Merge ../linux-2.6

25 files changed, 484 insertions, 215 deletions

diff --git a/kernel/audit.c b/kernel/audit.c
index d417ca1db79b..0a36091ed712 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -690,9 +690,7 @@ static const struct inotify_operations audit_inotify_ops = {
 /* Initialize audit support at boot time. */
 static int __init audit_init(void)
 {
-#ifdef CONFIG_AUDITSYSCALL
         int i;
-#endif
 
         printk(KERN_INFO "audit: initializing netlink socket (%s)\n",
                audit_default ? "enabled" : "disabled");
@@ -717,10 +715,10 @@ static int __init audit_init(void)
         audit_ih = inotify_init(&audit_inotify_ops);
         if (IS_ERR(audit_ih))
                 audit_panic("cannot initialize inotify handle");
+#endif
 
         for (i = 0; i < AUDIT_INODE_BUCKETS; i++)
                 INIT_LIST_HEAD(&audit_inode_hash[i]);
-#endif
 
         return 0;
 }
diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c
index 5b4e16276ca0..6a9a5c5a4e7d 100644
--- a/kernel/auditfilter.c
+++ b/kernel/auditfilter.c
@@ -442,6 +442,7 @@ static struct audit_entry *audit_rule_to_entry(struct audit_rule *rule)
                 case AUDIT_EQUAL:
                         break;
                 default:
+                        err = -EINVAL;
                         goto exit_free;
                 }
         }
@@ -579,6 +580,7 @@ static struct audit_entry *audit_data_to_entry(struct audit_rule_data *data,
                 case AUDIT_EQUAL:
                         break;
                 default:
+                        err = -EINVAL;
                         goto exit_free;
                 }
         }
@@ -1134,6 +1136,14 @@ static inline int audit_add_rule(struct audit_entry *entry,
         struct audit_watch *watch = entry->rule.watch;
         struct nameidata *ndp, *ndw;
         int h, err, putnd_needed = 0;
+#ifdef CONFIG_AUDITSYSCALL
+        int dont_count = 0;
+
+        /* If either of these, don't count towards total */
+        if (entry->rule.listnr == AUDIT_FILTER_USER ||
+                entry->rule.listnr == AUDIT_FILTER_TYPE)
+                dont_count = 1;
+#endif
 
         if (inode_f) {
                 h = audit_hash_ino(inode_f->val);
@@ -1174,6 +1184,10 @@ static inline int audit_add_rule(struct audit_entry *entry,
         } else {
                 list_add_tail_rcu(&entry->list, list);
         }
+#ifdef CONFIG_AUDITSYSCALL
+        if (!dont_count)
+                audit_n_rules++;
+#endif
         mutex_unlock(&audit_filter_mutex);
 
         if (putnd_needed)
@@ -1198,6 +1212,14 @@ static inline int audit_del_rule(struct audit_entry *entry,
         struct audit_watch *watch, *tmp_watch = entry->rule.watch;
         LIST_HEAD(inotify_list);
         int h, ret = 0;
+#ifdef CONFIG_AUDITSYSCALL
+        int dont_count = 0;
+
+        /* If either of these, don't count towards total */
+        if (entry->rule.listnr == AUDIT_FILTER_USER ||
+                entry->rule.listnr == AUDIT_FILTER_TYPE)
+                dont_count = 1;
+#endif
 
         if (inode_f) {
                 h = audit_hash_ino(inode_f->val);
@@ -1235,6 +1257,10 @@ static inline int audit_del_rule(struct audit_entry *entry,
         list_del_rcu(&e->list);
         call_rcu(&e->rcu, audit_free_rule_rcu);
 
+#ifdef CONFIG_AUDITSYSCALL
+        if (!dont_count)
+                audit_n_rules--;
+#endif
         mutex_unlock(&audit_filter_mutex);
 
         if (!list_empty(&inotify_list))
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index ae40ac8c39e7..efc1b74bebf3 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -85,6 +85,9 @@ extern int audit_enabled;
 /* Indicates that audit should log the full pathname. */
 #define AUDIT_NAME_FULL -1
 
+/* number of audit rules */
+int audit_n_rules;
+
 /* When fs/namei.c:getname() is called, we store the pointer in name and
  * we don't let putname() free it (instead we free all of the saved
  * pointers at syscall exit time).
@@ -174,6 +177,7 @@ struct audit_aux_data_path {
 
 /* The per-task audit context. */
 struct audit_context {
+        int                 dummy;      /* must be the first element */
         int                 in_syscall; /* 1 if task is in a syscall */
         enum audit_state    state;
         unsigned int        serial;     /* serial number for record */
@@ -514,7 +518,7 @@ static inline struct audit_context *audit_get_context(struct task_struct *tsk,
         context->return_valid = return_valid;
         context->return_code  = return_code;
 
-        if (context->in_syscall && !context->auditable) {
+        if (context->in_syscall && !context->dummy && !context->auditable) {
                 enum audit_state state;
 
                 state = audit_filter_syscall(tsk, context, &audit_filter_list[AUDIT_FILTER_EXIT]);
@@ -530,17 +534,7 @@ static inline struct audit_context *audit_get_context(struct task_struct *tsk,
         }
 
 get_context:
-        context->pid = tsk->pid;
-        context->ppid = sys_getppid();  /* sic.  tsk == current in all cases */
-        context->uid = tsk->uid;
-        context->gid = tsk->gid;
-        context->euid = tsk->euid;
-        context->suid = tsk->suid;
-        context->fsuid = tsk->fsuid;
-        context->egid = tsk->egid;
-        context->sgid = tsk->sgid;
-        context->fsgid = tsk->fsgid;
-        context->personality = tsk->personality;
+
         tsk->audit_context = NULL;
         return context;
 }
@@ -749,6 +743,17 @@ static void audit_log_exit(struct audit_context *context, struct task_struct *ts
         const char *tty;
 
         /* tsk == current */
+        context->pid = tsk->pid;
+        context->ppid = sys_getppid();  /* sic.  tsk == current in all cases */
+        context->uid = tsk->uid;
+        context->gid = tsk->gid;
+        context->euid = tsk->euid;
+        context->suid = tsk->suid;
+        context->fsuid = tsk->fsuid;
+        context->egid = tsk->egid;
+        context->sgid = tsk->sgid;
+        context->fsgid = tsk->fsgid;
+        context->personality = tsk->personality;
 
         ab = audit_log_start(context, GFP_KERNEL, AUDIT_SYSCALL);
         if (!ab)
@@ -1066,7 +1071,8 @@ void audit_syscall_entry(int arch, int major,
         context->argv[3]    = a4;
 
         state = context->state;
-        if (state == AUDIT_SETUP_CONTEXT || state == AUDIT_BUILD_CONTEXT)
+        context->dummy = !audit_n_rules;
+        if (!context->dummy && (state == AUDIT_SETUP_CONTEXT || state == AUDIT_BUILD_CONTEXT))
                 state = audit_filter_syscall(tsk, context, &audit_filter_list[AUDIT_FILTER_ENTRY]);
         if (likely(state == AUDIT_DISABLED))
                 return;
@@ -1199,14 +1205,18 @@ void audit_putname(const char *name)
 #endif
 }
 
-static void audit_inode_context(int idx, const struct inode *inode)
+/* Copy inode data into an audit_names. */
+static void audit_copy_inode(struct audit_names *name, const struct inode *inode)
 {
-        struct audit_context *context = current->audit_context;
-
-        selinux_get_inode_sid(inode, &context->names[idx].osid);
+        name->ino   = inode->i_ino;
+        name->dev   = inode->i_sb->s_dev;
+        name->mode  = inode->i_mode;
+        name->uid   = inode->i_uid;
+        name->gid   = inode->i_gid;
+        name->rdev  = inode->i_rdev;
+        selinux_get_inode_sid(inode, &name->osid);
 }
 
-
 /**
  * audit_inode - store the inode and device from a lookup
  * @name: name being audited
@@ -1240,20 +1250,14 @@ void __audit_inode(const char *name, const struct inode *inode)
                 ++context->ino_count;
 #endif
         }
-        context->names[idx].ino   = inode->i_ino;
-        context->names[idx].dev   = inode->i_sb->s_dev;
-        context->names[idx].mode  = inode->i_mode;
-        context->names[idx].uid   = inode->i_uid;
-        context->names[idx].gid   = inode->i_gid;
-        context->names[idx].rdev  = inode->i_rdev;
-        audit_inode_context(idx, inode);
+        audit_copy_inode(&context->names[idx], inode);
 }
 
