12 files changed, 129 insertions, 31 deletions

diff --git a/kernel/audit.c b/kernel/audit.c
index be55cb503633..b782b046543d 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -1269,8 +1269,8 @@ static void audit_log_n_string(struct audit_buffer *ab, size_t slen,
 
 /**
  * audit_string_contains_control - does a string need to be logged in hex
- * @string - string to be checked
- * @len - max length of the string to check
+ * @string: string to be checked
+ * @len: max length of the string to check
  */
 int audit_string_contains_control(const char *string, size_t len)
 {
@@ -1285,7 +1285,7 @@ int audit_string_contains_control(const char *string, size_t len)
 /**
  * audit_log_n_untrustedstring - log a string that may contain random characters
  * @ab: audit_buffer
- * @len: lenth of string (not including trailing null)
+ * @len: length of string (not including trailing null)
  * @string: string to be logged
  *
  * This code will escape a string that is passed to it if the string
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index e9c2fb01e89b..2727f9238359 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -782,7 +782,14 @@ static int parse_cgroupfs_options(char *data,
                 if (!*token)
                         return -EINVAL;
                 if (!strcmp(token, "all")) {
-                        opts->subsys_bits = (1 << CGROUP_SUBSYS_COUNT) - 1;
+                        /* Add all non-disabled subsystems */
+                        int i;
+                        opts->subsys_bits = 0;
+                        for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
+                                struct cgroup_subsys *ss = subsys[i];
+                                if (!ss->disabled)
+                                        opts->subsys_bits |= 1ul << i;
+                        }
                 } else if (!strcmp(token, "noprefix")) {
                         set_bit(ROOT_NOPREFIX, &opts->flags);
                 } else if (!strncmp(token, "release_agent=", 14)) {
@@ -800,7 +807,8 @@ static int parse_cgroupfs_options(char *data,
                         for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
                                 ss = subsys[i];
                                 if (!strcmp(token, ss->name)) {
-                                        set_bit(i, &opts->subsys_bits);
+                                        if (!ss->disabled)
+                                                set_bit(i, &opts->subsys_bits);
                                         break;
                                 }
                         }
@@ -2082,7 +2090,7 @@ static int cgroup_tasks_open(struct inode *unused, struct file *file)
 
                 kfree(pidarray);
         } else {
-                ctr->buf = 0;
+                ctr->buf = NULL;
                 ctr->bufsz = 0;
         }
         file->private_data = ctr;
@@ -2561,6 +2569,7 @@ static int proc_cgroup_show(struct seq_file *m, void *v)
                 /* Skip this hierarchy if it has no active subsystems */
                 if (!root->actual_subsys_bits)
                         continue;
+                seq_printf(m, "%lu:", root->subsys_bits);
                 for_each_subsys(root, ss)
                         seq_printf(m, "%s%s", count++ ? "," : "", ss->name);
                 seq_putc(m, ':');
@@ -2600,13 +2609,13 @@ static int proc_cgroupstats_show(struct seq_file *m, void *v)
 {
         int i;
 
-        seq_puts(m, "#subsys_name\thierarchy\tnum_cgroups\n");
+        seq_puts(m, "#subsys_name\thierarchy\tnum_cgroups\tenabled\n");
         mutex_lock(&cgroup_mutex);
         for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
                 struct cgroup_subsys *ss = subsys[i];
-                seq_printf(m, "%s\t%lu\t%d\n",
+                seq_printf(m, "%s\t%lu\t%d\t%d\n",
                            ss->name, ss->root->subsys_bits,
-                           ss->root->number_of_cgroups);
+                           ss->root->number_of_cgroups, !ss->disabled);
         }
         mutex_unlock(&cgroup_mutex);
         return 0;
@@ -2614,7 +2623,7 @@ static int proc_cgroupstats_show(struct seq_file *m, void *v)
 
 static int cgroupstats_open(struct inode *inode, struct file *file)
 {
-        return single_open(file, proc_cgroupstats_show, 0);
+        return single_open(file, proc_cgroupstats_show, NULL);
 }
 
 static struct file_operations proc_cgroupstats_operations = {
@@ -3010,3 +3019,27 @@ static void cgroup_release_agent(struct work_struct *work)
         spin_unlock(&release_list_lock);
         mutex_unlock(&cgroup_mutex);
 }
+
+static int __init cgroup_disable(char *str)
+{
+        int i;
+        char *token;
+
+        while ((token = strsep(&str, ",")) != NULL) {
+                if (!*token)
+                        continue;
+
+                for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
+                        struct cgroup_subsys *ss = subsys[i];
+
+                        if (!strcmp(token, ss->name)) {
+                                ss->disabled = 1;
+                                printk(KERN_INFO "Disabling %s control group"
+                                        " subsystem\n", ss->name);
+                                break;
+                        }
+                }
+        }
+        return 1;
+}
+__setup("cgroup_disable=", cgroup_disable);
diff --git a/kernel/exit.c b/kernel/exit.c
index 53872bf993fa..073005b1cfb2 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -1608,7 +1608,7 @@ asmlinkage long sys_waitid(int which, pid_t upid,
         put_pid(pid);
 
