Merge branch 'for-rmk' of git://git.kernel.org/pub/scm/linux/kernel/git/nico/orion into fixes

15 files changed, 500 insertions, 488 deletions

diff --git a/kernel/Makefile b/kernel/Makefile
index 188c43223f52..1c9938addb9d 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -9,7 +9,7 @@ obj-y     = sched.o fork.o exec_domain.o panic.o printk.o profile.o \
             rcupdate.o extable.o params.o posix-timers.o \
             kthread.o wait.o kfifo.o sys_ni.o posix-cpu-timers.o mutex.o \
             hrtimer.o rwsem.o nsproxy.o srcu.o semaphore.o \
-            notifier.o ksysfs.o pm_qos_params.o
+            notifier.o ksysfs.o pm_qos_params.o sched_clock.o
 
 obj-$(CONFIG_SYSCTL_SYSCALL_CHECK) += sysctl_check.o
 obj-$(CONFIG_STACKTRACE) += stacktrace.o
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 8da627d33804..86ea9e34e326 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -1031,11 +1031,9 @@ int current_cpuset_is_being_rebound(void)
         return task_cs(current) == cpuset_being_rebound;
 }
 
-static int update_relax_domain_level(struct cpuset *cs, char *buf)
+static int update_relax_domain_level(struct cpuset *cs, s64 val)
 {
-        int val = simple_strtol(buf, NULL, 10);
-
-        if (val < 0)
+        if ((int)val < 0)
                 val = -1;
 
         if (val != cs->relax_domain_level) {
@@ -1280,9 +1278,6 @@ static ssize_t cpuset_common_file_write(struct cgroup *cont,
         case FILE_MEMLIST:
                 retval = update_nodemask(cs, buffer);
                 break;
-        case FILE_SCHED_RELAX_DOMAIN_LEVEL:
-                retval = update_relax_domain_level(cs, buffer);
-                break;
         default:
                 retval = -EINVAL;
                 goto out2;
@@ -1348,6 +1343,30 @@ static int cpuset_write_u64(struct cgroup *cgrp, struct cftype *cft, u64 val)
         return retval;
 }
 
+static int cpuset_write_s64(struct cgroup *cgrp, struct cftype *cft, s64 val)
+{
+        int retval = 0;
+        struct cpuset *cs = cgroup_cs(cgrp);
+        cpuset_filetype_t type = cft->private;
+
+        cgroup_lock();
+
+        if (cgroup_is_removed(cgrp)) {
+                cgroup_unlock();
+                return -ENODEV;
+        }
+        switch (type) {
+        case FILE_SCHED_RELAX_DOMAIN_LEVEL:
+                retval = update_relax_domain_level(cs, val);
+                break;
+        default:
+                retval = -EINVAL;
+                break;
+        }
+        cgroup_unlock();
+        return retval;
+}
+
 /*
  * These ascii lists should be read in a single call, by using a user
  * buffer large enough to hold the entire map.  If read in smaller
@@ -1406,9 +1425,6 @@ static ssize_t cpuset_common_file_read(struct cgroup *cont,
         case FILE_MEMLIST:
                 s += cpuset_sprintf_memlist(s, cs);
                 break;
-        case FILE_SCHED_RELAX_DOMAIN_LEVEL:
-                s += sprintf(s, "%d", cs->relax_domain_level);
-                break;
         default:
                 retval = -EINVAL;
                 goto out;
@@ -1449,6 +1465,18 @@ static u64 cpuset_read_u64(struct cgroup *cont, struct cftype *cft)
         }
 }
 
+static s64 cpuset_read_s64(struct cgroup *cont, struct cftype *cft)
+{
+        struct cpuset *cs = cgroup_cs(cont);
+        cpuset_filetype_t type = cft->private;
+        switch (type) {
+        case FILE_SCHED_RELAX_DOMAIN_LEVEL:
+                return cs->relax_domain_level;
+        default:
+                BUG();
+        }
+}
+
 
 /*
  * for the common functions, 'private' gives the type of file
@@ -1499,8 +1527,8 @@ static struct cftype files[] = {
 
         {
                 .name = "sched_relax_domain_level",
-                .read_u64 = cpuset_read_u64,
-                .write_u64 = cpuset_write_u64,
+                .read_s64 = cpuset_read_s64,
+                .write_s64 = cpuset_write_s64,
                 .private = FILE_SCHED_RELAX_DOMAIN_LEVEL,
         },
 
diff --git a/kernel/futex.c b/kernel/futex.c
index 98092c9817f4..449def8074fe 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -104,10 +104,6 @@ struct futex_q {
         /* Key which the futex is hashed on: */
         union futex_key key;
 
-        /* For fd, sigio sent using these: */
-        int fd;
-        struct file *filp;
-
         /* Optional priority inheritance state: */
         struct futex_pi_state *pi_state;
         struct task_struct *task;
@@ -126,9 +122,6 @@ struct futex_hash_bucket {
 
 static struct futex_hash_bucket futex_queues[1<<FUTEX_HASHBITS];
 
-/* Futex-fs vfsmount entry: */
-static struct vfsmount *futex_mnt;
-
 /*
  * Take mm->mmap_sem, when futex is shared
  */
@@ -610,8 +603,6 @@ lookup_pi_state(u32 uval, struct futex_hash_bucket *hb,
 static void wake_futex(struct futex_q *q)
 {
         plist_del(&q->list, &q->list.plist);
-        if (q->filp)
-                send_sigio(&q->filp->f_owner, q->fd, POLL_IN);
         /*
          * The lock in wake_up_all() is a crucial memory barrier after the
          * plist_del() and also before assigning to q->lock_ptr.
@@ -988,14 +979,10 @@ out:
 }
 
 /* The key must be already stored in q->key. */
-static inline struct futex_hash_bucket *
-queue_lock(struct futex_q *q, int fd, struct file *filp)
+static inline struct futex_hash_bucket *queue_lock(struct futex_q *q)
 {
         struct futex_hash_bucket *hb;
 
-        q->fd = fd;
-        q->filp = filp;
-
         init_waitqueue_head(&q->waiters);
 
         get_futex_key_refs(&q->key);
@@ -1006,7 +993,7 @@ queue_lock(struct futex_q *q, int fd, struct file *filp)
         return hb;
 }
 
-static inline void __queue_me(struct futex_q *q, struct futex_hash_bucket *hb)
+static inline void queue_me(struct futex_q *q, struct futex_hash_bucket *hb)
 {
         int prio;
 
@@ -1041,15 +1028,6 @@ queue_unlock(struct futex_q *q, struct futex_hash_bucket *hb)
  * exactly once.  They are called with the hashed spinlock held.
  */
 
-/* The key must be already stored in q->key. */
-static void queue_me(struct futex_q *q, int fd, struct file *filp)
-{
-        struct futex_hash_bucket *hb;
-
-        hb = queue_lock(q, fd, filp);
-        __queue_me(q, hb);
-}
-
 /* Return 1 if we were still queued (ie. 0 means we were woken) */
 static int unqueue_me(struct futex_q *q)
 {
@@ -1194,7 +1172,7 @@ static int futex_wait(u32 __user *uaddr, struct rw_semaphore *fshared,
         if (unlikely(ret != 0))
                 goto out_release_sem;
 
-        hb = queue_lock(&q, -1, NULL);
+        hb = queue_lock(&q);
 
         /*
          * Access the page AFTER the futex is queued.
@@ -1238,7 +1216,7 @@ static int futex_wait(u32 __user *uaddr, struct rw_semaphore *fshared,
                 goto out_unlock_release_sem;
 
         /* Only actually queue if *uaddr contained val.  */
-        __queue_me(&q, hb);
+        queue_me(&q, hb);
 