 /**
  * audit_inode_child - collect inode info for created/removed objects
  * @dname: inode's dentry name
  * @inode: inode being audited
- * @pino: inode number of dentry parent
+ * @parent: inode of dentry parent
  *
  * For syscalls that create or remove filesystem objects, audit_inode
  * can only collect information for the filesystem object's parent.
@@ -1264,7 +1268,7 @@ void __audit_inode(const char *name, const struct inode *inode)
  * unsuccessful attempts.
  */
 void __audit_inode_child(const char *dname, const struct inode *inode,
-                         unsigned long pino)
+                         const struct inode *parent)
 {
         int idx;
         struct audit_context *context = current->audit_context;
@@ -1278,7 +1282,7 @@ void __audit_inode_child(const char *dname, const struct inode *inode,
         if (!dname)
                 goto update_context;
         for (idx = 0; idx < context->name_count; idx++)
-                if (context->names[idx].ino == pino) {
+                if (context->names[idx].ino == parent->i_ino) {
                         const char *name = context->names[idx].name;
 
                         if (!name)
@@ -1302,16 +1306,47 @@ update_context:
         context->names[idx].name_len = AUDIT_NAME_FULL;
         context->names[idx].name_put = 0;       /* don't call __putname() */
 
-        if (inode) {
-                context->names[idx].ino   = inode->i_ino;
-                context->names[idx].dev   = inode->i_sb->s_dev;
-                context->names[idx].mode  = inode->i_mode;
-                context->names[idx].uid   = inode->i_uid;
-                context->names[idx].gid   = inode->i_gid;
-                context->names[idx].rdev  = inode->i_rdev;
-                audit_inode_context(idx, inode);
-        } else
-                context->names[idx].ino   = (unsigned long)-1;
+        if (!inode)
+                context->names[idx].ino = (unsigned long)-1;
+        else
+                audit_copy_inode(&context->names[idx], inode);
+
+        /* A parent was not found in audit_names, so copy the inode data for the
+         * provided parent. */
+        if (!found_name) {
+                idx = context->name_count++;
+#if AUDIT_DEBUG
+                context->ino_count++;
+#endif
+                audit_copy_inode(&context->names[idx], parent);
+        }
+}
+
+/**
+ * audit_inode_update - update inode info for last collected name
+ * @inode: inode being audited
+ *
+ * When open() is called on an existing object with the O_CREAT flag, the inode
+ * data audit initially collects is incorrect.  This additional hook ensures
+ * audit has the inode data for the actual object to be opened.
+ */
+void __audit_inode_update(const struct inode *inode)
+{
+        struct audit_context *context = current->audit_context;
+        int idx;
+
+        if (!context->in_syscall || !inode)
+                return;
+
+        if (context->name_count == 0) {
+                context->name_count++;
+#if AUDIT_DEBUG
+                context->ino_count++;
+#endif
+        }
+        idx = context->name_count - 1;
+
+        audit_copy_inode(&context->names[idx], inode);
 }
 
 /**
@@ -1642,7 +1677,7 @@ int audit_bprm(struct linux_binprm *bprm)
         unsigned long p, next;
         void *to;
 
-        if (likely(!audit_enabled || !context))
+        if (likely(!audit_enabled || !context || context->dummy))
                 return 0;
 
         ax = kmalloc(sizeof(*ax) + PAGE_SIZE * MAX_ARG_PAGES - bprm->p,
@@ -1680,7 +1715,7 @@ int audit_socketcall(int nargs, unsigned long *args)
         struct audit_aux_data_socketcall *ax;
         struct audit_context *context = current->audit_context;
 
-        if (likely(!context))
+        if (likely(!context || context->dummy))
                 return 0;
 
         ax = kmalloc(sizeof(*ax) + nargs * sizeof(unsigned long), GFP_KERNEL);
@@ -1708,7 +1743,7 @@ int audit_sockaddr(int len, void *a)
         struct audit_aux_data_sockaddr *ax;
         struct audit_context *context = current->audit_context;
 
-        if (likely(!context))
+        if (likely(!context || context->dummy))
                 return 0;
 
         ax = kmalloc(sizeof(*ax) + len, GFP_KERNEL);
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 1a649f2bb9bb..4ea6f0dc2fc5 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -816,6 +816,10 @@ static int update_cpumask(struct cpuset *cs, char *buf)
         struct cpuset trialcs;
         int retval, cpus_unchanged;
 
+        /* top_cpuset.cpus_allowed tracks cpu_online_map; it's read-only */
+        if (cs == &top_cpuset)
+                return -EACCES;
+
         trialcs = *cs;
         retval = cpulist_parse(buf, trialcs.cpus_allowed);
         if (retval < 0)
@@ -2033,6 +2037,33 @@ out:
         return err;
 }
 
+/*
+ * The top_cpuset tracks what CPUs and Memory Nodes are online,
+ * period.  This is necessary in order to make cpusets transparent
+ * (of no affect) on systems that are actively using CPU hotplug
+ * but making no active use of cpusets.
+ *
+ * This handles CPU hotplug (cpuhp) events.  If someday Memory
+ * Nodes can be hotplugged (dynamically changing node_online_map)
+ * then we should handle that too, perhaps in a similar way.
+ */
+
+#ifdef CONFIG_HOTPLUG_CPU
+static int cpuset_handle_cpuhp(struct notifier_block *nb,
+                                unsigned long phase, void *cpu)
+{
+        mutex_lock(&manage_mutex);
+        mutex_lock(&callback_mutex);
+
+        top_cpuset.cpus_allowed = cpu_online_map;
+
+        mutex_unlock(&callback_mutex);
+        mutex_unlock(&manage_mutex);
+
+        return 0;
+}
+#endif
+
 /**
  * cpuset_init_smp - initialize cpus_allowed
  *
@@ -2043,6 +2074,8 @@ void __init cpuset_init_smp(void)
 {
         top_cpuset.cpus_allowed = cpu_online_map;
         top_cpuset.mems_allowed = node_online_map;
+
+        hotcpu_notifier(cpuset_handle_cpuhp, 0);
 }
 
 /**
@@ -2387,7 +2420,7 @@ EXPORT_SYMBOL_GPL(cpuset_mem_spread_node);
 int cpuset_excl_nodes_overlap(const struct task_struct *p)
 {
         const struct cpuset *cs1, *cs2; /* my and p's cpuset ancestors */
-        int overlap = 0;                /* do cpusets overlap? */
+        int overlap = 1;                /* do cpusets overlap? */
 
         task_lock(current);
         if (current->flags & PF_EXITING) {
diff --git a/kernel/delayacct.c b/kernel/delayacct.c
index f05392d64267..57ca3730205d 100644
--- a/kernel/delayacct.c
+++ b/kernel/delayacct.c
@@ -19,15 +19,15 @@
 #include <linux/sysctl.h>
 #include <linux/delayacct.h>
 
-int delayacct_on __read_mostly; /* Delay accounting turned on/off */
+int delayacct_on __read_mostly = 1;     /* Delay accounting turned on/off */
 kmem_cache_t *delayacct_cache;
 
-static int __init delayacct_setup_enable(char *str)
+static int __init delayacct_setup_disable(char *str)
 {
-        delayacct_on = 1;
+        delayacct_on = 0;
         return 1;
 }
-__setup("delayacct", delayacct_setup_enable);
+__setup("nodelayacct", delayacct_setup_disable);
 
 void delayacct_init(void)
 {
diff --git a/kernel/fork.c b/kernel/fork.c
index 1b0f7b1e0881..aa36c43783cc 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1387,8 +1387,10 @@ long do_fork(unsigned long clone_flags,
 
                 if (clone_flags & CLONE_VFORK) {
                         wait_for_completion(&vfork);
-                        if (unlikely (current->ptrace & PT_TRACE_VFORK_DONE))
+                        if (unlikely (current->ptrace & PT_TRACE_VFORK_DONE)) {
+                                current->ptrace_message = nr;
                                 ptrace_notify ((PTRACE_EVENT_VFORK_DONE << 8) | SIGTRAP);
+                        }
                 }
         } else {
                 free_pid(pid);
diff --git a/kernel/futex.c b/kernel/futex.c
index cf0c8e21d1ab..b9b8aea5389e 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -297,7 +297,7 @@ static int futex_handle_fault(unsigned long address, int attempt)
         struct vm_area_struct * vma;
         struct mm_struct *mm = current->mm;
 