         /* avoid REGPARM breakage on x86: */
-        prevent_tail_call(ret);
+        asmlinkage_protect(5, ret, which, upid, infop, options, ru);
         return ret;
 }
 
@@ -1640,7 +1640,7 @@ asmlinkage long sys_wait4(pid_t upid, int __user *stat_addr,
         put_pid(pid);
 
         /* avoid REGPARM breakage on x86: */
-        prevent_tail_call(ret);
+        asmlinkage_protect(4, ret, upid, stat_addr, options, ru);
         return ret;
 }
 
diff --git a/kernel/fork.c b/kernel/fork.c
index dd249c37b3a3..9c042f901570 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -394,7 +394,6 @@ void __mmdrop(struct mm_struct *mm)
 {
         BUG_ON(mm == &init_mm);
         mm_free_pgd(mm);
-        mm_free_cgroup(mm);
         destroy_context(mm);
         free_mm(mm);
 }
@@ -416,6 +415,7 @@ void mmput(struct mm_struct *mm)
                         spin_unlock(&mmlist_lock);
                 }
                 put_swap_token(mm);
+                mm_free_cgroup(mm);
                 mmdrop(mm);
         }
 }
diff --git a/kernel/futex.c b/kernel/futex.c
index 06968cd79200..e43945e995f5 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -281,7 +281,7 @@ static int get_futex_key(u32 __user *uaddr, struct rw_semaphore *fshared,
  */
 static void get_futex_key_refs(union futex_key *key)
 {
-        if (key->both.ptr == 0)
+        if (key->both.ptr == NULL)
                 return;
         switch (key->both.offset & (FUT_OFF_INODE|FUT_OFF_MMSHARED)) {
                 case FUT_OFF_INODE:
@@ -2158,7 +2158,7 @@ static struct file_system_type futex_fs_type = {
         .kill_sb        = kill_anon_super,
 };
 
-static int __init init(void)
+static int __init futex_init(void)
 {
         u32 curval;
         int i;
@@ -2194,4 +2194,4 @@ static int __init init(void)
 
         return 0;
 }
-__initcall(init);
+__initcall(futex_init);
diff --git a/kernel/futex_compat.c b/kernel/futex_compat.c
index ff90f049f8f6..04ac3a9e42cf 100644
--- a/kernel/futex_compat.c
+++ b/kernel/futex_compat.c
@@ -30,7 +30,7 @@ fetch_robust_entry(compat_uptr_t *uentry, struct robust_list __user **entry,
         return 0;
 }
 
-static void __user *futex_uaddr(struct robust_list *entry,
+static void __user *futex_uaddr(struct robust_list __user *entry,
                                 compat_long_t futex_offset)
 {
         compat_uptr_t base = ptr_to_compat(entry);
diff --git a/kernel/marker.c b/kernel/marker.c
index 041c33e3e95c..005b95954593 100644
--- a/kernel/marker.c
+++ b/kernel/marker.c
@@ -671,6 +671,9 @@ int marker_probe_register(const char *name, const char *format,
         entry->rcu_pending = 1;
         /* write rcu_pending before calling the RCU callback */
         smp_wmb();
+#ifdef CONFIG_PREEMPT_RCU
+        synchronize_sched();    /* Until we have the call_rcu_sched() */
+#endif
         call_rcu(&entry->rcu, free_old_closure);
 end:
         mutex_unlock(&markers_mutex);
@@ -714,6 +717,9 @@ int marker_probe_unregister(const char *name,
         entry->rcu_pending = 1;
         /* write rcu_pending before calling the RCU callback */
         smp_wmb();
+#ifdef CONFIG_PREEMPT_RCU
+        synchronize_sched();    /* Until we have the call_rcu_sched() */
+#endif
         call_rcu(&entry->rcu, free_old_closure);
         remove_marker(name);    /* Ignore busy error message */
         ret = 0;
@@ -792,6 +798,9 @@ int marker_probe_unregister_private_data(marker_probe_func *probe,
         entry->rcu_pending = 1;
         /* write rcu_pending before calling the RCU callback */
         smp_wmb();
+#ifdef CONFIG_PREEMPT_RCU
+        synchronize_sched();    /* Until we have the call_rcu_sched() */
+#endif
         call_rcu(&entry->rcu, free_old_closure);
         remove_marker(entry->name);     /* Ignore busy error message */
 end:
diff --git a/kernel/relay.c b/kernel/relay.c
index 4c035a8a248c..d6204a485818 100644
--- a/kernel/relay.c
+++ b/kernel/relay.c
@@ -736,7 +736,7 @@ static int relay_file_open(struct inode *inode, struct file *filp)
         kref_get(&buf->kref);
         filp->private_data = buf;
 