         /*
          * Now the futex is queued and we have checked the data, we
@@ -1386,7 +1364,7 @@ static int futex_lock_pi(u32 __user *uaddr, struct rw_semaphore *fshared,
                 goto out_release_sem;
 
  retry_unlocked:
-        hb = queue_lock(&q, -1, NULL);
+        hb = queue_lock(&q);
 
  retry_locked:
         ret = lock_taken = 0;
@@ -1499,7 +1477,7 @@ static int futex_lock_pi(u32 __user *uaddr, struct rw_semaphore *fshared,
         /*
          * Only actually queue now that the atomic ops are done:
          */
-        __queue_me(&q, hb);
+        queue_me(&q, hb);
 
         /*
          * Now the futex is queued and we have checked the data, we
@@ -1746,121 +1724,6 @@ pi_faulted:
         return ret;
 }
 
-static int futex_close(struct inode *inode, struct file *filp)
-{
-        struct futex_q *q = filp->private_data;
-
-        unqueue_me(q);
-        kfree(q);
-
-        return 0;
-}
-
-/* This is one-shot: once it's gone off you need a new fd */
-static unsigned int futex_poll(struct file *filp,
-                               struct poll_table_struct *wait)
-{
-        struct futex_q *q = filp->private_data;
-        int ret = 0;
-
-        poll_wait(filp, &q->waiters, wait);
-
-        /*
-         * plist_node_empty() is safe here without any lock.
-         * q->lock_ptr != 0 is not safe, because of ordering against wakeup.
-         */
-        if (plist_node_empty(&q->list))
-                ret = POLLIN | POLLRDNORM;
-
-        return ret;
-}
-
-static const struct file_operations futex_fops = {
-        .release        = futex_close,
-        .poll           = futex_poll,
-};
-
-/*
- * Signal allows caller to avoid the race which would occur if they
- * set the sigio stuff up afterwards.
- */
-static int futex_fd(u32 __user *uaddr, int signal)
-{
-        struct futex_q *q;
-        struct file *filp;
-        int ret, err;
-        struct rw_semaphore *fshared;
-        static unsigned long printk_interval;
-
-        if (printk_timed_ratelimit(&printk_interval, 60 * 60 * 1000)) {
-                printk(KERN_WARNING "Process `%s' used FUTEX_FD, which "
-                       "will be removed from the kernel in June 2007\n",
-                       current->comm);
-        }
-
-        ret = -EINVAL;
-        if (!valid_signal(signal))
-                goto out;
-
-        ret = get_unused_fd();
-        if (ret < 0)
-                goto out;
-        filp = get_empty_filp();
-        if (!filp) {
-                put_unused_fd(ret);
-                ret = -ENFILE;
-                goto out;
-        }
-        filp->f_op = &futex_fops;
-        filp->f_path.mnt = mntget(futex_mnt);
-        filp->f_path.dentry = dget(futex_mnt->mnt_root);
-        filp->f_mapping = filp->f_path.dentry->d_inode->i_mapping;
-
-        if (signal) {
-                err = __f_setown(filp, task_pid(current), PIDTYPE_PID, 1);
-                if (err < 0) {
-                        goto error;
-                }
-                filp->f_owner.signum = signal;
-        }
-
-        q = kmalloc(sizeof(*q), GFP_KERNEL);
-        if (!q) {
-                err = -ENOMEM;
-                goto error;
-        }
-        q->pi_state = NULL;
-
-        fshared = &current->mm->mmap_sem;
-        down_read(fshared);
-        err = get_futex_key(uaddr, fshared, &q->key);
-
-        if (unlikely(err != 0)) {
-                up_read(fshared);
-                kfree(q);
-                goto error;
-        }
-
-        /*
-         * queue_me() must be called before releasing mmap_sem, because
-         * key->shared.inode needs to be referenced while holding it.
-         */
-        filp->private_data = q;
-
-        queue_me(q, ret, filp);
-        up_read(fshared);
-
-        /* Now we map fd to filp, so userspace can access it */
-        fd_install(ret, filp);
-out:
-        return ret;
-error:
-        put_unused_fd(ret);
-        put_filp(filp);
-        ret = err;
-        goto out;
-}
-
 /*
  * Support for robust futexes: the kernel cleans up held futexes at
  * thread exit time.
@@ -2092,10 +1955,6 @@ long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout,
         case FUTEX_WAKE_BITSET:
                 ret = futex_wake(uaddr, fshared, val, val3);
                 break;
-        case FUTEX_FD:
-                /* non-zero val means F_SETOWN(getpid()) & F_SETSIG(val) */
-                ret = futex_fd(uaddr, val);
-                break;
         case FUTEX_REQUEUE:
                 ret = futex_requeue(uaddr, fshared, uaddr2, val, val2, NULL);
                 break;
@@ -2156,19 +2015,6 @@ asmlinkage long sys_futex(u32 __user *uaddr, int op, u32 val,
         return do_futex(uaddr, op, val, tp, uaddr2, val2, val3);
 }
 
-static int futexfs_get_sb(struct file_system_type *fs_type,
-                          int flags, const char *dev_name, void *data,
-                          struct vfsmount *mnt)
-{
-        return get_sb_pseudo(fs_type, "futex", NULL, FUTEXFS_SUPER_MAGIC, mnt);
-}
-
-static struct file_system_type futex_fs_type = {
-        .name           = "futexfs",
-        .get_sb         = futexfs_get_sb,
-        .kill_sb        = kill_anon_super,
-};
-
 static int __init futex_init(void)
 {
         u32 curval;
@@ -2193,16 +2039,6 @@ static int __init futex_init(void)
                 spin_lock_init(&futex_queues[i].lock);
         }
 
-        i = register_filesystem(&futex_fs_type);
-        if (i)
-                return i;
-
-        futex_mnt = kern_mount(&futex_fs_type);
-        if (IS_ERR(futex_mnt)) {
-                unregister_filesystem(&futex_fs_type);
-                return PTR_ERR(futex_mnt);
-        }
-
         return 0;
 }
 __initcall(futex_init);
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index 9af1d6a8095e..421be5fe5cc7 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -154,15 +154,6 @@ static void hrtimer_get_softirq_time(struct hrtimer_cpu_base *base)
 }
 
 /*
- * Helper function to check, whether the timer is running the callback
- * function
- */
-static inline int hrtimer_callback_running(struct hrtimer *timer)
-{
-        return timer->state & HRTIMER_STATE_CALLBACK;
-}
-
-/*
  * Functions and macros which are different for UP/SMP systems are kept in a
  * single place
  */
diff --git a/kernel/kgdb.c b/kernel/kgdb.c
index 1bd0ec1c80b2..39e31a036f5b 100644
--- a/kernel/kgdb.c
+++ b/kernel/kgdb.c
@@ -61,7 +61,7 @@ struct kgdb_state {
         int                     err_code;
         int                     cpu;
         int                     pass_exception;
-        long                    threadid;
+        unsigned long           threadid;
         long                    kgdb_usethreadid;
         struct pt_regs          *linux_regs;
 };
@@ -146,7 +146,7 @@ atomic_t			kgdb_cpu_doing_single_step = ATOMIC_INIT(-1);
  * the other CPUs might interfere with your debugging context, so
  * use this with care:
  */
-int                             kgdb_do_roundup = 1;
+static int kgdb_do_roundup = 1;
 
 static int __init opt_nokgdbroundup(char *str)
 {
@@ -438,7 +438,7 @@ int kgdb_hex2mem(char *buf, char *mem, int count)
  * While we find nice hex chars, build a long_val.
  * Return number of chars processed.
  */
-int kgdb_hex2long(char **ptr, long *long_val)
+int kgdb_hex2long(char **ptr, unsigned long *long_val)
 {
         int hex_val;
         int num = 0;
@@ -709,7 +709,7 @@ int kgdb_isremovedbreak(unsigned long addr)
         return 0;
 }
 