-        if (attempt >= 2 || !(vma = find_vma(mm, address)) ||
+        if (attempt > 2 || !(vma = find_vma(mm, address)) ||
             vma->vm_start > address || !(vma->vm_flags & VM_WRITE))
                 return -EFAULT;
 
@@ -397,7 +397,7 @@ static struct task_struct * futex_find_get_task(pid_t pid)
                 p = NULL;
                 goto out_unlock;
         }
-        if (p->state == EXIT_ZOMBIE || p->exit_state == EXIT_ZOMBIE) {
+        if (p->exit_state != 0) {
                 p = NULL;
                 goto out_unlock;
         }
@@ -415,15 +415,15 @@ out_unlock:
  */
 void exit_pi_state_list(struct task_struct *curr)
 {
-        struct futex_hash_bucket *hb;
         struct list_head *next, *head = &curr->pi_state_list;
         struct futex_pi_state *pi_state;
+        struct futex_hash_bucket *hb;
         union futex_key key;
 
         /*
          * We are a ZOMBIE and nobody can enqueue itself on
          * pi_state_list anymore, but we have to be careful
-         * versus waiters unqueueing themselfs
+         * versus waiters unqueueing themselves:
          */
         spin_lock_irq(&curr->pi_lock);
         while (!list_empty(head)) {
@@ -431,21 +431,24 @@ void exit_pi_state_list(struct task_struct *curr)
                 next = head->next;
                 pi_state = list_entry(next, struct futex_pi_state, list);
                 key = pi_state->key;
+                hb = hash_futex(&key);
                 spin_unlock_irq(&curr->pi_lock);
 
-                hb = hash_futex(&key);
                 spin_lock(&hb->lock);
 
                 spin_lock_irq(&curr->pi_lock);
+                /*
+                 * We dropped the pi-lock, so re-check whether this
+                 * task still owns the PI-state:
+                 */
                 if (head->next != next) {
                         spin_unlock(&hb->lock);
                         continue;
                 }
 
-                list_del_init(&pi_state->list);
-
                 WARN_ON(pi_state->owner != curr);
-
+                WARN_ON(list_empty(&pi_state->list));
+                list_del_init(&pi_state->list);
                 pi_state->owner = NULL;
                 spin_unlock_irq(&curr->pi_lock);
 
@@ -470,7 +473,7 @@ lookup_pi_state(u32 uval, struct futex_hash_bucket *hb, struct futex_q *me)
         head = &hb->chain;
 
         list_for_each_entry_safe(this, next, head, list) {
-                if (match_futex (&this->key, &me->key)) {
+                if (match_futex(&this->key, &me->key)) {
                         /*
                          * Another waiter already exists - bump up
                          * the refcount and return its pi_state:
@@ -482,6 +485,8 @@ lookup_pi_state(u32 uval, struct futex_hash_bucket *hb, struct futex_q *me)
                         if (unlikely(!pi_state))
                                 return -EINVAL;
 
+                        WARN_ON(!atomic_read(&pi_state->refcount));
+
                         atomic_inc(&pi_state->refcount);
                         me->pi_state = pi_state;
 
@@ -490,10 +495,13 @@ lookup_pi_state(u32 uval, struct futex_hash_bucket *hb, struct futex_q *me)
         }
 
         /*
-         * We are the first waiter - try to look up the real owner and
-         * attach the new pi_state to it:
+         * We are the first waiter - try to look up the real owner and attach
+         * the new pi_state to it, but bail out when the owner died bit is set
+         * and TID = 0:
          */
         pid = uval & FUTEX_TID_MASK;
+        if (!pid && (uval & FUTEX_OWNER_DIED))
+                return -ESRCH;
         p = futex_find_get_task(pid);
         if (!p)
                 return -ESRCH;
@@ -510,6 +518,7 @@ lookup_pi_state(u32 uval, struct futex_hash_bucket *hb, struct futex_q *me)
         pi_state->key = me->key;
 
         spin_lock_irq(&p->pi_lock);
+        WARN_ON(!list_empty(&pi_state->list));
         list_add(&pi_state->list, &p->pi_state_list);
         pi_state->owner = p;
         spin_unlock_irq(&p->pi_lock);
@@ -573,20 +582,29 @@ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_q *this)
          * kept enabled while there is PI state around. We must also
          * preserve the owner died bit.)
          */
-        newval = (uval & FUTEX_OWNER_DIED) | FUTEX_WAITERS | new_owner->pid;
+        if (!(uval & FUTEX_OWNER_DIED)) {
+                newval = FUTEX_WAITERS | new_owner->pid;
 
-        inc_preempt_count();
-        curval = futex_atomic_cmpxchg_inatomic(uaddr, uval, newval);
-        dec_preempt_count();
+                inc_preempt_count();
+                curval = futex_atomic_cmpxchg_inatomic(uaddr, uval, newval);
+                dec_preempt_count();
+                if (curval == -EFAULT)
+                        return -EFAULT;
+                if (curval != uval)
+                        return -EINVAL;
+        }
 
-        if (curval == -EFAULT)
-                return -EFAULT;
-        if (curval != uval)
-                return -EINVAL;
+        spin_lock_irq(&pi_state->owner->pi_lock);
+        WARN_ON(list_empty(&pi_state->list));
+        list_del_init(&pi_state->list);
+        spin_unlock_irq(&pi_state->owner->pi_lock);
 
-        list_del_init(&pi_state->owner->pi_state_list);
+        spin_lock_irq(&new_owner->pi_lock);
+        WARN_ON(!list_empty(&pi_state->list));
         list_add(&pi_state->list, &new_owner->pi_state_list);
         pi_state->owner = new_owner;
+        spin_unlock_irq(&new_owner->pi_lock);
+
         rt_mutex_unlock(&pi_state->pi_mutex);
 
         return 0;
@@ -729,8 +747,10 @@ retry:
                  */
                 if (attempt++) {
                         if (futex_handle_fault((unsigned long)uaddr2,
-                                               attempt))
+                                                attempt)) {
+                                ret = -EFAULT;
                                 goto out;
+                        }
                         goto retry;
                 }
 
@@ -930,6 +950,7 @@ static int unqueue_me(struct futex_q *q)
         /* In the common case we don't take the spinlock, which is nice. */
  retry:
         lock_ptr = q->lock_ptr;
+        barrier();
         if (lock_ptr != 0) {
                 spin_lock(lock_ptr);
                 /*
@@ -1236,6 +1257,7 @@ static int do_futex_lock_pi(u32 __user *uaddr, int detect, int trylock,
                 /* Owner died? */
                 if (q.pi_state->owner != NULL) {
                         spin_lock_irq(&q.pi_state->owner->pi_lock);
+                        WARN_ON(list_empty(&q.pi_state->list));
                         list_del_init(&q.pi_state->list);
                         spin_unlock_irq(&q.pi_state->owner->pi_lock);
                 } else
@@ -1244,6 +1266,7 @@ static int do_futex_lock_pi(u32 __user *uaddr, int detect, int trylock,
                 q.pi_state->owner = current;
 
                 spin_lock_irq(&current->pi_lock);
+                WARN_ON(!list_empty(&q.pi_state->list));
                 list_add(&q.pi_state->list, &current->pi_state_list);
                 spin_unlock_irq(&current->pi_lock);
 
@@ -1301,9 +1324,10 @@ static int do_futex_lock_pi(u32 __user *uaddr, int detect, int trylock,
          * still holding the mmap_sem.
          */
         if (attempt++) {
-                if (futex_handle_fault((unsigned long)uaddr, attempt))
+                if (futex_handle_fault((unsigned long)uaddr, attempt)) {
+                        ret = -EFAULT;
                         goto out_unlock_release_sem;
-
+                }
                 goto retry_locked;
         }
 
