 
+        new_timer->it_sigev_notify     = event.sigev_notify;
+        new_timer->sigq->info.si_signo = event.sigev_signo;
+        new_timer->sigq->info.si_value = event.sigev_value;
+        new_timer->sigq->info.si_tid   = new_timer->it_id;
+        new_timer->sigq->info.si_code  = SI_TIMER;
+
+        spin_lock_irq(&current->sighand->siglock);
+        new_timer->it_process = process;
+        list_add(&new_timer->list, &current->signal->posix_timers);
+        spin_unlock_irq(&current->sighand->siglock);
+
+        return 0;
         /*
          * In the case of the timer belonging to another task, after
          * the task is unlocked, the timer is owned by the other task
          * and may cease to exist at any time.  Don't use or modify
          * new_timer after the unlock call.
          */
-
 out:
-        if (error)
-                release_posix_timer(new_timer, it_id_set);
-
+        release_posix_timer(new_timer, it_id_set);
         return error;
 }
 
@@ -597,7 +571,7 @@ out:
  * the find to the timer lock.  To avoid a dead lock, the timer id MUST
  * be release with out holding the timer lock.
  */
-static struct k_itimer * lock_timer(timer_t timer_id, unsigned long *flags)
+static struct k_itimer *lock_timer(timer_t timer_id, unsigned long *flags)
 {
         struct k_itimer *timr;
         /*
@@ -605,23 +579,20 @@ static struct k_itimer * lock_timer(timer_t timer_id, unsigned long *flags)
          * flags part over to the timer lock.  Must not let interrupts in
          * while we are moving the lock.
          */
-
         spin_lock_irqsave(&idr_lock, *flags);
-        timr = (struct k_itimer *) idr_find(&posix_timers_id, (int) timer_id);
+        timr = idr_find(&posix_timers_id, (int)timer_id);
         if (timr) {
                 spin_lock(&timr->it_lock);
-
-                if ((timr->it_id != timer_id) || !(timr->it_process) ||
-                                !same_thread_group(timr->it_process, current)) {
-                        spin_unlock(&timr->it_lock);
-                        spin_unlock_irqrestore(&idr_lock, *flags);
-                        timr = NULL;
-                } else
+                if (timr->it_process &&
+                    same_thread_group(timr->it_process, current)) {
                         spin_unlock(&idr_lock);
-        } else
-                spin_unlock_irqrestore(&idr_lock, *flags);
+                        return timr;
+                }
+                spin_unlock(&timr->it_lock);
+        }
+        spin_unlock_irqrestore(&idr_lock, *flags);
 
-        return timr;
+        return NULL;
 }
 
 /*
@@ -862,8 +833,7 @@ retry_delete:
          * This keeps any tasks waiting on the spin lock from thinking
          * they got something (see the lock code above).
          */
-        if (timer->it_sigev_notify == (SIGEV_SIGNAL|SIGEV_THREAD_ID))
-                put_task_struct(timer->it_process);
+        put_task_struct(timer->it_process);
         timer->it_process = NULL;
 
         unlock_timer(timer, flags);
@@ -890,8 +860,7 @@ retry_delete:
          * This keeps any tasks waiting on the spin lock from thinking
          * they got something (see the lock code above).
          */
-        if (timer->it_sigev_notify == (SIGEV_SIGNAL|SIGEV_THREAD_ID))
-                put_task_struct(timer->it_process);
+        put_task_struct(timer->it_process);
         timer->it_process = NULL;
 
         unlock_timer(timer, flags);
diff --git a/kernel/power/process.c b/kernel/power/process.c
index 278946aecaf0..ca634019497a 100644
--- a/kernel/power/process.c
+++ b/kernel/power/process.c
@@ -28,121 +28,6 @@ static inline int freezeable(struct task_struct * p)
         return 1;
 }
 