-int remove_all_break(void)
+static int remove_all_break(void)
 {
         unsigned long addr;
         int error;
diff --git a/kernel/module.c b/kernel/module.c
index 8674a390a2e8..8e4528c9909f 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -890,6 +890,19 @@ static struct module_attribute *modinfo_attrs[] = {
 
 static const char vermagic[] = VERMAGIC_STRING;
 
+static int try_to_force_load(struct module *mod, const char *symname)
+{
+#ifdef CONFIG_MODULE_FORCE_LOAD
+        if (!(tainted & TAINT_FORCED_MODULE))
+                printk("%s: no version for \"%s\" found: kernel tainted.\n",
+                       mod->name, symname);
+        add_taint_module(mod, TAINT_FORCED_MODULE);
+        return 0;
+#else
+        return -ENOEXEC;
+#endif
+}
+
 #ifdef CONFIG_MODVERSIONS
 static int check_version(Elf_Shdr *sechdrs,
                          unsigned int versindex,
@@ -914,18 +927,18 @@ static int check_version(Elf_Shdr *sechdrs,
 
                 if (versions[i].crc == *crc)
                         return 1;
-                printk("%s: disagrees about version of symbol %s\n",
-                       mod->name, symname);
                 DEBUGP("Found checksum %lX vs module %lX\n",
                        *crc, versions[i].crc);
-                return 0;
+                goto bad_version;
         }
-        /* Not in module's version table.  OK, but that taints the kernel. */
-        if (!(tainted & TAINT_FORCED_MODULE))
-                printk("%s: no version for \"%s\" found: kernel tainted.\n",
-                       mod->name, symname);
-        add_taint_module(mod, TAINT_FORCED_MODULE);
-        return 1;
+
+        if (!try_to_force_load(mod, symname))
+                return 1;
+
+bad_version:
+        printk("%s: disagrees about version of symbol %s\n",
+               mod->name, symname);
+        return 0;
 }
 
 static inline int check_modstruct_version(Elf_Shdr *sechdrs,
@@ -1853,9 +1866,9 @@ static struct module *load_module(void __user *umod,
         modmagic = get_modinfo(sechdrs, infoindex, "vermagic");
         /* This is allowed: modprobe --force will invalidate it. */
         if (!modmagic) {
-                add_taint_module(mod, TAINT_FORCED_MODULE);
-                printk(KERN_WARNING "%s: no version magic, tainting kernel.\n",
-                       mod->name);
+                err = try_to_force_load(mod, "magic");
+                if (err)
+                        goto free_hdr;
         } else if (!same_magic(modmagic, vermagic)) {
                 printk(KERN_ERR "%s: version magic '%s' should be '%s'\n",
                        mod->name, modmagic, vermagic);
@@ -2006,9 +2019,10 @@ static struct module *load_module(void __user *umod,
             (mod->num_gpl_future_syms && !gplfuturecrcindex) ||
             (mod->num_unused_syms && !unusedcrcindex) ||
             (mod->num_unused_gpl_syms && !unusedgplcrcindex)) {
-                printk(KERN_WARNING "%s: No versions for exported symbols."
-                       " Tainting kernel.\n", mod->name);
-                add_taint_module(mod, TAINT_FORCED_MODULE);
+                printk(KERN_WARNING "%s: No versions for exported symbols.\n", mod->name);
+                err = try_to_force_load(mod, "nocrc");
+                if (err)
+                        goto cleanup;
         }
 #endif
         markersindex = find_sec(hdr, sechdrs, secstrings, "__markers");
diff --git a/kernel/relay.c b/kernel/relay.c
index 7de644cdec43..bc24dcdc570f 100644
--- a/kernel/relay.c
+++ b/kernel/relay.c
@@ -1191,7 +1191,7 @@ static ssize_t relay_file_splice_read(struct file *in,
         ret = 0;
         spliced = 0;
 
-        while (len && !spliced) {
+        while (len) {
                 ret = subbuf_splice_actor(in, ppos, pipe, len, flags, &nonpad_ret);
                 if (ret < 0)
                         break;
diff --git a/kernel/sched.c b/kernel/sched.c
index 34bcc5bc120e..58fb8af15776 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -75,16 +75,6 @@
 #include <asm/irq_regs.h>
 
 /*
- * Scheduler clock - returns current time in nanosec units.
- * This is default implementation.
- * Architectures and sub-architectures can override this.
- */
-unsigned long long __attribute__((weak)) sched_clock(void)
-{
-        return (unsigned long long)jiffies * (NSEC_PER_SEC / HZ);
-}
-
-/*
  * Convert user-nice values [ -20 ... 0 ... 19 ]
  * to static priority [ MAX_RT_PRIO..MAX_PRIO-1 ],
  * and back.
@@ -242,6 +232,12 @@ static void destroy_rt_bandwidth(struct rt_bandwidth *rt_b)
 }
 #endif
 
+/*
+ * sched_domains_mutex serializes calls to arch_init_sched_domains,
+ * detach_destroy_domains and partition_sched_domains.
+ */
+static DEFINE_MUTEX(sched_domains_mutex);
+
 #ifdef CONFIG_GROUP_SCHED
 
 #include <linux/cgroup.h>
@@ -308,9 +304,6 @@ static DEFINE_PER_CPU(struct rt_rq, init_rt_rq) ____cacheline_aligned_in_smp;
  */
 static DEFINE_SPINLOCK(task_group_lock);
 
-/* doms_cur_mutex serializes access to doms_cur[] array */
-static DEFINE_MUTEX(doms_cur_mutex);
-
 #ifdef CONFIG_FAIR_GROUP_SCHED
 #ifdef CONFIG_USER_SCHED
 # define INIT_TASK_GROUP_LOAD   (2*NICE_0_LOAD)
@@ -318,7 +311,13 @@ static DEFINE_MUTEX(doms_cur_mutex);
 # define INIT_TASK_GROUP_LOAD   NICE_0_LOAD
 #endif
 
+/*
+ * A weight of 0, 1 or ULONG_MAX can cause arithmetics problems.
+ * (The default weight is 1024 - so there's no practical
+ *  limitation from this.)
+ */
 #define MIN_SHARES      2
+#define MAX_SHARES      (ULONG_MAX - 1)
 
 static int init_task_group_load = INIT_TASK_GROUP_LOAD;
 #endif
@@ -358,21 +357,9 @@ static inline void set_task_rq(struct task_struct *p, unsigned int cpu)
 #endif
 }
 
-static inline void lock_doms_cur(void)
-{
-        mutex_lock(&doms_cur_mutex);
-}
-
-static inline void unlock_doms_cur(void)
-{
-        mutex_unlock(&doms_cur_mutex);
-}
-
 #else
 
 static inline void set_task_rq(struct task_struct *p, unsigned int cpu) { }
-static inline void lock_doms_cur(void) { }
-static inline void unlock_doms_cur(void) { }
 
 #endif  /* CONFIG_GROUP_SCHED */
 
@@ -560,13 +547,7 @@ struct rq {
         unsigned long next_balance;
         struct mm_struct *prev_mm;
 
-        u64 clock, prev_clock_raw;
-        s64 clock_max_delta;
-
-        unsigned int clock_warps, clock_overflows, clock_underflows;
-        u64 idle_clock;
-        unsigned int clock_deep_idle_events;
-        u64 tick_timestamp;
+        u64 clock;
 
         atomic_t nr_iowait;
 