@@ -1427,9 +1451,11 @@ retry_locked:
          * again. If it succeeds then we can return without waking
          * anyone else up:
          */
-        inc_preempt_count();
-        uval = futex_atomic_cmpxchg_inatomic(uaddr, current->pid, 0);
-        dec_preempt_count();
+        if (!(uval & FUTEX_OWNER_DIED)) {
+                inc_preempt_count();
+                uval = futex_atomic_cmpxchg_inatomic(uaddr, current->pid, 0);
+                dec_preempt_count();
+        }
 
         if (unlikely(uval == -EFAULT))
                 goto pi_faulted;
@@ -1462,9 +1488,11 @@ retry_locked:
         /*
          * No waiters - kernel unlocks the futex:
          */
-        ret = unlock_futex_pi(uaddr, uval);
-        if (ret == -EFAULT)
-                goto pi_faulted;
+        if (!(uval & FUTEX_OWNER_DIED)) {
+                ret = unlock_futex_pi(uaddr, uval);
+                if (ret == -EFAULT)
+                        goto pi_faulted;
+        }
 
 out_unlock:
         spin_unlock(&hb->lock);
@@ -1481,9 +1509,10 @@ pi_faulted:
          * still holding the mmap_sem.
          */
         if (attempt++) {
-                if (futex_handle_fault((unsigned long)uaddr, attempt))
+                if (futex_handle_fault((unsigned long)uaddr, attempt)) {
+                        ret = -EFAULT;
                         goto out_unlock;
-
+                }
                 goto retry_locked;
         }
 
@@ -1683,9 +1712,9 @@ err_unlock:
  * Process a futex-list entry, check whether it's owned by the
  * dying task, and do notification if so:
  */
-int handle_futex_death(u32 __user *uaddr, struct task_struct *curr)
+int handle_futex_death(u32 __user *uaddr, struct task_struct *curr, int pi)
 {
-        u32 uval, nval;
+        u32 uval, nval, mval;
 
 retry:
         if (get_user(uval, uaddr))
@@ -1702,21 +1731,45 @@ retry:
                  * thread-death.) The rest of the cleanup is done in
                  * userspace.
                  */
-                nval = futex_atomic_cmpxchg_inatomic(uaddr, uval,
-                                                     uval | FUTEX_OWNER_DIED);
+                mval = (uval & FUTEX_WAITERS) | FUTEX_OWNER_DIED;
+                nval = futex_atomic_cmpxchg_inatomic(uaddr, uval, mval);
+
                 if (nval == -EFAULT)
                         return -1;
 
                 if (nval != uval)
                         goto retry;
 
-                if (uval & FUTEX_WAITERS)
-                        futex_wake(uaddr, 1);
+                /*
+                 * Wake robust non-PI futexes here. The wakeup of
+                 * PI futexes happens in exit_pi_state():
+                 */
+                if (!pi) {
+                        if (uval & FUTEX_WAITERS)
+                                futex_wake(uaddr, 1);
+                }
         }
         return 0;
 }
 
 /*
+ * Fetch a robust-list pointer. Bit 0 signals PI futexes:
+ */
+static inline int fetch_robust_entry(struct robust_list __user **entry,
+                                     struct robust_list __user **head, int *pi)
+{
+        unsigned long uentry;
+
+        if (get_user(uentry, (unsigned long *)head))
+                return -EFAULT;
+
+        *entry = (void *)(uentry & ~1UL);
+        *pi = uentry & 1;
+
+        return 0;
+}
+
+/*
  * Walk curr->robust_list (very carefully, it's a userspace list!)
  * and mark any locks found there dead, and notify any waiters.
  *
@@ -1726,14 +1779,14 @@ void exit_robust_list(struct task_struct *curr)
 {
         struct robust_list_head __user *head = curr->robust_list;
         struct robust_list __user *entry, *pending;
-        unsigned int limit = ROBUST_LIST_LIMIT;
+        unsigned int limit = ROBUST_LIST_LIMIT, pi, pip;
         unsigned long futex_offset;
 
         /*
          * Fetch the list head (which was registered earlier, via
          * sys_set_robust_list()):
          */
-        if (get_user(entry, &head->list.next))
+        if (fetch_robust_entry(&entry, &head->list.next, &pi))
                 return;
         /*
          * Fetch the relative futex offset:
@@ -1744,10 +1797,11 @@ void exit_robust_list(struct task_struct *curr)
          * Fetch any possibly pending lock-add first, and handle it
          * if it exists:
          */
-        if (get_user(pending, &head->list_op_pending))
+        if (fetch_robust_entry(&pending, &head->list_op_pending, &pip))
                 return;
+
         if (pending)
-                handle_futex_death((void *)pending + futex_offset, curr);
+                handle_futex_death((void *)pending + futex_offset, curr, pip);
 
         while (entry != &head->list) {
                 /*
@@ -1756,12 +1810,12 @@ void exit_robust_list(struct task_struct *curr)
                  */
                 if (entry != pending)
                         if (handle_futex_death((void *)entry + futex_offset,
-                                                curr))
+                                                curr, pi))
                                 return;
                 /*
                  * Fetch the next entry in the list:
                  */
-                if (get_user(entry, &entry->next))
+                if (fetch_robust_entry(&entry, &entry->next, &pi))
                         return;
                 /*
                  * Avoid excessively long or circular lists:
diff --git a/kernel/futex_compat.c b/kernel/futex_compat.c
index d1d92b441fb7..c5cca3f65cb7 100644
--- a/kernel/futex_compat.c
+++ b/kernel/futex_compat.c
@@ -12,6 +12,23 @@
 
 #include <asm/uaccess.h>
 
+
+/*
+ * Fetch a robust-list pointer. Bit 0 signals PI futexes:
+ */
+static inline int
+fetch_robust_entry(compat_uptr_t *uentry, struct robust_list __user **entry,
+                   compat_uptr_t *head, int *pi)
+{
+        if (get_user(*uentry, head))
+                return -EFAULT;
+
+        *entry = compat_ptr((*uentry) & ~1);
+        *pi = (unsigned int)(*uentry) & 1;
+
+        return 0;
+}
+
 /*
  * Walk curr->robust_list (very carefully, it's a userspace list!)
  * and mark any locks found there dead, and notify any waiters.
@@ -22,17 +39,16 @@ void compat_exit_robust_list(struct task_struct *curr)
 {
         struct compat_robust_list_head __user *head = curr->compat_robust_list;
         struct robust_list __user *entry, *pending;
+        unsigned int limit = ROBUST_LIST_LIMIT, pi, pip;
         compat_uptr_t uentry, upending;
-        unsigned int limit = ROBUST_LIST_LIMIT;
         compat_long_t futex_offset;
 
         /*
          * Fetch the list head (which was registered earlier, via
          * sys_set_robust_list()):
          */
-        if (get_user(uentry, &head->list.next))
+        if (fetch_robust_entry(&uentry, &entry, &head->list.next, &pi))
                 return;
-        entry = compat_ptr(uentry);
         /*
          * Fetch the relative futex offset:
          */
@@ -42,11 +58,11 @@ void compat_exit_robust_list(struct task_struct *curr)
          * Fetch any possibly pending lock-add first, and handle it
          * if it exists:
          */
-        if (get_user(upending, &head->list_op_pending))
+        if (fetch_robust_entry(&upending, &pending,
+                               &head->list_op_pending, &pip))
                 return;
-        pending = compat_ptr(upending);
         if (upending)
-                handle_futex_death((void *)pending + futex_offset, curr);
+                handle_futex_death((void *)pending + futex_offset, curr, pip);
 
         while (compat_ptr(uentry) != &head->list) {
                 /*
@@ -55,15 +71,15 @@ void compat_exit_robust_list(struct task_struct *curr)
                  */
                 if (entry != pending)
                         if (handle_futex_death((void *)entry + futex_offset,
-                                                curr))
+                                                curr, pi))
                                 return;
 
                 /*
                  * Fetch the next entry in the list:
                  */
-                if (get_user(uentry, (compat_uptr_t *)&entry->next))
+                if (fetch_robust_entry(&uentry, &entry,
+                                       (compat_uptr_t *)&entry->next, &pi))
                         return;
-                entry = compat_ptr(uentry);
                 /*
                  * Avoid excessively long or circular lists:
                  */
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index d17766d40dab..21c38a7e666b 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -187,7 +187,7 @@ switch_hrtimer_base(struct hrtimer *timer, struct hrtimer_base *base)
 {
         struct hrtimer_base *new_base;
 
-        new_base = &__get_cpu_var(hrtimer_bases[base->index]);
+        new_base = &__get_cpu_var(hrtimer_bases)[base->index];
 
         if (base != new_base) {
                 /*
@@ -835,7 +835,7 @@ static void migrate_hrtimers(int cpu)
 }
 #endif /* CONFIG_HOTPLUG_CPU */
 