-        return 0;
+        return nonseekable_open(inode, filp);
 }
 
 /**
@@ -1056,6 +1056,10 @@ static struct pipe_buf_operations relay_pipe_buf_ops = {
         .get = generic_pipe_buf_get,
 };
 
+static void relay_page_release(struct splice_pipe_desc *spd, unsigned int i)
+{
+}
+
 /*
  *      subbuf_splice_actor - splice up to one subbuf's worth of data
  */
@@ -1083,6 +1087,7 @@ static int subbuf_splice_actor(struct file *in,
                 .partial = partial,
                 .flags = flags,
                 .ops = &relay_pipe_buf_ops,
+                .spd_release = relay_page_release,
         };
 
         if (rbuf->subbufs_produced == rbuf->subbufs_consumed)
diff --git a/kernel/sched.c b/kernel/sched.c
index 28c73f07efb2..8dcdec6fe0fe 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -1052,6 +1052,49 @@ static void resched_cpu(int cpu)
         resched_task(cpu_curr(cpu));
         spin_unlock_irqrestore(&rq->lock, flags);
 }
+
+#ifdef CONFIG_NO_HZ
+/*
+ * When add_timer_on() enqueues a timer into the timer wheel of an
+ * idle CPU then this timer might expire before the next timer event
+ * which is scheduled to wake up that CPU. In case of a completely
+ * idle system the next event might even be infinite time into the
+ * future. wake_up_idle_cpu() ensures that the CPU is woken up and
+ * leaves the inner idle loop so the newly added timer is taken into
+ * account when the CPU goes back to idle and evaluates the timer
+ * wheel for the next timer event.
+ */
+void wake_up_idle_cpu(int cpu)
+{
+        struct rq *rq = cpu_rq(cpu);
+
+        if (cpu == smp_processor_id())
+                return;
+
+        /*
+         * This is safe, as this function is called with the timer
+         * wheel base lock of (cpu) held. When the CPU is on the way
+         * to idle and has not yet set rq->curr to idle then it will
+         * be serialized on the timer wheel base lock and take the new
+         * timer into account automatically.
+         */
+        if (rq->curr != rq->idle)
+                return;
+
+        /*
+         * We can set TIF_RESCHED on the idle task of the other CPU
+         * lockless. The worst case is that the other CPU runs the
+         * idle task through an additional NOOP schedule()
+         */
+        set_tsk_thread_flag(rq->idle, TIF_NEED_RESCHED);
+
+        /* NEED_RESCHED must be visible before we test polling */
+        smp_mb();
+        if (!tsk_is_polling(rq->idle))
+                smp_send_reschedule(cpu);
+}
+#endif
+
 #else
 static void __resched_task(struct task_struct *p, int tif_bit)
 {
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index 278534bbca95..7f60097d443a 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -174,7 +174,7 @@ static void clocksource_check_watchdog(struct clocksource *cs)
                         if (watchdog)
                                 del_timer(&watchdog_timer);
                         watchdog = cs;
-                        init_timer_deferrable(&watchdog_timer);
+                        init_timer(&watchdog_timer);
                         watchdog_timer.function = clocksource_watchdog;
 
                         /* Reset watchdog cycles */
diff --git a/kernel/timer.c b/kernel/timer.c
index 99b00a25f88b..b024106daa70 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -451,10 +451,18 @@ void add_timer_on(struct timer_list *timer, int cpu)
         spin_lock_irqsave(&base->lock, flags);
         timer_set_base(timer, base);
         internal_add_timer(base, timer);
+        /*
+         * Check whether the other CPU is idle and needs to be
+         * triggered to reevaluate the timer wheel when nohz is
+         * active. We are protected against the other CPU fiddling
+         * with the timer by holding the timer base lock. This also
+         * makes sure that a CPU on the way to idle can not evaluate
+         * the timer wheel.
+         */
+        wake_up_idle_cpu(cpu);
         spin_unlock_irqrestore(&base->lock, flags);
 }
 