@@ -631,82 +612,6 @@ static inline int cpu_of(struct rq *rq)
 #endif
 }
 
-#ifdef CONFIG_NO_HZ
-static inline bool nohz_on(int cpu)
-{
-        return tick_get_tick_sched(cpu)->nohz_mode != NOHZ_MODE_INACTIVE;
-}
-
-static inline u64 max_skipped_ticks(struct rq *rq)
-{
-        return nohz_on(cpu_of(rq)) ? jiffies - rq->last_tick_seen + 2 : 1;
-}
-
-static inline void update_last_tick_seen(struct rq *rq)
-{
-        rq->last_tick_seen = jiffies;
-}
-#else
-static inline u64 max_skipped_ticks(struct rq *rq)
-{
-        return 1;
-}
-
-static inline void update_last_tick_seen(struct rq *rq)
-{
-}
-#endif
-
-/*
- * Update the per-runqueue clock, as finegrained as the platform can give
- * us, but without assuming monotonicity, etc.:
- */
-static void __update_rq_clock(struct rq *rq)
-{
-        u64 prev_raw = rq->prev_clock_raw;
-        u64 now = sched_clock();
-        s64 delta = now - prev_raw;
-        u64 clock = rq->clock;
-
-#ifdef CONFIG_SCHED_DEBUG
-        WARN_ON_ONCE(cpu_of(rq) != smp_processor_id());
-#endif
-        /*
-         * Protect against sched_clock() occasionally going backwards:
-         */
-        if (unlikely(delta < 0)) {
-                clock++;
-                rq->clock_warps++;
-        } else {
-                /*
-                 * Catch too large forward jumps too:
-                 */
-                u64 max_jump = max_skipped_ticks(rq) * TICK_NSEC;
-                u64 max_time = rq->tick_timestamp + max_jump;
-
-                if (unlikely(clock + delta > max_time)) {
-                        if (clock < max_time)
-                                clock = max_time;
-                        else
-                                clock++;
-                        rq->clock_overflows++;
-                } else {
-                        if (unlikely(delta > rq->clock_max_delta))
-                                rq->clock_max_delta = delta;
-                        clock += delta;
-                }
-        }
-
-        rq->prev_clock_raw = now;
-        rq->clock = clock;
-}
-
-static void update_rq_clock(struct rq *rq)
-{
-        if (likely(smp_processor_id() == cpu_of(rq)))
-                __update_rq_clock(rq);
-}
-
 /*
  * The domain tree (rq->sd) is protected by RCU's quiescent state transition.
  * See detach_destroy_domains: synchronize_sched for details.
@@ -722,6 +627,11 @@ static void update_rq_clock(struct rq *rq)
 #define task_rq(p)              cpu_rq(task_cpu(p))
 #define cpu_curr(cpu)           (cpu_rq(cpu)->curr)
 
+static inline void update_rq_clock(struct rq *rq)
+{
+        rq->clock = sched_clock_cpu(cpu_of(rq));
+}
+
 /*
  * Tunables that become constants when CONFIG_SCHED_DEBUG is off:
  */
@@ -757,14 +667,14 @@ const_debug unsigned int sysctl_sched_features =
 #define SCHED_FEAT(name, enabled)       \
         #name ,
 
-__read_mostly char *sched_feat_names[] = {
+static __read_mostly char *sched_feat_names[] = {
 #include "sched_features.h"
         NULL
 };
 
 #undef SCHED_FEAT
 
-int sched_feat_open(struct inode *inode, struct file *filp)
+static int sched_feat_open(struct inode *inode, struct file *filp)
 {
         filp->private_data = inode->i_private;
         return 0;
@@ -899,7 +809,7 @@ static inline u64 global_rt_runtime(void)
         return (u64)sysctl_sched_rt_runtime * NSEC_PER_USEC;
 }
 
-static const unsigned long long time_sync_thresh = 100000;
+unsigned long long time_sync_thresh = 100000;
 
 static DEFINE_PER_CPU(unsigned long long, time_offset);
 static DEFINE_PER_CPU(unsigned long long, prev_cpu_time);
@@ -913,11 +823,14 @@ static DEFINE_PER_CPU(unsigned long long, prev_cpu_time);
 static DEFINE_SPINLOCK(time_sync_lock);
 static unsigned long long prev_global_time;
 
-static unsigned long long __sync_cpu_clock(cycles_t time, int cpu)
+static unsigned long long __sync_cpu_clock(unsigned long long time, int cpu)
 {
-        unsigned long flags;
-
-        spin_lock_irqsave(&time_sync_lock, flags);
+        /*
+         * We want this inlined, to not get tracer function calls
+         * in this critical section:
+         */
+        spin_acquire(&time_sync_lock.dep_map, 0, 0, _THIS_IP_);
+        __raw_spin_lock(&time_sync_lock.raw_lock);
 
         if (time < prev_global_time) {
                 per_cpu(time_offset, cpu) += prev_global_time - time;
@@ -926,7 +839,8 @@ static unsigned long long __sync_cpu_clock(cycles_t time, int cpu)
                 prev_global_time = time;
         }
 
-        spin_unlock_irqrestore(&time_sync_lock, flags);
+        __raw_spin_unlock(&time_sync_lock.raw_lock);
+        spin_release(&time_sync_lock.dep_map, 1, _THIS_IP_);
 
         return time;
 }
@@ -934,8 +848,6 @@ static unsigned long long __sync_cpu_clock(cycles_t time, int cpu)
 static unsigned long long __cpu_clock(int cpu)
 {
         unsigned long long now;
-        unsigned long flags;
-        struct rq *rq;
 
         /*
          * Only call sched_clock() if the scheduler has already been
@@ -944,11 +856,7 @@ static unsigned long long __cpu_clock(int cpu)
         if (unlikely(!scheduler_running))
                 return 0;
 
-        local_irq_save(flags);
-        rq = cpu_rq(cpu);
-        update_rq_clock(rq);
-        now = rq->clock;
-        local_irq_restore(flags);
+        now = sched_clock_cpu(cpu);
 
         return now;
 }
@@ -960,13 +868,18 @@ static unsigned long long __cpu_clock(int cpu)
 unsigned long long cpu_clock(int cpu)
 {
         unsigned long long prev_cpu_time, time, delta_time;
+        unsigned long flags;
 
+        local_irq_save(flags);
         prev_cpu_time = per_cpu(prev_cpu_time, cpu);
         time = __cpu_clock(cpu) + per_cpu(time_offset, cpu);
         delta_time = time-prev_cpu_time;
 
-        if (unlikely(delta_time > time_sync_thresh))
+        if (unlikely(delta_time > time_sync_thresh)) {
                 time = __sync_cpu_clock(time, cpu);
+                per_cpu(prev_cpu_time, cpu) = time;
+        }
+        local_irq_restore(flags);
 
         return time;
 }
@@ -1117,43 +1030,6 @@ static struct rq *this_rq_lock(void)
         return rq;
 }
 
-/*
- * We are going deep-idle (irqs are disabled):
- */
-void sched_clock_idle_sleep_event(void)
-{
-        struct rq *rq = cpu_rq(smp_processor_id());
-
-        spin_lock(&rq->lock);
-        __update_rq_clock(rq);
-        spin_unlock(&rq->lock);
-        rq->clock_deep_idle_events++;
-}
-EXPORT_SYMBOL_GPL(sched_clock_idle_sleep_event);
-
-/*
- * We just idled delta nanoseconds (called with irqs disabled):
- */
-void sched_clock_idle_wakeup_event(u64 delta_ns)
-{
-        struct rq *rq = cpu_rq(smp_processor_id());
-        u64 now = sched_clock();
-
-        rq->idle_clock += delta_ns;
-        /*
-         * Override the previous timestamp and ignore all
-         * sched_clock() deltas that occured while we idled,
-         * and use the PM-provided delta_ns to advance the
-         * rq clock:
-         */
-        spin_lock(&rq->lock);
-        rq->prev_clock_raw = now;
-        rq->clock += delta_ns;
-        spin_unlock(&rq->lock);
-        touch_softlockup_watchdog();
-}
-EXPORT_SYMBOL_GPL(sched_clock_idle_wakeup_event);
-
 static void __resched_task(struct task_struct *p, int tif_bit);
 
 static inline void resched_task(struct task_struct *p)
@@ -1189,6 +1065,7 @@ static inline void resched_rq(struct rq *rq)
 enum {
         HRTICK_SET,             /* re-programm hrtick_timer */
         HRTICK_RESET,           /* not a new slice */
+        HRTICK_BLOCK,           /* stop hrtick operations */
 };
 