-static int __devinit hrtimer_cpu_notify(struct notifier_block *self,
+static int __cpuinit hrtimer_cpu_notify(struct notifier_block *self,
                                         unsigned long action, void *hcpu)
 {
         long cpu = (long)hcpu;
@@ -859,7 +859,7 @@ static int __devinit hrtimer_cpu_notify(struct notifier_block *self,
         return NOTIFY_OK;
 }
 
-static struct notifier_block __devinitdata hrtimers_nb = {
+static struct notifier_block __cpuinitdata hrtimers_nb = {
         .notifier_call = hrtimer_cpu_notify,
 };
 
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 4e461438e48b..92be519eff26 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -137,16 +137,40 @@ EXPORT_SYMBOL(enable_irq);
  *      @irq:   interrupt to control
  *      @on:    enable/disable power management wakeup
  *
- *      Enable/disable power management wakeup mode
+ *      Enable/disable power management wakeup mode, which is
+ *      disabled by default.  Enables and disables must match,
+ *      just as they match for non-wakeup mode support.
+ *
+ *      Wakeup mode lets this IRQ wake the system from sleep
+ *      states like "suspend to RAM".
  */
 int set_irq_wake(unsigned int irq, unsigned int on)
 {
         struct irq_desc *desc = irq_desc + irq;
         unsigned long flags;
         int ret = -ENXIO;
+        int (*set_wake)(unsigned, unsigned) = desc->chip->set_wake;
 
+        /* wakeup-capable irqs can be shared between drivers that
+         * don't need to have the same sleep mode behaviors.
+         */
         spin_lock_irqsave(&desc->lock, flags);
-        if (desc->chip->set_wake)
+        if (on) {
+                if (desc->wake_depth++ == 0)
+                        desc->status |= IRQ_WAKEUP;
+                else
+                        set_wake = NULL;
+        } else {
+                if (desc->wake_depth == 0) {
+                        printk(KERN_WARNING "Unbalanced IRQ %d "
+                                        "wake disable\n", irq);
+                        WARN_ON(1);
+                } else if (--desc->wake_depth == 0)
+                        desc->status &= ~IRQ_WAKEUP;
+                else
+                        set_wake = NULL;
+        }
+        if (set_wake)
                 ret = desc->chip->set_wake(irq, on);
         spin_unlock_irqrestore(&desc->lock, flags);
         return ret;
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 64aab081153b..3f57dfdc8f92 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -393,6 +393,7 @@ static int __kprobes add_new_kprobe(struct kprobe *old_p, struct kprobe *p)
 static inline void add_aggr_kprobe(struct kprobe *ap, struct kprobe *p)
 {
         copy_kprobe(p, ap);
+        flush_insn_slot(ap);
         ap->addr = p->addr;
         ap->pre_handler = aggr_pre_handler;
         ap->fault_handler = aggr_fault_handler;
diff --git a/kernel/panic.c b/kernel/panic.c
index d8a0bca21233..9b8dcfd1ca93 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -18,6 +18,7 @@
 #include <linux/interrupt.h>
 #include <linux/nmi.h>
 #include <linux/kexec.h>
+#include <linux/debug_locks.h>
 
 int panic_on_oops;
 int tainted;
diff --git a/kernel/power/process.c b/kernel/power/process.c
index b2a5f671d6cd..72e72d2c61e6 100644
--- a/kernel/power/process.c
+++ b/kernel/power/process.c
@@ -66,13 +66,25 @@ static inline void freeze_process(struct task_struct *p)
         }
 }
 
+static void cancel_freezing(struct task_struct *p)
+{
+        unsigned long flags;
+
+        if (freezing(p)) {
+                pr_debug("  clean up: %s\n", p->comm);
+                do_not_freeze(p);
+                spin_lock_irqsave(&p->sighand->siglock, flags);
+                recalc_sigpending_tsk(p);
+                spin_unlock_irqrestore(&p->sighand->siglock, flags);
+        }
+}
+
 /* 0 = success, else # of processes that we failed to stop */
 int freeze_processes(void)
 {
         int todo, nr_user, user_frozen;
         unsigned long start_time;
         struct task_struct *g, *p;
-        unsigned long flags;
 
         printk( "Stopping tasks: " );
         start_time = jiffies;
@@ -85,6 +97,10 @@ int freeze_processes(void)
                                 continue;
                         if (frozen(p))
                                 continue;
+                        if (p->state == TASK_TRACED && frozen(p->parent)) {
+                                cancel_freezing(p);
+                                continue;
+                        }
                         if (p->mm && !(p->flags & PF_BORROWED_MM)) {
                                 /* The task is a user-space one.
                                  * Freeze it unless there's a vfork completion
@@ -126,13 +142,7 @@ int freeze_processes(void)
                 do_each_thread(g, p) {
                         if (freezeable(p) && !frozen(p))
                                 printk(KERN_ERR "  %s\n", p->comm);
-                        if (freezing(p)) {
-                                pr_debug("  clean up: %s\n", p->comm);
-                                p->flags &= ~PF_FREEZE;
-                                spin_lock_irqsave(&p->sighand->siglock, flags);
-                                recalc_sigpending_tsk(p);
-                                spin_unlock_irqrestore(&p->sighand->siglock, flags);
-                        }
+                        cancel_freezing(p);
                 } while_each_thread(g, p);
                 read_unlock(&tasklist_lock);
                 return todo;
diff --git a/kernel/printk.c b/kernel/printk.c
index 65ca0688f86f..1149365e989e 100644
--- a/kernel/printk.c
+++ b/kernel/printk.c
@@ -799,6 +799,9 @@ void release_console_sem(void)
                 up(&secondary_console_sem);
                 return;
         }
+
+        console_may_schedule = 0;
+
         for ( ; ; ) {
                 spin_lock_irqsave(&logbuf_lock, flags);
                 wake_klogd |= log_start - log_end;
@@ -812,7 +815,6 @@ void release_console_sem(void)
                 local_irq_restore(flags);
         }
         console_locked = 0;
-        console_may_schedule = 0;
         up(&console_sem);
         spin_unlock_irqrestore(&logbuf_lock, flags);
         if (wake_klogd && !oops_in_progress && waitqueue_active(&log_wait)) {
diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c
index 759805c9859a..436ab35f6fa7 100644
--- a/kernel/rcupdate.c
+++ b/kernel/rcupdate.c
@@ -548,7 +548,7 @@ static void __devinit rcu_online_cpu(int cpu)
         tasklet_init(&per_cpu(rcu_tasklet, cpu), rcu_process_callbacks, 0UL);
 }
 
-static int __devinit rcu_cpu_notify(struct notifier_block *self,
+static int __cpuinit rcu_cpu_notify(struct notifier_block *self,
                                 unsigned long action, void *hcpu)
 {
         long cpu = (long)hcpu;
@@ -565,7 +565,7 @@ static int __devinit rcu_cpu_notify(struct notifier_block *self,
         return NOTIFY_OK;
 }
 
-static struct notifier_block __devinitdata rcu_nb = {
+static struct notifier_block __cpuinitdata rcu_nb = {
         .notifier_call  = rcu_cpu_notify,
 };
 
diff --git a/kernel/resource.c b/kernel/resource.c
index 0dd3a857579e..46286434af80 100644
--- a/kernel/resource.c
+++ b/kernel/resource.c
@@ -244,6 +244,7 @@ int find_next_system_ram(struct resource *res)
 
         start = res->start;
         end = res->end;
+        BUG_ON(start >= end);
 
         read_lock(&resource_lock);
         for (p = iomem_resource.child; p ; p = p->sibling) {
@@ -254,15 +255,17 @@ int find_next_system_ram(struct resource *res)
                         p = NULL;
                         break;
                 }
-                if (p->start >= start)
+                if ((p->end >= start) && (p->start < end))
                         break;
         }
         read_unlock(&resource_lock);
         if (!p)
                 return -1;
         /* copy data */
-        res->start = p->start;
-        res->end = p->end;
+        if (res->start < p->start)
+                res->start = p->start;
+        if (res->end > p->end)
+                res->end = p->end;
         return 0;
 }
 #endif
diff --git a/kernel/rtmutex.c b/kernel/rtmutex.c
index d2ef13b485e7..3e13a1e5856f 100644
--- a/kernel/rtmutex.c
+++ b/kernel/rtmutex.c
@@ -7,6 +7,8 @@
  *  Copyright (C) 2005-2006 Timesys Corp., Thomas Gleixner <tglx@timesys.com>
  *  Copyright (C) 2005 Kihon Technologies Inc., Steven Rostedt
  *  Copyright (C) 2006 Esben Nielsen
+ *
+ *  See Documentation/rt-mutex-design.txt for details.
  */
 #include <linux/spinlock.h>
 #include <linux/module.h>
diff --git a/kernel/sched.c b/kernel/sched.c
index b44b9a43b0fc..a234fbee1238 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -4162,10 +4162,8 @@ do_sched_setscheduler(pid_t pid, int policy, struct sched_param __user *param)
                 read_unlock_irq(&tasklist_lock);
                 return -ESRCH;
         }
-        get_task_struct(p);
-        read_unlock_irq(&tasklist_lock);
         retval = sched_setscheduler(p, policy, &lparam);
-        put_task_struct(p);
+        read_unlock_irq(&tasklist_lock);
 
         return retval;
 }
@@ -4456,9 +4454,9 @@ asmlinkage long sys_sched_yield(void)
         return 0;
 }
 