-
 /**
  * mod_timer - modify a timer's timeout
  * @timer: the timer to be modified
diff --git a/kernel/uid16.c b/kernel/uid16.c
index dd308ba4e03b..3e41c1673e2f 100644
--- a/kernel/uid16.c
+++ b/kernel/uid16.c
@@ -21,7 +21,7 @@ asmlinkage long sys_chown16(const char __user * filename, old_uid_t user, old_gi
 {
         long ret = sys_chown(filename, low2highuid(user), low2highgid(group));
         /* avoid REGPARM breakage on x86: */
-        prevent_tail_call(ret);
+        asmlinkage_protect(3, ret, filename, user, group);
         return ret;
 }
 
@@ -29,7 +29,7 @@ asmlinkage long sys_lchown16(const char __user * filename, old_uid_t user, old_g
 {
         long ret = sys_lchown(filename, low2highuid(user), low2highgid(group));
         /* avoid REGPARM breakage on x86: */
-        prevent_tail_call(ret);
+        asmlinkage_protect(3, ret, filename, user, group);
         return ret;
 }
 
@@ -37,7 +37,7 @@ asmlinkage long sys_fchown16(unsigned int fd, old_uid_t user, old_gid_t group)
 {
         long ret = sys_fchown(fd, low2highuid(user), low2highgid(group));
         /* avoid REGPARM breakage on x86: */
-        prevent_tail_call(ret);
+        asmlinkage_protect(3, ret, fd, user, group);
         return ret;
 }
 
@@ -45,7 +45,7 @@ asmlinkage long sys_setregid16(old_gid_t rgid, old_gid_t egid)
 {
         long ret = sys_setregid(low2highgid(rgid), low2highgid(egid));
         /* avoid REGPARM breakage on x86: */
-        prevent_tail_call(ret);
+        asmlinkage_protect(2, ret, rgid, egid);
         return ret;
 }
 
@@ -53,7 +53,7 @@ asmlinkage long sys_setgid16(old_gid_t gid)
 {
         long ret = sys_setgid(low2highgid(gid));
         /* avoid REGPARM breakage on x86: */
-        prevent_tail_call(ret);
+        asmlinkage_protect(1, ret, gid);
         return ret;
 }
 
@@ -61,7 +61,7 @@ asmlinkage long sys_setreuid16(old_uid_t ruid, old_uid_t euid)
 {
         long ret = sys_setreuid(low2highuid(ruid), low2highuid(euid));
         /* avoid REGPARM breakage on x86: */
-        prevent_tail_call(ret);
+        asmlinkage_protect(2, ret, ruid, euid);
         return ret;
 }
 
@@ -69,7 +69,7 @@ asmlinkage long sys_setuid16(old_uid_t uid)
 {
         long ret = sys_setuid(low2highuid(uid));
         /* avoid REGPARM breakage on x86: */
-        prevent_tail_call(ret);
+        asmlinkage_protect(1, ret, uid);
         return ret;
 }
 
@@ -78,7 +78,7 @@ asmlinkage long sys_setresuid16(old_uid_t ruid, old_uid_t euid, old_uid_t suid)
         long ret = sys_setresuid(low2highuid(ruid), low2highuid(euid),
                                  low2highuid(suid));
         /* avoid REGPARM breakage on x86: */
-        prevent_tail_call(ret);
+        asmlinkage_protect(3, ret, ruid, euid, suid);
         return ret;
 }
 
@@ -98,7 +98,7 @@ asmlinkage long sys_setresgid16(old_gid_t rgid, old_gid_t egid, old_gid_t sgid)
         long ret = sys_setresgid(low2highgid(rgid), low2highgid(egid),
                                  low2highgid(sgid));
         /* avoid REGPARM breakage on x86: */
-        prevent_tail_call(ret);
+        asmlinkage_protect(3, ret, rgid, egid, sgid);
         return ret;
 }
 
@@ -117,7 +117,7 @@ asmlinkage long sys_setfsuid16(old_uid_t uid)
 {
         long ret = sys_setfsuid(low2highuid(uid));
         /* avoid REGPARM breakage on x86: */
-        prevent_tail_call(ret);
+        asmlinkage_protect(1, ret, uid);
         return ret;
 }
 
@@ -125,7 +125,7 @@ asmlinkage long sys_setfsgid16(old_gid_t gid)
 {
         long ret = sys_setfsgid(low2highgid(gid));
         /* avoid REGPARM breakage on x86: */
-        prevent_tail_call(ret);
+        asmlinkage_protect(1, ret, gid);
         return ret;
 }