 /*
@@ -1200,6 +1077,8 @@ static inline int hrtick_enabled(struct rq *rq)
 {
         if (!sched_feat(HRTICK))
                 return 0;
+        if (unlikely(test_bit(HRTICK_BLOCK, &rq->hrtick_flags)))
+                return 0;
         return hrtimer_is_hres_active(&rq->hrtick_timer);
 }
 
@@ -1275,14 +1154,70 @@ static enum hrtimer_restart hrtick(struct hrtimer *timer)
         WARN_ON_ONCE(cpu_of(rq) != smp_processor_id());
 
         spin_lock(&rq->lock);
-        __update_rq_clock(rq);
+        update_rq_clock(rq);
         rq->curr->sched_class->task_tick(rq, rq->curr, 1);
         spin_unlock(&rq->lock);
 
         return HRTIMER_NORESTART;
 }
 
-static inline void init_rq_hrtick(struct rq *rq)
+static void hotplug_hrtick_disable(int cpu)
+{
+        struct rq *rq = cpu_rq(cpu);
+        unsigned long flags;
+
+        spin_lock_irqsave(&rq->lock, flags);
+        rq->hrtick_flags = 0;
+        __set_bit(HRTICK_BLOCK, &rq->hrtick_flags);
+        spin_unlock_irqrestore(&rq->lock, flags);
+
+        hrtick_clear(rq);
+}
+
+static void hotplug_hrtick_enable(int cpu)
+{
+        struct rq *rq = cpu_rq(cpu);
+        unsigned long flags;
+
+        spin_lock_irqsave(&rq->lock, flags);
+        __clear_bit(HRTICK_BLOCK, &rq->hrtick_flags);
+        spin_unlock_irqrestore(&rq->lock, flags);
+}
+
+static int
+hotplug_hrtick(struct notifier_block *nfb, unsigned long action, void *hcpu)
+{
+        int cpu = (int)(long)hcpu;
+
+        switch (action) {
+        case CPU_UP_CANCELED:
+        case CPU_UP_CANCELED_FROZEN:
+        case CPU_DOWN_PREPARE:
+        case CPU_DOWN_PREPARE_FROZEN:
+        case CPU_DEAD:
+        case CPU_DEAD_FROZEN:
+                hotplug_hrtick_disable(cpu);
+                return NOTIFY_OK;
+
+        case CPU_UP_PREPARE:
+        case CPU_UP_PREPARE_FROZEN:
+        case CPU_DOWN_FAILED:
+        case CPU_DOWN_FAILED_FROZEN:
+        case CPU_ONLINE:
+        case CPU_ONLINE_FROZEN:
+                hotplug_hrtick_enable(cpu);
+                return NOTIFY_OK;
+        }
+
+        return NOTIFY_DONE;
+}
+
+static void init_hrtick(void)
+{
+        hotcpu_notifier(hotplug_hrtick, 0);
+}
+
+static void init_rq_hrtick(struct rq *rq)
 {
         rq->hrtick_flags = 0;
         hrtimer_init(&rq->hrtick_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
@@ -1319,6 +1254,10 @@ static inline void init_rq_hrtick(struct rq *rq)
 void hrtick_resched(void)
 {
 }
+
+static inline void init_hrtick(void)
+{
+}
 #endif
 
 /*
@@ -1438,8 +1377,8 @@ calc_delta_mine(unsigned long delta_exec, unsigned long weight,
 {
         u64 tmp;
 
-        if (unlikely(!lw->inv_weight))
-                lw->inv_weight = (WMULT_CONST-lw->weight/2) / (lw->weight+1);
+        if (!lw->inv_weight)
+                lw->inv_weight = 1 + (WMULT_CONST-lw->weight/2)/(lw->weight+1);
 
         tmp = (u64)delta_exec * weight;
         /*
@@ -1748,6 +1687,8 @@ __update_group_shares_cpu(struct task_group *tg, struct sched_domain *sd,
 
         if (shares < MIN_SHARES)
                 shares = MIN_SHARES;
+        else if (shares > MAX_SHARES)
+                shares = MAX_SHARES;
 
         __set_se_shares(tg->se[tcpu], shares);
 }
@@ -4339,8 +4280,10 @@ void account_system_time(struct task_struct *p, int hardirq_offset,
         struct rq *rq = this_rq();
         cputime64_t tmp;
 
-        if ((p->flags & PF_VCPU) && (irq_count() - hardirq_offset == 0))
-                return account_guest_time(p, cputime);
+        if ((p->flags & PF_VCPU) && (irq_count() - hardirq_offset == 0)) {
+                account_guest_time(p, cputime);
+                return;
+        }
 
         p->stime = cputime_add(p->stime, cputime);
 
@@ -4404,19 +4347,11 @@ void scheduler_tick(void)
         int cpu = smp_processor_id();
         struct rq *rq = cpu_rq(cpu);
         struct task_struct *curr = rq->curr;
-        u64 next_tick = rq->tick_timestamp + TICK_NSEC;
+
+        sched_clock_tick();
 
         spin_lock(&rq->lock);
-        __update_rq_clock(rq);
-        /*
-         * Let rq->clock advance by at least TICK_NSEC:
-         */
-        if (unlikely(rq->clock < next_tick)) {
-                rq->clock = next_tick;
-                rq->clock_underflows++;
-        }
-        rq->tick_timestamp = rq->clock;
-        update_last_tick_seen(rq);
+        update_rq_clock(rq);
         update_cpu_load(rq);
         curr->sched_class->task_tick(rq, curr, 0);
         spin_unlock(&rq->lock);
@@ -4570,7 +4505,7 @@ need_resched_nonpreemptible:
          * Do the rq-clock update outside the rq lock:
          */
         local_irq_disable();
-        __update_rq_clock(rq);
+        update_rq_clock(rq);
         spin_lock(&rq->lock);
         clear_tsk_need_resched(prev);
 
@@ -4595,9 +4530,9 @@ need_resched_nonpreemptible:
         prev->sched_class->put_prev_task(rq, prev);
         next = pick_next_task(rq, prev);
 
-        sched_info_switch(prev, next);
-
         if (likely(prev != next)) {
+                sched_info_switch(prev, next);
+
                 rq->nr_switches++;
                 rq->curr = next;
                 ++*switch_count;
@@ -7755,7 +7690,7 @@ void partition_sched_domains(int ndoms_new, cpumask_t *doms_new,
 {
         int i, j;
 
-        lock_doms_cur();
+        mutex_lock(&sched_domains_mutex);
 
         /* always unregister in case we don't destroy any domains */
         unregister_sched_domain_sysctl();
@@ -7804,7 +7739,7 @@ match2:
 
         register_sched_domain_sysctl();
 