-static inline int __resched_legal(void)
+static inline int __resched_legal(int expected_preempt_count)
 {
-        if (unlikely(preempt_count()))
+        if (unlikely(preempt_count() != expected_preempt_count))
                 return 0;
         if (unlikely(system_state != SYSTEM_RUNNING))
                 return 0;
@@ -4484,7 +4482,7 @@ static void __cond_resched(void)
 
 int __sched cond_resched(void)
 {
-        if (need_resched() && __resched_legal()) {
+        if (need_resched() && __resched_legal(0)) {
                 __cond_resched();
                 return 1;
         }
@@ -4510,7 +4508,7 @@ int cond_resched_lock(spinlock_t *lock)
                 ret = 1;
                 spin_lock(lock);
         }
-        if (need_resched() && __resched_legal()) {
+        if (need_resched() && __resched_legal(1)) {
                 spin_release(&lock->dep_map, 1, _THIS_IP_);
                 _raw_spin_unlock(lock);
                 preempt_enable_no_resched();
@@ -4526,7 +4524,7 @@ int __sched cond_resched_softirq(void)
 {
         BUG_ON(!in_softirq());
 
-        if (need_resched() && __resched_legal()) {
+        if (need_resched() && __resched_legal(0)) {
                 raw_local_irq_disable();
                 _local_bh_enable();
                 raw_local_irq_enable();
@@ -6494,7 +6492,12 @@ static int build_sched_domains(const cpumask_t *cpu_map)
         for (i = 0; i < MAX_NUMNODES; i++)
                 init_numa_sched_groups_power(sched_group_nodes[i]);
 
-        init_numa_sched_groups_power(sched_group_allnodes);
+        if (sched_group_allnodes) {
+                int group = cpu_to_allnodes_group(first_cpu(*cpu_map));
+                struct sched_group *sg = &sched_group_allnodes[group];
+
+                init_numa_sched_groups_power(sg);
+        }
 #endif
 
         /* Attach the domains */
@@ -6761,6 +6764,11 @@ void __init sched_init(void)
         }
 
         set_load_weight(&init_task);
+
+#ifdef CONFIG_RT_MUTEXES
+        plist_head_init(&init_task.pi_waiters, &init_task.pi_lock);
+#endif
+
         /*
          * The boot idle thread does lazy MMU switching as well:
          */
diff --git a/kernel/signal.c b/kernel/signal.c
index 7fe874d12fae..bfdb5686fa3e 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -791,22 +791,31 @@ out:
 /*
  * Force a signal that the process can't ignore: if necessary
  * we unblock the signal and change any SIG_IGN to SIG_DFL.
+ *
+ * Note: If we unblock the signal, we always reset it to SIG_DFL,
+ * since we do not want to have a signal handler that was blocked
+ * be invoked when user space had explicitly blocked it.
+ *
+ * We don't want to have recursive SIGSEGV's etc, for example.
  */
-
 int
 force_sig_info(int sig, struct siginfo *info, struct task_struct *t)
 {
         unsigned long int flags;
-        int ret;
+        int ret, blocked, ignored;
+        struct k_sigaction *action;
 
         spin_lock_irqsave(&t->sighand->siglock, flags);
-        if (t->sighand->action[sig-1].sa.sa_handler == SIG_IGN) {
-                t->sighand->action[sig-1].sa.sa_handler = SIG_DFL;
-        }
-        if (sigismember(&t->blocked, sig)) {
-                sigdelset(&t->blocked, sig);
+        action = &t->sighand->action[sig-1];
+        ignored = action->sa.sa_handler == SIG_IGN;
+        blocked = sigismember(&t->blocked, sig);
+        if (blocked || ignored) {
+                action->sa.sa_handler = SIG_DFL;
+                if (blocked) {
+                        sigdelset(&t->blocked, sig);
+                        recalc_sigpending_tsk(t);
+                }
         }
-        recalc_sigpending_tsk(t);
         ret = specific_send_sig_info(sig, info, t);
         spin_unlock_irqrestore(&t->sighand->siglock, flags);
 
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 0f08a84ae307..3789ca98197c 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -65,6 +65,7 @@ static inline void wakeup_softirqd(void)
  * This one is for softirq.c-internal use,
  * where hardirqs are disabled legitimately:
  */
+#ifdef CONFIG_TRACE_IRQFLAGS
 static void __local_bh_disable(unsigned long ip)
 {
         unsigned long flags;
@@ -80,6 +81,13 @@ static void __local_bh_disable(unsigned long ip)
                 trace_softirqs_off(ip);
         raw_local_irq_restore(flags);
 }
+#else /* !CONFIG_TRACE_IRQFLAGS */
+static inline void __local_bh_disable(unsigned long ip)
+{
+        add_preempt_count(SOFTIRQ_OFFSET);
+        barrier();
+}
+#endif /* CONFIG_TRACE_IRQFLAGS */
 
 void local_bh_disable(void)
 {
@@ -121,12 +129,16 @@ EXPORT_SYMBOL(_local_bh_enable);
 
 void local_bh_enable(void)
 {
+#ifdef CONFIG_TRACE_IRQFLAGS
         unsigned long flags;
 
         WARN_ON_ONCE(in_irq());
+#endif
         WARN_ON_ONCE(irqs_disabled());
 
+#ifdef CONFIG_TRACE_IRQFLAGS
         local_irq_save(flags);
+#endif
         /*
          * Are softirqs going to be turned on now:
          */
@@ -142,18 +154,22 @@ void local_bh_enable(void)
                 do_softirq();
 
         dec_preempt_count();
+#ifdef CONFIG_TRACE_IRQFLAGS
         local_irq_restore(flags);
+#endif
         preempt_check_resched();
 }
 EXPORT_SYMBOL(local_bh_enable);
 
 void local_bh_enable_ip(unsigned long ip)
 {
+#ifdef CONFIG_TRACE_IRQFLAGS
         unsigned long flags;
 
         WARN_ON_ONCE(in_irq());
 
         local_irq_save(flags);
+#endif
         /*
          * Are softirqs going to be turned on now:
          */
@@ -169,7 +185,9 @@ void local_bh_enable_ip(unsigned long ip)
                 do_softirq();
 
         dec_preempt_count();
+#ifdef CONFIG_TRACE_IRQFLAGS
         local_irq_restore(flags);
+#endif
         preempt_check_resched();
 }
 EXPORT_SYMBOL(local_bh_enable_ip);
@@ -547,7 +565,7 @@ static void takeover_tasklets(unsigned int cpu)
 }
 #endif /* CONFIG_HOTPLUG_CPU */
 
-static int __devinit cpu_callback(struct notifier_block *nfb,
+static int __cpuinit cpu_callback(struct notifier_block *nfb,
                                   unsigned long action,
                                   void *hcpu)
 {
@@ -587,7 +605,7 @@ static int __devinit cpu_callback(struct notifier_block *nfb,
         return NOTIFY_OK;
 }
 
-static struct notifier_block __devinitdata cpu_nfb = {
+static struct notifier_block __cpuinitdata cpu_nfb = {
         .notifier_call = cpu_callback
 };
 
diff --git a/kernel/softlockup.c b/kernel/softlockup.c
index 6b76caa22981..03e6a2b0b787 100644
--- a/kernel/softlockup.c
+++ b/kernel/softlockup.c
@@ -104,7 +104,7 @@ static int watchdog(void * __bind_cpu)
 /*
  * Create/destroy watchdog threads as CPUs come and go:
  */
-static int __devinit
+static int __cpuinit
 cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu)
 {
         int hotcpu = (unsigned long)hcpu;
@@ -142,7 +142,7 @@ cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu)
         return NOTIFY_OK;
 }
 