-/*
- * freezing is complete, mark current process as frozen
- */
-static inline void frozen_process(void)
-{
-        if (!unlikely(current->flags & PF_NOFREEZE)) {
-                current->flags |= PF_FROZEN;
-                wmb();
-        }
-        clear_freeze_flag(current);
-}
-
-/* Refrigerator is place where frozen processes are stored :-). */
-void refrigerator(void)
-{
-        /* Hmm, should we be allowed to suspend when there are realtime
-           processes around? */
-        long save;
-
-        task_lock(current);
-        if (freezing(current)) {
-                frozen_process();
-                task_unlock(current);
-        } else {
-                task_unlock(current);
-                return;
-        }
-        save = current->state;
-        pr_debug("%s entered refrigerator\n", current->comm);
-
-        spin_lock_irq(&current->sighand->siglock);
-        recalc_sigpending(); /* We sent fake signal, clean it up */
-        spin_unlock_irq(&current->sighand->siglock);
-
-        for (;;) {
-                set_current_state(TASK_UNINTERRUPTIBLE);
-                if (!frozen(current))
-                        break;
-                schedule();
-        }
-        pr_debug("%s left refrigerator\n", current->comm);
-        __set_current_state(save);
-}
-
-static void fake_signal_wake_up(struct task_struct *p)
-{
-        unsigned long flags;
-
-        spin_lock_irqsave(&p->sighand->siglock, flags);
-        signal_wake_up(p, 0);
-        spin_unlock_irqrestore(&p->sighand->siglock, flags);
-}
-
-static inline bool should_send_signal(struct task_struct *p)
-{
-        return !(p->flags & PF_FREEZER_NOSIG);
-}
-
-/**
- *      freeze_task - send a freeze request to given task
- *      @p: task to send the request to
- *      @sig_only: if set, the request will only be sent if the task has the
- *              PF_FREEZER_NOSIG flag unset
- *      Return value: 'false', if @sig_only is set and the task has
- *              PF_FREEZER_NOSIG set or the task is frozen, 'true', otherwise
- *
- *      The freeze request is sent by setting the tasks's TIF_FREEZE flag and
- *      either sending a fake signal to it or waking it up, depending on whether
- *      or not it has PF_FREEZER_NOSIG set.  If @sig_only is set and the task
- *      has PF_FREEZER_NOSIG set (ie. it is a typical kernel thread), its
- *      TIF_FREEZE flag will not be set.
- */
-static bool freeze_task(struct task_struct *p, bool sig_only)
-{
-        /*
-         * We first check if the task is freezing and next if it has already
-         * been frozen to avoid the race with frozen_process() which first marks
-         * the task as frozen and next clears its TIF_FREEZE.
-         */
-        if (!freezing(p)) {
-                rmb();
-                if (frozen(p))
-                        return false;
-
-                if (!sig_only || should_send_signal(p))
-                        set_freeze_flag(p);
-                else
-                        return false;
-        }
-
-        if (should_send_signal(p)) {
-                if (!signal_pending(p))
-                        fake_signal_wake_up(p);
-        } else if (sig_only) {
-                return false;
-        } else {
-                wake_up_state(p, TASK_INTERRUPTIBLE);
-        }
-
-        return true;
-}
-
-static void cancel_freezing(struct task_struct *p)
-{
-        unsigned long flags;
-
-        if (freezing(p)) {
-                pr_debug("  clean up: %s\n", p->comm);
-                clear_freeze_flag(p);
-                spin_lock_irqsave(&p->sighand->siglock, flags);
-                recalc_sigpending_and_wake(p);
-                spin_unlock_irqrestore(&p->sighand->siglock, flags);
-        }
-}
-
 static int try_to_freeze_tasks(bool sig_only)
 {
         struct task_struct *g, *p;
@@ -250,6 +135,9 @@ static void thaw_tasks(bool nosig_only)
                 if (nosig_only && should_send_signal(p))
                         continue;
 
+                if (cgroup_frozen(p))
+                        continue;
+
                 thaw_process(p);
         } while_each_thread(g, p);
         read_unlock(&tasklist_lock);
@@ -264,4 +152,3 @@ void thaw_processes(void)
         printk("done.\n");
 }
 
-EXPORT_SYMBOL(refrigerator);
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 356699a96d56..1e68e4c39e2c 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -45,7 +45,7 @@ void __ptrace_link(struct task_struct *child, struct task_struct *new_parent)
  * TASK_TRACED, resume it now.
  * Requires that irqs be disabled.
  */
-void ptrace_untrace(struct task_struct *child)
+static void ptrace_untrace(struct task_struct *child)
 {
         spin_lock(&child->sighand->siglock);
         if (task_is_traced(child)) {
diff --git a/kernel/rcupreempt.c b/kernel/rcupreempt.c
index ca4bbbe04aa4..59236e8b9daa 100644
--- a/kernel/rcupreempt.c
+++ b/kernel/rcupreempt.c
@@ -54,9 +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>
+#include <asm/byteorder.h>
 