-        unlock_doms_cur();
+        mutex_unlock(&sched_domains_mutex);
 }
 
 #if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT)
@@ -7813,8 +7748,10 @@ int arch_reinit_sched_domains(void)
         int err;
 
         get_online_cpus();
+        mutex_lock(&sched_domains_mutex);
         detach_destroy_domains(&cpu_online_map);
         err = arch_init_sched_domains(&cpu_online_map);
+        mutex_unlock(&sched_domains_mutex);
         put_online_cpus();
 
         return err;
@@ -7932,13 +7869,16 @@ void __init sched_init_smp(void)
         BUG_ON(sched_group_nodes_bycpu == NULL);
 #endif
         get_online_cpus();
+        mutex_lock(&sched_domains_mutex);
         arch_init_sched_domains(&cpu_online_map);
         cpus_andnot(non_isolated_cpus, cpu_possible_map, cpu_isolated_map);
         if (cpus_empty(non_isolated_cpus))
                 cpu_set(smp_processor_id(), non_isolated_cpus);
+        mutex_unlock(&sched_domains_mutex);
         put_online_cpus();
         /* XXX: Theoretical race here - CPU may be hotplugged now */
         hotcpu_notifier(update_sched_domains, 0);
+        init_hrtick();
 
         /* Move init over to a non-isolated CPU */
         if (set_cpus_allowed_ptr(current, &non_isolated_cpus) < 0)
@@ -8025,7 +7965,7 @@ static void init_tg_cfs_entry(struct task_group *tg, struct cfs_rq *cfs_rq,
 
         se->my_q = cfs_rq;
         se->load.weight = tg->shares;
-        se->load.inv_weight = div64_u64(1ULL<<32, se->load.weight);
+        se->load.inv_weight = 0;
         se->parent = parent;
 }
 #endif
@@ -8149,8 +8089,6 @@ void __init sched_init(void)
                 spin_lock_init(&rq->lock);
                 lockdep_set_class(&rq->lock, &rq->rq_lock_key);
                 rq->nr_running = 0;
-                rq->clock = 1;
-                update_last_tick_seen(rq);
                 init_cfs_rq(&rq->cfs, rq);
                 init_rt_rq(&rq->rt, rq);
 #ifdef CONFIG_FAIR_GROUP_SCHED
@@ -8294,6 +8232,7 @@ EXPORT_SYMBOL(__might_sleep);
 static void normalize_task(struct rq *rq, struct task_struct *p)
 {
         int on_rq;
+
         update_rq_clock(rq);
         on_rq = p->se.on_rq;
         if (on_rq)
@@ -8325,7 +8264,6 @@ void normalize_rt_tasks(void)
                 p->se.sleep_start               = 0;
                 p->se.block_start               = 0;
 #endif
-                task_rq(p)->clock               = 0;
 
                 if (!rt_task(p)) {
                         /*
@@ -8692,7 +8630,7 @@ static void __set_se_shares(struct sched_entity *se, unsigned long shares)
                 dequeue_entity(cfs_rq, se, 0);
 
         se->load.weight = shares;
-        se->load.inv_weight = div64_u64((1ULL<<32), shares);
+        se->load.inv_weight = 0;
 
         if (on_rq)
                 enqueue_entity(cfs_rq, se, 0);
@@ -8722,13 +8660,10 @@ int sched_group_set_shares(struct task_group *tg, unsigned long shares)
         if (!tg->se[0])
                 return -EINVAL;
 
-        /*
-         * A weight of 0 or 1 can cause arithmetics problems.
-         * (The default weight is 1024 - so there's no practical
-         *  limitation from this.)
-         */
         if (shares < MIN_SHARES)
                 shares = MIN_SHARES;
+        else if (shares > MAX_SHARES)
+                shares = MAX_SHARES;
 
         mutex_lock(&shares_mutex);
         if (tg->shares == shares)
@@ -8753,7 +8688,7 @@ int sched_group_set_shares(struct task_group *tg, unsigned long shares)
                  * force a rebalance
                  */
                 cfs_rq_set_shares(tg->cfs_rq[i], 0);
-                set_se_shares(tg->se[i], shares/nr_cpu_ids);
+                set_se_shares(tg->se[i], shares);
         }
 