-static struct notifier_block __devinitdata cpu_nfb = {
+static struct notifier_block __cpuinitdata cpu_nfb = {
         .notifier_call = cpu_callback
 };
 
diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c
index dcfb5d731466..51cacd111dbd 100644
--- a/kernel/stop_machine.c
+++ b/kernel/stop_machine.c
@@ -111,7 +111,6 @@ static int stop_machine(void)
         /* If some failed, kill them all. */
         if (ret < 0) {
                 stopmachine_set_state(STOPMACHINE_EXIT);
-                up(&stopmachine_mutex);
                 return ret;
         }
 
diff --git a/kernel/taskstats.c b/kernel/taskstats.c
index f45179ce028e..e78187657330 100644
--- a/kernel/taskstats.c
+++ b/kernel/taskstats.c
@@ -121,46 +121,45 @@ static int send_reply(struct sk_buff *skb, pid_t pid)
 /*
  * Send taskstats data in @skb to listeners registered for @cpu's exit data
  */
-static int send_cpu_listeners(struct sk_buff *skb, unsigned int cpu)
+static void send_cpu_listeners(struct sk_buff *skb, unsigned int cpu)
 {
         struct genlmsghdr *genlhdr = nlmsg_data((struct nlmsghdr *)skb->data);
         struct listener_list *listeners;
         struct listener *s, *tmp;
         struct sk_buff *skb_next, *skb_cur = skb;
         void *reply = genlmsg_data(genlhdr);
-        int rc, ret, delcount = 0;
+        int rc, delcount = 0;
 
         rc = genlmsg_end(skb, reply);
         if (rc < 0) {
                 nlmsg_free(skb);
-                return rc;
+                return;
         }
 
         rc = 0;
         listeners = &per_cpu(listener_array, cpu);
         down_read(&listeners->sem);
-        list_for_each_entry_safe(s, tmp, &listeners->list, list) {
+        list_for_each_entry(s, &listeners->list, list) {
                 skb_next = NULL;
                 if (!list_is_last(&s->list, &listeners->list)) {
                         skb_next = skb_clone(skb_cur, GFP_KERNEL);
-                        if (!skb_next) {
-                                nlmsg_free(skb_cur);
-                                rc = -ENOMEM;
+                        if (!skb_next)
                                 break;
-                        }
                 }
-                ret = genlmsg_unicast(skb_cur, s->pid);
-                if (ret == -ECONNREFUSED) {
+                rc = genlmsg_unicast(skb_cur, s->pid);
+                if (rc == -ECONNREFUSED) {
                         s->valid = 0;
                         delcount++;
-                        rc = ret;
                 }
                 skb_cur = skb_next;
         }
         up_read(&listeners->sem);
 
+        if (skb_cur)
+                nlmsg_free(skb_cur);
+
         if (!delcount)
-                return rc;
+                return;
 
         /* Delete invalidated entries */
         down_write(&listeners->sem);
@@ -171,13 +170,12 @@ static int send_cpu_listeners(struct sk_buff *skb, unsigned int cpu)
                 }
         }
         up_write(&listeners->sem);
-        return rc;
 }
 
 static int fill_pid(pid_t pid, struct task_struct *pidtsk,
                 struct taskstats *stats)
 {
-        int rc;
+        int rc = 0;
         struct task_struct *tsk = pidtsk;
 
         if (!pidtsk) {
@@ -196,12 +194,10 @@ static int fill_pid(pid_t pid, struct task_struct *pidtsk,
          * Each accounting subsystem adds calls to its functions to
          * fill in relevant parts of struct taskstsats as follows
          *
-         *      rc = per-task-foo(stats, tsk);
-         *      if (rc)
-         *              goto err;
+         *      per-task-foo(stats, tsk);
          */
 
-        rc = delayacct_add_tsk(stats, tsk);
+        delayacct_add_tsk(stats, tsk);
         stats->version = TASKSTATS_VERSION;
 
         /* Define err: label here if needed */
diff --git a/kernel/timer.c b/kernel/timer.c
index 05809c2e2fd6..1d7dd6267c2d 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -84,7 +84,7 @@ typedef struct tvec_t_base_s tvec_base_t;
 
 tvec_base_t boot_tvec_bases;
 EXPORT_SYMBOL(boot_tvec_bases);
-static DEFINE_PER_CPU(tvec_base_t *, tvec_bases) = { &boot_tvec_bases };
+static DEFINE_PER_CPU(tvec_base_t *, tvec_bases) = &boot_tvec_bases;
 
 static inline void set_running_timer(tvec_base_t *base,
                                         struct timer_list *timer)
@@ -408,7 +408,7 @@ static int cascade(tvec_base_t *base, tvec_t *tv, int index)
  * This function cascades all vectors and executes all expired timer
  * vectors.
  */
-#define INDEX(N) (base->timer_jiffies >> (TVR_BITS + N * TVN_BITS)) & TVN_MASK
+#define INDEX(N) ((base->timer_jiffies >> (TVR_BITS + (N) * TVN_BITS)) & TVN_MASK)
 
 static inline void __run_timers(tvec_base_t *base)
 {
@@ -1324,46 +1324,19 @@ asmlinkage long sys_getpid(void)
 }
 
 /*
- * Accessing ->group_leader->real_parent is not SMP-safe, it could
- * change from under us. However, rather than getting any lock
- * we can use an optimistic algorithm: get the parent
- * pid, and go back and check that the parent is still
- * the same. If it has changed (which is extremely unlikely
- * indeed), we just try again..
- *
- * NOTE! This depends on the fact that even if we _do_
- * get an old value of "parent", we can happily dereference
- * the pointer (it was and remains a dereferencable kernel pointer
- * no matter what): we just can't necessarily trust the result
- * until we know that the parent pointer is valid.
- *
- * NOTE2: ->group_leader never changes from under us.
+ * Accessing ->real_parent is not SMP-safe, it could
+ * change from under us. However, we can use a stale
+ * value of ->real_parent under rcu_read_lock(), see
+ * release_task()->call_rcu(delayed_put_task_struct).
  */
 asmlinkage long sys_getppid(void)
 {
         int pid;
-        struct task_struct *me = current;
-        struct task_struct *parent;
 
-        parent = me->group_leader->real_parent;
-        for (;;) {
-                pid = parent->tgid;
-#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT)
-{
-                struct task_struct *old = parent;
+        rcu_read_lock();
+        pid = rcu_dereference(current->real_parent)->tgid;
+        rcu_read_unlock();
 
-                /*
-                 * Make sure we read the pid before re-reading the
-                 * parent pointer:
-                 */
-                smp_rmb();
-                parent = me->group_leader->real_parent;
-                if (old != parent)
-                        continue;
-}
-#endif
-                break;
-        }
         return pid;
 }
 
@@ -1688,7 +1661,7 @@ static void __devinit migrate_timers(int cpu)
 }
 #endif /* CONFIG_HOTPLUG_CPU */
 
-static int __devinit timer_cpu_notify(struct notifier_block *self,
+static int __cpuinit timer_cpu_notify(struct notifier_block *self,
                                 unsigned long action, void *hcpu)
 {
         long cpu = (long)hcpu;
@@ -1708,7 +1681,7 @@ static int __devinit timer_cpu_notify(struct notifier_block *self,
         return NOTIFY_OK;
 }
 
-static struct notifier_block __devinitdata timers_nb = {
+static struct notifier_block __cpuinitdata timers_nb = {
         .notifier_call  = timer_cpu_notify,
 };
 
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index eebb1d839235..835fe28b87a8 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -68,7 +68,7 @@ struct workqueue_struct {
 
 /* All the per-cpu workqueues on the system, for hotplug cpu to add/remove
    threads to each one as cpus come/go. */
-static DEFINE_SPINLOCK(workqueue_lock);
+static DEFINE_MUTEX(workqueue_mutex);
 static LIST_HEAD(workqueues);
 
 static int singlethread_cpu;
@@ -93,9 +93,12 @@ static void __queue_work(struct cpu_workqueue_struct *cwq,
         spin_unlock_irqrestore(&cwq->lock, flags);
 }
 