 /*
  * PREEMPT_RCU data structures.
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/sched.c b/kernel/sched.c
index 3d1ad130c24e..d906f72b42d2 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -4047,23 +4047,26 @@ 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;
@@ -4080,6 +4083,7 @@ 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);
@@ -4104,6 +4108,7 @@ 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);
@@ -4139,6 +4144,7 @@ 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);
@@ -4180,6 +4186,7 @@ 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
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 18fd17172eb6..f604dae71316 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -449,6 +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);
         }
 }
 
diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c
index cdf5740ab03e..b446dc87494f 100644
--- a/kernel/sched_rt.c
+++ b/kernel/sched_rt.c
@@ -526,6 +526,8 @@ 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);
 
@@ -1458,7 +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;
         }
 }
 
diff --git a/kernel/sched_stats.h b/kernel/sched_stats.h
index 8385d43987e2..b8c156979cf2 100644
--- a/kernel/sched_stats.h
+++ b/kernel/sched_stats.h
@@ -270,3 +270,89 @@ 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/signal.c b/kernel/signal.c
index bf40ecc87b26..105217da5c82 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -1341,6 +1341,7 @@ int do_notify_parent(struct task_struct *tsk, int sig)
         struct siginfo info;
         unsigned long flags;
         struct sighand_struct *psig;
+        struct task_cputime cputime;
         int ret = sig;
 
         BUG_ON(sig == -1);
@@ -1371,10 +1372,9 @@ int do_notify_parent(struct task_struct *tsk, int sig)
 
         info.si_uid = tsk->uid;
 
-        info.si_utime = cputime_to_clock_t(cputime_add(tsk->utime,
-                                                       tsk->signal->utime));
-        info.si_stime = cputime_to_clock_t(cputime_add(tsk->stime,
-                                                       tsk->signal->stime));
+        thread_group_cputime(tsk, &cputime);
+        info.si_utime = cputime_to_jiffies(cputime.utime);
+        info.si_stime = cputime_to_jiffies(cputime.stime);
 
         info.si_status = tsk->exit_code & 0x7f;
         if (tsk->exit_code & 0x80)
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 83ba21a13bd4..7110daeb9a90 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -267,16 +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
diff --git a/kernel/sys.c b/kernel/sys.c
index 0bc8fa3c2288..53879cdae483 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -853,38 +853,28 @@ asmlinkage long sys_setfsgid(gid_t gid)
         return old_fsgid;
 }
 
+void do_sys_times(struct tms *tms)
+{
+        struct task_cputime cputime;
+        cputime_t cutime, cstime;
+
+        spin_lock_irq(&current->sighand->siglock);
+        thread_group_cputime(current, &cputime);
+        cutime = current->signal->cutime;
+        cstime = current->signal->cstime;
+        spin_unlock_irq(&current->sighand->siglock);
+        tms->tms_utime = cputime_to_clock_t(cputime.utime);
+        tms->tms_stime = cputime_to_clock_t(cputime.stime);
+        tms->tms_cutime = cputime_to_clock_t(cutime);
+        tms->tms_cstime = cputime_to_clock_t(cstime);
+}
+
 asmlinkage long sys_times(struct tms __user * tbuf)
 {
-        /*
-         *      In the SMP world we might just be unlucky and have one of
-         *      the times increment as we use it. Since the value is an
-         *      atomically safe type this is just fine. Conceptually its
-         *      as if the syscall took an instant longer to occur.
-         */
         if (tbuf) {
                 struct tms tmp;
-                struct task_struct *tsk = current;
-                struct task_struct *t;
-                cputime_t utime, stime, cutime, cstime;
-
-                spin_lock_irq(&tsk->sighand->siglock);
-                utime = tsk->signal->utime;
-                stime = tsk->signal->stime;
-                t = tsk;
-                do {
-                        utime = cputime_add(utime, t->utime);
-                        stime = cputime_add(stime, t->stime);
-                        t = next_thread(t);
-                } while (t != tsk);
-
-                cutime = tsk->signal->cutime;
-                cstime = tsk->signal->cstime;
-                spin_unlock_irq(&tsk->sighand->siglock);
-
-                tmp.tms_utime = cputime_to_clock_t(utime);
-                tmp.tms_stime = cputime_to_clock_t(stime);
-                tmp.tms_cutime = cputime_to_clock_t(cutime);
-                tmp.tms_cstime = cputime_to_clock_t(cstime);
+
+                do_sys_times(&tmp);
                 if (copy_to_user(tbuf, &tmp, sizeof(struct tms)))
                         return -EFAULT;
         }
@@ -1449,7 +1439,6 @@ 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)
@@ -1503,18 +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;
 }
@@ -1552,11 +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;
@@ -1570,12 +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;
         }
 