         /*
diff --git a/kernel/sched_clock.c b/kernel/sched_clock.c
new file mode 100644
index 000000000000..9c597e37f7de
--- /dev/null
+++ b/kernel/sched_clock.c
@@ -0,0 +1,236 @@
+/*
+ * sched_clock for unstable cpu clocks
+ *
+ *  Copyright (C) 2008 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ *
+ * Based on code by:
+ *   Ingo Molnar <mingo@redhat.com>
+ *   Guillaume Chazarain <guichaz@gmail.com>
+ *
+ * Create a semi stable clock from a mixture of other events, including:
+ *  - gtod
+ *  - jiffies
+ *  - sched_clock()
+ *  - explicit idle events
+ *
+ * We use gtod as base and the unstable clock deltas. The deltas are filtered,
+ * making it monotonic and keeping it within an expected window.  This window
+ * is set up using jiffies.
+ *
+ * Furthermore, explicit sleep and wakeup hooks allow us to account for time
+ * that is otherwise invisible (TSC gets stopped).
+ *
+ * The clock: sched_clock_cpu() is monotonic per cpu, and should be somewhat
+ * consistent between cpus (never more than 1 jiffies difference).
+ */
+#include <linux/sched.h>
+#include <linux/percpu.h>
+#include <linux/spinlock.h>
+#include <linux/ktime.h>
+#include <linux/module.h>
+
+
+#ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
+
+struct sched_clock_data {
+        /*
+         * Raw spinlock - this is a special case: this might be called
+         * from within instrumentation code so we dont want to do any
+         * instrumentation ourselves.
+         */
+        raw_spinlock_t          lock;
+
+        unsigned long           prev_jiffies;
+        u64                     prev_raw;
+        u64                     tick_raw;
+        u64                     tick_gtod;
+        u64                     clock;
+};
+
+static DEFINE_PER_CPU_SHARED_ALIGNED(struct sched_clock_data, sched_clock_data);
+
+static inline struct sched_clock_data *this_scd(void)
+{
+        return &__get_cpu_var(sched_clock_data);
+}
+
+static inline struct sched_clock_data *cpu_sdc(int cpu)
+{
+        return &per_cpu(sched_clock_data, cpu);
+}
+
+void sched_clock_init(void)
+{
+        u64 ktime_now = ktime_to_ns(ktime_get());
+        u64 now = 0;
+        int cpu;
+
+        for_each_possible_cpu(cpu) {
+                struct sched_clock_data *scd = cpu_sdc(cpu);
+
+                scd->lock = (raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED;
+                scd->prev_jiffies = jiffies;
+                scd->prev_raw = now;
+                scd->tick_raw = now;
+                scd->tick_gtod = ktime_now;
+                scd->clock = ktime_now;
+        }
+}
+
+/*
+ * update the percpu scd from the raw @now value
+ *
+ *  - filter out backward motion
+ *  - use jiffies to generate a min,max window to clip the raw values
+ */
+static void __update_sched_clock(struct sched_clock_data *scd, u64 now)
+{
+        unsigned long now_jiffies = jiffies;
+        long delta_jiffies = now_jiffies - scd->prev_jiffies;
+        u64 clock = scd->clock;
+        u64 min_clock, max_clock;
+        s64 delta = now - scd->prev_raw;
+
+        WARN_ON_ONCE(!irqs_disabled());
+        min_clock = scd->tick_gtod + delta_jiffies * TICK_NSEC;
+
+        if (unlikely(delta < 0)) {
+                clock++;
+                goto out;
+        }
+
+        max_clock = min_clock + TICK_NSEC;
+
+        if (unlikely(clock + delta > max_clock)) {
+                if (clock < max_clock)
+                        clock = max_clock;
+                else
+                        clock++;
+        } else {
+                clock += delta;
+        }
+
+ out:
+        if (unlikely(clock < min_clock))
+                clock = min_clock;
+
+        scd->prev_raw = now;
+        scd->prev_jiffies = now_jiffies;
+        scd->clock = clock;
+}
+
+static void lock_double_clock(struct sched_clock_data *data1,
+                                struct sched_clock_data *data2)
+{
+        if (data1 < data2) {
+                __raw_spin_lock(&data1->lock);
+                __raw_spin_lock(&data2->lock);
+        } else {
+                __raw_spin_lock(&data2->lock);
+                __raw_spin_lock(&data1->lock);
+        }
+}
+
+u64 sched_clock_cpu(int cpu)
+{
+        struct sched_clock_data *scd = cpu_sdc(cpu);
+        u64 now, clock;
+
+        WARN_ON_ONCE(!irqs_disabled());
+        now = sched_clock();
+
+        if (cpu != raw_smp_processor_id()) {
+                /*
+                 * in order to update a remote cpu's clock based on our
+                 * unstable raw time rebase it against:
+                 *   tick_raw           (offset between raw counters)
+                 *   tick_gotd          (tick offset between cpus)
+                 */
+                struct sched_clock_data *my_scd = this_scd();
+
+                lock_double_clock(scd, my_scd);
+
+                now -= my_scd->tick_raw;
+                now += scd->tick_raw;
+
+                now -= my_scd->tick_gtod;
+                now += scd->tick_gtod;
+
+                __raw_spin_unlock(&my_scd->lock);
+        } else {
+                __raw_spin_lock(&scd->lock);
+        }
+
+        __update_sched_clock(scd, now);
+        clock = scd->clock;
+
+        __raw_spin_unlock(&scd->lock);
+
+        return clock;
+}
+
+void sched_clock_tick(void)
+{
+        struct sched_clock_data *scd = this_scd();
+        u64 now, now_gtod;
+
+        WARN_ON_ONCE(!irqs_disabled());
+
+        now = sched_clock();
+        now_gtod = ktime_to_ns(ktime_get());
+
+        __raw_spin_lock(&scd->lock);
+        __update_sched_clock(scd, now);
+        /*
+         * update tick_gtod after __update_sched_clock() because that will
+         * already observe 1 new jiffy; adding a new tick_gtod to that would
+         * increase the clock 2 jiffies.
+         */
+        scd->tick_raw = now;
+        scd->tick_gtod = now_gtod;
+        __raw_spin_unlock(&scd->lock);
+}
+
+/*
+ * We are going deep-idle (irqs are disabled):
+ */
+void sched_clock_idle_sleep_event(void)
+{
+        sched_clock_cpu(smp_processor_id());
+}
+EXPORT_SYMBOL_GPL(sched_clock_idle_sleep_event);
+
+/*
+ * We just idled delta nanoseconds (called with irqs disabled):
+ */
+void sched_clock_idle_wakeup_event(u64 delta_ns)
+{
+        struct sched_clock_data *scd = this_scd();
+        u64 now = sched_clock();
+
+        /*
+         * Override the previous timestamp and ignore all
+         * sched_clock() deltas that occured while we idled,
+         * and use the PM-provided delta_ns to advance the
+         * rq clock:
+         */
+        __raw_spin_lock(&scd->lock);
+        scd->prev_raw = now;
+        scd->clock += delta_ns;
+        __raw_spin_unlock(&scd->lock);
+
+        touch_softlockup_watchdog();
+}
+EXPORT_SYMBOL_GPL(sched_clock_idle_wakeup_event);
+
+#endif
+
+/*
+ * Scheduler clock - returns current time in nanosec units.
+ * This is default implementation.
+ * Architectures and sub-architectures can override this.
+ */
+unsigned long long __attribute__((weak)) sched_clock(void)
+{
+        return (unsigned long long)jiffies * (NSEC_PER_SEC / HZ);
+}
diff --git a/kernel/sched_debug.c b/kernel/sched_debug.c
index 6b4a12558e88..5f06118fbc31 100644
--- a/kernel/sched_debug.c
+++ b/kernel/sched_debug.c
@@ -204,13 +204,6 @@ static void print_cpu(struct seq_file *m, int cpu)
         PN(next_balance);
         P(curr->pid);
         PN(clock);
-        PN(idle_clock);
-        PN(prev_clock_raw);
-        P(clock_warps);
-        P(clock_overflows);
-        P(clock_underflows);
-        P(clock_deep_idle_events);
-        PN(clock_max_delta);
         P(cpu_load[0]);
         P(cpu_load[1]);
         P(cpu_load[2]);
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 89fa32b4edf2..e24ecd39c4b8 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -662,10 +662,15 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial)
         if (!initial) {
                 /* sleeps upto a single latency don't count. */
                 if (sched_feat(NEW_FAIR_SLEEPERS)) {
+                        unsigned long thresh = sysctl_sched_latency;
+
+                        /*
+                         * convert the sleeper threshold into virtual time
+                         */
                         if (sched_feat(NORMALIZED_SLEEPER))
-                                vruntime -= calc_delta_weight(sysctl_sched_latency, se);
-                        else
-                                vruntime -= sysctl_sched_latency;
+                                thresh = calc_delta_fair(thresh, se);
+
+                        vruntime -= thresh;
                 }
 
                 /* ensure we never gain time by being placed backwards. */
@@ -682,6 +687,7 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int wakeup)
          * Update run-time statistics of the 'current'.
          */
         update_curr(cfs_rq);
+        account_entity_enqueue(cfs_rq, se);
 
         if (wakeup) {
                 place_entity(cfs_rq, se, 0);
@@ -692,7 +698,6 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int wakeup)
         check_spread(cfs_rq, se);
         if (se != cfs_rq->curr)
                 __enqueue_entity(cfs_rq, se);
-        account_entity_enqueue(cfs_rq, se);
 }
 
 static void update_avg(u64 *avg, u64 sample)
@@ -841,8 +846,10 @@ entity_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr, int queued)
          * queued ticks are scheduled to match the slice, so don't bother
          * validating it and just reschedule.
          */
-        if (queued)
-                return resched_task(rq_of(cfs_rq)->curr);
+        if (queued) {
+                resched_task(rq_of(cfs_rq)->curr);
+                return;
+        }
         /*
          * don't let the period tick interfere with the hrtick preemption
          */
@@ -957,7 +964,7 @@ static void yield_task_fair(struct rq *rq)
                 return;
 
         if (likely(!sysctl_sched_compat_yield) && curr->policy != SCHED_BATCH) {
-                __update_rq_clock(rq);
+                update_rq_clock(rq);
                 /*
                  * Update run-time statistics of the 'current'.
                  */
@@ -1007,7 +1014,7 @@ static int wake_idle(int cpu, struct task_struct *p)
          * sibling runqueue info. This will avoid the checks and cache miss
          * penalities associated with that.
          */
-        if (idle_cpu(cpu) || cpu_rq(cpu)->nr_running > 1)
+        if (idle_cpu(cpu) || cpu_rq(cpu)->cfs.nr_running > 1)
                 return cpu;
 
         for_each_domain(cpu, sd) {
@@ -1611,30 +1618,6 @@ static const struct sched_class fair_sched_class = {
 };
 