-/*
- * Queue work on a workqueue. Return non-zero if it was successfully
- * added.
+/**
+ * queue_work - queue work on a workqueue
+ * @wq: workqueue to use
+ * @work: work to queue
+ *
+ * Returns non-zero if it was successfully added.
  *
  * We queue the work to the CPU it was submitted, but there is no
  * guarantee that it will be processed by that CPU.
@@ -128,6 +131,14 @@ static void delayed_work_timer_fn(unsigned long __data)
         __queue_work(per_cpu_ptr(wq->cpu_wq, cpu), work);
 }
 
+/**
+ * queue_delayed_work - queue work on a workqueue after delay
+ * @wq: workqueue to use
+ * @work: work to queue
+ * @delay: number of jiffies to wait before queueing
+ *
+ * Returns non-zero if it was successfully added.
+ */
 int fastcall queue_delayed_work(struct workqueue_struct *wq,
                         struct work_struct *work, unsigned long delay)
 {
@@ -150,6 +161,15 @@ int fastcall queue_delayed_work(struct workqueue_struct *wq,
 }
 EXPORT_SYMBOL_GPL(queue_delayed_work);
 
+/**
+ * queue_delayed_work_on - queue work on specific CPU after delay
+ * @cpu: CPU number to execute work on
+ * @wq: workqueue to use
+ * @work: work to queue
+ * @delay: number of jiffies to wait before queueing
+ *
+ * Returns non-zero if it was successfully added.
+ */
 int queue_delayed_work_on(int cpu, struct workqueue_struct *wq,
                         struct work_struct *work, unsigned long delay)
 {
@@ -275,8 +295,9 @@ static void flush_cpu_workqueue(struct cpu_workqueue_struct *cwq)
         }
 }
 
-/*
+/**
  * flush_workqueue - ensure that any scheduled work has run to completion.
+ * @wq: workqueue to flush
  *
  * Forces execution of the workqueue and blocks until its completion.
  * This is typically used in driver shutdown handlers.
@@ -299,10 +320,10 @@ void fastcall flush_workqueue(struct workqueue_struct *wq)
         } else {
                 int cpu;
 
-                lock_cpu_hotplug();
+                mutex_lock(&workqueue_mutex);
                 for_each_online_cpu(cpu)
                         flush_cpu_workqueue(per_cpu_ptr(wq->cpu_wq, cpu));
-                unlock_cpu_hotplug();
+                mutex_unlock(&workqueue_mutex);
         }
 }
 EXPORT_SYMBOL_GPL(flush_workqueue);
@@ -350,8 +371,7 @@ struct workqueue_struct *__create_workqueue(const char *name,
         }
 
         wq->name = name;
-        /* We don't need the distraction of CPUs appearing and vanishing. */
-        lock_cpu_hotplug();
+        mutex_lock(&workqueue_mutex);
         if (singlethread) {
                 INIT_LIST_HEAD(&wq->list);
                 p = create_workqueue_thread(wq, singlethread_cpu);
@@ -360,9 +380,7 @@ struct workqueue_struct *__create_workqueue(const char *name,
                 else
                         wake_up_process(p);
         } else {
-                spin_lock(&workqueue_lock);
                 list_add(&wq->list, &workqueues);
-                spin_unlock(&workqueue_lock);
                 for_each_online_cpu(cpu) {
                         p = create_workqueue_thread(wq, cpu);
                         if (p) {
@@ -372,7 +390,7 @@ struct workqueue_struct *__create_workqueue(const char *name,
                                 destroy = 1;
                 }
         }
-        unlock_cpu_hotplug();
+        mutex_unlock(&workqueue_mutex);
 
         /*
          * Was there any error during startup? If yes then clean up:
@@ -400,6 +418,12 @@ static void cleanup_workqueue_thread(struct workqueue_struct *wq, int cpu)
                 kthread_stop(p);
 }
 
+/**
+ * destroy_workqueue - safely terminate a workqueue
+ * @wq: target workqueue
+ *
+ * Safely destroy a workqueue. All work currently pending will be done first.
+ */
 void destroy_workqueue(struct workqueue_struct *wq)
 {
         int cpu;
@@ -407,17 +431,15 @@ void destroy_workqueue(struct workqueue_struct *wq)
         flush_workqueue(wq);
 
         /* We don't need the distraction of CPUs appearing and vanishing. */
-        lock_cpu_hotplug();
+        mutex_lock(&workqueue_mutex);
         if (is_single_threaded(wq))
                 cleanup_workqueue_thread(wq, singlethread_cpu);
         else {
                 for_each_online_cpu(cpu)
                         cleanup_workqueue_thread(wq, cpu);
-                spin_lock(&workqueue_lock);
                 list_del(&wq->list);
-                spin_unlock(&workqueue_lock);
         }
-        unlock_cpu_hotplug();
+        mutex_unlock(&workqueue_mutex);
         free_percpu(wq->cpu_wq);
         kfree(wq);
 }
@@ -425,18 +447,41 @@ EXPORT_SYMBOL_GPL(destroy_workqueue);
 
 static struct workqueue_struct *keventd_wq;
 
+/**
+ * schedule_work - put work task in global workqueue
+ * @work: job to be done
+ *
+ * This puts a job in the kernel-global workqueue.
+ */
 int fastcall schedule_work(struct work_struct *work)
 {
         return queue_work(keventd_wq, work);
 }
 EXPORT_SYMBOL(schedule_work);
 
+/**
+ * schedule_delayed_work - put work task in global workqueue after delay
+ * @work: job to be done
+ * @delay: number of jiffies to wait
+ *
+ * After waiting for a given time this puts a job in the kernel-global
+ * workqueue.
+ */
 int fastcall schedule_delayed_work(struct work_struct *work, unsigned long delay)
 {
         return queue_delayed_work(keventd_wq, work, delay);
 }
 EXPORT_SYMBOL(schedule_delayed_work);
 
+/**
+ * schedule_delayed_work_on - queue work in global workqueue on CPU after delay
+ * @cpu: cpu to use
+ * @work: job to be done
+ * @delay: number of jiffies to wait
+ *
+ * After waiting for a given time this puts a job in the kernel-global
+ * workqueue on the specified CPU.
+ */
 int schedule_delayed_work_on(int cpu,
                         struct work_struct *work, unsigned long delay)
 {
@@ -465,11 +510,13 @@ int schedule_on_each_cpu(void (*func)(void *info), void *info)
         if (!works)
                 return -ENOMEM;
 
+        mutex_lock(&workqueue_mutex);
         for_each_online_cpu(cpu) {
                 INIT_WORK(per_cpu_ptr(works, cpu), func, info);
                 __queue_work(per_cpu_ptr(keventd_wq->cpu_wq, cpu),
                                 per_cpu_ptr(works, cpu));
         }
+        mutex_unlock(&workqueue_mutex);
         flush_workqueue(keventd_wq);
         free_percpu(works);
         return 0;
@@ -585,6 +632,7 @@ static int __devinit workqueue_cpu_callback(struct notifier_block *nfb,
 
         switch (action) {
         case CPU_UP_PREPARE:
+                mutex_lock(&workqueue_mutex);
                 /* Create a new workqueue thread for it. */
                 list_for_each_entry(wq, &workqueues, list) {
                         if (!create_workqueue_thread(wq, hotcpu)) {
@@ -603,6 +651,7 @@ static int __devinit workqueue_cpu_callback(struct notifier_block *nfb,
                         kthread_bind(cwq->thread, hotcpu);
                         wake_up_process(cwq->thread);
                 }
+                mutex_unlock(&workqueue_mutex);
                 break;
 
         case CPU_UP_CANCELED:
@@ -614,6 +663,15 @@ static int __devinit workqueue_cpu_callback(struct notifier_block *nfb,
                                      any_online_cpu(cpu_online_map));
                         cleanup_workqueue_thread(wq, hotcpu);
                 }
+                mutex_unlock(&workqueue_mutex);
+                break;
+
+        case CPU_DOWN_PREPARE:
+                mutex_lock(&workqueue_mutex);
+                break;
+
+        case CPU_DOWN_FAILED:
+                mutex_unlock(&workqueue_mutex);
                 break;
 
         case CPU_DEAD:
@@ -621,6 +679,7 @@ static int __devinit workqueue_cpu_callback(struct notifier_block *nfb,
                         cleanup_workqueue_thread(wq, hotcpu);
                 list_for_each_entry(wq, &workqueues, list)
                         take_over_work(wq, hotcpu);
+                mutex_unlock(&workqueue_mutex);
                 break;
         }