@@ -1598,8 +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;
@@ -1608,7 +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;
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 619eb9f3acd8..edb1075f80d2 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -833,6 +833,16 @@ 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
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index 093d4acf993b..9ed2eec97526 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -325,6 +325,9 @@ int clocksource_register(struct clocksource *c)
         unsigned long flags;
         int ret;
 
+        /* save mult_orig on registration */
+        c->mult_orig = c->mult;
+
         spin_lock_irqsave(&clocksource_lock, flags);
         ret = clocksource_enqueue(c);
         if (!ret)
diff --git a/kernel/time/jiffies.c b/kernel/time/jiffies.c
index 4c256fdb8875..1ca99557e929 100644
--- a/kernel/time/jiffies.c
+++ b/kernel/time/jiffies.c
@@ -61,6 +61,7 @@ struct clocksource clocksource_jiffies = {
         .read           = jiffies_read,
         .mask           = 0xffffffff, /*32bits*/
         .mult           = NSEC_PER_JIFFY << JIFFIES_SHIFT, /* details above */
+        .mult_orig      = NSEC_PER_JIFFY << JIFFIES_SHIFT,
         .shift          = JIFFIES_SHIFT,
 };
 
diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
index 1ad46f3df6e7..1a20715bfd6e 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>
 
 /*
@@ -218,11 +218,11 @@ void second_overflow(void)
 /* Disable the cmos update - used by virtualization and embedded */
 int no_sync_cmos_clock  __read_mostly;
 
-static void sync_cmos_clock(unsigned long dummy);
+static void sync_cmos_clock(struct work_struct *work);
 
-static DEFINE_TIMER(sync_cmos_timer, sync_cmos_clock, 0, 0);
+static DECLARE_DELAYED_WORK(sync_cmos_work, sync_cmos_clock);
 
-static void sync_cmos_clock(unsigned long dummy)
+static void sync_cmos_clock(struct work_struct *work)
 {
         struct timespec now, next;
         int fail = 1;
@@ -258,13 +258,13 @@ 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 +277,50 @@ 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 +387,8 @@ 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 +396,18 @@ 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 cb01cd8f919b..f98a1b7b16e9 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -384,6 +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)
diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h
index 469248782c23..b1c05bf75ee0 100644
--- a/kernel/time/tick-internal.h
+++ b/kernel/time/tick-internal.h
@@ -36,6 +36,7 @@ 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)
 {
@@ -45,6 +46,7 @@ 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 */
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index b711ffcb106c..0581c11fe6c6 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -155,7 +155,7 @@ void tick_nohz_update_jiffies(void)
         touch_softlockup_watchdog();
 }
 
-void tick_nohz_stop_idle(int cpu)
+static void tick_nohz_stop_idle(int cpu)
 {
         struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
 
@@ -377,6 +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);
+        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);
+
+                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();
+        }
+}
+
 /**
  * tick_nohz_restart_sched_tick - restart the idle tick from the idle task
  *
@@ -430,28 +456,7 @@ 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);
-
-                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();
-        }
+        tick_nohz_restart(ts, now);
         local_irq_enable();
 }
 
@@ -503,10 +508,6 @@ 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);
@@ -552,6 +553,27 @@ 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);
+
+        if (!ts->tick_stopped)
+                return;
+
+        tick_nohz_restart(ts, ktime_get());
+}
+
 #else
 
 static inline void tick_nohz_switch_to_nohz(void) { }
@@ -559,6 +581,19 @@ 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
@@ -611,10 +646,6 @@ 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;
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..f6426911e35a 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);
@@ -99,7 +100,7 @@ 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 +110,7 @@ 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 +185,16 @@ 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 +228,7 @@ 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 +238,7 @@ 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 +250,7 @@ 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 510fe69351ca..56becf373c58 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -1436,9 +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);
@@ -1453,8 +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 */