 #ifdef CONFIG_SCHED_DEBUG
-static void
-print_cfs_rq_tasks(struct seq_file *m, struct cfs_rq *cfs_rq, int depth)
-{
-        struct sched_entity *se;
-
-        if (!cfs_rq)
-                return;
-
-        list_for_each_entry_rcu(se, &cfs_rq->tasks, group_node) {
-                int i;
-
-                for (i = depth; i; i--)
-                        seq_puts(m, "  ");
-
-                seq_printf(m, "%lu %s %lu\n",
-                                se->load.weight,
-                                entity_is_task(se) ? "T" : "G",
-                                calc_delta_weight(SCHED_LOAD_SCALE, se)
-                                );
-                if (!entity_is_task(se))
-                        print_cfs_rq_tasks(m, group_cfs_rq(se), depth + 1);
-        }
-}
-
 static void print_cfs_stats(struct seq_file *m, int cpu)
 {
         struct cfs_rq *cfs_rq;
@@ -1642,9 +1625,6 @@ static void print_cfs_stats(struct seq_file *m, int cpu)
         rcu_read_lock();
         for_each_leaf_cfs_rq(cpu_rq(cpu), cfs_rq)
                 print_cfs_rq(m, cpu, cfs_rq);
-
-        seq_printf(m, "\nWeight tree:\n");
-        print_cfs_rq_tasks(m, &cpu_rq(cpu)->cfs, 1);
         rcu_read_unlock();
 }
 #endif
diff --git a/kernel/sched_idletask.c b/kernel/sched_idletask.c
index 2bcafa375633..3a4f92dbbe66 100644
--- a/kernel/sched_idletask.c
+++ b/kernel/sched_idletask.c
@@ -99,7 +99,7 @@ static void prio_changed_idle(struct rq *rq, struct task_struct *p,
 /*
  * Simple, special scheduling class for the per-CPU idle tasks:
  */
-const struct sched_class idle_sched_class = {
+static const struct sched_class idle_sched_class = {
         /* .next is NULL */
         /* no enqueue/yield_task for idle tasks */
 
diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c
index c2730a5a4f05..060e87b0cb1c 100644
--- a/kernel/sched_rt.c
+++ b/kernel/sched_rt.c
@@ -1098,11 +1098,14 @@ static void post_schedule_rt(struct rq *rq)
         }
 }
 
-
+/*
+ * If we are not running and we are not going to reschedule soon, we should
+ * try to push tasks away now
+ */
 static void task_wake_up_rt(struct rq *rq, struct task_struct *p)
 {
         if (!task_running(rq, p) &&
-            (p->prio >= rq->rt.highest_prio) &&
+            !test_tsk_need_resched(rq->curr) &&
             rq->rt.overloaded)
                 push_rt_tasks(rq);
 }
@@ -1309,7 +1312,7 @@ static void set_curr_task_rt(struct rq *rq)
         p->se.exec_start = rq->clock;
 }
 
-const struct sched_class rt_sched_class = {
+static const struct sched_class rt_sched_class = {
         .next                   = &fair_sched_class,
         .enqueue_task           = enqueue_task_rt,
         .dequeue_task           = dequeue_task_rt,
diff --git a/kernel/semaphore.c b/kernel/semaphore.c
index 5c2942e768cd..5e41217239e8 100644
--- a/kernel/semaphore.c
+++ b/kernel/semaphore.c
@@ -54,10 +54,9 @@ void down(struct semaphore *sem)
         unsigned long flags;
 
         spin_lock_irqsave(&sem->lock, flags);
-        if (likely(sem->count > 0))
-                sem->count--;
-        else
+        if (unlikely(!sem->count))
                 __down(sem);
+        sem->count--;
         spin_unlock_irqrestore(&sem->lock, flags);
 }
 EXPORT_SYMBOL(down);
@@ -77,10 +76,10 @@ int down_interruptible(struct semaphore *sem)
         int result = 0;
 
         spin_lock_irqsave(&sem->lock, flags);
-        if (likely(sem->count > 0))
-                sem->count--;
-        else
+        if (unlikely(!sem->count))
                 result = __down_interruptible(sem);
+        if (!result)
+                sem->count--;
         spin_unlock_irqrestore(&sem->lock, flags);
 
         return result;
@@ -103,10 +102,10 @@ int down_killable(struct semaphore *sem)
         int result = 0;
 
         spin_lock_irqsave(&sem->lock, flags);
-        if (likely(sem->count > 0))
-                sem->count--;
-        else
+        if (unlikely(!sem->count))
                 result = __down_killable(sem);
+        if (!result)
+                sem->count--;
         spin_unlock_irqrestore(&sem->lock, flags);
 
         return result;
@@ -157,10 +156,10 @@ int down_timeout(struct semaphore *sem, long jiffies)
         int result = 0;
 
         spin_lock_irqsave(&sem->lock, flags);
-        if (likely(sem->count > 0))
-                sem->count--;
-        else
+        if (unlikely(!sem->count))
                 result = __down_timeout(sem, jiffies);
+        if (!result)
+                sem->count--;
         spin_unlock_irqrestore(&sem->lock, flags);
 
         return result;
@@ -179,9 +178,8 @@ void up(struct semaphore *sem)
         unsigned long flags;
 
         spin_lock_irqsave(&sem->lock, flags);
-        if (likely(list_empty(&sem->wait_list)))
-                sem->count++;
-        else
+        sem->count++;
+        if (unlikely(!list_empty(&sem->wait_list)))
                 __up(sem);
         spin_unlock_irqrestore(&sem->lock, flags);
 }
@@ -192,7 +190,6 @@ EXPORT_SYMBOL(up);
 struct semaphore_waiter {
         struct list_head list;
         struct task_struct *task;
-        int up;
 };
 
 /*
@@ -205,33 +202,34 @@ static inline int __sched __down_common(struct semaphore *sem, long state,
 {
         struct task_struct *task = current;
         struct semaphore_waiter waiter;
+        int ret = 0;
 
-        list_add_tail(&waiter.list, &sem->wait_list);
         waiter.task = task;
-        waiter.up = 0;
+        list_add_tail(&waiter.list, &sem->wait_list);
 
         for (;;) {
-                if (state == TASK_INTERRUPTIBLE && signal_pending(task))
-                        goto interrupted;
-                if (state == TASK_KILLABLE && fatal_signal_pending(task))
-                        goto interrupted;
-                if (timeout <= 0)
-                        goto timed_out;
+                if (state == TASK_INTERRUPTIBLE && signal_pending(task)) {
+                        ret = -EINTR;
+                        break;
+                }
+                if (state == TASK_KILLABLE && fatal_signal_pending(task)) {
+                        ret = -EINTR;
+                        break;
+                }
+                if (timeout <= 0) {
+                        ret = -ETIME;
+                        break;
+                }
                 __set_task_state(task, state);
                 spin_unlock_irq(&sem->lock);
                 timeout = schedule_timeout(timeout);
                 spin_lock_irq(&sem->lock);
-                if (waiter.up)
-                        return 0;
+                if (sem->count > 0)
+                        break;
         }
 
- timed_out:
-        list_del(&waiter.list);
-        return -ETIME;
-
- interrupted:
         list_del(&waiter.list);
-        return -EINTR;
+        return ret;
 }
 
 static noinline void __sched __down(struct semaphore *sem)
@@ -258,7 +256,5 @@ static noinline void __sched __up(struct semaphore *sem)
 {
         struct semaphore_waiter *waiter = list_first_entry(&sem->wait_list,
                                                 struct semaphore_waiter, list);
-        list_del(&waiter->list);
-        waiter->up = 1;
         wake_up_process(waiter->task);
 }
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index 73961f35fdc8..dadde5361f32 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -471,10 +471,10 @@ sysfs_show_available_clocksources(struct sys_device *dev, char *buf)
 /*
  * Sysfs setup bits:
  */
-static SYSDEV_ATTR(current_clocksource, 0600, sysfs_show_current_clocksources,
+static SYSDEV_ATTR(current_clocksource, 0644, sysfs_show_current_clocksources,
                    sysfs_override_clocksource);
 
-static SYSDEV_ATTR(available_clocksource, 0600,
+static SYSDEV_ATTR(available_clocksource, 0444,
                    sysfs_show_available_clocksources, NULL);
 
 static struct sysdev_class clocksource_sysclass = {